1615 files changed, 51544 insertions, 40789 deletions

diff --git a/.mailmap b/.mailmap
index 29ddeb1bf015..d96147eb1a68 100644
--- a/.mailmap
+++ b/.mailmap
@@ -81,6 +81,9 @@ Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
 Jean Tourrilhes <jt@hpl.hp.com>
 Jeff Garzik <jgarzik@pretzel.yyz.us>
+Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
+Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net>
+Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com>
 Jens Axboe <axboe@suse.de>
 Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 Johan Hovold <johan@kernel.org> <jhovold@gmail.com>
diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats
index f91a973a37fe..abac31d216de 100644
--- a/Documentation/ABI/testing/procfs-diskstats
+++ b/Documentation/ABI/testing/procfs-diskstats
@@ -5,6 +5,7 @@ Description:
 		The /proc/diskstats file displays the I/O statistics
 		of block devices. Each line contains the following 14
 		fields:
+
 		 1 - major number
 		 2 - minor mumber
 		 3 - device name
@@ -19,4 +20,13 @@ Description:
 		12 - I/Os currently in progress
 		13 - time spent doing I/Os (ms)
 		14 - weighted time spent doing I/Os (ms)
+
+		Kernel 4.18+ appends four more fields for discard
+		tracking putting the total at 18:
+
+		15 - discards completed successfully
+		16 - discards merged
+		17 - sectors discarded
+		18 - time spent discarding
+
 		For more details refer to Documentation/iostats.txt
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 9c5e7732d249..73318225a368 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -476,6 +476,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
+		/sys/devices/system/cpu/vulnerabilities/l1tf
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
@@ -487,3 +488,26 @@ Description:	Information about CPU vulnerabilities
 		"Not affected"	  CPU is not affected by the vulnerability
 		"Vulnerable"	  CPU is affected and no mitigation in effect
 		"Mitigation: $M"  CPU is affected and mitigation $M is in effect
+
+		Details about the l1tf file can be found in
+		Documentation/admin-guide/l1tf.rst
+
+What:		/sys/devices/system/cpu/smt
+		/sys/devices/system/cpu/smt/active
+		/sys/devices/system/cpu/smt/control
+Date:		June 2018
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Control Symetric Multi Threading (SMT)
+
+		active:  Tells whether SMT is active (enabled and siblings online)
+
+		control: Read/write interface to control SMT. Possible
+			 values:
+
+			 "on"		SMT is enabled
+			 "off"		SMT is disabled
+			 "forceoff"	SMT is force disabled. Cannot be changed.
+			 "notsupported" SMT is not supported by the CPU
+
+			 If control status is "forceoff" or "notsupported" writes
+			 are rejected.
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
index 6c06e10bd04b..f5120a00f511 100644
--- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html
+++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
@@ -380,31 +380,26 @@ and therefore need no protection.
 as follows:
 
 <pre>
-  1   unsigned long gpnum;
-  2   unsigned long completed;
+  1   unsigned long gp_seq;
 </pre>
 
 <p>RCU grace periods are numbered, and
-the <tt>-&gt;gpnum</tt> field contains the number of the grace
-period that started most recently.
-The <tt>-&gt;completed</tt> field contains the number of the
-grace period that completed most recently.
-If the two fields are equal, the RCU grace period that most recently
-started has already completed, and therefore the corresponding
-flavor of RCU is idle.
-If <tt>-&gt;gpnum</tt> is one greater than <tt>-&gt;completed</tt>,
-then <tt>-&gt;gpnum</tt> gives the number of the current RCU
-grace period, which has not yet completed.
-Any other combination of values indicates that something is broken.
-These two fields are protected by the root <tt>rcu_node</tt>'s
+the <tt>-&gt;gp_seq</tt> field contains the current grace-period
+sequence number.
+The bottom two bits are the state of the current grace period,
+which can be zero for not yet started or one for in progress.
+In other words, if the bottom two bits of <tt>-&gt;gp_seq</tt> are
+zero, the corresponding flavor of RCU is idle.
+Any other value in the bottom two bits indicates that something is broken.
+This field is protected by the root <tt>rcu_node</tt> structure's
 <tt>-&gt;lock</tt> field.
 
-</p><p>There are <tt>-&gt;gpnum</tt> and <tt>-&gt;completed</tt> fields
+</p><p>There are <tt>-&gt;gp_seq</tt> fields
 in the <tt>rcu_node</tt> and <tt>rcu_data</tt> structures
 as well.
 The fields in the <tt>rcu_state</tt> structure represent the
-most current values, and those of the other structures are compared
-in order to detect the start of a new grace period in a distributed
+most current value, and those of the other structures are compared
+in order to detect the beginnings and ends of grace periods in a distributed
 fashion.
 The values flow from <tt>rcu_state</tt> to <tt>rcu_node</tt>
 (down the tree from the root to the leaves) to <tt>rcu_data</tt>.
@@ -512,27 +507,47 @@ than to be heisenbugged out of existence.
 as follows:
 
 <pre>
-  1   unsigned long gpnum;
-  2   unsigned long completed;
+  1   unsigned long gp_seq;
+  2   unsigned long gp_seq_needed;
 </pre>
 
-<p>These fields are the counterparts of the fields of the same name in
-the <tt>rcu_state</tt> structure.
-They each may lag up to one behind their <tt>rcu_state</tt>
-counterparts.
-If a given <tt>rcu_node</tt> structure's <tt>-&gt;gpnum</tt> and
-<tt>-&gt;complete</tt> fields are equal, then this <tt>rcu_node</tt>
+<p>The <tt>rcu_node</tt> structures' <tt>-&gt;gp_seq</tt> fields are
+the counterparts of the field of the same name in the <tt>rcu_state</tt>
+structure.
+They each may lag up to one step behind their <tt>rcu_state</tt>
+counterpart.
+If the bottom two bits of a given <tt>rcu_node</tt> structure's
+<tt>-&gt;gp_seq</tt> field is zero, then this <tt>rcu_node</tt>
 structure believes that RCU is idle.
-Otherwise, as with the <tt>rcu_state</tt> structure,
-the <tt>-&gt;gpnum</tt> field will be one greater than the
-<tt>-&gt;complete</tt> fields, with <tt>-&gt;gpnum</tt>
-indicating which grace period this <tt>rcu_node</tt> believes
-is still being waited for.
+</p><p>The <tt>&gt;gp_seq</tt> field of each <tt>rcu_node</tt>
+structure is updated at the beginning and the end
+of each grace period.
+
+<p>The <tt>-&gt;gp_seq_needed</tt> fields record the
+furthest-in-the-future grace period request seen by the corresponding
+<tt>rcu_node</tt> structure.  The request is considered fulfilled when
+the value of the <tt>-&gt;gp_seq</tt> field equals or exceeds that of
+the <tt>-&gt;gp_seq_needed</tt> field.
 
-</p><p>The <tt>&gt;gpnum</tt> field of each <tt>rcu_node</tt>
-structure is updated at the beginning
-of each grace period, and the <tt>-&gt;completed</tt> fields are
-updated at the end of each grace period.
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	Suppose that this <tt>rcu_node</tt> structure doesn't see
+	a request for a very long time.
+	Won't wrapping of the <tt>-&gt;gp_seq</tt> field cause
+	problems?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	No, because if the <tt>-&gt;gp_seq_needed</tt> field lags behind the
+	<tt>-&gt;gp_seq</tt> field, the <tt>-&gt;gp_seq_needed</tt> field
+	will be updated at the end of the grace period.
+	Modulo-arithmetic comparisons therefore will always get the
+	correct answer, even with wrapping.
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
 
 <h5>Quiescent-State Tracking</h5>
 
@@ -626,9 +641,8 @@ normal and expedited grace periods, respectively.
 	</ol>
 
 	<p><font color="ffffff">So the locking is absolutely required in
-	order to coordinate
-	clearing of the bits with the grace-period numbers in
-	<tt>-&gt;gpnum</tt> and <tt>-&gt;completed</tt>.
+	order to coordinate clearing of the bits with updating of the
+	grace-period sequence number in <tt>-&gt;gp_seq</tt>.
 </font></td></tr>
 <tr><td>&nbsp;</td></tr>
 </table>
@@ -1038,15 +1052,15 @@ out any <tt>rcu_data</tt> structure for which this flag is not set.
 as follows:
 
 <pre>
-  1   unsigned long completed;
-  2   unsigned long gpnum;
+  1   unsigned long gp_seq;
+  2   unsigned long gp_seq_needed;
   3   bool cpu_no_qs;
   4   bool core_needs_qs;
   5   bool gpwrap;
   6   unsigned long rcu_qs_ctr_snap;
 </pre>
 
-<p>The <tt>completed</tt> and <tt>gpnum</tt>
+<p>The <tt>-&gt;gp_seq</tt> and <tt>-&gt;gp_seq_needed</tt>
 fields are the counterparts of the fields of the same name
 in the <tt>rcu_state</tt> and <tt>rcu_node</tt> structures.
 They may each lag up to one behind their <tt>rcu_node</tt>
@@ -1054,15 +1068,9 @@ counterparts, but in <tt>CONFIG_NO_HZ_IDLE</tt> and
 <tt>CONFIG_NO_HZ_FULL</tt> kernels can lag
 arbitrarily far behind for CPUs in dyntick-idle mode (but these counters
 will catch up upon exit from dyntick-idle mode).
-If a given <tt>rcu_data</tt> structure's <tt>-&gt;gpnum</tt> and
-<tt>-&gt;complete</tt> fields are equal, then this <tt>rcu_data</tt>
+If the lower two bits of a given <tt>rcu_data</tt> structure's
+<tt>-&gt;gp_seq</tt> are zero, then this <tt>rcu_data</tt>
 structure believes that RCU is idle.
-Otherwise, as with the <tt>rcu_state</tt> and <tt>rcu_node</tt>
-structure,
-the <tt>-&gt;gpnum</tt> field will be one greater than the
-<tt>-&gt;complete</tt> fields, with <tt>-&gt;gpnum</tt>
-indicating which grace period this <tt>rcu_data</tt> believes
-is still being waited for.
 
 <table>
 <tr><th>&nbsp;</th></tr>
@@ -1070,13 +1078,13 @@ is still being waited for.
 <tr><td>
 	All this replication of the grace period numbers can only cause
 	massive confusion.
-	Why not just keep a global pair of counters and be done with it???
+	Why not just keep a global sequence number and be done with it???
 </td></tr>
 <tr><th align="left">Answer:</th></tr>
 <tr><td bgcolor="#ffffff"><font color="ffffff">
-	Because if there was only a single global pair of grace-period
+	Because if there was only a single global sequence
 	numbers, there would need to be a single global lock to allow
-	safely accessing and updating them.
+	safely accessing and updating it.
 	And if we are not going to have a single global lock, we need
 	to carefully manage the numbers on a per-node basis.
 	Recall from the answer to a previous Quick Quiz that the consequences
@@ -1091,8 +1099,8 @@ CPU has not yet passed through a quiescent state,
 while the <tt>-&gt;core_needs_qs</tt> flag indicates that the
 RCU core needs a quiescent state from the corresponding CPU.
 The <tt>-&gt;gpwrap</tt> field indicates that the corresponding
-CPU has remained idle for so long that the <tt>completed</tt>
-and <tt>gpnum</tt> counters are in danger of overflow, which
+CPU has remained idle for so long that the
+<tt>gp_seq</tt> counter is in danger of overflow, which
 will cause the CPU to disregard the values of its counters on
 its next exit from idle.
 Finally, the <tt>rcu_qs_ctr_snap</tt> field is used to detect
@@ -1130,10 +1138,10 @@ The CPU advances the callbacks in its <tt>rcu_data</tt> structure
 whenever it notices that another RCU grace period has completed.
 The CPU detects the completion of an RCU grace period by noticing
 that the value of its <tt>rcu_data</tt> structure's
-<tt>-&gt;completed</tt> field differs from that of its leaf
+<tt>-&gt;gp_seq</tt> field differs from that of its leaf
 <tt>rcu_node</tt> structure.
 Recall that each <tt>rcu_node</tt> structure's
-<tt>-&gt;completed</tt> field is updated at the end of each
+<tt>-&gt;gp_seq</tt> field is updated at the beginnings and ends of each
 grace period.
 
 <p>
diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
index 8651b0b4fd79..a346ce0116eb 100644
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
+++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
@@ -357,7 +357,7 @@ parts, starting in this section with the various phases of
 grace-period initialization.
 
 <p>The first ordering-related grace-period initialization action is to
-increment the <tt>rcu_state</tt> structure's <tt>-&gt;gpnum</tt>
+advance the <tt>rcu_state</tt> structure's <tt>-&gt;gp_seq</tt>
 grace-period-number counter, as shown below:
 
 </p><p><img src="TreeRCU-gp-init-1.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
@@ -388,7 +388,7 @@ its last CPU and if the next <tt>rcu_node</tt> structure has no online CPUs).
 
 <p>The final <tt>rcu_gp_init()</tt> pass through the <tt>rcu_node</tt>
 tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's
-<tt>-&gt;gpnum</tt> field to the newly incremented value from the
+<tt>-&gt;gp_seq</tt> field to the newly advanced value from the
 <tt>rcu_state</tt> structure, as shown in the following diagram.
 
 </p><p><img src="TreeRCU-gp-init-3.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
@@ -398,9 +398,9 @@ tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's
 to notice that a new grace period has started, as described in the next
 section.
 But because the grace-period kthread started the grace period at the
-root (with the increment of the <tt>rcu_state</tt> structure's
-<tt>-&gt;gpnum</tt> field) before setting each leaf <tt>rcu_node</tt>
-structure's <tt>-&gt;gpnum</tt> field, each CPU's observation of
+root (with the advancing of the <tt>rcu_state</tt> structure's
+<tt>-&gt;gp_seq</tt> field) before setting each leaf <tt>rcu_node</tt>
+structure's <tt>-&gt;gp_seq</tt> field, each CPU's observation of
 the start of the grace period will happen after the actual start
 of the grace period.
 
@@ -466,7 +466,7 @@ section that the grace period must wait on.
 <tr><td>
 	But a RCU read-side critical section might have started
 	after the beginning of the grace period
-	(the <tt>-&gt;gpnum++</tt> from earlier), so why should
+	(the advancing of <tt>-&gt;gp_seq</tt> from earlier), so why should
 	the grace period wait on such a critical section?
 </td></tr>
 <tr><th align="left">Answer:</th></tr>
@@ -609,10 +609,8 @@ states outstanding from other CPUs.
 <h4><a name="Grace-Period Cleanup">Grace-Period Cleanup</a></h4>
 
 <p>Grace-period cleanup first scans the <tt>rcu_node</tt> tree
-breadth-first setting all the <tt>-&gt;completed</tt> fields equal
-to the number of the newly completed grace period, then it sets
-the <tt>rcu_state</tt> structure's <tt>-&gt;completed</tt> field,
-again to the number of the newly completed grace period.
+breadth-first advancing all the <tt>-&gt;gp_seq</tt> fields, then it
+advances the <tt>rcu_state</tt> structure's <tt>-&gt;gp_seq</tt> field.
 The ordering effects are shown below:
 
 </p><p><img src="TreeRCU-gp-cleanup.svg" alt="TreeRCU-gp-cleanup.svg" width="75%">
@@ -634,7 +632,7 @@ grace-period cleanup is complete, the next grace period can begin.
 	CPU has reported its quiescent state, but it may be some
 	milliseconds before RCU becomes aware of this.
 	The latest reasonable candidate is once the <tt>rcu_state</tt>
-	structure's <tt>-&gt;completed</tt> field has been updated,
+	structure's <tt>-&gt;gp_seq</tt> field has been updated,
 	but it is quite possible that some CPUs have already completed
 	phase two of their updates by that time.
 	In short, if you are going to work with RCU, you need to
@@ -647,7 +645,7 @@ grace-period cleanup is complete, the next grace period can begin.
 <h4><a name="Callback Invocation">Callback Invocation</a></h4>
 
 <p>Once a given CPU's leaf <tt>rcu_node</tt> structure's
-<tt>-&gt;completed</tt> field has been updated, that CPU can begin
+<tt>-&gt;gp_seq</tt> field has been updated, that CPU can begin
 invoking its RCU callbacks that were waiting for this grace period
 to end.
 These callbacks are identified by <tt>rcu_advance_cbs()</tt>,
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg
index 754f426b297a..bf84fbab27ee 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg
@@ -384,11 +384,11 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.70710678"
-     inkscape:cx="617.89017"
-     inkscape:cy="542.52419"
-     inkscape:window-x="86"
-     inkscape:window-y="28"
+     inkscape:zoom="0.78716603"
+     inkscape:cx="513.06403"
+     inkscape:cy="623.1214"
+     inkscape:window-x="102"
+     inkscape:window-y="38"
      inkscape:window-maximized="0"
      inkscape:current-layer="g3188-3"
      fit-margin-top="5"
@@ -417,13 +417,15 @@
      id="g3188">
     <text
        xml:space="preserve"
-       x="3199.1516"
+       x="3145.9592"
        y="13255.592"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3143">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     <g
        id="g3107"
        transform="translate(947.90548,11584.029)">
@@ -502,13 +504,15 @@
     </g>
     <text
        xml:space="preserve"
-       x="5324.5371"
-       y="15414.598"
+       x="5264.4731"
+       y="15428.84"
        font-style="normal"
        font-weight="bold"
        font-size="192"
-       id="text202-753"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       id="text202-36-7"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-5">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      style="fill:none;stroke-width:0.025in"
@@ -547,15 +551,6 @@
        sodipodi:linespacing="125%"><tspan
          style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
          id="tspan3104-6-5-6-0">Leaf</tspan></text>
-    <text
-       xml:space="preserve"
-       x="7479.5796"
-       y="17699.943"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-9"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
     <path
        sodipodi:nodetypes="cc"
        inkscape:connector-curvature="0"
@@ -566,15 +561,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(-737.93887,7732.6672)"
        id="g3188-3">
-      <text
-         xml:space="preserve"
-         x="3225.7478"
-         y="13175.802"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-60"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp-&gt;completed =</text>
       <g
          id="g3107-62"
          transform="translate(947.90548,11584.029)">
@@ -607,15 +593,6 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-7">Root</tspan></text>
-      <text
-         xml:space="preserve"
-         x="3225.7478"
-         y="13390.038"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-60-3"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">       rnp-&gt;completed</text>
       <flowRoot
          xml:space="preserve"
          id="flowRoot3356"
@@ -627,7 +604,18 @@
              height="63.63961"
              x="332.34018"
              y="681.87292" /></flowRegion><flowPara
-           id="flowPara3362" /></flowRoot>    </g>
+           id="flowPara3362" /></flowRoot>      <text
+         xml:space="preserve"
+         x="3156.6121"
+         y="13317.754"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-36-6"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-0">rcu_seq_end(&amp;rsp-&gt;gp_seq)</tspan></text>
+    </g>
     <g
        style="fill:none;stroke-width:0.025in"
        transform="translate(-858.40227,7769.0342)"
@@ -859,6 +847,17 @@
        id="path3414-8-3-6-6"
        inkscape:connector-curvature="0"
        sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       x="7418.769"
+       y="17646.104"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-70"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-93">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      transform="translate(-1642.5377,-11611.245)"
@@ -887,13 +886,15 @@
     </g>
     <text
        xml:space="preserve"
-       x="5327.3057"
+       x="5274.1133"
        y="15428.84"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-36"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      transform="translate(-151.71746,-11647.612)"
@@ -972,13 +973,15 @@
          id="tspan3104-6-5-6-0-92">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7486.4907"
-       y="17670.119"
+       x="7408.5918"
+       y="17619.504"
        font-style="normal"
        font-weight="bold"
        font-size="192"
-       id="text202-6"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       id="text202-36-2"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-9">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      transform="translate(-6817.1997,-11647.612)"
@@ -1019,13 +1022,15 @@
          id="tspan3104-6-5-6-0-1">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7474.1382"
-       y="17688.926"
+       x="7416.8003"
+       y="17619.504"
        font-style="normal"
        font-weight="bold"
        font-size="192"
-       id="text202-5"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       id="text202-36-3"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-56">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <path
      style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -1059,15 +1064,6 @@
      id="path3414-8-3-6"
      inkscape:connector-curvature="0"
      sodipodi:nodetypes="cc" />
-  <text
-     xml:space="preserve"
-     x="7318.9653"
-     y="6031.6353"
-     font-style="normal"
-     font-weight="bold"
-     font-size="192"
-     id="text202-2"
-     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
   <g
      style="fill:none;stroke-width:0.025in"
      id="g4504-3-9"
@@ -1123,4 +1119,15 @@
      id="path3134-9-0-3-5"
      d="m 6875.6003,15833.906 1595.7755,0"
      style="fill:none;stroke:#969696;stroke-width:53.19251633;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send-36)" />
+  <text
+     xml:space="preserve"
+     x="7275.2612"
+     y="5971.8916"
+     font-style="normal"
+     font-weight="bold"
+     font-size="192"
+     id="text202-36-1"
+     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+       style="font-size:172.87567139px"
+       id="tspan3166-2">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
 </svg>
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg
index 0161262904ec..8c207550818f 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg
@@ -272,13 +272,13 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.70710678"
-     inkscape:cx="617.89019"
-     inkscape:cy="636.57143"
-     inkscape:window-x="697"
+     inkscape:zoom="2.6330492"
+     inkscape:cx="524.82797"
+     inkscape:cy="519.31194"
+     inkscape:window-x="79"
      inkscape:window-y="28"
      inkscape:window-maximized="0"
-     inkscape:current-layer="svg2"
+     inkscape:current-layer="g3188"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
@@ -305,13 +305,15 @@
      id="g3188">
     <text
        xml:space="preserve"
-       x="3305.5364"
+       x="3119.363"
        y="13255.592"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp-&gt;gpnum++</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3071">rcu_seq_start(rsp-&gt;gp_seq)</tspan></text>
     <g
        id="g3107"
        transform="translate(947.90548,11584.029)">
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg
index de6ecc51b00e..d24d7d555dbc 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg
@@ -19,7 +19,7 @@
    id="svg2"
    version="1.1"
    inkscape:version="0.48.4 r9939"
-   sodipodi:docname="TreeRCU-gp-init-2.svg">
+   sodipodi:docname="TreeRCU-gp-init-3.svg">
   <metadata
      id="metadata212">
     <rdf:RDF>
@@ -257,18 +257,22 @@
      inkscape:window-width="1087"
      inkscape:window-height="1144"
      id="namedview208"
-     showgrid="false"
-     inkscape:zoom="0.70710678"
+     showgrid="true"
+     inkscape:zoom="0.68224756"
      inkscape:cx="617.89019"
      inkscape:cy="625.84293"
-     inkscape:window-x="697"
+     inkscape:window-x="54"
      inkscape:window-y="28"
      inkscape:window-maximized="0"
-     inkscape:current-layer="svg2"
+     inkscape:current-layer="g3153"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
-     fit-margin-bottom="5" />
+     fit-margin-bottom="5">
+    <inkscape:grid
+       type="xygrid"
+       id="grid3090" />
+  </sodipodi:namedview>
   <path
      sodipodi:nodetypes="cccccccccccccccccccccccc"
      inkscape:connector-curvature="0"
@@ -281,13 +285,13 @@
      id="g3188">
     <text
        xml:space="preserve"
-       x="3305.5364"
+       x="3145.9592"
        y="13255.592"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     <g
        id="g3107"
        transform="translate(947.90548,11584.029)">
@@ -366,13 +370,13 @@
     </g>
     <text
        xml:space="preserve"
-       x="5392.3345"
-       y="15407.104"
+       x="5253.6904"
+       y="15407.032"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-6"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      style="fill:none;stroke-width:0.025in"
@@ -413,13 +417,13 @@
          id="tspan3104-6-5-6-0">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7536.4883"
-       y="17640.934"
+       x="7415.4365"
+       y="17670.572"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-9"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      transform="translate(-1642.5375,-11610.962)"
@@ -448,13 +452,13 @@
     </g>
     <text
        xml:space="preserve"
-       x="5378.4146"
-       y="15436.927"
+       x="5258.0688"
+       y="15412.313"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-3"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      transform="translate(-151.71726,-11647.329)"
@@ -533,13 +537,13 @@
          id="tspan3104-6-5-6-0-92">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7520.1294"
-       y="17673.639"
+       x="7405.2607"
+       y="17670.572"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-35"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      transform="translate(-6817.1998,-11647.329)"
@@ -580,13 +584,13 @@
          id="tspan3104-6-5-6-0-1">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7521.4663"
-       y="17666.062"
+       x="7413.4688"
+       y="17670.566"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-75"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <path
      style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -622,11 +626,11 @@
      sodipodi:nodetypes="cc" />
   <text
      xml:space="preserve"
-     x="7370.856"
-     y="5997.5972"
+     x="7271.9297"
+     y="6023.2412"
      font-style="normal"
      font-weight="bold"
      font-size="192"
      id="text202-62"
-     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
 </svg>
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
index b13b7b01bb3a..acd73c7ad0f4 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
@@ -1070,13 +1070,13 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.6004608"
-     inkscape:cx="826.65969"
-     inkscape:cy="483.3047"
-     inkscape:window-x="66"
-     inkscape:window-y="28"
+     inkscape:zoom="0.81932583"
+     inkscape:cx="840.45848"
+     inkscape:cy="5052.4242"
+     inkscape:window-x="787"
+     inkscape:window-y="24"
      inkscape:window-maximized="0"
-     inkscape:current-layer="svg2"
+     inkscape:current-layer="g4"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
@@ -1543,15 +1543,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(1749.0282,658.72243)"
        id="g3188">
-      <text
-         xml:space="preserve"
-         x="3305.5364"
-         y="13255.592"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-5"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp-&gt;gpnum++</text>
       <g
          id="g3107-62"
          transform="translate(947.90548,11584.029)">
@@ -1584,6 +1575,17 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-7">Root</tspan></text>
+      <text
+         xml:space="preserve"
+         x="3137.9988"
+         y="13271.316"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-626"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3071">rcu_seq_start(rsp-&gt;gp_seq)</tspan></text>
     </g>
     <rect
        ry="0"
@@ -2318,15 +2320,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(1739.0986,17188.625)"
        id="g3188-6">
-      <text
-         xml:space="preserve"
-         x="3305.5364"
-         y="13255.592"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-1"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
       <g
          id="g3107-5"
          transform="translate(947.90548,11584.029)">
@@ -2359,6 +2352,15 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-1">Root</tspan></text>
+      <text
+         xml:space="preserve"
+         x="3147.9268"
+         y="13240.524"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-1"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        style="fill:none;stroke-width:0.025in"
@@ -2387,13 +2389,13 @@
       </g>
       <text
          xml:space="preserve"
-         x="5392.3345"
-         y="15407.104"
+         x="5263.1094"
+         y="15411.646"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-6-7"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-92"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        style="fill:none;stroke-width:0.025in"
@@ -2434,13 +2436,13 @@
            id="tspan3104-6-5-6-0-94">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7536.4883"
-         y="17640.934"
+         x="7417.4053"
+         y="17655.502"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-9"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-759"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        transform="translate(-2353.8462,17224.992)"
@@ -2469,13 +2471,13 @@
       </g>
       <text
          xml:space="preserve"
-         x="5378.4146"
-         y="15436.927"
+         x="5246.1548"
+         y="15411.648"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-3"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-87"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        transform="translate(-863.02613,17188.625)"
@@ -2554,13 +2556,13 @@
            id="tspan3104-6-5-6-0-92-6">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7520.1294"
-         y="17673.639"
+         x="7433.8257"
+         y="17682.098"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-35"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-2"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        transform="translate(-7528.5085,17188.625)"
@@ -2601,13 +2603,13 @@
            id="tspan3104-6-5-6-0-1-8">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7521.4663"
-         y="17666.062"
+         x="7415.4404"
+         y="17682.098"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-75-1"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-0"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <path
        style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -2641,15 +2643,6 @@
        id="path3414-8-3-6-4"
        inkscape:connector-curvature="0"
        sodipodi:nodetypes="cc" />
-    <text
-       xml:space="preserve"
-       x="6659.5469"
-       y="34833.551"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-62"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
     <path
        sodipodi:nodetypes="ccc"
        inkscape:connector-curvature="0"
@@ -3844,7 +3837,7 @@
          font-weight="bold"
          font-size="192"
          id="text202-6-6-5"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gpnum</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gp_seq</text>
       <text
          xml:space="preserve"
          x="5035.4155"
@@ -4284,15 +4277,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(1874.038,53203.538)"
        id="g3188-7">
-      <text
-         xml:space="preserve"
-         x="3199.1516"
-         y="13255.592"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-82"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
       <g
          id="g3107-53"
          transform="translate(947.90548,11584.029)">
@@ -4325,6 +4309,17 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-19">Root</tspan></text>
+      <text
+         xml:space="preserve"
+         x="3175.896"
+         y="13240.11"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-36-3"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <rect
        ry="0"
@@ -4371,13 +4366,15 @@
       </g>
       <text
          xml:space="preserve"
-         x="5324.5371"
-         y="15414.598"
+         x="5264.4829"
+         y="15411.231"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-753"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         id="text202-36-7"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-5">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <g
        style="fill:none;stroke-width:0.025in"
@@ -4412,30 +4409,12 @@
        sodipodi:linespacing="125%"><tspan
          style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
          id="tspan3104-6-5-6-0-4">Leaf</tspan></text>
-    <text
-       xml:space="preserve"
-       x="10084.225"
-       y="70903.312"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-9-0"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
     <path
        sodipodi:nodetypes="ccc"
        inkscape:connector-curvature="0"
        id="path3134-9-0-3-9"
        d="m 6315.6122,72629.054 -20.9533,8108.684 1648.968,0"
        style="fill:none;stroke:#969696;stroke-width:53.19251251;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send)" />
-    <text
-       xml:space="preserve"
-       x="5092.4683"
-       y="74111.672"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-60"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rsp-&gt;completed =</text>
     <g
        style="fill:none;stroke-width:0.025in"
        id="g3107-62-6"
@@ -4469,15 +4448,6 @@
        sodipodi:linespacing="125%"><tspan
          style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
          id="tspan3104-6-5-7-7">Root</tspan></text>
-    <text
-       xml:space="preserve"
-       x="5092.4683"
-       y="74325.906"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-60-3"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">       rnp-&gt;completed</text>
     <g
        style="fill:none;stroke-width:0.025in"
        transform="translate(1746.2528,60972.572)"
@@ -4736,13 +4706,15 @@
       </g>
       <text
          xml:space="preserve"
-         x="5327.3057"
-         y="15428.84"
+         x="5274.1216"
+         y="15411.231"
          font-style="normal"
          font-weight="bold"
          font-size="192"
          id="text202-36"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-6">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <g
        transform="translate(-728.08545,53203.538)"
@@ -4821,13 +4793,15 @@
            id="tspan3104-6-5-6-0-92-5">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7486.4907"
-         y="17670.119"
+         x="7435.1987"
+         y="17708.281"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-6-2"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         id="text202-36-9"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-1">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <g
        transform="translate(-7393.5687,53203.538)"
@@ -4868,13 +4842,15 @@
            id="tspan3104-6-5-6-0-1-5">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7474.1382"
-         y="17688.926"
+         x="7416.8125"
+         y="17708.281"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-5-1"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         id="text202-36-35"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-62">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <path
        style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -4908,15 +4884,6 @@
        id="path3414-8-3-6-67"
        inkscape:connector-curvature="0"
        sodipodi:nodetypes="cc" />
-    <text
-       xml:space="preserve"
-       x="6742.6001"
-       y="70882.617"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-2"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
     <g
        style="fill:none;stroke-width:0.025in"
        id="g4504-3-9-6"
@@ -5131,5 +5098,47 @@
        font-size="192"
        id="text202-7-9-6-6-7"
        style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_do_batch()</text>
+    <text
+       xml:space="preserve"
+       x="6698.9019"
+       y="70885.211"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-2"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-7">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
+    <text
+       xml:space="preserve"
+       x="10023.457"
+       y="70885.234"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-0"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-9">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
+    <text
+       xml:space="preserve"
+       x="5023.3389"
+       y="74209.773"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-36"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-0">rcu_seq_end(&amp;rsp-&gt;gp_seq)</tspan></text>
+    <text
+       xml:space="preserve"
+       x="6562.5884"
+       y="34870.727"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-3"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
 </svg>
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
index de3992f4cbe1..149bec2a4493 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
@@ -300,13 +300,13 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.70710678"
-     inkscape:cx="616.47598"
-     inkscape:cy="595.41964"
-     inkscape:window-x="813"
+     inkscape:zoom="0.96484375"
+     inkscape:cx="507.0191"
+     inkscape:cy="885.62207"
+     inkscape:window-x="47"
      inkscape:window-y="28"
      inkscape:window-maximized="0"
-     inkscape:current-layer="g4405"
+     inkscape:current-layer="g3115"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
@@ -710,7 +710,7 @@
          font-weight="bold"
          font-size="192"
          id="text202-6-6"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gpnum</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gp_seq</text>
       <text
          xml:space="preserve"
          x="5035.4155"
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 4259f95c3261..f99cf11b314b 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -172,7 +172,7 @@ it will print a message similar to the following:
 	INFO: rcu_sched detected stalls on CPUs/tasks:
 	2-...: (3 GPs behind) idle=06c/0/0 softirq=1453/1455 fqs=0
 	16-...: (0 ticks this GP) idle=81c/0/0 softirq=764/764 fqs=0
-	(detected by 32, t=2603 jiffies, g=7073, c=7072, q=625)
+	(detected by 32, t=2603 jiffies, g=7075, q=625)
 
 This message indicates that CPU 32 detected that CPUs 2 and 16 were both
 causing stalls, and that the stall was affecting RCU-sched.  This message
@@ -215,11 +215,10 @@ CPU since the last time that this CPU noted the beginning of a grace
 period.
 
 The "detected by" line indicates which CPU detected the stall (in this
-case, CPU 32), how many jiffies have elapsed since the start of the
-grace period (in this case 2603), the number of the last grace period
-to start and to complete (7073 and 7072, respectively), and an estimate
-of the total number of RCU callbacks queued across all CPUs (625 in
-this case).
+case, CPU 32), how many jiffies have elapsed since the start of the grace
+period (in this case 2603), the grace-period sequence number (7075), and
+an estimate of the total number of RCU callbacks queued across all CPUs
+(625 in this case).
 
 In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed
 for each CPU:
@@ -266,15 +265,16 @@ If the relevant grace-period kthread has been unable to run prior to
 the stall warning, as was the case in the "All QSes seen" line above,
 the following additional line is printed:
 
-	kthread starved for 23807 jiffies! g7073 c7072 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1
+	kthread starved for 23807 jiffies! g7075 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1 ->cpu=5
 
 Starving the grace-period kthreads of CPU time can of course result
 in RCU CPU stall warnings even when all CPUs and tasks have passed
-through the required quiescent states.  The "g" and "c" numbers flag the
-number of the last grace period started and completed, respectively,
-the "f" precedes the ->gp_flags command to the grace-period kthread,
-the "RCU_GP_WAIT_FQS" indicates that the kthread is waiting for a short
-timeout, and the "state" precedes value of the task_struct ->state field.
+through the required quiescent states.  The "g" number shows the current
+grace-period sequence number, the "f" precedes the ->gp_flags command
+to the grace-period kthread, the "RCU_GP_WAIT_FQS" indicates that the
+kthread is waiting for a short timeout, the "state" precedes value of the
+task_struct ->state field, and the "cpu" indicates that the grace-period
+kthread last ran on CPU 5.
 
 
 Multiple Warnings From One Stall
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 65eb856526b7..c2a7facf7ff9 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -588,6 +588,7 @@ It is extremely simple:
 	void synchronize_rcu(void)
 	{
 		write_lock(&rcu_gp_mutex);
+		smp_mb__after_spinlock();
 		write_unlock(&rcu_gp_mutex);
 	}
 
@@ -609,12 +610,15 @@ don't forget about them when submitting patches making use of RCU!]
 
 The rcu_read_lock() and rcu_read_unlock() primitive read-acquire
 and release a global reader-writer lock.  The synchronize_rcu()
-primitive write-acquires this same lock, then immediately releases
-it.  This means that once synchronize_rcu() exits, all RCU read-side
-critical sections that were in progress before synchronize_rcu() was
-called are guaranteed to have completed -- there is no way that
-synchronize_rcu() would have been able to write-acquire the lock
-otherwise.
+primitive write-acquires this same lock, then releases it.  This means
+that once synchronize_rcu() exits, all RCU read-side critical sections
+that were in progress before synchronize_rcu() was called are guaranteed
+to have completed -- there is no way that synchronize_rcu() would have
+been able to write-acquire the lock otherwise.  The smp_mb__after_spinlock()
+promotes synchronize_rcu() to a full memory barrier in compliance with
+the "Memory-Barrier Guarantees" listed in:
+
+	Documentation/RCU/Design/Requirements/Requirements.html.
 
 It is possible to nest rcu_read_lock(), since reader-writer locks may
 be recursively acquired.  Note also that rcu_read_lock() is immune
@@ -816,11 +820,13 @@ RCU list traversal:
 	list_next_rcu
 	list_for_each_entry_rcu
 	list_for_each_entry_continue_rcu
+	list_for_each_entry_from_rcu
 	hlist_first_rcu
 	hlist_next_rcu
 	hlist_pprev_rcu
 	hlist_for_each_entry_rcu
 	hlist_for_each_entry_rcu_bh
+	hlist_for_each_entry_from_rcu
 	hlist_for_each_entry_continue_rcu
 	hlist_for_each_entry_continue_rcu_bh
 	hlist_nulls_first_rcu
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 8a2c52d5c53b..1746131bc9cb 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -51,6 +51,9 @@ v1 is available under Documentation/cgroup-v1/.
      5-3. IO
        5-3-1. IO Interface Files
        5-3-2. Writeback
+       5-3-3. IO Latency
+         5-3-3-1. How IO Latency Throttling Works
+         5-3-3-2. IO Latency Interface Files
      5-4. PID
        5-4-1. PID Interface Files
      5-5. Device
@@ -1314,17 +1317,19 @@ IO Interface Files
 	Lines are keyed by $MAJ:$MIN device numbers and not ordered.
 	The following nested keys are defined.
 
-	  ======	===================
+	  ======	=====================
 	  rbytes	Bytes read
 	  wbytes	Bytes written
 	  rios		Number of read IOs
 	  wios		Number of write IOs
-	  ======	===================
+	  dbytes	Bytes discarded
+	  dios		Number of discard IOs
+	  ======	=====================
 
 	An example read output follows:
 
-	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353
-	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252
+	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 dbytes=0 dios=0
+	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 dbytes=50331648 dios=3021
 
   io.weight
 	A read-write flat-keyed file which exists on non-root cgroups.
@@ -1446,6 +1451,85 @@ writeback as follows.
 	vm.dirty[_background]_ratio.
 
 
+IO Latency
+~~~~~~~~~~
+
+This is a cgroup v2 controller for IO workload protection.  You provide a group
+with a latency target, and if the average latency exceeds that target the
+controller will throttle any peers that have a lower latency target than the
+protected workload.
+
+The limits are only applied at the peer level in the hierarchy.  This means that
+in the diagram below, only groups A, B, and C will influence each other, and
+groups D and F will influence each other.  Group G will influence nobody.
+
+			[root]
+		/	   |		\
+		A	   B		C
+	       /  \        |
+	      D    F	   G
+
+
+So the ideal way to configure this is to set io.latency in groups A, B, and C.
+Generally you do not want to set a value lower than the latency your device
+supports.  Experiment to find the value that works best for your workload.
+Start at higher than the expected latency for your device and watch the
+avg_lat value in io.stat for your workload group to get an idea of the
+latency you see during normal operation.  Use the avg_lat value as a basis for
+your real setting, setting at 10-15% higher than the value in io.stat.
+
+How IO Latency Throttling Works
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+io.latency is work conserving; so as long as everybody is meeting their latency
+target the controller doesn't do anything.  Once a group starts missing its
+target it begins throttling any peer group that has a higher target than itself.
+This throttling takes 2 forms:
+
+- Queue depth throttling.  This is the number of outstanding IO's a group is
+  allowed to have.  We will clamp down relatively quickly, starting at no limit
+  and going all the way down to 1 IO at a time.
+
+- Artificial delay induction.  There are certain types of IO that cannot be
+  throttled without possibly adversely affecting higher priority groups.  This
+  includes swapping and metadata IO.  These types of IO are allowed to occur
+  normally, however they are "charged" to the originating group.  If the
+  originating group is being throttled you will see the use_delay and delay
+  fields in io.stat increase.  The delay value is how many microseconds that are
+  being added to any process that runs in this group.  Because this number can
+  grow quite large if there is a lot of swapping or metadata IO occurring we
+  limit the individual delay events to 1 second at a time.
+
+Once the victimized group starts meeting its latency target again it will start
+unthrottling any peer groups that were throttled previously.  If the victimized
+group simply stops doing IO the global counter will unthrottle appropriately.
+
+IO Latency Interface Files
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+  io.latency
+	This takes a similar format as the other controllers.
+
+		"MAJOR:MINOR target=<target time in microseconds"
+
+  io.stat
+	If the controller is enabled you will see extra stats in io.stat in
+	addition to the normal ones.
+
+	  depth
+		This is the current queue depth for the group.
+
+	  avg_lat
+		This is an exponential moving average with a decay rate of 1/exp
+		bound by the sampling interval.  The decay rate interval can be
+		calculated by multiplying the win value in io.stat by the
+		corresponding number of samples based on the win value.
+
+	  win
+		The sampling window size in milliseconds.  This is the minimum
+		duration of time between evaluation events.  Windows only elapse
+		with IO activity.  Idle periods extend the most recent window.
+
 PID
 ---
 
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index 48d70af11652..0873685bab0f 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -17,6 +17,15 @@ etc.
    kernel-parameters
    devices
 
+This section describes CPU vulnerabilities and provides an overview of the
+possible mitigations along with guidance for selecting mitigations if they
+are configurable at compile, boot or run time.
+
+.. toctree::
+   :maxdepth: 1
+
+   l1tf
+
 Here is a set of documents aimed at users who are trying to track down
 problems and bugs in particular.
 
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 533ff5c68970..5a67e409d370 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1967,10 +1967,84 @@
 			(virtualized real and unpaged mode) on capable
 			Intel chips. Default is 1 (enabled)
 
+	kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
+			CVE-2018-3620.
+
+			Valid arguments: never, cond, always
+
+			always: L1D cache flush on every VMENTER.
+			cond:	Flush L1D on VMENTER only when the code between
+				VMEXIT and VMENTER can leak host memory.
+			never:	Disables the mitigation
+
+			Default is cond (do L1 cache flush in specific instances)
+
 	kvm-intel.vpid=	[KVM,Intel] Disable Virtual Processor Identification
 			feature (tagged TLBs) on capable Intel chips.
 			Default is 1 (enabled)
 
+	l1tf=           [X86] Control mitigation of the L1TF vulnerability on
+			      affected CPUs
+
+			The kernel PTE inversion protection is unconditionally
+			enabled and cannot be disabled.
+
+			full
+				Provides all available mitigations for the
+				L1TF vulnerability. Disables SMT and
+				enables all mitigations in the
+				hypervisors, i.e. unconditional L1D flush.
+
+				SMT control and L1D flush control via the
+				sysfs interface is still possible after
+				boot.  Hypervisors will issue a warning
+				when the first VM is started in a
+				potentially insecure configuration,
+				i.e. SMT enabled or L1D flush disabled.
+
+			full,force
+				Same as 'full', but disables SMT and L1D
+				flush runtime control. Implies the
+				'nosmt=force' command line option.
+				(i.e. sysfs control of SMT is disabled.)
+
+			flush
+				Leaves SMT enabled and enables the default
+				hypervisor mitigation, i.e. conditional
+				L1D flush.
+
+				SMT control and L1D flush control via the
+				sysfs interface is still possible after
+				boot.  Hypervisors will issue a warning
+				when the first VM is started in a
+				potentially insecure configuration,
+				i.e. SMT enabled or L1D flush disabled.
+
+			flush,nosmt
+
+				Disables SMT and enables the default
+				hypervisor mitigation.
+
+				SMT control and L1D flush control via the
+				sysfs interface is still possible after
+				boot.  Hypervisors will issue a warning
+				when the first VM is started in a
+				potentially insecure configuration,
+				i.e. SMT enabled or L1D flush disabled.
+
+			flush,nowarn
+				Same as 'flush', but hypervisors will not
+				warn when a VM is started in a potentially
+				insecure configuration.
+
+			off
+				Disables hypervisor mitigations and doesn't
+				emit any warnings.
+
+			Default is 'flush'.
+
+			For details see: Documentation/admin-guide/l1tf.rst
+
 	l2cr=		[PPC]
 
 	l3cr=		[PPC]
@@ -2687,6 +2761,10 @@
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
+			[KNL,x86] Disable symmetric multithreading (SMT).
+			nosmt=force: Force disable SMT, cannot be undone
+				     via the sysfs control file.
+
 	nospectre_v2	[X86] Disable all mitigations for the Spectre variant 2
 			(indirect branch prediction) vulnerability. System may
 			allow data leaks with this option, which is equivalent
@@ -2835,8 +2913,6 @@
 
 	nosync		[HW,M68K] Disables sync negotiation for all devices.
 
-	notsc		[BUGS=X86-32] Disable Time Stamp Counter
-
 	nowatchdog	[KNL] Disable both lockup detectors, i.e.
 			soft-lockup and NMI watchdog (hard-lockup).
 
@@ -3632,8 +3708,8 @@
 			Set time (s) after boot for CPU-hotplug testing.
 
 	rcutorture.onoff_interval= [KNL]
-			Set time (s) between CPU-hotplug operations, or
-			zero to disable CPU-hotplug testing.
+			Set time (jiffies) between CPU-hotplug operations,
+			or zero to disable CPU-hotplug testing.
 
 	rcutorture.shuffle_interval= [KNL]
 			Set task-shuffle interval (s).  Shuffling tasks
diff --git a/Documentation/admin-guide/l1tf.rst b/Documentation/admin-guide/l1tf.rst
new file mode 100644
index 000000000000..bae52b845de0
--- /dev/null
+++ b/Documentation/admin-guide/l1tf.rst
@@ -0,0 +1,610 @@
+L1TF - L1 Terminal Fault
+========================
+
+L1 Terminal Fault is a hardware vulnerability which allows unprivileged
+speculative access to data which is available in the Level 1 Data Cache
+when the page table entry controlling the virtual address, which is used
+for the access, has the Present bit cleared or other reserved bits set.
+
+Affected processors
+-------------------
+
+This vulnerability affects a wide range of Intel processors. The
+vulnerability is not present on:
+
+   - Processors from AMD, Centaur and other non Intel vendors
+
+   - Older processor models, where the CPU family is < 6
+
+   - A range of Intel ATOM processors (Cedarview, Cloverview, Lincroft,
+     Penwell, Pineview, Silvermont, Airmont, Merrifield)
+
+   - The Intel XEON PHI family
+
+   - Intel processors which have the ARCH_CAP_RDCL_NO bit set in the
+     IA32_ARCH_CAPABILITIES MSR. If the bit is set the CPU is not affected
+     by the Meltdown vulnerability either. These CPUs should become
+     available by end of 2018.
+
+Whether a processor is affected or not can be read out from the L1TF
+vulnerability file in sysfs. See :ref:`l1tf_sys_info`.
+
+Related CVEs
+------------
+
+The following CVE entries are related to the L1TF vulnerability:
+
+   =============  =================  ==============================
+   CVE-2018-3615  L1 Terminal Fault  SGX related aspects
+   CVE-2018-3620  L1 Terminal Fault  OS, SMM related aspects
+   CVE-2018-3646  L1 Terminal Fault  Virtualization related aspects
+   =============  =================  ==============================
+
+Problem
+-------
+
+If an instruction accesses a virtual address for which the relevant page
+table entry (PTE) has the Present bit cleared or other reserved bits set,
+then speculative execution ignores the invalid PTE and loads the referenced
+data if it is present in the Level 1 Data Cache, as if the page referenced
+by the address bits in the PTE was still present and accessible.
+
+While this is a purely speculative mechanism and the instruction will raise
+a page fault when it is retired eventually, the pure act of loading the
+data and making it available to other speculative instructions opens up the
+opportunity for side channel attacks to unprivileged malicious code,
+similar to the Meltdown attack.
+
+While Meltdown breaks the user space to kernel space protection, L1TF
+allows to attack any physical memory address in the system and the attack
+works across all protection domains. It allows an attack of SGX and also
+works from inside virtual machines because the speculation bypasses the
+extended page table (EPT) protection mechanism.
+
+
+Attack scenarios
+----------------
+
+1. Malicious user space
+^^^^^^^^^^^^^^^^^^^^^^^
+
+   Operating Systems store arbitrary information in the address bits of a
+   PTE which is marked non present. This allows a malicious user space
+   application to attack the physical memory to which these PTEs resolve.
+   In some cases user-space can maliciously influence the information
+   encoded in the address bits of the PTE, thus making attacks more
+   deterministic and more practical.
+
+   The Linux kernel contains a mitigation for this attack vector, PTE
+   inversion, which is permanently enabled and has no performance
+   impact. The kernel ensures that the address bits of PTEs, which are not
+   marked present, never point to cacheable physical memory space.
+
+   A system with an up to date kernel is protected against attacks from
+   malicious user space applications.
+
+2. Malicious guest in a virtual machine
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The fact that L1TF breaks all domain protections allows malicious guest
+   OSes, which can control the PTEs directly, and malicious guest user
+   space applications, which run on an unprotected guest kernel lacking the
+   PTE inversion mitigation for L1TF, to attack physical host memory.
+
+   A special aspect of L1TF in the context of virtualization is symmetric
+   multi threading (SMT). The Intel implementation of SMT is called
+   HyperThreading. The fact that Hyperthreads on the affected processors
+   share the L1 Data Cache (L1D) is important for this. As the flaw allows
+   only to attack data which is present in L1D, a malicious guest running
+   on one Hyperthread can attack the data which is brought into the L1D by
+   the context which runs on the sibling Hyperthread of the same physical
+   core. This context can be host OS, host user space or a different guest.
+
+   If the processor does not support Extended Page Tables, the attack is
+   only possible, when the hypervisor does not sanitize the content of the
+   effective (shadow) page tables.
+
+   While solutions exist to mitigate these attack vectors fully, these
+   mitigations are not enabled by default in the Linux kernel because they
+   can affect performance significantly. The kernel provides several
+   mechanisms which can be utilized to address the problem depending on the
+   deployment scenario. The mitigations, their protection scope and impact
+   are described in the next sections.
+
+   The default mitigations and the rationale for choosing them are explained
+   at the end of this document. See :ref:`default_mitigations`.
+
+.. _l1tf_sys_info:
+
+L1TF system information
+-----------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current L1TF
+status of the system: whether the system is vulnerable, and which
+mitigations are active. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/l1tf
+
+The possible values in this file are:
+
+  ===========================   ===============================
+  'Not affected'		The processor is not vulnerable
+  'Mitigation: PTE Inversion'	The host protection is active
+  ===========================   ===============================
+
+If KVM/VMX is enabled and the processor is vulnerable then the following
+information is appended to the 'Mitigation: PTE Inversion' part:
+
+  - SMT status:
+
+    =====================  ================
+    'VMX: SMT vulnerable'  SMT is enabled
+    'VMX: SMT disabled'    SMT is disabled
+    =====================  ================
+
+  - L1D Flush mode:
+
+    ================================  ====================================
+    'L1D vulnerable'		      L1D flushing is disabled
+
+    'L1D conditional cache flushes'   L1D flush is conditionally enabled
+
+    'L1D cache flushes'		      L1D flush is unconditionally enabled
+    ================================  ====================================
+
+The resulting grade of protection is discussed in the following sections.
+
+
+Host mitigation mechanism
+-------------------------
+
+The kernel is unconditionally protected against L1TF attacks from malicious
+user space running on the host.
+
+
+Guest mitigation mechanisms
+---------------------------
+
+.. _l1d_flush:
+
+1. L1D flush on VMENTER
+^^^^^^^^^^^^^^^^^^^^^^^
+
+   To make sure that a guest cannot attack data which is present in the L1D
+   the hypervisor flushes the L1D before entering the guest.
+
+   Flushing the L1D evicts not only the data which should not be accessed
+   by a potentially malicious guest, it also flushes the guest
+   data. Flushing the L1D has a performance impact as the processor has to
+   bring the flushed guest data back into the L1D. Depending on the
+   frequency of VMEXIT/VMENTER and the type of computations in the guest
+   performance degradation in the range of 1% to 50% has been observed. For
+   scenarios where guest VMEXIT/VMENTER are rare the performance impact is
+   minimal. Virtio and mechanisms like posted interrupts are designed to
+   confine the VMEXITs to a bare minimum, but specific configurations and
+   application scenarios might still suffer from a high VMEXIT rate.
+
+   The kernel provides two L1D flush modes:
+    - conditional ('cond')
+    - unconditional ('always')
+
+   The conditional mode avoids L1D flushing after VMEXITs which execute
+   only audited code paths before the corresponding VMENTER. These code
+   paths have been verified that they cannot expose secrets or other
+   interesting data to an attacker, but they can leak information about the
+   address space layout of the hypervisor.
+
+   Unconditional mode flushes L1D on all VMENTER invocations and provides
+   maximum protection. It has a higher overhead than the conditional
+   mode. The overhead cannot be quantified correctly as it depends on the
+   workload scenario and the resulting number of VMEXITs.
+
+   The general recommendation is to enable L1D flush on VMENTER. The kernel
+   defaults to conditional mode on affected processors.
+
+   **Note**, that L1D flush does not prevent the SMT problem because the
+   sibling thread will also bring back its data into the L1D which makes it
+   attackable again.
+
+   L1D flush can be controlled by the administrator via the kernel command
+   line and sysfs control files. See :ref:`mitigation_control_command_line`
+   and :ref:`mitigation_control_kvm`.
+
+.. _guest_confinement:
+
+2. Guest VCPU confinement to dedicated physical cores
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   To address the SMT problem, it is possible to make a guest or a group of
+   guests affine to one or more physical cores. The proper mechanism for
+   that is to utilize exclusive cpusets to ensure that no other guest or
+   host tasks can run on these cores.
+
+   If only a single guest or related guests run on sibling SMT threads on
+   the same physical core then they can only attack their own memory and
+   restricted parts of the host memory.
+
+   Host memory is attackable, when one of the sibling SMT threads runs in
+   host OS (hypervisor) context and the other in guest context. The amount
+   of valuable information from the host OS context depends on the context
+   which the host OS executes, i.e. interrupts, soft interrupts and kernel
+   threads. The amount of valuable data from these contexts cannot be
+   declared as non-interesting for an attacker without deep inspection of
+   the code.
+
+   **Note**, that assigning guests to a fixed set of physical cores affects
+   the ability of the scheduler to do load balancing and might have
+   negative effects on CPU utilization depending on the hosting
+   scenario. Disabling SMT might be a viable alternative for particular
+   scenarios.
+
+   For further information about confining guests to a single or to a group
+   of cores consult the cpusets documentation:
+
+   https://www.kernel.org/doc/Documentation/cgroup-v1/cpusets.txt
+
+.. _interrupt_isolation:
+
+3. Interrupt affinity
+^^^^^^^^^^^^^^^^^^^^^
+
+   Interrupts can be made affine to logical CPUs. This is not universally
+   true because there are types of interrupts which are truly per CPU
+   interrupts, e.g. the local timer interrupt. Aside of that multi queue
+   devices affine their interrupts to single CPUs or groups of CPUs per
+   queue without allowing the administrator to control the affinities.
+
+   Moving the interrupts, which can be affinity controlled, away from CPUs
+   which run untrusted guests, reduces the attack vector space.
+
+   Whether the interrupts with are affine to CPUs, which run untrusted
+   guests, provide interesting data for an attacker depends on the system
+   configuration and the scenarios which run on the system. While for some
+   of the interrupts it can be assumed that they won't expose interesting
+   information beyond exposing hints about the host OS memory layout, there
+   is no way to make general assumptions.
+
+   Interrupt affinity can be controlled by the administrator via the
+   /proc/irq/$NR/smp_affinity[_list] files. Limited documentation is
+   available at:
+
+   https://www.kernel.org/doc/Documentation/IRQ-affinity.txt
+
+.. _smt_control:
+
+4. SMT control
+^^^^^^^^^^^^^^
+
+   To prevent the SMT issues of L1TF it might be necessary to disable SMT
+   completely. Disabling SMT can have a significant performance impact, but
+   the impact depends on the hosting scenario and the type of workloads.
+   The impact of disabling SMT needs also to be weighted against the impact
+   of other mitigation solutions like confining guests to dedicated cores.
+
+   The kernel provides a sysfs interface to retrieve the status of SMT and
+   to control it. It also provides a kernel command line interface to
+   control SMT.
+
+   The kernel command line interface consists of the following options:
+
+     =========== ==========================================================
+     nosmt	 Affects the bring up of the secondary CPUs during boot. The
+		 kernel tries to bring all present CPUs online during the
+		 boot process. "nosmt" makes sure that from each physical
+		 core only one - the so called primary (hyper) thread is
+		 activated. Due to a design flaw of Intel processors related
+		 to Machine Check Exceptions the non primary siblings have
+		 to be brought up at least partially and are then shut down
+		 again.  "nosmt" can be undone via the sysfs interface.
+
+     nosmt=force Has the same effect as "nosmt" but it does not allow to
+		 undo the SMT disable via the sysfs interface.
+     =========== ==========================================================
+
+   The sysfs interface provides two files:
+
+   - /sys/devices/system/cpu/smt/control
+   - /sys/devices/system/cpu/smt/active
+
+   /sys/devices/system/cpu/smt/control:
+
+     This file allows to read out the SMT control state and provides the
+     ability to disable or (re)enable SMT. The possible states are:
+
+	==============  ===================================================
+	on		SMT is supported by the CPU and enabled. All
+			logical CPUs can be onlined and offlined without
+			restrictions.
+
+	off		SMT is supported by the CPU and disabled. Only
+			the so called primary SMT threads can be onlined
+			and offlined without restrictions. An attempt to
+			online a non-primary sibling is rejected
+
+	forceoff	Same as 'off' but the state cannot be controlled.
+			Attempts to write to the control file are rejected.
+
+	notsupported	The processor does not support SMT. It's therefore
+			not affected by the SMT implications of L1TF.
+			Attempts to write to the control file are rejected.
+	==============  ===================================================
+
+     The possible states which can be written into this file to control SMT
+     state are:
+
+     - on
+     - off
+     - forceoff
+
+   /sys/devices/system/cpu/smt/active:
+
+     This file reports whether SMT is enabled and active, i.e. if on any
+     physical core two or more sibling threads are online.
+
+   SMT control is also possible at boot time via the l1tf kernel command
+   line parameter in combination with L1D flush control. See
+   :ref:`mitigation_control_command_line`.
+
+5. Disabling EPT
+^^^^^^^^^^^^^^^^
+
+  Disabling EPT for virtual machines provides full mitigation for L1TF even
+  with SMT enabled, because the effective page tables for guests are
+  managed and sanitized by the hypervisor. Though disabling EPT has a
+  significant performance impact especially when the Meltdown mitigation
+  KPTI is enabled.
+
+  EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter.
+
+There is ongoing research and development for new mitigation mechanisms to
+address the performance impact of disabling SMT or EPT.
+
+.. _mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the L1TF mitigations at boot
+time with the option "l1tf=". The valid arguments for this option are:
+
+  ============  =============================================================
+  full		Provides all available mitigations for the L1TF
+		vulnerability. Disables SMT and enables all mitigations in
+		the hypervisors, i.e. unconditional L1D flushing
+
+		SMT control and L1D flush control via the sysfs interface
+		is still possible after boot.  Hypervisors will issue a
+		warning when the first VM is started in a potentially
+		insecure configuration, i.e. SMT enabled or L1D flush
+		disabled.
+
+  full,force	Same as 'full', but disables SMT and L1D flush runtime
+		control. Implies the 'nosmt=force' command line option.
+		(i.e. sysfs control of SMT is disabled.)
+
+  flush		Leaves SMT enabled and enables the default hypervisor
+		mitigation, i.e. conditional L1D flushing
+
+		SMT control and L1D flush control via the sysfs interface
+		is still possible after boot.  Hypervisors will issue a
+		warning when the first VM is started in a potentially
+		insecure configuration, i.e. SMT enabled or L1D flush
+		disabled.
+
+  flush,nosmt	Disables SMT and enables the default hypervisor mitigation,
+		i.e. conditional L1D flushing.
+
+		SMT control and L1D flush control via the sysfs interface
+		is still possible after boot.  Hypervisors will issue a
+		warning when the first VM is started in a potentially
+		insecure configuration, i.e. SMT enabled or L1D flush
+		disabled.
+
+  flush,nowarn	Same as 'flush', but hypervisors will not warn when a VM is
+		started in a potentially insecure configuration.
+
+  off		Disables hypervisor mitigations and doesn't emit any
+		warnings.
+  ============  =============================================================
+
+The default is 'flush'. For details about L1D flushing see :ref:`l1d_flush`.
+
+
+.. _mitigation_control_kvm:
+
+Mitigation control for KVM - module parameter
+-------------------------------------------------------------
+
+The KVM hypervisor mitigation mechanism, flushing the L1D cache when
+entering a guest, can be controlled with a module parameter.
+
+The option/parameter is "kvm-intel.vmentry_l1d_flush=". It takes the
+following arguments:
+
+  ============  ==============================================================
+  always	L1D cache flush on every VMENTER.
+
+  cond		Flush L1D on VMENTER only when the code between VMEXIT and
+		VMENTER can leak host memory which is considered
+		interesting for an attacker. This still can leak host memory
+		which allows e.g. to determine the hosts address space layout.
+
+  never		Disables the mitigation
+  ============  ==============================================================
+
+The parameter can be provided on the kernel command line, as a module
+parameter when loading the modules and at runtime modified via the sysfs
+file:
+
+/sys/module/kvm_intel/parameters/vmentry_l1d_flush
+
+The default is 'cond'. If 'l1tf=full,force' is given on the kernel command
+line, then 'always' is enforced and the kvm-intel.vmentry_l1d_flush
+module parameter is ignored and writes to the sysfs file are rejected.
+
+
+Mitigation selection guide
+--------------------------
+
+1. No virtualization in use
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The system is protected by the kernel unconditionally and no further
+   action is required.
+
+2. Virtualization with trusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   If the guest comes from a trusted source and the guest OS kernel is
+   guaranteed to have the L1TF mitigations in place the system is fully
+   protected against L1TF and no further action is required.
+
+   To avoid the overhead of the default L1D flushing on VMENTER the
+   administrator can disable the flushing via the kernel command line and
+   sysfs control files. See :ref:`mitigation_control_command_line` and
+   :ref:`mitigation_control_kvm`.
+
+
+3. Virtualization with untrusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+3.1. SMT not supported or disabled
+""""""""""""""""""""""""""""""""""
+
+  If SMT is not supported by the processor or disabled in the BIOS or by
+  the kernel, it's only required to enforce L1D flushing on VMENTER.
+
+  Conditional L1D flushing is the default behaviour and can be tuned. See
+  :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`.
+
+3.2. EPT not supported or disabled
+""""""""""""""""""""""""""""""""""
+
+  If EPT is not supported by the processor or disabled in the hypervisor,
+  the system is fully protected. SMT can stay enabled and L1D flushing on
+  VMENTER is not required.
+
+  EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter.
+
+3.3. SMT and EPT supported and active
+"""""""""""""""""""""""""""""""""""""
+
+  If SMT and EPT are supported and active then various degrees of
+  mitigations can be employed:
+
+  - L1D flushing on VMENTER:
+
+    L1D flushing on VMENTER is the minimal protection requirement, but it
+    is only potent in combination with other mitigation methods.
+
+    Conditional L1D flushing is the default behaviour and can be tuned. See
+    :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`.
+
+  - Guest confinement:
+
+    Confinement of guests to a single or a group of physical cores which
+    are not running any other processes, can reduce the attack surface
+    significantly, but interrupts, soft interrupts and kernel threads can
+    still expose valuable data to a potential attacker. See
+    :ref:`guest_confinement`.
+
+  - Interrupt isolation:
+
+    Isolating the guest CPUs from interrupts can reduce the attack surface
+    further, but still allows a malicious guest to explore a limited amount
+    of host physical memory. This can at least be used to gain knowledge
+    about the host address space layout. The interrupts which have a fixed
+    affinity to the CPUs which run the untrusted guests can depending on
+    the scenario still trigger soft interrupts and schedule kernel threads
+    which might expose valuable information. See
+    :ref:`interrupt_isolation`.
+
+The above three mitigation methods combined can provide protection to a
+certain degree, but the risk of the remaining attack surface has to be
+carefully analyzed. For full protection the following methods are
+available:
+
+  - Disabling SMT:
+
+    Disabling SMT and enforcing the L1D flushing provides the maximum
+    amount of protection. This mitigation is not depending on any of the
+    above mitigation methods.
+
+    SMT control and L1D flushing can be tuned by the command line
+    parameters 'nosmt', 'l1tf', 'kvm-intel.vmentry_l1d_flush' and at run
+    time with the matching sysfs control files. See :ref:`smt_control`,
+    :ref:`mitigation_control_command_line` and
+    :ref:`mitigation_control_kvm`.
+
+  - Disabling EPT:
+
+    Disabling EPT provides the maximum amount of protection as well. It is
+    not depending on any of the above mitigation methods. SMT can stay
+    enabled and L1D flushing is not required, but the performance impact is
+    significant.
+
+    EPT can be disabled in the hypervisor via the 'kvm-intel.ept'
+    parameter.
+
+3.4. Nested virtual machines
+""""""""""""""""""""""""""""
+
+When nested virtualization is in use, three operating systems are involved:
+the bare metal hypervisor, the nested hypervisor and the nested virtual
+machine.  VMENTER operations from the nested hypervisor into the nested
+guest will always be processed by the bare metal hypervisor. If KVM is the
+bare metal hypervisor it wiil:
+
+ - Flush the L1D cache on every switch from the nested hypervisor to the
+   nested virtual machine, so that the nested hypervisor's secrets are not
+   exposed to the nested virtual machine;
+
+ - Flush the L1D cache on every switch from the nested virtual machine to
+   the nested hypervisor; this is a complex operation, and flushing the L1D
+   cache avoids that the bare metal hypervisor's secrets are exposed to the
+   nested virtual machine;
+
+ - Instruct the nested hypervisor to not perform any L1D cache flush. This
+   is an optimization to avoid double L1D flushing.
+
+
+.. _default_mitigations:
+
+Default mitigations
+-------------------
+
+  The kernel default mitigations for vulnerable processors are:
+
+  - PTE inversion to protect against malicious user space. This is done
+    unconditionally and cannot be controlled.
+
+  - L1D conditional flushing on VMENTER when EPT is enabled for
+    a guest.
+
+  The kernel does not by default enforce the disabling of SMT, which leaves
+  SMT systems vulnerable when running untrusted guests with EPT enabled.
+
+  The rationale for this choice is:
+
+  - Force disabling SMT can break existing setups, especially with
+    unattended updates.
+
+  - If regular users run untrusted guests on their machine, then L1TF is
+    just an add on to other malware which might be embedded in an untrusted
+    guest, e.g. spam-bots or attacks on the local network.
+
+    There is no technical way to prevent a user from running untrusted code
+    on their machines blindly.
+
+  - It's technically extremely unlikely and from today's knowledge even
+    impossible that L1TF can be exploited via the most popular attack
+    mechanisms like JavaScript because these mechanisms have no way to
+    control PTEs. If this would be possible and not other mitigation would
+    be possible, then the default might be different.
+
+  - The administrators of cloud and hosting setups have to carefully
+    analyze the risk for their scenarios and make the appropriate
+    mitigation choices, which might even vary across their deployed
+    machines and also result in other changes of their overall setup.
+    There is no way for the kernel to provide a sensible default for this
+    kind of scenarios.
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt
index 07f147381f32..ea2dafe49ae8 100644
--- a/Documentation/block/null_blk.txt
+++ b/Documentation/block/null_blk.txt
@@ -85,3 +85,10 @@ shared_tags=[0/1]: Default: 0
   0: Tag set is not shared.
   1: Tag set shared between devices for blk-mq. Only makes sense with
      nr_devices > 1, otherwise there's no tag set to share.
+
+zoned=[0/1]: Default: 0
+  0: Block device is exposed as a random-access block device.
+  1: Block device is exposed as a host-managed zoned block device.
+
+zone_size=[MB]: Default: 256
+  Per zone size when exposed as a zoned block device. Must be a power of two.
diff --git a/Documentation/block/stat.txt b/Documentation/block/stat.txt
index 0dbc946de2ea..0aace9cc536c 100644
--- a/Documentation/block/stat.txt
+++ b/Documentation/block/stat.txt
@@ -31,28 +31,32 @@ write ticks     milliseconds  total wait time for write requests
 in_flight       requests      number of I/Os currently in flight
 io_ticks        milliseconds  total time this block device has been active
 time_in_queue   milliseconds  total wait time for all requests
+discard I/Os    requests      number of discard I/Os processed
+discard merges  requests      number of discard I/Os merged with in-queue I/O
+discard sectors sectors       number of sectors discarded
+discard ticks   milliseconds  total wait time for discard requests
 
-read I/Os, write I/Os
-=====================
+read I/Os, write I/Os, discard I/0s
+===================================
 
 These values increment when an I/O request completes.
 
-read merges, write merges
-=========================
+read merges, write merges, discard merges
+=========================================
 
 These values increment when an I/O request is merged with an
 already-queued I/O request.
 
-read sectors, write sectors
-===========================
+read sectors, write sectors, discard_sectors
+============================================
 
-These values count the number of sectors read from or written to this
-block device.  The "sectors" in question are the standard UNIX 512-byte
-sectors, not any device- or filesystem-specific block size.  The
-counters are incremented when the I/O completes.
+These values count the number of sectors read from, written to, or
+discarded from this block device.  The "sectors" in question are the
+standard UNIX 512-byte sectors, not any device- or filesystem-specific
+block size.  The counters are incremented when the I/O completes.
 
-read ticks, write ticks
-=======================
+read ticks, write ticks, discard ticks
+======================================
 
 These values count the number of milliseconds that I/O requests have
 waited on this block device.  If there are multiple I/O requests waiting,
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 62ac5a9f3a9f..b691af4831fa 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -34,7 +34,7 @@ needs_sphinx = '1.3'
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain', 'kfigure']
+extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain', 'kfigure', 'sphinx.ext.ifconfig']
 
 # The name of the math extension changed on Sphinx 1.4
 if major == 1 and minor > 3:
diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst
index 2e7165f86f55..724583453e1f 100644
--- a/Documentation/core-api/atomic_ops.rst
+++ b/Documentation/core-api/atomic_ops.rst
@@ -29,7 +29,7 @@ updated by one CPU, local_t is probably more appropriate. Please see
 local_t.
 
 The first operations to implement for atomic_t's are the initializers and
-plain reads. ::
+plain writes. ::
 
 	#define ATOMIC_INIT(i)		{ (i) }
 	#define atomic_set(v, i)	((v)->counter = (i))
diff --git a/Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt b/Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt
new file mode 100644
index 000000000000..28f43e929f6d
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt
@@ -0,0 +1,84 @@
+Nuvoton NPCM7xx PWM and Fan Tacho controller device
+
+The Nuvoton BMC NPCM7XX supports 8 Pulse-width modulation (PWM)
+controller outputs and 16 Fan tachometer controller inputs.
+
+Required properties for pwm-fan node
+- #address-cells : should be 1.
+- #size-cells	: should be 0.
+- compatible	: "nuvoton,npcm750-pwm-fan" for Poleg NPCM7XX.
+- reg			: specifies physical base address and size of the registers.
+- reg-names	: must contain:
+					* "pwm" for the PWM registers.
+					* "fan" for the Fan registers.
+- clocks		: phandle of reference clocks.
+- clock-names	: must contain
+					* "pwm" for PWM controller operating clock.
+					* "fan" for Fan controller operating clock.
+- interrupts	: contain the Fan interrupts with flags for falling edge.
+- pinctrl-names	: a pinctrl state named "default" must be defined.
+- pinctrl-0	: phandle referencing pin configuration of the PWM and Fan
+					controller ports.
+
+fan subnode format:
+===================
+Under fan subnode can be upto 8 child nodes, each child node representing a fan.
+Each fan subnode must have one PWM channel and atleast one Fan tach channel.
+
+For PWM channel can be configured cooling-levels to create cooling device.
+Cooling device could be bound to a thermal zone for the thermal control.
+
+Required properties for each child node:
+- reg : specify the PWM output channel.
+	integer value in the range 0 through 7, that represent
+	the PWM channel number that used.
+
+- fan-tach-ch : specify the Fan tach input channel.
+		integer value in the range 0 through 15, that represent
+		the fan tach channel number that used.
+
+		At least one Fan tach input channel is required
+
+Optional property for each child node:
+- cooling-levels: PWM duty cycle values in a range from 0 to 255
+                  which correspond to thermal cooling states.
+
+Examples:
+
+pwm_fan:pwm-fan-controller@103000 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "nuvoton,npcm750-pwm-fan";
+	reg = <0x103000 0x2000>,
+		<0x180000 0x8000>;
+	reg-names = "pwm", "fan";
+	clocks = <&clk NPCM7XX_CLK_APB3>,
+		<&clk NPCM7XX_CLK_APB4>;
+	clock-names = "pwm","fan";
+	interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pwm0_pins &pwm1_pins &pwm2_pins
+			&fanin0_pins &fanin1_pins &fanin2_pins
+			&fanin3_pins &fanin4_pins>;
+	fan@0 {
+		reg = <0x00>;
+		fan-tach-ch = /bits/ 8 <0x00 0x01>;
+		cooling-levels = <127 255>;
+	};
+	fan@1 {
+		reg = <0x01>;
+		fan-tach-ch = /bits/ 8 <0x02 0x03>;
+	};
+	fan@2 {
+		reg = <0x02>;
+		fan-tach-ch = /bits/ 8 <0x04>;
+	};
+
+};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
index 5f89fb635a1b..f97fd8ab5e45 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
@@ -4,6 +4,7 @@ Required properties:
 
 - compatible : should be "ingenic,<socname>-intc". Valid strings are:
     ingenic,jz4740-intc
+    ingenic,jz4725b-intc
     ingenic,jz4770-intc
     ingenic,jz4775-intc
     ingenic,jz4780-intc
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
index 20f121daa910..697ca2f26d1b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
@@ -7,6 +7,7 @@ Required properties:
     - "renesas,irqc-r8a73a4" (R-Mobile APE6)
     - "renesas,irqc-r8a7743" (RZ/G1M)
     - "renesas,irqc-r8a7745" (RZ/G1E)
+    - "renesas,irqc-r8a77470" (RZ/G1C)
     - "renesas,irqc-r8a7790" (R-Car H2)
     - "renesas,irqc-r8a7791" (R-Car M2-W)
     - "renesas,irqc-r8a7792" (R-Car V2H)
@@ -16,6 +17,7 @@ Required properties:
     - "renesas,intc-ex-r8a7796" (R-Car M3-W)
     - "renesas,intc-ex-r8a77965" (R-Car M3-N)
     - "renesas,intc-ex-r8a77970" (R-Car V3M)
+    - "renesas,intc-ex-r8a77980" (R-Car V3H)
     - "renesas,intc-ex-r8a77995" (R-Car D3)
 - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
   interrupts.txt in this directory
diff --git a/Documentation/devicetree/bindings/mtd/denali-nand.txt b/Documentation/devicetree/bindings/mtd/denali-nand.txt
index 0ee8edb60efc..f33da8782741 100644
--- a/Documentation/devicetree/bindings/mtd/denali-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/denali-nand.txt
@@ -8,6 +8,9 @@ Required properties:
   - reg : should contain registers location and length for data and reg.
   - reg-names: Should contain the reg names "nand_data" and "denali_reg"
   - interrupts : The interrupt number.
+  - clocks: should contain phandle of the controller core clock, the bus
+    interface clock, and the ECC circuit clock.
+  - clock-names: should contain "nand", "nand_x", "ecc"
 
 Optional properties:
   - nand-ecc-step-size: see nand.txt for details.  If present, the value must be
@@ -31,5 +34,7 @@ nand: nand@ff900000 {
 	compatible = "altr,socfpga-denali-nand";
 	reg = <0xff900000 0x20>, <0xffb80000 0x1000>;
 	reg-names = "nand_data", "denali_reg";
+	clocks = <&nand_clk>, <&nand_x_clk>, <&nand_ecc_clk>;
+	clock-names = "nand", "nand_x", "ecc";
 	interrupts = <0 144 4>;
 };
diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
index 956bb046e599..f03be904d3c2 100644
--- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
+++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
@@ -69,6 +69,15 @@ Optional properties:
                    all chips and support for it can not be detected at runtime.
                    Refer to your chips' datasheet to check if this is supported
                    by your chip.
+- broken-flash-reset : Some flash devices utilize stateful addressing modes
+		   (e.g., for 32-bit addressing) which need to be managed
+		   carefully by a system. Because these sorts of flash don't
+		   have a standardized software reset command, and because some
+		   systems don't toggle the flash RESET# pin upon system reset
+		   (if the pin even exists at all), there are systems which
+		   cannot reboot properly if the flash is left in the "wrong"
+		   state. This boolean flag can be used on such systems, to
+		   denote the absence of a reliable reset mechanism.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt
index 8bb11d809429..e949c778e983 100644
--- a/Documentation/devicetree/bindings/mtd/nand.txt
+++ b/Documentation/devicetree/bindings/mtd/nand.txt
@@ -25,7 +25,7 @@ Optional NAND chip properties:
 		  Deprecated values:
 		  "soft_bch": use "soft" and nand-ecc-algo instead
 - nand-ecc-algo: string, algorithm of NAND ECC.
-		 Supported values are: "hamming", "bch".
+		 Valid values are: "hamming", "bch", "rs".
 - nand-bus-width : 8 or 16 bus width if not present 8
 - nand-on-flash-bbt: boolean to enable on flash bbt option if not present false
 
@@ -43,6 +43,10 @@ Optional NAND chip properties:
 		     This is particularly useful when only the in-band area is
 		     used by the upper layers, and you want to make your NAND
 		     as reliable as possible.
+- nand-is-boot-medium: Whether the NAND chip is a boot medium. Drivers might use
+		       this information to select ECC algorithms supported by
+		       the boot ROM or similar restrictions.
+
 - nand-rb: shall contain the native Ready/Busy ids.
 
 The ECC strength and ECC step size properties define the correction capability
diff --git a/Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt b/Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt
new file mode 100644
index 000000000000..b2f2ca12f9e6
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt
@@ -0,0 +1,64 @@
+NVIDIA Tegra NAND Flash controller
+
+Required properties:
+- compatible: Must be one of:
+  - "nvidia,tegra20-nand"
+- reg: MMIO address range
+- interrupts: interrupt output of the NFC controller
+- clocks: Must contain an entry for each entry in clock-names.
+  See ../clocks/clock-bindings.txt for details.
+- clock-names: Must include the following entries:
+  - nand
+- resets: Must contain an entry for each entry in reset-names.
+  See ../reset/reset.txt for details.
+- reset-names: Must include the following entries:
+  - nand
+
+Optional children nodes:
+Individual NAND chips are children of the NAND controller node. Currently
+only one NAND chip supported.
+
+Required children node properties:
+- reg: An integer ranging from 1 to 6 representing the CS line to use.
+
+Optional children node properties:
+- nand-ecc-mode: String, operation mode of the NAND ecc mode. Currently only
+		 "hw" is supported.
+- nand-ecc-algo: string, algorithm of NAND ECC.
+		 Supported values with "hw" ECC mode are: "rs", "bch".
+- nand-bus-width : See nand.txt
+- nand-on-flash-bbt: See nand.txt
+- nand-ecc-strength: integer representing the number of bits to correct
+		     per ECC step (always 512). Supported strength using HW ECC
+		     modes are:
+		     - RS: 4, 6, 8
+		     - BCH: 4, 8, 14, 16
+- nand-ecc-maximize: See nand.txt
+- nand-is-boot-medium: Makes sure only ECC strengths supported by the boot ROM
+		       are chosen.
+- wp-gpios: GPIO specifier for the write protect pin.
+
+Optional child node of NAND chip nodes:
+Partitions: see partition.txt
+
+  Example:
+	nand-controller@70008000 {
+		compatible = "nvidia,tegra20-nand";
+		reg = <0x70008000 0x100>;
+		interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&tegra_car TEGRA20_CLK_NDFLASH>;
+		clock-names = "nand";
+		resets = <&tegra_car 13>;
+		reset-names = "nand";
+
+		nand@0 {
+			reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			nand-bus-width = <8>;
+			nand-on-flash-bbt;
+			nand-ecc-algo = "bch";
+			nand-ecc-strength = <8>;
+			wp-gpios = <&gpio TEGRA_GPIO(S, 0) GPIO_ACTIVE_LOW>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mtd/partition.txt b/Documentation/devicetree/bindings/mtd/partition.txt
index a8f382642ba9..afbbd870496d 100644
--- a/Documentation/devicetree/bindings/mtd/partition.txt
+++ b/Documentation/devicetree/bindings/mtd/partition.txt
@@ -14,6 +14,13 @@ method is used for a given flash device. To describe the method there should be
 a subnode of the flash device that is named 'partitions'. It must have a
 'compatible' property, which is used to identify the method to use.
 
+When a single partition is represented with a DT node (it depends on a used
+format) it may also be described using above rules ('compatible' and optionally
+some extra properties / subnodes). It allows describing more complex,
+hierarchical (multi-level) layouts and should be used if there is some
+significant relation between partitions or some partition internally uses
+another partitioning method.
+
 Available bindings are listed in the "partitions" subdirectory.
 
 
@@ -109,3 +116,42 @@ flash@2 {
 		};
 	};
 };
+
+flash@3 {
+	partitions {
+		compatible = "fixed-partitions";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partition@0 {
+			label = "bootloader";
+			reg = <0x000000 0x100000>;
+			read-only;
+		};
+
+		firmware@100000 {
+			label = "firmware";
+			reg = <0x100000 0xe00000>;
+			compatible = "brcm,trx";
+		};
+
+		calibration@f00000 {
+			label = "calibration";
+			reg = <0xf00000 0x100000>;
+			compatible = "fixed-partitions";
+			ranges = <0 0xf00000 0x100000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "wifi0";
+				reg = <0x000000 0x080000>;
+			};
+
+			partition@80000 {
+				label = "wifi1";
+				reg = <0x080000 0x080000>;
+			};
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt b/Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt
new file mode 100644
index 000000000000..b677147ca4e1
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt
@@ -0,0 +1,37 @@
+Broadcom TRX Container Partition
+================================
+
+TRX is Broadcom's official firmware format for the BCM947xx boards. It's used by
+most of the vendors building devices based on Broadcom's BCM47xx SoCs and is
+supported by the CFE bootloader.
+
+Design of the TRX format is very minimalistic. Its header contains
+identification fields, CRC32 checksum and the locations of embedded partitions.
+Its purpose is to store a few partitions in a format that can be distributed as
+a standalone file and written in a flash memory.
+
+Container can hold up to 4 partitions. The first partition has to contain a
+device executable binary (e.g. a kernel) as it's what the CFE bootloader starts
+executing. Other partitions can be used for operating system purposes. This is
+useful for systems that keep kernel and rootfs separated.
+
+TRX doesn't enforce any strict partition boundaries or size limits. All
+partitions have to be less than the 4GiB max size limit.
+
+There are two existing/known TRX variants:
+1) v1 which contains 3 partitions
+2) v2 which contains 4 partitions
+
+There aren't separated compatible bindings for them as version can be trivialy
+detected by a software parsing TRX header.
+
+Required properties:
+- compatible : (required) must be "brcm,trx"
+
+Example:
+
+flash@0 {
+	partitions {
+		compatible = "brcm,trx";
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/qcom_nandc.txt b/Documentation/devicetree/bindings/mtd/qcom_nandc.txt
index 73d336befa08..1123cc6d56ef 100644
--- a/Documentation/devicetree/bindings/mtd/qcom_nandc.txt
+++ b/Documentation/devicetree/bindings/mtd/qcom_nandc.txt
@@ -45,11 +45,12 @@ Required properties:
 			number (e.g., 0, 1, 2, etc.)
 - #address-cells:	see partition.txt
 - #size-cells:		see partition.txt
-- nand-ecc-strength:	see nand.txt
-- nand-ecc-step-size:	must be 512. see nand.txt for more details.
 
 Optional properties:
 - nand-bus-width:	see nand.txt
+- nand-ecc-strength:	see nand.txt. If not specified, then ECC strength will
+			be used according to chip requirement and available
+			OOB size.
 
 Each nandcs device node may optionally contain a 'partitions' sub-node, which
 further contains sub-nodes describing the flash partition mapping. See
@@ -77,7 +78,6 @@ nand-controller@1ac00000 {
 		reg = <0>;
 
 		nand-ecc-strength = <4>;
-		nand-ecc-step-size = <512>;
 		nand-bus-width = <8>;
 
 		partitions {
@@ -117,7 +117,6 @@ nand-controller@79b0000 {
 	nand@0 {
 		reg = <0>;
 		nand-ecc-strength = <4>;
-		nand-ecc-step-size = <512>;
 		nand-bus-width = <8>;
 
 		partitions {
diff --git a/Documentation/devicetree/bindings/mtd/spi-nand.txt b/Documentation/devicetree/bindings/mtd/spi-nand.txt
new file mode 100644
index 000000000000..8b51f3b6d55c
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/spi-nand.txt
@@ -0,0 +1,5 @@
+SPI NAND flash
+
+Required properties:
+- compatible: should be "spi-nand"
+- reg: should encode the chip-select line used to access the NAND chip
diff --git a/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt b/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
index cafe2197dad9..c3a29c5feea3 100644
--- a/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
+++ b/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
@@ -3,7 +3,7 @@
 Required properties:
 - compatible: "qca,ar7100-usb-phy"
 - #phys-cells: should be 0
-- reset-names: "usb-phy"[, "usb-suspend-override"]
+- reset-names: "phy"[, "suspend-override"]
 - resets: references to the reset controllers
 
 Example:
@@ -11,7 +11,7 @@ Example:
 	usb-phy {
 		compatible = "qca,ar7100-usb-phy";
 
-		reset-names = "usb-phy", "usb-suspend-override";
+		reset-names = "phy", "suspend-override";
 		resets = <&rst 4>, <&rst 3>;
 
 		#phy-cells = <0>;
diff --git a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
index b1fe7e9de1b4..18d4d0166c76 100644
--- a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
+++ b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
@@ -1,19 +1,25 @@
-Mediatek MT6577, MT6572 and MT6589 Timers
----------------------------------------
+Mediatek Timers
+---------------
+
+Mediatek SoCs have two different timers on different platforms,
+- GPT (General Purpose Timer)
+- SYST (System Timer)
+
+The proper timer will be selected automatically by driver.
 
 Required properties:
 - compatible should contain:
-	* "mediatek,mt2701-timer" for MT2701 compatible timers
-	* "mediatek,mt6580-timer" for MT6580 compatible timers
-	* "mediatek,mt6589-timer" for MT6589 compatible timers
-	* "mediatek,mt7623-timer" for MT7623 compatible timers
-	* "mediatek,mt8127-timer" for MT8127 compatible timers
-	* "mediatek,mt8135-timer" for MT8135 compatible timers
-	* "mediatek,mt8173-timer" for MT8173 compatible timers
-	* "mediatek,mt6577-timer" for MT6577 and all above compatible timers
-- reg: Should contain location and length for timers register.
-- clocks: Clocks driving the timer hardware. This list should include two
-	clocks. The order is system clock and as second clock the RTC clock.
+	* "mediatek,mt2701-timer" for MT2701 compatible timers (GPT)
+	* "mediatek,mt6580-timer" for MT6580 compatible timers (GPT)
+	* "mediatek,mt6589-timer" for MT6589 compatible timers (GPT)
+	* "mediatek,mt7623-timer" for MT7623 compatible timers (GPT)
+	* "mediatek,mt8127-timer" for MT8127 compatible timers (GPT)
+	* "mediatek,mt8135-timer" for MT8135 compatible timers (GPT)
+	* "mediatek,mt8173-timer" for MT8173 compatible timers (GPT)
+	* "mediatek,mt6577-timer" for MT6577 and all above compatible timers (GPT)
+	* "mediatek,mt6765-timer" for MT6765 compatible timers (SYST)
+- reg: Should contain location and length for timer register.
+- clocks: Should contain system clock.
 
 Examples:
 
@@ -21,5 +27,5 @@ Examples:
 		compatible = "mediatek,mt6577-timer";
 		reg = <0x10008000 0x80>;
 		interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_LOW>;
-		clocks = <&system_clk>, <&rtc_clk>;
+		clocks = <&system_clk>;
 	};
diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
index dbdf62907703..c7858dd1ea8f 100644
--- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt
+++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
@@ -5,10 +5,10 @@
 #
 # Architecture requirements
 #
-# * arm64
+# * arm/arm64
 #
-# Rely on eret context synchronization when returning from IPI handler, and
-# when returning to user-space.
+# Rely on implicit context synchronization as a result of exception return
+# when returning from IPI handler, and when returning to user-space.
 #
 # * x86
 #
@@ -31,7 +31,7 @@
     -----------------------
     |       alpha: | TODO |
     |         arc: | TODO |
-    |         arm: | TODO |
+    |         arm: |  ok  |
     |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 37bf0a9de75c..7cca82ed2ed1 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -64,7 +64,7 @@ prototypes:
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *,
 				struct file *, unsigned open_flag,
-				umode_t create_mode, int *opened);
+				umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 
 locking rules:
diff --git a/Documentation/filesystems/cifs/CHANGES b/Documentation/filesystems/cifs/CHANGES
index 455e1cc494a9..1df7f4910eb2 100644
--- a/Documentation/filesystems/cifs/CHANGES
+++ b/Documentation/filesystems/cifs/CHANGES
@@ -1,1068 +1,4 @@
-See https://wiki.samba.org/index.php/LinuxCIFSKernel for
-more current information.
-
-Version 1.62
-------------
-Add sockopt=TCP_NODELAY mount option. EA (xattr) routines hardened
-to more strictly handle corrupt frames.
-
-Version 1.61
-------------
-Fix append problem to Samba servers (files opened with O_APPEND could
-have duplicated data). Fix oops in cifs_lookup. Workaround problem
-mounting to OS/400 Netserve. Fix oops in cifs_get_tcp_session.
-Disable use of server inode numbers when server only
-partially supports them (e.g. for one server querying inode numbers on
-FindFirst fails but QPathInfo queries works). Fix oops with dfs in 
-cifs_put_smb_ses. Fix mmap to work on directio mounts (needed
-for OpenOffice when on forcedirectio mount e.g.)
-
-Version 1.60
--------------
-Fix memory leak in reconnect.  Fix oops in DFS mount error path.
-Set s_maxbytes to smaller (the max that vfs can handle) so that
-sendfile will now work over cifs mounts again.  Add noforcegid
-and noforceuid mount parameters. Fix small mem leak when using
-ntlmv2. Fix 2nd mount to same server but with different port to
-be allowed (rather than reusing the 1st port) - only when the
-user explicitly overrides the port on the 2nd mount.
-
-Version 1.59
-------------
-Client uses server inode numbers (which are persistent) rather than
-client generated ones by default (mount option "serverino" turned
-on by default if server supports it).  Add forceuid and forcegid
-mount options (so that when negotiating unix extensions specifying
-which uid mounted does not immediately force the server's reported
-uids to be overridden).  Add support for scope mount parm. Improve
-hard link detection to use same inode for both.  Do not set
-read-only dos attribute on directories (for chmod) since Windows
-explorer special cases this attribute bit for directories for
-a different purpose.
-
-Version 1.58
-------------
-Guard against buffer overruns in various UCS-2 to UTF-8 string conversions
-when the UTF-8 string is composed of unusually long (more than 4 byte) converted
-characters. Add support for mounting root of a share which redirects immediately
-to DFS target. Convert string conversion functions from Unicode to more
-accurately mark string length before allocating memory (which may help the
-rare cases where a UTF-8 string is much larger than the UCS2 string that
-we converted from).  Fix endianness of the vcnum field used during
-session setup to distinguish multiple mounts to same server from different
-userids. Raw NTLMSSP fixed (it requires /proc/fs/cifs/experimental
-flag to be set to 2, and mount must enable krb5 to turn on extended security).
-Performance of file create to Samba improved (posix create on lookup
-removes 1 of 2 network requests sent on file create)
- 
-Version 1.57
-------------
-Improve support for multiple security contexts to the same server. We
-used to use the same "vcnumber" for all connections which could cause
-the server to treat subsequent connections, especially those that
-are authenticated as guest, as reconnections, invalidating the earlier
-user's smb session.  This fix allows cifs to mount multiple times to the
-same server with different userids without risking invalidating earlier
-established security contexts.  fsync now sends SMB Flush operation
-to better ensure that we wait for server to write all of the data to
-server disk (not just write it over the network).  Add new mount
-parameter to allow user to disable sending the (slow) SMB flush on
-fsync if desired (fsync still flushes all cached write data to the server).
-Posix file open support added (turned off after one attempt if server
-fails to support it properly, as with Samba server versions prior to 3.3.2)
-Fix "redzone overwritten" bug in cifs_put_tcon (CIFSTcon may allocate too
-little memory for the "nativeFileSystem" field returned by the server
-during mount).  Endian convert inode numbers if necessary (makes it easier
-to compare inode numbers on network files from big endian systems). 
-
-Version 1.56
-------------
-Add "forcemandatorylock" mount option to allow user to use mandatory
-rather than posix (advisory) byte range locks, even though server would
-support posix byte range locks.  Fix query of root inode when prefixpath
-specified and user does not have access to query information about the
-top of the share.  Fix problem in 2.6.28 resolving DFS paths to
-Samba servers (worked to Windows).  Fix rmdir so that pending search
-(readdir) requests do not get invalid results which include the now
-removed directory.  Fix oops in cifs_dfs_ref.c when prefixpath is not reachable
-when using DFS.  Add better file create support to servers which support
-the CIFS POSIX protocol extensions (this adds support for new flags
-on create, and improves semantics for write of locked ranges).
-
-Version 1.55
-------------
-Various fixes to make delete of open files behavior more predictable
-(when delete of an open file fails we mark the file as "delete-on-close"
-in a way that more servers accept, but only if we can first rename the
-file to a temporary name).  Add experimental support for more safely
-handling fcntl(F_SETLEASE).  Convert cifs to using blocking tcp
-sends, and also let tcp autotune the socket send and receive buffers.
-This reduces the number of EAGAIN errors returned by TCP/IP in
-high stress workloads (and the number of retries on socket writes
-when sending large SMBWriteX requests).  Fix case in which a portion of
-data can in some cases not get written to the file on the server before the
-file is closed.  Fix DFS parsing to properly handle path consumed field,
-and to handle certain codepage conversions better.  Fix mount and
-umount race that can cause oops in mount or umount or reconnect.
-
-Version 1.54
-------------
-Fix premature write failure on congested networks (we would give up
-on EAGAIN from the socket too quickly on large writes).
-Cifs_mkdir and cifs_create now respect the setgid bit on parent dir.
-Fix endian problems in acl (mode from/to cifs acl) on bigendian
-architectures.  Fix problems with preserving timestamps on copying open
-files (e.g. "cp -a") to Windows servers.  For mkdir and create honor setgid bit
-on parent directory when server supports Unix Extensions but not POSIX
-create. Update cifs.upcall version to handle new Kerberos sec flags
-(this requires update of cifs.upcall program from Samba).  Fix memory leak
-on dns_upcall (resolving DFS referralls).  Fix plain text password
-authentication (requires setting SecurityFlags to 0x30030 to enable
-lanman and plain text though).  Fix writes to be at correct offset when
-file is open with O_APPEND and file is on a directio (forcediretio) mount.
-Fix bug in rewinding readdir directory searches.  Add nodfs mount option.
-
-Version 1.53
-------------
-DFS support added (Microsoft Distributed File System client support needed
-for referrals which enable a hierarchical name space among servers).
-Disable temporary caching of mode bits to servers which do not support
-storing of mode (e.g. Windows servers, when client mounts without cifsacl
-mount option) and add new "dynperm" mount option to enable temporary caching
-of mode (enable old behavior).  Fix hang on mount caused when server crashes
-tcp session during negotiate protocol.
-
-Version 1.52
-------------
-Fix oops on second mount to server when null auth is used.
-Enable experimental Kerberos support.  Return writebehind errors on flush
-and sync so that events like out of disk space get reported properly on
-cached files. Fix setxattr failure to certain Samba versions. Fix mount
-of second share to disconnected server session (autoreconnect on this).
-Add ability to modify cifs acls for handling chmod (when mounted with
-cifsacl flag). Fix prefixpath path separator so we can handle mounts
-with prefixpaths longer than one directory (one path component) when
-mounted to Windows servers.  Fix slow file open when cifsacl
-enabled. Fix memory leak in FindNext when the SMB call returns -EBADF.
-
-
-Version 1.51
-------------
-Fix memory leak in statfs when mounted to very old servers (e.g.
-Windows 9x).  Add new feature "POSIX open" which allows servers
-which support the current POSIX Extensions to provide better semantics
-(e.g. delete for open files opened with posix open).  Take into
-account umask on posix mkdir not just older style mkdir.  Add
-ability to mount to IPC$ share (which allows CIFS named pipes to be
-opened, read and written as if they were files).  When 1st tree
-connect fails (e.g. due to signing negotiation failure) fix
-leak that causes cifsd not to stop and rmmod to fail to cleanup
-cifs_request_buffers pool. Fix problem with POSIX Open/Mkdir on
-bigendian architectures. Fix possible memory corruption when
-EAGAIN returned on kern_recvmsg. Return better error if server
-requires packet signing but client has disabled it. When mounted
-with cifsacl mount option - mode bits are approximated based
-on the contents of the ACL of the file or directory. When cifs
-mount helper is missing convert make sure that UNC name 
-has backslash (not forward slash) between ip address of server
-and the share name.
-
-Version 1.50
-------------
-Fix NTLMv2 signing. NFS server mounted over cifs works (if cifs mount is
-done with "serverino" mount option).  Add support for POSIX Unlink
-(helps with certain sharing violation cases when server such as
-Samba supports newer POSIX CIFS Protocol Extensions). Add "nounix"
-mount option to allow disabling the CIFS Unix Extensions for just
-that mount. Fix hang on spinlock in find_writable_file (race when
-reopening file after session crash).  Byte range unlock request to
-windows server could unlock more bytes (on server copy of file)
-than intended if start of unlock request is well before start of
-a previous byte range lock that we issued.
-
-Version 1.49
-------------
-IPv6 support.  Enable ipv6 addresses to be passed on mount (put the ipv6
-address after the "ip=" mount option, at least until mount.cifs is fixed to
-handle DNS host to ipv6 name translation).  Accept override of uid or gid
-on mount even when Unix Extensions are negotiated (it used to be ignored
-when Unix Extensions were ignored).  This allows users to override the
-default uid and gid for files when they are certain that the uids or
-gids on the server do not match those of the client.  Make "sec=none"
-mount override username (so that null user connection is attempted)
-to match what documentation said. Support for very large reads, over 127K,
-available to some newer servers (such as Samba 3.0.26 and later but
-note that it also requires setting CIFSMaxBufSize at module install
-time to a larger value which may hurt performance in some cases).
-Make sign option force signing (or fail if server does not support it).
-
-Version 1.48
-------------
-Fix mtime bouncing around from local idea of last write times to remote time.
-Fix hang (in i_size_read) when simultaneous size update of same remote file
-on smp system corrupts sequence number. Do not reread unnecessarily partial page
-(which we are about to overwrite anyway) when writing out file opened rw.
-When DOS attribute of file on non-Unix server's file changes on the server side
-from read-only back to read-write, reflect this change in default file mode
-(we had been leaving a file's mode read-only until the inode were reloaded).
-Allow setting of attribute back to ATTR_NORMAL (removing readonly dos attribute
-when archive dos attribute not set and we are changing mode back to writeable
-on server which does not support the Unix Extensions).  Remove read only dos
-attribute on chmod when adding any write permission (ie on any of
-user/group/other (not all of user/group/other ie  0222) when
-mounted to windows.  Add support for POSIX MkDir (slight performance
-enhancement and eliminates the network race between the mkdir and set 
-path info of the mode).
-
-
-Version 1.47
-------------
-Fix oops in list_del during mount caused by unaligned string.
-Fix file corruption which could occur on some large file
-copies caused by writepages page i/o completion bug.
-Seek to SEEK_END forces check for update of file size for non-cached
-files. Allow file size to be updated on remote extend of locally open,
-non-cached file.  Fix reconnect to newer Samba servers (or other servers
-which support the CIFS Unix/POSIX extensions) so that we again tell the
-server the Unix/POSIX cifs capabilities which we support (SetFSInfo).
-Add experimental support for new POSIX Open/Mkdir (which returns
-stat information on the open, and allows setting the mode).
-
-Version 1.46
-------------
-Support deep tree mounts.  Better support OS/2, Win9x (DOS) time stamps.
-Allow null user to be specified on mount ("username="). Do not return
-EINVAL on readdir when filldir fails due to overwritten blocksize
-(fixes FC problem).  Return error in rename 2nd attempt retry (ie report
-if rename by handle also fails, after rename by path fails, we were
-not reporting whether the retry worked or not). Fix NTLMv2 to
-work to Windows servers (mount with option "sec=ntlmv2").
-
-Version 1.45
-------------
-Do not time out lockw calls when using posix extensions. Do not
-time out requests if server still responding reasonably fast
-on requests on other threads.  Improve POSIX locking emulation,
-(lock cancel now works, and unlock of merged range works even
-to Windows servers now).  Fix oops on mount to lanman servers
-(win9x, os/2 etc.) when null password.  Do not send listxattr
-(SMB to query all EAs) if nouser_xattr specified.  Fix SE Linux
-problem (instantiate inodes/dentries in right order for readdir).
-
-Version 1.44
-------------
-Rewritten sessionsetup support, including support for legacy SMB
-session setup needed for OS/2 and older servers such as Windows 95 and 98.
-Fix oops on ls to OS/2 servers.  Add support for level 1 FindFirst
-so we can do search (ls etc.) to OS/2.  Do not send NTCreateX
-or recent levels of FindFirst unless server says it supports NT SMBs
-(instead use legacy equivalents from LANMAN dialect). Fix to allow
-NTLMv2 authentication support (now can use stronger password hashing
-on mount if corresponding /proc/fs/cifs/SecurityFlags is set (0x4004).
-Allow override of global cifs security flags on mount via "sec=" option(s).
-
-Version 1.43
-------------
-POSIX locking to servers which support CIFS POSIX Extensions
-(disabled by default controlled by proc/fs/cifs/Experimental).
-Handle conversion of long share names (especially Asian languages)
-to Unicode during mount. Fix memory leak in sess struct on reconnect.
-Fix rare oops after acpi suspend.  Fix O_TRUNC opens to overwrite on
-cifs open which helps rare case when setpathinfo fails or server does
-not support it. 
-
-Version 1.42
-------------
-Fix slow oplock break when mounted to different servers at the same time and
-the tids match and we try to find matching fid on wrong server. Fix read
-looping when signing required by server (2.6.16 kernel only). Fix readdir
-vs. rename race which could cause each to hang. Return . and .. even
-if server does not.  Allow searches to skip first three entries and
-begin at any location. Fix oops in find_writeable_file.
-
-Version 1.41
-------------
-Fix NTLMv2 security (can be enabled in /proc/fs/cifs) so customers can
-configure stronger authentication.  Fix sfu symlinks so they can
-be followed (not just recognized).  Fix wraparound of bcc on
-read responses when buffer size over 64K and also fix wrap of
-max smb buffer size when CIFSMaxBufSize over 64K.  Fix oops in
-cifs_user_read and cifs_readpages (when EAGAIN on send of smb
-on socket is returned over and over).  Add POSIX (advisory) byte range
-locking support (requires server with newest CIFS UNIX Extensions
-to the protocol implemented). Slow down negprot slightly in port 139
-RFC1001 case to give session_init time on buggy servers.
-
-Version 1.40
-------------
-Use fsuid (fsgid) more consistently instead of uid (gid). Improve performance
-of readpages by eliminating one extra memcpy. Allow update of file size
-from remote server even if file is open for write as long as mount is
-directio.  Recognize share mode security and send NTLM encrypted password
-on tree connect if share mode negotiated.
-
-Version 1.39
-------------
-Defer close of a file handle slightly if pending writes depend on that handle
-(this reduces the EBADF bad file handle errors that can be logged under heavy
-stress on writes). Modify cifs Kconfig options to expose CONFIG_CIFS_STATS2 
-Fix SFU style symlinks and mknod needed for servers which do not support the
-CIFS Unix Extensions.  Fix setfacl/getfacl on bigendian. Timeout negative
-dentries so files that the client sees as deleted but that later get created
-on the server will be recognized.  Add client side permission check on setattr.
-Timeout stuck requests better (where server has never responded or sent corrupt
-responses)
-
-Version 1.38
-------------
-Fix tcp socket retransmission timeouts (e.g. on ENOSPACE from the socket)
-to be smaller at first (but increasing) so large write performance performance
-over GigE is better.  Do not hang thread on illegal byte range lock response
-from Windows (Windows can send an RFC1001 size which does not match smb size) by
-allowing an SMBs TCP length to be up to a few bytes longer than it should be.
-wsize and rsize can now be larger than negotiated buffer size if server
-supports large readx/writex, even when directio mount flag not specified.
-Write size will in many cases now be 16K instead of 4K which greatly helps
-file copy performance on lightly loaded networks.  Fix oops in dnotify
-when experimental config flag enabled. Make cifsFYI more granular.
-
-Version 1.37
-------------
-Fix readdir caching when unlink removes file in current search buffer,
-and this is followed by a rewind search to just before the deleted entry.
-Do not attempt to set ctime unless atime and/or mtime change requested
-(most servers throw it away anyway). Fix length check of received smbs
-to be more accurate. Fix big endian problem with mapchars mount option,
-and with a field returned by statfs.
-
-Version 1.36
-------------
-Add support for mounting to older pre-CIFS servers such as Windows9x and ME.
-For these older servers, add option for passing netbios name of server in
-on mount (servernetbiosname).  Add suspend support for power management, to
-avoid cifsd thread preventing software suspend from working.
-Add mount option for disabling the default behavior of sending byte range lock
-requests to the server (necessary for certain applications which break with
-mandatory lock behavior such as Evolution), and also mount option for
-requesting case insensitive matching for path based requests (requesting
-case sensitive is the default).
-
-Version 1.35
-------------
-Add writepage performance improvements.  Fix path name conversions
-for long filenames on mounts which were done with "mapchars" mount option
-specified.  Ensure multiplex ids do not collide.  Fix case in which 
-rmmod can oops if done soon after last unmount.  Fix truncated
-search (readdir) output when resume filename was a long filename.
-Fix filename conversion when mapchars mount option was specified and
-filename was a long filename.
-
-Version 1.34
-------------
-Fix error mapping of the TOO_MANY_LINKS (hardlinks) case.
-Do not oops if root user kills cifs oplock kernel thread or
-kills the cifsd thread (NB: killing the cifs kernel threads is not
-recommended, unmount and rmmod cifs will kill them when they are
-no longer needed).  Fix readdir to ASCII servers (ie older servers
-which do not support Unicode) and also require asterisk.
-Fix out of memory case in which data could be written one page
-off in the page cache.
-
-Version 1.33
-------------
-Fix caching problem, in which readdir of directory containing a file
-which was cached could cause the file's time stamp to be updated
-without invalidating the readahead data (so we could get stale
-file data on the client for that file even as the server copy changed).
-Cleanup response processing so cifsd can not loop when abnormally
-terminated.
-
-
-Version 1.32
-------------
-Fix oops in ls when Transact2 FindFirst (or FindNext) returns more than one
-transact response for an SMB request and search entry split across two frames.
-Add support for lsattr (getting ext2/ext3/reiserfs attr flags from the server)
-as new protocol extensions. Do not send Get/Set calls for POSIX ACLs
-unless server explicitly claims to support them in CIFS Unix extensions
-POSIX ACL capability bit. Fix packet signing when multiuser mounting with
-different users from the same client to the same server. Fix oops in
-cifs_close. Add mount option for remapping reserved characters in
-filenames (also allow recognizing files with created by SFU which have any
-of these seven reserved characters, except backslash, to be recognized).
-Fix invalid transact2 message (we were sometimes trying to interpret
-oplock breaks as SMB responses). Add ioctl for checking that the
-current uid matches the uid of the mounter (needed by umount.cifs).
-Reduce the number of large buffer allocations in cifs response processing
-(significantly reduces memory pressure under heavy stress with multiple
-processes accessing the same server at the same time).
-
-Version 1.31
-------------
-Fix updates of DOS attributes and time fields so that files on NT4 servers
-do not get marked delete on close. Display sizes of cifs buffer pools in
-cifs stats. Fix oops in unmount when cifsd thread being killed by 
-shutdown. Add generic readv/writev and aio support. Report inode numbers 
-consistently in readdir and lookup (when serverino mount option is
-specified use the inode number that the server reports - for both lookup
-and readdir, otherwise by default the locally generated inode number is used
-for inodes created in either path since servers are not always able to 
-provide unique inode numbers when exporting multiple volumes from under one
-sharename).
-
-Version 1.30
-------------
-Allow new nouser_xattr mount parm to disable xattr support for user namespace.
-Do not flag user_xattr mount parm in dmesg.  Retry failures setting file time  
-(mostly affects NT4 servers) by retry with handle based network operation. 
-Add new POSIX Query FS Info for returning statfs info more accurately.
-Handle passwords with multiple commas in them.
-
-Version 1.29
-------------
-Fix default mode in sysfs of cifs module parms.  Remove old readdir routine.
-Fix capabilities flags for large readx so as to allow reads larger than 64K.
-
-Version 1.28
-------------
-Add module init parm for large SMB buffer size (to allow it to be changed
-from its default of 16K) which is especially useful for large file copy
-when mounting with the directio mount option. Fix oops after 
-returning from mount when experimental ExtendedSecurity enabled and
-SpnegoNegotiated returning invalid error. Fix case to retry better when 
-peek returns from 1 to 3 bytes on socket which should have more data.
-Fixed path based calls (such as cifs lookup) to handle path names
-longer than 530 (now can handle PATH_MAX). Fix pass through authentication
-from Samba server to DC (Samba required dummy LM password).
-
-Version 1.27
-------------
-Turn off DNOTIFY (directory change notification support) by default
-(unless built with the experimental flag) to fix hang with KDE
-file browser. Fix DNOTIFY flag mappings.  Fix hang (in wait_event
-waiting on an SMB response) in SendReceive when session dies but
-reconnects quickly from another task.  Add module init  parms for
-minimum number of large and small network buffers in the buffer pools,
-and for the maximum number of simultaneous requests.
-
-Version 1.26
-------------
-Add setfacl support to allow setting of ACLs remotely to Samba 3.10 and later
-and other POSIX CIFS compliant servers.  Fix error mapping for getfacl 
-to EOPNOTSUPP when server does not support posix acls on the wire. Fix 
-improperly zeroed buffer in CIFS Unix extensions set times call. 
-
-Version 1.25
-------------
-Fix internationalization problem in cifs readdir with filenames that map to 
-longer UTF-8 strings than the string on the wire was in Unicode.  Add workaround
-for readdir to netapp servers. Fix search rewind (seek into readdir to return 
-non-consecutive entries).  Do not do readdir when server negotiates 
-buffer size to small to fit filename. Add support for reading POSIX ACLs from
-the server (add also acl and noacl mount options).
-
-Version 1.24
-------------
-Optionally allow using server side inode numbers, rather than client generated
-ones by specifying mount option "serverino" - this is required for some apps
-to work which double check hardlinked files and have persistent inode numbers.
-
-Version 1.23
-------------
-Multiple bigendian fixes. On little endian systems (for reconnect after
-network failure) fix tcp session reconnect code so we do not try first
-to reconnect on reverse of port 445. Treat reparse points (NTFS junctions)
-as directories rather than symlinks because we can do follow link on them.
-
-Version 1.22
-------------
-Add config option to enable XATTR (extended attribute) support, mapping
-xattr names in the "user." namespace space to SMB/CIFS EAs. Lots of
-minor fixes pointed out by the Stanford SWAT checker (mostly missing
-or out of order NULL pointer checks in little used error paths).
-
-Version 1.21
-------------
-Add new mount parm to control whether mode check (generic_permission) is done
-on the client.  If Unix extensions are enabled and the uids on the client
-and server do not match, client permission checks are meaningless on
-server uids that do not exist on the client (this does not affect the
-normal ACL check which occurs on the server).  Fix default uid
-on mknod to match create and mkdir. Add optional mount parm to allow
-override of the default uid behavior (in which the server sets the uid
-and gid of newly created files). Normally for network filesystem mounts
-user want the server to set the uid/gid on newly created files (rather than 
-using uid of the client processes you would in a local filesystem).
-
-Version 1.20
-------------
-Make transaction counts more consistent. Merge /proc/fs/cifs/SimultaneousOps
-info into /proc/fs/cifs/DebugData.  Fix oops in rare oops in readdir 
-(in build_wildcard_path_from_dentry).  Fix mknod to pass type field
-(block/char/fifo) properly.  Remove spurious mount warning log entry when
-credentials passed as mount argument. Set major/minor device number in
-inode for block and char devices when unix extensions enabled.
-
-Version 1.19
-------------
-Fix /proc/fs/cifs/Stats and DebugData display to handle larger
-amounts of return data. Properly limit requests to MAX_REQ (50
-is the usual maximum active multiplex SMB/CIFS requests per server).
-Do not kill cifsd (and thus hurt the other SMB session) when more than one
-session to the same server (but with different userids) exists and one
-of the two user's smb sessions is being removed while leaving the other.
-Do not loop reconnecting in cifsd demultiplex thread when admin
-kills the thread without going through unmount.
-
-Version 1.18
-------------
-Do not rename hardlinked files (since that should be a noop). Flush
-cached write behind data when reopening a file after session abend,
-except when already in write. Grab per socket sem during reconnect 
-to avoid oops in sendmsg if overlapping with reconnect. Do not
-reset cached inode file size on readdir for files open for write on 
-client.
-
-
-Version 1.17
-------------
-Update number of blocks in file so du command is happier (in Linux a fake
-blocksize of 512 is required for calculating number of blocks in inode).
-Fix prepare write of partial pages to read in data from server if possible.
-Fix race on tcpStatus field between unmount and reconnection code, causing
-cifsd process sometimes to hang around forever. Improve out of memory
-checks in cifs_filldir
-
-Version 1.16
-------------
-Fix incorrect file size in file handle based setattr on big endian hardware.
-Fix oops in build_path_from_dentry when out of memory.  Add checks for invalid
-and closing file structs in writepage/partialpagewrite.  Add statistics
-for each mounted share (new menuconfig option). Fix endianness problem in
-volume information displayed in /proc/fs/cifs/DebugData (only affects
-affects big endian architectures). Prevent renames while constructing
-path names for open, mkdir and rmdir.
-
-Version 1.15
-------------
-Change to mempools for alloc smb request buffers and multiplex structs
-to better handle low memory problems (and potential deadlocks).
-
-Version 1.14
-------------
-Fix incomplete listings of large directories on Samba servers when Unix
-extensions enabled.  Fix oops when smb_buffer can not be allocated. Fix
-rename deadlock when writing out dirty pages at same time.
-
-Version 1.13
-------------
-Fix open of files in which O_CREATE can cause the mode to change in
-some cases. Fix case in which retry of write overlaps file close.
-Fix PPC64 build error.  Reduce excessive stack usage in smb password
-hashing. Fix overwrite of Linux user's view of file mode to Windows servers.
-
-Version 1.12
-------------
-Fixes for large file copy, signal handling, socket retry, buffer
-allocation and low memory situations.
-
-Version 1.11
-------------
-Better port 139 support to Windows servers (RFC1001/RFC1002 Session_Initialize)
-also now allowing support for specifying client netbiosname.  NT4 support added.
-
-Version 1.10
-------------
-Fix reconnection (and certain failed mounts) to properly wake up the
-blocked users thread so it does not seem hung (in some cases was blocked
-until the cifs receive timeout expired). Fix spurious error logging
-to kernel log when application with open network files killed. 
-
-Version 1.09
-------------
-Fix /proc/fs module unload warning message (that could be logged
-to the kernel log). Fix intermittent failure in connectathon
-test7 (hardlink count not immediately refreshed in case in which
-inode metadata can be incorrectly kept cached when time near zero)
-
-Version 1.08
-------------
-Allow file_mode and dir_mode (specified at mount time) to be enforced
-locally (the server already enforced its own ACLs too) for servers
-that do not report the correct mode (do not support the 
-CIFS Unix Extensions).
-
-Version 1.07
-------------
-Fix some small memory leaks in some unmount error paths. Fix major leak
-of cache pages in readpages causing multiple read oriented stress
-testcases (including fsx, and even large file copy) to fail over time. 
-
-Version 1.06
-------------
-Send NTCreateX with ATTR_POSIX if Linux/Unix extensions negotiated with server.
-This allows files that differ only in case and improves performance of file
-creation and file open to such servers.  Fix semaphore conflict which causes 
-slow delete of open file to Samba (which unfortunately can cause an oplock
-break to self while vfs_unlink held i_sem) which can hang for 20 seconds.
-
-Version 1.05
-------------
-fixes to cifs_readpages for fsx test case
-
-Version 1.04
-------------
-Fix caching data integrity bug when extending file size especially when no
-oplock on file.  Fix spurious logging of valid already parsed mount options
-that are parsed outside of the cifs vfs such as nosuid.
-
-
-Version 1.03
-------------
-Connect to server when port number override not specified, and tcp port
-unitialized.  Reset search to restart at correct file when kernel routine
-filldir returns error during large directory searches (readdir). 
-
-Version 1.02
-------------
-Fix caching problem when files opened by multiple clients in which 
-page cache could contain stale data, and write through did
-not occur often enough while file was still open when read ahead
-(read oplock) not allowed.  Treat "sep=" when first mount option
-as an override of comma as the default separator between mount
-options. 
-
-Version 1.01
-------------
-Allow passwords longer than 16 bytes. Allow null password string.
-
-Version 1.00
-------------
-Gracefully clean up failed mounts when attempting to mount to servers such as
-Windows 98 that terminate tcp sessions during protocol negotiation.  Handle
-embedded commas in mount parsing of passwords.
-
-Version 0.99
-------------
-Invalidate local inode cached pages on oplock break and when last file
-instance is closed so that the client does not continue using stale local
-copy rather than later modified server copy of file.  Do not reconnect
-when server drops the tcp session prematurely before negotiate
-protocol response.  Fix oops in reopen_file when dentry freed.  Allow
-the support for CIFS Unix Extensions to be disabled via proc interface.
-
-Version 0.98
-------------
-Fix hang in commit_write during reconnection of open files under heavy load.
-Fix unload_nls oops in a mount failure path. Serialize writes to same socket
-which also fixes any possible races when cifs signatures are enabled in SMBs
-being sent out of signature sequence number order.    
-
-Version 0.97
-------------
-Fix byte range locking bug (endian problem) causing bad offset and
-length.
-
-Version 0.96
-------------
-Fix oops (in send_sig) caused by CIFS unmount code trying to
-wake up the demultiplex thread after it had exited. Do not log
-error on harmless oplock release of closed handle.
-
-Version 0.95
-------------
-Fix unsafe global variable usage and password hash failure on gcc 3.3.1
-Fix problem reconnecting secondary mounts to same server after session 
-failure.  Fix invalid dentry - race in mkdir when directory gets created
-by another client between the lookup and mkdir.
- 
-Version 0.94
-------------
-Fix to list processing in reopen_files. Fix reconnection when server hung
-but tcpip session still alive.  Set proper timeout on socket read.
-
-Version 0.93
-------------
-Add missing mount options including iocharset.  SMP fixes in write and open. 
-Fix errors in reconnecting after TCP session failure.  Fix module unloading
-of default nls codepage
-
-Version 0.92
-------------
-Active smb transactions should never go negative (fix double FreeXid). Fix
-list processing in file routines. Check return code on kmalloc in open.
-Fix spinlock usage for SMP.
-
-Version 0.91
-------------
-Fix oops in reopen_files when invalid dentry. drop dentry on server rename 
-and on revalidate errors. Fix cases where pid is now tgid.  Fix return code
-on create hard link when server does not support them. 
-
-Version 0.90
-------------
-Fix scheduling while atomic error in getting inode info on newly created file. 
-Fix truncate of existing files opened with O_CREAT but not O_TRUNC set.
-
-Version 0.89
-------------
-Fix oops on write to dead tcp session. Remove error log write for case when file open
-O_CREAT but not O_EXCL
-
-Version 0.88
-------------
-Fix non-POSIX behavior on rename of open file and delete of open file by taking 
-advantage of trans2 SetFileInfo rename facility if available on target server.
-Retry on ENOSPC and EAGAIN socket errors.
-
-Version 0.87
-------------
-Fix oops on big endian readdir.  Set blksize to be even power of two (2**blkbits) to fix
-allocation size miscalculation. After oplock token lost do not read through
-cache. 
-
-Version 0.86
-------------
-Fix oops on empty file readahead.  Fix for file size handling for locally cached files.
-
-Version 0.85
-------------
-Fix oops in mkdir when server fails to return inode info. Fix oops in reopen_files
-during auto reconnection to server after server recovered from failure.
-
-Version 0.84
-------------
-Finish support for Linux 2.5 open/create changes, which removes the
-redundant NTCreate/QPathInfo/close that was sent during file create.
-Enable oplock by default. Enable packet signing by default (needed to 
-access many recent Windows servers)
-
-Version 0.83
-------------
-Fix oops when mounting to long server names caused by inverted parms to kmalloc.
-Fix MultiuserMount (/proc/fs/cifs configuration setting) so that when enabled
-we will choose a cifs user session (smb uid) that better matches the local
-uid if a) the mount uid does not match the current uid and b) we have another
-session to the same server (ip address) for a different mount which
-matches the current local uid.
-
-Version 0.82
-------------
-Add support for mknod of block or character devices.  Fix oplock
-code (distributed caching) to properly send response to oplock
-break from server.
-
-Version 0.81
-------------
-Finish up CIFS packet digital signing for the default
-NTLM security case. This should help Windows 2003
-network interoperability since it is common for
-packet signing to be required now. Fix statfs (stat -f)
-which recently started returning errors due to 
-invalid value (-1 instead of 0) being set in the
-struct kstatfs f_ffiles field.
-
-Version 0.80
------------
-Fix oops on stopping oplock thread when removing cifs when
-built as module.
-
-Version 0.79
-------------
-Fix mount options for ro (readonly), uid, gid and file and directory mode. 
-
-Version 0.78
-------------
-Fix errors displayed on failed mounts to be more understandable.
-Fixed various incorrect or misleading smb to posix error code mappings.
-
-Version 0.77
-------------
-Fix display of NTFS DFS junctions to display as symlinks.
-They are the network equivalent.  Fix oops in 
-cifs_partialpagewrite caused by missing spinlock protection
-of openfile linked list.  Allow writebehind caching errors to 
-be returned to the application at file close.
-
-Version 0.76
-------------
-Clean up options displayed in /proc/mounts by show_options to
-be more consistent with other filesystems.
-
-Version 0.75
-------------
-Fix delete of readonly file to Windows servers.  Reflect
-presence or absence of read only dos attribute in mode
-bits for servers that do not support CIFS Unix extensions.
-Fix shortened results on readdir of large directories to
-servers supporting CIFS Unix extensions (caused by
-incorrect resume key).
-
-Version 0.74
-------------
-Fix truncate bug (set file size) that could cause hangs e.g. running fsx
-
-Version 0.73
-------------
-unload nls if mount fails.
-
-Version 0.72
-------------
-Add resume key support to search (readdir) code to workaround
-Windows bug.  Add /proc/fs/cifs/LookupCacheEnable which
-allows disabling caching of attribute information for
-lookups.
-
-Version 0.71
-------------
-Add more oplock handling (distributed caching code).  Remove
-dead code.  Remove excessive stack space utilization from
-symlink routines.
-
-Version 0.70
-------------
-Fix oops in get dfs referral (triggered when null path sent in to
-mount).  Add support for overriding rsize at mount time.
-
-Version 0.69
-------------
-Fix buffer overrun in readdir which caused intermittent kernel oopses.
-Fix writepage code to release kmap on write data.  Allow "-ip=" new 
-mount option to be passed in on parameter distinct from the first part
-(server name portion of) the UNC name.  Allow override of the
-tcp port of the target server via new mount option "-port="  
-
-Version 0.68
-------------
-Fix search handle leak on rewind.  Fix setuid and gid so that they are 
-reflected in the local inode immediately.  Cleanup of whitespace
-to make 2.4 and 2.5 versions more consistent.
-
-
-Version 0.67
-------------
-Fix signal sending so that captive thread (cifsd) exits on umount 
-(which was causing the warning in kmem_cache_free of the request buffers
-at rmmod time).  This had broken as a sideeffect of the recent global
-kernel change to daemonize.  Fix memory leak in readdir code which
-showed up in "ls -R" (and applications that did search rewinding).
-
-Version 0.66
-------------
-Reconnect tids and fids after session reconnection (still do not
-reconnect byte range locks though).  Fix problem caching
-lookup information for directory inodes, improving performance,
-especially in deep directory trees.  Fix various build warnings.
-
-Version 0.65
-------------
-Finish fixes to commit write for caching/readahead consistency.  fsx 
-now works to Samba servers.  Fix oops caused when readahead
-was interrupted by a signal.
-
-Version 0.64
-------------
-Fix data corruption (in partial page after truncate) that caused fsx to
-fail to Windows servers.  Cleaned up some extraneous error logging in
-common error paths.  Add generic sendfile support.
-
-Version 0.63
-------------
-Fix memory leak in AllocMidQEntry.
-Finish reconnection logic, so connection with server can be dropped
-(or server rebooted) and the cifs client will reconnect.  
-
-Version 0.62
-------------
-Fix temporary socket leak when bad userid or password specified 
-(or other SMBSessSetup failure).  Increase maximum buffer size to slightly
-over 16K to allow negotiation of up to Samba and Windows server default read 
-sizes.  Add support for readpages
-
-Version 0.61
-------------
-Fix oops when username not passed in on mount.  Extensive fixes and improvements
-to error logging (strip redundant newlines, change debug macros to ensure newline
-passed in and to be more consistent).  Fix writepage wrong file handle problem,
-a readonly file handle could be incorrectly used to attempt to write out
-file updates through the page cache to multiply open files.  This could cause
-the iozone benchmark to fail on the fwrite test. Fix bug mounting two different
-shares to the same Windows server when using different usernames
-(doing this to Samba servers worked but Windows was rejecting it) - now it is
-possible to use different userids when connecting to the same server from a
-Linux client. Fix oops when treeDisconnect called during unmount on
-previously freed socket.
-
-Version 0.60
-------------
-Fix oops in readpages caused by not setting address space operations in inode in 
-rare code path. 
-
-Version 0.59
-------------
-Includes support for deleting of open files and renaming over existing files (per POSIX
-requirement).  Add readlink support for Windows junction points (directory symlinks).
-
-Version 0.58
-------------
-Changed read and write to go through pagecache. Added additional address space operations.
-Memory mapped operations now working.
-
-Version 0.57
-------------
-Added writepage code for additional memory mapping support.  Fixed leak in xids causing
-the simultaneous operations counter (/proc/fs/cifs/SimultaneousOps) to increase on 
-every stat call.  Additional formatting cleanup. 
-
-Version 0.56
-------------
-Fix bigendian bug in order of time conversion. Merge 2.5 to 2.4 version.  Formatting cleanup.   
-
-Version 0.55
-------------
-Fixes from Zwane Mwaikambo for adding missing return code checking in a few places.
-Also included a modified version of his fix to protect global list manipulation of
-the smb session and tree connection and mid related global variables.
-
-Version 0.54
-------------
-Fix problem with captive thread hanging around at unmount time.  Adjust to 2.5.42-pre
-changes to superblock layout.   Remove wasteful allocation of smb buffers (now the send 
-buffer is reused for responses).  Add more oplock handling. Additional minor cleanup.
-
-Version 0.53
-------------
-More stylistic updates to better match kernel style.  Add additional statistics
-for filesystem which can be viewed via /proc/fs/cifs.  Add more pieces of NTLMv2
-and CIFS Packet Signing enablement.
-
-Version 0.52
-------------
-Replace call to sleep_on with safer wait_on_event.
-Make stylistic changes to better match kernel style recommendations.
-Remove most typedef usage (except for the PDUs themselves).
-
-Version 0.51
-------------
-Update mount so the -unc mount option is no longer required (the ip address can be specified
-in a UNC style device name.   Implementation of readpage/writepage started.
-
-Version 0.50
-------------
-Fix intermittent problem with incorrect smb header checking on badly 
-fragmented tcp responses
-
-Version 0.49
-------------
-Fixes to setting of allocation size and file size.
-
-Version 0.48
-------------
-Various 2.5.38 fixes.  Now works on 2.5.38
-
-Version 0.47
-------------
-Prepare for 2.5 kernel merge.  Remove ifdefs.
-
-Version 0.46
-------------
-Socket buffer management fixes.  Fix dual free.
-
-Version 0.45
-------------
-Various big endian fixes for hardlinks and symlinks and also for dfs.
-
-Version 0.44
-------------
-Various big endian fixes for servers with Unix extensions such as Samba
-
-Version 0.43
-------------
-Various FindNext fixes for incorrect filenames on large directory searches on big endian
-clients.  basic posix file i/o tests now work on big endian machines, not just le
-
-Version 0.42
-------------
-SessionSetup and NegotiateProtocol now work from Big Endian machines.
-Various Big Endian fixes found during testing on the Linux on 390.  Various fixes for compatibility with older
-versions of 2.4 kernel (now builds and works again on kernels at least as early as 2.4.7).
-
-Version 0.41
-------------
-Various minor fixes for Connectathon Posix "basic" file i/o test suite.  Directory caching fixed so hardlinked
-files now return the correct number of links on fstat as they are repeatedly linked and unlinked.
-
-Version 0.40
-------------
-Implemented "Raw" (i.e. not encapsulated in SPNEGO) NTLMSSP (i.e. the Security Provider Interface used to negotiate
-session advanced session authentication).  Raw NTLMSSP is preferred by Windows 2000 Professional and Windows XP.
-Began implementing support for SPNEGO encapsulation of NTLMSSP based session authentication blobs
-(which is the mechanism preferred by Windows 2000 server in the absence of Kerberos).
-
-Version 0.38
-------------
-Introduced optional mount helper utility mount.cifs and made coreq changes to cifs vfs to enable
-it. Fixed a few bugs in the DFS code (e.g. bcc two bytes too short and incorrect uid in PDU).
-
-Version 0.37
-------------
-Rewrote much of connection and mount/unmount logic to handle bugs with
-multiple uses to same share, multiple users to same server etc.
-
-Version 0.36
-------------
-Fixed major problem with dentry corruption (missing call to dput)
-
-Version 0.35
-------------
-Rewrite of readdir code to fix bug. Various fixes for bigendian machines.
-Begin adding oplock support.  Multiusermount and oplockEnabled flags added to /proc/fs/cifs
-although corresponding function not fully implemented in the vfs yet
-
-Version 0.34
-------------
-Fixed dentry caching bug, misc. cleanup 
-
-Version 0.33
-------------
-Fixed 2.5 support to handle build and configure changes as well as misc. 2.5 changes.  Now can build
-on current 2.5 beta version (2.5.24) of the Linux kernel as well as on 2.4 Linux kernels.
-Support for STATUS codes (newer 32 bit NT error codes) added.  DFS support begun to be added.
-
-Version 0.32
-------------
-Unix extensions (symlink, readlink, hardlink, chmod and some chgrp and chown) implemented
-and tested against Samba 2.2.5
-
-
-Version 0.31
-------------
-1) Fixed lockrange to be correct (it was one byte too short)
-
-2) Fixed GETLK (i.e. the fcntl call to test a range of bytes in a file to see if locked) to correctly 
-show range as locked when there is a conflict with an existing lock.
-
-3) default file perms are now 2767 (indicating support for mandatory locks) instead of 777 for directories
-in most cases.  Eventually will offer optional ability to query server for the correct perms.
-
-3) Fixed eventual trap when mounting twice to different shares on the same server when the first succeeded 
-but the second one was invalid and failed (the second one was incorrectly disconnecting the tcp and smb
-session) 
-
-4) Fixed error logging of valid mount options
-
-5) Removed logging of password field.
-
-6) Moved negotiate, treeDisconnect and uloggoffX (only tConx and SessSetup remain in connect.c) to cifssmb.c
-and cleaned them up and made them more consistent with other cifs functions. 
-
-7) Server support for Unix extensions is now fully detected and FindFirst is implemented both ways 
-(with or without Unix extensions) but FindNext and QueryPathInfo with the Unix extensions are not completed,
-nor is the symlink support using the Unix extensions
-
-8) Started adding the readlink and follow_link code 
-
-Version 0.3 
------------
-Initial drop
-
+See https://wiki.samba.org/index.php/LinuxCIFSKernel for summary
+information (that may be easier to read than parsing the output of
+"git log fs/cifs") about fixes/improvements to CIFS/SMB2/SMB3 support (changes
+to cifs.ko module) by kernel version (and cifs internal module version).
diff --git a/Documentation/filesystems/cifs/README b/Documentation/filesystems/cifs/README
index 99ce3d25003d..4a804619cff2 100644
--- a/Documentation/filesystems/cifs/README
+++ b/Documentation/filesystems/cifs/README
@@ -603,8 +603,7 @@ DebugData		Displays information about active CIFS sessions and
 			shares, features enabled as well as the cifs.ko
 			version.
 Stats			Lists summary resource usage information as well as per
-			share statistics, if CONFIG_CIFS_STATS in enabled
-			in the kernel configuration.
+			share statistics.
 
 Configuration pseudo-files:
 SecurityFlags		Flags which control security negotiation and
@@ -687,23 +686,22 @@ cifsFYI functions as a bit mask. Setting it to 1 enables additional kernel
 logging of various informational messages.  2 enables logging of non-zero
 SMB return codes while 4 enables logging of requests that take longer
 than one second to complete (except for byte range lock requests). 
-Setting it to 4 requires defining CONFIG_CIFS_STATS2 manually in the
-source code (typically by setting it in the beginning of cifsglob.h),
-and setting it to seven enables all three.  Finally, tracing
+Setting it to 4 requires CONFIG_CIFS_STATS2 to be set in kernel configuration
+(.config). Setting it to seven enables all three.  Finally, tracing
 the start of smb requests and responses can be enabled via:
 
 	echo 1 > /proc/fs/cifs/traceSMB
 
-Per share (per client mount) statistics are available in /proc/fs/cifs/Stats
-if the kernel was configured with cifs statistics enabled.  The statistics
-represent the number of successful (ie non-zero return code from the server) 
-SMB responses to some of the more common commands (open, delete, mkdir etc.).
+Per share (per client mount) statistics are available in /proc/fs/cifs/Stats.
+Additional information is available if CONFIG_CIFS_STATS2 is enabled in the
+kernel configuration (.config).  The statistics returned include counters which
+represent the number of attempted and failed (ie non-zero return code from the
+server) SMB3 (or cifs) requests grouped by request type (read, write, close etc.).
 Also recorded is the total bytes read and bytes written to the server for
 that share.  Note that due to client caching effects this can be less than the
 number of bytes read and written by the application running on the client.
-The statistics for the number of total SMBs and oplock breaks are different in
-that they represent all for that share, not just those for which the server
-returned success.
+Statistics can be reset to zero by "echo 0 > /proc/fs/cifs/Stats" which may be
+useful if comparing performance of two different scenarios.
 	
 Also note that "cat /proc/fs/cifs/DebugData" will display information about
 the active sessions and the shares that are mounted.
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4/ext4.rst
index 7f628b9f7c4b..9d4368d591fa 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4/ext4.rst
@@ -1,6 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
 
-Ext4 Filesystem
-===============
+========================
+General Information
+========================
 
 Ext4 is an advanced level of the ext3 filesystem which incorporates
 scalability and reliability enhancements for supporting large filesystems
@@ -11,37 +13,30 @@ Mailing list:	linux-ext4@vger.kernel.org
 Web site:	http://ext4.wiki.kernel.org
 
 
-1. Quick usage instructions:
-===========================
+Quick usage instructions
+========================
 
 Note: More extensive information for getting started with ext4 can be
-      found at the ext4 wiki site at the URL:
-      http://ext4.wiki.kernel.org/index.php/Ext4_Howto
+found at the ext4 wiki site at the URL:
+http://ext4.wiki.kernel.org/index.php/Ext4_Howto
 
-  - Compile and install the latest version of e2fsprogs (as of this
-    writing version 1.41.3) from:
+  - The latest version of e2fsprogs can be found at:
+
+    https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
 
-    http://sourceforge.net/project/showfiles.php?group_id=2406
-	
 	or
 
-    https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
+    http://sourceforge.net/project/showfiles.php?group_id=2406
 
 	or grab the latest git repository from:
 
-    git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
-
-  - Note that it is highly important to install the mke2fs.conf file
-    that comes with the e2fsprogs 1.41.x sources in /etc/mke2fs.conf. If
-    you have edited the /etc/mke2fs.conf file installed on your system,
-    you will need to merge your changes with the version from e2fsprogs
-    1.41.x.
+   https://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
 
   - Create a new filesystem using the ext4 filesystem type:
 
-    	# mke2fs -t ext4 /dev/hda1
+        # mke2fs -t ext4 /dev/hda1
 
-    Or to configure an existing ext3 filesystem to support extents: 
+    Or to configure an existing ext3 filesystem to support extents:
 
 	# tune2fs -O extents /dev/hda1
 
@@ -50,10 +45,6 @@ Note: More extensive information for getting started with ext4 can be
 
         # tune2fs -I 256 /dev/hda1
 
-    (Note: we currently do not have tools to convert an ext4
-    filesystem back to ext3; so please do not do try this on production
-    filesystems.)
-
   - Mounting:
 
 	# mount -t ext4 /dev/hda1 /wherever
@@ -75,10 +66,11 @@ Note: More extensive information for getting started with ext4 can be
     the filesystem with a large journal can also be helpful for
     metadata-intensive workloads.
 
-2. Features
-===========
+Features
+========
 
-2.1 Currently available
+Currently Available
+-------------------
 
 * ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
@@ -103,31 +95,15 @@ Note: More extensive information for getting started with ext4 can be
 [1] Filesystems with a block size of 1k may see a limit imposed by the
 directory hash tree having a maximum depth of two.
 
-2.2 Candidate features for future inclusion
-
-* online defrag (patches available but not well tested)
-* reduced mke2fs time via lazy itable initialization in conjunction with
-  the uninit_bg feature (capability to do this is available in e2fsprogs
-  but a kernel thread to do lazy zeroing of unused inode table blocks
-  after filesystem is first mounted is required for safety)
-
-There are several others under discussion, whether they all make it in is
-partly a function of how much time everyone has to work on them. Features like
-metadata checksumming have been discussed and planned for a bit but no patches
-exist yet so I'm not sure they're in the near-term roadmap.
-
-The big performance win will come with mballoc, delalloc and flex_bg
-grouping of bitmaps and inode tables.  Some test results available here:
-
- - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-write-2.6.27-rc1.html
- - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-readwrite-2.6.27-rc1.html
-
-3. Options
-==========
+Options
+=======
 
 When mounting an ext4 filesystem, the following option are accepted:
 (*) == default
 
+======================= =======================================================
+Mount Option            Description
+======================= =======================================================
 ro                   	Mount filesystem read only. Note that ext4 will
                      	replay the journal (and thus write to the
                      	partition) even when mounted "read only". The
@@ -387,33 +363,38 @@ i_version		Enable 64-bit inode version support. This option is
 dax			Use direct access (no page cache).  See
 			Documentation/filesystems/dax.txt.  Note that
 			this option is incompatible with data=journal.
+======================= =======================================================
 
 Data Mode
 =========
 There are 3 different data modes:
 
 * writeback mode
-In data=writeback mode, ext4 does not journal data at all.  This mode provides
-a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
-mode - metadata journaling.  A crash+recovery can cause incorrect data to
-appear in files which were written shortly before the crash.  This mode will
-typically provide the best ext4 performance.
+
+  In data=writeback mode, ext4 does not journal data at all.  This mode provides
+  a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
+  mode - metadata journaling.  A crash+recovery can cause incorrect data to
+  appear in files which were written shortly before the crash.  This mode will
+  typically provide the best ext4 performance.
 
 * ordered mode
-In data=ordered mode, ext4 only officially journals metadata, but it logically
-groups metadata information related to data changes with the data blocks into a
-single unit called a transaction.  When it's time to write the new metadata
-out to disk, the associated data blocks are written first.  In general,
-this mode performs slightly slower than writeback but significantly faster than journal mode.
+
+  In data=ordered mode, ext4 only officially journals metadata, but it logically
+  groups metadata information related to data changes with the data blocks into
+  a single unit called a transaction.  When it's time to write the new metadata
+  out to disk, the associated data blocks are written first.  In general, this
+  mode performs slightly slower than writeback but significantly faster than
+  journal mode.
 
 * journal mode
-data=journal mode provides full data and metadata journaling.  All new data is
-written to the journal first, and then to its final location.
-In the event of a crash, the journal can be replayed, bringing both data and
-metadata into a consistent state.  This mode is the slowest except when data
-needs to be read from and written to disk at the same time where it
-outperforms all others modes.  Enabling this mode will disable delayed
-allocation and O_DIRECT support.
+
+  data=journal mode provides full data and metadata journaling.  All new data is
+  written to the journal first, and then to its final location.  In the event of
+  a crash, the journal can be replayed, bringing both data and metadata into a
+  consistent state.  This mode is the slowest except when data needs to be read
+  from and written to disk at the same time where it outperforms all others
+  modes.  Enabling this mode will disable delayed allocation and O_DIRECT
+  support.
 
 /proc entries
 =============
@@ -425,10 +406,12 @@ Information about mounted ext4 file systems can be found in
 in table below.
 
 Files in /proc/fs/ext4/<devname>
-..............................................................................
+
+================ =======
  File            Content
+================ =======
  mb_groups       details of multiblock allocator buddy cache of free blocks
-..............................................................................
+================ =======
 
 /sys entries
 ============
@@ -439,28 +422,30 @@ Information about mounted ext4 file systems can be found in
 /sys/fs/ext4/dm-0).   The files in each per-device directory are shown
 in table below.
 
-Files in /sys/fs/ext4/<devname>
+Files in /sys/fs/ext4/<devname>:
+
 (see also Documentation/ABI/testing/sysfs-fs-ext4)
-..............................................................................
- File                         Content
 
+============================= =================================================
+File                          Content
+============================= =================================================
  delayed_allocation_blocks    This file is read-only and shows the number of
                               blocks that are dirty in the page cache, but
                               which do not have their location in the
                               filesystem allocated yet.
 
- inode_goal                   Tuning parameter which (if non-zero) controls
+inode_goal                    Tuning parameter which (if non-zero) controls
                               the goal inode used by the inode allocator in
                               preference to all other allocation heuristics.
                               This is intended for debugging use only, and
                               should be 0 on production systems.
 
- inode_readahead_blks         Tuning parameter which controls the maximum
+inode_readahead_blks          Tuning parameter which controls the maximum
                               number of inode table blocks that ext4's inode
                               table readahead algorithm will pre-read into
                               the buffer cache
 
- lifetime_write_kbytes        This file is read-only and shows the number of
+lifetime_write_kbytes         This file is read-only and shows the number of
                               kilobytes of data that have been written to this
                               filesystem since it was created.
 
@@ -508,7 +493,7 @@ Files in /sys/fs/ext4/<devname>
                               in the file system. If there is not enough space
                               for the reserved space when mounting the file
                               mount will _not_ fail.
-..............................................................................
+============================= =================================================
 
 Ioctls
 ======
@@ -518,8 +503,10 @@ through the system call interfaces. The list of all Ext4 specific ioctls are
 shown in the table below.
 
 Table of Ext4 specific ioctls
-..............................................................................
- Ioctl			      Description
+
+============================= =================================================
+Ioctl			      Description
+============================= =================================================
  EXT4_IOC_GETFLAGS	      Get additional attributes associated with inode.
 			      The ioctl argument is an integer bitfield, with
 			      bit values described in ext4.h. This ioctl is an
@@ -610,8 +597,7 @@ Table of Ext4 specific ioctls
 			      normal user by accident.
 			      The data blocks of the previous boot loader
 			      will be associated with the given inode.
-
-..............................................................................
+============================= =================================================
 
 References
 ==========
diff --git a/Documentation/filesystems/ext4/index.rst b/Documentation/filesystems/ext4/index.rst
new file mode 100644
index 000000000000..71121605558c
--- /dev/null
+++ b/Documentation/filesystems/ext4/index.rst
@@ -0,0 +1,17 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+ext4 Filesystem
+===============
+
+General usage and on-disk artifacts writen by ext4.  More documentation may
+be ported from the wiki as time permits.  This should be considered the
+canonical source of information as the details here have been reviewed by
+the ext4 community.
+
+.. toctree::
+   :maxdepth: 5
+   :numbered:
+
+   ext4
+   ondisk/index
diff --git a/Documentation/filesystems/ext4/ondisk/about.rst b/Documentation/filesystems/ext4/ondisk/about.rst
new file mode 100644
index 000000000000..0aadba052264
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/about.rst
@@ -0,0 +1,44 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+About this Book
+===============
+
+This document attempts to describe the on-disk format for ext4
+filesystems. The same general ideas should apply to ext2/3 filesystems
+as well, though they do not support all the features that ext4 supports,
+and the fields will be shorter.
+
+**NOTE**: This is a work in progress, based on notes that the author
+(djwong) made while picking apart a filesystem by hand. The data
+structure definitions should be current as of Linux 4.18 and
+e2fsprogs-1.44. All comments and corrections are welcome, since there is
+undoubtedly plenty of lore that might not be reflected in freshly
+created demonstration filesystems.
+
+License
+-------
+This book is licensed under the terms of the GNU Public License, v2.
+
+Terminology
+-----------
+
+ext4 divides a storage device into an array of logical blocks both to
+reduce bookkeeping overhead and to increase throughput by forcing larger
+transfer sizes. Generally, the block size will be 4KiB (the same size as
+pages on x86 and the block layer's default block size), though the
+actual size is calculated as 2 ^ (10 + ``sb.s_log_block_size``) bytes.
+Throughout this document, disk locations are given in terms of these
+logical blocks, not raw LBAs, and not 1024-byte blocks. For the sake of
+convenience, the logical block size will be referred to as
+``$block_size`` throughout the rest of the document.
+
+When referenced in ``preformatted text`` blocks, ``sb`` refers to fields
+in the super block, and ``inode`` refers to fields in an inode table
+entry.
+
+Other References
+----------------
+
+Also see http://www.nongnu.org/ext2-doc/ for quite a collection of
+information about ext2/3. Here's another old reference:
+http://wiki.osdev.org/Ext2
diff --git a/Documentation/filesystems/ext4/ondisk/allocators.rst b/Documentation/filesystems/ext4/ondisk/allocators.rst
new file mode 100644
index 000000000000..7aa85152ace3
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/allocators.rst
@@ -0,0 +1,56 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Block and Inode Allocation Policy
+---------------------------------
+
+ext4 recognizes (better than ext3, anyway) that data locality is
+generally a desirably quality of a filesystem. On a spinning disk,
+keeping related blocks near each other reduces the amount of movement
+that the head actuator and disk must perform to access a data block,
+thus speeding up disk IO. On an SSD there of course are no moving parts,
+but locality can increase the size of each transfer request while
+reducing the total number of requests. This locality may also have the
+effect of concentrating writes on a single erase block, which can speed
+up file rewrites significantly. Therefore, it is useful to reduce
+fragmentation whenever possible.
+
+The first tool that ext4 uses to combat fragmentation is the multi-block
+allocator. When a file is first created, the block allocator
+speculatively allocates 8KiB of disk space to the file on the assumption
+that the space will get written soon. When the file is closed, the
+unused speculative allocations are of course freed, but if the
+speculation is correct (typically the case for full writes of small
+files) then the file data gets written out in a single multi-block
+extent. A second related trick that ext4 uses is delayed allocation.
+Under this scheme, when a file needs more blocks to absorb file writes,
+the filesystem defers deciding the exact placement on the disk until all
+the dirty buffers are being written out to disk. By not committing to a
+particular placement until it's absolutely necessary (the commit timeout
+is hit, or sync() is called, or the kernel runs out of memory), the hope
+is that the filesystem can make better location decisions.
+
+The third trick that ext4 (and ext3) uses is that it tries to keep a
+file's data blocks in the same block group as its inode. This cuts down
+on the seek penalty when the filesystem first has to read a file's inode
+to learn where the file's data blocks live and then seek over to the
+file's data blocks to begin I/O operations.
+
+The fourth trick is that all the inodes in a directory are placed in the
+same block group as the directory, when feasible. The working assumption
+here is that all the files in a directory might be related, therefore it
+is useful to try to keep them all together.
+
+The fifth trick is that the disk volume is cut up into 128MB block
+groups; these mini-containers are used as outlined above to try to
+maintain data locality. However, there is a deliberate quirk -- when a
+directory is created in the root directory, the inode allocator scans
+the block groups and puts that directory into the least heavily loaded
+block group that it can find. This encourages directories to spread out
+over a disk; as the top-level directory/file blobs fill up one block
+group, the allocators simply move on to the next block group. Allegedly
+this scheme evens out the loading on the block groups, though the author
+suspects that the directories which are so unlucky as to land towards
+the end of a spinning drive get a raw deal performance-wise.
+
+Of course if all of these mechanisms fail, one can always use e4defrag
+to defragment files.
diff --git a/Documentation/filesystems/ext4/ondisk/attributes.rst b/Documentation/filesystems/ext4/ondisk/attributes.rst
new file mode 100644
index 000000000000..0b01b67b81fe
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/attributes.rst
@@ -0,0 +1,191 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Extended Attributes
+-------------------
+
+Extended attributes (xattrs) are typically stored in a separate data
+block on the disk and referenced from inodes via ``inode.i_file_acl*``.
+The first use of extended attributes seems to have been for storing file
+ACLs and other security data (selinux). With the ``user_xattr`` mount
+option it is possible for users to store extended attributes so long as
+all attribute names begin with “user�; this restriction seems to have
+disappeared as of Linux 3.0.
+
+There are two places where extended attributes can be found. The first
+place is between the end of each inode entry and the beginning of the
+next inode entry. For example, if inode.i\_extra\_isize = 28 and
+sb.inode\_size = 256, then there are 256 - (128 + 28) = 100 bytes
+available for in-inode extended attribute storage. The second place
+where extended attributes can be found is in the block pointed to by
+``inode.i_file_acl``. As of Linux 3.11, it is not possible for this
+block to contain a pointer to a second extended attribute block (or even
+the remaining blocks of a cluster). In theory it is possible for each
+attribute's value to be stored in a separate data block, though as of
+Linux 3.11 the code does not permit this.
+
+Keys are generally assumed to be ASCIIZ strings, whereas values can be
+strings or binary data.
+
+Extended attributes, when stored after the inode, have a header
+``ext4_xattr_ibody_header`` that is 4 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - h\_magic
+     - Magic number for identification, 0xEA020000. This value is set by the
+       Linux driver, though e2fsprogs doesn't seem to check it(?)
+
+The beginning of an extended attribute block is in
+``struct ext4_xattr_header``, which is 32 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - h\_magic
+     - Magic number for identification, 0xEA020000.
+   * - 0x4
+     - \_\_le32
+     - h\_refcount
+     - Reference count.
+   * - 0x8
+     - \_\_le32
+     - h\_blocks
+     - Number of disk blocks used.
+   * - 0xC
+     - \_\_le32
+     - h\_hash
+     - Hash value of all attributes.
+   * - 0x10
+     - \_\_le32
+     - h\_checksum
+     - Checksum of the extended attribute block.
+   * - 0x14
+     - \_\_u32
+     - h\_reserved[2]
+     - Zero.
+
+The checksum is calculated against the FS UUID, the 64-bit block number
+of the extended attribute block, and the entire block (header +
+entries).
+
+Following the ``struct ext4_xattr_header`` or
+``struct ext4_xattr_ibody_header`` is an array of
+``struct ext4_xattr_entry``; each of these entries is at least 16 bytes
+long. When stored in an external block, the ``struct ext4_xattr_entry``
+entries must be stored in sorted order. The sort order is
+``e_name_index``, then ``e_name_len``, and finally ``e_name``.
+Attributes stored inside an inode do not need be stored in sorted order.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_u8
+     - e\_name\_len
+     - Length of name.
+   * - 0x1
+     - \_\_u8
+     - e\_name\_index
+     - Attribute name index. There is a discussion of this below.
+   * - 0x2
+     - \_\_le16
+     - e\_value\_offs
+     - Location of this attribute's value on the disk block where it is stored.
+       Multiple attributes can share the same value. For an inode attribute
+       this value is relative to the start of the first entry; for a block this
+       value is relative to the start of the block (i.e. the header).
+   * - 0x4
+     - \_\_le32
+     - e\_value\_inum
+     - The inode where the value is stored. Zero indicates the value is in the
+       same block as this entry. This field is only used if the
+       INCOMPAT\_EA\_INODE feature is enabled.
+   * - 0x8
+     - \_\_le32
+     - e\_value\_size
+     - Length of attribute value.
+   * - 0xC
+     - \_\_le32
+     - e\_hash
+     - Hash value of attribute name and attribute value. The kernel doesn't
+       update the hash for in-inode attributes, so for that case this value
+       must be zero, because e2fsck validates any non-zero hash regardless of
+       where the xattr lives.
+   * - 0x10
+     - char
+     - e\_name[e\_name\_len]
+     - Attribute name. Does not include trailing NULL.
+
+Attribute values can follow the end of the entry table. There appears to
+be a requirement that they be aligned to 4-byte boundaries. The values
+are stored starting at the end of the block and grow towards the
+xattr\_header/xattr\_entry table. When the two collide, the overflow is
+put into a separate disk block. If the disk block fills up, the
+filesystem returns -ENOSPC.
+
+The first four fields of the ``ext4_xattr_entry`` are set to zero to
+mark the end of the key list.
+
+Attribute Name Indices
+~~~~~~~~~~~~~~~~~~~~~~
+
+Logically speaking, extended attributes are a series of key=value pairs.
+The keys are assumed to be NULL-terminated strings. To reduce the amount
+of on-disk space that the keys consume, the beginning of the key string
+is matched against the attribute name index. If a match is found, the
+attribute name index field is set, and matching string is removed from
+the key name. Here is a map of name index values to key prefixes:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Name Index
+     - Key Prefix
+   * - 0
+     - (no prefix)
+   * - 1
+     - “user.�
+   * - 2
+     - “system.posix\_acl\_access�
+   * - 3
+     - “system.posix\_acl\_default�
+   * - 4
+     - “trusted.�
+   * - 6
+     - “security.�
+   * - 7
+     - “system.� (inline\_data only?)
+   * - 8
+     - “system.richacl� (SuSE kernels only?)
+
+For example, if the attribute key is “user.fubar�, the attribute name
+index is set to 1 and the “fubar� name is recorded on disk.
+
+POSIX ACLs
+~~~~~~~~~~
+
+POSIX ACLs are stored in a reduced version of the Linux kernel (and
+libacl's) internal ACL format. The key difference is that the version
+number is different (1) and the ``e_id`` field is only stored for named
+user and group ACLs.
diff --git a/Documentation/filesystems/ext4/ondisk/bigalloc.rst b/Documentation/filesystems/ext4/ondisk/bigalloc.rst
new file mode 100644
index 000000000000..c6d88557553c
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/bigalloc.rst
@@ -0,0 +1,22 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Bigalloc
+--------
+
+At the moment, the default size of a block is 4KiB, which is a commonly
+supported page size on most MMU-capable hardware. This is fortunate, as
+ext4 code is not prepared to handle the case where the block size
+exceeds the page size. However, for a filesystem of mostly huge files,
+it is desirable to be able to allocate disk blocks in units of multiple
+blocks to reduce both fragmentation and metadata overhead. The
+`bigalloc <Bigalloc>`__ feature provides exactly this ability. The
+administrator can set a block cluster size at mkfs time (which is stored
+in the s\_log\_cluster\_size field in the superblock); from then on, the
+block bitmaps track clusters, not individual blocks. This means that
+block groups can be several gigabytes in size (instead of just 128MiB);
+however, the minimum allocation unit becomes a cluster, not a block,
+even for directories. TaoBao had a patchset to extend the “use units of
+clusters instead of blocks� to the extent tree, though it is not clear
+where those patches went-- they eventually morphed into “extent tree v2�
+but that code has not landed as of May 2015.
+
diff --git a/Documentation/filesystems/ext4/ondisk/bitmaps.rst b/Documentation/filesystems/ext4/ondisk/bitmaps.rst
new file mode 100644
index 000000000000..c7546dbc197a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/bitmaps.rst
@@ -0,0 +1,28 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Block and inode Bitmaps
+-----------------------
+
+The data block bitmap tracks the usage of data blocks within the block
+group.
+
+The inode bitmap records which entries in the inode table are in use.
+
+As with most bitmaps, one bit represents the usage status of one data
+block or inode table entry. This implies a block group size of 8 \*
+number\_of\_bytes\_in\_a\_logical\_block.
+
+NOTE: If ``BLOCK_UNINIT`` is set for a given block group, various parts
+of the kernel and e2fsprogs code pretends that the block bitmap contains
+zeros (i.e. all blocks in the group are free). However, it is not
+necessarily the case that no blocks are in use -- if ``meta_bg`` is set,
+the bitmaps and group descriptor live inside the group. Unfortunately,
+ext2fs\_test\_block\_bitmap2() will return '0' for those locations,
+which produces confusing debugfs output.
+
+Inode Table
+-----------
+Inode tables are statically allocated at mkfs time.  Each block group
+descriptor points to the start of the table, and the superblock records
+the number of inodes per group.  See the section on inodes for more
+information.
diff --git a/Documentation/filesystems/ext4/ondisk/blockgroup.rst b/Documentation/filesystems/ext4/ondisk/blockgroup.rst
new file mode 100644
index 000000000000..baf888e4c06a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/blockgroup.rst
@@ -0,0 +1,135 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Layout
+------
+
+The layout of a standard block group is approximately as follows (each
+of these fields is discussed in a separate section below):
+
+.. list-table::
+   :widths: 1 1 1 1 1 1 1 1
+   :header-rows: 1
+
+   * - Group 0 Padding
+     - ext4 Super Block
+     - Group Descriptors
+     - Reserved GDT Blocks
+     - Data Block Bitmap
+     - inode Bitmap
+     - inode Table
+     - Data Blocks
+   * - 1024 bytes
+     - 1 block
+     - many blocks
+     - many blocks
+     - 1 block
+     - 1 block
+     - many blocks
+     - many more blocks
+
+For the special case of block group 0, the first 1024 bytes are unused,
+to allow for the installation of x86 boot sectors and other oddities.
+The superblock will start at offset 1024 bytes, whichever block that
+happens to be (usually 0). However, if for some reason the block size =
+1024, then block 0 is marked in use and the superblock goes in block 1.
+For all other block groups, there is no padding.
+
+The ext4 driver primarily works with the superblock and the group
+descriptors that are found in block group 0. Redundant copies of the
+superblock and group descriptors are written to some of the block groups
+across the disk in case the beginning of the disk gets trashed, though
+not all block groups necessarily host a redundant copy (see following
+paragraph for more details). If the group does not have a redundant
+copy, the block group begins with the data block bitmap. Note also that
+when the filesystem is freshly formatted, mkfs will allocate “reserve
+GDT block� space after the block group descriptors and before the start
+of the block bitmaps to allow for future expansion of the filesystem. By
+default, a filesystem is allowed to increase in size by a factor of
+1024x over the original filesystem size.
+
+The location of the inode table is given by ``grp.bg_inode_table_*``. It
+is continuous range of blocks large enough to contain
+``sb.s_inodes_per_group * sb.s_inode_size`` bytes.
+
+As for the ordering of items in a block group, it is generally
+established that the super block and the group descriptor table, if
+present, will be at the beginning of the block group. The bitmaps and
+the inode table can be anywhere, and it is quite possible for the
+bitmaps to come after the inode table, or for both to be in different
+groups (flex\_bg). Leftover space is used for file data blocks, indirect
+block maps, extent tree blocks, and extended attributes.
+
+Flexible Block Groups
+---------------------
+
+Starting in ext4, there is a new feature called flexible block groups
+(flex\_bg). In a flex\_bg, several block groups are tied together as one
+logical block group; the bitmap spaces and the inode table space in the
+first block group of the flex\_bg are expanded to include the bitmaps
+and inode tables of all other block groups in the flex\_bg. For example,
+if the flex\_bg size is 4, then group 0 will contain (in order) the
+superblock, group descriptors, data block bitmaps for groups 0-3, inode
+bitmaps for groups 0-3, inode tables for groups 0-3, and the remaining
+space in group 0 is for file data. The effect of this is to group the
+block metadata close together for faster loading, and to enable large
+files to be continuous on disk. Backup copies of the superblock and
+group descriptors are always at the beginning of block groups, even if
+flex\_bg is enabled. The number of block groups that make up a flex\_bg
+is given by 2 ^ ``sb.s_log_groups_per_flex``.
+
+Meta Block Groups
+-----------------
+
+Without the option META\_BG, for safety concerns, all block group
+descriptors copies are kept in the first block group. Given the default
+128MiB(2^27 bytes) block group size and 64-byte group descriptors, ext4
+can have at most 2^27/64 = 2^21 block groups. This limits the entire
+filesystem size to 2^21 ∗ 2^27 = 2^48bytes or 256TiB.
+
+The solution to this problem is to use the metablock group feature
+(META\_BG), which is already in ext3 for all 2.6 releases. With the
+META\_BG feature, ext4 filesystems are partitioned into many metablock
+groups. Each metablock group is a cluster of block groups whose group
+descriptor structures can be stored in a single disk block. For ext4
+filesystems with 4 KB block size, a single metablock group partition
+includes 64 block groups, or 8 GiB of disk space. The metablock group
+feature moves the location of the group descriptors from the congested
+first block group of the whole filesystem into the first group of each
+metablock group itself. The backups are in the second and last group of
+each metablock group. This increases the 2^21 maximum block groups limit
+to the hard limit 2^32, allowing support for a 512PiB filesystem.
+
+The change in the filesystem format replaces the current scheme where
+the superblock is followed by a variable-length set of block group
+descriptors. Instead, the superblock and a single block group descriptor
+block is placed at the beginning of the first, second, and last block
+groups in a meta-block group. A meta-block group is a collection of
+block groups which can be described by a single block group descriptor
+block. Since the size of the block group descriptor structure is 32
+bytes, a meta-block group contains 32 block groups for filesystems with
+a 1KB block size, and 128 block groups for filesystems with a 4KB
+blocksize. Filesystems can either be created using this new block group
+descriptor layout, or existing filesystems can be resized on-line, and
+the field s\_first\_meta\_bg in the superblock will indicate the first
+block group using this new layout.
+
+Please see an important note about ``BLOCK_UNINIT`` in the section about
+block and inode bitmaps.
+
+Lazy Block Group Initialization
+-------------------------------
+
+A new feature for ext4 are three block group descriptor flags that
+enable mkfs to skip initializing other parts of the block group
+metadata. Specifically, the INODE\_UNINIT and BLOCK\_UNINIT flags mean
+that the inode and block bitmaps for that group can be calculated and
+therefore the on-disk bitmap blocks are not initialized. This is
+generally the case for an empty block group or a block group containing
+only fixed-location block group metadata. The INODE\_ZEROED flag means
+that the inode table has been initialized; mkfs will unset this flag and
+rely on the kernel to initialize the inode tables in the background.
+
+By not writing zeroes to the bitmaps and inode table, mkfs time is
+reduced considerably. Note the feature flag is RO\_COMPAT\_GDT\_CSUM,
+but the dumpe2fs output prints this as “uninit\_bg�. They are the same
+thing.
diff --git a/Documentation/filesystems/ext4/ondisk/blockmap.rst b/Documentation/filesystems/ext4/ondisk/blockmap.rst
new file mode 100644
index 000000000000..30e25750d88a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/blockmap.rst
@@ -0,0 +1,49 @@
+.. SPDX-License-Identifier: GPL-2.0
+
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| i.i\_block Offset   | Where It Points                                                                                                                                                                                                              |
++=====================+==============================================================================================================================================================================================================================+
+| 0 to 11             | Direct map to file blocks 0 to 11.                                                                                                                                                                                           |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| 12                  | Indirect block: (file blocks 12 to (``$block_size`` / 4) + 11, or 12 to 1035 if 4KiB blocks)                                                                                                                                 |
+|                     |                                                                                                                                                                                                                              |
+|                     | +------------------------------+--------------------------------------------------------------------+                                                                                                                        |
+|                     | | Indirect Block Offset        | Where It Points                                                    |                                                                                                                        |
+|                     | +==============================+====================================================================+                                                                                                                        |
+|                     | | 0 to (``$block_size`` / 4)   | Direct map to (``$block_size`` / 4) blocks (1024 if 4KiB blocks)   |                                                                                                                        |
+|                     | +------------------------------+--------------------------------------------------------------------+                                                                                                                        |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| 13                  | Double-indirect block: (file blocks ``$block_size``/4 + 12 to (``$block_size`` / 4) ^ 2 + (``$block_size`` / 4) + 11, or 1036 to 1049611 if 4KiB blocks)                                                                     |
+|                     |                                                                                                                                                                                                                              |
+|                     | +--------------------------------+---------------------------------------------------------------------------------------------------------+                                                                                 |
+|                     | | Double Indirect Block Offset   | Where It Points                                                                                         |                                                                                 |
+|                     | +================================+=========================================================================================================+                                                                                 |
+|                     | | 0 to (``$block_size`` / 4)     | Map to (``$block_size`` / 4) indirect blocks (1024 if 4KiB blocks)                                      |                                                                                 |
+|                     | |                                |                                                                                                         |                                                                                 |
+|                     | |                                | +------------------------------+--------------------------------------------------------------------+   |                                                                                 |
+|                     | |                                | | Indirect Block Offset        | Where It Points                                                    |   |                                                                                 |
+|                     | |                                | +==============================+====================================================================+   |                                                                                 |
+|                     | |                                | | 0 to (``$block_size`` / 4)   | Direct map to (``$block_size`` / 4) blocks (1024 if 4KiB blocks)   |   |                                                                                 |
+|                     | |                                | +------------------------------+--------------------------------------------------------------------+   |                                                                                 |
+|                     | +--------------------------------+---------------------------------------------------------------------------------------------------------+                                                                                 |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| 14                  | Triple-indirect block: (file blocks (``$block_size`` / 4) ^ 2 + (``$block_size`` / 4) + 12 to (``$block_size`` / 4) ^ 3 + (``$block_size`` / 4) ^ 2 + (``$block_size`` / 4) + 12, or 1049612 to 1074791436 if 4KiB blocks)   |
+|                     |                                                                                                                                                                                                                              |
+|                     | +--------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------+                                          |
+|                     | | Triple Indirect Block Offset   | Where It Points                                                                                                                                |                                          |
+|                     | +================================+================================================================================================================================================+                                          |
+|                     | | 0 to (``$block_size`` / 4)     | Map to (``$block_size`` / 4) double indirect blocks (1024 if 4KiB blocks)                                                                      |                                          |
+|                     | |                                |                                                                                                                                                |                                          |
+|                     | |                                | +--------------------------------+---------------------------------------------------------------------------------------------------------+   |                                          |
+|                     | |                                | | Double Indirect Block Offset   | Where It Points                                                                                         |   |                                          |
+|                     | |                                | +================================+=========================================================================================================+   |                                          |
+|                     | |                                | | 0 to (``$block_size`` / 4)     | Map to (``$block_size`` / 4) indirect blocks (1024 if 4KiB blocks)                                      |   |                                          |
+|                     | |                                | |                                |                                                                                                         |   |                                          |
+|                     | |                                | |                                | +------------------------------+--------------------------------------------------------------------+   |   |                                          |
+|                     | |                                | |                                | | Indirect Block Offset        | Where It Points                                                    |   |   |                                          |
+|                     | |                                | |                                | +==============================+====================================================================+   |   |                                          |
+|                     | |                                | |                                | | 0 to (``$block_size`` / 4)   | Direct map to (``$block_size`` / 4) blocks (1024 if 4KiB blocks)   |   |   |                                          |
+|                     | |                                | |                                | +------------------------------+--------------------------------------------------------------------+   |   |                                          |
+|                     | |                                | +--------------------------------+---------------------------------------------------------------------------------------------------------+   |                                          |
+|                     | +--------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------+                                          |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
diff --git a/Documentation/filesystems/ext4/ondisk/blocks.rst b/Documentation/filesystems/ext4/ondisk/blocks.rst
new file mode 100644
index 000000000000..73d4dc0f7bda
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/blocks.rst
@@ -0,0 +1,142 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Blocks
+------
+
+ext4 allocates storage space in units of “blocks�. A block is a group of
+sectors between 1KiB and 64KiB, and the number of sectors must be an
+integral power of 2. Blocks are in turn grouped into larger units called
+block groups. Block size is specified at mkfs time and typically is
+4KiB. You may experience mounting problems if block size is greater than
+page size (i.e. 64KiB blocks on a i386 which only has 4KiB memory
+pages). By default a filesystem can contain 2^32 blocks; if the '64bit'
+feature is enabled, then a filesystem can have 2^64 blocks.
+
+For 32-bit filesystems, limits are as follows:
+
+.. list-table::
+   :widths: 1 1 1 1 1
+   :header-rows: 1
+
+   * - Item
+     - 1KiB
+     - 2KiB
+     - 4KiB
+     - 64KiB
+   * - Blocks
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - Inodes
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - File System Size
+     - 4TiB
+     - 8TiB
+     - 16TiB
+     - 256PiB
+   * - Blocks Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Inodes Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Block Group Size
+     - 8MiB
+     - 32MiB
+     - 128MiB
+     - 32GiB
+   * - Blocks Per File, Extents
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - Blocks Per File, Block Maps
+     - 16,843,020
+     - 134,480,396
+     - 1,074,791,436
+     - 4,398,314,962,956 (really 2^32 due to field size limitations)
+   * - File Size, Extents
+     - 4TiB
+     - 8TiB
+     - 16TiB
+     - 256TiB
+   * - File Size, Block Maps
+     - 16GiB
+     - 256GiB
+     - 4TiB
+     - 256TiB
+
+For 64-bit filesystems, limits are as follows:
+
+.. list-table::
+   :widths: 1 1 1 1 1
+   :header-rows: 1
+
+   * - Item
+     - 1KiB
+     - 2KiB
+     - 4KiB
+     - 64KiB
+   * - Blocks
+     - 2^64
+     - 2^64
+     - 2^64
+     - 2^64
+   * - Inodes
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - File System Size
+     - 16ZiB
+     - 32ZiB
+     - 64ZiB
+     - 1YiB
+   * - Blocks Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Inodes Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Block Group Size
+     - 8MiB
+     - 32MiB
+     - 128MiB
+     - 32GiB
+   * - Blocks Per File, Extents
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - Blocks Per File, Block Maps
+     - 16,843,020
+     - 134,480,396
+     - 1,074,791,436
+     - 4,398,314,962,956 (really 2^32 due to field size limitations)
+   * - File Size, Extents
+     - 4TiB
+     - 8TiB
+     - 16TiB
+     - 256TiB
+   * - File Size, Block Maps
+     - 16GiB
+     - 256GiB
+     - 4TiB
+     - 256TiB
+
+Note: Files not using extents (i.e. files using block maps) must be
+placed within the first 2^32 blocks of a filesystem. Files with extents
+must be placed within the first 2^48 blocks of a filesystem. It's not
+clear what happens with larger filesystems.
diff --git a/Documentation/filesystems/ext4/ondisk/checksums.rst b/Documentation/filesystems/ext4/ondisk/checksums.rst
new file mode 100644
index 000000000000..9d6a793b2e03
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/checksums.rst
@@ -0,0 +1,73 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Checksums
+---------
+
+Starting in early 2012, metadata checksums were added to all major ext4
+and jbd2 data structures. The associated feature flag is metadata\_csum.
+The desired checksum algorithm is indicated in the superblock, though as
+of October 2012 the only supported algorithm is crc32c. Some data
+structures did not have space to fit a full 32-bit checksum, so only the
+lower 16 bits are stored. Enabling the 64bit feature increases the data
+structure size so that full 32-bit checksums can be stored for many data
+structures. However, existing 32-bit filesystems cannot be extended to
+enable 64bit mode, at least not without the experimental resize2fs
+patches to do so.
+
+Existing filesystems can have checksumming added by running
+``tune2fs -O metadata_csum`` against the underlying device. If tune2fs
+encounters directory blocks that lack sufficient empty space to add a
+checksum, it will request that you run ``e2fsck -D`` to have the
+directories rebuilt with checksums. This has the added benefit of
+removing slack space from the directory files and rebalancing the htree
+indexes. If you \_ignore\_ this step, your directories will not be
+protected by a checksum!
+
+The following table describes the data elements that go into each type
+of checksum. The checksum function is whatever the superblock describes
+(crc32c as of October 2013) unless noted otherwise.
+
+.. list-table::
+   :widths: 1 1 4
+   :header-rows: 1
+
+   * - Metadata
+     - Length
+     - Ingredients
+   * - Superblock
+     - \_\_le32
+     - The entire superblock up to the checksum field. The UUID lives inside
+       the superblock.
+   * - MMP
+     - \_\_le32
+     - UUID + the entire MMP block up to the checksum field.
+   * - Extended Attributes
+     - \_\_le32
+     - UUID + the entire extended attribute block. The checksum field is set to
+       zero.
+   * - Directory Entries
+     - \_\_le32
+     - UUID + inode number + inode generation + the directory block up to the
+       fake entry enclosing the checksum field.
+   * - HTREE Nodes
+     - \_\_le32
+     - UUID + inode number + inode generation + all valid extents + HTREE tail.
+       The checksum field is set to zero.
+   * - Extents
+     - \_\_le32
+     - UUID + inode number + inode generation + the entire extent block up to
+       the checksum field.
+   * - Bitmaps
+     - \_\_le32 or \_\_le16
+     - UUID + the entire bitmap. Checksums are stored in the group descriptor,
+       and truncated if the group descriptor size is 32 bytes (i.e. ^64bit)
+   * - Inodes
+     - \_\_le32
+     - UUID + inode number + inode generation + the entire inode. The checksum
+       field is set to zero. Each inode has its own checksum.
+   * - Group Descriptors
+     - \_\_le16
+     - If metadata\_csum, then UUID + group number + the entire descriptor;
+       else if gdt\_csum, then crc16(UUID + group number + the entire
+       descriptor). In all cases, only the lower 16 bits are stored.
+
diff --git a/Documentation/filesystems/ext4/ondisk/directory.rst b/Documentation/filesystems/ext4/ondisk/directory.rst
new file mode 100644
index 000000000000..8fcba68c2884
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/directory.rst
@@ -0,0 +1,426 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Directory Entries
+-----------------
+
+In an ext4 filesystem, a directory is more or less a flat file that maps
+an arbitrary byte string (usually ASCII) to an inode number on the
+filesystem. There can be many directory entries across the filesystem
+that reference the same inode number--these are known as hard links, and
+that is why hard links cannot reference files on other filesystems. As
+such, directory entries are found by reading the data block(s)
+associated with a directory file for the particular directory entry that
+is desired.
+
+Linear (Classic) Directories
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+By default, each directory lists its entries in an “almost-linear�
+array. I write “almost� because it's not a linear array in the memory
+sense because directory entries are not split across filesystem blocks.
+Therefore, it is more accurate to say that a directory is a series of
+data blocks and that each block contains a linear array of directory
+entries. The end of each per-block array is signified by reaching the
+end of the block; the last entry in the block has a record length that
+takes it all the way to the end of the block. The end of the entire
+directory is of course signified by reaching the end of the file. Unused
+directory entries are signified by inode = 0. By default the filesystem
+uses ``struct ext4_dir_entry_2`` for directory entries unless the
+“filetype� feature flag is not set, in which case it uses
+``struct ext4_dir_entry``.
+
+The original directory entry format is ``struct ext4_dir_entry``, which
+is at most 263 bytes long, though on disk you'll need to reference
+``dirent.rec_len`` to know for sure.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - inode
+     - Number of the inode that this directory entry points to.
+   * - 0x4
+     - \_\_le16
+     - rec\_len
+     - Length of this directory entry. Must be a multiple of 4.
+   * - 0x6
+     - \_\_le16
+     - name\_len
+     - Length of the file name.
+   * - 0x8
+     - char
+     - name[EXT4\_NAME\_LEN]
+     - File name.
+
+Since file names cannot be longer than 255 bytes, the new directory
+entry format shortens the rec\_len field and uses the space for a file
+type flag, probably to avoid having to load every inode during directory
+tree traversal. This format is ``ext4_dir_entry_2``, which is at most
+263 bytes long, though on disk you'll need to reference
+``dirent.rec_len`` to know for sure.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - inode
+     - Number of the inode that this directory entry points to.
+   * - 0x4
+     - \_\_le16
+     - rec\_len
+     - Length of this directory entry.
+   * - 0x6
+     - \_\_u8
+     - name\_len
+     - Length of the file name.
+   * - 0x7
+     - \_\_u8
+     - file\_type
+     - File type code, see ftype_ table below.
+   * - 0x8
+     - char
+     - name[EXT4\_NAME\_LEN]
+     - File name.
+
+.. _ftype:
+
+The directory file type is one of the following values:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0
+     - Unknown.
+   * - 0x1
+     - Regular file.
+   * - 0x2
+     - Directory.
+   * - 0x3
+     - Character device file.
+   * - 0x4
+     - Block device file.
+   * - 0x5
+     - FIFO.
+   * - 0x6
+     - Socket.
+   * - 0x7
+     - Symbolic link.
+
+In order to add checksums to these classic directory blocks, a phony
+``struct ext4_dir_entry`` is placed at the end of each leaf block to
+hold the checksum. The directory entry is 12 bytes long. The inode
+number and name\_len fields are set to zero to fool old software into
+ignoring an apparently empty directory entry, and the checksum is stored
+in the place where the name normally goes. The structure is
+``struct ext4_dir_entry_tail``:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - det\_reserved\_zero1
+     - Inode number, which must be zero.
+   * - 0x4
+     - \_\_le16
+     - det\_rec\_len
+     - Length of this directory entry, which must be 12.
+   * - 0x6
+     - \_\_u8
+     - det\_reserved\_zero2
+     - Length of the file name, which must be zero.
+   * - 0x7
+     - \_\_u8
+     - det\_reserved\_ft
+     - File type, which must be 0xDE.
+   * - 0x8
+     - \_\_le32
+     - det\_checksum
+     - Directory leaf block checksum.
+
+The leaf directory block checksum is calculated against the FS UUID, the
+directory's inode number, the directory's inode generation number, and
+the entire directory entry block up to (but not including) the fake
+directory entry.
+
+Hash Tree Directories
+~~~~~~~~~~~~~~~~~~~~~
+
+A linear array of directory entries isn't great for performance, so a
+new feature was added to ext3 to provide a faster (but peculiar)
+balanced tree keyed off a hash of the directory entry name. If the
+EXT4\_INDEX\_FL (0x1000) flag is set in the inode, this directory uses a
+hashed btree (htree) to organize and find directory entries. For
+backwards read-only compatibility with ext2, this tree is actually
+hidden inside the directory file, masquerading as “empty� directory data
+blocks! It was stated previously that the end of the linear directory
+entry table was signified with an entry pointing to inode 0; this is
+(ab)used to fool the old linear-scan algorithm into thinking that the
+rest of the directory block is empty so that it moves on.
+
+The root of the tree always lives in the first data block of the
+directory. By ext2 custom, the '.' and '..' entries must appear at the
+beginning of this first block, so they are put here as two
+``struct ext4_dir_entry_2``\ s and not stored in the tree. The rest of
+the root node contains metadata about the tree and finally a hash->block
+map to find nodes that are lower in the htree. If
+``dx_root.info.indirect_levels`` is non-zero then the htree has two
+levels; the data block pointed to by the root node's map is an interior
+node, which is indexed by a minor hash. Interior nodes in this tree
+contains a zeroed out ``struct ext4_dir_entry_2`` followed by a
+minor\_hash->block map to find leafe nodes. Leaf nodes contain a linear
+array of all ``struct ext4_dir_entry_2``; all of these entries
+(presumably) hash to the same value. If there is an overflow, the
+entries simply overflow into the next leaf node, and the
+least-significant bit of the hash (in the interior node map) that gets
+us to this next leaf node is set.
+
+To traverse the directory as a htree, the code calculates the hash of
+the desired file name and uses it to find the corresponding block
+number. If the tree is flat, the block is a linear array of directory
+entries that can be searched; otherwise, the minor hash of the file name
+is computed and used against this second block to find the corresponding
+third block number. That third block number will be a linear array of
+directory entries.
+
+To traverse the directory as a linear array (such as the old code does),
+the code simply reads every data block in the directory. The blocks used
+for the htree will appear to have no entries (aside from '.' and '..')
+and so only the leaf nodes will appear to have any interesting content.
+
+The root of the htree is in ``struct dx_root``, which is the full length
+of a data block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - dot.inode
+     - inode number of this directory.
+   * - 0x4
+     - \_\_le16
+     - dot.rec\_len
+     - Length of this record, 12.
+   * - 0x6
+     - u8
+     - dot.name\_len
+     - Length of the name, 1.
+   * - 0x7
+     - u8
+     - dot.file\_type
+     - File type of this entry, 0x2 (directory) (if the feature flag is set).
+   * - 0x8
+     - char
+     - dot.name[4]
+     - “.\\0\\0\\0�
+   * - 0xC
+     - \_\_le32
+     - dotdot.inode
+     - inode number of parent directory.
+   * - 0x10
+     - \_\_le16
+     - dotdot.rec\_len
+     - block\_size - 12. The record length is long enough to cover all htree
+       data.
+   * - 0x12
+     - u8
+     - dotdot.name\_len
+     - Length of the name, 2.
+   * - 0x13
+     - u8
+     - dotdot.file\_type
+     - File type of this entry, 0x2 (directory) (if the feature flag is set).
+   * - 0x14
+     - char
+     - dotdot\_name[4]
+     - “..\\0\\0�
+   * - 0x18
+     - \_\_le32
+     - struct dx\_root\_info.reserved\_zero
+     - Zero.
+   * - 0x1C
+     - u8
+     - struct dx\_root\_info.hash\_version
+     - Hash type, see dirhash_ table below.
+   * - 0x1D
+     - u8
+     - struct dx\_root\_info.info\_length
+     - Length of the tree information, 0x8.
+   * - 0x1E
+     - u8
+     - struct dx\_root\_info.indirect\_levels
+     - Depth of the htree. Cannot be larger than 3 if the INCOMPAT\_LARGEDIR
+       feature is set; cannot be larger than 2 otherwise.
+   * - 0x1F
+     - u8
+     - struct dx\_root\_info.unused\_flags
+     -
+   * - 0x20
+     - \_\_le16
+     - limit
+     - Maximum number of dx\_entries that can follow this header, plus 1 for
+       the header itself.
+   * - 0x22
+     - \_\_le16
+     - count
+     - Actual number of dx\_entries that follow this header, plus 1 for the
+       header itself.
+   * - 0x24
+     - \_\_le32
+     - block
+     - The block number (within the directory file) that goes with hash=0.
+   * - 0x28
+     - struct dx\_entry
+     - entries[0]
+     - As many 8-byte ``struct dx_entry`` as fits in the rest of the data block.
+
+.. _dirhash:
+
+The directory hash is one of the following values:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0
+     - Legacy.
+   * - 0x1
+     - Half MD4.
+   * - 0x2
+     - Tea.
+   * - 0x3
+     - Legacy, unsigned.
+   * - 0x4
+     - Half MD4, unsigned.
+   * - 0x5
+     - Tea, unsigned.
+
+Interior nodes of an htree are recorded as ``struct dx_node``, which is
+also the full length of a data block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - fake.inode
+     - Zero, to make it look like this entry is not in use.
+   * - 0x4
+     - \_\_le16
+     - fake.rec\_len
+     - The size of the block, in order to hide all of the dx\_node data.
+   * - 0x6
+     - u8
+     - name\_len
+     - Zero. There is no name for this “unused� directory entry.
+   * - 0x7
+     - u8
+     - file\_type
+     - Zero. There is no file type for this “unused� directory entry.
+   * - 0x8
+     - \_\_le16
+     - limit
+     - Maximum number of dx\_entries that can follow this header, plus 1 for
+       the header itself.
+   * - 0xA
+     - \_\_le16
+     - count
+     - Actual number of dx\_entries that follow this header, plus 1 for the
+       header itself.
+   * - 0xE
+     - \_\_le32
+     - block
+     - The block number (within the directory file) that goes with the lowest
+       hash value of this block. This value is stored in the parent block.
+   * - 0x12
+     - struct dx\_entry
+     - entries[0]
+     - As many 8-byte ``struct dx_entry`` as fits in the rest of the data block.
+
+The hash maps that exist in both ``struct dx_root`` and
+``struct dx_node`` are recorded as ``struct dx_entry``, which is 8 bytes
+long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - hash
+     - Hash code.
+   * - 0x4
+     - \_\_le32
+     - block
+     - Block number (within the directory file, not filesystem blocks) of the
+       next node in the htree.
+
+(If you think this is all quite clever and peculiar, so does the
+author.)
+
+If metadata checksums are enabled, the last 8 bytes of the directory
+block (precisely the length of one dx\_entry) are used to store a
+``struct dx_tail``, which contains the checksum. The ``limit`` and
+``count`` entries in the dx\_root/dx\_node structures are adjusted as
+necessary to fit the dx\_tail into the block. If there is no space for
+the dx\_tail, the user is notified to run e2fsck -D to rebuild the
+directory index (which will ensure that there's space for the checksum.
+The dx\_tail structure is 8 bytes long and looks like this:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - u32
+     - dt\_reserved
+     - Zero.
+   * - 0x4
+     - \_\_le32
+     - dt\_checksum
+     - Checksum of the htree directory block.
+
+The checksum is calculated against the FS UUID, the htree index header
+(dx\_root or dx\_node), all of the htree indices (dx\_entry) that are in
+use, and the tail block (dx\_tail).
diff --git a/Documentation/filesystems/ext4/ondisk/dynamic.rst b/Documentation/filesystems/ext4/ondisk/dynamic.rst
new file mode 100644
index 000000000000..bb0c84333341
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/dynamic.rst
@@ -0,0 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Dynamic Structures
+==================
+
+Dynamic metadata are created on the fly when files and blocks are
+allocated to files.
+
+.. include:: inodes.rst
+.. include:: ifork.rst
+.. include:: directory.rst
+.. include:: attributes.rst
diff --git a/Documentation/filesystems/ext4/ondisk/eainode.rst b/Documentation/filesystems/ext4/ondisk/eainode.rst
new file mode 100644
index 000000000000..ecc0d01a0a72
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/eainode.rst
@@ -0,0 +1,18 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Large Extended Attribute Values
+-------------------------------
+
+To enable ext4 to store extended attribute values that do not fit in the
+inode or in the single extended attribute block attached to an inode,
+the EA\_INODE feature allows us to store the value in the data blocks of
+a regular file inode. This “EA inode� is linked only from the extended
+attribute name index and must not appear in a directory entry. The
+inode's i\_atime field is used to store a checksum of the xattr value;
+and i\_ctime/i\_version store a 64-bit reference count, which enables
+sharing of large xattr values between multiple owning inodes. For
+backward compatibility with older versions of this feature, the
+i\_mtime/i\_generation *may* store a back-reference to the inode number
+and i\_generation of the **one** owning inode (in cases where the EA
+inode is not referenced by multiple inodes) to verify that the EA inode
+is the correct one being accessed.
diff --git a/Documentation/filesystems/ext4/ondisk/globals.rst b/Documentation/filesystems/ext4/ondisk/globals.rst
new file mode 100644
index 000000000000..368bf7662b96
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/globals.rst
@@ -0,0 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Global Structures
+=================
+
+The filesystem is sharded into a number of block groups, each of which
+have static metadata at fixed locations.
+
+.. include:: super.rst
+.. include:: group_descr.rst
+.. include:: bitmaps.rst
+.. include:: mmp.rst
+.. include:: journal.rst
diff --git a/Documentation/filesystems/ext4/ondisk/group_descr.rst b/Documentation/filesystems/ext4/ondisk/group_descr.rst
new file mode 100644
index 000000000000..759827e5d2cf
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/group_descr.rst
@@ -0,0 +1,170 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Block Group Descriptors
+-----------------------
+
+Each block group on the filesystem has one of these descriptors
+associated with it. As noted in the Layout section above, the group
+descriptors (if present) are the second item in the block group. The
+standard configuration is for each block group to contain a full copy of
+the block group descriptor table unless the sparse\_super feature flag
+is set.
+
+Notice how the group descriptor records the location of both bitmaps and
+the inode table (i.e. they can float). This means that within a block
+group, the only data structures with fixed locations are the superblock
+and the group descriptor table. The flex\_bg mechanism uses this
+property to group several block groups into a flex group and lay out all
+of the groups' bitmaps and inode tables into one long run in the first
+group of the flex group.
+
+If the meta\_bg feature flag is set, then several block groups are
+grouped together into a meta group. Note that in the meta\_bg case,
+however, the first and last two block groups within the larger meta
+group contain only group descriptors for the groups inside the meta
+group.
+
+flex\_bg and meta\_bg do not appear to be mutually exclusive features.
+
+In ext2, ext3, and ext4 (when the 64bit feature is not enabled), the
+block group descriptor was only 32 bytes long and therefore ends at
+bg\_checksum. On an ext4 filesystem with the 64bit feature enabled, the
+block group descriptor expands to at least the 64 bytes described below;
+the size is stored in the superblock.
+
+If gdt\_csum is set and metadata\_csum is not set, the block group
+checksum is the crc16 of the FS UUID, the group number, and the group
+descriptor structure. If metadata\_csum is set, then the block group
+checksum is the lower 16 bits of the checksum of the FS UUID, the group
+number, and the group descriptor structure. Both block and inode bitmap
+checksums are calculated against the FS UUID, the group number, and the
+entire bitmap.
+
+The block group descriptor is laid out in ``struct ext4_group_desc``.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - bg\_block\_bitmap\_lo
+     - Lower 32-bits of location of block bitmap.
+   * - 0x4
+     - \_\_le32
+     - bg\_inode\_bitmap\_lo
+     - Lower 32-bits of location of inode bitmap.
+   * - 0x8
+     - \_\_le32
+     - bg\_inode\_table\_lo
+     - Lower 32-bits of location of inode table.
+   * - 0xC
+     - \_\_le16
+     - bg\_free\_blocks\_count\_lo
+     - Lower 16-bits of free block count.
+   * - 0xE
+     - \_\_le16
+     - bg\_free\_inodes\_count\_lo
+     - Lower 16-bits of free inode count.
+   * - 0x10
+     - \_\_le16
+     - bg\_used\_dirs\_count\_lo
+     - Lower 16-bits of directory count.
+   * - 0x12
+     - \_\_le16
+     - bg\_flags
+     - Block group flags. See the bgflags_ table below.
+   * - 0x14
+     - \_\_le32
+     - bg\_exclude\_bitmap\_lo
+     - Lower 32-bits of location of snapshot exclusion bitmap.
+   * - 0x18
+     - \_\_le16
+     - bg\_block\_bitmap\_csum\_lo
+     - Lower 16-bits of the block bitmap checksum.
+   * - 0x1A
+     - \_\_le16
+     - bg\_inode\_bitmap\_csum\_lo
+     - Lower 16-bits of the inode bitmap checksum.
+   * - 0x1C
+     - \_\_le16
+     - bg\_itable\_unused\_lo
+     - Lower 16-bits of unused inode count. If set, we needn't scan past the
+       ``(sb.s_inodes_per_group - gdt.bg_itable_unused)``\ th entry in the
+       inode table for this group.
+   * - 0x1E
+     - \_\_le16
+     - bg\_checksum
+     - Group descriptor checksum; crc16(sb\_uuid+group+desc) if the
+       RO\_COMPAT\_GDT\_CSUM feature is set, or crc32c(sb\_uuid+group\_desc) &
+       0xFFFF if the RO\_COMPAT\_METADATA\_CSUM feature is set.
+   * -
+     -
+     -
+     - These fields only exist if the 64bit feature is enabled and s_desc_size
+       > 32.
+   * - 0x20
+     - \_\_le32
+     - bg\_block\_bitmap\_hi
+     - Upper 32-bits of location of block bitmap.
+   * - 0x24
+     - \_\_le32
+     - bg\_inode\_bitmap\_hi
+     - Upper 32-bits of location of inodes bitmap.
+   * - 0x28
+     - \_\_le32
+     - bg\_inode\_table\_hi
+     - Upper 32-bits of location of inodes table.
+   * - 0x2C
+     - \_\_le16
+     - bg\_free\_blocks\_count\_hi
+     - Upper 16-bits of free block count.
+   * - 0x2E
+     - \_\_le16
+     - bg\_free\_inodes\_count\_hi
+     - Upper 16-bits of free inode count.
+   * - 0x30
+     - \_\_le16
+     - bg\_used\_dirs\_count\_hi
+     - Upper 16-bits of directory count.
+   * - 0x32
+     - \_\_le16
+     - bg\_itable\_unused\_hi
+     - Upper 16-bits of unused inode count.
+   * - 0x34
+     - \_\_le32
+     - bg\_exclude\_bitmap\_hi
+     - Upper 32-bits of location of snapshot exclusion bitmap.
+   * - 0x38
+     - \_\_le16
+     - bg\_block\_bitmap\_csum\_hi
+     - Upper 16-bits of the block bitmap checksum.
+   * - 0x3A
+     - \_\_le16
+     - bg\_inode\_bitmap\_csum\_hi
+     - Upper 16-bits of the inode bitmap checksum.
+   * - 0x3C
+     - \_\_u32
+     - bg\_reserved
+     - Padding to 64 bytes.
+
+.. _bgflags:
+
+Block group flags can be any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - inode table and bitmap are not initialized (EXT4\_BG\_INODE\_UNINIT).
+   * - 0x2
+     - block bitmap is not initialized (EXT4\_BG\_BLOCK\_UNINIT).
+   * - 0x4
+     - inode table is zeroed (EXT4\_BG\_INODE\_ZEROED).
diff --git a/Documentation/filesystems/ext4/ondisk/ifork.rst b/Documentation/filesystems/ext4/ondisk/ifork.rst
new file mode 100644
index 000000000000..5dbe3b2b121a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/ifork.rst
@@ -0,0 +1,194 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+The Contents of inode.i\_block
+------------------------------
+
+Depending on the type of file an inode describes, the 60 bytes of
+storage in ``inode.i_block`` can be used in different ways. In general,
+regular files and directories will use it for file block indexing
+information, and special files will use it for special purposes.
+
+Symbolic Links
+~~~~~~~~~~~~~~
+
+The target of a symbolic link will be stored in this field if the target
+string is less than 60 bytes long. Otherwise, either extents or block
+maps will be used to allocate data blocks to store the link target.
+
+Direct/Indirect Block Addressing
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In ext2/3, file block numbers were mapped to logical block numbers by
+means of an (up to) three level 1-1 block map. To find the logical block
+that stores a particular file block, the code would navigate through
+this increasingly complicated structure. Notice that there is neither a
+magic number nor a checksum to provide any level of confidence that the
+block isn't full of garbage.
+
+.. ifconfig:: builder != 'latex'
+
+   .. include:: blockmap.rst
+
+.. ifconfig:: builder == 'latex'
+
+   [Table omitted because LaTeX doesn't support nested tables.]
+
+Note that with this block mapping scheme, it is necessary to fill out a
+lot of mapping data even for a large contiguous file! This inefficiency
+led to the creation of the extent mapping scheme, discussed below.
+
+Notice also that a file using this mapping scheme cannot be placed
+higher than 2^32 blocks.
+
+Extent Tree
+~~~~~~~~~~~
+
+In ext4, the file to logical block map has been replaced with an extent
+tree. Under the old scheme, allocating a contiguous run of 1,000 blocks
+requires an indirect block to map all 1,000 entries; with extents, the
+mapping is reduced to a single ``struct ext4_extent`` with
+``ee_len = 1000``. If flex\_bg is enabled, it is possible to allocate
+very large files with a single extent, at a considerable reduction in
+metadata block use, and some improvement in disk efficiency. The inode
+must have the extents flag (0x80000) flag set for this feature to be in
+use.
+
+Extents are arranged as a tree. Each node of the tree begins with a
+``struct ext4_extent_header``. If the node is an interior node
+(``eh.eh_depth`` > 0), the header is followed by ``eh.eh_entries``
+instances of ``struct ext4_extent_idx``; each of these index entries
+points to a block containing more nodes in the extent tree. If the node
+is a leaf node (``eh.eh_depth == 0``), then the header is followed by
+``eh.eh_entries`` instances of ``struct ext4_extent``; these instances
+point to the file's data blocks. The root node of the extent tree is
+stored in ``inode.i_block``, which allows for the first four extents to
+be recorded without the use of extra metadata blocks.
+
+The extent tree header is recorded in ``struct ext4_extent_header``,
+which is 12 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - eh\_magic
+     - Magic number, 0xF30A.
+   * - 0x2
+     - \_\_le16
+     - eh\_entries
+     - Number of valid entries following the header.
+   * - 0x4
+     - \_\_le16
+     - eh\_max
+     - Maximum number of entries that could follow the header.
+   * - 0x6
+     - \_\_le16
+     - eh\_depth
+     - Depth of this extent node in the extent tree. 0 = this extent node
+       points to data blocks; otherwise, this extent node points to other
+       extent nodes. The extent tree can be at most 5 levels deep: a logical
+       block number can be at most ``2^32``, and the smallest ``n`` that
+       satisfies ``4*(((blocksize - 12)/12)^n) >= 2^32`` is 5.
+   * - 0x8
+     - \_\_le32
+     - eh\_generation
+     - Generation of the tree. (Used by Lustre, but not standard ext4).
+
+Internal nodes of the extent tree, also known as index nodes, are
+recorded as ``struct ext4_extent_idx``, and are 12 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - ei\_block
+     - This index node covers file blocks from 'block' onward.
+   * - 0x4
+     - \_\_le32
+     - ei\_leaf\_lo
+     - Lower 32-bits of the block number of the extent node that is the next
+       level lower in the tree. The tree node pointed to can be either another
+       internal node or a leaf node, described below.
+   * - 0x8
+     - \_\_le16
+     - ei\_leaf\_hi
+     - Upper 16-bits of the previous field.
+   * - 0xA
+     - \_\_u16
+     - ei\_unused
+     -
+
+Leaf nodes of the extent tree are recorded as ``struct ext4_extent``,
+and are also 12 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - ee\_block
+     - First file block number that this extent covers.
+   * - 0x4
+     - \_\_le16
+     - ee\_len
+     - Number of blocks covered by extent. If the value of this field is <=
+       32768, the extent is initialized. If the value of the field is > 32768,
+       the extent is uninitialized and the actual extent length is ``ee_len`` -
+       32768. Therefore, the maximum length of a initialized extent is 32768
+       blocks, and the maximum length of an uninitialized extent is 32767.
+   * - 0x6
+     - \_\_le16
+     - ee\_start\_hi
+     - Upper 16-bits of the block number to which this extent points.
+   * - 0x8
+     - \_\_le32
+     - ee\_start\_lo
+     - Lower 32-bits of the block number to which this extent points.
+
+Prior to the introduction of metadata checksums, the extent header +
+extent entries always left at least 4 bytes of unallocated space at the
+end of each extent tree data block (because (2^x % 12) >= 4). Therefore,
+the 32-bit checksum is inserted into this space. The 4 extents in the
+inode do not need checksumming, since the inode is already checksummed.
+The checksum is calculated against the FS UUID, the inode number, the
+inode generation, and the entire extent block leading up to (but not
+including) the checksum itself.
+
+``struct ext4_extent_tail`` is 4 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - eb\_checksum
+     - Checksum of the extent block, crc32c(uuid+inum+igeneration+extentblock)
+
+Inline Data
+~~~~~~~~~~~
+
+If the inline data feature is enabled for the filesystem and the flag is
+set for the inode, it is possible that the first 60 bytes of the file
+data are stored here.
diff --git a/Documentation/filesystems/ext4/ondisk/index.rst b/Documentation/filesystems/ext4/ondisk/index.rst
new file mode 100644
index 000000000000..f7d082c3a435
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/index.rst
@@ -0,0 +1,9 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================
+Data Structures and Algorithms
+==============================
+.. include:: about.rst
+.. include:: overview.rst
+.. include:: globals.rst
+.. include:: dynamic.rst
diff --git a/Documentation/filesystems/ext4/ondisk/inlinedata.rst b/Documentation/filesystems/ext4/ondisk/inlinedata.rst
new file mode 100644
index 000000000000..d1075178ce0b
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/inlinedata.rst
@@ -0,0 +1,37 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Inline Data
+-----------
+
+The inline data feature was designed to handle the case that a file's
+data is so tiny that it readily fits inside the inode, which
+(theoretically) reduces disk block consumption and reduces seeks. If the
+file is smaller than 60 bytes, then the data are stored inline in
+``inode.i_block``. If the rest of the file would fit inside the extended
+attribute space, then it might be found as an extended attribute
+“system.data� within the inode body (“ibody EA�). This of course
+constrains the amount of extended attributes one can attach to an inode.
+If the data size increases beyond i\_block + ibody EA, a regular block
+is allocated and the contents moved to that block.
+
+Pending a change to compact the extended attribute key used to store
+inline data, one ought to be able to store 160 bytes of data in a
+256-byte inode (as of June 2015, when i\_extra\_isize is 28). Prior to
+that, the limit was 156 bytes due to inefficient use of inode space.
+
+The inline data feature requires the presence of an extended attribute
+for “system.data�, even if the attribute value is zero length.
+
+Inline Directories
+~~~~~~~~~~~~~~~~~~
+
+The first four bytes of i\_block are the inode number of the parent
+directory. Following that is a 56-byte space for an array of directory
+entries; see ``struct ext4_dir_entry``. If there is a “system.data�
+attribute in the inode body, the EA value is an array of
+``struct ext4_dir_entry`` as well. Note that for inline directories, the
+i\_block and EA space are treated as separate dirent blocks; directory
+entries cannot span the two.
+
+Inline directory entries are not checksummed, as the inode checksum
+should protect all inline data contents.
diff --git a/Documentation/filesystems/ext4/ondisk/inodes.rst b/Documentation/filesystems/ext4/ondisk/inodes.rst
new file mode 100644
index 000000000000..655ce898f3f5
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/inodes.rst
@@ -0,0 +1,575 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Index Nodes
+-----------
+
+In a regular UNIX filesystem, the inode stores all the metadata
+pertaining to the file (time stamps, block maps, extended attributes,
+etc), not the directory entry. To find the information associated with a
+file, one must traverse the directory files to find the directory entry
+associated with a file, then load the inode to find the metadata for
+that file. ext4 appears to cheat (for performance reasons) a little bit
+by storing a copy of the file type (normally stored in the inode) in the
+directory entry. (Compare all this to FAT, which stores all the file
+information directly in the directory entry, but does not support hard
+links and is in general more seek-happy than ext4 due to its simpler
+block allocator and extensive use of linked lists.)
+
+The inode table is a linear array of ``struct ext4_inode``. The table is
+sized to have enough blocks to store at least
+``sb.s_inode_size * sb.s_inodes_per_group`` bytes. The number of the
+block group containing an inode can be calculated as
+``(inode_number - 1) / sb.s_inodes_per_group``, and the offset into the
+group's table is ``(inode_number - 1) % sb.s_inodes_per_group``. There
+is no inode 0.
+
+The inode checksum is calculated against the FS UUID, the inode number,
+and the inode structure itself.
+
+The inode table entry is laid out in ``struct ext4_inode``.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - i\_mode
+     - File mode. See the table i_mode_ below.
+   * - 0x2
+     - \_\_le16
+     - i\_uid
+     - Lower 16-bits of Owner UID.
+   * - 0x4
+     - \_\_le32
+     - i\_size\_lo
+     - Lower 32-bits of size in bytes.
+   * - 0x8
+     - \_\_le32
+     - i\_atime
+     - Last access time, in seconds since the epoch. However, if the EA\_INODE
+       inode flag is set, this inode stores an extended attribute value and
+       this field contains the checksum of the value.
+   * - 0xC
+     - \_\_le32
+     - i\_ctime
+     - Last inode change time, in seconds since the epoch. However, if the
+       EA\_INODE inode flag is set, this inode stores an extended attribute
+       value and this field contains the lower 32 bits of the attribute value's
+       reference count.
+   * - 0x10
+     - \_\_le32
+     - i\_mtime
+     - Last data modification time, in seconds since the epoch. However, if the
+       EA\_INODE inode flag is set, this inode stores an extended attribute
+       value and this field contains the number of the inode that owns the
+       extended attribute.
+   * - 0x14
+     - \_\_le32
+     - i\_dtime
+     - Deletion Time, in seconds since the epoch.
+   * - 0x18
+     - \_\_le16
+     - i\_gid
+     - Lower 16-bits of GID.
+   * - 0x1A
+     - \_\_le16
+     - i\_links\_count
+     - Hard link count. Normally, ext4 does not permit an inode to have more
+       than 65,000 hard links. This applies to files as well as directories,
+       which means that there cannot be more than 64,998 subdirectories in a
+       directory (each subdirectory's '..' entry counts as a hard link, as does
+       the '.' entry in the directory itself). With the DIR\_NLINK feature
+       enabled, ext4 supports more than 64,998 subdirectories by setting this
+       field to 1 to indicate that the number of hard links is not known.
+   * - 0x1C
+     - \_\_le32
+     - i\_blocks\_lo
+     - Lower 32-bits of “block� count. If the huge\_file feature flag is not
+       set on the filesystem, the file consumes ``i_blocks_lo`` 512-byte blocks
+       on disk. If huge\_file is set and EXT4\_HUGE\_FILE\_FL is NOT set in
+       ``inode.i_flags``, then the file consumes ``i_blocks_lo + (i_blocks_hi
+       << 32)`` 512-byte blocks on disk. If huge\_file is set and
+       EXT4\_HUGE\_FILE\_FL IS set in ``inode.i_flags``, then this file
+       consumes (``i_blocks_lo + i_blocks_hi`` << 32) filesystem blocks on
+       disk.
+   * - 0x20
+     - \_\_le32
+     - i\_flags
+     - Inode flags. See the table i_flags_ below.
+   * - 0x24
+     - 4 bytes
+     - i\_osd1
+     - See the table i_osd1_ for more details.
+   * - 0x28
+     - 60 bytes
+     - i\_block[EXT4\_N\_BLOCKS=15]
+     - Block map or extent tree. See the section “The Contents of inode.i\_block�.
+   * - 0x64
+     - \_\_le32
+     - i\_generation
+     - File version (for NFS).
+   * - 0x68
+     - \_\_le32
+     - i\_file\_acl\_lo
+     - Lower 32-bits of extended attribute block. ACLs are of course one of
+       many possible extended attributes; I think the name of this field is a
+       result of the first use of extended attributes being for ACLs.
+   * - 0x6C
+     - \_\_le32
+     - i\_size\_high / i\_dir\_acl
+     - Upper 32-bits of file/directory size. In ext2/3 this field was named
+       i\_dir\_acl, though it was usually set to zero and never used.
+   * - 0x70
+     - \_\_le32
+     - i\_obso\_faddr
+     - (Obsolete) fragment address.
+   * - 0x74
+     - 12 bytes
+     - i\_osd2
+     - See the table i_osd2_ for more details.
+   * - 0x80
+     - \_\_le16
+     - i\_extra\_isize
+     - Size of this inode - 128. Alternately, the size of the extended inode
+       fields beyond the original ext2 inode, including this field.
+   * - 0x82
+     - \_\_le16
+     - i\_checksum\_hi
+     - Upper 16-bits of the inode checksum.
+   * - 0x84
+     - \_\_le32
+     - i\_ctime\_extra
+     - Extra change time bits. This provides sub-second precision. See Inode
+       Timestamps section.
+   * - 0x88
+     - \_\_le32
+     - i\_mtime\_extra
+     - Extra modification time bits. This provides sub-second precision.
+   * - 0x8C
+     - \_\_le32
+     - i\_atime\_extra
+     - Extra access time bits. This provides sub-second precision.
+   * - 0x90
+     - \_\_le32
+     - i\_crtime
+     - File creation time, in seconds since the epoch.
+   * - 0x94
+     - \_\_le32
+     - i\_crtime\_extra
+     - Extra file creation time bits. This provides sub-second precision.
+   * - 0x98
+     - \_\_le32
+     - i\_version\_hi
+     - Upper 32-bits for version number.
+   * - 0x9C
+     - \_\_le32
+     - i\_projid
+     - Project ID.
+
+.. _i_mode:
+
+The ``i_mode`` value is a combination of the following flags:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - S\_IXOTH (Others may execute)
+   * - 0x2
+     - S\_IWOTH (Others may write)
+   * - 0x4
+     - S\_IROTH (Others may read)
+   * - 0x8
+     - S\_IXGRP (Group members may execute)
+   * - 0x10
+     - S\_IWGRP (Group members may write)
+   * - 0x20
+     - S\_IRGRP (Group members may read)
+   * - 0x40
+     - S\_IXUSR (Owner may execute)
+   * - 0x80
+     - S\_IWUSR (Owner may write)
+   * - 0x100
+     - S\_IRUSR (Owner may read)
+   * - 0x200
+     - S\_ISVTX (Sticky bit)
+   * - 0x400
+     - S\_ISGID (Set GID)
+   * - 0x800
+     - S\_ISUID (Set UID)
+   * -
+     - These are mutually-exclusive file types:
+   * - 0x1000
+     - S\_IFIFO (FIFO)
+   * - 0x2000
+     - S\_IFCHR (Character device)
+   * - 0x4000
+     - S\_IFDIR (Directory)
+   * - 0x6000
+     - S\_IFBLK (Block device)
+   * - 0x8000
+     - S\_IFREG (Regular file)
+   * - 0xA000
+     - S\_IFLNK (Symbolic link)
+   * - 0xC000
+     - S\_IFSOCK (Socket)
+
+.. _i_flags:
+
+The ``i_flags`` field is a combination of these values:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - This file requires secure deletion (EXT4\_SECRM\_FL). (not implemented)
+   * - 0x2
+     - This file should be preserved, should undeletion be desired
+       (EXT4\_UNRM\_FL). (not implemented)
+   * - 0x4
+     - File is compressed (EXT4\_COMPR\_FL). (not really implemented)
+   * - 0x8
+     - All writes to the file must be synchronous (EXT4\_SYNC\_FL).
+   * - 0x10
+     - File is immutable (EXT4\_IMMUTABLE\_FL).
+   * - 0x20
+     - File can only be appended (EXT4\_APPEND\_FL).
+   * - 0x40
+     - The dump(1) utility should not dump this file (EXT4\_NODUMP\_FL).
+   * - 0x80
+     - Do not update access time (EXT4\_NOATIME\_FL).
+   * - 0x100
+     - Dirty compressed file (EXT4\_DIRTY\_FL). (not used)
+   * - 0x200
+     - File has one or more compressed clusters (EXT4\_COMPRBLK\_FL). (not used)
+   * - 0x400
+     - Do not compress file (EXT4\_NOCOMPR\_FL). (not used)
+   * - 0x800
+     - Encrypted inode (EXT4\_ENCRYPT\_FL). This bit value previously was
+       EXT4\_ECOMPR\_FL (compression error), which was never used.
+   * - 0x1000
+     - Directory has hashed indexes (EXT4\_INDEX\_FL).
+   * - 0x2000
+     - AFS magic directory (EXT4\_IMAGIC\_FL).
+   * - 0x4000
+     - File data must always be written through the journal
+       (EXT4\_JOURNAL\_DATA\_FL).
+   * - 0x8000
+     - File tail should not be merged (EXT4\_NOTAIL\_FL). (not used by ext4)
+   * - 0x10000
+     - All directory entry data should be written synchronously (see
+       ``dirsync``) (EXT4\_DIRSYNC\_FL).
+   * - 0x20000
+     - Top of directory hierarchy (EXT4\_TOPDIR\_FL).
+   * - 0x40000
+     - This is a huge file (EXT4\_HUGE\_FILE\_FL).
+   * - 0x80000
+     - Inode uses extents (EXT4\_EXTENTS\_FL).
+   * - 0x200000
+     - Inode stores a large extended attribute value in its data blocks
+       (EXT4\_EA\_INODE\_FL).
+   * - 0x400000
+     - This file has blocks allocated past EOF (EXT4\_EOFBLOCKS\_FL).
+       (deprecated)
+   * - 0x01000000
+     - Inode is a snapshot (``EXT4_SNAPFILE_FL``). (not in mainline)
+   * - 0x04000000
+     - Snapshot is being deleted (``EXT4_SNAPFILE_DELETED_FL``). (not in
+       mainline)
+   * - 0x08000000
+     - Snapshot shrink has completed (``EXT4_SNAPFILE_SHRUNK_FL``). (not in
+       mainline)
+   * - 0x10000000
+     - Inode has inline data (EXT4\_INLINE\_DATA\_FL).
+   * - 0x20000000
+     - Create children with the same project ID (EXT4\_PROJINHERIT\_FL).
+   * - 0x80000000
+     - Reserved for ext4 library (EXT4\_RESERVED\_FL).
+   * -
+     - Aggregate flags:
+   * - 0x4BDFFF
+     - User-visible flags.
+   * - 0x4B80FF
+     - User-modifiable flags. Note that while EXT4\_JOURNAL\_DATA\_FL and
+       EXT4\_EXTENTS\_FL can be set with setattr, they are not in the kernel's
+       EXT4\_FL\_USER\_MODIFIABLE mask, since it needs to handle the setting of
+       these flags in a special manner and they are masked out of the set of
+       flags that are saved directly to i\_flags.
+
+.. _i_osd1:
+
+The ``osd1`` field has multiple meanings depending on the creator:
+
+Linux:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - l\_i\_version
+     - Inode version. However, if the EA\_INODE inode flag is set, this inode
+       stores an extended attribute value and this field contains the upper 32
+       bits of the attribute value's reference count.
+
+Hurd:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - h\_i\_translator
+     - ??
+
+Masix:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - m\_i\_reserved
+     - ??
+
+.. _i_osd2:
+
+The ``osd2`` field has multiple meanings depending on the filesystem creator:
+
+Linux:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - l\_i\_blocks\_high
+     - Upper 16-bits of the block count. Please see the note attached to
+       i\_blocks\_lo.
+   * - 0x2
+     - \_\_le16
+     - l\_i\_file\_acl\_high
+     - Upper 16-bits of the extended attribute block (historically, the file
+       ACL location). See the Extended Attributes section below.
+   * - 0x4
+     - \_\_le16
+     - l\_i\_uid\_high
+     - Upper 16-bits of the Owner UID.
+   * - 0x6
+     - \_\_le16
+     - l\_i\_gid\_high
+     - Upper 16-bits of the GID.
+   * - 0x8
+     - \_\_le16
+     - l\_i\_checksum\_lo
+     - Lower 16-bits of the inode checksum.
+   * - 0xA
+     - \_\_le16
+     - l\_i\_reserved
+     - Unused.
+
+Hurd:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - h\_i\_reserved1
+     - ??
+   * - 0x2
+     - \_\_u16
+     - h\_i\_mode\_high
+     - Upper 16-bits of the file mode.
+   * - 0x4
+     - \_\_le16
+     - h\_i\_uid\_high
+     - Upper 16-bits of the Owner UID.
+   * - 0x6
+     - \_\_le16
+     - h\_i\_gid\_high
+     - Upper 16-bits of the GID.
+   * - 0x8
+     - \_\_u32
+     - h\_i\_author
+     - Author code?
+
+Masix:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - h\_i\_reserved1
+     - ??
+   * - 0x2
+     - \_\_u16
+     - m\_i\_file\_acl\_high
+     - Upper 16-bits of the extended attribute block (historically, the file
+       ACL location).
+   * - 0x4
+     - \_\_u32
+     - m\_i\_reserved2[2]
+     - ??
+
+Inode Size
+~~~~~~~~~~
+
+In ext2 and ext3, the inode structure size was fixed at 128 bytes
+(``EXT2_GOOD_OLD_INODE_SIZE``) and each inode had a disk record size of
+128 bytes. Starting with ext4, it is possible to allocate a larger
+on-disk inode at format time for all inodes in the filesystem to provide
+space beyond the end of the original ext2 inode. The on-disk inode
+record size is recorded in the superblock as ``s_inode_size``. The
+number of bytes actually used by struct ext4\_inode beyond the original
+128-byte ext2 inode is recorded in the ``i_extra_isize`` field for each
+inode, which allows struct ext4\_inode to grow for a new kernel without
+having to upgrade all of the on-disk inodes. Access to fields beyond
+EXT2\_GOOD\_OLD\_INODE\_SIZE should be verified to be within
+``i_extra_isize``. By default, ext4 inode records are 256 bytes, and (as
+of October 2013) the inode structure is 156 bytes
+(``i_extra_isize = 28``). The extra space between the end of the inode
+structure and the end of the inode record can be used to store extended
+attributes. Each inode record can be as large as the filesystem block
+size, though this is not terribly efficient.
+
+Finding an Inode
+~~~~~~~~~~~~~~~~
+
+Each block group contains ``sb->s_inodes_per_group`` inodes. Because
+inode 0 is defined not to exist, this formula can be used to find the
+block group that an inode lives in:
+``bg = (inode_num - 1) / sb->s_inodes_per_group``. The particular inode
+can be found within the block group's inode table at
+``index = (inode_num - 1) % sb->s_inodes_per_group``. To get the byte
+address within the inode table, use
+``offset = index * sb->s_inode_size``.
+
+Inode Timestamps
+~~~~~~~~~~~~~~~~
+
+Four timestamps are recorded in the lower 128 bytes of the inode
+structure -- inode change time (ctime), access time (atime), data
+modification time (mtime), and deletion time (dtime). The four fields
+are 32-bit signed integers that represent seconds since the Unix epoch
+(1970-01-01 00:00:00 GMT), which means that the fields will overflow in
+January 2038. For inodes that are not linked from any directory but are
+still open (orphan inodes), the dtime field is overloaded for use with
+the orphan list. The superblock field ``s_last_orphan`` points to the
+first inode in the orphan list; dtime is then the number of the next
+orphaned inode, or zero if there are no more orphans.
+
+If the inode structure size ``sb->s_inode_size`` is larger than 128
+bytes and the ``i_inode_extra`` field is large enough to encompass the
+respective ``i_[cma]time_extra`` field, the ctime, atime, and mtime
+inode fields are widened to 64 bits. Within this “extra� 32-bit field,
+the lower two bits are used to extend the 32-bit seconds field to be 34
+bit wide; the upper 30 bits are used to provide nanosecond timestamp
+accuracy. Therefore, timestamps should not overflow until May 2446.
+dtime was not widened. There is also a fifth timestamp to record inode
+creation time (crtime); this field is 64-bits wide and decoded in the
+same manner as 64-bit [cma]time. Neither crtime nor dtime are accessible
+through the regular stat() interface, though debugfs will report them.
+
+We use the 32-bit signed time value plus (2^32 \* (extra epoch bits)).
+In other words:
+
+.. list-table::
+   :widths: 20 20 20 20 20
+   :header-rows: 1
+
+   * - Extra epoch bits
+     - MSB of 32-bit time
+     - Adjustment for signed 32-bit to 64-bit tv\_sec
+     - Decoded 64-bit tv\_sec
+     - valid time range
+   * - 0 0
+     - 1
+     - 0
+     - ``-0x80000000 - -0x00000001``
+     - 1901-12-13 to 1969-12-31
+   * - 0 0
+     - 0
+     - 0
+     - ``0x000000000 - 0x07fffffff``
+     - 1970-01-01 to 2038-01-19
+   * - 0 1
+     - 1
+     - 0x100000000
+     - ``0x080000000 - 0x0ffffffff``
+     - 2038-01-19 to 2106-02-07
+   * - 0 1
+     - 0
+     - 0x100000000
+     - ``0x100000000 - 0x17fffffff``
+     - 2106-02-07 to 2174-02-25
+   * - 1 0
+     - 1
+     - 0x200000000
+     - ``0x180000000 - 0x1ffffffff``
+     - 2174-02-25 to 2242-03-16
+   * - 1 0
+     - 0
+     - 0x200000000
+     - ``0x200000000 - 0x27fffffff``
+     - 2242-03-16 to 2310-04-04
+   * - 1 1
+     - 1
+     - 0x300000000
+     - ``0x280000000 - 0x2ffffffff``
+     - 2310-04-04 to 2378-04-22
+   * - 1 1
+     - 0
+     - 0x300000000
+     - ``0x300000000 - 0x37fffffff``
+     - 2378-04-22 to 2446-05-10
+
+This is a somewhat odd encoding since there are effectively seven times
+as many positive values as negative values. There have also been
+long-standing bugs decoding and encoding dates beyond 2038, which don't
+seem to be fixed as of kernel 3.12 and e2fsprogs 1.42.8. 64-bit kernels
+incorrectly use the extra epoch bits 1,1 for dates between 1901 and
+1970. At some point the kernel will be fixed and e2fsck will fix this
+situation, assuming that it is run before 2310.
diff --git a/Documentation/filesystems/ext4/ondisk/journal.rst b/Documentation/filesystems/ext4/ondisk/journal.rst
new file mode 100644
index 000000000000..e7031af86876
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/journal.rst
@@ -0,0 +1,611 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Journal (jbd2)
+--------------
+
+Introduced in ext3, the ext4 filesystem employs a journal to protect the
+filesystem against corruption in the case of a system crash. A small
+continuous region of disk (default 128MiB) is reserved inside the
+filesystem as a place to land “important� data writes on-disk as quickly
+as possible. Once the important data transaction is fully written to the
+disk and flushed from the disk write cache, a record of the data being
+committed is also written to the journal. At some later point in time,
+the journal code writes the transactions to their final locations on
+disk (this could involve a lot of seeking or a lot of small
+read-write-erases) before erasing the commit record. Should the system
+crash during the second slow write, the journal can be replayed all the
+way to the latest commit record, guaranteeing the atomicity of whatever
+gets written through the journal to the disk. The effect of this is to
+guarantee that the filesystem does not become stuck midway through a
+metadata update.
+
+For performance reasons, ext4 by default only writes filesystem metadata
+through the journal. This means that file data blocks are /not/
+guaranteed to be in any consistent state after a crash. If this default
+guarantee level (``data=ordered``) is not satisfactory, there is a mount
+option to control journal behavior. If ``data=journal``, all data and
+metadata are written to disk through the journal. This is slower but
+safest. If ``data=writeback``, dirty data blocks are not flushed to the
+disk before the metadata are written to disk through the journal.
+
+The journal inode is typically inode 8. The first 68 bytes of the
+journal inode are replicated in the ext4 superblock. The journal itself
+is normal (but hidden) file within the filesystem. The file usually
+consumes an entire block group, though mke2fs tries to put it in the
+middle of the disk.
+
+All fields in jbd2 are written to disk in big-endian order. This is the
+opposite of ext4.
+
+NOTE: Both ext4 and ocfs2 use jbd2.
+
+The maximum size of a journal embedded in an ext4 filesystem is 2^32
+blocks. jbd2 itself does not seem to care.
+
+Layout
+~~~~~~
+
+Generally speaking, the journal has this format:
+
+.. list-table::
+   :widths: 1 1 78
+   :header-rows: 1
+
+   * - Superblock
+     - descriptor\_block (data\_blocks or revocation\_block) [more data or
+       revocations] commmit\_block
+     - [more transactions...]
+   * - 
+     - One transaction
+     -
+
+Notice that a transaction begins with either a descriptor and some data,
+or a block revocation list. A finished transaction always ends with a
+commit. If there is no commit record (or the checksums don't match), the
+transaction will be discarded during replay.
+
+External Journal
+~~~~~~~~~~~~~~~~
+
+Optionally, an ext4 filesystem can be created with an external journal
+device (as opposed to an internal journal, which uses a reserved inode).
+In this case, on the filesystem device, ``s_journal_inum`` should be
+zero and ``s_journal_uuid`` should be set. On the journal device there
+will be an ext4 super block in the usual place, with a matching UUID.
+The journal superblock will be in the next full block after the
+superblock.
+
+.. list-table::
+   :widths: 1 1 1 1 76
+   :header-rows: 1
+
+   * - 1024 bytes of padding
+     - ext4 Superblock
+     - Journal Superblock
+     - descriptor\_block (data\_blocks or revocation\_block) [more data or
+       revocations] commmit\_block
+     - [more transactions...]
+   * - 
+     -
+     -
+     - One transaction
+     -
+
+Block Header
+~~~~~~~~~~~~
+
+Every block in the journal starts with a common 12-byte header
+``struct journal_header_s``:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_be32
+     - h\_magic
+     - jbd2 magic number, 0xC03B3998.
+   * - 0x4
+     - \_\_be32
+     - h\_blocktype
+     - Description of what this block contains. See the jbd2_blocktype_ table
+       below.
+   * - 0x8
+     - \_\_be32
+     - h\_sequence
+     - The transaction ID that goes with this block.
+
+.. _jbd2_blocktype:
+
+The journal block type can be any one of:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 1
+     - Descriptor. This block precedes a series of data blocks that were
+       written through the journal during a transaction.
+   * - 2
+     - Block commit record. This block signifies the completion of a
+       transaction.
+   * - 3
+     - Journal superblock, v1.
+   * - 4
+     - Journal superblock, v2.
+   * - 5
+     - Block revocation records. This speeds up recovery by enabling the
+       journal to skip writing blocks that were subsequently rewritten.
+
+Super Block
+~~~~~~~~~~~
+
+The super block for the journal is much simpler as compared to ext4's.
+The key data kept within are size of the journal, and where to find the
+start of the log of transactions.
+
+The journal superblock is recorded as ``struct journal_superblock_s``,
+which is 1024 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * -
+     -
+     -
+     - Static information describing the journal.
+   * - 0x0
+     - journal\_header\_t (12 bytes)
+     - s\_header
+     - Common header identifying this as a superblock.
+   * - 0xC
+     - \_\_be32
+     - s\_blocksize
+     - Journal device block size.
+   * - 0x10
+     - \_\_be32
+     - s\_maxlen
+     - Total number of blocks in this journal.
+   * - 0x14
+     - \_\_be32
+     - s\_first
+     - First block of log information.
+   * -
+     -
+     -
+     - Dynamic information describing the current state of the log.
+   * - 0x18
+     - \_\_be32
+     - s\_sequence
+     - First commit ID expected in log.
+   * - 0x1C
+     - \_\_be32
+     - s\_start
+     - Block number of the start of log. Contrary to the comments, this field
+       being zero does not imply that the journal is clean!
+   * - 0x20
+     - \_\_be32
+     - s\_errno
+     - Error value, as set by jbd2\_journal\_abort().
+   * -
+     -
+     -
+     - The remaining fields are only valid in a v2 superblock.
+   * - 0x24
+     - \_\_be32
+     - s\_feature\_compat;
+     - Compatible feature set. See the table jbd2_compat_ below.
+   * - 0x28
+     - \_\_be32
+     - s\_feature\_incompat
+     - Incompatible feature set. See the table jbd2_incompat_ below.
+   * - 0x2C
+     - \_\_be32
+     - s\_feature\_ro\_compat
+     - Read-only compatible feature set. There aren't any of these currently.
+   * - 0x30
+     - \_\_u8
+     - s\_uuid[16]
+     - 128-bit uuid for journal. This is compared against the copy in the ext4
+       super block at mount time.
+   * - 0x40
+     - \_\_be32
+     - s\_nr\_users
+     - Number of file systems sharing this journal.
+   * - 0x44
+     - \_\_be32
+     - s\_dynsuper
+     - Location of dynamic super block copy. (Not used?)
+   * - 0x48
+     - \_\_be32
+     - s\_max\_transaction
+     - Limit of journal blocks per transaction. (Not used?)
+   * - 0x4C
+     - \_\_be32
+     - s\_max\_trans\_data
+     - Limit of data blocks per transaction. (Not used?)
+   * - 0x50
+     - \_\_u8
+     - s\_checksum\_type
+     - Checksum algorithm used for the journal.  See jbd2_checksum_type_ for
+       more info.
+   * - 0x51
+     - \_\_u8[3]
+     - s\_padding2
+     -
+   * - 0x54
+     - \_\_u32
+     - s\_padding[42]
+     -
+   * - 0xFC
+     - \_\_be32
+     - s\_checksum
+     - Checksum of the entire superblock, with this field set to zero.
+   * - 0x100
+     - \_\_u8
+     - s\_users[16\*48]
+     - ids of all file systems sharing the log. e2fsprogs/Linux don't allow
+       shared external journals, but I imagine Lustre (or ocfs2?), which use
+       the jbd2 code, might.
+
+.. _jbd2_compat:
+
+The journal compat features are any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Journal maintains checksums on the data blocks.
+       (JBD2\_FEATURE\_COMPAT\_CHECKSUM)
+
+.. _jbd2_incompat:
+
+The journal incompat features are any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Journal has block revocation records. (JBD2\_FEATURE\_INCOMPAT\_REVOKE)
+   * - 0x2
+     - Journal can deal with 64-bit block numbers.
+       (JBD2\_FEATURE\_INCOMPAT\_64BIT)
+   * - 0x4
+     - Journal commits asynchronously. (JBD2\_FEATURE\_INCOMPAT\_ASYNC\_COMMIT)
+   * - 0x8
+     - This journal uses v2 of the checksum on-disk format. Each journal
+       metadata block gets its own checksum, and the block tags in the
+       descriptor table contain checksums for each of the data blocks in the
+       journal. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2)
+   * - 0x10
+     - This journal uses v3 of the checksum on-disk format. This is the same as
+       v2, but the journal block tag size is fixed regardless of the size of
+       block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3)
+
+.. _jbd2_checksum_type:
+
+Journal checksum type codes are one of the following.  crc32 or crc32c are the
+most likely choices.
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 1
+     - CRC32
+   * - 2
+     - MD5
+   * - 3
+     - SHA1
+   * - 4
+     - CRC32C
+
+Descriptor Block
+~~~~~~~~~~~~~~~~
+
+The descriptor block contains an array of journal block tags that
+describe the final locations of the data blocks that follow in the
+journal. Descriptor blocks are open-coded instead of being completely
+described by a data structure, but here is the block structure anyway.
+Descriptor blocks consume at least 36 bytes, but use a full block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - journal\_header\_t
+     - (open coded)
+     - Common block header.
+   * - 0xC
+     - struct journal\_block\_tag\_s
+     - open coded array[]
+     - Enough tags either to fill up the block or to describe all the data
+       blocks that follow this descriptor block.
+
+Journal block tags have any of the following formats, depending on which
+journal feature and block tag flags are set.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is set, the journal block tag is
+defined as ``struct journal_block_tag3_s``, which looks like the
+following. The size is 16 or 32 bytes.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - \_\_be32
+     - t\_blocknr
+     - Lower 32-bits of the location of where the corresponding data block
+       should end up on disk.
+   * - 0x4
+     - \_\_be32
+     - t\_flags
+     - Flags that go with the descriptor. See the table jbd2_tag_flags_ for
+       more info.
+   * - 0x8
+     - \_\_be32
+     - t\_blocknr\_high
+     - Upper 32-bits of the location of where the corresponding data block
+       should end up on disk. This is zero if JBD2\_FEATURE\_INCOMPAT\_64BIT is
+       not enabled.
+   * - 0xC
+     - \_\_be32
+     - t\_checksum
+     - Checksum of the journal UUID, the sequence number, and the data block.
+   * -
+     -
+     -
+     - This field appears to be open coded. It always comes at the end of the
+       tag, after t_checksum. This field is not present if the "same UUID" flag
+       is set.
+   * - 0x8 or 0xC
+     - char
+     - uuid[16]
+     - A UUID to go with this tag. This field appears to be copied from the
+       ``j_uuid`` field in ``struct journal_s``, but only tune2fs touches that
+       field.
+
+.. _jbd2_tag_flags:
+
+The journal tag flags are any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - On-disk block is escaped. The first four bytes of the data block just
+       happened to match the jbd2 magic number.
+   * - 0x2
+     - This block has the same UUID as previous, therefore the UUID field is
+       omitted.
+   * - 0x4
+     - The data block was deleted by the transaction. (Not used?)
+   * - 0x8
+     - This is the last tag in this descriptor block.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is NOT set, the journal block tag
+is defined as ``struct journal_block_tag_s``, which looks like the
+following. The size is 8, 12, 24, or 28 bytes:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - \_\_be32
+     - t\_blocknr
+     - Lower 32-bits of the location of where the corresponding data block
+       should end up on disk.
+   * - 0x4
+     - \_\_be16
+     - t\_checksum
+     - Checksum of the journal UUID, the sequence number, and the data block.
+       Note that only the lower 16 bits are stored.
+   * - 0x6
+     - \_\_be16
+     - t\_flags
+     - Flags that go with the descriptor. See the table jbd2_tag_flags_ for
+       more info.
+   * -
+     -
+     -
+     - This next field is only present if the super block indicates support for
+       64-bit block numbers.
+   * - 0x8
+     - \_\_be32
+     - t\_blocknr\_high
+     - Upper 32-bits of the location of where the corresponding data block
+       should end up on disk.
+   * -
+     -
+     -
+     - This field appears to be open coded. It always comes at the end of the
+       tag, after t_flags or t_blocknr_high. This field is not present if the
+       "same UUID" flag is set.
+   * - 0x8 or 0xC
+     - char
+     - uuid[16]
+     - A UUID to go with this tag. This field appears to be copied from the
+       ``j_uuid`` field in ``struct journal_s``, but only tune2fs touches that
+       field.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or
+JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the block is a
+``struct jbd2_journal_block_tail``, which looks like this:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - \_\_be32
+     - t\_checksum
+     - Checksum of the journal UUID + the descriptor block, with this field set
+       to zero.
+
+Data Block
+~~~~~~~~~~
+
+In general, the data blocks being written to disk through the journal
+are written verbatim into the journal file after the descriptor block.
+However, if the first four bytes of the block match the jbd2 magic
+number then those four bytes are replaced with zeroes and the “escaped�
+flag is set in the descriptor block tag.
+
+Revocation Block
+~~~~~~~~~~~~~~~~
+
+A revocation block is used to prevent replay of a block in an earlier
+transaction. This is used to mark blocks that were journalled at one
+time but are no longer journalled. Typically this happens if a metadata
+block is freed and re-allocated as a file data block; in this case, a
+journal replay after the file block was written to disk will cause
+corruption.
+
+**NOTE**: This mechanism is NOT used to express “this journal block is
+superseded by this other journal block�, as the author (djwong)
+mistakenly thought. Any block being added to a transaction will cause
+the removal of all existing revocation records for that block.
+
+Revocation blocks are described in
+``struct jbd2_journal_revoke_header_s``, are at least 16 bytes in
+length, but use a full block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - journal\_header\_t
+     - r\_header
+     - Common block header.
+   * - 0xC
+     - \_\_be32
+     - r\_count
+     - Number of bytes used in this block.
+   * - 0x10
+     - \_\_be32 or \_\_be64
+     - blocks[0]
+     - Blocks to revoke.
+
+After r\_count is a linear array of block numbers that are effectively
+revoked by this transaction. The size of each block number is 8 bytes if
+the superblock advertises 64-bit block number support, or 4 bytes
+otherwise.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or
+JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the revocation
+block is a ``struct jbd2_journal_revoke_tail``, which has this format:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_be32
+     - r\_checksum
+     - Checksum of the journal UUID + revocation block
+
+Commit Block
+~~~~~~~~~~~~
+
+The commit block is a sentry that indicates that a transaction has been
+completely written to the journal. Once this commit block reaches the
+journal, the data stored with this transaction can be written to their
+final locations on disk.
+
+The commit block is described by ``struct commit_header``, which is 32
+bytes long (but uses a full block):
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - journal\_header\_s
+     - (open coded)
+     - Common block header.
+   * - 0xC
+     - unsigned char
+     - h\_chksum\_type
+     - The type of checksum to use to verify the integrity of the data blocks
+       in the transaction. See jbd2_checksum_type_ for more info.
+   * - 0xD
+     - unsigned char
+     - h\_chksum\_size
+     - The number of bytes used by the checksum. Most likely 4.
+   * - 0xE
+     - unsigned char
+     - h\_padding[2]
+     -
+   * - 0x10
+     - \_\_be32
+     - h\_chksum[JBD2\_CHECKSUM\_BYTES]
+     - 32 bytes of space to store checksums. If
+       JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3
+       are set, the first ``__be32`` is the checksum of the journal UUID and
+       the entire commit block, with this field zeroed. If
+       JBD2\_FEATURE\_COMPAT\_CHECKSUM is set, the first ``__be32`` is the
+       crc32 of all the blocks already written to the transaction.
+   * - 0x30
+     - \_\_be64
+     - h\_commit\_sec
+     - The time that the transaction was committed, in seconds since the epoch.
+   * - 0x38
+     - \_\_be32
+     - h\_commit\_nsec
+     - Nanoseconds component of the above timestamp.
+
diff --git a/Documentation/filesystems/ext4/ondisk/mmp.rst b/Documentation/filesystems/ext4/ondisk/mmp.rst
new file mode 100644
index 000000000000..b7d7a3137f80
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/mmp.rst
@@ -0,0 +1,77 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Multiple Mount Protection
+-------------------------
+
+Multiple mount protection (MMP) is a feature that protects the
+filesystem against multiple hosts trying to use the filesystem
+simultaneously. When a filesystem is opened (for mounting, or fsck,
+etc.), the MMP code running on the node (call it node A) checks a
+sequence number. If the sequence number is EXT4\_MMP\_SEQ\_CLEAN, the
+open continues. If the sequence number is EXT4\_MMP\_SEQ\_FSCK, then
+fsck is (hopefully) running, and open fails immediately. Otherwise, the
+open code will wait for twice the specified MMP check interval and check
+the sequence number again. If the sequence number has changed, then the
+filesystem is active on another machine and the open fails. If the MMP
+code passes all of those checks, a new MMP sequence number is generated
+and written to the MMP block, and the mount proceeds.
+
+While the filesystem is live, the kernel sets up a timer to re-check the
+MMP block at the specified MMP check interval. To perform the re-check,
+the MMP sequence number is re-read; if it does not match the in-memory
+MMP sequence number, then another node (node B) has mounted the
+filesystem, and node A remounts the filesystem read-only. If the
+sequence numbers match, the sequence number is incremented both in
+memory and on disk, and the re-check is complete.
+
+The hostname and device filename are written into the MMP block whenever
+an open operation succeeds. The MMP code does not use these values; they
+are provided purely for informational purposes.
+
+The checksum is calculated against the FS UUID and the MMP structure.
+The MMP structure (``struct mmp_struct``) is as follows:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - mmp\_magic
+     - Magic number for MMP, 0x004D4D50 (“MMP�).
+   * - 0x4
+     - \_\_le32
+     - mmp\_seq
+     - Sequence number, updated periodically.
+   * - 0x8
+     - \_\_le64
+     - mmp\_time
+     - Time that the MMP block was last updated.
+   * - 0x10
+     - char[64]
+     - mmp\_nodename
+     - Hostname of the node that opened the filesystem.
+   * - 0x50
+     - char[32]
+     - mmp\_bdevname
+     - Block device name of the filesystem.
+   * - 0x70
+     - \_\_le16
+     - mmp\_check\_interval
+     - The MMP re-check interval, in seconds.
+   * - 0x72
+     - \_\_le16
+     - mmp\_pad1
+     - Zero.
+   * - 0x74
+     - \_\_le32[226]
+     - mmp\_pad2
+     - Zero.
+   * - 0x3FC
+     - \_\_le32
+     - mmp\_checksum
+     - Checksum of the MMP block.
diff --git a/Documentation/filesystems/ext4/ondisk/overview.rst b/Documentation/filesystems/ext4/ondisk/overview.rst
new file mode 100644
index 000000000000..cbab18baba12
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/overview.rst
@@ -0,0 +1,26 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+High Level Design
+=================
+
+An ext4 file system is split into a series of block groups. To reduce
+performance difficulties due to fragmentation, the block allocator tries
+very hard to keep each file's blocks within the same group, thereby
+reducing seek times. The size of a block group is specified in
+``sb.s_blocks_per_group`` blocks, though it can also calculated as 8 \*
+``block_size_in_bytes``. With the default block size of 4KiB, each group
+will contain 32,768 blocks, for a length of 128MiB. The number of block
+groups is the size of the device divided by the size of a block group.
+
+All fields in ext4 are written to disk in little-endian order. HOWEVER,
+all fields in jbd2 (the journal) are written to disk in big-endian
+order.
+
+.. include:: blocks.rst
+.. include:: blockgroup.rst
+.. include:: special_inodes.rst
+.. include:: allocators.rst
+.. include:: checksums.rst
+.. include:: bigalloc.rst
+.. include:: inlinedata.rst
+.. include:: eainode.rst
diff --git a/Documentation/filesystems/ext4/ondisk/special_inodes.rst b/Documentation/filesystems/ext4/ondisk/special_inodes.rst
new file mode 100644
index 000000000000..a82f70c9baeb
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/special_inodes.rst
@@ -0,0 +1,38 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Special inodes
+--------------
+
+ext4 reserves some inode for special features, as follows:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - inode Number
+     - Purpose
+   * - 0
+     - Doesn't exist; there is no inode 0.
+   * - 1
+     - List of defective blocks.
+   * - 2
+     - Root directory.
+   * - 3
+     - User quota.
+   * - 4
+     - Group quota.
+   * - 5
+     - Boot loader.
+   * - 6
+     - Undelete directory.
+   * - 7
+     - Reserved group descriptors inode. (“resize inode�)
+   * - 8
+     - Journal inode.
+   * - 9
+     - The “exclude� inode, for snapshots(?)
+   * - 10
+     - Replica inode, used for some non-upstream feature?
+   * - 11
+     - Traditional first non-reserved inode. Usually this is the lost+found directory. See s\_first\_ino in the superblock.
+
diff --git a/Documentation/filesystems/ext4/ondisk/super.rst b/Documentation/filesystems/ext4/ondisk/super.rst
new file mode 100644
index 000000000000..5f81dd87e0b9
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/super.rst
@@ -0,0 +1,801 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Super Block
+-----------
+
+The superblock records various information about the enclosing
+filesystem, such as block counts, inode counts, supported features,
+maintenance information, and more.
+
+If the sparse\_super feature flag is set, redundant copies of the
+superblock and group descriptors are kept only in the groups whose group
+number is either 0 or a power of 3, 5, or 7. If the flag is not set,
+redundant copies are kept in all groups.
+
+The superblock checksum is calculated against the superblock structure,
+which includes the FS UUID.
+
+The ext4 superblock is laid out as follows in
+``struct ext4_super_block``:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - s\_inodes\_count
+     - Total inode count.
+   * - 0x4
+     - \_\_le32
+     - s\_blocks\_count\_lo
+     - Total block count.
+   * - 0x8
+     - \_\_le32
+     - s\_r\_blocks\_count\_lo
+     - This number of blocks can only be allocated by the super-user.
+   * - 0xC
+     - \_\_le32
+     - s\_free\_blocks\_count\_lo
+     - Free block count.
+   * - 0x10
+     - \_\_le32
+     - s\_free\_inodes\_count
+     - Free inode count.
+   * - 0x14
+     - \_\_le32
+     - s\_first\_data\_block
+     - First data block. This must be at least 1 for 1k-block filesystems and
+       is typically 0 for all other block sizes.
+   * - 0x18
+     - \_\_le32
+     - s\_log\_block\_size
+     - Block size is 2 ^ (10 + s\_log\_block\_size).
+   * - 0x1C
+     - \_\_le32
+     - s\_log\_cluster\_size
+     - Cluster size is (2 ^ s\_log\_cluster\_size) blocks if bigalloc is
+       enabled. Otherwise s\_log\_cluster\_size must equal s\_log\_block\_size.
+   * - 0x20
+     - \_\_le32
+     - s\_blocks\_per\_group
+     - Blocks per group.
+   * - 0x24
+     - \_\_le32
+     - s\_clusters\_per\_group
+     - Clusters per group, if bigalloc is enabled. Otherwise
+       s\_clusters\_per\_group must equal s\_blocks\_per\_group.
+   * - 0x28
+     - \_\_le32
+     - s\_inodes\_per\_group
+     - Inodes per group.
+   * - 0x2C
+     - \_\_le32
+     - s\_mtime
+     - Mount time, in seconds since the epoch.
+   * - 0x30
+     - \_\_le32
+     - s\_wtime
+     - Write time, in seconds since the epoch.
+   * - 0x34
+     - \_\_le16
+     - s\_mnt\_count
+     - Number of mounts since the last fsck.
+   * - 0x36
+     - \_\_le16
+     - s\_max\_mnt\_count
+     - Number of mounts beyond which a fsck is needed.
+   * - 0x38
+     - \_\_le16
+     - s\_magic
+     - Magic signature, 0xEF53
+   * - 0x3A
+     - \_\_le16
+     - s\_state
+     - File system state. See super_state_ for more info.
+   * - 0x3C
+     - \_\_le16
+     - s\_errors
+     - Behaviour when detecting errors. See super_errors_ for more info.
+   * - 0x3E
+     - \_\_le16
+     - s\_minor\_rev\_level
+     - Minor revision level.
+   * - 0x40
+     - \_\_le32
+     - s\_lastcheck
+     - Time of last check, in seconds since the epoch.
+   * - 0x44
+     - \_\_le32
+     - s\_checkinterval
+     - Maximum time between checks, in seconds.
+   * - 0x48
+     - \_\_le32
+     - s\_creator\_os
+     - Creator OS. See the table super_creator_ for more info.
+   * - 0x4C
+     - \_\_le32
+     - s\_rev\_level
+     - Revision level. See the table super_revision_ for more info.
+   * - 0x50
+     - \_\_le16
+     - s\_def\_resuid
+     - Default uid for reserved blocks.
+   * - 0x52
+     - \_\_le16
+     - s\_def\_resgid
+     - Default gid for reserved blocks.
+   * -
+     -
+     -
+     - These fields are for EXT4_DYNAMIC_REV superblocks only.
+       
+       Note: the difference between the compatible feature set and the
+       incompatible feature set is that if there is a bit set in the
+       incompatible feature set that the kernel doesn't know about, it should
+       refuse to mount the filesystem.
+       
+       e2fsck's requirements are more strict; if it doesn't know
+       about a feature in either the compatible or incompatible feature set, it
+       must abort and not try to meddle with things it doesn't understand...
+   * - 0x54
+     - \_\_le32
+     - s\_first\_ino
+     - First non-reserved inode.
+   * - 0x58
+     - \_\_le16
+     - s\_inode\_size
+     - Size of inode structure, in bytes.
+   * - 0x5A
+     - \_\_le16
+     - s\_block\_group\_nr
+     - Block group # of this superblock.
+   * - 0x5C
+     - \_\_le32
+     - s\_feature\_compat
+     - Compatible feature set flags. Kernel can still read/write this fs even
+       if it doesn't understand a flag; fsck should not do that. See the
+       super_compat_ table for more info.
+   * - 0x60
+     - \_\_le32
+     - s\_feature\_incompat
+     - Incompatible feature set. If the kernel or fsck doesn't understand one
+       of these bits, it should stop. See the super_incompat_ table for more
+       info.
+   * - 0x64
+     - \_\_le32
+     - s\_feature\_ro\_compat
+     - Readonly-compatible feature set. If the kernel doesn't understand one of
+       these bits, it can still mount read-only. See the super_rocompat_ table
+       for more info.
+   * - 0x68
+     - \_\_u8
+     - s\_uuid[16]
+     - 128-bit UUID for volume.
+   * - 0x78
+     - char
+     - s\_volume\_name[16]
+     - Volume label.
+   * - 0x88
+     - char
+     - s\_last\_mounted[64]
+     - Directory where filesystem was last mounted.
+   * - 0xC8
+     - \_\_le32
+     - s\_algorithm\_usage\_bitmap
+     - For compression (Not used in e2fsprogs/Linux)
+   * -
+     -
+     -
+     - Performance hints.  Directory preallocation should only happen if the
+       EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
+   * - 0xCC
+     - \_\_u8
+     - s\_prealloc\_blocks
+     - #. of blocks to try to preallocate for ... files? (Not used in
+       e2fsprogs/Linux)
+   * - 0xCD
+     - \_\_u8
+     - s\_prealloc\_dir\_blocks
+     - #. of blocks to preallocate for directories. (Not used in
+       e2fsprogs/Linux)
+   * - 0xCE
+     - \_\_le16
+     - s\_reserved\_gdt\_blocks
+     - Number of reserved GDT entries for future filesystem expansion.
+   * -
+     -
+     -
+     - Journalling support is valid only if EXT4_FEATURE_COMPAT_HAS_JOURNAL is
+       set.
+   * - 0xD0
+     - \_\_u8
+     - s\_journal\_uuid[16]
+     - UUID of journal superblock
+   * - 0xE0
+     - \_\_le32
+     - s\_journal\_inum
+     - inode number of journal file.
+   * - 0xE4
+     - \_\_le32
+     - s\_journal\_dev
+     - Device number of journal file, if the external journal feature flag is
+       set.
+   * - 0xE8
+     - \_\_le32
+     - s\_last\_orphan
+     - Start of list of orphaned inodes to delete.
+   * - 0xEC
+     - \_\_le32
+     - s\_hash\_seed[4]
+     - HTREE hash seed.
+   * - 0xFC
+     - \_\_u8
+     - s\_def\_hash\_version
+     - Default hash algorithm to use for directory hashes. See super_def_hash_
+       for more info.
+   * - 0xFD
+     - \_\_u8
+     - s\_jnl\_backup\_type
+     - If this value is 0 or EXT3\_JNL\_BACKUP\_BLOCKS (1), then the
+       ``s_jnl_blocks`` field contains a duplicate copy of the inode's
+       ``i_block[]`` array and ``i_size``.
+   * - 0xFE
+     - \_\_le16
+     - s\_desc\_size
+     - Size of group descriptors, in bytes, if the 64bit incompat feature flag
+       is set.
+   * - 0x100
+     - \_\_le32
+     - s\_default\_mount\_opts
+     - Default mount options. See the super_mountopts_ table for more info.
+   * - 0x104
+     - \_\_le32
+     - s\_first\_meta\_bg
+     - First metablock block group, if the meta\_bg feature is enabled.
+   * - 0x108
+     - \_\_le32
+     - s\_mkfs\_time
+     - When the filesystem was created, in seconds since the epoch.
+   * - 0x10C
+     - \_\_le32
+     - s\_jnl\_blocks[17]
+     - Backup copy of the journal inode's ``i_block[]`` array in the first 15
+       elements and i\_size\_high and i\_size in the 16th and 17th elements,
+       respectively.
+   * -
+     -
+     -
+     - 64bit support is valid only if EXT4_FEATURE_COMPAT_64BIT is set.
+   * - 0x150
+     - \_\_le32
+     - s\_blocks\_count\_hi
+     - High 32-bits of the block count.
+   * - 0x154
+     - \_\_le32
+     - s\_r\_blocks\_count\_hi
+     - High 32-bits of the reserved block count.
+   * - 0x158
+     - \_\_le32
+     - s\_free\_blocks\_count\_hi
+     - High 32-bits of the free block count.
+   * - 0x15C
+     - \_\_le16
+     - s\_min\_extra\_isize
+     - All inodes have at least # bytes.
+   * - 0x15E
+     - \_\_le16
+     - s\_want\_extra\_isize
+     - New inodes should reserve # bytes.
+   * - 0x160
+     - \_\_le32
+     - s\_flags
+     - Miscellaneous flags. See the super_flags_ table for more info.
+   * - 0x164
+     - \_\_le16
+     - s\_raid\_stride
+     - RAID stride. This is the number of logical blocks read from or written
+       to the disk before moving to the next disk. This affects the placement
+       of filesystem metadata, which will hopefully make RAID storage faster.
+   * - 0x166
+     - \_\_le16
+     - s\_mmp\_interval
+     - #. seconds to wait in multi-mount prevention (MMP) checking. In theory,
+       MMP is a mechanism to record in the superblock which host and device
+       have mounted the filesystem, in order to prevent multiple mounts. This
+       feature does not seem to be implemented...
+   * - 0x168
+     - \_\_le64
+     - s\_mmp\_block
+     - Block # for multi-mount protection data.
+   * - 0x170
+     - \_\_le32
+     - s\_raid\_stripe\_width
+     - RAID stripe width. This is the number of logical blocks read from or
+       written to the disk before coming back to the current disk. This is used
+       by the block allocator to try to reduce the number of read-modify-write
+       operations in a RAID5/6.
+   * - 0x174
+     - \_\_u8
+     - s\_log\_groups\_per\_flex
+     - Size of a flexible block group is 2 ^ ``s_log_groups_per_flex``.
+   * - 0x175
+     - \_\_u8
+     - s\_checksum\_type
+     - Metadata checksum algorithm type. The only valid value is 1 (crc32c).
+   * - 0x176
+     - \_\_le16
+     - s\_reserved\_pad
+     -
+   * - 0x178
+     - \_\_le64
+     - s\_kbytes\_written
+     - Number of KiB written to this filesystem over its lifetime.
+   * - 0x180
+     - \_\_le32
+     - s\_snapshot\_inum
+     - inode number of active snapshot. (Not used in e2fsprogs/Linux.)
+   * - 0x184
+     - \_\_le32
+     - s\_snapshot\_id
+     - Sequential ID of active snapshot. (Not used in e2fsprogs/Linux.)
+   * - 0x188
+     - \_\_le64
+     - s\_snapshot\_r\_blocks\_count
+     - Number of blocks reserved for active snapshot's future use. (Not used in
+       e2fsprogs/Linux.)
+   * - 0x190
+     - \_\_le32
+     - s\_snapshot\_list
+     - inode number of the head of the on-disk snapshot list. (Not used in
+       e2fsprogs/Linux.)
+   * - 0x194
+     - \_\_le32
+     - s\_error\_count
+     - Number of errors seen.
+   * - 0x198
+     - \_\_le32
+     - s\_first\_error\_time
+     - First time an error happened, in seconds since the epoch.
+   * - 0x19C
+     - \_\_le32
+     - s\_first\_error\_ino
+     - inode involved in first error.
+   * - 0x1A0
+     - \_\_le64
+     - s\_first\_error\_block
+     - Number of block involved of first error.
+   * - 0x1A8
+     - \_\_u8
+     - s\_first\_error\_func[32]
+     - Name of function where the error happened.
+   * - 0x1C8
+     - \_\_le32
+     - s\_first\_error\_line
+     - Line number where error happened.
+   * - 0x1CC
+     - \_\_le32
+     - s\_last\_error\_time
+     - Time of most recent error, in seconds since the epoch.
+   * - 0x1D0
+     - \_\_le32
+     - s\_last\_error\_ino
+     - inode involved in most recent error.
+   * - 0x1D4
+     - \_\_le32
+     - s\_last\_error\_line
+     - Line number where most recent error happened.
+   * - 0x1D8
+     - \_\_le64
+     - s\_last\_error\_block
+     - Number of block involved in most recent error.
+   * - 0x1E0
+     - \_\_u8
+     - s\_last\_error\_func[32]
+     - Name of function where the most recent error happened.
+   * - 0x200
+     - \_\_u8
+     - s\_mount\_opts[64]
+     - ASCIIZ string of mount options.
+   * - 0x240
+     - \_\_le32
+     - s\_usr\_quota\_inum
+     - Inode number of user `quota <quota>`__ file.
+   * - 0x244
+     - \_\_le32
+     - s\_grp\_quota\_inum
+     - Inode number of group `quota <quota>`__ file.
+   * - 0x248
+     - \_\_le32
+     - s\_overhead\_blocks
+     - Overhead blocks/clusters in fs. (Huh? This field is always zero, which
+       means that the kernel calculates it dynamically.)
+   * - 0x24C
+     - \_\_le32
+     - s\_backup\_bgs[2]
+     - Block groups containing superblock backups (if sparse\_super2)
+   * - 0x254
+     - \_\_u8
+     - s\_encrypt\_algos[4]
+     - Encryption algorithms in use. There can be up to four algorithms in use
+       at any time; valid algorithm codes are given in the super_encrypt_ table
+       below.
+   * - 0x258
+     - \_\_u8
+     - s\_encrypt\_pw\_salt[16]
+     - Salt for the string2key algorithm for encryption.
+   * - 0x268
+     - \_\_le32
+     - s\_lpf\_ino
+     - Inode number of lost+found
+   * - 0x26C
+     - \_\_le32
+     - s\_prj\_quota\_inum
+     - Inode that tracks project quotas.
+   * - 0x270
+     - \_\_le32
+     - s\_checksum\_seed
+     - Checksum seed used for metadata\_csum calculations. This value is
+       crc32c(~0, $orig\_fs\_uuid).
+   * - 0x274
+     - \_\_u8
+     - s\_wtime_hi
+     - Upper 8 bits of the s_wtime field.
+   * - 0x275
+     - \_\_u8
+     - s\_wtime_hi
+     - Upper 8 bits of the s_mtime field.
+   * - 0x276
+     - \_\_u8
+     - s\_mkfs_time_hi
+     - Upper 8 bits of the s_mkfs_time field.
+   * - 0x277
+     - \_\_u8
+     - s\_lastcheck_hi
+     - Upper 8 bits of the s_lastcheck_hi field.
+   * - 0x278
+     - \_\_u8
+     - s\_first_error_time_hi
+     - Upper 8 bits of the s_first_error_time_hi field.
+   * - 0x279
+     - \_\_u8
+     - s\_last_error_time_hi
+     - Upper 8 bits of the s_last_error_time_hi field.
+   * - 0x27A
+     - \_\_u8[2]
+     - s\_pad
+     - Zero padding.
+   * - 0x27C
+     - \_\_le32
+     - s\_reserved[96]
+     - Padding to the end of the block.
+   * - 0x3FC
+     - \_\_le32
+     - s\_checksum
+     - Superblock checksum.
+
+.. _super_state:
+
+The superblock state is some combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0001
+     - Cleanly umounted
+   * - 0x0002
+     - Errors detected
+   * - 0x0004
+     - Orphans being recovered
+
+.. _super_errors:
+
+The superblock error policy is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 1
+     - Continue
+   * - 2
+     - Remount read-only
+   * - 3
+     - Panic
+
+.. _super_creator:
+
+The filesystem creator is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0
+     - Linux
+   * - 1
+     - Hurd
+   * - 2
+     - Masix
+   * - 3
+     - FreeBSD
+   * - 4
+     - Lites
+
+.. _super_revision:
+
+The superblock revision is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0
+     - Original format
+   * - 1
+     - v2 format w/ dynamic inode sizes
+
+Note that ``EXT4_DYNAMIC_REV`` refers to a revision 1 or newer filesystem.
+
+.. _super_compat:
+
+The superblock compatible features field is a combination of any of the
+following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Directory preallocation (COMPAT\_DIR\_PREALLOC).
+   * - 0x2
+     - “imagic inodes�. Not clear from the code what this does
+       (COMPAT\_IMAGIC\_INODES).
+   * - 0x4
+     - Has a journal (COMPAT\_HAS\_JOURNAL).
+   * - 0x8
+     - Supports extended attributes (COMPAT\_EXT\_ATTR).
+   * - 0x10
+     - Has reserved GDT blocks for filesystem expansion
+       (COMPAT\_RESIZE\_INODE). Requires RO\_COMPAT\_SPARSE\_SUPER.
+   * - 0x20
+     - Has directory indices (COMPAT\_DIR\_INDEX).
+   * - 0x40
+     - “Lazy BG�. Not in Linux kernel, seems to have been for uninitialized
+       block groups? (COMPAT\_LAZY\_BG)
+   * - 0x80
+     - “Exclude inode�. Not used. (COMPAT\_EXCLUDE\_INODE).
+   * - 0x100
+     - “Exclude bitmap�. Seems to be used to indicate the presence of
+       snapshot-related exclude bitmaps? Not defined in kernel or used in
+       e2fsprogs (COMPAT\_EXCLUDE\_BITMAP).
+   * - 0x200
+     - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs
+       points to the two block groups that contain backup superblocks
+       (COMPAT\_SPARSE\_SUPER2).
+
+.. _super_incompat:
+
+The superblock incompatible features field is a combination of any of the
+following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Compression (INCOMPAT\_COMPRESSION).
+   * - 0x2
+     - Directory entries record the file type. See ext4\_dir\_entry\_2 below
+       (INCOMPAT\_FILETYPE).
+   * - 0x4
+     - Filesystem needs recovery (INCOMPAT\_RECOVER).
+   * - 0x8
+     - Filesystem has a separate journal device (INCOMPAT\_JOURNAL\_DEV).
+   * - 0x10
+     - Meta block groups. See the earlier discussion of this feature
+       (INCOMPAT\_META\_BG).
+   * - 0x40
+     - Files in this filesystem use extents (INCOMPAT\_EXTENTS).
+   * - 0x80
+     - Enable a filesystem size of 2^64 blocks (INCOMPAT\_64BIT).
+   * - 0x100
+     - Multiple mount protection. Not implemented (INCOMPAT\_MMP).
+   * - 0x200
+     - Flexible block groups. See the earlier discussion of this feature
+       (INCOMPAT\_FLEX\_BG).
+   * - 0x400
+     - Inodes can be used to store large extended attribute values
+       (INCOMPAT\_EA\_INODE).
+   * - 0x1000
+     - Data in directory entry (INCOMPAT\_DIRDATA). (Not implemented?)
+   * - 0x2000
+     - Metadata checksum seed is stored in the superblock. This feature enables
+       the administrator to change the UUID of a metadata\_csum filesystem
+       while the filesystem is mounted; without it, the checksum definition
+       requires all metadata blocks to be rewritten (INCOMPAT\_CSUM\_SEED).
+   * - 0x4000
+     - Large directory >2GB or 3-level htree (INCOMPAT\_LARGEDIR). Prior to
+       this feature, directories could not be larger than 4GiB and could not
+       have an htree more than 2 levels deep. If this feature is enabled,
+       directories can be larger than 4GiB and have a maximum htree depth of 3.
+   * - 0x8000
+     - Data in inode (INCOMPAT\_INLINE\_DATA).
+   * - 0x10000
+     - Encrypted inodes are present on the filesystem. (INCOMPAT\_ENCRYPT).
+
+.. _super_rocompat:
+
+The superblock read-only compatible features field is a combination of any of
+the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Sparse superblocks. See the earlier discussion of this feature
+       (RO\_COMPAT\_SPARSE\_SUPER).
+   * - 0x2
+     - This filesystem has been used to store a file greater than 2GiB
+       (RO\_COMPAT\_LARGE\_FILE).
+   * - 0x4
+     - Not used in kernel or e2fsprogs (RO\_COMPAT\_BTREE\_DIR).
+   * - 0x8
+     - This filesystem has files whose sizes are represented in units of
+       logical blocks, not 512-byte sectors. This implies a very large file
+       indeed! (RO\_COMPAT\_HUGE\_FILE)
+   * - 0x10
+     - Group descriptors have checksums. In addition to detecting corruption,
+       this is useful for lazy formatting with uninitialized groups
+       (RO\_COMPAT\_GDT\_CSUM).
+   * - 0x20
+     - Indicates that the old ext3 32,000 subdirectory limit no longer applies
+       (RO\_COMPAT\_DIR\_NLINK). A directory's i\_links\_count will be set to 1
+       if it is incremented past 64,999.
+   * - 0x40
+     - Indicates that large inodes exist on this filesystem
+       (RO\_COMPAT\_EXTRA\_ISIZE).
+   * - 0x80
+     - This filesystem has a snapshot (RO\_COMPAT\_HAS\_SNAPSHOT).
+   * - 0x100
+     - `Quota <Quota>`__ (RO\_COMPAT\_QUOTA).
+   * - 0x200
+     - This filesystem supports “bigalloc�, which means that file extents are
+       tracked in units of clusters (of blocks) instead of blocks
+       (RO\_COMPAT\_BIGALLOC).
+   * - 0x400
+     - This filesystem supports metadata checksumming.
+       (RO\_COMPAT\_METADATA\_CSUM; implies RO\_COMPAT\_GDT\_CSUM, though
+       GDT\_CSUM must not be set)
+   * - 0x800
+     - Filesystem supports replicas. This feature is neither in the kernel nor
+       e2fsprogs. (RO\_COMPAT\_REPLICA)
+   * - 0x1000
+     - Read-only filesystem image; the kernel will not mount this image
+       read-write and most tools will refuse to write to the image.
+       (RO\_COMPAT\_READONLY)
+   * - 0x2000
+     - Filesystem tracks project quotas. (RO\_COMPAT\_PROJECT)
+
+.. _super_def_hash:
+
+The ``s_def_hash_version`` field is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0
+     - Legacy.
+   * - 0x1
+     - Half MD4.
+   * - 0x2
+     - Tea.
+   * - 0x3
+     - Legacy, unsigned.
+   * - 0x4
+     - Half MD4, unsigned.
+   * - 0x5
+     - Tea, unsigned.
+
+.. _super_mountopts:
+
+The ``s_default_mount_opts`` field is any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0001
+     - Print debugging info upon (re)mount. (EXT4\_DEFM\_DEBUG)
+   * - 0x0002
+     - New files take the gid of the containing directory (instead of the fsgid
+       of the current process). (EXT4\_DEFM\_BSDGROUPS)
+   * - 0x0004
+     - Support userspace-provided extended attributes. (EXT4\_DEFM\_XATTR\_USER)
+   * - 0x0008
+     - Support POSIX access control lists (ACLs). (EXT4\_DEFM\_ACL)
+   * - 0x0010
+     - Do not support 32-bit UIDs. (EXT4\_DEFM\_UID16)
+   * - 0x0020
+     - All data and metadata are commited to the journal.
+       (EXT4\_DEFM\_JMODE\_DATA)
+   * - 0x0040
+     - All data are flushed to the disk before metadata are committed to the
+       journal. (EXT4\_DEFM\_JMODE\_ORDERED)
+   * - 0x0060
+     - Data ordering is not preserved; data may be written after the metadata
+       has been written. (EXT4\_DEFM\_JMODE\_WBACK)
+   * - 0x0100
+     - Disable write flushes. (EXT4\_DEFM\_NOBARRIER)
+   * - 0x0200
+     - Track which blocks in a filesystem are metadata and therefore should not
+       be used as data blocks. This option will be enabled by default on 3.18,
+       hopefully. (EXT4\_DEFM\_BLOCK\_VALIDITY)
+   * - 0x0400
+     - Enable DISCARD support, where the storage device is told about blocks
+       becoming unused. (EXT4\_DEFM\_DISCARD)
+   * - 0x0800
+     - Disable delayed allocation. (EXT4\_DEFM\_NODELALLOC)
+
+.. _super_flags:
+
+The ``s_flags`` field is any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0001
+     - Signed directory hash in use.
+   * - 0x0002
+     - Unsigned directory hash in use.
+   * - 0x0004
+     - To test development code.
+
+.. _super_encrypt:
+
+The ``s_encrypt_algos`` list can contain any of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0
+     - Invalid algorithm (ENCRYPTION\_MODE\_INVALID).
+   * - 1
+     - 256-bit AES in XTS mode (ENCRYPTION\_MODE\_AES\_256\_XTS).
+   * - 2
+     - 256-bit AES in GCM mode (ENCRYPTION\_MODE\_AES\_256\_GCM).
+   * - 3
+     - 256-bit AES in CBC mode (ENCRYPTION\_MODE\_AES\_256\_CBC).
+
+Total size of the superblock is 1024 bytes.
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 53b89d0edc15..46d1b1be3a51 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -71,6 +71,39 @@ Other Functions
 .. kernel-doc:: fs/block_dev.c
    :export:
 
+.. kernel-doc:: fs/anon_inodes.c
+   :export:
+
+.. kernel-doc:: fs/attr.c
+   :export:
+
+.. kernel-doc:: fs/d_path.c
+   :export:
+
+.. kernel-doc:: fs/dax.c
+   :export:
+
+.. kernel-doc:: fs/direct-io.c
+   :export:
+
+.. kernel-doc:: fs/file_table.c
+   :export:
+
+.. kernel-doc:: fs/libfs.c
+   :export:
+
+.. kernel-doc:: fs/posix_acl.c
+   :export:
+
+.. kernel-doc:: fs/stat.c
+   :export:
+
+.. kernel-doc:: fs/sync.c
+   :export:
+
+.. kernel-doc:: fs/xattr.c
+   :export:
+
 The proc filesystem
 ===================
 
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 17bb4dc28fae..7b7b845c490a 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -602,3 +602,23 @@ in your dentry operations instead.
 	dentry separately, and it now has request_mask and query_flags arguments
 	to specify the fields and sync type requested by statx.  Filesystems not
 	supporting any statx-specific features may ignore the new arguments.
+--
+[mandatory]
+	->atomic_open() calling conventions have changed.  Gone is int *opened,
+	along with FILE_OPENED/FILE_CREATED.  In place of those we have
+	FMODE_OPENED/FMODE_CREATED, set in file->f_mode.  Additionally, return
+	value for 'called finish_no_open(), open it yourself' case has become
+	0, not 1.  Since finish_no_open() itself is returning 0 now, that part
+	does not need any changes in ->atomic_open() instances.
+--
+[mandatory]
+	alloc_file() has become static now; two wrappers are to be used instead.
+	alloc_file_pseudo(inode, vfsmount, name, flags, ops) is for the cases
+	when dentry needs to be created; that's the majority of old alloc_file()
+	users.  Calling conventions: on success a reference to new struct file
+	is returned and callers reference to inode is subsumed by that.  On
+	failure, ERR_PTR() is returned and no caller's references are affected,
+	so the caller needs to drop the inode reference it held.
+	alloc_file_clone(file, flags, ops) does not affect any caller's references.
+	On success you get a new struct file sharing the mount/dentry with the
+	original, on failure - ERR_PTR().
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index f608180ad59d..85907d5b9c2c 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -386,7 +386,7 @@ struct inode_operations {
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *, struct file *,
-			unsigned open_flag, umode_t create_mode, int *opened);
+			unsigned open_flag, umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 };
 
@@ -496,13 +496,15 @@ otherwise noted.
 
   atomic_open: called on the last component of an open.  Using this optional
   	method the filesystem can look up, possibly create and open the file in
-  	one atomic operation.  If it cannot perform this (e.g. the file type
-  	turned out to be wrong) it may signal this by returning 1 instead of
-	usual 0 or -ve .  This method is only called if the last component is
-	negative or needs lookup.  Cached positive dentries are still handled by
-	f_op->open().  If the file was created, the FILE_CREATED flag should be
-	set in "opened".  In case of O_EXCL the method must only succeed if the
-	file didn't exist and hence FILE_CREATED shall always be set on success.
+	one atomic operation.  If it wants to leave actual opening to the
+	caller (e.g. if the file turned out to be a symlink, device, or just
+	something filesystem won't do atomic open for), it may signal this by
+	returning finish_no_open(file, dentry).  This method is only called if
+	the last component is negative or needs lookup.  Cached positive dentries
+	are still handled by f_op->open().  If the file was created,
+	FMODE_CREATED flag should be set in file->f_mode.  In case of O_EXCL
+	the method must only succeed if the file didn't exist and hence FMODE_CREATED
+	shall always be set on success.
 
   tmpfile: called in the end of O_TMPFILE open().  Optional, equivalent to
 	atomically creating, opening and unlinking a file in given directory.
diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt
index 4d9ff0a7f8e1..a9ae82fb9d13 100644
--- a/Documentation/filesystems/xfs.txt
+++ b/Documentation/filesystems/xfs.txt
@@ -223,8 +223,6 @@ Deprecated Mount Options
 
   Name				Removal Schedule
   ----				----------------
-  barrier			no earlier than v4.15
-  nobarrier			no earlier than v4.15
 
 
 Removed Mount Options
@@ -236,6 +234,8 @@ Removed Mount Options
   ihashsize			v4.0
   irixsgid			v4.0
   osyncisdsync/osyncisosync	v4.0
+  barrier			v4.19
+  nobarrier			v4.19
 
 
 sysctls
diff --git a/Documentation/hwmon/max34440 b/Documentation/hwmon/max34440
index 9ba6587b7657..b2de8fa49273 100644
--- a/Documentation/hwmon/max34440
+++ b/Documentation/hwmon/max34440
@@ -16,6 +16,11 @@ Supported chips:
     Prefixes: 'max34446'
     Addresses scanned: -
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34446.pdf
+  * Maxim MAX34451
+    PMBus 16-Channel V/I Monitor and 12-Channel Sequencer/Marginer
+    Prefixes: 'max34451'
+    Addresses scanned: -
+    Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34451.pdf
   * Maxim MAX34460
     PMBus 12-Channel Voltage Monitor & Sequencer
     Prefix: 'max34460'
@@ -36,9 +41,10 @@ Description
 This driver supports hardware monitoring for Maxim MAX34440 PMBus 6-Channel
 Power-Supply Manager, MAX34441 PMBus 5-Channel Power-Supply Manager
 and Intelligent Fan Controller, and MAX34446 PMBus Power-Supply Data Logger.
-It also supports the MAX34460 and MAX34461 PMBus Voltage Monitor & Sequencers.
-The MAX34460 supports 12 voltage channels, and the MAX34461 supports 16 voltage
-channels.
+It also supports the MAX34451, MAX34460, and MAX34461 PMBus Voltage Monitor &
+Sequencers. The MAX34451 supports monitoring voltage or current of 12 channels
+based on GIN pins. The MAX34460 supports 12 voltage channels, and the MAX34461
+supports 16 voltage channels.
 
 The driver is a client driver to the core PMBus driver. Please see
 Documentation/hwmon/pmbus for details on PMBus client drivers.
@@ -93,7 +99,7 @@ curr[1-6]_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
 curr[1-6]_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT register.
 curr[1-6]_max_alarm	Current high alarm. From IOUT_OC_WARNING status.
 curr[1-6]_crit_alarm	Current critical high alarm. From IOUT_OC_FAULT status.
-curr[1-4]_average	Historical average current (MAX34446 only).
+curr[1-4]_average	Historical average current (MAX34446/34451 only).
 curr[1-6]_highest	Historical maximum current.
 curr[1-6]_reset_history	Write any value to reset history.
 
@@ -123,5 +129,7 @@ temp[1-8]_reset_history	Write any value to reset history.
 			temp7 and temp8 attributes only exist for MAX34440.
 			MAX34446 only supports temp[1-3].
 
+MAX34451 supports attribute groups in[1-16] (or curr[1-16] based on input pins)
+and temp[1-5].
 MAX34460 supports attribute groups in[1-12] and temp[1-5].
 MAX34461 supports attribute groups in[1-16] and temp[1-5].
diff --git a/Documentation/hwmon/mlxreg-fan b/Documentation/hwmon/mlxreg-fan
new file mode 100644
index 000000000000..fc531c6978d4
--- /dev/null
+++ b/Documentation/hwmon/mlxreg-fan
@@ -0,0 +1,60 @@
+Kernel driver mlxreg-fan
+========================
+
+Provides FAN control for the next Mellanox systems:
+QMB700, equipped with 40x200GbE InfiniBand ports;
+MSN3700, equipped with 32x200GbE or 16x400GbE Ethernet ports;
+MSN3410, equipped with 6x400GbE plus 48x50GbE Ethernet ports;
+MSN3800, equipped with 64x1000GbE Ethernet ports;
+These are the Top of the Rack systems, equipped with Mellanox switch
+board with Mellanox Quantum or Spectrume-2 devices.
+FAN controller is implemented by the programmable device logic.
+
+The default registers offsets set within the programmable device is as
+following:
+- pwm1			0xe3
+- fan1 (tacho1)		0xe4
+- fan2 (tacho2)		0xe5
+- fan3 (tacho3)		0xe6
+- fan4 (tacho4)		0xe7
+- fan5 (tacho5)		0xe8
+- fan6 (tacho6)		0xe9
+- fan7 (tacho7)		0xea
+- fan8 (tacho8)		0xeb
+- fan9 (tacho9)		0xec
+- fan10 (tacho10)	0xed
+- fan11 (tacho11)	0xee
+- fan12 (tacho12)	0xef
+This setup can be re-programmed with other registers.
+
+Author: Vadim Pasternak <vadimp@mellanox.com>
+
+Description
+-----------
+
+The driver implements a simple interface for driving a fan connected to
+a PWM output and tachometer inputs.
+This driver obtains PWM and tachometers registers location according to
+the system configuration and creates FAN/PWM hwmon objects and a cooling
+device. PWM and tachometers are sensed through the on-board programmable
+device, which exports its register map. This device could be attached to
+any bus type, for which register mapping is supported.
+Single instance is created with one PWM control, up to 12 tachometers and
+one cooling device. It could be as many instances as programmable device
+supports.
+The driver exposes the fan to the user space through the hwmon's and
+thermal's sysfs interfaces.
+
+/sys files in hwmon subsystem
+-----------------------------
+
+fan[1-12]_fault - RO files for tachometers TACH1-TACH12 fault indication
+fan[1-12]_input - RO files for tachometers TACH1-TACH12 input (in RPM)
+pwm1		- RW file for fan[1-12] target duty cycle (0..255)
+
+/sys files in thermal subsystem
+-------------------------------
+
+cur_state	- RW file for current cooling state of the cooling device
+		  (0..max_state)
+max_state	- RO file for maximum cooling state of the cooling device
diff --git a/Documentation/hwmon/npcm750-pwm-fan b/Documentation/hwmon/npcm750-pwm-fan
new file mode 100644
index 000000000000..6156ef7398e6
--- /dev/null
+++ b/Documentation/hwmon/npcm750-pwm-fan
@@ -0,0 +1,22 @@
+Kernel driver npcm750-pwm-fan
+=============================
+
+Supported chips:
+	NUVOTON NPCM750/730/715/705
+
+Authors:
+	<tomer.maimon@nuvoton.com>
+
+Description:
+------------
+This driver implements support for NUVOTON NPCM7XX PWM and Fan Tacho
+controller. The PWM controller supports up to 8 PWM outputs. The Fan tacho
+controller supports up to 16 tachometer inputs.
+
+The driver provides the following sensor accesses in sysfs:
+
+fanX_input	ro	provide current fan rotation value in RPM as reported
+			by the fan to the device.
+
+pwmX		rw	get or set PWM fan control value. This is an integer
+			value between 0(off) and 255(full speed).
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index fc337c317c67..2b9e1005d88b 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -171,6 +171,13 @@ in[0-*]_label	Suggested voltage channel label.
 		user-space.
 		RO
 
+in[0-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 cpu[0-*]_vid	CPU core reference voltage.
 		Unit: millivolt
 		RO
@@ -236,6 +243,13 @@ fan[1-*]_label	Suggested fan channel label.
 		In all other cases, the label is provided by user-space.
 		RO
 
+fan[1-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 Also see the Alarms section for status flags associated with fans.
 
 
@@ -409,6 +423,13 @@ temp_reset_history
 		Reset temp_lowest and temp_highest for all sensors
 		WO
 
+temp[1-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 Some chips measure temperature using external thermistors and an ADC, and
 report the temperature measurement as a voltage. Converting this voltage
 back to a temperature (or the other way around for limits) requires
@@ -468,6 +489,13 @@ curr_reset_history
 		Reset currX_lowest and currX_highest for all sensors
 		WO
 
+curr[1-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 Also see the Alarms section for status flags associated with currents.
 
 *********
@@ -566,6 +594,13 @@ power[1-*]_crit			Critical maximum power.
 				Unit: microWatt
 				RW
 
+power[1-*]_enable		Enable or disable the sensors.
+				When disabled the sensor read will return
+				-ENODATA.
+				1: Enable
+				0: Disable
+				RW
+
 Also see the Alarms section for status flags associated with power readings.
 
 **********
@@ -576,6 +611,12 @@ energy[1-*]_input		Cumulative energy use
 				Unit: microJoule
 				RO
 
+energy[1-*]_enable		Enable or disable the sensors.
+				When disabled the sensor read will return
+				-ENODATA.
+				1: Enable
+				0: Disable
+				RW
 
 ************
 * Humidity *
@@ -586,6 +627,13 @@ humidity[1-*]_input		Humidity
 				RO
 
 
+humidity[1-*]_enable		Enable or disable the sensors
+				When disabled the sensor read will return
+				-ENODATA.
+				1: Enable
+				0: Disable
+				RW
+
 **********
 * Alarms *
 **********
diff --git a/Documentation/index.rst b/Documentation/index.rst
index fdc585703498..f95ba981f8cd 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -102,6 +102,17 @@ implementation.
 
    sh/index
 
+Filesystem Documentation
+------------------------
+
+The documentation in this section are provided by specific filesystem
+subprojects.
+
+.. toctree::
+   :maxdepth: 2
+
+   filesystems/ext4/index
+
 Korean translations
 -------------------
 
diff --git a/Documentation/iostats.txt b/Documentation/iostats.txt
index 04d394a2e06c..49df45f90e8a 100644
--- a/Documentation/iostats.txt
+++ b/Documentation/iostats.txt
@@ -31,6 +31,9 @@ Here are examples of these different formats::
       3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
       3    1   hda1 35486 38030 38030 38030
 
+   4.18+ diskstats:
+      3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160 0 0 0 0
+
 On 2.4 you might execute ``grep 'hda ' /proc/partitions``. On 2.6+, you have
 a choice of ``cat /sys/block/hda/stat`` or ``grep 'hda ' /proc/diskstats``.
 
@@ -101,6 +104,18 @@ Field 11 -- weighted # of milliseconds spent doing I/Os
     last update of this field.  This can provide an easy measure of both
     I/O completion time and the backlog that may be accumulating.
 
+Field 12 -- # of discards completed
+    This is the total number of discards completed successfully.
+
+Field 13 -- # of discards merged
+    See the description of field 2
+
+Field 14 -- # of sectors discarded
+    This is the total number of sectors discarded successfully.
+
+Field 15 -- # of milliseconds spent discarding
+    This is the total number of milliseconds spent by all discards (as
+    measured from __make_request() to end_that_request_last()).
 
 To avoid introducing performance bottlenecks, no locks are held while
 modifying these counters.  This implies that minor inaccuracies may be
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index cb3b0de83fc6..10f4499e677c 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -80,6 +80,26 @@ After the instruction is single-stepped, Kprobes executes the
 "post_handler," if any, that is associated with the kprobe.
 Execution then continues with the instruction following the probepoint.
 
+Changing Execution Path
+-----------------------
+
+Since kprobes can probe into a running kernel code, it can change the
+register set, including instruction pointer. This operation requires
+maximum care, such as keeping the stack frame, recovering the execution
+path etc. Since it operates on a running kernel and needs deep knowledge
+of computer architecture and concurrent computing, you can easily shoot
+your foot.
+
+If you change the instruction pointer (and set up other related
+registers) in pre_handler, you must return !0 so that kprobes stops
+single stepping and just returns to the given address.
+This also means post_handler should not be called anymore.
+
+Note that this operation may be harder on some architectures which use
+TOC (Table of Contents) for function call, since you have to setup a new
+TOC for your function in your module, and recover the old one after
+returning from it.
+
 Return Probes
 -------------
 
@@ -262,7 +282,7 @@ is optimized, that modification is ignored.  Thus, if you want to
 tweak the kernel's execution path, you need to suppress optimization,
 using one of the following techniques:
 
-- Specify an empty function for the kprobe's post_handler or break_handler.
+- Specify an empty function for the kprobe's post_handler.
 
 or
 
@@ -474,7 +494,7 @@ error occurs during registration, all probes in the array, up to
 the bad probe, are safely unregistered before the register_*probes
 function returns.
 
-- kps/rps/jps: an array of pointers to ``*probe`` data structures
+- kps/rps: an array of pointers to ``*probe`` data structures
 - num: the number of the array entries.
 
 .. note::
@@ -566,12 +586,11 @@ the same handler) may run concurrently on different CPUs.
 Kprobes does not use mutexes or allocate memory except during
 registration and unregistration.
 
-Probe handlers are run with preemption disabled.  Depending on the
-architecture and optimization state, handlers may also run with
-interrupts disabled (e.g., kretprobe handlers and optimized kprobe
-handlers run without interrupt disabled on x86/x86-64).  In any case,
-your handler should not yield the CPU (e.g., by attempting to acquire
-a semaphore).
+Probe handlers are run with preemption disabled or interrupt disabled,
+which depends on the architecture and optimization state.  (e.g.,
+kretprobe handlers and optimized kprobe handlers run without interrupt
+disabled on x86/x86-64).  In any case, your handler should not yield
+the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O).
 
 Since a return probe is implemented by replacing the return
 address with the trampoline's address, stack backtraces and calls
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index a02d6bbfc9d0..0d8d7ef131e9 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -2179,32 +2179,41 @@ or:
 	event_indicated = 1;
 	wake_up_process(event_daemon);
 
-A write memory barrier is implied by wake_up() and co.  if and only if they
-wake something up.  The barrier occurs before the task state is cleared, and so
-sits between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+A general memory barrier is executed by wake_up() if it wakes something up.
+If it doesn't wake anything up then a memory barrier may or may not be
+executed; you must not rely on it.  The barrier occurs before the task state
+is accessed, in particular, it sits between the STORE to indicate the event
+and the STORE to set TASK_RUNNING:
 
-	CPU 1				CPU 2
+	CPU 1 (Sleeper)			CPU 2 (Waker)
 	===============================	===============================
 	set_current_state();		STORE event_indicated
 	  smp_store_mb();		wake_up();
-	    STORE current->state	  <write barrier>
-	    <general barrier>		  STORE current->state
-	LOAD event_indicated
+	    STORE current->state	  ...
+	    <general barrier>		  <general barrier>
+	LOAD event_indicated		  if ((LOAD task->state) & TASK_NORMAL)
+					    STORE task->state
 
-To repeat, this write memory barrier is present if and only if something
-is actually awakened.  To see this, consider the following sequence of
-events, where X and Y are both initially zero:
+where "task" is the thread being woken up and it equals CPU 1's "current".
+
+To repeat, a general memory barrier is guaranteed to be executed by wake_up()
+if something is actually awakened, but otherwise there is no such guarantee.
+To see this, consider the following sequence of events, where X and Y are both
+initially zero:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	X = 1;				STORE event_indicated
+	X = 1;				Y = 1;
 	smp_mb();			wake_up();
-	Y = 1;				wait_event(wq, Y == 1);
-	wake_up();			  load from Y sees 1, no memory barrier
-					load from X might see 0
+	LOAD Y				LOAD X
+
+If a wakeup does occur, one (at least) of the two loads must see 1.  If, on
+the other hand, a wakeup does not occur, both loads might see 0.
 
-In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed
-to see 1.
+wake_up_process() always executes a general memory barrier.  The barrier again
+occurs before the task state is accessed.  In particular, if the wake_up() in
+the previous snippet were replaced by a call to wake_up_process() then one of
+the two loads would be guaranteed to see 1.
 
 The available waker functions include:
 
@@ -2224,6 +2233,8 @@ The available waker functions include:
 	wake_up_poll();
 	wake_up_process();
 
+In terms of memory ordering, these functions all provide the same guarantees of
+a wake_up() (or stronger).
 
 [!] Note that the memory barriers implied by the sleeper and the waker do _not_
 order multiple stores before the wake-up with respect to loads of those stored
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index 921739d00f69..7f01fb1c1084 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -1891,22 +1891,22 @@ Mandatory 배리어들ì�€ SMP 시스템ì—�ì„œë�„ UP 시스템ì—�ì„œë�„ SMP 효ê³
 		/* 소유권� 수정 */
 		desc->status = DEVICE_OWN;
 
-		/* MMIO 를 통해 디바�스� 공지를 하기 전� 메모리를 �기화 */
-		wmb();
-
 		/* 업��트� 디스�립터� 디바�스� 공지 */
 		writel(DESC_NOTIFY, doorbell);
 	}
 
      dma_rmb() 는 디스�립터로부터 ��터를 �어오기 전� 디바�스가 소유권�
-     내놓았�� 보장하게 하고, dma_wmb() 는 디바�스가 �신� 소유권� 다시
-     가졌�� 보기 전� 디스�립터� ��터가 쓰였�� 보장합니다.  wmb() 는
-     �시 �관성� 없는 (cache incoherent) MMIO �역� 쓰기를 시�하기 전�
-     �시 �관성� 있는 메모리 (cache coherent memory) 쓰기가 완료�었��
-     보장해주기 위해 필요합니다.
-
-     consistent memory � 대한 �세한 내용� 위해선 Documentation/DMA-API.txt
-     문서를 참고하세요.
+     내려놓았� 것� 보장하고, dma_wmb() 는 디바�스가 �신� 소유권� 다시
+     가졌�� 보기 전� 디스�립터� ��터가 쓰였� 것� 보장합니다.  참고로,
+     writel() � 사용하면 �시 �관성� 있는 메모리 (cache coherent memory)
+     쓰기가 MMIO �역�� 쓰기 전� 완료�었� 것� 보장하므로 writel() 앞�
+     wmb() 를 실행할 필요가 없�� 알아�시기 바�니다.  writel() 보다 비용�
+     저렴한 writel_relaxed() 는 �런 보장� 제공하지 않으므로 여기선 사용�지
+     않아야 합니다.
+
+     writel_relaxed() 와 같� 완화� I/O 접근�들� 대한 �세한 내용� 위해서는
+     "커� I/O 배리어� 효과" 섹션�, consistent memory � 대한 �세한 내용�
+     위해선 Documentation/DMA-API.txt 문서를 참고하세요.
 
 
 MMIO 쓰기 배리어
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index d10944e619d3..cb8db4f9d097 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4391,6 +4391,22 @@ all such vmexits.
 
 Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
 
+7.14 KVM_CAP_S390_HPAGE_1M
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success, -EINVAL if hpage module parameter was not set
+	 or cmma is enabled
+
+With this capability the KVM support for memory backing with 1m pages
+through hugetlbfs can be enabled for a VM. After the capability is
+enabled, cmma can't be enabled anymore and pfmfi and the storage key
+interpretation are disabled. If cmma has already been enabled or the
+hpage module parameter is not set to 1, -EINVAL is returned.
+
+While it is generally possible to create a huge page backed VM without
+this capability, the VM will not be able to run.
+
 8. Other capabilities.
 ----------------------
 
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index a16aa2113840..f662d3c530e5 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -29,7 +29,11 @@ mount options are:
 L2 and L3 CDP are controlled seperately.
 
 RDT features are orthogonal. A particular system may support only
-monitoring, only control, or both monitoring and control.
+monitoring, only control, or both monitoring and control.  Cache
+pseudo-locking is a unique way of using cache control to "pin" or
+"lock" data in the cache. Details can be found in
+"Cache Pseudo-Locking".
+
 
 The mount succeeds if either of allocation or monitoring is present, but
 only those files and directories supported by the system will be created.
@@ -65,6 +69,29 @@ related to allocation:
 			some platforms support devices that have their
 			own settings for cache use which can over-ride
 			these bits.
+"bit_usage":		Annotated capacity bitmasks showing how all
+			instances of the resource are used. The legend is:
+			"0" - Corresponding region is unused. When the system's
+			      resources have been allocated and a "0" is found
+			      in "bit_usage" it is a sign that resources are
+			      wasted.
+			"H" - Corresponding region is used by hardware only
+			      but available for software use. If a resource
+			      has bits set in "shareable_bits" but not all
+			      of these bits appear in the resource groups'
+			      schematas then the bits appearing in
+			      "shareable_bits" but no resource group will
+			      be marked as "H".
+			"X" - Corresponding region is available for sharing and
+			      used by hardware and software. These are the
+			      bits that appear in "shareable_bits" as
+			      well as a resource group's allocation.
+			"S" - Corresponding region is used by software
+			      and available for sharing.
+			"E" - Corresponding region is used exclusively by
+			      one resource group. No sharing allowed.
+			"P" - Corresponding region is pseudo-locked. No
+			      sharing allowed.
 
 Memory bandwitdh(MB) subdirectory contains the following files
 with respect to allocation:
@@ -151,6 +178,9 @@ All groups contain the following files:
 	CPUs to/from this group. As with the tasks file a hierarchy is
 	maintained where MON groups may only include CPUs owned by the
 	parent CTRL_MON group.
+	When the resouce group is in pseudo-locked mode this file will
+	only be readable, reflecting the CPUs associated with the
+	pseudo-locked region.
 
 
 "cpus_list":
@@ -163,6 +193,21 @@ When control is enabled all CTRL_MON groups will also contain:
 	A list of all the resources available to this group.
 	Each resource has its own line and format - see below for details.
 
+"size":
+	Mirrors the display of the "schemata" file to display the size in
+	bytes of each allocation instead of the bits representing the
+	allocation.
+
+"mode":
+	The "mode" of the resource group dictates the sharing of its
+	allocations. A "shareable" resource group allows sharing of its
+	allocations while an "exclusive" resource group does not. A
+	cache pseudo-locked region is created by first writing
+	"pseudo-locksetup" to the "mode" file before writing the cache
+	pseudo-locked region's schemata to the resource group's "schemata"
+	file. On successful pseudo-locked region creation the mode will
+	automatically change to "pseudo-locked".
+
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
@@ -379,6 +424,170 @@ L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
 L3DATA:0=fffff;1=fffff;2=3c0;3=fffff
 L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
 
+Cache Pseudo-Locking
+--------------------
+CAT enables a user to specify the amount of cache space that an
+application can fill. Cache pseudo-locking builds on the fact that a
+CPU can still read and write data pre-allocated outside its current
+allocated area on a cache hit. With cache pseudo-locking, data can be
+preloaded into a reserved portion of cache that no application can
+fill, and from that point on will only serve cache hits. The cache
+pseudo-locked memory is made accessible to user space where an
+application can map it into its virtual address space and thus have
+a region of memory with reduced average read latency.
+
+The creation of a cache pseudo-locked region is triggered by a request
+from the user to do so that is accompanied by a schemata of the region
+to be pseudo-locked. The cache pseudo-locked region is created as follows:
+- Create a CAT allocation CLOSNEW with a CBM matching the schemata
+  from the user of the cache region that will contain the pseudo-locked
+  memory. This region must not overlap with any current CAT allocation/CLOS
+  on the system and no future overlap with this cache region is allowed
+  while the pseudo-locked region exists.
+- Create a contiguous region of memory of the same size as the cache
+  region.
+- Flush the cache, disable hardware prefetchers, disable preemption.
+- Make CLOSNEW the active CLOS and touch the allocated memory to load
+  it into the cache.
+- Set the previous CLOS as active.
+- At this point the closid CLOSNEW can be released - the cache
+  pseudo-locked region is protected as long as its CBM does not appear in
+  any CAT allocation. Even though the cache pseudo-locked region will from
+  this point on not appear in any CBM of any CLOS an application running with
+  any CLOS will be able to access the memory in the pseudo-locked region since
+  the region continues to serve cache hits.
+- The contiguous region of memory loaded into the cache is exposed to
+  user-space as a character device.
+
+Cache pseudo-locking increases the probability that data will remain
+in the cache via carefully configuring the CAT feature and controlling
+application behavior. There is no guarantee that data is placed in
+cache. Instructions like INVD, WBINVD, CLFLUSH, etc. can still evict
+“locked� data from cache. Power management C-states may shrink or
+power off cache. Deeper C-states will automatically be restricted on
+pseudo-locked region creation.
+
+It is required that an application using a pseudo-locked region runs
+with affinity to the cores (or a subset of the cores) associated
+with the cache on which the pseudo-locked region resides. A sanity check
+within the code will not allow an application to map pseudo-locked memory
+unless it runs with affinity to cores associated with the cache on which the
+pseudo-locked region resides. The sanity check is only done during the
+initial mmap() handling, there is no enforcement afterwards and the
+application self needs to ensure it remains affine to the correct cores.
+
+Pseudo-locking is accomplished in two stages:
+1) During the first stage the system administrator allocates a portion
+   of cache that should be dedicated to pseudo-locking. At this time an
+   equivalent portion of memory is allocated, loaded into allocated
+   cache portion, and exposed as a character device.
+2) During the second stage a user-space application maps (mmap()) the
+   pseudo-locked memory into its address space.
+
+Cache Pseudo-Locking Interface
+------------------------------
+A pseudo-locked region is created using the resctrl interface as follows:
+
+1) Create a new resource group by creating a new directory in /sys/fs/resctrl.
+2) Change the new resource group's mode to "pseudo-locksetup" by writing
+   "pseudo-locksetup" to the "mode" file.
+3) Write the schemata of the pseudo-locked region to the "schemata" file. All
+   bits within the schemata should be "unused" according to the "bit_usage"
+   file.
+
+On successful pseudo-locked region creation the "mode" file will contain
+"pseudo-locked" and a new character device with the same name as the resource
+group will exist in /dev/pseudo_lock. This character device can be mmap()'ed
+by user space in order to obtain access to the pseudo-locked memory region.
+
+An example of cache pseudo-locked region creation and usage can be found below.
+
+Cache Pseudo-Locking Debugging Interface
+---------------------------------------
+The pseudo-locking debugging interface is enabled by default (if
+CONFIG_DEBUG_FS is enabled) and can be found in /sys/kernel/debug/resctrl.
+
+There is no explicit way for the kernel to test if a provided memory
+location is present in the cache. The pseudo-locking debugging interface uses
+the tracing infrastructure to provide two ways to measure cache residency of
+the pseudo-locked region:
+1) Memory access latency using the pseudo_lock_mem_latency tracepoint. Data
+   from these measurements are best visualized using a hist trigger (see
+   example below). In this test the pseudo-locked region is traversed at
+   a stride of 32 bytes while hardware prefetchers and preemption
+   are disabled. This also provides a substitute visualization of cache
+   hits and misses.
+2) Cache hit and miss measurements using model specific precision counters if
+   available. Depending on the levels of cache on the system the pseudo_lock_l2
+   and pseudo_lock_l3 tracepoints are available.
+   WARNING: triggering this  measurement uses from two (for just L2
+   measurements) to four (for L2 and L3 measurements) precision counters on
+   the system, if any other measurements are in progress the counters and
+   their corresponding event registers will be clobbered.
+
+When a pseudo-locked region is created a new debugfs directory is created for
+it in debugfs as /sys/kernel/debug/resctrl/<newdir>. A single
+write-only file, pseudo_lock_measure, is present in this directory. The
+measurement on the pseudo-locked region depends on the number, 1 or 2,
+written to this debugfs file. Since the measurements are recorded with the
+tracing infrastructure the relevant tracepoints need to be enabled before the
+measurement is triggered.
+
+Example of latency debugging interface:
+In this example a pseudo-locked region named "newlock" was created. Here is
+how we can measure the latency in cycles of reading from this region and
+visualize this data with a histogram that is available if CONFIG_HIST_TRIGGERS
+is set:
+# :> /sys/kernel/debug/tracing/trace
+# echo 'hist:keys=latency' > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/trigger
+# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
+# echo 1 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure
+# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
+# cat /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/hist
+
+# event histogram
+#
+# trigger info: hist:keys=latency:vals=hitcount:sort=hitcount:size=2048 [active]
+#
+
+{ latency:        456 } hitcount:          1
+{ latency:         50 } hitcount:         83
+{ latency:         36 } hitcount:         96
+{ latency:         44 } hitcount:        174
+{ latency:         48 } hitcount:        195
+{ latency:         46 } hitcount:        262
+{ latency:         42 } hitcount:        693
+{ latency:         40 } hitcount:       3204
+{ latency:         38 } hitcount:       3484
+
+Totals:
+    Hits: 8192
+    Entries: 9
+   Dropped: 0
+
+Example of cache hits/misses debugging:
+In this example a pseudo-locked region named "newlock" was created on the L2
+cache of a platform. Here is how we can obtain details of the cache hits
+and misses using the platform's precision counters.
+
+# :> /sys/kernel/debug/tracing/trace
+# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable
+# echo 2 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure
+# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable
+# cat /sys/kernel/debug/tracing/trace
+
+# tracer: nop
+#
+#                              _-----=> irqs-off
+#                             / _----=> need-resched
+#                            | / _---=> hardirq/softirq
+#                            || / _--=> preempt-depth
+#                            ||| /     delay
+#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+#              | |       |   ||||       |         |
+ pseudo_lock_mea-1672  [002] ....  3132.860500: pseudo_lock_l2: hits=4097 miss=0
+
+
 Examples for RDT allocation usage:
 
 Example 1
@@ -502,7 +711,172 @@ siblings and only the real time threads are scheduled on the cores 4-7.
 
 # echo F0 > p0/cpus
 
-4) Locking between applications
+Example 4
+---------
+
+The resource groups in previous examples were all in the default "shareable"
+mode allowing sharing of their cache allocations. If one resource group
+configures a cache allocation then nothing prevents another resource group
+to overlap with that allocation.
+
+In this example a new exclusive resource group will be created on a L2 CAT
+system with two L2 cache instances that can be configured with an 8-bit
+capacity bitmask. The new exclusive resource group will be configured to use
+25% of each cache instance.
+
+# mount -t resctrl resctrl /sys/fs/resctrl/
+# cd /sys/fs/resctrl
+
+First, we observe that the default group is configured to allocate to all L2
+cache:
+
+# cat schemata
+L2:0=ff;1=ff
+
+We could attempt to create the new resource group at this point, but it will
+fail because of the overlap with the schemata of the default group:
+# mkdir p0
+# echo 'L2:0=0x3;1=0x3' > p0/schemata
+# cat p0/mode
+shareable
+# echo exclusive > p0/mode
+-sh: echo: write error: Invalid argument
+# cat info/last_cmd_status
+schemata overlaps
+
+To ensure that there is no overlap with another resource group the default
+resource group's schemata has to change, making it possible for the new
+resource group to become exclusive.
+# echo 'L2:0=0xfc;1=0xfc' > schemata
+# echo exclusive > p0/mode
+# grep . p0/*
+p0/cpus:0
+p0/mode:exclusive
+p0/schemata:L2:0=03;1=03
+p0/size:L2:0=262144;1=262144
+
+A new resource group will on creation not overlap with an exclusive resource
+group:
+# mkdir p1
+# grep . p1/*
+p1/cpus:0
+p1/mode:shareable
+p1/schemata:L2:0=fc;1=fc
+p1/size:L2:0=786432;1=786432
+
+The bit_usage will reflect how the cache is used:
+# cat info/L2/bit_usage
+0=SSSSSSEE;1=SSSSSSEE
+
+A resource group cannot be forced to overlap with an exclusive resource group:
+# echo 'L2:0=0x1;1=0x1' > p1/schemata
+-sh: echo: write error: Invalid argument
+# cat info/last_cmd_status
+overlaps with exclusive group
+
+Example of Cache Pseudo-Locking
+-------------------------------
+Lock portion of L2 cache from cache id 1 using CBM 0x3. Pseudo-locked
+region is exposed at /dev/pseudo_lock/newlock that can be provided to
+application for argument to mmap().
+
+# mount -t resctrl resctrl /sys/fs/resctrl/
+# cd /sys/fs/resctrl
+
+Ensure that there are bits available that can be pseudo-locked, since only
+unused bits can be pseudo-locked the bits to be pseudo-locked needs to be
+removed from the default resource group's schemata:
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSSSS
+# echo 'L2:1=0xfc' > schemata
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSS00
+
+Create a new resource group that will be associated with the pseudo-locked
+region, indicate that it will be used for a pseudo-locked region, and
+configure the requested pseudo-locked region capacity bitmask:
+
+# mkdir newlock
+# echo pseudo-locksetup > newlock/mode
+# echo 'L2:1=0x3' > newlock/schemata
+
+On success the resource group's mode will change to pseudo-locked, the
+bit_usage will reflect the pseudo-locked region, and the character device
+exposing the pseudo-locked region will exist:
+
+# cat newlock/mode
+pseudo-locked
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSSPP
+# ls -l /dev/pseudo_lock/newlock
+crw------- 1 root root 243, 0 Apr  3 05:01 /dev/pseudo_lock/newlock
+
+/*
+ * Example code to access one page of pseudo-locked cache region
+ * from user space.
+ */
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/mman.h>
+
+/*
+ * It is required that the application runs with affinity to only
+ * cores associated with the pseudo-locked region. Here the cpu
+ * is hardcoded for convenience of example.
+ */
+static int cpuid = 2;
+
+int main(int argc, char *argv[])
+{
+	cpu_set_t cpuset;
+	long page_size;
+	void *mapping;
+	int dev_fd;
+	int ret;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpuid, &cpuset);
+	ret = sched_setaffinity(0, sizeof(cpuset), &cpuset);
+	if (ret < 0) {
+		perror("sched_setaffinity");
+		exit(EXIT_FAILURE);
+	}
+
+	dev_fd = open("/dev/pseudo_lock/newlock", O_RDWR);
+	if (dev_fd < 0) {
+		perror("open");
+		exit(EXIT_FAILURE);
+	}
+
+	mapping = mmap(0, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		       dev_fd, 0);
+	if (mapping == MAP_FAILED) {
+		perror("mmap");
+		close(dev_fd);
+		exit(EXIT_FAILURE);
+	}
+
+	/* Application interacts with pseudo-locked memory @mapping */
+
+	ret = munmap(mapping, page_size);
+	if (ret < 0) {
+		perror("munmap");
+		close(dev_fd);
+		exit(EXIT_FAILURE);
+	}
+
+	close(dev_fd);
+	exit(EXIT_SUCCESS);
+}
+
+Locking between applications
+----------------------------
 
 Certain operations on the resctrl filesystem, composed of read/writes
 to/from multiple files, must be atomic.
@@ -510,7 +884,7 @@ to/from multiple files, must be atomic.
 As an example, the allocation of an exclusive reservation of L3 cache
 involves:
 
-  1. Read the cbmmasks from each directory
+  1. Read the cbmmasks from each directory or the per-resource "bit_usage"
   2. Find a contiguous set of bits in the global CBM bitmask that is clear
      in any of the directory cbmmasks
   3. Create a new directory
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 8d109ef67ab6..ad6d2a80cf05 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -92,9 +92,7 @@ APICs
 Timing
 
   notsc
-  Don't use the CPU time stamp counter to read the wall time.
-  This can be used to work around timing problems on multiprocessor systems
-  with not properly synchronized CPUs.
+  Deprecated, use tsc=unstable instead.
 
   nohpet
   Don't use the HPET timer.
@@ -156,6 +154,10 @@ NUMA
 		If given as an integer, fills all system RAM with N fake nodes
 		interleaved over physical nodes.
 
+  numa=fake=<N>U
+		If given as an integer followed by 'U', it will divide each
+		physical node into N emulated nodes.
+
 ACPI
 
   acpi=off	Don't enable ACPI
diff --git a/MAINTAINERS b/MAINTAINERS
index 7cebd5bba8a8..78608226c30a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5930,7 +5930,7 @@ F:	Documentation/dev-tools/gcov.rst
 
 GDB KERNEL DEBUGGING HELPER SCRIPTS
 M:	Jan Kiszka <jan.kiszka@siemens.com>
-M:	Kieran Bingham <kieran@bingham.xyz>
+M:	Kieran Bingham <kbingham@kernel.org>
 S:	Supported
 F:	scripts/gdb/
 
@@ -8317,10 +8317,16 @@ M:	Jade Alglave <j.alglave@ucl.ac.uk>
 M:	Luc Maranget <luc.maranget@inria.fr>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 R:	Akira Yokosawa <akiyks@gmail.com>
+R:	Daniel Lustig <dlustig@nvidia.com>
 L:	linux-kernel@vger.kernel.org
+L:	linux-arch@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	tools/memory-model/
+F:	Documentation/atomic_bitops.txt
+F:	Documentation/atomic_t.txt
+F:	Documentation/core-api/atomic_ops.rst
+F:	Documentation/core-api/refcount-vs-atomic.rst
 F:	Documentation/memory-barriers.txt
 
 LINUX SECURITY MODULE (LSM) FRAMEWORK
@@ -9347,7 +9353,6 @@ F:	drivers/media/platform/atmel/atmel-isc-regs.h
 F:	devicetree/bindings/media/atmel-isc.txt
 
 MICROCHIP / ATMEL NAND DRIVER
-M:	Wenyou Yang <wenyou.yang@microchip.com>
 M:	Josh Wu <rainyfeeling@outlook.com>
 L:	linux-mtd@lists.infradead.org
 S:	Supported
@@ -12039,9 +12044,9 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/
 X:	Documentation/RCU/torture.txt
 F:	include/linux/rcu*
-X:	include/linux/srcu.h
+X:	include/linux/srcu*.h
 F:	kernel/rcu/
-X:	kernel/torture.c
+X:	kernel/rcu/srcu*.c
 
 REAL TIME CLOCK (RTC) SUBSYSTEM
 M:	Alessandro Zummo <a.zummo@towertech.it>
@@ -12402,7 +12407,6 @@ F:	drivers/pci/hotplug/s390_pci_hpc.c
 
 S390 VFIO-CCW DRIVER
 M:	Cornelia Huck <cohuck@redhat.com>
-M:	Dong Jia Shi <bjsdjshi@linux.ibm.com>
 M:	Halil Pasic <pasic@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	kvm@vger.kernel.org
@@ -13078,8 +13082,8 @@ L:	linux-kernel@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
-F:	include/linux/srcu.h
-F:	kernel/rcu/srcu.c
+F:	include/linux/srcu*.h
+F:	kernel/rcu/srcu*.c
 
 SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus)
 M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
@@ -14058,6 +14062,13 @@ M:	Laxman Dewangan <ldewangan@nvidia.com>
 S:	Supported
 F:	drivers/input/keyboard/tegra-kbc.c
 
+TEGRA NAND DRIVER
+M:	Stefan Agner <stefan@agner.ch>
+M:	Lucas Stach <dev@lynxeye.de>
+S:	Maintained
+F:	Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt
+F:	drivers/mtd/nand/raw/tegra_nand.c
+
 TEGRA PWM DRIVER
 M:	Thierry Reding <thierry.reding@gmail.com>
 S:	Supported
@@ -14438,6 +14449,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/torture.txt
 F:	kernel/torture.c
 F:	kernel/rcu/rcutorture.c
+F:	kernel/rcu/rcuperf.c
 F:	kernel/locking/locktorture.c
 
 TOSHIBA ACPI EXTRAS DRIVER
diff --git a/Makefile b/Makefile
index 7a3c4548162b..863f58503bee 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 18
 SUBLEVEL = 0
-EXTRAVERSION = -rc8
+EXTRAVERSION =
 NAME = Merciless Moray
 
 # *DOCUMENTATION*
diff --git a/arch/Kconfig b/arch/Kconfig
index 1aa59063f1fd..d1f2ed462ac8 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -13,6 +13,9 @@ config KEXEC_CORE
 config HAVE_IMA_KEXEC
 	bool
 
+config HOTPLUG_SMT
+	bool
+
 config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 767bfdd42992..150a1c5d6a2c 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -18,11 +18,11 @@
  * To ensure dependency ordering is preserved for the _relaxed and
  * _release atomics, an smp_read_barrier_depends() is unconditionally
  * inserted into the _relaxed variants, which are used to build the
- * barriered versions. To avoid redundant back-to-back fences, we can
- * define the _acquire and _fence versions explicitly.
+ * barriered versions. Avoid redundant back-to-back fences in the
+ * _acquire and _fence versions.
  */
-#define __atomic_op_acquire(op, args...)	op##_relaxed(args)
-#define __atomic_op_fence			__atomic_op_release
+#define __atomic_acquire_fence()
+#define __atomic_post_full_fence()
 
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -206,7 +206,7 @@ ATOMIC_OPS(xor, xor)
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -214,7 +214,7 @@ ATOMIC_OPS(xor, xor)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, new, old;
 	smp_mb();
@@ -235,38 +235,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	smp_mb();
 	return old;
 }
-
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
  * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
+ * Returns the old value of @v.
  */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
-	long c, tmp;
+	long c, new, old;
 	smp_mb();
 	__asm__ __volatile__(
-	"1:	ldq_l	%[tmp],%[mem]\n"
-	"	cmpeq	%[tmp],%[u],%[c]\n"
-	"	addq	%[tmp],%[a],%[tmp]\n"
+	"1:	ldq_l	%[old],%[mem]\n"
+	"	cmpeq	%[old],%[u],%[c]\n"
+	"	addq	%[old],%[a],%[new]\n"
 	"	bne	%[c],2f\n"
-	"	stq_c	%[tmp],%[mem]\n"
-	"	beq	%[tmp],3f\n"
+	"	stq_c	%[new],%[mem]\n"
+	"	beq	%[new],3f\n"
 	"2:\n"
 	".subsection 2\n"
 	"3:	br	1b\n"
 	".previous"
-	: [tmp] "=&r"(tmp), [c] "=&r"(c)
+	: [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c)
 	: [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u)
 	: "memory");
 	smp_mb();
-	return !c;
+	return old;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
@@ -295,31 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	smp_mb();
 	return old - 1;
 }
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-#define atomic64_dec_return(v) atomic64_sub_return(1,(v))
-
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-#define atomic64_inc_return(v) atomic64_add_return(1,(v))
-
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0)
-#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0)
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
-#define atomic_inc(v) atomic_add(1,(v))
-#define atomic64_inc(v) atomic64_add(1,(v))
-
-#define atomic_dec(v) atomic_sub(1,(v))
-#define atomic64_dec(v) atomic64_sub(1,(v))
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #endif /* _ALPHA_ATOMIC_H */
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 11859287c52a..4e0072730241 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -187,7 +187,8 @@ static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
-#define atomic_andnot atomic_andnot
+#define atomic_andnot		atomic_andnot
+#define atomic_fetch_andnot	atomic_fetch_andnot
 
 #undef ATOMIC_OPS
 #define ATOMIC_OPS(op, c_op, asm_op)					\
@@ -296,8 +297,6 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
 	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
-#define atomic_andnot(mask, v) atomic_and(~(mask), (v))
-#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v))
 ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
 ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 
@@ -308,48 +307,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v
- */
-#define __atomic_add_unless(v, a, u)					\
-({									\
-	int c, old;							\
-									\
-	/*								\
-	 * Explicit full memory barrier needed before/after as		\
-	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
-	 */								\
-	smp_mb();							\
-									\
-	c = atomic_read(v);						\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
-		c = old;						\
-									\
-	smp_mb();							\
-									\
-	c;								\
-})
-
-#define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
-
-#define atomic_inc(v)			atomic_add(1, v)
-#define atomic_dec(v)			atomic_sub(1, v)
-
-#define atomic_inc_and_test(v)		(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i, v)	(atomic_add_return(i, v) < 0)
-
-
 #ifdef CONFIG_GENERIC_ATOMIC64
 
 #include <asm-generic/atomic64.h>
@@ -472,7 +429,8 @@ static inline long long atomic64_fetch_##op(long long a, atomic64_t *v)	\
 	ATOMIC64_OP_RETURN(op, op1, op2)				\
 	ATOMIC64_FETCH_OP(op, op1, op2)
 
-#define atomic64_andnot atomic64_andnot
+#define atomic64_andnot		atomic64_andnot
+#define atomic64_fetch_andnot	atomic64_fetch_andnot
 
 ATOMIC64_OPS(add, add.f, adc)
 ATOMIC64_OPS(sub, sub.f, sbc)
@@ -559,53 +517,43 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 
 	return val;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
- * if (v != u) { v += a; ret = 1} else {ret = 0}
- * Returns 1 iff @v was not @u (i.e. if add actually happened)
+ * Atomically adds @a to @v, if it was not @u.
+ * Returns the old value of @v
  */
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	long long val;
-	int op_done;
+	long long old, temp;
 
 	smp_mb();
 
 	__asm__ __volatile__(
 	"1:	llockd  %0, [%2]	\n"
-	"	mov	%1, 1		\n"
 	"	brne	%L0, %L4, 2f	# continue to add since v != u \n"
 	"	breq.d	%H0, %H4, 3f	# return since v == u \n"
-	"	mov	%1, 0		\n"
 	"2:				\n"
-	"	add.f   %L0, %L0, %L3	\n"
-	"	adc     %H0, %H0, %H3	\n"
-	"	scondd  %0, [%2]	\n"
+	"	add.f   %L1, %L0, %L3	\n"
+	"	adc     %H1, %H0, %H3	\n"
+	"	scondd  %1, [%2]	\n"
 	"	bnz     1b		\n"
 	"3:				\n"
-	: "=&r"(val), "=&r" (op_done)
+	: "=&r"(old), "=&r" (temp)
 	: "r"(&v->counter), "r"(a), "r"(u)
 	: "cc");	/* memory clobber comes from smp_mb() */
 
 	smp_mb();
 
-	return op_done;
+	return old;
 }
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif	/* !CONFIG_GENERIC_ATOMIC64 */
 
diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h
index 2e52d18e6bc7..2c1b479d5aea 100644
--- a/arch/arc/include/asm/kprobes.h
+++ b/arch/arc/include/asm/kprobes.h
@@ -45,8 +45,6 @@ struct prev_kprobe {
 
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 42b05046fad9..df35d4c0b0b8 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -225,24 +225,18 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
 
 		/* If we have no pre-handler or it returned 0, we continue with
 		 * normal processing. If we have a pre-handler and it returned
-		 * non-zero - which is expected from setjmp_pre_handler for
-		 * jprobe, we return without single stepping and leave that to
-		 * the break-handler which is invoked by a kprobe from
-		 * jprobe_return
+		 * non-zero - which means user handler setup registers to exit
+		 * to another instruction, we must skip the single stepping.
 		 */
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			setup_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_HIT_SS;
+		} else {
+			reset_current_kprobe();
+			preempt_enable_no_resched();
 		}
 
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			setup_singlestep(p, regs);
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			return 1;
-		}
 	}
 
 	/* no_kprobe: */
@@ -386,38 +380,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long sp_addr = regs->sp;
-
-	kcb->jprobe_saved_regs = *regs;
-	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
-	regs->ret = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	__asm__ __volatile__("unimp_s");
-	return;
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long sp_addr;
-
-	*regs = kcb->jprobe_saved_regs;
-	sp_addr = regs->sp;
-	memcpy((void *)sp_addr, kcb->jprobes_stack, MIN_STACK_SIZE(sp_addr));
-	preempt_enable_no_resched();
-
-	return 1;
-}
-
 static void __used kretprobe_trampoline_holder(void)
 {
 	__asm__ __volatile__(".global kretprobe_trampoline\n"
@@ -483,9 +445,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	regs->ret = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 843edfd000be..0f328d639d51 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -9,6 +9,7 @@ config ARM
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_SET_MEMORY
@@ -337,8 +338,8 @@ config ARCH_MULTIPLATFORM
 	select TIMER_OF
 	select COMMON_CLK
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select MIGHT_HAVE_PCI
-	select MULTI_IRQ_HANDLER
 	select PCI_DOMAINS if PCI
 	select SPARSE_IRQ
 	select USE_OF
@@ -465,9 +466,9 @@ config ARCH_DOVE
 	bool "Marvell Dove"
 	select CPU_PJ4
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select MIGHT_HAVE_PCI
-	select MULTI_IRQ_HANDLER
 	select MVEBU_MBUS
 	select PINCTRL
 	select PINCTRL_DOVE
@@ -512,8 +513,8 @@ config ARCH_LPC32XX
 	select COMMON_CLK
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
-	select MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 	select USE_OF
 	help
@@ -532,11 +533,11 @@ config ARCH_PXA
 	select TIMER_OF
 	select CPU_XSCALE if !CPU_XSC3
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIO_PXA
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
 	select PLAT_PXA
 	select SPARSE_IRQ
 	help
@@ -572,11 +573,11 @@ config ARCH_SA1100
 	select CPU_FREQ
 	select CPU_SA1100
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
 	select ISA
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_MEMORY_H
 	select SPARSE_IRQ
 	help
@@ -590,10 +591,10 @@ config ARCH_S3C24XX
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
 	select GPIOLIB
+	select GENERIC_IRQ_MULTI_HANDLER
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_S3C_RTC if RTC_CLASS
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_IO_H
 	select SAMSUNG_ATAGS
 	select USE_OF
@@ -627,10 +628,10 @@ config ARCH_OMAP1
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_IO_H if PCCARD
 	select NEED_MACH_MEMORY_H
 	select SPARSE_IRQ
@@ -921,11 +922,6 @@ config IWMMXT
 	  Enable support for iWMMXt context switching at run time if
 	  running on a CPU that supports it.
 
-config MULTI_IRQ_HANDLER
-	bool
-	help
-	  Allow each machine to specify it's own IRQ handler at run time.
-
 if !MMU
 source "arch/arm/Kconfig-nommu"
 endif
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index fc26c3d7b9b6..62ebeae9f837 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -46,12 +46,12 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN),y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__ARMEB__
 AS		+= -EB
-LD		+= -EB
+LDFLAGS		+= -EB
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 CHECKFLAGS	+= -D__ARMEL__
 AS		+= -EL
-LD		+= -EL
+LDFLAGS		+= -EL
 endif
 
 #
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 0cd4dccbae78..b17ee03d280b 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -460,6 +460,10 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	adds	\tmp, \addr, #\size - 1
 	sbcccs	\tmp, \tmp, \limit
 	bcs	\bad
+#ifdef CONFIG_CPU_SPECTRE
+	movcs	\addr, #0
+	csdb
+#endif
 #endif
 	.endm
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 66d0e215a773..f74756641410 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -130,7 +130,7 @@ static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
 }
 #define atomic_cmpxchg_relaxed		atomic_cmpxchg_relaxed
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int oldval, newval;
 	unsigned long tmp;
@@ -156,6 +156,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return oldval;
 }
+#define atomic_fetch_add_unless		atomic_fetch_add_unless
 
 #else /* ARM_ARCH_6 */
 
@@ -215,15 +216,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
-		c = old;
-	return c;
-}
+#define atomic_fetch_andnot		atomic_fetch_andnot
 
 #endif /* __LINUX_ARM_ARCH__ */
 
@@ -254,17 +247,6 @@ ATOMIC_OPS(xor, ^=, eor)
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-#define atomic_inc(v)		atomic_add(1, v)
-#define atomic_dec(v)		atomic_sub(1, v)
-
-#define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return_relaxed(v)    (atomic_add_return_relaxed(1, v))
-#define atomic_dec_return_relaxed(v)    (atomic_sub_return_relaxed(1, v))
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
-
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
 	long long counter;
@@ -494,12 +476,13 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 
 	return result;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	long long val;
+	long long oldval, newval;
 	unsigned long tmp;
-	int ret = 1;
 
 	smp_mb();
 	prefetchw(&v->counter);
@@ -508,33 +491,23 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 "1:	ldrexd	%0, %H0, [%4]\n"
 "	teq	%0, %5\n"
 "	teqeq	%H0, %H5\n"
-"	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%Q0, %Q0, %Q6\n"
-"	adc	%R0, %R0, %R6\n"
-"	strexd	%2, %0, %H0, [%4]\n"
+"	adds	%Q1, %Q0, %Q6\n"
+"	adc	%R1, %R0, %R6\n"
+"	strexd	%2, %1, %H1, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
 "2:"
-	: "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter)
+	: "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (u), "r" (a)
 	: "cc");
 
-	if (ret)
+	if (oldval != u)
 		smp_mb();
 
-	return ret;
+	return oldval;
 }
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1LL, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif /* !CONFIG_GENERIC_ATOMIC64 */
 #endif
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 4cab9bb823fb..c92e42a5c8f7 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -215,7 +215,6 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 
 #if __LINUX_ARM_ARCH__ < 5
 
-#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/fls.h>
@@ -223,93 +222,20 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 
 #else
 
-static inline int constant_fls(int x)
-{
-	int r = 32;
-
-	if (!x)
-		return 0;
-	if (!(x & 0xffff0000u)) {
-		x <<= 16;
-		r -= 16;
-	}
-	if (!(x & 0xff000000u)) {
-		x <<= 8;
-		r -= 8;
-	}
-	if (!(x & 0xf0000000u)) {
-		x <<= 4;
-		r -= 4;
-	}
-	if (!(x & 0xc0000000u)) {
-		x <<= 2;
-		r -= 2;
-	}
-	if (!(x & 0x80000000u)) {
-		x <<= 1;
-		r -= 1;
-	}
-	return r;
-}
-
-/*
- * On ARMv5 and above those functions can be implemented around the
- * clz instruction for much better code efficiency.  __clz returns
- * the number of leading zeros, zero input will return 32, and
- * 0x80000000 will return 0.
- */
-static inline unsigned int __clz(unsigned int x)
-{
-	unsigned int ret;
-
-	asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
-
-	return ret;
-}
-
-/*
- * fls() returns zero if the input is zero, otherwise returns the bit
- * position of the last set bit, where the LSB is 1 and MSB is 32.
- */
-static inline int fls(int x)
-{
-	if (__builtin_constant_p(x))
-	       return constant_fls(x);
-
-	return 32 - __clz(x);
-}
-
-/*
- * __fls() returns the bit position of the last bit set, where the
- * LSB is 0 and MSB is 31.  Zero input is undefined.
- */
-static inline unsigned long __fls(unsigned long x)
-{
-	return fls(x) - 1;
-}
-
-/*
- * ffs() returns zero if the input was zero, otherwise returns the bit
- * position of the first set bit, where the LSB is 1 and MSB is 32.
- */
-static inline int ffs(int x)
-{
-	return fls(x & -x);
-}
-
 /*
- * __ffs() returns the bit position of the first bit set, where the
- * LSB is 0 and MSB is 31.  Zero input is undefined.
+ * On ARMv5 and above, the gcc built-ins may rely on the clz instruction
+ * and produce optimal inlined code in all cases. On ARMv7 it is even
+ * better by also using the rbit instruction.
  */
-static inline unsigned long __ffs(unsigned long x)
-{
-	return ffs(x) - 1;
-}
-
-#define ffz(x) __ffs( ~(x) )
+#include <asm-generic/bitops/builtin-__fls.h>
+#include <asm-generic/bitops/builtin-__ffs.h>
+#include <asm-generic/bitops/builtin-fls.h>
+#include <asm-generic/bitops/builtin-ffs.h>
 
 #endif
 
+#include <asm-generic/bitops/ffz.h>
+
 #include <asm-generic/bitops/fls64.h>
 
 #include <asm-generic/bitops/sched.h>
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 17f1f1a814ff..38badaae8d9d 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -58,6 +58,9 @@ void efi_virtmap_unload(void);
 #define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
 #define efi_is_64bit()			(false)
 
+#define efi_table_attr(table, attr, instance)				\
+	((table##_t *)instance)->attr
+
 #define efi_call_proto(protocol, f, instance, ...)			\
 	((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
 
diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index e46e4e7bdba3..ac54c06764e6 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -111,14 +111,17 @@ static inline void decode_ctrl_reg(u32 reg,
 	asm volatile("mcr p14, 0, %0, " #N "," #M ", " #OP2 : : "r" (VAL));\
 } while (0)
 
+struct perf_event_attr;
 struct notifier_block;
 struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  int *gen_len, int *gen_type);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index b6f319606e30..c883fcbe93b6 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -31,11 +31,6 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *);
 void handle_IRQ(unsigned int, struct pt_regs *);
 void init_IRQ(void);
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-extern void (*handle_arch_irq)(struct pt_regs *);
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-#endif
-
 #ifdef CONFIG_SMP
 extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
 					   bool exclude_self);
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index 59655459da59..82290f212d8e 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -44,8 +44,6 @@ struct prev_kprobe {
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
 	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 5c1ad11aa392..bb8851208e17 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -59,7 +59,7 @@ struct machine_desc {
 	void			(*init_time)(void);
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	void			(*handle_irq)(struct pt_regs *);
 #endif
 	void			(*restart)(enum reboot_mode, const char *);
diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index 0f79e4dec7f9..4ac3a019a46f 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -13,7 +13,6 @@
 extern void timer_tick(void);
 
 typedef void (*clock_access_fn)(struct timespec64 *);
-extern int register_persistent_clock(clock_access_fn read_boot,
-				     clock_access_fn read_persistent);
+extern int register_persistent_clock(clock_access_fn read_persistent);
 
 #endif
diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h
index 1e5b9bb92270..991c9127c650 100644
--- a/arch/arm/include/asm/probes.h
+++ b/arch/arm/include/asm/probes.h
@@ -51,7 +51,6 @@ struct arch_probes_insn {
  * We assume one instruction can consume at most 64 bytes stack, which is
  * 'push {r0-r15}'. Instructions consume more or unknown stack space like
  * 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe.
- * Both kprobe and jprobe use this macro.
  */
 #define MAX_STACK_SIZE			64
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index e71cc35de163..9b37b6ab27fe 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -123,8 +123,8 @@ struct user_vfp_exc;
 
 extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *,
 					   struct user_vfp_exc __user *);
-extern int vfp_restore_user_hwstate(struct user_vfp __user *,
-				    struct user_vfp_exc __user *);
+extern int vfp_restore_user_hwstate(struct user_vfp *,
+				    struct user_vfp_exc *);
 #endif
 
 /*
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index d5562f9ce600..f854148c8d7c 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -292,5 +292,13 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 {
 }
 
+static inline void tlb_flush_remove_tables(struct mm_struct *mm)
+{
+}
+
+static inline void tlb_flush_remove_tables_local(void *arg)
+{
+}
+
 #endif /* CONFIG_MMU */
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 3d614e90c19f..5451e1f05a19 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -85,6 +85,13 @@ static inline void set_fs(mm_segment_t fs)
 	flag; })
 
 /*
+ * This is a type: either unsigned long, if the argument fits into
+ * that type, or otherwise unsigned long long.
+ */
+#define __inttype(x) \
+	__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
+
+/*
  * Single-value transfer routines.  They automatically use the right
  * size if we just have the right pointer type.  Note that the functions
  * which read from user space (*get_*) need to take care not to leak
@@ -153,7 +160,7 @@ extern int __get_user_64t_4(void *);
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register typeof(*(p)) __user *__p asm("r0") = (p);	\
-		register typeof(x) __r2 asm("r2");			\
+		register __inttype(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		unsigned int __ua_flags = uaccess_save_and_enable();	\
@@ -243,6 +250,16 @@ static inline void set_fs(mm_segment_t fs)
 #define user_addr_max() \
 	(uaccess_kernel() ? ~0UL : get_fs())
 
+#ifdef CONFIG_CPU_SPECTRE
+/*
+ * When mitigating Spectre variant 1, it is not worth fixing the non-
+ * verifying accessors, because we need to add verification of the
+ * address space there.  Force these to use the standard get_user()
+ * version instead.
+ */
+#define __get_user(x, ptr) get_user(x, ptr)
+#else
+
 /*
  * The "__xxx" versions of the user access functions do not verify the
  * address space - it must have been done previously with a separate
@@ -259,12 +276,6 @@ static inline void set_fs(mm_segment_t fs)
 	__gu_err;							\
 })
 
-#define __get_user_error(x, ptr, err)					\
-({									\
-	__get_user_err((x), (ptr), err);				\
-	(void) 0;							\
-})
-
 #define __get_user_err(x, ptr, err)					\
 do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
@@ -324,6 +335,7 @@ do {									\
 
 #define __get_user_asm_word(x, addr, err)			\
 	__get_user_asm(x, addr, err, ldr)
+#endif
 
 
 #define __put_user_switch(x, ptr, __err, __fn)				\
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 179a9f6bd1e3..e85a3af9ddeb 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -22,7 +22,7 @@
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
 #include <asm/vfpmacros.h>
-#ifndef CONFIG_MULTI_IRQ_HANDLER
+#ifndef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 #include <mach/entry-macro.S>
 #endif
 #include <asm/thread_notify.h>
@@ -39,7 +39,7 @@
  * Interrupt handling.
  */
 	.macro	irq_handler
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	ldr	r1, =handle_arch_irq
 	mov	r0, sp
 	badr	lr, 9997f
@@ -1226,9 +1226,3 @@ vector_addrexcptn:
 	.globl	cr_alignment
 cr_alignment:
 	.space	4
-
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-	.globl	handle_arch_irq
-handle_arch_irq:
-	.space	4
-#endif
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 7a9b86978ee1..ec29de250076 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -53,7 +53,11 @@ ENTRY(stext)
  THUMB(1:			)
 #endif
 
-	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
+#ifdef CONFIG_ARM_VIRT_EXT
+	bl	__hyp_stub_install
+#endif
+	@ ensure svc mode and all interrupts masked
+	safe_svcmode_maskall r9
 						@ and irqs disabled
 #if defined(CONFIG_CPU_CP15)
 	mrc	p15, 0, r9, c0, c0		@ get processor id
@@ -89,7 +93,11 @@ ENTRY(secondary_startup)
 	 * the processor type - there is no need to check the machine type
 	 * as it has already been validated by the primary processor.
 	 */
-	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
+#ifdef CONFIG_ARM_VIRT_EXT
+	bl	__hyp_stub_install_secondary
+#endif
+	safe_svcmode_maskall r9
+
 #ifndef CONFIG_CPU_CP15
 	ldr	r9, =CONFIG_PROCESSOR_ID
 #else
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 629e25152c0d..1d5fbf1d1c67 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -456,14 +456,13 @@ static int get_hbp_len(u8 hbp_len)
 /*
  * Check whether bp virtual address is in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->ctrl.len);
+	va = hw->address;
+	len = get_hbp_len(hw->ctrl.len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -518,42 +517,42 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+		hw->ctrl.type = ARM_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->ctrl.type = ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
-		if ((info->ctrl.type != ARM_BREAKPOINT_EXECUTE)
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
+		if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE)
 			&& max_watchpoint_len >= 8)
 			break;
 	default:
@@ -566,24 +565,24 @@ static int arch_build_bp_info(struct perf_event *bp)
 	 * by the hardware and must be aligned to the appropriate number of
 	 * bytes.
 	 */
-	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
-	    info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
-	    info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+	if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
+	    hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+	    hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
 		return -EINVAL;
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/* Privilege */
-	info->ctrl.privilege = ARM_BREAKPOINT_USER;
-	if (arch_check_bp_in_kernelspace(bp))
-		info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
+	hw->ctrl.privilege = ARM_BREAKPOINT_USER;
+	if (arch_check_bp_in_kernelspace(hw))
+		hw->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
 
 	/* Enabled? */
-	info->ctrl.enabled = !bp->attr.disabled;
+	hw->ctrl.enabled = !attr->disabled;
 
 	/* Mismatch */
-	info->ctrl.mismatch = 0;
+	hw->ctrl.mismatch = 0;
 
 	return 0;
 }
@@ -591,9 +590,10 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings.
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	int ret = 0;
 	u32 offset, alignment_mask = 0x3;
 
@@ -602,14 +602,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		return -ENODEV;
 
 	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		goto out;
 
 	/* Check address alignment. */
-	if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+	if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
 		alignment_mask = 0x7;
-	offset = info->address & alignment_mask;
+	offset = hw->address & alignment_mask;
 	switch (offset) {
 	case 0:
 		/* Aligned */
@@ -617,19 +617,19 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	case 1:
 	case 2:
 		/* Allow halfword watchpoints and breakpoints. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
 	case 3:
 		/* Allow single byte watchpoint. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 			break;
 	default:
 		ret = -EINVAL;
 		goto out;
 	}
 
-	info->address &= ~alignment_mask;
-	info->ctrl.len <<= offset;
+	hw->address &= ~alignment_mask;
+	hw->ctrl.len <<= offset;
 
 	if (is_default_overflow_handler(bp)) {
 		/*
@@ -640,7 +640,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 			return -EINVAL;
 
 		/* We don't allow mismatch breakpoints in kernel space. */
-		if (arch_check_bp_in_kernelspace(bp))
+		if (arch_check_bp_in_kernelspace(hw))
 			return -EPERM;
 
 		/*
@@ -655,8 +655,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		 * reports them.
 		 */
 		if (!debug_exception_updates_fsr() &&
-		    (info->ctrl.type == ARM_BREAKPOINT_LOAD ||
-		     info->ctrl.type == ARM_BREAKPOINT_STORE))
+		    (hw->ctrl.type == ARM_BREAKPOINT_LOAD ||
+		     hw->ctrl.type == ARM_BREAKPOINT_STORE))
 			return -EINVAL;
 	}
 
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index ece04a457486..9908dacf9229 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -102,16 +102,6 @@ void __init init_IRQ(void)
 	uniphier_cache_init();
 }
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	if (handle_arch_irq)
-		return;
-
-	handle_arch_irq = handle_irq;
-}
-#endif
-
 #ifdef CONFIG_SPARSE_IRQ
 int __init arch_probe_nr_irqs(void)
 {
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 35ca494c028c..4c249cb261f3 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1145,7 +1145,7 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_crashkernel();
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	handle_arch_irq = mdesc->handle_irq;
 #endif
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index dec130e7078c..b8f766cf3a90 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -150,22 +150,18 @@ static int preserve_vfp_context(struct vfp_sigframe __user *frame)
 
 static int restore_vfp_context(char __user **auxp)
 {
-	struct vfp_sigframe __user *frame =
-		(struct vfp_sigframe __user *)*auxp;
-	unsigned long magic;
-	unsigned long size;
-	int err = 0;
-
-	__get_user_error(magic, &frame->magic, err);
-	__get_user_error(size, &frame->size, err);
+	struct vfp_sigframe frame;
+	int err;
 
+	err = __copy_from_user(&frame, *auxp, sizeof(frame));
 	if (err)
-		return -EFAULT;
-	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
+		return err;
+
+	if (frame.magic != VFP_MAGIC || frame.size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
-	*auxp += size;
-	return vfp_restore_user_hwstate(&frame->ufp, &frame->ufp_exc);
+	*auxp += sizeof(frame);
+	return vfp_restore_user_hwstate(&frame.ufp, &frame.ufp_exc);
 }
 
 #endif
@@ -176,6 +172,7 @@ static int restore_vfp_context(char __user **auxp)
 
 static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 {
+	struct sigcontext context;
 	char __user *aux;
 	sigset_t set;
 	int err;
@@ -184,23 +181,26 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 	if (err == 0)
 		set_current_blocked(&set);
 
-	__get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
-	__get_user_error(regs->ARM_r1, &sf->uc.uc_mcontext.arm_r1, err);
-	__get_user_error(regs->ARM_r2, &sf->uc.uc_mcontext.arm_r2, err);
-	__get_user_error(regs->ARM_r3, &sf->uc.uc_mcontext.arm_r3, err);
-	__get_user_error(regs->ARM_r4, &sf->uc.uc_mcontext.arm_r4, err);
-	__get_user_error(regs->ARM_r5, &sf->uc.uc_mcontext.arm_r5, err);
-	__get_user_error(regs->ARM_r6, &sf->uc.uc_mcontext.arm_r6, err);
-	__get_user_error(regs->ARM_r7, &sf->uc.uc_mcontext.arm_r7, err);
-	__get_user_error(regs->ARM_r8, &sf->uc.uc_mcontext.arm_r8, err);
-	__get_user_error(regs->ARM_r9, &sf->uc.uc_mcontext.arm_r9, err);
-	__get_user_error(regs->ARM_r10, &sf->uc.uc_mcontext.arm_r10, err);
-	__get_user_error(regs->ARM_fp, &sf->uc.uc_mcontext.arm_fp, err);
-	__get_user_error(regs->ARM_ip, &sf->uc.uc_mcontext.arm_ip, err);
-	__get_user_error(regs->ARM_sp, &sf->uc.uc_mcontext.arm_sp, err);
-	__get_user_error(regs->ARM_lr, &sf->uc.uc_mcontext.arm_lr, err);
-	__get_user_error(regs->ARM_pc, &sf->uc.uc_mcontext.arm_pc, err);
-	__get_user_error(regs->ARM_cpsr, &sf->uc.uc_mcontext.arm_cpsr, err);
+	err |= __copy_from_user(&context, &sf->uc.uc_mcontext, sizeof(context));
+	if (err == 0) {
+		regs->ARM_r0 = context.arm_r0;
+		regs->ARM_r1 = context.arm_r1;
+		regs->ARM_r2 = context.arm_r2;
+		regs->ARM_r3 = context.arm_r3;
+		regs->ARM_r4 = context.arm_r4;
+		regs->ARM_r5 = context.arm_r5;
+		regs->ARM_r6 = context.arm_r6;
+		regs->ARM_r7 = context.arm_r7;
+		regs->ARM_r8 = context.arm_r8;
+		regs->ARM_r9 = context.arm_r9;
+		regs->ARM_r10 = context.arm_r10;
+		regs->ARM_fp = context.arm_fp;
+		regs->ARM_ip = context.arm_ip;
+		regs->ARM_sp = context.arm_sp;
+		regs->ARM_lr = context.arm_lr;
+		regs->ARM_pc = context.arm_pc;
+		regs->ARM_cpsr = context.arm_cpsr;
+	}
 
 	err |= !valid_user_regs(regs);
 
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 1df21a61e379..f0dd4b6ebb63 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -329,9 +329,11 @@ asmlinkage long sys_oabi_semtimedop(int semid,
 		return -ENOMEM;
 	err = 0;
 	for (i = 0; i < nsops; i++) {
-		__get_user_error(sops[i].sem_num, &tsops->sem_num, err);
-		__get_user_error(sops[i].sem_op,  &tsops->sem_op,  err);
-		__get_user_error(sops[i].sem_flg, &tsops->sem_flg, err);
+		struct oabi_sembuf osb;
+		err |= __copy_from_user(&osb, tsops, sizeof(osb));
+		sops[i].sem_num = osb.sem_num;
+		sops[i].sem_op = osb.sem_op;
+		sops[i].sem_flg = osb.sem_flg;
 		tsops++;
 	}
 	if (timeout) {
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index cf2701cb0de8..078b259ead4e 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -83,29 +83,18 @@ static void dummy_clock_access(struct timespec64 *ts)
 }
 
 static clock_access_fn __read_persistent_clock = dummy_clock_access;
-static clock_access_fn __read_boot_clock = dummy_clock_access;
 
 void read_persistent_clock64(struct timespec64 *ts)
 {
 	__read_persistent_clock(ts);
 }
 
-void read_boot_clock64(struct timespec64 *ts)
-{
-	__read_boot_clock(ts);
-}
-
-int __init register_persistent_clock(clock_access_fn read_boot,
-				     clock_access_fn read_persistent)
+int __init register_persistent_clock(clock_access_fn read_persistent)
 {
 	/* Only allow the clockaccess functions to be registered once */
-	if (__read_persistent_clock == dummy_clock_access &&
-	    __read_boot_clock == dummy_clock_access) {
-		if (read_boot)
-			__read_boot_clock = read_boot;
+	if (__read_persistent_clock == dummy_clock_access) {
 		if (read_persistent)
 			__read_persistent_clock = read_persistent;
-
 		return 0;
 	}
 
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 7a4b06049001..a826df3d3814 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -90,6 +90,15 @@
 	.text
 
 ENTRY(arm_copy_from_user)
+#ifdef CONFIG_CPU_SPECTRE
+	get_thread_info r3
+	ldr	r3, [r3, #TI_ADDR_LIMIT]
+	adds	ip, r1, r2	@ ip=addr+size
+	sub	r3, r3, #1	@ addr_limit - 1
+	cmpcc	ip, r3		@ if (addr+size > addr_limit - 1)
+	movcs	r1, #0		@ addr = NULL
+	csdb
+#endif
 
 #include "copy_template.S"
 
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index f4f8f23bda8c..af46d2182533 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -688,7 +688,6 @@ struct platform_nand_data balloon3_nand_pdata = {
 		.chip_delay	= 50,
 	},
 	.ctrl = {
-		.hwcontrol	= 0,
 		.dev_ready	= balloon3_nand_dev_ready,
 		.select_chip	= balloon3_nand_select_chip,
 		.cmd_ctrl	= balloon3_nand_cmd_ctl,
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 49022ad338e9..29be04c6cc48 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -346,7 +346,6 @@ struct platform_nand_data em_x270_nand_platdata = {
 		.chip_delay = 20,
 	},
 	.ctrl = {
-		.hwcontrol = 0,
 		.dev_ready = em_x270_nand_device_ready,
 		.select_chip = 0,
 		.cmd_ctrl = em_x270_nand_cmd_ctl,
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 96a7b6cf459b..b169e580bf82 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -702,7 +702,6 @@ config ARM_THUMBEE
 
 config ARM_VIRT_EXT
 	bool
-	depends on MMU
 	default y if CPU_V7
 	help
 	  Enable the kernel to make use of the ARM Virtualization
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 5dd6c58d653b..7d67c70bbded 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -53,7 +53,8 @@ static inline bool security_extensions_enabled(void)
 {
 	/* Check CPUID Identification Scheme before ID_PFR1 read */
 	if ((read_cpuid_id() & 0x000f0000) == 0x000f0000)
-		return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+		return cpuid_feature_extract(CPUID_EXT_PFR1, 4) ||
+			cpuid_feature_extract(CPUID_EXT_PFR1, 20);
 	return 0;
 }
 
diff --git a/arch/arm/mm/tcm.h b/arch/arm/mm/tcm.h
index 8015ad434a40..24101925fe64 100644
--- a/arch/arm/mm/tcm.h
+++ b/arch/arm/mm/tcm.h
@@ -11,7 +11,7 @@
 void __init tcm_init(void);
 #else
 /* No TCM support, just blank inlines to be optimized out */
-inline void tcm_init(void)
+static inline void tcm_init(void)
 {
 }
 #endif
diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c
index 2438b96004c1..fcc5bfec8bd1 100644
--- a/arch/arm/plat-omap/counter_32k.c
+++ b/arch/arm/plat-omap/counter_32k.c
@@ -110,7 +110,7 @@ int __init omap_init_clocksource_32k(void __iomem *vbase)
 	}
 
 	sched_clock_register(omap_32k_read_sched_clock, 32, 32768);
-	register_persistent_clock(NULL, omap_read_persistent_clock64);
+	register_persistent_clock(omap_read_persistent_clock64);
 	pr_info("OMAP clocksource: 32k_counter at 32768 Hz\n");
 
 	return 0;
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index e90cc8a08186..f8bd523d64d1 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -47,9 +47,6 @@
 			   (unsigned long)(addr) +	\
 			   (size))
 
-/* Used as a marker in ARM_pc to note when we're in a jprobe. */
-#define JPROBE_MAGIC_ADDR		0xffffffff
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -289,8 +286,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				break;
 			case KPROBE_REENTER:
 				/* A nested probe was hit in FIQ, it is a BUG */
-				pr_warn("Unrecoverable kprobe detected at %p.\n",
-					p->addr);
+				pr_warn("Unrecoverable kprobe detected.\n");
+				dump_kprobe(p);
 				/* fall through */
 			default:
 				/* impossible cases */
@@ -303,10 +300,10 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 
 			/*
 			 * If we have no pre-handler or it returned 0, we
-			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry,
-			 * so get out doing nothing more here.
+			 * continue with normal processing. If we have a
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				kcb->kprobe_status = KPROBE_HIT_SS;
@@ -315,20 +312,9 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 					kcb->kprobe_status = KPROBE_HIT_SSDONE;
 					p->post_handler(p, regs, 0);
 				}
-				reset_current_kprobe();
-			}
-		}
-	} else if (cur) {
-		/* We probably hit a jprobe.  Call its break handler. */
-		if (cur->break_handler && cur->break_handler(cur, regs)) {
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			singlestep(cur, regs, kcb);
-			if (cur->post_handler) {
-				kcb->kprobe_status = KPROBE_HIT_SSDONE;
-				cur->post_handler(cur, regs, 0);
 			}
+			reset_current_kprobe();
 		}
-		reset_current_kprobe();
 	} else {
 		/*
 		 * The probe was removed and a race is in progress.
@@ -521,117 +507,6 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	regs->ARM_lr = (unsigned long)&kretprobe_trampoline;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long sp_addr = regs->ARM_sp;
-	long cpsr;
-
-	kcb->jprobe_saved_regs = *regs;
-	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
-	regs->ARM_pc = (long)jp->entry;
-
-	cpsr = regs->ARM_cpsr | PSR_I_BIT;
-#ifdef CONFIG_THUMB2_KERNEL
-	/* Set correct Thumb state in cpsr */
-	if (regs->ARM_pc & 1)
-		cpsr |= PSR_T_BIT;
-	else
-		cpsr &= ~PSR_T_BIT;
-#endif
-	regs->ARM_cpsr = cpsr;
-
-	preempt_disable();
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	__asm__ __volatile__ (
-		/*
-		 * Setup an empty pt_regs. Fill SP and PC fields as
-		 * they're needed by longjmp_break_handler.
-		 *
-		 * We allocate some slack between the original SP and start of
-		 * our fabricated regs. To be precise we want to have worst case
-		 * covered which is STMFD with all 16 regs so we allocate 2 *
-		 * sizeof(struct_pt_regs)).
-		 *
-		 * This is to prevent any simulated instruction from writing
-		 * over the regs when they are accessing the stack.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"sub    r0, %0, %1		\n\t"
-		"mov    sp, r0			\n\t"
-#else
-		"sub    sp, %0, %1		\n\t"
-#endif
-		"ldr    r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
-		"str    %0, [sp, %2]		\n\t"
-		"str    r0, [sp, %3]		\n\t"
-		"mov    r0, sp			\n\t"
-		"bl     kprobe_handler		\n\t"
-
-		/*
-		 * Return to the context saved by setjmp_pre_handler
-		 * and restored by longjmp_break_handler.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"ldr	lr, [sp, %2]		\n\t" /* lr = saved sp */
-		"ldrd	r0, r1, [sp, %5]	\n\t" /* r0,r1 = saved lr,pc */
-		"ldr	r2, [sp, %4]		\n\t" /* r2 = saved psr */
-		"stmdb	lr!, {r0, r1, r2}	\n\t" /* push saved lr and */
-						      /* rfe context */
-		"ldmia	sp, {r0 - r12}		\n\t"
-		"mov	sp, lr			\n\t"
-		"ldr	lr, [sp], #4		\n\t"
-		"rfeia	sp!			\n\t"
-#else
-		"ldr	r0, [sp, %4]		\n\t"
-		"msr	cpsr_cxsf, r0		\n\t"
-		"ldmia	sp, {r0 - pc}		\n\t"
-#endif
-		:
-		: "r" (kcb->jprobe_saved_regs.ARM_sp),
-		  "I" (sizeof(struct pt_regs) * 2),
-		  "J" (offsetof(struct pt_regs, ARM_sp)),
-		  "J" (offsetof(struct pt_regs, ARM_pc)),
-		  "J" (offsetof(struct pt_regs, ARM_cpsr)),
-		  "J" (offsetof(struct pt_regs, ARM_lr))
-		: "memory", "cc");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long stack_addr = kcb->jprobe_saved_regs.ARM_sp;
-	long orig_sp = regs->ARM_sp;
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-
-	if (regs->ARM_pc == JPROBE_MAGIC_ADDR) {
-		if (orig_sp != stack_addr) {
-			struct pt_regs *saved_regs =
-				(struct pt_regs *)kcb->jprobe_saved_regs.ARM_sp;
-			printk("current sp %lx does not match saved sp %lx\n",
-			       orig_sp, stack_addr);
-			printk("Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk("Current registers\n");
-			show_regs(regs);
-			BUG();
-		}
-		*regs = kcb->jprobe_saved_regs;
-		memcpy((void *)stack_addr, kcb->jprobes_stack,
-		       MIN_STACK_SIZE(stack_addr));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
 {
 	return 0;
diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c
index 14db14152909..cc237fa9b90f 100644
--- a/arch/arm/probes/kprobes/test-core.c
+++ b/arch/arm/probes/kprobes/test-core.c
@@ -1461,7 +1461,6 @@ fail:
 	print_registers(&result_regs);
 
 	if (mem) {
-		pr_err("current_stack=%p\n", current_stack);
 		pr_err("expected_memory:\n");
 		print_memory(expected_memory, mem_size);
 		pr_err("result_memory:\n");
diff --git a/arch/arm/vfp/Makefile b/arch/arm/vfp/Makefile
index a81404c09d5d..94516c40ebd3 100644
--- a/arch/arm/vfp/Makefile
+++ b/arch/arm/vfp/Makefile
@@ -8,8 +8,5 @@
 # asflags-y := -DDEBUG
 
 KBUILD_AFLAGS	:=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp -mfloat-abi=soft)
-LDFLAGS		+=--no-warn-mismatch
 
-obj-y			+= vfp.o
-
-vfp-$(CONFIG_VFP)	+= vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o
+obj-y		+= vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 35d0f823e823..dc7e6b50ef67 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -596,13 +596,11 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
 }
 
 /* Sanitise and restore the current VFP state from the provided structures. */
-int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
-			     struct user_vfp_exc __user *ufp_exc)
+int vfp_restore_user_hwstate(struct user_vfp *ufp, struct user_vfp_exc *ufp_exc)
 {
 	struct thread_info *thread = current_thread_info();
 	struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
 	unsigned long fpexc;
-	int err = 0;
 
 	/* Disable VFP to avoid corrupting the new thread state. */
 	vfp_flush_hwstate(thread);
@@ -611,17 +609,16 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
 	 * Copy the floating point registers. There can be unused
 	 * registers see asm/hwcap.h for details.
 	 */
-	err |= __copy_from_user(&hwstate->fpregs, &ufp->fpregs,
-				sizeof(hwstate->fpregs));
+	memcpy(&hwstate->fpregs, &ufp->fpregs, sizeof(hwstate->fpregs));
 	/*
 	 * Copy the status and control register.
 	 */
-	__get_user_error(hwstate->fpscr, &ufp->fpscr, err);
+	hwstate->fpscr = ufp->fpscr;
 
 	/*
 	 * Sanitise and restore the exception registers.
 	 */
-	__get_user_error(fpexc, &ufp_exc->fpexc, err);
+	fpexc = ufp_exc->fpexc;
 
 	/* Ensure the VFP is enabled. */
 	fpexc |= FPEXC_EN;
@@ -630,10 +627,10 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
 	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
 	hwstate->fpexc = fpexc;
 
-	__get_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
-	__get_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
+	hwstate->fpinst = ufp_exc->fpinst;
+	hwstate->fpinst2 = ufp_exc->fpinst2;
 
-	return err ? -EFAULT : 0;
+	return 0;
 }
 
 /*
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 42c090cf0292..3d1011957823 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -74,6 +74,7 @@ config ARM64
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
@@ -264,9 +265,6 @@ config ARCH_SUPPORTS_UPROBES
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
 
-config MULTI_IRQ_HANDLER
-	def_bool y
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index 88f5aef7934c..e3a375c4cb83 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -19,33 +19,24 @@
 	 *			     u32 *macp, u8 const rk[], u32 rounds);
 	 */
 ENTRY(ce_aes_ccm_auth_data)
-	frame_push	7
-
-	mov	x19, x0
-	mov	x20, x1
-	mov	x21, x2
-	mov	x22, x3
-	mov	x23, x4
-	mov	x24, x5
-
-	ldr	w25, [x22]			/* leftover from prev round? */
+	ldr	w8, [x3]			/* leftover from prev round? */
 	ld1	{v0.16b}, [x0]			/* load mac */
-	cbz	w25, 1f
-	sub	w25, w25, #16
+	cbz	w8, 1f
+	sub	w8, w8, #16
 	eor	v1.16b, v1.16b, v1.16b
-0:	ldrb	w7, [x20], #1			/* get 1 byte of input */
-	subs	w21, w21, #1
-	add	w25, w25, #1
+0:	ldrb	w7, [x1], #1			/* get 1 byte of input */
+	subs	w2, w2, #1
+	add	w8, w8, #1
 	ins	v1.b[0], w7
 	ext	v1.16b, v1.16b, v1.16b, #1	/* rotate in the input bytes */
 	beq	8f				/* out of input? */
-	cbnz	w25, 0b
+	cbnz	w8, 0b
 	eor	v0.16b, v0.16b, v1.16b
-1:	ld1	{v3.4s}, [x23]			/* load first round key */
-	prfm	pldl1strm, [x20]
-	cmp	w24, #12			/* which key size? */
-	add	x6, x23, #16
-	sub	w7, w24, #2			/* modified # of rounds */
+1:	ld1	{v3.4s}, [x4]			/* load first round key */
+	prfm	pldl1strm, [x1]
+	cmp	w5, #12				/* which key size? */
+	add	x6, x4, #16
+	sub	w7, w5, #2			/* modified # of rounds */
 	bmi	2f
 	bne	5f
 	mov	v5.16b, v3.16b
@@ -64,43 +55,33 @@ ENTRY(ce_aes_ccm_auth_data)
 	ld1	{v5.4s}, [x6], #16		/* load next round key */
 	bpl	3b
 	aese	v0.16b, v4.16b
-	subs	w21, w21, #16			/* last data? */
+	subs	w2, w2, #16			/* last data? */
 	eor	v0.16b, v0.16b, v5.16b		/* final round */
 	bmi	6f
-	ld1	{v1.16b}, [x20], #16		/* load next input block */
+	ld1	{v1.16b}, [x1], #16		/* load next input block */
 	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
-	beq	6f
-
-	if_will_cond_yield_neon
-	st1	{v0.16b}, [x19]			/* store mac */
-	do_cond_yield_neon
-	ld1	{v0.16b}, [x19]			/* reload mac */
-	endif_yield_neon
-
-	b	1b
-6:	st1	{v0.16b}, [x19]			/* store mac */
+	bne	1b
+6:	st1	{v0.16b}, [x0]			/* store mac */
 	beq	10f
-	adds	w21, w21, #16
+	adds	w2, w2, #16
 	beq	10f
-	mov	w25, w21
-7:	ldrb	w7, [x20], #1
+	mov	w8, w2
+7:	ldrb	w7, [x1], #1
 	umov	w6, v0.b[0]
 	eor	w6, w6, w7
-	strb	w6, [x19], #1
-	subs	w21, w21, #1
+	strb	w6, [x0], #1
+	subs	w2, w2, #1
 	beq	10f
 	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
 	b	7b
-8:	mov	w7, w25
-	add	w25, w25, #16
+8:	mov	w7, w8
+	add	w8, w8, #16
 9:	ext	v1.16b, v1.16b, v1.16b, #1
 	adds	w7, w7, #1
 	bne	9b
 	eor	v0.16b, v0.16b, v1.16b
-	st1	{v0.16b}, [x19]
-10:	str	w25, [x22]
-
-	frame_pop
+	st1	{v0.16b}, [x0]
+10:	str	w8, [x3]
 	ret
 ENDPROC(ce_aes_ccm_auth_data)
 
@@ -145,29 +126,19 @@ ENTRY(ce_aes_ccm_final)
 ENDPROC(ce_aes_ccm_final)
 
 	.macro	aes_ccm_do_crypt,enc
-	frame_push	8
-
-	mov	x19, x0
-	mov	x20, x1
-	mov	x21, x2
-	mov	x22, x3
-	mov	x23, x4
-	mov	x24, x5
-	mov	x25, x6
-
-	ldr	x26, [x25, #8]			/* load lower ctr */
-	ld1	{v0.16b}, [x24]			/* load mac */
-CPU_LE(	rev	x26, x26		)	/* keep swabbed ctr in reg */
+	ldr	x8, [x6, #8]			/* load lower ctr */
+	ld1	{v0.16b}, [x5]			/* load mac */
+CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 0:	/* outer loop */
-	ld1	{v1.8b}, [x25]			/* load upper ctr */
-	prfm	pldl1strm, [x20]
-	add	x26, x26, #1
-	rev	x9, x26
-	cmp	w23, #12			/* which key size? */
-	sub	w7, w23, #2			/* get modified # of rounds */
+	ld1	{v1.8b}, [x6]			/* load upper ctr */
+	prfm	pldl1strm, [x1]
+	add	x8, x8, #1
+	rev	x9, x8
+	cmp	w4, #12				/* which key size? */
+	sub	w7, w4, #2			/* get modified # of rounds */
 	ins	v1.d[1], x9			/* no carry in lower ctr */
-	ld1	{v3.4s}, [x22]			/* load first round key */
-	add	x10, x22, #16
+	ld1	{v3.4s}, [x3]			/* load first round key */
+	add	x10, x3, #16
 	bmi	1f
 	bne	4f
 	mov	v5.16b, v3.16b
@@ -194,9 +165,9 @@ CPU_LE(	rev	x26, x26		)	/* keep swabbed ctr in reg */
 	bpl	2b
 	aese	v0.16b, v4.16b
 	aese	v1.16b, v4.16b
-	subs	w21, w21, #16
-	bmi	7f				/* partial block? */
-	ld1	{v2.16b}, [x20], #16		/* load next input block */
+	subs	w2, w2, #16
+	bmi	6f				/* partial block? */
+	ld1	{v2.16b}, [x1], #16		/* load next input block */
 	.if	\enc == 1
 	eor	v2.16b, v2.16b, v5.16b		/* final round enc+mac */
 	eor	v1.16b, v1.16b, v2.16b		/* xor with crypted ctr */
@@ -205,29 +176,18 @@ CPU_LE(	rev	x26, x26		)	/* keep swabbed ctr in reg */
 	eor	v1.16b, v2.16b, v5.16b		/* final round enc */
 	.endif
 	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
-	st1	{v1.16b}, [x19], #16		/* write output block */
-	beq	5f
-
-	if_will_cond_yield_neon
-	st1	{v0.16b}, [x24]			/* store mac */
-	do_cond_yield_neon
-	ld1	{v0.16b}, [x24]			/* reload mac */
-	endif_yield_neon
-
-	b	0b
-5:
-CPU_LE(	rev	x26, x26			)
-	st1	{v0.16b}, [x24]			/* store mac */
-	str	x26, [x25, #8]			/* store lsb end of ctr (BE) */
-
-6:	frame_pop
-	ret
-
-7:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
+	st1	{v1.16b}, [x0], #16		/* write output block */
+	bne	0b
+CPU_LE(	rev	x8, x8			)
+	st1	{v0.16b}, [x5]			/* store mac */
+	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
+5:	ret
+
+6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
 	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
-	st1	{v0.16b}, [x24]			/* store mac */
-	add	w21, w21, #16			/* process partial tail block */
-8:	ldrb	w9, [x20], #1			/* get 1 byte of input */
+	st1	{v0.16b}, [x5]			/* store mac */
+	add	w2, w2, #16			/* process partial tail block */
+7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
 	umov	w6, v1.b[0]			/* get top crypted ctr byte */
 	umov	w7, v0.b[0]			/* get top mac byte */
 	.if	\enc == 1
@@ -237,13 +197,13 @@ CPU_LE(	rev	x26, x26			)
 	eor	w9, w9, w6
 	eor	w7, w7, w9
 	.endif
-	strb	w9, [x19], #1			/* store out byte */
-	strb	w7, [x24], #1			/* store mac byte */
-	subs	w21, w21, #1
-	beq	6b
+	strb	w9, [x0], #1			/* store out byte */
+	strb	w7, [x5], #1			/* store mac byte */
+	subs	w2, w2, #1
+	beq	5b
 	ext	v0.16b, v0.16b, v0.16b, #1	/* shift out mac byte */
 	ext	v1.16b, v1.16b, v1.16b, #1	/* shift out ctr byte */
-	b	8b
+	b	7b
 	.endm
 
 	/*
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index dcffb9e77589..c723647b37db 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -322,55 +322,41 @@ ENDPROC(pmull_ghash_update_p8)
 	.endm
 
 	.macro		pmull_gcm_do_crypt, enc
-	frame_push	10
+	ld1		{SHASH.2d}, [x4]
+	ld1		{XL.2d}, [x1]
+	ldr		x8, [x5, #8]			// load lower counter
 
-	mov		x19, x0
-	mov		x20, x1
-	mov		x21, x2
-	mov		x22, x3
-	mov		x23, x4
-	mov		x24, x5
-	mov		x25, x6
-	mov		x26, x7
-	.if		\enc == 1
-	ldr		x27, [sp, #96]			// first stacked arg
-	.endif
-
-	ldr		x28, [x24, #8]			// load lower counter
-CPU_LE(	rev		x28, x28	)
-
-0:	mov		x0, x25
-	load_round_keys	w26, x0
-	ld1		{SHASH.2d}, [x23]
-	ld1		{XL.2d}, [x20]
+	load_round_keys	w7, x6
 
 	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+CPU_LE(	rev		x8, x8		)
 	shl		MASK.2d, MASK.2d, #57
 	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	.if		\enc == 1
-	ld1		{KS.16b}, [x27]
+	ldr		x10, [sp]
+	ld1		{KS.16b}, [x10]
 	.endif
 
-1:	ld1		{CTR.8b}, [x24]			// load upper counter
-	ld1		{INP.16b}, [x22], #16
-	rev		x9, x28
-	add		x28, x28, #1
-	sub		w19, w19, #1
+0:	ld1		{CTR.8b}, [x5]			// load upper counter
+	ld1		{INP.16b}, [x3], #16
+	rev		x9, x8
+	add		x8, x8, #1
+	sub		w0, w0, #1
 	ins		CTR.d[1], x9			// set lower counter
 
 	.if		\enc == 1
 	eor		INP.16b, INP.16b, KS.16b	// encrypt input
-	st1		{INP.16b}, [x21], #16
+	st1		{INP.16b}, [x2], #16
 	.endif
 
 	rev64		T1.16b, INP.16b
 
-	cmp		w26, #12
-	b.ge		4f				// AES-192/256?
+	cmp		w7, #12
+	b.ge		2f				// AES-192/256?
 
-2:	enc_round	CTR, v21
+1:	enc_round	CTR, v21
 
 	ext		T2.16b, XL.16b, XL.16b, #8
 	ext		IN1.16b, T1.16b, T1.16b, #8
@@ -425,39 +411,27 @@ CPU_LE(	rev		x28, x28	)
 
 	.if		\enc == 0
 	eor		INP.16b, INP.16b, KS.16b
-	st1		{INP.16b}, [x21], #16
+	st1		{INP.16b}, [x2], #16
 	.endif
 
-	cbz		w19, 3f
+	cbnz		w0, 0b
 
-	if_will_cond_yield_neon
-	st1		{XL.2d}, [x20]
-	.if		\enc == 1
-	st1		{KS.16b}, [x27]
-	.endif
-	do_cond_yield_neon
-	b		0b
-	endif_yield_neon
+CPU_LE(	rev		x8, x8		)
+	st1		{XL.2d}, [x1]
+	str		x8, [x5, #8]			// store lower counter
 
-	b		1b
-
-3:	st1		{XL.2d}, [x20]
 	.if		\enc == 1
-	st1		{KS.16b}, [x27]
+	st1		{KS.16b}, [x10]
 	.endif
 
-CPU_LE(	rev		x28, x28	)
-	str		x28, [x24, #8]			// store lower counter
-
-	frame_pop
 	ret
 
-4:	b.eq		5f				// AES-192?
+2:	b.eq		3f				// AES-192?
 	enc_round	CTR, v17
 	enc_round	CTR, v18
-5:	enc_round	CTR, v19
+3:	enc_round	CTR, v19
 	enc_round	CTR, v20
-	b		2b
+	b		1b
 	.endm
 
 	/*
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index c0235e0ff849..9bca54dda75c 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -40,17 +40,6 @@
 
 #include <asm/cmpxchg.h>
 
-#define ___atomic_add_unless(v, a, u, sfx)				\
-({									\
-	typeof((v)->counter) c, old;					\
-									\
-	c = atomic##sfx##_read(v);					\
-	while (c != (u) &&						\
-	      (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c)	\
-		c = old;						\
-	c;								\
- })
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 #define atomic_read(v)			READ_ONCE((v)->counter)
@@ -61,21 +50,11 @@
 #define atomic_add_return_release	atomic_add_return_release
 #define atomic_add_return		atomic_add_return
 
-#define atomic_inc_return_relaxed(v)	atomic_add_return_relaxed(1, (v))
-#define atomic_inc_return_acquire(v)	atomic_add_return_acquire(1, (v))
-#define atomic_inc_return_release(v)	atomic_add_return_release(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
 #define atomic_sub_return_relaxed	atomic_sub_return_relaxed
 #define atomic_sub_return_acquire	atomic_sub_return_acquire
 #define atomic_sub_return_release	atomic_sub_return_release
 #define atomic_sub_return		atomic_sub_return
 
-#define atomic_dec_return_relaxed(v)	atomic_sub_return_relaxed(1, (v))
-#define atomic_dec_return_acquire(v)	atomic_sub_return_acquire(1, (v))
-#define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-
 #define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
 #define atomic_fetch_add_acquire	atomic_fetch_add_acquire
 #define atomic_fetch_add_release	atomic_fetch_add_release
@@ -119,13 +98,6 @@
 	cmpxchg_release(&((v)->counter), (old), (new))
 #define atomic_cmpxchg(v, old, new)	cmpxchg(&((v)->counter), (old), (new))
 
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_add_negative(i, v)	(atomic_add_return((i), (v)) < 0)
-#define __atomic_add_unless(v, a, u)	___atomic_add_unless(v, a, u,)
 #define atomic_andnot			atomic_andnot
 
 /*
@@ -140,21 +112,11 @@
 #define atomic64_add_return_release	atomic64_add_return_release
 #define atomic64_add_return		atomic64_add_return
 
-#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1, (v))
-#define atomic64_inc_return_acquire(v)	atomic64_add_return_acquire(1, (v))
-#define atomic64_inc_return_release(v)	atomic64_add_return_release(1, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-
 #define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
 #define atomic64_sub_return_acquire	atomic64_sub_return_acquire
 #define atomic64_sub_return_release	atomic64_sub_return_release
 #define atomic64_sub_return		atomic64_sub_return
 
-#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1, (v))
-#define atomic64_dec_return_acquire(v)	atomic64_sub_return_acquire(1, (v))
-#define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
-
 #define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
 #define atomic64_fetch_add_acquire	atomic64_fetch_add_acquire
 #define atomic64_fetch_add_release	atomic64_fetch_add_release
@@ -195,16 +157,9 @@
 #define atomic64_cmpxchg_release	atomic_cmpxchg_release
 #define atomic64_cmpxchg		atomic_cmpxchg
 
-#define atomic64_inc(v)			atomic64_add(1, (v))
-#define atomic64_dec(v)			atomic64_sub(1, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i, v)	(atomic64_sub_return((i), (v)) == 0)
-#define atomic64_add_negative(i, v)	(atomic64_add_return((i), (v)) < 0)
-#define atomic64_add_unless(v, a, u)	(___atomic_add_unless(v, a, u, 64) != u)
 #define atomic64_andnot			atomic64_andnot
 
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
+#define atomic64_dec_if_positive	atomic64_dec_if_positive
 
 #endif
 #endif
diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h
index 9c19594ce7cb..10d536b1af74 100644
--- a/arch/arm64/include/asm/bitops.h
+++ b/arch/arm64/include/asm/bitops.h
@@ -17,22 +17,11 @@
 #define __ASM_BITOPS_H
 
 #include <linux/compiler.h>
-#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
 #endif
 
-/*
- * Little endian assembly atomic bitops.
- */
-extern void set_bit(int nr, volatile unsigned long *p);
-extern void clear_bit(int nr, volatile unsigned long *p);
-extern void change_bit(int nr, volatile unsigned long *p);
-extern int test_and_set_bit(int nr, volatile unsigned long *p);
-extern int test_and_clear_bit(int nr, volatile unsigned long *p);
-extern int test_and_change_bit(int nr, volatile unsigned long *p);
-
 #include <asm-generic/bitops/builtin-__ffs.h>
 #include <asm-generic/bitops/builtin-ffs.h>
 #include <asm-generic/bitops/builtin-__fls.h>
@@ -44,15 +33,11 @@ extern int test_and_change_bit(int nr, volatile unsigned long *p);
 
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/non-atomic.h>
 #include <asm-generic/bitops/le.h>
-
-/*
- * Ext2 is defined to use little-endian byte ordering.
- */
-#define ext2_set_bit_atomic(lock, nr, p)	test_and_set_bit_le(nr, p)
-#define ext2_clear_bit_atomic(lock, nr, p)	test_and_clear_bit_le(nr, p)
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
 
 #endif /* __ASM_BITOPS_H */
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 192d791f1103..7ed320895d1f 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -87,6 +87,9 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
 #define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
 #define efi_is_64bit()			(true)
 
+#define efi_table_attr(table, attr, instance)				\
+	((table##_t *)instance)->attr
+
 #define efi_call_proto(protocol, f, instance, ...)			\
 	((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
 
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 41770766d964..6a53e59ced95 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -119,13 +119,16 @@ static inline void decode_ctrl_reg(u32 reg,
 
 struct task_struct;
 struct notifier_block;
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  int *gen_len, int *gen_type, int *offset);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index a0fee6985e6a..b2b0c6405eb0 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -8,8 +8,6 @@
 
 struct pt_regs;
 
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
 static inline int nr_legacy_irqs(void)
 {
 	return 0;
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 6deb8d726041..d5a44cf859e9 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -48,7 +48,6 @@ struct kprobe_ctlblk {
 	unsigned long saved_irqflag;
 	struct prev_kprobe prev_kprobe;
 	struct kprobe_step_ctx ss_ctx;
-	struct pt_regs jprobe_saved_regs;
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 413dbe530da8..8c9644376326 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -343,14 +343,13 @@ static int get_hbp_len(u8 hbp_len)
 /*
  * Check whether bp virtual address is in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->ctrl.len);
+	va = hw->address;
+	len = get_hbp_len(hw->ctrl.len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -421,53 +420,53 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+		hw->ctrl.type = ARM_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->ctrl.type = ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_3:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_3;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_3;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_5:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_5;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_5;
 		break;
 	case HW_BREAKPOINT_LEN_6:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_6;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_6;
 		break;
 	case HW_BREAKPOINT_LEN_7:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_7;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_7;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
 		break;
 	default:
 		return -EINVAL;
@@ -478,37 +477,37 @@ static int arch_build_bp_info(struct perf_event *bp)
 	 * AArch32 also requires breakpoints of length 2 for Thumb.
 	 * Watchpoints can be of length 1, 2, 4 or 8 bytes.
 	 */
-	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
+	if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		if (is_compat_bp(bp)) {
-			if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
-			    info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+			if (hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+			    hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
 				return -EINVAL;
-		} else if (info->ctrl.len != ARM_BREAKPOINT_LEN_4) {
+		} else if (hw->ctrl.len != ARM_BREAKPOINT_LEN_4) {
 			/*
 			 * FIXME: Some tools (I'm looking at you perf) assume
 			 *	  that breakpoints should be sizeof(long). This
 			 *	  is nonsense. For now, we fix up the parameter
 			 *	  but we should probably return -EINVAL instead.
 			 */
-			info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+			hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		}
 	}
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/*
 	 * Privilege
 	 * Note that we disallow combined EL0/EL1 breakpoints because
 	 * that would complicate the stepping code.
 	 */
-	if (arch_check_bp_in_kernelspace(bp))
-		info->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
+	if (arch_check_bp_in_kernelspace(hw))
+		hw->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
 	else
-		info->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
+		hw->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
 
 	/* Enabled? */
-	info->ctrl.enabled = !bp->attr.disabled;
+	hw->ctrl.enabled = !attr->disabled;
 
 	return 0;
 }
@@ -516,14 +515,15 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings.
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	int ret;
 	u64 alignment_mask, offset;
 
 	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
@@ -537,42 +537,42 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * that here.
 	 */
 	if (is_compat_bp(bp)) {
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
 			alignment_mask = 0x7;
 		else
 			alignment_mask = 0x3;
-		offset = info->address & alignment_mask;
+		offset = hw->address & alignment_mask;
 		switch (offset) {
 		case 0:
 			/* Aligned */
 			break;
 		case 1:
 			/* Allow single byte watchpoint. */
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 				break;
 		case 2:
 			/* Allow halfword watchpoints and breakpoints. */
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 				break;
 		default:
 			return -EINVAL;
 		}
 	} else {
-		if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE)
+		if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE)
 			alignment_mask = 0x3;
 		else
 			alignment_mask = 0x7;
-		offset = info->address & alignment_mask;
+		offset = hw->address & alignment_mask;
 	}
 
-	info->address &= ~alignment_mask;
-	info->ctrl.len <<= offset;
+	hw->address &= ~alignment_mask;
+	hw->ctrl.len <<= offset;
 
 	/*
 	 * Disallow per-task kernel breakpoints since these would
 	 * complicate the stepping code.
 	 */
-	if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
+	if (hw->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 60e5fc661f74..780a12f59a8f 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -42,16 +42,6 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-void (*handle_arch_irq)(struct pt_regs *) = NULL;
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	if (handle_arch_irq)
-		return;
-
-	handle_arch_irq = handle_irq;
-}
-
 #ifdef CONFIG_VMAP_STACK
 static void init_irq_stacks(void)
 {
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d849d9804011..e78c3ef04d95 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -275,7 +275,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p,
 		break;
 	case KPROBE_HIT_SS:
 	case KPROBE_REENTER:
-		pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr);
+		pr_warn("Unrecoverable kprobe detected.\n");
 		dump_kprobe(p);
 		BUG();
 		break;
@@ -395,9 +395,9 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			/*
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry,
-			 * so get out doing nothing more here.
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
 			 *
 			 * pre_handler can hit a breakpoint and can step thru
 			 * before return, keep PSTATE D-flag enabled until
@@ -405,16 +405,8 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				setup_singlestep(p, regs, kcb, 0);
-				return;
-			}
-		}
-	} else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) ==
-	    BRK64_OPCODE_KPROBES) && cur_kprobe) {
-		/* We probably hit a jprobe.  Call its break handler. */
-		if (cur_kprobe->break_handler  &&
-		     cur_kprobe->break_handler(cur_kprobe, regs)) {
-			setup_singlestep(cur_kprobe, regs, kcb, 0);
-			return;
+			} else
+				reset_current_kprobe();
 		}
 	}
 	/*
@@ -465,74 +457,6 @@ kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
 	return DBG_HOOK_HANDLED;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	/*
-	 * Since we can't be sure where in the stack frame "stacked"
-	 * pass-by-value arguments are stored we just don't try to
-	 * duplicate any of the stack. Do not use jprobes on functions that
-	 * use more than 64 bytes (after padding each to an 8 byte boundary)
-	 * of arguments, or pass individual arguments larger than 16 bytes.
-	 */
-
-	instruction_pointer_set(regs, (unsigned long) jp->entry);
-	preempt_disable();
-	pause_graph_tracing();
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	/*
-	 * Jprobe handler return by entering break exception,
-	 * encoded same as kprobe, but with following conditions
-	 * -a special PC to identify it from the other kprobes.
-	 * -restore stack addr to original saved pt_regs
-	 */
-	asm volatile("				mov sp, %0	\n"
-		     "jprobe_return_break:	brk %1		\n"
-		     :
-		     : "r" (kcb->jprobe_saved_regs.sp),
-		       "I" (BRK64_ESR_KPROBES)
-		     : "memory");
-
-	unreachable();
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long stack_addr = kcb->jprobe_saved_regs.sp;
-	long orig_sp = kernel_stack_pointer(regs);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	extern const char jprobe_return_break[];
-
-	if (instruction_pointer(regs) != (u64) jprobe_return_break)
-		return 0;
-
-	if (orig_sp != stack_addr) {
-		struct pt_regs *saved_regs =
-		    (struct pt_regs *)kcb->jprobe_saved_regs.sp;
-		pr_err("current sp %lx does not match saved sp %lx\n",
-		       orig_sp, stack_addr);
-		pr_err("Saved registers for jprobe %p\n", jp);
-		__show_regs(saved_regs);
-		pr_err("Current registers\n");
-		__show_regs(regs);
-		BUG();
-	}
-	unpause_graph_tracing();
-	*regs = kcb->jprobe_saved_regs;
-	preempt_enable_no_resched();
-	return 1;
-}
-
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	if ((addr >= (unsigned long)__kprobes_text_start &&
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 137710f4dac3..68755fd70dcf 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-lib-y		:= bitops.o clear_user.o delay.o copy_from_user.o	\
+lib-y		:= clear_user.o delay.o copy_from_user.o		\
 		   copy_to_user.o copy_in_user.o copy_page.o		\
 		   clear_page.o memchr.o memcpy.o memmove.o memset.o	\
 		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
deleted file mode 100644
index 43ac736baa5b..000000000000
--- a/arch/arm64/lib/bitops.S
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * Based on arch/arm/lib/bitops.h
- *
- * Copyright (C) 2013 ARM Ltd.
- *
- * 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, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/lse.h>
-
-/*
- * x0: bits 5:0  bit offset
- *     bits 31:6 word offset
- * x1: address
- */
-	.macro	bitop, name, llsc, lse
-ENTRY(	\name	)
-	and	w3, w0, #63		// Get bit offset
-	eor	w0, w0, w3		// Clear low bits
-	mov	x2, #1
-	add	x1, x1, x0, lsr #3	// Get word offset
-alt_lse "	prfm	pstl1strm, [x1]",	"nop"
-	lsl	x3, x2, x3		// Create mask
-
-alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x3, [x1]"
-alt_lse	"	\llsc	x2, x2, x3",		"nop"
-alt_lse	"	stxr	w0, x2, [x1]",		"nop"
-alt_lse	"	cbnz	w0, 1b",		"nop"
-
-	ret
-ENDPROC(\name	)
-	.endm
-
-	.macro	testop, name, llsc, lse
-ENTRY(	\name	)
-	and	w3, w0, #63		// Get bit offset
-	eor	w0, w0, w3		// Clear low bits
-	mov	x2, #1
-	add	x1, x1, x0, lsr #3	// Get word offset
-alt_lse "	prfm	pstl1strm, [x1]",	"nop"
-	lsl	x4, x2, x3		// Create mask
-
-alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x4, x2, [x1]"
-	lsr	x0, x2, x3
-alt_lse	"	\llsc	x2, x2, x4",		"nop"
-alt_lse	"	stlxr	w5, x2, [x1]",		"nop"
-alt_lse	"	cbnz	w5, 1b",		"nop"
-alt_lse	"	dmb	ish",			"nop"
-
-	and	x0, x0, #1
-	ret
-ENDPROC(\name	)
-	.endm
-
-/*
- * Atomic bit operations.
- */
-	bitop	change_bit, eor, steor
-	bitop	clear_bit, bic, stclr
-	bitop	set_bit, orr, stset
-
-	testop	test_and_change_bit, eor, ldeoral
-	testop	test_and_clear_bit, bic, ldclral
-	testop	test_and_set_bit, orr, ldsetal
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 493ff75670ff..8ae5d7ae4af3 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -977,12 +977,12 @@ int pmd_clear_huge(pmd_t *pmdp)
 	return 1;
 }
 
-int pud_free_pmd_page(pud_t *pud)
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
 	return pud_none(*pud);
 }
 
-int pmd_free_pte_page(pmd_t *pmd)
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	return pmd_none(*pmd);
 }
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 941e7554e886..c6b6a06231b2 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -2,8 +2,10 @@
 #ifndef __ARCH_H8300_ATOMIC__
 #define __ARCH_H8300_ATOMIC__
 
+#include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/irqflags.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -15,8 +17,6 @@
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
-#include <linux/kernel.h>
-
 #define ATOMIC_OP_RETURN(op, c_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)	\
 {								\
@@ -69,18 +69,6 @@ ATOMIC_OPS(sub, -=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
-
-#define atomic_inc_return(v)		atomic_add_return(1, v)
-#define atomic_dec_return(v)		atomic_sub_return(1, v)
-
-#define atomic_inc(v)			(void)atomic_inc_return(v)
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-
-#define atomic_dec(v)			(void)atomic_dec_return(v)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
@@ -94,7 +82,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int ret;
 	h8300flags flags;
@@ -106,5 +94,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	arch_local_irq_restore(flags);
 	return ret;
 }
+#define atomic_fetch_add_unless		atomic_fetch_add_unless
 
 #endif /* __ARCH_H8300_ATOMIC __ */
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index fb3dfb2a667e..311b9894ccc8 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -164,7 +164,7 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer to value
  * @a: amount to add
  * @u: unless value is equal to u
@@ -173,7 +173,7 @@ ATOMIC_OPS(xor)
  *
  */
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int __oldval;
 	register int tmp;
@@ -196,18 +196,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	);
 	return __oldval;
 }
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-#define atomic_inc(v) atomic_add(1, (v))
-#define atomic_dec(v) atomic_sub(1, (v))
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0)
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
-#define atomic_inc_return(v) (atomic_add_return(1, v))
-#define atomic_dec_return(v) (atomic_sub_return(1, v))
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #endif
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 2524fb60fbc2..206530d0751b 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -215,91 +215,10 @@ ATOMIC64_FETCH_OP(xor, ^)
 	(cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
-
-static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
-/*
- * Atomically add I to V and return TRUE if the resulting value is
- * negative.
- */
-static __inline__ int
-atomic_add_negative (int i, atomic_t *v)
-{
-	return atomic_add_return(i, v) < 0;
-}
-
-static __inline__ long
-atomic64_add_negative (__s64 i, atomic64_t *v)
-{
-	return atomic64_add_return(i, v) < 0;
-}
-
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
-#define atomic_inc_and_test(v)		(atomic_add_return(1, (v)) == 0)
-#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i), (v)) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_sub_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v)	(atomic64_add_return(1, (v)) == 0)
-
 #define atomic_add(i,v)			(void)atomic_add_return((i), (v))
 #define atomic_sub(i,v)			(void)atomic_sub_return((i), (v))
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
 
 #define atomic64_add(i,v)		(void)atomic64_add_return((i), (v))
 #define atomic64_sub(i,v)		(void)atomic64_sub_return((i), (v))
-#define atomic64_inc(v)			atomic64_add(1, (v))
-#define atomic64_dec(v)			atomic64_sub(1, (v))
 
 #endif /* _ASM_IA64_ATOMIC_H */
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index fb0651961e2c..6f952171abf9 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -83,12 +83,14 @@ virt_to_phys (volatile void *address)
 {
 	return (unsigned long) address - PAGE_OFFSET;
 }
+#define virt_to_phys virt_to_phys
 
 static inline void*
 phys_to_virt (unsigned long address)
 {
 	return (void *) (address + PAGE_OFFSET);
 }
+#define phys_to_virt phys_to_virt
 
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
 extern u64 kern_mem_attribute (unsigned long phys_addr, unsigned long size);
@@ -433,9 +435,11 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo
 {
 	return ioremap(phys_addr, size);
 }
+#define ioremap ioremap
+#define ioremap_nocache ioremap_nocache
 #define ioremap_cache ioremap_cache
 #define ioremap_uc ioremap_nocache
-
+#define iounmap iounmap
 
 /*
  * String version of IO memory access ops:
@@ -444,6 +448,13 @@ extern void memcpy_fromio(void *dst, const volatile void __iomem *src, long n);
 extern void memcpy_toio(volatile void __iomem *dst, const void *src, long n);
 extern void memset_io(volatile void __iomem *s, int c, long n);
 
+#define memcpy_fromio memcpy_fromio
+#define memcpy_toio memcpy_toio
+#define memset_io memset_io
+#define xlate_dev_kmem_ptr xlate_dev_kmem_ptr
+#define xlate_dev_mem_ptr xlate_dev_mem_ptr
+#include <asm-generic/io.h>
+
 # endif /* __KERNEL__ */
 
 #endif /* _ASM_IA64_IO_H */
diff --git a/arch/ia64/include/asm/kprobes.h b/arch/ia64/include/asm/kprobes.h
index 0302b3664789..580356a2eea6 100644
--- a/arch/ia64/include/asm/kprobes.h
+++ b/arch/ia64/include/asm/kprobes.h
@@ -82,8 +82,6 @@ struct prev_kprobe {
 #define ARCH_PREV_KPROBE_SZ 2
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
-	struct pt_regs jprobe_saved_regs;
-	unsigned long jprobes_saved_stacked_regs[MAX_PARAM_RSE_SIZE];
 	unsigned long *bsp;
 	unsigned long cfm;
 	atomic_t prev_kprobe_index;
diff --git a/arch/ia64/include/uapi/asm/break.h b/arch/ia64/include/uapi/asm/break.h
index 5d742bcb0018..4ca110f0a94b 100644
--- a/arch/ia64/include/uapi/asm/break.h
+++ b/arch/ia64/include/uapi/asm/break.h
@@ -14,7 +14,6 @@
  */
 #define __IA64_BREAK_KDB		0x80100
 #define __IA64_BREAK_KPROBE		0x81000 /* .. 0x81fff */
-#define __IA64_BREAK_JPROBE		0x82000
 
 /*
  * OS-specific break numbers:
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 498f3da3f225..d0c0ccdd656a 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -25,7 +25,7 @@ obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_PERFMON)		+= perfmon_default_smpl.o
 obj-$(CONFIG_IA64_CYCLONE)	+= cyclone.o
 obj-$(CONFIG_IA64_MCA_RECOVERY)	+= mca_recovery.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o jprobes.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S
deleted file mode 100644
index f69389c7be1d..000000000000
--- a/arch/ia64/kernel/jprobes.S
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Jprobe specific operations
- *
- * 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, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) Intel Corporation, 2005
- *
- * 2005-May     Rusty Lynch <rusty.lynch@intel.com> and Anil S Keshavamurthy
- *              <anil.s.keshavamurthy@intel.com> initial implementation
- *
- * Jprobes (a.k.a. "jump probes" which is built on-top of kprobes) allow a
- * probe to be inserted into the beginning of a function call.  The fundamental
- * difference between a jprobe and a kprobe is the jprobe handler is executed
- * in the same context as the target function, while the kprobe handlers
- * are executed in interrupt context.
- *
- * For jprobes we initially gain control by placing a break point in the
- * first instruction of the targeted function.  When we catch that specific
- * break, we:
- *        * set the return address to our jprobe_inst_return() function
- *        * jump to the jprobe handler function
- *
- * Since we fixed up the return address, the jprobe handler will return to our
- * jprobe_inst_return() function, giving us control again.  At this point we
- * are back in the parents frame marker, so we do yet another call to our
- * jprobe_break() function to fix up the frame marker as it would normally
- * exist in the target function.
- *
- * Our jprobe_return function then transfers control back to kprobes.c by
- * executing a break instruction using one of our reserved numbers.  When we
- * catch that break in kprobes.c, we continue like we do for a normal kprobe
- * by single stepping the emulated instruction, and then returning execution
- * to the correct location.
- */
-#include <asm/asmmacro.h>
-#include <asm/break.h>
-
-	/*
-	 * void jprobe_break(void)
-	 */
-	.section .kprobes.text, "ax"
-ENTRY(jprobe_break)
-	break.m __IA64_BREAK_JPROBE
-END(jprobe_break)
-
-	/*
-	 * void jprobe_inst_return(void)
-	 */
-GLOBAL_ENTRY(jprobe_inst_return)
-	br.call.sptk.many b0=jprobe_break
-END(jprobe_inst_return)
-
-GLOBAL_ENTRY(invalidate_stacked_regs)
-	movl r16=invalidate_restore_cfm
-	;;
-	mov b6=r16
-	;;
-	br.ret.sptk.many b6
-	;;
-invalidate_restore_cfm:
-	mov r16=ar.rsc
-	;;
-	mov ar.rsc=r0
-	;;
-	loadrs
-	;;
-	mov ar.rsc=r16
-	;;
-	br.cond.sptk.many rp
-END(invalidate_stacked_regs)
-
-GLOBAL_ENTRY(flush_register_stack)
-	// flush dirty regs to backing store (must be first in insn group)
-	flushrs
-	;;
-	br.ret.sptk.many rp
-END(flush_register_stack)
-
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index f5f3a5e6fcd1..aa41bd5cf9b7 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -35,8 +35,6 @@
 #include <asm/sections.h>
 #include <asm/exception.h>
 
-extern void jprobe_inst_return(void);
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -480,12 +478,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 			 */
 			break;
 	}
-
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
@@ -819,14 +814,6 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 			prepare_ss(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			return 1;
-		} else if (args->err == __IA64_BREAK_JPROBE) {
-			/*
-			 * jprobe instrumented function just completed
-			 */
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				goto ss_probe;
-			}
 		} else if (!is_ia64_break_inst(regs)) {
 			/* The breakpoint instruction was removed by
 			 * another cpu right after we hit, no further
@@ -861,15 +848,12 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 	set_current_kprobe(p, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/*
-		 * Our pre-handler is specifically requesting that we just
-		 * do a return.  This is used for both the jprobe pre-handler
-		 * and the kretprobe trampoline
-		 */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 #if !defined(CONFIG_PREEMPT)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
@@ -992,7 +976,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	case DIE_BREAK:
 		/* err is break number from ia64_bad_break() */
 		if ((args->err >> 12) == (__IA64_BREAK_KPROBE >> 12)
-			|| args->err == __IA64_BREAK_JPROBE
 			|| args->err == 0)
 			if (pre_kprobes_handler(args))
 				ret = NOTIFY_STOP;
@@ -1040,74 +1023,6 @@ unsigned long arch_deref_entry_point(void *entry)
 	return ((struct fnptr *)entry)->ip;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr = arch_deref_entry_point(jp->entry);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	struct param_bsp_cfm pa;
-	int bytes;
-
-	/*
-	 * Callee owns the argument space and could overwrite it, eg
-	 * tail call optimization. So to be absolutely safe
-	 * we save the argument space before transferring the control
-	 * to instrumented jprobe function which runs in
-	 * the process context
-	 */
-	pa.ip = regs->cr_iip;
-	unw_init_running(ia64_get_bsp_cfm, &pa);
-	bytes = (char *)ia64_rse_skip_regs(pa.bsp, pa.cfm & 0x3f)
-				- (char *)pa.bsp;
-	memcpy( kcb->jprobes_saved_stacked_regs,
-		pa.bsp,
-		bytes );
-	kcb->bsp = pa.bsp;
-	kcb->cfm = pa.cfm;
-
-	/* save architectural state */
-	kcb->jprobe_saved_regs = *regs;
-
-	/* after rfi, execute the jprobe instrumented function */
-	regs->cr_iip = addr & ~0xFULL;
-	ia64_psr(regs)->ri = addr & 0xf;
-	regs->r1 = ((struct fnptr *)(jp->entry))->gp;
-
-	/*
-	 * fix the return address to our jprobe_inst_return() function
-	 * in the jprobes.S file
-	 */
-	regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip;
-
-	return 1;
-}
-
-/* ia64 does not need this */
-void __kprobes jprobe_return(void)
-{
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	int bytes;
-
-	/* restoring architectural state */
-	*regs = kcb->jprobe_saved_regs;
-
-	/* restoring the original argument space */
-	flush_register_stack();
-	bytes = (char *)ia64_rse_skip_regs(kcb->bsp, kcb->cfm & 0x3f)
-				- (char *)kcb->bsp;
-	memcpy( kcb->bsp,
-		kcb->jprobes_saved_stacked_regs,
-		bytes );
-	invalidate_stacked_regs();
-
-	preempt_enable_no_resched();
-	return 1;
-}
-
 static struct kprobe trampoline_p = {
 	.pre_handler = trampoline_probe_handler
 };
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 785612b576f7..b29f93774d95 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -2,6 +2,7 @@
 config M68K
 	bool
 	default y
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA
 	select ARCH_MIGHT_HAVE_PC_PARPORT if ISA
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 	select HAVE_IDE
@@ -24,6 +25,10 @@ config M68K
 	select MODULES_USE_ELF_RELA
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
+	select DMA_NONCOHERENT_OPS if HAS_DMA
+	select HAVE_MEMBLOCK
+	select ARCH_DISCARD_MEMBLOCK
+	select NO_BOOTMEM
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index b2a6bc63f8cd..aef8d42e078d 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -31,7 +31,6 @@ extern void dn_sched_init(irq_handler_t handler);
 extern void dn_init_IRQ(void);
 extern u32 dn_gettimeoffset(void);
 extern int dn_dummy_hwclk(int, struct rtc_time *);
-extern int dn_dummy_set_clock_mmss(unsigned long);
 extern void dn_dummy_reset(void);
 #ifdef CONFIG_HEARTBEAT
 static void dn_heartbeat(int on);
@@ -156,7 +155,6 @@ void __init config_apollo(void)
 	arch_gettimeoffset   = dn_gettimeoffset;
 	mach_max_dma_address = 0xffffffff;
 	mach_hwclk           = dn_dummy_hwclk; /* */
-	mach_set_clock_mmss  = dn_dummy_set_clock_mmss; /* */
 	mach_reset	     = dn_dummy_reset;  /* */
 #ifdef CONFIG_HEARTBEAT
 	mach_heartbeat = dn_heartbeat;
@@ -240,12 +238,6 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) {
 
 }
 
-int dn_dummy_set_clock_mmss(unsigned long nowtime)
-{
-	pr_info("set_clock_mmss\n");
-	return 0;
-}
-
 void dn_dummy_reset(void) {
 
   dn_serial_print("The end !\n");
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 565c6f06ab0b..bd96702a1ad0 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -81,9 +81,6 @@ extern void atari_sched_init(irq_handler_t);
 extern u32 atari_gettimeoffset(void);
 extern int atari_mste_hwclk (int, struct rtc_time *);
 extern int atari_tt_hwclk (int, struct rtc_time *);
-extern int atari_mste_set_clock_mmss (unsigned long);
-extern int atari_tt_set_clock_mmss (unsigned long);
-
 
 /* ++roman: This is a more elaborate test for an SCC chip, since the plain
  * Medusa board generates DTACK at the SCC's standard addresses, but a SCC
@@ -362,13 +359,11 @@ void __init config_atari(void)
 		ATARIHW_SET(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);
 		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)) {
diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c
index c549b48174ec..9cca64286464 100644
--- a/arch/m68k/atari/time.c
+++ b/arch/m68k/atari/time.c
@@ -285,69 +285,6 @@ int atari_tt_hwclk( int op, struct rtc_time *t )
     return( 0 );
 }
 
-
-int atari_mste_set_clock_mmss (unsigned long nowtime)
-{
-    short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-    struct MSTE_RTC val;
-    unsigned char rtc_minutes;
-
-    mste_read(&val);
-    rtc_minutes= val.min_ones + val.min_tens * 10;
-    if ((rtc_minutes < real_minutes
-         ? real_minutes - rtc_minutes
-         : rtc_minutes - real_minutes) < 30)
-    {
-        val.sec_ones = real_seconds % 10;
-        val.sec_tens = real_seconds / 10;
-        val.min_ones = real_minutes % 10;
-        val.min_tens = real_minutes / 10;
-        mste_write(&val);
-    }
-    else
-        return -1;
-    return 0;
-}
-
-int atari_tt_set_clock_mmss (unsigned long nowtime)
-{
-    int retval = 0;
-    short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-    unsigned char save_control, save_freq_select, rtc_minutes;
-
-    save_control = RTC_READ (RTC_CONTROL); /* tell the clock it's being set */
-    RTC_WRITE (RTC_CONTROL, save_control | RTC_SET);
-
-    save_freq_select = RTC_READ (RTC_FREQ_SELECT); /* stop and reset prescaler */
-    RTC_WRITE (RTC_FREQ_SELECT, save_freq_select | RTC_DIV_RESET2);
-
-    rtc_minutes = RTC_READ (RTC_MINUTES);
-    if (!(save_control & RTC_DM_BINARY))
-	rtc_minutes = bcd2bin(rtc_minutes);
-
-    /* Since we're only adjusting minutes and seconds, don't interfere
-       with hour overflow.  This avoids messing with unknown time zones
-       but requires your RTC not to be off by more than 30 minutes.  */
-    if ((rtc_minutes < real_minutes
-         ? real_minutes - rtc_minutes
-         : rtc_minutes - real_minutes) < 30)
-        {
-            if (!(save_control & RTC_DM_BINARY))
-                {
-		    real_seconds = bin2bcd(real_seconds);
-		    real_minutes = bin2bcd(real_minutes);
-                }
-            RTC_WRITE (RTC_SECONDS, real_seconds);
-            RTC_WRITE (RTC_MINUTES, real_minutes);
-        }
-    else
-        retval = -1;
-
-    RTC_WRITE (RTC_FREQ_SELECT, save_freq_select);
-    RTC_WRITE (RTC_CONTROL, save_control);
-    return retval;
-}
-
 /*
  * Local variables:
  *  c-indent-level: 4
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 2cfff4765040..143ee9fa3893 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -41,7 +41,6 @@ static void bvme6000_get_model(char *model);
 extern void bvme6000_sched_init(irq_handler_t handler);
 extern u32 bvme6000_gettimeoffset(void);
 extern int bvme6000_hwclk (int, struct rtc_time *);
-extern int bvme6000_set_clock_mmss (unsigned long);
 extern void bvme6000_reset (void);
 void bvme6000_set_vectors (void);
 
@@ -113,7 +112,6 @@ void __init config_bvme6000(void)
     mach_init_IRQ        = bvme6000_init_IRQ;
     arch_gettimeoffset   = bvme6000_gettimeoffset;
     mach_hwclk           = bvme6000_hwclk;
-    mach_set_clock_mmss	 = bvme6000_set_clock_mmss;
     mach_reset		 = bvme6000_reset;
     mach_get_model       = bvme6000_get_model;
 
@@ -305,46 +303,3 @@ int bvme6000_hwclk(int op, struct rtc_time *t)
 
 	return 0;
 }
-
-/*
- * Set the minutes and seconds from seconds value 'nowtime'.  Fail if
- * clock is out by > 30 minutes.  Logic lifted from atari code.
- * Algorithm is to wait for the 10ms register to change, and then to
- * wait a short while, and then set it.
- */
-
-int bvme6000_set_clock_mmss (unsigned long nowtime)
-{
-	int retval = 0;
-	short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-	unsigned char rtc_minutes, rtc_tenms;
-	volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE;
-	unsigned char msr = rtc->msr & 0xc0;
-	unsigned long flags;
-	volatile int i;
-
-	rtc->msr = 0;		/* Ensure clock accessible */
-	rtc_minutes = bcd2bin (rtc->bcd_min);
-
-	if ((rtc_minutes < real_minutes
-		? real_minutes - rtc_minutes
-			: rtc_minutes - real_minutes) < 30)
-	{
-		local_irq_save(flags);
-		rtc_tenms = rtc->bcd_tenms;
-		while (rtc_tenms == rtc->bcd_tenms)
-			;
-		for (i = 0; i < 1000; i++)
-			;
-		rtc->bcd_min = bin2bcd(real_minutes);
-		rtc->bcd_sec = bin2bcd(real_seconds);
-		local_irq_restore(flags);
-	}
-	else
-		retval = -1;
-
-	rtc->msr = msr;
-
-	return retval;
-}
-
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index a874e54404d1..1d5483f6e457 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -52,6 +52,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -98,18 +99,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -122,6 +119,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -200,7 +198,6 @@ 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
@@ -231,7 +228,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -260,7 +256,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -356,6 +352,7 @@ CONFIG_A2091_SCSI=y
 CONFIG_GVP11_SCSI=y
 CONFIG_SCSI_A4000T=y
 CONFIG_SCSI_ZORRO7XX=y
+CONFIG_SCSI_ZORRO_ESP=y
 CONFIG_MD=y
 CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
@@ -363,6 +360,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -402,8 +400,8 @@ CONFIG_A2065=y
 CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -412,8 +410,10 @@ CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
+CONFIG_XSURF100=y
 CONFIG_HYDRA=y
 CONFIG_APNE=y
 CONFIG_ZORRO8390=y
@@ -426,9 +426,9 @@ CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -478,6 +478,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -499,7 +500,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -600,6 +601,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -622,6 +624,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -657,6 +664,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 8ce39e23aa42..52a0af127951 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -198,7 +196,6 @@ 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
@@ -229,7 +226,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -381,14 +378,15 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -400,9 +398,9 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -440,6 +438,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -458,7 +457,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -559,6 +558,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -581,6 +581,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -616,6 +621,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 346c4e75edf8..b3103e51268a 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -198,7 +196,6 @@ 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
@@ -229,7 +226,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -391,14 +388,15 @@ CONFIG_VETH=m
 CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
 CONFIG_NE2000=y
@@ -411,9 +409,9 @@ CONFIG_NE2000=y
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -480,7 +478,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -581,6 +579,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -603,6 +602,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -638,6 +642,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index fca9c7aa71a3..fb7d651a4cab 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -196,7 +194,6 @@ 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
@@ -227,7 +224,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -380,14 +377,15 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -399,9 +397,9 @@ CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -433,6 +431,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index f9eab174915c..6b37f5537c39 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -198,7 +196,6 @@ 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
@@ -229,7 +226,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -382,14 +379,15 @@ CONFIG_VETH=m
 CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -401,9 +399,9 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -443,6 +441,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -460,7 +459,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -561,6 +560,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -583,6 +583,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -618,6 +623,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index b52e597899eb..930cc2965a11 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -49,6 +49,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -95,18 +96,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -119,6 +116,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -197,7 +195,6 @@ 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
@@ -228,7 +225,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -257,7 +253,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -398,8 +395,8 @@ CONFIG_VETH=m
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -407,6 +404,7 @@ CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 CONFIG_MACSONIC=y
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -420,9 +418,9 @@ CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -465,6 +463,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -482,7 +481,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -583,6 +582,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -605,6 +605,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -640,6 +645,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 2a84eeec5b02..e7dd25300127 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -59,6 +59,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -105,18 +106,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -129,6 +126,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -207,7 +205,6 @@ 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
@@ -238,7 +235,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -267,7 +263,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -311,6 +306,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -373,6 +369,7 @@ CONFIG_A2091_SCSI=y
 CONFIG_GVP11_SCSI=y
 CONFIG_SCSI_A4000T=y
 CONFIG_SCSI_ZORRO7XX=y
+CONFIG_SCSI_ZORRO_ESP=y
 CONFIG_ATARI_SCSI=y
 CONFIG_MAC_SCSI=y
 CONFIG_SCSI_MAC_ESP=y
@@ -387,6 +384,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -438,8 +436,8 @@ CONFIG_SUN3LANCE=y
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -449,9 +447,11 @@ CONFIG_BVME6000_NET=y
 CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 CONFIG_MACSONIC=y
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
+CONFIG_XSURF100=y
 CONFIG_HYDRA=y
 CONFIG_MAC8390=y
 CONFIG_NE2000=y
@@ -466,9 +466,9 @@ CONFIG_ZORRO8390=y
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PLIP=m
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -533,6 +533,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -562,7 +563,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -663,6 +664,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -685,6 +687,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -720,6 +727,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 476e69994340..b383327fd77a 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -47,6 +47,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -93,18 +94,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -117,6 +114,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -195,7 +193,6 @@ 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
@@ -226,7 +223,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -255,7 +251,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -296,6 +291,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -343,6 +339,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -380,14 +377,15 @@ CONFIG_VETH=m
 CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -399,9 +397,9 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -433,6 +431,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 1477cda9146e..9783d3deb9e9 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -196,7 +194,6 @@ 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
@@ -227,7 +224,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -380,14 +377,15 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -399,9 +397,9 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -433,6 +431,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index b3a543dc48a0..a35d10ee10cb 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -196,7 +194,6 @@ 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
@@ -227,7 +224,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -350,6 +346,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -388,8 +385,8 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -398,6 +395,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
 CONFIG_NE2000=y
@@ -410,9 +408,9 @@ CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PLIP=m
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -455,6 +453,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -473,7 +472,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -574,6 +573,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -596,6 +596,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -631,6 +636,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index d543ed5dfa96..573bf922d448 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -193,7 +191,6 @@ 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
@@ -224,7 +221,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -385,6 +382,7 @@ CONFIG_SUN3LANCE=y
 CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -397,9 +395,9 @@ CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -435,6 +433,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -574,6 +574,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -609,6 +614,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index a67e54246023..efb27a7fcc55 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -193,7 +191,6 @@ 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
@@ -224,7 +221,6 @@ 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_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -378,14 +375,15 @@ CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -397,9 +395,9 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -435,6 +433,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -575,6 +575,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -610,6 +615,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 4d8d68c4e3dd..a4b8d3331a9e 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,6 +1,7 @@
 generic-y += barrier.h
 generic-y += compat.h
 generic-y += device.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index e993e2860ee1..47228b0d4163 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -126,11 +126,13 @@ static inline void atomic_inc(atomic_t *v)
 {
 	__asm__ __volatile__("addql #1,%0" : "+m" (*v));
 }
+#define atomic_inc atomic_inc
 
 static inline void atomic_dec(atomic_t *v)
 {
 	__asm__ __volatile__("subql #1,%0" : "+m" (*v));
 }
+#define atomic_dec atomic_dec
 
 static inline int atomic_dec_and_test(atomic_t *v)
 {
@@ -138,6 +140,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
 	__asm__ __volatile__("subql #1,%1; seq %0" : "=d" (c), "+m" (*v));
 	return c != 0;
 }
+#define atomic_dec_and_test atomic_dec_and_test
 
 static inline int atomic_dec_and_test_lt(atomic_t *v)
 {
@@ -155,6 +158,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
 	__asm__ __volatile__("addql #1,%1; seq %0" : "=d" (c), "+m" (*v));
 	return c != 0;
 }
+#define atomic_inc_and_test atomic_inc_and_test
 
 #ifdef CONFIG_RMW_INSNS
 
@@ -190,9 +194,6 @@ static inline int atomic_xchg(atomic_t *v, int new)
 
 #endif /* !CONFIG_RMW_INSNS */
 
-#define atomic_dec_return(v)	atomic_sub_return(1, (v))
-#define atomic_inc_return(v)	atomic_add_return(1, (v))
-
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
 	char c;
@@ -201,6 +202,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v)
 			     : ASM_DI (i));
 	return c != 0;
 }
+#define atomic_sub_and_test atomic_sub_and_test
 
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
@@ -210,20 +212,6 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 			     : ASM_DI (i));
 	return c != 0;
 }
-
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
+#define atomic_add_negative atomic_add_negative
 
 #endif /* __ARCH_M68K_ATOMIC __ */
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index 93b47b1f6fb4..d979f38af751 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -454,7 +454,7 @@ static inline unsigned long ffz(unsigned long word)
  */
 #if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \
 	!defined(CONFIG_M68000) && !defined(CONFIG_MCPU32)
-static inline int __ffs(int x)
+static inline unsigned long __ffs(unsigned long x)
 {
 	__asm__ __volatile__ ("bitrev %0; ff1 %0"
 		: "=d" (x)
@@ -493,7 +493,11 @@ static inline int ffs(int x)
 		: "dm" (x & -x));
 	return 32 - cnt;
 }
-#define __ffs(x) (ffs(x) - 1)
+
+static inline unsigned long __ffs(unsigned long x)
+{
+	return ffs(x) - 1;
+}
 
 /*
  *	fls: find last bit set.
@@ -515,12 +519,16 @@ static inline int __fls(int x)
 
 #endif
 
+/* Simple test-and-set bit locks */
+#define test_and_set_bit_lock	test_and_set_bit
+#define clear_bit_unlock	clear_bit
+#define __clear_bit_unlock	clear_bit_unlock
+
 #include <asm-generic/bitops/ext2-atomic.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
 
 #endif /* _M68K_BITOPS_H */
diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h
deleted file mode 100644
index e3722ed04fbb..000000000000
--- a/arch/m68k/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _M68K_DMA_MAPPING_H
-#define _M68K_DMA_MAPPING_H
-
-extern const struct dma_map_ops m68k_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-        return &m68k_dma_ops;
-}
-
-#endif  /* _M68K_DMA_MAPPING_H */
diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h
index ca2849afb087..aabe6420ead2 100644
--- a/arch/m68k/include/asm/io.h
+++ b/arch/m68k/include/asm/io.h
@@ -1,6 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _M68K_IO_H
+#define _M68K_IO_H
+
 #if defined(__uClinux__) || defined(CONFIG_COLDFIRE)
 #include <asm/io_no.h>
 #else
 #include <asm/io_mm.h>
 #endif
+
+#include <asm-generic/io.h>
+
+#endif /* _M68K_IO_H */
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index fe485f4f5fac..782b78f8a048 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -16,13 +16,11 @@
  *    isa_readX(),isa_writeX()  are for ISA memory
  */
 
-#ifndef _IO_H
-#define _IO_H
+#ifndef _M68K_IO_MM_H
+#define _M68K_IO_MM_H
 
 #ifdef __KERNEL__
 
-#define ARCH_HAS_IOREMAP_WT
-
 #include <linux/compiler.h>
 #include <asm/raw_io.h>
 #include <asm/virtconvert.h>
@@ -369,40 +367,6 @@ static inline void isa_delay(void)
 #define writew(val, addr)	out_le16((addr), (val))
 #endif /* CONFIG_ATARI_ROM_ISA */
 
-#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
-/*
- * We need to define dummy functions for GENERIC_IOMAP support.
- */
-#define inb(port)          0xff
-#define inb_p(port)        0xff
-#define outb(val,port)     ((void)0)
-#define outb_p(val,port)   ((void)0)
-#define inw(port)          0xffff
-#define inw_p(port)        0xffff
-#define outw(val,port)     ((void)0)
-#define outw_p(val,port)   ((void)0)
-#define inl(port)          0xffffffffUL
-#define inl_p(port)        0xffffffffUL
-#define outl(val,port)     ((void)0)
-#define outl_p(val,port)   ((void)0)
-
-#define insb(port,buf,nr)  ((void)0)
-#define outsb(port,buf,nr) ((void)0)
-#define insw(port,buf,nr)  ((void)0)
-#define outsw(port,buf,nr) ((void)0)
-#define insl(port,buf,nr)  ((void)0)
-#define outsl(port,buf,nr) ((void)0)
-
-/*
- * These should be valid on any ioremap()ed region
- */
-#define readb(addr)      in_8(addr)
-#define writeb(val,addr) out_8((addr),(val))
-#define readw(addr)      in_le16(addr)
-#define writew(val,addr) out_le16((addr),(val))
-
-#endif /* !CONFIG_ISA && !CONFIG_ATARI_ROM_ISA */
-
 #define readl(addr)      in_le32(addr)
 #define writel(val,addr) out_le32((addr),(val))
 
@@ -444,4 +408,4 @@ static inline void isa_delay(void)
 #define writew_relaxed(b, addr)	writew(b, addr)
 #define writel_relaxed(b, addr)	writel(b, addr)
 
-#endif /* _IO_H */
+#endif /* _M68K_IO_MM_H */
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index 83a0a6d449f4..0498192e1d98 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -131,19 +131,7 @@ static inline void writel(u32 value, volatile void __iomem *addr)
 #define PCI_SPACE_LIMIT	PCI_IO_MASK
 #endif /* CONFIG_PCI */
 
-/*
- * These are defined in kmap.h as static inline functions. To maintain
- * previous behavior we put these define guards here so io_mm.h doesn't
- * see them.
- */
-#ifdef CONFIG_MMU
-#define memset_io memset_io
-#define memcpy_fromio memcpy_fromio
-#define memcpy_toio memcpy_toio
-#endif
-
 #include <asm/kmap.h>
 #include <asm/virtconvert.h>
-#include <asm-generic/io.h>
 
 #endif /* _M68KNOMMU_IO_H */
diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h
index 84b8333db8ad..aac7f045f7f0 100644
--- a/arch/m68k/include/asm/kmap.h
+++ b/arch/m68k/include/asm/kmap.h
@@ -4,6 +4,8 @@
 
 #ifdef CONFIG_MMU
 
+#define ARCH_HAS_IOREMAP_WT
+
 /* Values for nocacheflag and cmode */
 #define IOMAP_FULL_CACHING		0
 #define IOMAP_NOCACHE_SER		1
@@ -16,6 +18,7 @@
  */
 extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size,
 			       int cacheflag);
+#define iounmap iounmap
 extern void iounmap(void __iomem *addr);
 extern void __iounmap(void *addr, unsigned long size);
 
@@ -33,31 +36,35 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr,
 }
 
 #define ioremap_uc ioremap_nocache
+#define ioremap_wt ioremap_wt
 static inline void __iomem *ioremap_wt(unsigned long physaddr,
 				       unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
 }
 
-#define ioremap_fillcache ioremap_fullcache
+#define ioremap_fullcache ioremap_fullcache
 static inline void __iomem *ioremap_fullcache(unsigned long physaddr,
 					      unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
 }
 
+#define memset_io memset_io
 static inline void memset_io(volatile void __iomem *addr, unsigned char val,
 			     int count)
 {
 	__builtin_memset((void __force *) addr, val, count);
 }
 
+#define memcpy_fromio memcpy_fromio
 static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
 				 int count)
 {
 	__builtin_memcpy(dst, (void __force *) src, count);
 }
 
+#define memcpy_toio memcpy_toio
 static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
 			       int count)
 {
diff --git a/arch/m68k/include/asm/machdep.h b/arch/m68k/include/asm/machdep.h
index 1605da48ebf2..49bd3266b4b1 100644
--- a/arch/m68k/include/asm/machdep.h
+++ b/arch/m68k/include/asm/machdep.h
@@ -22,7 +22,6 @@ extern int (*mach_hwclk)(int, struct rtc_time*);
 extern unsigned int (*mach_get_ss)(void);
 extern int (*mach_get_rtc_pll)(struct rtc_pll_info *);
 extern int (*mach_set_rtc_pll)(struct rtc_pll_info *);
-extern int (*mach_set_clock_mmss)(unsigned long);
 extern void (*mach_reset)( void );
 extern void (*mach_halt)( void );
 extern void (*mach_power_off)( void );
diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h
index 9b840c03ebb7..08cee11180e6 100644
--- a/arch/m68k/include/asm/macintosh.h
+++ b/arch/m68k/include/asm/macintosh.h
@@ -57,7 +57,6 @@ struct mac_model
 #define MAC_SCSI_IIFX		5
 #define MAC_SCSI_DUO		6
 #define MAC_SCSI_LC		7
-#define MAC_SCSI_LATE		8
 
 #define MAC_IDE_NONE		0
 #define MAC_IDE_QUADRA		1
diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
index e644c4daf540..6bbe52025de3 100644
--- a/arch/m68k/include/asm/page_no.h
+++ b/arch/m68k/include/asm/page_no.h
@@ -18,7 +18,7 @@ extern unsigned long memory_end;
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 #define __pa(vaddr)		((unsigned long)(vaddr))
-#define __va(paddr)		((void *)(paddr))
+#define __va(paddr)		((void *)((unsigned long)(paddr)))
 
 #define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
 #define pfn_to_virt(pfn)	__va((pfn) << PAGE_SHIFT)
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 463572c4943f..e99993c57d6b 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -6,7 +6,7 @@
 
 #undef DEBUG
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
@@ -19,7 +19,7 @@
 
 #if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE)
 
-static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		gfp_t flag, unsigned long attrs)
 {
 	struct page *page, **map;
@@ -62,7 +62,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	return addr;
 }
 
-static void m68k_dma_free(struct device *dev, size_t size, void *addr,
+void arch_dma_free(struct device *dev, size_t size, void *addr,
 		dma_addr_t handle, unsigned long attrs)
 {
 	pr_debug("dma_free_coherent: %p, %x\n", addr, handle);
@@ -73,8 +73,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *addr,
 
 #include <asm/cacheflush.h>
 
-static void *m68k_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	void *ret;
 
@@ -89,7 +89,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size,
 	return ret;
 }
 
-static void m68k_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	free_pages((unsigned long)vaddr, get_order(size));
@@ -97,8 +97,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *vaddr,
 
 #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */
 
-static void m68k_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle,
+		size_t size, enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
@@ -115,58 +115,6 @@ static void m68k_dma_sync_single_for_device(struct device *dev,
 	}
 }
 
-static void m68k_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sglist, int nents, enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
-					   dir);
-	}
-}
-
-static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	dma_addr_t handle = page_to_phys(page) + offset;
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_sync_single_for_device(dev, handle, size, dir);
-
-	return handle;
-}
-
-static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		sg->dma_address = sg_phys(sg);
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
-					   dir);
-	}
-	return nents;
-}
-
-const struct dma_map_ops m68k_dma_ops = {
-	.alloc			= m68k_dma_alloc,
-	.free			= m68k_dma_free,
-	.map_page		= m68k_dma_map_page,
-	.map_sg			= m68k_dma_map_sg,
-	.sync_single_for_device	= m68k_dma_sync_single_for_device,
-	.sync_sg_for_device	= m68k_dma_sync_sg_for_device,
-};
-EXPORT_SYMBOL(m68k_dma_ops);
-
 void arch_setup_pdev_archdata(struct platform_device *pdev)
 {
 	if (pdev->dev.coherent_dma_mask == DMA_MASK_NONE &&
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index f35e3ebd6331..5d3596c180f9 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/module.h>
@@ -88,7 +89,6 @@ void (*mach_get_hardware_list) (struct seq_file *m);
 /* machine dependent timer functions */
 int (*mach_hwclk) (int, struct rtc_time*);
 EXPORT_SYMBOL(mach_hwclk);
-int (*mach_set_clock_mmss) (unsigned long);
 unsigned int (*mach_get_ss)(void);
 int (*mach_get_rtc_pll)(struct rtc_pll_info *);
 int (*mach_set_rtc_pll)(struct rtc_pll_info *);
@@ -165,6 +165,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 					be32_to_cpu(m->addr);
 				m68k_memory[m68k_num_memory].size =
 					be32_to_cpu(m->size);
+				memblock_add(m68k_memory[m68k_num_memory].addr,
+					     m68k_memory[m68k_num_memory].size);
 				m68k_num_memory++;
 			} else
 				pr_warn("%s: too many memory chunks\n",
@@ -224,10 +226,6 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 
 void __init setup_arch(char **cmdline_p)
 {
-#ifndef CONFIG_SUN3
-	int i;
-#endif
-
 	/* The bootinfo is located right after the kernel */
 	if (!CPU_IS_COLDFIRE)
 		m68k_parse_bootinfo((const struct bi_record *)_end);
@@ -356,14 +354,9 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 #ifndef CONFIG_SUN3
-	for (i = 1; i < m68k_num_memory; i++)
-		free_bootmem_node(NODE_DATA(i), m68k_memory[i].addr,
-				  m68k_memory[i].size);
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (m68k_ramdisk.size) {
-		reserve_bootmem_node(__virt_to_node(phys_to_virt(m68k_ramdisk.addr)),
-				     m68k_ramdisk.addr, m68k_ramdisk.size,
-				     BOOTMEM_DEFAULT);
+		memblock_reserve(m68k_ramdisk.addr, m68k_ramdisk.size);
 		initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr);
 		initrd_end = initrd_start + m68k_ramdisk.size;
 		pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end);
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index a98af1018201..cfd5475bfc31 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -28,6 +28,7 @@
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/initrd.h>
@@ -51,7 +52,6 @@ char __initdata command_line[COMMAND_LINE_SIZE];
 
 /* machine dependent timer functions */
 void (*mach_sched_init)(irq_handler_t handler) __initdata = NULL;
-int (*mach_set_clock_mmss)(unsigned long);
 int (*mach_hwclk) (int, struct rtc_time*);
 
 /* machine dependent reboot functions */
@@ -86,8 +86,6 @@ void (*mach_power_off)(void);
 
 void __init setup_arch(char **cmdline_p)
 {
-	int bootmap_size;
-
 	memory_start = PAGE_ALIGN(_ramstart);
 	memory_end = _ramend;
 
@@ -142,6 +140,8 @@ void __init setup_arch(char **cmdline_p)
 	pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ",
 		 __bss_stop, memory_start, memory_start, memory_end);
 
+	memblock_add(memory_start, memory_end - memory_start);
+
 	/* Keep a copy of command line */
 	*cmdline_p = &command_line[0];
 	memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
@@ -158,23 +158,10 @@ void __init setup_arch(char **cmdline_p)
 	min_low_pfn = PFN_DOWN(memory_start);
 	max_pfn = max_low_pfn = PFN_DOWN(memory_end);
 
-	bootmap_size = init_bootmem_node(
-			NODE_DATA(0),
-			min_low_pfn,		/* map goes here */
-			PFN_DOWN(PAGE_OFFSET),
-			max_pfn);
-	/*
-	 * Free the usable memory, we have to make sure we do not free
-	 * the bootmem bitmap so we then reserve it after freeing it :-)
-	 */
-	free_bootmem(memory_start, memory_end - memory_start);
-	reserve_bootmem(memory_start, bootmap_size, BOOTMEM_DEFAULT);
-
 #if defined(CONFIG_UBOOT) && defined(CONFIG_BLK_DEV_INITRD)
 	if ((initrd_start > 0) && (initrd_start < initrd_end) &&
 			(initrd_end < memory_end))
-		reserve_bootmem(initrd_start, initrd_end - initrd_start,
-				 BOOTMEM_DEFAULT);
+		memblock_reserve(initrd_start, initrd_end - initrd_start);
 #endif /* if defined(CONFIG_BLK_DEV_INITRD) */
 
 	/*
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index e522307db47c..b02d7254b73a 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -57,7 +57,6 @@ static unsigned long mac_orig_videoaddr;
 /* Mac specific timer functions */
 extern u32 mac_gettimeoffset(void);
 extern int mac_hwclk(int, struct rtc_time *);
-extern int mac_set_clock_mmss(unsigned long);
 extern void iop_preinit(void);
 extern void iop_init(void);
 extern void via_init(void);
@@ -158,7 +157,6 @@ void __init config_mac(void)
 	mach_get_model = mac_get_model;
 	arch_gettimeoffset = mac_gettimeoffset;
 	mach_hwclk = mac_hwclk;
-	mach_set_clock_mmss = mac_set_clock_mmss;
 	mach_reset = mac_reset;
 	mach_halt = mac_poweroff;
 	mach_power_off = mac_poweroff;
@@ -709,7 +707,7 @@ static struct mac_model mac_data_table[] = {
 		.name		= "PowerBook 520",
 		.adb_type	= MAC_ADB_PB2,
 		.via_type	= MAC_VIA_QUADRA,
-		.scsi_type	= MAC_SCSI_LATE,
+		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
@@ -943,18 +941,6 @@ static const struct resource mac_scsi_old_rsrc[] __initconst = {
 	},
 };
 
-static const struct resource mac_scsi_late_rsrc[] __initconst = {
-	{
-		.flags = IORESOURCE_IRQ,
-		.start = IRQ_MAC_SCSI,
-		.end   = IRQ_MAC_SCSI,
-	}, {
-		.flags = IORESOURCE_MEM,
-		.start = 0x50010000,
-		.end   = 0x50011FFF,
-	},
-};
-
 static const struct resource mac_scsi_ccl_rsrc[] __initconst = {
 	{
 		.flags = IORESOURCE_IRQ,
@@ -1064,11 +1050,6 @@ int __init mac_platform_init(void)
 		platform_device_register_simple("mac_scsi", 0,
 			mac_scsi_old_rsrc, ARRAY_SIZE(mac_scsi_old_rsrc));
 		break;
-	case MAC_SCSI_LATE:
-		/* XXX PDMA support for PowerBook 500 series needs testing */
-		platform_device_register_simple("mac_scsi", 0,
-			mac_scsi_late_rsrc, ARRAY_SIZE(mac_scsi_late_rsrc));
-		break;
 	case MAC_SCSI_LC:
 		/* Addresses from Mac LC data in Designing Cards & Drivers 3ed.
 		 * Also from the Developer Notes for Classic II, LC III,
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index c68054361615..19e9d8eef1f2 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -26,33 +26,38 @@
 
 #include <asm/machdep.h>
 
-/* Offset between Unix time (1970-based) and Mac time (1904-based) */
+/*
+ * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU
+ * times wrap in 2040. If we need to handle later times, the read_time functions
+ * need to be changed to interpret wrapped times as post-2040.
+ */
 
 #define RTC_OFFSET 2082844800
 
 static void (*rom_reset)(void);
 
 #ifdef CONFIG_ADB_CUDA
-static long cuda_read_time(void)
+static time64_t cuda_read_time(void)
 {
 	struct adb_request req;
-	long time;
+	time64_t time;
 
 	if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0)
 		return 0;
 	while (!req.complete)
 		cuda_poll();
 
-	time = (req.reply[3] << 24) | (req.reply[4] << 16) |
-	       (req.reply[5] << 8) | req.reply[6];
+	time = (u32)((req.reply[3] << 24) | (req.reply[4] << 16) |
+		     (req.reply[5] << 8) | req.reply[6]);
+
 	return time - RTC_OFFSET;
 }
 
-static void cuda_write_time(long data)
+static void cuda_write_time(time64_t time)
 {
 	struct adb_request req;
+	u32 data = lower_32_bits(time + RTC_OFFSET);
 
-	data += RTC_OFFSET;
 	if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME,
 			 (data >> 24) & 0xFF, (data >> 16) & 0xFF,
 			 (data >> 8) & 0xFF, data & 0xFF) < 0)
@@ -86,26 +91,27 @@ static void cuda_write_pram(int offset, __u8 data)
 #endif /* CONFIG_ADB_CUDA */
 
 #ifdef CONFIG_ADB_PMU68K
-static long pmu_read_time(void)
+static time64_t pmu_read_time(void)
 {
 	struct adb_request req;
-	long time;
+	time64_t time;
 
 	if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
 		return 0;
 	while (!req.complete)
 		pmu_poll();
 
-	time = (req.reply[1] << 24) | (req.reply[2] << 16) |
-	       (req.reply[3] << 8) | req.reply[4];
+	time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) |
+		     (req.reply[3] << 8) | req.reply[4]);
+
 	return time - RTC_OFFSET;
 }
 
-static void pmu_write_time(long data)
+static void pmu_write_time(time64_t time)
 {
 	struct adb_request req;
+	u32 data = lower_32_bits(time + RTC_OFFSET);
 
-	data += RTC_OFFSET;
 	if (pmu_request(&req, NULL, 5, PMU_SET_RTC,
 			(data >> 24) & 0xFF, (data >> 16) & 0xFF,
 			(data >> 8) & 0xFF, data & 0xFF) < 0)
@@ -245,11 +251,11 @@ static void via_write_pram(int offset, __u8 data)
  * is basically any machine with Mac II-style ADB.
  */
 
-static long via_read_time(void)
+static time64_t via_read_time(void)
 {
 	union {
 		__u8 cdata[4];
-		long idata;
+		__u32 idata;
 	} result, last_result;
 	int count = 1;
 
@@ -270,7 +276,7 @@ static long via_read_time(void)
 		via_pram_command(0x8D, &result.cdata[0]);
 
 		if (result.idata == last_result.idata)
-			return result.idata - RTC_OFFSET;
+			return (time64_t)result.idata - RTC_OFFSET;
 
 		if (++count > 10)
 			break;
@@ -278,8 +284,8 @@ static long via_read_time(void)
 		last_result.idata = result.idata;
 	}
 
-	pr_err("via_read_time: failed to read a stable value; got 0x%08lx then 0x%08lx\n",
-	       last_result.idata, result.idata);
+	pr_err("%s: failed to read a stable value; got 0x%08x then 0x%08x\n",
+	       __func__, last_result.idata, result.idata);
 
 	return 0;
 }
@@ -291,11 +297,11 @@ static long via_read_time(void)
  * is basically any machine with Mac II-style ADB.
  */
 
-static void via_write_time(long time)
+static void via_write_time(time64_t time)
 {
 	union {
 		__u8 cdata[4];
-		long idata;
+		__u32 idata;
 	} data;
 	__u8 temp;
 
@@ -304,7 +310,7 @@ static void via_write_time(long time)
 	temp = 0x55;
 	via_pram_command(0x35, &temp);
 
-	data.idata = time + RTC_OFFSET;
+	data.idata = lower_32_bits(time + RTC_OFFSET);
 	via_pram_command(0x01, &data.cdata[3]);
 	via_pram_command(0x05, &data.cdata[2]);
 	via_pram_command(0x09, &data.cdata[1]);
@@ -585,12 +591,15 @@ void mac_reset(void)
  * This function translates seconds since 1970 into a proper date.
  *
  * Algorithm cribbed from glibc2.1, __offtime().
+ *
+ * This is roughly same as rtc_time64_to_tm(), which we should probably
+ * use here, but it's only available when CONFIG_RTC_LIB is enabled.
  */
 #define SECS_PER_MINUTE (60)
 #define SECS_PER_HOUR  (SECS_PER_MINUTE * 60)
 #define SECS_PER_DAY   (SECS_PER_HOUR * 24)
 
-static void unmktime(unsigned long time, long offset,
+static void unmktime(time64_t time, long offset,
 		     int *yearp, int *monp, int *dayp,
 		     int *hourp, int *minp, int *secp)
 {
@@ -602,11 +611,10 @@ static void unmktime(unsigned long time, long offset,
 		/* Leap years.  */
 		{ 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 }
 	};
-	long int days, rem, y, wday, yday;
+	int days, rem, y, wday, yday;
 	const unsigned short int *ip;
 
-	days = time / SECS_PER_DAY;
-	rem = time % SECS_PER_DAY;
+	days = div_u64_rem(time, SECS_PER_DAY, &rem);
 	rem += offset;
 	while (rem < 0) {
 		rem += SECS_PER_DAY;
@@ -657,7 +665,7 @@ static void unmktime(unsigned long time, long offset,
 
 int mac_hwclk(int op, struct rtc_time *t)
 {
-	unsigned long now;
+	time64_t now;
 
 	if (!op) { /* read */
 		switch (macintosh_config->adb_type) {
@@ -693,8 +701,8 @@ int mac_hwclk(int op, struct rtc_time *t)
 		         __func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
 		         t->tm_hour, t->tm_min, t->tm_sec);
 
-		now = mktime(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
-			     t->tm_hour, t->tm_min, t->tm_sec);
+		now = mktime64(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
+			       t->tm_hour, t->tm_min, t->tm_sec);
 
 		switch (macintosh_config->adb_type) {
 		case MAC_ADB_IOP:
@@ -719,19 +727,3 @@ int mac_hwclk(int op, struct rtc_time *t)
 	}
 	return 0;
 }
-
-/*
- * Set minutes/seconds in the hardware clock
- */
-
-int mac_set_clock_mmss (unsigned long nowtime)
-{
-	struct rtc_time now;
-
-	mac_hwclk(0, &now);
-	now.tm_sec = nowtime % 60;
-	now.tm_min = (nowtime / 60) % 60;
-	mac_hwclk(1, &now);
-
-	return 0;
-}
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 8827b7f91402..38e2b272c220 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -71,7 +71,6 @@ void __init m68k_setup_node(int node)
 		pg_data_table[i] = pg_data_map + node;
 	}
 #endif
-	pg_data_map[node].bdata = bootmem_node_data + node;
 	node_set_online(node);
 }
 
diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c
index 2925d795d71a..70dde040779b 100644
--- a/arch/m68k/mm/mcfmmu.c
+++ b/arch/m68k/mm/mcfmmu.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>
@@ -153,31 +154,31 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word)
 
 void __init cf_bootmem_alloc(void)
 {
-	unsigned long start_pfn;
 	unsigned long memstart;
 
 	/* _rambase and _ramend will be naturally page aligned */
 	m68k_memory[0].addr = _rambase;
 	m68k_memory[0].size = _ramend - _rambase;
 
+	memblock_add(m68k_memory[0].addr, m68k_memory[0].size);
+
 	/* compute total pages in system */
 	num_pages = PFN_DOWN(_ramend - _rambase);
 
 	/* page numbers */
 	memstart = PAGE_ALIGN(_ramstart);
 	min_low_pfn = PFN_DOWN(_rambase);
-	start_pfn = PFN_DOWN(memstart);
 	max_pfn = max_low_pfn = PFN_DOWN(_ramend);
 	high_memory = (void *)_ramend;
 
+	/* Reserve kernel text/data/bss */
+	memblock_reserve(memstart, memstart - _rambase);
+
 	m68k_virt_to_node_shift = fls(_ramend - 1) - 6;
 	module_fixup(NULL, __start_fixup, __stop_fixup);
 
-	/* setup bootmem data */
+	/* setup node data */
 	m68k_setup_node(0);
-	memstart += init_bootmem_node(NODE_DATA(0), start_pfn,
-		min_low_pfn, max_low_pfn);
-	free_bootmem_node(NODE_DATA(0), memstart, _ramend - memstart);
 }
 
 /*
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index e490ecc7842c..4e17ecb5928a 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/gfp.h>
 
 #include <asm/setup.h>
@@ -208,7 +209,7 @@ void __init paging_init(void)
 {
 	unsigned long zones_size[MAX_NR_ZONES] = { 0, };
 	unsigned long min_addr, max_addr;
-	unsigned long addr, size, end;
+	unsigned long addr;
 	int i;
 
 #ifdef DEBUG
@@ -253,34 +254,20 @@ void __init paging_init(void)
 	min_low_pfn = availmem >> PAGE_SHIFT;
 	max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT;
 
-	for (i = 0; i < m68k_num_memory; i++) {
-		addr = m68k_memory[i].addr;
-		end = addr + m68k_memory[i].size;
-		m68k_setup_node(i);
-		availmem = PAGE_ALIGN(availmem);
-		availmem += init_bootmem_node(NODE_DATA(i),
-					      availmem >> PAGE_SHIFT,
-					      addr >> PAGE_SHIFT,
-					      end >> PAGE_SHIFT);
-	}
+	/* Reserve kernel text/data/bss and the memory allocated in head.S */
+	memblock_reserve(m68k_memory[0].addr, availmem - m68k_memory[0].addr);
 
 	/*
 	 * Map the physical memory available into the kernel virtual
-	 * address space. First initialize the bootmem allocator with
-	 * the memory we already mapped, so map_node() has something
-	 * to allocate.
+	 * address space. Make sure memblock will not try to allocate
+	 * pages beyond the memory we already mapped in head.S
 	 */
-	addr = m68k_memory[0].addr;
-	size = m68k_memory[0].size;
-	free_bootmem_node(NODE_DATA(0), availmem,
-			  min(m68k_init_mapped_size, size) - (availmem - addr));
-	map_node(0);
-	if (size > m68k_init_mapped_size)
-		free_bootmem_node(NODE_DATA(0), addr + m68k_init_mapped_size,
-				  size - m68k_init_mapped_size);
-
-	for (i = 1; i < m68k_num_memory; i++)
+	memblock_set_bottom_up(true);
+
+	for (i = 0; i < m68k_num_memory; i++) {
+		m68k_setup_node(i);
 		map_node(i);
+	}
 
 	flush_tlb_all();
 
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index f8a710fd84cd..adea549d240e 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -40,7 +40,6 @@ static void mvme147_get_model(char *model);
 extern void mvme147_sched_init(irq_handler_t handler);
 extern u32 mvme147_gettimeoffset(void);
 extern int mvme147_hwclk (int, struct rtc_time *);
-extern int mvme147_set_clock_mmss (unsigned long);
 extern void mvme147_reset (void);
 
 
@@ -92,7 +91,6 @@ void __init config_mvme147(void)
 	mach_init_IRQ		= mvme147_init_IRQ;
 	arch_gettimeoffset	= mvme147_gettimeoffset;
 	mach_hwclk		= mvme147_hwclk;
-	mach_set_clock_mmss	= mvme147_set_clock_mmss;
 	mach_reset		= mvme147_reset;
 	mach_get_model		= mvme147_get_model;
 
@@ -164,8 +162,3 @@ int mvme147_hwclk(int op, struct rtc_time *t)
 	}
 	return 0;
 }
-
-int mvme147_set_clock_mmss (unsigned long nowtime)
-{
-	return 0;
-}
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 4ffd9ef98de4..6ee36a5b528d 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -46,7 +46,6 @@ static void mvme16x_get_model(char *model);
 extern void mvme16x_sched_init(irq_handler_t handler);
 extern u32 mvme16x_gettimeoffset(void);
 extern int mvme16x_hwclk (int, struct rtc_time *);
-extern int mvme16x_set_clock_mmss (unsigned long);
 extern void mvme16x_reset (void);
 
 int bcd2int (unsigned char b);
@@ -280,7 +279,6 @@ void __init config_mvme16x(void)
     mach_init_IRQ        = mvme16x_init_IRQ;
     arch_gettimeoffset   = mvme16x_gettimeoffset;
     mach_hwclk           = mvme16x_hwclk;
-    mach_set_clock_mmss	 = mvme16x_set_clock_mmss;
     mach_reset		 = mvme16x_reset;
     mach_get_model       = mvme16x_get_model;
     mach_get_hardware_list = mvme16x_get_hardware_list;
@@ -411,9 +409,3 @@ int mvme16x_hwclk(int op, struct rtc_time *t)
 	}
 	return 0;
 }
-
-int mvme16x_set_clock_mmss (unsigned long nowtime)
-{
-	return 0;
-}
-
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 71c0867ecf20..96810d91da2b 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -43,7 +43,6 @@ extern void q40_sched_init(irq_handler_t handler);
 static u32 q40_gettimeoffset(void);
 static int q40_hwclk(int, struct rtc_time *);
 static unsigned int q40_get_ss(void);
-static int q40_set_clock_mmss(unsigned long);
 static int q40_get_rtc_pll(struct rtc_pll_info *pll);
 static int q40_set_rtc_pll(struct rtc_pll_info *pll);
 
@@ -175,7 +174,6 @@ void __init config_q40(void)
 	mach_get_ss = q40_get_ss;
 	mach_get_rtc_pll = q40_get_rtc_pll;
 	mach_set_rtc_pll = q40_set_rtc_pll;
-	mach_set_clock_mmss = q40_set_clock_mmss;
 
 	mach_reset = q40_reset;
 	mach_get_model = q40_get_model;
@@ -267,34 +265,6 @@ static unsigned int q40_get_ss(void)
 	return bcd2bin(Q40_RTC_SECS);
 }
 
-/*
- * Set the minutes and seconds from seconds value 'nowtime'.  Fail if
- * clock is out by > 30 minutes.  Logic lifted from atari code.
- */
-
-static int q40_set_clock_mmss(unsigned long nowtime)
-{
-	int retval = 0;
-	short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-
-	int rtc_minutes;
-
-	rtc_minutes = bcd2bin(Q40_RTC_MINS);
-
-	if ((rtc_minutes < real_minutes ?
-	     real_minutes - rtc_minutes :
-	     rtc_minutes - real_minutes) < 30) {
-		Q40_RTC_CTRL |= Q40_RTC_WRITE;
-		Q40_RTC_MINS = bin2bcd(real_minutes);
-		Q40_RTC_SECS = bin2bcd(real_seconds);
-		Q40_RTC_CTRL &= ~(Q40_RTC_WRITE);
-	} else
-		retval = -1;
-
-	return retval;
-}
-
-
 /* get and set PLL calibration of RTC clock */
 #define Q40_RTC_PLL_MASK ((1<<5)-1)
 #define Q40_RTC_PLL_SIGN (1<<5)
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index 1d28d380e8cc..79a2bb857906 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -123,10 +123,6 @@ static void __init sun3_bootmem_alloc(unsigned long memory_start,
 	availmem = memory_start;
 
 	m68k_setup_node(0);
-	availmem += init_bootmem(start_page, num_pages);
-	availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK;
-
-	free_bootmem(__pa(availmem), memory_end - (availmem));
 }
 
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 08c10c518f83..642a56e2a1ea 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -16,6 +16,7 @@ config MIPS
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select CPU_PM if CPU_IDLE
+	select DMA_DIRECT_OPS
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CMOS_UPDATE
@@ -97,6 +98,7 @@ config MIPS_GENERIC
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
 	select LIBFDT
+	select MIPS_AUTO_PFN_OFFSET
 	select MIPS_CPU_SCACHE
 	select MIPS_GIC
 	select MIPS_L1_CACHE_SHIFT_7
@@ -193,6 +195,7 @@ config ATH79
 	select CSRC_R4K
 	select DMA_NONCOHERENT
 	select GPIOLIB
+	select PINCTRL
 	select HAVE_CLK
 	select COMMON_CLK
 	select CLKDEV_LOOKUP
@@ -211,6 +214,8 @@ config ATH79
 
 config BMIPS_GENERIC
 	bool "Broadcom Generic BMIPS kernel"
+	select ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+	select ARCH_HAS_PHYS_TO_DMA
 	select BOOT_RAW
 	select NO_EXCEPT_FILL
 	select USE_OF
@@ -438,7 +443,6 @@ config MACH_LOONGSON32
 
 config MACH_LOONGSON64
 	bool "Loongson-2/3 family of machines"
-	select ARCH_HAS_PHYS_TO_DMA
 	select SYS_SUPPORTS_ZBOOT
 	help
 	  This enables the support of Loongson-2/3 family of machines.
@@ -662,11 +666,11 @@ config SGI_IP22
 
 config SGI_IP27
 	bool "SGI IP27 (Origin200/2000)"
+	select ARCH_HAS_PHYS_TO_DMA
 	select FW_ARC
 	select FW_ARC64
 	select BOOT_ELF64
 	select DEFAULT_SGI_PARTITION
-	select DMA_COHERENT
 	select SYS_HAS_EARLY_PRINTK
 	select HW_HAS_PCI
 	select NR_CPUS_DEFAULT_64
@@ -721,6 +725,7 @@ config SGI_IP28
 
 config SGI_IP32
 	bool "SGI IP32 (O2)"
+	select ARCH_HAS_PHYS_TO_DMA
 	select FW_ARC
 	select FW_ARC32
 	select BOOT_ELF32
@@ -743,7 +748,6 @@ config SGI_IP32
 config SIBYTE_CRHINE
 	bool "Sibyte BCM91120C-CRhine"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -753,7 +757,6 @@ config SIBYTE_CRHINE
 config SIBYTE_CARMEL
 	bool "Sibyte BCM91120x-Carmel"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -763,7 +766,6 @@ config SIBYTE_CARMEL
 config SIBYTE_CRHONE
 	bool "Sibyte BCM91125C-CRhone"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1125
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -774,7 +776,6 @@ config SIBYTE_CRHONE
 config SIBYTE_RHONE
 	bool "Sibyte BCM91125E-Rhone"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1125H
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -784,7 +785,6 @@ config SIBYTE_RHONE
 config SIBYTE_SWARM
 	bool "Sibyte BCM91250A-SWARM"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select HAVE_PATA_PLATFORM
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -797,7 +797,6 @@ config SIBYTE_SWARM
 config SIBYTE_LITTLESUR
 	bool "Sibyte BCM91250C2-LittleSur"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select HAVE_PATA_PLATFORM
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -809,7 +808,6 @@ config SIBYTE_LITTLESUR
 config SIBYTE_SENTOSA
 	bool "Sibyte BCM91250E-Sentosa"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -819,7 +817,6 @@ config SIBYTE_SENTOSA
 config SIBYTE_BIGSUR
 	bool "Sibyte BCM91480B-BigSur"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select NR_CPUS_DEFAULT_4
 	select SIBYTE_BCM1x80
 	select SWAP_IO_SPACE
@@ -895,8 +892,8 @@ config CAVIUM_OCTEON_SOC
 	bool "Cavium Networks Octeon SoC based boards"
 	select CEVT_R4K
 	select ARCH_HAS_PHYS_TO_DMA
+	select HAS_RAPIDIO
 	select PHYS_ADDR_T_64BIT
-	select DMA_COHERENT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select EDAC_SUPPORT
@@ -945,7 +942,6 @@ config NLM_XLR_BOARD
 	select PHYS_ADDR_T_64BIT
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
-	select DMA_COHERENT
 	select NR_CPUS_DEFAULT_32
 	select CEVT_R4K
 	select CSRC_R4K
@@ -973,7 +969,6 @@ config NLM_XLP_BOARD
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
-	select DMA_COHERENT
 	select NR_CPUS_DEFAULT_32
 	select CEVT_R4K
 	select CSRC_R4K
@@ -992,7 +987,6 @@ config MIPS_PARAVIRT
 	bool "Para-Virtualized guest system"
 	select CEVT_R4K
 	select CSRC_R4K
-	select DMA_COHERENT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
@@ -1118,12 +1112,14 @@ config DMA_PERDEV_COHERENT
 	bool
 	select DMA_MAYBE_COHERENT
 
-config DMA_COHERENT
-	bool
-
 config DMA_NONCOHERENT
 	bool
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select NEED_DMA_MAP_STATE
+	select DMA_NONCOHERENT_MMAP
+	select DMA_NONCOHERENT_CACHE_SYNC
+	select DMA_NONCOHERENT_OPS
 
 config SYS_HAS_EARLY_PRINTK
 	bool
@@ -1365,6 +1361,7 @@ choice
 config CPU_LOONGSON3
 	bool "Loongson 3 CPU"
 	depends on SYS_HAS_CPU_LOONGSON3
+	select ARCH_HAS_PHYS_TO_DMA
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
@@ -1427,7 +1424,8 @@ config CPU_LOONGSON1B
 	select LEDS_GPIO_REGISTER
 	help
 	  The Loongson 1B is a 32-bit SoC, which implements the MIPS32
-	  release 2 instruction set.
+	  Release 1 instruction set and part of the MIPS32 Release 2
+	  instruction set.
 
 config CPU_LOONGSON1C
 	bool "Loongson 1C"
@@ -1436,7 +1434,8 @@ config CPU_LOONGSON1C
 	select LEDS_GPIO_REGISTER
 	help
 	  The Loongson 1C is a 32-bit SoC, which implements the MIPS32
-	  release 2 instruction set.
+	  Release 1 instruction set and part of the MIPS32 Release 2
+	  instruction set.
 
 config CPU_MIPS32_R1
 	bool "MIPS32 Release 1"
@@ -1831,11 +1830,12 @@ config CPU_LOONGSON2
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
+	select ARCH_HAS_PHYS_TO_DMA
 
 config CPU_LOONGSON1
 	bool
 	select CPU_MIPS32
-	select CPU_MIPSR2
+	select CPU_MIPSR1
 	select CPU_HAS_PREFETCH
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1979,12 +1979,6 @@ config SYS_HAS_CPU_XLR
 config SYS_HAS_CPU_XLP
 	bool
 
-config MIPS_MALTA_PM
-	depends on MIPS_MALTA
-	depends on PCI
-	bool
-	default y
-
 #
 # CPU may reorder R->R, R->W, W->R, W->W
 # Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC
@@ -2994,6 +2988,9 @@ config PGTABLE_LEVELS
 	default 3 if 64BIT && !PAGE_SIZE_64KB
 	default 2
 
+config MIPS_AUTO_PFN_OFFSET
+	bool
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
@@ -3115,10 +3112,13 @@ config ZONE_DMA32
 
 source "drivers/pcmcia/Kconfig"
 
+config HAS_RAPIDIO
+	bool
+	default n
+
 config RAPIDIO
 	tristate "RapidIO support"
-	depends on PCI
-	default n
+	depends on HAS_RAPIDIO || PCI
 	help
 	  If you say Y here, the kernel will include drivers and
 	  infrastructure code to support RapidIO interconnect devices.
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index e2122cca4ae2..5425df002a6b 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -122,12 +122,22 @@ cflags-y += -ffreestanding
 # are used, so we kludge that here.  A bug has been filed at
 # http://gcc.gnu.org/bugzilla/show_bug.cgi?id=29413.
 #
+# clang doesn't suffer from these issues and our checks against -dumpmachine
+# don't work so well when cross compiling, since without providing --target
+# clang's output will be based upon the build machine. So for clang we simply
+# unconditionally specify -EB or -EL as appropriate.
+#
+ifeq ($(cc-name),clang)
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -EB
+cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -EL
+else
 undef-all += -UMIPSEB -U_MIPSEB -U__MIPSEB -U__MIPSEB__
 undef-all += -UMIPSEL -U_MIPSEL -U__MIPSEL -U__MIPSEL__
 predef-be += -DMIPSEB -D_MIPSEB -D__MIPSEB -D__MIPSEB__
 predef-le += -DMIPSEL -D_MIPSEL -D__MIPSEL -D__MIPSEL__
 cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' && echo -EB $(undef-all) $(predef-be))
 cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' || echo -EL $(undef-all) $(predef-le))
+endif
 
 cflags-$(CONFIG_SB1XXX_CORELIS)	+= $(call cc-option,-mno-sched-prolog) \
 				   -fno-omit-frame-pointer
@@ -155,15 +165,11 @@ cflags-$(CONFIG_CPU_R4300)	+= -march=r4300 -Wa,--trap
 cflags-$(CONFIG_CPU_VR41XX)	+= -march=r4100 -Wa,--trap
 cflags-$(CONFIG_CPU_R4X00)	+= -march=r4600 -Wa,--trap
 cflags-$(CONFIG_CPU_TX49XX)	+= -march=r4600 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS32_R1)	+= $(call cc-option,-march=mips32,-mips32 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
-			-Wa,-mips32 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS32_R2)	+= $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
-			-Wa,-mips32r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS32_R1)	+= -march=mips32 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS32_R2)	+= -march=mips32r2 -Wa,--trap
 cflags-$(CONFIG_CPU_MIPS32_R6)	+= -march=mips32r6 -Wa,--trap -modd-spreg
-cflags-$(CONFIG_CPU_MIPS64_R1)	+= $(call cc-option,-march=mips64,-mips64 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
-			-Wa,-mips64 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS64_R2)	+= $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
-			-Wa,-mips64r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS64_R1)	+= -march=mips64 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS64_R2)	+= -march=mips64r2 -Wa,--trap
 cflags-$(CONFIG_CPU_MIPS64_R6)	+= -march=mips64r6 -Wa,--trap
 cflags-$(CONFIG_CPU_R5000)	+= -march=r5000 -Wa,--trap
 cflags-$(CONFIG_CPU_R5432)	+= $(call cc-option,-march=r5400,-march=r5000) \
diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c
index fa75d75b5ba9..ddff9a02513d 100644
--- a/arch/mips/alchemy/board-gpr.c
+++ b/arch/mips/alchemy/board-gpr.c
@@ -34,6 +34,7 @@
 #include <asm/bootinfo.h>
 #include <asm/idle.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/gpio-au1000.h>
 #include <prom.h>
@@ -60,7 +61,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index aab55aaf3d62..d625e6f99ae7 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -31,6 +31,7 @@
 #include <mtd/mtd-abi.h>
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/gpio-au1000.h>
 #include <asm/mach-au1x00/au1xxx_eth.h>
@@ -58,7 +59,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c
index 0fc53e08a894..5f05b8714385 100644
--- a/arch/mips/alchemy/board-xxs1500.c
+++ b/arch/mips/alchemy/board-xxs1500.c
@@ -29,6 +29,7 @@
 #include <linux/pm.h>
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <prom.h>
 
@@ -55,7 +56,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/devboards/platform.c b/arch/mips/alchemy/devboards/platform.c
index 203854ddd1bb..8d4b65c3268a 100644
--- a/arch/mips/alchemy/devboards/platform.c
+++ b/arch/mips/alchemy/devboards/platform.c
@@ -14,6 +14,7 @@
 #include <asm/bootinfo.h>
 #include <asm/idle.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-db1x00/bcsr.h>
 
@@ -36,7 +37,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	if (alchemy_get_cputype() == ALCHEMY_CPU_AU1300)
 		alchemy_uart_putchar(AU1300_UART2_PHYS_ADDR, c);
diff --git a/arch/mips/ar7/clock.c b/arch/mips/ar7/clock.c
index 0137656107a9..6b64fd96dba8 100644
--- a/arch/mips/ar7/clock.c
+++ b/arch/mips/ar7/clock.c
@@ -476,3 +476,32 @@ void __init ar7_init_clocks(void)
 	/* adjust vbus clock rate */
 	vbus_clk.rate = bus_clk.rate / 2;
 }
+
+/* dummy functions, should not be called */
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_round_rate);
+
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_rate);
+
+int clk_set_parent(struct clk *clk, struct clk *parent)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_parent);
+
+struct clk *clk_get_parent(struct clk *clk)
+{
+	WARN_ON(clk);
+	return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
diff --git a/arch/mips/ar7/prom.c b/arch/mips/ar7/prom.c
index dd53987a690f..2ec8d9ac91ec 100644
--- a/arch/mips/ar7/prom.c
+++ b/arch/mips/ar7/prom.c
@@ -25,6 +25,7 @@
 #include <linux/string.h>
 #include <linux/io.h>
 #include <asm/bootinfo.h>
+#include <asm/setup.h>
 
 #include <asm/mach-ar7/ar7.h>
 #include <asm/mach-ar7/prom.h>
@@ -259,10 +260,9 @@ static inline void serial_out(int offset, int value)
 	writel(value, (void *)PORT(offset));
 }
 
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	while ((serial_in(UART_LSR) & UART_LSR_TEMT) == 0)
 		;
 	serial_out(UART_TX, c);
-	return 1;
 }
diff --git a/arch/mips/ath25/Kconfig b/arch/mips/ath25/Kconfig
index 7070b4bcd01d..2c1dfd06c366 100644
--- a/arch/mips/ath25/Kconfig
+++ b/arch/mips/ath25/Kconfig
@@ -12,6 +12,7 @@ config SOC_AR2315
 config PCI_AR2315
 	bool "Atheros AR2315 PCI controller support"
 	depends on SOC_AR2315
+	select ARCH_HAS_PHYS_TO_DMA
 	select HW_HAS_PCI
 	select PCI
 	default y
diff --git a/arch/mips/ath25/board.c b/arch/mips/ath25/board.c
index 6d11ae581ea7..989e71015ee6 100644
--- a/arch/mips/ath25/board.c
+++ b/arch/mips/ath25/board.c
@@ -146,10 +146,10 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size)
 			pr_info("Fixing up empty mac addresses\n");
 			config->reset_config_gpio = 0xffff;
 			config->sys_led_gpio = 0xffff;
-			random_ether_addr(config->wlan0_mac);
+			eth_random_addr(config->wlan0_mac);
 			config->wlan0_mac[0] &= ~0x06;
-			random_ether_addr(config->enet0_mac);
-			random_ether_addr(config->enet1_mac);
+			eth_random_addr(config->enet0_mac);
+			eth_random_addr(config->enet1_mac);
 		}
 	}
 
diff --git a/arch/mips/ath25/early_printk.c b/arch/mips/ath25/early_printk.c
index 36035b628161..d534761e9cda 100644
--- a/arch/mips/ath25/early_printk.c
+++ b/arch/mips/ath25/early_printk.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/io.h>
 #include <linux/serial_reg.h>
+#include <asm/setup.h>
 
 #include "devices.h"
 #include "ar2315_regs.h"
@@ -25,7 +26,7 @@ static inline unsigned char prom_uart_rr(void __iomem *base, unsigned reg)
 	return __raw_readl(base + 4 * reg);
 }
 
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
 {
 	static void __iomem *base;
 
@@ -38,7 +39,7 @@ void prom_putchar(unsigned char ch)
 
 	while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0)
 		;
-	prom_uart_wr(base, UART_TX, ch);
+	prom_uart_wr(base, UART_TX, (unsigned char)ch);
 	while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0)
 		;
 }
diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c
index 6b1000b6a6a6..cf9158e3c2d9 100644
--- a/arch/mips/ath79/clock.c
+++ b/arch/mips/ath79/clock.c
@@ -355,6 +355,91 @@ static void __init ar934x_clocks_init(void)
 	iounmap(dpll_base);
 }
 
+static void __init qca953x_clocks_init(void)
+{
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
+	u32 pll, out_div, ref_div, nint, frac, clk_ctrl, postdiv;
+	u32 cpu_pll, ddr_pll;
+	u32 bootstrap;
+
+	bootstrap = ath79_reset_rr(QCA953X_RESET_REG_BOOTSTRAP);
+	if (bootstrap &	QCA953X_BOOTSTRAP_REF_CLK_40)
+		ref_rate = 40 * 1000 * 1000;
+	else
+		ref_rate = 25 * 1000 * 1000;
+
+	pll = ath79_pll_rr(QCA953X_PLL_CPU_CONFIG_REG);
+	out_div = (pll >> QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
+		  QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
+		  QCA953X_PLL_CPU_CONFIG_REFDIV_MASK;
+	nint = (pll >> QCA953X_PLL_CPU_CONFIG_NINT_SHIFT) &
+	       QCA953X_PLL_CPU_CONFIG_NINT_MASK;
+	frac = (pll >> QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT) &
+	       QCA953X_PLL_CPU_CONFIG_NFRAC_MASK;
+
+	cpu_pll = nint * ref_rate / ref_div;
+	cpu_pll += frac * (ref_rate >> 6) / ref_div;
+	cpu_pll /= (1 << out_div);
+
+	pll = ath79_pll_rr(QCA953X_PLL_DDR_CONFIG_REG);
+	out_div = (pll >> QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT) &
+		  QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT) &
+		  QCA953X_PLL_DDR_CONFIG_REFDIV_MASK;
+	nint = (pll >> QCA953X_PLL_DDR_CONFIG_NINT_SHIFT) &
+	       QCA953X_PLL_DDR_CONFIG_NINT_MASK;
+	frac = (pll >> QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT) &
+	       QCA953X_PLL_DDR_CONFIG_NFRAC_MASK;
+
+	ddr_pll = nint * ref_rate / ref_div;
+	ddr_pll += frac * (ref_rate >> 6) / (ref_div << 4);
+	ddr_pll /= (1 << out_div);
+
+	clk_ctrl = ath79_pll_rr(QCA953X_PLL_CLK_CTRL_REG);
+
+	postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) &
+		  QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
+		cpu_rate = ref_rate;
+	else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL)
+		cpu_rate = cpu_pll / (postdiv + 1);
+	else
+		cpu_rate = ddr_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
+		  QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
+		ddr_rate = ref_rate;
+	else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL)
+		ddr_rate = ddr_pll / (postdiv + 1);
+	else
+		ddr_rate = cpu_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
+		  QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
+		ahb_rate = ref_rate;
+	else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
+		ahb_rate = ddr_pll / (postdiv + 1);
+	else
+		ahb_rate = cpu_pll / (postdiv + 1);
+
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
+
+	clk_add_alias("wdt", NULL, "ref", NULL);
+	clk_add_alias("uart", NULL, "ref", NULL);
+}
+
 static void __init qca955x_clocks_init(void)
 {
 	unsigned long ref_rate;
@@ -440,6 +525,110 @@ static void __init qca955x_clocks_init(void)
 	clk_add_alias("uart", NULL, "ref", NULL);
 }
 
+static void __init qca956x_clocks_init(void)
+{
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
+	u32 pll, out_div, ref_div, nint, hfrac, lfrac, clk_ctrl, postdiv;
+	u32 cpu_pll, ddr_pll;
+	u32 bootstrap;
+
+	/*
+	 * QCA956x timer init workaround has to be applied right before setting
+	 * up the clock. Else, there will be no jiffies
+	 */
+	u32 misc;
+
+	misc = ath79_reset_rr(AR71XX_RESET_REG_MISC_INT_ENABLE);
+	misc |= MISC_INT_MIPS_SI_TIMERINT_MASK;
+	ath79_reset_wr(AR71XX_RESET_REG_MISC_INT_ENABLE, misc);
+
+	bootstrap = ath79_reset_rr(QCA956X_RESET_REG_BOOTSTRAP);
+	if (bootstrap &	QCA956X_BOOTSTRAP_REF_CLK_40)
+		ref_rate = 40 * 1000 * 1000;
+	else
+		ref_rate = 25 * 1000 * 1000;
+
+	pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG_REG);
+	out_div = (pll >> QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
+		  QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
+		  QCA956X_PLL_CPU_CONFIG_REFDIV_MASK;
+
+	pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG1_REG);
+	nint = (pll >> QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT) &
+	       QCA956X_PLL_CPU_CONFIG1_NINT_MASK;
+	hfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT) &
+	       QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK;
+	lfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT) &
+	       QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK;
+
+	cpu_pll = nint * ref_rate / ref_div;
+	cpu_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13);
+	cpu_pll += (hfrac >> 13) * ref_rate / ref_div;
+	cpu_pll /= (1 << out_div);
+
+	pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG_REG);
+	out_div = (pll >> QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT) &
+		  QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT) &
+		  QCA956X_PLL_DDR_CONFIG_REFDIV_MASK;
+	pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG1_REG);
+	nint = (pll >> QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT) &
+	       QCA956X_PLL_DDR_CONFIG1_NINT_MASK;
+	hfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT) &
+	       QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK;
+	lfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT) &
+	       QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK;
+
+	ddr_pll = nint * ref_rate / ref_div;
+	ddr_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13);
+	ddr_pll += (hfrac >> 13) * ref_rate / ref_div;
+	ddr_pll /= (1 << out_div);
+
+	clk_ctrl = ath79_pll_rr(QCA956X_PLL_CLK_CTRL_REG);
+
+	postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) &
+		  QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
+		cpu_rate = ref_rate;
+	else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL)
+		cpu_rate = ddr_pll / (postdiv + 1);
+	else
+		cpu_rate = cpu_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
+		  QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
+		ddr_rate = ref_rate;
+	else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL)
+		ddr_rate = cpu_pll / (postdiv + 1);
+	else
+		ddr_rate = ddr_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
+		  QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
+		ahb_rate = ref_rate;
+	else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
+		ahb_rate = ddr_pll / (postdiv + 1);
+	else
+		ahb_rate = cpu_pll / (postdiv + 1);
+
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
+
+	clk_add_alias("wdt", NULL, "ref", NULL);
+	clk_add_alias("uart", NULL, "ref", NULL);
+}
+
 void __init ath79_clocks_init(void)
 {
 	if (soc_is_ar71xx())
@@ -450,8 +639,12 @@ void __init ath79_clocks_init(void)
 		ar933x_clocks_init();
 	else if (soc_is_ar934x())
 		ar934x_clocks_init();
+	else if (soc_is_qca953x())
+		qca953x_clocks_init();
 	else if (soc_is_qca955x())
 		qca955x_clocks_init();
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		qca956x_clocks_init();
 	else
 		BUG();
 }
diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
index c782b10ddf50..cd6055f9e7a0 100644
--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -103,8 +103,12 @@ void ath79_device_reset_set(u32 mask)
 		reg = AR933X_RESET_REG_RESET_MODULE;
 	else if (soc_is_ar934x())
 		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
 	else if (soc_is_qca955x())
 		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
 	else
 		BUG();
 
@@ -131,8 +135,12 @@ void ath79_device_reset_clear(u32 mask)
 		reg = AR933X_RESET_REG_RESET_MODULE;
 	else if (soc_is_ar934x())
 		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
 	else if (soc_is_qca955x())
 		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
 	else
 		BUG();
 
diff --git a/arch/mips/ath79/early_printk.c b/arch/mips/ath79/early_printk.c
index d1adc59af5bf..4b1063117ef7 100644
--- a/arch/mips/ath79/early_printk.c
+++ b/arch/mips/ath79/early_printk.c
@@ -13,12 +13,13 @@
 #include <linux/errno.h>
 #include <linux/serial_reg.h>
 #include <asm/addrspace.h>
+#include <asm/setup.h>
 
 #include <asm/mach-ath79/ath79.h>
 #include <asm/mach-ath79/ar71xx_regs.h>
 #include <asm/mach-ath79/ar933x_uart.h>
 
-static void (*_prom_putchar) (unsigned char);
+static void (*_prom_putchar)(char);
 
 static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
 {
@@ -33,31 +34,72 @@ static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
 
 #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
 
-static void prom_putchar_ar71xx(unsigned char ch)
+static void prom_putchar_ar71xx(char ch)
 {
 	void __iomem *base = (void __iomem *)(KSEG1ADDR(AR71XX_UART_BASE));
 
 	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
-	__raw_writel(ch, base + UART_TX * 4);
+	__raw_writel((unsigned char)ch, base + UART_TX * 4);
 	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
 }
 
-static void prom_putchar_ar933x(unsigned char ch)
+static void prom_putchar_ar933x(char ch)
 {
 	void __iomem *base = (void __iomem *)(KSEG1ADDR(AR933X_UART_BASE));
 
 	prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR,
 			  AR933X_UART_DATA_TX_CSR);
-	__raw_writel(AR933X_UART_DATA_TX_CSR | ch, base + AR933X_UART_DATA_REG);
+	__raw_writel(AR933X_UART_DATA_TX_CSR | (unsigned char)ch,
+		     base + AR933X_UART_DATA_REG);
 	prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR,
 			  AR933X_UART_DATA_TX_CSR);
 }
 
-static void prom_putchar_dummy(unsigned char ch)
+static void prom_putchar_dummy(char ch)
 {
 	/* nothing to do */
 }
 
+static void prom_enable_uart(u32 id)
+{
+	void __iomem *gpio_base;
+	u32 uart_en;
+	u32 t;
+
+	switch (id) {
+	case REV_ID_MAJOR_AR71XX:
+		uart_en = AR71XX_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR7240:
+	case REV_ID_MAJOR_AR7241:
+	case REV_ID_MAJOR_AR7242:
+		uart_en = AR724X_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR913X:
+		uart_en = AR913X_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR9330:
+	case REV_ID_MAJOR_AR9331:
+		uart_en = AR933X_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR9341:
+	case REV_ID_MAJOR_AR9342:
+	case REV_ID_MAJOR_AR9344:
+		/* TODO */
+	default:
+		return;
+	}
+
+	gpio_base = (void __iomem *)KSEG1ADDR(AR71XX_GPIO_BASE);
+	t = __raw_readl(gpio_base + AR71XX_GPIO_REG_FUNC);
+	t |= uart_en;
+	__raw_writel(t, gpio_base + AR71XX_GPIO_REG_FUNC);
+}
+
 static void prom_putchar_init(void)
 {
 	void __iomem *base;
@@ -76,8 +118,12 @@ static void prom_putchar_init(void)
 	case REV_ID_MAJOR_AR9341:
 	case REV_ID_MAJOR_AR9342:
 	case REV_ID_MAJOR_AR9344:
+	case REV_ID_MAJOR_QCA9533:
+	case REV_ID_MAJOR_QCA9533_V2:
 	case REV_ID_MAJOR_QCA9556:
 	case REV_ID_MAJOR_QCA9558:
+	case REV_ID_MAJOR_TP9343:
+	case REV_ID_MAJOR_QCA956X:
 		_prom_putchar = prom_putchar_ar71xx;
 		break;
 
@@ -88,11 +134,13 @@ static void prom_putchar_init(void)
 
 	default:
 		_prom_putchar = prom_putchar_dummy;
-		break;
+		return;
 	}
+
+	prom_enable_uart(id);
 }
 
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
 {
 	if (!_prom_putchar)
 		prom_putchar_init();
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index f206dafbb0a3..4c7a93f4039a 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -40,6 +40,7 @@ static char ath79_sys_type[ATH79_SYS_TYPE_LEN];
 
 static void ath79_restart(char *command)
 {
+	local_irq_disable();
 	ath79_device_reset_set(AR71XX_RESET_FULL_CHIP);
 	for (;;)
 		if (cpu_wait)
@@ -59,6 +60,7 @@ static void __init ath79_detect_sys_type(void)
 	u32 major;
 	u32 minor;
 	u32 rev = 0;
+	u32 ver = 1;
 
 	id = ath79_reset_rr(AR71XX_RESET_REG_REV_ID);
 	major = id & REV_ID_MAJOR_MASK;
@@ -151,6 +153,17 @@ static void __init ath79_detect_sys_type(void)
 		rev = id & AR934X_REV_ID_REVISION_MASK;
 		break;
 
+	case REV_ID_MAJOR_QCA9533_V2:
+		ver = 2;
+		ath79_soc_rev = 2;
+		/* drop through */
+
+	case REV_ID_MAJOR_QCA9533:
+		ath79_soc = ATH79_SOC_QCA9533;
+		chip = "9533";
+		rev = id & QCA953X_REV_ID_REVISION_MASK;
+		break;
+
 	case REV_ID_MAJOR_QCA9556:
 		ath79_soc = ATH79_SOC_QCA9556;
 		chip = "9556";
@@ -163,14 +176,30 @@ static void __init ath79_detect_sys_type(void)
 		rev = id & QCA955X_REV_ID_REVISION_MASK;
 		break;
 
+	case REV_ID_MAJOR_QCA956X:
+		ath79_soc = ATH79_SOC_QCA956X;
+		chip = "956X";
+		rev = id & QCA956X_REV_ID_REVISION_MASK;
+		break;
+
+	case REV_ID_MAJOR_TP9343:
+		ath79_soc = ATH79_SOC_TP9343;
+		chip = "9343";
+		rev = id & QCA956X_REV_ID_REVISION_MASK;
+		break;
+
 	default:
 		panic("ath79: unknown SoC, id:0x%08x", id);
 	}
 
-	ath79_soc_rev = rev;
+	if (ver == 1)
+		ath79_soc_rev = rev;
 
-	if (soc_is_qca955x())
-		sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s rev %u",
+	if (soc_is_qca953x() || soc_is_qca955x() || soc_is_qca956x())
+		sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s ver %u rev %u",
+			chip, ver, rev);
+	else if (soc_is_tp9343())
+		sprintf(ath79_sys_type, "Qualcomm Atheros TP%s rev %u",
 			chip, rev);
 	else
 		sprintf(ath79_sys_type, "Atheros AR%s rev %u", chip, rev);
diff --git a/arch/mips/bcm63xx/early_printk.c b/arch/mips/bcm63xx/early_printk.c
index 6092226a6d76..9e9ec27c282f 100644
--- a/arch/mips/bcm63xx/early_printk.c
+++ b/arch/mips/bcm63xx/early_printk.c
@@ -8,6 +8,7 @@
 
 #include <bcm63xx_io.h>
 #include <linux/serial_bcm63xx.h>
+#include <asm/setup.h>
 
 static void wait_xfered(void)
 {
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index 6dec30842b2f..3d13c77c125f 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -17,7 +17,7 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/types.h>
-#include <dma-coherence.h>
+#include <asm/bmips.h>
 
 /*
  * BCM338x has configurable address translation windows which allow the
@@ -40,7 +40,7 @@ static struct bmips_dma_range *bmips_dma_ranges;
 
 #define FLUSH_RAC		0x100
 
-static dma_addr_t bmips_phys_to_dma(struct device *dev, phys_addr_t pa)
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
 {
 	struct bmips_dma_range *r;
 
@@ -52,17 +52,7 @@ static dma_addr_t bmips_phys_to_dma(struct device *dev, phys_addr_t pa)
 	return pa;
 }
 
-dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
-	return bmips_phys_to_dma(dev, virt_to_phys(addr));
-}
-
-dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page)
-{
-	return bmips_phys_to_dma(dev, page_to_phys(page));
-}
-
-unsigned long plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	struct bmips_dma_range *r;
 
@@ -74,6 +64,22 @@ unsigned long plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
 	return dma_addr;
 }
 
+void arch_sync_dma_for_cpu_all(struct device *dev)
+{
+	void __iomem *cbr = BMIPS_GET_CBR();
+	u32 cfg;
+
+	if (boot_cpu_type() != CPU_BMIPS3300 &&
+	    boot_cpu_type() != CPU_BMIPS4350 &&
+	    boot_cpu_type() != CPU_BMIPS4380)
+		return;
+
+	/* Flush stale data out of the readahead cache */
+	cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
+	__raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG);
+	__raw_readl(cbr + BMIPS_RAC_CONFIG);
+}
+
 static int __init bmips_init_dma_ranges(void)
 {
 	struct device_node *np =
diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c
index 3b6f687f177c..231fc5ce375e 100644
--- a/arch/mips/bmips/setup.c
+++ b/arch/mips/bmips/setup.c
@@ -202,13 +202,6 @@ void __init device_tree_init(void)
 	of_node_put(np);
 }
 
-int __init plat_of_setup(void)
-{
-	return __dt_register_buses("simple-bus", NULL);
-}
-
-arch_initcall(plat_of_setup);
-
 static int __init plat_dev_init(void)
 {
 	of_clk_init(NULL);
diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index c22da16d67b8..35704c28a28b 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -105,28 +105,29 @@ $(obj)/uImage: $(obj)/uImage.$(suffix-y)
 # Flattened Image Tree (.itb) images
 #
 
-targets += vmlinux.itb
-targets += vmlinux.gz.itb
-targets += vmlinux.bz2.itb
-targets += vmlinux.lzma.itb
-targets += vmlinux.lzo.itb
-
 ifeq ($(ADDR_BITS),32)
-	itb_addr_cells = 1
+itb_addr_cells = 1
 endif
 ifeq ($(ADDR_BITS),64)
-	itb_addr_cells = 2
+itb_addr_cells = 2
 endif
 
+targets += vmlinux.its.S
+
 quiet_cmd_its_cat = CAT     $@
-      cmd_its_cat = cat $^ >$@
+      cmd_its_cat = cat $(filter-out $(PHONY), $^) >$@
 
-$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS))
+$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS)) FORCE
 	$(call if_changed,its_cat)
 
+targets += vmlinux.its
+targets += vmlinux.gz.its
+targets += vmlinux.bz2.its
+targets += vmlinux.lzmo.its
+targets += vmlinux.lzo.its
+
 quiet_cmd_cpp_its_S = ITS     $@
-      cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \
-			-D__ASSEMBLY__ \
+      cmd_cpp_its_S = $(CPP) -P -C -o $@ $< \
 		        -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \
 			-DVMLINUX_BINARY="\"$(3)\"" \
 			-DVMLINUX_COMPRESSION="\"$(2)\"" \
@@ -136,19 +137,25 @@ quiet_cmd_cpp_its_S = ITS     $@
 			-DADDR_CELLS=$(itb_addr_cells)
 
 $(obj)/vmlinux.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,none,vmlinux.bin)
+	$(call if_changed,cpp_its_S,none,vmlinux.bin)
 
 $(obj)/vmlinux.gz.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,gzip,vmlinux.bin.gz)
+	$(call if_changed,cpp_its_S,gzip,vmlinux.bin.gz)
 
 $(obj)/vmlinux.bz2.its: $(obj)/vmlinux.its.S $(VMLINUX)  FORCE
-	$(call if_changed_dep,cpp_its_S,bzip2,vmlinux.bin.bz2)
+	$(call if_changed,cpp_its_S,bzip2,vmlinux.bin.bz2)
 
 $(obj)/vmlinux.lzma.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,lzma,vmlinux.bin.lzma)
+	$(call if_changed,cpp_its_S,lzma,vmlinux.bin.lzma)
 
 $(obj)/vmlinux.lzo.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,lzo,vmlinux.bin.lzo)
+	$(call if_changed,cpp_its_S,lzo,vmlinux.bin.lzo)
+
+targets += vmlinux.itb
+targets += vmlinux.gz.itb
+targets += vmlinux.bz2.itb
+targets += vmlinux.lzma.itb
+targets += vmlinux.lzo.itb
 
 quiet_cmd_itb-image = ITB     $@
       cmd_itb-image = \
@@ -162,14 +169,5 @@ quiet_cmd_itb-image = ITB     $@
 $(obj)/vmlinux.itb: $(obj)/vmlinux.its $(obj)/vmlinux.bin FORCE
 	$(call if_changed,itb-image,$<)
 
-$(obj)/vmlinux.gz.itb: $(obj)/vmlinux.gz.its $(obj)/vmlinux.bin.gz FORCE
-	$(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.bz2.itb: $(obj)/vmlinux.bz2.its $(obj)/vmlinux.bin.bz2 FORCE
-	$(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.lzma.itb: $(obj)/vmlinux.lzma.its $(obj)/vmlinux.bin.lzma FORCE
-	$(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.lzo.itb: $(obj)/vmlinux.lzo.its $(obj)/vmlinux.bin.lzo FORCE
+$(obj)/vmlinux.%.itb: $(obj)/vmlinux.%.its $(obj)/vmlinux.bin.% FORCE
 	$(call if_changed,itb-image,$<)
diff --git a/arch/mips/boot/compressed/uart-prom.c b/arch/mips/boot/compressed/uart-prom.c
index d6f0fee0a151..a8a0a32e05d1 100644
--- a/arch/mips/boot/compressed/uart-prom.c
+++ b/arch/mips/boot/compressed/uart-prom.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-
-extern void prom_putchar(unsigned char ch);
+#include <asm/setup.h>
 
 void putc(char c)
 {
diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi
index aa4e8f75ff5d..ce93d57f1b4d 100644
--- a/arch/mips/boot/dts/ingenic/jz4780.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi
@@ -155,6 +155,25 @@
 		};
 	};
 
+	spi_gpio {
+		compatible = "spi-gpio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		num-chipselects = <2>;
+
+		gpio-miso = <&gpe 14 0>;
+		gpio-sck = <&gpe 15 0>;
+		gpio-mosi = <&gpe 17 0>;
+		cs-gpios = <&gpe 16 0
+			    &gpe 18 0>;
+
+		spidev@0 {
+			compatible = "spidev";
+			reg = <0>;
+			spi-max-frequency = <1000000>;
+		};
+	};
+
 	uart0: serial@10030000 {
 		compatible = "ingenic,jz4780-uart";
 		reg = <0x10030000 0x100>;
diff --git a/arch/mips/boot/dts/mscc/Makefile b/arch/mips/boot/dts/mscc/Makefile
index 3c6aed9f5439..9a9bb7ea0503 100644
--- a/arch/mips/boot/dts/mscc/Makefile
+++ b/arch/mips/boot/dts/mscc/Makefile
@@ -1,3 +1,3 @@
-dtb-$(CONFIG_LEGACY_BOARD_OCELOT)	+= ocelot_pcb123.dtb
+dtb-$(CONFIG_MSCC_OCELOT)	+= ocelot_pcb123.dtb
 
 obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index 4f33dbc67348..f7eb612b46ba 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -91,6 +91,17 @@
 			status = "disabled";
 		};
 
+		spi: spi@101000 {
+			compatible = "mscc,ocelot-spi", "snps,dw-apb-ssi";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x101000 0x100>, <0x3c 0x18>;
+			interrupts = <9>;
+			clocks = <&ahb_clk>;
+
+			status = "disabled";
+		};
+
 		switch@1010000 {
 			compatible = "mscc,vsc7514-switch";
 			reg = <0x1010000 0x10000>,
@@ -168,6 +179,9 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-ranges = <&gpio 0 0 22>;
+			interrupt-controller;
+			interrupts = <13>;
+			#interrupt-cells = <2>;
 
 			uart_pins: uart-pins {
 				pins = "GPIO_6", "GPIO_7";
@@ -178,13 +192,18 @@
 				pins = "GPIO_12", "GPIO_13";
 				function = "uart2";
 			};
+
+			miim1: miim1 {
+				pins = "GPIO_14", "GPIO_15";
+				function = "miim1";
+			};
 		};
 
 		mdio0: mdio@107009c {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "mscc,ocelot-miim";
-			reg = <0x107009c 0x36>, <0x10700f0 0x8>;
+			reg = <0x107009c 0x24>, <0x10700f0 0x8>;
 			interrupts = <14>;
 			status = "disabled";
 
@@ -201,5 +220,16 @@
 				reg = <3>;
 			};
 		};
+
+		mdio1: mdio@10700c0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "mscc,ocelot-miim";
+			reg = <0x10700c0 0x24>;
+			interrupts = <15>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&miim1>;
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
index 4ccd65379059..2266027759f9 100644
--- a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
+++ b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
@@ -26,6 +26,16 @@
 	status = "okay";
 };
 
+&spi {
+	status = "okay";
+
+	flash@0 {
+		compatible = "macronix,mx25l25635f", "jedec,spi-nor";
+		spi-max-frequency = <20000000>;
+		reg = <0>;
+	};
+};
+
 &mdio0 {
 	status = "okay";
 };
diff --git a/arch/mips/boot/dts/qca/ar9132.dtsi b/arch/mips/boot/dts/qca/ar9132.dtsi
index 1fe561c5f90e..61dcfa5b6ca7 100644
--- a/arch/mips/boot/dts/qca/ar9132.dtsi
+++ b/arch/mips/boot/dts/qca/ar9132.dtsi
@@ -161,7 +161,7 @@
 	usb_phy: usb-phy {
 		compatible = "qca,ar7100-usb-phy";
 
-		reset-names = "usb-phy", "usb-suspend-override";
+		reset-names = "phy", "suspend-override";
 		resets = <&rst 4>, <&rst 3>;
 
 		#phy-cells = <0>;
diff --git a/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts b/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
index 3931033e47c8..7fccf6357225 100644
--- a/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
+++ b/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
@@ -22,11 +22,10 @@
 	};
 
 	gpio-keys {
-		compatible = "gpio-keys-polled";
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		poll-interval = <20>;
 		button@0 {
 			label = "reset";
 			linux,code = <KEY_RESTART>;
diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi
index efd5f0722206..2bae201aa365 100644
--- a/arch/mips/boot/dts/qca/ar9331.dtsi
+++ b/arch/mips/boot/dts/qca/ar9331.dtsi
@@ -146,7 +146,7 @@
 	usb_phy: usb-phy {
 		compatible = "qca,ar7100-usb-phy";
 
-		reset-names = "usb-phy", "usb-suspend-override";
+		reset-names = "phy", "suspend-override";
 		resets = <&rst 4>, <&rst 3>;
 
 		#phy-cells = <0>;
diff --git a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
index d4e4502daaa8..e7af2cf5f4c1 100644
--- a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
+++ b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
@@ -29,11 +29,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "reset";
diff --git a/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts b/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts
index 4f95ccf17c4c..d38aa73f1a2e 100644
--- a/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts
+++ b/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts
@@ -47,11 +47,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "jumpstart";
diff --git a/arch/mips/boot/dts/qca/ar9331_omega.dts b/arch/mips/boot/dts/qca/ar9331_omega.dts
index f70f79c4d0d5..11778abacf66 100644
--- a/arch/mips/boot/dts/qca/ar9331_omega.dts
+++ b/arch/mips/boot/dts/qca/ar9331_omega.dts
@@ -29,11 +29,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "reset";
diff --git a/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts b/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts
index 748131aea22e..c8290d36cfbe 100644
--- a/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts
+++ b/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts
@@ -47,11 +47,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "wps";
diff --git a/arch/mips/boot/ecoff.h b/arch/mips/boot/ecoff.h
index b3e73c22c345..5be79ebfc3f8 100644
--- a/arch/mips/boot/ecoff.h
+++ b/arch/mips/boot/ecoff.h
@@ -2,14 +2,17 @@
 /*
  * Some ECOFF definitions.
  */
+
+#include <stdint.h>
+
 typedef struct filehdr {
-	unsigned short	f_magic;	/* magic number */
-	unsigned short	f_nscns;	/* number of sections */
-	long		f_timdat;	/* time & date stamp */
-	long		f_symptr;	/* file pointer to symbolic header */
-	long		f_nsyms;	/* sizeof(symbolic hdr) */
-	unsigned short	f_opthdr;	/* sizeof(optional hdr) */
-	unsigned short	f_flags;	/* flags */
+	uint16_t	f_magic;	/* magic number */
+	uint16_t	f_nscns;	/* number of sections */
+	int32_t		f_timdat;	/* time & date stamp */
+	int32_t		f_symptr;	/* file pointer to symbolic header */
+	int32_t		f_nsyms;	/* sizeof(symbolic hdr) */
+	uint16_t	f_opthdr;	/* sizeof(optional hdr) */
+	uint16_t	f_flags;	/* flags */
 } FILHDR;
 #define FILHSZ	sizeof(FILHDR)
 
@@ -18,32 +21,32 @@ typedef struct filehdr {
 
 typedef struct scnhdr {
 	char		s_name[8];	/* section name */
-	long		s_paddr;	/* physical address, aliased s_nlib */
-	long		s_vaddr;	/* virtual address */
-	long		s_size;		/* section size */
-	long		s_scnptr;	/* file ptr to raw data for section */
-	long		s_relptr;	/* file ptr to relocation */
-	long		s_lnnoptr;	/* file ptr to gp histogram */
-	unsigned short	s_nreloc;	/* number of relocation entries */
-	unsigned short	s_nlnno;	/* number of gp histogram entries */
-	long		s_flags;	/* flags */
+	int32_t		s_paddr;	/* physical address, aliased s_nlib */
+	int32_t		s_vaddr;	/* virtual address */
+	int32_t		s_size;		/* section size */
+	int32_t		s_scnptr;	/* file ptr to raw data for section */
+	int32_t		s_relptr;	/* file ptr to relocation */
+	int32_t		s_lnnoptr;	/* file ptr to gp histogram */
+	uint16_t	s_nreloc;	/* number of relocation entries */
+	uint16_t	s_nlnno;	/* number of gp histogram entries */
+	int32_t		s_flags;	/* flags */
 } SCNHDR;
 #define SCNHSZ		sizeof(SCNHDR)
-#define SCNROUND	((long)16)
+#define SCNROUND	((int32_t)16)
 
 typedef struct aouthdr {
-	short	magic;		/* see above				*/
-	short	vstamp;		/* version stamp			*/
-	long	tsize;		/* text size in bytes, padded to DW bdry*/
-	long	dsize;		/* initialized data "  "		*/
-	long	bsize;		/* uninitialized data "	  "		*/
-	long	entry;		/* entry pt.				*/
-	long	text_start;	/* base of text used for this file	*/
-	long	data_start;	/* base of data used for this file	*/
-	long	bss_start;	/* base of bss used for this file	*/
-	long	gprmask;	/* general purpose register mask	*/
-	long	cprmask[4];	/* co-processor register masks		*/
-	long	gp_value;	/* the gp value used for this object	*/
+	int16_t	magic;		/* see above				*/
+	int16_t	vstamp;		/* version stamp			*/
+	int32_t	tsize;		/* text size in bytes, padded to DW bdry*/
+	int32_t	dsize;		/* initialized data "  "		*/
+	int32_t	bsize;		/* uninitialized data "	  "		*/
+	int32_t	entry;		/* entry pt.				*/
+	int32_t	text_start;	/* base of text used for this file	*/
+	int32_t	data_start;	/* base of data used for this file	*/
+	int32_t	bss_start;	/* base of bss used for this file	*/
+	int32_t	gprmask;	/* general purpose register mask	*/
+	int32_t	cprmask[4];	/* co-processor register masks		*/
+	int32_t	gp_value;	/* the gp value used for this object	*/
 } AOUTHDR;
 #define AOUTHSZ sizeof(AOUTHDR)
 
diff --git a/arch/mips/boot/elf2ecoff.c b/arch/mips/boot/elf2ecoff.c
index 266c8137e859..6972b97235da 100644
--- a/arch/mips/boot/elf2ecoff.c
+++ b/arch/mips/boot/elf2ecoff.c
@@ -43,6 +43,8 @@
 #include <limits.h>
 #include <netinet/in.h>
 #include <stdlib.h>
+#include <stdint.h>
+#include <inttypes.h>
 
 #include "ecoff.h"
 
@@ -55,8 +57,8 @@
 /* -------------------------------------------------------------------- */
 
 struct sect {
-	unsigned long vaddr;
-	unsigned long len;
+	uint32_t vaddr;
+	uint32_t len;
 };
 
 int *symTypeTable;
@@ -153,16 +155,16 @@ static char *saveRead(int file, off_t offset, off_t len, char *name)
 }
 
 #define swab16(x) \
-	((unsigned short)( \
-		(((unsigned short)(x) & (unsigned short)0x00ffU) << 8) | \
-		(((unsigned short)(x) & (unsigned short)0xff00U) >> 8) ))
+	((uint16_t)( \
+		(((uint16_t)(x) & (uint16_t)0x00ffU) << 8) | \
+		(((uint16_t)(x) & (uint16_t)0xff00U) >> 8) ))
 
 #define swab32(x) \
 	((unsigned int)( \
-		(((unsigned int)(x) & (unsigned int)0x000000ffUL) << 24) | \
-		(((unsigned int)(x) & (unsigned int)0x0000ff00UL) <<  8) | \
-		(((unsigned int)(x) & (unsigned int)0x00ff0000UL) >>  8) | \
-		(((unsigned int)(x) & (unsigned int)0xff000000UL) >> 24) ))
+		(((uint32_t)(x) & (uint32_t)0x000000ffUL) << 24) | \
+		(((uint32_t)(x) & (uint32_t)0x0000ff00UL) <<  8) | \
+		(((uint32_t)(x) & (uint32_t)0x00ff0000UL) >>  8) | \
+		(((uint32_t)(x) & (uint32_t)0xff000000UL) >> 24) ))
 
 static void convert_elf_hdr(Elf32_Ehdr * e)
 {
@@ -274,7 +276,7 @@ int main(int argc, char *argv[])
 	struct aouthdr eah;
 	struct scnhdr esecs[6];
 	int infile, outfile;
-	unsigned long cur_vma = ULONG_MAX;
+	uint32_t cur_vma = UINT32_MAX;
 	int addflag = 0;
 	int nosecs;
 
@@ -518,7 +520,7 @@ int main(int argc, char *argv[])
 
 		for (i = 0; i < nosecs; i++) {
 			printf
-			    ("Section %d: %s phys %lx  size %lx	 file offset %lx\n",
+			    ("Section %d: %s phys %"PRIx32"  size %"PRIx32"\t file offset %"PRIx32"\n",
 			     i, esecs[i].s_name, esecs[i].s_paddr,
 			     esecs[i].s_size, esecs[i].s_scnptr);
 		}
@@ -564,17 +566,16 @@ int main(int argc, char *argv[])
 		   the section can be loaded before copying. */
 		if (ph[i].p_type == PT_LOAD && ph[i].p_filesz) {
 			if (cur_vma != ph[i].p_vaddr) {
-				unsigned long gap =
-				    ph[i].p_vaddr - cur_vma;
+				uint32_t gap = ph[i].p_vaddr - cur_vma;
 				char obuf[1024];
 				if (gap > 65536) {
 					fprintf(stderr,
-						"Intersegment gap (%ld bytes) too large.\n",
+						"Intersegment gap (%"PRId32" bytes) too large.\n",
 						gap);
 					exit(1);
 				}
 				fprintf(stderr,
-					"Warning: %ld byte intersegment gap.\n",
+					"Warning: %d byte intersegment gap.\n",
 					gap);
 				memset(obuf, 0, sizeof obuf);
 				while (gap) {
diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 7b335ab21697..236833be6fbe 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -11,9 +11,7 @@
  * Copyright (C) 2010 Cavium Networks, Inc.
  */
 #include <linux/dma-direct.h>
-#include <linux/scatterlist.h>
 #include <linux/bootmem.h>
-#include <linux/export.h>
 #include <linux/swiotlb.h>
 #include <linux/types.h>
 #include <linux/init.h>
@@ -24,10 +22,16 @@
 #include <asm/octeon/octeon.h>
 
 #ifdef CONFIG_PCI
+#include <linux/pci.h>
 #include <asm/octeon/pci-octeon.h>
 #include <asm/octeon/cvmx-npi-defs.h>
 #include <asm/octeon/cvmx-pci-defs.h>
 
+struct octeon_dma_map_ops {
+	dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr);
+	phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr);
+};
+
 static dma_addr_t octeon_hole_phys_to_dma(phys_addr_t paddr)
 {
 	if (paddr >= CVMX_PCIE_BAR1_PHYS_BASE && paddr < (CVMX_PCIE_BAR1_PHYS_BASE + CVMX_PCIE_BAR1_PHYS_SIZE))
@@ -61,6 +65,11 @@ static phys_addr_t octeon_gen1_dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return daddr;
 }
 
+static const struct octeon_dma_map_ops octeon_gen1_ops = {
+	.phys_to_dma	= octeon_gen1_phys_to_dma,
+	.dma_to_phys	= octeon_gen1_dma_to_phys,
+};
+
 static dma_addr_t octeon_gen2_phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return octeon_hole_phys_to_dma(paddr);
@@ -71,6 +80,11 @@ static phys_addr_t octeon_gen2_dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return octeon_hole_dma_to_phys(daddr);
 }
 
+static const struct octeon_dma_map_ops octeon_gen2_ops = {
+	.phys_to_dma	= octeon_gen2_phys_to_dma,
+	.dma_to_phys	= octeon_gen2_dma_to_phys,
+};
+
 static dma_addr_t octeon_big_phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	if (paddr >= 0x410000000ull && paddr < 0x420000000ull)
@@ -93,6 +107,11 @@ static phys_addr_t octeon_big_dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return daddr;
 }
 
+static const struct octeon_dma_map_ops octeon_big_ops = {
+	.phys_to_dma	= octeon_big_phys_to_dma,
+	.dma_to_phys	= octeon_big_dma_to_phys,
+};
+
 static dma_addr_t octeon_small_phys_to_dma(struct device *dev,
 					   phys_addr_t paddr)
 {
@@ -121,105 +140,51 @@ static phys_addr_t octeon_small_dma_to_phys(struct device *dev,
 	return daddr;
 }
 
-#endif /* CONFIG_PCI */
-
-static dma_addr_t octeon_dma_map_page(struct device *dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
-					    direction, attrs);
-	mb();
-
-	return daddr;
-}
-
-static int octeon_dma_map_sg(struct device *dev, struct scatterlist *sg,
-	int nents, enum dma_data_direction direction, unsigned long attrs)
-{
-	int r = swiotlb_map_sg_attrs(dev, sg, nents, direction, attrs);
-	mb();
-	return r;
-}
-
-static void octeon_dma_sync_single_for_device(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	swiotlb_sync_single_for_device(dev, dma_handle, size, direction);
-	mb();
-}
-
-static void octeon_dma_sync_sg_for_device(struct device *dev,
-	struct scatterlist *sg, int nelems, enum dma_data_direction direction)
-{
-	swiotlb_sync_sg_for_device(dev, sg, nelems, direction);
-	mb();
-}
-
-static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
-
-	mb();
+static const struct octeon_dma_map_ops octeon_small_ops = {
+	.phys_to_dma	= octeon_small_phys_to_dma,
+	.dma_to_phys	= octeon_small_dma_to_phys,
+};
 
-	return ret;
-}
+static const struct octeon_dma_map_ops *octeon_pci_dma_ops;
 
-static dma_addr_t octeon_unity_phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return paddr;
-}
-
-static phys_addr_t octeon_unity_dma_to_phys(struct device *dev, dma_addr_t daddr)
+void __init octeon_pci_dma_init(void)
 {
-	return daddr;
+	switch (octeon_dma_bar_type) {
+	case OCTEON_DMA_BAR_TYPE_PCIE:
+		octeon_pci_dma_ops = &octeon_gen1_ops;
+		break;
+	case OCTEON_DMA_BAR_TYPE_PCIE2:
+		octeon_pci_dma_ops = &octeon_gen2_ops;
+		break;
+	case OCTEON_DMA_BAR_TYPE_BIG:
+		octeon_pci_dma_ops = &octeon_big_ops;
+		break;
+	case OCTEON_DMA_BAR_TYPE_SMALL:
+		octeon_pci_dma_ops = &octeon_small_ops;
+		break;
+	default:
+		BUG();
+	}
 }
-
-struct octeon_dma_map_ops {
-	const struct dma_map_ops dma_map_ops;
-	dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr);
-	phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr);
-};
+#endif /* CONFIG_PCI */
 
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
-						      struct octeon_dma_map_ops,
-						      dma_map_ops);
-
-	return ops->phys_to_dma(dev, paddr);
+#ifdef CONFIG_PCI
+	if (dev && dev_is_pci(dev))
+		return octeon_pci_dma_ops->phys_to_dma(dev, paddr);
+#endif
+	return paddr;
 }
-EXPORT_SYMBOL(__phys_to_dma);
 
 phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-	struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
-						      struct octeon_dma_map_ops,
-						      dma_map_ops);
-
-	return ops->dma_to_phys(dev, daddr);
+#ifdef CONFIG_PCI
+	if (dev && dev_is_pci(dev))
+		return octeon_pci_dma_ops->dma_to_phys(dev, daddr);
+#endif
+	return daddr;
 }
-EXPORT_SYMBOL(__dma_to_phys);
-
-static struct octeon_dma_map_ops octeon_linear_dma_map_ops = {
-	.dma_map_ops = {
-		.alloc = octeon_dma_alloc_coherent,
-		.free = swiotlb_free,
-		.map_page = octeon_dma_map_page,
-		.unmap_page = swiotlb_unmap_page,
-		.map_sg = octeon_dma_map_sg,
-		.unmap_sg = swiotlb_unmap_sg_attrs,
-		.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-		.sync_single_for_device = octeon_dma_sync_single_for_device,
-		.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-		.sync_sg_for_device = octeon_dma_sync_sg_for_device,
-		.mapping_error = swiotlb_dma_mapping_error,
-		.dma_supported = swiotlb_dma_supported
-	},
-	.phys_to_dma = octeon_unity_phys_to_dma,
-	.dma_to_phys = octeon_unity_dma_to_phys
-};
 
 char *octeon_swiotlb;
 
@@ -283,52 +248,4 @@ void __init plat_swiotlb_setup(void)
 
 	if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM)
 		panic("Cannot allocate SWIOTLB buffer");
-
-	mips_dma_map_ops = &octeon_linear_dma_map_ops.dma_map_ops;
 }
-
-#ifdef CONFIG_PCI
-static struct octeon_dma_map_ops _octeon_pci_dma_map_ops = {
-	.dma_map_ops = {
-		.alloc = octeon_dma_alloc_coherent,
-		.free = swiotlb_free,
-		.map_page = octeon_dma_map_page,
-		.unmap_page = swiotlb_unmap_page,
-		.map_sg = octeon_dma_map_sg,
-		.unmap_sg = swiotlb_unmap_sg_attrs,
-		.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-		.sync_single_for_device = octeon_dma_sync_single_for_device,
-		.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-		.sync_sg_for_device = octeon_dma_sync_sg_for_device,
-		.mapping_error = swiotlb_dma_mapping_error,
-		.dma_supported = swiotlb_dma_supported
-	},
-};
-
-const struct dma_map_ops *octeon_pci_dma_map_ops;
-
-void __init octeon_pci_dma_init(void)
-{
-	switch (octeon_dma_bar_type) {
-	case OCTEON_DMA_BAR_TYPE_PCIE2:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_gen2_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_gen2_dma_to_phys;
-		break;
-	case OCTEON_DMA_BAR_TYPE_PCIE:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_gen1_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_gen1_dma_to_phys;
-		break;
-	case OCTEON_DMA_BAR_TYPE_BIG:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_big_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_big_dma_to_phys;
-		break;
-	case OCTEON_DMA_BAR_TYPE_SMALL:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_small_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_small_dma_to_phys;
-		break;
-	default:
-		BUG();
-	}
-	octeon_pci_dma_map_ops = &_octeon_pci_dma_map_ops.dma_map_ops;
-}
-#endif /* CONFIG_PCI */
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
index d18ed5af62f4..b8898e2b8a6f 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -42,9 +42,6 @@
 #include <asm/octeon/cvmx-asxx-defs.h>
 #include <asm/octeon/cvmx-dbg-defs.h>
 
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_asxx_enable(int block);
-
 /**
  * Probe RGMII ports and determine the number present
  *
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
index 578283350776..a176358c5a21 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -39,10 +39,7 @@
 
 #include <asm/octeon/cvmx-gmxx-defs.h>
 #include <asm/octeon/cvmx-pcsx-defs.h>
-
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
-void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
+#include <asm/octeon/cvmx-pcsxx-defs.h>
 
 /**
  * Perform initialization required only once for an SGMII port.
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c
index ef16aa00167b..2a574d272671 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -25,10 +25,6 @@
  * Contact Cavium Networks for more information
  ***********************license end**************************************/
 
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_spxx_int_msk_enable(int index);
-void __cvmx_interrupt_stxx_int_msk_enable(int index);
-
 /*
  * Functions for SPI initialization, configuration,
  * and monitoring.
@@ -41,6 +37,8 @@ void __cvmx_interrupt_stxx_int_msk_enable(int index);
 
 #include <asm/octeon/cvmx-pip-defs.h>
 #include <asm/octeon/cvmx-pko-defs.h>
+#include <asm/octeon/cvmx-spxx-defs.h>
+#include <asm/octeon/cvmx-stxx-defs.h>
 
 /*
  * CVMX_HELPER_SPI_TIMEOUT is used to determine how long the SPI
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
index 19d54e02c185..2bb6912a580d 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -39,12 +39,9 @@
 
 #include <asm/octeon/cvmx-pko-defs.h>
 #include <asm/octeon/cvmx-gmxx-defs.h>
+#include <asm/octeon/cvmx-pcsx-defs.h>
 #include <asm/octeon/cvmx-pcsxx-defs.h>
 
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
-void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
-
 int __cvmx_helper_xaui_enumerate(int interface)
 {
 	union cvmx_gmxx_hg2_control gmx_hg2_control;
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index b3aec101a65d..8272d8c648ca 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -814,7 +814,7 @@ static int octeon_irq_ciu_set_affinity(struct irq_data *data,
 			pen = &per_cpu(octeon_irq_ciu1_en_mirror, cpu);
 
 		if (cpumask_test_cpu(cpu, dest) && enable_one) {
-			enable_one = 0;
+			enable_one = false;
 			__set_bit(cd->bit, pen);
 		} else {
 			__clear_bit(cd->bit, pen);
diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index 8505db478904..807cadaf554e 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -322,6 +322,7 @@ static int __init octeon_ehci_device_init(void)
 		return 0;
 
 	pd = of_find_device_by_node(ehci_node);
+	of_node_put(ehci_node);
 	if (!pd)
 		return 0;
 
@@ -384,6 +385,7 @@ static int __init octeon_ohci_device_init(void)
 		return 0;
 
 	pd = of_find_device_by_node(ohci_node);
+	of_node_put(ohci_node);
 	if (!pd)
 		return 0;
 
@@ -1067,6 +1069,6 @@ end_led:
 
 static int __init octeon_publish_devices(void)
 {
-	return of_platform_bus_probe(NULL, octeon_ids, NULL);
+	return of_platform_populate(NULL, octeon_ids, NULL, NULL);
 }
 arch_initcall(octeon_publish_devices);
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index a8034d0dcade..c2426232db06 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -36,6 +36,7 @@
 #include <asm/mipsregs.h>
 #include <asm/bootinfo.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 #include <asm/time.h>
 
 #include <asm/octeon/octeon.h>
@@ -1108,7 +1109,7 @@ void __init plat_mem_setup(void)
  * Emit one character to the boot UART.	 Exported for use by the
  * watchdog timer.
  */
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	uint64_t lsrval;
 
@@ -1119,7 +1120,6 @@ int prom_putchar(char c)
 
 	/* Write the byte */
 	cvmx_write_csr(CVMX_MIO_UARTX_THR(octeon_uart), c & 0xffull);
-	return 1;
 }
 EXPORT_SYMBOL(prom_putchar);
 
@@ -1154,11 +1154,7 @@ void __init prom_free_prom_memory(void)
 }
 
 void __init octeon_fill_mac_addresses(void);
-int octeon_prune_device_tree(void);
 
-extern const char __appended_dtb;
-extern const char __dtb_octeon_3xxx_begin;
-extern const char __dtb_octeon_68xx_begin;
 void __init device_tree_init(void)
 {
 	const void *fdt;
diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig
index be23fd25eeaa..030ff9c205fb 100644
--- a/arch/mips/configs/ci20_defconfig
+++ b/arch/mips/configs/ci20_defconfig
@@ -92,6 +92,8 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_I2C=y
 CONFIG_I2C_JZ4780=y
+CONFIG_SPI=y
+CONFIG_SPI_GPIO=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_INGENIC=y
 # CONFIG_HWMON is not set
diff --git a/arch/mips/configs/generic_defconfig b/arch/mips/configs/generic_defconfig
index 26b1cd5ffbf5..684c9dcba126 100644
--- a/arch/mips/configs/generic_defconfig
+++ b/arch/mips/configs/generic_defconfig
@@ -43,9 +43,6 @@ CONFIG_NETFILTER=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_SCSI=y
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_HW_RANDOM=y
 # CONFIG_HWMON is not set
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index df8a9a15ca83..81058295d35f 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -317,6 +317,7 @@ CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 14df9ef15d40..5c10cddc39d3 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -328,6 +328,7 @@ CONFIG_INPUT_MOUSEDEV=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig
index 25092e344574..bb694f5065f1 100644
--- a/arch/mips/configs/malta_kvm_guest_defconfig
+++ b/arch/mips/configs/malta_kvm_guest_defconfig
@@ -330,6 +330,7 @@ CONFIG_INPUT_MOUSEDEV=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
index 210bf609f785..5b5306b80576 100644
--- a/arch/mips/configs/malta_qemu_32r6_defconfig
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -133,6 +133,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig
index e5934aa98397..85543599448f 100644
--- a/arch/mips/configs/maltaaprp_defconfig
+++ b/arch/mips/configs/maltaaprp_defconfig
@@ -133,6 +133,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig
index cb2ca11c1789..067bb84ac916 100644
--- a/arch/mips/configs/maltasmvp_defconfig
+++ b/arch/mips/configs/maltasmvp_defconfig
@@ -134,6 +134,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index be29fcec69fc..dfc78c3172a3 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -137,6 +137,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig
index 40462d4c90a0..50a2288c69f8 100644
--- a/arch/mips/configs/maltaup_defconfig
+++ b/arch/mips/configs/maltaup_defconfig
@@ -132,6 +132,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 4e50176cb3df..99a19cf5f9ba 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -326,6 +326,7 @@ CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/fw/arc/arc_con.c b/arch/mips/fw/arc/arc_con.c
index 769d4b9ac82e..365e3913231e 100644
--- a/arch/mips/fw/arc/arc_con.c
+++ b/arch/mips/fw/arc/arc_con.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/fs.h>
+#include <asm/setup.h>
 #include <asm/sgialib.h>
 
 static void prom_console_write(struct console *co, const char *s,
diff --git a/arch/mips/fw/arc/promlib.c b/arch/mips/fw/arc/promlib.c
index 7e8ba5ce95be..be381307fbb0 100644
--- a/arch/mips/fw/arc/promlib.c
+++ b/arch/mips/fw/arc/promlib.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <asm/sgialib.h>
 #include <asm/bcache.h>
+#include <asm/setup.h>
 
 /*
  * IP22 boardcache is not compatible with board caches.	 Thus we disable it
diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c
index 6aa264b9856a..8772617b64ce 100644
--- a/arch/mips/fw/sni/sniprom.c
+++ b/arch/mips/fw/sni/sniprom.c
@@ -19,6 +19,7 @@
 #include <asm/mipsprom.h>
 #include <asm/mipsregs.h>
 #include <asm/bootinfo.h>
+#include <asm/setup.h>
 
 /* special SNI prom calls */
 /*
diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig
index ba9b2c8cce68..08e33c6b2539 100644
--- a/arch/mips/generic/Kconfig
+++ b/arch/mips/generic/Kconfig
@@ -35,13 +35,13 @@ config LEGACY_BOARD_OCELOT
 	depends on LEGACY_BOARD_SEAD3=n
 	select LEGACY_BOARDS
 	select MSCC_OCELOT
+	select SYS_HAS_EARLY_PRINTK
+	select USE_GENERIC_EARLY_PRINTK_8250
 
 config MSCC_OCELOT
 	bool
 	select GPIOLIB
 	select MSCC_OCELOT_IRQ
-	select SYS_HAS_EARLY_PRINTK
-	select USE_GENERIC_EARLY_PRINTK_8250
 
 comment "FIT/UHI Boards"
 
@@ -65,6 +65,14 @@ config FIT_IMAGE_FDT_XILFPGA
 	  Enable this to include the FDT for the MIPSfpga platform
 	  from Imagination Technologies in the FIT kernel image.
 
+config FIT_IMAGE_FDT_OCELOT_PCB123
+	bool "Include FDT for Microsemi Ocelot PCB123"
+	select MSCC_OCELOT
+	help
+	  Enable this to include the FDT for the Ocelot PCB123 platform
+	  from Microsemi in the FIT kernel image.
+	  This requires u-boot on the platform.
+
 config VIRT_BOARD_RANCHU
 	bool "Support Ranchu platform for Android emulator"
 	help
diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform
index 0dd0d5d460a5..879cb80396c8 100644
--- a/arch/mips/generic/Platform
+++ b/arch/mips/generic/Platform
@@ -16,4 +16,5 @@ all-$(CONFIG_MIPS_GENERIC)	:= vmlinux.gz.itb
 its-y					:= vmlinux.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_BOSTON)	+= board-boston.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_NI169445)	+= board-ni169445.its.S
+its-$(CONFIG_FIT_IMAGE_FDT_OCELOT_PCB123) += board-ocelot_pcb123.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_XILFPGA)	+= board-xilfpga.its.S
diff --git a/arch/mips/generic/board-ocelot_pcb123.its.S b/arch/mips/generic/board-ocelot_pcb123.its.S
new file mode 100644
index 000000000000..5a7d5e1c878a
--- /dev/null
+++ b/arch/mips/generic/board-ocelot_pcb123.its.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/ {
+	images {
+		fdt@ocelot_pcb123 {
+			description = "MSCC Ocelot PCB123 Device Tree";
+			data = /incbin/("boot/dts/mscc/ocelot_pcb123.dtb");
+			type = "flat_dt";
+			arch = "mips";
+			compression = "none";
+			hash@0 {
+				algo = "sha1";
+			};
+		};
+	};
+
+	configurations {
+		conf@ocelot_pcb123 {
+			description = "Ocelot Linux kernel";
+			kernel = "kernel@0";
+			fdt = "fdt@ocelot_pcb123";
+		};
+	};
+};
diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c
index 5ba6fcc26fa7..a106f8113842 100644
--- a/arch/mips/generic/init.c
+++ b/arch/mips/generic/init.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/irqchip.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 
 #include <asm/bootinfo.h>
 #include <asm/fw/fw.h>
@@ -204,22 +203,11 @@ void __init arch_init_irq(void)
 					    "mti,cpu-interrupt-controller");
 	if (!cpu_has_veic && !intc_node)
 		mips_cpu_irq_init();
+	of_node_put(intc_node);
 
 	irqchip_init();
 }
 
-static int __init publish_devices(void)
-{
-	if (!of_have_populated_dt())
-		panic("Device-tree not present");
-
-	if (of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL))
-		panic("Failed to populate DT");
-
-	return 0;
-}
-arch_initcall(publish_devices);
-
 void __init prom_free_prom_memory(void)
 {
 }
diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c
index b408dac722ac..7ba4ad5cc1d6 100644
--- a/arch/mips/generic/yamon-dt.c
+++ b/arch/mips/generic/yamon-dt.c
@@ -28,8 +28,6 @@ __init int yamon_dt_append_cmdline(void *fdt)
 	/* find or add chosen node */
 	chosen_off = fdt_path_offset(fdt, "/chosen");
 	if (chosen_off == -FDT_ERR_NOTFOUND)
-		chosen_off = fdt_path_offset(fdt, "/chosen@0");
-	if (chosen_off == -FDT_ERR_NOTFOUND)
 		chosen_off = fdt_add_subnode(fdt, 0, "chosen");
 	if (chosen_off < 0) {
 		pr_err("Unable to find or add DT chosen node: %d\n",
@@ -221,8 +219,6 @@ __init int yamon_dt_serial_config(void *fdt)
 	/* find or add chosen node */
 	chosen_off = fdt_path_offset(fdt, "/chosen");
 	if (chosen_off == -FDT_ERR_NOTFOUND)
-		chosen_off = fdt_path_offset(fdt, "/chosen@0");
-	if (chosen_off == -FDT_ERR_NOTFOUND)
 		chosen_off = fdt_add_subnode(fdt, 0, "chosen");
 	if (chosen_off < 0) {
 		pr_err("Unable to find or add DT chosen node: %d\n",
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 45d541baf359..58351e48421e 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -8,6 +8,7 @@ generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += msi.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 0ab176bdb8e8..0269b3de8b51 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -22,6 +22,17 @@
 #include <asm/cmpxchg.h>
 #include <asm/war.h>
 
+/*
+ * Using a branch-likely instruction to check the result of an sc instruction
+ * works around a bug present in R10000 CPUs prior to revision 3.0 that could
+ * cause ll-sc sequences to execute non-atomically.
+ */
+#if R10000_LLSC_WAR
+# define __scbeqz "beqzl"
+#else
+# define __scbeqz "beqz"
+#endif
+
 #define ATOMIC_INIT(i)	  { (i) }
 
 /*
@@ -44,31 +55,18 @@
 #define ATOMIC_OP(op, c_op, asm_op)					      \
 static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 {									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	ll	%0, %1		# atomic_" #op "	\n"   \
 		"	" #asm_op " %0, %2				\n"   \
 		"	sc	%0, %1					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		int temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	ll	%0, %1		# atomic_" #op "\n"   \
-			"	" #asm_op " %0, %2			\n"   \
-			"	sc	%0, %1				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)  \
-			: "Ir" (i));					      \
-		} while (unlikely(!temp));				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -83,36 +81,20 @@ static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v)	      \
 {									      \
 	int result;							      \
 									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	ll	%1, %2		# atomic_" #op "_return	\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	sc	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		int temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	ll	%1, %2	# atomic_" #op "_return	\n"   \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	sc	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i));					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp; result c_op i;				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -131,36 +113,20 @@ static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v)	      \
 {									      \
 	int result;							      \
 									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	ll	%1, %2		# atomic_fetch_" #op "	\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	sc	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	move	%0, %1					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		int temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	ll	%1, %2	# atomic_fetch_" #op "	\n"   \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	sc	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i));					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp;						      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -218,38 +184,17 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 
 	smp_mb__before_llsc();
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		int temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
-		"	subu	%0, %1, %3				\n"
-		"	bltz	%0, 1f					\n"
-		"	sc	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqzl	%0, 1b					\n"
-		"	 subu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
-		"1:							\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
-		: "memory");
-	} else if (kernel_uses_llsc) {
+	if (kernel_uses_llsc) {
 		int temp;
 
 		__asm__ __volatile__(
 		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
 		"	subu	%0, %1, %3				\n"
+		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
-		"	sc	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqz	%0, 1b					\n"
-		"	 subu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
+		"	sc	%1, %2					\n"
+		"\t" __scbeqz "	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
@@ -274,97 +219,12 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-
-/*
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-/*
- * atomic_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-
 /*
  * atomic_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
  */
 #define atomic_dec_if_positive(v)	atomic_sub_if_positive(1, v)
 
-/*
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1, (v))
-
-/*
- * atomic_dec - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1, (v))
-
-/*
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
 #ifdef CONFIG_64BIT
 
 #define ATOMIC64_INIT(i)    { (i) }
@@ -386,31 +246,18 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 #define ATOMIC64_OP(op, c_op, asm_op)					      \
 static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 {									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	lld	%0, %1		# atomic64_" #op "	\n"   \
 		"	" #asm_op " %0, %2				\n"   \
 		"	scd	%0, %1					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		long temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	lld	%0, %1		# atomic64_" #op "\n" \
-			"	" #asm_op " %0, %2			\n"   \
-			"	scd	%0, %1				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
-			: "Ir" (i));					      \
-		} while (unlikely(!temp));				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -425,37 +272,20 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
 {									      \
 	long result;							      \
 									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	lld	%1, %2		# atomic64_" #op "_return\n"  \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	scd	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		long temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	lld	%1, %2	# atomic64_" #op "_return\n"  \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	scd	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
-			: "memory");					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp; result c_op i;				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -478,33 +308,16 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)  \
 		long temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	lld	%1, %2		# atomic64_fetch_" #op "\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	scd	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	move	%0, %1					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		long temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	lld	%1, %2	# atomic64_fetch_" #op "\n"   \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	scd	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
-			: "memory");					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp;						      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -563,38 +376,17 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 
 	smp_mb__before_llsc();
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		long temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	bltz	%0, 1f					\n"
-		"	scd	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqzl	%0, 1b					\n"
-		"	 dsubu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
-		"1:							\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp),
-		  "=" GCC_OFF_SMALL_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
-		: "memory");
-	} else if (kernel_uses_llsc) {
+	if (kernel_uses_llsc) {
 		long temp;
 
 		__asm__ __volatile__(
 		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
 		"	dsubu	%0, %1, %3				\n"
+		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
-		"	scd	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqz	%0, 1b					\n"
-		"	 dsubu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
+		"	scd	%1, %2					\n"
+		"\t" __scbeqz "	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
@@ -620,99 +412,12 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1, (v))
-
-/*
- * atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0)
-
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-/*
- * atomic64_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic64_t
  */
 #define atomic64_dec_if_positive(v)	atomic64_sub_if_positive(1, v)
 
-/*
- * atomic64_inc - increment atomic variable
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic64_inc(v) atomic64_add(1, (v))
-
-/*
- * atomic64_dec - decrement and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic64_dec(v) atomic64_sub(1, (v))
-
-/*
- * atomic64_add_negative - add and test if negative
- * @v: pointer of type atomic64_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0)
-
 #endif /* CONFIG_64BIT */
 
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h
index b3e2975f83d3..bf6a8afd7ad2 100644
--- a/arch/mips/include/asm/bmips.h
+++ b/arch/mips/include/asm/bmips.h
@@ -123,22 +123,6 @@ static inline void bmips_write_zscm_reg(unsigned int offset, unsigned long data)
 	barrier();
 }
 
-static inline void bmips_post_dma_flush(struct device *dev)
-{
-	void __iomem *cbr = BMIPS_GET_CBR();
-	u32 cfg;
-
-	if (boot_cpu_type() != CPU_BMIPS3300 &&
-	    boot_cpu_type() != CPU_BMIPS4350 &&
-	    boot_cpu_type() != CPU_BMIPS4380)
-		return;
-
-	/* Flush stale data out of the readahead cache */
-	cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
-	__raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG);
-	__raw_readl(cbr + BMIPS_RAC_CONFIG);
-}
-
 #endif /* !defined(__ASSEMBLY__) */
 
 #endif /* _ASM_BMIPS_H */
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 9cdb4e4ce258..0edba3e75747 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -14,39 +14,77 @@
 #include <asm/isa-rev.h>
 #include <cpu-feature-overrides.h>
 
+#define __ase(ase)			(cpu_data[0].ases & (ase))
+#define __opt(opt)			(cpu_data[0].options & (opt))
+
+/*
+ * Check if MIPS_ISA_REV is >= isa *and* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * Note that these should only be used in cases where a kernel built for an
+ * older ISA *cannot* run on a CPU which supports the feature in question. For
+ * example this may be used for features introduced with MIPSr6, since a kernel
+ * built for an older ISA cannot run on a MIPSr6 CPU. This should not be used
+ * for MIPSr2 features however, since a MIPSr1 or earlier kernel might run on a
+ * MIPSr2 CPU.
+ */
+#define __isa_ge_and_ase(isa, ase)	((MIPS_ISA_REV >= (isa)) && __ase(ase))
+#define __isa_ge_and_opt(isa, opt)	((MIPS_ISA_REV >= (isa)) && __opt(opt))
+
+/*
+ * Check if MIPS_ISA_REV is >= isa *or* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * These are for use with features that are optional up until a particular ISA
+ * revision & then become required.
+ */
+#define __isa_ge_or_ase(isa, ase)	((MIPS_ISA_REV >= (isa)) || __ase(ase))
+#define __isa_ge_or_opt(isa, opt)	((MIPS_ISA_REV >= (isa)) || __opt(opt))
+
+/*
+ * Check if MIPS_ISA_REV is < isa *and* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * These are for use with features that are optional up until a particular ISA
+ * revision & are then removed - ie. no longer present in any CPU implementing
+ * the given ISA revision.
+ */
+#define __isa_lt_and_ase(isa, ase)	((MIPS_ISA_REV < (isa)) && __ase(ase))
+#define __isa_lt_and_opt(isa, opt)	((MIPS_ISA_REV < (isa)) && __opt(opt))
+
 /*
  * SMP assumption: Options of CPU 0 are a superset of all processors.
  * This is true for all known MIPS systems.
  */
 #ifndef cpu_has_tlb
-#define cpu_has_tlb		(cpu_data[0].options & MIPS_CPU_TLB)
+#define cpu_has_tlb		__opt(MIPS_CPU_TLB)
 #endif
 #ifndef cpu_has_ftlb
-#define cpu_has_ftlb		(cpu_data[0].options & MIPS_CPU_FTLB)
+#define cpu_has_ftlb		__opt(MIPS_CPU_FTLB)
 #endif
 #ifndef cpu_has_tlbinv
-#define cpu_has_tlbinv		(cpu_data[0].options & MIPS_CPU_TLBINV)
+#define cpu_has_tlbinv		__opt(MIPS_CPU_TLBINV)
 #endif
 #ifndef cpu_has_segments
-#define cpu_has_segments	(cpu_data[0].options & MIPS_CPU_SEGMENTS)
+#define cpu_has_segments	__opt(MIPS_CPU_SEGMENTS)
 #endif
 #ifndef cpu_has_eva
-#define cpu_has_eva		(cpu_data[0].options & MIPS_CPU_EVA)
+#define cpu_has_eva		__opt(MIPS_CPU_EVA)
 #endif
 #ifndef cpu_has_htw
-#define cpu_has_htw		(cpu_data[0].options & MIPS_CPU_HTW)
+#define cpu_has_htw		__opt(MIPS_CPU_HTW)
 #endif
 #ifndef cpu_has_ldpte
-#define cpu_has_ldpte		(cpu_data[0].options & MIPS_CPU_LDPTE)
+#define cpu_has_ldpte		__opt(MIPS_CPU_LDPTE)
 #endif
 #ifndef cpu_has_rixiex
-#define cpu_has_rixiex		(cpu_data[0].options & MIPS_CPU_RIXIEX)
+#define cpu_has_rixiex		__isa_ge_or_opt(6, MIPS_CPU_RIXIEX)
 #endif
 #ifndef cpu_has_maar
-#define cpu_has_maar		(cpu_data[0].options & MIPS_CPU_MAAR)
+#define cpu_has_maar		__opt(MIPS_CPU_MAAR)
 #endif
 #ifndef cpu_has_rw_llb
-#define cpu_has_rw_llb		(cpu_data[0].options & MIPS_CPU_RW_LLB)
+#define cpu_has_rw_llb		__isa_ge_or_opt(6, MIPS_CPU_RW_LLB)
 #endif
 
 /*
@@ -59,18 +97,18 @@
 #define cpu_has_3kex		(!cpu_has_4kex)
 #endif
 #ifndef cpu_has_4kex
-#define cpu_has_4kex		(cpu_data[0].options & MIPS_CPU_4KEX)
+#define cpu_has_4kex		__isa_ge_or_opt(1, MIPS_CPU_4KEX)
 #endif
 #ifndef cpu_has_3k_cache
-#define cpu_has_3k_cache	(cpu_data[0].options & MIPS_CPU_3K_CACHE)
+#define cpu_has_3k_cache	__isa_lt_and_opt(1, MIPS_CPU_3K_CACHE)
 #endif
 #define cpu_has_6k_cache	0
 #define cpu_has_8k_cache	0
 #ifndef cpu_has_4k_cache
-#define cpu_has_4k_cache	(cpu_data[0].options & MIPS_CPU_4K_CACHE)
+#define cpu_has_4k_cache	__isa_ge_or_opt(1, MIPS_CPU_4K_CACHE)
 #endif
 #ifndef cpu_has_tx39_cache
-#define cpu_has_tx39_cache	(cpu_data[0].options & MIPS_CPU_TX39_CACHE)
+#define cpu_has_tx39_cache	__opt(MIPS_CPU_TX39_CACHE)
 #endif
 #ifndef cpu_has_octeon_cache
 #define cpu_has_octeon_cache	0
@@ -83,92 +121,92 @@
 #define raw_cpu_has_fpu		cpu_has_fpu
 #endif
 #ifndef cpu_has_32fpr
-#define cpu_has_32fpr		(cpu_data[0].options & MIPS_CPU_32FPR)
+#define cpu_has_32fpr		__isa_ge_or_opt(1, MIPS_CPU_32FPR)
 #endif
 #ifndef cpu_has_counter
-#define cpu_has_counter		(cpu_data[0].options & MIPS_CPU_COUNTER)
+#define cpu_has_counter		__opt(MIPS_CPU_COUNTER)
 #endif
 #ifndef cpu_has_watch
-#define cpu_has_watch		(cpu_data[0].options & MIPS_CPU_WATCH)
+#define cpu_has_watch		__opt(MIPS_CPU_WATCH)
 #endif
 #ifndef cpu_has_divec
-#define cpu_has_divec		(cpu_data[0].options & MIPS_CPU_DIVEC)
+#define cpu_has_divec		__isa_ge_or_opt(1, MIPS_CPU_DIVEC)
 #endif
 #ifndef cpu_has_vce
-#define cpu_has_vce		(cpu_data[0].options & MIPS_CPU_VCE)
+#define cpu_has_vce		__opt(MIPS_CPU_VCE)
 #endif
 #ifndef cpu_has_cache_cdex_p
-#define cpu_has_cache_cdex_p	(cpu_data[0].options & MIPS_CPU_CACHE_CDEX_P)
+#define cpu_has_cache_cdex_p	__opt(MIPS_CPU_CACHE_CDEX_P)
 #endif
 #ifndef cpu_has_cache_cdex_s
-#define cpu_has_cache_cdex_s	(cpu_data[0].options & MIPS_CPU_CACHE_CDEX_S)
+#define cpu_has_cache_cdex_s	__opt(MIPS_CPU_CACHE_CDEX_S)
 #endif
 #ifndef cpu_has_prefetch
-#define cpu_has_prefetch	(cpu_data[0].options & MIPS_CPU_PREFETCH)
+#define cpu_has_prefetch	__isa_ge_or_opt(1, MIPS_CPU_PREFETCH)
 #endif
 #ifndef cpu_has_mcheck
-#define cpu_has_mcheck		(cpu_data[0].options & MIPS_CPU_MCHECK)
+#define cpu_has_mcheck		__isa_ge_or_opt(1, MIPS_CPU_MCHECK)
 #endif
 #ifndef cpu_has_ejtag
-#define cpu_has_ejtag		(cpu_data[0].options & MIPS_CPU_EJTAG)
+#define cpu_has_ejtag		__opt(MIPS_CPU_EJTAG)
 #endif
 #ifndef cpu_has_llsc
-#define cpu_has_llsc		(cpu_data[0].options & MIPS_CPU_LLSC)
+#define cpu_has_llsc		__isa_ge_or_opt(1, MIPS_CPU_LLSC)
 #endif
 #ifndef cpu_has_bp_ghist
-#define cpu_has_bp_ghist	(cpu_data[0].options & MIPS_CPU_BP_GHIST)
+#define cpu_has_bp_ghist	__opt(MIPS_CPU_BP_GHIST)
 #endif
 #ifndef kernel_uses_llsc
 #define kernel_uses_llsc	cpu_has_llsc
 #endif
 #ifndef cpu_has_guestctl0ext
-#define cpu_has_guestctl0ext	(cpu_data[0].options & MIPS_CPU_GUESTCTL0EXT)
+#define cpu_has_guestctl0ext	__opt(MIPS_CPU_GUESTCTL0EXT)
 #endif
 #ifndef cpu_has_guestctl1
-#define cpu_has_guestctl1	(cpu_data[0].options & MIPS_CPU_GUESTCTL1)
+#define cpu_has_guestctl1	__opt(MIPS_CPU_GUESTCTL1)
 #endif
 #ifndef cpu_has_guestctl2
-#define cpu_has_guestctl2	(cpu_data[0].options & MIPS_CPU_GUESTCTL2)
+#define cpu_has_guestctl2	__opt(MIPS_CPU_GUESTCTL2)
 #endif
 #ifndef cpu_has_guestid
-#define cpu_has_guestid		(cpu_data[0].options & MIPS_CPU_GUESTID)
+#define cpu_has_guestid		__opt(MIPS_CPU_GUESTID)
 #endif
 #ifndef cpu_has_drg
-#define cpu_has_drg		(cpu_data[0].options & MIPS_CPU_DRG)
+#define cpu_has_drg		__opt(MIPS_CPU_DRG)
 #endif
 #ifndef cpu_has_mips16
-#define cpu_has_mips16		(cpu_data[0].ases & MIPS_ASE_MIPS16)
+#define cpu_has_mips16		__isa_lt_and_ase(6, MIPS_ASE_MIPS16)
 #endif
 #ifndef cpu_has_mips16e2
-#define cpu_has_mips16e2	(cpu_data[0].ases & MIPS_ASE_MIPS16E2)
+#define cpu_has_mips16e2	__isa_lt_and_ase(6, MIPS_ASE_MIPS16E2)
 #endif
 #ifndef cpu_has_mdmx
-#define cpu_has_mdmx		(cpu_data[0].ases & MIPS_ASE_MDMX)
+#define cpu_has_mdmx		__isa_lt_and_ase(6, MIPS_ASE_MDMX)
 #endif
 #ifndef cpu_has_mips3d
-#define cpu_has_mips3d		(cpu_data[0].ases & MIPS_ASE_MIPS3D)
+#define cpu_has_mips3d		__isa_lt_and_ase(6, MIPS_ASE_MIPS3D)
 #endif
 #ifndef cpu_has_smartmips
-#define cpu_has_smartmips	(cpu_data[0].ases & MIPS_ASE_SMARTMIPS)
+#define cpu_has_smartmips	__isa_lt_and_ase(6, MIPS_ASE_SMARTMIPS)
 #endif
 
 #ifndef cpu_has_rixi
-#define cpu_has_rixi		(cpu_data[0].options & MIPS_CPU_RIXI)
+#define cpu_has_rixi		__isa_ge_or_opt(6, MIPS_CPU_RIXI)
 #endif
 
 #ifndef cpu_has_mmips
 # ifdef CONFIG_SYS_SUPPORTS_MICROMIPS
-#  define cpu_has_mmips		(cpu_data[0].options & MIPS_CPU_MICROMIPS)
+#  define cpu_has_mmips		__opt(MIPS_CPU_MICROMIPS)
 # else
 #  define cpu_has_mmips		0
 # endif
 #endif
 
 #ifndef cpu_has_lpa
-#define cpu_has_lpa		(cpu_data[0].options & MIPS_CPU_LPA)
+#define cpu_has_lpa		__opt(MIPS_CPU_LPA)
 #endif
 #ifndef cpu_has_mvh
-#define cpu_has_mvh		(cpu_data[0].options & MIPS_CPU_MVH)
+#define cpu_has_mvh		__opt(MIPS_CPU_MVH)
 #endif
 #ifndef cpu_has_xpa
 #define cpu_has_xpa		(cpu_has_lpa && cpu_has_mvh)
@@ -338,32 +376,32 @@
 #endif
 
 #ifndef cpu_has_dsp
-#define cpu_has_dsp		(cpu_data[0].ases & MIPS_ASE_DSP)
+#define cpu_has_dsp		__ase(MIPS_ASE_DSP)
 #endif
 
 #ifndef cpu_has_dsp2
-#define cpu_has_dsp2		(cpu_data[0].ases & MIPS_ASE_DSP2P)
+#define cpu_has_dsp2		__ase(MIPS_ASE_DSP2P)
 #endif
 
 #ifndef cpu_has_dsp3
-#define cpu_has_dsp3		(cpu_data[0].ases & MIPS_ASE_DSP3)
+#define cpu_has_dsp3		__ase(MIPS_ASE_DSP3)
 #endif
 
 #ifndef cpu_has_mipsmt
-#define cpu_has_mipsmt		(cpu_data[0].ases & MIPS_ASE_MIPSMT)
+#define cpu_has_mipsmt		__isa_lt_and_ase(6, MIPS_ASE_MIPSMT)
 #endif
 
 #ifndef cpu_has_vp
-#define cpu_has_vp		(cpu_data[0].options & MIPS_CPU_VP)
+#define cpu_has_vp		__isa_ge_and_opt(6, MIPS_CPU_VP)
 #endif
 
 #ifndef cpu_has_userlocal
-#define cpu_has_userlocal	(cpu_data[0].options & MIPS_CPU_ULRI)
+#define cpu_has_userlocal	__isa_ge_or_opt(6, MIPS_CPU_ULRI)
 #endif
 
 #ifdef CONFIG_32BIT
 # ifndef cpu_has_nofpuex
-# define cpu_has_nofpuex	(cpu_data[0].options & MIPS_CPU_NOFPUEX)
+# define cpu_has_nofpuex	__isa_lt_and_opt(1, MIPS_CPU_NOFPUEX)
 # endif
 # ifndef cpu_has_64bits
 # define cpu_has_64bits		(cpu_data[0].isa_level & MIPS_CPU_ISA_64BIT)
@@ -405,19 +443,19 @@
 #endif
 
 #if defined(CONFIG_CPU_MIPSR2_IRQ_VI) && !defined(cpu_has_vint)
-# define cpu_has_vint		(cpu_data[0].options & MIPS_CPU_VINT)
+# define cpu_has_vint		__opt(MIPS_CPU_VINT)
 #elif !defined(cpu_has_vint)
 # define cpu_has_vint			0
 #endif
 
 #if defined(CONFIG_CPU_MIPSR2_IRQ_EI) && !defined(cpu_has_veic)
-# define cpu_has_veic		(cpu_data[0].options & MIPS_CPU_VEIC)
+# define cpu_has_veic		__opt(MIPS_CPU_VEIC)
 #elif !defined(cpu_has_veic)
 # define cpu_has_veic			0
 #endif
 
 #ifndef cpu_has_inclusive_pcaches
-#define cpu_has_inclusive_pcaches	(cpu_data[0].options & MIPS_CPU_INCLUSIVE_CACHES)
+#define cpu_has_inclusive_pcaches	__opt(MIPS_CPU_INCLUSIVE_CACHES)
 #endif
 
 #ifndef cpu_dcache_line_size
@@ -438,63 +476,63 @@
 #endif
 
 #ifndef cpu_has_perf_cntr_intr_bit
-#define cpu_has_perf_cntr_intr_bit	(cpu_data[0].options & MIPS_CPU_PCI)
+#define cpu_has_perf_cntr_intr_bit	__opt(MIPS_CPU_PCI)
 #endif
 
 #ifndef cpu_has_vz
-#define cpu_has_vz		(cpu_data[0].ases & MIPS_ASE_VZ)
+#define cpu_has_vz		__ase(MIPS_ASE_VZ)
 #endif
 
 #if defined(CONFIG_CPU_HAS_MSA) && !defined(cpu_has_msa)
-# define cpu_has_msa		(cpu_data[0].ases & MIPS_ASE_MSA)
+# define cpu_has_msa		__ase(MIPS_ASE_MSA)
 #elif !defined(cpu_has_msa)
 # define cpu_has_msa		0
 #endif
 
 #ifndef cpu_has_ufr
-# define cpu_has_ufr		(cpu_data[0].options & MIPS_CPU_UFR)
+# define cpu_has_ufr		__opt(MIPS_CPU_UFR)
 #endif
 
 #ifndef cpu_has_fre
-# define cpu_has_fre		(cpu_data[0].options & MIPS_CPU_FRE)
+# define cpu_has_fre		__opt(MIPS_CPU_FRE)
 #endif
 
 #ifndef cpu_has_cdmm
-# define cpu_has_cdmm		(cpu_data[0].options & MIPS_CPU_CDMM)
+# define cpu_has_cdmm		__opt(MIPS_CPU_CDMM)
 #endif
 
 #ifndef cpu_has_small_pages
-# define cpu_has_small_pages	(cpu_data[0].options & MIPS_CPU_SP)
+# define cpu_has_small_pages	__opt(MIPS_CPU_SP)
 #endif
 
 #ifndef cpu_has_nan_legacy
-#define cpu_has_nan_legacy	(cpu_data[0].options & MIPS_CPU_NAN_LEGACY)
+#define cpu_has_nan_legacy	__isa_lt_and_opt(6, MIPS_CPU_NAN_LEGACY)
 #endif
 #ifndef cpu_has_nan_2008
-#define cpu_has_nan_2008	(cpu_data[0].options & MIPS_CPU_NAN_2008)
+#define cpu_has_nan_2008	__isa_ge_or_opt(6, MIPS_CPU_NAN_2008)
 #endif
 
 #ifndef cpu_has_ebase_wg
-# define cpu_has_ebase_wg	(cpu_data[0].options & MIPS_CPU_EBASE_WG)
+# define cpu_has_ebase_wg	__opt(MIPS_CPU_EBASE_WG)
 #endif
 
 #ifndef cpu_has_badinstr
-# define cpu_has_badinstr	(cpu_data[0].options & MIPS_CPU_BADINSTR)
+# define cpu_has_badinstr	__isa_ge_or_opt(6, MIPS_CPU_BADINSTR)
 #endif
 
 #ifndef cpu_has_badinstrp
-# define cpu_has_badinstrp	(cpu_data[0].options & MIPS_CPU_BADINSTRP)
+# define cpu_has_badinstrp	__isa_ge_or_opt(6, MIPS_CPU_BADINSTRP)
 #endif
 
 #ifndef cpu_has_contextconfig
-# define cpu_has_contextconfig	(cpu_data[0].options & MIPS_CPU_CTXTC)
+# define cpu_has_contextconfig	__opt(MIPS_CPU_CTXTC)
 #endif
 
 #ifndef cpu_has_perf
-# define cpu_has_perf		(cpu_data[0].options & MIPS_CPU_PERF)
+# define cpu_has_perf		__opt(MIPS_CPU_PERF)
 #endif
 
-#if defined(CONFIG_SMP) && (MIPS_ISA_REV >= 6)
+#ifdef CONFIG_SMP
 /*
  * Some systems share FTLB RAMs between threads within a core (siblings in
  * kernel parlance). This means that FTLB entries may become invalid at almost
@@ -507,7 +545,7 @@
  */
 # ifndef cpu_has_shared_ftlb_ram
 #  define cpu_has_shared_ftlb_ram \
-	(current_cpu_data.options & MIPS_CPU_SHARED_FTLB_RAM)
+	__isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_RAM)
 # endif
 
 /*
@@ -524,9 +562,9 @@
  */
 # ifndef cpu_has_shared_ftlb_entries
 #  define cpu_has_shared_ftlb_entries \
-	(current_cpu_data.options & MIPS_CPU_SHARED_FTLB_ENTRIES)
+	__isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_ENTRIES)
 # endif
-#endif /* SMP && MIPS_ISA_REV >= 6 */
+#endif /* SMP */
 
 #ifndef cpu_has_shared_ftlb_ram
 # define cpu_has_shared_ftlb_ram 0
@@ -537,7 +575,7 @@
 
 #ifdef CONFIG_MIPS_MT_SMP
 # define cpu_has_mipsmt_pertccounters \
-	(cpu_data[0].options & MIPS_CPU_MT_PER_TC_PERF_COUNTERS)
+	__isa_lt_and_opt(6, MIPS_CPU_MT_PER_TC_PERF_COUNTERS)
 #else
 # define cpu_has_mipsmt_pertccounters 0
 #endif /* CONFIG_MIPS_MT_SMP */
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 5b9d02ef4f60..dacbdb84516a 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -225,31 +225,32 @@
  * Definitions for 7:0 on legacy processors
  */
 
-#define PRID_REV_TX4927		0x0022
-#define PRID_REV_TX4937		0x0030
-#define PRID_REV_R4400		0x0040
-#define PRID_REV_R3000A		0x0030
-#define PRID_REV_R3000		0x0020
-#define PRID_REV_R2000A		0x0010
-#define PRID_REV_TX3912		0x0010
-#define PRID_REV_TX3922		0x0030
-#define PRID_REV_TX3927		0x0040
-#define PRID_REV_VR4111		0x0050
-#define PRID_REV_VR4181		0x0050	/* Same as VR4111 */
-#define PRID_REV_VR4121		0x0060
-#define PRID_REV_VR4122		0x0070
-#define PRID_REV_VR4181A	0x0070	/* Same as VR4122 */
-#define PRID_REV_VR4130		0x0080
-#define PRID_REV_34K_V1_0_2	0x0022
-#define PRID_REV_LOONGSON1B	0x0020
-#define PRID_REV_LOONGSON1C	0x0020	/* Same as Loongson-1B */
-#define PRID_REV_LOONGSON2E	0x0002
-#define PRID_REV_LOONGSON2F	0x0003
-#define PRID_REV_LOONGSON3A_R1	0x0005
-#define PRID_REV_LOONGSON3B_R1	0x0006
-#define PRID_REV_LOONGSON3B_R2	0x0007
-#define PRID_REV_LOONGSON3A_R2	0x0008
-#define PRID_REV_LOONGSON3A_R3	0x0009
+#define PRID_REV_TX4927			0x0022
+#define PRID_REV_TX4937			0x0030
+#define PRID_REV_R4400			0x0040
+#define PRID_REV_R3000A			0x0030
+#define PRID_REV_R3000			0x0020
+#define PRID_REV_R2000A			0x0010
+#define PRID_REV_TX3912			0x0010
+#define PRID_REV_TX3922			0x0030
+#define PRID_REV_TX3927			0x0040
+#define PRID_REV_VR4111			0x0050
+#define PRID_REV_VR4181			0x0050	/* Same as VR4111 */
+#define PRID_REV_VR4121			0x0060
+#define PRID_REV_VR4122			0x0070
+#define PRID_REV_VR4181A		0x0070	/* Same as VR4122 */
+#define PRID_REV_VR4130			0x0080
+#define PRID_REV_34K_V1_0_2		0x0022
+#define PRID_REV_LOONGSON1B		0x0020
+#define PRID_REV_LOONGSON1C		0x0020	/* Same as Loongson-1B */
+#define PRID_REV_LOONGSON2E		0x0002
+#define PRID_REV_LOONGSON2F		0x0003
+#define PRID_REV_LOONGSON3A_R1		0x0005
+#define PRID_REV_LOONGSON3B_R1		0x0006
+#define PRID_REV_LOONGSON3B_R2		0x0007
+#define PRID_REV_LOONGSON3A_R2		0x0008
+#define PRID_REV_LOONGSON3A_R3_0	0x0009
+#define PRID_REV_LOONGSON3A_R3_1	0x000d
 
 /*
  * Older processors used to encode processor version and revision in two
diff --git a/arch/mips/include/asm/dma-coherence.h b/arch/mips/include/asm/dma-coherence.h
index 72d0eab02afc..8eda48748ed5 100644
--- a/arch/mips/include/asm/dma-coherence.h
+++ b/arch/mips/include/asm/dma-coherence.h
@@ -21,10 +21,10 @@ enum coherent_io_user_state {
 extern enum coherent_io_user_state coherentio;
 extern int hw_coherentio;
 #else
-#ifdef CONFIG_DMA_COHERENT
-#define coherentio	IO_COHERENCE_ENABLED
-#else
+#ifdef CONFIG_DMA_NONCOHERENT
 #define coherentio	IO_COHERENCE_DISABLED
+#else
+#define coherentio	IO_COHERENCE_ENABLED
 #endif
 #define hw_coherentio	0
 #endif /* CONFIG_DMA_MAYBE_COHERENT */
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index f32f15530aba..b5c240806e1b 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -1 +1,16 @@
-#include <asm/dma-coherence.h>
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MIPS_DMA_DIRECT_H
+#define _MIPS_DMA_DIRECT_H 1
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return false;
+
+	return addr + size - 1 <= *dev->dma_mask;
+}
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
+
+#endif /* _MIPS_DMA_DIRECT_H */
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 886e75a383f2..e81c4e97ff1a 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -2,19 +2,21 @@
 #ifndef _ASM_DMA_MAPPING_H
 #define _ASM_DMA_MAPPING_H
 
-#include <linux/scatterlist.h>
-#include <asm/dma-coherence.h>
-#include <asm/cache.h>
+#include <linux/swiotlb.h>
 
-#ifndef CONFIG_SGI_IP27 /* Kludge to fix 2.6.39 build for IP27 */
-#include <dma-coherence.h>
-#endif
-
-extern const struct dma_map_ops *mips_dma_map_ops;
+extern const struct dma_map_ops jazz_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return mips_dma_map_ops;
+#if defined(CONFIG_MACH_JAZZ)
+	return &jazz_dma_ops;
+#elif defined(CONFIG_SWIOTLB)
+	return &swiotlb_dma_ops;
+#elif defined(CONFIG_DMA_NONCOHERENT_OPS)
+	return &dma_noncoherent_ops;
+#else
+	return &dma_direct_ops;
+#endif
 }
 
 #define arch_setup_dma_ops arch_setup_dma_ops
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index cea8ad864b3f..54c730aed327 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -12,6 +12,8 @@
 #ifndef _ASM_IO_H
 #define _ASM_IO_H
 
+#define ARCH_HAS_IOREMAP_WC
+
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -141,14 +143,14 @@ static inline void * phys_to_virt(unsigned long address)
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
  */
-static inline unsigned long isa_virt_to_bus(volatile void * address)
+static inline unsigned long isa_virt_to_bus(volatile void *address)
 {
-	return (unsigned long)address - PAGE_OFFSET;
+	return virt_to_phys(address);
 }
 
-static inline void * isa_bus_to_virt(unsigned long address)
+static inline void *isa_bus_to_virt(unsigned long address)
 {
-	return (void *)(address + PAGE_OFFSET);
+	return phys_to_virt(address);
 }
 
 #define isa_page_to_bus page_to_phys
@@ -278,15 +280,25 @@ static inline void __iomem * __ioremap_mode(phys_addr_t offset, unsigned long si
 #define ioremap_cache ioremap_cachable
 
 /*
- * These two are MIPS specific ioremap variant.	 ioremap_cacheable_cow
- * requests a cachable mapping, ioremap_uncached_accelerated requests a
- * mapping using the uncached accelerated mode which isn't supported on
- * all processors.
+ * ioremap_wc     -   map bus memory into CPU space
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap_wc performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked uncachable
+ * but accelerated by means of write-combining feature. It is specifically
+ * useful for PCIe prefetchable windows, which may vastly improve a
+ * communications performance. If it was determined on boot stage, what
+ * CPU CCA doesn't support UCA, the method shall fall-back to the
+ * _CACHE_UNCACHED option (see cpu_probe() method).
  */
-#define ioremap_cacheable_cow(offset, size)				\
-	__ioremap_mode((offset), (size), _CACHE_CACHABLE_COW)
-#define ioremap_uncached_accelerated(offset, size)			\
-	__ioremap_mode((offset), (size), _CACHE_UNCACHED_ACCELERATED)
+#define ioremap_wc(offset, size)					\
+	__ioremap_mode((offset), (size), boot_cpu_data.writecombine)
 
 static inline void iounmap(const volatile void __iomem *addr)
 {
@@ -590,7 +602,7 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int
  *
  * This API used to be exported; it now is for arch code internal use only.
  */
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 extern void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
 extern void (*_dma_cache_wback)(unsigned long start, unsigned long size);
@@ -609,7 +621,7 @@ extern void (*_dma_cache_inv)(unsigned long start, unsigned long size);
 #define dma_cache_inv(start,size)	\
 	do { (void) (start); (void) (size); } while (0)
 
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 /*
  * Read a 32-bit register that requires a 64-bit read cycle on the bus.
diff --git a/arch/mips/include/asm/kprobes.h b/arch/mips/include/asm/kprobes.h
index ad1a99948f27..a72dfbf1babb 100644
--- a/arch/mips/include/asm/kprobes.h
+++ b/arch/mips/include/asm/kprobes.h
@@ -68,16 +68,6 @@ struct prev_kprobe {
 	unsigned long saved_epc;
 };
 
-#define MAX_JPROBES_STACK_SIZE 128
-#define MAX_JPROBES_STACK_ADDR \
-	(((unsigned long)current_thread_info()) + THREAD_SIZE - 32 - sizeof(struct pt_regs))
-
-#define MIN_JPROBES_STACK_SIZE(ADDR)					\
-	((((ADDR) + MAX_JPROBES_STACK_SIZE) > MAX_JPROBES_STACK_ADDR)	\
-		? MAX_JPROBES_STACK_ADDR - (ADDR)			\
-		: MAX_JPROBES_STACK_SIZE)
-
-
 #define SKIP_DELAYSLOT 0x0001
 
 /* per-cpu kprobe control block */
@@ -86,12 +76,9 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_old_SR;
 	unsigned long kprobe_saved_SR;
 	unsigned long kprobe_saved_epc;
-	unsigned long jprobe_saved_sp;
-	struct pt_regs jprobe_saved_regs;
 	/* Per-thread fields, used while emulating branches */
 	unsigned long flags;
 	unsigned long target_epc;
-	u8 jprobes_stack[MAX_JPROBES_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/mips/include/asm/mach-ar7/spaces.h b/arch/mips/include/asm/mach-ar7/spaces.h
index 660ab64c0fc9..a004d94dfbdd 100644
--- a/arch/mips/include/asm/mach-ar7/spaces.h
+++ b/arch/mips/include/asm/mach-ar7/spaces.h
@@ -17,9 +17,6 @@
 #define PAGE_OFFSET	_AC(0x94000000, UL)
 #define PHYS_OFFSET	_AC(0x14000000, UL)
 
-#define UNCAC_BASE	_AC(0xb4000000, UL)	/* 0xa0000000 + PHYS_OFFSET */
-#define IO_BASE		UNCAC_BASE
-
 #include <asm/mach-generic/spaces.h>
 
 #endif /* __ASM_AR7_SPACES_H */
diff --git a/arch/mips/include/asm/mach-ath25/dma-coherence.h b/arch/mips/include/asm/mach-ath25/dma-coherence.h
deleted file mode 100644
index d5defdde32db..000000000000
--- a/arch/mips/include/asm/mach-ath25/dma-coherence.h
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2007  Felix Fietkau <nbd@openwrt.org>
- *
- */
-#ifndef __ASM_MACH_ATH25_DMA_COHERENCE_H
-#define __ASM_MACH_ATH25_DMA_COHERENCE_H
-
-#include <linux/device.h>
-
-/*
- * We need some arbitrary non-zero value to be programmed to the BAR1 register
- * of PCI host controller to enable DMA. The same value should be used as the
- * offset to calculate the physical address of DMA buffer for PCI devices.
- */
-#define AR2315_PCI_HOST_SDRAM_BASEADDR	0x20000000
-
-static inline dma_addr_t ath25_dev_offset(struct device *dev)
-{
-#ifdef CONFIG_PCI
-	extern struct bus_type pci_bus_type;
-
-	if (dev && dev->bus == &pci_bus_type)
-		return AR2315_PCI_HOST_SDRAM_BASEADDR;
-#endif
-	return 0;
-}
-
-static inline dma_addr_t
-plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
-	return virt_to_phys(addr) + ath25_dev_offset(dev);
-}
-
-static inline dma_addr_t
-plat_map_dma_mem_page(struct device *dev, struct page *page)
-{
-	return page_to_phys(page) + ath25_dev_offset(dev);
-}
-
-static inline unsigned long
-plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr - ath25_dev_offset(dev);
-}
-
-static inline void
-plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, size_t size,
-		   enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_COHERENT
-	return 1;
-#endif
-#ifdef CONFIG_DMA_NONCOHERENT
-	return 0;
-#endif
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-#endif /* __ASM_MACH_ATH25_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
index d99ca862dae3..284b4fa23e03 100644
--- a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
+++ b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
@@ -20,6 +20,10 @@
 #include <linux/bitops.h>
 
 #define AR71XX_APB_BASE		0x18000000
+#define AR71XX_GE0_BASE		0x19000000
+#define AR71XX_GE0_SIZE		0x10000
+#define AR71XX_GE1_BASE		0x1a000000
+#define AR71XX_GE1_SIZE		0x10000
 #define AR71XX_EHCI_BASE	0x1b000000
 #define AR71XX_EHCI_SIZE	0x1000
 #define AR71XX_OHCI_BASE	0x1c000000
@@ -39,6 +43,8 @@
 #define AR71XX_PLL_SIZE		0x100
 #define AR71XX_RESET_BASE	(AR71XX_APB_BASE + 0x00060000)
 #define AR71XX_RESET_SIZE	0x100
+#define AR71XX_MII_BASE		(AR71XX_APB_BASE + 0x00070000)
+#define AR71XX_MII_SIZE		0x100
 
 #define AR71XX_PCI_MEM_BASE	0x10000000
 #define AR71XX_PCI_MEM_SIZE	0x07000000
@@ -81,18 +87,39 @@
 
 #define AR933X_UART_BASE	(AR71XX_APB_BASE + 0x00020000)
 #define AR933X_UART_SIZE	0x14
+#define AR933X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define AR933X_GMAC_SIZE	0x04
 #define AR933X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
 #define AR933X_WMAC_SIZE	0x20000
 #define AR933X_EHCI_BASE	0x1b000000
 #define AR933X_EHCI_SIZE	0x1000
 
+#define AR934X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define AR934X_GMAC_SIZE	0x14
 #define AR934X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
 #define AR934X_WMAC_SIZE	0x20000
 #define AR934X_EHCI_BASE	0x1b000000
 #define AR934X_EHCI_SIZE	0x200
+#define AR934X_NFC_BASE		0x1b000200
+#define AR934X_NFC_SIZE		0xb8
 #define AR934X_SRIF_BASE	(AR71XX_APB_BASE + 0x00116000)
 #define AR934X_SRIF_SIZE	0x1000
 
+#define QCA953X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA953X_GMAC_SIZE	0x14
+#define QCA953X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
+#define QCA953X_WMAC_SIZE	0x20000
+#define QCA953X_EHCI_BASE	0x1b000000
+#define QCA953X_EHCI_SIZE	0x200
+#define QCA953X_SRIF_BASE	(AR71XX_APB_BASE + 0x00116000)
+#define QCA953X_SRIF_SIZE	0x1000
+
+#define QCA953X_PCI_CFG_BASE0	0x14000000
+#define QCA953X_PCI_CTRL_BASE0	(AR71XX_APB_BASE + 0x000f0000)
+#define QCA953X_PCI_CRP_BASE0	(AR71XX_APB_BASE + 0x000c0000)
+#define QCA953X_PCI_MEM_BASE0	0x10000000
+#define QCA953X_PCI_MEM_SIZE	0x02000000
+
 #define QCA955X_PCI_MEM_BASE0	0x10000000
 #define QCA955X_PCI_MEM_BASE1	0x12000000
 #define QCA955X_PCI_MEM_SIZE	0x02000000
@@ -106,11 +133,72 @@
 #define QCA955X_PCI_CTRL_BASE1	(AR71XX_APB_BASE + 0x00280000)
 #define QCA955X_PCI_CTRL_SIZE	0x100
 
+#define QCA955X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA955X_GMAC_SIZE	0x40
 #define QCA955X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
 #define QCA955X_WMAC_SIZE	0x20000
 #define QCA955X_EHCI0_BASE	0x1b000000
 #define QCA955X_EHCI1_BASE	0x1b400000
 #define QCA955X_EHCI_SIZE	0x1000
+#define QCA955X_NFC_BASE	0x1b800200
+#define QCA955X_NFC_SIZE	0xb8
+
+#define QCA956X_PCI_MEM_BASE1	0x12000000
+#define QCA956X_PCI_MEM_SIZE	0x02000000
+#define QCA956X_PCI_CFG_BASE1	0x16000000
+#define QCA956X_PCI_CFG_SIZE	0x1000
+#define QCA956X_PCI_CRP_BASE1	(AR71XX_APB_BASE + 0x00250000)
+#define QCA956X_PCI_CRP_SIZE	0x1000
+#define QCA956X_PCI_CTRL_BASE1	(AR71XX_APB_BASE + 0x00280000)
+#define QCA956X_PCI_CTRL_SIZE	0x100
+
+#define QCA956X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
+#define QCA956X_WMAC_SIZE	0x20000
+#define QCA956X_EHCI0_BASE	0x1b000000
+#define QCA956X_EHCI1_BASE	0x1b400000
+#define QCA956X_EHCI_SIZE	0x200
+#define QCA956X_GMAC_SGMII_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA956X_GMAC_SGMII_SIZE	0x64
+#define QCA956X_PLL_BASE	(AR71XX_APB_BASE + 0x00050000)
+#define QCA956X_PLL_SIZE	0x50
+#define QCA956X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA956X_GMAC_SIZE	0x64
+
+/*
+ * Hidden Registers
+ */
+#define QCA956X_MAC_CFG_BASE		0xb9000000
+#define QCA956X_MAC_CFG_SIZE		0x64
+
+#define QCA956X_MAC_CFG1_REG		0x00
+#define QCA956X_MAC_CFG1_SOFT_RST	BIT(31)
+#define QCA956X_MAC_CFG1_RX_RST		BIT(19)
+#define QCA956X_MAC_CFG1_TX_RST		BIT(18)
+#define QCA956X_MAC_CFG1_LOOPBACK	BIT(8)
+#define QCA956X_MAC_CFG1_RX_EN		BIT(2)
+#define QCA956X_MAC_CFG1_TX_EN		BIT(0)
+
+#define QCA956X_MAC_CFG2_REG		0x04
+#define QCA956X_MAC_CFG2_IF_1000	BIT(9)
+#define QCA956X_MAC_CFG2_IF_10_100	BIT(8)
+#define QCA956X_MAC_CFG2_HUGE_FRAME_EN	BIT(5)
+#define QCA956X_MAC_CFG2_LEN_CHECK	BIT(4)
+#define QCA956X_MAC_CFG2_PAD_CRC_EN	BIT(2)
+#define QCA956X_MAC_CFG2_FDX		BIT(0)
+
+#define QCA956X_MAC_MII_MGMT_CFG_REG	0x20
+#define QCA956X_MGMT_CFG_CLK_DIV_20	0x07
+
+#define QCA956X_MAC_FIFO_CFG0_REG	0x48
+#define QCA956X_MAC_FIFO_CFG1_REG	0x4c
+#define QCA956X_MAC_FIFO_CFG2_REG	0x50
+#define QCA956X_MAC_FIFO_CFG3_REG	0x54
+#define QCA956X_MAC_FIFO_CFG4_REG	0x58
+#define QCA956X_MAC_FIFO_CFG5_REG	0x5c
+
+#define QCA956X_DAM_RESET_OFFSET	0xb90001bc
+#define QCA956X_DAM_RESET_SIZE		0x4
+#define QCA956X_INLINE_CHKSUM_ENG	BIT(27)
 
 /*
  * DDR_CTRL block
@@ -149,6 +237,12 @@
 #define AR934X_DDR_REG_FLUSH_PCIE	0xa8
 #define AR934X_DDR_REG_FLUSH_WMAC	0xac
 
+#define QCA953X_DDR_REG_FLUSH_GE0	0x9c
+#define QCA953X_DDR_REG_FLUSH_GE1	0xa0
+#define QCA953X_DDR_REG_FLUSH_USB	0xa4
+#define QCA953X_DDR_REG_FLUSH_PCIE	0xa8
+#define QCA953X_DDR_REG_FLUSH_WMAC	0xac
+
 /*
  * PLL block
  */
@@ -166,9 +260,15 @@
 #define AR71XX_AHB_DIV_SHIFT		20
 #define AR71XX_AHB_DIV_MASK		0x7
 
+#define AR71XX_ETH0_PLL_SHIFT		17
+#define AR71XX_ETH1_PLL_SHIFT		19
+
 #define AR724X_PLL_REG_CPU_CONFIG	0x00
 #define AR724X_PLL_REG_PCIE_CONFIG	0x10
 
+#define AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS	BIT(16)
+#define AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET	BIT(25)
+
 #define AR724X_PLL_FB_SHIFT		0
 #define AR724X_PLL_FB_MASK		0x3ff
 #define AR724X_PLL_REF_DIV_SHIFT	10
@@ -178,6 +278,8 @@
 #define AR724X_DDR_DIV_SHIFT		22
 #define AR724X_DDR_DIV_MASK		0x3
 
+#define AR7242_PLL_REG_ETH0_INT_CLOCK	0x2c
+
 #define AR913X_PLL_REG_CPU_CONFIG	0x00
 #define AR913X_PLL_REG_ETH_CONFIG	0x04
 #define AR913X_PLL_REG_ETH0_INT_CLOCK	0x14
@@ -190,6 +292,9 @@
 #define AR913X_AHB_DIV_SHIFT		19
 #define AR913X_AHB_DIV_MASK		0x1
 
+#define AR913X_ETH0_PLL_SHIFT		20
+#define AR913X_ETH1_PLL_SHIFT		22
+
 #define AR933X_PLL_CPU_CONFIG_REG	0x00
 #define AR933X_PLL_CLOCK_CTRL_REG	0x08
 
@@ -211,6 +316,8 @@
 #define AR934X_PLL_CPU_CONFIG_REG		0x00
 #define AR934X_PLL_DDR_CONFIG_REG		0x04
 #define AR934X_PLL_CPU_DDR_CLK_CTRL_REG		0x08
+#define AR934X_PLL_SWITCH_CLOCK_CONTROL_REG	0x24
+#define AR934X_PLL_ETH_XMII_CONTROL_REG		0x2c
 
 #define AR934X_PLL_CPU_CONFIG_NFRAC_SHIFT	0
 #define AR934X_PLL_CPU_CONFIG_NFRAC_MASK	0x3f
@@ -243,9 +350,52 @@
 #define AR934X_PLL_CPU_DDR_CLK_CTRL_DDRCLK_FROM_DDRPLL	BIT(21)
 #define AR934X_PLL_CPU_DDR_CLK_CTRL_AHBCLK_FROM_DDRPLL	BIT(24)
 
+#define AR934X_PLL_SWITCH_CLOCK_CONTROL_MDIO_CLK_SEL	BIT(6)
+
+#define QCA953X_PLL_CPU_CONFIG_REG		0x00
+#define QCA953X_PLL_DDR_CONFIG_REG		0x04
+#define QCA953X_PLL_CLK_CTRL_REG		0x08
+#define QCA953X_PLL_SWITCH_CLOCK_CONTROL_REG	0x24
+#define QCA953X_PLL_ETH_XMII_CONTROL_REG	0x2c
+#define QCA953X_PLL_ETH_SGMII_CONTROL_REG	0x48
+
+#define QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT	0
+#define QCA953X_PLL_CPU_CONFIG_NFRAC_MASK	0x3f
+#define QCA953X_PLL_CPU_CONFIG_NINT_SHIFT	6
+#define QCA953X_PLL_CPU_CONFIG_NINT_MASK	0x3f
+#define QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT	12
+#define QCA953X_PLL_CPU_CONFIG_REFDIV_MASK	0x1f
+#define QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT	19
+#define QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK	0x7
+
+#define QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT	0
+#define QCA953X_PLL_DDR_CONFIG_NFRAC_MASK	0x3ff
+#define QCA953X_PLL_DDR_CONFIG_NINT_SHIFT	10
+#define QCA953X_PLL_DDR_CONFIG_NINT_MASK	0x3f
+#define QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT	16
+#define QCA953X_PLL_DDR_CONFIG_REFDIV_MASK	0x1f
+#define QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT	23
+#define QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK	0x7
+
+#define QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS		BIT(2)
+#define QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS		BIT(3)
+#define QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS		BIT(4)
+#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT		5
+#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK		0x1f
+#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT		10
+#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK		0x1f
+#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT		15
+#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK		0x1f
+#define QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL		BIT(20)
+#define QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL		BIT(21)
+#define QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL		BIT(24)
+
 #define QCA955X_PLL_CPU_CONFIG_REG		0x00
 #define QCA955X_PLL_DDR_CONFIG_REG		0x04
 #define QCA955X_PLL_CLK_CTRL_REG		0x08
+#define QCA955X_PLL_ETH_XMII_CONTROL_REG	0x28
+#define QCA955X_PLL_ETH_SGMII_CONTROL_REG	0x48
+#define QCA955X_PLL_ETH_SGMII_SERDES_REG	0x4c
 
 #define QCA955X_PLL_CPU_CONFIG_NFRAC_SHIFT	0
 #define QCA955X_PLL_CPU_CONFIG_NFRAC_MASK	0x3f
@@ -278,6 +428,81 @@
 #define QCA955X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL		BIT(21)
 #define QCA955X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL		BIT(24)
 
+#define QCA955X_PLL_ETH_SGMII_SERDES_LOCK_DETECT	BIT(2)
+#define QCA955X_PLL_ETH_SGMII_SERDES_PLL_REFCLK		BIT(1)
+#define QCA955X_PLL_ETH_SGMII_SERDES_EN_PLL		BIT(0)
+
+#define QCA956X_PLL_CPU_CONFIG_REG			0x00
+#define QCA956X_PLL_CPU_CONFIG1_REG			0x04
+#define QCA956X_PLL_DDR_CONFIG_REG			0x08
+#define QCA956X_PLL_DDR_CONFIG1_REG			0x0c
+#define QCA956X_PLL_CLK_CTRL_REG			0x10
+#define QCA956X_PLL_SWITCH_CLOCK_CONTROL_REG		0x28
+#define QCA956X_PLL_ETH_XMII_CONTROL_REG		0x30
+#define QCA956X_PLL_ETH_SGMII_SERDES_REG		0x4c
+
+#define QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT		12
+#define QCA956X_PLL_CPU_CONFIG_REFDIV_MASK		0x1f
+#define QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT		19
+#define QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK		0x7
+
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT		0
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK		0x1f
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT		5
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK		0x1fff
+#define QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT		18
+#define QCA956X_PLL_CPU_CONFIG1_NINT_MASK		0x1ff
+
+#define QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT		16
+#define QCA956X_PLL_DDR_CONFIG_REFDIV_MASK		0x1f
+#define QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT		23
+#define QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK		0x7
+
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT		0
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK		0x1f
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT		5
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK		0x1fff
+#define QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT		18
+#define QCA956X_PLL_DDR_CONFIG1_NINT_MASK		0x1ff
+
+#define QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS		BIT(2)
+#define QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS		BIT(3)
+#define QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS		BIT(4)
+#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT		5
+#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK		0x1f
+#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT		10
+#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK		0x1f
+#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT		15
+#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK		0x1f
+#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL	BIT(20)
+#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL	BIT(21)
+#define QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL		BIT(24)
+
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_I2C_CLK_SELB		BIT(5)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_1		BIT(6)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_UART1_CLK_SEL		BIT(7)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_SHIFT 8
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_MASK	 0xf
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EN_PLL_TOP		BIT(12)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_2		BIT(13)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_1		BIT(14)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_2		BIT(15)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCH_FUNC_TST_MODE	BIT(16)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EEE_ENABLE		BIT(17)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_OEN_CLK125M_PLL		BIT(18)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCHCLK_SEL		BIT(19)
+
+#define QCA956X_PLL_ETH_XMII_TX_INVERT			BIT(1)
+#define QCA956X_PLL_ETH_XMII_GIGE			BIT(25)
+#define QCA956X_PLL_ETH_XMII_RX_DELAY_SHIFT		28
+#define QCA956X_PLL_ETH_XMII_RX_DELAY_MASK		0x3
+#define QCA956X_PLL_ETH_XMII_TX_DELAY_SHIFT		26
+#define QCA956X_PLL_ETH_XMII_TX_DELAY_MASK		3
+
+#define QCA956X_PLL_ETH_SGMII_SERDES_LOCK_DETECT		BIT(2)
+#define QCA956X_PLL_ETH_SGMII_SERDES_PLL_REFCLK			BIT(1)
+#define QCA956X_PLL_ETH_SGMII_SERDES_EN_PLL			BIT(0)
+
 /*
  * USB_CONFIG block
  */
@@ -317,10 +542,19 @@
 #define AR934X_RESET_REG_BOOTSTRAP		0xb0
 #define AR934X_RESET_REG_PCIE_WMAC_INT_STATUS	0xac
 
+#define QCA953X_RESET_REG_RESET_MODULE		0x1c
+#define QCA953X_RESET_REG_BOOTSTRAP		0xb0
+#define QCA953X_RESET_REG_PCIE_WMAC_INT_STATUS	0xac
+
 #define QCA955X_RESET_REG_RESET_MODULE		0x1c
 #define QCA955X_RESET_REG_BOOTSTRAP		0xb0
 #define QCA955X_RESET_REG_EXT_INT_STATUS	0xac
 
+#define QCA956X_RESET_REG_RESET_MODULE		0x1c
+#define QCA956X_RESET_REG_BOOTSTRAP		0xb0
+#define QCA956X_RESET_REG_EXT_INT_STATUS	0xac
+
+#define MISC_INT_MIPS_SI_TIMERINT_MASK	BIT(28)
 #define MISC_INT_ETHSW			BIT(12)
 #define MISC_INT_TIMER4			BIT(10)
 #define MISC_INT_TIMER3			BIT(9)
@@ -370,16 +604,123 @@
 #define AR913X_RESET_USB_HOST		BIT(5)
 #define AR913X_RESET_USB_PHY		BIT(4)
 
+#define AR933X_RESET_GE1_MDIO		BIT(23)
+#define AR933X_RESET_GE0_MDIO		BIT(22)
+#define AR933X_RESET_GE1_MAC		BIT(13)
 #define AR933X_RESET_WMAC		BIT(11)
+#define AR933X_RESET_GE0_MAC		BIT(9)
 #define AR933X_RESET_USB_HOST		BIT(5)
 #define AR933X_RESET_USB_PHY		BIT(4)
 #define AR933X_RESET_USBSUS_OVERRIDE	BIT(3)
 
+#define AR934X_RESET_HOST		BIT(31)
+#define AR934X_RESET_SLIC		BIT(30)
+#define AR934X_RESET_HDMA		BIT(29)
+#define AR934X_RESET_EXTERNAL		BIT(28)
+#define AR934X_RESET_RTC		BIT(27)
+#define AR934X_RESET_PCIE_EP_INT	BIT(26)
+#define AR934X_RESET_CHKSUM_ACC		BIT(25)
+#define AR934X_RESET_FULL_CHIP		BIT(24)
+#define AR934X_RESET_GE1_MDIO		BIT(23)
+#define AR934X_RESET_GE0_MDIO		BIT(22)
+#define AR934X_RESET_CPU_NMI		BIT(21)
+#define AR934X_RESET_CPU_COLD		BIT(20)
+#define AR934X_RESET_HOST_RESET_INT	BIT(19)
+#define AR934X_RESET_PCIE_EP		BIT(18)
+#define AR934X_RESET_UART1		BIT(17)
+#define AR934X_RESET_DDR		BIT(16)
+#define AR934X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define AR934X_RESET_NANDF		BIT(14)
+#define AR934X_RESET_GE1_MAC		BIT(13)
+#define AR934X_RESET_ETH_SWITCH_ANALOG	BIT(12)
 #define AR934X_RESET_USB_PHY_ANALOG	BIT(11)
+#define AR934X_RESET_HOST_DMA_INT	BIT(10)
+#define AR934X_RESET_GE0_MAC		BIT(9)
+#define AR934X_RESET_ETH_SWITCH		BIT(8)
+#define AR934X_RESET_PCIE_PHY		BIT(7)
+#define AR934X_RESET_PCIE		BIT(6)
 #define AR934X_RESET_USB_HOST		BIT(5)
 #define AR934X_RESET_USB_PHY		BIT(4)
 #define AR934X_RESET_USBSUS_OVERRIDE	BIT(3)
-
+#define AR934X_RESET_LUT		BIT(2)
+#define AR934X_RESET_MBOX		BIT(1)
+#define AR934X_RESET_I2S		BIT(0)
+
+#define QCA953X_RESET_USB_EXT_PWR	BIT(29)
+#define QCA953X_RESET_EXTERNAL		BIT(28)
+#define QCA953X_RESET_RTC		BIT(27)
+#define QCA953X_RESET_FULL_CHIP		BIT(24)
+#define QCA953X_RESET_GE1_MDIO		BIT(23)
+#define QCA953X_RESET_GE0_MDIO		BIT(22)
+#define QCA953X_RESET_CPU_NMI		BIT(21)
+#define QCA953X_RESET_CPU_COLD		BIT(20)
+#define QCA953X_RESET_DDR		BIT(16)
+#define QCA953X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define QCA953X_RESET_GE1_MAC		BIT(13)
+#define QCA953X_RESET_ETH_SWITCH_ANALOG	BIT(12)
+#define QCA953X_RESET_USB_PHY_ANALOG	BIT(11)
+#define QCA953X_RESET_GE0_MAC		BIT(9)
+#define QCA953X_RESET_ETH_SWITCH	BIT(8)
+#define QCA953X_RESET_PCIE_PHY		BIT(7)
+#define QCA953X_RESET_PCIE		BIT(6)
+#define QCA953X_RESET_USB_HOST		BIT(5)
+#define QCA953X_RESET_USB_PHY		BIT(4)
+#define QCA953X_RESET_USBSUS_OVERRIDE	BIT(3)
+
+#define QCA955X_RESET_HOST		BIT(31)
+#define QCA955X_RESET_SLIC		BIT(30)
+#define QCA955X_RESET_HDMA		BIT(29)
+#define QCA955X_RESET_EXTERNAL		BIT(28)
+#define QCA955X_RESET_RTC		BIT(27)
+#define QCA955X_RESET_PCIE_EP_INT	BIT(26)
+#define QCA955X_RESET_CHKSUM_ACC	BIT(25)
+#define QCA955X_RESET_FULL_CHIP		BIT(24)
+#define QCA955X_RESET_GE1_MDIO		BIT(23)
+#define QCA955X_RESET_GE0_MDIO		BIT(22)
+#define QCA955X_RESET_CPU_NMI		BIT(21)
+#define QCA955X_RESET_CPU_COLD		BIT(20)
+#define QCA955X_RESET_HOST_RESET_INT	BIT(19)
+#define QCA955X_RESET_PCIE_EP		BIT(18)
+#define QCA955X_RESET_UART1		BIT(17)
+#define QCA955X_RESET_DDR		BIT(16)
+#define QCA955X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define QCA955X_RESET_NANDF		BIT(14)
+#define QCA955X_RESET_GE1_MAC		BIT(13)
+#define QCA955X_RESET_SGMII_ANALOG	BIT(12)
+#define QCA955X_RESET_USB_PHY_ANALOG	BIT(11)
+#define QCA955X_RESET_HOST_DMA_INT	BIT(10)
+#define QCA955X_RESET_GE0_MAC		BIT(9)
+#define QCA955X_RESET_SGMII		BIT(8)
+#define QCA955X_RESET_PCIE_PHY		BIT(7)
+#define QCA955X_RESET_PCIE		BIT(6)
+#define QCA955X_RESET_USB_HOST		BIT(5)
+#define QCA955X_RESET_USB_PHY		BIT(4)
+#define QCA955X_RESET_USBSUS_OVERRIDE	BIT(3)
+#define QCA955X_RESET_LUT		BIT(2)
+#define QCA955X_RESET_MBOX		BIT(1)
+#define QCA955X_RESET_I2S		BIT(0)
+
+#define QCA956X_RESET_EXTERNAL		BIT(28)
+#define QCA956X_RESET_FULL_CHIP		BIT(24)
+#define QCA956X_RESET_GE1_MDIO		BIT(23)
+#define QCA956X_RESET_GE0_MDIO		BIT(22)
+#define QCA956X_RESET_CPU_NMI		BIT(21)
+#define QCA956X_RESET_CPU_COLD		BIT(20)
+#define QCA956X_RESET_DMA		BIT(19)
+#define QCA956X_RESET_DDR		BIT(16)
+#define QCA956X_RESET_GE1_MAC		BIT(13)
+#define QCA956X_RESET_SGMII_ANALOG	BIT(12)
+#define QCA956X_RESET_USB_PHY_ANALOG	BIT(11)
+#define QCA956X_RESET_GE0_MAC		BIT(9)
+#define QCA956X_RESET_SGMII		BIT(8)
+#define QCA956X_RESET_USB_HOST		BIT(5)
+#define QCA956X_RESET_USB_PHY		BIT(4)
+#define QCA956X_RESET_USBSUS_OVERRIDE	BIT(3)
+#define QCA956X_RESET_SWITCH_ANALOG	BIT(2)
+#define QCA956X_RESET_SWITCH		BIT(0)
+
+#define AR933X_BOOTSTRAP_MDIO_GPIO_EN	BIT(18)
+#define AR933X_BOOTSTRAP_EEPBUSY	BIT(4)
 #define AR933X_BOOTSTRAP_REF_CLK_40	BIT(0)
 
 #define AR934X_BOOTSTRAP_SW_OPTION8	BIT(23)
@@ -398,8 +739,17 @@
 #define AR934X_BOOTSTRAP_SDRAM_DISABLED BIT(1)
 #define AR934X_BOOTSTRAP_DDR1		BIT(0)
 
+#define QCA953X_BOOTSTRAP_SW_OPTION2	BIT(12)
+#define QCA953X_BOOTSTRAP_SW_OPTION1	BIT(11)
+#define QCA953X_BOOTSTRAP_EJTAG_MODE	BIT(5)
+#define QCA953X_BOOTSTRAP_REF_CLK_40	BIT(4)
+#define QCA953X_BOOTSTRAP_SDRAM_DISABLED BIT(1)
+#define QCA953X_BOOTSTRAP_DDR1		BIT(0)
+
 #define QCA955X_BOOTSTRAP_REF_CLK_40	BIT(4)
 
+#define QCA956X_BOOTSTRAP_REF_CLK_40	BIT(2)
+
 #define AR934X_PCIE_WMAC_INT_WMAC_MISC		BIT(0)
 #define AR934X_PCIE_WMAC_INT_WMAC_TX		BIT(1)
 #define AR934X_PCIE_WMAC_INT_WMAC_RXLP		BIT(2)
@@ -418,6 +768,24 @@
 	 AR934X_PCIE_WMAC_INT_PCIE_RC1 | AR934X_PCIE_WMAC_INT_PCIE_RC2 | \
 	 AR934X_PCIE_WMAC_INT_PCIE_RC3)
 
+#define QCA953X_PCIE_WMAC_INT_WMAC_MISC		BIT(0)
+#define QCA953X_PCIE_WMAC_INT_WMAC_TX		BIT(1)
+#define QCA953X_PCIE_WMAC_INT_WMAC_RXLP		BIT(2)
+#define QCA953X_PCIE_WMAC_INT_WMAC_RXHP		BIT(3)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC		BIT(4)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC0		BIT(5)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC1		BIT(6)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC2		BIT(7)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC3		BIT(8)
+#define QCA953X_PCIE_WMAC_INT_WMAC_ALL \
+	(QCA953X_PCIE_WMAC_INT_WMAC_MISC | QCA953X_PCIE_WMAC_INT_WMAC_TX | \
+	 QCA953X_PCIE_WMAC_INT_WMAC_RXLP | QCA953X_PCIE_WMAC_INT_WMAC_RXHP)
+
+#define QCA953X_PCIE_WMAC_INT_PCIE_ALL \
+	(QCA953X_PCIE_WMAC_INT_PCIE_RC | QCA953X_PCIE_WMAC_INT_PCIE_RC0 | \
+	 QCA953X_PCIE_WMAC_INT_PCIE_RC1 | QCA953X_PCIE_WMAC_INT_PCIE_RC2 | \
+	 QCA953X_PCIE_WMAC_INT_PCIE_RC3)
+
 #define QCA955X_EXT_INT_WMAC_MISC		BIT(0)
 #define QCA955X_EXT_INT_WMAC_TX			BIT(1)
 #define QCA955X_EXT_INT_WMAC_RXLP		BIT(2)
@@ -449,6 +817,37 @@
 	 QCA955X_EXT_INT_PCIE_RC2_INT1 | QCA955X_EXT_INT_PCIE_RC2_INT2 | \
 	 QCA955X_EXT_INT_PCIE_RC2_INT3)
 
+#define QCA956X_EXT_INT_WMAC_MISC		BIT(0)
+#define QCA956X_EXT_INT_WMAC_TX			BIT(1)
+#define QCA956X_EXT_INT_WMAC_RXLP		BIT(2)
+#define QCA956X_EXT_INT_WMAC_RXHP		BIT(3)
+#define QCA956X_EXT_INT_PCIE_RC1		BIT(4)
+#define QCA956X_EXT_INT_PCIE_RC1_INT0		BIT(5)
+#define QCA956X_EXT_INT_PCIE_RC1_INT1		BIT(6)
+#define QCA956X_EXT_INT_PCIE_RC1_INT2		BIT(7)
+#define QCA956X_EXT_INT_PCIE_RC1_INT3		BIT(8)
+#define QCA956X_EXT_INT_PCIE_RC2		BIT(12)
+#define QCA956X_EXT_INT_PCIE_RC2_INT0		BIT(13)
+#define QCA956X_EXT_INT_PCIE_RC2_INT1		BIT(14)
+#define QCA956X_EXT_INT_PCIE_RC2_INT2		BIT(15)
+#define QCA956X_EXT_INT_PCIE_RC2_INT3		BIT(16)
+#define QCA956X_EXT_INT_USB1			BIT(24)
+#define QCA956X_EXT_INT_USB2			BIT(28)
+
+#define QCA956X_EXT_INT_WMAC_ALL \
+	(QCA956X_EXT_INT_WMAC_MISC | QCA956X_EXT_INT_WMAC_TX | \
+	 QCA956X_EXT_INT_WMAC_RXLP | QCA956X_EXT_INT_WMAC_RXHP)
+
+#define QCA956X_EXT_INT_PCIE_RC1_ALL \
+	(QCA956X_EXT_INT_PCIE_RC1 | QCA956X_EXT_INT_PCIE_RC1_INT0 | \
+	 QCA956X_EXT_INT_PCIE_RC1_INT1 | QCA956X_EXT_INT_PCIE_RC1_INT2 | \
+	 QCA956X_EXT_INT_PCIE_RC1_INT3)
+
+#define QCA956X_EXT_INT_PCIE_RC2_ALL \
+	(QCA956X_EXT_INT_PCIE_RC2 | QCA956X_EXT_INT_PCIE_RC2_INT0 | \
+	 QCA956X_EXT_INT_PCIE_RC2_INT1 | QCA956X_EXT_INT_PCIE_RC2_INT2 | \
+	 QCA956X_EXT_INT_PCIE_RC2_INT3)
+
 #define REV_ID_MAJOR_MASK		0xfff0
 #define REV_ID_MAJOR_AR71XX		0x00a0
 #define REV_ID_MAJOR_AR913X		0x00b0
@@ -460,8 +859,12 @@
 #define REV_ID_MAJOR_AR9341		0x0120
 #define REV_ID_MAJOR_AR9342		0x1120
 #define REV_ID_MAJOR_AR9344		0x2120
+#define REV_ID_MAJOR_QCA9533		0x0140
+#define REV_ID_MAJOR_QCA9533_V2		0x0160
 #define REV_ID_MAJOR_QCA9556		0x0130
 #define REV_ID_MAJOR_QCA9558		0x1130
+#define REV_ID_MAJOR_TP9343		0x0150
+#define REV_ID_MAJOR_QCA956X		0x1150
 
 #define AR71XX_REV_ID_MINOR_MASK	0x3
 #define AR71XX_REV_ID_MINOR_AR7130	0x0
@@ -482,8 +885,12 @@
 
 #define AR934X_REV_ID_REVISION_MASK	0xf
 
+#define QCA953X_REV_ID_REVISION_MASK	0xf
+
 #define QCA955X_REV_ID_REVISION_MASK	0xf
 
+#define QCA956X_REV_ID_REVISION_MASK	0xf
+
 /*
  * SPI block
  */
@@ -521,15 +928,63 @@
 #define AR71XX_GPIO_REG_INT_ENABLE	0x24
 #define AR71XX_GPIO_REG_FUNC		0x28
 
+#define AR934X_GPIO_REG_OUT_FUNC0	0x2c
+#define AR934X_GPIO_REG_OUT_FUNC1	0x30
+#define AR934X_GPIO_REG_OUT_FUNC2	0x34
+#define AR934X_GPIO_REG_OUT_FUNC3	0x38
+#define AR934X_GPIO_REG_OUT_FUNC4	0x3c
+#define AR934X_GPIO_REG_OUT_FUNC5	0x40
 #define AR934X_GPIO_REG_FUNC		0x6c
 
+#define QCA953X_GPIO_REG_OUT_FUNC0	0x2c
+#define QCA953X_GPIO_REG_OUT_FUNC1	0x30
+#define QCA953X_GPIO_REG_OUT_FUNC2	0x34
+#define QCA953X_GPIO_REG_OUT_FUNC3	0x38
+#define QCA953X_GPIO_REG_OUT_FUNC4	0x3c
+#define QCA953X_GPIO_REG_IN_ENABLE0	0x44
+#define QCA953X_GPIO_REG_FUNC		0x6c
+
+#define QCA953X_GPIO_OUT_MUX_SPI_CS1		10
+#define QCA953X_GPIO_OUT_MUX_SPI_CS2		11
+#define QCA953X_GPIO_OUT_MUX_SPI_CS0		9
+#define QCA953X_GPIO_OUT_MUX_SPI_CLK		8
+#define QCA953X_GPIO_OUT_MUX_SPI_MOSI		12
+#define QCA953X_GPIO_OUT_MUX_LED_LINK1		41
+#define QCA953X_GPIO_OUT_MUX_LED_LINK2		42
+#define QCA953X_GPIO_OUT_MUX_LED_LINK3		43
+#define QCA953X_GPIO_OUT_MUX_LED_LINK4		44
+#define QCA953X_GPIO_OUT_MUX_LED_LINK5		45
+
+#define QCA955X_GPIO_REG_OUT_FUNC0	0x2c
+#define QCA955X_GPIO_REG_OUT_FUNC1	0x30
+#define QCA955X_GPIO_REG_OUT_FUNC2	0x34
+#define QCA955X_GPIO_REG_OUT_FUNC3	0x38
+#define QCA955X_GPIO_REG_OUT_FUNC4	0x3c
+#define QCA955X_GPIO_REG_OUT_FUNC5	0x40
+#define QCA955X_GPIO_REG_FUNC		0x6c
+
+#define QCA956X_GPIO_REG_OUT_FUNC0	0x2c
+#define QCA956X_GPIO_REG_OUT_FUNC1	0x30
+#define QCA956X_GPIO_REG_OUT_FUNC2	0x34
+#define QCA956X_GPIO_REG_OUT_FUNC3	0x38
+#define QCA956X_GPIO_REG_OUT_FUNC4	0x3c
+#define QCA956X_GPIO_REG_OUT_FUNC5	0x40
+#define QCA956X_GPIO_REG_IN_ENABLE0	0x44
+#define QCA956X_GPIO_REG_IN_ENABLE3	0x50
+#define QCA956X_GPIO_REG_FUNC		0x6c
+
+#define QCA956X_GPIO_OUT_MUX_GE0_MDO	32
+#define QCA956X_GPIO_OUT_MUX_GE0_MDC	33
+
 #define AR71XX_GPIO_COUNT		16
 #define AR7240_GPIO_COUNT		18
 #define AR7241_GPIO_COUNT		20
 #define AR913X_GPIO_COUNT		22
 #define AR933X_GPIO_COUNT		30
 #define AR934X_GPIO_COUNT		23
+#define QCA953X_GPIO_COUNT		18
 #define QCA955X_GPIO_COUNT		24
+#define QCA956X_GPIO_COUNT		23
 
 /*
  * SRIF block
@@ -552,4 +1007,318 @@
 #define AR934X_SRIF_DPLL2_OUTDIV_SHIFT	13
 #define AR934X_SRIF_DPLL2_OUTDIV_MASK	0x7
 
+#define QCA953X_SRIF_CPU_DPLL1_REG	0x1c0
+#define QCA953X_SRIF_CPU_DPLL2_REG	0x1c4
+#define QCA953X_SRIF_CPU_DPLL3_REG	0x1c8
+
+#define QCA953X_SRIF_DDR_DPLL1_REG	0x240
+#define QCA953X_SRIF_DDR_DPLL2_REG	0x244
+#define QCA953X_SRIF_DDR_DPLL3_REG	0x248
+
+#define QCA953X_SRIF_DPLL1_REFDIV_SHIFT	27
+#define QCA953X_SRIF_DPLL1_REFDIV_MASK	0x1f
+#define QCA953X_SRIF_DPLL1_NINT_SHIFT	18
+#define QCA953X_SRIF_DPLL1_NINT_MASK	0x1ff
+#define QCA953X_SRIF_DPLL1_NFRAC_MASK	0x0003ffff
+
+#define QCA953X_SRIF_DPLL2_LOCAL_PLL	BIT(30)
+#define QCA953X_SRIF_DPLL2_OUTDIV_SHIFT	13
+#define QCA953X_SRIF_DPLL2_OUTDIV_MASK	0x7
+
+#define AR71XX_GPIO_FUNC_STEREO_EN		BIT(17)
+#define AR71XX_GPIO_FUNC_SLIC_EN		BIT(16)
+#define AR71XX_GPIO_FUNC_SPI_CS2_EN		BIT(13)
+#define AR71XX_GPIO_FUNC_SPI_CS1_EN		BIT(12)
+#define AR71XX_GPIO_FUNC_UART_EN		BIT(8)
+#define AR71XX_GPIO_FUNC_USB_OC_EN		BIT(4)
+#define AR71XX_GPIO_FUNC_USB_CLK_EN		BIT(0)
+
+#define AR724X_GPIO_FUNC_GE0_MII_CLK_EN		BIT(19)
+#define AR724X_GPIO_FUNC_SPI_EN			BIT(18)
+#define AR724X_GPIO_FUNC_SPI_CS_EN2		BIT(14)
+#define AR724X_GPIO_FUNC_SPI_CS_EN1		BIT(13)
+#define AR724X_GPIO_FUNC_CLK_OBS5_EN		BIT(12)
+#define AR724X_GPIO_FUNC_CLK_OBS4_EN		BIT(11)
+#define AR724X_GPIO_FUNC_CLK_OBS3_EN		BIT(10)
+#define AR724X_GPIO_FUNC_CLK_OBS2_EN		BIT(9)
+#define AR724X_GPIO_FUNC_CLK_OBS1_EN		BIT(8)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED4_EN	BIT(7)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED3_EN	BIT(6)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED2_EN	BIT(5)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED1_EN	BIT(4)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED0_EN	BIT(3)
+#define AR724X_GPIO_FUNC_UART_RTS_CTS_EN	BIT(2)
+#define AR724X_GPIO_FUNC_UART_EN		BIT(1)
+#define AR724X_GPIO_FUNC_JTAG_DISABLE		BIT(0)
+
+#define AR913X_GPIO_FUNC_WMAC_LED_EN		BIT(22)
+#define AR913X_GPIO_FUNC_EXP_PORT_CS_EN		BIT(21)
+#define AR913X_GPIO_FUNC_I2S_REFCLKEN		BIT(20)
+#define AR913X_GPIO_FUNC_I2S_MCKEN		BIT(19)
+#define AR913X_GPIO_FUNC_I2S1_EN		BIT(18)
+#define AR913X_GPIO_FUNC_I2S0_EN		BIT(17)
+#define AR913X_GPIO_FUNC_SLIC_EN		BIT(16)
+#define AR913X_GPIO_FUNC_UART_RTSCTS_EN		BIT(9)
+#define AR913X_GPIO_FUNC_UART_EN		BIT(8)
+#define AR913X_GPIO_FUNC_USB_CLK_EN		BIT(4)
+
+#define AR933X_GPIO_FUNC_SPDIF2TCK		BIT(31)
+#define AR933X_GPIO_FUNC_SPDIF_EN		BIT(30)
+#define AR933X_GPIO_FUNC_I2SO_22_18_EN		BIT(29)
+#define AR933X_GPIO_FUNC_I2S_MCK_EN		BIT(27)
+#define AR933X_GPIO_FUNC_I2SO_EN		BIT(26)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_DUPL	BIT(25)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_COLL	BIT(24)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_ACT	BIT(23)
+#define AR933X_GPIO_FUNC_SPI_EN			BIT(18)
+#define AR933X_GPIO_FUNC_SPI_CS_EN2		BIT(14)
+#define AR933X_GPIO_FUNC_SPI_CS_EN1		BIT(13)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED4_EN	BIT(7)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED3_EN	BIT(6)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED2_EN	BIT(5)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED1_EN	BIT(4)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED0_EN	BIT(3)
+#define AR933X_GPIO_FUNC_UART_RTS_CTS_EN	BIT(2)
+#define AR933X_GPIO_FUNC_UART_EN		BIT(1)
+#define AR933X_GPIO_FUNC_JTAG_DISABLE		BIT(0)
+
+#define AR934X_GPIO_FUNC_CLK_OBS7_EN		BIT(9)
+#define AR934X_GPIO_FUNC_CLK_OBS6_EN		BIT(8)
+#define AR934X_GPIO_FUNC_CLK_OBS5_EN		BIT(7)
+#define AR934X_GPIO_FUNC_CLK_OBS4_EN		BIT(6)
+#define AR934X_GPIO_FUNC_CLK_OBS3_EN		BIT(5)
+#define AR934X_GPIO_FUNC_CLK_OBS2_EN		BIT(4)
+#define AR934X_GPIO_FUNC_CLK_OBS1_EN		BIT(3)
+#define AR934X_GPIO_FUNC_CLK_OBS0_EN		BIT(2)
+#define AR934X_GPIO_FUNC_JTAG_DISABLE		BIT(1)
+
+#define AR934X_GPIO_OUT_GPIO		0
+#define AR934X_GPIO_OUT_SPI_CS1	7
+#define AR934X_GPIO_OUT_LED_LINK0	41
+#define AR934X_GPIO_OUT_LED_LINK1	42
+#define AR934X_GPIO_OUT_LED_LINK2	43
+#define AR934X_GPIO_OUT_LED_LINK3	44
+#define AR934X_GPIO_OUT_LED_LINK4	45
+#define AR934X_GPIO_OUT_EXT_LNA0	46
+#define AR934X_GPIO_OUT_EXT_LNA1	47
+
+#define QCA955X_GPIO_FUNC_CLK_OBS7_EN		BIT(9)
+#define QCA955X_GPIO_FUNC_CLK_OBS6_EN		BIT(8)
+#define QCA955X_GPIO_FUNC_CLK_OBS5_EN		BIT(7)
+#define QCA955X_GPIO_FUNC_CLK_OBS4_EN		BIT(6)
+#define QCA955X_GPIO_FUNC_CLK_OBS3_EN		BIT(5)
+#define QCA955X_GPIO_FUNC_CLK_OBS2_EN		BIT(4)
+#define QCA955X_GPIO_FUNC_CLK_OBS1_EN		BIT(3)
+#define QCA955X_GPIO_FUNC_JTAG_DISABLE		BIT(1)
+
+#define QCA955X_GPIO_OUT_GPIO		0
+#define QCA955X_MII_EXT_MDI		1
+#define QCA955X_SLIC_DATA_OUT		3
+#define QCA955X_SLIC_PCM_FS		4
+#define QCA955X_SLIC_PCM_CLK		5
+#define QCA955X_SPI_CLK			8
+#define QCA955X_SPI_CS_0		9
+#define QCA955X_SPI_CS_1		10
+#define QCA955X_SPI_CS_2		11
+#define QCA955X_SPI_MISO		12
+#define QCA955X_I2S_CLK			13
+#define QCA955X_I2S_WS			14
+#define QCA955X_I2S_SD			15
+#define QCA955X_I2S_MCK			16
+#define QCA955X_SPDIF_OUT		17
+#define QCA955X_UART1_TD		18
+#define QCA955X_UART1_RTS		19
+#define QCA955X_UART1_RD		20
+#define QCA955X_UART1_CTS		21
+#define QCA955X_UART0_SOUT		22
+#define QCA955X_SPDIF2_OUT		23
+#define QCA955X_LED_SGMII_SPEED0	24
+#define QCA955X_LED_SGMII_SPEED1	25
+#define QCA955X_LED_SGMII_DUPLEX	26
+#define QCA955X_LED_SGMII_LINK_UP	27
+#define QCA955X_SGMII_SPEED0_INVERT	28
+#define QCA955X_SGMII_SPEED1_INVERT	29
+#define QCA955X_SGMII_DUPLEX_INVERT	30
+#define QCA955X_SGMII_LINK_UP_INVERT	31
+#define QCA955X_GE1_MII_MDO		32
+#define QCA955X_GE1_MII_MDC		33
+#define QCA955X_SWCOM2			38
+#define QCA955X_SWCOM3			39
+#define QCA955X_MAC2_GPIO		40
+#define QCA955X_MAC3_GPIO		41
+#define QCA955X_ATT_LED			42
+#define QCA955X_PWR_LED			43
+#define QCA955X_TX_FRAME		44
+#define QCA955X_RX_CLEAR_EXTERNAL	45
+#define QCA955X_LED_NETWORK_EN		46
+#define QCA955X_LED_POWER_EN		47
+#define QCA955X_WMAC_GLUE_WOW		68
+#define QCA955X_RX_CLEAR_EXTENSION	70
+#define QCA955X_CP_NAND_CS1		73
+#define QCA955X_USB_SUSPEND		74
+#define QCA955X_ETH_TX_ERR		75
+#define QCA955X_DDR_DQ_OE		76
+#define QCA955X_CLKREQ_N_EP		77
+#define QCA955X_CLKREQ_N_RC		78
+#define QCA955X_CLK_OBS0		79
+#define QCA955X_CLK_OBS1		80
+#define QCA955X_CLK_OBS2		81
+#define QCA955X_CLK_OBS3		82
+#define QCA955X_CLK_OBS4		83
+#define QCA955X_CLK_OBS5		84
+
+/*
+ * MII_CTRL block
+ */
+#define AR71XX_MII_REG_MII0_CTRL	0x00
+#define AR71XX_MII_REG_MII1_CTRL	0x04
+
+#define AR71XX_MII_CTRL_IF_MASK		3
+#define AR71XX_MII_CTRL_SPEED_SHIFT	4
+#define AR71XX_MII_CTRL_SPEED_MASK	3
+#define AR71XX_MII_CTRL_SPEED_10	0
+#define AR71XX_MII_CTRL_SPEED_100	1
+#define AR71XX_MII_CTRL_SPEED_1000	2
+
+#define AR71XX_MII0_CTRL_IF_GMII	0
+#define AR71XX_MII0_CTRL_IF_MII		1
+#define AR71XX_MII0_CTRL_IF_RGMII	2
+#define AR71XX_MII0_CTRL_IF_RMII	3
+
+#define AR71XX_MII1_CTRL_IF_RGMII	0
+#define AR71XX_MII1_CTRL_IF_RMII	1
+
+/*
+ * AR933X GMAC interface
+ */
+#define AR933X_GMAC_REG_ETH_CFG		0x00
+
+#define AR933X_ETH_CFG_RGMII_GE0	BIT(0)
+#define AR933X_ETH_CFG_MII_GE0		BIT(1)
+#define AR933X_ETH_CFG_GMII_GE0		BIT(2)
+#define AR933X_ETH_CFG_MII_GE0_MASTER	BIT(3)
+#define AR933X_ETH_CFG_MII_GE0_SLAVE	BIT(4)
+#define AR933X_ETH_CFG_MII_GE0_ERR_EN	BIT(5)
+#define AR933X_ETH_CFG_SW_PHY_SWAP	BIT(7)
+#define AR933X_ETH_CFG_SW_PHY_ADDR_SWAP	BIT(8)
+#define AR933X_ETH_CFG_RMII_GE0		BIT(9)
+#define AR933X_ETH_CFG_RMII_GE0_SPD_10	0
+#define AR933X_ETH_CFG_RMII_GE0_SPD_100	BIT(10)
+
+/*
+ * AR934X GMAC Interface
+ */
+#define AR934X_GMAC_REG_ETH_CFG		0x00
+
+#define AR934X_ETH_CFG_RGMII_GMAC0	BIT(0)
+#define AR934X_ETH_CFG_MII_GMAC0	BIT(1)
+#define AR934X_ETH_CFG_GMII_GMAC0	BIT(2)
+#define AR934X_ETH_CFG_MII_GMAC0_MASTER	BIT(3)
+#define AR934X_ETH_CFG_MII_GMAC0_SLAVE	BIT(4)
+#define AR934X_ETH_CFG_MII_GMAC0_ERR_EN	BIT(5)
+#define AR934X_ETH_CFG_SW_ONLY_MODE	BIT(6)
+#define AR934X_ETH_CFG_SW_PHY_SWAP	BIT(7)
+#define AR934X_ETH_CFG_SW_APB_ACCESS	BIT(9)
+#define AR934X_ETH_CFG_RMII_GMAC0	BIT(10)
+#define AR933X_ETH_CFG_MII_CNTL_SPEED	BIT(11)
+#define AR934X_ETH_CFG_RMII_GMAC0_MASTER BIT(12)
+#define AR933X_ETH_CFG_SW_ACC_MSB_FIRST	BIT(13)
+#define AR934X_ETH_CFG_RXD_DELAY        BIT(14)
+#define AR934X_ETH_CFG_RXD_DELAY_MASK   0x3
+#define AR934X_ETH_CFG_RXD_DELAY_SHIFT  14
+#define AR934X_ETH_CFG_RDV_DELAY        BIT(16)
+#define AR934X_ETH_CFG_RDV_DELAY_MASK   0x3
+#define AR934X_ETH_CFG_RDV_DELAY_SHIFT  16
+
+/*
+ * QCA953X GMAC Interface
+ */
+#define QCA953X_GMAC_REG_ETH_CFG		0x00
+
+#define QCA953X_ETH_CFG_SW_ONLY_MODE		BIT(6)
+#define QCA953X_ETH_CFG_SW_PHY_SWAP		BIT(7)
+#define QCA953X_ETH_CFG_SW_APB_ACCESS		BIT(9)
+#define QCA953X_ETH_CFG_SW_ACC_MSB_FIRST	BIT(13)
+
+/*
+ * QCA955X GMAC Interface
+ */
+
+#define QCA955X_GMAC_REG_ETH_CFG	0x00
+#define QCA955X_GMAC_REG_SGMII_SERDES	0x18
+
+#define QCA955X_ETH_CFG_RGMII_EN	BIT(0)
+#define QCA955X_ETH_CFG_MII_GE0		BIT(1)
+#define QCA955X_ETH_CFG_GMII_GE0	BIT(2)
+#define QCA955X_ETH_CFG_MII_GE0_MASTER	BIT(3)
+#define QCA955X_ETH_CFG_MII_GE0_SLAVE	BIT(4)
+#define QCA955X_ETH_CFG_GE0_ERR_EN	BIT(5)
+#define QCA955X_ETH_CFG_GE0_SGMII	BIT(6)
+#define QCA955X_ETH_CFG_RMII_GE0	BIT(10)
+#define QCA955X_ETH_CFG_MII_CNTL_SPEED	BIT(11)
+#define QCA955X_ETH_CFG_RMII_GE0_MASTER	BIT(12)
+#define QCA955X_ETH_CFG_RXD_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_RXD_DELAY_SHIFT	14
+#define QCA955X_ETH_CFG_RDV_DELAY	BIT(16)
+#define QCA955X_ETH_CFG_RDV_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_RDV_DELAY_SHIFT	16
+#define QCA955X_ETH_CFG_TXD_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_TXD_DELAY_SHIFT	18
+#define QCA955X_ETH_CFG_TXE_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_TXE_DELAY_SHIFT	20
+
+#define QCA955X_SGMII_SERDES_LOCK_DETECT_STATUS	BIT(15)
+#define QCA955X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23
+#define QCA955X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf
+/*
+ * QCA956X GMAC Interface
+ */
+
+#define QCA956X_GMAC_REG_ETH_CFG	0x00
+#define QCA956X_GMAC_REG_SGMII_RESET	0x14
+#define QCA956X_GMAC_REG_SGMII_SERDES	0x18
+#define QCA956X_GMAC_REG_MR_AN_CONTROL	0x1c
+#define QCA956X_GMAC_REG_SGMII_CONFIG	0x34
+#define QCA956X_GMAC_REG_SGMII_DEBUG	0x58
+
+#define QCA956X_ETH_CFG_RGMII_EN		BIT(0)
+#define QCA956X_ETH_CFG_GE0_SGMII		BIT(6)
+#define QCA956X_ETH_CFG_SW_ONLY_MODE		BIT(7)
+#define QCA956X_ETH_CFG_SW_PHY_SWAP		BIT(8)
+#define QCA956X_ETH_CFG_SW_PHY_ADDR_SWAP	BIT(9)
+#define QCA956X_ETH_CFG_SW_APB_ACCESS		BIT(10)
+#define QCA956X_ETH_CFG_SW_ACC_MSB_FIRST	BIT(13)
+#define QCA956X_ETH_CFG_RXD_DELAY_MASK		0x3
+#define QCA956X_ETH_CFG_RXD_DELAY_SHIFT		14
+#define QCA956X_ETH_CFG_RDV_DELAY_MASK		0x3
+#define QCA956X_ETH_CFG_RDV_DELAY_SHIFT		16
+
+#define QCA956X_SGMII_RESET_RX_CLK_N_RESET	0x0
+#define QCA956X_SGMII_RESET_RX_CLK_N		BIT(0)
+#define QCA956X_SGMII_RESET_TX_CLK_N		BIT(1)
+#define QCA956X_SGMII_RESET_RX_125M_N		BIT(2)
+#define QCA956X_SGMII_RESET_TX_125M_N		BIT(3)
+#define QCA956X_SGMII_RESET_HW_RX_125M_N	BIT(4)
+
+#define QCA956X_SGMII_SERDES_CDR_BW_MASK	0x3
+#define QCA956X_SGMII_SERDES_CDR_BW_SHIFT	1
+#define QCA956X_SGMII_SERDES_TX_DR_CTRL_MASK	0x7
+#define QCA956X_SGMII_SERDES_TX_DR_CTRL_SHIFT	4
+#define QCA956X_SGMII_SERDES_PLL_BW		BIT(8)
+#define QCA956X_SGMII_SERDES_VCO_FAST		BIT(9)
+#define QCA956X_SGMII_SERDES_VCO_SLOW		BIT(10)
+#define QCA956X_SGMII_SERDES_LOCK_DETECT_STATUS	BIT(15)
+#define QCA956X_SGMII_SERDES_EN_SIGNAL_DETECT	BIT(16)
+#define QCA956X_SGMII_SERDES_FIBER_SDO		BIT(17)
+#define QCA956X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23
+#define QCA956X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf
+#define QCA956X_SGMII_SERDES_VCO_REG_SHIFT	27
+#define QCA956X_SGMII_SERDES_VCO_REG_MASK	0xf
+
+#define QCA956X_MR_AN_CONTROL_AN_ENABLE		BIT(12)
+#define QCA956X_MR_AN_CONTROL_PHY_RESET		BIT(15)
+
+#define QCA956X_SGMII_CONFIG_MODE_CTRL_SHIFT	0
+#define QCA956X_SGMII_CONFIG_MODE_CTRL_MASK	0x7
+
 #endif /* __ASM_MACH_AR71XX_REGS_H */
diff --git a/arch/mips/include/asm/mach-ath79/ath79.h b/arch/mips/include/asm/mach-ath79/ath79.h
index 441faa92c3cd..73dcd63b8243 100644
--- a/arch/mips/include/asm/mach-ath79/ath79.h
+++ b/arch/mips/include/asm/mach-ath79/ath79.h
@@ -32,8 +32,11 @@ enum ath79_soc_type {
 	ATH79_SOC_AR9341,
 	ATH79_SOC_AR9342,
 	ATH79_SOC_AR9344,
+	ATH79_SOC_QCA9533,
 	ATH79_SOC_QCA9556,
 	ATH79_SOC_QCA9558,
+	ATH79_SOC_TP9343,
+	ATH79_SOC_QCA956X,
 };
 
 extern enum ath79_soc_type ath79_soc;
@@ -100,6 +103,16 @@ static inline int soc_is_ar934x(void)
 	return soc_is_ar9341() || soc_is_ar9342() || soc_is_ar9344();
 }
 
+static inline int soc_is_qca9533(void)
+{
+	return ath79_soc == ATH79_SOC_QCA9533;
+}
+
+static inline int soc_is_qca953x(void)
+{
+	return soc_is_qca9533();
+}
+
 static inline int soc_is_qca9556(void)
 {
 	return ath79_soc == ATH79_SOC_QCA9556;
@@ -115,6 +128,26 @@ static inline int soc_is_qca955x(void)
 	return soc_is_qca9556() || soc_is_qca9558();
 }
 
+static inline int soc_is_tp9343(void)
+{
+	return ath79_soc == ATH79_SOC_TP9343;
+}
+
+static inline int soc_is_qca9561(void)
+{
+	return ath79_soc == ATH79_SOC_QCA956X;
+}
+
+static inline int soc_is_qca9563(void)
+{
+	return ath79_soc == ATH79_SOC_QCA956X;
+}
+
+static inline int soc_is_qca956x(void)
+{
+	return soc_is_qca9561() || soc_is_qca9563();
+}
+
 void ath79_ddr_wb_flush(unsigned int reg);
 void ath79_ddr_set_pci_windows(void);
 
@@ -134,6 +167,7 @@ static inline u32 ath79_pll_rr(unsigned reg)
 static inline void ath79_reset_wr(unsigned reg, u32 val)
 {
 	__raw_writel(val, ath79_reset_base + reg);
+	(void) __raw_readl(ath79_reset_base + reg); /* flush */
 }
 
 static inline u32 ath79_reset_rr(unsigned reg)
diff --git a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
index 0089a740e5ae..026ad90c8ac0 100644
--- a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
@@ -36,6 +36,7 @@
 #define cpu_has_mdmx		0
 #define cpu_has_mips3d		0
 #define cpu_has_smartmips	0
+#define cpu_has_rixi		0
 
 #define cpu_has_mips32r1	1
 #define cpu_has_mips32r2	1
@@ -43,6 +44,7 @@
 #define cpu_has_mips64r2	0
 
 #define cpu_has_mipsmt		0
+#define cpu_has_userlocal	0
 
 #define cpu_has_64bits		0
 #define cpu_has_64bit_zero_reg	0
@@ -51,5 +53,9 @@
 
 #define cpu_dcache_line_size()	32
 #define cpu_icache_line_size()	32
+#define cpu_has_vtag_icache	0
+#define cpu_has_dc_aliases	1
+#define cpu_has_ic_fills_f_dc	0
+#define cpu_has_pindexed_dcache	0
 
 #endif /* __ASM_MACH_ATH79_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-bmips/dma-coherence.h b/arch/mips/include/asm/mach-bmips/dma-coherence.h
deleted file mode 100644
index d29781f02285..000000000000
--- a/arch/mips/include/asm/mach-bmips/dma-coherence.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2009 Broadcom Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#ifndef __ASM_MACH_BMIPS_DMA_COHERENCE_H
-#define __ASM_MACH_BMIPS_DMA_COHERENCE_H
-
-#include <asm/bmips.h>
-#include <asm/cpu-type.h>
-#include <asm/cpu.h>
-
-struct device;
-
-extern dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size);
-extern dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page);
-extern unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr);
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;
-}
-
-#define plat_post_dma_flush	bmips_post_dma_flush
-
-#endif /* __ASM_MACH_BMIPS_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
deleted file mode 100644
index 6eb1ee548b11..000000000000
--- a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- *
- * Similar to mach-generic/dma-coherence.h except
- * plat_device_is_coherent hard coded to return 1.
- *
- */
-#ifndef __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
-#define __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
-
-#include <linux/bug.h>
-
-struct device;
-
-extern void octeon_pci_dma_init(void);
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	BUG();
-	return 0;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	BUG();
-	return 0;
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	BUG();
-	return 0;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-	BUG();
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	BUG();
-	return 0;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
-
-struct dma_map_ops;
-extern const struct dma_map_ops *octeon_pci_dma_map_ops;
-extern char *octeon_swiotlb;
-
-#endif /* __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-generic/dma-coherence.h b/arch/mips/include/asm/mach-generic/dma-coherence.h
deleted file mode 100644
index 8ad7a40ca786..000000000000
--- a/arch/mips/include/asm/mach-generic/dma-coherence.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_GENERIC_DMA_COHERENCE_H
-#define __ASM_MACH_GENERIC_DMA_COHERENCE_H
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	return virt_to_phys(addr);
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	return page_to_phys(page);
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return dma_addr;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_PERDEV_COHERENT
-	return dev->archdata.dma_coherent;
-#else
-	switch (coherentio) {
-	default:
-	case IO_COHERENCE_DEFAULT:
-		return hw_coherentio;
-	case IO_COHERENCE_ENABLED:
-		return 1;
-	case IO_COHERENCE_DISABLED:
-		return 0;
-	}
-#endif
-}
-
-#ifndef plat_post_dma_flush
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-#endif
-
-#endif /* __ASM_MACH_GENERIC_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-generic/kmalloc.h b/arch/mips/include/asm/mach-generic/kmalloc.h
index 74207c7bd00d..649a98338886 100644
--- a/arch/mips/include/asm/mach-generic/kmalloc.h
+++ b/arch/mips/include/asm/mach-generic/kmalloc.h
@@ -2,8 +2,7 @@
 #ifndef __ASM_MACH_GENERIC_KMALLOC_H
 #define __ASM_MACH_GENERIC_KMALLOC_H
 
-
-#ifndef CONFIG_DMA_COHERENT
+#ifdef CONFIG_DMA_NONCOHERENT
 /*
  * Total overkill for most systems but need as a safe default.
  * Set this one if any device in the system might do non-coherent DMA.
diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h
index 952b0fdfda0e..ee5ebe98f6cf 100644
--- a/arch/mips/include/asm/mach-generic/spaces.h
+++ b/arch/mips/include/asm/mach-generic/spaces.h
@@ -17,9 +17,13 @@
 /*
  * This gives the physical RAM offset.
  */
-#ifndef PHYS_OFFSET
-#define PHYS_OFFSET		_AC(0, UL)
-#endif
+#ifndef __ASSEMBLY__
+# if defined(CONFIG_MIPS_AUTO_PFN_OFFSET)
+#  define PHYS_OFFSET		((unsigned long)PFN_PHYS(ARCH_PFN_OFFSET))
+# elif !defined(PHYS_OFFSET)
+#  define PHYS_OFFSET		_AC(0, UL)
+# endif
+#endif /* __ASSEMBLY__ */
 
 #ifdef CONFIG_32BIT
 #ifdef CONFIG_KVM_GUEST
diff --git a/arch/mips/include/asm/mach-ip27/dma-coherence.h b/arch/mips/include/asm/mach-ip27/dma-coherence.h
deleted file mode 100644
index 04d862020ac9..000000000000
--- a/arch/mips/include/asm/mach-ip27/dma-coherence.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_IP27_DMA_COHERENCE_H
-#define __ASM_MACH_IP27_DMA_COHERENCE_H
-
-#include <asm/pci/bridge.h>
-
-#define pdev_to_baddr(pdev, addr) \
-	(BRIDGE_CONTROLLER(pdev->bus)->baddr + (addr))
-#define dev_to_baddr(dev, addr) \
-	pdev_to_baddr(to_pci_dev(dev), (addr))
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	dma_addr_t pa = dev_to_baddr(dev, virt_to_phys(addr));
-
-	return pa;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	dma_addr_t pa = dev_to_baddr(dev, page_to_phys(page));
-
-	return pa;
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return dma_addr & ~(0xffUL << 56);
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 1;		/* IP27 non-coherent mode is unsupported */
-}
-
-#endif /* __ASM_MACH_IP27_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-ip32/dma-coherence.h b/arch/mips/include/asm/mach-ip32/dma-coherence.h
deleted file mode 100644
index 7bdf212587a0..000000000000
--- a/arch/mips/include/asm/mach-ip32/dma-coherence.h
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_IP32_DMA_COHERENCE_H
-#define __ASM_MACH_IP32_DMA_COHERENCE_H
-
-#include <asm/ip32/crime.h>
-
-struct device;
-
-/*
- * Few notes.
- * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M
- * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for
- *    native-endian)
- * 3. All other devices see memory as one big chunk at 0x40000000
- * 4. Non-PCI devices will pass NULL as struct device*
- *
- * Thus we translate differently, depending on device.
- */
-
-#define RAM_OFFSET_MASK 0x3fffffffUL
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	dma_addr_t pa = virt_to_phys(addr) & RAM_OFFSET_MASK;
-
-	if (dev == NULL)
-		pa += CRIME_HI_MEM_BASE;
-
-	return pa;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	dma_addr_t pa;
-
-	pa = page_to_phys(page) & RAM_OFFSET_MASK;
-
-	if (dev == NULL)
-		pa += CRIME_HI_MEM_BASE;
-
-	return pa;
-}
-
-/* This is almost certainly wrong but it's what dma-ip32.c used to use	*/
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	unsigned long addr = dma_addr & RAM_OFFSET_MASK;
-
-	if (dma_addr >= 256*1024*1024)
-		addr += CRIME_HI_MEM_BASE;
-
-	return addr;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;		/* IP32 is non-coherent */
-}
-
-#endif /* __ASM_MACH_IP32_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-jazz/dma-coherence.h b/arch/mips/include/asm/mach-jazz/dma-coherence.h
deleted file mode 100644
index dc347c25c343..000000000000
--- a/arch/mips/include/asm/mach-jazz/dma-coherence.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- */
-#ifndef __ASM_MACH_JAZZ_DMA_COHERENCE_H
-#define __ASM_MACH_JAZZ_DMA_COHERENCE_H
-
-#include <asm/jazzdma.h>
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
-	return vdma_alloc(virt_to_phys(addr), size);
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	return vdma_alloc(page_to_phys(page), PAGE_SIZE);
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return vdma_log2phys(dma_addr);
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-	vdma_free(dma_addr);
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;
-}
-
-#endif /* __ASM_MACH_JAZZ_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-loongson64/dma-coherence.h b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
deleted file mode 100644
index 64fc44dec0a8..000000000000
--- a/arch/mips/include/asm/mach-loongson64/dma-coherence.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006, 07  Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology
- * Author: Fuxin Zhang, zhangfx@lemote.com
- *
- */
-#ifndef __ASM_MACH_LOONGSON64_DMA_COHERENCE_H
-#define __ASM_MACH_LOONGSON64_DMA_COHERENCE_H
-
-#ifdef CONFIG_SWIOTLB
-#include <linux/swiotlb.h>
-#endif
-
-struct device;
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-extern dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-extern phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-					  size_t size)
-{
-#ifdef CONFIG_CPU_LOONGSON3
-	return __phys_to_dma(dev, virt_to_phys(addr));
-#else
-	return virt_to_phys(addr) | 0x80000000;
-#endif
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-					       struct page *page)
-{
-#ifdef CONFIG_CPU_LOONGSON3
-	return __phys_to_dma(dev, page_to_phys(page));
-#else
-	return page_to_phys(page) | 0x80000000;
-#endif
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-#if defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_64BIT)
-	return __dma_to_phys(dev, dma_addr);
-#elif defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
-	return (dma_addr > 0x8fffffff) ? dma_addr : (dma_addr & 0x0fffffff);
-#else
-	return dma_addr & 0x7fffffff;
-#endif
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_NONCOHERENT
-	return 0;
-#else
-	return 1;
-#endif /* CONFIG_DMA_NONCOHERENT */
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-#endif /* __ASM_MACH_LOONGSON64_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
index 8393bc548987..312739117bb0 100644
--- a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
@@ -19,18 +19,18 @@
 	.set	push
 	.set	mips64
 	/* Set LPA on LOONGSON3 config3 */
-	mfc0	t0, $16, 3
+	mfc0	t0, CP0_CONFIG3
 	or	t0, (0x1 << 7)
-	mtc0	t0, $16, 3
+	mtc0	t0, CP0_CONFIG3
 	/* Set ELPA on LOONGSON3 pagegrain */
-	mfc0	t0, $5, 1
+	mfc0	t0, CP0_PAGEGRAIN
 	or	t0, (0x1 << 29)
-	mtc0	t0, $5, 1
+	mtc0	t0, CP0_PAGEGRAIN
 #ifdef CONFIG_LOONGSON3_ENHANCEMENT
 	/* Enable STFill Buffer */
-	mfc0	t0, $16, 6
+	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
-	mtc0	t0, $16, 6
+	mtc0	t0, CP0_CONFIG6
 #endif
 	_ehb
 	.set	pop
@@ -45,18 +45,18 @@
 	.set	push
 	.set	mips64
 	/* Set LPA on LOONGSON3 config3 */
-	mfc0	t0, $16, 3
+	mfc0	t0, CP0_CONFIG3
 	or	t0, (0x1 << 7)
-	mtc0	t0, $16, 3
+	mtc0	t0, CP0_CONFIG3
 	/* Set ELPA on LOONGSON3 pagegrain */
-	mfc0	t0, $5, 1
+	mfc0	t0, CP0_PAGEGRAIN
 	or	t0, (0x1 << 29)
-	mtc0	t0, $5, 1
+	mtc0	t0, CP0_PAGEGRAIN
 #ifdef CONFIG_LOONGSON3_ENHANCEMENT
 	/* Enable STFill Buffer */
-	mfc0	t0, $16, 6
+	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
-	mtc0	t0, $16, 6
+	mtc0	t0, CP0_CONFIG6
 #endif
 	_ehb
 	.set	pop
diff --git a/arch/mips/include/asm/mach-pic32/spaces.h b/arch/mips/include/asm/mach-pic32/spaces.h
index 046a0a9aa8b3..a1b9783b76ea 100644
--- a/arch/mips/include/asm/mach-pic32/spaces.h
+++ b/arch/mips/include/asm/mach-pic32/spaces.h
@@ -16,7 +16,6 @@
 
 #ifdef CONFIG_PIC32MZDA
 #define PHYS_OFFSET	_AC(0x08000000, UL)
-#define UNCAC_BASE	_AC(0xa8000000, UL)
 #endif
 
 #include <asm/mach-generic/spaces.h>
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index ae461d91cd1f..01df9ad62fb8 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -16,6 +16,7 @@
 #include <linux/linkage.h>
 #include <linux/types.h>
 #include <asm/hazards.h>
+#include <asm/isa-rev.h>
 #include <asm/war.h>
 
 /*
@@ -51,6 +52,7 @@
 #define CP0_GLOBALNUMBER $3, 1
 #define CP0_CONTEXT $4
 #define CP0_PAGEMASK $5
+#define CP0_PAGEGRAIN $5, 1
 #define CP0_SEGCTL0 $5, 2
 #define CP0_SEGCTL1 $5, 3
 #define CP0_SEGCTL2 $5, 4
@@ -77,6 +79,7 @@
 #define CP0_CONFIG $16
 #define CP0_CONFIG3 $16, 3
 #define CP0_CONFIG5 $16, 5
+#define CP0_CONFIG6 $16, 6
 #define CP0_LLADDR $17
 #define CP0_WATCHLO $18
 #define CP0_WATCHHI $19
@@ -1481,32 +1484,38 @@ do {									\
 
 #define __write_64bit_c0_split(source, sel, val)			\
 do {									\
-	unsigned long long __tmp;					\
+	unsigned long long __tmp = (val);				\
 	unsigned long __flags;						\
 									\
 	local_irq_save(__flags);					\
-	if (sel == 0)							\
+	if (MIPS_ISA_REV >= 2)						\
+		__asm__ __volatile__(					\
+			".set\tpush\n\t"				\
+			".set\t" MIPS_ISA_LEVEL "\n\t"			\
+			"dins\t%L0, %M0, 32, 32\n\t"			\
+			"dmtc0\t%L0, " #source ", " #sel "\n\t"		\
+			".set\tpop"					\
+			: "+r" (__tmp));				\
+	else if (sel == 0)						\
 		__asm__ __volatile__(					\
 			".set\tmips64\n\t"				\
-			"dsll\t%L0, %L1, 32\n\t"			\
+			"dsll\t%L0, %L0, 32\n\t"			\
 			"dsrl\t%L0, %L0, 32\n\t"			\
-			"dsll\t%M0, %M1, 32\n\t"			\
+			"dsll\t%M0, %M0, 32\n\t"			\
 			"or\t%L0, %L0, %M0\n\t"				\
 			"dmtc0\t%L0, " #source "\n\t"			\
 			".set\tmips0"					\
-			: "=&r,r" (__tmp)				\
-			: "r,0" (val));					\
+			: "+r" (__tmp));				\
 	else								\
 		__asm__ __volatile__(					\
 			".set\tmips64\n\t"				\
-			"dsll\t%L0, %L1, 32\n\t"			\
+			"dsll\t%L0, %L0, 32\n\t"			\
 			"dsrl\t%L0, %L0, 32\n\t"			\
-			"dsll\t%M0, %M1, 32\n\t"			\
+			"dsll\t%M0, %M0, 32\n\t"			\
 			"or\t%L0, %L0, %M0\n\t"				\
 			"dmtc0\t%L0, " #source ", " #sel "\n\t"		\
 			".set\tmips0"					\
-			: "=&r,r" (__tmp)				\
-			: "r,0" (val));					\
+			: "+r" (__tmp));				\
 	local_irq_restore(__flags);					\
 } while (0)
 
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index da2004cef2d5..b509371a6b0c 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -126,8 +126,6 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	for_each_possible_cpu(i)
 		cpu_context(i, mm) = 0;
 
-	atomic_set(&mm->context.fp_mode_switching, 0);
-
 	mm->context.bd_emupage_allocmap = NULL;
 	spin_lock_init(&mm->context.bd_emupage_lock);
 	init_waitqueue_head(&mm->context.bd_emupage_queue);
diff --git a/arch/mips/include/asm/netlogic/xlr/fmn.h b/arch/mips/include/asm/netlogic/xlr/fmn.h
index 5604db3d1836..d79c68fa78d9 100644
--- a/arch/mips/include/asm/netlogic/xlr/fmn.h
+++ b/arch/mips/include/asm/netlogic/xlr/fmn.h
@@ -301,8 +301,6 @@ static inline int nlm_fmn_send(unsigned int size, unsigned int code,
 	for (i = 0; i < 8; i++) {
 		nlm_msgsnd(dest);
 		status = nlm_read_c2_status0();
-		if ((status & 0x2) == 1)
-			pr_info("Send pending fail!\n");
 		if ((status & 0x4) == 0)
 			return 0;
 	}
diff --git a/arch/mips/include/asm/octeon/cvmx-asxx-defs.h b/arch/mips/include/asm/octeon/cvmx-asxx-defs.h
index a1e21a3854cf..1eef155979f3 100644
--- a/arch/mips/include/asm/octeon/cvmx-asxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-asxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -55,6 +55,8 @@
 #define CVMX_ASXX_TX_HI_WATERX(offset, block_id) (CVMX_ADD_IO_SEG(0x00011800B0000080ull) + (((offset) & 3) + ((block_id) & 1) * 0x1000000ull) * 8)
 #define CVMX_ASXX_TX_PRT_EN(block_id) (CVMX_ADD_IO_SEG(0x00011800B0000008ull) + ((block_id) & 1) * 0x8000000ull)
 
+void __cvmx_interrupt_asxx_enable(int block);
+
 union cvmx_asxx_gmii_rx_clk_set {
 	uint64_t u64;
 	struct cvmx_asxx_gmii_rx_clk_set_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
index 6e61792d9248..1d18be8cdddc 100644
--- a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
@@ -1,10014 +1,176 @@
-/***********************license start***************
- * Author: Cavium Networks
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Octeon CIU definitions
  *
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2012 Cavium Networks
- *
- * This file 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 file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
+ * Copyright (C) 2003-2018 Cavium, Inc.
+ */
 
 #ifndef __CVMX_CIU_DEFS_H__
 #define __CVMX_CIU_DEFS_H__
 
-#define CVMX_CIU_BIST (CVMX_ADD_IO_SEG(0x0001070000000730ull))
-#define CVMX_CIU_BLOCK_INT (CVMX_ADD_IO_SEG(0x00010700000007C0ull))
-#define CVMX_CIU_DINT (CVMX_ADD_IO_SEG(0x0001070000000720ull))
-#define CVMX_CIU_EN2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x000107000000A600ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_IOX_INT_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CE00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_IOX_INT_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AE00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x000107000000A000ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP2_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000C800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP2_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000A800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x000107000000A200ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CA00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AA00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x000107000000A400ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CC00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AC00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_FUSE (CVMX_ADD_IO_SEG(0x0001070000000728ull))
-#define CVMX_CIU_GSTOP (CVMX_ADD_IO_SEG(0x0001070000000710ull))
-#define CVMX_CIU_INT33_SUM0 (CVMX_ADD_IO_SEG(0x0001070000000110ull))
-#define CVMX_CIU_INTX_EN0(offset) (CVMX_ADD_IO_SEG(0x0001070000000200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1(offset) (CVMX_ADD_IO_SEG(0x0001070000000208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN4_0(offset) (CVMX_ADD_IO_SEG(0x0001070000000C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1(offset) (CVMX_ADD_IO_SEG(0x0001070000000C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_SUM0(offset) (CVMX_ADD_IO_SEG(0x0001070000000000ull) + ((offset) & 63) * 8)
-#define CVMX_CIU_INTX_SUM4(offset) (CVMX_ADD_IO_SEG(0x0001070000000C00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_INT_DBG_SEL (CVMX_ADD_IO_SEG(0x00010700000007D0ull))
-#define CVMX_CIU_INT_SUM1 (CVMX_ADD_IO_SEG(0x0001070000000108ull))
-static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned long offset)
+#include <asm/bitfield.h>
+
+#define CVMX_CIU_ADDR(addr, coreid, coremask, offset)			       \
+	(CVMX_ADD_IO_SEG(0x0001070000000000ull + addr##ull) +		       \
+	(((coreid) & (coremask)) * offset))
+
+#define CVMX_CIU_EN2_PPX_IP4(c)		CVMX_CIU_ADDR(0xA400, c, 0x0F, 8)
+#define CVMX_CIU_EN2_PPX_IP4_W1C(c)	CVMX_CIU_ADDR(0xCC00, c, 0x0F, 8)
+#define CVMX_CIU_EN2_PPX_IP4_W1S(c)	CVMX_CIU_ADDR(0xAC00, c, 0x0F, 8)
+#define CVMX_CIU_FUSE			CVMX_CIU_ADDR(0x0728, 0, 0x00, 0)
+#define CVMX_CIU_INT_SUM1		CVMX_CIU_ADDR(0x0108, 0, 0x00, 0)
+#define CVMX_CIU_INTX_EN0(c)		CVMX_CIU_ADDR(0x0200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN0_W1C(c)	CVMX_CIU_ADDR(0x2200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN0_W1S(c)	CVMX_CIU_ADDR(0x6200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1(c)		CVMX_CIU_ADDR(0x0208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1_W1C(c)	CVMX_CIU_ADDR(0x2208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1_W1S(c)	CVMX_CIU_ADDR(0x6208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_SUM0(c)		CVMX_CIU_ADDR(0x0000, c, 0x3F, 8)
+#define CVMX_CIU_NMI			CVMX_CIU_ADDR(0x0718, 0, 0x00, 0)
+#define CVMX_CIU_PCI_INTA		CVMX_CIU_ADDR(0x0750, 0, 0x00, 0)
+#define CVMX_CIU_PP_BIST_STAT		CVMX_CIU_ADDR(0x07E0, 0, 0x00, 0)
+#define CVMX_CIU_PP_DBG			CVMX_CIU_ADDR(0x0708, 0, 0x00, 0)
+#define CVMX_CIU_PP_RST			CVMX_CIU_ADDR(0x0700, 0, 0x00, 0)
+#define CVMX_CIU_QLM0			CVMX_CIU_ADDR(0x0780, 0, 0x00, 0)
+#define CVMX_CIU_QLM1			CVMX_CIU_ADDR(0x0788, 0, 0x00, 0)
+#define CVMX_CIU_QLM_JTGC		CVMX_CIU_ADDR(0x0768, 0, 0x00, 0)
+#define CVMX_CIU_QLM_JTGD		CVMX_CIU_ADDR(0x0770, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_BIST		CVMX_CIU_ADDR(0x0738, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_PRST1		CVMX_CIU_ADDR(0x0758, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_PRST		CVMX_CIU_ADDR(0x0748, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_RST		CVMX_CIU_ADDR(0x0740, 0, 0x00, 0)
+#define CVMX_CIU_SUM2_PPX_IP4(c)	CVMX_CIU_ADDR(0x8C00, c, 0x0F, 8)
+#define CVMX_CIU_TIM_MULTI_CAST		CVMX_CIU_ADDR(0xC200, 0, 0x00, 0)
+#define CVMX_CIU_TIMX(c)		CVMX_CIU_ADDR(0x0480, c, 0x0F, 8)
+
+static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned int coreid)
 {
-	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100600ull) + (offset) * 8;
-	}
-	return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
+	if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK))
+		return CVMX_CIU_ADDR(0x100100600, coreid, 0x0F, 8);
+	else
+		return CVMX_CIU_ADDR(0x000000680, coreid, 0x0F, 8);
 }
 
-static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned long offset)
+static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned int coreid)
 {
-	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100400ull) + (offset) * 8;
-	}
-	return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
+	if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK))
+		return CVMX_CIU_ADDR(0x100100400, coreid, 0x0F, 8);
+	else
+		return CVMX_CIU_ADDR(0x000000600, coreid, 0x0F, 8);
 }
 
-#define CVMX_CIU_NMI (CVMX_ADD_IO_SEG(0x0001070000000718ull))
-#define CVMX_CIU_PCI_INTA (CVMX_ADD_IO_SEG(0x0001070000000750ull))
-#define CVMX_CIU_PP_BIST_STAT (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
-#define CVMX_CIU_PP_DBG (CVMX_ADD_IO_SEG(0x0001070000000708ull))
-static inline uint64_t CVMX_CIU_PP_POKEX(unsigned long offset)
+static inline uint64_t CVMX_CIU_PP_POKEX(unsigned int coreid)
 {
 	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN70XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
 	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100200ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x100100200, coreid, 0x0F, 8);
 	case OCTEON_CNF75XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN73XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN78XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001010000030000ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x000030000, coreid, 0x0F, 8) -
+			0x60000000000ull;
+	default:
+		return CVMX_CIU_ADDR(0x000000580, coreid, 0x0F, 8);
 	}
-	return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
 }
 
-#define CVMX_CIU_PP_RST (CVMX_ADD_IO_SEG(0x0001070000000700ull))
-#define CVMX_CIU_QLM0 (CVMX_ADD_IO_SEG(0x0001070000000780ull))
-#define CVMX_CIU_QLM1 (CVMX_ADD_IO_SEG(0x0001070000000788ull))
-#define CVMX_CIU_QLM2 (CVMX_ADD_IO_SEG(0x0001070000000790ull))
-#define CVMX_CIU_QLM3 (CVMX_ADD_IO_SEG(0x0001070000000798ull))
-#define CVMX_CIU_QLM4 (CVMX_ADD_IO_SEG(0x00010700000007A0ull))
-#define CVMX_CIU_QLM_DCOK (CVMX_ADD_IO_SEG(0x0001070000000760ull))
-#define CVMX_CIU_QLM_JTGC (CVMX_ADD_IO_SEG(0x0001070000000768ull))
-#define CVMX_CIU_QLM_JTGD (CVMX_ADD_IO_SEG(0x0001070000000770ull))
-#define CVMX_CIU_SOFT_BIST (CVMX_ADD_IO_SEG(0x0001070000000738ull))
-#define CVMX_CIU_SOFT_PRST (CVMX_ADD_IO_SEG(0x0001070000000748ull))
-#define CVMX_CIU_SOFT_PRST1 (CVMX_ADD_IO_SEG(0x0001070000000758ull))
-#define CVMX_CIU_SOFT_PRST2 (CVMX_ADD_IO_SEG(0x00010700000007D8ull))
-#define CVMX_CIU_SOFT_PRST3 (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
-#define CVMX_CIU_SOFT_RST (CVMX_ADD_IO_SEG(0x0001070000000740ull))
-#define CVMX_CIU_SUM1_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008600ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_SUM1_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008000ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM1_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008200ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM1_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008400ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008E00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_SUM2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008A00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008C00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_TIMX(offset) (CVMX_ADD_IO_SEG(0x0001070000000480ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_TIM_MULTI_CAST (CVMX_ADD_IO_SEG(0x000107000000C200ull))
-static inline uint64_t CVMX_CIU_WDOGX(unsigned long offset)
+static inline uint64_t CVMX_CIU_WDOGX(unsigned int coreid)
 {
 	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN70XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
 	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100000ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x100100000, coreid, 0x0F, 8);
 	case OCTEON_CNF75XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN73XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN78XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001010000020000ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x000020000, coreid, 0x0F, 8) -
+			0x60000000000ull;
+	default:
+		return CVMX_CIU_ADDR(0x000000500, coreid, 0x0F, 8);
 	}
-	return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
 }
 
-union cvmx_ciu_bist {
-	uint64_t u64;
-	struct cvmx_ciu_bist_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_7_63:57;
-		uint64_t bist:7;
-#else
-		uint64_t bist:7;
-		uint64_t reserved_7_63:57;
-#endif
-	} s;
-	struct cvmx_ciu_bist_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t bist:4;
-#else
-		uint64_t bist:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_bist_cn30xx cn31xx;
-	struct cvmx_ciu_bist_cn30xx cn38xx;
-	struct cvmx_ciu_bist_cn30xx cn38xxp2;
-	struct cvmx_ciu_bist_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t bist:2;
-#else
-		uint64_t bist:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_bist_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_3_63:61;
-		uint64_t bist:3;
-#else
-		uint64_t bist:3;
-		uint64_t reserved_3_63:61;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_bist_cn52xx cn52xxp1;
-	struct cvmx_ciu_bist_cn30xx cn56xx;
-	struct cvmx_ciu_bist_cn30xx cn56xxp1;
-	struct cvmx_ciu_bist_cn30xx cn58xx;
-	struct cvmx_ciu_bist_cn30xx cn58xxp1;
-	struct cvmx_ciu_bist_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t bist:6;
-#else
-		uint64_t bist:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_bist_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_5_63:59;
-		uint64_t bist:5;
-#else
-		uint64_t bist:5;
-		uint64_t reserved_5_63:59;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_bist_cn63xx cn63xxp1;
-	struct cvmx_ciu_bist_cn61xx cn66xx;
-	struct cvmx_ciu_bist_s cn68xx;
-	struct cvmx_ciu_bist_s cn68xxp1;
-	struct cvmx_ciu_bist_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_block_int {
-	uint64_t u64;
-	struct cvmx_ciu_block_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_62_63:2;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_43_59:17;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t dfm:1;
-		uint64_t reserved_34_39:6;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_31_31:1;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_24_24:1;
-		uint64_t asxpcs1:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t gmx1:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t gmx1:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t asxpcs1:1;
-		uint64_t reserved_24_24:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_31:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t reserved_34_39:6;
-		uint64_t dfm:1;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_59:17;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_63:2;
-#endif
-	} s;
-	struct cvmx_ciu_block_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_43_63:21;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t reserved_31_40:10;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_24_24:1;
-		uint64_t asxpcs1:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t gmx1:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t gmx1:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t asxpcs1:1;
-		uint64_t reserved_24_24:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_40:10;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_63:21;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_block_int_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_43_63:21;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t dfm:1;
-		uint64_t reserved_34_39:6;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_31_31:1;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t reserved_2_2:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t reserved_2_2:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_31:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t reserved_34_39:6;
-		uint64_t dfm:1;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_63:21;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_block_int_cn63xx cn63xxp1;
-	struct cvmx_ciu_block_int_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_62_63:2;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_43_59:17;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t dfm:1;
-		uint64_t reserved_33_39:7;
-		uint64_t srio0:1;
-		uint64_t reserved_31_31:1;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_24_24:1;
-		uint64_t asxpcs1:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t gmx1:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t gmx1:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t asxpcs1:1;
-		uint64_t reserved_24_24:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_31:1;
-		uint64_t srio0:1;
-		uint64_t reserved_33_39:7;
-		uint64_t dfm:1;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_59:17;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_63:2;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_block_int_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_43_63:21;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t reserved_31_40:10;
-		uint64_t iob:1;
-		uint64_t reserved_27_29:3;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_6_8:3;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t reserved_2_2:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t reserved_2_2:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t reserved_6_8:3;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_29:3;
-		uint64_t iob:1;
-		uint64_t reserved_31_40:10;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_63:21;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_dint {
-	uint64_t u64;
-	struct cvmx_ciu_dint_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t dint:32;
-#else
-		uint64_t dint:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_dint_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t dint:1;
-#else
-		uint64_t dint:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_dint_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t dint:2;
-#else
-		uint64_t dint:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_dint_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t dint:16;
-#else
-		uint64_t dint:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_dint_cn38xx cn38xxp2;
-	struct cvmx_ciu_dint_cn31xx cn50xx;
-	struct cvmx_ciu_dint_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t dint:4;
-#else
-		uint64_t dint:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_dint_cn52xx cn52xxp1;
-	struct cvmx_ciu_dint_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t dint:12;
-#else
-		uint64_t dint:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_dint_cn56xx cn56xxp1;
-	struct cvmx_ciu_dint_cn38xx cn58xx;
-	struct cvmx_ciu_dint_cn38xx cn58xxp1;
-	struct cvmx_ciu_dint_cn52xx cn61xx;
-	struct cvmx_ciu_dint_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t dint:6;
-#else
-		uint64_t dint:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_dint_cn63xx cn63xxp1;
-	struct cvmx_ciu_dint_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t dint:10;
-#else
-		uint64_t dint:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_dint_s cn68xx;
-	struct cvmx_ciu_dint_s cn68xxp1;
-	struct cvmx_ciu_dint_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int {
-	uint64_t u64;
-	struct cvmx_ciu_en2_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_iox_int_cn61xx cn66xx;
-	struct cvmx_ciu_en2_iox_int_s cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_iox_int_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_iox_int_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_iox_int_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_iox_int_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_iox_int_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_iox_int_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_iox_int_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_iox_int_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2 {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip2_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip2_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3 {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip3_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip3_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4 {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip4_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip4_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_fuse {
-	uint64_t u64;
-	struct cvmx_ciu_fuse_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t fuse:32;
-#else
-		uint64_t fuse:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_fuse_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t fuse:1;
-#else
-		uint64_t fuse:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_fuse_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t fuse:2;
-#else
-		uint64_t fuse:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_fuse_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t fuse:16;
-#else
-		uint64_t fuse:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_fuse_cn38xx cn38xxp2;
-	struct cvmx_ciu_fuse_cn31xx cn50xx;
-	struct cvmx_ciu_fuse_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t fuse:4;
-#else
-		uint64_t fuse:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_fuse_cn52xx cn52xxp1;
-	struct cvmx_ciu_fuse_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t fuse:12;
-#else
-		uint64_t fuse:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_fuse_cn56xx cn56xxp1;
-	struct cvmx_ciu_fuse_cn38xx cn58xx;
-	struct cvmx_ciu_fuse_cn38xx cn58xxp1;
-	struct cvmx_ciu_fuse_cn52xx cn61xx;
-	struct cvmx_ciu_fuse_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t fuse:6;
-#else
-		uint64_t fuse:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_fuse_cn63xx cn63xxp1;
-	struct cvmx_ciu_fuse_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t fuse:10;
-#else
-		uint64_t fuse:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_fuse_s cn68xx;
-	struct cvmx_ciu_fuse_s cn68xxp1;
-	struct cvmx_ciu_fuse_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_gstop {
-	uint64_t u64;
-	struct cvmx_ciu_gstop_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t gstop:1;
-#else
-		uint64_t gstop:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_gstop_s cn30xx;
-	struct cvmx_ciu_gstop_s cn31xx;
-	struct cvmx_ciu_gstop_s cn38xx;
-	struct cvmx_ciu_gstop_s cn38xxp2;
-	struct cvmx_ciu_gstop_s cn50xx;
-	struct cvmx_ciu_gstop_s cn52xx;
-	struct cvmx_ciu_gstop_s cn52xxp1;
-	struct cvmx_ciu_gstop_s cn56xx;
-	struct cvmx_ciu_gstop_s cn56xxp1;
-	struct cvmx_ciu_gstop_s cn58xx;
-	struct cvmx_ciu_gstop_s cn58xxp1;
-	struct cvmx_ciu_gstop_s cn61xx;
-	struct cvmx_ciu_gstop_s cn63xx;
-	struct cvmx_ciu_gstop_s cn63xxp1;
-	struct cvmx_ciu_gstop_s cn66xx;
-	struct cvmx_ciu_gstop_s cn68xx;
-	struct cvmx_ciu_gstop_s cn68xxp1;
-	struct cvmx_ciu_gstop_s cnf71xx;
-};
-
-union cvmx_ciu_intx_en0 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en0_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_intx_en0_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_intx_en0_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_intx_en0_cn38xx cn38xxp2;
-	struct cvmx_ciu_intx_en0_cn30xx cn50xx;
-	struct cvmx_ciu_intx_en0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en0_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_en0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en0_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en0_cn38xx cn58xx;
-	struct cvmx_ciu_intx_en0_cn38xx cn58xxp1;
-	struct cvmx_ciu_intx_en0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en0_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en0_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en0_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en0_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en0_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en0_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en0_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en0_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en0_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en0_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en0_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en0_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en0_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en0_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en0_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en0_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en0_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en0_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en1 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en1_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t wdog:1;
-#else
-		uint64_t wdog:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_intx_en1_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t wdog:2;
-#else
-		uint64_t wdog:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_intx_en1_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_intx_en1_cn38xx cn38xxp2;
-	struct cvmx_ciu_intx_en1_cn31xx cn50xx;
-	struct cvmx_ciu_intx_en1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn52xxp1;
-	struct cvmx_ciu_intx_en1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en1_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en1_cn38xx cn58xx;
-	struct cvmx_ciu_intx_en1_cn38xx cn58xxp1;
-	struct cvmx_ciu_intx_en1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en1_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en1_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en1_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en1_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en1_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en1_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en1_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en1_w1c_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en1_w1c_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en1_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en1_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en1_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en1_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en1_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en1_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en1_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en1_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en1_w1s_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en1_w1s_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en1_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en1_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_0_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_en4_0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_0_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en4_0_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_0_cn58xx cn58xxp1;
-	struct cvmx_ciu_intx_en4_0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_0_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_0_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_0_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_0_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_0_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_0_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_1_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t wdog:2;
-#else
-		uint64_t wdog:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_intx_en4_1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn52xxp1;
-	struct cvmx_ciu_intx_en4_1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_1_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en4_1_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_1_cn58xx cn58xxp1;
-	struct cvmx_ciu_intx_en4_1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en4_1_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_1_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_1_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_1_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_1_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_1_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_1_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_sum0 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_sum0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_sum0_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_intx_sum0_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_intx_sum0_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_intx_sum0_cn38xx cn38xxp2;
-	struct cvmx_ciu_intx_sum0_cn30xx cn50xx;
-	struct cvmx_ciu_intx_sum0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_sum0_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_sum0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_sum0_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_sum0_cn38xx cn58xx;
-	struct cvmx_ciu_intx_sum0_cn38xx cn58xxp1;
-	struct cvmx_ciu_intx_sum0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_sum0_cn52xx cn63xx;
-	struct cvmx_ciu_intx_sum0_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_sum0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_sum0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_sum4 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_sum4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_sum4_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_intx_sum4_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_sum4_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_sum4_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_sum4_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_sum4_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_sum4_cn58xx cn58xxp1;
-	struct cvmx_ciu_intx_sum4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_sum4_cn52xx cn63xx;
-	struct cvmx_ciu_intx_sum4_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_sum4_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_sum4_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_int33_sum0 {
-	uint64_t u64;
-	struct cvmx_ciu_int33_sum0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_int33_sum0_s cn61xx;
-	struct cvmx_ciu_int33_sum0_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_int33_sum0_cn63xx cn63xxp1;
-	struct cvmx_ciu_int33_sum0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_int33_sum0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_int_dbg_sel {
-	uint64_t u64;
-	struct cvmx_ciu_int_dbg_sel_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t sel:3;
-		uint64_t reserved_10_15:6;
-		uint64_t irq:2;
-		uint64_t reserved_5_7:3;
-		uint64_t pp:5;
-#else
-		uint64_t pp:5;
-		uint64_t reserved_5_7:3;
-		uint64_t irq:2;
-		uint64_t reserved_10_15:6;
-		uint64_t sel:3;
-		uint64_t reserved_19_63:45;
-#endif
-	} s;
-	struct cvmx_ciu_int_dbg_sel_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t sel:3;
-		uint64_t reserved_10_15:6;
-		uint64_t irq:2;
-		uint64_t reserved_4_7:4;
-		uint64_t pp:4;
-#else
-		uint64_t pp:4;
-		uint64_t reserved_4_7:4;
-		uint64_t irq:2;
-		uint64_t reserved_10_15:6;
-		uint64_t sel:3;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_int_dbg_sel_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t sel:3;
-		uint64_t reserved_10_15:6;
-		uint64_t irq:2;
-		uint64_t reserved_3_7:5;
-		uint64_t pp:3;
-#else
-		uint64_t pp:3;
-		uint64_t reserved_3_7:5;
-		uint64_t irq:2;
-		uint64_t reserved_10_15:6;
-		uint64_t sel:3;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_int_dbg_sel_cn61xx cn66xx;
-	struct cvmx_ciu_int_dbg_sel_s cn68xx;
-	struct cvmx_ciu_int_dbg_sel_s cn68xxp1;
-	struct cvmx_ciu_int_dbg_sel_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_int_sum1 {
-	uint64_t u64;
-	struct cvmx_ciu_int_sum1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_int_sum1_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t wdog:1;
-#else
-		uint64_t wdog:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_int_sum1_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t wdog:2;
-#else
-		uint64_t wdog:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_int_sum1_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_int_sum1_cn38xx cn38xxp2;
-	struct cvmx_ciu_int_sum1_cn31xx cn50xx;
-	struct cvmx_ciu_int_sum1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_int_sum1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn52xxp1;
-	struct cvmx_ciu_int_sum1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_int_sum1_cn56xx cn56xxp1;
-	struct cvmx_ciu_int_sum1_cn38xx cn58xx;
-	struct cvmx_ciu_int_sum1_cn38xx cn58xxp1;
-	struct cvmx_ciu_int_sum1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_int_sum1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_int_sum1_cn63xx cn63xxp1;
-	struct cvmx_ciu_int_sum1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_int_sum1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_37_46:10;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_46:10;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_mbox_clrx {
-	uint64_t u64;
-	struct cvmx_ciu_mbox_clrx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t bits:32;
-#else
-		uint64_t bits:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_mbox_clrx_s cn30xx;
-	struct cvmx_ciu_mbox_clrx_s cn31xx;
-	struct cvmx_ciu_mbox_clrx_s cn38xx;
-	struct cvmx_ciu_mbox_clrx_s cn38xxp2;
-	struct cvmx_ciu_mbox_clrx_s cn50xx;
-	struct cvmx_ciu_mbox_clrx_s cn52xx;
-	struct cvmx_ciu_mbox_clrx_s cn52xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn56xx;
-	struct cvmx_ciu_mbox_clrx_s cn56xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn58xx;
-	struct cvmx_ciu_mbox_clrx_s cn58xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn61xx;
-	struct cvmx_ciu_mbox_clrx_s cn63xx;
-	struct cvmx_ciu_mbox_clrx_s cn63xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn66xx;
-	struct cvmx_ciu_mbox_clrx_s cn68xx;
-	struct cvmx_ciu_mbox_clrx_s cn68xxp1;
-	struct cvmx_ciu_mbox_clrx_s cnf71xx;
-};
-
-union cvmx_ciu_mbox_setx {
-	uint64_t u64;
-	struct cvmx_ciu_mbox_setx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t bits:32;
-#else
-		uint64_t bits:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_mbox_setx_s cn30xx;
-	struct cvmx_ciu_mbox_setx_s cn31xx;
-	struct cvmx_ciu_mbox_setx_s cn38xx;
-	struct cvmx_ciu_mbox_setx_s cn38xxp2;
-	struct cvmx_ciu_mbox_setx_s cn50xx;
-	struct cvmx_ciu_mbox_setx_s cn52xx;
-	struct cvmx_ciu_mbox_setx_s cn52xxp1;
-	struct cvmx_ciu_mbox_setx_s cn56xx;
-	struct cvmx_ciu_mbox_setx_s cn56xxp1;
-	struct cvmx_ciu_mbox_setx_s cn58xx;
-	struct cvmx_ciu_mbox_setx_s cn58xxp1;
-	struct cvmx_ciu_mbox_setx_s cn61xx;
-	struct cvmx_ciu_mbox_setx_s cn63xx;
-	struct cvmx_ciu_mbox_setx_s cn63xxp1;
-	struct cvmx_ciu_mbox_setx_s cn66xx;
-	struct cvmx_ciu_mbox_setx_s cn68xx;
-	struct cvmx_ciu_mbox_setx_s cn68xxp1;
-	struct cvmx_ciu_mbox_setx_s cnf71xx;
-};
-
-union cvmx_ciu_nmi {
-	uint64_t u64;
-	struct cvmx_ciu_nmi_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t nmi:32;
-#else
-		uint64_t nmi:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_nmi_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t nmi:1;
-#else
-		uint64_t nmi:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_nmi_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t nmi:2;
-#else
-		uint64_t nmi:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_nmi_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t nmi:16;
-#else
-		uint64_t nmi:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_nmi_cn38xx cn38xxp2;
-	struct cvmx_ciu_nmi_cn31xx cn50xx;
-	struct cvmx_ciu_nmi_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t nmi:4;
-#else
-		uint64_t nmi:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_nmi_cn52xx cn52xxp1;
-	struct cvmx_ciu_nmi_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t nmi:12;
-#else
-		uint64_t nmi:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_nmi_cn56xx cn56xxp1;
-	struct cvmx_ciu_nmi_cn38xx cn58xx;
-	struct cvmx_ciu_nmi_cn38xx cn58xxp1;
-	struct cvmx_ciu_nmi_cn52xx cn61xx;
-	struct cvmx_ciu_nmi_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t nmi:6;
-#else
-		uint64_t nmi:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_nmi_cn63xx cn63xxp1;
-	struct cvmx_ciu_nmi_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t nmi:10;
-#else
-		uint64_t nmi:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_nmi_s cn68xx;
-	struct cvmx_ciu_nmi_s cn68xxp1;
-	struct cvmx_ciu_nmi_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_pci_inta {
-	uint64_t u64;
-	struct cvmx_ciu_pci_inta_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t intr:2;
-#else
-		uint64_t intr:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} s;
-	struct cvmx_ciu_pci_inta_s cn30xx;
-	struct cvmx_ciu_pci_inta_s cn31xx;
-	struct cvmx_ciu_pci_inta_s cn38xx;
-	struct cvmx_ciu_pci_inta_s cn38xxp2;
-	struct cvmx_ciu_pci_inta_s cn50xx;
-	struct cvmx_ciu_pci_inta_s cn52xx;
-	struct cvmx_ciu_pci_inta_s cn52xxp1;
-	struct cvmx_ciu_pci_inta_s cn56xx;
-	struct cvmx_ciu_pci_inta_s cn56xxp1;
-	struct cvmx_ciu_pci_inta_s cn58xx;
-	struct cvmx_ciu_pci_inta_s cn58xxp1;
-	struct cvmx_ciu_pci_inta_s cn61xx;
-	struct cvmx_ciu_pci_inta_s cn63xx;
-	struct cvmx_ciu_pci_inta_s cn63xxp1;
-	struct cvmx_ciu_pci_inta_s cn66xx;
-	struct cvmx_ciu_pci_inta_s cn68xx;
-	struct cvmx_ciu_pci_inta_s cn68xxp1;
-	struct cvmx_ciu_pci_inta_s cnf71xx;
-};
-
-union cvmx_ciu_pp_bist_stat {
-	uint64_t u64;
-	struct cvmx_ciu_pp_bist_stat_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t pp_bist:32;
-#else
-		uint64_t pp_bist:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_pp_bist_stat_s cn68xx;
-	struct cvmx_ciu_pp_bist_stat_s cn68xxp1;
-};
-
-union cvmx_ciu_pp_dbg {
-	uint64_t u64;
-	struct cvmx_ciu_pp_dbg_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t ppdbg:32;
-#else
-		uint64_t ppdbg:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_pp_dbg_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t ppdbg:1;
-#else
-		uint64_t ppdbg:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_pp_dbg_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t ppdbg:2;
-#else
-		uint64_t ppdbg:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_pp_dbg_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t ppdbg:16;
-#else
-		uint64_t ppdbg:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_pp_dbg_cn38xx cn38xxp2;
-	struct cvmx_ciu_pp_dbg_cn31xx cn50xx;
-	struct cvmx_ciu_pp_dbg_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t ppdbg:4;
-#else
-		uint64_t ppdbg:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_pp_dbg_cn52xx cn52xxp1;
-	struct cvmx_ciu_pp_dbg_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t ppdbg:12;
-#else
-		uint64_t ppdbg:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_pp_dbg_cn56xx cn56xxp1;
-	struct cvmx_ciu_pp_dbg_cn38xx cn58xx;
-	struct cvmx_ciu_pp_dbg_cn38xx cn58xxp1;
-	struct cvmx_ciu_pp_dbg_cn52xx cn61xx;
-	struct cvmx_ciu_pp_dbg_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t ppdbg:6;
-#else
-		uint64_t ppdbg:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_pp_dbg_cn63xx cn63xxp1;
-	struct cvmx_ciu_pp_dbg_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t ppdbg:10;
-#else
-		uint64_t ppdbg:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_pp_dbg_s cn68xx;
-	struct cvmx_ciu_pp_dbg_s cn68xxp1;
-	struct cvmx_ciu_pp_dbg_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_pp_pokex {
-	uint64_t u64;
-	struct cvmx_ciu_pp_pokex_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t poke:64;
-#else
-		uint64_t poke:64;
-#endif
-	} s;
-	struct cvmx_ciu_pp_pokex_s cn30xx;
-	struct cvmx_ciu_pp_pokex_s cn31xx;
-	struct cvmx_ciu_pp_pokex_s cn38xx;
-	struct cvmx_ciu_pp_pokex_s cn38xxp2;
-	struct cvmx_ciu_pp_pokex_s cn50xx;
-	struct cvmx_ciu_pp_pokex_s cn52xx;
-	struct cvmx_ciu_pp_pokex_s cn52xxp1;
-	struct cvmx_ciu_pp_pokex_s cn56xx;
-	struct cvmx_ciu_pp_pokex_s cn56xxp1;
-	struct cvmx_ciu_pp_pokex_s cn58xx;
-	struct cvmx_ciu_pp_pokex_s cn58xxp1;
-	struct cvmx_ciu_pp_pokex_s cn61xx;
-	struct cvmx_ciu_pp_pokex_s cn63xx;
-	struct cvmx_ciu_pp_pokex_s cn63xxp1;
-	struct cvmx_ciu_pp_pokex_s cn66xx;
-	struct cvmx_ciu_pp_pokex_s cn68xx;
-	struct cvmx_ciu_pp_pokex_s cn68xxp1;
-	struct cvmx_ciu_pp_pokex_s cnf71xx;
-};
-
-union cvmx_ciu_pp_rst {
-	uint64_t u64;
-	struct cvmx_ciu_pp_rst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t rst:31;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:31;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_pp_rst_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_pp_rst_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t rst:1;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:1;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_pp_rst_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t rst:15;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:15;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_pp_rst_cn38xx cn38xxp2;
-	struct cvmx_ciu_pp_rst_cn31xx cn50xx;
-	struct cvmx_ciu_pp_rst_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t rst:3;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:3;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_pp_rst_cn52xx cn52xxp1;
-	struct cvmx_ciu_pp_rst_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t rst:11;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:11;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_pp_rst_cn56xx cn56xxp1;
-	struct cvmx_ciu_pp_rst_cn38xx cn58xx;
-	struct cvmx_ciu_pp_rst_cn38xx cn58xxp1;
-	struct cvmx_ciu_pp_rst_cn52xx cn61xx;
-	struct cvmx_ciu_pp_rst_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t rst:5;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:5;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_pp_rst_cn63xx cn63xxp1;
-	struct cvmx_ciu_pp_rst_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t rst:9;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:9;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_pp_rst_s cn68xx;
-	struct cvmx_ciu_pp_rst_s cn68xxp1;
-	struct cvmx_ciu_pp_rst_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_qlm0 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm0_s cn61xx;
-	struct cvmx_ciu_qlm0_s cn63xx;
-	struct cvmx_ciu_qlm0_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_20_30:11;
-		uint64_t txdeemph:4;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:4;
-		uint64_t reserved_20_30:11;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn63xxp1;
-	struct cvmx_ciu_qlm0_s cn66xx;
-	struct cvmx_ciu_qlm0_cn68xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn68xx;
-	struct cvmx_ciu_qlm0_cn68xx cn68xxp1;
-	struct cvmx_ciu_qlm0_s cnf71xx;
-};
-
-union cvmx_ciu_qlm1 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm1_s cn61xx;
-	struct cvmx_ciu_qlm1_s cn63xx;
-	struct cvmx_ciu_qlm1_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_20_30:11;
-		uint64_t txdeemph:4;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:4;
-		uint64_t reserved_20_30:11;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn63xxp1;
-	struct cvmx_ciu_qlm1_s cn66xx;
-	struct cvmx_ciu_qlm1_s cn68xx;
-	struct cvmx_ciu_qlm1_s cn68xxp1;
-	struct cvmx_ciu_qlm1_s cnf71xx;
-};
-
-union cvmx_ciu_qlm2 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_qlm2_cn61xx cn63xx;
-	struct cvmx_ciu_qlm2_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_20_30:11;
-		uint64_t txdeemph:4;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:4;
-		uint64_t reserved_20_30:11;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn63xxp1;
-	struct cvmx_ciu_qlm2_cn61xx cn66xx;
-	struct cvmx_ciu_qlm2_s cn68xx;
-	struct cvmx_ciu_qlm2_s cn68xxp1;
-	struct cvmx_ciu_qlm2_cn61xx cnf71xx;
-};
 
-union cvmx_ciu_qlm3 {
+union cvmx_ciu_qlm {
 	uint64_t u64;
-	struct cvmx_ciu_qlm3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
+	struct cvmx_ciu_qlm_s {
+		__BITFIELD_FIELD(uint64_t g2bypass:1,
+		__BITFIELD_FIELD(uint64_t reserved_53_62:10,
+		__BITFIELD_FIELD(uint64_t g2deemph:5,
+		__BITFIELD_FIELD(uint64_t reserved_45_47:3,
+		__BITFIELD_FIELD(uint64_t g2margin:5,
+		__BITFIELD_FIELD(uint64_t reserved_32_39:8,
+		__BITFIELD_FIELD(uint64_t txbypass:1,
+		__BITFIELD_FIELD(uint64_t reserved_21_30:10,
+		__BITFIELD_FIELD(uint64_t txdeemph:5,
+		__BITFIELD_FIELD(uint64_t reserved_13_15:3,
+		__BITFIELD_FIELD(uint64_t txmargin:5,
+		__BITFIELD_FIELD(uint64_t reserved_4_7:4,
+		__BITFIELD_FIELD(uint64_t lane_en:4,
+		;)))))))))))))
 	} s;
-	struct cvmx_ciu_qlm3_s cn68xx;
-	struct cvmx_ciu_qlm3_s cn68xxp1;
-};
-
-union cvmx_ciu_qlm4 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm4_s cn68xx;
-	struct cvmx_ciu_qlm4_s cn68xxp1;
-};
-
-union cvmx_ciu_qlm_dcok {
-	uint64_t u64;
-	struct cvmx_ciu_qlm_dcok_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t qlm_dcok:4;
-#else
-		uint64_t qlm_dcok:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} s;
-	struct cvmx_ciu_qlm_dcok_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t qlm_dcok:2;
-#else
-		uint64_t qlm_dcok:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_qlm_dcok_cn52xx cn52xxp1;
-	struct cvmx_ciu_qlm_dcok_s cn56xx;
-	struct cvmx_ciu_qlm_dcok_s cn56xxp1;
 };
 
 union cvmx_ciu_qlm_jtgc {
 	uint64_t u64;
 	struct cvmx_ciu_qlm_jtgc_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_17_63:47;
-		uint64_t bypass_ext:1;
-		uint64_t reserved_11_15:5;
-		uint64_t clk_div:3;
-		uint64_t reserved_7_7:1;
-		uint64_t mux_sel:3;
-		uint64_t bypass:4;
-#else
-		uint64_t bypass:4;
-		uint64_t mux_sel:3;
-		uint64_t reserved_7_7:1;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_15:5;
-		uint64_t bypass_ext:1;
-		uint64_t reserved_17_63:47;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_17_63:47,
+		__BITFIELD_FIELD(uint64_t bypass_ext:1,
+		__BITFIELD_FIELD(uint64_t reserved_11_15:5,
+		__BITFIELD_FIELD(uint64_t clk_div:3,
+		__BITFIELD_FIELD(uint64_t reserved_7_7:1,
+		__BITFIELD_FIELD(uint64_t mux_sel:3,
+		__BITFIELD_FIELD(uint64_t bypass:4,
+		;)))))))
 	} s;
-	struct cvmx_ciu_qlm_jtgc_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_11_63:53;
-		uint64_t clk_div:3;
-		uint64_t reserved_5_7:3;
-		uint64_t mux_sel:1;
-		uint64_t reserved_2_3:2;
-		uint64_t bypass:2;
-#else
-		uint64_t bypass:2;
-		uint64_t reserved_2_3:2;
-		uint64_t mux_sel:1;
-		uint64_t reserved_5_7:3;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_63:53;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_qlm_jtgc_cn52xx cn52xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_11_63:53;
-		uint64_t clk_div:3;
-		uint64_t reserved_6_7:2;
-		uint64_t mux_sel:2;
-		uint64_t bypass:4;
-#else
-		uint64_t bypass:4;
-		uint64_t mux_sel:2;
-		uint64_t reserved_6_7:2;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_63:53;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_qlm_jtgc_cn56xx cn56xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_11_63:53;
-		uint64_t clk_div:3;
-		uint64_t reserved_6_7:2;
-		uint64_t mux_sel:2;
-		uint64_t reserved_3_3:1;
-		uint64_t bypass:3;
-#else
-		uint64_t bypass:3;
-		uint64_t reserved_3_3:1;
-		uint64_t mux_sel:2;
-		uint64_t reserved_6_7:2;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_63:53;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cn63xx;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cn63xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cn66xx;
-	struct cvmx_ciu_qlm_jtgc_s cn68xx;
-	struct cvmx_ciu_qlm_jtgc_s cn68xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cnf71xx;
 };
 
 union cvmx_ciu_qlm_jtgd {
 	uint64_t u64;
 	struct cvmx_ciu_qlm_jtgd_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_45_60:16;
-		uint64_t select:5;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:5;
-		uint64_t reserved_45_60:16;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm_jtgd_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_42_60:19;
-		uint64_t select:2;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:2;
-		uint64_t reserved_42_60:19;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_qlm_jtgd_cn52xx cn52xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_44_60:17;
-		uint64_t select:4;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:4;
-		uint64_t reserved_44_60:17;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_qlm_jtgd_cn56xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_37_60:24;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_60:24;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn56xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_43_60:18;
-		uint64_t select:3;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:3;
-		uint64_t reserved_43_60:18;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cn63xx;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cn63xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cn66xx;
-	struct cvmx_ciu_qlm_jtgd_s cn68xx;
-	struct cvmx_ciu_qlm_jtgd_s cn68xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_soft_bist {
-	uint64_t u64;
-	struct cvmx_ciu_soft_bist_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_bist:1;
-#else
-		uint64_t soft_bist:1;
-		uint64_t reserved_1_63:63;
-#endif
+		__BITFIELD_FIELD(uint64_t capture:1,
+		__BITFIELD_FIELD(uint64_t shift:1,
+		__BITFIELD_FIELD(uint64_t update:1,
+		__BITFIELD_FIELD(uint64_t reserved_45_60:16,
+		__BITFIELD_FIELD(uint64_t select:5,
+		__BITFIELD_FIELD(uint64_t reserved_37_39:3,
+		__BITFIELD_FIELD(uint64_t shft_cnt:5,
+		__BITFIELD_FIELD(uint64_t shft_reg:32,
+		;))))))))
 	} s;
-	struct cvmx_ciu_soft_bist_s cn30xx;
-	struct cvmx_ciu_soft_bist_s cn31xx;
-	struct cvmx_ciu_soft_bist_s cn38xx;
-	struct cvmx_ciu_soft_bist_s cn38xxp2;
-	struct cvmx_ciu_soft_bist_s cn50xx;
-	struct cvmx_ciu_soft_bist_s cn52xx;
-	struct cvmx_ciu_soft_bist_s cn52xxp1;
-	struct cvmx_ciu_soft_bist_s cn56xx;
-	struct cvmx_ciu_soft_bist_s cn56xxp1;
-	struct cvmx_ciu_soft_bist_s cn58xx;
-	struct cvmx_ciu_soft_bist_s cn58xxp1;
-	struct cvmx_ciu_soft_bist_s cn61xx;
-	struct cvmx_ciu_soft_bist_s cn63xx;
-	struct cvmx_ciu_soft_bist_s cn63xxp1;
-	struct cvmx_ciu_soft_bist_s cn66xx;
-	struct cvmx_ciu_soft_bist_s cn68xx;
-	struct cvmx_ciu_soft_bist_s cn68xxp1;
-	struct cvmx_ciu_soft_bist_s cnf71xx;
 };
 
 union cvmx_ciu_soft_prst {
 	uint64_t u64;
 	struct cvmx_ciu_soft_prst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_3_63:61;
-		uint64_t host64:1;
-		uint64_t npi:1;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t npi:1;
-		uint64_t host64:1;
-		uint64_t reserved_3_63:61;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst_s cn30xx;
-	struct cvmx_ciu_soft_prst_s cn31xx;
-	struct cvmx_ciu_soft_prst_s cn38xx;
-	struct cvmx_ciu_soft_prst_s cn38xxp2;
-	struct cvmx_ciu_soft_prst_s cn50xx;
-	struct cvmx_ciu_soft_prst_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn52xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cn56xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn56xxp1;
-	struct cvmx_ciu_soft_prst_s cn58xx;
-	struct cvmx_ciu_soft_prst_s cn58xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cn61xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn63xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn63xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cn66xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn68xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn68xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_soft_prst1 {
-	uint64_t u64;
-	struct cvmx_ciu_soft_prst1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst1_s cn52xx;
-	struct cvmx_ciu_soft_prst1_s cn52xxp1;
-	struct cvmx_ciu_soft_prst1_s cn56xx;
-	struct cvmx_ciu_soft_prst1_s cn56xxp1;
-	struct cvmx_ciu_soft_prst1_s cn61xx;
-	struct cvmx_ciu_soft_prst1_s cn63xx;
-	struct cvmx_ciu_soft_prst1_s cn63xxp1;
-	struct cvmx_ciu_soft_prst1_s cn66xx;
-	struct cvmx_ciu_soft_prst1_s cn68xx;
-	struct cvmx_ciu_soft_prst1_s cn68xxp1;
-	struct cvmx_ciu_soft_prst1_s cnf71xx;
-};
-
-union cvmx_ciu_soft_prst2 {
-	uint64_t u64;
-	struct cvmx_ciu_soft_prst2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst2_s cn66xx;
-};
-
-union cvmx_ciu_soft_prst3 {
-	uint64_t u64;
-	struct cvmx_ciu_soft_prst3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst3_s cn66xx;
-};
-
-union cvmx_ciu_soft_rst {
-	uint64_t u64;
-	struct cvmx_ciu_soft_rst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_rst:1;
-#else
-		uint64_t soft_rst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_rst_s cn30xx;
-	struct cvmx_ciu_soft_rst_s cn31xx;
-	struct cvmx_ciu_soft_rst_s cn38xx;
-	struct cvmx_ciu_soft_rst_s cn38xxp2;
-	struct cvmx_ciu_soft_rst_s cn50xx;
-	struct cvmx_ciu_soft_rst_s cn52xx;
-	struct cvmx_ciu_soft_rst_s cn52xxp1;
-	struct cvmx_ciu_soft_rst_s cn56xx;
-	struct cvmx_ciu_soft_rst_s cn56xxp1;
-	struct cvmx_ciu_soft_rst_s cn58xx;
-	struct cvmx_ciu_soft_rst_s cn58xxp1;
-	struct cvmx_ciu_soft_rst_s cn61xx;
-	struct cvmx_ciu_soft_rst_s cn63xx;
-	struct cvmx_ciu_soft_rst_s cn63xxp1;
-	struct cvmx_ciu_soft_rst_s cn66xx;
-	struct cvmx_ciu_soft_rst_s cn68xx;
-	struct cvmx_ciu_soft_rst_s cn68xxp1;
-	struct cvmx_ciu_soft_rst_s cnf71xx;
-};
-
-union cvmx_ciu_sum1_iox_int {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_3_63:61,
+		__BITFIELD_FIELD(uint64_t host64:1,
+		__BITFIELD_FIELD(uint64_t npi:1,
+		__BITFIELD_FIELD(uint64_t soft_prst:1,
+		;))))
 	} s;
-	struct cvmx_ciu_sum1_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_iox_int_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_iox_int_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip2 {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_ppx_ip2_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_ppx_ip2_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip3 {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_ppx_ip3_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_ppx_ip3_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip4 {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_ppx_ip4_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_ppx_ip4_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum2_iox_int {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_iox_int_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_iox_int_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip2 {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_ppx_ip2_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_ppx_ip2_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip3 {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_ppx_ip3_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_ppx_ip3_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip4 {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_ppx_ip4_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_ppx_ip4_s cnf71xx;
 };
 
 union cvmx_ciu_timx {
 	uint64_t u64;
 	struct cvmx_ciu_timx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_37_63:27;
-		uint64_t one_shot:1;
-		uint64_t len:36;
-#else
-		uint64_t len:36;
-		uint64_t one_shot:1;
-		uint64_t reserved_37_63:27;
-#endif
-	} s;
-	struct cvmx_ciu_timx_s cn30xx;
-	struct cvmx_ciu_timx_s cn31xx;
-	struct cvmx_ciu_timx_s cn38xx;
-	struct cvmx_ciu_timx_s cn38xxp2;
-	struct cvmx_ciu_timx_s cn50xx;
-	struct cvmx_ciu_timx_s cn52xx;
-	struct cvmx_ciu_timx_s cn52xxp1;
-	struct cvmx_ciu_timx_s cn56xx;
-	struct cvmx_ciu_timx_s cn56xxp1;
-	struct cvmx_ciu_timx_s cn58xx;
-	struct cvmx_ciu_timx_s cn58xxp1;
-	struct cvmx_ciu_timx_s cn61xx;
-	struct cvmx_ciu_timx_s cn63xx;
-	struct cvmx_ciu_timx_s cn63xxp1;
-	struct cvmx_ciu_timx_s cn66xx;
-	struct cvmx_ciu_timx_s cn68xx;
-	struct cvmx_ciu_timx_s cn68xxp1;
-	struct cvmx_ciu_timx_s cnf71xx;
-};
-
-union cvmx_ciu_tim_multi_cast {
-	uint64_t u64;
-	struct cvmx_ciu_tim_multi_cast_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t en:1;
-#else
-		uint64_t en:1;
-		uint64_t reserved_1_63:63;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_37_63:27,
+		__BITFIELD_FIELD(uint64_t one_shot:1,
+		__BITFIELD_FIELD(uint64_t len:36,
+		;)))
 	} s;
-	struct cvmx_ciu_tim_multi_cast_s cn61xx;
-	struct cvmx_ciu_tim_multi_cast_s cn66xx;
-	struct cvmx_ciu_tim_multi_cast_s cnf71xx;
 };
 
 union cvmx_ciu_wdogx {
 	uint64_t u64;
 	struct cvmx_ciu_wdogx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_46_63:18;
-		uint64_t gstopen:1;
-		uint64_t dstop:1;
-		uint64_t cnt:24;
-		uint64_t len:16;
-		uint64_t state:2;
-		uint64_t mode:2;
-#else
-		uint64_t mode:2;
-		uint64_t state:2;
-		uint64_t len:16;
-		uint64_t cnt:24;
-		uint64_t dstop:1;
-		uint64_t gstopen:1;
-		uint64_t reserved_46_63:18;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_46_63:18,
+		__BITFIELD_FIELD(uint64_t gstopen:1,
+		__BITFIELD_FIELD(uint64_t dstop:1,
+		__BITFIELD_FIELD(uint64_t cnt:24,
+		__BITFIELD_FIELD(uint64_t len:16,
+		__BITFIELD_FIELD(uint64_t state:2,
+		__BITFIELD_FIELD(uint64_t mode:2,
+		;)))))))
 	} s;
-	struct cvmx_ciu_wdogx_s cn30xx;
-	struct cvmx_ciu_wdogx_s cn31xx;
-	struct cvmx_ciu_wdogx_s cn38xx;
-	struct cvmx_ciu_wdogx_s cn38xxp2;
-	struct cvmx_ciu_wdogx_s cn50xx;
-	struct cvmx_ciu_wdogx_s cn52xx;
-	struct cvmx_ciu_wdogx_s cn52xxp1;
-	struct cvmx_ciu_wdogx_s cn56xx;
-	struct cvmx_ciu_wdogx_s cn56xxp1;
-	struct cvmx_ciu_wdogx_s cn58xx;
-	struct cvmx_ciu_wdogx_s cn58xxp1;
-	struct cvmx_ciu_wdogx_s cn61xx;
-	struct cvmx_ciu_wdogx_s cn63xx;
-	struct cvmx_ciu_wdogx_s cn63xxp1;
-	struct cvmx_ciu_wdogx_s cn66xx;
-	struct cvmx_ciu_wdogx_s cn68xx;
-	struct cvmx_ciu_wdogx_s cn68xxp1;
-	struct cvmx_ciu_wdogx_s cnf71xx;
 };
 
-#endif
+#endif /* __CVMX_CIU_DEFS_H__ */
diff --git a/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h b/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h
index e347496a33c3..80e4f8358b81 100644
--- a/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -2070,6 +2070,8 @@ static inline uint64_t CVMX_GMXX_XAUI_EXT_LOOPBACK(unsigned long block_id)
 	return CVMX_ADD_IO_SEG(0x0001180008000540ull) + (block_id) * 0x8000000ull;
 }
 
+void __cvmx_interrupt_gmxx_enable(int interface);
+
 union cvmx_gmxx_bad_reg {
 	uint64_t u64;
 	struct cvmx_gmxx_bad_reg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h b/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h
index a5e8fd861c37..39da7f9d7b3f 100644
--- a/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -334,6 +334,8 @@ static inline uint64_t CVMX_PCSX_TX_RXX_POLARITY_REG(unsigned long offset, unsig
 	return CVMX_ADD_IO_SEG(0x00011800B0001048ull) + ((offset) + (block_id) * 0x20000ull) * 1024;
 }
 
+void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
+
 union cvmx_pcsx_anx_adv_reg {
 	uint64_t u64;
 	struct cvmx_pcsx_anx_adv_reg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h b/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h
index b5b45d26f1c5..847dd9dca6ea 100644
--- a/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -268,6 +268,8 @@ static inline uint64_t CVMX_PCSXX_TX_RX_STATES_REG(unsigned long block_id)
 	return CVMX_ADD_IO_SEG(0x00011800B0000830ull) + (block_id) * 0x1000000ull;
 }
 
+void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
+
 union cvmx_pcsxx_10gbx_status_reg {
 	uint64_t u64;
 	struct cvmx_pcsxx_10gbx_status_reg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-spxx-defs.h b/arch/mips/include/asm/octeon/cvmx-spxx-defs.h
index c7d601d9446e..f4c4e8051160 100644
--- a/arch/mips/include/asm/octeon/cvmx-spxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-spxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -45,6 +45,8 @@
 #define CVMX_SPXX_TPA_SEL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000328ull) + ((block_id) & 1) * 0x8000000ull)
 #define CVMX_SPXX_TRN4_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000360ull) + ((block_id) & 1) * 0x8000000ull)
 
+void __cvmx_interrupt_spxx_int_msk_enable(int index);
+
 union cvmx_spxx_bckprs_cnt {
 	uint64_t u64;
 	struct cvmx_spxx_bckprs_cnt_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-stxx-defs.h b/arch/mips/include/asm/octeon/cvmx-stxx-defs.h
index 146354005d3b..3c409a854d91 100644
--- a/arch/mips/include/asm/octeon/cvmx-stxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-stxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -45,6 +45,8 @@
 #define CVMX_STXX_STAT_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000638ull) + ((block_id) & 1) * 0x8000000ull)
 #define CVMX_STXX_STAT_PKT_XMT(block_id) (CVMX_ADD_IO_SEG(0x0001180090000640ull) + ((block_id) & 1) * 0x8000000ull)
 
+void __cvmx_interrupt_stxx_int_msk_enable(int index);
+
 union cvmx_stxx_arb_ctl {
 	uint64_t u64;
 	struct cvmx_stxx_arb_ctl_s {
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index c99c4b6a79f4..60481502826a 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -279,13 +279,12 @@ union octeon_cvmemctl {
 	} s;
 };
 
-extern void octeon_write_lcd(const char *s);
 extern void octeon_check_cpu_bist(void);
-extern int octeon_get_boot_uart(void);
 
-struct uart_port;
-extern unsigned int octeon_serial_in(struct uart_port *, int);
-extern void octeon_serial_out(struct uart_port *, int, int);
+int octeon_prune_device_tree(void);
+extern const char __appended_dtb;
+extern const char __dtb_octeon_3xxx_begin;
+extern const char __dtb_octeon_68xx_begin;
 
 /**
  * Write a 32bit value to the Octeon NPI register space
diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h
index 1884609741a8..b12d9a3fbfb6 100644
--- a/arch/mips/include/asm/octeon/pci-octeon.h
+++ b/arch/mips/include/asm/octeon/pci-octeon.h
@@ -63,4 +63,7 @@ enum octeon_dma_bar_type {
  */
 extern enum octeon_dma_bar_type octeon_dma_bar_type;
 
+void octeon_pci_dma_init(void);
+extern char *octeon_swiotlb;
+
 #endif
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index ad461216b5a1..e8cc328fce2d 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -80,7 +80,12 @@ extern void build_copy_page(void);
  * used in our early mem init code for all memory models.
  * So always define it.
  */
-#define ARCH_PFN_OFFSET		PFN_UP(PHYS_OFFSET)
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+extern unsigned long ARCH_PFN_OFFSET;
+# define ARCH_PFN_OFFSET	ARCH_PFN_OFFSET
+#else
+# define ARCH_PFN_OFFSET	PFN_UP(PHYS_OFFSET)
+#endif
 
 extern void clear_page(void * page);
 extern void copy_page(void * to, void * from);
@@ -252,8 +257,8 @@ extern int __virt_addr_valid(const volatile void *kaddr);
 	 ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
 	 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
-#define UNCAC_ADDR(addr)	((addr) - PAGE_OFFSET + UNCAC_BASE)
-#define CAC_ADDR(addr)		((addr) - UNCAC_BASE + PAGE_OFFSET)
+#define UNCAC_ADDR(addr)	(UNCAC_BASE + __pa(addr))
+#define CAC_ADDR(addr)		((unsigned long)__va((addr) - UNCAC_BASE))
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index af34afbc32d9..b2fa62922d88 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -141,7 +141,7 @@ struct mips_fpu_struct {
 
 #define NUM_DSP_REGS   6
 
-typedef __u32 dspreg_t;
+typedef unsigned long dspreg_t;
 
 struct mips_dsp_state {
 	dspreg_t	dspr[NUM_DSP_REGS];
@@ -386,7 +386,20 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29])
 #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
 
+#ifdef CONFIG_CPU_LOONGSON3
+/*
+ * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a
+ * tight read loop is executed, because reads take priority over writes & the
+ * hardware (incorrectly) doesn't ensure that writes will eventually occur.
+ *
+ * Since spin loops of any kind should have a cpu_relax() in them, force an SFB
+ * flush from cpu_relax() such that any pending writes will become visible as
+ * expected.
+ */
+#define cpu_relax()	smp_mb()
+#else
 #define cpu_relax()	barrier()
+#endif
 
 /*
  * Return_address is a replacement for __builtin_return_address(count)
diff --git a/arch/mips/include/asm/setup.h b/arch/mips/include/asm/setup.h
index d49d247d48a1..bb36a400203d 100644
--- a/arch/mips/include/asm/setup.h
+++ b/arch/mips/include/asm/setup.h
@@ -2,8 +2,10 @@
 #ifndef _MIPS_SETUP_H
 #define _MIPS_SETUP_H
 
+#include <linux/types.h>
 #include <uapi/asm/setup.h>
 
+extern void prom_putchar(char);
 extern void setup_early_printk(void);
 
 #ifdef CONFIG_EARLY_PRINTK_8250
diff --git a/arch/mips/include/asm/sgialib.h b/arch/mips/include/asm/sgialib.h
index 195db5045ae5..0d9fad5915fe 100644
--- a/arch/mips/include/asm/sgialib.h
+++ b/arch/mips/include/asm/sgialib.h
@@ -31,7 +31,6 @@ extern int prom_flags;
 #define PROM_FLAG_DONT_FREE_TEMP	4
 
 /* Simple char-by-char console I/O. */
-extern void prom_putchar(char c);
 extern char prom_getchar(void);
 
 /* Get next memory descriptor after CURR, returns first descriptor
diff --git a/arch/mips/include/asm/sim.h b/arch/mips/include/asm/sim.h
index 91831800c480..59f31a95facd 100644
--- a/arch/mips/include/asm/sim.h
+++ b/arch/mips/include/asm/sim.h
@@ -39,8 +39,6 @@ __asm__(								\
 	".end\t__" #symbol "\n\t"					\
 	".size\t__" #symbol",. - __" #symbol)
 
-#define nabi_no_regargs
-
 #endif /* CONFIG_32BIT */
 
 #ifdef CONFIG_64BIT
@@ -67,16 +65,6 @@ __asm__(								\
 	".end\t__" #symbol "\n\t"					\
 	".size\t__" #symbol",. - __" #symbol)
 
-#define nabi_no_regargs							\
-	unsigned long __dummy0,						\
-	unsigned long __dummy1,						\
-	unsigned long __dummy2,						\
-	unsigned long __dummy3,						\
-	unsigned long __dummy4,						\
-	unsigned long __dummy5,						\
-	unsigned long __dummy6,						\
-	unsigned long __dummy7,
-
 #endif /* CONFIG_64BIT */
 
 #endif /* _ASM_SIM_H */
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index 88ebd83b3bf9..056a6bf13491 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -25,7 +25,17 @@ extern cpumask_t cpu_sibling_map[];
 extern cpumask_t cpu_core_map[];
 extern cpumask_t cpu_foreign_map[];
 
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+static inline int raw_smp_processor_id(void)
+{
+#if defined(__VDSO__)
+	extern int vdso_smp_processor_id(void)
+		__compiletime_error("VDSO should not call smp_processor_id()");
+	return vdso_smp_processor_id();
+#else
+	return current_thread_info()->cpu;
+#endif
+}
+#define raw_smp_processor_id raw_smp_processor_id
 
 /* Map from cpu id to sequential logical cpu number.  This will only
    not be idempotent when cpus failed to come on-line.	*/
diff --git a/arch/mips/include/asm/txx9/generic.h b/arch/mips/include/asm/txx9/generic.h
index 64887d3c7ec3..9a2c47bf3c40 100644
--- a/arch/mips/include/asm/txx9/generic.h
+++ b/arch/mips/include/asm/txx9/generic.h
@@ -49,7 +49,6 @@ void txx9_spi_init(int busid, unsigned long base, int irq);
 void txx9_ethaddr_init(unsigned int id, unsigned char *ethaddr);
 void txx9_sio_init(unsigned long baseaddr, int irq,
 		   unsigned int line, unsigned int sclk, int nocts);
-void prom_putchar(char c);
 #ifdef CONFIG_EARLY_PRINTK
 extern void (*txx9_prom_putchar)(char c);
 void txx9_sio_putchar_init(unsigned long baseaddr);
diff --git a/arch/mips/include/asm/txx9/tx4939.h b/arch/mips/include/asm/txx9/tx4939.h
index 6d667087f2aa..00805ac6e9fc 100644
--- a/arch/mips/include/asm/txx9/tx4939.h
+++ b/arch/mips/include/asm/txx9/tx4939.h
@@ -101,13 +101,6 @@ struct tx4939_irc_reg {
 	struct tx4939_le_reg maskext;
 };
 
-struct tx4939_rtc_reg {
-	__u32 ctl;
-	__u32 adr;
-	__u32 dat;
-	__u32 tbc;
-};
-
 struct tx4939_crypto_reg {
 	struct tx4939_le_reg csr;
 	struct tx4939_le_reg idesptr;
@@ -370,26 +363,6 @@ struct tx4939_vpc_desc {
 #define TX4939_CLKCTR_CYPRST	0x00000001
 
 /*
- * RTC
- */
-#define TX4939_RTCCTL_ALME	0x00000080
-#define TX4939_RTCCTL_ALMD	0x00000040
-#define TX4939_RTCCTL_BUSY	0x00000020
-
-#define TX4939_RTCCTL_COMMAND	0x00000007
-#define TX4939_RTCCTL_COMMAND_NOP	0x00000000
-#define TX4939_RTCCTL_COMMAND_GETTIME	0x00000001
-#define TX4939_RTCCTL_COMMAND_SETTIME	0x00000002
-#define TX4939_RTCCTL_COMMAND_GETALARM	0x00000003
-#define TX4939_RTCCTL_COMMAND_SETALARM	0x00000004
-
-#define TX4939_RTCTBC_PM	0x00000080
-#define TX4939_RTCTBC_COMP	0x0000007f
-
-#define TX4939_RTC_REG_RAMSIZE	0x00000100
-#define TX4939_RTC_REG_RWBSIZE	0x00000006
-
-/*
  * CRYPTO
  */
 #define TX4939_CRYPTO_CSR_SAESO 0x08000000
@@ -498,8 +471,6 @@ struct tx4939_vpc_desc {
 #define tx4939_ccfgptr \
 		((struct tx4939_ccfg_reg __iomem *)TX4939_CCFG_REG)
 #define tx4939_sramcptr		tx4938_sramcptr
-#define tx4939_rtcptr \
-		((struct tx4939_rtc_reg __iomem *)TX4939_RTC_REG)
 #define tx4939_cryptoptr \
 		((struct tx4939_crypto_reg __iomem *)TX4939_CRYPTO_REG)
 #define tx4939_vpcptr	((struct tx4939_vpc_reg __iomem *)TX4939_VPC_REG)
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index d626a9a391cc..d31bc2f01208 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -16,6 +16,8 @@
 #include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
 #include <asm/io.h>
@@ -86,6 +88,7 @@ static int __init vdma_init(void)
 	printk(KERN_INFO "VDMA: R4030 DMA pagetables initialized.\n");
 	return 0;
 }
+arch_initcall(vdma_init);
 
 /*
  * Allocate DMA pagetables using a simple first-fit algorithm
@@ -556,4 +559,140 @@ int vdma_get_enable(int channel)
 	return enable;
 }
 
-arch_initcall(vdma_init);
+static void *jazz_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	void *ret;
+
+	ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+	if (!ret)
+		return NULL;
+
+	*dma_handle = vdma_alloc(virt_to_phys(ret), size);
+	if (*dma_handle == VDMA_ERROR) {
+		dma_direct_free(dev, size, ret, *dma_handle, attrs);
+		return NULL;
+	}
+
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT)) {
+		dma_cache_wback_inv((unsigned long)ret, size);
+		ret = (void *)UNCAC_ADDR(ret);
+	}
+	return ret;
+}
+
+static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	vdma_free(dma_handle);
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT))
+		vaddr = (void *)CAC_ADDR((unsigned long)vaddr);
+	return dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+}
+
+static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(dev, phys, size, dir);
+	return vdma_alloc(phys, size);
+}
+
+static void jazz_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_cpu(dev, vdma_log2phys(dma_addr), size, dir);
+	vdma_free(dma_addr);
+}
+
+static int jazz_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nents, i) {
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+				dir);
+		sg->dma_address = vdma_alloc(sg_phys(sg), sg->length);
+		if (sg->dma_address == VDMA_ERROR)
+			return 0;
+		sg_dma_len(sg) = sg->length;
+	}
+
+	return nents;
+}
+
+static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nents, i) {
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length,
+				dir);
+		vdma_free(sg->dma_address);
+	}
+}
+
+static void jazz_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	arch_sync_dma_for_device(dev, vdma_log2phys(addr), size, dir);
+}
+
+static void jazz_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	arch_sync_dma_for_cpu(dev, vdma_log2phys(addr), size, dir);
+}
+
+static void jazz_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+}
+
+static void jazz_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+}
+
+static int jazz_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == VDMA_ERROR;
+}
+
+const struct dma_map_ops jazz_dma_ops = {
+	.alloc			= jazz_dma_alloc,
+	.free			= jazz_dma_free,
+	.mmap			= arch_dma_mmap,
+	.map_page		= jazz_dma_map_page,
+	.unmap_page		= jazz_dma_unmap_page,
+	.map_sg			= jazz_dma_map_sg,
+	.unmap_sg		= jazz_dma_unmap_sg,
+	.sync_single_for_cpu	= jazz_dma_sync_single_for_cpu,
+	.sync_single_for_device	= jazz_dma_sync_single_for_device,
+	.sync_sg_for_cpu	= jazz_dma_sync_sg_for_cpu,
+	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
+	.dma_supported		= dma_direct_supported,
+	.cache_sync		= arch_dma_cache_sync,
+	.mapping_error		= jazz_dma_mapping_error,
+};
+EXPORT_SYMBOL(jazz_dma_ops);
diff --git a/arch/mips/jazz/setup.c b/arch/mips/jazz/setup.c
index 448fd41792e4..1b5e121c3f0d 100644
--- a/arch/mips/jazz/setup.c
+++ b/arch/mips/jazz/setup.c
@@ -16,6 +16,7 @@
 #include <linux/screen_info.h>
 #include <linux/platform_device.h>
 #include <linux/serial_8250.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/jazz.h>
 #include <asm/jazzdma.h>
@@ -136,10 +137,16 @@ static struct resource jazz_esp_rsrc[] = {
 	}
 };
 
+static u64 jazz_esp_dma_mask = DMA_BIT_MASK(32);
+
 static struct platform_device jazz_esp_pdev = {
 	.name		= "jazz_esp",
 	.num_resources	= ARRAY_SIZE(jazz_esp_rsrc),
-	.resource	= jazz_esp_rsrc
+	.resource	= jazz_esp_rsrc,
+	.dev = {
+		.dma_mask	   = &jazz_esp_dma_mask,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
+	}
 };
 
 static struct resource jazz_sonic_rsrc[] = {
@@ -155,10 +162,16 @@ static struct resource jazz_sonic_rsrc[] = {
 	}
 };
 
+static u64 jazz_sonic_dma_mask = DMA_BIT_MASK(32);
+
 static struct platform_device jazz_sonic_pdev = {
 	.name		= "jazzsonic",
 	.num_resources	= ARRAY_SIZE(jazz_sonic_rsrc),
-	.resource	= jazz_sonic_rsrc
+	.resource	= jazz_sonic_rsrc,
+	.dev = {
+		.dma_mask	   = &jazz_sonic_dma_mask,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
+	}
 };
 
 static struct resource jazz_cmos_rsrc[] = {
diff --git a/arch/mips/jz4740/Platform b/arch/mips/jz4740/Platform
index 28448d358c10..a2a5a85ea1f9 100644
--- a/arch/mips/jz4740/Platform
+++ b/arch/mips/jz4740/Platform
@@ -1,4 +1,4 @@
 platform-$(CONFIG_MACH_INGENIC)	+= jz4740/
 cflags-$(CONFIG_MACH_INGENIC)	+= -I$(srctree)/arch/mips/include/asm/mach-jz4740
 load-$(CONFIG_MACH_INGENIC)	+= 0xffffffff80010000
-zload-$(CONFIG_MACH_INGENIC)	+= 0xffffffff80600000
+zload-$(CONFIG_MACH_INGENIC)	+= 0xffffffff81000000
diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c
index 60f0767507c6..af0c8ace0141 100644
--- a/arch/mips/jz4740/board-qi_lb60.c
+++ b/arch/mips/jz4740/board-qi_lb60.c
@@ -29,10 +29,11 @@
 #include <linux/power/gpio-charger.h>
 #include <linux/pwm.h>
 
+#include <linux/platform_data/jz4740/jz4740_nand.h>
+
 #include <asm/mach-jz4740/gpio.h>
 #include <asm/mach-jz4740/jz4740_fb.h>
 #include <asm/mach-jz4740/jz4740_mmc.h>
-#include <asm/mach-jz4740/jz4740_nand.h>
 
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index b2509c19cfb5..d535fc706a8b 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1849,7 +1849,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 			set_elf_platform(cpu, "loongson3a");
 			set_isa(c, MIPS_CPU_ISA_M64R2);
 			break;
-		case PRID_REV_LOONGSON3A_R3:
+		case PRID_REV_LOONGSON3A_R3_0:
+		case PRID_REV_LOONGSON3A_R3_1:
 			c->cputype = CPU_LOONGSON3;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
diff --git a/arch/mips/kernel/early_printk.c b/arch/mips/kernel/early_printk.c
index 505cb77d1280..4a1647ddfbd9 100644
--- a/arch/mips/kernel/early_printk.c
+++ b/arch/mips/kernel/early_printk.c
@@ -14,8 +14,6 @@
 
 #include <asm/setup.h>
 
-extern void prom_putchar(char);
-
 static void early_console_write(struct console *con, const char *s, unsigned n)
 {
 	while (n-- && *s) {
diff --git a/arch/mips/kernel/early_printk_8250.c b/arch/mips/kernel/early_printk_8250.c
index 83cea3767556..ea26614afac6 100644
--- a/arch/mips/kernel/early_printk_8250.c
+++ b/arch/mips/kernel/early_printk_8250.c
@@ -20,6 +20,7 @@
 #include <linux/io.h>
 #include <linux/serial_core.h>
 #include <linux/serial_reg.h>
+#include <asm/setup.h>
 
 static void __iomem *serial8250_base;
 static unsigned int serial8250_reg_shift;
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 37b9383eacd3..6c257b52f57f 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -354,16 +354,56 @@ NESTED(ejtag_debug_handler, PT_SIZE, sp)
 	sll	k0, k0, 30	# Check for SDBBP.
 	bgez	k0, ejtag_return
 
+#ifdef CONFIG_SMP
+1:	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	ll	k0, 0(k0)
+	bnez	k0, 1b
+	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	sc	k0, 0(k0)
+	beqz	k0, 1b
+# ifdef CONFIG_WEAK_REORDERING_BEYOND_LLSC
+	sync
+# endif
+
+	PTR_LA	k0, ejtag_debug_buffer
+	LONG_S	k1, 0(k0)
+
+	ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+	PTR_SRL	k1, SMP_CPUID_PTRSHIFT
+	PTR_SLL	k1, LONGLOG
+	PTR_LA	k0, ejtag_debug_buffer_per_cpu
+	PTR_ADDU k0, k1
+
+	PTR_LA	k1, ejtag_debug_buffer
+	LONG_L	k1, 0(k1)
+	LONG_S	k1, 0(k0)
+
+	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	sw	zero, 0(k0)
+#else
 	PTR_LA	k0, ejtag_debug_buffer
 	LONG_S	k1, 0(k0)
+#endif
+
 	SAVE_ALL
 	move	a0, sp
 	jal	ejtag_exception_handler
 	RESTORE_ALL
+
+#ifdef CONFIG_SMP
+	ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+	PTR_SRL	k1, SMP_CPUID_PTRSHIFT
+	PTR_SLL	k1, LONGLOG
+	PTR_LA	k0, ejtag_debug_buffer_per_cpu
+	PTR_ADDU k0, k1
+	LONG_L	k1, 0(k0)
+#else
 	PTR_LA	k0, ejtag_debug_buffer
 	LONG_L	k1, 0(k0)
+#endif
 
 ejtag_return:
+	back_to_back_c0_hazard
 	MFC0	k0, CP0_DESAVE
 	.set	mips32
 	deret
@@ -377,6 +417,12 @@ ejtag_return:
 	.data
 EXPORT(ejtag_debug_buffer)
 	.fill	LONGSIZE
+#ifdef CONFIG_SMP
+EXPORT(ejtag_debug_buffer_spinlock)
+	.fill	LONGSIZE
+EXPORT(ejtag_debug_buffer_per_cpu)
+	.fill	LONGSIZE * NR_CPUS
+#endif
 	.previous
 
 	__INIT
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 7c246b69c545..046846999efd 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -33,21 +33,21 @@
 void (*cpu_wait)(void);
 EXPORT_SYMBOL(cpu_wait);
 
-static void r3081_wait(void)
+static void __cpuidle r3081_wait(void)
 {
 	unsigned long cfg = read_c0_conf();
 	write_c0_conf(cfg | R30XX_CONF_HALT);
 	local_irq_enable();
 }
 
-static void r39xx_wait(void)
+static void __cpuidle r39xx_wait(void)
 {
 	if (!need_resched())
 		write_c0_conf(read_c0_conf() | TX39_CONF_HALT);
 	local_irq_enable();
 }
 
-void r4k_wait(void)
+void __cpuidle r4k_wait(void)
 {
 	local_irq_enable();
 	__r4k_wait();
@@ -60,7 +60,7 @@ void r4k_wait(void)
  * interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes
  * using this version a gamble.
  */
-void r4k_wait_irqoff(void)
+void __cpuidle r4k_wait_irqoff(void)
 {
 	if (!need_resched())
 		__asm__(
@@ -75,7 +75,7 @@ void r4k_wait_irqoff(void)
  * The RM7000 variant has to handle erratum 38.	 The workaround is to not
  * have any pending stores when the WAIT instruction is executed.
  */
-static void rm7k_wait_irqoff(void)
+static void __cpuidle rm7k_wait_irqoff(void)
 {
 	if (!need_resched())
 		__asm__(
@@ -96,7 +96,7 @@ static void rm7k_wait_irqoff(void)
  * since coreclock (and the cp0 counter) stops upon executing it. Only an
  * interrupt can wake it, so they must be enabled before entering idle modes.
  */
-static void au1k_wait(void)
+static void __cpuidle au1k_wait(void)
 {
 	unsigned long c0status = read_c0_status() | 1;	/* irqs on */
 
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index f5c8bce70db2..54cd675c5d1d 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -326,19 +326,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				preempt_enable_no_resched();
 			}
 			return 1;
-		} else {
-			if (addr->word != breakpoint_insn.word) {
-				/*
-				 * The breakpoint instruction was removed by
-				 * another cpu right after we hit, no further
-				 * handling of this interrupt is appropriate
-				 */
-				ret = 1;
-				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs))
-				goto ss_probe;
+		} else if (addr->word != breakpoint_insn.word) {
+			/*
+			 * The breakpoint instruction was removed by
+			 * another cpu right after we hit, no further
+			 * handling of this interrupt is appropriate
+			 */
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -364,10 +358,11 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
 	}
 
-ss_probe:
 	prepare_singlestep(p, regs, kcb);
 	if (kcb->flags & SKIP_DELAYSLOT) {
 		kcb->kprobe_status = KPROBE_HIT_SSDONE;
@@ -468,51 +463,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_sp = regs->regs[29];
-
-	memcpy(kcb->jprobes_stack, (void *)kcb->jprobe_saved_sp,
-	       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
-
-	regs->cp0_epc = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-/* Defined in the inline asm below. */
-void jprobe_return_end(void);
-
-void __kprobes jprobe_return(void)
-{
-	/* Assembler quirk necessitates this '0,code' business.	 */
-	asm volatile(
-		"break 0,%0\n\t"
-		".globl jprobe_return_end\n"
-		"jprobe_return_end:\n"
-		: : "n" (BRK_KPROBE_BP) : "memory");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (regs->cp0_epc >= (unsigned long)jprobe_return &&
-	    regs->cp0_epc <= (unsigned long)jprobe_return_end) {
-		*regs = kcb->jprobe_saved_regs;
-		memcpy((void *)kcb->jprobe_saved_sp, kcb->jprobes_stack,
-		       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
-		preempt_enable_no_resched();
-
-		return 1;
-	}
-	return 0;
-}
-
 /*
  * Function return probe trampoline:
  *	- init_kprobes() establishes a probepoint here
@@ -595,9 +545,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	instruction_pointer(regs) = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 318f1c05c5b3..6b61be486303 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -43,17 +43,6 @@
 #include <asm/mmu_context.h>
 #include <asm/mman.h>
 
-/* Use this to get at 32-bit user passed pointers. */
-/* A() macro should be used for places where you e.g.
-   have some internal variable u32 and just want to get
-   rid of a compiler warning. AA() has to be used in
-   places where you want to convert a function argument
-   to 32bit pointer or when you e.g. access pt_regs
-   structure and want to consider 32bit registers only.
- */
-#define A(__x) ((unsigned long)(__x))
-#define AA(__x) ((unsigned long)((int)__x))
-
 #ifdef __MIPSEB__
 #define merge_64(r1, r2) ((((r1) & 0xffffffffUL) << 32) + ((r2) & 0xffffffffUL))
 #endif
@@ -61,24 +50,6 @@
 #define merge_64(r1, r2) ((((r2) & 0xffffffffUL) << 32) + ((r1) & 0xffffffffUL))
 #endif
 
-SYSCALL_DEFINE6(32_mmap2, unsigned long, addr, unsigned long, len,
-	unsigned long, prot, unsigned long, flags, unsigned long, fd,
-	unsigned long, pgoff)
-{
-	if (pgoff & (~PAGE_MASK >> 12))
-		return -EINVAL;
-	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
-			       pgoff >> (PAGE_SHIFT-12));
-}
-
-#define RLIM_INFINITY32 0x7fffffff
-#define RESOURCE32(x) ((x > RLIM_INFINITY32) ? RLIM_INFINITY32 : x)
-
-struct rlimit32 {
-	int	rlim_cur;
-	int	rlim_max;
-};
-
 SYSCALL_DEFINE4(32_truncate64, const char __user *, path,
 	unsigned long, __dummy, unsigned long, a2, unsigned long, a3)
 {
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 9670e70139fd..8fc69891e117 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -30,6 +30,7 @@
 #include <linux/random.h>
 #include <linux/prctl.h>
 #include <linux/nmi.h>
+#include <linux/cpu.h>
 
 #include <asm/asm.h>
 #include <asm/bootinfo.h>
@@ -706,19 +707,25 @@ int mips_get_process_fp_mode(struct task_struct *task)
 	return value;
 }
 
-static void prepare_for_fp_mode_switch(void *info)
+static long prepare_for_fp_mode_switch(void *unused)
 {
-	struct mm_struct *mm = info;
-
-	if (current->mm == mm)
-		lose_fpu(1);
+	/*
+	 * This is icky, but we use this to simply ensure that all CPUs have
+	 * context switched, regardless of whether they were previously running
+	 * kernel or user code. This ensures that no CPU currently has its FPU
+	 * enabled, or is about to attempt to enable it through any path other
+	 * than enable_restore_fp_context() which will wait appropriately for
+	 * fp_mode_switching to be zero.
+	 */
+	return 0;
 }
 
 int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 {
 	const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE;
 	struct task_struct *t;
-	int max_users;
+	struct cpumask process_cpus;
+	int cpu;
 
 	/* If nothing to change, return right away, successfully.  */
 	if (value == mips_get_process_fp_mode(task))
@@ -751,35 +758,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 	if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
 		return -EOPNOTSUPP;
 
-	/* Proceed with the mode switch */
-	preempt_disable();
-
-	/* Save FP & vector context, then disable FPU & MSA */
-	if (task->signal == current->signal)
-		lose_fpu(1);
-
-	/* Prevent any threads from obtaining live FP context */
-	atomic_set(&task->mm->context.fp_mode_switching, 1);
-	smp_mb__after_atomic();
-
-	/*
-	 * If there are multiple online CPUs then force any which are running
-	 * threads in this process to lose their FPU context, which they can't
-	 * regain until fp_mode_switching is cleared later.
-	 */
-	if (num_online_cpus() > 1) {
-		/* No need to send an IPI for the local CPU */
-		max_users = (task->mm == current->mm) ? 1 : 0;
-
-		if (atomic_read(&current->mm->mm_users) > max_users)
-			smp_call_function(prepare_for_fp_mode_switch,
-					  (void *)current->mm, 1);
-	}
-
-	/*
-	 * There are now no threads of the process with live FP context, so it
-	 * is safe to proceed with the FP mode switch.
-	 */
+	/* Indicate the new FP mode in each thread */
 	for_each_thread(task, t) {
 		/* Update desired FP register width */
 		if (value & PR_FP_MODE_FR) {
@@ -796,9 +775,34 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 			clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
 	}
 
-	/* Allow threads to use FP again */
-	atomic_set(&task->mm->context.fp_mode_switching, 0);
-	preempt_enable();
+	/*
+	 * We need to ensure that all threads in the process have switched mode
+	 * before returning, in order to allow userland to not worry about
+	 * races. We can do this by forcing all CPUs that any thread in the
+	 * process may be running on to schedule something else - in this case
+	 * prepare_for_fp_mode_switch().
+	 *
+	 * We begin by generating a mask of all CPUs that any thread in the
+	 * process may be running on.
+	 */
+	cpumask_clear(&process_cpus);
+	for_each_thread(task, t)
+		cpumask_set_cpu(task_cpu(t), &process_cpus);
+
+	/*
+	 * Now we schedule prepare_for_fp_mode_switch() on each of those CPUs.
+	 *
+	 * The CPUs may have rescheduled already since we switched mode or
+	 * generated the cpumask, but that doesn't matter. If the task in this
+	 * process is scheduled out then our scheduling
+	 * prepare_for_fp_mode_switch() will simply be redundant. If it's
+	 * scheduled in then it will already have picked up the new FP mode
+	 * whilst doing so.
+	 */
+	get_online_cpus();
+	for_each_cpu_and(cpu, &process_cpus, cpu_online_mask)
+		work_on_cpu(cpu, prepare_for_fp_mode_switch, NULL);
+	put_online_cpus();
 
 	wake_up_var(&task->mm->context.fp_mode_switching);
 
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 9f6c3f2aa2e2..e5ba56c01ee0 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -41,6 +41,7 @@
 #include <asm/mipsmtregs.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
+#include <asm/processor.h>
 #include <asm/syscall.h>
 #include <linux/uaccess.h>
 #include <asm/bootinfo.h>
@@ -589,9 +590,226 @@ static int fpr_set(struct task_struct *target,
 	return err;
 }
 
+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
+/*
+ * Copy the DSP context to the supplied 32-bit NT_MIPS_DSP buffer.
+ */
+static int dsp32_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u32 dspregs[NUM_DSP_REGS + 1];
+
+	BUG_ON(count % sizeof(u32));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u32);
+	num_regs = count / sizeof(u32);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			dspregs[i] = target->thread.dsp.dspr[i];
+			break;
+		case NUM_DSP_REGS:
+			dspregs[i] = target->thread.dsp.dspcontrol;
+			break;
+		}
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				   sizeof(dspregs));
+}
+
+/*
+ * Copy the supplied 32-bit NT_MIPS_DSP buffer to the DSP context.
+ */
+static int dsp32_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u32 dspregs[NUM_DSP_REGS + 1];
+	int err;
+
+	BUG_ON(count % sizeof(u32));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u32);
+	num_regs = count / sizeof(u32);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				 sizeof(dspregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			target->thread.dsp.dspr[i] = (s32)dspregs[i];
+			break;
+		case NUM_DSP_REGS:
+			target->thread.dsp.dspcontrol = (s32)dspregs[i];
+			break;
+		}
+
+	return 0;
+}
+
+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Copy the DSP context to the supplied 64-bit NT_MIPS_DSP buffer.
+ */
+static int dsp64_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u64 dspregs[NUM_DSP_REGS + 1];
+
+	BUG_ON(count % sizeof(u64));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u64);
+	num_regs = count / sizeof(u64);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			dspregs[i] = target->thread.dsp.dspr[i];
+			break;
+		case NUM_DSP_REGS:
+			dspregs[i] = target->thread.dsp.dspcontrol;
+			break;
+		}
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				   sizeof(dspregs));
+}
+
+/*
+ * Copy the supplied 64-bit NT_MIPS_DSP buffer to the DSP context.
+ */
+static int dsp64_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u64 dspregs[NUM_DSP_REGS + 1];
+	int err;
+
+	BUG_ON(count % sizeof(u64));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u64);
+	num_regs = count / sizeof(u64);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				 sizeof(dspregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			target->thread.dsp.dspr[i] = dspregs[i];
+			break;
+		case NUM_DSP_REGS:
+			target->thread.dsp.dspcontrol = dspregs[i];
+			break;
+		}
+
+	return 0;
+}
+
+#endif /* CONFIG_64BIT */
+
+/*
+ * Determine whether the DSP context is present.
+ */
+static int dsp_active(struct task_struct *target,
+		      const struct user_regset *regset)
+{
+	return cpu_has_dsp ? NUM_DSP_REGS + 1 : -ENODEV;
+}
+
+/* Copy the FP mode setting to the supplied NT_MIPS_FP_MODE buffer.  */
+static int fp_mode_get(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       void *kbuf, void __user *ubuf)
+{
+	int fp_mode;
+
+	fp_mode = mips_get_process_fp_mode(target);
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fp_mode, 0,
+				   sizeof(fp_mode));
+}
+
+/*
+ * Copy the supplied NT_MIPS_FP_MODE buffer to the FP mode setting.
+ *
+ * We optimize for the case where `count % sizeof(int) == 0', which
+ * is supposed to have been guaranteed by the kernel before calling
+ * us, e.g. in `ptrace_regset'.  We enforce that requirement, so
+ * that we can safely avoid preinitializing temporaries for partial
+ * mode writes.
+ */
+static int fp_mode_set(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       const void *kbuf, const void __user *ubuf)
+{
+	int fp_mode;
+	int err;
+
+	BUG_ON(count % sizeof(int));
+
+	if (pos + count > sizeof(fp_mode))
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fp_mode, 0,
+				 sizeof(fp_mode));
+	if (err)
+		return err;
+
+	if (count > 0)
+		err = mips_set_process_fp_mode(target, fp_mode);
+
+	return err;
+}
+
 enum mips_regset {
 	REGSET_GPR,
 	REGSET_FPR,
+	REGSET_DSP,
+	REGSET_FP_MODE,
 };
 
 struct pt_regs_offset {
@@ -697,6 +915,23 @@ static const struct user_regset mips_regsets[] = {
 		.get		= fpr_get,
 		.set		= fpr_set,
 	},
+	[REGSET_DSP] = {
+		.core_note_type	= NT_MIPS_DSP,
+		.n		= NUM_DSP_REGS + 1,
+		.size		= sizeof(u32),
+		.align		= sizeof(u32),
+		.get		= dsp32_get,
+		.set		= dsp32_set,
+		.active		= dsp_active,
+	},
+	[REGSET_FP_MODE] = {
+		.core_note_type	= NT_MIPS_FP_MODE,
+		.n		= 1,
+		.size		= sizeof(int),
+		.align		= sizeof(int),
+		.get		= fp_mode_get,
+		.set		= fp_mode_set,
+	},
 };
 
 static const struct user_regset_view user_mips_view = {
@@ -728,6 +963,23 @@ static const struct user_regset mips64_regsets[] = {
 		.get		= fpr_get,
 		.set		= fpr_set,
 	},
+	[REGSET_DSP] = {
+		.core_note_type	= NT_MIPS_DSP,
+		.n		= NUM_DSP_REGS + 1,
+		.size		= sizeof(u64),
+		.align		= sizeof(u64),
+		.get		= dsp64_get,
+		.set		= dsp64_set,
+		.active		= dsp_active,
+	},
+	[REGSET_FP_MODE] = {
+		.core_note_type	= NT_MIPS_FP_MODE,
+		.n		= 1,
+		.size		= sizeof(int),
+		.align		= sizeof(int),
+		.get		= fp_mode_get,
+		.set		= fp_mode_set,
+	},
 };
 
 static const struct user_regset_view user_mips64_view = {
@@ -856,7 +1108,7 @@ long arch_ptrace(struct task_struct *child, long request,
 				goto out;
 			}
 			dregs = __get_dsp_regs(child);
-			tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+			tmp = dregs[addr - DSP_BASE];
 			break;
 		}
 		case DSP_CONTROL:
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 7edc629304c8..bc348d44d151 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -142,7 +142,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 				goto out;
 			}
 			dregs = __get_dsp_regs(child);
-			tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+			tmp = dregs[addr - DSP_BASE];
 			break;
 		}
 		case DSP_CONTROL:
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index c6bbf2165051..419c92197b2f 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -85,7 +85,7 @@ done:
 
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 	/* We need to flush I-cache before jumping to new kernel.
-	 * Unfortunatelly, this code is cpu-specific.
+	 * Unfortunately, this code is cpu-specific.
 	 */
 	.set push
 	.set noreorder
@@ -145,7 +145,7 @@ LEAF(kexec_smp_wait)
 #endif
 
 /* All parameters to new kernel are passed in registers a0-a3.
- * kexec_args[0..3] are uses to prepare register values.
+ * kexec_args[0..3] are used to prepare register values.
  */
 
 kexec_args:
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 2c96c0c68116..c71d1eb7da59 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -36,6 +36,7 @@
 #include <asm/cdmm.h>
 #include <asm/cpu.h>
 #include <asm/debug.h>
+#include <asm/dma-coherence.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp-ops.h>
@@ -84,6 +85,11 @@ static struct resource bss_resource = { .name = "Kernel bss", };
 
 static void *detect_magic __initdata = detect_memory_region;
 
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+unsigned long ARCH_PFN_OFFSET;
+EXPORT_SYMBOL(ARCH_PFN_OFFSET);
+#endif
+
 void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type)
 {
 	int x = boot_mem_map.nr_map;
@@ -441,6 +447,12 @@ static void __init bootmem_init(void)
 		mapstart = max(reserved_end, start);
 	}
 
+	if (min_low_pfn >= max_low_pfn)
+		panic("Incorrect memory mapping !!!");
+
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+	ARCH_PFN_OFFSET = PFN_UP(ramstart);
+#else
 	/*
 	 * Reserve any memory between the start of RAM and PHYS_OFFSET
 	 */
@@ -448,8 +460,6 @@ static void __init bootmem_init(void)
 		add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET,
 				  BOOT_MEM_RESERVED);
 
-	if (min_low_pfn >= max_low_pfn)
-		panic("Incorrect memory mapping !!!");
 	if (min_low_pfn > ARCH_PFN_OFFSET) {
 		pr_info("Wasting %lu bytes for tracking %lu unused pages\n",
 			(min_low_pfn - ARCH_PFN_OFFSET) * sizeof(struct page),
@@ -459,6 +469,7 @@ static void __init bootmem_init(void)
 			ARCH_PFN_OFFSET - min_low_pfn);
 	}
 	min_low_pfn = ARCH_PFN_OFFSET;
+#endif
 
 	/*
 	 * Determine low and high memory ranges
@@ -1055,3 +1066,26 @@ static int __init debugfs_mips(void)
 }
 arch_initcall(debugfs_mips);
 #endif
+
+#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
+/* User defined DMA coherency from command line. */
+enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
+EXPORT_SYMBOL_GPL(coherentio);
+int hw_coherentio = 0;	/* Actual hardware supported DMA coherency setting. */
+
+static int __init setcoherentio(char *str)
+{
+	coherentio = IO_COHERENCE_ENABLED;
+	pr_info("Hardware DMA cache coherency (command line)\n");
+	return 0;
+}
+early_param("coherentio", setcoherentio);
+
+static int __init setnocoherentio(char *str)
+{
+	coherentio = IO_COHERENCE_DISABLED;
+	pr_info("Software DMA cache coherency (command line)\n");
+	return 0;
+}
+early_param("nocoherentio", setnocoherentio);
+#endif
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 0a9cfe7a0372..109ed163a6a6 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -592,13 +592,15 @@ SYSCALL_DEFINE3(sigaction, int, sig, const struct sigaction __user *, act,
 #endif
 
 #ifdef CONFIG_TRAD_SIGNALS
-asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys_sigreturn(void)
 {
 	struct sigframe __user *frame;
+	struct pt_regs *regs;
 	sigset_t blocked;
 	int sig;
 
-	frame = (struct sigframe __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct sigframe __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&blocked, &frame->sf_mask, sizeof(blocked)))
@@ -606,7 +608,7 @@ asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&blocked);
 
-	sig = restore_sigcontext(&regs, &frame->sf_sc);
+	sig = restore_sigcontext(regs, &frame->sf_sc);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -618,8 +620,8 @@ asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
@@ -627,13 +629,15 @@ badframe:
 }
 #endif /* CONFIG_TRAD_SIGNALS */
 
-asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys_rt_sigreturn(void)
 {
 	struct rt_sigframe __user *frame;
+	struct pt_regs *regs;
 	sigset_t set;
 	int sig;
 
-	frame = (struct rt_sigframe __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct rt_sigframe __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&set, &frame->rs_uc.uc_sigmask, sizeof(set)))
@@ -641,7 +645,7 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&set);
 
-	sig = restore_sigcontext(&regs, &frame->rs_uc.uc_mcontext);
+	sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -656,8 +660,8 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c
index b672cebb4a1a..8f65aaf9206d 100644
--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@@ -64,13 +64,15 @@ struct rt_sigframe_n32 {
 	struct ucontextn32 rs_uc;
 };
 
-asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sysn32_rt_sigreturn(void)
 {
 	struct rt_sigframe_n32 __user *frame;
+	struct pt_regs *regs;
 	sigset_t set;
 	int sig;
 
-	frame = (struct rt_sigframe_n32 __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct rt_sigframe_n32 __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
@@ -78,7 +80,7 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&set);
 
-	sig = restore_sigcontext(&regs, &frame->rs_uc.uc_mcontext);
+	sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -93,8 +95,8 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
diff --git a/arch/mips/kernel/signal_o32.c b/arch/mips/kernel/signal_o32.c
index 2b3572fb5f1b..b6e3ddef48a0 100644
--- a/arch/mips/kernel/signal_o32.c
+++ b/arch/mips/kernel/signal_o32.c
@@ -151,13 +151,15 @@ static int setup_frame_32(void *sig_return, struct ksignal *ksig,
 	return 0;
 }
 
-asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys32_rt_sigreturn(void)
 {
 	struct rt_sigframe32 __user *frame;
+	struct pt_regs *regs;
 	sigset_t set;
 	int sig;
 
-	frame = (struct rt_sigframe32 __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct rt_sigframe32 __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
@@ -165,7 +167,7 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&set);
 
-	sig = restore_sigcontext32(&regs, &frame->rs_uc.uc_mcontext);
+	sig = restore_sigcontext32(regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -180,8 +182,8 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
@@ -251,13 +253,15 @@ struct mips_abi mips_abi_32 = {
 };
 
 
-asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys32_sigreturn(void)
 {
 	struct sigframe32 __user *frame;
+	struct pt_regs *regs;
 	sigset_t blocked;
 	int sig;
 
-	frame = (struct sigframe32 __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct sigframe32 __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask))
@@ -265,7 +269,7 @@ asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&blocked);
 
-	sig = restore_sigcontext32(&regs, &frame->sf_sc);
+	sig = restore_sigcontext32(regs, &frame->sf_sc);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -277,8 +281,8 @@ asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 8d505a21396e..f8871d5b7eb3 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1221,13 +1221,6 @@ static int enable_restore_fp_context(int msa)
 {
 	int err, was_fpu_owner, prior_msa;
 
-	/*
-	 * If an FP mode switch is currently underway, wait for it to
-	 * complete before proceeding.
-	 */
-	wait_var_event(&current->mm->context.fp_mode_switching,
-		       !atomic_read(&current->mm->context.fp_mode_switching));
-
 	if (!used_math()) {
 		/* First time FP context user. */
 		preempt_disable();
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 7cd76f93a438..f7ea8e21656b 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -515,7 +515,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 	dvcpu->arch.wait = 0;
 
 	if (swq_has_sleeper(&dvcpu->wq))
-		swake_up(&dvcpu->wq);
+		swake_up_one(&dvcpu->wq);
 
 	return 0;
 }
@@ -1204,7 +1204,7 @@ static void kvm_mips_comparecount_func(unsigned long data)
 
 	vcpu->arch.wait = 0;
 	if (swq_has_sleeper(&vcpu->wq))
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 }
 
 /* low level hrtimer wake routine */
diff --git a/arch/mips/lantiq/early_printk.c b/arch/mips/lantiq/early_printk.c
index 44bccaee822b..c4aa140b7c91 100644
--- a/arch/mips/lantiq/early_printk.c
+++ b/arch/mips/lantiq/early_printk.c
@@ -8,6 +8,7 @@
 
 #include <linux/cpu.h>
 #include <lantiq_soc.h>
+#include <asm/setup.h>
 
 #define ASC_BUF		1024
 #define LTQ_ASC_FSTAT	((u32 *)(LTQ_EARLY_ASC + 0x0048))
diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c
index 9ff7ccde9de0..d984bd5c2ec5 100644
--- a/arch/mips/lantiq/prom.c
+++ b/arch/mips/lantiq/prom.c
@@ -9,7 +9,6 @@
 #include <linux/export.h>
 #include <linux/clk.h>
 #include <linux/bootmem.h>
-#include <linux/of_platform.h>
 #include <linux/of_fdt.h>
 
 #include <asm/bootinfo.h>
@@ -114,10 +113,3 @@ void __init prom_init(void)
 		panic("failed to register_vsmp_smp_ops()");
 #endif
 }
-
-int __init plat_of_setup(void)
-{
-	return of_platform_default_populate(NULL, NULL, NULL);
-}
-
-arch_initcall(plat_of_setup);
diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c
index 805b3a6ab2d6..4b9fbb6744ad 100644
--- a/arch/mips/lantiq/xway/dma.c
+++ b/arch/mips/lantiq/xway/dma.c
@@ -130,10 +130,9 @@ ltq_dma_alloc(struct ltq_dma_channel *ch)
 	unsigned long flags;
 
 	ch->desc = 0;
-	ch->desc_base = dma_alloc_coherent(NULL,
+	ch->desc_base = dma_zalloc_coherent(NULL,
 				LTQ_DESC_NUM * LTQ_DESC_SIZE,
 				&ch->phys, GFP_ATOMIC);
-	memset(ch->desc_base, 0, LTQ_DESC_NUM * LTQ_DESC_SIZE);
 
 	spin_lock_irqsave(&ltq_dma_lock, flags);
 	ltq_dma_w32(ch->nr, LTQ_DMA_CS);
diff --git a/arch/mips/lasat/prom.c b/arch/mips/lasat/prom.c
index 17e15b50a551..37b8fc5b9ac9 100644
--- a/arch/mips/lasat/prom.c
+++ b/arch/mips/lasat/prom.c
@@ -13,6 +13,7 @@
 #include <asm/bootinfo.h>
 #include <asm/lasat/lasat.h>
 #include <asm/cpu.h>
+#include <asm/setup.h>
 
 #include "at93c.h"
 #include <asm/lasat/eeprom.h>
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 1cc306520a55..3a6f34ef5ffc 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -195,6 +195,7 @@
 #endif
 #else
 	 PTR_SUBU	t0, $0, a2
+	move		a2, zero		/* No remaining longs */
 	PTR_ADDIU	t0, 1
 	STORE_BYTE(0)
 	STORE_BYTE(1)
@@ -231,16 +232,25 @@
 
 #ifdef CONFIG_CPU_MIPSR6
 .Lbyte_fixup\@:
-	PTR_SUBU	a2, $0, t0
+	/*
+	 * unset_bytes = (#bytes - (#unaligned bytes)) - (-#unaligned bytes remaining + 1) + 1
+	 *      a2     =             a2                -              t0                   + 1
+	 */
+	PTR_SUBU	a2, t0
 	jr		ra
 	 PTR_ADDIU	a2, 1
 #endif /* CONFIG_CPU_MIPSR6 */
 
 .Lfirst_fixup\@:
+	/* unset_bytes already in a2 */
 	jr	ra
 	 nop
 
 .Lfwd_fixup\@:
+	/*
+	 * unset_bytes = partial_start_addr +  #bytes   -     fault_addr
+	 *      a2     =         t1         + (a2 & 3f) - $28->task->BUADDR
+	 */
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, 0x3f
 	LONG_L		t0, THREAD_BUADDR(t0)
@@ -249,6 +259,10 @@
 	 LONG_SUBU	a2, t0
 
 .Lpartial_fixup\@:
+	/*
+	 * unset_bytes = partial_end_addr +      #bytes     -     fault_addr
+	 *      a2     =       a0         + (a2 & STORMASK) - $28->task->BUADDR
+	 */
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, STORMASK
 	LONG_L		t0, THREAD_BUADDR(t0)
@@ -257,10 +271,15 @@
 	 LONG_SUBU	a2, t0
 
 .Llast_fixup\@:
+	/* unset_bytes already in a2 */
 	jr		ra
 	 nop
 
 .Lsmall_fixup\@:
+	/*
+	 * unset_bytes = end_addr - current_addr + 1
+	 *      a2     =    t1    -      a0      + 1
+	 */
 	PTR_SUBU	a2, t1, a0
 	jr		ra
 	 PTR_ADDIU	a2, 1
diff --git a/arch/mips/loongson32/Platform b/arch/mips/loongson32/Platform
index ffe01c6d0037..a0dbb3b2f2de 100644
--- a/arch/mips/loongson32/Platform
+++ b/arch/mips/loongson32/Platform
@@ -1,8 +1,4 @@
-cflags-$(CONFIG_CPU_LOONGSON1)	+= \
-	$(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
-	-Wa,-mips32r2 -Wa,--trap
-
+cflags-$(CONFIG_CPU_LOONGSON1)		+= -march=mips32 -Wa,--trap
 platform-$(CONFIG_MACH_LOONGSON32)	+= loongson32/
 cflags-$(CONFIG_MACH_LOONGSON32)	+= -I$(srctree)/arch/mips/include/asm/mach-loongson32
-load-$(CONFIG_LOONGSON1_LS1B)		+= 0xffffffff80100000
-load-$(CONFIG_LOONGSON1_LS1C)		+= 0xffffffff80100000
+load-$(CONFIG_CPU_LOONGSON1)		+= 0xffffffff80100000
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index c79e6a565572..c865b4b9b775 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -91,7 +91,6 @@ config LOONGSON_MACH3X
 	select LOONGSON_MC146818
 	select ZONE_DMA32
 	select LEFI_FIRMWARE_INTERFACE
-	select PHYS48_TO_HT40
 	help
 		Generic Loongson 3 family machines utilize the 3A/3B revision
 		of Loongson processor and RS780/SBX00 chipset.
@@ -130,10 +129,6 @@ config LOONGSON_UART_BASE
 	default y
 	depends on EARLY_PRINTK || SERIAL_8250
 
-config PHYS48_TO_HT40
-	bool
-	default y if CPU_LOONGSON3
-
 config LOONGSON_MC146818
 	bool
 	default n
diff --git a/arch/mips/loongson64/common/Makefile b/arch/mips/loongson64/common/Makefile
index 8235ac7eac95..57ee03022941 100644
--- a/arch/mips/loongson64/common/Makefile
+++ b/arch/mips/loongson64/common/Makefile
@@ -6,6 +6,7 @@
 obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
     bonito-irq.o mem.o machtype.o platform.o serial.o
 obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_CPU_LOONGSON2) += dma.o
 
 #
 # Serial port support
@@ -25,8 +26,3 @@ obj-$(CONFIG_CS5536) += cs5536/
 #
 
 obj-$(CONFIG_SUSPEND) += pm.o
-
-#
-# Big Memory (SWIOTLB) Support
-#
-obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c b/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
index f7c905e50dc4..92dc6bafc127 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
+++ b/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
@@ -138,7 +138,7 @@ u32 pci_ohci_read_reg(int reg)
 		break;
 	case PCI_OHCI_INT_REG:
 		_rdmsr(DIVIL_MSR_REG(PIC_YSEL_LOW), &hi, &lo);
-		if ((lo & 0x00000f00) == CS5536_USB_INTR)
+		if (((lo >> PIC_YSEL_LOW_USB_SHIFT) & 0xf) == CS5536_USB_INTR)
 			conf_data = 1;
 		break;
 	default:
diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
deleted file mode 100644
index 6a739f8ae110..000000000000
--- a/arch/mips/loongson64/common/dma-swiotlb.c
+++ /dev/null
@@ -1,109 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/mm.h>
-#include <linux/init.h>
-#include <linux/dma-mapping.h>
-#include <linux/scatterlist.h>
-#include <linux/swiotlb.h>
-#include <linux/bootmem.h>
-
-#include <asm/bootinfo.h>
-#include <boot_param.h>
-#include <dma-coherence.h>
-
-static void *loongson_dma_alloc_coherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
-
-	mb();
-	return ret;
-}
-
-static dma_addr_t loongson_dma_map_page(struct device *dev, struct page *page,
-				unsigned long offset, size_t size,
-				enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
-					dir, attrs);
-	mb();
-	return daddr;
-}
-
-static int loongson_dma_map_sg(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, attrs);
-	mb();
-
-	return r;
-}
-
-static void loongson_dma_sync_single_for_device(struct device *dev,
-				dma_addr_t dma_handle, size_t size,
-				enum dma_data_direction dir)
-{
-	swiotlb_sync_single_for_device(dev, dma_handle, size, dir);
-	mb();
-}
-
-static void loongson_dma_sync_sg_for_device(struct device *dev,
-				struct scatterlist *sg, int nents,
-				enum dma_data_direction dir)
-{
-	swiotlb_sync_sg_for_device(dev, sg, nents, dir);
-	mb();
-}
-
-static int loongson_dma_supported(struct device *dev, u64 mask)
-{
-	if (mask > DMA_BIT_MASK(loongson_sysconf.dma_mask_bits))
-		return 0;
-	return swiotlb_dma_supported(dev, mask);
-}
-
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	long nid;
-#ifdef CONFIG_PHYS48_TO_HT40
-	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
-	 * Loongson-3's 48bit address space and embed it into 40bit */
-	nid = (paddr >> 44) & 0x3;
-	paddr = ((nid << 44) ^ paddr) | (nid << 37);
-#endif
-	return paddr;
-}
-
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	long nid;
-#ifdef CONFIG_PHYS48_TO_HT40
-	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
-	 * Loongson-3's 48bit address space and embed it into 40bit */
-	nid = (daddr >> 37) & 0x3;
-	daddr = ((nid << 37) ^ daddr) | (nid << 44);
-#endif
-	return daddr;
-}
-
-static const struct dma_map_ops loongson_dma_map_ops = {
-	.alloc = loongson_dma_alloc_coherent,
-	.free = swiotlb_free,
-	.map_page = loongson_dma_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.map_sg = loongson_dma_map_sg,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = loongson_dma_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = loongson_dma_sync_sg_for_device,
-	.mapping_error = swiotlb_dma_mapping_error,
-	.dma_supported = loongson_dma_supported,
-};
-
-void __init plat_swiotlb_setup(void)
-{
-	swiotlb_init(1);
-	mips_dma_map_ops = &loongson_dma_map_ops;
-}
diff --git a/arch/mips/loongson64/common/dma.c b/arch/mips/loongson64/common/dma.c
new file mode 100644
index 000000000000..48f04126bde2
--- /dev/null
+++ b/arch/mips/loongson64/common/dma.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-direct.h>
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr | 0x80000000;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+#if defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
+	if (dma_addr > 0x8fffffff)
+		return dma_addr;
+	return dma_addr & 0x0fffffff;
+#else
+	return dma_addr & 0x7fffffff;
+#endif
+}
diff --git a/arch/mips/loongson64/common/early_printk.c b/arch/mips/loongson64/common/early_printk.c
index 6ca632e529dc..a782e2b24747 100644
--- a/arch/mips/loongson64/common/early_printk.c
+++ b/arch/mips/loongson64/common/early_printk.c
@@ -10,6 +10,7 @@
  *  option) any later version.
  */
 #include <linux/serial_reg.h>
+#include <asm/setup.h>
 
 #include <loongson.h>
 
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c
index 1e8a955ae5a8..8f68ee02a8c2 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/common/env.c
@@ -198,7 +198,8 @@ void __init prom_init_env(void)
 			break;
 		case PRID_REV_LOONGSON3A_R1:
 		case PRID_REV_LOONGSON3A_R2:
-		case PRID_REV_LOONGSON3A_R3:
+		case PRID_REV_LOONGSON3A_R3_0:
+		case PRID_REV_LOONGSON3A_R3_1:
 			cpu_clock_freq = 900000000;
 			break;
 		case PRID_REV_LOONGSON3B_R1:
diff --git a/arch/mips/loongson64/loongson-3/Makefile b/arch/mips/loongson64/loongson-3/Makefile
index 44bc1482158b..b5a0c2fa5446 100644
--- a/arch/mips/loongson64/loongson-3/Makefile
+++ b/arch/mips/loongson64/loongson-3/Makefile
@@ -1,7 +1,7 @@
 #
 # Makefile for Loongson-3 family machines
 #
-obj-y			+= irq.o cop2-ex.o platform.o acpi_init.o
+obj-y			+= irq.o cop2-ex.o platform.o acpi_init.o dma.o
 
 obj-$(CONFIG_SMP)	+= smp.o
 
diff --git a/arch/mips/loongson64/loongson-3/dma.c b/arch/mips/loongson64/loongson-3/dma.c
new file mode 100644
index 000000000000..5e86635f71db
--- /dev/null
+++ b/arch/mips/loongson64/loongson-3/dma.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-direct.h>
+#include <linux/init.h>
+#include <linux/swiotlb.h>
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
+	 * Loongson-3's 48bit address space and embed it into 40bit */
+	long nid = (paddr >> 44) & 0x3;
+	return ((nid << 44) ^ paddr) | (nid << 37);
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
+	 * Loongson-3's 48bit address space and embed it into 40bit */
+	long nid = (daddr >> 37) & 0x3;
+	return ((nid << 37) ^ daddr) | (nid << 44);
+}
+
+void __init plat_swiotlb_setup(void)
+{
+	swiotlb_init(1);
+}
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index 8501109bb0f0..fea95d003269 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -682,7 +682,8 @@ void play_dead(void)
 			(void *)CKSEG1ADDR((unsigned long)loongson3a_r1_play_dead);
 		break;
 	case PRID_REV_LOONGSON3A_R2:
-	case PRID_REV_LOONGSON3A_R3:
+	case PRID_REV_LOONGSON3A_R3_0:
+	case PRID_REV_LOONGSON3A_R3_1:
 		play_dead_at_ckseg1 =
 			(void *)CKSEG1ADDR((unsigned long)loongson3a_r2r3_play_dead);
 		break;
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index c463bdad45c7..3e5bb203c95a 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the Linux/MIPS-specific parts of the memory manager.
 #
 
-obj-y				+= cache.o dma-default.o extable.o fault.o \
+obj-y				+= cache.o extable.o fault.o \
 				   gup.o init.o mmap.o page.o page-funcs.o \
 				   pgtable.o tlbex.o tlbex-fault.o tlb-funcs.o
 
@@ -17,6 +17,7 @@ obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-noncoherent.o
 
 obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o
 obj-$(CONFIG_CPU_R3000)		+= c-r3k.o tlb-r3k.o
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index e12dfa48b478..a9ef057c79fe 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -830,12 +830,13 @@ static void r4k_flush_icache_user_range(unsigned long start, unsigned long end)
 	return __r4k_flush_icache_range(start, end, true);
 }
 
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
@@ -871,7 +872,8 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
@@ -904,7 +906,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 	bc_inv(addr, size);
 	__sync();
 }
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 struct flush_cache_sigtramp_args {
 	struct mm_struct *mm;
@@ -1505,6 +1507,14 @@ static void probe_pcache(void)
 	if (c->dcache.flags & MIPS_CACHE_PINDEX)
 		c->dcache.flags &= ~MIPS_CACHE_ALIASES;
 
+	/*
+	 * In systems with CM the icache fills from L2 or closer caches, and
+	 * thus sees remote stores without needing to write them back any
+	 * further than that.
+	 */
+	if (mips_cm_present())
+		c->icache.flags |= MIPS_IC_SNOOPS_REMOTE;
+
 	switch (current_cpu_type()) {
 	case CPU_20KC:
 		/*
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 0d3c656feba0..70a523151ff3 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(local_flush_data_cache_page);
 EXPORT_SYMBOL(flush_data_cache_page);
 EXPORT_SYMBOL(flush_icache_all);
 
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 /* DMA cache operations. */
 void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
@@ -65,7 +65,7 @@ void (*_dma_cache_inv)(unsigned long start, unsigned long size);
 
 EXPORT_SYMBOL(_dma_cache_wback_inv);
 
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 /*
  * We could optimize the case where the cache argument is not BCACHE but
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
deleted file mode 100644
index f9fef0028ca2..000000000000
--- a/arch/mips/mm/dma-default.c
+++ /dev/null
@@ -1,404 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
- * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
- * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
- */
-
-#include <linux/types.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/export.h>
-#include <linux/scatterlist.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/highmem.h>
-#include <linux/dma-contiguous.h>
-
-#include <asm/cache.h>
-#include <asm/cpu-type.h>
-#include <asm/io.h>
-
-#include <dma-coherence.h>
-
-#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
-/* User defined DMA coherency from command line. */
-enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
-EXPORT_SYMBOL_GPL(coherentio);
-int hw_coherentio = 0;	/* Actual hardware supported DMA coherency setting. */
-
-static int __init setcoherentio(char *str)
-{
-	coherentio = IO_COHERENCE_ENABLED;
-	pr_info("Hardware DMA cache coherency (command line)\n");
-	return 0;
-}
-early_param("coherentio", setcoherentio);
-
-static int __init setnocoherentio(char *str)
-{
-	coherentio = IO_COHERENCE_DISABLED;
-	pr_info("Software DMA cache coherency (command line)\n");
-	return 0;
-}
-early_param("nocoherentio", setnocoherentio);
-#endif
-
-static inline struct page *dma_addr_to_page(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return pfn_to_page(
-		plat_dma_addr_to_phys(dev, dma_addr) >> PAGE_SHIFT);
-}
-
-/*
- * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
- * speculatively fill random cachelines with stale data at any time,
- * requiring an extra flush post-DMA.
- *
- * Warning on the terminology - Linux calls an uncached area coherent;
- * MIPS terminology calls memory areas with hardware maintained coherency
- * coherent.
- *
- * Note that the R14000 and R16000 should also be checked for in this
- * condition.  However this function is only called on non-I/O-coherent
- * systems and only the R10000 and R12000 are used in such systems, the
- * SGI IP28 Indigo² rsp. SGI IP32 aka O2.
- */
-static inline bool cpu_needs_post_dma_flush(struct device *dev)
-{
-	if (plat_device_is_coherent(dev))
-		return false;
-
-	switch (boot_cpu_type()) {
-	case CPU_R10000:
-	case CPU_R12000:
-	case CPU_BMIPS5000:
-		return true;
-
-	default:
-		/*
-		 * Presence of MAARs suggests that the CPU supports
-		 * speculatively prefetching data, and therefore requires
-		 * the post-DMA flush/invalidate.
-		 */
-		return cpu_has_maar;
-	}
-}
-
-static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
-{
-	gfp_t dma_flag;
-
-#ifdef CONFIG_ISA
-	if (dev == NULL)
-		dma_flag = __GFP_DMA;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && defined(CONFIG_ZONE_DMA)
-	     if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(32))
-			dma_flag = __GFP_DMA;
-	else if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
-			dma_flag = __GFP_DMA32;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_ZONE_DMA)
-	     if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(64))
-		dma_flag = __GFP_DMA32;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
-	     if (dev == NULL ||
-		 dev->coherent_dma_mask < DMA_BIT_MASK(sizeof(phys_addr_t) * 8))
-		dma_flag = __GFP_DMA;
-	else
-#endif
-		dma_flag = 0;
-
-	/* Don't invoke OOM killer */
-	gfp |= __GFP_NORETRY;
-
-	return gfp | dma_flag;
-}
-
-static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret;
-	struct page *page = NULL;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	gfp = massage_gfp_flags(dev, gfp);
-
-	if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
-		page = dma_alloc_from_contiguous(dev, count, get_order(size),
-						 gfp);
-	if (!page)
-		page = alloc_pages(gfp, get_order(size));
-
-	if (!page)
-		return NULL;
-
-	ret = page_address(page);
-	memset(ret, 0, size);
-	*dma_handle = plat_map_dma_mem(dev, ret, size);
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT) &&
-	    !plat_device_is_coherent(dev)) {
-		dma_cache_wback_inv((unsigned long) ret, size);
-		ret = UNCAC_ADDR(ret);
-	}
-
-	return ret;
-}
-
-static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-	dma_addr_t dma_handle, unsigned long attrs)
-{
-	unsigned long addr = (unsigned long) vaddr;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct page *page = NULL;
-
-	plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
-
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !plat_device_is_coherent(dev))
-		addr = CAC_ADDR(addr);
-
-	page = virt_to_page((void *) addr);
-
-	if (!dma_release_from_contiguous(dev, page, count))
-		__free_pages(page, get_order(size));
-}
-
-static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-	void *cpu_addr, dma_addr_t dma_addr, size_t size,
-	unsigned long attrs)
-{
-	unsigned long user_count = vma_pages(vma);
-	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long addr = (unsigned long)cpu_addr;
-	unsigned long off = vma->vm_pgoff;
-	unsigned long pfn;
-	int ret = -ENXIO;
-
-	if (!plat_device_is_coherent(dev))
-		addr = CAC_ADDR(addr);
-
-	pfn = page_to_pfn(virt_to_page((void *)addr));
-
-	if (attrs & DMA_ATTR_WRITE_COMBINE)
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-	else
-		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
-	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
-		return ret;
-
-	if (off < count && user_count <= (count - off)) {
-		ret = remap_pfn_range(vma, vma->vm_start,
-				      pfn + off,
-				      user_count << PAGE_SHIFT,
-				      vma->vm_page_prot);
-	}
-
-	return ret;
-}
-
-static inline void __dma_sync_virtual(void *addr, size_t size,
-	enum dma_data_direction direction)
-{
-	switch (direction) {
-	case DMA_TO_DEVICE:
-		dma_cache_wback((unsigned long)addr, size);
-		break;
-
-	case DMA_FROM_DEVICE:
-		dma_cache_inv((unsigned long)addr, size);
-		break;
-
-	case DMA_BIDIRECTIONAL:
-		dma_cache_wback_inv((unsigned long)addr, size);
-		break;
-
-	default:
-		BUG();
-	}
-}
-
-/*
- * A single sg entry may refer to multiple physically contiguous
- * pages. But we still need to process highmem pages individually.
- * If highmem is not configured then the bulk of this loop gets
- * optimized out.
- */
-static inline void __dma_sync(struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction)
-{
-	size_t left = size;
-
-	do {
-		size_t len = left;
-
-		if (PageHighMem(page)) {
-			void *addr;
-
-			if (offset + len > PAGE_SIZE) {
-				if (offset >= PAGE_SIZE) {
-					page += offset >> PAGE_SHIFT;
-					offset &= ~PAGE_MASK;
-				}
-				len = PAGE_SIZE - offset;
-			}
-
-			addr = kmap_atomic(page);
-			__dma_sync_virtual(addr + offset, len, direction);
-			kunmap_atomic(addr);
-		} else
-			__dma_sync_virtual(page_address(page) + offset,
-					   size, direction);
-		offset = 0;
-		page++;
-		left -= len;
-	} while (left);
-}
-
-static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction, unsigned long attrs)
-{
-	if (cpu_needs_post_dma_flush(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(dma_addr_to_page(dev, dma_addr),
-			   dma_addr & ~PAGE_MASK, size, direction);
-	plat_post_dma_flush(dev);
-	plat_unmap_dma_mem(dev, dma_addr, size, direction);
-}
-
-static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-	int nents, enum dma_data_direction direction, unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		if (!plat_device_is_coherent(dev) &&
-		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		sg->dma_length = sg->length;
-#endif
-		sg->dma_address = plat_map_dma_mem_page(dev, sg_page(sg)) +
-				  sg->offset;
-	}
-
-	return nents;
-}
-
-static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	if (!plat_device_is_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(page, offset, size, direction);
-
-	return plat_map_dma_mem_page(dev, page) + offset;
-}
-
-static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-	int nhwentries, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nhwentries, i) {
-		if (!plat_device_is_coherent(dev) &&
-		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-		    direction != DMA_TO_DEVICE)
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		plat_unmap_dma_mem(dev, sg->dma_address, sg->length, direction);
-	}
-}
-
-static void mips_dma_sync_single_for_cpu(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	if (cpu_needs_post_dma_flush(dev))
-		__dma_sync(dma_addr_to_page(dev, dma_handle),
-			   dma_handle & ~PAGE_MASK, size, direction);
-	plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_single_for_device(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	if (!plat_device_is_coherent(dev))
-		__dma_sync(dma_addr_to_page(dev, dma_handle),
-			   dma_handle & ~PAGE_MASK, size, direction);
-}
-
-static void mips_dma_sync_sg_for_cpu(struct device *dev,
-	struct scatterlist *sglist, int nelems,
-	enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	if (cpu_needs_post_dma_flush(dev)) {
-		for_each_sg(sglist, sg, nelems, i) {
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		}
-	}
-	plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_sg_for_device(struct device *dev,
-	struct scatterlist *sglist, int nelems,
-	enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	if (!plat_device_is_coherent(dev)) {
-		for_each_sg(sglist, sg, nelems, i) {
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		}
-	}
-}
-
-static int mips_dma_supported(struct device *dev, u64 mask)
-{
-	return plat_dma_supported(dev, mask);
-}
-
-static void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-			 enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	if (!plat_device_is_coherent(dev))
-		__dma_sync_virtual(vaddr, size, direction);
-}
-
-static const struct dma_map_ops mips_default_dma_map_ops = {
-	.alloc = mips_dma_alloc_coherent,
-	.free = mips_dma_free_coherent,
-	.mmap = mips_dma_mmap,
-	.map_page = mips_dma_map_page,
-	.unmap_page = mips_dma_unmap_page,
-	.map_sg = mips_dma_map_sg,
-	.unmap_sg = mips_dma_unmap_sg,
-	.sync_single_for_cpu = mips_dma_sync_single_for_cpu,
-	.sync_single_for_device = mips_dma_sync_single_for_device,
-	.sync_sg_for_cpu = mips_dma_sync_sg_for_cpu,
-	.sync_sg_for_device = mips_dma_sync_sg_for_device,
-	.dma_supported = mips_dma_supported,
-	.cache_sync = mips_dma_cache_sync,
-};
-
-const struct dma_map_ops *mips_dma_map_ops = &mips_default_dma_map_ops;
-EXPORT_SYMBOL(mips_dma_map_ops);
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
new file mode 100644
index 000000000000..2aca1236af36
--- /dev/null
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
+ * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
+ * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
+ */
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/dma-contiguous.h>
+#include <linux/highmem.h>
+
+#include <asm/cache.h>
+#include <asm/cpu-type.h>
+#include <asm/dma-coherence.h>
+#include <asm/io.h>
+
+#ifdef CONFIG_DMA_PERDEV_COHERENT
+static inline int dev_is_coherent(struct device *dev)
+{
+	return dev->archdata.dma_coherent;
+}
+#else
+static inline int dev_is_coherent(struct device *dev)
+{
+	switch (coherentio) {
+	default:
+	case IO_COHERENCE_DEFAULT:
+		return hw_coherentio;
+	case IO_COHERENCE_ENABLED:
+		return 1;
+	case IO_COHERENCE_DISABLED:
+		return 0;
+	}
+}
+#endif /* CONFIG_DMA_PERDEV_COHERENT */
+
+/*
+ * The affected CPUs below in 'cpu_needs_post_dma_flush()' can speculatively
+ * fill random cachelines with stale data at any time, requiring an extra
+ * flush post-DMA.
+ *
+ * Warning on the terminology - Linux calls an uncached area coherent;  MIPS
+ * terminology calls memory areas with hardware maintained coherency coherent.
+ *
+ * Note that the R14000 and R16000 should also be checked for in this condition.
+ * However this function is only called on non-I/O-coherent systems and only the
+ * R10000 and R12000 are used in such systems, the SGI IP28 Indigo² rsp.
+ * SGI IP32 aka O2.
+ */
+static inline bool cpu_needs_post_dma_flush(struct device *dev)
+{
+	if (dev_is_coherent(dev))
+		return false;
+
+	switch (boot_cpu_type()) {
+	case CPU_R10000:
+	case CPU_R12000:
+	case CPU_BMIPS5000:
+		return true;
+	default:
+		/*
+		 * Presence of MAARs suggests that the CPU supports
+		 * speculatively prefetching data, and therefore requires
+		 * the post-DMA flush/invalidate.
+		 */
+		return cpu_has_maar;
+	}
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	void *ret;
+
+	ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+	if (!ret)
+		return NULL;
+
+	if (!dev_is_coherent(dev) && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
+		dma_cache_wback_inv((unsigned long) ret, size);
+		ret = (void *)UNCAC_ADDR(ret);
+	}
+
+	return ret;
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs)
+{
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !dev_is_coherent(dev))
+		cpu_addr = (void *)CAC_ADDR((unsigned long)cpu_addr);
+	dma_direct_free(dev, size, cpu_addr, dma_addr, attrs);
+}
+
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	unsigned long user_count = vma_pages(vma);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)cpu_addr;
+	unsigned long off = vma->vm_pgoff;
+	unsigned long pfn;
+	int ret = -ENXIO;
+
+	if (!dev_is_coherent(dev))
+		addr = CAC_ADDR(addr);
+
+	pfn = page_to_pfn(virt_to_page((void *)addr));
+
+	if (attrs & DMA_ATTR_WRITE_COMBINE)
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < count && user_count <= (count - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      user_count << PAGE_SHIFT,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
+static inline void dma_sync_virt(void *addr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_wback((unsigned long)addr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		dma_cache_inv((unsigned long)addr, size);
+		break;
+
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv((unsigned long)addr, size);
+		break;
+
+	default:
+		BUG();
+	}
+}
+
+/*
+ * A single sg entry may refer to multiple physically contiguous pages.  But
+ * we still need to process highmem pages individually.  If highmem is not
+ * configured then the bulk of this loop gets optimized out.
+ */
+static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	unsigned long offset = paddr & ~PAGE_MASK;
+	size_t left = size;
+
+	do {
+		size_t len = left;
+
+		if (PageHighMem(page)) {
+			void *addr;
+
+			if (offset + len > PAGE_SIZE) {
+				if (offset >= PAGE_SIZE) {
+					page += offset >> PAGE_SHIFT;
+					offset &= ~PAGE_MASK;
+				}
+				len = PAGE_SIZE - offset;
+			}
+
+			addr = kmap_atomic(page);
+			dma_sync_virt(addr + offset, len, dir);
+			kunmap_atomic(addr);
+		} else
+			dma_sync_virt(page_address(page) + offset, size, dir);
+		offset = 0;
+		page++;
+		left -= len;
+	} while (left);
+}
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (!dev_is_coherent(dev))
+		dma_sync_phys(paddr, size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (cpu_needs_post_dma_flush(dev))
+		dma_sync_phys(paddr, size, dir);
+}
+
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		enum dma_data_direction direction)
+{
+	BUG_ON(direction == DMA_NONE);
+
+	if (!dev_is_coherent(dev))
+		dma_sync_virt(vaddr, size, direction);
+}
diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index d5d02993aa21..56e4f8bffd4c 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -623,21 +623,6 @@ struct dmadscr {
 	u64 pad_b;
 } ____cacheline_aligned_in_smp page_descr[DM_NUM_CHANNELS];
 
-void sb1_dma_init(void)
-{
-	int i;
-
-	for (i = 0; i < DM_NUM_CHANNELS; i++) {
-		const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) |
-				     V_DM_DSCR_BASE_RINGSZ(1);
-		void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE));
-
-		__raw_writeq(base_val, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg);
-	}
-}
-
 void clear_page(void *page)
 {
 	u64 to_phys = CPHYSADDR((unsigned long)page);
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 79b9f2ad3ff5..49312a14cd17 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1509,7 +1509,7 @@ static void setup_pw(void)
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	write_c0_pwctl(1 << 6 | psn);
 #endif
-	write_c0_kpgd(swapper_pg_dir);
+	write_c0_kpgd((long)swapper_pg_dir);
 	kscratch_used_mask |= (1 << 7); /* KScratch6 is used for KPGD */
 }
 
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index 9bb6baa45da3..24e5b0d06899 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -19,7 +19,6 @@
 #include <asm/inst.h>
 #include <asm/elf.h>
 #include <asm/bugs.h>
-#define UASM_ISA	_UASM_ISA_MICROMIPS
 #include <asm/uasm.h>
 
 #define RS_MASK		0x1f
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 9fea6c6bbf49..60ceb93c71a0 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -19,7 +19,6 @@
 #include <asm/inst.h>
 #include <asm/elf.h>
 #include <asm/bugs.h>
-#define UASM_ISA	_UASM_ISA_CLASSIC
 #include <asm/uasm.h>
 
 #define RS_MASK		0x1f
diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile
index 63940bdce698..17c7fd471a27 100644
--- a/arch/mips/mti-malta/Makefile
+++ b/arch/mips/mti-malta/Makefile
@@ -13,11 +13,9 @@ obj-y				+= malta-init.o
 obj-y				+= malta-int.o
 obj-y				+= malta-memory.o
 obj-y				+= malta-platform.o
-obj-y				+= malta-reset.o
 obj-y				+= malta-setup.o
 obj-y				+= malta-time.o
 
 obj-$(CONFIG_MIPS_CMP)		+= malta-amon.o
-obj-$(CONFIG_MIPS_MALTA_PM)	+= malta-pm.o
 
 CFLAGS_malta-dtshim.o = -I$(src)/../../../scripts/dtc/libfdt
diff --git a/arch/mips/mti-malta/malta-pm.c b/arch/mips/mti-malta/malta-pm.c
deleted file mode 100644
index efbd659fb602..000000000000
--- a/arch/mips/mti-malta/malta-pm.c
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * Copyright (C) 2014 Imagination Technologies
- * Author: Paul Burton <paul.burton@mips.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/delay.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/pci.h>
-
-#include <asm/mach-malta/malta-pm.h>
-
-static struct pci_bus *pm_pci_bus;
-static resource_size_t pm_io_offset;
-
-int mips_pm_suspend(unsigned state)
-{
-	int spec_devid;
-	u16 sts;
-
-	if (!pm_pci_bus || !pm_io_offset)
-		return -ENODEV;
-
-	/* Ensure the power button status is clear */
-	while (1) {
-		sts = inw(pm_io_offset + PIIX4_FUNC3IO_PMSTS);
-		if (!(sts & PIIX4_FUNC3IO_PMSTS_PWRBTN_STS))
-			break;
-		outw(sts, pm_io_offset + PIIX4_FUNC3IO_PMSTS);
-	}
-
-	/* Enable entry to suspend */
-	outw(state | PIIX4_FUNC3IO_PMCNTRL_SUS_EN,
-	     pm_io_offset + PIIX4_FUNC3IO_PMCNTRL);
-
-	/* If the special cycle occurs too soon this doesn't work... */
-	mdelay(10);
-
-	/*
-	 * The PIIX4 will enter the suspend state only after seeing a special
-	 * cycle with the correct magic data on the PCI bus. Generate that
-	 * cycle now.
-	 */
-	spec_devid = PCI_DEVID(0, PCI_DEVFN(0x1f, 0x7));
-	pci_bus_write_config_dword(pm_pci_bus, spec_devid, 0,
-				   PIIX4_SUSPEND_MAGIC);
-
-	/* Give the system some time to power down */
-	mdelay(1000);
-
-	return 0;
-}
-
-static int __init malta_pm_setup(void)
-{
-	struct pci_dev *dev;
-	int res, io_region = PCI_BRIDGE_RESOURCES;
-
-	/* Find a reference to the PCI bus */
-	pm_pci_bus = pci_find_next_bus(NULL);
-	if (!pm_pci_bus) {
-		pr_warn("malta-pm: failed to find reference to PCI bus\n");
-		return -ENODEV;
-	}
-
-	/* Find the PIIX4 PM device */
-	dev = pci_get_subsys(PCI_VENDOR_ID_INTEL,
-			     PCI_DEVICE_ID_INTEL_82371AB_3, PCI_ANY_ID,
-			     PCI_ANY_ID, NULL);
-	if (!dev) {
-		pr_warn("malta-pm: failed to find PIIX4 PM\n");
-		return -ENODEV;
-	}
-
-	/* Request access to the PIIX4 PM IO registers */
-	res = pci_request_region(dev, io_region, "PIIX4 PM IO registers");
-	if (res) {
-		pr_warn("malta-pm: failed to request PM IO registers (%d)\n",
-			res);
-		pci_dev_put(dev);
-		return -ENODEV;
-	}
-
-	/* Find the offset to the PIIX4 PM IO registers */
-	pm_io_offset = pci_resource_start(dev, io_region);
-
-	pci_dev_put(dev);
-	return 0;
-}
-
-late_initcall(malta_pm_setup);
diff --git a/arch/mips/mti-malta/malta-reset.c b/arch/mips/mti-malta/malta-reset.c
deleted file mode 100644
index dd6f62ad4417..000000000000
--- a/arch/mips/mti-malta/malta-reset.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 1999,2000 MIPS Technologies, Inc.  All rights reserved.
- */
-#include <linux/io.h>
-#include <linux/pm.h>
-#include <linux/reboot.h>
-
-#include <asm/reboot.h>
-#include <asm/mach-malta/malta-pm.h>
-
-static void mips_machine_power_off(void)
-{
-	mips_pm_suspend(PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF);
-
-	pr_info("Failed to power down, resetting\n");
-	machine_restart(NULL);
-}
-
-static int __init mips_reboot_setup(void)
-{
-	pm_power_off = mips_machine_power_off;
-
-	return 0;
-}
-arch_initcall(mips_reboot_setup);
diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index 7b63914d2e58..5d4c5e5fbd69 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -26,6 +26,7 @@
 #include <linux/screen_info.h>
 #include <linux/time.h>
 
+#include <asm/dma-coherence.h>
 #include <asm/fw/fw.h>
 #include <asm/mach-malta/malta-dtshim.h>
 #include <asm/mips-cps.h>
@@ -144,12 +145,6 @@ static int __init plat_enable_iocoherency(void)
 
 static void __init plat_setup_iocoherency(void)
 {
-#ifdef CONFIG_DMA_NONCOHERENT
-	/*
-	 * Kernel has been configured with software coherency
-	 * but we might choose to turn it off and use hardware
-	 * coherency instead.
-	 */
 	if (plat_enable_iocoherency()) {
 		if (coherentio == IO_COHERENCE_DISABLED)
 			pr_info("Hardware DMA cache coherency disabled\n");
@@ -161,10 +156,6 @@ static void __init plat_setup_iocoherency(void)
 		else
 			pr_info("Software DMA cache coherency enabled\n");
 	}
-#else
-	if (!plat_enable_iocoherency())
-		panic("Hardware DMA cache coherency not supported!");
-#endif
 }
 
 static void __init pci_clock_check(void)
@@ -226,29 +217,6 @@ static void __init bonito_quirks_setup(void)
 		pr_info("Enabled Bonito debug mode\n");
 	} else
 		BONITO_BONGENCFG &= ~BONITO_BONGENCFG_DEBUGMODE;
-
-#ifdef CONFIG_DMA_COHERENT
-	if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) {
-		BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN;
-		pr_info("Enabled Bonito CPU coherency\n");
-
-		argptr = fw_getcmdline();
-		if (strstr(argptr, "iobcuncached")) {
-			BONITO_PCICACHECTRL &= ~BONITO_PCICACHECTRL_IOBCCOH_EN;
-			BONITO_PCIMEMBASECFG = BONITO_PCIMEMBASECFG &
-				~(BONITO_PCIMEMBASECFG_MEMBASE0_CACHED |
-					BONITO_PCIMEMBASECFG_MEMBASE1_CACHED);
-			pr_info("Disabled Bonito IOBC coherency\n");
-		} else {
-			BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_IOBCCOH_EN;
-			BONITO_PCIMEMBASECFG |=
-				(BONITO_PCIMEMBASECFG_MEMBASE0_CACHED |
-					BONITO_PCIMEMBASECFG_MEMBASE1_CACHED);
-			pr_info("Enabled Bonito IOBC coherency\n");
-		}
-	} else
-		panic("Hardware DMA cache coherency not supported");
-#endif
 }
 
 void __init *plat_get_fdt(void)
@@ -279,11 +247,6 @@ void __init plat_mem_setup(void)
 	 */
 	enable_dma(4);
 
-#ifdef CONFIG_DMA_COHERENT
-	if (mips_revision_sconid != MIPS_REVISION_SCON_BONITO)
-		panic("Hardware DMA cache coherency not supported");
-#endif
-
 	if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO)
 		bonito_quirks_setup();
 
diff --git a/arch/mips/netlogic/common/earlycons.c b/arch/mips/netlogic/common/earlycons.c
index 769f93032c53..8f5bc1597550 100644
--- a/arch/mips/netlogic/common/earlycons.c
+++ b/arch/mips/netlogic/common/earlycons.c
@@ -36,6 +36,7 @@
 #include <linux/serial_reg.h>
 
 #include <asm/mipsregs.h>
+#include <asm/setup.h>
 #include <asm/netlogic/haldefs.h>
 #include <asm/netlogic/common.h>
 
diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c
index 856a6e6d296e..b5ba83f4c646 100644
--- a/arch/mips/netlogic/xlp/dt.c
+++ b/arch/mips/netlogic/xlp/dt.c
@@ -93,17 +93,3 @@ void __init device_tree_init(void)
 {
 	unflatten_and_copy_device_tree();
 }
-
-static struct of_device_id __initdata xlp_ids[] = {
-	{ .compatible = "simple-bus", },
-	{},
-};
-
-int __init xlp8xx_ds_publish_devices(void)
-{
-	if (!of_have_populated_dt())
-		return 0;
-	return of_platform_bus_probe(NULL, xlp_ids, NULL);
-}
-
-device_initcall(xlp8xx_ds_publish_devices);
diff --git a/arch/mips/paravirt/serial.c b/arch/mips/paravirt/serial.c
index 02b665c02272..a37b6f9f0ede 100644
--- a/arch/mips/paravirt/serial.c
+++ b/arch/mips/paravirt/serial.c
@@ -9,16 +9,15 @@
 #include <linux/kernel.h>
 #include <linux/virtio_console.h>
 #include <linux/kvm_para.h>
+#include <asm/setup.h>
 
 /*
  * Emit one character to the boot console.
  */
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	kvm_hypercall3(KVM_HC_MIPS_CONSOLE_OUTPUT, 0 /*  port 0 */,
 		(unsigned long)&c, 1 /* len == 1 */);
-
-	return 1;
 }
 
 #ifdef CONFIG_VIRTIO_CONSOLE
diff --git a/arch/mips/pci/ops-bridge.c b/arch/mips/pci/ops-bridge.c
index 57e1463fcd02..a1d2c4ae0d1b 100644
--- a/arch/mips/pci/ops-bridge.c
+++ b/arch/mips/pci/ops-bridge.c
@@ -167,7 +167,7 @@ oh_my_gawd:
 static int pci_read_config(struct pci_bus *bus, unsigned int devfn,
 			   int where, int size, u32 * value)
 {
-	if (bus->number > 0)
+	if (!pci_is_root_bus(bus))
 		return pci_conf1_read_config(bus, devfn, where, size, value);
 
 	return pci_conf0_read_config(bus, devfn, where, size, value);
@@ -310,7 +310,7 @@ oh_my_gawd:
 static int pci_write_config(struct pci_bus *bus, unsigned int devfn,
 	int where, int size, u32 value)
 {
-	if (bus->number > 0)
+	if (!pci_is_root_bus(bus))
 		return pci_conf1_write_config(bus, devfn, where, size, value);
 
 	return pci_conf0_write_config(bus, devfn, where, size, value);
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index b4fa6413c4e5..c539d0d2b0cf 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -149,6 +149,13 @@
 #define AR2315_PCI_HOST_SLOT	3
 #define AR2315_PCI_HOST_DEVID	((0xff18 << 16) | PCI_VENDOR_ID_ATHEROS)
 
+/*
+ * We need some arbitrary non-zero value to be programmed to the BAR1 register
+ * of PCI host controller to enable DMA. The same value should be used as the
+ * offset to calculate the physical address of DMA buffer for PCI devices.
+ */
+#define AR2315_PCI_HOST_SDRAM_BASEADDR	0x20000000
+
 /* ??? access BAR */
 #define AR2315_PCI_HOST_MBAR0		0x10000000
 /* RAM access BAR */
@@ -167,6 +174,23 @@ struct ar2315_pci_ctrl {
 	struct resource io_res;
 };
 
+static inline dma_addr_t ar2315_dev_offset(struct device *dev)
+{
+	if (dev && dev_is_pci(dev))
+		return AR2315_PCI_HOST_SDRAM_BASEADDR;
+	return 0;
+}
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr + ar2315_dev_offset(dev);
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr - ar2315_dev_offset(dev);
+}
+
 static inline struct ar2315_pci_ctrl *ar2315_pci_bus_to_apc(struct pci_bus *bus)
 {
 	struct pci_controller *hose = bus->sysdata;
diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c
index 1e23c8d587bd..64b58cc48a91 100644
--- a/arch/mips/pci/pci-ar724x.c
+++ b/arch/mips/pci/pci-ar724x.c
@@ -12,14 +12,18 @@
 #include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <asm/mach-ath79/ath79.h>
 #include <asm/mach-ath79/ar71xx_regs.h>
 
+#define AR724X_PCI_REG_APP		0x00
 #define AR724X_PCI_REG_RESET		0x18
 #define AR724X_PCI_REG_INT_STATUS	0x4c
 #define AR724X_PCI_REG_INT_MASK		0x50
 
+#define AR724X_PCI_APP_LTSSM_ENABLE	BIT(0)
+
 #define AR724X_PCI_RESET_LINK_UP	BIT(0)
 
 #define AR724X_PCI_INT_DEV0		BIT(14)
@@ -325,6 +329,37 @@ static void ar724x_pci_irq_init(struct ar724x_pci_controller *apc,
 					 apc);
 }
 
+static void ar724x_pci_hw_init(struct ar724x_pci_controller *apc)
+{
+	u32 ppl, app;
+	int wait = 0;
+
+	/* deassert PCIe host controller and PCIe PHY reset */
+	ath79_device_reset_clear(AR724X_RESET_PCIE);
+	ath79_device_reset_clear(AR724X_RESET_PCIE_PHY);
+
+	/* remove the reset of the PCIE PLL */
+	ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG);
+	ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET;
+	ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl);
+
+	/* deassert bypass for the PCIE PLL */
+	ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG);
+	ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS;
+	ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl);
+
+	/* set PCIE Application Control to ready */
+	app = __raw_readl(apc->ctrl_base + AR724X_PCI_REG_APP);
+	app |= AR724X_PCI_APP_LTSSM_ENABLE;
+	__raw_writel(app, apc->ctrl_base + AR724X_PCI_REG_APP);
+
+	/* wait up to 100ms for PHY link up */
+	do {
+		mdelay(10);
+		wait++;
+	} while (wait < 10 && !ar724x_pci_check_link(apc));
+}
+
 static int ar724x_pci_probe(struct platform_device *pdev)
 {
 	struct ar724x_pci_controller *apc;
@@ -383,6 +418,13 @@ static int ar724x_pci_probe(struct platform_device *pdev)
 	apc->pci_controller.io_resource = &apc->io_res;
 	apc->pci_controller.mem_resource = &apc->mem_res;
 
+	/*
+	 * Do the full PCIE Root Complex Initialization Sequence if the PCIe
+	 * host controller is in reset.
+	 */
+	if (ath79_reset_rr(AR724X_RESET_REG_RESET_MODULE) & AR724X_RESET_PCIE)
+		ar724x_pci_hw_init(apc);
+
 	apc->link_up = ar724x_pci_check_link(apc);
 	if (!apc->link_up)
 		dev_warn(&pdev->dev, "PCIe link is down\n");
diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c
index 0f09eafa5e3a..c94a66070a60 100644
--- a/arch/mips/pci/pci-ip27.c
+++ b/arch/mips/pci/pci-ip27.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/smp.h>
+#include <linux/dma-direct.h>
 #include <asm/sn/arch.h>
 #include <asm/pci/bridge.h>
 #include <asm/paccess.h>
@@ -182,6 +183,19 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 	return 0;
 }
 
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
+
+	return bc->baddr + paddr;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr & ~(0xffUL << 56);
+}
+
 /*
  * Device might live on a subordinate PCI bus.	XXX Walk up the chain of buses
  * to find the slot number in sense of the bridge device register.
@@ -200,17 +214,6 @@ static inline void pci_disable_swapping(struct pci_dev *dev)
 	bridge->b_widget.w_tflush;	/* Flush */
 }
 
-static inline void pci_enable_swapping(struct pci_dev *dev)
-{
-	struct bridge_controller *bc = BRIDGE_CONTROLLER(dev->bus);
-	bridge_t *bridge = bc->base;
-	int slot = PCI_SLOT(dev->devfn);
-
-	/* Turn on byte swapping */
-	bridge->b_device[slot].reg |= BRIDGE_DEV_SWAP_DIR;
-	bridge->b_widget.w_tflush;	/* Flush */
-}
-
 static void pci_fixup_ioc3(struct pci_dev *d)
 {
 	pci_disable_swapping(d);
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index 3e92a06fa772..5017d5843c5a 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -21,8 +21,6 @@
 #include <asm/octeon/cvmx-pci-defs.h>
 #include <asm/octeon/pci-octeon.h>
 
-#include <dma-coherence.h>
-
 #define USE_OCTEON_INTERNAL_ARBITER
 
 /*
@@ -166,8 +164,6 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 		pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, dconfig);
 	}
 
-	dev->dev.dma_ops = octeon_pci_dma_map_ops;
-
 	return 0;
 }
 
diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
index 87ba86bd8696..d919a0d813a1 100644
--- a/arch/mips/pci/pcie-octeon.c
+++ b/arch/mips/pci/pcie-octeon.c
@@ -94,8 +94,6 @@ union cvmx_pcie_address {
 
 static int cvmx_pcie_rc_initialize(int pcie_port);
 
-#include <dma-coherence.h>
-
 /**
  * Return the Core virtual base address for PCIe IO access. IOs are
  * read/written as an offset from this address.
@@ -1239,14 +1237,14 @@ static int __cvmx_pcie_rc_initialize_gen2(int pcie_port)
 	/* CN63XX Pass 1.0 errata G-14395 requires the QLM De-emphasis be programmed */
 	if (OCTEON_IS_MODEL(OCTEON_CN63XX_PASS1_0)) {
 		if (pcie_port) {
-			union cvmx_ciu_qlm1 ciu_qlm;
+			union cvmx_ciu_qlm ciu_qlm;
 			ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM1);
 			ciu_qlm.s.txbypass = 1;
 			ciu_qlm.s.txdeemph = 5;
 			ciu_qlm.s.txmargin = 0x17;
 			cvmx_write_csr(CVMX_CIU_QLM1, ciu_qlm.u64);
 		} else {
-			union cvmx_ciu_qlm0 ciu_qlm;
+			union cvmx_ciu_qlm ciu_qlm;
 			ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM0);
 			ciu_qlm.s.txbypass = 1;
 			ciu_qlm.s.txdeemph = 5;
diff --git a/arch/mips/pic32/pic32mzda/early_console.c b/arch/mips/pic32/pic32mzda/early_console.c
index d7b783463fac..8ed4961b1271 100644
--- a/arch/mips/pic32/pic32mzda/early_console.c
+++ b/arch/mips/pic32/pic32mzda/early_console.c
@@ -13,6 +13,7 @@
  */
 #include <asm/mach-pic32/pic32.h>
 #include <asm/fw/fw.h>
+#include <asm/setup.h>
 
 #include "pic32mzda.h"
 #include "early_pin.h"
@@ -157,7 +158,7 @@ void __init fw_init_early_console(char port)
 	setup_early_console(port, baud);
 }
 
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	if (console_port >= 0) {
 		while (__raw_readl(
@@ -166,6 +167,4 @@ int prom_putchar(char c)
 
 		__raw_writel(c, uart_base + U_TXR(console_port));
 	}
-
-	return 1;
 }
diff --git a/arch/mips/ralink/early_printk.c b/arch/mips/ralink/early_printk.c
index 3c59ffe5f5f5..ecd30ddfb3db 100644
--- a/arch/mips/ralink/early_printk.c
+++ b/arch/mips/ralink/early_printk.c
@@ -10,6 +10,7 @@
 #include <linux/serial_reg.h>
 
 #include <asm/addrspace.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_SOC_RT288X
 #define EARLY_UART_BASE		0x300c00
@@ -68,7 +69,7 @@ static void find_uart_base(void)
 	}
 }
 
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
 {
 	if (!init_complete) {
 		find_uart_base();
@@ -76,13 +77,13 @@ void prom_putchar(unsigned char ch)
 	}
 
 	if (IS_ENABLED(CONFIG_SOC_MT7621) || soc_is_mt7628()) {
-		uart_w32(ch, UART_TX);
+		uart_w32((unsigned char)ch, UART_TX);
 		while ((uart_r32(UART_REG_LSR) & UART_LSR_THRE) == 0)
 			;
 	} else {
 		while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0)
 			;
-		uart_w32(ch, UART_REG_TX);
+		uart_w32((unsigned char)ch, UART_REG_TX);
 		while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0)
 			;
 	}
diff --git a/arch/mips/sgi-ip27/ip27-console.c b/arch/mips/sgi-ip27/ip27-console.c
index 45fdfbcbd4c6..6bdb48d41276 100644
--- a/arch/mips/sgi-ip27/ip27-console.c
+++ b/arch/mips/sgi-ip27/ip27-console.c
@@ -7,6 +7,7 @@
  */
 
 #include <asm/page.h>
+#include <asm/setup.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/sn0/hub.h>
 #include <asm/sn/klconfig.h>
diff --git a/arch/mips/sgi-ip32/Makefile b/arch/mips/sgi-ip32/Makefile
index 60f0227425e7..4745cd94df11 100644
--- a/arch/mips/sgi-ip32/Makefile
+++ b/arch/mips/sgi-ip32/Makefile
@@ -4,4 +4,4 @@
 #
 
 obj-y	+= ip32-berr.o ip32-irq.o ip32-platform.o ip32-setup.o ip32-reset.o \
-	   crime.o ip32-memory.o
+	   crime.o ip32-memory.o ip32-dma.o
diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c
new file mode 100644
index 000000000000..fa7b17cb5385
--- /dev/null
+++ b/arch/mips/sgi-ip32/ip32-dma.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
+ */
+#include <linux/dma-direct.h>
+#include <asm/ip32/crime.h>
+
+/*
+ * Few notes.
+ * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M
+ * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for
+ *    native-endian)
+ * 3. All other devices see memory as one big chunk at 0x40000000
+ * 4. Non-PCI devices will pass NULL as struct device*
+ *
+ * Thus we translate differently, depending on device.
+ */
+
+#define RAM_OFFSET_MASK 0x3fffffffUL
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	dma_addr_t dma_addr = paddr & RAM_OFFSET_MASK;
+
+	if (!dev)
+		dma_addr += CRIME_HI_MEM_BASE;
+	return dma_addr;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK;
+
+	if (dma_addr >= 256*1024*1024)
+		paddr += CRIME_HI_MEM_BASE;
+	return paddr;
+}
diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig
index f4dbce25bc6a..7ec278d72096 100644
--- a/arch/mips/sibyte/Kconfig
+++ b/arch/mips/sibyte/Kconfig
@@ -70,7 +70,6 @@ config SIBYTE_BCM1x55
 
 config SIBYTE_SB1xxx_SOC
 	bool
-	select DMA_COHERENT
 	select IRQ_MIPS_CPU
 	select SWAP_IO_SPACE
 	select SYS_SUPPORTS_32BIT_KERNEL
diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c
index 115399202eab..092fb2a6ec4a 100644
--- a/arch/mips/sibyte/common/cfe.c
+++ b/arch/mips/sibyte/common/cfe.c
@@ -27,6 +27,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/sibyte/board.h>
 #include <asm/smp-ops.h>
 
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 1791a44ee570..f6d9182ef82a 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -20,6 +20,7 @@
 #include <linux/err.h>
 #include <linux/gpio/driver.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 #include <linux/serial_core.h>
 #include <linux/mtd/physmap.h>
 #include <linux/leds.h>
@@ -32,10 +33,10 @@
 #include <asm/reboot.h>
 #include <asm/r4kcache.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 #include <asm/txx9/generic.h>
 #include <asm/txx9/pci.h>
 #include <asm/txx9tmr.h>
-#include <asm/txx9/ndfmc.h>
 #include <asm/txx9/dmac.h>
 #ifdef CONFIG_CPU_TX49XX
 #include <asm/txx9/tx4938.h>
diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c
index 85d1795652da..17395d5d15ca 100644
--- a/arch/mips/txx9/generic/setup_tx4938.c
+++ b/arch/mips/txx9/generic/setup_tx4938.c
@@ -17,13 +17,13 @@
 #include <linux/ptrace.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 #include <asm/reboot.h>
 #include <asm/traps.h>
 #include <asm/txx9irq.h>
 #include <asm/txx9tmr.h>
 #include <asm/txx9pio.h>
 #include <asm/txx9/generic.h>
-#include <asm/txx9/ndfmc.h>
 #include <asm/txx9/dmac.h>
 #include <asm/txx9/tx4938.h>
 
diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c
index 274928987a21..360c388f4c82 100644
--- a/arch/mips/txx9/generic/setup_tx4939.c
+++ b/arch/mips/txx9/generic/setup_tx4939.c
@@ -21,13 +21,13 @@
 #include <linux/ptrace.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
 #include <asm/traps.h>
 #include <asm/txx9irq.h>
 #include <asm/txx9tmr.h>
 #include <asm/txx9/generic.h>
-#include <asm/txx9/ndfmc.h>
 #include <asm/txx9/dmac.h>
 #include <asm/txx9/tx4939.h>
 
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index ce196046ac3e..34605ca21498 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -7,7 +7,13 @@ ccflags-vdso := \
 	$(filter -I%,$(KBUILD_CFLAGS)) \
 	$(filter -E%,$(KBUILD_CFLAGS)) \
 	$(filter -mmicromips,$(KBUILD_CFLAGS)) \
-	$(filter -march=%,$(KBUILD_CFLAGS))
+	$(filter -march=%,$(KBUILD_CFLAGS)) \
+	-D__VDSO__
+
+ifeq ($(cc-name),clang)
+ccflags-vdso += $(filter --target=%,$(KBUILD_CFLAGS))
+endif
+
 cflags-vdso := $(ccflags-vdso) \
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
 	-O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
@@ -38,6 +44,7 @@ endif
 # VDSO linker flags.
 VDSO_LDFLAGS := \
 	-Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \
+	$(addprefix -Wl$(comma),$(filter -E%,$(KBUILD_CFLAGS))) \
 	-nostdlib -shared \
 	$(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
 	$(call cc-ldoption, -Wl$(comma)--build-id)
diff --git a/arch/mips/vdso/genvdso.h b/arch/mips/vdso/genvdso.h
index 94334727059a..611b06f01a3c 100644
--- a/arch/mips/vdso/genvdso.h
+++ b/arch/mips/vdso/genvdso.h
@@ -15,8 +15,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso)
 	ELF(Shdr) *shdr;
 	char *shstrtab, *name;
 	uint16_t sh_count, sh_entsize, i;
-	unsigned int local_gotno, symtabno, gotsym;
-	ELF(Dyn) *dyn = NULL;
 
 	shdrs = vdso + FUNC(swap_uint)(ehdr->e_shoff);
 	sh_count = swap_uint16(ehdr->e_shnum);
@@ -41,9 +39,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso)
 				"%s: '%s' contains relocation sections\n",
 				program_name, path);
 			return false;
-		case SHT_DYNAMIC:
-			dyn = vdso + FUNC(swap_uint)(shdr->sh_offset);
-			break;
 		}
 
 		/* Check for existing sections. */
@@ -61,52 +56,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso)
 		}
 	}
 
-	/*
-	 * Ensure the GOT has no entries other than the standard 2, for the same
-	 * reason we check that there's no relocation sections above.
-	 * The standard two entries are:
-	 * - Lazy resolver
-	 * - Module pointer
-	 */
-	if (dyn) {
-		local_gotno = symtabno = gotsym = 0;
-
-		while (FUNC(swap_uint)(dyn->d_tag) != DT_NULL) {
-			switch (FUNC(swap_uint)(dyn->d_tag)) {
-			/*
-			 * This member holds the number of local GOT entries.
-			 */
-			case DT_MIPS_LOCAL_GOTNO:
-				local_gotno = FUNC(swap_uint)(dyn->d_un.d_val);
-				break;
-			/*
-			 * This member holds the number of entries in the
-			 * .dynsym section.
-			 */
-			case DT_MIPS_SYMTABNO:
-				symtabno = FUNC(swap_uint)(dyn->d_un.d_val);
-				break;
-			/*
-			 * This member holds the index of the first dynamic
-			 * symbol table entry that corresponds to an entry in
-			 * the GOT.
-			 */
-			case DT_MIPS_GOTSYM:
-				gotsym = FUNC(swap_uint)(dyn->d_un.d_val);
-				break;
-			}
-
-			dyn++;
-		}
-
-		if (local_gotno > 2 || symtabno - gotsym) {
-			fprintf(stderr,
-				"%s: '%s' contains unexpected GOT entries\n",
-				program_name, path);
-			return false;
-		}
-	}
-
 	return true;
 }
 
diff --git a/arch/mips/vr41xx/common/pmu.c b/arch/mips/vr41xx/common/pmu.c
index 39a0db3e2b34..16e684b59875 100644
--- a/arch/mips/vr41xx/common/pmu.c
+++ b/arch/mips/vr41xx/common/pmu.c
@@ -17,6 +17,7 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
+#include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
@@ -46,7 +47,7 @@ static void __iomem *pmu_base;
 #define pmu_read(offset)		readw(pmu_base + (offset))
 #define pmu_write(offset, value)	writew((value), pmu_base + (offset))
 
-static void vr41xx_cpu_wait(void)
+static void __cpuidle vr41xx_cpu_wait(void)
 {
 	local_irq_disable();
 	if (!need_resched())
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 3d4ec88f1db1..92035042cf62 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -1,6 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 config NIOS2
 	def_bool y
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_NONCOHERENT_OPS
 	select TIMER_OF
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 64ed3d656956..8fde4fa2c34f 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/nios2/include/asm/dma-mapping.h b/arch/nios2/include/asm/dma-mapping.h
deleted file mode 100644
index 6ceb92251da0..000000000000
--- a/arch/nios2/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (C) 2011 Tobias Klauser <tklauser@distanz.ch>
- * Copyright (C) 2009 Wind River Systems Inc
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file COPYING in the main directory of this
- * archive for more details.
- */
-
-#ifndef _ASM_NIOS2_DMA_MAPPING_H
-#define _ASM_NIOS2_DMA_MAPPING_H
-
-extern const struct dma_map_ops nios2_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &nios2_dma_ops;
-}
-
-#endif /* _ASM_NIOS2_DMA_MAPPING_H */
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index 4be815519dd4..4af9e5b5ba1c 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -12,18 +12,18 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <linux/export.h>
 #include <linux/string.h>
-#include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/cache.h>
 #include <asm/cacheflush.h>
 
-static inline void __dma_sync_for_device(void *vaddr, size_t size,
-			      enum dma_data_direction direction)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	switch (direction) {
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
 	case DMA_FROM_DEVICE:
 		invalidate_dcache_range((unsigned long)vaddr,
 			(unsigned long)(vaddr + size));
@@ -42,10 +42,12 @@ static inline void __dma_sync_for_device(void *vaddr, size_t size,
 	}
 }
 
-static inline void __dma_sync_for_cpu(void *vaddr, size_t size,
-			      enum dma_data_direction direction)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	switch (direction) {
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
 	case DMA_BIDIRECTIONAL:
 	case DMA_FROM_DEVICE:
 		invalidate_dcache_range((unsigned long)vaddr,
@@ -58,8 +60,8 @@ static inline void __dma_sync_for_cpu(void *vaddr, size_t size,
 	}
 }
 
-static void *nios2_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	void *ret;
 
@@ -80,125 +82,10 @@ static void *nios2_dma_alloc(struct device *dev, size_t size,
 	return ret;
 }
 
-static void nios2_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	unsigned long addr = (unsigned long) CAC_ADDR((unsigned long) vaddr);
 
 	free_pages(addr, get_order(size));
 }
-
-static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int i;
-
-	for_each_sg(sg, sg, nents, i) {
-		void *addr = sg_virt(sg);
-
-		if (!addr)
-			continue;
-
-		sg->dma_address = sg_phys(sg);
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		__dma_sync_for_device(addr, sg->length, direction);
-	}
-
-	return nents;
-}
-
-static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page,
-			unsigned long offset, size_t size,
-			enum dma_data_direction direction,
-			unsigned long attrs)
-{
-	void *addr = page_address(page) + offset;
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync_for_device(addr, size, direction);
-
-	return page_to_phys(page) + offset;
-}
-
-static void nios2_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-		size_t size, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
-}
-
-static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nhwentries, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	void *addr;
-	int i;
-
-	if (direction == DMA_TO_DEVICE)
-		return;
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	for_each_sg(sg, sg, nhwentries, i) {
-		addr = sg_virt(sg);
-		if (addr)
-			__dma_sync_for_cpu(addr, sg->length, direction);
-	}
-}
-
-static void nios2_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	__dma_sync_for_cpu(phys_to_virt(dma_handle), size, direction);
-}
-
-static void nios2_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	__dma_sync_for_device(phys_to_virt(dma_handle), size, direction);
-}
-
-static void nios2_dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sg, int nelems,
-		enum dma_data_direction direction)
-{
-	int i;
-
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for_each_sg(sg, sg, nelems, i)
-		__dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
-}
-
-static void nios2_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sg, int nelems,
-		enum dma_data_direction direction)
-{
-	int i;
-
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for_each_sg(sg, sg, nelems, i)
-		__dma_sync_for_device(sg_virt(sg), sg->length, direction);
-
-}
-
-const struct dma_map_ops nios2_dma_ops = {
-	.alloc			= nios2_dma_alloc,
-	.free			= nios2_dma_free,
-	.map_page		= nios2_dma_map_page,
-	.unmap_page		= nios2_dma_unmap_page,
-	.map_sg			= nios2_dma_map_sg,
-	.unmap_sg		= nios2_dma_unmap_sg,
-	.sync_single_for_device	= nios2_dma_sync_single_for_device,
-	.sync_single_for_cpu	= nios2_dma_sync_single_for_cpu,
-	.sync_sg_for_cpu	= nios2_dma_sync_sg_for_cpu,
-	.sync_sg_for_device	= nios2_dma_sync_sg_for_device,
-};
-EXPORT_SYMBOL(nios2_dma_ops);
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 9ecad05bfc73..dfb6a79ba7ff 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -27,7 +27,6 @@ config OPENRISC
 	select GENERIC_STRNLEN_USER
 	select GENERIC_SMP_IDLE_THREAD
 	select MODULES_USE_ELF_RELA
-	select MULTI_IRQ_HANDLER
 	select HAVE_DEBUG_STACKOVERFLOW
 	select OR1K_PIC
 	select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1
@@ -36,6 +35,7 @@ config OPENRISC
 	select ARCH_USE_QUEUED_RWLOCKS
 	select OMPIC if SMP
 	select ARCH_WANT_FRAME_POINTERS
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config CPU_BIG_ENDIAN
 	def_bool y
@@ -69,9 +69,6 @@ config STACKTRACE_SUPPORT
 config LOCKDEP_SUPPORT
 	def_bool  y
 
-config MULTI_IRQ_HANDLER
-	def_bool y
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/openrisc/include/asm/atomic.h b/arch/openrisc/include/asm/atomic.h
index 146e1660f00e..b589fac39b92 100644
--- a/arch/openrisc/include/asm/atomic.h
+++ b/arch/openrisc/include/asm/atomic.h
@@ -100,7 +100,7 @@ ATOMIC_OP(xor)
  *
  * This is often used through atomic_inc_not_zero()
  */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int old, tmp;
 
@@ -119,7 +119,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return old;
 }
-#define __atomic_add_unless	__atomic_add_unless
+#define atomic_fetch_add_unless	atomic_fetch_add_unless
 
 #include <asm-generic/atomic.h>
 
diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
index d29f7db53906..f9cd43a39d72 100644
--- a/arch/openrisc/include/asm/cmpxchg.h
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -16,8 +16,9 @@
 #ifndef __ASM_OPENRISC_CMPXCHG_H
 #define __ASM_OPENRISC_CMPXCHG_H
 
+#include  <linux/bits.h>
+#include  <linux/compiler.h>
 #include  <linux/types.h>
-#include  <linux/bitops.h>
 
 #define __HAVE_ARCH_CMPXCHG 1
 
diff --git a/arch/openrisc/include/asm/irq.h b/arch/openrisc/include/asm/irq.h
index d9eee0a2b7b4..eb612b1865d2 100644
--- a/arch/openrisc/include/asm/irq.h
+++ b/arch/openrisc/include/asm/irq.h
@@ -24,6 +24,4 @@
 
 #define NO_IRQ		(-1)
 
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
 #endif /* __ASM_OPENRISC_IRQ_H__ */
diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c
index 35e478a93116..5f9445effaf8 100644
--- a/arch/openrisc/kernel/irq.c
+++ b/arch/openrisc/kernel/irq.c
@@ -41,13 +41,6 @@ void __init init_IRQ(void)
 	irqchip_init();
 }
 
-static void (*handle_arch_irq)(struct pt_regs *);
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	handle_arch_irq = handle_irq;
-}
-
 void __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	handle_arch_irq(regs);
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 17526bebcbd2..e21751fb24aa 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -11,7 +11,6 @@ config PARISC
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_WANTS_UBSAN_NO_NULL
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select RTC_CLASS
 	select RTC_DRV_GENERIC
@@ -46,6 +45,7 @@ config PARISC
 	select HAVE_ARCH_HASH
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_REGS_AND_STACK_ACCESS_API
 	select GENERIC_SCHED_CLOCK
 	select HAVE_UNSTABLE_SCHED_CLOCK if SMP
 	select GENERIC_CLOCKEVENTS
@@ -188,6 +188,10 @@ config PA20
 config PA11
 	def_bool y
 	depends on PA7000 || PA7100LC || PA7200 || PA7300LC
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_NONCOHERENT_OPS
+	select DMA_NONCOHERENT_CACHE_SYNC
 
 config PREFETCH
 	def_bool y
@@ -195,7 +199,7 @@ config PREFETCH
 
 config MLONGCALLS
 	bool "Enable the -mlong-calls compiler option for big kernels"
-	def_bool y if (!MODULES)
+	default y
 	depends on PA8X00
 	help
 	  If you configure the kernel to include many drivers built-in instead
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 60e6f07b7e32..e9c6385ef0d1 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -36,6 +36,7 @@
 #define RP_OFFSET	16
 #define FRAME_SIZE	128
 #define CALLEE_REG_FRAME_SIZE	144
+#define REG_SZ		8
 #define ASM_ULONG_INSN	.dword
 #else	/* CONFIG_64BIT */
 #define LDREG	ldw
@@ -50,6 +51,7 @@
 #define RP_OFFSET	20
 #define FRAME_SIZE	64
 #define CALLEE_REG_FRAME_SIZE	128
+#define REG_SZ		4
 #define ASM_ULONG_INSN	.word
 #endif
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 88bae6676c9b..118953d41763 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -77,30 +77,6 @@ static __inline__ int atomic_read(const atomic_t *v)
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define ATOMIC_OP(op, c_op)						\
 static __inline__ void atomic_##op(int i, atomic_t *v)			\
 {									\
@@ -160,28 +136,6 @@ ATOMIC_OPS(xor, ^=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_inc(v)	(atomic_add(   1,(v)))
-#define atomic_dec(v)	(atomic_add(  -1,(v)))
-
-#define atomic_inc_return(v)	(atomic_add_return(   1,(v)))
-#define atomic_dec_return(v)	(atomic_add_return(  -1,(v)))
-
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v)	(atomic_dec_return(v) == 0)
-
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i),(v)) == 0)
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef CONFIG_64BIT
@@ -264,72 +218,11 @@ atomic64_read(const atomic64_t *v)
 	return READ_ONCE((v)->counter);
 }
 
-#define atomic64_inc(v)		(atomic64_add(   1,(v)))
-#define atomic64_dec(v)		(atomic64_add(  -1,(v)))
-
-#define atomic64_inc_return(v)		(atomic64_add_return(   1,(v)))
-#define atomic64_dec_return(v)		(atomic64_add_return(  -1,(v)))
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
-#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i),(v)) == 0)
-
 /* exported interface */
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-/*
- * atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
 #endif /* !CONFIG_64BIT */
 
 
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
new file mode 100644
index 000000000000..dbaaca84f27f
--- /dev/null
+++ b/arch/parisc/include/asm/barrier.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_BARRIER_H
+#define __ASM_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+/* The synchronize caches instruction executes as a nop on systems in
+   which all memory references are performed in order. */
+#define synchronize_caches() __asm__ __volatile__ ("sync" : : : "memory")
+
+#if defined(CONFIG_SMP)
+#define mb()		do { synchronize_caches(); } while (0)
+#define rmb()		mb()
+#define wmb()		mb()
+#define dma_rmb()	mb()
+#define dma_wmb()	mb()
+#else
+#define mb()		barrier()
+#define rmb()		barrier()
+#define wmb()		barrier()
+#define dma_rmb()	barrier()
+#define dma_wmb()	barrier()
+#endif
+
+#define __smp_mb()	mb()
+#define __smp_rmb()	mb()
+#define __smp_wmb()	mb()
+
+#include <asm-generic/barrier.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_BARRIER_H */
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index 01e1fc057c83..44a9f97194aa 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -21,11 +21,6 @@
 ** flush/purge and allocate "regular" cacheable pages for everything.
 */
 
-#ifdef CONFIG_PA11
-extern const struct dma_map_ops pcxl_dma_ops;
-extern const struct dma_map_ops pcx_dma_ops;
-#endif
-
 extern const struct dma_map_ops *hppa_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/arch/parisc/include/asm/linkage.h b/arch/parisc/include/asm/linkage.h
index 9a69bf6fc4b6..49f6f3d772cc 100644
--- a/arch/parisc/include/asm/linkage.h
+++ b/arch/parisc/include/asm/linkage.h
@@ -18,9 +18,9 @@
 #ifdef __ASSEMBLY__
 
 #define ENTRY(name) \
-	.export name !\
-	ALIGN !\
-name:
+	ALIGN	!\
+name:		ASM_NL\
+	.export name
 
 #ifdef CONFIG_64BIT
 #define ENDPROC(name) \
@@ -31,13 +31,18 @@ name:
 	END(name)
 #endif
 
-#define ENTRY_CFI(name) \
+#define ENTRY_CFI(name, ...) \
 	ENTRY(name)	ASM_NL\
+	.proc		ASM_NL\
+	.callinfo __VA_ARGS__	ASM_NL\
+	.entry		ASM_NL\
 	CFI_STARTPROC
 
 #define ENDPROC_CFI(name) \
-	ENDPROC(name)	ASM_NL\
-	CFI_ENDPROC
+	CFI_ENDPROC	ASM_NL\
+	.exit		ASM_NL\
+	.procend	ASM_NL\
+	ENDPROC(name)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/parisc/include/asm/ptrace.h b/arch/parisc/include/asm/ptrace.h
index 46da07670c2b..2a27b275ab09 100644
--- a/arch/parisc/include/asm/ptrace.h
+++ b/arch/parisc/include/asm/ptrace.h
@@ -25,4 +25,15 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->gr[20];
 }
 
+static inline void instruction_pointer_set(struct pt_regs *regs,
+						unsigned long val)
+{
+        regs->iaoq[0] = val;
+}
+
+/* Query offset/name of register from its name/offset */
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, ipsw))
+
 #endif
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 6f84b6acc86e..8a63515f03bf 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -20,7 +20,6 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 {
 	volatile unsigned int *a;
 
-	mb();
 	a = __ldcw_align(x);
 	while (__ldcw(a) == 0)
 		while (*a == 0)
@@ -30,17 +29,16 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 				local_irq_disable();
 			} else
 				cpu_relax();
-	mb();
 }
 #define arch_spin_lock_flags arch_spin_lock_flags
 
 static inline void arch_spin_unlock(arch_spinlock_t *x)
 {
 	volatile unsigned int *a;
-	mb();
+
 	a = __ldcw_align(x);
-	*a = 1;
 	mb();
+	*a = 1;
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *x)
@@ -48,10 +46,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *x)
 	volatile unsigned int *a;
 	int ret;
 
-	mb();
 	a = __ldcw_align(x);
         ret = __ldcw(a) != 0;
-	mb();
 
 	return ret;
 }
diff --git a/arch/parisc/include/asm/unwind.h b/arch/parisc/include/asm/unwind.h
index c73a3ee20226..f133b7efbebb 100644
--- a/arch/parisc/include/asm/unwind.h
+++ b/arch/parisc/include/asm/unwind.h
@@ -4,6 +4,9 @@
 
 #include <linux/list.h>
 
+/* Max number of levels to backtrace */
+#define MAX_UNWIND_ENTRIES	30
+
 /* From ABI specifications */
 struct unwind_table_entry {
 	unsigned int region_start;
diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index fc0df353ff0d..87245c584784 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -113,7 +113,6 @@
 #define	ELOOP		249	/* Too many symbolic links encountered */
 #define	ENOSYS		251	/* Function not implemented */
 
-#define ENOTSUP		252	/* Function not implemented (POSIX.4 / HPUX) */
 #define ECANCELLED	253	/* aio request was canceled before complete (POSIX.4 / HPUX) */
 #define ECANCELED	ECANCELLED	/* SuSv3 and Solaris wants one 'L' */
 
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index e95207c0565e..c7508f5717fb 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -482,6 +482,8 @@
 	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
 	or,COND(=)	%r0,\spc,%r0
+	sync
+	or,COND(=)	%r0,\spc,%r0
 	stw             \spc,0(\tmp)
 #endif
 	.endm
@@ -764,7 +766,6 @@ END(fault_vector_11)
 #endif
 	/* Fault vector is separately protected and *must* be on its own page */
 	.align		PAGE_SIZE
-ENTRY(end_fault_vector)
 
 	.import		handle_interruption,code
 	.import		do_cpu_irq_mask,code
@@ -776,7 +777,6 @@ ENTRY(end_fault_vector)
 	 */
 
 ENTRY_CFI(ret_from_kernel_thread)
-
 	/* Call schedule_tail first though */
 	BL	schedule_tail, %r2
 	nop
@@ -815,8 +815,9 @@ ENTRY_CFI(_switch_to)
 	LDREG	TASK_THREAD_INFO(%r25), %r25
 	bv	%r0(%r2)
 	mtctl   %r25,%cr30
+ENDPROC_CFI(_switch_to)
 
-_switch_to_ret:
+ENTRY_CFI(_switch_to_ret)
 	mtctl	%r0, %cr0		/* Needed for single stepping */
 	callee_rest
 	callee_rest_float
@@ -824,7 +825,7 @@ _switch_to_ret:
 	LDREG	-RP_OFFSET(%r30), %r2
 	bv	%r0(%r2)
 	copy	%r26, %r28
-ENDPROC_CFI(_switch_to)
+ENDPROC_CFI(_switch_to_ret)
 
 	/*
 	 * Common rfi return path for interruptions, kernel execve, and
@@ -885,12 +886,14 @@ ENTRY_CFI(syscall_exit_rfi)
 	STREG   %r19,PT_SR5(%r16)
 	STREG   %r19,PT_SR6(%r16)
 	STREG   %r19,PT_SR7(%r16)
+ENDPROC_CFI(syscall_exit_rfi)
 
-intr_return:
+ENTRY_CFI(intr_return)
 	/* check for reschedule */
 	mfctl   %cr30,%r1
 	LDREG   TI_FLAGS(%r1),%r19	/* sched.h: TIF_NEED_RESCHED */
 	bb,<,n	%r19,31-TIF_NEED_RESCHED,intr_do_resched /* forward */
+ENDPROC_CFI(intr_return)
 
 	.import do_notify_resume,code
 intr_check_sig:
@@ -1046,7 +1049,6 @@ intr_extint:
 
 	b	do_cpu_irq_mask
 	ldo	R%intr_return(%r2), %r2	/* return to intr_return, not here */
-ENDPROC_CFI(syscall_exit_rfi)
 
 
 	/* Generic interruptions (illegal insn, unaligned, page fault, etc) */
@@ -1997,12 +1999,9 @@ ENDPROC_CFI(syscall_exit)
 	.align L1_CACHE_BYTES
 	.globl mcount
 	.type  mcount, @function
-ENTRY(mcount)
+ENTRY_CFI(mcount, caller)
 _mcount:
 	.export _mcount,data
-	.proc
-	.callinfo caller,frame=0
-	.entry
 	/*
 	 * The 64bit mcount() function pointer needs 4 dwords, of which the
 	 * first two are free.  We optimize it here and put 2 instructions for
@@ -2024,18 +2023,13 @@ ftrace_stub:
 	.dword mcount
 	.dword 0 /* code in head.S puts value of global gp here */
 #endif
-	.exit
-	.procend
-ENDPROC(mcount)
+ENDPROC_CFI(mcount)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	.align 8
 	.globl return_to_handler
 	.type  return_to_handler, @function
-ENTRY_CFI(return_to_handler)
-	.proc
-	.callinfo caller,frame=FRAME_SIZE
-	.entry
+ENTRY_CFI(return_to_handler, caller,frame=FRAME_SIZE)
 	.export parisc_return_to_handler,data
 parisc_return_to_handler:
 	copy %r3,%r1
@@ -2074,8 +2068,6 @@ parisc_return_to_handler:
 	bv	%r0(%rp)
 #endif
 	LDREGM -FRAME_SIZE(%sp),%r3
-	.exit
-	.procend
 ENDPROC_CFI(return_to_handler)
 
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -2085,31 +2077,30 @@ ENDPROC_CFI(return_to_handler)
 #ifdef CONFIG_IRQSTACKS
 /* void call_on_stack(unsigned long param1, void *func,
 		      unsigned long new_stack) */
-ENTRY_CFI(call_on_stack)
+ENTRY_CFI(call_on_stack, FRAME=2*FRAME_SIZE,CALLS,SAVE_RP,SAVE_SP)
 	copy	%sp, %r1
 
 	/* Regarding the HPPA calling conventions for function pointers,
 	   we assume the PIC register is not changed across call.  For
 	   CONFIG_64BIT, the argument pointer is left to point at the
 	   argument region allocated for the call to call_on_stack. */
+
+	/* Switch to new stack.  We allocate two frames.  */
+	ldo	2*FRAME_SIZE(%arg2), %sp
 # ifdef CONFIG_64BIT
-	/* Switch to new stack.  We allocate two 128 byte frames.  */
-	ldo	256(%arg2), %sp
 	/* Save previous stack pointer and return pointer in frame marker */
-	STREG	%rp, -144(%sp)
+	STREG	%rp, -FRAME_SIZE-RP_OFFSET(%sp)
 	/* Calls always use function descriptor */
 	LDREG	16(%arg1), %arg1
 	bve,l	(%arg1), %rp
-	STREG	%r1, -136(%sp)
-	LDREG	-144(%sp), %rp
+	STREG	%r1, -FRAME_SIZE-REG_SZ(%sp)
+	LDREG	-FRAME_SIZE-RP_OFFSET(%sp), %rp
 	bve	(%rp)
-	LDREG	-136(%sp), %sp
+	LDREG	-FRAME_SIZE-REG_SZ(%sp), %sp
 # else
-	/* Switch to new stack.  We allocate two 64 byte frames.  */
-	ldo	128(%arg2), %sp
 	/* Save previous stack pointer and return pointer in frame marker */
-	STREG	%r1, -68(%sp)
-	STREG	%rp, -84(%sp)
+	STREG	%r1, -FRAME_SIZE-REG_SZ(%sp)
+	STREG	%rp, -FRAME_SIZE-RP_OFFSET(%sp)
 	/* Calls use function descriptor if PLABEL bit is set */
 	bb,>=,n	%arg1, 30, 1f
 	depwi	0,31,2, %arg1
@@ -2117,9 +2108,9 @@ ENTRY_CFI(call_on_stack)
 1:
 	be,l	0(%sr4,%arg1), %sr0, %r31
 	copy	%r31, %rp
-	LDREG	-84(%sp), %rp
+	LDREG	-FRAME_SIZE-RP_OFFSET(%sp), %rp
 	bv	(%rp)
-	LDREG	-68(%sp), %sp
+	LDREG	-FRAME_SIZE-REG_SZ(%sp), %sp
 # endif /* CONFIG_64BIT */
 ENDPROC_CFI(call_on_stack)
 #endif /* CONFIG_IRQSTACKS */
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 22e6374ece44..f33bf2d306d6 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -44,10 +44,6 @@
 	.align	16
 
 ENTRY_CFI(flush_tlb_all_local)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/*
 	 * The pitlbe and pdtlbe instructions should only be used to
 	 * flush the entire tlb. Also, there needs to be no intervening
@@ -189,18 +185,11 @@ fdtdone:
 
 2:      bv		%r0(%r2)
 	nop
-
-	.exit
-	.procend
 ENDPROC_CFI(flush_tlb_all_local)
 
 	.import cache_info,data
 
 ENTRY_CFI(flush_instruction_cache_local)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	load32		cache_info, %r1
 
 	/* Flush Instruction Cache */
@@ -256,18 +245,11 @@ fisync:
 	mtsm		%r22			/* restore I-bit */
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_instruction_cache_local)
 
 
 	.import cache_info, data
 ENTRY_CFI(flush_data_cache_local)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	load32		cache_info, %r1
 
 	/* Flush Data Cache */
@@ -324,9 +306,6 @@ fdsync:
 	mtsm		%r22			/* restore I-bit */
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_data_cache_local)
 
 /* Macros to serialize TLB purge operations on SMP.  */
@@ -353,6 +332,7 @@ ENDPROC_CFI(flush_data_cache_local)
 	.macro	tlb_unlock	la,flags,tmp
 #ifdef CONFIG_SMP
 	ldi		1,\tmp
+	sync
 	stw		\tmp,0(\la)
 	mtsm		\flags
 #endif
@@ -361,10 +341,6 @@ ENDPROC_CFI(flush_data_cache_local)
 /* Clear page using kernel mapping.  */
 
 ENTRY_CFI(clear_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 #ifdef CONFIG_64BIT
 
 	/* Unroll the loop.  */
@@ -423,18 +399,11 @@ ENTRY_CFI(clear_page_asm)
 #endif
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(clear_page_asm)
 
 /* Copy page using kernel mapping.  */
 
 ENTRY_CFI(copy_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 #ifdef CONFIG_64BIT
 	/* PA8x00 CPUs can consume 2 loads or 1 store per cycle.
 	 * Unroll the loop by hand and arrange insn appropriately.
@@ -541,9 +510,6 @@ ENTRY_CFI(copy_page_asm)
 #endif
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(copy_page_asm)
 
 /*
@@ -597,10 +563,6 @@ ENDPROC_CFI(copy_page_asm)
 	 */
 
 ENTRY_CFI(copy_user_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/* Convert virtual `to' and `from' addresses to physical addresses.
 	   Move `from' physical address to non shadowed register.  */
 	ldil		L%(__PAGE_OFFSET), %r1
@@ -749,16 +711,9 @@ ENTRY_CFI(copy_user_page_asm)
 
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(copy_user_page_asm)
 
 ENTRY_CFI(clear_user_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	tophys_r1	%r26
 
 	ldil		L%(TMPALIAS_MAP_START), %r28
@@ -835,16 +790,9 @@ ENTRY_CFI(clear_user_page_asm)
 
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(clear_user_page_asm)
 
 ENTRY_CFI(flush_dcache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%(TMPALIAS_MAP_START), %r28
 #ifdef CONFIG_64BIT
 #if (TMPALIAS_MAP_START >= 0x80000000)
@@ -902,16 +850,9 @@ ENTRY_CFI(flush_dcache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_dcache_page_asm)
 
 ENTRY_CFI(flush_icache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%(TMPALIAS_MAP_START), %r28
 #ifdef CONFIG_64BIT
 #if (TMPALIAS_MAP_START >= 0x80000000)
@@ -976,16 +917,9 @@ ENTRY_CFI(flush_icache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_icache_page_asm)
 
 ENTRY_CFI(flush_kernel_dcache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 
@@ -1019,16 +953,9 @@ ENTRY_CFI(flush_kernel_dcache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_kernel_dcache_page_asm)
 
 ENTRY_CFI(purge_kernel_dcache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 
@@ -1061,16 +988,9 @@ ENTRY_CFI(purge_kernel_dcache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(purge_kernel_dcache_page_asm)
 
 ENTRY_CFI(flush_user_dcache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1082,16 +1002,9 @@ ENTRY_CFI(flush_user_dcache_range_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_user_dcache_range_asm)
 
 ENTRY_CFI(flush_kernel_dcache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1104,16 +1017,9 @@ ENTRY_CFI(flush_kernel_dcache_range_asm)
 	syncdma
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_kernel_dcache_range_asm)
 
 ENTRY_CFI(purge_kernel_dcache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1126,16 +1032,9 @@ ENTRY_CFI(purge_kernel_dcache_range_asm)
 	syncdma
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(purge_kernel_dcache_range_asm)
 
 ENTRY_CFI(flush_user_icache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1147,16 +1046,9 @@ ENTRY_CFI(flush_user_icache_range_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_user_icache_range_asm)
 
 ENTRY_CFI(flush_kernel_icache_page)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 
@@ -1190,16 +1082,9 @@ ENTRY_CFI(flush_kernel_icache_page)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_kernel_icache_page)
 
 ENTRY_CFI(flush_kernel_icache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1211,8 +1096,6 @@ ENTRY_CFI(flush_kernel_icache_range_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-	.procend
 ENDPROC_CFI(flush_kernel_icache_range_asm)
 
 	__INIT
@@ -1222,10 +1105,6 @@ ENDPROC_CFI(flush_kernel_icache_range_asm)
 	 */
 	.align	256
 ENTRY_CFI(disable_sr_hashing_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/*
 	 * Switch to real mode
 	 */
@@ -1307,9 +1186,6 @@ srdis_done:
 
 2:      bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(disable_sr_hashing_asm)
 
 	.end
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 6df07ce4f3c2..04c48f1ef3fb 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -21,13 +21,12 @@
 #include <linux/init.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
-#include <linux/pci.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/types.h>
-#include <linux/scatterlist.h>
-#include <linux/export.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 
 #include <asm/cacheflush.h>
 #include <asm/dma.h>    /* for DMA_CHUNK_SIZE */
@@ -395,7 +394,7 @@ pcxl_dma_init(void)
 
 __initcall(pcxl_dma_init);
 
-static void *pa11_dma_alloc(struct device *dev, size_t size,
+static void *pcxl_dma_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
 {
 	unsigned long vaddr;
@@ -422,190 +421,60 @@ static void *pa11_dma_alloc(struct device *dev, size_t size,
 	return (void *)vaddr;
 }
 
-static void pa11_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
+static void *pcx_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
 {
-	int order;
-
-	order = get_order(size);
-	size = 1 << (order + PAGE_SHIFT);
-	unmap_uncached_pages((unsigned long)vaddr, size);
-	pcxl_free_range((unsigned long)vaddr, size);
-	free_pages((unsigned long)__va(dma_handle), order);
-}
+	void *addr;
 
-static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size,
-		enum dma_data_direction direction, unsigned long attrs)
-{
-	void *addr = page_address(page) + offset;
-	BUG_ON(direction == DMA_NONE);
+	if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
+		return NULL;
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		flush_kernel_dcache_range((unsigned long) addr, size);
+	addr = (void *)__get_free_pages(flag, get_order(size));
+	if (addr)
+		*dma_handle = (dma_addr_t)virt_to_phys(addr);
 
-	return virt_to_phys(addr);
+	return addr;
 }
 
-static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
-		size_t size, enum dma_data_direction direction,
-		unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
-	BUG_ON(direction == DMA_NONE);
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
 
-	if (direction == DMA_TO_DEVICE)
-		return;
-
-	/*
-	 * For PCI_DMA_FROMDEVICE this flush is not necessary for the
-	 * simple map/unmap case. However, it IS necessary if if
-	 * pci_dma_sync_single_* has been called and the buffer reused.
-	 */
-
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), size);
+	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl)
+		return pcxl_dma_alloc(dev, size, dma_handle, gfp, attrs);
+	else
+		return pcx_dma_alloc(dev, size, dma_handle, gfp, attrs);
 }
 
-static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
 {
-	int i;
-	struct scatterlist *sg;
-
-	BUG_ON(direction == DMA_NONE);
+	int order = get_order(size);
 
-	for_each_sg(sglist, sg, nents, i) {
-		unsigned long vaddr = (unsigned long)sg_virt(sg);
+	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
+		size = 1 << (order + PAGE_SHIFT);
+		unmap_uncached_pages((unsigned long)vaddr, size);
+		pcxl_free_range((unsigned long)vaddr, size);
 
-		sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr);
-		sg_dma_len(sg) = sg->length;
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		flush_kernel_dcache_range(vaddr, sg->length);
+		vaddr = __va(dma_handle);
 	}
-	return nents;
-}
-
-static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	BUG_ON(direction == DMA_NONE);
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	if (direction == DMA_TO_DEVICE)
-		return;
-
-	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
-	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_vmap_range(sg_virt(sg), sg->length);
-}
-
-static void pa11_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
-			size);
-}
-
-static void pa11_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
-			size);
+	free_pages((unsigned long)vaddr, get_order(size));
 }
 
-static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	int i;
-	struct scatterlist *sg;
-
-	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
-	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_vmap_range(sg_virt(sg), sg->length);
+	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
 
-static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	int i;
-	struct scatterlist *sg;
-
-	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
-	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_vmap_range(sg_virt(sg), sg->length);
+	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
 
-static void pa11_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction)
 {
 	flush_kernel_dcache_range((unsigned long)vaddr, size);
 }
-
-const struct dma_map_ops pcxl_dma_ops = {
-	.alloc =		pa11_dma_alloc,
-	.free =			pa11_dma_free,
-	.map_page =		pa11_dma_map_page,
-	.unmap_page =		pa11_dma_unmap_page,
-	.map_sg =		pa11_dma_map_sg,
-	.unmap_sg =		pa11_dma_unmap_sg,
-	.sync_single_for_cpu =	pa11_dma_sync_single_for_cpu,
-	.sync_single_for_device = pa11_dma_sync_single_for_device,
-	.sync_sg_for_cpu =	pa11_dma_sync_sg_for_cpu,
-	.sync_sg_for_device =	pa11_dma_sync_sg_for_device,
-	.cache_sync =		pa11_dma_cache_sync,
-};
-
-static void *pcx_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
-{
-	void *addr;
-
-	if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
-		return NULL;
-
-	addr = (void *)__get_free_pages(flag, get_order(size));
-	if (addr)
-		*dma_handle = (dma_addr_t)virt_to_phys(addr);
-
-	return addr;
-}
-
-static void pcx_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t iova, unsigned long attrs)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-	return;
-}
-
-const struct dma_map_ops pcx_dma_ops = {
-	.alloc =		pcx_dma_alloc,
-	.free =			pcx_dma_free,
-	.map_page =		pa11_dma_map_page,
-	.unmap_page =		pa11_dma_unmap_page,
-	.map_sg =		pa11_dma_map_sg,
-	.unmap_sg =		pa11_dma_unmap_sg,
-	.sync_single_for_cpu =	pa11_dma_sync_single_for_cpu,
-	.sync_single_for_device = pa11_dma_sync_single_for_device,
-	.sync_sg_for_cpu =	pa11_dma_sync_sg_for_cpu,
-	.sync_sg_for_device =	pa11_dma_sync_sg_for_device,
-	.cache_sync =		pa11_dma_cache_sync,
-};
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index b931745815e0..eb39e7e380d7 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -302,7 +302,7 @@ get_wchan(struct task_struct *p)
 		ip = info.ip;
 		if (!in_sched_functions(ip))
 			return ip;
-	} while (count++ < 16);
+	} while (count++ < MAX_UNWIND_ENTRIES);
 	return 0;
 }
 
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 7aa1d4d0d444..2582df1c529b 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -676,3 +676,103 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 #endif
 	return &user_parisc_native_view;
 }
+
+
+/* HAVE_REGS_AND_STACK_ACCESS_API feature */
+
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(r)    {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_INDEX(r,i) {.name = #r#i, .offset = offsetof(struct pt_regs, r[i])}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_INDEX(gr,0),
+	REG_OFFSET_INDEX(gr,1),
+	REG_OFFSET_INDEX(gr,2),
+	REG_OFFSET_INDEX(gr,3),
+	REG_OFFSET_INDEX(gr,4),
+	REG_OFFSET_INDEX(gr,5),
+	REG_OFFSET_INDEX(gr,6),
+	REG_OFFSET_INDEX(gr,7),
+	REG_OFFSET_INDEX(gr,8),
+	REG_OFFSET_INDEX(gr,9),
+	REG_OFFSET_INDEX(gr,10),
+	REG_OFFSET_INDEX(gr,11),
+	REG_OFFSET_INDEX(gr,12),
+	REG_OFFSET_INDEX(gr,13),
+	REG_OFFSET_INDEX(gr,14),
+	REG_OFFSET_INDEX(gr,15),
+	REG_OFFSET_INDEX(gr,16),
+	REG_OFFSET_INDEX(gr,17),
+	REG_OFFSET_INDEX(gr,18),
+	REG_OFFSET_INDEX(gr,19),
+	REG_OFFSET_INDEX(gr,20),
+	REG_OFFSET_INDEX(gr,21),
+	REG_OFFSET_INDEX(gr,22),
+	REG_OFFSET_INDEX(gr,23),
+	REG_OFFSET_INDEX(gr,24),
+	REG_OFFSET_INDEX(gr,25),
+	REG_OFFSET_INDEX(gr,26),
+	REG_OFFSET_INDEX(gr,27),
+	REG_OFFSET_INDEX(gr,28),
+	REG_OFFSET_INDEX(gr,29),
+	REG_OFFSET_INDEX(gr,30),
+	REG_OFFSET_INDEX(gr,31),
+	REG_OFFSET_INDEX(sr,0),
+	REG_OFFSET_INDEX(sr,1),
+	REG_OFFSET_INDEX(sr,2),
+	REG_OFFSET_INDEX(sr,3),
+	REG_OFFSET_INDEX(sr,4),
+	REG_OFFSET_INDEX(sr,5),
+	REG_OFFSET_INDEX(sr,6),
+	REG_OFFSET_INDEX(sr,7),
+	REG_OFFSET_INDEX(iasq,0),
+	REG_OFFSET_INDEX(iasq,1),
+	REG_OFFSET_INDEX(iaoq,0),
+	REG_OFFSET_INDEX(iaoq,1),
+	REG_OFFSET_NAME(cr27),
+	REG_OFFSET_NAME(ksp),
+	REG_OFFSET_NAME(kpc),
+	REG_OFFSET_NAME(sar),
+	REG_OFFSET_NAME(iir),
+	REG_OFFSET_NAME(isr),
+	REG_OFFSET_NAME(ior),
+	REG_OFFSET_NAME(ipsw),
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset:	the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (roff->offset == offset)
+			return roff->name;
+	return NULL;
+}
diff --git a/arch/parisc/kernel/real2.S b/arch/parisc/kernel/real2.S
index cc9963421a19..2b16d8d6598f 100644
--- a/arch/parisc/kernel/real2.S
+++ b/arch/parisc/kernel/real2.S
@@ -35,12 +35,6 @@ real32_stack:
 real64_stack:
 	.block	8192
 
-#ifdef CONFIG_64BIT
-#  define REG_SZ 8
-#else
-#  define REG_SZ 4
-#endif
-
 #define N_SAVED_REGS 9
 
 save_cr_space:
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 8d3a7b80ac42..4e87c35c22b7 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -97,14 +97,12 @@ void __init dma_ops_init(void)
 		panic(	"PA-RISC Linux currently only supports machines that conform to\n"
 			"the PA-RISC 1.1 or 2.0 architecture specification.\n");
 
-	case pcxs:
-	case pcxt:
-		hppa_dma_ops = &pcx_dma_ops;
-		break;
 	case pcxl2:
 		pa7300lc_init();
 	case pcxl: /* falls through */
-		hppa_dma_ops = &pcxl_dma_ops;
+	case pcxs:
+	case pcxt:
+		hppa_dma_ops = &dma_noncoherent_ops;
 		break;
 	default:
 		break;
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index e775f80ae28c..5f7e57fcaeef 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -629,11 +629,12 @@ cas_action:
 	stw	%r1, 4(%sr2,%r20)
 #endif
 	/* The load and store could fail */
-1:	ldw,ma	0(%r26), %r28
+1:	ldw	0(%r26), %r28
 	sub,<>	%r28, %r25, %r0
-2:	stw,ma	%r24, 0(%r26)
+2:	stw	%r24, 0(%r26)
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
 	stw	%r0, 4(%sr2,%r20)
@@ -647,6 +648,7 @@ cas_action:
 3:		
 	/* Error occurred on load or store */
 	/* Free lock */
+	sync
 	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	stw	%r0, 4(%sr2,%r20)
@@ -796,30 +798,30 @@ cas2_action:
 	ldo	1(%r0),%r28
 
 	/* 8bit CAS */
-13:	ldb,ma	0(%r26), %r29
+13:	ldb	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-14:	stb,ma	%r24, 0(%r26)
+14:	stb	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop
 
 	/* 16bit CAS */
-15:	ldh,ma	0(%r26), %r29
+15:	ldh	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-16:	sth,ma	%r24, 0(%r26)
+16:	sth	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop
 
 	/* 32bit CAS */
-17:	ldw,ma	0(%r26), %r29
+17:	ldw	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-18:	stw,ma	%r24, 0(%r26)
+18:	stw	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
@@ -827,10 +829,10 @@ cas2_action:
 
 	/* 64bit CAS */
 #ifdef CONFIG_64BIT
-19:	ldd,ma	0(%r26), %r29
+19:	ldd	0(%r26), %r29
 	sub,*=	%r29, %r25, %r0
 	b,n	cas2_end
-20:	std,ma	%r24, 0(%r26)
+20:	std	%r24, 0(%r26)
 	copy	%r0, %r28
 #else
 	/* Compare first word */
@@ -848,7 +850,8 @@ cas2_action:
 
 cas2_end:
 	/* Free lock */
-	stw,ma	%r20, 0(%sr2,%r20)
+	sync
+	stw	%r20, 0(%sr2,%r20)
 	/* Enable interrupts */
 	ssm	PSW_SM_I, %r0
 	/* Return to userspace, set no error */
@@ -858,6 +861,7 @@ cas2_end:
 22:
 	/* Error occurred on load or store */
 	/* Free lock */
+	sync
 	stw	%r20, 0(%sr2,%r20)
 	ssm	PSW_SM_I, %r0
 	ldo	1(%r0),%r28
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 4309ad31a874..318815212518 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -172,7 +172,7 @@ static void do_show_stack(struct unwind_frame_info *info)
 	int i = 1;
 
 	printk(KERN_CRIT "Backtrace:\n");
-	while (i <= 16) {
+	while (i <= MAX_UNWIND_ENTRIES) {
 		if (unwind_once(info) < 0 || info->ip == 0)
 			break;
 
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index 2ef83d78eec4..5cdf13069dd9 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -13,7 +13,6 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/kallsyms.h>
 #include <linux/sort.h>
 
 #include <linux/uaccess.h>
@@ -117,7 +116,8 @@ unwind_table_init(struct unwind_table *table, const char *name,
 	for (; start <= end; start++) {
 		if (start < end && 
 		    start->region_end > (start+1)->region_start) {
-			printk("WARNING: Out of order unwind entry! %p and %p\n", start, start+1);
+			pr_warn("Out of order unwind entry! %px and %px\n",
+				start, start+1);
 		}
 
 		start->region_start += base_addr;
@@ -203,25 +203,60 @@ int __init unwind_init(void)
 	return 0;
 }
 
-#ifdef CONFIG_64BIT
-#define get_func_addr(fptr) fptr[2]
-#else
-#define get_func_addr(fptr) fptr[0]
-#endif
-
 static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int frame_size)
 {
-	extern void handle_interruption(int, struct pt_regs *);
-	static unsigned long *hi = (unsigned long *)&handle_interruption;
-
-	if (pc == get_func_addr(hi)) {
+	/*
+	 * We have to use void * instead of a function pointer, because
+	 * function pointers aren't a pointer to the function on 64-bit.
+	 * Make them const so the compiler knows they live in .text
+	 */
+	extern void * const handle_interruption;
+	extern void * const ret_from_kernel_thread;
+	extern void * const syscall_exit;
+	extern void * const intr_return;
+	extern void * const _switch_to_ret;
+#ifdef CONFIG_IRQSTACKS
+	extern void * const call_on_stack;
+#endif /* CONFIG_IRQSTACKS */
+
+	if (pc == (unsigned long) &handle_interruption) {
 		struct pt_regs *regs = (struct pt_regs *)(info->sp - frame_size - PT_SZ_ALGN);
 		dbg("Unwinding through handle_interruption()\n");
 		info->prev_sp = regs->gr[30];
 		info->prev_ip = regs->iaoq[0];
+		return 1;
+	}
+
+	if (pc == (unsigned long) &ret_from_kernel_thread ||
+	    pc == (unsigned long) &syscall_exit) {
+		info->prev_sp = info->prev_ip = 0;
+		return 1;
+	}
+
+	if (pc == (unsigned long) &intr_return) {
+		struct pt_regs *regs;
+
+		dbg("Found intr_return()\n");
+		regs = (struct pt_regs *)(info->sp - PT_SZ_ALGN);
+		info->prev_sp = regs->gr[30];
+		info->prev_ip = regs->iaoq[0];
+		info->rp = regs->gr[2];
+		return 1;
+	}
+
+	if (pc == (unsigned long) &_switch_to_ret) {
+		info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
+		info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
+		return 1;
+	}
 
+#ifdef CONFIG_IRQSTACKS
+	if (pc == (unsigned long) &call_on_stack) {
+		info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ);
+		info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET);
 		return 1;
 	}
+#endif
 
 	return 0;
 }
@@ -238,34 +273,8 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
 	if (e == NULL) {
 		unsigned long sp;
 
-		dbg("Cannot find unwind entry for 0x%lx; forced unwinding\n", info->ip);
-
-#ifdef CONFIG_KALLSYMS
-		/* Handle some frequent special cases.... */
-		{
-			char symname[KSYM_NAME_LEN];
-			char *modname;
-
-			kallsyms_lookup(info->ip, NULL, NULL, &modname,
-				symname);
-
-			dbg("info->ip = 0x%lx, name = %s\n", info->ip, symname);
-
-			if (strcmp(symname, "_switch_to_ret") == 0) {
-				info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
-				info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
-				dbg("_switch_to_ret @ %lx - setting "
-				    "prev_sp=%lx prev_ip=%lx\n", 
-				    info->ip, info->prev_sp, 
-				    info->prev_ip);
-				return;
-			} else if (strcmp(symname, "ret_from_kernel_thread") == 0 ||
-				   strcmp(symname, "syscall_exit") == 0) {
-				info->prev_ip = info->prev_sp = 0;
-				return;
-			}
-		}
-#endif
+		dbg("Cannot find unwind entry for %pS; forced unwinding\n",
+			(void *) info->ip);
 
 		/* Since we are doing the unwinding blind, we don't know if
 		   we are adjusting the stack correctly or extracting the rp
@@ -439,8 +448,8 @@ unsigned long return_address(unsigned int level)
 	/* initialize unwind info */
 	asm volatile ("copy %%r30, %0" : "=r"(sp));
 	memset(&r, 0, sizeof(struct pt_regs));
-	r.iaoq[0] = (unsigned long) current_text_addr();
-	r.gr[2] = (unsigned long) __builtin_return_address(0);
+	r.iaoq[0] = _THIS_IP_;
+	r.gr[2] = _RET_IP_;
 	r.gr[30] = sp;
 	unwind_frame_init(&info, current, &r);
 
diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S
index d4fe19806d57..b53fb6fedf06 100644
--- a/arch/parisc/lib/lusercopy.S
+++ b/arch/parisc/lib/lusercopy.S
@@ -64,9 +64,6 @@
 	 */
 
 ENTRY_CFI(lclear_user)
-	.proc
-	.callinfo NO_CALLS
-	.entry
 	comib,=,n   0,%r25,$lclu_done
 	get_sr
 $lclu_loop:
@@ -81,13 +78,9 @@ $lclu_done:
 	ldo         1(%r25),%r25
 
 	ASM_EXCEPTIONTABLE_ENTRY(1b,2b)
-
-	.exit
 ENDPROC_CFI(lclear_user)
 
 
-	.procend
-
 	/*
 	 * long lstrnlen_user(char *s, long n)
 	 *
@@ -97,9 +90,6 @@ ENDPROC_CFI(lclear_user)
 	 */
 
 ENTRY_CFI(lstrnlen_user)
-	.proc
-	.callinfo NO_CALLS
-	.entry
 	comib,=     0,%r25,$lslen_nzero
 	copy	    %r26,%r24
 	get_sr
@@ -111,7 +101,6 @@ $lslen_loop:
 $lslen_done:
 	bv          %r0(%r2)
 	sub	    %r26,%r24,%r28
-	.exit
 
 $lslen_nzero:
 	b           $lslen_done
@@ -125,9 +114,6 @@ $lslen_nzero:
 
 ENDPROC_CFI(lstrnlen_user)
 
-	.procend
-
-
 
 /*
  * unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
@@ -186,10 +172,6 @@ ENDPROC_CFI(lstrnlen_user)
 	save_len = r31
 
 ENTRY_CFI(pa_memcpy)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/* Last destination address */
 	add	dst,len,end
 
@@ -439,9 +421,6 @@ ENTRY_CFI(pa_memcpy)
 	b	.Lcopy_done
 10:	stw,ma	t1,4(dstspc,dst)
 	ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
-
-	.exit
 ENDPROC_CFI(pa_memcpy)
-	.procend
 
 	.end
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 2607d2d33405..74842d28a7a1 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -19,7 +19,6 @@
 #include <linux/gfp.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/pci.h>		/* for hppa_dma_ops and pcxl_dma_ops */
 #include <linux/initrd.h>
 #include <linux/swap.h>
 #include <linux/unistd.h>
@@ -616,17 +615,13 @@ void __init mem_init(void)
 	free_all_bootmem();
 
 #ifdef CONFIG_PA11
-	if (hppa_dma_ops == &pcxl_dma_ops) {
+	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
 		pcxl_dma_start = (unsigned long)SET_MAP_OFFSET(MAP_START);
 		parisc_vmalloc_start = SET_MAP_OFFSET(pcxl_dma_start
 						+ PCXL_DMA_MAP_SIZE);
-	} else {
-		pcxl_dma_start = 0;
-		parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
-	}
-#else
-	parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
+	} else
 #endif
+		parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
 
 	mem_init_print_info(NULL);
 
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 682b3e6a1e21..963abf8bf1c0 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -18,18 +18,11 @@
  * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
  * on the platform without lwsync.
  */
-#define __atomic_op_acquire(op, args...)				\
-({									\
-	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory");	\
-	__ret;								\
-})
-
-#define __atomic_op_release(op, args...)				\
-({									\
-	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory");	\
-	op##_relaxed(args);						\
-})
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory")
 
 static __inline__ int atomic_read(const atomic_t *v)
 {
@@ -129,8 +122,6 @@ ATOMIC_OPS(xor, xor)
 #undef ATOMIC_OP_RETURN_RELAXED
 #undef ATOMIC_OP
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
 static __inline__ void atomic_inc(atomic_t *v)
 {
 	int t;
@@ -145,6 +136,7 @@ static __inline__ void atomic_inc(atomic_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic_inc atomic_inc
 
 static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 {
@@ -163,16 +155,6 @@ static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 	return t;
 }
 
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
 static __inline__ void atomic_dec(atomic_t *v)
 {
 	int t;
@@ -187,6 +169,7 @@ static __inline__ void atomic_dec(atomic_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic_dec atomic_dec
 
 static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 {
@@ -218,7 +201,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -226,13 +209,13 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%1		# __atomic_add_unless\n\
+"1:	lwarx	%0,0,%1		# atomic_fetch_add_unless\n\
 	cmpw	0,%0,%3 \n\
 	beq	2f \n\
 	add	%0,%2,%0 \n"
@@ -248,6 +231,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return t;
 }
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 /**
  * atomic_inc_not_zero - increment unless the number is zero
@@ -280,9 +264,6 @@ static __inline__ int atomic_inc_not_zero(atomic_t *v)
 }
 #define atomic_inc_not_zero(v) atomic_inc_not_zero((v))
 
-#define atomic_sub_and_test(a, v)	(atomic_sub_return((a), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return((v)) == 0)
-
 /*
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1, even if
@@ -412,8 +393,6 @@ ATOMIC64_OPS(xor, xor)
 #undef ATOMIC64_OP_RETURN_RELAXED
 #undef ATOMIC64_OP
 
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
 static __inline__ void atomic64_inc(atomic64_t *v)
 {
 	long t;
@@ -427,6 +406,7 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic64_inc atomic64_inc
 
 static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 {
@@ -444,16 +424,6 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 	return t;
 }
 
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
 static __inline__ void atomic64_dec(atomic64_t *v)
 {
 	long t;
@@ -467,6 +437,7 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic64_dec atomic64_dec
 
 static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 {
@@ -487,9 +458,6 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
 #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
 
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-
 /*
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1.
@@ -513,6 +481,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 
 	return t;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_cmpxchg_relaxed(v, o, n) \
@@ -524,7 +493,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -532,13 +501,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
 	long t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
-"1:	ldarx	%0,0,%1		# __atomic_add_unless\n\
+"1:	ldarx	%0,0,%1		# atomic64_fetch_add_unless\n\
 	cmpd	0,%0,%3 \n\
 	beq	2f \n\
 	add	%0,%2,%0 \n"
@@ -551,8 +520,9 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 	: "r" (&v->counter), "r" (a), "r" (u)
 	: "cc", "memory");
 
-	return t != u;
+	return t;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 /**
  * atomic_inc64_not_zero - increment unless the number is zero
@@ -582,6 +552,7 @@ static __inline__ int atomic64_inc_not_zero(atomic64_t *v)
 
 	return t1 != 0;
 }
+#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v))
 
 #endif /* __powerpc64__ */
 
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 8e7b09703ca4..27d6e3c8fde9 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -52,6 +52,7 @@ struct arch_hw_breakpoint {
 #include <asm/reg.h>
 #include <asm/debug.h>
 
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 struct perf_sample_data;
@@ -60,8 +61,10 @@ struct perf_sample_data;
 
 extern int hw_breakpoint_slots(int type);
 extern int arch_bp_generic_fields(int type, int *gen_bp_type);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 						unsigned long val, void *data);
 int arch_install_hw_breakpoint(struct perf_event *bp);
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 9f3be5c8a4a3..785c464b6588 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -88,7 +88,6 @@ struct prev_kprobe {
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_saved_msr;
-	struct pt_regs jprobe_saved_regs;
 	struct prev_kprobe prev_kprobe;
 };
 
@@ -103,17 +102,6 @@ extern int kprobe_exceptions_notify(struct notifier_block *self,
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_handler(struct pt_regs *regs);
 extern int kprobe_post_handler(struct pt_regs *regs);
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int __is_active_jprobe(unsigned long addr);
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			   struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				  struct kprobe_ctlblk *kcb)
-{
-	return 0;
-}
-#endif
 #else
 static inline int kprobe_handler(struct pt_regs *regs) { return 0; }
 static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; }
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 80547dad37da..fec8a6773119 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -119,11 +119,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp)
 /*
  * Check for virtual address in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	return is_kernel_addr(info->address);
+	return is_kernel_addr(hw->address);
 }
 
 int arch_bp_generic_fields(int type, int *gen_bp_type)
@@ -141,30 +139,31 @@ int arch_bp_generic_fields(int type, int *gen_bp_type)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
 	int ret = -EINVAL, length_max;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
 	if (!bp)
 		return ret;
 
-	info->type = HW_BRK_TYPE_TRANSLATE;
-	if (bp->attr.bp_type & HW_BREAKPOINT_R)
-		info->type |= HW_BRK_TYPE_READ;
-	if (bp->attr.bp_type & HW_BREAKPOINT_W)
-		info->type |= HW_BRK_TYPE_WRITE;
-	if (info->type == HW_BRK_TYPE_TRANSLATE)
+	hw->type = HW_BRK_TYPE_TRANSLATE;
+	if (attr->bp_type & HW_BREAKPOINT_R)
+		hw->type |= HW_BRK_TYPE_READ;
+	if (attr->bp_type & HW_BREAKPOINT_W)
+		hw->type |= HW_BRK_TYPE_WRITE;
+	if (hw->type == HW_BRK_TYPE_TRANSLATE)
 		/* must set alteast read or write */
 		return ret;
-	if (!(bp->attr.exclude_user))
-		info->type |= HW_BRK_TYPE_USER;
-	if (!(bp->attr.exclude_kernel))
-		info->type |= HW_BRK_TYPE_KERNEL;
-	if (!(bp->attr.exclude_hv))
-		info->type |= HW_BRK_TYPE_HYP;
-	info->address = bp->attr.bp_addr;
-	info->len = bp->attr.bp_len;
+	if (!attr->exclude_user)
+		hw->type |= HW_BRK_TYPE_USER;
+	if (!attr->exclude_kernel)
+		hw->type |= HW_BRK_TYPE_KERNEL;
+	if (!attr->exclude_hv)
+		hw->type |= HW_BRK_TYPE_HYP;
+	hw->address = attr->bp_addr;
+	hw->len = attr->bp_len;
 
 	/*
 	 * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8)
@@ -178,12 +177,12 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	if (cpu_has_feature(CPU_FTR_DAWR)) {
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
-		if ((bp->attr.bp_addr >> 9) !=
-		    ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9))
+		if ((attr->bp_addr >> 9) !=
+		    ((attr->bp_addr + attr->bp_len - 1) >> 9))
 			return -EINVAL;
 	}
-	if (info->len >
-	    (length_max - (info->address & HW_BREAKPOINT_ALIGN)))
+	if (hw->len >
+	    (length_max - (hw->address & HW_BREAKPOINT_ALIGN)))
 		return -EINVAL;
 	return 0;
 }
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 7a1f99f1b47f..e4a49c051325 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -25,50 +25,6 @@
 #include <linux/preempt.h>
 #include <linux/ftrace.h>
 
-/*
- * This is called from ftrace code after invoking registered handlers to
- * disambiguate regs->nip changes done by jprobes and livepatch. We check if
- * there is an active jprobe at the provided address (mcount location).
- */
-int __is_active_jprobe(unsigned long addr)
-{
-	if (!preemptible()) {
-		struct kprobe *p = raw_cpu_read(current_kprobe);
-		return (p && (unsigned long)p->addr == addr) ? 1 : 0;
-	}
-
-	return 0;
-}
-
-static nokprobe_inline
-int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		      struct kprobe_ctlblk *kcb, unsigned long orig_nip)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->nip)
-	 * as if there is a nop
-	 */
-	regs->nip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-	if (orig_nip)
-		regs->nip = orig_nip;
-	return 1;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		    struct kprobe_ctlblk *kcb)
-{
-	if (kprobe_ftrace(p))
-		return __skip_singlestep(p, regs, kcb, 0);
-	else
-		return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
 /* Ftrace callback handler for kprobes */
 void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 			   struct ftrace_ops *ops, struct pt_regs *regs)
@@ -76,18 +32,14 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
-	preempt_disable();
-
 	p = get_kprobe((kprobe_opcode_t *)nip);
 	if (unlikely(!p) || kprobe_disabled(p))
-		goto end;
+		return;
 
 	kcb = get_kprobe_ctlblk();
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(p);
 	} else {
-		unsigned long orig_nip = regs->nip;
-
 		/*
 		 * On powerpc, NIP is *before* this instruction for the
 		 * pre handler
@@ -96,19 +48,23 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (!p->pre_handler || !p->pre_handler(p, regs))
-			__skip_singlestep(p, regs, kcb, orig_nip);
-		else {
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			/*
-			 * If pre_handler returns !0, it sets regs->nip and
-			 * resets current kprobe. In this case, we should not
-			 * re-enable preemption.
+			 * Emulate singlestep (and also recover regs->nip)
+			 * as if there is a nop
 			 */
-			return;
+			regs->nip += MCOUNT_INSN_SIZE;
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
 		}
+		/*
+		 * If pre_handler returns !0, it changes regs->nip. We have to
+		 * skip emulating post_handler.
+		 */
+		__this_cpu_write(current_kprobe, NULL);
 	}
-end:
-	preempt_enable_no_resched();
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index e4c5bf33970b..5c60bb0f927f 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -317,25 +317,17 @@ int kprobe_handler(struct pt_regs *regs)
 			}
 			prepare_singlestep(p, regs);
 			return 1;
-		} else {
-			if (*addr != BREAKPOINT_INSTRUCTION) {
-				/* If trap variant, then it belongs not to us */
-				kprobe_opcode_t cur_insn = *addr;
-				if (is_trap(cur_insn))
-		       			goto no_kprobe;
-				/* The breakpoint instruction was removed by
-				 * another cpu right after we hit, no further
-				 * handling of this interrupt is appropriate
-				 */
-				ret = 1;
+		} else if (*addr != BREAKPOINT_INSTRUCTION) {
+			/* If trap variant, then it belongs not to us */
+			kprobe_opcode_t cur_insn = *addr;
+
+			if (is_trap(cur_insn))
 				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				if (!skip_singlestep(p, regs, kcb))
-					goto ss_probe;
-				ret = 1;
-			}
+			/* The breakpoint instruction was removed by
+			 * another cpu right after we hit, no further
+			 * handling of this interrupt is appropriate
+			 */
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -350,7 +342,7 @@ int kprobe_handler(struct pt_regs *regs)
 			 */
 			kprobe_opcode_t cur_insn = *addr;
 			if (is_trap(cur_insn))
-		       		goto no_kprobe;
+				goto no_kprobe;
 			/*
 			 * The breakpoint instruction was removed right
 			 * after we hit it.  Another cpu has removed
@@ -366,11 +358,13 @@ int kprobe_handler(struct pt_regs *regs)
 
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 	set_current_kprobe(p, regs, kcb);
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/* handler has already set things up, so skip ss setup */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		/* handler changed execution path, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 	if (p->ainsn.boostable >= 0) {
 		ret = try_to_emulate(p, regs);
 
@@ -611,60 +605,6 @@ unsigned long arch_deref_entry_point(void *entry)
 }
 NOKPROBE_SYMBOL(arch_deref_entry_point);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
-	/* setup return addr to the jprobe handler routine */
-	regs->nip = arch_deref_entry_point(jp->entry);
-#ifdef PPC64_ELF_ABI_v2
-	regs->gpr[12] = (unsigned long)jp->entry;
-#elif defined(PPC64_ELF_ABI_v1)
-	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
-#endif
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void __used jprobe_return(void)
-{
-	asm volatile("jprobe_return_trap:\n"
-		     "trap\n"
-		     ::: "memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (regs->nip != ppc_kallsyms_lookup_name("jprobe_return_trap")) {
-		pr_debug("longjmp_break_handler NIP (0x%lx) does not match jprobe_return_trap (0x%lx)\n",
-				regs->nip, ppc_kallsyms_lookup_name("jprobe_return_trap"));
-		return 0;
-	}
-
-	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
-	/* It's OK to start function graph tracing again */
-	unpause_graph_tracing();
-	preempt_enable_no_resched();
-	return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 static struct kprobe trampoline_p = {
 	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 9a5b5a513604..32476a6e4e9c 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -104,39 +104,13 @@ ftrace_regs_call:
 	bl	ftrace_stub
 	nop
 
-	/* Load the possibly modified NIP */
-	ld	r15, _NIP(r1)
-
+	/* Load ctr with the possibly modified NIP */
+	ld	r3, _NIP(r1)
+	mtctr	r3
 #ifdef CONFIG_LIVEPATCH
-	cmpd	r14, r15	/* has NIP been altered? */
+	cmpd	r14, r3		/* has NIP been altered? */
 #endif
 
-#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
-	/* NIP has not been altered, skip over further checks */
-	beq	1f
-
-	/* Check if there is an active jprobe on us */
-	subi	r3, r14, 4
-	bl	__is_active_jprobe
-	nop
-
-	/*
-	 * If r3 == 1, then this is a kprobe/jprobe.
-	 * else, this is livepatched function.
-	 *
-	 * The conditional branch for livepatch_handler below will use the
-	 * result of this comparison. For kprobe/jprobe, we just need to branch to
-	 * the new NIP, not call livepatch_handler. The branch below is bne, so we
-	 * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
-	 * CR0[EQ] = (r3 == 1).
-	 */
-	cmpdi	r3, 1
-1:
-#endif
-
-	/* Load CTR with the possibly modified NIP */
-	mtctr	r15
-
 	/* Restore gprs */
 	REST_GPR(0,r1)
 	REST_10GPRS(2,r1)
@@ -154,10 +128,7 @@ ftrace_regs_call:
 	addi r1, r1, SWITCH_FRAME_SIZE
 
 #ifdef CONFIG_LIVEPATCH
-        /*
-	 * Based on the cmpd or cmpdi above, if the NIP was altered and we're
-	 * not on a kprobe/jprobe, then handle livepatch.
-	 */
+        /* Based on the cmpd above, if the NIP was altered handle livepatch */
 	bne-	livepatch_handler
 #endif
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de686b340f4a..ee4a8854985e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -216,7 +216,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
 	if (swq_has_sleeper(wqp)) {
-		swake_up(wqp);
+		swake_up_one(wqp);
 		++vcpu->stat.halt_wakeup;
 	}
 
@@ -3188,7 +3188,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 		}
 	}
 
-	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 
 	if (kvmppc_vcore_check_block(vc)) {
 		finish_swait(&vc->wq, &wait);
@@ -3311,7 +3311,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			swake_up(&vc->wq);
+			swake_up_one(&vc->wq);
 		}
 
 	}
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 3f66fcf8ad99..19d8ab49d1bd 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1469,7 +1469,7 @@ static int collect_events(struct perf_event *group, int max_count,
 }
 
 /*
- * Add a event to the PMU.
+ * Add an event to the PMU.
  * If all events are not already frozen, then we disable and
  * re-enable the PMU in order to get hw_perf_enable to do the
  * actual work of reconfiguring the PMU.
@@ -1548,7 +1548,7 @@ nocheck:
 }
 
 /*
- * Remove a event from the PMU.
+ * Remove an event from the PMU.
  */
 static void power_pmu_del(struct perf_event *event, int ef_flags)
 {
@@ -1742,7 +1742,7 @@ static int power_pmu_commit_txn(struct pmu *pmu)
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
- * A event can only go on a limited PMC if it counts something
+ * An event can only go on a limited PMC if it counts something
  * that a limited PMC can count, doesn't require interrupts, and
  * doesn't exclude any processor mode.
  */
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 855115ace98c..c452359c9cb8 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -25,18 +25,11 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define __atomic_op_acquire(op, args...)				\
-({									\
-	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory");	\
-	__ret;								\
-})
-
-#define __atomic_op_release(op, args...)				\
-({									\
-	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");	\
-	op##_relaxed(args);						\
-})
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");
 
 static __always_inline int atomic_read(const atomic_t *v)
 {
@@ -209,130 +202,8 @@ ATOMIC_OPS(xor, xor, i)
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
-/*
- * The extra atomic operations that are constructed from one of the core
- * AMO-based operations above (aside from sub, which is easier to fit above).
- * These are required to perform a full barrier, but they're OK this way
- * because atomic_*_return is also required to perform a full barrier.
- *
- */
-#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix)		\
-static __always_inline							\
-bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
-{									\
-	return atomic##prefix##_##func_op##_return(i, v) comp_op I;	\
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, func_op, comp_op, I)				\
-        ATOMIC_OP(op, func_op, comp_op, I,  int,   )
-#else
-#define ATOMIC_OPS(op, func_op, comp_op, I)				\
-        ATOMIC_OP(op, func_op, comp_op, I,  int,   )			\
-        ATOMIC_OP(op, func_op, comp_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(add_and_test, add, ==, 0)
-ATOMIC_OPS(sub_and_test, sub, ==, 0)
-ATOMIC_OPS(add_negative, add,  <, 0)
-
-#undef ATOMIC_OP
-#undef ATOMIC_OPS
-
-#define ATOMIC_OP(op, func_op, I, c_type, prefix)			\
-static __always_inline							\
-void atomic##prefix##_##op(atomic##prefix##_t *v)			\
-{									\
-	atomic##prefix##_##func_op(I, v);				\
-}
-
-#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix)			\
-static __always_inline							\
-c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v)	\
-{									\
-	return atomic##prefix##_fetch_##func_op##_relaxed(I, v);	\
-}									\
-static __always_inline							\
-c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)		\
-{									\
-	return atomic##prefix##_fetch_##func_op(I, v);			\
-}
-
-#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix)		\
-static __always_inline							\
-c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v)	\
-{									\
-        return atomic##prefix##_fetch_##op##_relaxed(v) c_op I;		\
-}									\
-static __always_inline							\
-c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v)		\
-{									\
-        return atomic##prefix##_fetch_##op(v) c_op I;			\
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
-        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )
-#else
-#define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
-        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )			\
-        ATOMIC_OP(       op, asm_op,       I, long, 64)			\
-        ATOMIC_FETCH_OP( op, asm_op,       I, long, 64)			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(inc, add, +,  1)
-ATOMIC_OPS(dec, add, +, -1)
-
-#define atomic_inc_return_relaxed	atomic_inc_return_relaxed
-#define atomic_dec_return_relaxed	atomic_dec_return_relaxed
-#define atomic_inc_return		atomic_inc_return
-#define atomic_dec_return		atomic_dec_return
-
-#define atomic_fetch_inc_relaxed	atomic_fetch_inc_relaxed
-#define atomic_fetch_dec_relaxed	atomic_fetch_dec_relaxed
-#define atomic_fetch_inc		atomic_fetch_inc
-#define atomic_fetch_dec		atomic_fetch_dec
-
-#ifndef CONFIG_GENERIC_ATOMIC64
-#define atomic64_inc_return_relaxed	atomic64_inc_return_relaxed
-#define atomic64_dec_return_relaxed	atomic64_dec_return_relaxed
-#define atomic64_inc_return		atomic64_inc_return
-#define atomic64_dec_return		atomic64_dec_return
-
-#define atomic64_fetch_inc_relaxed	atomic64_fetch_inc_relaxed
-#define atomic64_fetch_dec_relaxed	atomic64_fetch_dec_relaxed
-#define atomic64_fetch_inc		atomic64_fetch_inc
-#define atomic64_fetch_dec		atomic64_fetch_dec
-#endif
-
-#undef ATOMIC_OPS
-#undef ATOMIC_OP
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP_RETURN
-
-#define ATOMIC_OP(op, func_op, comp_op, I, prefix)			\
-static __always_inline							\
-bool atomic##prefix##_##op(atomic##prefix##_t *v)			\
-{									\
-	return atomic##prefix##_##func_op##_return(v) comp_op I;	\
-}
-
-ATOMIC_OP(inc_and_test, inc, ==, 0,   )
-ATOMIC_OP(dec_and_test, dec, ==, 0,   )
-#ifndef CONFIG_GENERIC_ATOMIC64
-ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
-ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
-#endif
-
-#undef ATOMIC_OP
-
 /* This is required to provide a full barrier on success. */
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
        int prev, rc;
 
@@ -349,9 +220,10 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 		: "memory");
 	return prev;
 }
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
+static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
        long prev, rc;
 
@@ -368,27 +240,7 @@ static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
 		: "memory");
 	return prev;
 }
-
-static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	return __atomic64_add_unless(v, a, u) != u;
-}
-#endif
-
-/*
- * The extra atomic operations that are constructed from one of the core
- * LR/SC-based operations above.
- */
-static __always_inline int atomic_inc_not_zero(atomic_t *v)
-{
-        return __atomic_add_unless(v, 1, 0);
-}
-
-#ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
-{
-        return atomic64_add_unless(v, 1, 0);
-}
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 #endif
 
 /*
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8a1863d9ed53..515240576930 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -106,7 +106,6 @@ config S390
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
-	select ARCH_WANTS_UBSAN_NO_NULL
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS2
@@ -146,6 +145,7 @@ config S390
 	select HAVE_KERNEL_LZ4
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
+	select HAVE_KERNEL_UNCOMPRESSED
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 68a690442be0..eee6703093c3 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -14,8 +14,18 @@ LD_BFD		:= elf64-s390
 LDFLAGS		:= -m elf64_s390
 KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
-KBUILD_CFLAGS	+= -m64
 KBUILD_AFLAGS	+= -m64
+KBUILD_CFLAGS	+= -m64
+aflags_dwarf	:= -Wa,-gdwarf-2
+KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__
+KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
+KBUILD_CFLAGS_DECOMPRESSOR := -m64 -O2
+KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
+KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float
+KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
+KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding)
+KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
+KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
 UTS_MACHINE	:= s390x
 STACK_SIZE	:= 16384
 CHECKFLAGS	+= -D__s390__ -D__s390x__
@@ -52,18 +62,14 @@ cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include
 #
 cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls
 
-# old style option for packed stacks
-ifeq ($(call cc-option-yn,-mkernel-backchain),y)
-cflags-$(CONFIG_PACK_STACK)  += -mkernel-backchain -D__PACK_STACK
-aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
-endif
-
-# new style option for packed stacks
 ifeq ($(call cc-option-yn,-mpacked-stack),y)
 cflags-$(CONFIG_PACK_STACK)  += -mpacked-stack -D__PACK_STACK
 aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
 endif
 
+KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y)
+KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y)
+
 ifeq ($(call cc-option-yn,-mstack-size=8192 -mstack-guard=128),y)
 cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE)
 ifneq ($(call cc-option-yn,-mstack-size=8192),y)
@@ -71,8 +77,11 @@ cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD)
 endif
 endif
 
-ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y)
-cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack
+ifdef CONFIG_WARN_DYNAMIC_STACK
+  ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y)
+    KBUILD_CFLAGS += -mwarn-dynamicstack
+    KBUILD_CFLAGS_DECOMPRESSOR += -mwarn-dynamicstack
+  endif
 endif
 
 ifdef CONFIG_EXPOLINE
@@ -82,6 +91,7 @@ ifdef CONFIG_EXPOLINE
     CC_FLAGS_EXPOLINE += -mindirect-branch-table
     export CC_FLAGS_EXPOLINE
     cflags-y += $(CC_FLAGS_EXPOLINE) -DCC_USING_EXPOLINE
+    aflags-y += -DCC_USING_EXPOLINE
   endif
 endif
 
@@ -102,11 +112,12 @@ KBUILD_CFLAGS	+= -mbackchain -msoft-float $(cflags-y)
 KBUILD_CFLAGS	+= -pipe -fno-strength-reduce -Wno-sign-compare
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables $(cfi)
 KBUILD_AFLAGS	+= $(aflags-y) $(cfi)
+export KBUILD_AFLAGS_DECOMPRESSOR
+export KBUILD_CFLAGS_DECOMPRESSOR
 
 OBJCOPYFLAGS	:= -O binary
 
-head-y		:= arch/s390/kernel/head.o
-head-y		+= arch/s390/kernel/head64.o
+head-y		:= arch/s390/kernel/head64.o
 
 # See arch/s390/Kbuild for content of core part of the kernel
 core-y		+= arch/s390/
@@ -121,7 +132,7 @@ boot		:= arch/s390/boot
 syscalls	:= arch/s390/kernel/syscalls
 tools		:= arch/s390/tools
 
-all: image bzImage
+all: bzImage
 
 #KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg...
 KBUILD_IMAGE	:= $(boot)/bzImage
@@ -129,7 +140,7 @@ KBUILD_IMAGE	:= $(boot)/bzImage
 install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
-image bzImage: vmlinux
+bzImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zfcpdump:
@@ -152,8 +163,7 @@ archprepare:
 
 # Don't use tabs in echo arguments
 define archhelp
-  echo  '* image           - Kernel image for IPL ($(boot)/image)'
-  echo	'* bzImage         - Compressed kernel image for IPL ($(boot)/bzImage)'
+  echo	'* bzImage         - Kernel image for IPL ($(boot)/bzImage)'
   echo	'  install         - Install kernel using'
   echo	'                    (your) ~/bin/$(INSTALLKERNEL) or'
   echo	'                    (distribution) /sbin/$(INSTALLKERNEL) or'
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index ee6a9c387c87..9bf8489df6e6 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -206,35 +206,28 @@ static int
 appldata_timer_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	unsigned int len;
-	char buf[2];
+	int timer_active = appldata_timer_active;
+	int zero = 0;
+	int one = 1;
+	int rc;
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &timer_active,
+		.maxlen		= sizeof(int),
+		.extra1		= &zero,
+		.extra2		= &one,
+	};
+
+	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
-		return 0;
-	}
-	if (!write) {
-		strncpy(buf, appldata_timer_active ? "1\n" : "0\n",
-			ARRAY_SIZE(buf));
-		len = strnlen(buf, ARRAY_SIZE(buf));
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
-		return -EFAULT;
 	spin_lock(&appldata_timer_lock);
-	if (buf[0] == '1')
+	if (timer_active)
 		__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
-	else if (buf[0] == '0')
+	else
 		__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
 	spin_unlock(&appldata_timer_lock);
-out:
-	*lenp = len;
-	*ppos += len;
 	return 0;
 }
 
@@ -248,37 +241,24 @@ static int
 appldata_interval_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	unsigned int len;
-	int interval;
-	char buf[16];
+	int interval = appldata_interval;
+	int one = 1;
+	int rc;
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &interval,
+		.maxlen		= sizeof(int),
+		.extra1		= &one,
+	};
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
-		return 0;
-	}
-	if (!write) {
-		len = sprintf(buf, "%i\n", appldata_interval);
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
-		return -EFAULT;
-	interval = 0;
-	sscanf(buf, "%i", &interval);
-	if (interval <= 0)
-		return -EINVAL;
+	rc = proc_dointvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
 	spin_lock(&appldata_timer_lock);
 	appldata_interval = interval;
 	__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
 	spin_unlock(&appldata_timer_lock);
-out:
-	*lenp = len;
-	*ppos += len;
 	return 0;
 }
 
@@ -293,10 +273,17 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct appldata_ops *ops = NULL, *tmp_ops;
-	unsigned int len;
-	int rc, found;
-	char buf[2];
 	struct list_head *lh;
+	int rc, found;
+	int active;
+	int zero = 0;
+	int one = 1;
+	struct ctl_table ctl_entry = {
+		.data		= &active,
+		.maxlen		= sizeof(int),
+		.extra1		= &zero,
+		.extra2		= &one,
+	};
 
 	found = 0;
 	mutex_lock(&appldata_ops_mutex);
@@ -317,31 +304,15 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 	}
 	mutex_unlock(&appldata_ops_mutex);
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
+	active = ops->active;
+	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write) {
 		module_put(ops->owner);
-		return 0;
-	}
-	if (!write) {
-		strncpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf));
-		len = strnlen(buf, ARRAY_SIZE(buf));
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len)) {
-			module_put(ops->owner);
-			return -EFAULT;
-		}
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer,
-			   len > sizeof(buf) ? sizeof(buf) : len)) {
-		module_put(ops->owner);
-		return -EFAULT;
+		return rc;
 	}
 
 	mutex_lock(&appldata_ops_mutex);
-	if ((buf[0] == '1') && (ops->active == 0)) {
+	if (active && (ops->active == 0)) {
 		// protect work queue callback
 		if (!try_module_get(ops->owner)) {
 			mutex_unlock(&appldata_ops_mutex);
@@ -359,7 +330,7 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 			module_put(ops->owner);
 		} else
 			ops->active = 1;
-	} else if ((buf[0] == '0') && (ops->active == 1)) {
+	} else if (!active && (ops->active == 1)) {
 		ops->active = 0;
 		rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
 				(unsigned long) ops->data, ops->size,
@@ -370,9 +341,6 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 		module_put(ops->owner);
 	}
 	mutex_unlock(&appldata_ops_mutex);
-out:
-	*lenp = len;
-	*ppos += len;
 	module_put(ops->owner);
 	return 0;
 }
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index d1fa37fcce83..9e6668ee93de 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -3,19 +3,52 @@
 # Makefile for the linux s390-specific parts of the memory manager.
 #
 
-targets := image
-targets += bzImage
-subdir- := compressed
+KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
 
-$(obj)/image: vmlinux FORCE
-	$(call if_changed,objcopy)
+KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
+KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
+
+#
+# Use -march=z900 for als.c to be able to print an error
+# message if the kernel is started on a machine which is too old
+#
+ifneq ($(CC_FLAGS_MARCH),-march=z900)
+AFLAGS_REMOVE_head.o		+= $(CC_FLAGS_MARCH)
+AFLAGS_head.o			+= -march=z900
+AFLAGS_REMOVE_mem.o		+= $(CC_FLAGS_MARCH)
+AFLAGS_mem.o			+= -march=z900
+CFLAGS_REMOVE_als.o		+= $(CC_FLAGS_MARCH)
+CFLAGS_als.o			+= -march=z900
+CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
+CFLAGS_sclp_early_core.o	+= -march=z900
+endif
+
+CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
+
+obj-y	:= head.o als.o ebcdic.o sclp_early_core.o mem.o
+targets	:= bzImage startup.a $(obj-y)
+subdir-	:= compressed
+
+OBJECTS := $(addprefix $(obj)/,$(obj-y))
 
 $(obj)/bzImage: $(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
 
-$(obj)/compressed/vmlinux: FORCE
+$(obj)/compressed/vmlinux: $(obj)/startup.a FORCE
 	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
 
+quiet_cmd_ar = AR      $@
+      cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(filter $(OBJECTS), $^)
+
+$(obj)/startup.a: $(OBJECTS) FORCE
+	$(call if_changed,ar)
+
 install: $(CONFIGURE) $(obj)/bzImage
 	sh -x  $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
 	      System.map "$(INSTALL_PATH)"
+
+chkbss := $(OBJECTS)
+chkbss-target := $(obj)/startup.a
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/als.c b/arch/s390/boot/als.c
index d1892bf36cab..d592e0d90d9f 100644
--- a/arch/s390/kernel/als.c
+++ b/arch/s390/boot/als.c
@@ -3,12 +3,10 @@
  *    Copyright IBM Corp. 2016
  */
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <asm/processor.h>
 #include <asm/facility.h>
 #include <asm/lowcore.h>
 #include <asm/sclp.h>
-#include "entry.h"
 
 /*
  * The code within this file will be called very early. It may _not_
@@ -18,9 +16,9 @@
  * For temporary objects the stack (16k) should be used.
  */
 
-static unsigned long als[] __initdata = { FACILITIES_ALS };
+static unsigned long als[] = { FACILITIES_ALS };
 
-static void __init u16_to_hex(char *str, u16 val)
+static void u16_to_hex(char *str, u16 val)
 {
 	int i, num;
 
@@ -33,9 +31,9 @@ static void __init u16_to_hex(char *str, u16 val)
 	*str = '\0';
 }
 
-static void __init print_machine_type(void)
+static void print_machine_type(void)
 {
-	static char mach_str[80] __initdata = "Detected machine-type number: ";
+	static char mach_str[80] = "Detected machine-type number: ";
 	char type_str[5];
 	struct cpuid id;
 
@@ -46,7 +44,7 @@ static void __init print_machine_type(void)
 	sclp_early_printk(mach_str);
 }
 
-static void __init u16_to_decimal(char *str, u16 val)
+static void u16_to_decimal(char *str, u16 val)
 {
 	int div = 1;
 
@@ -60,9 +58,9 @@ static void __init u16_to_decimal(char *str, u16 val)
 	*str = '\0';
 }
 
-static void __init print_missing_facilities(void)
+static void print_missing_facilities(void)
 {
-	static char als_str[80] __initdata = "Missing facilities: ";
+	static char als_str[80] = "Missing facilities: ";
 	unsigned long val;
 	char val_str[6];
 	int i, j, first;
@@ -95,7 +93,7 @@ static void __init print_missing_facilities(void)
 	sclp_early_printk("See Principles of Operations for facility bits\n");
 }
 
-static void __init facility_mismatch(void)
+static void facility_mismatch(void)
 {
 	sclp_early_printk("The Linux kernel requires more recent processor hardware\n");
 	print_machine_type();
@@ -103,7 +101,7 @@ static void __init facility_mismatch(void)
 	disabled_wait(0x8badcccc);
 }
 
-void __init verify_facilities(void)
+void verify_facilities(void)
 {
 	int i;
 
diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore
index 2088cc140629..45aeb4f08752 100644
--- a/arch/s390/boot/compressed/.gitignore
+++ b/arch/s390/boot/compressed/.gitignore
@@ -1,4 +1,5 @@
 sizes.h
 vmlinux
 vmlinux.lds
+vmlinux.scr.lds
 vmlinux.bin.full
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 5766f7b9b271..04609478d18b 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -6,39 +6,29 @@
 #
 
 KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
 
+obj-y	:= $(if $(CONFIG_KERNEL_UNCOMPRESSED),,head.o misc.o) piggy.o
 targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
-targets += misc.o piggy.o sizes.h head.o
-
-KBUILD_CFLAGS := -m64 -D__KERNEL__ -O2
-KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
-KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float
-KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
-KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
-KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
+targets += vmlinux.scr.lds $(obj-y) $(if $(CONFIG_KERNEL_UNCOMPRESSED),,sizes.h)
 
-GCOV_PROFILE := n
-UBSAN_SANITIZE := n
+KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
+KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 
-OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o ebcdic.o als.o)
-OBJECTS += $(objtree)/drivers/s390/char/sclp_early_core.o
-OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
+OBJECTS := $(addprefix $(obj)/,$(obj-y))
 
 LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS)
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS)
 	$(call if_changed,ld)
 
-TRIM_HEAD_SIZE := 0x11000
-
-sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - $(TRIM_HEAD_SIZE))/p'
+# extract required uncompressed vmlinux symbols and adjust them to reflect offsets inside vmlinux.bin
+sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - 0x100000)/p'
 
 quiet_cmd_sizes = GEN     $@
       cmd_sizes = $(NM) $< | sed -n $(sed-sizes) > $@
 
-quiet_cmd_trim_head = TRIM    $@
-      cmd_trim_head = tail -c +$$(($(TRIM_HEAD_SIZE) + 1)) $< > $@
-
 $(obj)/sizes.h: vmlinux
 	$(call if_changed,sizes)
 
@@ -48,21 +38,18 @@ $(obj)/head.o: $(obj)/sizes.h
 CFLAGS_misc.o += -I$(objtree)/$(obj)
 $(obj)/misc.o: $(obj)/sizes.h
 
-OBJCOPYFLAGS_vmlinux.bin.full :=  -R .comment -S
-$(obj)/vmlinux.bin.full: vmlinux
+OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
+$(obj)/vmlinux.bin: vmlinux
 	$(call if_changed,objcopy)
 
-$(obj)/vmlinux.bin: $(obj)/vmlinux.bin.full
-	$(call if_changed,trim_head)
-
 vmlinux.bin.all-y := $(obj)/vmlinux.bin
 
-suffix-$(CONFIG_KERNEL_GZIP)  := gz
-suffix-$(CONFIG_KERNEL_BZIP2) := bz2
-suffix-$(CONFIG_KERNEL_LZ4)  := lz4
-suffix-$(CONFIG_KERNEL_LZMA)  := lzma
-suffix-$(CONFIG_KERNEL_LZO)  := lzo
-suffix-$(CONFIG_KERNEL_XZ)  := xz
+suffix-$(CONFIG_KERNEL_GZIP)  := .gz
+suffix-$(CONFIG_KERNEL_BZIP2) := .bz2
+suffix-$(CONFIG_KERNEL_LZ4)  := .lz4
+suffix-$(CONFIG_KERNEL_LZMA)  := .lzma
+suffix-$(CONFIG_KERNEL_LZO)  := .lzo
+suffix-$(CONFIG_KERNEL_XZ)  := .xz
 
 $(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
 	$(call if_changed,gzip)
@@ -78,5 +65,9 @@ $(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y)
 	$(call if_changed,xzkern)
 
 LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y)
+$(obj)/piggy.o: $(obj)/vmlinux.scr.lds $(obj)/vmlinux.bin$(suffix-y)
 	$(call if_changed,ld)
+
+chkbss := $(filter-out $(obj)/misc.o $(obj)/piggy.o,$(OBJECTS))
+chkbss-target := $(obj)/vmlinux.bin
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S
index 9f94eca0f467..df8dbbc17bcc 100644
--- a/arch/s390/boot/compressed/head.S
+++ b/arch/s390/boot/compressed/head.S
@@ -15,7 +15,7 @@
 #include "sizes.h"
 
 __HEAD
-ENTRY(startup_continue)
+ENTRY(startup_decompressor)
 	basr	%r13,0			# get base
 .LPG1:
 	# setup stack
@@ -23,7 +23,7 @@ ENTRY(startup_continue)
 	aghi	%r15,-160
 	brasl	%r14,decompress_kernel
 	# Set up registers for memory mover. We move the decompressed image to
-	# 0x11000, where startup_continue of the decompressed image is supposed
+	# 0x100000, where startup_continue of the decompressed image is supposed
 	# to be.
 	lgr	%r4,%r2
 	lg	%r2,.Loffset-.LPG1(%r13)
@@ -33,7 +33,7 @@ ENTRY(startup_continue)
 	la	%r1,0x200
 	mvc	0(mover_end-mover,%r1),mover-.LPG1(%r13)
 	# When the memory mover is done we pass control to
-	# arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in
+	# arch/s390/kernel/head64.S:startup_continue which lives at 0x100000 in
 	# the decompressed image.
 	lgr	%r6,%r2
 	br	%r1
@@ -47,6 +47,6 @@ mover_end:
 .Lstack:
 	.quad	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
 .Loffset:
-	.quad	0x11000
+	.quad	0x100000
 .Lmvsize:
 	.quad	SZ__bss_start
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index 511b2cc9b91a..f66ad73c205b 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -71,43 +71,6 @@ static int puts(const char *s)
 	return 0;
 }
 
-void *memset(void *s, int c, size_t n)
-{
-	char *xs;
-
-	xs = s;
-	while (n--)
-		*xs++ = c;
-	return s;
-}
-
-void *memcpy(void *dest, const void *src, size_t n)
-{
-	const char *s = src;
-	char *d = dest;
-
-	while (n--)
-		*d++ = *s++;
-	return dest;
-}
-
-void *memmove(void *dest, const void *src, size_t n)
-{
-	const char *s = src;
-	char *d = dest;
-
-	if (d <= s) {
-		while (n--)
-			*d++ = *s++;
-	} else {
-		d += n;
-		s += n;
-		while (n--)
-			*--d = *--s;
-	}
-	return dest;
-}
-
 static void error(char *x)
 {
 	unsigned long long psw = 0x000a0000deadbeefULL;
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index d43c2db12d30..b16ac8b3c439 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -23,13 +23,10 @@ SECTIONS
 		*(.text.*)
 		_etext = . ;
 	}
-	.rodata.compressed : {
-		*(.rodata.compressed)
-	}
 	.rodata : {
 		_rodata = . ;
 		*(.rodata)	 /* read-only data */
-		*(.rodata.*)
+		*(EXCLUDE_FILE (*piggy.o) .rodata.compressed)
 		_erodata = . ;
 	}
 	.data :	{
@@ -38,6 +35,15 @@ SECTIONS
 		*(.data.*)
 		_edata = . ;
 	}
+	startup_continue = 0x100000;
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
+	. = 0x100000;
+#else
+	. = ALIGN(8);
+#endif
+	.rodata.compressed : {
+		*(.rodata.compressed)
+	}
 	. = ALIGN(256);
 	.bss : {
 		_bss = . ;
@@ -54,5 +60,6 @@ SECTIONS
 		*(.eh_frame)
 		*(__ex_table)
 		*(*__ksymtab*)
+		*(___kcrctab*)
 	}
 }
diff --git a/arch/s390/boot/compressed/vmlinux.scr b/arch/s390/boot/compressed/vmlinux.scr.lds.S
index 42a242597f34..ff01d18c9222 100644
--- a/arch/s390/boot/compressed/vmlinux.scr
+++ b/arch/s390/boot/compressed/vmlinux.scr.lds.S
@@ -2,10 +2,14 @@
 SECTIONS
 {
   .rodata.compressed : {
+#ifndef CONFIG_KERNEL_UNCOMPRESSED
 	input_len = .;
 	LONG(input_data_end - input_data) input_data = .;
+#endif
 	*(.data)
+#ifndef CONFIG_KERNEL_UNCOMPRESSED
 	output_len = . - 4;
 	input_data_end = .;
+#endif
 	}
 }
diff --git a/arch/s390/boot/ebcdic.c b/arch/s390/boot/ebcdic.c
new file mode 100644
index 000000000000..7391e7d36086
--- /dev/null
+++ b/arch/s390/boot/ebcdic.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../kernel/ebcdic.c"
diff --git a/arch/s390/kernel/head.S b/arch/s390/boot/head.S
index 5c42f16a54c4..f721913b73f1 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/boot/head.S
@@ -272,14 +272,14 @@ iplstart:
 	.org	0x10000
 ENTRY(startup)
 	j	.Lep_startup_normal
-	.org	0x10008
+	.org	EP_OFFSET
 #
 # This is a list of s390 kernel entry points. At address 0x1000f the number of
 # valid entry points is stored.
 #
 # IMPORTANT: Do not change this table, it is s390 kernel ABI!
 #
-	.ascii	"S390EP"
+	.ascii	EP_STRING
 	.byte	0x00,0x01
 #
 # kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
@@ -310,10 +310,11 @@ ENTRY(startup_kdump)
 	l	%r15,.Lstack-.LPG0(%r13)
 	ahi	%r15,-STACK_FRAME_OVERHEAD
 	brasl	%r14,verify_facilities
-# For uncompressed images, continue in
-# arch/s390/kernel/head64.S. For compressed images, continue in
-# arch/s390/boot/compressed/head.S.
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
 	jg	startup_continue
+#else
+	jg	startup_decompressor
+#endif
 
 .Lstack:
 	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/boot/head_kdump.S
index 174d6959bf5b..174d6959bf5b 100644
--- a/arch/s390/kernel/head_kdump.S
+++ b/arch/s390/boot/head_kdump.S
diff --git a/arch/s390/boot/mem.S b/arch/s390/boot/mem.S
new file mode 100644
index 000000000000..b33463633f03
--- /dev/null
+++ b/arch/s390/boot/mem.S
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "../lib/mem.S"
diff --git a/arch/s390/boot/sclp_early_core.c b/arch/s390/boot/sclp_early_core.c
new file mode 100644
index 000000000000..5a19fd7020b5
--- /dev/null
+++ b/arch/s390/boot/sclp_early_core.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../drivers/s390/char/sclp_early_core.c"
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index a2945b289a29..3452e18bb1ca 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -497,7 +497,7 @@ static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 	}
 	diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer);
 	rc = hypfs_create_str(cpu_dir, "type", buffer);
-	return PTR_RET(rc);
+	return PTR_ERR_OR_ZERO(rc);
 }
 
 static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr)
@@ -544,7 +544,7 @@ static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 		return PTR_ERR(rc);
 	diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer);
 	rc = hypfs_create_str(cpu_dir, "type", buffer);
-	return PTR_RET(rc);
+	return PTR_ERR_OR_ZERO(rc);
 }
 
 static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr)
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 06b513d192b9..c681329fdeec 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -36,7 +36,7 @@ struct hypfs_sb_info {
 	kuid_t uid;			/* uid used for files and dirs */
 	kgid_t gid;			/* gid used for files and dirs */
 	struct dentry *update_file;	/* file to trigger update */
-	time_t last_update;		/* last update time in secs since 1970 */
+	time64_t last_update;		/* last update, CLOCK_MONOTONIC time */
 	struct mutex lock;		/* lock to protect update process */
 };
 
@@ -52,7 +52,7 @@ static void hypfs_update_update(struct super_block *sb)
 	struct hypfs_sb_info *sb_info = sb->s_fs_info;
 	struct inode *inode = d_inode(sb_info->update_file);
 
-	sb_info->last_update = get_seconds();
+	sb_info->last_update = ktime_get_seconds();
 	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 }
 
@@ -179,7 +179,7 @@ static ssize_t hypfs_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	 *    to restart data collection in this case.
 	 */
 	mutex_lock(&fs_info->lock);
-	if (fs_info->last_update == get_seconds()) {
+	if (fs_info->last_update == ktime_get_seconds()) {
 		rc = -EBUSY;
 		goto out;
 	}
diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index c1bedb4c8de0..046e044a48d0 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -47,6 +47,50 @@ struct ap_queue_status {
 };
 
 /**
+ * ap_intructions_available() - Test if AP instructions are available.
+ *
+ * Returns 0 if the AP instructions are installed.
+ */
+static inline int ap_instructions_available(void)
+{
+	register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
+	register unsigned long reg1 asm ("1") = -ENODEV;
+	register unsigned long reg2 asm ("2");
+
+	asm volatile(
+		"   .long 0xb2af0000\n"		/* PQAP(TAPQ) */
+		"0: la    %0,0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: "+d" (reg1), "=d" (reg2)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
+/**
+ * ap_tapq(): Test adjunct processor queue.
+ * @qid: The AP queue number
+ * @info: Pointer to queue descriptor
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
+{
+	register unsigned long reg0 asm ("0") = qid;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm ("2");
+
+	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
+		     : "=d" (reg1), "=d" (reg2)
+		     : "d" (reg0)
+		     : "cc");
+	if (info)
+		*info = reg2;
+	return reg1;
+}
+
+/**
  * ap_test_queue(): Test adjunct processor queue.
  * @qid: The AP queue number
  * @tbit: Test facilities bit
@@ -54,10 +98,57 @@ struct ap_queue_status {
  *
  * Returns AP queue status structure.
  */
-struct ap_queue_status ap_test_queue(ap_qid_t qid,
-				     int tbit,
-				     unsigned long *info);
+static inline struct ap_queue_status ap_test_queue(ap_qid_t qid,
+						   int tbit,
+						   unsigned long *info)
+{
+	if (tbit)
+		qid |= 1UL << 23; /* set T bit*/
+	return ap_tapq(qid, info);
+}
 
+/**
+ * ap_pqap_rapq(): Reset adjunct processor queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
+{
+	register unsigned long reg0 asm ("0") = qid | (1UL << 24);
+	register struct ap_queue_status reg1 asm ("1");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(RAPQ) */
+		: "=d" (reg1)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
+/**
+ * ap_pqap_zapq(): Reset and zeroize adjunct processor queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_zapq(ap_qid_t qid)
+{
+	register unsigned long reg0 asm ("0") = qid | (2UL << 24);
+	register struct ap_queue_status reg1 asm ("1");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(ZAPQ) */
+		: "=d" (reg1)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
+/**
+ * struct ap_config_info - convenience struct for AP crypto
+ * config info as returned by the ap_qci() function.
+ */
 struct ap_config_info {
 	unsigned int apsc	 : 1;	/* S bit */
 	unsigned int apxa	 : 1;	/* N bit */
@@ -74,50 +165,189 @@ struct ap_config_info {
 	unsigned char _reserved4[16];
 } __aligned(8);
 
-/*
- * ap_query_configuration(): Fetch cryptographic config info
+/**
+ * ap_qci(): Get AP configuration data
  *
- * Returns the ap configuration info fetched via PQAP(QCI).
- * On success 0 is returned, on failure a negative errno
- * is returned, e.g. if the PQAP(QCI) instruction is not
- * available, the return value will be -EOPNOTSUPP.
+ * Returns 0 on success, or -EOPNOTSUPP.
  */
-int ap_query_configuration(struct ap_config_info *info);
+static inline int ap_qci(struct ap_config_info *config)
+{
+	register unsigned long reg0 asm ("0") = 4UL << 24;
+	register unsigned long reg1 asm ("1") = -EOPNOTSUPP;
+	register struct ap_config_info *reg2 asm ("2") = config;
+
+	asm volatile(
+		".long 0xb2af0000\n"		/* PQAP(QCI) */
+		"0: la    %0,0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: "+d" (reg1)
+		: "d" (reg0), "d" (reg2)
+		: "cc", "memory");
+
+	return reg1;
+}
 
 /*
  * struct ap_qirq_ctrl - convenient struct for easy invocation
- * of the ap_queue_irq_ctrl() function. This struct is passed
- * as GR1 parameter to the PQAP(AQIC) instruction. For details
- * please see the AR documentation.
+ * of the ap_aqic() function. This struct is passed as GR1
+ * parameter to the PQAP(AQIC) instruction. For details please
+ * see the AR documentation.
  */
 struct ap_qirq_ctrl {
 	unsigned int _res1 : 8;
-	unsigned int zone  : 8;  /* zone info */
-	unsigned int ir    : 1;  /* ir flag: enable (1) or disable (0) irq */
+	unsigned int zone  : 8;	/* zone info */
+	unsigned int ir    : 1;	/* ir flag: enable (1) or disable (0) irq */
 	unsigned int _res2 : 4;
-	unsigned int gisc  : 3;  /* guest isc field */
+	unsigned int gisc  : 3;	/* guest isc field */
 	unsigned int _res3 : 6;
-	unsigned int gf    : 2;  /* gisa format */
+	unsigned int gf    : 2;	/* gisa format */
 	unsigned int _res4 : 1;
-	unsigned int gisa  : 27; /* gisa origin */
+	unsigned int gisa  : 27;	/* gisa origin */
 	unsigned int _res5 : 1;
-	unsigned int isc   : 3;  /* irq sub class */
+	unsigned int isc   : 3;	/* irq sub class */
 };
 
 /**
- * ap_queue_irq_ctrl(): Control interruption on a AP queue.
+ * ap_aqic(): Control interruption for a specific AP.
  * @qid: The AP queue number
- * @qirqctrl: struct ap_qirq_ctrl, see above
+ * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
  * @ind: The notification indicator byte
  *
  * Returns AP queue status.
+ */
+static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
+					     struct ap_qirq_ctrl qirqctrl,
+					     void *ind)
+{
+	register unsigned long reg0 asm ("0") = qid | (3UL << 24);
+	register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
+	register struct ap_queue_status reg1_out asm ("1");
+	register void *reg2 asm ("2") = ind;
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(AQIC) */
+		: "=d" (reg1_out)
+		: "d" (reg0), "d" (reg1_in), "d" (reg2)
+		: "cc");
+	return reg1_out;
+}
+
+/*
+ * union ap_qact_ap_info - used together with the
+ * ap_aqic() function to provide a convenient way
+ * to handle the ap info needed by the qact function.
+ */
+union ap_qact_ap_info {
+	unsigned long val;
+	struct {
+		unsigned int	  : 3;
+		unsigned int mode : 3;
+		unsigned int	  : 26;
+		unsigned int cat  : 8;
+		unsigned int	  : 8;
+		unsigned char ver[2];
+	};
+};
+
+/**
+ * ap_qact(): Query AP combatibility type.
+ * @qid: The AP queue number
+ * @apinfo: On input the info about the AP queue. On output the
+ *	    alternate AP queue info provided by the qact function
+ *	    in GR2 is stored in.
  *
- * Control interruption on the given AP queue.
- * Just a simple wrapper function for the low level PQAP(AQIC)
- * instruction available for other kernel modules.
+ * Returns AP queue status. Check response_code field for failures.
  */
-struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid,
-					 struct ap_qirq_ctrl qirqctrl,
-					 void *ind);
+static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
+					     union ap_qact_ap_info *apinfo)
+{
+	register unsigned long reg0 asm ("0") = qid | (5UL << 24)
+		| ((ifbit & 0x01) << 22);
+	register unsigned long reg1_in asm ("1") = apinfo->val;
+	register struct ap_queue_status reg1_out asm ("1");
+	register unsigned long reg2 asm ("2");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(QACT) */
+		: "+d" (reg1_in), "=d" (reg1_out), "=d" (reg2)
+		: "d" (reg0)
+		: "cc");
+	apinfo->val = reg2;
+	return reg1_out;
+}
+
+/**
+ * ap_nqap(): Send message to adjunct processor queue.
+ * @qid: The AP queue number
+ * @psmid: The program supplied message identifier
+ * @msg: The message text
+ * @length: The message length
+ *
+ * Returns AP queue status structure.
+ * Condition code 1 on NQAP can't happen because the L bit is 1.
+ * Condition code 2 on NQAP also means the send is incomplete,
+ * because a segment boundary was reached. The NQAP is repeated.
+ */
+static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
+					     unsigned long long psmid,
+					     void *msg, size_t length)
+{
+	register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm ("2") = (unsigned long) msg;
+	register unsigned long reg3 asm ("3") = (unsigned long) length;
+	register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
+	register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
+
+	asm volatile (
+		"0: .long 0xb2ad0042\n"		/* NQAP */
+		"   brc   2,0b"
+		: "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
+		: "d" (reg4), "d" (reg5)
+		: "cc", "memory");
+	return reg1;
+}
+
+/**
+ * ap_dqap(): Receive message from adjunct processor queue.
+ * @qid: The AP queue number
+ * @psmid: Pointer to program supplied message identifier
+ * @msg: The message text
+ * @length: The message length
+ *
+ * Returns AP queue status structure.
+ * Condition code 1 on DQAP means the receive has taken place
+ * but only partially.	The response is incomplete, hence the
+ * DQAP is repeated.
+ * Condition code 2 on DQAP also means the receive is incomplete,
+ * this time because a segment boundary was reached. Again, the
+ * DQAP is repeated.
+ * Note that gpr2 is used by the DQAP instruction to keep track of
+ * any 'residual' length, in case the instruction gets interrupted.
+ * Hence it gets zeroed before the instruction.
+ */
+static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
+					     unsigned long long *psmid,
+					     void *msg, size_t length)
+{
+	register unsigned long reg0 asm("0") = qid | 0x80000000UL;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm("2") = 0UL;
+	register unsigned long reg4 asm("4") = (unsigned long) msg;
+	register unsigned long reg5 asm("5") = (unsigned long) length;
+	register unsigned long reg6 asm("6") = 0UL;
+	register unsigned long reg7 asm("7") = 0UL;
+
+
+	asm volatile(
+		"0: .long 0xb2ae0064\n"		/* DQAP */
+		"   brc   6,0b\n"
+		: "+d" (reg0), "=d" (reg1), "+d" (reg2),
+		  "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7)
+		: : "cc", "memory");
+	*psmid = (((unsigned long long) reg6) << 32) + reg7;
+	return reg1;
+}
 
 #endif /* _ASM_S390_AP_H_ */
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 4b55532f15c4..fd20ab5d4cf7 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -55,17 +55,9 @@ static inline void atomic_add(int i, atomic_t *v)
 	__atomic_add(i, &v->counter);
 }
 
-#define atomic_add_negative(_i, _v)	(atomic_add_return(_i, _v) < 0)
-#define atomic_inc(_v)			atomic_add(1, _v)
-#define atomic_inc_return(_v)		atomic_add_return(1, _v)
-#define atomic_inc_and_test(_v)		(atomic_add_return(1, _v) == 0)
 #define atomic_sub(_i, _v)		atomic_add(-(int)(_i), _v)
 #define atomic_sub_return(_i, _v)	atomic_add_return(-(int)(_i), _v)
 #define atomic_fetch_sub(_i, _v)	atomic_fetch_add(-(int)(_i), _v)
-#define atomic_sub_and_test(_i, _v)	(atomic_sub_return(_i, _v) == 0)
-#define atomic_dec(_v)			atomic_sub(1, _v)
-#define atomic_dec_return(_v)		atomic_sub_return(1, _v)
-#define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
 #define ATOMIC_OPS(op)							\
 static inline void atomic_##op(int i, atomic_t *v)			\
@@ -90,21 +82,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return __atomic_cmpxchg(&v->counter, old, new);
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == u))
-			break;
-		old = atomic_cmpxchg(v, c, c + a);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define ATOMIC64_INIT(i)  { (i) }
 
 static inline long atomic64_read(const atomic64_t *v)
@@ -168,50 +145,8 @@ ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
 
-static inline int atomic64_add_unless(atomic64_t *v, long i, long u)
-{
-	long c, old;
-
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == u))
-			break;
-		old = atomic64_cmpxchg(v, c, c + i);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != u;
-}
-
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
-#define atomic64_add_negative(_i, _v)	(atomic64_add_return(_i, _v) < 0)
-#define atomic64_inc(_v)		atomic64_add(1, _v)
-#define atomic64_inc_return(_v)		atomic64_add_return(1, _v)
-#define atomic64_inc_and_test(_v)	(atomic64_add_return(1, _v) == 0)
 #define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long)(_i), _v)
 #define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long)(_i), _v)
 #define atomic64_sub(_i, _v)		atomic64_add(-(long)(_i), _v)
-#define atomic64_sub_and_test(_i, _v)	(atomic64_sub_return(_i, _v) == 0)
-#define atomic64_dec(_v)		atomic64_sub(1, _v)
-#define atomic64_dec_return(_v)		atomic64_sub_return(1, _v)
-#define atomic64_dec_and_test(_v)	(atomic64_sub_return(1, _v) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
 #endif /* __ARCH_S390_ATOMIC__  */
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index de023a9a88ca..bf2cbff926ef 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -2,7 +2,7 @@
 /*
  * CPU-measurement facilities
  *
- *  Copyright IBM Corp. 2012
+ *  Copyright IBM Corp. 2012, 2018
  *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *	       Jan Glauber <jang@linux.vnet.ibm.com>
  */
@@ -139,8 +139,14 @@ struct hws_trailer_entry {
 	unsigned char timestamp[16];	 /* 16 - 31 timestamp		      */
 	unsigned long long reserved1;	 /* 32 -Reserved		      */
 	unsigned long long reserved2;	 /*				      */
-	unsigned long long progusage1;	 /* 48 - reserved for programming use */
-	unsigned long long progusage2;	 /*				      */
+	union {				 /* 48 - reserved for programming use */
+		struct {
+			unsigned int clock_base:1; /* in progusage2 */
+			unsigned long long progusage1:63;
+			unsigned long long progusage2;
+		};
+		unsigned long long progusage[2];
+	};
 } __packed;
 
 /* Load program parameter */
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index e07cce88dfb0..fcbd638fb9f4 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -9,6 +9,14 @@
 #ifndef _ASM_S390_GMAP_H
 #define _ASM_S390_GMAP_H
 
+/* Generic bits for GMAP notification on DAT table entry changes. */
+#define GMAP_NOTIFY_SHADOW	0x2
+#define GMAP_NOTIFY_MPROT	0x1
+
+/* Status bits only for huge segment entries */
+#define _SEGMENT_ENTRY_GMAP_IN		0x8000	/* invalidation notify bit */
+#define _SEGMENT_ENTRY_GMAP_UC		0x4000	/* dirty (migration) */
+
 /**
  * struct gmap_struct - guest address space
  * @list: list head for the mm->context gmap list
@@ -132,4 +140,6 @@ void gmap_pte_notify(struct mm_struct *, unsigned long addr, pte_t *,
 int gmap_mprotect_notify(struct gmap *, unsigned long start,
 			 unsigned long len, int prot);
 
+void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
+			     unsigned long gaddr, unsigned long vmaddr);
 #endif /* _ASM_S390_GMAP_H */
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 9c5fc50204dd..2d1afa58a4b6 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -37,7 +37,10 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-#define arch_clear_hugepage_flags(page)		do { } while (0)
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_arch_1, &page->flags);
+}
 
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep, unsigned long sz)
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 13de80cf741c..b106aa29bf55 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -68,8 +68,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_saved_imask;
 	unsigned long kprobe_saved_ctl[3];
 	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *p);
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 5bc888841eaf..406d940173ab 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -185,7 +185,7 @@ struct lowcore {
 	/* Transaction abort diagnostic block */
 	__u8	pgm_tdb[256];			/* 0x1800 */
 	__u8	pad_0x1900[0x2000-0x1900];	/* 0x1900 */
-} __packed;
+} __packed __aligned(8192);
 
 #define S390_lowcore (*((struct lowcore *) 0))
 
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index f5ff9dbad8ac..f31a15044c24 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -24,6 +24,8 @@ typedef struct {
 	unsigned int uses_skeys:1;
 	/* The mmu context uses CMM. */
 	unsigned int uses_cmm:1;
+	/* The gmaps associated with this context are allowed to use huge pages. */
+	unsigned int allow_gmap_hpage_1m:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index d16bc79c30bb..0717ee76885d 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -32,6 +32,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.has_pgste = 0;
 	mm->context.uses_skeys = 0;
 	mm->context.uses_cmm = 0;
+	mm->context.allow_gmap_hpage_1m = 0;
 #endif
 	switch (mm->context.asce_limit) {
 	case _REGION2_SIZE:
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
index a01f81186e86..123dac3717b3 100644
--- a/arch/s390/include/asm/nospec-insn.h
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -8,7 +8,7 @@
 
 #ifdef __ASSEMBLY__
 
-#ifdef CONFIG_EXPOLINE
+#ifdef CC_USING_EXPOLINE
 
 _LC_BR_R1 = __LC_BR_R1
 
@@ -189,7 +189,7 @@ _LC_BR_R1 = __LC_BR_R1
 	.macro BASR_EX rsave,rtarget,ruse=%r1
 	basr	\rsave,\rtarget
 	.endm
-#endif
+#endif /* CC_USING_EXPOLINE */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 94f8db468c9b..10fe982f2b4b 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -51,6 +51,10 @@ struct zpci_fmb_fmt2 {
 	u64 max_work_units;
 };
 
+struct zpci_fmb_fmt3 {
+	u64 tx_bytes;
+};
+
 struct zpci_fmb {
 	u32 format	: 8;
 	u32 fmt_ind	: 24;
@@ -66,6 +70,7 @@ struct zpci_fmb {
 		struct zpci_fmb_fmt0 fmt0;
 		struct zpci_fmb_fmt1 fmt1;
 		struct zpci_fmb_fmt2 fmt2;
+		struct zpci_fmb_fmt3 fmt3;
 	};
 } __packed __aligned(128);
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5ab636089c60..0e7cb0dc9c33 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -268,8 +268,10 @@ static inline int is_module_addr(void *addr)
 #define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL
 
 /* Bits in the segment table entry */
-#define _SEGMENT_ENTRY_BITS	0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_BITS			0xfffffffffffffe33UL
+#define _SEGMENT_ENTRY_BITS_LARGE		0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS		0xfffffffffffffe30UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE	0xfffffffffff00730UL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
 #define _SEGMENT_ENTRY_ORIGIN	~0x7ffUL/* page table origin		    */
 #define _SEGMENT_ENTRY_PROTECT	0x200	/* segment protection bit	    */
@@ -1101,7 +1103,8 @@ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
 		    pte_t *sptep, pte_t *tptep, pte_t pte);
 void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep);
 
-bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address);
+bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long address,
+			    pte_t *ptep);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq);
 int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
@@ -1116,6 +1119,10 @@ int set_pgste_bits(struct mm_struct *mm, unsigned long addr,
 int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep);
 int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 			unsigned long *oldpte, unsigned long *oldpgste);
+void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 
 /*
  * Certain architectures need to do special things when PTEs
diff --git a/arch/s390/include/asm/purgatory.h b/arch/s390/include/asm/purgatory.h
index 6090670df51f..e297bcfc476f 100644
--- a/arch/s390/include/asm/purgatory.h
+++ b/arch/s390/include/asm/purgatory.h
@@ -13,11 +13,5 @@
 
 int verify_sha256_digest(void);
 
-extern u64 kernel_entry;
-extern u64 kernel_type;
-
-extern u64 crash_start;
-extern u64 crash_size;
-
 #endif	/* __ASSEMBLY__ */
 #endif /* _S390_PURGATORY_H_ */
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index de11ecc99c7c..9c9970a5dfb1 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -262,7 +262,6 @@ struct qdio_outbuf_state {
 	void *user;
 };
 
-#define QDIO_OUTBUF_STATE_FLAG_NONE	0x00
 #define QDIO_OUTBUF_STATE_FLAG_PENDING	0x01
 
 #define CHSC_AC1_INITIATE_INPUTQ	0x80
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 54f81f8ed662..724faede8ac5 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -4,6 +4,4 @@
 
 #include <asm-generic/sections.h>
 
-extern char _ehead[];
-
 #endif
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 9c30ebe046f3..1d66016f4170 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -9,8 +9,10 @@
 #include <linux/const.h>
 #include <uapi/asm/setup.h>
 
-
+#define EP_OFFSET		0x10008
+#define EP_STRING		"S390EP"
 #define PARMAREA		0x10400
+#define PARMAREA_END		0x11000
 
 /*
  * Machine features detected in early.c
diff --git a/arch/s390/include/uapi/asm/chsc.h b/arch/s390/include/uapi/asm/chsc.h
index dc329aa03f76..83a574e95b3a 100644
--- a/arch/s390/include/uapi/asm/chsc.h
+++ b/arch/s390/include/uapi/asm/chsc.h
@@ -23,29 +23,29 @@ struct chsc_async_header {
 	__u32 key : 4;
 	__u32 : 28;
 	struct subchannel_id sid;
-} __attribute__ ((packed));
+};
 
 struct chsc_async_area {
 	struct chsc_async_header header;
 	__u8 data[CHSC_SIZE - sizeof(struct chsc_async_header)];
-} __attribute__ ((packed));
+};
 
 struct chsc_header {
 	__u16 length;
 	__u16 code;
-} __attribute__ ((packed));
+};
 
 struct chsc_sync_area {
 	struct chsc_header header;
 	__u8 data[CHSC_SIZE - sizeof(struct chsc_header)];
-} __attribute__ ((packed));
+};
 
 struct chsc_response_struct {
 	__u16 length;
 	__u16 code;
 	__u32 parms;
 	__u8 data[CHSC_SIZE - 2 * sizeof(__u16) - sizeof(__u32)];
-} __attribute__ ((packed));
+};
 
 struct chsc_chp_cd {
 	struct chp_id chpid;
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 2fed39b26b42..dbfd1730e631 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -9,39 +9,21 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o		= $(CC_FLAGS_FTRACE)
 
 # Do not trace early setup code
-CFLAGS_REMOVE_als.o		= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_early.o		= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_early_nobss.o	= $(CC_FLAGS_FTRACE)
 
 endif
 
-GCOV_PROFILE_als.o		:= n
 GCOV_PROFILE_early.o		:= n
 GCOV_PROFILE_early_nobss.o	:= n
 
-KCOV_INSTRUMENT_als.o		:= n
 KCOV_INSTRUMENT_early.o		:= n
 KCOV_INSTRUMENT_early_nobss.o	:= n
 
-UBSAN_SANITIZE_als.o		:= n
 UBSAN_SANITIZE_early.o		:= n
 UBSAN_SANITIZE_early_nobss.o	:= n
 
 #
-# Use -march=z900 for als.c to be able to print an error
-# message if the kernel is started on a machine which is too old
-#
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_EXPOLINE)
-CFLAGS_als.o		+= -march=z900
-AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
-AFLAGS_head.o		+= -march=z900
-endif
-
-CFLAGS_als.o		+= -D__NO_FORTIFY
-
-#
 # Passing null pointers is ok for smp code, since we access the lowcore here.
 #
 CFLAGS_smp.o		:= -Wno-nonnull
@@ -61,13 +43,13 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o early_nobss.o
+obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
 obj-y	+= nospec-branch.o
 
-extra-y				+= head.o head64.o vmlinux.lds
+extra-y				+= head64.o vmlinux.lds
 
 obj-$(CONFIG_SYSFS)		+= nospec-sysfs.o
 CFLAGS_REMOVE_nospec-branch.o	+= $(CC_FLAGS_EXPOLINE)
@@ -99,5 +81,5 @@ obj-$(CONFIG_TRACEPOINTS)	+= trace.o
 obj-y				+= vdso64/
 obj-$(CONFIG_COMPAT)		+= vdso32/
 
-chkbss := head.o head64.o als.o early_nobss.o
+chkbss := head64.o early_nobss.o
 include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 9f5ea9d87069..c3620bafc374 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -306,6 +306,15 @@ static void *kzalloc_panic(int len)
 	return rc;
 }
 
+static const char *nt_name(Elf64_Word type)
+{
+	const char *name = "LINUX";
+
+	if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
+		name = KEXEC_CORE_NOTE_NAME;
+	return name;
+}
+
 /*
  * Initialize ELF note
  */
@@ -332,11 +341,26 @@ static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len,
 
 static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len)
 {
-	const char *note_name = "LINUX";
+	return nt_init_name(buf, type, desc, d_len, nt_name(type));
+}
+
+/*
+ * Calculate the size of ELF note
+ */
+static size_t nt_size_name(int d_len, const char *name)
+{
+	size_t size;
 
-	if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
-		note_name = KEXEC_CORE_NOTE_NAME;
-	return nt_init_name(buf, type, desc, d_len, note_name);
+	size = sizeof(Elf64_Nhdr);
+	size += roundup(strlen(name) + 1, 4);
+	size += roundup(d_len, 4);
+
+	return size;
+}
+
+static inline size_t nt_size(Elf64_Word type, int d_len)
+{
+	return nt_size_name(d_len, nt_name(type));
 }
 
 /*
@@ -375,6 +399,29 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa)
 }
 
 /*
+ * Calculate size of ELF notes per cpu
+ */
+static size_t get_cpu_elf_notes_size(void)
+{
+	struct save_area *sa = NULL;
+	size_t size;
+
+	size =	nt_size(NT_PRSTATUS, sizeof(struct elf_prstatus));
+	size +=  nt_size(NT_PRFPREG, sizeof(elf_fpregset_t));
+	size +=  nt_size(NT_S390_TIMER, sizeof(sa->timer));
+	size +=  nt_size(NT_S390_TODCMP, sizeof(sa->todcmp));
+	size +=  nt_size(NT_S390_TODPREG, sizeof(sa->todpreg));
+	size +=  nt_size(NT_S390_CTRS, sizeof(sa->ctrs));
+	size +=  nt_size(NT_S390_PREFIX, sizeof(sa->prefix));
+	if (MACHINE_HAS_VX) {
+		size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high));
+		size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low));
+	}
+
+	return size;
+}
+
+/*
  * Initialize prpsinfo note (new kernel)
  */
 static void *nt_prpsinfo(void *ptr)
@@ -429,6 +476,30 @@ static void *nt_vmcoreinfo(void *ptr)
 	return nt_init_name(ptr, 0, vmcoreinfo, size, "VMCOREINFO");
 }
 
+static size_t nt_vmcoreinfo_size(void)
+{
+	const char *name = "VMCOREINFO";
+	char nt_name[11];
+	Elf64_Nhdr note;
+	void *addr;
+
+	if (copy_oldmem_kernel(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
+		return 0;
+
+	if (copy_oldmem_kernel(&note, addr, sizeof(note)))
+		return 0;
+
+	memset(nt_name, 0, sizeof(nt_name));
+	if (copy_oldmem_kernel(nt_name, addr + sizeof(note),
+			       sizeof(nt_name) - 1))
+		return 0;
+
+	if (strcmp(nt_name, name) != 0)
+		return 0;
+
+	return nt_size_name(note.n_descsz, name);
+}
+
 /*
  * Initialize final note (needed for /proc/vmcore code)
  */
@@ -539,6 +610,27 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 	return ptr;
 }
 
+static size_t get_elfcorehdr_size(int mem_chunk_cnt)
+{
+	size_t size;
+
+	size = sizeof(Elf64_Ehdr);
+	/* PT_NOTES */
+	size += sizeof(Elf64_Phdr);
+	/* nt_prpsinfo */
+	size += nt_size(NT_PRPSINFO, sizeof(struct elf_prpsinfo));
+	/* regsets */
+	size += get_cpu_cnt() * get_cpu_elf_notes_size();
+	/* nt_vmcoreinfo */
+	size += nt_vmcoreinfo_size();
+	/* nt_final */
+	size += sizeof(Elf64_Nhdr);
+	/* PT_LOADS */
+	size += mem_chunk_cnt * sizeof(Elf64_Phdr);
+
+	return size;
+}
+
 /*
  * Create ELF core header (new kernel)
  */
@@ -566,8 +658,8 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 
 	mem_chunk_cnt = get_mem_chunk_cnt();
 
-	alloc_size = 0x1000 + get_cpu_cnt() * 0x4a0 +
-		mem_chunk_cnt * sizeof(Elf64_Phdr);
+	alloc_size = get_elfcorehdr_size(mem_chunk_cnt);
+
 	hdr = kzalloc_panic(alloc_size);
 	/* Init elf header */
 	ptr = ehdr_init(hdr, mem_chunk_cnt);
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 827699eb48fa..5b28b434f8a1 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -331,8 +331,20 @@ static void __init setup_boot_command_line(void)
 	append_to_cmdline(append_ipl_scpdata);
 }
 
+static void __init check_image_bootable(void)
+{
+	if (!memcmp(EP_STRING, (void *)EP_OFFSET, strlen(EP_STRING)))
+		return;
+
+	sclp_early_printk("Linux kernel boot failure: An attempt to boot a vmlinux ELF image failed.\n");
+	sclp_early_printk("This image does not contain all parts necessary for starting up. Use\n");
+	sclp_early_printk("bzImage or arch/s390/boot/compressed/vmlinux instead.\n");
+	disabled_wait(0xbadb007);
+}
+
 void __init startup_init(void)
 {
+	check_image_bootable();
 	time_early_init();
 	init_kernel_storage_key();
 	lockdep_off();
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 961abfac2c5f..472fa2f1a4a5 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -83,7 +83,6 @@ long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user
 
 DECLARE_PER_CPU(u64, mt_cycles[8]);
 
-void verify_facilities(void);
 void gs_load_bc_cb(struct pt_regs *regs);
 void set_fs_fixup(void);
 
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 791cb9000e86..6d14ad42ba88 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -48,11 +48,23 @@ ENTRY(startup_continue)
 # Early machine initialization and detection functions.
 #
 	brasl	%r14,startup_init
-	lpswe	.Lentry-.LPG1(13)	# jump to _stext in primary-space,
-					# virtual and never return ...
+
+# check control registers
+	stctg	%c0,%c15,0(%r15)
+	oi	6(%r15),0x60		# enable sigp emergency & external call
+	oi	4(%r15),0x10		# switch on low address proctection
+	lctlg	%c0,%c15,0(%r15)
+
+	lam	0,15,.Laregs-.LPG1(%r13)	# load acrs needed by uaccess
+	brasl	%r14,start_kernel		# go to C code
+#
+# We returned from start_kernel ?!? PANIK
+#
+	basr	%r13,0
+	lpswe	.Ldw-.(%r13)		# load disabled wait psw
+
 	.align	16
 .LPG1:
-.Lentry:.quad	0x0000000180000000,_stext
 .Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
 	.quad	0			# cr1: primary space segment table
 	.quad	.Lduct			# cr2: dispatchable unit control table
@@ -85,30 +97,5 @@ ENTRY(startup_continue)
 	.endr
 .Llinkage_stack:
 	.long	0,0,0x89000000,0,0,0,0x8a000000,0
-
-ENTRY(_ehead)
-
-	.org	0x100000 - 0x11000	# head.o ends at 0x11000
-#
-# startup-code, running in absolute addressing mode
-#
-ENTRY(_stext)
-	basr	%r13,0			# get base
-.LPG3:
-# check control registers
-	stctg	%c0,%c15,0(%r15)
-	oi	6(%r15),0x60		# enable sigp emergency & external call
-	oi	4(%r15),0x10		# switch on low address proctection
-	lctlg	%c0,%c15,0(%r15)
-
-	lam	0,15,.Laregs-.LPG3(%r13)	# load acrs needed by uaccess
-	brasl	%r14,start_kernel	# go to C code
-#
-# We returned from start_kernel ?!? PANIK
-#
-	basr	%r13,0
-	lpswe	.Ldw-.(%r13)		# load disabled wait psw
-
-	.align	8
 .Ldw:	.quad	0x0002000180000000,0x0000000000000000
 .Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 60f60afa645c..7c0a095e9c5f 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -321,38 +321,20 @@ static int kprobe_handler(struct pt_regs *regs)
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with single stepping. If we have a
 			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry
-			 * for jprobe processing, so get out doing nothing
-			 * more here.
+			 * for changing execution path, so get out doing
+			 * nothing more here.
 			 */
 			push_kprobe(kcb, p);
 			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-			if (p->pre_handler && p->pre_handler(p, regs))
+			if (p->pre_handler && p->pre_handler(p, regs)) {
+				pop_kprobe(kcb);
+				preempt_enable_no_resched();
 				return 1;
+			}
 			kcb->kprobe_status = KPROBE_HIT_SS;
 		}
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			/*
-			 * Continuation after the jprobe completed and
-			 * caused the jprobe_return trap. The jprobe
-			 * break_handler "returns" to the original
-			 * function that still has the kprobe breakpoint
-			 * installed. We continue with single stepping.
-			 */
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			enable_singlestep(kcb, regs,
-					  (unsigned long) p->ainsn.insn);
-			return 1;
-		} /* else:
-		   * No kprobe at this address and the current kprobe
-		   * has no break handler (no jprobe!). The kernel just
-		   * exploded, let the standard trap handler pick up the
-		   * pieces.
-		   */
 	} /* else:
 	   * No kprobe at this address and no active kprobe. The trap has
 	   * not been caused by a kprobe breakpoint. The race of breakpoint
@@ -452,9 +434,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 
 	regs->psw.addr = orig_ret_address;
 
-	pop_kprobe(get_kprobe_ctlblk());
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
@@ -661,60 +641,6 @@ int kprobe_exceptions_notify(struct notifier_block *self,
 }
 NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack;
-
-	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
-	/* setup return addr to the jprobe handler routine */
-	regs->psw.addr = (unsigned long) jp->entry;
-	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
-
-	/* r15 is the stack pointer */
-	stack = (unsigned long) regs->gprs[15];
-
-	memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack));
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer to get messed up.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void jprobe_return(void)
-{
-	asm volatile(".word 0x0002");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack;
-
-	/* It's OK to start function graph tracing again */
-	unpause_graph_tracing();
-
-	stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15];
-
-	/* Put the regs back */
-	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
-	/* put the stack back */
-	memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack));
-	preempt_enable_no_resched();
-	return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 static struct kprobe trampoline = {
 	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index 18ae7b9c71d6..bdddaae96559 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -35,6 +35,8 @@ early_param("nospec", nospec_setup_early);
 
 static int __init nospec_report(void)
 {
+	if (test_facility(156))
+		pr_info("Spectre V2 mitigation: etokens\n");
 	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
 		pr_info("Spectre V2 mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
@@ -56,7 +58,15 @@ early_param("nospectre_v2", nospectre_v2_setup_early);
 
 void __init nospec_auto_detect(void)
 {
-	if (IS_ENABLED(CC_USING_EXPOLINE)) {
+	if (test_facility(156)) {
+		/*
+		 * The machine supports etokens.
+		 * Disable expolines and disable nobp.
+		 */
+		if (IS_ENABLED(CC_USING_EXPOLINE))
+			nospec_disable = 1;
+		__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+	} else if (IS_ENABLED(CC_USING_EXPOLINE)) {
 		/*
 		 * The kernel has been compiled with expolines.
 		 * Keep expolines enabled and disable nobp.
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
index 8affad5f18cb..e30e580ae362 100644
--- a/arch/s390/kernel/nospec-sysfs.c
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -13,6 +13,8 @@ ssize_t cpu_show_spectre_v1(struct device *dev,
 ssize_t cpu_show_spectre_v2(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
+	if (test_facility(156))
+		return sprintf(buf, "Mitigation: etokens\n");
 	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
 		return sprintf(buf, "Mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 0292d68e7dde..cb198d4a6dca 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -2,7 +2,7 @@
 /*
  * Performance event support for the System z CPU-measurement Sampling Facility
  *
- * Copyright IBM Corp. 2013
+ * Copyright IBM Corp. 2013, 2018
  * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
 #define KMSG_COMPONENT	"cpum_sf"
@@ -1587,6 +1587,17 @@ static void aux_buffer_free(void *data)
 			    "%lu SDBTs\n", num_sdbt);
 }
 
+static void aux_sdb_init(unsigned long sdb)
+{
+	struct hws_trailer_entry *te;
+
+	te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb);
+
+	/* Save clock base */
+	te->clock_base = 1;
+	memcpy(&te->progusage2, &tod_clock_base[1], 8);
+}
+
 /*
  * aux_buffer_setup() - Setup AUX buffer for diagnostic mode sampling
  * @cpu:	On which to allocate, -1 means current
@@ -1666,6 +1677,7 @@ static void *aux_buffer_setup(int cpu, void **pages, int nr_pages,
 		/* Tail is the entry in a SDBT */
 		*tail = (unsigned long)pages[i];
 		aux->sdb_index[i] = (unsigned long)pages[i];
+		aux_sdb_init((unsigned long)pages[i]);
 	}
 	sfb->num_sdb = nr_pages;
 
diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index 54e2d634b849..4352a504f235 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -12,9 +12,6 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
 	freg_t fp;
 
-	if (WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX))
-		return 0;
-
 	if (idx >= PERF_REG_S390_R0 && idx <= PERF_REG_S390_R15)
 		return regs->gprs[idx];
 
@@ -33,7 +30,8 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	if (idx == PERF_REG_S390_PC)
 		return regs->psw.addr;
 
-	return regs->gprs[idx];
+	WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX);
+	return 0;
 }
 
 #define REG_RESERVED (~((1UL << PERF_REG_S390_MAX) - 1))
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index d82a9ec64ea9..c637c12f9e37 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -674,12 +674,12 @@ static void __init reserve_kernel(void)
 #ifdef CONFIG_DMA_API_DEBUG
 	/*
 	 * DMA_API_DEBUG code stumbles over addresses from the
-	 * range [_ehead, _stext]. Mark the memory as reserved
+	 * range [PARMAREA_END, _stext]. Mark the memory as reserved
 	 * so it is not used for CONFIG_DMA_API_DEBUG=y.
 	 */
 	memblock_reserve(0, PFN_PHYS(start_pfn));
 #else
-	memblock_reserve(0, (unsigned long)_ehead);
+	memblock_reserve(0, PARMAREA_END);
 	memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
 			 - (unsigned long)_stext);
 #endif
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 54f5496913fa..12f80d1f0415 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -59,6 +59,8 @@ int stsi(void *sysinfo, int fc, int sel1, int sel2)
 }
 EXPORT_SYMBOL(stsi);
 
+#ifdef CONFIG_PROC_FS
+
 static bool convert_ext_name(unsigned char encoding, char *name, size_t len)
 {
 	switch (encoding) {
@@ -301,6 +303,8 @@ static int __init sysinfo_create_proc(void)
 }
 device_initcall(sysinfo_create_proc);
 
+#endif /* CONFIG_PROC_FS */
+
 /*
  * Service levels interface.
  */
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index cf561160ea88..e8766beee5ad 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -221,17 +221,22 @@ void read_persistent_clock64(struct timespec64 *ts)
 	ext_to_timespec64(clk, ts);
 }
 
-void read_boot_clock64(struct timespec64 *ts)
+void __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+						 struct timespec64 *boot_offset)
 {
 	unsigned char clk[STORE_CLOCK_EXT_SIZE];
+	struct timespec64 boot_time;
 	__u64 delta;
 
 	delta = initial_leap_seconds + TOD_UNIX_EPOCH;
-	memcpy(clk, tod_clock_base, 16);
-	*(__u64 *) &clk[1] -= delta;
-	if (*(__u64 *) &clk[1] > delta)
+	memcpy(clk, tod_clock_base, STORE_CLOCK_EXT_SIZE);
+	*(__u64 *)&clk[1] -= delta;
+	if (*(__u64 *)&clk[1] > delta)
 		clk[0]--;
-	ext_to_timespec64(clk, ts);
+	ext_to_timespec64(clk, &boot_time);
+
+	read_persistent_clock64(wall_time);
+	*boot_offset = timespec64_sub(*wall_time, boot_time);
 }
 
 static u64 read_tod_clock(struct clocksource *cs)
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 4b6e0397f66d..e8184a15578a 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -579,41 +579,33 @@ early_param("topology", topology_setup);
 static int topology_ctl_handler(struct ctl_table *ctl, int write,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	unsigned int len;
+	int enabled = topology_is_enabled();
 	int new_mode;
-	char buf[2];
+	int zero = 0;
+	int one = 1;
+	int rc;
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &enabled,
+		.maxlen		= sizeof(int),
+		.extra1		= &zero,
+		.extra2		= &one,
+	};
+
+	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
-		return 0;
-	}
-	if (!write) {
-		strncpy(buf, topology_is_enabled() ? "1\n" : "0\n",
-			ARRAY_SIZE(buf));
-		len = strnlen(buf, ARRAY_SIZE(buf));
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
-		return -EFAULT;
-	if (buf[0] != '0' && buf[0] != '1')
-		return -EINVAL;
 	mutex_lock(&smp_cpu_state_mutex);
-	new_mode = topology_get_mode(buf[0] == '1');
+	new_mode = topology_get_mode(enabled);
 	if (topology_mode != new_mode) {
 		topology_mode = new_mode;
 		topology_schedule_update();
 	}
 	mutex_unlock(&smp_cpu_state_mutex);
 	topology_flush_work();
-out:
-	*lenp = len;
-	*ppos += len;
-	return 0;
+
+	return rc;
 }
 
 static struct ctl_table topology_ctl_table[] = {
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 09abae40f917..3031cc6dd0ab 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -47,7 +47,7 @@ static struct page **vdso64_pagelist;
  */
 unsigned int __read_mostly vdso_enabled = 1;
 
-static int vdso_fault(const struct vm_special_mapping *sm,
+static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
 		      struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct page **vdso_pagelist;
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index f0414f52817b..b43f8d33a369 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -19,7 +19,7 @@
 
 OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
 OUTPUT_ARCH(s390:64-bit)
-ENTRY(startup)
+ENTRY(startup_continue)
 jiffies = jiffies_64;
 
 PHDRS {
@@ -30,16 +30,12 @@ PHDRS {
 
 SECTIONS
 {
-	. = 0x00000000;
+	. = 0x100000;
+	_stext = .;		/* Start of text section */
 	.text : {
 		/* Text and read-only data */
+		_text = .;
 		HEAD_TEXT
-		/*
-		 * E.g. perf doesn't like symbols starting at address zero,
-		 * therefore skip the initial PSW and channel program located
-		 * at address zero and let _text start at 0x200.
-		 */
-	_text = 0x200;
 		TEXT_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT
@@ -47,6 +43,7 @@ SECTIONS
 		KPROBES_TEXT
 		IRQENTRY_TEXT
 		SOFTIRQENTRY_TEXT
+		*(.text.*_indirect_*)
 		*(.fixup)
 		*(.gnu.warning)
 	} :text = 0x0700
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index daa09f89ca2d..fcb55b02990e 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1145,7 +1145,7 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 		 * yield-candidate.
 		 */
 		vcpu->preempted = true;
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
 	}
 	/*
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 3b7a5151b6a5..f9d90337e64a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -172,6 +172,10 @@ static int nested;
 module_param(nested, int, S_IRUGO);
 MODULE_PARM_DESC(nested, "Nested virtualization support");
 
+/* allow 1m huge page guest backing, if !nested */
+static int hpage;
+module_param(hpage, int, 0444);
+MODULE_PARM_DESC(hpage, "1m huge page backing support");
 
 /*
  * For now we handle at most 16 double words as this is what the s390 base
@@ -475,6 +479,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_AIS_MIGRATION:
 		r = 1;
 		break;
+	case KVM_CAP_S390_HPAGE_1M:
+		r = 0;
+		if (hpage)
+			r = 1;
+		break;
 	case KVM_CAP_S390_MEM_OP:
 		r = MEM_OP_MAX_SIZE;
 		break;
@@ -511,19 +520,30 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 }
 
 static void kvm_s390_sync_dirty_log(struct kvm *kvm,
-					struct kvm_memory_slot *memslot)
+				    struct kvm_memory_slot *memslot)
 {
+	int i;
 	gfn_t cur_gfn, last_gfn;
-	unsigned long address;
+	unsigned long gaddr, vmaddr;
 	struct gmap *gmap = kvm->arch.gmap;
+	DECLARE_BITMAP(bitmap, _PAGE_ENTRIES);
 
-	/* Loop over all guest pages */
+	/* Loop over all guest segments */
+	cur_gfn = memslot->base_gfn;
 	last_gfn = memslot->base_gfn + memslot->npages;
-	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
-		address = gfn_to_hva_memslot(memslot, cur_gfn);
+	for (; cur_gfn <= last_gfn; cur_gfn += _PAGE_ENTRIES) {
+		gaddr = gfn_to_gpa(cur_gfn);
+		vmaddr = gfn_to_hva_memslot(memslot, cur_gfn);
+		if (kvm_is_error_hva(vmaddr))
+			continue;
+
+		bitmap_zero(bitmap, _PAGE_ENTRIES);
+		gmap_sync_dirty_log_pmd(gmap, bitmap, gaddr, vmaddr);
+		for (i = 0; i < _PAGE_ENTRIES; i++) {
+			if (test_bit(i, bitmap))
+				mark_page_dirty(kvm, cur_gfn + i);
+		}
 
-		if (test_and_clear_guest_dirty(gmap->mm, address))
-			mark_page_dirty(kvm, cur_gfn);
 		if (fatal_signal_pending(current))
 			return;
 		cond_resched();
@@ -667,6 +687,27 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_GS %s",
 			 r ? "(not available)" : "(success)");
 		break;
+	case KVM_CAP_S390_HPAGE_1M:
+		mutex_lock(&kvm->lock);
+		if (kvm->created_vcpus)
+			r = -EBUSY;
+		else if (!hpage || kvm->arch.use_cmma)
+			r = -EINVAL;
+		else {
+			r = 0;
+			kvm->mm->context.allow_gmap_hpage_1m = 1;
+			/*
+			 * We might have to create fake 4k page
+			 * tables. To avoid that the hardware works on
+			 * stale PGSTEs, we emulate these instructions.
+			 */
+			kvm->arch.use_skf = 0;
+			kvm->arch.use_pfmfi = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s",
+			 r ? "(not available)" : "(success)");
+		break;
 	case KVM_CAP_S390_USER_STSI:
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
 		kvm->arch.user_stsi = 1;
@@ -714,10 +755,13 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		if (!sclp.has_cmma)
 			break;
 
-		ret = -EBUSY;
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
 		mutex_lock(&kvm->lock);
-		if (!kvm->created_vcpus) {
+		if (kvm->created_vcpus)
+			ret = -EBUSY;
+		else if (kvm->mm->context.allow_gmap_hpage_1m)
+			ret = -EINVAL;
+		else {
 			kvm->arch.use_cmma = 1;
 			/* Not compatible with cmma. */
 			kvm->arch.use_pfmfi = 0;
@@ -1540,6 +1584,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	uint8_t *keys;
 	uint64_t hva;
 	int srcu_idx, i, r = 0;
+	bool unlocked;
 
 	if (args->flags != 0)
 		return -EINVAL;
@@ -1564,9 +1609,11 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	if (r)
 		goto out;
 
+	i = 0;
 	down_read(&current->mm->mmap_sem);
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	for (i = 0; i < args->count; i++) {
+        while (i < args->count) {
+		unlocked = false;
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
 		if (kvm_is_error_hva(hva)) {
 			r = -EFAULT;
@@ -1580,8 +1627,14 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 		}
 
 		r = set_guest_storage_key(current->mm, hva, keys[i], 0);
-		if (r)
-			break;
+		if (r) {
+			r = fixup_user_fault(current, current->mm, hva,
+					     FAULT_FLAG_WRITE, &unlocked);
+			if (r)
+				break;
+		}
+		if (!r)
+			i++;
 	}
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	up_read(&current->mm->mmap_sem);
@@ -4082,6 +4135,11 @@ static int __init kvm_s390_init(void)
 		return -ENODEV;
 	}
 
+	if (nested && hpage) {
+		pr_info("nested (vSIE) and hpage (huge page backing) can currently not be activated concurrently");
+		return -EINVAL;
+	}
+
 	for (i = 0; i < 16; i++)
 		kvm_s390_fac_base[i] |=
 			S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index eb0eb60c7be6..cfc5a62329f6 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -246,9 +246,10 @@ static int try_handle_skey(struct kvm_vcpu *vcpu)
 
 static int handle_iske(struct kvm_vcpu *vcpu)
 {
-	unsigned long addr;
+	unsigned long gaddr, vmaddr;
 	unsigned char key;
 	int reg1, reg2;
+	bool unlocked;
 	int rc;
 
 	vcpu->stat.instruction_iske++;
@@ -262,18 +263,28 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
-	addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
-	addr = kvm_s390_logical_to_effective(vcpu, addr);
-	addr = kvm_s390_real_to_abs(vcpu, addr);
-	addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
-	if (kvm_is_error_hva(addr))
+	gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	gaddr = kvm_s390_logical_to_effective(vcpu, gaddr);
+	gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
+	vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr));
+	if (kvm_is_error_hva(vmaddr))
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+retry:
+	unlocked = false;
 	down_read(&current->mm->mmap_sem);
-	rc = get_guest_storage_key(current->mm, addr, &key);
-	up_read(&current->mm->mmap_sem);
+	rc = get_guest_storage_key(current->mm, vmaddr, &key);
+
+	if (rc) {
+		rc = fixup_user_fault(current, current->mm, vmaddr,
+				      FAULT_FLAG_WRITE, &unlocked);
+		if (!rc) {
+			up_read(&current->mm->mmap_sem);
+			goto retry;
+		}
+	}
 	if (rc)
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	up_read(&current->mm->mmap_sem);
 	vcpu->run->s.regs.gprs[reg1] &= ~0xff;
 	vcpu->run->s.regs.gprs[reg1] |= key;
 	return 0;
@@ -281,8 +292,9 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 
 static int handle_rrbe(struct kvm_vcpu *vcpu)
 {
-	unsigned long addr;
+	unsigned long vmaddr, gaddr;
 	int reg1, reg2;
+	bool unlocked;
 	int rc;
 
 	vcpu->stat.instruction_rrbe++;
@@ -296,19 +308,27 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
 
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
-	addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
-	addr = kvm_s390_logical_to_effective(vcpu, addr);
-	addr = kvm_s390_real_to_abs(vcpu, addr);
-	addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
-	if (kvm_is_error_hva(addr))
+	gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	gaddr = kvm_s390_logical_to_effective(vcpu, gaddr);
+	gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
+	vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr));
+	if (kvm_is_error_hva(vmaddr))
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+retry:
+	unlocked = false;
 	down_read(&current->mm->mmap_sem);
-	rc = reset_guest_reference_bit(current->mm, addr);
-	up_read(&current->mm->mmap_sem);
+	rc = reset_guest_reference_bit(current->mm, vmaddr);
+	if (rc < 0) {
+		rc = fixup_user_fault(current, current->mm, vmaddr,
+				      FAULT_FLAG_WRITE, &unlocked);
+		if (!rc) {
+			up_read(&current->mm->mmap_sem);
+			goto retry;
+		}
+	}
 	if (rc < 0)
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+	up_read(&current->mm->mmap_sem);
 	kvm_s390_set_psw_cc(vcpu, rc);
 	return 0;
 }
@@ -323,6 +343,7 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 	unsigned long start, end;
 	unsigned char key, oldkey;
 	int reg1, reg2;
+	bool unlocked;
 	int rc;
 
 	vcpu->stat.instruction_sske++;
@@ -355,19 +376,28 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 	}
 
 	while (start != end) {
-		unsigned long addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+		unsigned long vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+		unlocked = false;
 
-		if (kvm_is_error_hva(addr))
+		if (kvm_is_error_hva(vmaddr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 		down_read(&current->mm->mmap_sem);
-		rc = cond_set_guest_storage_key(current->mm, addr, key, &oldkey,
+		rc = cond_set_guest_storage_key(current->mm, vmaddr, key, &oldkey,
 						m3 & SSKE_NQ, m3 & SSKE_MR,
 						m3 & SSKE_MC);
-		up_read(&current->mm->mmap_sem);
-		if (rc < 0)
+
+		if (rc < 0) {
+			rc = fixup_user_fault(current, current->mm, vmaddr,
+					      FAULT_FLAG_WRITE, &unlocked);
+			rc = !rc ? -EAGAIN : rc;
+		}
+		if (rc == -EFAULT)
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		start += PAGE_SIZE;
+
+		up_read(&current->mm->mmap_sem);
+		if (rc >= 0)
+			start += PAGE_SIZE;
 	}
 
 	if (m3 & (SSKE_MC | SSKE_MR)) {
@@ -948,15 +978,16 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 	}
 
 	while (start != end) {
-		unsigned long useraddr;
+		unsigned long vmaddr;
+		bool unlocked = false;
 
 		/* Translate guest address to host address */
-		useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
-		if (kvm_is_error_hva(useraddr))
+		vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+		if (kvm_is_error_hva(vmaddr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 		if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
-			if (clear_user((void __user *)useraddr, PAGE_SIZE))
+			if (clear_user((void __user *)vmaddr, PAGE_SIZE))
 				return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 		}
 
@@ -966,14 +997,20 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 			if (rc)
 				return rc;
 			down_read(&current->mm->mmap_sem);
-			rc = cond_set_guest_storage_key(current->mm, useraddr,
+			rc = cond_set_guest_storage_key(current->mm, vmaddr,
 							key, NULL, nq, mr, mc);
-			up_read(&current->mm->mmap_sem);
-			if (rc < 0)
+			if (rc < 0) {
+				rc = fixup_user_fault(current, current->mm, vmaddr,
+						      FAULT_FLAG_WRITE, &unlocked);
+				rc = !rc ? -EAGAIN : rc;
+			}
+			if (rc == -EFAULT)
 				return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		}
 
-		start += PAGE_SIZE;
+			up_read(&current->mm->mmap_sem);
+			if (rc >= 0)
+				start += PAGE_SIZE;
+		}
 	}
 	if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
 		if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) {
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 2311f15be9cf..40c4d59c926e 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -17,7 +17,7 @@
 ENTRY(memmove)
 	ltgr	%r4,%r4
 	lgr	%r1,%r2
-	bzr	%r14
+	jz	.Lmemmove_exit
 	aghi	%r4,-1
 	clgr	%r2,%r3
 	jnh	.Lmemmove_forward
@@ -36,6 +36,7 @@ ENTRY(memmove)
 .Lmemmove_forward_remainder:
 	larl	%r5,.Lmemmove_mvc
 	ex	%r4,0(%r5)
+.Lmemmove_exit:
 	BR_EX	%r14
 .Lmemmove_reverse:
 	ic	%r0,0(%r4,%r3)
@@ -65,7 +66,7 @@ EXPORT_SYMBOL(memmove)
  */
 ENTRY(memset)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.Lmemset_exit
 	ltgr	%r3,%r3
 	jnz	.Lmemset_fill
 	aghi	%r4,-1
@@ -80,6 +81,7 @@ ENTRY(memset)
 .Lmemset_clear_remainder:
 	larl	%r3,.Lmemset_xc
 	ex	%r4,0(%r3)
+.Lmemset_exit:
 	BR_EX	%r14
 .Lmemset_fill:
 	cghi	%r4,1
@@ -115,7 +117,7 @@ EXPORT_SYMBOL(memset)
  */
 ENTRY(memcpy)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.Lmemcpy_exit
 	aghi	%r4,-1
 	srlg	%r5,%r4,8
 	ltgr	%r5,%r5
@@ -124,6 +126,7 @@ ENTRY(memcpy)
 .Lmemcpy_remainder:
 	larl	%r5,.Lmemcpy_mvc
 	ex	%r4,0(%r5)
+.Lmemcpy_exit:
 	BR_EX	%r14
 .Lmemcpy_loop:
 	mvc	0(256,%r1),0(%r3)
@@ -145,9 +148,9 @@ EXPORT_SYMBOL(memcpy)
 .macro __MEMSET bits,bytes,insn
 ENTRY(__memset\bits)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.L__memset_exit\bits
 	cghi	%r4,\bytes
-	je	.L__memset_exit\bits
+	je	.L__memset_store\bits
 	aghi	%r4,-(\bytes+1)
 	srlg	%r5,%r4,8
 	ltgr	%r5,%r5
@@ -163,8 +166,9 @@ ENTRY(__memset\bits)
 	larl	%r5,.L__memset_mvc\bits
 	ex	%r4,0(%r5)
 	BR_EX	%r14
-.L__memset_exit\bits:
+.L__memset_store\bits:
 	\insn	%r3,0(%r2)
+.L__memset_exit\bits:
 	BR_EX	%r14
 .L__memset_mvc\bits:
 	mvc	\bytes(1,%r1),0(%r1)
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 6cf024eb2085..510a18299196 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -191,12 +191,7 @@ static void cmm_set_timer(void)
 			del_timer(&cmm_timer);
 		return;
 	}
-	if (timer_pending(&cmm_timer)) {
-		if (mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds*HZ))
-			return;
-	}
-	cmm_timer.expires = jiffies + cmm_timeout_seconds*HZ;
-	add_timer(&cmm_timer);
+	mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds * HZ);
 }
 
 static void cmm_timer_fn(struct timer_list *unused)
@@ -251,45 +246,42 @@ static int cmm_skip_blanks(char *cp, char **endp)
 	return str != cp;
 }
 
-static struct ctl_table cmm_table[];
-
 static int cmm_pages_handler(struct ctl_table *ctl, int write,
 			     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	char buf[16], *p;
-	unsigned int len;
-	long nr;
+	long nr = cmm_get_pages();
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &nr,
+		.maxlen		= sizeof(long),
+	};
+	int rc;
 
-	if (!*lenp || (*ppos && !write)) {
-		*lenp = 0;
-		return 0;
-	}
+	rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
-	if (write) {
-		len = *lenp;
-		if (copy_from_user(buf, buffer,
-				   len > sizeof(buf) ? sizeof(buf) : len))
-			return -EFAULT;
-		buf[sizeof(buf) - 1] = '\0';
-		cmm_skip_blanks(buf, &p);
-		nr = simple_strtoul(p, &p, 0);
-		if (ctl == &cmm_table[0])
-			cmm_set_pages(nr);
-		else
-			cmm_add_timed_pages(nr);
-	} else {
-		if (ctl == &cmm_table[0])
-			nr = cmm_get_pages();
-		else
-			nr = cmm_get_timed_pages();
-		len = sprintf(buf, "%ld\n", nr);
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-	}
-	*lenp = len;
-	*ppos += len;
+	cmm_set_pages(nr);
+	return 0;
+}
+
+static int cmm_timed_pages_handler(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	long nr = cmm_get_timed_pages();
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &nr,
+		.maxlen		= sizeof(long),
+	};
+	int rc;
+
+	rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
+
+	cmm_add_timed_pages(nr);
 	return 0;
 }
 
@@ -338,7 +330,7 @@ static struct ctl_table cmm_table[] = {
 	{
 		.procname	= "cmm_timed_pages",
 		.mode		= 0644,
-		.proc_handler	= cmm_pages_handler,
+		.proc_handler	= cmm_timed_pages_handler,
 	},
 	{
 		.procname	= "cmm_timeout",
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 6ad15d3fab81..84111a43ea29 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -80,7 +80,7 @@ struct qin64 {
 struct dcss_segment {
 	struct list_head list;
 	char dcss_name[8];
-	char res_name[15];
+	char res_name[16];
 	unsigned long start_addr;
 	unsigned long end;
 	atomic_t ref_count;
@@ -433,7 +433,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 	memcpy(&seg->res_name, seg->dcss_name, 8);
 	EBCASC(seg->res_name, 8);
 	seg->res_name[8] = '\0';
-	strncat(seg->res_name, " (DCSS)", 7);
+	strlcat(seg->res_name, " (DCSS)", sizeof(seg->res_name));
 	seg->res->name = seg->res_name;
 	rc = seg->vm_segtype;
 	if (rc == SEG_TYPE_SC ||
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index e074480d3598..4cc3f06b0ab3 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -502,6 +502,8 @@ retry:
 	/* No reason to continue if interrupted by SIGKILL. */
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
 		fault = VM_FAULT_SIGNAL;
+		if (flags & FAULT_FLAG_RETRY_NOWAIT)
+			goto out_up;
 		goto out;
 	}
 	if (unlikely(fault & VM_FAULT_ERROR))
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index bc56ec8abcf7..bb44990c8212 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2,8 +2,10 @@
 /*
  *  KVM guest address space mapping code
  *
- *    Copyright IBM Corp. 2007, 2016
+ *    Copyright IBM Corp. 2007, 2016, 2018
  *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *		 David Hildenbrand <david@redhat.com>
+ *		 Janosch Frank <frankja@linux.vnet.ibm.com>
  */
 
 #include <linux/kernel.h>
@@ -521,6 +523,9 @@ void gmap_unlink(struct mm_struct *mm, unsigned long *table,
 	rcu_read_unlock();
 }
 
+static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *old, pmd_t new,
+			   unsigned long gaddr);
+
 /**
  * gmap_link - set up shadow page tables to connect a host to a guest address
  * @gmap: pointer to guest mapping meta data structure
@@ -541,6 +546,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
+	u64 unprot;
 	int rc;
 
 	BUG_ON(gmap_is_shadow(gmap));
@@ -584,8 +590,8 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 		return -EFAULT;
 	pmd = pmd_offset(pud, vmaddr);
 	VM_BUG_ON(pmd_none(*pmd));
-	/* large pmds cannot yet be handled */
-	if (pmd_large(*pmd))
+	/* Are we allowed to use huge pages? */
+	if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m)
 		return -EFAULT;
 	/* Link gmap segment table entry location to page table. */
 	rc = radix_tree_preload(GFP_KERNEL);
@@ -596,10 +602,22 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	if (*table == _SEGMENT_ENTRY_EMPTY) {
 		rc = radix_tree_insert(&gmap->host_to_guest,
 				       vmaddr >> PMD_SHIFT, table);
-		if (!rc)
-			*table = pmd_val(*pmd);
-	} else
-		rc = 0;
+		if (!rc) {
+			if (pmd_large(*pmd)) {
+				*table = (pmd_val(*pmd) &
+					  _SEGMENT_ENTRY_HARDWARE_BITS_LARGE)
+					| _SEGMENT_ENTRY_GMAP_UC;
+			} else
+				*table = pmd_val(*pmd) &
+					_SEGMENT_ENTRY_HARDWARE_BITS;
+		}
+	} else if (*table & _SEGMENT_ENTRY_PROTECT &&
+		   !(pmd_val(*pmd) & _SEGMENT_ENTRY_PROTECT)) {
+		unprot = (u64)*table;
+		unprot &= ~_SEGMENT_ENTRY_PROTECT;
+		unprot |= _SEGMENT_ENTRY_GMAP_UC;
+		gmap_pmdp_xchg(gmap, (pmd_t *)table, __pmd(unprot), gaddr);
+	}
 	spin_unlock(&gmap->guest_table_lock);
 	spin_unlock(ptl);
 	radix_tree_preload_end();
@@ -690,6 +708,12 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
 		vmaddr |= gaddr & ~PMD_MASK;
 		/* Find vma in the parent mm */
 		vma = find_vma(gmap->mm, vmaddr);
+		/*
+		 * We do not discard pages that are backed by
+		 * hugetlbfs, so we don't have to refault them.
+		 */
+		if (vma && is_vm_hugetlb_page(vma))
+			continue;
 		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
 		zap_page_range(vma, vmaddr, size);
 	}
@@ -864,7 +888,128 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
  */
 static void gmap_pte_op_end(spinlock_t *ptl)
 {
-	spin_unlock(ptl);
+	if (ptl)
+		spin_unlock(ptl);
+}
+
+/**
+ * gmap_pmd_op_walk - walk the gmap tables, get the guest table lock
+ *		      and return the pmd pointer
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ *
+ * Returns a pointer to the pmd for a guest address, or NULL
+ */
+static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr)
+{
+	pmd_t *pmdp;
+
+	BUG_ON(gmap_is_shadow(gmap));
+	spin_lock(&gmap->guest_table_lock);
+	pmdp = (pmd_t *) gmap_table_walk(gmap, gaddr, 1);
+
+	if (!pmdp || pmd_none(*pmdp)) {
+		spin_unlock(&gmap->guest_table_lock);
+		return NULL;
+	}
+
+	/* 4k page table entries are locked via the pte (pte_alloc_map_lock). */
+	if (!pmd_large(*pmdp))
+		spin_unlock(&gmap->guest_table_lock);
+	return pmdp;
+}
+
+/**
+ * gmap_pmd_op_end - release the guest_table_lock if needed
+ * @gmap: pointer to the guest mapping meta data structure
+ * @pmdp: pointer to the pmd
+ */
+static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp)
+{
+	if (pmd_large(*pmdp))
+		spin_unlock(&gmap->guest_table_lock);
+}
+
+/*
+ * gmap_protect_pmd - remove access rights to memory and set pmd notification bits
+ * @pmdp: pointer to the pmd to be protected
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: notification bits to set
+ *
+ * Returns:
+ * 0 if successfully protected
+ * -EAGAIN if a fixup is needed
+ * -EINVAL if unsupported notifier bits have been specified
+ *
+ * Expected to be called with sg->mm->mmap_sem in read and
+ * guest_table_lock held.
+ */
+static int gmap_protect_pmd(struct gmap *gmap, unsigned long gaddr,
+			    pmd_t *pmdp, int prot, unsigned long bits)
+{
+	int pmd_i = pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID;
+	int pmd_p = pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT;
+	pmd_t new = *pmdp;
+
+	/* Fixup needed */
+	if ((pmd_i && (prot != PROT_NONE)) || (pmd_p && (prot == PROT_WRITE)))
+		return -EAGAIN;
+
+	if (prot == PROT_NONE && !pmd_i) {
+		pmd_val(new) |= _SEGMENT_ENTRY_INVALID;
+		gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
+	}
+
+	if (prot == PROT_READ && !pmd_p) {
+		pmd_val(new) &= ~_SEGMENT_ENTRY_INVALID;
+		pmd_val(new) |= _SEGMENT_ENTRY_PROTECT;
+		gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
+	}
+
+	if (bits & GMAP_NOTIFY_MPROT)
+		pmd_val(*pmdp) |= _SEGMENT_ENTRY_GMAP_IN;
+
+	/* Shadow GMAP protection needs split PMDs */
+	if (bits & GMAP_NOTIFY_SHADOW)
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * gmap_protect_pte - remove access rights to memory and set pgste bits
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @pmdp: pointer to the pmd associated with the pte
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: notification bits to set
+ *
+ * Returns 0 if successfully protected, -ENOMEM if out of memory and
+ * -EAGAIN if a fixup is needed.
+ *
+ * Expected to be called with sg->mm->mmap_sem in read
+ */
+static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
+			    pmd_t *pmdp, int prot, unsigned long bits)
+{
+	int rc;
+	pte_t *ptep;
+	spinlock_t *ptl = NULL;
+	unsigned long pbits = 0;
+
+	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+		return -EAGAIN;
+
+	ptep = pte_alloc_map_lock(gmap->mm, pmdp, gaddr, &ptl);
+	if (!ptep)
+		return -ENOMEM;
+
+	pbits |= (bits & GMAP_NOTIFY_MPROT) ? PGSTE_IN_BIT : 0;
+	pbits |= (bits & GMAP_NOTIFY_SHADOW) ? PGSTE_VSIE_BIT : 0;
+	/* Protect and unlock. */
+	rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, pbits);
+	gmap_pte_op_end(ptl);
+	return rc;
 }
 
 /*
@@ -883,30 +1028,45 @@ static void gmap_pte_op_end(spinlock_t *ptl)
 static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
 			      unsigned long len, int prot, unsigned long bits)
 {
-	unsigned long vmaddr;
-	spinlock_t *ptl;
-	pte_t *ptep;
+	unsigned long vmaddr, dist;
+	pmd_t *pmdp;
 	int rc;
 
 	BUG_ON(gmap_is_shadow(gmap));
 	while (len) {
 		rc = -EAGAIN;
-		ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
-		if (ptep) {
-			rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, bits);
-			gmap_pte_op_end(ptl);
+		pmdp = gmap_pmd_op_walk(gmap, gaddr);
+		if (pmdp) {
+			if (!pmd_large(*pmdp)) {
+				rc = gmap_protect_pte(gmap, gaddr, pmdp, prot,
+						      bits);
+				if (!rc) {
+					len -= PAGE_SIZE;
+					gaddr += PAGE_SIZE;
+				}
+			} else {
+				rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot,
+						      bits);
+				if (!rc) {
+					dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK);
+					len = len < dist ? 0 : len - dist;
+					gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE;
+				}
+			}
+			gmap_pmd_op_end(gmap, pmdp);
 		}
 		if (rc) {
+			if (rc == -EINVAL)
+				return rc;
+
+			/* -EAGAIN, fixup of userspace mm and gmap */
 			vmaddr = __gmap_translate(gmap, gaddr);
 			if (IS_ERR_VALUE(vmaddr))
 				return vmaddr;
 			rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot);
 			if (rc)
 				return rc;
-			continue;
 		}
-		gaddr += PAGE_SIZE;
-		len -= PAGE_SIZE;
 	}
 	return 0;
 }
@@ -935,7 +1095,7 @@ int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr,
 	if (!MACHINE_HAS_ESOP && prot == PROT_READ)
 		return -EINVAL;
 	down_read(&gmap->mm->mmap_sem);
-	rc = gmap_protect_range(gmap, gaddr, len, prot, PGSTE_IN_BIT);
+	rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT);
 	up_read(&gmap->mm->mmap_sem);
 	return rc;
 }
@@ -1474,6 +1634,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
 	unsigned long limit;
 	int rc;
 
+	BUG_ON(parent->mm->context.allow_gmap_hpage_1m);
 	BUG_ON(gmap_is_shadow(parent));
 	spin_lock(&parent->shadow_lock);
 	sg = gmap_find_shadow(parent, asce, edat_level);
@@ -1526,7 +1687,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
 	down_read(&parent->mm->mmap_sem);
 	rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN,
 				((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE,
-				PROT_READ, PGSTE_VSIE_BIT);
+				PROT_READ, GMAP_NOTIFY_SHADOW);
 	up_read(&parent->mm->mmap_sem);
 	spin_lock(&parent->shadow_lock);
 	new->initialized = true;
@@ -2092,6 +2253,225 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
 }
 EXPORT_SYMBOL_GPL(ptep_notify);
 
+static void pmdp_notify_gmap(struct gmap *gmap, pmd_t *pmdp,
+			     unsigned long gaddr)
+{
+	pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_IN;
+	gmap_call_notifier(gmap, gaddr, gaddr + HPAGE_SIZE - 1);
+}
+
+/**
+ * gmap_pmdp_xchg - exchange a gmap pmd with another
+ * @gmap: pointer to the guest address space structure
+ * @pmdp: pointer to the pmd entry
+ * @new: replacement entry
+ * @gaddr: the affected guest address
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *pmdp, pmd_t new,
+			   unsigned long gaddr)
+{
+	gaddr &= HPAGE_MASK;
+	pmdp_notify_gmap(gmap, pmdp, gaddr);
+	pmd_val(new) &= ~_SEGMENT_ENTRY_GMAP_IN;
+	if (MACHINE_HAS_TLB_GUEST)
+		__pmdp_idte(gaddr, (pmd_t *)pmdp, IDTE_GUEST_ASCE, gmap->asce,
+			    IDTE_GLOBAL);
+	else if (MACHINE_HAS_IDTE)
+		__pmdp_idte(gaddr, (pmd_t *)pmdp, 0, 0, IDTE_GLOBAL);
+	else
+		__pmdp_csp(pmdp);
+	*pmdp = new;
+}
+
+static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
+			    int purge)
+{
+	pmd_t *pmdp;
+	struct gmap *gmap;
+	unsigned long gaddr;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		spin_lock(&gmap->guest_table_lock);
+		pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest,
+						  vmaddr >> PMD_SHIFT);
+		if (pmdp) {
+			gaddr = __gmap_segment_gaddr((unsigned long *)pmdp);
+			pmdp_notify_gmap(gmap, pmdp, gaddr);
+			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+						   _SEGMENT_ENTRY_GMAP_UC));
+			if (purge)
+				__pmdp_csp(pmdp);
+			pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
+		}
+		spin_unlock(&gmap->guest_table_lock);
+	}
+	rcu_read_unlock();
+}
+
+/**
+ * gmap_pmdp_invalidate - invalidate all affected guest pmd entries without
+ *                        flushing
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr)
+{
+	gmap_pmdp_clear(mm, vmaddr, 0);
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_invalidate);
+
+/**
+ * gmap_pmdp_csp - csp all affected guest pmd entries
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr)
+{
+	gmap_pmdp_clear(mm, vmaddr, 1);
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_csp);
+
+/**
+ * gmap_pmdp_idte_local - invalidate and clear a guest pmd entry
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
+{
+	unsigned long *entry, gaddr;
+	struct gmap *gmap;
+	pmd_t *pmdp;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		spin_lock(&gmap->guest_table_lock);
+		entry = radix_tree_delete(&gmap->host_to_guest,
+					  vmaddr >> PMD_SHIFT);
+		if (entry) {
+			pmdp = (pmd_t *)entry;
+			gaddr = __gmap_segment_gaddr(entry);
+			pmdp_notify_gmap(gmap, pmdp, gaddr);
+			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+					   _SEGMENT_ENTRY_GMAP_UC));
+			if (MACHINE_HAS_TLB_GUEST)
+				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
+					    gmap->asce, IDTE_LOCAL);
+			else if (MACHINE_HAS_IDTE)
+				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL);
+			*entry = _SEGMENT_ENTRY_EMPTY;
+		}
+		spin_unlock(&gmap->guest_table_lock);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local);
+
+/**
+ * gmap_pmdp_idte_global - invalidate and clear a guest pmd entry
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
+{
+	unsigned long *entry, gaddr;
+	struct gmap *gmap;
+	pmd_t *pmdp;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		spin_lock(&gmap->guest_table_lock);
+		entry = radix_tree_delete(&gmap->host_to_guest,
+					  vmaddr >> PMD_SHIFT);
+		if (entry) {
+			pmdp = (pmd_t *)entry;
+			gaddr = __gmap_segment_gaddr(entry);
+			pmdp_notify_gmap(gmap, pmdp, gaddr);
+			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+					   _SEGMENT_ENTRY_GMAP_UC));
+			if (MACHINE_HAS_TLB_GUEST)
+				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
+					    gmap->asce, IDTE_GLOBAL);
+			else if (MACHINE_HAS_IDTE)
+				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL);
+			else
+				__pmdp_csp(pmdp);
+			*entry = _SEGMENT_ENTRY_EMPTY;
+		}
+		spin_unlock(&gmap->guest_table_lock);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global);
+
+/**
+ * gmap_test_and_clear_dirty_pmd - test and reset segment dirty status
+ * @gmap: pointer to guest address space
+ * @pmdp: pointer to the pmd to be tested
+ * @gaddr: virtual address in the guest address space
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp,
+				   unsigned long gaddr)
+{
+	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+		return false;
+
+	/* Already protected memory, which did not change is clean */
+	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT &&
+	    !(pmd_val(*pmdp) & _SEGMENT_ENTRY_GMAP_UC))
+		return false;
+
+	/* Clear UC indication and reset protection */
+	pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_UC;
+	gmap_protect_pmd(gmap, gaddr, pmdp, PROT_READ, 0);
+	return true;
+}
+
+/**
+ * gmap_sync_dirty_log_pmd - set bitmap based on dirty status of segment
+ * @gmap: pointer to guest address space
+ * @bitmap: dirty bitmap for this pmd
+ * @gaddr: virtual address in the guest address space
+ * @vmaddr: virtual address in the host address space
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4],
+			     unsigned long gaddr, unsigned long vmaddr)
+{
+	int i;
+	pmd_t *pmdp;
+	pte_t *ptep;
+	spinlock_t *ptl;
+
+	pmdp = gmap_pmd_op_walk(gmap, gaddr);
+	if (!pmdp)
+		return;
+
+	if (pmd_large(*pmdp)) {
+		if (gmap_test_and_clear_dirty_pmd(gmap, pmdp, gaddr))
+			bitmap_fill(bitmap, _PAGE_ENTRIES);
+	} else {
+		for (i = 0; i < _PAGE_ENTRIES; i++, vmaddr += PAGE_SIZE) {
+			ptep = pte_alloc_map_lock(gmap->mm, pmdp, vmaddr, &ptl);
+			if (!ptep)
+				continue;
+			if (ptep_test_and_clear_uc(gmap->mm, vmaddr, ptep))
+				set_bit(i, bitmap);
+			spin_unlock(ptl);
+		}
+	}
+	gmap_pmd_op_end(gmap, pmdp);
+}
+EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd);
+
 static inline void thp_split_mm(struct mm_struct *mm)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -2168,17 +2548,45 @@ EXPORT_SYMBOL_GPL(s390_enable_sie);
  * Enable storage key handling from now on and initialize the storage
  * keys with the default key.
  */
-static int __s390_enable_skey(pte_t *pte, unsigned long addr,
-			      unsigned long next, struct mm_walk *walk)
+static int __s390_enable_skey_pte(pte_t *pte, unsigned long addr,
+				  unsigned long next, struct mm_walk *walk)
 {
 	/* Clear storage key */
 	ptep_zap_key(walk->mm, addr, pte);
 	return 0;
 }
 
+static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
+				      unsigned long hmask, unsigned long next,
+				      struct mm_walk *walk)
+{
+	pmd_t *pmd = (pmd_t *)pte;
+	unsigned long start, end;
+	struct page *page = pmd_page(*pmd);
+
+	/*
+	 * The write check makes sure we do not set a key on shared
+	 * memory. This is needed as the walker does not differentiate
+	 * between actual guest memory and the process executable or
+	 * shared libraries.
+	 */
+	if (pmd_val(*pmd) & _SEGMENT_ENTRY_INVALID ||
+	    !(pmd_val(*pmd) & _SEGMENT_ENTRY_WRITE))
+		return 0;
+
+	start = pmd_val(*pmd) & HPAGE_MASK;
+	end = start + HPAGE_SIZE - 1;
+	__storage_key_init_range(start, end);
+	set_bit(PG_arch_1, &page->flags);
+	return 0;
+}
+
 int s390_enable_skey(void)
 {
-	struct mm_walk walk = { .pte_entry = __s390_enable_skey };
+	struct mm_walk walk = {
+		.hugetlb_entry = __s390_enable_skey_hugetlb,
+		.pte_entry = __s390_enable_skey_pte,
+	};
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	int rc = 0;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index e804090f4470..b0246c705a19 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -123,6 +123,29 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 	return pte;
 }
 
+static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
+{
+	struct page *page;
+	unsigned long size, paddr;
+
+	if (!mm_uses_skeys(mm) ||
+	    rste & _SEGMENT_ENTRY_INVALID)
+		return;
+
+	if ((rste & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) {
+		page = pud_page(__pud(rste));
+		size = PUD_SIZE;
+		paddr = rste & PUD_MASK;
+	} else {
+		page = pmd_page(__pmd(rste));
+		size = PMD_SIZE;
+		paddr = rste & PMD_MASK;
+	}
+
+	if (!test_and_set_bit(PG_arch_1, &page->flags))
+		__storage_key_init_range(paddr, paddr + size - 1);
+}
+
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte)
 {
@@ -137,6 +160,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE;
 	else
 		rste |= _SEGMENT_ENTRY_LARGE;
+	clear_huge_pte_skeys(mm, rste);
 	pte_val(*ptep) = rste;
 }
 
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index 382153ff17e3..dc3cede7f2ec 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -271,7 +271,7 @@ void arch_set_page_states(int make_stable)
 			list_for_each(l, &zone->free_area[order].free_list[t]) {
 				page = list_entry(l, struct page, lru);
 				if (make_stable)
-					set_page_stable_dat(page, 0);
+					set_page_stable_dat(page, order);
 				else
 					set_page_unused(page, order);
 			}
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index c44171588d08..f8c6faab41f4 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -14,7 +14,7 @@
 
 static inline unsigned long sske_frame(unsigned long addr, unsigned char skey)
 {
-	asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0"
+	asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],1,0"
 		     : [addr] "+a" (addr) : [skey] "d" (skey));
 	return addr;
 }
@@ -23,8 +23,6 @@ void __storage_key_init_range(unsigned long start, unsigned long end)
 {
 	unsigned long boundary, size;
 
-	if (!PAGE_DEFAULT_KEY)
-		return;
 	while (start < end) {
 		if (MACHINE_HAS_EDAT1) {
 			/* set storage keys for a 1MB frame */
@@ -37,7 +35,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end)
 				continue;
 			}
 		}
-		page_set_storage_key(start, PAGE_DEFAULT_KEY, 0);
+		page_set_storage_key(start, PAGE_DEFAULT_KEY, 1);
 		start += PAGE_SIZE;
 	}
 }
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index e3bd5627afef..76d89ee8b428 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -28,7 +28,7 @@ static struct ctl_table page_table_sysctl[] = {
 		.data		= &page_table_allocate_pgste,
 		.maxlen		= sizeof(int),
 		.mode		= S_IRUGO | S_IWUSR,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &page_table_allocate_pgste_min,
 		.extra2		= &page_table_allocate_pgste_max,
 	},
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 301e466e4263..f2cc7da473e4 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -347,18 +347,27 @@ static inline void pmdp_idte_local(struct mm_struct *mm,
 			    mm->context.asce, IDTE_LOCAL);
 	else
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_LOCAL);
+	if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+		gmap_pmdp_idte_local(mm, addr);
 }
 
 static inline void pmdp_idte_global(struct mm_struct *mm,
 				    unsigned long addr, pmd_t *pmdp)
 {
-	if (MACHINE_HAS_TLB_GUEST)
+	if (MACHINE_HAS_TLB_GUEST) {
 		__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
 			    mm->context.asce, IDTE_GLOBAL);
-	else if (MACHINE_HAS_IDTE)
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+			gmap_pmdp_idte_global(mm, addr);
+	} else if (MACHINE_HAS_IDTE) {
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL);
-	else
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+			gmap_pmdp_idte_global(mm, addr);
+	} else {
 		__pmdp_csp(pmdp);
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
+			gmap_pmdp_csp(mm, addr);
+	}
 }
 
 static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
@@ -392,6 +401,8 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 			  cpumask_of(smp_processor_id()))) {
 		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
 		mm->context.flush_mm = 1;
+		if (mm_has_pgste(mm))
+			gmap_pmdp_invalidate(mm, addr);
 	} else {
 		pmdp_idte_global(mm, addr, pmdp);
 	}
@@ -399,6 +410,24 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 	return old;
 }
 
+static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+	pmd = pmd_alloc(mm, pud, addr);
+	return pmd;
+}
+
 pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t new)
 {
@@ -693,40 +722,14 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 /*
  * Test and reset if a guest page is dirty
  */
-bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
+bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long addr,
+		       pte_t *ptep)
 {
-	spinlock_t *ptl;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
 	pgste_t pgste;
-	pte_t *ptep;
 	pte_t pte;
 	bool dirty;
 	int nodat;
 
-	pgd = pgd_offset(mm, addr);
-	p4d = p4d_alloc(mm, pgd, addr);
-	if (!p4d)
-		return false;
-	pud = pud_alloc(mm, p4d, addr);
-	if (!pud)
-		return false;
-	pmd = pmd_alloc(mm, pud, addr);
-	if (!pmd)
-		return false;
-	/* We can't run guests backed by huge pages, but userspace can
-	 * still set them up and then try to migrate them without any
-	 * migration support.
-	 */
-	if (pmd_large(*pmd))
-		return true;
-
-	ptep = pte_alloc_map_lock(mm, pmd, addr, &ptl);
-	if (unlikely(!ptep))
-		return false;
-
 	pgste = pgste_get_lock(ptep);
 	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
 	pgste_val(pgste) &= ~PGSTE_UC_BIT;
@@ -742,21 +745,43 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
 		*ptep = pte;
 	}
 	pgste_set_unlock(ptep, pgste);
-
-	spin_unlock(ptl);
 	return dirty;
 }
-EXPORT_SYMBOL_GPL(test_and_clear_guest_dirty);
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_uc);
 
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq)
 {
-	unsigned long keyul;
+	unsigned long keyul, paddr;
 	spinlock_t *ptl;
 	pgste_t old, new;
+	pmd_t *pmdp;
 	pte_t *ptep;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pmdp = pmd_alloc_map(mm, addr);
+	if (unlikely(!pmdp))
+		return -EFAULT;
+
+	ptl = pmd_lock(mm, pmdp);
+	if (!pmd_present(*pmdp)) {
+		spin_unlock(ptl);
+		return -EFAULT;
+	}
+
+	if (pmd_large(*pmdp)) {
+		paddr = pmd_val(*pmdp) & HPAGE_MASK;
+		paddr |= addr & ~HPAGE_MASK;
+		/*
+		 * Huge pmds need quiescing operations, they are
+		 * always mapped.
+		 */
+		page_set_storage_key(paddr, key, 1);
+		spin_unlock(ptl);
+		return 0;
+	}
+	spin_unlock(ptl);
+
+	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
 
@@ -767,14 +792,14 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	pgste_val(new) |= (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
 	pgste_val(new) |= (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-		unsigned long address, bits, skey;
+		unsigned long bits, skey;
 
-		address = pte_val(*ptep) & PAGE_MASK;
-		skey = (unsigned long) page_get_storage_key(address);
+		paddr = pte_val(*ptep) & PAGE_MASK;
+		skey = (unsigned long) page_get_storage_key(paddr);
 		bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
 		skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT);
 		/* Set storage key ACC and FP */
-		page_set_storage_key(address, skey, !nq);
+		page_set_storage_key(paddr, skey, !nq);
 		/* Merge host changed & referenced into pgste  */
 		pgste_val(new) |= bits << 52;
 	}
@@ -830,11 +855,32 @@ EXPORT_SYMBOL(cond_set_guest_storage_key);
 int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 {
 	spinlock_t *ptl;
+	unsigned long paddr;
 	pgste_t old, new;
+	pmd_t *pmdp;
 	pte_t *ptep;
 	int cc = 0;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pmdp = pmd_alloc_map(mm, addr);
+	if (unlikely(!pmdp))
+		return -EFAULT;
+
+	ptl = pmd_lock(mm, pmdp);
+	if (!pmd_present(*pmdp)) {
+		spin_unlock(ptl);
+		return -EFAULT;
+	}
+
+	if (pmd_large(*pmdp)) {
+		paddr = pmd_val(*pmdp) & HPAGE_MASK;
+		paddr |= addr & ~HPAGE_MASK;
+		cc = page_reset_referenced(paddr);
+		spin_unlock(ptl);
+		return cc;
+	}
+	spin_unlock(ptl);
+
+	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
 
@@ -843,7 +889,8 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	pgste_val(new) &= ~PGSTE_GR_BIT;
 
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-		cc = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
+		paddr = pte_val(*ptep) & PAGE_MASK;
+		cc = page_reset_referenced(paddr);
 		/* Merge real referenced bit into host-set */
 		pgste_val(new) |= ((unsigned long) cc << 53) & PGSTE_HR_BIT;
 	}
@@ -862,18 +909,42 @@ EXPORT_SYMBOL(reset_guest_reference_bit);
 int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char *key)
 {
+	unsigned long paddr;
 	spinlock_t *ptl;
 	pgste_t pgste;
+	pmd_t *pmdp;
 	pte_t *ptep;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pmdp = pmd_alloc_map(mm, addr);
+	if (unlikely(!pmdp))
+		return -EFAULT;
+
+	ptl = pmd_lock(mm, pmdp);
+	if (!pmd_present(*pmdp)) {
+		/* Not yet mapped memory has a zero key */
+		spin_unlock(ptl);
+		*key = 0;
+		return 0;
+	}
+
+	if (pmd_large(*pmdp)) {
+		paddr = pmd_val(*pmdp) & HPAGE_MASK;
+		paddr |= addr & ~HPAGE_MASK;
+		*key = page_get_storage_key(paddr);
+		spin_unlock(ptl);
+		return 0;
+	}
+	spin_unlock(ptl);
+
+	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
 
 	pgste = pgste_get_lock(ptep);
 	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+	paddr = pte_val(*ptep) & PAGE_MASK;
 	if (!(pte_val(*ptep) & _PAGE_INVALID))
-		*key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);
+		*key = page_get_storage_key(paddr);
 	/* Reflect guest's logical view, not physical */
 	*key |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
 	pgste_set_unlock(ptep, pgste);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 5f0234ec8038..d7052cbe984f 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -485,8 +485,6 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 			/* br %r1 */
 			_EMIT2(0x07f1);
 		} else {
-			/* larl %r1,.+14 */
-			EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
 			/* ex 0,S390_lowcore.br_r1_tampoline */
 			EMIT4_DISP(0x44000000, REG_0, REG_0,
 				   offsetof(struct lowcore, br_r1_trampoline));
diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index 06a80434cfe6..5bd374491f94 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -134,6 +134,8 @@ void __init numa_setup(void)
 {
 	pr_info("NUMA mode: %s\n", mode->name);
 	nodes_clear(node_possible_map);
+	/* Initially attach all possible CPUs to node 0. */
+	cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
 	if (mode->setup)
 		mode->setup();
 	numa_setup_memory();
@@ -141,20 +143,6 @@ void __init numa_setup(void)
 }
 
 /*
- * numa_init_early() - Initialization initcall
- *
- * This runs when only one CPU is online and before the first
- * topology update is called for by the scheduler.
- */
-static int __init numa_init_early(void)
-{
-	/* Attach all possible CPUs to node 0 for now. */
-	cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
-	return 0;
-}
-early_initcall(numa_init_early);
-
-/*
  * numa_init_late() - Initialization initcall
  *
  * Register NUMA nodes.
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index b482e95b6249..57f7cdac70a3 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -48,6 +48,10 @@ static char *pci_fmt2_names[] = {
 	"Maximum work units",
 };
 
+static char *pci_fmt3_names[] = {
+	"Transmitted bytes",
+};
+
 static char *pci_sw_names[] = {
 	"Allocated pages",
 	"Mapped pages",
@@ -112,6 +116,10 @@ static int pci_perf_show(struct seq_file *m, void *v)
 		pci_fmb_show(m, pci_fmt2_names, ARRAY_SIZE(pci_fmt2_names),
 			     &zdev->fmb->fmt2.consumed_work_units);
 		break;
+	case 3:
+		pci_fmb_show(m, pci_fmt3_names, ARRAY_SIZE(pci_fmt3_names),
+			     &zdev->fmb->fmt3.tx_bytes);
+		break;
 	default:
 		seq_puts(m, "Unknown format\n");
 	}
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index 1ace023cbdce..8d61218a71aa 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -7,13 +7,13 @@ purgatory-y := head.o purgatory.o string.o sha256.o mem.o
 targets += $(purgatory-y) purgatory.ro kexec-purgatory.c
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 
-$(obj)/sha256.o: $(srctree)/lib/sha256.c
+$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S
+$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
 
-$(obj)/string.o: $(srctree)/arch/s390/lib/string.c
+$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib
@@ -21,8 +21,9 @@ LDFLAGS_purgatory.ro += -z nodefaultlib
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
-KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float
+KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
+KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S
index 660c96a05a9b..2e3707b12edd 100644
--- a/arch/s390/purgatory/head.S
+++ b/arch/s390/purgatory/head.S
@@ -243,33 +243,26 @@ gprregs:
 	.quad	0
 	.endr
 
-purgatory_sha256_digest:
-	.global purgatory_sha256_digest
-	.rept	32	/* SHA256_DIGEST_SIZE */
-	.byte	0
-	.endr
-
-purgatory_sha_regions:
-	.global purgatory_sha_regions
-	.rept	16 * __KEXEC_SHA_REGION_SIZE	/* KEXEC_SEGMENTS_MAX */
-	.byte	0
-	.endr
-
-kernel_entry:
-	.global kernel_entry
-	.quad	0
-
-kernel_type:
-	.global kernel_type
-	.quad	0
-
-crash_start:
-	.global crash_start
-	.quad	0
+/* Macro to define a global variable with name and size (in bytes) to be
+ * shared with C code.
+ *
+ * Add the .size and .type attribute to satisfy checks on the Elf_Sym during
+ * purgatory load.
+ */
+.macro GLOBAL_VARIABLE name,size
+\name:
+	.global \name
+	.size	\name,\size
+	.type	\name,object
+	.skip	\size,0
+.endm
 
-crash_size:
-	.global crash_size
-	.quad	0
+GLOBAL_VARIABLE purgatory_sha256_digest,32
+GLOBAL_VARIABLE purgatory_sha_regions,16*__KEXEC_SHA_REGION_SIZE
+GLOBAL_VARIABLE kernel_entry,8
+GLOBAL_VARIABLE kernel_type,8
+GLOBAL_VARIABLE crash_start,8
+GLOBAL_VARIABLE crash_size,8
 
 	.align	PAGE_SIZE
 stack:
diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c
index 4e2beb3c29b7..3528e6da4e87 100644
--- a/arch/s390/purgatory/purgatory.c
+++ b/arch/s390/purgatory/purgatory.c
@@ -12,15 +12,6 @@
 #include <linux/string.h>
 #include <asm/purgatory.h>
 
-struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX];
-u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE];
-
-u64 kernel_entry;
-u64 kernel_type;
-
-u64 crash_start;
-u64 crash_size;
-
 int verify_sha256_digest(void)
 {
 	struct kexec_sha_region *ptr, *end;
diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss
index d92f2d94a5d9..9bba2c14e0ca 100644
--- a/arch/s390/scripts/Makefile.chkbss
+++ b/arch/s390/scripts/Makefile.chkbss
@@ -2,13 +2,22 @@
 
 quiet_cmd_chkbss = CHKBSS  $<
 define cmd_chkbss
+	rm -f $@; \
 	if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
 		echo "error: $< .bss section is not empty" >&2; exit 1; \
 	fi; \
 	touch $@;
 endef
 
-$(obj)/built-in.a: $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+chkbss-target ?= $(obj)/built-in.a
+ifneq (,$(findstring /,$(chkbss)))
+chkbss-files := $(patsubst %, %.chkbss, $(chkbss))
+else
+chkbss-files := $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+endif
+
+$(chkbss-target): $(chkbss-files)
+targets += $(notdir $(chkbss-files))
 
 %.o.chkbss: %.o
 	$(call cmd,chkbss)
diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c
index 259aa0680d1a..a1bc02b29c81 100644
--- a/arch/s390/tools/gen_opcode_table.c
+++ b/arch/s390/tools/gen_opcode_table.c
@@ -257,7 +257,7 @@ static void add_to_group(struct gen_opcode *desc, struct insn *insn, int offset)
 	if (!desc->group)
 		exit(EXIT_FAILURE);
 	group = &desc->group[desc->nr_groups - 1];
-	strncpy(group->opcode, insn->opcode, 2);
+	memcpy(group->opcode, insn->opcode, 2);
 	group->type = insn->type;
 	group->offset = offset;
 	group->count = 1;
@@ -283,7 +283,7 @@ static void print_opcode_table(struct gen_opcode *desc)
 			continue;
 		add_to_group(desc, insn, offset);
 		if (strncmp(opcode, insn->opcode, 2)) {
-			strncpy(opcode, insn->opcode, 2);
+			memcpy(opcode, insn->opcode, 2);
 			printf("\t/* %.2s */ \\\n", opcode);
 		}
 		print_opcode(insn, offset);
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index dd4f3d3e644f..da4db4b5359f 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -51,7 +51,6 @@ config SUPERH
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_NMI
-	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
 
 	help
@@ -159,10 +158,13 @@ config SWAP_IO_SPACE
 	bool
 
 config DMA_COHERENT
+	select DMA_DIRECT_OPS
 	bool
 
 config DMA_NONCOHERENT
 	def_bool !DMA_COHERENT
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_NONCOHERENT_OPS
 
 config PGTABLE_LEVELS
 	default 3 if X2TLB
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 46dd82ab2c29..6a5609a55965 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -2,6 +2,7 @@ generic-y += compat.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += irq_regs.h
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index 0fd0099f43cc..f37b95a80232 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -32,44 +32,9 @@
 #include <asm/atomic-irq.h>
 #endif
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
-
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
-
 #define atomic_xchg(v, new)		(xchg(&((v)->counter), new))
 #define atomic_cmpxchg(v, o, n)		(cmpxchg(&((v)->counter), (o), (n)))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-
-	return c;
-}
-
 #endif /* CONFIG_CPU_J2 */
 
 #endif /* __ASM_SH_ATOMIC_H */
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index d103ab5a4e4b..b932e42ef028 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -101,5 +101,12 @@ void kunmap_coherent(void *kvaddr);
 
 void cpu_cache_init(void);
 
+static inline void *sh_cacheop_vaddr(void *vaddr)
+{
+	if (__in_29bit_mode())
+		vaddr = (void *)CAC_ADDR((unsigned long)vaddr);
+	return vaddr;
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_CACHEFLUSH_H */
diff --git a/arch/sh/include/asm/cmpxchg-xchg.h b/arch/sh/include/asm/cmpxchg-xchg.h
index 1e881f5db659..593a9704782b 100644
--- a/arch/sh/include/asm/cmpxchg-xchg.h
+++ b/arch/sh/include/asm/cmpxchg-xchg.h
@@ -8,7 +8,8 @@
  * This work is licensed under the terms of the GNU GPL, version 2.  See the
  * file "COPYING" in the main directory of this archive for more details.
  */
-#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/compiler.h>
 #include <asm/byteorder.h>
 
 /*
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
deleted file mode 100644
index 41167931e5d9..000000000000
--- a/arch/sh/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_SH_DMA_MAPPING_H
-#define __ASM_SH_DMA_MAPPING_H
-
-extern const struct dma_map_ops *dma_ops;
-extern void no_iommu_init(void);
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return dma_ops;
-}
-
-extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_addr, gfp_t flag,
-					unsigned long attrs);
-extern void dma_generic_free_coherent(struct device *dev, size_t size,
-				      void *vaddr, dma_addr_t dma_handle,
-				      unsigned long attrs);
-
-void sh_sync_dma_for_device(void *vaddr, size_t size,
-	    enum dma_data_direction dir);
-
-#endif /* __ASM_SH_DMA_MAPPING_H */
diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
index 7431c172c0cb..199d17b765f2 100644
--- a/arch/sh/include/asm/hw_breakpoint.h
+++ b/arch/sh/include/asm/hw_breakpoint.h
@@ -10,7 +10,6 @@
 #include <linux/types.h>
 
 struct arch_hw_breakpoint {
-	char		*name; /* Contains name of the symbol to set bkpt */
 	unsigned long	address;
 	u16		len;
 	u16		type;
@@ -41,6 +40,7 @@ struct sh_ubc {
 	struct clk	*clk;	/* optional interface clock / MSTP bit */
 };
 
+struct perf_event_attr;
 struct perf_event;
 struct task_struct;
 struct pmu;
@@ -54,8 +54,10 @@ static inline int hw_breakpoint_slots(int type)
 }
 
 /* arch/sh/kernel/hw_breakpoint.c */
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h
index 85d8bcaa8493..6171682f7798 100644
--- a/arch/sh/include/asm/kprobes.h
+++ b/arch/sh/include/asm/kprobes.h
@@ -27,7 +27,6 @@ struct kprobe;
 
 void arch_remove_kprobe(struct kprobe *);
 void kretprobe_trampoline(void);
-void jprobe_return_end(void);
 
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
@@ -43,9 +42,6 @@ struct prev_kprobe {
 /* per-cpu kprobe control block */
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
-	unsigned long jprobe_saved_r15;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index dc80041f7363..59673f8a3379 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -12,7 +12,7 @@ endif
 
 CFLAGS_REMOVE_return_address.o = -pg
 
-obj-y	:= debugtraps.o dma-nommu.o dumpstack.o 		\
+obj-y	:= debugtraps.o dumpstack.o 		\
 	   idle.o io.o irq.o irq_$(BITS).o kdebugfs.o			\
 	   machvec.o nmi_debug.o process.o				\
 	   process_$(BITS).o ptrace.o ptrace_$(BITS).o			\
@@ -45,7 +45,7 @@ obj-$(CONFIG_DUMP_CODE)		+= disassemble.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o
 obj-$(CONFIG_DWARF_UNWINDER)	+= dwarf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_callchain.o
-
+obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-coherent.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)		+= hw_breakpoint.o
 
 ccflags-y := -Werror
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
new file mode 100644
index 000000000000..a0021eef956b
--- /dev/null
+++ b/arch/sh/kernel/dma-coherent.c
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2004 - 2007  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/module.h>
+#include <asm/cacheflush.h>
+#include <asm/addrspace.h>
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
+{
+	void *ret, *ret_nocache;
+	int order = get_order(size);
+
+	gfp |= __GFP_ZERO;
+
+	ret = (void *)__get_free_pages(gfp, order);
+	if (!ret)
+		return NULL;
+
+	/*
+	 * Pages from the page allocator may have data present in
+	 * cache. So flush the cache before using uncached memory.
+	 */
+	arch_sync_dma_for_device(dev, virt_to_phys(ret), size,
+			DMA_BIDIRECTIONAL);
+
+	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
+	if (!ret_nocache) {
+		free_pages((unsigned long)ret, order);
+		return NULL;
+	}
+
+	split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
+
+	*dma_handle = virt_to_phys(ret);
+	if (!WARN_ON(!dev))
+		*dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
+
+	return ret_nocache;
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	int order = get_order(size);
+	unsigned long pfn = (dma_handle >> PAGE_SHIFT);
+	int k;
+
+	if (!WARN_ON(!dev))
+		pfn += dev->dma_pfn_offset;
+
+	for (k = 0; k < (1 << order); k++)
+		__free_pages(pfn_to_page(pfn + k), 0);
+
+	iounmap(vaddr);
+}
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	void *addr = sh_cacheop_vaddr(phys_to_virt(paddr));
+
+	switch (dir) {
+	case DMA_FROM_DEVICE:		/* invalidate only */
+		__flush_invalidate_region(addr, size);
+		break;
+	case DMA_TO_DEVICE:		/* writeback only */
+		__flush_wback_region(addr, size);
+		break;
+	case DMA_BIDIRECTIONAL:		/* writeback and invalidate */
+		__flush_purge_region(addr, size);
+		break;
+	default:
+		BUG();
+	}
+}
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
deleted file mode 100644
index 3e3a32fc676e..000000000000
--- a/arch/sh/kernel/dma-nommu.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * DMA mapping support for platforms lacking IOMMUs.
- *
- * Copyright (C) 2009  Paul Mundt
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/dma-mapping.h>
-#include <linux/io.h>
-#include <asm/cacheflush.h>
-
-static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction dir,
-				 unsigned long attrs)
-{
-	dma_addr_t addr = page_to_phys(page) + offset
-		- PFN_PHYS(dev->dma_pfn_offset);
-
-	WARN_ON(size == 0);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		sh_sync_dma_for_device(page_address(page) + offset, size, dir);
-
-	return addr;
-}
-
-static int nommu_map_sg(struct device *dev, struct scatterlist *sg,
-			int nents, enum dma_data_direction dir,
-			unsigned long attrs)
-{
-	struct scatterlist *s;
-	int i;
-
-	WARN_ON(nents == 0 || sg[0].length == 0);
-
-	for_each_sg(sg, s, nents, i) {
-		dma_addr_t offset = PFN_PHYS(dev->dma_pfn_offset);
-
-		BUG_ON(!sg_page(s));
-
-		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			sh_sync_dma_for_device(sg_virt(s), s->length, dir);
-
-		s->dma_address = sg_phys(s) - offset;
-		s->dma_length = s->length;
-	}
-
-	return nents;
-}
-
-#ifdef CONFIG_DMA_NONCOHERENT
-static void nommu_sync_single_for_device(struct device *dev, dma_addr_t addr,
-			      size_t size, enum dma_data_direction dir)
-{
-	sh_sync_dma_for_device(phys_to_virt(addr), size, dir);
-}
-
-static void nommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-			  int nelems, enum dma_data_direction dir)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nelems, i)
-		sh_sync_dma_for_device(sg_virt(s), s->length, dir);
-}
-#endif
-
-const struct dma_map_ops nommu_dma_ops = {
-	.alloc			= dma_generic_alloc_coherent,
-	.free			= dma_generic_free_coherent,
-	.map_page		= nommu_map_page,
-	.map_sg			= nommu_map_sg,
-#ifdef CONFIG_DMA_NONCOHERENT
-	.sync_single_for_device	= nommu_sync_single_for_device,
-	.sync_sg_for_device	= nommu_sync_sg_for_device,
-#endif
-};
-
-void __init no_iommu_init(void)
-{
-	if (dma_ops)
-		return;
-	dma_ops = &nommu_dma_ops;
-}
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index 8648ed05ccf0..d9ff3b42da7c 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -124,14 +124,13 @@ static int get_hbp_len(u16 hbp_len)
 /*
  * Check for virtual address in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->len);
+	va = hw->address;
+	len = get_hbp_len(hw->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -174,40 +173,40 @@ int arch_bp_generic_fields(int sh_len, int sh_type,
 	return 0;
 }
 
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->len = SH_BREAKPOINT_LEN_1;
+		hw->len = SH_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->len = SH_BREAKPOINT_LEN_2;
+		hw->len = SH_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->len = SH_BREAKPOINT_LEN_4;
+		hw->len = SH_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->len = SH_BREAKPOINT_LEN_8;
+		hw->len = SH_BREAKPOINT_LEN_8;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_R:
-		info->type = SH_BREAKPOINT_READ;
+		hw->type = SH_BREAKPOINT_READ;
 		break;
 	case HW_BREAKPOINT_W:
-		info->type = SH_BREAKPOINT_WRITE;
+		hw->type = SH_BREAKPOINT_WRITE;
 		break;
 	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
-		info->type = SH_BREAKPOINT_RW;
+		hw->type = SH_BREAKPOINT_RW;
 		break;
 	default:
 		return -EINVAL;
@@ -219,19 +218,20 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
 	int ret;
 
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
 	ret = -EINVAL;
 
-	switch (info->len) {
+	switch (hw->len) {
 	case SH_BREAKPOINT_LEN_1:
 		align = 0;
 		break;
@@ -249,17 +249,10 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	}
 
 	/*
-	 * For kernel-addresses, either the address or symbol name can be
-	 * specified.
-	 */
-	if (info->name)
-		info->address = (unsigned long)kallsyms_lookup_name(info->name);
-
-	/*
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
 	 */
-	if (info->address & align)
+	if (hw->address & align)
 		return -EINVAL;
 
 	return 0;
@@ -346,7 +339,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 		perf_bp_event(bp, args->regs);
 
 		/* Deliver the signal to userspace */
-		if (!arch_check_bp_in_kernelspace(bp)) {
+		if (!arch_check_bp_in_kernelspace(&bp->hw.info)) {
 			force_sig_fault(SIGTRAP, TRAP_HWBKPT,
 					(void __user *)NULL, current);
 		}
diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c
index 52a5e11247d1..241e903dd3ee 100644
--- a/arch/sh/kernel/kprobes.c
+++ b/arch/sh/kernel/kprobes.c
@@ -248,11 +248,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			prepare_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			return 1;
-		} else {
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				goto ss_probe;
-			}
 		}
 		goto no_kprobe;
 	}
@@ -277,11 +272,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 	prepare_singlestep(p, regs);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;
@@ -358,8 +355,6 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->pc = orig_ret_address;
 	kretprobe_hash_unlock(current, &flags);
 
-	preempt_enable_no_resched();
-
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
@@ -508,14 +503,8 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 				if (post_kprobe_handler(args->regs))
 					ret = NOTIFY_STOP;
 			} else {
-				if (kprobe_handler(args->regs)) {
+				if (kprobe_handler(args->regs))
 					ret = NOTIFY_STOP;
-				} else {
-					p = __this_cpu_read(current_kprobe);
-					if (p->break_handler &&
-					    p->break_handler(p, args->regs))
-						ret = NOTIFY_STOP;
-				}
 			}
 		}
 	}
@@ -523,57 +512,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_r15 = regs->regs[15];
-	addr = kcb->jprobe_saved_r15;
-
-	/*
-	 * TBD: As Linus pointed out, gcc assumes that the callee
-	 * owns the argument space and could overwrite it, e.g.
-	 * tailcall optimization. So, to be absolutely safe
-	 * we also save and restore enough stack bytes to cover
-	 * the argument area.
-	 */
-	memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr,
-	       MIN_STACK_SIZE(addr));
-
-	regs->pc = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack_addr = kcb->jprobe_saved_r15;
-	u8 *addr = (u8 *)regs->pc;
-
-	if ((addr >= (u8 *)jprobe_return) &&
-	    (addr <= (u8 *)jprobe_return_end)) {
-		*regs = kcb->jprobe_saved_regs;
-
-		memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack,
-		       MIN_STACK_SIZE(stack_addr));
-
-		kcb->kprobe_status = KPROBE_HIT_SS;
-		preempt_enable_no_resched();
-		return 1;
-	}
-
-	return 0;
-}
-
 static struct kprobe trampoline_p = {
 	.addr = (kprobe_opcode_t *)&kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index fceb2adfcac7..792f36129062 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -1,10 +1,6 @@
 /*
- * arch/sh/mm/consistent.c
- *
  * Copyright (C) 2004 - 2007  Paul Mundt
  *
- * Declared coherent memory functions based on arch/x86/kernel/pci-dma_32.c
- *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
@@ -13,90 +9,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
-#include <linux/dma-debug.h>
 #include <linux/io.h>
-#include <linux/module.h>
-#include <linux/gfp.h>
-#include <asm/cacheflush.h>
-#include <asm/addrspace.h>
-
-const struct dma_map_ops *dma_ops;
-EXPORT_SYMBOL(dma_ops);
-
-void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_handle, gfp_t gfp,
-				 unsigned long attrs)
-{
-	void *ret, *ret_nocache;
-	int order = get_order(size);
-
-	gfp |= __GFP_ZERO;
-
-	ret = (void *)__get_free_pages(gfp, order);
-	if (!ret)
-		return NULL;
-
-	/*
-	 * Pages from the page allocator may have data present in
-	 * cache. So flush the cache before using uncached memory.
-	 */
-	sh_sync_dma_for_device(ret, size, DMA_BIDIRECTIONAL);
-
-	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
-	if (!ret_nocache) {
-		free_pages((unsigned long)ret, order);
-		return NULL;
-	}
-
-	split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
-
-	*dma_handle = virt_to_phys(ret);
-	if (!WARN_ON(!dev))
-		*dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
-
-	return ret_nocache;
-}
-
-void dma_generic_free_coherent(struct device *dev, size_t size,
-			       void *vaddr, dma_addr_t dma_handle,
-			       unsigned long attrs)
-{
-	int order = get_order(size);
-	unsigned long pfn = dma_handle >> PAGE_SHIFT;
-	int k;
-
-	if (!WARN_ON(!dev))
-		pfn += dev->dma_pfn_offset;
-
-	for (k = 0; k < (1 << order); k++)
-		__free_pages(pfn_to_page(pfn + k), 0);
-
-	iounmap(vaddr);
-}
-
-void sh_sync_dma_for_device(void *vaddr, size_t size,
-		    enum dma_data_direction direction)
-{
-	void *addr;
-
-	addr = __in_29bit_mode() ?
-	       (void *)CAC_ADDR((unsigned long)vaddr) : vaddr;
-
-	switch (direction) {
-	case DMA_FROM_DEVICE:		/* invalidate only */
-		__flush_invalidate_region(addr, size);
-		break;
-	case DMA_TO_DEVICE:		/* writeback only */
-		__flush_wback_region(addr, size);
-		break;
-	case DMA_BIDIRECTIONAL:		/* writeback and invalidate */
-		__flush_purge_region(addr, size);
-		break;
-	default:
-		BUG();
-	}
-}
-EXPORT_SYMBOL(sh_sync_dma_for_device);
 
 static int __init memchunk_setup(char *str)
 {
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 4034035fbede..7713c084d040 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -339,22 +339,12 @@ void __init paging_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
-/*
- * Early initialization for any I/O MMUs we might have.
- */
-static void __init iommu_init(void)
-{
-	no_iommu_init();
-}
-
 unsigned int mem_init_done = 0;
 
 void __init mem_init(void)
 {
 	pg_data_t *pgdat;
 
-	iommu_init();
-
 	high_memory = NULL;
 	for_each_online_pgdat(pgdat)
 		high_memory = max_t(void *, high_memory,
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index d13ce517f4b9..94c930f0bc62 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -27,17 +27,17 @@ int atomic_fetch_or(int, atomic_t *);
 int atomic_fetch_xor(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
 int atomic_xchg(atomic_t *, int);
-int __atomic_add_unless(atomic_t *, int, int);
+int atomic_fetch_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
+#define atomic_fetch_add_unless	atomic_fetch_add_unless
+
 #define atomic_set_release(v, i)	atomic_set((v), (i))
 
 #define atomic_read(v)          READ_ONCE((v)->counter)
 
 #define atomic_add(i, v)	((void)atomic_add_return( (int)(i), (v)))
 #define atomic_sub(i, v)	((void)atomic_add_return(-(int)(i), (v)))
-#define atomic_inc(v)		((void)atomic_add_return(        1, (v)))
-#define atomic_dec(v)		((void)atomic_add_return(       -1, (v)))
 
 #define atomic_and(i, v)	((void)atomic_fetch_and((i), (v)))
 #define atomic_or(i, v)		((void)atomic_fetch_or((i), (v)))
@@ -46,22 +46,4 @@ void atomic_set(atomic_t *, int);
 #define atomic_sub_return(i, v)	(atomic_add_return(-(int)(i), (v)))
 #define atomic_fetch_sub(i, v)  (atomic_fetch_add (-(int)(i), (v)))
 
-#define atomic_inc_return(v)	(atomic_add_return(        1, (v)))
-#define atomic_dec_return(v)	(atomic_add_return(       -1, (v)))
-
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
 #endif /* !(__ARCH_SPARC_ATOMIC__) */
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 28db058d471b..6963482c81d8 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -50,38 +50,6 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_dec_return(v)   atomic_sub_return(1, v)
-#define atomic64_dec_return(v) atomic64_sub_return(1, v)
-
-#define atomic_inc_return(v)   atomic_add_return(1, v)
-#define atomic64_inc_return(v) atomic64_add_return(1, v)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0)
-
-#define atomic_inc(v) atomic_add(1, v)
-#define atomic64_inc(v) atomic64_add(1, v)
-
-#define atomic_dec(v) atomic_sub(1, v)
-#define atomic64_dec(v) atomic64_sub(1, v)
-
-#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0)
-
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 
 static inline int atomic_xchg(atomic_t *v, int new)
@@ -89,42 +57,11 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	return xchg(&v->counter, new);
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
 long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 9a1e9cbc7e6d..b162c23ae8c2 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -243,35 +243,42 @@ void insb(unsigned long, void *, unsigned long);
 void insw(unsigned long, void *, unsigned long);
 void insl(unsigned long, void *, unsigned long);
 
-static inline void ioread8_rep(void __iomem *port, void *buf, unsigned long count)
+static inline void readsb(void __iomem *port, void *buf, unsigned long count)
 {
 	insb((unsigned long __force)port, buf, count);
 }
-static inline void ioread16_rep(void __iomem *port, void *buf, unsigned long count)
+static inline void readsw(void __iomem *port, void *buf, unsigned long count)
 {
 	insw((unsigned long __force)port, buf, count);
 }
 
-static inline void ioread32_rep(void __iomem *port, void *buf, unsigned long count)
+static inline void readsl(void __iomem *port, void *buf, unsigned long count)
 {
 	insl((unsigned long __force)port, buf, count);
 }
 
-static inline void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count)
+static inline void writesb(void __iomem *port, const void *buf, unsigned long count)
 {
 	outsb((unsigned long __force)port, buf, count);
 }
 
-static inline void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count)
+static inline void writesw(void __iomem *port, const void *buf, unsigned long count)
 {
 	outsw((unsigned long __force)port, buf, count);
 }
 
-static inline void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count)
+static inline void writesl(void __iomem *port, const void *buf, unsigned long count)
 {
 	outsl((unsigned long __force)port, buf, count);
 }
 
+#define ioread8_rep(p,d,l)	readsb(p,d,l)
+#define ioread16_rep(p,d,l)	readsw(p,d,l)
+#define ioread32_rep(p,d,l)	readsl(p,d,l)
+#define iowrite8_rep(p,d,l)	writesb(p,d,l)
+#define iowrite16_rep(p,d,l)	writesw(p,d,l)
+#define iowrite32_rep(p,d,l)	writesl(p,d,l)
+
 /* Valid I/O Space regions are anywhere, because each PCI bus supported
  * can live in an arbitrary area of the physical address range.
  */
diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h
index 3704490b4488..bfcaa6326c20 100644
--- a/arch/sparc/include/asm/kprobes.h
+++ b/arch/sparc/include/asm/kprobes.h
@@ -44,7 +44,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_orig_tnpc;
 	unsigned long kprobe_orig_tstate_pil;
-	struct pt_regs jprobe_saved_regs;
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index ab4ba4347941..dfbca2470536 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -147,18 +147,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			kcb->kprobe_status = KPROBE_REENTER;
 			prepare_singlestep(p, regs, kcb);
 			return 1;
-		} else {
-			if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
+		} else if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
 			/* The breakpoint instruction was removed by
 			 * another cpu right after we hit, no further
 			 * handling of this interrupt is appropriate
 			 */
-				ret = 1;
-				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs))
-				goto ss_probe;
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -181,10 +175,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
-ss_probe:
 	prepare_singlestep(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;
@@ -441,53 +437,6 @@ out:
 	exception_exit(prev_state);
 }
 
-/* Jprobes support.  */
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	memcpy(&(kcb->jprobe_saved_regs), regs, sizeof(*regs));
-
-	regs->tpc  = (unsigned long) jp->entry;
-	regs->tnpc = ((unsigned long) jp->entry) + 0x4UL;
-	regs->tstate |= TSTATE_PIL;
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	register unsigned long orig_fp asm("g1");
-
-	orig_fp = kcb->jprobe_saved_regs.u_regs[UREG_FP];
-	__asm__ __volatile__("\n"
-"1:	cmp		%%sp, %0\n\t"
-	"blu,a,pt	%%xcc, 1b\n\t"
-	" restore\n\t"
-	".globl		jprobe_return_trap_instruction\n"
-"jprobe_return_trap_instruction:\n\t"
-	"ta		0x70"
-	: /* no outputs */
-	: "r" (orig_fp));
-}
-
-extern void jprobe_return_trap_instruction(void);
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	u32 *addr = (u32 *) regs->tpc;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (addr == (u32 *) jprobe_return_trap_instruction) {
-		memcpy(regs, &(kcb->jprobe_saved_regs), sizeof(*regs));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
 /* The value stored in the return address register is actually 2
  * instructions before where the callee will return to.
  * Sequences usually look something like this
@@ -562,9 +511,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	regs->tpc = orig_ret_address;
 	regs->tnpc = orig_ret_address + 4;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 465a901a0ada..281fa634bb1a 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -95,7 +95,7 @@ int atomic_cmpxchg(atomic_t *v, int old, int new)
 }
 EXPORT_SYMBOL(atomic_cmpxchg);
 
-int __atomic_add_unless(atomic_t *v, int a, int u)
+int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int ret;
 	unsigned long flags;
@@ -107,7 +107,7 @@ int __atomic_add_unless(atomic_t *v, int a, int u)
 	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
 	return ret;
 }
-EXPORT_SYMBOL(__atomic_add_unless);
+EXPORT_SYMBOL(atomic_fetch_add_unless);
 
 /* Atomic operations are already serializing */
 void atomic_set(atomic_t *v, int i)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 887d3a7bb646..0b767d6577b7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -180,13 +180,14 @@ config X86
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_RELIABLE_STACKTRACE		if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION
+	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
 	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if X86_64
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
+	select HOTPLUG_SMT			if SMP
 	select IRQ_FORCED_THREADING
 	select NEED_SG_DMA_LENGTH
 	select PCI_LOCKLESS_CONFIG
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index a08e82856563..7e3c07d6ad42 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -80,11 +80,6 @@ ifeq ($(CONFIG_X86_32),y)
         # alignment instructions.
         KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4))
 
-        # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
-        # a lot more stack due to the lack of sharing of stacklots:
-        KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0400, \
-				$(call cc-option,-fno-unit-at-a-time))
-
         # CPU-specific tuning. Anything which can be shared with UML should go here.
         include arch/x86/Makefile_32.cpu
         KBUILD_CFLAGS += $(cflags-y)
diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h
index 0d41d68131cc..2e1382486e91 100644
--- a/arch/x86/boot/bitops.h
+++ b/arch/x86/boot/bitops.h
@@ -17,6 +17,7 @@
 #define _LINUX_BITOPS_H		/* Inhibit inclusion of <linux/bitops.h> */
 
 #include <linux/types.h>
+#include <asm/asm.h>
 
 static inline bool constant_test_bit(int nr, const void *addr)
 {
@@ -28,7 +29,7 @@ static inline bool variable_test_bit(int nr, const void *addr)
 	bool v;
 	const u32 *p = (const u32 *)addr;
 
-	asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));
+	asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr));
 	return v;
 }
 
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index e98522ea6f09..1458b1700fc7 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -34,74 +34,13 @@ 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;				\
+	c->runtime_services	= table->runtime;			\
+	c->boot_services	= table->boottime;			\
+	c->text_output		= table->con_out;			\
 }
 BOOT_SERVICES(32);
 BOOT_SERVICES(64);
 
-static inline efi_status_t __open_volume32(void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_32_t *image = __image;
-	efi_file_handle_32_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-	unsigned long func;
-
-	status = efi_call_early(handle_protocol, handle,
-				&fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	func = (unsigned long)io->open_volume;
-	status = efi_early->call(func, io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table, "Failed to open volume\n");
-
-	*__fh = fh;
-	return status;
-}
-
-static inline efi_status_t __open_volume64(void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_64_t *image = __image;
-	efi_file_handle_64_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-	unsigned long func;
-
-	status = efi_call_early(handle_protocol, handle,
-				&fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	func = (unsigned long)io->open_volume;
-	status = efi_early->call(func, io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table, "Failed to open volume\n");
-
-	*__fh = fh;
-	return status;
-}
-
-efi_status_t
-efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
-{
-	if (efi_early->is64)
-		return __open_volume64(__image, __fh);
-
-	return __open_volume32(__image, __fh);
-}
-
 void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 {
 	efi_call_proto(efi_simple_text_output_protocol, output_string,
@@ -109,7 +48,7 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 }
 
 static efi_status_t
-__setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
+preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 {
 	struct pci_setup_rom *rom = NULL;
 	efi_status_t status;
@@ -134,16 +73,16 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 
 	status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for rom\n");
+		efi_printk(sys_table, "Failed to allocate memory for 'rom'\n");
 		return status;
 	}
 
 	memset(rom, 0, sizeof(*rom));
 
-	rom->data.type = SETUP_PCI;
-	rom->data.len = size - sizeof(struct setup_data);
-	rom->data.next = 0;
-	rom->pcilen = pci->romsize;
+	rom->data.type	= SETUP_PCI;
+	rom->data.len	= size - sizeof(struct setup_data);
+	rom->data.next	= 0;
+	rom->pcilen	= pci->romsize;
 	*__rom = rom;
 
 	status = efi_call_proto(efi_pci_io_protocol, pci.read, pci,
@@ -179,96 +118,6 @@ free_struct:
 	return status;
 }
 
-static void
-setup_efi_pci32(struct boot_params *params, void **pci_handle,
-		unsigned long size)
-{
-	efi_pci_io_protocol_t *pci = NULL;
-	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
-	u32 *handles = (u32 *)(unsigned long)pci_handle;
-	efi_status_t status;
-	unsigned long nr_pci;
-	struct setup_data *data;
-	int i;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	nr_pci = size / sizeof(u32);
-	for (i = 0; i < nr_pci; i++) {
-		struct pci_setup_rom *rom = NULL;
-		u32 h = handles[i];
-
-		status = efi_call_early(handle_protocol, h,
-					&pci_proto, (void **)&pci);
-
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (!pci)
-			continue;
-
-		status = __setup_efi_pci(pci, &rom);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (data)
-			data->next = (unsigned long)rom;
-		else
-			params->hdr.setup_data = (unsigned long)rom;
-
-		data = (struct setup_data *)rom;
-
-	}
-}
-
-static void
-setup_efi_pci64(struct boot_params *params, void **pci_handle,
-		unsigned long size)
-{
-	efi_pci_io_protocol_t *pci = NULL;
-	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
-	u64 *handles = (u64 *)(unsigned long)pci_handle;
-	efi_status_t status;
-	unsigned long nr_pci;
-	struct setup_data *data;
-	int i;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	nr_pci = size / sizeof(u64);
-	for (i = 0; i < nr_pci; i++) {
-		struct pci_setup_rom *rom = NULL;
-		u64 h = handles[i];
-
-		status = efi_call_early(handle_protocol, h,
-					&pci_proto, (void **)&pci);
-
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (!pci)
-			continue;
-
-		status = __setup_efi_pci(pci, &rom);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (data)
-			data->next = (unsigned long)rom;
-		else
-			params->hdr.setup_data = (unsigned long)rom;
-
-		data = (struct setup_data *)rom;
-
-	}
-}
-
 /*
  * There's no way to return an informative status from this function,
  * because any analysis (and printing of error messages) needs to be
@@ -284,6 +133,9 @@ static void setup_efi_pci(struct boot_params *params)
 	void **pci_handle = NULL;
 	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
 	unsigned long size = 0;
+	unsigned long nr_pci;
+	struct setup_data *data;
+	int i;
 
 	status = efi_call_early(locate_handle,
 				EFI_LOCATE_BY_PROTOCOL,
@@ -295,7 +147,7 @@ static void setup_efi_pci(struct boot_params *params)
 					size, (void **)&pci_handle);
 
 		if (status != EFI_SUCCESS) {
-			efi_printk(sys_table, "Failed to alloc mem for pci_handle\n");
+			efi_printk(sys_table, "Failed to allocate memory for 'pci_handle'\n");
 			return;
 		}
 
@@ -307,10 +159,34 @@ static void setup_efi_pci(struct boot_params *params)
 	if (status != EFI_SUCCESS)
 		goto free_handle;
 
-	if (efi_early->is64)
-		setup_efi_pci64(params, pci_handle, size);
-	else
-		setup_efi_pci32(params, pci_handle, size);
+	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+	while (data && data->next)
+		data = (struct setup_data *)(unsigned long)data->next;
+
+	nr_pci = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32));
+	for (i = 0; i < nr_pci; i++) {
+		efi_pci_io_protocol_t *pci = NULL;
+		struct pci_setup_rom *rom;
+
+		status = efi_call_early(handle_protocol,
+					efi_is_64bit() ? ((u64 *)pci_handle)[i]
+						       : ((u32 *)pci_handle)[i],
+					&pci_proto, (void **)&pci);
+		if (status != EFI_SUCCESS || !pci)
+			continue;
+
+		status = preserve_pci_rom_image(pci, &rom);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		if (data)
+			data->next = (unsigned long)rom;
+		else
+			params->hdr.setup_data = (unsigned long)rom;
+
+		data = (struct setup_data *)rom;
+	}
 
 free_handle:
 	efi_call_early(free_pool, pci_handle);
@@ -341,8 +217,7 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 		status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
 					size + sizeof(struct setup_data), &new);
 		if (status != EFI_SUCCESS) {
-			efi_printk(sys_table,
-					"Failed to alloc mem for properties\n");
+			efi_printk(sys_table, "Failed to allocate memory for 'properties'\n");
 			return;
 		}
 
@@ -358,9 +233,9 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 	new->next = 0;
 
 	data = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
-	if (!data)
+	if (!data) {
 		boot_params->hdr.setup_data = (unsigned long)new;
-	else {
+	} else {
 		while (data->next)
 			data = (struct setup_data *)(unsigned long)data->next;
 		data->next = (unsigned long)new;
@@ -380,81 +255,55 @@ static void setup_quirks(struct boot_params *boot_params)
 	}
 }
 
+/*
+ * See if we have Universal Graphics Adapter (UGA) protocol
+ */
 static efi_status_t
-setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size)
 {
-	struct efi_uga_draw_protocol *uga = NULL, *first_uga;
-	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+	efi_status_t status;
+	u32 width, height;
+	void **uga_handle = NULL;
+	efi_uga_draw_protocol_t *uga = NULL, *first_uga;
 	unsigned long nr_ugas;
-	u32 *handles = (u32 *)uga_handle;
-	efi_status_t status = EFI_INVALID_PARAMETER;
 	int i;
 
-	first_uga = NULL;
-	nr_ugas = size / sizeof(u32);
-	for (i = 0; i < nr_ugas; i++) {
-		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
-		u32 w, h, depth, refresh;
-		void *pciio;
-		u32 handle = handles[i];
-
-		status = efi_call_early(handle_protocol, handle,
-					&uga_proto, (void **)&uga);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
-
-		status = efi_early->call((unsigned long)uga->get_mode, uga,
-					 &w, &h, &depth, &refresh);
-		if (status == EFI_SUCCESS && (!first_uga || pciio)) {
-			*width = w;
-			*height = h;
-
-			/*
-			 * Once we've found a UGA supporting PCIIO,
-			 * don't bother looking any further.
-			 */
-			if (pciio)
-				break;
-
-			first_uga = uga;
-		}
-	}
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				size, (void **)&uga_handle);
+	if (status != EFI_SUCCESS)
+		return status;
 
-	return status;
-}
+	status = efi_call_early(locate_handle,
+				EFI_LOCATE_BY_PROTOCOL,
+				uga_proto, NULL, &size, uga_handle);
+	if (status != EFI_SUCCESS)
+		goto free_handle;
 
-static efi_status_t
-setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
-{
-	struct efi_uga_draw_protocol *uga = NULL, *first_uga;
-	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
-	unsigned long nr_ugas;
-	u64 *handles = (u64 *)uga_handle;
-	efi_status_t status = EFI_INVALID_PARAMETER;
-	int i;
+	height = 0;
+	width = 0;
 
 	first_uga = NULL;
-	nr_ugas = size / sizeof(u64);
+	nr_ugas = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32));
 	for (i = 0; i < nr_ugas; i++) {
 		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
 		u32 w, h, depth, refresh;
 		void *pciio;
-		u64 handle = handles[i];
+		unsigned long handle = efi_is_64bit() ? ((u64 *)uga_handle)[i]
+						      : ((u32 *)uga_handle)[i];
 
 		status = efi_call_early(handle_protocol, handle,
-					&uga_proto, (void **)&uga);
+					uga_proto, (void **)&uga);
 		if (status != EFI_SUCCESS)
 			continue;
 
+		pciio = NULL;
 		efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
 
-		status = efi_early->call((unsigned long)uga->get_mode, uga,
-					 &w, &h, &depth, &refresh);
+		status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga,
+					&w, &h, &depth, &refresh);
 		if (status == EFI_SUCCESS && (!first_uga || pciio)) {
-			*width = w;
-			*height = h;
+			width = w;
+			height = h;
 
 			/*
 			 * Once we've found a UGA supporting PCIIO,
@@ -467,59 +316,28 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 		}
 	}
 
-	return status;
-}
-
-/*
- * See if we have Universal Graphics Adapter (UGA) protocol
- */
-static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
-			      unsigned long size)
-{
-	efi_status_t status;
-	u32 width, height;
-	void **uga_handle = NULL;
-
-	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
-				size, (void **)&uga_handle);
-	if (status != EFI_SUCCESS)
-		return status;
-
-	status = efi_call_early(locate_handle,
-				EFI_LOCATE_BY_PROTOCOL,
-				uga_proto, NULL, &size, uga_handle);
-	if (status != EFI_SUCCESS)
-		goto free_handle;
-
-	height = 0;
-	width = 0;
-
-	if (efi_early->is64)
-		status = setup_uga64(uga_handle, size, &width, &height);
-	else
-		status = setup_uga32(uga_handle, size, &width, &height);
-
 	if (!width && !height)
 		goto free_handle;
 
 	/* EFI framebuffer */
-	si->orig_video_isVGA = VIDEO_TYPE_EFI;
+	si->orig_video_isVGA	= VIDEO_TYPE_EFI;
 
-	si->lfb_depth = 32;
-	si->lfb_width = width;
-	si->lfb_height = height;
+	si->lfb_depth		= 32;
+	si->lfb_width		= width;
+	si->lfb_height		= height;
 
-	si->red_size = 8;
-	si->red_pos = 16;
-	si->green_size = 8;
-	si->green_pos = 8;
-	si->blue_size = 8;
-	si->blue_pos = 0;
-	si->rsvd_size = 8;
-	si->rsvd_pos = 24;
+	si->red_size		= 8;
+	si->red_pos		= 16;
+	si->green_size		= 8;
+	si->green_pos		= 8;
+	si->blue_size		= 8;
+	si->blue_pos		= 0;
+	si->rsvd_size		= 8;
+	si->rsvd_pos		= 24;
 
 free_handle:
 	efi_call_early(free_pool, uga_handle);
+
 	return status;
 }
 
@@ -586,7 +404,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		return NULL;
 
-	if (efi_early->is64)
+	if (efi_is_64bit())
 		setup_boot_services64(efi_early);
 	else
 		setup_boot_services32(efi_early);
@@ -601,7 +419,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	status = efi_low_alloc(sys_table, 0x4000, 1,
 			       (unsigned long *)&boot_params);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc lowmem for boot params\n");
+		efi_printk(sys_table, "Failed to allocate lowmem for boot params\n");
 		return NULL;
 	}
 
@@ -617,9 +435,9 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	 * Fill out some of the header fields ourselves because the
 	 * EFI firmware loader doesn't load the first sector.
 	 */
-	hdr->root_flags = 1;
-	hdr->vid_mode = 0xffff;
-	hdr->boot_flag = 0xAA55;
+	hdr->root_flags	= 1;
+	hdr->vid_mode	= 0xffff;
+	hdr->boot_flag	= 0xAA55;
 
 	hdr->type_of_loader = 0x21;
 
@@ -627,6 +445,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size);
 	if (!cmdline_ptr)
 		goto fail;
+
 	hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
 	/* Fill in upper bits of command line address, NOP on 32 bit  */
 	boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32;
@@ -663,10 +482,12 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	boot_params->ext_ramdisk_size  = (u64)ramdisk_size >> 32;
 
 	return boot_params;
+
 fail2:
 	efi_free(sys_table, options_size, hdr->cmd_line_ptr);
 fail:
 	efi_free(sys_table, 0x4000, (unsigned long)boot_params);
+
 	return NULL;
 }
 
@@ -678,7 +499,7 @@ static void add_e820ext(struct boot_params *params,
 	unsigned long size;
 
 	e820ext->type = SETUP_E820_EXT;
-	e820ext->len = nr_entries * sizeof(struct boot_e820_entry);
+	e820ext->len  = nr_entries * sizeof(struct boot_e820_entry);
 	e820ext->next = 0;
 
 	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
@@ -692,8 +513,8 @@ static void add_e820ext(struct boot_params *params,
 		params->hdr.setup_data = (unsigned long)e820ext;
 }
 
-static efi_status_t setup_e820(struct boot_params *params,
-			       struct setup_data *e820ext, u32 e820ext_size)
+static efi_status_t
+setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size)
 {
 	struct boot_e820_entry *entry = params->e820_table;
 	struct efi_info *efi = &params->efi_info;
@@ -814,11 +635,10 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
 }
 
 struct exit_boot_struct {
-	struct boot_params *boot_params;
-	struct efi_info *efi;
-	struct setup_data *e820ext;
-	__u32 e820ext_size;
-	bool is64;
+	struct boot_params	*boot_params;
+	struct efi_info		*efi;
+	struct setup_data	*e820ext;
+	__u32			e820ext_size;
 };
 
 static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
@@ -845,25 +665,25 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
 		first = false;
 	}
 
-	signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+	signature = efi_is_64bit() ? EFI64_LOADER_SIGNATURE
+				   : EFI32_LOADER_SIGNATURE;
 	memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
 
-	p->efi->efi_systab = (unsigned long)sys_table_arg;
-	p->efi->efi_memdesc_size = *map->desc_size;
-	p->efi->efi_memdesc_version = *map->desc_ver;
-	p->efi->efi_memmap = (unsigned long)*map->map;
-	p->efi->efi_memmap_size = *map->map_size;
+	p->efi->efi_systab		= (unsigned long)sys_table_arg;
+	p->efi->efi_memdesc_size	= *map->desc_size;
+	p->efi->efi_memdesc_version	= *map->desc_ver;
+	p->efi->efi_memmap		= (unsigned long)*map->map;
+	p->efi->efi_memmap_size		= *map->map_size;
 
 #ifdef CONFIG_X86_64
-	p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
-	p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
+	p->efi->efi_systab_hi		= (unsigned long)sys_table_arg >> 32;
+	p->efi->efi_memmap_hi		= (unsigned long)*map->map >> 32;
 #endif
 
 	return EFI_SUCCESS;
 }
 
-static efi_status_t exit_boot(struct boot_params *boot_params,
-			      void *handle, bool is64)
+static efi_status_t exit_boot(struct boot_params *boot_params, void *handle)
 {
 	unsigned long map_sz, key, desc_size, buff_size;
 	efi_memory_desc_t *mem_map;
@@ -874,17 +694,16 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 	struct efi_boot_memmap map;
 	struct exit_boot_struct priv;
 
-	map.map =		&mem_map;
-	map.map_size =		&map_sz;
-	map.desc_size =		&desc_size;
-	map.desc_ver =		&desc_version;
-	map.key_ptr =		&key;
-	map.buff_size =		&buff_size;
-	priv.boot_params =	boot_params;
-	priv.efi =		&boot_params->efi_info;
-	priv.e820ext =		NULL;
-	priv.e820ext_size =	0;
-	priv.is64 =		is64;
+	map.map			= &mem_map;
+	map.map_size		= &map_sz;
+	map.desc_size		= &desc_size;
+	map.desc_ver		= &desc_version;
+	map.key_ptr		= &key;
+	map.buff_size		= &buff_size;
+	priv.boot_params	= boot_params;
+	priv.efi		= &boot_params->efi_info;
+	priv.e820ext		= NULL;
+	priv.e820ext_size	= 0;
 
 	/* Might as well exit boot services now */
 	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
@@ -892,10 +711,11 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 	if (status != EFI_SUCCESS)
 		return status;
 
-	e820ext = priv.e820ext;
-	e820ext_size = priv.e820ext_size;
+	e820ext			= priv.e820ext;
+	e820ext_size		= priv.e820ext_size;
+
 	/* Historic? */
-	boot_params->alt_mem_k = 32 * 1024;
+	boot_params->alt_mem_k	= 32 * 1024;
 
 	status = setup_e820(boot_params, e820ext, e820ext_size);
 	if (status != EFI_SUCCESS)
@@ -908,8 +728,8 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
  * On success we return a pointer to a boot_params structure, and NULL
  * on failure.
  */
-struct boot_params *efi_main(struct efi_config *c,
-			     struct boot_params *boot_params)
+struct boot_params *
+efi_main(struct efi_config *c, struct boot_params *boot_params)
 {
 	struct desc_ptr *gdt = NULL;
 	efi_loaded_image_t *image;
@@ -918,13 +738,11 @@ struct boot_params *efi_main(struct efi_config *c,
 	struct desc_struct *desc;
 	void *handle;
 	efi_system_table_t *_table;
-	bool is64;
 
 	efi_early = c;
 
 	_table = (efi_system_table_t *)(unsigned long)efi_early->table;
 	handle = (void *)(unsigned long)efi_early->image_handle;
-	is64 = efi_early->is64;
 
 	sys_table = _table;
 
@@ -932,7 +750,7 @@ struct boot_params *efi_main(struct efi_config *c,
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		goto fail;
 
-	if (is64)
+	if (efi_is_64bit())
 		setup_boot_services64(efi_early);
 	else
 		setup_boot_services32(efi_early);
@@ -957,7 +775,7 @@ struct boot_params *efi_main(struct efi_config *c,
 	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
 				sizeof(*gdt), (void **)&gdt);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
+		efi_printk(sys_table, "Failed to allocate memory for 'gdt' structure\n");
 		goto fail;
 	}
 
@@ -965,7 +783,7 @@ struct boot_params *efi_main(struct efi_config *c,
 	status = efi_low_alloc(sys_table, gdt->size, 8,
 			   (unsigned long *)&gdt->address);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for gdt\n");
+		efi_printk(sys_table, "Failed to allocate memory for 'gdt'\n");
 		goto fail;
 	}
 
@@ -988,7 +806,7 @@ struct boot_params *efi_main(struct efi_config *c,
 		hdr->code32_start = bzimage_addr;
 	}
 
-	status = exit_boot(boot_params, handle, is64);
+	status = exit_boot(boot_params, handle);
 	if (status != EFI_SUCCESS) {
 		efi_printk(sys_table, "exit_boot() failed!\n");
 		goto fail;
@@ -1002,19 +820,20 @@ struct boot_params *efi_main(struct efi_config *c,
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		/* __KERNEL32_CS */
-		desc->limit0 = 0xffff;
-		desc->base0 = 0x0000;
-		desc->base1 = 0x0000;
-		desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
-		desc->s = DESC_TYPE_CODE_DATA;
-		desc->dpl = 0;
-		desc->p = 1;
-		desc->limit1 = 0xf;
-		desc->avl = 0;
-		desc->l = 0;
-		desc->d = SEG_OP_SIZE_32BIT;
-		desc->g = SEG_GRANULARITY_4KB;
-		desc->base2 = 0x00;
+		desc->limit0	= 0xffff;
+		desc->base0	= 0x0000;
+		desc->base1	= 0x0000;
+		desc->type	= SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+		desc->s		= DESC_TYPE_CODE_DATA;
+		desc->dpl	= 0;
+		desc->p		= 1;
+		desc->limit1	= 0xf;
+		desc->avl	= 0;
+		desc->l		= 0;
+		desc->d		= SEG_OP_SIZE_32BIT;
+		desc->g		= SEG_GRANULARITY_4KB;
+		desc->base2	= 0x00;
+
 		desc++;
 	} else {
 		/* Second entry is unused on 32-bit */
@@ -1022,15 +841,16 @@ struct boot_params *efi_main(struct efi_config *c,
 	}
 
 	/* __KERNEL_CS */
-	desc->limit0 = 0xffff;
-	desc->base0 = 0x0000;
-	desc->base1 = 0x0000;
-	desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
-	desc->s = DESC_TYPE_CODE_DATA;
-	desc->dpl = 0;
-	desc->p = 1;
-	desc->limit1 = 0xf;
-	desc->avl = 0;
+	desc->limit0	= 0xffff;
+	desc->base0	= 0x0000;
+	desc->base1	= 0x0000;
+	desc->type	= SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+	desc->s		= DESC_TYPE_CODE_DATA;
+	desc->dpl	= 0;
+	desc->p		= 1;
+	desc->limit1	= 0xf;
+	desc->avl	= 0;
+
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		desc->l = 1;
 		desc->d = 0;
@@ -1038,41 +858,41 @@ struct boot_params *efi_main(struct efi_config *c,
 		desc->l = 0;
 		desc->d = SEG_OP_SIZE_32BIT;
 	}
-	desc->g = SEG_GRANULARITY_4KB;
-	desc->base2 = 0x00;
+	desc->g		= SEG_GRANULARITY_4KB;
+	desc->base2	= 0x00;
 	desc++;
 
 	/* __KERNEL_DS */
-	desc->limit0 = 0xffff;
-	desc->base0 = 0x0000;
-	desc->base1 = 0x0000;
-	desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
-	desc->s = DESC_TYPE_CODE_DATA;
-	desc->dpl = 0;
-	desc->p = 1;
-	desc->limit1 = 0xf;
-	desc->avl = 0;
-	desc->l = 0;
-	desc->d = SEG_OP_SIZE_32BIT;
-	desc->g = SEG_GRANULARITY_4KB;
-	desc->base2 = 0x00;
+	desc->limit0	= 0xffff;
+	desc->base0	= 0x0000;
+	desc->base1	= 0x0000;
+	desc->type	= SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
+	desc->s		= DESC_TYPE_CODE_DATA;
+	desc->dpl	= 0;
+	desc->p		= 1;
+	desc->limit1	= 0xf;
+	desc->avl	= 0;
+	desc->l		= 0;
+	desc->d		= SEG_OP_SIZE_32BIT;
+	desc->g		= SEG_GRANULARITY_4KB;
+	desc->base2	= 0x00;
 	desc++;
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		/* Task segment value */
-		desc->limit0 = 0x0000;
-		desc->base0 = 0x0000;
-		desc->base1 = 0x0000;
-		desc->type = SEG_TYPE_TSS;
-		desc->s = 0;
-		desc->dpl = 0;
-		desc->p = 1;
-		desc->limit1 = 0x0;
-		desc->avl = 0;
-		desc->l = 0;
-		desc->d = 0;
-		desc->g = SEG_GRANULARITY_4KB;
-		desc->base2 = 0x00;
+		desc->limit0	= 0x0000;
+		desc->base0	= 0x0000;
+		desc->base1	= 0x0000;
+		desc->type	= SEG_TYPE_TSS;
+		desc->s		= 0;
+		desc->dpl	= 0;
+		desc->p		= 1;
+		desc->limit1	= 0x0;
+		desc->avl	= 0;
+		desc->l		= 0;
+		desc->d		= 0;
+		desc->g		= SEG_GRANULARITY_4KB;
+		desc->base2	= 0x00;
 		desc++;
 	}
 
@@ -1082,5 +902,6 @@ struct boot_params *efi_main(struct efi_config *c,
 	return boot_params;
 fail:
 	efi_printk(sys_table, "efi_main() failed!\n");
+
 	return NULL;
 }
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index e799dc5c6448..8297387c4676 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -12,22 +12,22 @@
 
 #define DESC_TYPE_CODE_DATA	(1 << 0)
 
-struct efi_uga_draw_protocol_32 {
+typedef struct {
 	u32 get_mode;
 	u32 set_mode;
 	u32 blt;
-};
+} efi_uga_draw_protocol_32_t;
 
-struct efi_uga_draw_protocol_64 {
+typedef struct {
 	u64 get_mode;
 	u64 set_mode;
 	u64 blt;
-};
+} efi_uga_draw_protocol_64_t;
 
-struct efi_uga_draw_protocol {
+typedef struct {
 	void *get_mode;
 	void *set_mode;
 	void *blt;
-};
+} efi_uga_draw_protocol_t;
 
 #endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index b87a7582853d..302517929932 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -102,7 +102,7 @@ static bool memmap_too_large;
 
 
 /* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */
-unsigned long long mem_limit = ULLONG_MAX;
+static unsigned long long mem_limit = ULLONG_MAX;
 
 
 enum mem_avoid_index {
@@ -215,7 +215,36 @@ static void mem_avoid_memmap(char *str)
 		memmap_too_large = true;
 }
 
-static int handle_mem_memmap(void)
+/* Store the number of 1GB huge pages which users specified: */
+static unsigned long max_gb_huge_pages;
+
+static void parse_gb_huge_pages(char *param, char *val)
+{
+	static bool gbpage_sz;
+	char *p;
+
+	if (!strcmp(param, "hugepagesz")) {
+		p = val;
+		if (memparse(p, &p) != PUD_SIZE) {
+			gbpage_sz = false;
+			return;
+		}
+
+		if (gbpage_sz)
+			warn("Repeatedly set hugeTLB page size of 1G!\n");
+		gbpage_sz = true;
+		return;
+	}
+
+	if (!strcmp(param, "hugepages") && gbpage_sz) {
+		p = val;
+		max_gb_huge_pages = simple_strtoull(p, &p, 0);
+		return;
+	}
+}
+
+
+static int handle_mem_options(void)
 {
 	char *args = (char *)get_cmd_line_ptr();
 	size_t len = strlen((char *)args);
@@ -223,7 +252,8 @@ static int handle_mem_memmap(void)
 	char *param, *val;
 	u64 mem_size;
 
-	if (!strstr(args, "memmap=") && !strstr(args, "mem="))
+	if (!strstr(args, "memmap=") && !strstr(args, "mem=") &&
+		!strstr(args, "hugepages"))
 		return 0;
 
 	tmp_cmdline = malloc(len + 1);
@@ -248,6 +278,8 @@ static int handle_mem_memmap(void)
 
 		if (!strcmp(param, "memmap")) {
 			mem_avoid_memmap(val);
+		} else if (strstr(param, "hugepages")) {
+			parse_gb_huge_pages(param, val);
 		} else if (!strcmp(param, "mem")) {
 			char *p = val;
 
@@ -387,7 +419,7 @@ 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 */
-	handle_mem_memmap();
+	handle_mem_options();
 
 #ifdef CONFIG_X86_VERBOSE_BOOTUP
 	/* Make sure video RAM can be used. */
@@ -466,6 +498,60 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 	}
 }
 
+/*
+ * Skip as many 1GB huge pages as possible in the passed region
+ * according to the number which users specified:
+ */
+static void
+process_gb_huge_pages(struct mem_vector *region, unsigned long image_size)
+{
+	unsigned long addr, size = 0;
+	struct mem_vector tmp;
+	int i = 0;
+
+	if (!max_gb_huge_pages) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	addr = ALIGN(region->start, PUD_SIZE);
+	/* Did we raise the address above the passed in memory entry? */
+	if (addr < region->start + region->size)
+		size = region->size - (addr - region->start);
+
+	/* Check how many 1GB huge pages can be filtered out: */
+	while (size > PUD_SIZE && max_gb_huge_pages) {
+		size -= PUD_SIZE;
+		max_gb_huge_pages--;
+		i++;
+	}
+
+	/* No good 1GB huge pages found: */
+	if (!i) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	/*
+	 * Skip those 'i'*1GB good huge pages, and continue checking and
+	 * processing the remaining head or tail part of the passed region
+	 * if available.
+	 */
+
+	if (addr >= region->start + image_size) {
+		tmp.start = region->start;
+		tmp.size = addr - region->start;
+		store_slot_info(&tmp, image_size);
+	}
+
+	size  = region->size - (addr - region->start) - i * PUD_SIZE;
+	if (size >= image_size) {
+		tmp.start = addr + i * PUD_SIZE;
+		tmp.size = size;
+		store_slot_info(&tmp, image_size);
+	}
+}
+
 static unsigned long slots_fetch_random(void)
 {
 	unsigned long slot;
@@ -546,7 +632,7 @@ static void process_mem_region(struct mem_vector *entry,
 
 		/* If nothing overlaps, store the region and return. */
 		if (!mem_avoid_overlap(&region, &overlap)) {
-			store_slot_info(&region, image_size);
+			process_gb_huge_pages(&region, image_size);
 			return;
 		}
 
@@ -556,7 +642,7 @@ static void process_mem_region(struct mem_vector *entry,
 
 			beginning.start = region.start;
 			beginning.size = overlap.start - region.start;
-			store_slot_info(&beginning, image_size);
+			process_gb_huge_pages(&beginning, image_size);
 		}
 
 		/* Return if overlap extends to or past end of region. */
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 16f49123d747..c4428a176973 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/types.h>
+#include <asm/asm.h>
 #include "ctype.h"
 #include "string.h"
 
@@ -28,8 +29,8 @@
 int memcmp(const void *s1, const void *s2, size_t len)
 {
 	bool diff;
-	asm("repe; cmpsb; setnz %0"
-	    : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm("repe; cmpsb" CC_SET(nz)
+	    : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 
diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
index 717bf0776421..5f7e43d4f64a 100644
--- a/arch/x86/crypto/aegis128-aesni-asm.S
+++ b/arch/x86/crypto/aegis128-aesni-asm.S
@@ -75,7 +75,7 @@
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG, MSG
 
 	mov LEN, %r8
diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c
index 5de7c0d46edf..acd11b3bf639 100644
--- a/arch/x86/crypto/aegis128-aesni-glue.c
+++ b/arch/x86/crypto/aegis128-aesni-glue.c
@@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128_aesni_alg[] = {
 	}
 };
 
-static const struct x86_cpu_id aesni_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_AES),
-	X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
-
 static int __init crypto_aegis128_aesni_module_init(void)
 {
-	if (!x86_match_cpu(aesni_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_AES) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_aegis128_aesni_alg,
diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S
index 4eda2b8db9e1..491dd61c845c 100644
--- a/arch/x86/crypto/aegis128l-aesni-asm.S
+++ b/arch/x86/crypto/aegis128l-aesni-asm.S
@@ -66,7 +66,7 @@
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG0, MSG0
 	pxor MSG1, MSG1
 
diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c
index 876e4866e633..2071c3d1ae07 100644
--- a/arch/x86/crypto/aegis128l-aesni-glue.c
+++ b/arch/x86/crypto/aegis128l-aesni-glue.c
@@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis128l_aesni_alg[] = {
 	}
 };
 
-static const struct x86_cpu_id aesni_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_AES),
-	X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
-
 static int __init crypto_aegis128l_aesni_module_init(void)
 {
-	if (!x86_match_cpu(aesni_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_AES) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_aegis128l_aesni_alg,
diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S
index 32aae8397268..8870c7c5d9a4 100644
--- a/arch/x86/crypto/aegis256-aesni-asm.S
+++ b/arch/x86/crypto/aegis256-aesni-asm.S
@@ -59,7 +59,7 @@
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG, MSG
 
 	mov LEN, %r8
diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c
index 2b5dd3af8f4d..b5f2a8fd5a71 100644
--- a/arch/x86/crypto/aegis256-aesni-glue.c
+++ b/arch/x86/crypto/aegis256-aesni-glue.c
@@ -375,16 +375,12 @@ static struct aead_alg crypto_aegis256_aesni_alg[] = {
 	}
 };
 
-static const struct x86_cpu_id aesni_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_AES),
-	X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
-
 static int __init crypto_aegis256_aesni_module_init(void)
 {
-	if (!x86_match_cpu(aesni_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_AES) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_aegis256_aesni_alg,
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index e762ef417562..9bd139569b41 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -258,7 +258,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 .macro GCM_INIT Iv SUBKEY AAD AADLEN
 	mov \AADLEN, %r11
 	mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length
-	xor %r11, %r11
+	xor %r11d, %r11d
 	mov %r11, InLen(%arg2) # ctx_data.in_length = 0
 	mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0
 	mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0
@@ -286,7 +286,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	movdqu HashKey(%arg2), %xmm13
 	add %arg5, InLen(%arg2)
 
-	xor %r11, %r11 # initialise the data pointer offset as zero
+	xor %r11d, %r11d # initialise the data pointer offset as zero
 	PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation
 
 	sub %r11, %arg5		# sub partial block data used
@@ -702,7 +702,7 @@ _no_extra_mask_1_\@:
 
 	# GHASH computation for the last <16 Byte block
 	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
-	xor	%rax,%rax
+	xor	%eax, %eax
 
 	mov	%rax, PBlockLen(%arg2)
 	jmp	_dec_done_\@
@@ -737,7 +737,7 @@ _no_extra_mask_2_\@:
 
 	# GHASH computation for the last <16 Byte block
 	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
-	xor	%rax,%rax
+	xor	%eax, %eax
 
 	mov	%rax, PBlockLen(%arg2)
 	jmp	_encode_done_\@
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index faecb1518bf8..1985ea0b551b 100644
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -463,7 +463,7 @@ _get_AAD_rest_final\@:
 
 _get_AAD_done\@:
 	# initialize the data pointer offset as zero
-	xor     %r11, %r11
+	xor     %r11d, %r11d
 
 	# start AES for num_initial_blocks blocks
 	mov     arg5, %rax                     # rax = *Y0
@@ -1770,7 +1770,7 @@ _get_AAD_rest_final\@:
 
 _get_AAD_done\@:
 	# initialize the data pointer offset as zero
-	xor     %r11, %r11
+	xor     %r11d, %r11d
 
 	# start AES for num_initial_blocks blocks
 	mov     arg5, %rax                     # rax = *Y0
diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S
index 07653d4582a6..de182c460f82 100644
--- a/arch/x86/crypto/morus1280-avx2-asm.S
+++ b/arch/x86/crypto/morus1280-avx2-asm.S
@@ -113,7 +113,7 @@ ENDPROC(__morus1280_update_zero)
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	vpxor MSG, MSG, MSG
 
 	mov %rcx, %r8
diff --git a/arch/x86/crypto/morus1280-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c
index f111f36d26dc..6634907d6ccd 100644
--- a/arch/x86/crypto/morus1280-avx2-glue.c
+++ b/arch/x86/crypto/morus1280-avx2-glue.c
@@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor,
 
 MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400);
 
-static const struct x86_cpu_id avx2_cpu_id[] = {
-    X86_FEATURE_MATCH(X86_FEATURE_AVX2),
-    {}
-};
-MODULE_DEVICE_TABLE(x86cpu, avx2_cpu_id);
-
 static int __init crypto_morus1280_avx2_module_init(void)
 {
-	if (!x86_match_cpu(avx2_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_morus1280_avx2_algs,
diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S
index bd1aa1b60869..da5d2905db60 100644
--- a/arch/x86/crypto/morus1280-sse2-asm.S
+++ b/arch/x86/crypto/morus1280-sse2-asm.S
@@ -235,7 +235,7 @@ ENDPROC(__morus1280_update_zero)
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG_LO, MSG_LO
 	pxor MSG_HI, MSG_HI
 
diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c
index 839270aa713c..95cf857d2cbb 100644
--- a/arch/x86/crypto/morus1280-sse2-glue.c
+++ b/arch/x86/crypto/morus1280-sse2-glue.c
@@ -37,15 +37,11 @@ asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor,
 
 MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350);
 
-static const struct x86_cpu_id sse2_cpu_id[] = {
-    X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-    {}
-};
-MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id);
-
 static int __init crypto_morus1280_sse2_module_init(void)
 {
-	if (!x86_match_cpu(sse2_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_morus1280_sse2_algs,
diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S
index efa02816d921..414db480250e 100644
--- a/arch/x86/crypto/morus640-sse2-asm.S
+++ b/arch/x86/crypto/morus640-sse2-asm.S
@@ -113,7 +113,7 @@ ENDPROC(__morus640_update_zero)
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG, MSG
 
 	mov %rcx, %r8
diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c
index 26b47e2db8d2..615fb7bc9a32 100644
--- a/arch/x86/crypto/morus640-sse2-glue.c
+++ b/arch/x86/crypto/morus640-sse2-glue.c
@@ -37,15 +37,11 @@ asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor,
 
 MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400);
 
-static const struct x86_cpu_id sse2_cpu_id[] = {
-    X86_FEATURE_MATCH(X86_FEATURE_XMM2),
-    {}
-};
-MODULE_DEVICE_TABLE(x86cpu, sse2_cpu_id);
-
 static int __init crypto_morus640_sse2_module_init(void)
 {
-	if (!x86_match_cpu(sse2_cpu_id))
+	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
+	    !boot_cpu_has(X86_FEATURE_OSXSAVE) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
 	return crypto_register_aeads(crypto_morus640_sse2_algs,
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index 6204bd53528c..613d0bfc3d84 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -96,7 +96,7 @@
 	# cleanup workspace
 	mov	$8, %ecx
 	mov	%rsp, %rdi
-	xor	%rax, %rax
+	xor	%eax, %eax
 	rep stosq
 
 	mov	%rbp, %rsp		# deallocate workspace
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index c371bfee137a..2767c625a52c 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -65,7 +65,7 @@
 # define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
 #else
 # define preempt_stop(clobbers)
-# define resume_kernel		restore_all
+# define resume_kernel		restore_all_kernel
 #endif
 
 .macro TRACE_IRQS_IRET
@@ -77,6 +77,8 @@
 #endif
 .endm
 
+#define PTI_SWITCH_MASK         (1 << PAGE_SHIFT)
+
 /*
  * User gs save/restore
  *
@@ -154,7 +156,52 @@
 
 #endif /* CONFIG_X86_32_LAZY_GS */
 
-.macro SAVE_ALL pt_regs_ax=%eax
+/* Unconditionally switch to user cr3 */
+.macro SWITCH_TO_USER_CR3 scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+	movl	%cr3, \scratch_reg
+	orl	$PTI_SWITCH_MASK, \scratch_reg
+	movl	\scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro BUG_IF_WRONG_CR3 no_user_check=0
+#ifdef CONFIG_DEBUG_ENTRY
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	.if \no_user_check == 0
+	/* coming from usermode? */
+	testl	$SEGMENT_RPL_MASK, PT_CS(%esp)
+	jz	.Lend_\@
+	.endif
+	/* On user-cr3? */
+	movl	%cr3, %eax
+	testl	$PTI_SWITCH_MASK, %eax
+	jnz	.Lend_\@
+	/* From userspace with kernel cr3 - BUG */
+	ud2
+.Lend_\@:
+#endif
+.endm
+
+/*
+ * Switch to kernel cr3 if not already loaded and return current cr3 in
+ * \scratch_reg
+ */
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	movl	%cr3, \scratch_reg
+	/* Test if we are already on kernel CR3 */
+	testl	$PTI_SWITCH_MASK, \scratch_reg
+	jz	.Lend_\@
+	andl	$(~PTI_SWITCH_MASK), \scratch_reg
+	movl	\scratch_reg, %cr3
+	/* Return original CR3 in \scratch_reg */
+	orl	$PTI_SWITCH_MASK, \scratch_reg
+.Lend_\@:
+.endm
+
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
 	cld
 	PUSH_GS
 	pushl	%fs
@@ -173,6 +220,29 @@
 	movl	$(__KERNEL_PERCPU), %edx
 	movl	%edx, %fs
 	SET_KERNEL_GS %edx
+
+	/* Switch to kernel stack if necessary */
+.if \switch_stacks > 0
+	SWITCH_TO_KERNEL_STACK
+.endif
+
+.endm
+
+.macro SAVE_ALL_NMI cr3_reg:req
+	SAVE_ALL
+
+	BUG_IF_WRONG_CR3
+
+	/*
+	 * Now switch the CR3 when PTI is enabled.
+	 *
+	 * We can enter with either user or kernel cr3, the code will
+	 * store the old cr3 in \cr3_reg and switches to the kernel cr3
+	 * if necessary.
+	 */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=\cr3_reg
+
+.Lend_\@:
 .endm
 
 /*
@@ -221,6 +291,349 @@
 	POP_GS_EX
 .endm
 
+.macro RESTORE_ALL_NMI cr3_reg:req pop=0
+	/*
+	 * Now switch the CR3 when PTI is enabled.
+	 *
+	 * We enter with kernel cr3 and switch the cr3 to the value
+	 * stored on \cr3_reg, which is either a user or a kernel cr3.
+	 */
+	ALTERNATIVE "jmp .Lswitched_\@", "", X86_FEATURE_PTI
+
+	testl	$PTI_SWITCH_MASK, \cr3_reg
+	jz	.Lswitched_\@
+
+	/* User cr3 in \cr3_reg - write it to hardware cr3 */
+	movl	\cr3_reg, %cr3
+
+.Lswitched_\@:
+
+	BUG_IF_WRONG_CR3
+
+	RESTORE_REGS pop=\pop
+.endm
+
+.macro CHECK_AND_APPLY_ESPFIX
+#ifdef CONFIG_X86_ESPFIX32
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+
+	ALTERNATIVE	"jmp .Lend_\@", "", X86_BUG_ESPFIX
+
+	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
+	/*
+	 * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+	 * are returning to the kernel.
+	 * See comments in process.c:copy_thread() for details.
+	 */
+	movb	PT_OLDSS(%esp), %ah
+	movb	PT_CS(%esp), %al
+	andl	$(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+	cmpl	$((SEGMENT_LDT << 8) | USER_RPL), %eax
+	jne	.Lend_\@	# returning to user-space with LDT SS
+
+	/*
+	 * Setup and switch to ESPFIX stack
+	 *
+	 * We're returning to userspace with a 16 bit stack. The CPU will not
+	 * restore the high word of ESP for us on executing iret... This is an
+	 * "official" bug of all the x86-compatible CPUs, which we can work
+	 * around to make dosemu and wine happy. We do this by preloading the
+	 * high word of ESP with the high word of the userspace ESP while
+	 * compensating for the offset by changing to the ESPFIX segment with
+	 * a base address that matches for the difference.
+	 */
+	mov	%esp, %edx			/* load kernel esp */
+	mov	PT_OLDESP(%esp), %eax		/* load userspace esp */
+	mov	%dx, %ax			/* eax: new kernel esp */
+	sub	%eax, %edx			/* offset (low word is 0) */
+	shr	$16, %edx
+	mov	%dl, GDT_ESPFIX_SS + 4		/* bits 16..23 */
+	mov	%dh, GDT_ESPFIX_SS + 7		/* bits 24..31 */
+	pushl	$__ESPFIX_SS
+	pushl	%eax				/* new kernel esp */
+	/*
+	 * Disable interrupts, but do not irqtrace this section: we
+	 * will soon execute iret and the tracer was already set to
+	 * the irqstate after the IRET:
+	 */
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	lss	(%esp), %esp			/* switch to espfix segment */
+.Lend_\@:
+#endif /* CONFIG_X86_ESPFIX32 */
+.endm
+
+/*
+ * Called with pt_regs fully populated and kernel segments loaded,
+ * so we can access PER_CPU and use the integer registers.
+ *
+ * We need to be very careful here with the %esp switch, because an NMI
+ * can happen everywhere. If the NMI handler finds itself on the
+ * entry-stack, it will overwrite the task-stack and everything we
+ * copied there. So allocate the stack-frame on the task-stack and
+ * switch to it before we do any copying.
+ */
+
+#define CS_FROM_ENTRY_STACK	(1 << 31)
+#define CS_FROM_USER_CR3	(1 << 30)
+
+.macro SWITCH_TO_KERNEL_STACK
+
+	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+	BUG_IF_WRONG_CR3
+
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+
+	/*
+	 * %eax now contains the entry cr3 and we carry it forward in
+	 * that register for the time this macro runs
+	 */
+
+	/* Are we on the entry stack? Bail out if not! */
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%esp, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
+	jae	.Lend_\@
+
+	/* Load stack pointer into %esi and %edi */
+	movl	%esp, %esi
+	movl	%esi, %edi
+
+	/* Move %edi to the top of the entry stack */
+	andl	$(MASK_entry_stack), %edi
+	addl	$(SIZEOF_entry_stack), %edi
+
+	/* Load top of task-stack into %edi */
+	movl	TSS_entry2task_stack(%edi), %edi
+
+	/*
+	 * Clear unused upper bits of the dword containing the word-sized CS
+	 * slot in pt_regs in case hardware didn't clear it for us.
+	 */
+	andl	$(0x0000ffff), PT_CS(%esp)
+
+	/* Special case - entry from kernel mode via entry stack */
+#ifdef CONFIG_VM86
+	movl	PT_EFLAGS(%esp), %ecx		# mix EFLAGS and CS
+	movb	PT_CS(%esp), %cl
+	andl	$(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %ecx
+#else
+	movl	PT_CS(%esp), %ecx
+	andl	$SEGMENT_RPL_MASK, %ecx
+#endif
+	cmpl	$USER_RPL, %ecx
+	jb	.Lentry_from_kernel_\@
+
+	/* Bytes to copy */
+	movl	$PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+	testl	$X86_EFLAGS_VM, PT_EFLAGS(%esi)
+	jz	.Lcopy_pt_regs_\@
+
+	/*
+	 * Stack-frame contains 4 additional segment registers when
+	 * coming from VM86 mode
+	 */
+	addl	$(4 * 4), %ecx
+
+#endif
+.Lcopy_pt_regs_\@:
+
+	/* Allocate frame on task-stack */
+	subl	%ecx, %edi
+
+	/* Switch to task-stack */
+	movl	%edi, %esp
+
+	/*
+	 * We are now on the task-stack and can safely copy over the
+	 * stack-frame
+	 */
+	shrl	$2, %ecx
+	cld
+	rep movsl
+
+	jmp .Lend_\@
+
+.Lentry_from_kernel_\@:
+
+	/*
+	 * This handles the case when we enter the kernel from
+	 * kernel-mode and %esp points to the entry-stack. When this
+	 * happens we need to switch to the task-stack to run C code,
+	 * but switch back to the entry-stack again when we approach
+	 * iret and return to the interrupted code-path. This usually
+	 * happens when we hit an exception while restoring user-space
+	 * segment registers on the way back to user-space or when the
+	 * sysenter handler runs with eflags.tf set.
+	 *
+	 * When we switch to the task-stack here, we can't trust the
+	 * contents of the entry-stack anymore, as the exception handler
+	 * might be scheduled out or moved to another CPU. Therefore we
+	 * copy the complete entry-stack to the task-stack and set a
+	 * marker in the iret-frame (bit 31 of the CS dword) to detect
+	 * what we've done on the iret path.
+	 *
+	 * On the iret path we copy everything back and switch to the
+	 * entry-stack, so that the interrupted kernel code-path
+	 * continues on the same stack it was interrupted with.
+	 *
+	 * Be aware that an NMI can happen anytime in this code.
+	 *
+	 * %esi: Entry-Stack pointer (same as %esp)
+	 * %edi: Top of the task stack
+	 * %eax: CR3 on kernel entry
+	 */
+
+	/* Calculate number of bytes on the entry stack in %ecx */
+	movl	%esi, %ecx
+
+	/* %ecx to the top of entry-stack */
+	andl	$(MASK_entry_stack), %ecx
+	addl	$(SIZEOF_entry_stack), %ecx
+
+	/* Number of bytes on the entry stack to %ecx */
+	sub	%esi, %ecx
+
+	/* Mark stackframe as coming from entry stack */
+	orl	$CS_FROM_ENTRY_STACK, PT_CS(%esp)
+
+	/*
+	 * Test the cr3 used to enter the kernel and add a marker
+	 * so that we can switch back to it before iret.
+	 */
+	testl	$PTI_SWITCH_MASK, %eax
+	jz	.Lcopy_pt_regs_\@
+	orl	$CS_FROM_USER_CR3, PT_CS(%esp)
+
+	/*
+	 * %esi and %edi are unchanged, %ecx contains the number of
+	 * bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate
+	 * the stack-frame on task-stack and copy everything over
+	 */
+	jmp .Lcopy_pt_regs_\@
+
+.Lend_\@:
+.endm
+
+/*
+ * Switch back from the kernel stack to the entry stack.
+ *
+ * The %esp register must point to pt_regs on the task stack. It will
+ * first calculate the size of the stack-frame to copy, depending on
+ * whether we return to VM86 mode or not. With that it uses 'rep movsl'
+ * to copy the contents of the stack over to the entry stack.
+ *
+ * We must be very careful here, as we can't trust the contents of the
+ * task-stack once we switched to the entry-stack. When an NMI happens
+ * while on the entry-stack, the NMI handler will switch back to the top
+ * of the task stack, overwriting our stack-frame we are about to copy.
+ * Therefore we switch the stack only after everything is copied over.
+ */
+.macro SWITCH_TO_ENTRY_STACK
+
+	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+	/* Bytes to copy */
+	movl	$PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+	testl	$(X86_EFLAGS_VM), PT_EFLAGS(%esp)
+	jz	.Lcopy_pt_regs_\@
+
+	/* Additional 4 registers to copy when returning to VM86 mode */
+	addl    $(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+	/* Initialize source and destination for movsl */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+	subl	%ecx, %edi
+	movl	%esp, %esi
+
+	/* Save future stack pointer in %ebx */
+	movl	%edi, %ebx
+
+	/* Copy over the stack-frame */
+	shrl	$2, %ecx
+	cld
+	rep movsl
+
+	/*
+	 * Switch to entry-stack - needs to happen after everything is
+	 * copied because the NMI handler will overwrite the task-stack
+	 * when on entry-stack
+	 */
+	movl	%ebx, %esp
+
+.Lend_\@:
+.endm
+
+/*
+ * This macro handles the case when we return to kernel-mode on the iret
+ * path and have to switch back to the entry stack and/or user-cr3
+ *
+ * See the comments below the .Lentry_from_kernel_\@ label in the
+ * SWITCH_TO_KERNEL_STACK macro for more details.
+ */
+.macro PARANOID_EXIT_TO_KERNEL_MODE
+
+	/*
+	 * Test if we entered the kernel with the entry-stack. Most
+	 * likely we did not, because this code only runs on the
+	 * return-to-kernel path.
+	 */
+	testl	$CS_FROM_ENTRY_STACK, PT_CS(%esp)
+	jz	.Lend_\@
+
+	/* Unlikely slow-path */
+
+	/* Clear marker from stack-frame */
+	andl	$(~CS_FROM_ENTRY_STACK), PT_CS(%esp)
+
+	/* Copy the remaining task-stack contents to entry-stack */
+	movl	%esp, %esi
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+
+	/* Bytes on the task-stack to ecx */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %ecx
+	subl	%esi, %ecx
+
+	/* Allocate stack-frame on entry-stack */
+	subl	%ecx, %edi
+
+	/*
+	 * Save future stack-pointer, we must not switch until the
+	 * copy is done, otherwise the NMI handler could destroy the
+	 * contents of the task-stack we are about to copy.
+	 */
+	movl	%edi, %ebx
+
+	/* Do the copy */
+	shrl	$2, %ecx
+	cld
+	rep movsl
+
+	/* Safe to switch to entry-stack now */
+	movl	%ebx, %esp
+
+	/*
+	 * We came from entry-stack and need to check if we also need to
+	 * switch back to user cr3.
+	 */
+	testl	$CS_FROM_USER_CR3, PT_CS(%esp)
+	jz	.Lend_\@
+
+	/* Clear marker from stack-frame */
+	andl	$(~CS_FROM_USER_CR3), PT_CS(%esp)
+
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+.Lend_\@:
+.endm
 /*
  * %eax: prev task
  * %edx: next task
@@ -351,9 +764,9 @@ ENTRY(resume_kernel)
 	DISABLE_INTERRUPTS(CLBR_ANY)
 .Lneed_resched:
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
-	jnz	restore_all
+	jnz	restore_all_kernel
 	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
-	jz	restore_all
+	jz	restore_all_kernel
 	call	preempt_schedule_irq
 	jmp	.Lneed_resched
 END(resume_kernel)
@@ -412,7 +825,21 @@ ENTRY(xen_sysenter_target)
  * 0(%ebp) arg6
  */
 ENTRY(entry_SYSENTER_32)
-	movl	TSS_sysenter_sp0(%esp), %esp
+	/*
+	 * On entry-stack with all userspace-regs live - save and
+	 * restore eflags and %eax to use it as scratch-reg for the cr3
+	 * switch.
+	 */
+	pushfl
+	pushl	%eax
+	BUG_IF_WRONG_CR3 no_user_check=1
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+	popl	%eax
+	popfl
+
+	/* Stack empty again, switch to task stack */
+	movl	TSS_entry2task_stack(%esp), %esp
+
 .Lsysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
 	pushl	%ebp			/* pt_regs->sp (stashed in bp) */
@@ -421,7 +848,7 @@ ENTRY(entry_SYSENTER_32)
 	pushl	$__USER_CS		/* pt_regs->cs */
 	pushl	$0			/* pt_regs->ip = 0 (placeholder) */
 	pushl	%eax			/* pt_regs->orig_ax */
-	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
+	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest, stack already switched */
 
 	/*
 	 * SYSENTER doesn't filter flags, so we need to clear NT, AC
@@ -460,25 +887,49 @@ ENTRY(entry_SYSENTER_32)
 
 /* Opportunistic SYSEXIT */
 	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+
+	/*
+	 * Setup entry stack - we keep the pointer in %eax and do the
+	 * switch after almost all user-state is restored.
+	 */
+
+	/* Load entry stack pointer and allocate frame for eflags/eax */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %eax
+	subl	$(2*4), %eax
+
+	/* Copy eflags and eax to entry stack */
+	movl	PT_EFLAGS(%esp), %edi
+	movl	PT_EAX(%esp), %esi
+	movl	%edi, (%eax)
+	movl	%esi, 4(%eax)
+
+	/* Restore user registers and segments */
 	movl	PT_EIP(%esp), %edx	/* pt_regs->ip */
 	movl	PT_OLDESP(%esp), %ecx	/* pt_regs->sp */
 1:	mov	PT_FS(%esp), %fs
 	PTGS_TO_GS
+
 	popl	%ebx			/* pt_regs->bx */
 	addl	$2*4, %esp		/* skip pt_regs->cx and pt_regs->dx */
 	popl	%esi			/* pt_regs->si */
 	popl	%edi			/* pt_regs->di */
 	popl	%ebp			/* pt_regs->bp */
-	popl	%eax			/* pt_regs->ax */
+
+	/* Switch to entry stack */
+	movl	%eax, %esp
+
+	/* Now ready to switch the cr3 */
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
 
 	/*
 	 * Restore all flags except IF. (We restore IF separately because
 	 * STI gives a one-instruction window in which we won't be interrupted,
 	 * whereas POPF does not.)
 	 */
-	addl	$PT_EFLAGS-PT_DS, %esp	/* point esp at pt_regs->flags */
 	btrl	$X86_EFLAGS_IF_BIT, (%esp)
+	BUG_IF_WRONG_CR3 no_user_check=1
 	popfl
+	popl	%eax
 
 	/*
 	 * Return back to the vDSO, which will pop ecx and edx.
@@ -532,7 +983,8 @@ ENDPROC(entry_SYSENTER_32)
 ENTRY(entry_INT80_32)
 	ASM_CLAC
 	pushl	%eax			/* pt_regs->orig_ax */
-	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
+
+	SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1	/* save rest */
 
 	/*
 	 * User mode is traced as though IRQs are on, and the interrupt gate
@@ -546,24 +998,17 @@ ENTRY(entry_INT80_32)
 
 restore_all:
 	TRACE_IRQS_IRET
+	SWITCH_TO_ENTRY_STACK
 .Lrestore_all_notrace:
-#ifdef CONFIG_X86_ESPFIX32
-	ALTERNATIVE	"jmp .Lrestore_nocheck", "", X86_BUG_ESPFIX
-
-	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
-	/*
-	 * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
-	 * are returning to the kernel.
-	 * See comments in process.c:copy_thread() for details.
-	 */
-	movb	PT_OLDSS(%esp), %ah
-	movb	PT_CS(%esp), %al
-	andl	$(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
-	cmpl	$((SEGMENT_LDT << 8) | USER_RPL), %eax
-	je .Lldt_ss				# returning to user-space with LDT SS
-#endif
+	CHECK_AND_APPLY_ESPFIX
 .Lrestore_nocheck:
-	RESTORE_REGS 4				# skip orig_eax/error_code
+	/* Switch back to user CR3 */
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+	BUG_IF_WRONG_CR3
+
+	/* Restore user state */
+	RESTORE_REGS pop=4			# skip orig_eax/error_code
 .Lirq_return:
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
@@ -572,46 +1017,33 @@ restore_all:
 	 */
 	INTERRUPT_RETURN
 
+restore_all_kernel:
+	TRACE_IRQS_IRET
+	PARANOID_EXIT_TO_KERNEL_MODE
+	BUG_IF_WRONG_CR3
+	RESTORE_REGS 4
+	jmp	.Lirq_return
+
 .section .fixup, "ax"
 ENTRY(iret_exc	)
 	pushl	$0				# no error code
 	pushl	$do_iret_error
-	jmp	common_exception
-.previous
-	_ASM_EXTABLE(.Lirq_return, iret_exc)
 
-#ifdef CONFIG_X86_ESPFIX32
-.Lldt_ss:
-/*
- * Setup and switch to ESPFIX stack
- *
- * We're returning to userspace with a 16 bit stack. The CPU will not
- * restore the high word of ESP for us on executing iret... This is an
- * "official" bug of all the x86-compatible CPUs, which we can work
- * around to make dosemu and wine happy. We do this by preloading the
- * high word of ESP with the high word of the userspace ESP while
- * compensating for the offset by changing to the ESPFIX segment with
- * a base address that matches for the difference.
- */
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
-	mov	%esp, %edx			/* load kernel esp */
-	mov	PT_OLDESP(%esp), %eax		/* load userspace esp */
-	mov	%dx, %ax			/* eax: new kernel esp */
-	sub	%eax, %edx			/* offset (low word is 0) */
-	shr	$16, %edx
-	mov	%dl, GDT_ESPFIX_SS + 4		/* bits 16..23 */
-	mov	%dh, GDT_ESPFIX_SS + 7		/* bits 24..31 */
-	pushl	$__ESPFIX_SS
-	pushl	%eax				/* new kernel esp */
+#ifdef CONFIG_DEBUG_ENTRY
 	/*
-	 * Disable interrupts, but do not irqtrace this section: we
-	 * will soon execute iret and the tracer was already set to
-	 * the irqstate after the IRET:
+	 * The stack-frame here is the one that iret faulted on, so its a
+	 * return-to-user frame. We are on kernel-cr3 because we come here from
+	 * the fixup code. This confuses the CR3 checker, so switch to user-cr3
+	 * as the checker expects it.
 	 */
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	lss	(%esp), %esp			/* switch to espfix segment */
-	jmp	.Lrestore_nocheck
+	pushl	%eax
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+	popl	%eax
 #endif
+
+	jmp	common_exception
+.previous
+	_ASM_EXTABLE(.Lirq_return, iret_exc)
 ENDPROC(entry_INT80_32)
 
 .macro FIXUP_ESPFIX_STACK
@@ -671,7 +1103,8 @@ END(irq_entries_start)
 common_interrupt:
 	ASM_CLAC
 	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
-	SAVE_ALL
+
+	SAVE_ALL switch_stacks=1
 	ENCODE_FRAME_POINTER
 	TRACE_IRQS_OFF
 	movl	%esp, %eax
@@ -679,16 +1112,16 @@ common_interrupt:
 	jmp	ret_from_intr
 ENDPROC(common_interrupt)
 
-#define BUILD_INTERRUPT3(name, nr, fn)	\
-ENTRY(name)				\
-	ASM_CLAC;			\
-	pushl	$~(nr);			\
-	SAVE_ALL;			\
-	ENCODE_FRAME_POINTER;		\
-	TRACE_IRQS_OFF			\
-	movl	%esp, %eax;		\
-	call	fn;			\
-	jmp	ret_from_intr;		\
+#define BUILD_INTERRUPT3(name, nr, fn)			\
+ENTRY(name)						\
+	ASM_CLAC;					\
+	pushl	$~(nr);					\
+	SAVE_ALL switch_stacks=1;			\
+	ENCODE_FRAME_POINTER;				\
+	TRACE_IRQS_OFF					\
+	movl	%esp, %eax;				\
+	call	fn;					\
+	jmp	ret_from_intr;				\
 ENDPROC(name)
 
 #define BUILD_INTERRUPT(name, nr)		\
@@ -920,16 +1353,20 @@ common_exception:
 	pushl	%es
 	pushl	%ds
 	pushl	%eax
+	movl	$(__USER_DS), %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	$(__KERNEL_PERCPU), %eax
+	movl	%eax, %fs
 	pushl	%ebp
 	pushl	%edi
 	pushl	%esi
 	pushl	%edx
 	pushl	%ecx
 	pushl	%ebx
+	SWITCH_TO_KERNEL_STACK
 	ENCODE_FRAME_POINTER
 	cld
-	movl	$(__KERNEL_PERCPU), %ecx
-	movl	%ecx, %fs
 	UNWIND_ESPFIX_STACK
 	GS_TO_REG %ecx
 	movl	PT_GS(%esp), %edi		# get the function address
@@ -937,9 +1374,6 @@ common_exception:
 	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
 	REG_TO_PTGS %ecx
 	SET_KERNEL_GS %ecx
-	movl	$(__USER_DS), %ecx
-	movl	%ecx, %ds
-	movl	%ecx, %es
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
 	CALL_NOSPEC %edi
@@ -948,40 +1382,12 @@ END(common_exception)
 
 ENTRY(debug)
 	/*
-	 * #DB can happen at the first instruction of
-	 * entry_SYSENTER_32 or in Xen's SYSENTER prologue.  If this
-	 * happens, then we will be running on a very small stack.  We
-	 * need to detect this condition and switch to the thread
-	 * stack before calling any C code at all.
-	 *
-	 * If you edit this code, keep in mind that NMIs can happen in here.
+	 * Entry from sysenter is now handled in common_exception
 	 */
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
-	SAVE_ALL
-	ENCODE_FRAME_POINTER
-	xorl	%edx, %edx			# error code 0
-	movl	%esp, %eax			# pt_regs pointer
-
-	/* Are we currently on the SYSENTER stack? */
-	movl	PER_CPU_VAR(cpu_entry_area), %ecx
-	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
-	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
-	cmpl	$SIZEOF_entry_stack, %ecx
-	jb	.Ldebug_from_sysenter_stack
-
-	TRACE_IRQS_OFF
-	call	do_debug
-	jmp	ret_from_exception
-
-.Ldebug_from_sysenter_stack:
-	/* We're on the SYSENTER stack.  Switch off. */
-	movl	%esp, %ebx
-	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
-	TRACE_IRQS_OFF
-	call	do_debug
-	movl	%ebx, %esp
-	jmp	ret_from_exception
+	pushl	$do_debug
+	jmp	common_exception
 END(debug)
 
 /*
@@ -993,6 +1399,7 @@ END(debug)
  */
 ENTRY(nmi)
 	ASM_CLAC
+
 #ifdef CONFIG_X86_ESPFIX32
 	pushl	%eax
 	movl	%ss, %eax
@@ -1002,7 +1409,7 @@ ENTRY(nmi)
 #endif
 
 	pushl	%eax				# pt_regs->orig_ax
-	SAVE_ALL
+	SAVE_ALL_NMI cr3_reg=%edi
 	ENCODE_FRAME_POINTER
 	xorl	%edx, %edx			# zero error code
 	movl	%esp, %eax			# pt_regs pointer
@@ -1016,7 +1423,7 @@ ENTRY(nmi)
 
 	/* Not on SYSENTER stack. */
 	call	do_nmi
-	jmp	.Lrestore_all_notrace
+	jmp	.Lnmi_return
 
 .Lnmi_from_sysenter_stack:
 	/*
@@ -1027,7 +1434,11 @@ ENTRY(nmi)
 	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
 	call	do_nmi
 	movl	%ebx, %esp
-	jmp	.Lrestore_all_notrace
+
+.Lnmi_return:
+	CHECK_AND_APPLY_ESPFIX
+	RESTORE_ALL_NMI cr3_reg=%edi pop=4
+	jmp	.Lirq_return
 
 #ifdef CONFIG_X86_ESPFIX32
 .Lnmi_espfix_stack:
@@ -1042,12 +1453,12 @@ ENTRY(nmi)
 	pushl	16(%esp)
 	.endr
 	pushl	%eax
-	SAVE_ALL
+	SAVE_ALL_NMI cr3_reg=%edi
 	ENCODE_FRAME_POINTER
 	FIXUP_ESPFIX_STACK			# %eax == %esp
 	xorl	%edx, %edx			# zero error code
 	call	do_nmi
-	RESTORE_REGS
+	RESTORE_ALL_NMI cr3_reg=%edi
 	lss	12+4(%esp), %esp		# back to espfix stack
 	jmp	.Lirq_return
 #endif
@@ -1056,7 +1467,8 @@ END(nmi)
 ENTRY(int3)
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
-	SAVE_ALL
+
+	SAVE_ALL switch_stacks=1
 	ENCODE_FRAME_POINTER
 	TRACE_IRQS_OFF
 	xorl	%edx, %edx			# zero error code
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8ae7ffda8f98..957dfb693ecc 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -92,7 +92,7 @@ END(native_usergs_sysret64)
 .endm
 
 .macro TRACE_IRQS_IRETQ_DEBUG
-	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
+	btl	$9, EFLAGS(%rsp)		/* interrupts off? */
 	jnc	1f
 	TRACE_IRQS_ON_DEBUG
 1:
@@ -408,6 +408,7 @@ ENTRY(ret_from_fork)
 
 1:
 	/* kernel thread */
+	UNWIND_HINT_EMPTY
 	movq	%r12, %rdi
 	CALL_NOSPEC %rbx
 	/*
@@ -701,7 +702,7 @@ retint_kernel:
 #ifdef CONFIG_PREEMPT
 	/* Interrupts are off */
 	/* Check if we need preemption */
-	bt	$9, EFLAGS(%rsp)		/* were interrupts off? */
+	btl	$9, EFLAGS(%rsp)		/* were interrupts off? */
 	jnc	1f
 0:	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	1f
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 261802b1cc50..9f695f517747 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -46,10 +46,8 @@ targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
 
 CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
-			-Wl,--no-undefined \
-			-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
-			$(DISABLE_LTO)
+VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
+			-z max-page-size=4096 -z common-page-size=4096
 
 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
@@ -58,9 +56,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(src
 hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@
-define cmd_vdso2c
-	$(obj)/vdso2c $< $(<:%.dbg=%) $@
-endef
+      cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@
 
 $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 	$(call if_changed,vdso2c)
@@ -95,10 +91,8 @@ CFLAGS_REMOVE_vvar.o = -pg
 #
 
 CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
-			   -Wl,-soname=linux-vdso.so.1 \
-			   -Wl,-z,max-page-size=4096 \
-			   -Wl,-z,common-page-size=4096
+VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \
+			   -z max-page-size=4096 -z common-page-size=4096
 
 # x32-rebranded versions
 vobjx32s-y := $(vobjs-y:.o=-x32.o)
@@ -123,7 +117,7 @@ $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
 	$(call if_changed,vdso)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
+VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
 
 targets += vdso32/vdso32.lds
 targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
@@ -157,13 +151,13 @@ $(obj)/vdso32.so.dbg: FORCE \
 # The DSO images are built using a special linker script.
 #
 quiet_cmd_vdso = VDSO    $@
-      cmd_vdso = $(CC) -nostdlib -o $@ \
+      cmd_vdso = $(LD) -nostdlib -o $@ \
 		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
+		       -T $(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \
-	$(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS)
+VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \
+	$(call ld-option, --build-id) -Bsymbolic
 GCOV_PROFILE := n
 
 #
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 86f0c15dcc2d..035c37481f57 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2041,15 +2041,15 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
-
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
@@ -2068,17 +2068,19 @@ static void intel_pmu_read_event(struct perf_event *event)
 		x86_perf_event_update(event);
 }
 
-static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
-	u64 ctrl_val, bits, mask;
+	u64 ctrl_val, mask, bits = 0;
 
 	/*
-	 * Enable IRQ generation (0x8),
+	 * Enable IRQ generation (0x8), if not PEBS,
 	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
 	 * if requested:
 	 */
-	bits = 0x8ULL;
+	if (!event->attr.precise_ip)
+		bits |= 0x8;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
 		bits |= 0x2;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
@@ -2120,14 +2122,14 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	if (unlikely(event_is_checkpointed(event)))
 		cpuc->intel_cp_status |= (1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_enable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_enable_fixed(hwc);
+		intel_pmu_enable_fixed(event);
 		return;
 	}
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_enable(event);
-
 	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
@@ -2280,7 +2282,10 @@ again:
 	 * counters from the GLOBAL_STATUS mask and we always process PEBS
 	 * events via drain_pebs().
 	 */
-	status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		status &= ~cpuc->pebs_enabled;
+	else
+		status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
@@ -4072,7 +4077,6 @@ __init int intel_pmu_init(void)
 		intel_pmu_lbr_init_skl();
 
 		x86_pmu.event_constraints = intel_slm_event_constraints;
-		x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_glm_extra_regs;
 		/*
 		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
@@ -4082,6 +4086,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.lbr_pt_coexist = true;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.get_event_constraints = glp_get_event_constraints;
 		x86_pmu.cpu_events = glm_events_attrs;
 		/* Goldmont Plus has 4-wide pipeline */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8dbba77e0518..b7b01d762d32 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -713,12 +713,6 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_glp_pebs_event_constraints[] = {
-	/* Allow all events as PEBS with no flags */
-	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
-	EVENT_CONSTRAINT_END
-};
-
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
@@ -871,6 +865,13 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 		}
 	}
 
+	/*
+	 * Extended PEBS support
+	 * Makes the PEBS code search the normal constraints.
+	 */
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		return NULL;
+
 	return &emptyconstraint;
 }
 
@@ -896,10 +897,16 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
 	u64 threshold;
+	int reserved;
+
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
+	else
+		reserved = x86_pmu.max_pebs_events;
 
 	if (cpuc->n_pebs == cpuc->n_large_pebs) {
 		threshold = ds->pebs_absolute_maximum -
-			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+			reserved * x86_pmu.pebs_record_size;
 	} else {
 		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
 	}
@@ -963,7 +970,11 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
 	 */
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		ds->pebs_event_reset[hwc->idx] =
+		unsigned int idx = hwc->idx;
+
+		if (idx >= INTEL_PMC_IDX_FIXED)
+			idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+		ds->pebs_event_reset[idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
 	} else {
 		ds->pebs_event_reset[hwc->idx] = 0;
@@ -1481,9 +1492,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event;
 	void *base, *at, *top;
-	short counts[MAX_PEBS_EVENTS] = {};
-	short error[MAX_PEBS_EVENTS] = {};
-	int bit, i;
+	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	int bit, i, size;
+	u64 mask;
 
 	if (!x86_pmu.pebs_active)
 		return;
@@ -1493,6 +1505,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
+	mask = (1ULL << x86_pmu.max_pebs_events) - 1;
+	size = x86_pmu.max_pebs_events;
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
+		mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
+		size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+	}
+
 	if (unlikely(base >= top)) {
 		/*
 		 * The drain_pebs() could be called twice in a short period
@@ -1502,7 +1521,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		 * update the event->count for this case.
 		 */
 		for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
-				 x86_pmu.max_pebs_events) {
+				 size) {
 			event = cpuc->events[bit];
 			if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
 				intel_pmu_save_and_restart_reload(event, 0);
@@ -1515,12 +1534,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		u64 pebs_status;
 
 		pebs_status = p->status & cpuc->pebs_enabled;
-		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+		pebs_status &= mask;
 
 		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
 			for_each_set_bit(bit, (unsigned long *)&pebs_status,
-					 x86_pmu.max_pebs_events)
+					 size)
 				counts[bit]++;
 
 			continue;
@@ -1568,7 +1587,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		counts[bit]++;
 	}
 
-	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+	for (bit = 0; bit < size; bit++) {
 		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index cf372b90557e..f3e006bed9a7 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -216,6 +216,8 @@ static void intel_pmu_lbr_reset_64(void)
 
 void intel_pmu_lbr_reset(void)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
 	if (!x86_pmu.lbr_nr)
 		return;
 
@@ -223,6 +225,9 @@ void intel_pmu_lbr_reset(void)
 		intel_pmu_lbr_reset_32();
 	else
 		intel_pmu_lbr_reset_64();
+
+	cpuc->last_task_ctx = NULL;
+	cpuc->last_log_id = 0;
 }
 
 /*
@@ -334,6 +339,7 @@ static inline u64 rdlbr_to(unsigned int idx)
 
 static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 	unsigned lbr_idx, mask;
 	u64 tos;
@@ -344,9 +350,21 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		return;
 	}
 
-	mask = x86_pmu.lbr_nr - 1;
 	tos = task_ctx->tos;
-	for (i = 0; i < tos; i++) {
+	/*
+	 * Does not restore the LBR registers, if
+	 * - No one else touched them, and
+	 * - Did not enter C6
+	 */
+	if ((task_ctx == cpuc->last_task_ctx) &&
+	    (task_ctx->log_id == cpuc->last_log_id) &&
+	    rdlbr_from(tos)) {
+		task_ctx->lbr_stack_state = LBR_NONE;
+		return;
+	}
+
+	mask = x86_pmu.lbr_nr - 1;
+	for (i = 0; i < task_ctx->valid_lbrs; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
 		wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
@@ -354,14 +372,24 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+
+	for (; i < x86_pmu.lbr_nr; i++) {
+		lbr_idx = (tos - i) & mask;
+		wrlbr_from(lbr_idx, 0);
+		wrlbr_to(lbr_idx, 0);
+		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0);
+	}
+
 	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
 
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned lbr_idx, mask;
-	u64 tos;
+	u64 tos, from;
 	int i;
 
 	if (task_ctx->lbr_callstack_users == 0) {
@@ -371,15 +399,22 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 	mask = x86_pmu.lbr_nr - 1;
 	tos = intel_pmu_lbr_tos();
-	for (i = 0; i < tos; i++) {
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		lbr_idx = (tos - i) & mask;
-		task_ctx->lbr_from[i] = rdlbr_from(lbr_idx);
+		from = rdlbr_from(lbr_idx);
+		if (!from)
+			break;
+		task_ctx->lbr_from[i] = from;
 		task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->valid_lbrs = i;
 	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
+
+	cpuc->last_task_ctx = task_ctx;
+	cpuc->last_log_id = ++task_ctx->log_id;
 }
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
@@ -531,7 +566,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
  */
 static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
-	bool need_info = false;
+	bool need_info = false, call_stack = false;
 	unsigned long mask = x86_pmu.lbr_nr - 1;
 	int lbr_format = x86_pmu.intel_cap.lbr_format;
 	u64 tos = intel_pmu_lbr_tos();
@@ -542,7 +577,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	if (cpuc->lbr_sel) {
 		need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
 		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
-			num = tos;
+			call_stack = true;
 	}
 
 	for (i = 0; i < num; i++) {
@@ -555,6 +590,13 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		from = rdlbr_from(lbr_idx);
 		to   = rdlbr_to(lbr_idx);
 
+		/*
+		 * Read LBR call stack entries
+		 * until invalid entry (0s) is detected.
+		 */
+		if (call_stack && !from)
+			break;
+
 		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
 
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 9f3711470ec1..156286335351 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -163,6 +163,7 @@ struct intel_excl_cntrs {
 	unsigned	core_id;	/* per-core: core id */
 };
 
+struct x86_perf_task_context;
 #define MAX_LBR_ENTRIES		32
 
 enum {
@@ -214,6 +215,8 @@ struct cpu_hw_events {
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
 	u64				br_sel;
+	struct x86_perf_task_context	*last_task_ctx;
+	int				last_log_id;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -648,8 +651,10 @@ struct x86_perf_task_context {
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
 	int tos;
+	int valid_lbrs;
 	int lbr_callstack_users;
 	int lbr_stack_state;
+	int log_id;
 };
 
 #define x86_add_quirk(func_)						\
@@ -668,6 +673,7 @@ do {									\
 #define PMU_FL_HAS_RSP_1	0x2 /* has 2 equivalent offcore_rsp regs   */
 #define PMU_FL_EXCL_CNTRS	0x4 /* has exclusive counter requirements  */
 #define PMU_FL_EXCL_ENABLED	0x8 /* exclusive counter active */
+#define PMU_FL_PEBS_ALL		0x10 /* all events are valid PEBS events */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 402338365651..5b0f613428c2 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -31,6 +31,8 @@
 #include <asm/mshyperv.h>
 #include <asm/apic.h>
 
+#include <asm/trace/hyperv.h>
+
 static struct apic orig_apic;
 
 static u64 hv_apic_icr_read(void)
@@ -99,6 +101,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 	int nr_bank = 0;
 	int ret = 1;
 
+	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+		return false;
+
 	local_irq_save(flags);
 	arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
 
@@ -130,10 +135,10 @@ ipi_mask_ex_done:
 static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 {
 	int cur_cpu, vcpu;
-	struct ipi_arg_non_ex **arg;
-	struct ipi_arg_non_ex *ipi_arg;
+	struct ipi_arg_non_ex ipi_arg;
 	int ret = 1;
-	unsigned long flags;
+
+	trace_hyperv_send_ipi_mask(mask, vector);
 
 	if (cpumask_empty(mask))
 		return true;
@@ -144,40 +149,43 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
 		return false;
 
-	if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-		return __send_ipi_mask_ex(mask, vector);
-
-	local_irq_save(flags);
-	arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
-
-	ipi_arg = *arg;
-	if (unlikely(!ipi_arg))
-		goto ipi_mask_done;
-
-	ipi_arg->vector = vector;
-	ipi_arg->reserved = 0;
-	ipi_arg->cpu_mask = 0;
+	/*
+	 * From the supplied CPU set we need to figure out if we can get away
+	 * with cheaper HVCALL_SEND_IPI hypercall. This is possible when the
+	 * highest VP number in the set is < 64. As VP numbers are usually in
+	 * ascending order and match Linux CPU ids, here is an optimization:
+	 * we check the VP number for the highest bit in the supplied set first
+	 * so we can quickly find out if using HVCALL_SEND_IPI_EX hypercall is
+	 * a must. We will also check all VP numbers when walking the supplied
+	 * CPU set to remain correct in all cases.
+	 */
+	if (hv_cpu_number_to_vp_number(cpumask_last(mask)) >= 64)
+		goto do_ex_hypercall;
+
+	ipi_arg.vector = vector;
+	ipi_arg.cpu_mask = 0;
 
 	for_each_cpu(cur_cpu, mask) {
 		vcpu = hv_cpu_number_to_vp_number(cur_cpu);
 		if (vcpu == VP_INVAL)
-			goto ipi_mask_done;
+			return false;
 
 		/*
 		 * This particular version of the IPI hypercall can
 		 * only target upto 64 CPUs.
 		 */
 		if (vcpu >= 64)
-			goto ipi_mask_done;
+			goto do_ex_hypercall;
 
-		__set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask);
+		__set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask);
 	}
 
-	ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL);
-
-ipi_mask_done:
-	local_irq_restore(flags);
+	ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector,
+				     ipi_arg.cpu_mask);
 	return ((ret == 0) ? true : false);
+
+do_ex_hypercall:
+	return __send_ipi_mask_ex(mask, vector);
 }
 
 static bool __send_ipi_one(int cpu, int vector)
@@ -233,10 +241,7 @@ static void hv_send_ipi_self(int vector)
 void __init hv_apic_init(void)
 {
 	if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) {
-		if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-			pr_info("Hyper-V: Using ext hypercalls for IPI\n");
-		else
-			pr_info("Hyper-V: Using IPI hypercalls\n");
+		pr_info("Hyper-V: Using IPI hypercalls\n");
 		/*
 		 * Set the IPI entry points.
 		 */
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index de27615c51ea..1147e1fed7ff 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -16,6 +16,8 @@
 /* Each gva in gva_list encodes up to 4096 pages to flush */
 #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
 
+static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+				      const struct flush_tlb_info *info);
 
 /*
  * Fills in gva_list starting from offset. Returns the number of items added.
@@ -93,10 +95,29 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	if (cpumask_equal(cpus, cpu_present_mask)) {
 		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
 	} else {
+		/*
+		 * From the supplied CPU set we need to figure out if we can get
+		 * away with cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}
+		 * hypercalls. This is possible when the highest VP number in
+		 * the set is < 64. As VP numbers are usually in ascending order
+		 * and match Linux CPU ids, here is an optimization: we check
+		 * the VP number for the highest bit in the supplied set first
+		 * so we can quickly find out if using *_EX hypercalls is a
+		 * must. We will also check all VP numbers when walking the
+		 * supplied CPU set to remain correct in all cases.
+		 */
+		if (hv_cpu_number_to_vp_number(cpumask_last(cpus)) >= 64)
+			goto do_ex_hypercall;
+
 		for_each_cpu(cpu, cpus) {
 			vcpu = hv_cpu_number_to_vp_number(cpu);
-			if (vcpu >= 64)
+			if (vcpu == VP_INVAL) {
+				local_irq_restore(flags);
 				goto do_native;
+			}
+
+			if (vcpu >= 64)
+				goto do_ex_hypercall;
 
 			__set_bit(vcpu, (unsigned long *)
 				  &flush->processor_mask);
@@ -123,7 +144,12 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 		status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST,
 					     gva_n, 0, flush, NULL);
 	}
+	goto check_status;
+
+do_ex_hypercall:
+	status = hyperv_flush_tlb_others_ex(cpus, info);
 
+check_status:
 	local_irq_restore(flags);
 
 	if (!(status & HV_HYPERCALL_RESULT_MASK))
@@ -132,35 +158,22 @@ do_native:
 	native_flush_tlb_others(cpus, info);
 }
 
-static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
-				       const struct flush_tlb_info *info)
+static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+				      const struct flush_tlb_info *info)
 {
 	int nr_bank = 0, max_gvas, gva_n;
 	struct hv_tlb_flush_ex **flush_pcpu;
 	struct hv_tlb_flush_ex *flush;
-	u64 status = U64_MAX;
-	unsigned long flags;
+	u64 status;
 
-	trace_hyperv_mmu_flush_tlb_others(cpus, info);
-
-	if (!hv_hypercall_pg)
-		goto do_native;
-
-	if (cpumask_empty(cpus))
-		return;
-
-	local_irq_save(flags);
+	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+		return U64_MAX;
 
 	flush_pcpu = (struct hv_tlb_flush_ex **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
 
 	flush = *flush_pcpu;
 
-	if (unlikely(!flush)) {
-		local_irq_restore(flags);
-		goto do_native;
-	}
-
 	if (info->mm) {
 		/*
 		 * AddressSpace argument must match the CR3 with PCID bits
@@ -176,15 +189,10 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 
 	flush->hv_vp_set.valid_bank_mask = 0;
 
-	if (!cpumask_equal(cpus, cpu_present_mask)) {
-		flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
-		nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
-	}
-
-	if (!nr_bank) {
-		flush->hv_vp_set.format = HV_GENERIC_SET_ALL;
-		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
-	}
+	flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+	nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
+	if (nr_bank < 0)
+		return U64_MAX;
 
 	/*
 	 * We can flush not more than max_gvas with one hypercall. Flush the
@@ -213,12 +221,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 			gva_n, nr_bank, flush, NULL);
 	}
 
-	local_irq_restore(flags);
-
-	if (!(status & HV_HYPERCALL_RESULT_MASK))
-		return;
-do_native:
-	native_flush_tlb_others(cpus, info);
+	return status;
 }
 
 void hyperv_setup_mmu_ops(void)
@@ -226,11 +229,6 @@ void hyperv_setup_mmu_ops(void)
 	if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
 		return;
 
-	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) {
-		pr_info("Using hypercall for remote TLB flush\n");
-		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
-	} else {
-		pr_info("Using ext hypercall for remote TLB flush\n");
-		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex;
-	}
+	pr_info("Using hypercall for remote TLB flush\n");
+	pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
 }
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 74a9e06b6cfd..130e81e10fc7 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -10,6 +10,7 @@
 #include <asm/fixmap.h>
 #include <asm/mpspec.h>
 #include <asm/msr.h>
+#include <asm/hardirq.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
 
@@ -502,12 +503,19 @@ extern int default_check_phys_apicid_present(int phys_apicid);
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
+#ifdef CONFIG_SMP
+bool apic_id_is_primary_thread(unsigned int id);
+#else
+static inline bool apic_id_is_primary_thread(unsigned int id) { return false; }
+#endif
+
 extern void irq_enter(void);
 extern void irq_exit(void);
 
 static inline void entering_irq(void)
 {
 	irq_enter();
+	kvm_set_cpu_l1tf_flush_l1d();
 }
 
 static inline void entering_ack_irq(void)
@@ -520,6 +528,7 @@ static inline void ipi_entering_ack_irq(void)
 {
 	irq_enter();
 	ack_APIC_irq();
+	kvm_set_cpu_l1tf_flush_l1d();
 }
 
 static inline void exiting_irq(void)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 0db6bec95489..b143717b92b3 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -80,6 +80,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic_sub_and_test arch_atomic_sub_and_test
 static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
@@ -91,6 +92,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic_inc arch_atomic_inc
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
@@ -103,6 +105,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic_dec arch_atomic_dec
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
@@ -117,6 +120,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
+#define arch_atomic_dec_and_test arch_atomic_dec_and_test
 static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
@@ -130,6 +134,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic_inc_and_test arch_atomic_inc_and_test
 static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
@@ -144,6 +149,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
+#define arch_atomic_add_negative arch_atomic_add_negative
 static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
@@ -173,9 +179,6 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
 	return arch_atomic_add_return(-i, v);
 }
 
-#define arch_atomic_inc_return(v)  (arch_atomic_add_return(1, v))
-#define arch_atomic_dec_return(v)  (arch_atomic_sub_return(1, v))
-
 static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
 {
 	return xadd(&v->counter, i);
@@ -199,7 +202,7 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n
 
 static inline int arch_atomic_xchg(atomic_t *v, int new)
 {
-	return xchg(&v->counter, new);
+	return arch_xchg(&v->counter, new);
 }
 
 static inline void arch_atomic_and(int i, atomic_t *v)
@@ -253,27 +256,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
 	return val;
 }
 
-/**
- * __arch_atomic_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns the old value of @v.
- */
-static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c = arch_atomic_read(v);
-
-	do {
-		if (unlikely(c == u))
-			break;
-	} while (!arch_atomic_try_cmpxchg(v, &c, c + a));
-
-	return c;
-}
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 92212bf0484f..ef959f02d070 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -158,6 +158,7 @@ static inline long long arch_atomic64_inc_return(atomic64_t *v)
 			     "S" (v) : "memory", "ecx");
 	return a;
 }
+#define arch_atomic64_inc_return arch_atomic64_inc_return
 
 static inline long long arch_atomic64_dec_return(atomic64_t *v)
 {
@@ -166,6 +167,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v)
 			     "S" (v) : "memory", "ecx");
 	return a;
 }
+#define arch_atomic64_dec_return arch_atomic64_dec_return
 
 /**
  * arch_atomic64_add - add integer to atomic64 variable
@@ -198,25 +200,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
 }
 
 /**
- * arch_atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v)
-{
-	return arch_atomic64_sub_return(i, v) == 0;
-}
-
-/**
  * arch_atomic64_inc - increment atomic64 variable
  * @v: pointer to type atomic64_t
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic64_inc arch_atomic64_inc
 static inline void arch_atomic64_inc(atomic64_t *v)
 {
 	__alternative_atomic64(inc, inc_return, /* no output */,
@@ -229,6 +218,7 @@ static inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic64_dec arch_atomic64_dec
 static inline void arch_atomic64_dec(atomic64_t *v)
 {
 	__alternative_atomic64(dec, dec_return, /* no output */,
@@ -236,46 +226,6 @@ static inline void arch_atomic64_dec(atomic64_t *v)
 }
 
 /**
- * arch_atomic64_dec_and_test - decrement and test
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int arch_atomic64_dec_and_test(atomic64_t *v)
-{
-	return arch_atomic64_dec_return(v) == 0;
-}
-
-/**
- * atomic64_inc_and_test - increment and test
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_inc_and_test(atomic64_t *v)
-{
-	return arch_atomic64_inc_return(v) == 0;
-}
-
-/**
- * arch_atomic64_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int arch_atomic64_add_negative(long long i, atomic64_t *v)
-{
-	return arch_atomic64_add_return(i, v) < 0;
-}
-
-/**
  * arch_atomic64_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
@@ -295,7 +245,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
 	return (int)a;
 }
 
-
+#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
 static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
@@ -304,6 +254,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 	return r;
 }
 
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
 static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	long long r;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 6106b59d3260..4343d9b4f30e 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -71,6 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
 static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
@@ -82,6 +83,7 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic64_inc arch_atomic64_inc
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
@@ -95,6 +97,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic64_dec arch_atomic64_dec
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
@@ -110,6 +113,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
+#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
 static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
@@ -123,6 +127,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
 static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
@@ -137,6 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
+#define arch_atomic64_add_negative arch_atomic64_add_negative
 static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
@@ -169,9 +175,6 @@ static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v)
 	return xadd(&v->counter, -i);
 }
 
-#define arch_atomic64_inc_return(v)  (arch_atomic64_add_return(1, (v)))
-#define arch_atomic64_dec_return(v)  (arch_atomic64_sub_return(1, (v)))
-
 static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
 {
 	return arch_cmpxchg(&v->counter, old, new);
@@ -185,46 +188,7 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, l
 
 static inline long arch_atomic64_xchg(atomic64_t *v, long new)
 {
-	return xchg(&v->counter, new);
-}
-
-/**
- * arch_atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	s64 c = arch_atomic64_read(v);
-	do {
-		if (unlikely(c == u))
-			return false;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, c + a));
-	return true;
-}
-
-#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0)
-
-/*
- * arch_atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
-{
-	s64 dec, c = arch_atomic64_read(v);
-	do {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, dec));
-	return dec;
+	return arch_xchg(&v->counter, new);
 }
 
 static inline void arch_atomic64_and(long i, atomic64_t *v)
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index e3efd8a06066..a55d79b233d3 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -75,7 +75,7 @@ extern void __add_wrong_size(void)
  * use "asm volatile" and "memory" clobbers to prevent gcc from moving
  * information around.
  */
-#define xchg(ptr, v)	__xchg_op((ptr), (v), xchg, "")
+#define arch_xchg(ptr, v)	__xchg_op((ptr), (v), xchg, "")
 
 /*
  * Atomic compare and exchange.  Compare OLD with MEM, if identical,
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index bfca3b346c74..072e5459fe2f 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -10,13 +10,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 #define arch_cmpxchg64(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg((ptr), (o), (n));					\
+	arch_cmpxchg((ptr), (o), (n));					\
 })
 
 #define arch_cmpxchg64_local(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
+	arch_cmpxchg_local((ptr), (o), (n));				\
 })
 
 #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 5701f5cecd31..89a048c2faec 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -219,6 +219,8 @@
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
+#define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -229,7 +231,7 @@
 
 #define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
 #define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
-
+#define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -341,6 +343,7 @@
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
@@ -373,5 +376,6 @@
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h
index 0ab2ab27ad1f..b825cb201251 100644
--- a/arch/x86/include/asm/dmi.h
+++ b/arch/x86/include/asm/dmi.h
@@ -4,8 +4,8 @@
 
 #include <linux/compiler.h>
 #include <linux/init.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/setup.h>
 
 static __always_inline __init void *dmi_alloc(unsigned len)
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 740a428acf1e..d9069bb26c7f 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -3,10 +3,12 @@
 #define _ASM_X86_HARDIRQ_H
 
 #include <linux/threads.h>
-#include <linux/irq.h>
 
 typedef struct {
-	unsigned int __softirq_pending;
+	u16	     __softirq_pending;
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+	u8	     kvm_cpu_l1tf_flush_l1d;
+#endif
 	unsigned int __nmi_count;	/* arch dependent */
 #ifdef CONFIG_X86_LOCAL_APIC
 	unsigned int apic_timer_irqs;	/* arch dependent */
@@ -58,4 +60,24 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu);
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat		arch_irq_stat
 
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+static inline void kvm_set_cpu_l1tf_flush_l1d(void)
+{
+	__this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1);
+}
+
+static inline void kvm_clear_cpu_l1tf_flush_l1d(void)
+{
+	__this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 0);
+}
+
+static inline bool kvm_get_cpu_l1tf_flush_l1d(void)
+{
+	return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d);
+}
+#else /* !IS_ENABLED(CONFIG_KVM_INTEL) */
+static inline void kvm_set_cpu_l1tf_flush_l1d(void) { }
+#endif /* IS_ENABLED(CONFIG_KVM_INTEL) */
+
 #endif /* _ASM_X86_HARDIRQ_H */
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index f59c39835a5a..a1f0e90d0818 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -49,11 +49,14 @@ static inline int hw_breakpoint_slots(int type)
 	return HBP_NUM;
 }
 
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index cf090e584202..7ed08a7c3398 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -76,4 +76,17 @@
 #define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
 #define INTEL_FAM6_XEON_PHI_KNM		0x85 /* Knights Mill */
 
+/* Useful macros */
+#define INTEL_CPU_FAM_ANY(_family, _model, _driver_data)	\
+{								\
+	.vendor		= X86_VENDOR_INTEL,			\
+	.family		= _family,				\
+	.model		= _model,				\
+	.feature	= X86_FEATURE_ANY,			\
+	.driver_data	= (kernel_ulong_t)&_driver_data		\
+}
+
+#define INTEL_CPU_FAM6(_model, _driver_data)			\
+	INTEL_CPU_FAM_ANY(6, INTEL_FAM6_##_model, _driver_data)
+
 #endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index fe04491130ae..52f815a80539 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -80,35 +80,6 @@ enum intel_mid_cpu_type {
 
 extern enum intel_mid_cpu_type __intel_mid_cpu_chip;
 
-/**
- * struct intel_mid_ops - Interface between intel-mid & sub archs
- * @arch_setup: arch_setup function to re-initialize platform
- *		structures (x86_init, x86_platform_init)
- *
- * This structure can be extended if any new interface is required
- * between intel-mid & its sub arch files.
- */
-struct intel_mid_ops {
-	void (*arch_setup)(void);
-};
-
-/* Helper API's for INTEL_MID_OPS_INIT */
-#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid)				\
-	[cpuid] = get_##cpuname##_ops
-
-/* Maximum number of CPU ops */
-#define MAX_CPU_OPS(a)			(sizeof(a)/sizeof(void *))
-
-/*
- * For every new cpu addition, a weak get_<cpuname>_ops() function needs be
- * declared in arch/x86/platform/intel_mid/intel_mid_weak_decls.h.
- */
-#define INTEL_MID_OPS_INIT {							\
-	DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL),	\
-	DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW),	\
-	DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER)		\
-};
-
 #ifdef CONFIG_X86_INTEL_MID
 
 static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void)
@@ -136,20 +107,6 @@ enum intel_mid_timer_options {
 
 extern enum intel_mid_timer_options intel_mid_timer_options;
 
-/*
- * Penwell uses spread spectrum clock, so the freq number is not exactly
- * the same as reported by MSR based on SDM.
- */
-#define FSB_FREQ_83SKU			83200
-#define FSB_FREQ_100SKU			99840
-#define FSB_FREQ_133SKU			133000
-
-#define FSB_FREQ_167SKU			167000
-#define FSB_FREQ_200SKU			200000
-#define FSB_FREQ_267SKU			267000
-#define FSB_FREQ_333SKU			333000
-#define FSB_FREQ_400SKU			400000
-
 /* Bus Select SoC Fuse value */
 #define BSEL_SOC_FUSE_MASK		0x7
 /* FSB 133MHz */
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index 62a9f4966b42..ae26df1c2789 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -8,6 +8,7 @@
 
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS		8
+#define MAX_FIXED_PEBS_EVENTS	3
 
 /*
  * A debug store configuration.
@@ -23,7 +24,7 @@ struct debug_store {
 	u64	pebs_index;
 	u64	pebs_absolute_maximum;
 	u64	pebs_interrupt_threshold;
-	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+	u64	pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS];
 } __aligned(PAGE_SIZE);
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c4fc17220df9..c14f2a74b2be 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -13,6 +13,8 @@
  * Interrupt control:
  */
 
+/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */
+extern inline unsigned long native_save_fl(void);
 extern inline unsigned long native_save_fl(void)
 {
 	unsigned long flags;
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 367d99cff426..c8cec1b39b88 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -78,7 +78,7 @@ struct arch_specific_insn {
 	 * boostable = true: This instruction has been boosted: we have
 	 * added a relative jump after the instruction copy in insn,
 	 * so no single-step and fixup are needed (unless there's
-	 * a post_handler or break_handler).
+	 * a post_handler).
 	 */
 	bool boostable;
 	bool if_modifier;
@@ -111,9 +111,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_old_flags;
 	unsigned long kprobe_saved_flags;
-	unsigned long *jprobe_saved_sp;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/x86/include/asm/kvm_guest.h b/arch/x86/include/asm/kvm_guest.h
deleted file mode 100644
index 46185263d9c2..000000000000
--- a/arch/x86/include/asm/kvm_guest.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_KVM_GUEST_H
-#define _ASM_X86_KVM_GUEST_H
-
-int kvm_setup_vsyscall_timeinfo(void);
-
-#endif /* _ASM_X86_KVM_GUEST_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c13cd28d9d1b..acebb808c4b5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -17,6 +17,7 @@
 #include <linux/tracepoint.h>
 #include <linux/cpumask.h>
 #include <linux/irq_work.h>
+#include <linux/irq.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
@@ -713,6 +714,9 @@ struct kvm_vcpu_arch {
 
 	/* be preempted when it's in kernel-mode(cpl=0) */
 	bool preempted_in_kernel;
+
+	/* Flush the L1 Data cache for L1TF mitigation on VMENTER */
+	bool l1tf_flush_l1d;
 };
 
 struct kvm_lpage_info {
@@ -881,6 +885,7 @@ struct kvm_vcpu_stat {
 	u64 signal_exits;
 	u64 irq_window_exits;
 	u64 nmi_window_exits;
+	u64 l1d_flush;
 	u64 halt_exits;
 	u64 halt_successful_poll;
 	u64 halt_attempted_poll;
@@ -1413,6 +1418,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
 
+u64 kvm_get_arch_capabilities(void);
 void kvm_define_shared_msr(unsigned index, u32 msr);
 int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 3aea2658323a..4c723632c036 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -7,7 +7,6 @@
 #include <uapi/asm/kvm_para.h>
 
 extern void kvmclock_init(void);
-extern int kvm_register_clock(char *txt);
 
 #ifdef CONFIG_KVM_GUEST
 bool kvm_check_and_clear_guest_paused(void);
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index bbc796eb0a3b..eeeb9289c764 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -71,12 +71,7 @@ struct ldt_struct {
 
 static inline void *ldt_slot_va(int slot)
 {
-#ifdef CONFIG_X86_64
 	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
-#else
-	BUG();
-	return (void *)fix_to_virt(FIX_HOLE);
-#endif
 }
 
 /*
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 5a7375ed5f7c..19886fef1dfc 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -194,6 +194,40 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 		return hv_status;
 }
 
+/* Fast hypercall with 16 bytes of input */
+static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
+{
+	u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
+
+#ifdef CONFIG_X86_64
+	{
+		__asm__ __volatile__("mov %4, %%r8\n"
+				     CALL_NOSPEC
+				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
+				       "+c" (control), "+d" (input1)
+				     : "r" (input2),
+				       THUNK_TARGET(hv_hypercall_pg)
+				     : "cc", "r8", "r9", "r10", "r11");
+	}
+#else
+	{
+		u32 input1_hi = upper_32_bits(input1);
+		u32 input1_lo = lower_32_bits(input1);
+		u32 input2_hi = upper_32_bits(input2);
+		u32 input2_lo = lower_32_bits(input2);
+
+		__asm__ __volatile__ (CALL_NOSPEC
+				      : "=A"(hv_status),
+					"+c"(input1_lo), ASM_CALL_CONSTRAINT
+				      :	"A" (control), "b" (input1_hi),
+					"D"(input2_hi), "S"(input2_lo),
+					THUNK_TARGET(hv_hypercall_pg)
+				      : "cc");
+	}
+#endif
+		return hv_status;
+}
+
 /*
  * Rep hypercalls. Callers of this functions are supposed to ensure that
  * rep_count and varhead_size comply with Hyper-V hypercall definition.
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 68b2c3150de1..4731f0cf97c5 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -70,12 +70,19 @@
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
 #define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
 #define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	(1 << 3)   /* Skip L1D flush on vmentry */
 #define ARCH_CAP_SSB_NO			(1 << 4)   /*
 						    * Not susceptible to Speculative Store Bypass
 						    * attack, so no Speculative Store Bypass
 						    * control required.
 						    */
 
+#define MSR_IA32_FLUSH_CMD		0x0000010b
+#define L1D_FLUSH			(1 << 0)   /*
+						    * Writeback and invalidate the
+						    * L1 data cache.
+						    */
+
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index f6f6c63da62f..fd2a8c1b88bc 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -214,7 +214,7 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
 	SPECTRE_V2_RETPOLINE_GENERIC,
 	SPECTRE_V2_RETPOLINE_AMD,
-	SPECTRE_V2_IBRS,
+	SPECTRE_V2_IBRS_ENHANCED,
 };
 
 /* The Speculative Store Bypass disable variants */
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 9c9dc579bd7d..46f516dd80ce 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -88,6 +88,7 @@ struct orc_entry {
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
+	unsigned	end:1;
 } __packed;
 
 /*
@@ -101,6 +102,7 @@ struct unwind_hint {
 	s16		sp_offset;
 	u8		sp_reg;
 	u8		type;
+	u8		end;
 };
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index aa30c3241ea7..0d5c739eebd7 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -29,8 +29,13 @@
 #define N_EXCEPTION_STACKS 1
 
 #ifdef CONFIG_X86_PAE
-/* 44=32+12, the limit we can fit into an unsigned long pfn */
-#define __PHYSICAL_MASK_SHIFT	44
+/*
+ * This is beyond the 44 bit limit imposed by the 32bit long pfns,
+ * but we need the full mask to make sure inverted PROT_NONE
+ * entries have all the host bits set in a guest.
+ * The real limit is still 44 bits.
+ */
+#define __PHYSICAL_MASK_SHIFT	52
 #define __VIRTUAL_MASK_SHIFT	32
 
 #else  /* !CONFIG_X86_PAE */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index a06b07399d17..e9202a0de8f0 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -450,9 +450,10 @@ do {									\
 	bool __ret;							\
 	typeof(pcp1) __o1 = (o1), __n1 = (n1);				\
 	typeof(pcp2) __o2 = (o2), __n2 = (n2);				\
-	asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t"	\
-		    : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \
-		    :  "b" (__n1), "c" (__n2), "a" (__o1));		\
+	asm volatile("cmpxchg8b "__percpu_arg(1)			\
+		     CC_SET(z)						\
+		     : CC_OUT(z) (__ret), "+m" (pcp1), "+m" (pcp2), "+a" (__o1), "+d" (__o2) \
+		     : "b" (__n1), "c" (__n2));				\
 	__ret;								\
 })
 
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 685ffe8a0eaf..24c6cf5f16b7 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -19,6 +19,9 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte)
 
 static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd);
+#endif
 	*pmdp = pmd;
 }
 
@@ -58,6 +61,9 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #ifdef CONFIG_SMP
 static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0));
+#endif
 	return __pmd(xchg((pmdval_t *)xp, 0));
 }
 #else
@@ -67,6 +73,9 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #ifdef CONFIG_SMP
 static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0));
+#endif
 	return __pud(xchg((pudval_t *)xp, 0));
 }
 #else
@@ -95,4 +104,21 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
 
+/* No inverted PFNs on 2 level page tables */
+
+static inline u64 protnone_mask(u64 val)
+{
+	return 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	return val;
+}
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_PGTABLE_2LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index f982ef808e7e..6deb6cd236e3 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -35,4 +35,7 @@ typedef union {
 
 #define PTRS_PER_PTE	1024
 
+/* This covers all VMSPLIT_* and VMSPLIT_*_OPT variants */
+#define PGD_KERNEL_START	(CONFIG_PAGE_OFFSET >> PGDIR_SHIFT)
+
 #endif /* _ASM_X86_PGTABLE_2LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index f24df59c40b2..a564084c6141 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -98,6 +98,9 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 
 static inline void native_set_pud(pud_t *pudp, pud_t pud)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd);
+#endif
 	set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
 }
 
@@ -229,6 +232,10 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
 {
 	union split_pud res, *orig = (union split_pud *)pudp;
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pti_set_user_pgtbl(&pudp->p4d.pgd, __pgd(0));
+#endif
+
 	/* xchg acts as a barrier before setting of the high bits */
 	res.pud_low = xchg(&orig->pud_low, 0);
 	res.pud_high = orig->pud_high;
@@ -241,12 +248,43 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
 #endif
 
 /* Encode and de-code a swap entry */
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS)
+
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
 #define __swp_type(x)			(((x).val) & 0x1f)
 #define __swp_offset(x)			((x).val >> 5)
 #define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << 5})
-#define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
-#define __swp_entry_to_pte(x)		((pte_t){ { .pte_high = (x).val } })
+
+/*
+ * Normally, __swp_entry() converts from arch-independent swp_entry_t to
+ * arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result
+ * to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the
+ * whole 64 bits. Thus, we shift the "real" arch-dependent conversion to
+ * __swp_entry_to_pte() through the following helper macro based on 64bit
+ * __swp_entry().
+ */
+#define __swp_pteval_entry(type, offset) ((pteval_t) { \
+	(~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) })
+
+#define __swp_entry_to_pte(x)	((pte_t){ .pte = \
+		__swp_pteval_entry(__swp_type(x), __swp_offset(x)) })
+/*
+ * Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent
+ * swp_entry_t, but also has to convert it from 64bit to the 32bit
+ * intermediate representation, using the following macros based on 64bit
+ * __swp_type() and __swp_offset().
+ */
+#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS)))
+#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT))
+
+#define __pte_to_swp_entry(pte)	(__swp_entry(__pteval_swp_type(pte), \
+					     __pteval_swp_offset(pte)))
 
 #define gup_get_pte gup_get_pte
 /*
@@ -295,4 +333,6 @@ static inline pte_t gup_get_pte(pte_t *ptep)
 	return pte;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* _ASM_X86_PGTABLE_3LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 6a59a6d0cc50..858358a82b14 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -21,9 +21,10 @@ typedef union {
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_PARAVIRT
-#define SHARED_KERNEL_PMD	(pv_info.shared_kernel_pmd)
+#define SHARED_KERNEL_PMD	((!static_cpu_has(X86_FEATURE_PTI) &&	\
+				 (pv_info.shared_kernel_pmd)))
 #else
-#define SHARED_KERNEL_PMD	1
+#define SHARED_KERNEL_PMD	(!static_cpu_has(X86_FEATURE_PTI))
 #endif
 
 /*
@@ -45,5 +46,6 @@ typedef union {
 #define PTRS_PER_PTE	512
 
 #define MAX_POSSIBLE_PHYSMEM_BITS	36
+#define PGD_KERNEL_START	(CONFIG_PAGE_OFFSET >> PGDIR_SHIFT)
 
 #endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h
new file mode 100644
index 000000000000..44b1203ece12
--- /dev/null
+++ b/arch/x86/include/asm/pgtable-invert.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_PGTABLE_INVERT_H
+#define _ASM_PGTABLE_INVERT_H 1
+
+#ifndef __ASSEMBLY__
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return !(val & _PAGE_PRESENT);
+}
+
+/* Get a mask to xor with the page table entry to get the correct pfn. */
+static inline u64 protnone_mask(u64 val)
+{
+	return __pte_needs_invert(val) ?  ~0ull : 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	/*
+	 * When a PTE transitions from NONE to !NONE or vice-versa
+	 * invert the PFN part to stop speculation.
+	 * pte_pfn undoes this when needed.
+	 */
+	if (__pte_needs_invert(oldval) != __pte_needs_invert(val))
+		val = (val & ~mask) | (~val & mask);
+	return val;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5715647fc4fe..e4ffa565a69f 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -30,11 +30,14 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
 void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
 void ptdump_walk_pgd_level_checkwx(void);
+void ptdump_walk_user_pgd_level_checkwx(void);
 
 #ifdef CONFIG_DEBUG_WX
-#define debug_checkwx() ptdump_walk_pgd_level_checkwx()
+#define debug_checkwx()		ptdump_walk_pgd_level_checkwx()
+#define debug_checkwx_user()	ptdump_walk_user_pgd_level_checkwx()
 #else
-#define debug_checkwx() do { } while (0)
+#define debug_checkwx()		do { } while (0)
+#define debug_checkwx_user()	do { } while (0)
 #endif
 
 /*
@@ -185,19 +188,29 @@ static inline int pte_special(pte_t pte)
 	return pte_flags(pte) & _PAGE_SPECIAL;
 }
 
+/* Entries that were set to PROT_NONE are inverted */
+
+static inline u64 protnone_mask(u64 val);
+
 static inline unsigned long pte_pfn(pte_t pte)
 {
-	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
+	phys_addr_t pfn = pte_val(pte);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
+	phys_addr_t pfn = pmd_val(pmd);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pud_pfn(pud_t pud)
 {
-	return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
+	phys_addr_t pfn = pud_val(pud);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long p4d_pfn(p4d_t p4d)
@@ -400,11 +413,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_RW);
 }
 
-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
-{
-	return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
-}
-
 static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
 {
 	pudval_t v = native_pud_val(pud);
@@ -459,11 +467,6 @@ static inline pud_t pud_mkwrite(pud_t pud)
 	return pud_set_flags(pud, _PAGE_RW);
 }
 
-static inline pud_t pud_mknotpresent(pud_t pud)
-{
-	return pud_clear_flags(pud, _PAGE_PRESENT | _PAGE_PROTNONE);
-}
-
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline int pte_soft_dirty(pte_t pte)
 {
@@ -545,25 +548,45 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot)
 
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PTE_PFN_MASK;
+	return __pte(pfn | check_pgprot(pgprot));
 }
 
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PMD_PAGE_MASK;
+	return __pmd(pfn | check_pgprot(pgprot));
 }
 
 static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PUD_PAGE_MASK;
+	return __pud(pfn | check_pgprot(pgprot));
+}
+
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return pfn_pmd(pmd_pfn(pmd),
+		      __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
+}
+
+static inline pud_t pud_mknotpresent(pud_t pud)
+{
+	return pfn_pud(pud_pfn(pud),
+	      __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
 }
 
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);
+
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	pteval_t val = pte_val(pte);
+	pteval_t val = pte_val(pte), oldval = val;
 
 	/*
 	 * Chop off the NX bit (if present), and add the NX portion of
@@ -571,17 +594,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 */
 	val &= _PAGE_CHG_MASK;
 	val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PTE_PFN_MASK);
 	return __pte(val);
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	pmdval_t val = pmd_val(pmd);
+	pmdval_t val = pmd_val(pmd), oldval = val;
 
 	val &= _HPAGE_CHG_MASK;
 	val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);
 	return __pmd(val);
 }
 
@@ -640,8 +663,31 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 
 pmd_t *populate_extra_pmd(unsigned long vaddr);
 pte_t *populate_extra_pte(unsigned long vaddr);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return pgd;
+	return __pti_set_user_pgtbl(pgdp, pgd);
+}
+#else   /* CONFIG_PAGE_TABLE_ISOLATION */
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+#endif  /* CONFIG_PAGE_TABLE_ISOLATION */
+
 #endif	/* __ASSEMBLY__ */
 
+
 #ifdef CONFIG_X86_32
 # include <asm/pgtable_32.h>
 #else
@@ -1154,6 +1200,70 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 	}
 }
 #endif
+/*
+ * Page table pages are page-aligned.  The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+	unsigned long ptr = (unsigned long)__ptr;
+
+	return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
+}
+
+static inline int pgd_large(pgd_t pgd) { return 0; }
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
+ * the user one is in the last 4k.  To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr |= BIT(bit);
+	return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr &= ~BIT(bit);
+	return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
 
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
@@ -1320,6 +1430,14 @@ static inline bool pud_access_permitted(pud_t pud, bool write)
 	return __pte_access_permitted(pud_val(pud), write);
 }
 
+#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1
+extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot);
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return boot_cpu_has_bug(X86_BUG_L1TF);
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 88a056b01db4..b3ec519e3982 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -34,8 +34,6 @@ static inline void check_pgt_cache(void) { }
 void paging_init(void);
 void sync_initial_page_table(void);
 
-static inline int pgd_large(pgd_t pgd) { return 0; }
-
 /*
  * Define this if things work differently on an i386 and an i486:
  * it will (on an i486) warn about kernel memory accesses that are
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index d9a001a4a872..b0bc0fff5f1f 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -50,13 +50,18 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 	((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1))   \
 	 & PMD_MASK)
 
-#define PKMAP_BASE		\
+#define LDT_BASE_ADDR		\
 	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
+#define LDT_END_ADDR		(LDT_BASE_ADDR + PMD_SIZE)
+
+#define PKMAP_BASE		\
+	((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK)
+
 #ifdef CONFIG_HIGHMEM
 # define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
 #else
-# define VMALLOC_END	(CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
+# define VMALLOC_END	(LDT_BASE_ADDR - 2 * PAGE_SIZE)
 #endif
 
 #define MODULES_VADDR	VMALLOC_START
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 3c5385f9a88f..f773d5e6c8cc 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -132,90 +132,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-/*
- * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
- * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
- * the user one is in the last 4k.  To switch between them, you
- * just need to flip the 12th bit in their addresses.
- */
-#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
-
-/*
- * This generates better code than the inline assembly in
- * __set_bit().
- */
-static inline void *ptr_set_bit(void *ptr, int bit)
-{
-	unsigned long __ptr = (unsigned long)ptr;
-
-	__ptr |= BIT(bit);
-	return (void *)__ptr;
-}
-static inline void *ptr_clear_bit(void *ptr, int bit)
-{
-	unsigned long __ptr = (unsigned long)ptr;
-
-	__ptr &= ~BIT(bit);
-	return (void *)__ptr;
-}
-
-static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
-{
-	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
-{
-	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
-{
-	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
-{
-	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
-#endif /* CONFIG_PAGE_TABLE_ISOLATION */
-
-/*
- * Page table pages are page-aligned.  The lower half of the top
- * level is used for userspace and the top half for the kernel.
- *
- * Returns true for parts of the PGD that map userspace and
- * false for the parts that map the kernel.
- */
-static inline bool pgdp_maps_userspace(void *__ptr)
-{
-	unsigned long ptr = (unsigned long)__ptr;
-
-	return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
-}
-
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
-
-/*
- * Take a PGD location (pgdp) and a pgd value that needs to be set there.
- * Populates the user and returns the resulting PGD that must be set in
- * the kernel copy of the page tables.
- */
-static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	if (!static_cpu_has(X86_FEATURE_PTI))
-		return pgd;
-	return __pti_set_user_pgd(pgdp, pgd);
-}
-#else
-static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	return pgd;
-}
-#endif
-
 static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	pgd_t pgd;
@@ -226,7 +142,7 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 	}
 
 	pgd = native_make_pgd(native_p4d_val(p4d));
-	pgd = pti_set_user_pgd((pgd_t *)p4dp, pgd);
+	pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd);
 	*p4dp = native_make_p4d(native_pgd_val(pgd));
 }
 
@@ -237,7 +153,7 @@ static inline void native_p4d_clear(p4d_t *p4d)
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
-	*pgdp = pti_set_user_pgd(pgdp, pgd);
+	*pgdp = pti_set_user_pgtbl(pgdp, pgd);
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)
@@ -255,7 +171,6 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
 /*
  * Level 4 access.
  */
-static inline int pgd_large(pgd_t pgd) { return 0; }
 #define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
 
 /* PUD - Level3 access */
@@ -273,7 +188,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | OFFSET (14->63) | TYPE (9-13)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -286,20 +201,34 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
+ *
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
  */
-#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
-#define SWP_TYPE_BITS 5
-/* Place the offset above the type: */
-#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS)
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS)
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 
-#define __swp_type(x)			(((x).val >> (SWP_TYPE_FIRST_BIT)) \
-					 & ((1U << SWP_TYPE_BITS) - 1))
-#define __swp_offset(x)			((x).val >> SWP_OFFSET_FIRST_BIT)
-#define __swp_entry(type, offset)	((swp_entry_t) { \
-					 ((type) << (SWP_TYPE_FIRST_BIT)) \
-					 | ((offset) << SWP_OFFSET_FIRST_BIT) })
+/* Extract the high bits for type */
+#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS))
+
+/* Shift up (to get rid of type), then down to get value */
+#define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
+
+/*
+ * Shift the offset up "too far" by TYPE bits, then down again
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
+ */
+#define __swp_entry(type, offset) ((swp_entry_t) { \
+	(~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((unsigned long)(type) << (64-SWP_TYPE_BITS)) })
+
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __pmd_to_swp_entry(pmd)		((swp_entry_t) { pmd_val((pmd)) })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
@@ -343,5 +272,7 @@ static inline bool gup_fast_permitted(unsigned long start, int nr_pages,
 	return true;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_PGTABLE_64_H */
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 054765ab2da2..04edd2d58211 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -115,6 +115,7 @@ extern unsigned int ptrs_per_p4d;
 #define LDT_PGD_ENTRY_L5	-112UL
 #define LDT_PGD_ENTRY		(pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
 #define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
+#define LDT_END_ADDR		(LDT_BASE_ADDR + PGDIR_SIZE)
 
 #define __VMALLOC_BASE_L4	0xffffc90000000000UL
 #define __VMALLOC_BASE_L5 	0xffa0000000000000UL
@@ -153,4 +154,6 @@ extern unsigned int ptrs_per_p4d;
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
+#define PGD_KERNEL_START	((PAGE_SIZE / 2) / sizeof(pgd_t))
+
 #endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 99fff853c944..b64acb08a62b 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -50,6 +50,7 @@
 #define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
 #define _PAGE_SOFTW1	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
 #define _PAGE_SOFTW2	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
+#define _PAGE_SOFTW3	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW3)
 #define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
@@ -266,14 +267,37 @@ typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
 
 typedef struct { pgdval_t pgd; } pgd_t;
 
+#ifdef CONFIG_X86_PAE
+
+/*
+ * PHYSICAL_PAGE_MASK might be non-constant when SME is compiled in, so we can't
+ * use it here.
+ */
+
+#define PGD_PAE_PAGE_MASK	((signed long)PAGE_MASK)
+#define PGD_PAE_PHYS_MASK	(((1ULL << __PHYSICAL_MASK_SHIFT)-1) & PGD_PAE_PAGE_MASK)
+
+/*
+ * PAE allows Base Address, P, PWT, PCD and AVL bits to be set in PGD entries.
+ * All other bits are Reserved MBZ
+ */
+#define PGD_ALLOWED_BITS	(PGD_PAE_PHYS_MASK | _PAGE_PRESENT | \
+				 _PAGE_PWT | _PAGE_PCD | \
+				 _PAGE_SOFTW1 | _PAGE_SOFTW2 | _PAGE_SOFTW3)
+
+#else
+/* No need to mask any bits for !PAE */
+#define PGD_ALLOWED_BITS	(~0ULL)
+#endif
+
 static inline pgd_t native_make_pgd(pgdval_t val)
 {
-	return (pgd_t) { val };
+	return (pgd_t) { val & PGD_ALLOWED_BITS };
 }
 
 static inline pgdval_t native_pgd_val(pgd_t pgd)
 {
-	return pgd.pgd;
+	return pgd.pgd & PGD_ALLOWED_BITS;
 }
 
 static inline pgdval_t pgd_flags(pgd_t pgd)
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 625a52a5594f..02c2cbda4a74 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -39,10 +39,6 @@
 #define CR3_PCID_MASK	0xFFFull
 #define CR3_NOFLUSH	BIT_ULL(63)
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-# define X86_CR3_PTI_PCID_USER_BIT	11
-#endif
-
 #else
 /*
  * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
@@ -53,4 +49,8 @@
 #define CR3_NOFLUSH	0
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_PCID_USER_BIT	11
+#endif
+
 #endif /* _ASM_X86_PROCESSOR_FLAGS_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cfd29ee8c3da..682286aca881 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -181,6 +181,11 @@ extern const struct seq_operations cpuinfo_op;
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
 
+static inline unsigned long l1tf_pfn_limit(void)
+{
+	return BIT(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT) - 1;
+}
+
 extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);
@@ -966,6 +971,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 
 extern unsigned long arch_align_stack(unsigned long sp);
 extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+extern void free_kernel_image_pages(void *begin, void *end);
 
 void default_idle(void);
 #ifdef	CONFIG_XEN
@@ -977,4 +983,16 @@ bool xen_set_default_idle(void);
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
 void microcode_check(void);
+
+enum l1tf_mitigations {
+	L1TF_MITIGATION_OFF,
+	L1TF_MITIGATION_FLUSH_NOWARN,
+	L1TF_MITIGATION_FLUSH,
+	L1TF_MITIGATION_FLUSH_NOSMT,
+	L1TF_MITIGATION_FULL,
+	L1TF_MITIGATION_FULL_FORCE
+};
+
+extern enum l1tf_mitigations l1tf_mitigation;
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
index 38a17f1d5c9d..5df09a0b80b8 100644
--- a/arch/x86/include/asm/pti.h
+++ b/arch/x86/include/asm/pti.h
@@ -6,10 +6,9 @@
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 extern void pti_init(void);
 extern void pti_check_boottime_disable(void);
-extern void pti_clone_kernel_text(void);
+extern void pti_finalize(void);
 #else
 static inline void pti_check_boottime_disable(void) { }
-static inline void pti_clone_kernel_text(void) { }
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 4cf11d88d3b3..19b90521954c 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -5,6 +5,7 @@
  * PaX/grsecurity.
  */
 #include <linux/refcount.h>
+#include <asm/bug.h>
 
 /*
  * This is the first portion of the refcount error handling, which lives in
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 5c019d23d06b..4a911a382ade 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -7,6 +7,7 @@
 
 extern char __brk_base[], __brk_limit[];
 extern struct exception_table_entry __stop___ex_table[];
+extern char __end_rodata_aligned[];
 
 #if defined(CONFIG_X86_64)
 extern char __end_rodata_hpage_align[];
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index bd090367236c..34cffcef7375 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -46,6 +46,7 @@ int set_memory_np(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
 int set_memory_encrypted(unsigned long addr, int numpages);
 int set_memory_decrypted(unsigned long addr, int numpages);
+int set_memory_np_noalias(unsigned long addr, int numpages);
 
 int set_memory_array_uc(unsigned long *addr, int addrinarray);
 int set_memory_array_wc(unsigned long *addr, int addrinarray);
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index eb5f7999a893..36bd243843d6 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -87,15 +87,25 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
 #endif
 
 /* This is used when switching tasks or entering/exiting vm86 mode. */
-static inline void update_sp0(struct task_struct *task)
+static inline void update_task_stack(struct task_struct *task)
 {
-	/* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
+	/* sp0 always points to the entry trampoline stack, which is constant: */
 #ifdef CONFIG_X86_32
-	load_sp0(task->thread.sp0);
+	if (static_cpu_has(X86_FEATURE_XENPV))
+		load_sp0(task->thread.sp0);
+	else
+		this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
 #else
+	/*
+	 * x86-64 updates x86_tss.sp1 via cpu_current_top_of_stack. That
+	 * doesn't work on x86-32 because sp1 and
+	 * cpu_current_top_of_stack have different values (because of
+	 * the non-zero stack-padding on 32bit).
+	 */
 	if (static_cpu_has(X86_FEATURE_XENPV))
 		load_sp0(task_top_of_stack(task));
 #endif
+
 }
 
 #endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 2ecd34e2d46c..e85ff65c43c3 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -37,5 +37,6 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern int after_bootmem;
 
 #endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6690cd3fc8b1..511bf5fae8b8 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -148,22 +148,6 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 #define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
 #endif
 
-static inline bool tlb_defer_switch_to_init_mm(void)
-{
-	/*
-	 * If we have PCID, then switching to init_mm is reasonably
-	 * fast.  If we don't have PCID, then switching to init_mm is
-	 * quite slow, so we try to defer it in the hopes that we can
-	 * avoid it entirely.  The latter approach runs the risk of
-	 * receiving otherwise unnecessary IPIs.
-	 *
-	 * This choice is just a heuristic.  The tlb code can handle this
-	 * function returning true or false regardless of whether we have
-	 * PCID.
-	 */
-	return !static_cpu_has(X86_FEATURE_PCID);
-}
-
 struct tlb_context {
 	u64 ctx_id;
 	u64 tlb_gen;
@@ -554,4 +538,9 @@ extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 	native_flush_tlb_others(mask, info)
 #endif
 
+extern void tlb_flush_remove_tables(struct mm_struct *mm);
+extern void tlb_flush_remove_tables_local(void *arg);
+
+#define HAVE_TLB_FLUSH_REMOVE_TABLES
+
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index c1d2a9892352..453cf38a1c33 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -123,13 +123,17 @@ static inline int topology_max_smt_threads(void)
 }
 
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
-extern int topology_phys_to_logical_pkg(unsigned int pkg);
+int topology_phys_to_logical_pkg(unsigned int pkg);
+bool topology_is_primary_thread(unsigned int cpu);
+bool topology_smt_supported(void);
 #else
 #define topology_max_packages()			(1)
 static inline int
 topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
 static inline int topology_max_smt_threads(void) { return 1; }
+static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
+static inline bool topology_smt_supported(void) { return false; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h
index 4253bca99989..9c0d4b588e3f 100644
--- a/arch/x86/include/asm/trace/hyperv.h
+++ b/arch/x86/include/asm/trace/hyperv.h
@@ -28,6 +28,21 @@ TRACE_EVENT(hyperv_mmu_flush_tlb_others,
 		      __entry->addr, __entry->end)
 	);
 
+TRACE_EVENT(hyperv_send_ipi_mask,
+	    TP_PROTO(const struct cpumask *cpus,
+		     int vector),
+	    TP_ARGS(cpus, vector),
+	    TP_STRUCT__entry(
+		    __field(unsigned int, ncpus)
+		    __field(int, vector)
+		    ),
+	    TP_fast_assign(__entry->ncpus = cpumask_weight(cpus);
+			   __entry->vector = vector;
+		    ),
+	    TP_printk("ncpus %d vector %x",
+		      __entry->ncpus, __entry->vector)
+	);
+
 #endif /* CONFIG_HYPERV */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 2701d221583a..eb5bbfeccb66 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -33,13 +33,13 @@ static inline cycles_t get_cycles(void)
 extern struct system_counterval_t convert_art_to_tsc(u64 art);
 extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns);
 
-extern void tsc_early_delay_calibrate(void);
+extern void tsc_early_init(void);
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
 extern void mark_tsc_async_resets(char *reason);
-extern unsigned long native_calibrate_cpu(void);
+extern unsigned long native_calibrate_cpu_early(void);
 extern unsigned long native_calibrate_tsc(void);
 extern unsigned long long native_sched_clock_from_tsc(u64 tsc);
 
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index bae46fc6b9de..0bcdb1279361 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -26,7 +26,7 @@
  * the debuginfo as necessary.  It will also warn if it sees any
  * inconsistencies.
  */
-.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL
+.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0
 #ifdef CONFIG_STACK_VALIDATION
 .Lunwind_hint_ip_\@:
 	.pushsection .discard.unwind_hints
@@ -35,12 +35,14 @@
 		.short \sp_offset
 		.byte \sp_reg
 		.byte \type
+		.byte \end
+		.balign 4
 	.popsection
 #endif
 .endm
 
 .macro UNWIND_HINT_EMPTY
-	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED
+	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1
 .endm
 
 .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0
@@ -86,19 +88,21 @@
 
 #else /* !__ASSEMBLY__ */
 
-#define UNWIND_HINT(sp_reg, sp_offset, type)			\
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
 	"987: \n\t"						\
 	".pushsection .discard.unwind_hints\n\t"		\
 	/* struct unwind_hint */				\
 	".long 987b - .\n\t"					\
-	".short " __stringify(sp_offset) "\n\t"		\
+	".short " __stringify(sp_offset) "\n\t"			\
 	".byte " __stringify(sp_reg) "\n\t"			\
 	".byte " __stringify(type) "\n\t"			\
+	".byte " __stringify(end) "\n\t"			\
+	".balign 4 \n\t"					\
 	".popsection\n\t"
 
-#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE)
+#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0)
 
-#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE)
+#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 6aa8499e1f62..95f9107449bf 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -576,4 +576,15 @@ enum vm_instruction_error_number {
 	VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID = 28,
 };
 
+enum vmx_l1d_flush_state {
+	VMENTER_L1D_FLUSH_AUTO,
+	VMENTER_L1D_FLUSH_NEVER,
+	VMENTER_L1D_FLUSH_COND,
+	VMENTER_L1D_FLUSH_ALWAYS,
+	VMENTER_L1D_FLUSH_EPT_DISABLED,
+	VMENTER_L1D_FLUSH_NOT_REQUIRED,
+};
+
+extern enum vmx_l1d_flush_state l1tf_vmx_mitigation;
+
 #endif
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a481763a3776..014f214da581 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -668,6 +668,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 	local_irq_save(flags);
 	memcpy(addr, opcode, len);
 	local_irq_restore(flags);
+	sync_core();
 	/* Could also do a CLFLUSH here to speed up CPU recovery; but
 	   that causes hangs on some VIA CPUs. */
 	return addr;
@@ -693,6 +694,12 @@ void *text_poke(void *addr, const void *opcode, size_t len)
 	struct page *pages[2];
 	int i;
 
+	/*
+	 * While boot memory allocator is runnig we cannot use struct
+	 * pages as they are not yet initialized.
+	 */
+	BUG_ON(!after_bootmem);
+
 	if (!core_kernel_text((unsigned long)addr)) {
 		pages[0] = vmalloc_to_page(addr);
 		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index adbda5847b14..87ff6235bbfe 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -56,6 +56,7 @@
 #include <asm/hypervisor.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/irq_regs.h>
 
 unsigned int num_processors;
 
@@ -940,7 +941,7 @@ static int __init calibrate_APIC_clock(void)
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
 		pr_warning("APIC timer disabled due to verification failure\n");
-			return -1;
+		return -1;
 	}
 
 	return 0;
@@ -2192,6 +2193,21 @@ static int cpuid_to_apicid[] = {
 	[0 ... NR_CPUS - 1] = -1,
 };
 
+/**
+ * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread
+ * @id:	APIC ID to check
+ */
+bool apic_id_is_primary_thread(unsigned int apicid)
+{
+	u32 mask;
+
+	if (smp_num_siblings == 1)
+		return true;
+	/* Isolate the SMT bit(s) in the APICID and check for 0 */
+	mask = (1U << (fls(smp_num_siblings) - 1)) - 1;
+	return !(apicid & mask);
+}
+
 /*
  * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
  * and cpuid_to_apicid[] synchronized.
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 3982f79d2377..ff0d14cd9e82 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -33,6 +33,7 @@
 
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index ce503c99f5c4..72a94401f9e0 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -12,6 +12,7 @@
  */
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/dmar.h>
 #include <linux/hpet.h>
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 35aaee4fc028..9f148e3d45b4 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -11,6 +11,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/compiler.h>
@@ -218,7 +219,8 @@ static int reserve_irq_vector(struct irq_data *irqd)
 	return 0;
 }
 
-static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest)
+static int
+assign_vector_locked(struct irq_data *irqd, const struct cpumask *dest)
 {
 	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	bool resvd = apicd->has_reserved;
@@ -245,22 +247,12 @@ static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest)
 		return -EBUSY;
 
 	vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu);
-	if (vector > 0)
-		apic_update_vector(irqd, vector, cpu);
 	trace_vector_alloc(irqd->irq, vector, resvd, vector);
-	return vector;
-}
-
-static int assign_vector_locked(struct irq_data *irqd,
-				const struct cpumask *dest)
-{
-	struct apic_chip_data *apicd = apic_chip_data(irqd);
-	int vector = allocate_vector(irqd, dest);
-
 	if (vector < 0)
 		return vector;
+	apic_update_vector(irqd, vector, cpu);
+	apic_update_irq_cfg(irqd, vector, cpu);
 
-	apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu);
 	return 0;
 }
 
@@ -433,7 +425,7 @@ static int activate_managed(struct irq_data *irqd)
 		pr_err("Managed startup irq %u, no vector available\n",
 		       irqd->irq);
 	}
-       return ret;
+	return ret;
 }
 
 static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d492752f79e1..391f358ebb4c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -394,10 +394,10 @@ extern int uv_hub_info_version(void)
 EXPORT_SYMBOL(uv_hub_info_version);
 
 /* Default UV memory block size is 2GB */
-static unsigned long mem_block_size = (2UL << 30);
+static unsigned long mem_block_size __initdata = (2UL << 30);
 
 /* Kernel parameter to specify UV mem block size */
-static int parse_mem_block_size(char *ptr)
+static int __init parse_mem_block_size(char *ptr)
 {
 	unsigned long size = memparse(ptr, NULL);
 
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index dcb008c320fe..01de31db300d 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -103,4 +103,9 @@ void common(void) {
 	OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
 	OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
 	DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
+	DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1)));
+
+	/* Offset for sp0 and sp1 into the tss_struct */
+	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
+	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 }
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index a4a3be399f4b..82826f2275cc 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -46,8 +46,14 @@ void foo(void)
 	OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
 	BLANK();
 
-	/* Offset from the sysenter stack to tss.sp0 */
-	DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+	/*
+	 * Offset from the entry stack to task stack stored in TSS. Kernel entry
+	 * happens on the per-cpu entry-stack, and the asm code switches to the
+	 * task-stack pointer stored in x86_tss.sp1, which is a copy of
+	 * task->thread.sp0 where entry code can find it.
+	 */
+	DEFINE(TSS_entry2task_stack,
+	       offsetof(struct cpu_entry_area, tss.x86_tss.sp1) -
 	       offsetofend(struct cpu_entry_area, entry_stack_page.stack));
 
 #ifdef CONFIG_STACKPROTECTOR
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index b2dcd161f514..3b9405e7ba2b 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -65,8 +65,6 @@ int main(void)
 #undef ENTRY
 
 	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
-	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
-	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	BLANK();
 
 #ifdef CONFIG_STACKPROTECTOR
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 7a40196967cb..347137e80bf5 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -35,7 +35,9 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o
+obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o
+obj-$(CONFIG_INTEL_RDT)	+= intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o
+CFLAGS_intel_rdt_pseudo_lock.o = -I$(src)
 
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 38915fbfae73..22ab408177b2 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -232,8 +232,6 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
 		}
 	}
 
-	set_cpu_cap(c, X86_FEATURE_K7);
-
 	/* calling is from identify_secondary_cpu() ? */
 	if (!c->cpu_index)
 		return;
@@ -315,6 +313,13 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
 	c->cpu_core_id %= cus_per_node;
 }
 
+
+static void amd_get_topology_early(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_TOPOEXT))
+		smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
+}
+
 /*
  * Fixup core topology information for
  * (1) AMD multi-node processors
@@ -334,7 +339,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
 
 		node_id  = ecx & 0xff;
-		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
 
 		if (c->x86 == 0x15)
 			c->cu_id = ebx & 0xff;
@@ -613,10 +617,19 @@ clear_sev:
 
 static void early_init_amd(struct cpuinfo_x86 *c)
 {
+	u64 value;
 	u32 dummy;
 
 	early_init_amd_mc(c);
 
+#ifdef CONFIG_X86_32
+	if (c->x86 == 6)
+		set_cpu_cap(c, X86_FEATURE_K7);
+#endif
+
+	if (c->x86 >= 0xf)
+		set_cpu_cap(c, X86_FEATURE_K8);
+
 	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
 
 	/*
@@ -683,6 +696,22 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_AMD_E400);
 
 	early_detect_mem_encrypt(c);
+
+	/* Re-enable TopologyExtensions if switched off by BIOS */
+	if (c->x86 == 0x15 &&
+	    (c->x86_model >= 0x10 && c->x86_model <= 0x6f) &&
+	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+
+		if (msr_set_bit(0xc0011005, 54) > 0) {
+			rdmsrl(0xc0011005, value);
+			if (value & BIT_64(54)) {
+				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+				pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
+			}
+		}
+	}
+
+	amd_get_topology_early(c);
 }
 
 static void init_amd_k8(struct cpuinfo_x86 *c)
@@ -774,19 +803,6 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 {
 	u64 value;
 
-	/* re-enable TopologyExtensions if switched off by BIOS */
-	if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) &&
-	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
-
-		if (msr_set_bit(0xc0011005, 54) > 0) {
-			rdmsrl(0xc0011005, value);
-			if (value & BIT_64(54)) {
-				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
-				pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
-			}
-		}
-	}
-
 	/*
 	 * The way access filter has a performance penalty on some workloads.
 	 * Disable it on the affected CPUs.
@@ -850,22 +866,12 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	cpu_detect_cache_sizes(c);
 
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level >= 0x80000008) {
-		amd_detect_cmp(c);
-		amd_get_topology(c);
-		srat_detect_node(c);
-	}
-
-#ifdef CONFIG_X86_32
-	detect_ht(c);
-#endif
+	amd_detect_cmp(c);
+	amd_get_topology(c);
+	srat_detect_node(c);
 
 	init_amd_cacheinfo(c);
 
-	if (c->x86 >= 0xf)
-		set_cpu_cap(c, X86_FEATURE_K8);
-
 	if (cpu_has(c, X86_FEATURE_XMM2)) {
 		unsigned long long val;
 		int ret;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 5c0ea39311fe..27830880e7a7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -22,15 +22,18 @@
 #include <asm/processor-flags.h>
 #include <asm/fpu/internal.h>
 #include <asm/msr.h>
+#include <asm/vmx.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
 #include <asm/intel-family.h>
+#include <asm/e820/api.h>
 #include <asm/hypervisor.h>
 
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
+static void __init l1tf_select_mitigation(void);
 
 /*
  * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
@@ -56,6 +59,12 @@ void __init check_bugs(void)
 {
 	identify_boot_cpu();
 
+	/*
+	 * identify_boot_cpu() initialized SMT support information, let the
+	 * core code know.
+	 */
+	cpu_smt_check_topology_early();
+
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
 		print_cpu_info(&boot_cpu_data);
@@ -82,6 +91,8 @@ void __init check_bugs(void)
 	 */
 	ssb_select_mitigation();
 
+	l1tf_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -130,6 +141,7 @@ static const char *spectre_v2_strings[] = {
 	[SPECTRE_V2_RETPOLINE_MINIMAL_AMD]	= "Vulnerable: Minimal AMD ASM retpoline",
 	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
 	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
+	[SPECTRE_V2_IBRS_ENHANCED]		= "Mitigation: Enhanced IBRS",
 };
 
 #undef pr_fmt
@@ -313,23 +325,6 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	return cmd;
 }
 
-/* Check for Skylake-like CPUs (for RSB handling) */
-static bool __init is_skylake_era(void)
-{
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6) {
-		switch (boot_cpu_data.x86_model) {
-		case INTEL_FAM6_SKYLAKE_MOBILE:
-		case INTEL_FAM6_SKYLAKE_DESKTOP:
-		case INTEL_FAM6_SKYLAKE_X:
-		case INTEL_FAM6_KABYLAKE_MOBILE:
-		case INTEL_FAM6_KABYLAKE_DESKTOP:
-			return true;
-		}
-	}
-	return false;
-}
-
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -349,6 +344,13 @@ static void __init spectre_v2_select_mitigation(void)
 
 	case SPECTRE_V2_CMD_FORCE:
 	case SPECTRE_V2_CMD_AUTO:
+		if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
+			mode = SPECTRE_V2_IBRS_ENHANCED;
+			/* Force it so VMEXIT will restore correctly */
+			x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
+			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+			goto specv2_set_mode;
+		}
 		if (IS_ENABLED(CONFIG_RETPOLINE))
 			goto retpoline_auto;
 		break;
@@ -386,26 +388,20 @@ retpoline_auto:
 		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
 	}
 
+specv2_set_mode:
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If neither SMEP nor PTI are available, there is a risk of
-	 * hitting userspace addresses in the RSB after a context switch
-	 * from a shallow call stack to a deeper one. To prevent this fill
-	 * the entire RSB, even when using IBRS.
+	 * If spectre v2 protection has been enabled, unconditionally fill
+	 * RSB during a context switch; this protects against two independent
+	 * issues:
 	 *
-	 * Skylake era CPUs have a separate issue with *underflow* of the
-	 * RSB, when they will predict 'ret' targets from the generic BTB.
-	 * The proper mitigation for this is IBRS. If IBRS is not supported
-	 * or deactivated in favour of retpolines the RSB fill on context
-	 * switch is required.
+	 *	- RSB underflow (and switch to BTB) on Skylake+
+	 *	- SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
 	 */
-	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
-	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
-		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-		pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
-	}
+	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
@@ -415,9 +411,16 @@ retpoline_auto:
 
 	/*
 	 * Retpoline means the kernel is safe because it has no indirect
-	 * branches. But firmware isn't, so use IBRS to protect that.
+	 * branches. Enhanced IBRS protects firmware too, so, enable restricted
+	 * speculation around firmware calls only when Enhanced IBRS isn't
+	 * supported.
+	 *
+	 * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
+	 * the user might select retpoline on the kernel command line and if
+	 * the CPU supports Enhanced IBRS, kernel might un-intentionally not
+	 * enable IBRS around firmware calls.
 	 */
-	if (boot_cpu_has(X86_FEATURE_IBRS)) {
+	if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
@@ -654,8 +657,121 @@ void x86_spec_ctrl_setup_ap(void)
 		x86_amd_ssb_disable();
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"L1TF: " fmt
+
+/* Default mitigation for L1TF-affected CPUs */
+enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH;
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+EXPORT_SYMBOL_GPL(l1tf_mitigation);
+
+enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
+EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
+#endif
+
+static void __init l1tf_select_mitigation(void)
+{
+	u64 half_pa;
+
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return;
+
+	switch (l1tf_mitigation) {
+	case L1TF_MITIGATION_OFF:
+	case L1TF_MITIGATION_FLUSH_NOWARN:
+	case L1TF_MITIGATION_FLUSH:
+		break;
+	case L1TF_MITIGATION_FLUSH_NOSMT:
+	case L1TF_MITIGATION_FULL:
+		cpu_smt_disable(false);
+		break;
+	case L1TF_MITIGATION_FULL_FORCE:
+		cpu_smt_disable(true);
+		break;
+	}
+
+#if CONFIG_PGTABLE_LEVELS == 2
+	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
+	return;
+#endif
+
+	/*
+	 * This is extremely unlikely to happen because almost all
+	 * systems have far more MAX_PA/2 than RAM can be fit into
+	 * DIMM slots.
+	 */
+	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
+	if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
+		pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
+		return;
+	}
+
+	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
+}
+
+static int __init l1tf_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		l1tf_mitigation = L1TF_MITIGATION_OFF;
+	else if (!strcmp(str, "flush,nowarn"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOWARN;
+	else if (!strcmp(str, "flush"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH;
+	else if (!strcmp(str, "flush,nosmt"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+	else if (!strcmp(str, "full"))
+		l1tf_mitigation = L1TF_MITIGATION_FULL;
+	else if (!strcmp(str, "full,force"))
+		l1tf_mitigation = L1TF_MITIGATION_FULL_FORCE;
+
+	return 0;
+}
+early_param("l1tf", l1tf_cmdline);
+
+#undef pr_fmt
+
 #ifdef CONFIG_SYSFS
 
+#define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion"
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+static const char *l1tf_vmx_states[] = {
+	[VMENTER_L1D_FLUSH_AUTO]		= "auto",
+	[VMENTER_L1D_FLUSH_NEVER]		= "vulnerable",
+	[VMENTER_L1D_FLUSH_COND]		= "conditional cache flushes",
+	[VMENTER_L1D_FLUSH_ALWAYS]		= "cache flushes",
+	[VMENTER_L1D_FLUSH_EPT_DISABLED]	= "EPT disabled",
+	[VMENTER_L1D_FLUSH_NOT_REQUIRED]	= "flush not necessary"
+};
+
+static ssize_t l1tf_show_state(char *buf)
+{
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO)
+		return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
+
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED ||
+	    (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER &&
+	     cpu_smt_control == CPU_SMT_ENABLED))
+		return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG,
+			       l1tf_vmx_states[l1tf_vmx_mitigation]);
+
+	return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG,
+		       l1tf_vmx_states[l1tf_vmx_mitigation],
+		       cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled");
+}
+#else
+static ssize_t l1tf_show_state(char *buf)
+{
+	return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
+}
+#endif
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -684,6 +800,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_SPEC_STORE_BYPASS:
 		return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
 
+	case X86_BUG_L1TF:
+		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
+			return l1tf_show_state(buf);
+		break;
 	default:
 		break;
 	}
@@ -710,4 +830,9 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
 }
+
+ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index eb4cb3efd20e..f3234010847c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -661,33 +661,36 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
 }
 
-void detect_ht(struct cpuinfo_x86 *c)
+int detect_ht_early(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
-	int index_msb, core_bits;
-	static bool printed;
 
 	if (!cpu_has(c, X86_FEATURE_HT))
-		return;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		goto out;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
-		return;
+		return -1;
 
 	cpuid(1, &eax, &ebx, &ecx, &edx);
 
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
-
-	if (smp_num_siblings == 1) {
+	if (smp_num_siblings == 1)
 		pr_info_once("CPU0: Hyper-Threading is disabled\n");
-		goto out;
-	}
+#endif
+	return 0;
+}
 
-	if (smp_num_siblings <= 1)
-		goto out;
+void detect_ht(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	int index_msb, core_bits;
+
+	if (detect_ht_early(c) < 0)
+		return;
 
 	index_msb = get_count_order(smp_num_siblings);
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
@@ -700,15 +703,6 @@ void detect_ht(struct cpuinfo_x86 *c)
 
 	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
 				       ((1 << core_bits) - 1);
-
-out:
-	if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) {
-		pr_info("CPU: Physical Processor ID: %d\n",
-			c->phys_proc_id);
-		pr_info("CPU: Processor Core ID: %d\n",
-			c->cpu_core_id);
-		printed = 1;
-	}
 #endif
 }
 
@@ -987,6 +981,21 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
 	{}
 };
 
+static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
+	/* in addition to cpu_no_speculation */
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MOOREFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_DENVERTON	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GEMINI_LAKE	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
+	{}
+};
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
@@ -1005,6 +1014,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
+	if (ia32_cap & ARCH_CAP_IBRS_ALL)
+		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
+
 	if (x86_match_cpu(cpu_no_meltdown))
 		return;
 
@@ -1013,6 +1025,29 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 		return;
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+
+	if (x86_match_cpu(cpu_no_l1tf))
+		return;
+
+	setup_force_cpu_bug(X86_BUG_L1TF);
+}
+
+/*
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
+ * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
+ */
+static void detect_nopl(void)
+{
+#ifdef CONFIG_X86_32
+	setup_clear_cpu_cap(X86_FEATURE_NOPL);
+#else
+	setup_force_cpu_cap(X86_FEATURE_NOPL);
+#endif
 }
 
 /*
@@ -1089,6 +1124,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	if (!pgtable_l5_enabled())
 		setup_clear_cpu_cap(X86_FEATURE_LA57);
+
+	detect_nopl();
 }
 
 void __init early_cpu_init(void)
@@ -1124,24 +1161,6 @@ void __init early_cpu_init(void)
 	early_identify_cpu(&boot_cpu_data);
 }
 
-/*
- * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
- * unfortunately, that's not true in practice because of early VIA
- * chips and (more importantly) broken virtualizers that are not easy
- * to detect. In the latter case it doesn't even *fail* reliably, so
- * probing for it doesn't even work. Disable it completely on 32-bit
- * unless we can find a reliable way to detect all the broken cases.
- * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
- */
-static void detect_nopl(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_X86_32
-	clear_cpu_cap(c, X86_FEATURE_NOPL);
-#else
-	set_cpu_cap(c, X86_FEATURE_NOPL);
-#endif
-}
-
 static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_64
@@ -1204,8 +1223,6 @@ static void generic_identify(struct cpuinfo_x86 *c)
 
 	get_model_name(c); /* Default name */
 
-	detect_nopl(c);
-
 	detect_null_seg_behavior(c);
 
 	/*
@@ -1804,11 +1821,12 @@ void cpu_init(void)
 	enter_lazy_tlb(&init_mm, curr);
 
 	/*
-	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
-	 * task never enters user mode.
+	 * Initialize the TSS.  sp0 points to the entry trampoline stack
+	 * regardless of what task is running.
 	 */
 	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
+	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
 
 	load_mm_ldt(&init_mm);
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 38216f678fc3..e59c0ea82a33 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -55,7 +55,9 @@ extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 
 extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
+extern int detect_extended_topology_early(struct cpuinfo_x86 *c);
 extern int detect_extended_topology(struct cpuinfo_x86 *c);
+extern int detect_ht_early(struct cpuinfo_x86 *c);
 extern void detect_ht(struct cpuinfo_x86 *c);
 
 unsigned int aperfmperf_get_khz(int cpu);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index eb75564f2d25..401e8c133108 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -301,6 +301,13 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	}
 
 	check_mpx_erratum(c);
+
+	/*
+	 * Get the number of SMT siblings early from the extended topology
+	 * leaf, if available. Otherwise try the legacy SMT detection.
+	 */
+	if (detect_extended_topology_early(c) < 0)
+		detect_ht_early(c);
 }
 
 #ifdef CONFIG_X86_32
@@ -465,14 +472,17 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
 #define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC	0x00000001
 #define X86_VMX_FEATURE_PROC_CTLS2_EPT		0x00000002
 #define X86_VMX_FEATURE_PROC_CTLS2_VPID		0x00000020
+#define x86_VMX_FEATURE_EPT_CAP_AD		0x00200000
 
 	u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+	u32 msr_vpid_cap, msr_ept_cap;
 
 	clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
 	clear_cpu_cap(c, X86_FEATURE_VNMI);
 	clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
 	clear_cpu_cap(c, X86_FEATURE_EPT);
 	clear_cpu_cap(c, X86_FEATURE_VPID);
+	clear_cpu_cap(c, X86_FEATURE_EPT_AD);
 
 	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
 	msr_ctl = vmx_msr_high | vmx_msr_low;
@@ -487,8 +497,13 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
 		if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
 		    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
 			set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
-		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) {
 			set_cpu_cap(c, X86_FEATURE_EPT);
+			rdmsr(MSR_IA32_VMX_EPT_VPID_CAP,
+			      msr_ept_cap, msr_vpid_cap);
+			if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD)
+				set_cpu_cap(c, X86_FEATURE_EPT_AD);
+		}
 		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
 			set_cpu_cap(c, X86_FEATURE_VPID);
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index ec4754f81cbd..abb71ac70443 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -859,6 +859,8 @@ static __init bool get_rdt_resources(void)
 	return (rdt_mon_capable || rdt_alloc_capable);
 }
 
+static enum cpuhp_state rdt_online;
+
 static int __init intel_rdt_late_init(void)
 {
 	struct rdt_resource *r;
@@ -880,6 +882,7 @@ static int __init intel_rdt_late_init(void)
 		cpuhp_remove_state(state);
 		return ret;
 	}
+	rdt_online = state;
 
 	for_each_alloc_capable_rdt_resource(r)
 		pr_info("Intel RDT %s allocation detected\n", r->name);
@@ -891,3 +894,11 @@ static int __init intel_rdt_late_init(void)
 }
 
 late_initcall(intel_rdt_late_init);
+
+static void __exit intel_rdt_exit(void)
+{
+	cpuhp_remove_state(rdt_online);
+	rdtgroup_exit();
+}
+
+__exitcall(intel_rdt_exit);
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 39752825e376..4e588f36228f 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -81,6 +81,34 @@ enum rdt_group_type {
 };
 
 /**
+ * enum rdtgrp_mode - Mode of a RDT resource group
+ * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
+ * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed
+ * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking
+ * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations
+ *                          allowed AND the allocations are Cache Pseudo-Locked
+ *
+ * The mode of a resource group enables control over the allowed overlap
+ * between allocations associated with different resource groups (classes
+ * of service). User is able to modify the mode of a resource group by
+ * writing to the "mode" resctrl file associated with the resource group.
+ *
+ * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by
+ * writing the appropriate text to the "mode" file. A resource group enters
+ * "pseudo-locked" mode after the schemata is written while the resource
+ * group is in "pseudo-locksetup" mode.
+ */
+enum rdtgrp_mode {
+	RDT_MODE_SHAREABLE = 0,
+	RDT_MODE_EXCLUSIVE,
+	RDT_MODE_PSEUDO_LOCKSETUP,
+	RDT_MODE_PSEUDO_LOCKED,
+
+	/* Must be last */
+	RDT_NUM_MODES,
+};
+
+/**
  * struct mongroup - store mon group's data in resctrl fs.
  * @mon_data_kn		kernlfs node for the mon_data directory
  * @parent:			parent rdtgrp
@@ -95,6 +123,43 @@ struct mongroup {
 };
 
 /**
+ * struct pseudo_lock_region - pseudo-lock region information
+ * @r:			RDT resource to which this pseudo-locked region
+ *			belongs
+ * @d:			RDT domain to which this pseudo-locked region
+ *			belongs
+ * @cbm:		bitmask of the pseudo-locked region
+ * @lock_thread_wq:	waitqueue used to wait on the pseudo-locking thread
+ *			completion
+ * @thread_done:	variable used by waitqueue to test if pseudo-locking
+ *			thread completed
+ * @cpu:		core associated with the cache on which the setup code
+ *			will be run
+ * @line_size:		size of the cache lines
+ * @size:		size of pseudo-locked region in bytes
+ * @kmem:		the kernel memory associated with pseudo-locked region
+ * @minor:		minor number of character device associated with this
+ *			region
+ * @debugfs_dir:	pointer to this region's directory in the debugfs
+ *			filesystem
+ * @pm_reqs:		Power management QoS requests related to this region
+ */
+struct pseudo_lock_region {
+	struct rdt_resource	*r;
+	struct rdt_domain	*d;
+	u32			cbm;
+	wait_queue_head_t	lock_thread_wq;
+	int			thread_done;
+	int			cpu;
+	unsigned int		line_size;
+	unsigned int		size;
+	void			*kmem;
+	unsigned int		minor;
+	struct dentry		*debugfs_dir;
+	struct list_head	pm_reqs;
+};
+
+/**
  * struct rdtgroup - store rdtgroup's data in resctrl file system.
  * @kn:				kernfs node
  * @rdtgroup_list:		linked list for all rdtgroups
@@ -106,16 +171,20 @@ struct mongroup {
  * @type:			indicates type of this rdtgroup - either
  *				monitor only or ctrl_mon group
  * @mon:			mongroup related data
+ * @mode:			mode of resource group
+ * @plr:			pseudo-locked region
  */
 struct rdtgroup {
-	struct kernfs_node	*kn;
-	struct list_head	rdtgroup_list;
-	u32			closid;
-	struct cpumask		cpu_mask;
-	int			flags;
-	atomic_t		waitcount;
-	enum rdt_group_type	type;
-	struct mongroup		mon;
+	struct kernfs_node		*kn;
+	struct list_head		rdtgroup_list;
+	u32				closid;
+	struct cpumask			cpu_mask;
+	int				flags;
+	atomic_t			waitcount;
+	enum rdt_group_type		type;
+	struct mongroup			mon;
+	enum rdtgrp_mode		mode;
+	struct pseudo_lock_region	*plr;
 };
 
 /* rdtgroup.flags */
@@ -148,6 +217,7 @@ extern struct list_head rdt_all_groups;
 extern int max_name_width, max_data_width;
 
 int __init rdtgroup_init(void);
+void __exit rdtgroup_exit(void);
 
 /**
  * struct rftype - describe each file in the resctrl file system
@@ -216,22 +286,24 @@ struct mbm_state {
  * @mbps_val:	When mba_sc is enabled, this holds the bandwidth in MBps
  * @new_ctrl:	new ctrl value to be loaded
  * @have_new_ctrl: did user provide new_ctrl for this domain
+ * @plr:	pseudo-locked region (if any) associated with domain
  */
 struct rdt_domain {
-	struct list_head	list;
-	int			id;
-	struct cpumask		cpu_mask;
-	unsigned long		*rmid_busy_llc;
-	struct mbm_state	*mbm_total;
-	struct mbm_state	*mbm_local;
-	struct delayed_work	mbm_over;
-	struct delayed_work	cqm_limbo;
-	int			mbm_work_cpu;
-	int			cqm_work_cpu;
-	u32			*ctrl_val;
-	u32			*mbps_val;
-	u32			new_ctrl;
-	bool			have_new_ctrl;
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+	unsigned long			*rmid_busy_llc;
+	struct mbm_state		*mbm_total;
+	struct mbm_state		*mbm_local;
+	struct delayed_work		mbm_over;
+	struct delayed_work		cqm_limbo;
+	int				mbm_work_cpu;
+	int				cqm_work_cpu;
+	u32				*ctrl_val;
+	u32				*mbps_val;
+	u32				new_ctrl;
+	bool				have_new_ctrl;
+	struct pseudo_lock_region	*plr;
 };
 
 /**
@@ -351,7 +423,7 @@ struct rdt_resource {
 	struct rdt_cache	cache;
 	struct rdt_membw	membw;
 	const char		*format_str;
-	int (*parse_ctrlval)	(char *buf, struct rdt_resource *r,
+	int (*parse_ctrlval)	(void *data, struct rdt_resource *r,
 				 struct rdt_domain *d);
 	struct list_head	evt_list;
 	int			num_rmid;
@@ -359,8 +431,8 @@ struct rdt_resource {
 	unsigned long		fflags;
 };
 
-int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d);
-int parse_bw(char *buf, struct rdt_resource *r,  struct rdt_domain *d);
+int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d);
+int parse_bw(void *_buf, struct rdt_resource *r,  struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
@@ -368,7 +440,7 @@ extern struct rdt_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
-int __init rdtgroup_init(void);
+extern struct dentry *debugfs_resctrl;
 
 enum {
 	RDT_RESOURCE_L3,
@@ -439,13 +511,32 @@ void rdt_last_cmd_printf(const char *fmt, ...);
 void rdt_ctrl_update(void *arg);
 struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
 void rdtgroup_kn_unlock(struct kernfs_node *kn);
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+			     umode_t mask);
 struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 				   struct list_head **pos);
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+			   u32 _cbm, int closid, bool exclusive);
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
+				  u32 cbm);
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
+int rdtgroup_tasks_assigned(struct rdtgroup *r);
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm);
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
+int rdt_pseudo_lock_init(void);
+void rdt_pseudo_lock_release(void);
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
+int update_domains(struct rdt_resource *r, int closid);
+void closid_free(int closid);
 int alloc_rmid(void);
 void free_rmid(u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 116d57b248d3..af358ca05160 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -64,9 +64,10 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	return true;
 }
 
-int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d)
 {
 	unsigned long data;
+	char *buf = _buf;
 
 	if (d->have_new_ctrl) {
 		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
@@ -87,7 +88,7 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
  */
-static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
 	unsigned long first_bit, zero_bit, val;
 	unsigned int cbm_len = r->cache.cbm_len;
@@ -122,22 +123,64 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	return true;
 }
 
+struct rdt_cbm_parse_data {
+	struct rdtgroup		*rdtgrp;
+	char			*buf;
+};
+
 /*
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
-int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
 {
-	unsigned long data;
+	struct rdt_cbm_parse_data *data = _data;
+	struct rdtgroup *rdtgrp = data->rdtgrp;
+	u32 cbm_val;
 
 	if (d->have_new_ctrl) {
 		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
 		return -EINVAL;
 	}
 
-	if(!cbm_validate(buf, &data, r))
+	/*
+	 * Cannot set up more than one pseudo-locked region in a cache
+	 * hierarchy.
+	 */
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
+		rdt_last_cmd_printf("pseudo-locked region in hierarchy\n");
 		return -EINVAL;
-	d->new_ctrl = data;
+	}
+
+	if (!cbm_validate(data->buf, &cbm_val, r))
+		return -EINVAL;
+
+	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
+	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
+		rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * The CBM may not overlap with the CBM of another closid if
+	 * either is exclusive.
+	 */
+	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) {
+		rdt_last_cmd_printf("overlaps with exclusive group\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) {
+		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			rdt_last_cmd_printf("overlaps with other group\n");
+			return -EINVAL;
+		}
+	}
+
+	d->new_ctrl = cbm_val;
 	d->have_new_ctrl = true;
 
 	return 0;
@@ -149,8 +192,10 @@ int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
  * separated by ";". The "id" is in decimal, and must match one of
  * the "id"s for this resource.
  */
-static int parse_line(char *line, struct rdt_resource *r)
+static int parse_line(char *line, struct rdt_resource *r,
+		      struct rdtgroup *rdtgrp)
 {
+	struct rdt_cbm_parse_data data;
 	char *dom = NULL, *id;
 	struct rdt_domain *d;
 	unsigned long dom_id;
@@ -167,15 +212,32 @@ next:
 	dom = strim(dom);
 	list_for_each_entry(d, &r->domains, list) {
 		if (d->id == dom_id) {
-			if (r->parse_ctrlval(dom, r, d))
+			data.buf = dom;
+			data.rdtgrp = rdtgrp;
+			if (r->parse_ctrlval(&data, r, d))
 				return -EINVAL;
+			if (rdtgrp->mode ==  RDT_MODE_PSEUDO_LOCKSETUP) {
+				/*
+				 * In pseudo-locking setup mode and just
+				 * parsed a valid CBM that should be
+				 * pseudo-locked. Only one locked region per
+				 * resource group and domain so just do
+				 * the required initialization for single
+				 * region and return.
+				 */
+				rdtgrp->plr->r = r;
+				rdtgrp->plr->d = d;
+				rdtgrp->plr->cbm = d->new_ctrl;
+				d->plr = rdtgrp->plr;
+				return 0;
+			}
 			goto next;
 		}
 	}
 	return -EINVAL;
 }
 
-static int update_domains(struct rdt_resource *r, int closid)
+int update_domains(struct rdt_resource *r, int closid)
 {
 	struct msr_param msr_param;
 	cpumask_var_t cpu_mask;
@@ -220,13 +282,14 @@ done:
 	return 0;
 }
 
-static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
+static int rdtgroup_parse_resource(char *resname, char *tok,
+				   struct rdtgroup *rdtgrp)
 {
 	struct rdt_resource *r;
 
 	for_each_alloc_enabled_rdt_resource(r) {
-		if (!strcmp(resname, r->name) && closid < r->num_closid)
-			return parse_line(tok, r);
+		if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid)
+			return parse_line(tok, r, rdtgrp);
 	}
 	rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname);
 	return -EINVAL;
@@ -239,7 +302,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	struct rdt_domain *dom;
 	struct rdt_resource *r;
 	char *tok, *resname;
-	int closid, ret = 0;
+	int ret = 0;
 
 	/* Valid input requires a trailing newline */
 	if (nbytes == 0 || buf[nbytes - 1] != '\n')
@@ -253,7 +316,15 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	}
 	rdt_last_cmd_clear();
 
-	closid = rdtgrp->closid;
+	/*
+	 * No changes to pseudo-locked region allowed. It has to be removed
+	 * and re-created instead.
+	 */
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("resource group is pseudo-locked\n");
+		goto out;
+	}
 
 	for_each_alloc_enabled_rdt_resource(r) {
 		list_for_each_entry(dom, &r->domains, list)
@@ -272,17 +343,27 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 			ret = -EINVAL;
 			goto out;
 		}
-		ret = rdtgroup_parse_resource(resname, tok, closid);
+		ret = rdtgroup_parse_resource(resname, tok, rdtgrp);
 		if (ret)
 			goto out;
 	}
 
 	for_each_alloc_enabled_rdt_resource(r) {
-		ret = update_domains(r, closid);
+		ret = update_domains(r, rdtgrp->closid);
 		if (ret)
 			goto out;
 	}
 
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		/*
+		 * If pseudo-locking fails we keep the resource group in
+		 * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service
+		 * active and updated for just the domain the pseudo-locked
+		 * region was requested for.
+		 */
+		ret = rdtgroup_pseudo_lock_create(rdtgrp);
+	}
+
 out:
 	rdtgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
@@ -318,10 +399,18 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (rdtgrp) {
-		closid = rdtgrp->closid;
-		for_each_alloc_enabled_rdt_resource(r) {
-			if (closid < r->num_closid)
-				show_doms(s, r, closid);
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			for_each_alloc_enabled_rdt_resource(r)
+				seq_printf(s, "%s:uninitialized\n", r->name);
+		} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name,
+				   rdtgrp->plr->d->id, rdtgrp->plr->cbm);
+		} else {
+			closid = rdtgrp->closid;
+			for_each_alloc_enabled_rdt_resource(r) {
+				if (closid < r->num_closid)
+					show_doms(s, r, closid);
+			}
 		}
 	} else {
 		ret = -ENOENT;
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
new file mode 100644
index 000000000000..40f3903ae5d9
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -0,0 +1,1522 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Resource Director Technology (RDT)
+ *
+ * Pseudo-locking support built on top of Cache Allocation Technology (CAT)
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Author: Reinette Chatre <reinette.chatre@intel.com>
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/cacheinfo.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/debugfs.h>
+#include <linux/kthread.h>
+#include <linux/mman.h>
+#include <linux/pm_qos.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/intel-family.h>
+#include <asm/intel_rdt_sched.h>
+#include <asm/perf_event.h>
+
+#include "intel_rdt.h"
+
+#define CREATE_TRACE_POINTS
+#include "intel_rdt_pseudo_lock_event.h"
+
+/*
+ * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware
+ * prefetcher state. Details about this register can be found in the MSR
+ * tables for specific platforms found in Intel's SDM.
+ */
+#define MSR_MISC_FEATURE_CONTROL	0x000001a4
+
+/*
+ * The bits needed to disable hardware prefetching varies based on the
+ * platform. During initialization we will discover which bits to use.
+ */
+static u64 prefetch_disable_bits;
+
+/*
+ * Major number assigned to and shared by all devices exposing
+ * pseudo-locked regions.
+ */
+static unsigned int pseudo_lock_major;
+static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
+static struct class *pseudo_lock_class;
+
+/**
+ * get_prefetch_disable_bits - prefetch disable bits of supported platforms
+ *
+ * Capture the list of platforms that have been validated to support
+ * pseudo-locking. This includes testing to ensure pseudo-locked regions
+ * with low cache miss rates can be created under variety of load conditions
+ * as well as that these pseudo-locked regions can maintain their low cache
+ * miss rates under variety of load conditions for significant lengths of time.
+ *
+ * After a platform has been validated to support pseudo-locking its
+ * hardware prefetch disable bits are included here as they are documented
+ * in the SDM.
+ *
+ * When adding a platform here also add support for its cache events to
+ * measure_cycles_perf_fn()
+ *
+ * Return:
+ * If platform is supported, the bits to disable hardware prefetchers, 0
+ * if platform is not supported.
+ */
+static u64 get_prefetch_disable_bits(void)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+	    boot_cpu_data.x86 != 6)
+		return 0;
+
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_BROADWELL_X:
+		/*
+		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
+		 * as:
+		 * 0    L2 Hardware Prefetcher Disable (R/W)
+		 * 1    L2 Adjacent Cache Line Prefetcher Disable (R/W)
+		 * 2    DCU Hardware Prefetcher Disable (R/W)
+		 * 3    DCU IP Prefetcher Disable (R/W)
+		 * 63:4 Reserved
+		 */
+		return 0xF;
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+		/*
+		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
+		 * as:
+		 * 0     L2 Hardware Prefetcher Disable (R/W)
+		 * 1     Reserved
+		 * 2     DCU Hardware Prefetcher Disable (R/W)
+		 * 63:3  Reserved
+		 */
+		return 0x5;
+	}
+
+	return 0;
+}
+
+/*
+ * Helper to write 64bit value to MSR without tracing. Used when
+ * use of the cache should be restricted and use of registers used
+ * for local variables avoided.
+ */
+static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val)
+{
+	__wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
+}
+
+/**
+ * pseudo_lock_minor_get - Obtain available minor number
+ * @minor: Pointer to where new minor number will be stored
+ *
+ * A bitmask is used to track available minor numbers. Here the next free
+ * minor number is marked as unavailable and returned.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+static int pseudo_lock_minor_get(unsigned int *minor)
+{
+	unsigned long first_bit;
+
+	first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);
+
+	if (first_bit == MINORBITS)
+		return -ENOSPC;
+
+	__clear_bit(first_bit, &pseudo_lock_minor_avail);
+	*minor = first_bit;
+
+	return 0;
+}
+
+/**
+ * pseudo_lock_minor_release - Return minor number to available
+ * @minor: The minor number made available
+ */
+static void pseudo_lock_minor_release(unsigned int minor)
+{
+	__set_bit(minor, &pseudo_lock_minor_avail);
+}
+
+/**
+ * region_find_by_minor - Locate a pseudo-lock region by inode minor number
+ * @minor: The minor number of the device representing pseudo-locked region
+ *
+ * When the character device is accessed we need to determine which
+ * pseudo-locked region it belongs to. This is done by matching the minor
+ * number of the device to the pseudo-locked region it belongs.
+ *
+ * Minor numbers are assigned at the time a pseudo-locked region is associated
+ * with a cache instance.
+ *
+ * Return: On success return pointer to resource group owning the pseudo-locked
+ *         region, NULL on failure.
+ */
+static struct rdtgroup *region_find_by_minor(unsigned int minor)
+{
+	struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
+			rdtgrp_match = rdtgrp;
+			break;
+		}
+	}
+	return rdtgrp_match;
+}
+
+/**
+ * pseudo_lock_pm_req - A power management QoS request list entry
+ * @list:	Entry within the @pm_reqs list for a pseudo-locked region
+ * @req:	PM QoS request
+ */
+struct pseudo_lock_pm_req {
+	struct list_head list;
+	struct dev_pm_qos_request req;
+};
+
+static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
+{
+	struct pseudo_lock_pm_req *pm_req, *next;
+
+	list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
+		dev_pm_qos_remove_request(&pm_req->req);
+		list_del(&pm_req->list);
+		kfree(pm_req);
+	}
+}
+
+/**
+ * pseudo_lock_cstates_constrain - Restrict cores from entering C6
+ *
+ * To prevent the cache from being affected by power management entering
+ * C6 has to be avoided. This is accomplished by requesting a latency
+ * requirement lower than lowest C6 exit latency of all supported
+ * platforms as found in the cpuidle state tables in the intel_idle driver.
+ * At this time it is possible to do so with a single latency requirement
+ * for all supported platforms.
+ *
+ * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
+ * the ACPI latencies need to be considered while keeping in mind that C2
+ * may be set to map to deeper sleep states. In this case the latency
+ * requirement needs to prevent entering C2 also.
+ */
+static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
+{
+	struct pseudo_lock_pm_req *pm_req;
+	int cpu;
+	int ret;
+
+	for_each_cpu(cpu, &plr->d->cpu_mask) {
+		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
+		if (!pm_req) {
+			rdt_last_cmd_puts("fail allocating mem for PM QoS\n");
+			ret = -ENOMEM;
+			goto out_err;
+		}
+		ret = dev_pm_qos_add_request(get_cpu_device(cpu),
+					     &pm_req->req,
+					     DEV_PM_QOS_RESUME_LATENCY,
+					     30);
+		if (ret < 0) {
+			rdt_last_cmd_printf("fail to add latency req cpu%d\n",
+					    cpu);
+			kfree(pm_req);
+			ret = -1;
+			goto out_err;
+		}
+		list_add(&pm_req->list, &plr->pm_reqs);
+	}
+
+	return 0;
+
+out_err:
+	pseudo_lock_cstates_relax(plr);
+	return ret;
+}
+
+/**
+ * pseudo_lock_region_clear - Reset pseudo-lock region data
+ * @plr: pseudo-lock region
+ *
+ * All content of the pseudo-locked region is reset - any memory allocated
+ * freed.
+ *
+ * Return: void
+ */
+static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
+{
+	plr->size = 0;
+	plr->line_size = 0;
+	kfree(plr->kmem);
+	plr->kmem = NULL;
+	plr->r = NULL;
+	if (plr->d)
+		plr->d->plr = NULL;
+	plr->d = NULL;
+	plr->cbm = 0;
+	plr->debugfs_dir = NULL;
+}
+
+/**
+ * pseudo_lock_region_init - Initialize pseudo-lock region information
+ * @plr: pseudo-lock region
+ *
+ * Called after user provided a schemata to be pseudo-locked. From the
+ * schemata the &struct pseudo_lock_region is on entry already initialized
+ * with the resource, domain, and capacity bitmask. Here the information
+ * required for pseudo-locking is deduced from this data and &struct
+ * pseudo_lock_region initialized further. This information includes:
+ * - size in bytes of the region to be pseudo-locked
+ * - cache line size to know the stride with which data needs to be accessed
+ *   to be pseudo-locked
+ * - a cpu associated with the cache instance on which the pseudo-locking
+ *   flow can be executed
+ *
+ * Return: 0 on success, <0 on failure. Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
+{
+	struct cpu_cacheinfo *ci;
+	int ret;
+	int i;
+
+	/* Pick the first cpu we find that is associated with the cache. */
+	plr->cpu = cpumask_first(&plr->d->cpu_mask);
+
+	if (!cpu_online(plr->cpu)) {
+		rdt_last_cmd_printf("cpu %u associated with cache not online\n",
+				    plr->cpu);
+		ret = -ENODEV;
+		goto out_region;
+	}
+
+	ci = get_cpu_cacheinfo(plr->cpu);
+
+	plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm);
+
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == plr->r->cache_level) {
+			plr->line_size = ci->info_list[i].coherency_line_size;
+			return 0;
+		}
+	}
+
+	ret = -1;
+	rdt_last_cmd_puts("unable to determine cache line size\n");
+out_region:
+	pseudo_lock_region_clear(plr);
+	return ret;
+}
+
+/**
+ * pseudo_lock_init - Initialize a pseudo-lock region
+ * @rdtgrp: resource group to which new pseudo-locked region will belong
+ *
+ * A pseudo-locked region is associated with a resource group. When this
+ * association is created the pseudo-locked region is initialized. The
+ * details of the pseudo-locked region are not known at this time so only
+ * allocation is done and association established.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_init(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr;
+
+	plr = kzalloc(sizeof(*plr), GFP_KERNEL);
+	if (!plr)
+		return -ENOMEM;
+
+	init_waitqueue_head(&plr->lock_thread_wq);
+	INIT_LIST_HEAD(&plr->pm_reqs);
+	rdtgrp->plr = plr;
+	return 0;
+}
+
+/**
+ * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
+ * @plr: pseudo-lock region
+ *
+ * Initialize the details required to set up the pseudo-locked region and
+ * allocate the contiguous memory that will be pseudo-locked to the cache.
+ *
+ * Return: 0 on success, <0 on failure.  Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
+{
+	int ret;
+
+	ret = pseudo_lock_region_init(plr);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * We do not yet support contiguous regions larger than
+	 * KMALLOC_MAX_SIZE.
+	 */
+	if (plr->size > KMALLOC_MAX_SIZE) {
+		rdt_last_cmd_puts("requested region exceeds maximum size\n");
+		ret = -E2BIG;
+		goto out_region;
+	}
+
+	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
+	if (!plr->kmem) {
+		rdt_last_cmd_puts("unable to allocate memory\n");
+		ret = -ENOMEM;
+		goto out_region;
+	}
+
+	ret = 0;
+	goto out;
+out_region:
+	pseudo_lock_region_clear(plr);
+out:
+	return ret;
+}
+
+/**
+ * pseudo_lock_free - Free a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-locked region belonged
+ *
+ * The pseudo-locked region's resources have already been released, or not
+ * yet created at this point. Now it can be freed and disassociated from the
+ * resource group.
+ *
+ * Return: void
+ */
+static void pseudo_lock_free(struct rdtgroup *rdtgrp)
+{
+	pseudo_lock_region_clear(rdtgrp->plr);
+	kfree(rdtgrp->plr);
+	rdtgrp->plr = NULL;
+}
+
+/**
+ * pseudo_lock_fn - Load kernel memory into cache
+ * @_rdtgrp: resource group to which pseudo-lock region belongs
+ *
+ * This is the core pseudo-locking flow.
+ *
+ * First we ensure that the kernel memory cannot be found in the cache.
+ * Then, while taking care that there will be as little interference as
+ * possible, the memory to be loaded is accessed while core is running
+ * with class of service set to the bitmask of the pseudo-locked region.
+ * After this is complete no future CAT allocations will be allowed to
+ * overlap with this bitmask.
+ *
+ * Local register variables are utilized to ensure that the memory region
+ * to be locked is the only memory access made during the critical locking
+ * loop.
+ *
+ * Return: 0. Waiter on waitqueue will be woken on completion.
+ */
+static int pseudo_lock_fn(void *_rdtgrp)
+{
+	struct rdtgroup *rdtgrp = _rdtgrp;
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	u32 rmid_p, closid_p;
+	unsigned long i;
+#ifdef CONFIG_KASAN
+	/*
+	 * The registers used for local register variables are also used
+	 * when KASAN is active. When KASAN is active we use a regular
+	 * variable to ensure we always use a valid pointer, but the cost
+	 * is that this variable will enter the cache through evicting the
+	 * memory we are trying to lock into the cache. Thus expect lower
+	 * pseudo-locking success rate when KASAN is active.
+	 */
+	unsigned int line_size;
+	unsigned int size;
+	void *mem_r;
+#else
+	register unsigned int line_size asm("esi");
+	register unsigned int size asm("edi");
+#ifdef CONFIG_X86_64
+	register void *mem_r asm("rbx");
+#else
+	register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+	/*
+	 * Make sure none of the allocated memory is cached. If it is we
+	 * will get a cache hit in below loop from outside of pseudo-locked
+	 * region.
+	 * wbinvd (as opposed to clflush/clflushopt) is required to
+	 * increase likelihood that allocated cache portion will be filled
+	 * with associated memory.
+	 */
+	native_wbinvd();
+
+	/*
+	 * Always called with interrupts enabled. By disabling interrupts
+	 * ensure that we will not be preempted during this critical section.
+	 */
+	local_irq_disable();
+
+	/*
+	 * Call wrmsr and rdmsr as directly as possible to avoid tracing
+	 * clobbering local register variables or affecting cache accesses.
+	 *
+	 * Disable the hardware prefetcher so that when the end of the memory
+	 * being pseudo-locked is reached the hardware will not read beyond
+	 * the buffer and evict pseudo-locked memory read earlier from the
+	 * cache.
+	 */
+	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	closid_p = this_cpu_read(pqr_state.cur_closid);
+	rmid_p = this_cpu_read(pqr_state.cur_rmid);
+	mem_r = plr->kmem;
+	size = plr->size;
+	line_size = plr->line_size;
+	/*
+	 * Critical section begin: start by writing the closid associated
+	 * with the capacity bitmask of the cache region being
+	 * pseudo-locked followed by reading of kernel memory to load it
+	 * into the cache.
+	 */
+	__wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid);
+	/*
+	 * Cache was flushed earlier. Now access kernel memory to read it
+	 * into cache region associated with just activated plr->closid.
+	 * Loop over data twice:
+	 * - In first loop the cache region is shared with the page walker
+	 *   as it populates the paging structure caches (including TLB).
+	 * - In the second loop the paging structure caches are used and
+	 *   cache region is populated with the memory being referenced.
+	 */
+	for (i = 0; i < size; i += PAGE_SIZE) {
+		/*
+		 * Add a barrier to prevent speculative execution of this
+		 * loop reading beyond the end of the buffer.
+		 */
+		rmb();
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			:
+			: "r" (mem_r), "r" (i)
+			: "%eax", "memory");
+	}
+	for (i = 0; i < size; i += line_size) {
+		/*
+		 * Add a barrier to prevent speculative execution of this
+		 * loop reading beyond the end of the buffer.
+		 */
+		rmb();
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			:
+			: "r" (mem_r), "r" (i)
+			: "%eax", "memory");
+	}
+	/*
+	 * Critical section end: restore closid with capacity bitmask that
+	 * does not overlap with pseudo-locked region.
+	 */
+	__wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p);
+
+	/* Re-enable the hardware prefetcher(s) */
+	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	local_irq_enable();
+
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
+/**
+ * rdtgroup_monitor_in_progress - Test if monitoring in progress
+ * @r: resource group being queried
+ *
+ * Return: 1 if monitor groups have been created for this resource
+ * group, 0 otherwise.
+ */
+static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
+{
+	return !list_empty(&rdtgrp->mon.crdtgrp_list);
+}
+
+/**
+ * rdtgroup_locksetup_user_restrict - Restrict user access to group
+ * @rdtgrp: resource group needing access restricted
+ *
+ * A resource group used for cache pseudo-locking cannot have cpus or tasks
+ * assigned to it. This is communicated to the user by restricting access
+ * to all the files that can be used to make such changes.
+ *
+ * Permissions restored with rdtgroup_locksetup_user_restore()
+ *
+ * Return: 0 on success, <0 on failure. If a failure occurs during the
+ * restriction of access an attempt will be made to restore permissions but
+ * the state of the mode of these files will be uncertain when a failure
+ * occurs.
+ */
+static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+	if (ret)
+		goto err_tasks;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+	if (ret)
+		goto err_cpus;
+
+	if (rdt_mon_capable) {
+		ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
+		if (ret)
+			goto err_cpus_list;
+	}
+
+	ret = 0;
+	goto out;
+
+err_cpus_list:
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
+err_cpus:
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
+err_tasks:
+	rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_user_restore - Restore user access to group
+ * @rdtgrp: resource group needing access restored
+ *
+ * Restore all file access previously removed using
+ * rdtgroup_locksetup_user_restrict()
+ *
+ * Return: 0 on success, <0 on failure.  If a failure occurs during the
+ * restoration of access an attempt will be made to restrict permissions
+ * again but the state of the mode of these files will be uncertain when
+ * a failure occurs.
+ */
+static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
+	if (ret)
+		goto err_tasks;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
+	if (ret)
+		goto err_cpus;
+
+	if (rdt_mon_capable) {
+		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
+		if (ret)
+			goto err_cpus_list;
+	}
+
+	ret = 0;
+	goto out;
+
+err_cpus_list:
+	rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+err_cpus:
+	rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+err_tasks:
+	rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_enter - Resource group enters locksetup mode
+ * @rdtgrp: resource group requested to enter locksetup mode
+ *
+ * A resource group enters locksetup mode to reflect that it would be used
+ * to represent a pseudo-locked region and is in the process of being set
+ * up to do so. A resource group used for a pseudo-locked region would
+ * lose the closid associated with it so we cannot allow it to have any
+ * tasks or cpus assigned nor permit tasks or cpus to be assigned in the
+ * future. Monitoring of a pseudo-locked region is not allowed either.
+ *
+ * The above and more restrictions on a pseudo-locked region are checked
+ * for and enforced before the resource group enters the locksetup mode.
+ *
+ * Returns: 0 if the resource group successfully entered locksetup mode, <0
+ * on failure. On failure the last_cmd_status buffer is updated with text to
+ * communicate details of failure to the user.
+ */
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	/*
+	 * The default resource group can neither be removed nor lose the
+	 * default closid associated with it.
+	 */
+	if (rdtgrp == &rdtgroup_default) {
+		rdt_last_cmd_puts("cannot pseudo-lock default group\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Cache Pseudo-locking not supported when CDP is enabled.
+	 *
+	 * Some things to consider if you would like to enable this
+	 * support (using L3 CDP as example):
+	 * - When CDP is enabled two separate resources are exposed,
+	 *   L3DATA and L3CODE, but they are actually on the same cache.
+	 *   The implication for pseudo-locking is that if a
+	 *   pseudo-locked region is created on a domain of one
+	 *   resource (eg. L3CODE), then a pseudo-locked region cannot
+	 *   be created on that same domain of the other resource
+	 *   (eg. L3DATA). This is because the creation of a
+	 *   pseudo-locked region involves a call to wbinvd that will
+	 *   affect all cache allocations on particular domain.
+	 * - Considering the previous, it may be possible to only
+	 *   expose one of the CDP resources to pseudo-locking and
+	 *   hide the other. For example, we could consider to only
+	 *   expose L3DATA and since the L3 cache is unified it is
+	 *   still possible to place instructions there are execute it.
+	 * - If only one region is exposed to pseudo-locking we should
+	 *   still keep in mind that availability of a portion of cache
+	 *   for pseudo-locking should take into account both resources.
+	 *   Similarly, if a pseudo-locked region is created in one
+	 *   resource, the portion of cache used by it should be made
+	 *   unavailable to all future allocations from both resources.
+	 */
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled ||
+	    rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) {
+		rdt_last_cmd_puts("CDP enabled\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Not knowing the bits to disable prefetching implies that this
+	 * platform does not support Cache Pseudo-Locking.
+	 */
+	prefetch_disable_bits = get_prefetch_disable_bits();
+	if (prefetch_disable_bits == 0) {
+		rdt_last_cmd_puts("pseudo-locking not supported\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_monitor_in_progress(rdtgrp)) {
+		rdt_last_cmd_puts("monitoring in progress\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_tasks_assigned(rdtgrp)) {
+		rdt_last_cmd_puts("tasks assigned to resource group\n");
+		return -EINVAL;
+	}
+
+	if (!cpumask_empty(&rdtgrp->cpu_mask)) {
+		rdt_last_cmd_puts("CPUs assigned to resource group\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
+		rdt_last_cmd_puts("unable to modify resctrl permissions\n");
+		return -EIO;
+	}
+
+	ret = pseudo_lock_init(rdtgrp);
+	if (ret) {
+		rdt_last_cmd_puts("unable to init pseudo-lock region\n");
+		goto out_release;
+	}
+
+	/*
+	 * If this system is capable of monitoring a rmid would have been
+	 * allocated when the control group was created. This is not needed
+	 * anymore when this group would be used for pseudo-locking. This
+	 * is safe to call on platforms not capable of monitoring.
+	 */
+	free_rmid(rdtgrp->mon.rmid);
+
+	ret = 0;
+	goto out;
+
+out_release:
+	rdtgroup_locksetup_user_restore(rdtgrp);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_exit - resource group exist locksetup mode
+ * @rdtgrp: resource group
+ *
+ * When a resource group exits locksetup mode the earlier restrictions are
+ * lifted.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	if (rdt_mon_capable) {
+		ret = alloc_rmid();
+		if (ret < 0) {
+			rdt_last_cmd_puts("out of RMIDs\n");
+			return ret;
+		}
+		rdtgrp->mon.rmid = ret;
+	}
+
+	ret = rdtgroup_locksetup_user_restore(rdtgrp);
+	if (ret) {
+		free_rmid(rdtgrp->mon.rmid);
+		return ret;
+	}
+
+	pseudo_lock_free(rdtgrp);
+	return 0;
+}
+
+/**
+ * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
+ * @d: RDT domain
+ * @_cbm: CBM to test
+ *
+ * @d represents a cache instance and @_cbm a capacity bitmask that is
+ * considered for it. Determine if @_cbm overlaps with any existing
+ * pseudo-locked region on @d.
+ *
+ * Return: true if @_cbm overlaps with pseudo-locked region on @d, false
+ * otherwise.
+ */
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm)
+{
+	unsigned long *cbm = (unsigned long *)&_cbm;
+	unsigned long *cbm_b;
+	unsigned int cbm_len;
+
+	if (d->plr) {
+		cbm_len = d->plr->r->cache.cbm_len;
+		cbm_b = (unsigned long *)&d->plr->cbm;
+		if (bitmap_intersects(cbm, cbm_b, cbm_len))
+			return true;
+	}
+	return false;
+}
+
+/**
+ * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy
+ * @d: RDT domain under test
+ *
+ * The setup of a pseudo-locked region affects all cache instances within
+ * the hierarchy of the region. It is thus essential to know if any
+ * pseudo-locked regions exist within a cache hierarchy to prevent any
+ * attempts to create new pseudo-locked regions in the same hierarchy.
+ *
+ * Return: true if a pseudo-locked region exists in the hierarchy of @d or
+ *         if it is not possible to test due to memory allocation issue,
+ *         false otherwise.
+ */
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+{
+	cpumask_var_t cpu_with_psl;
+	struct rdt_resource *r;
+	struct rdt_domain *d_i;
+	bool ret = false;
+
+	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
+		return true;
+
+	/*
+	 * First determine which cpus have pseudo-locked regions
+	 * associated with them.
+	 */
+	for_each_alloc_enabled_rdt_resource(r) {
+		list_for_each_entry(d_i, &r->domains, list) {
+			if (d_i->plr)
+				cpumask_or(cpu_with_psl, cpu_with_psl,
+					   &d_i->cpu_mask);
+		}
+	}
+
+	/*
+	 * Next test if new pseudo-locked region would intersect with
+	 * existing region.
+	 */
+	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+		ret = true;
+
+	free_cpumask_var(cpu_with_psl);
+	return ret;
+}
+
+/**
+ * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory
+ * @_plr: pseudo-lock region to measure
+ *
+ * There is no deterministic way to test if a memory region is cached. One
+ * way is to measure how long it takes to read the memory, the speed of
+ * access is a good way to learn how close to the cpu the data was. Even
+ * more, if the prefetcher is disabled and the memory is read at a stride
+ * of half the cache line, then a cache miss will be easy to spot since the
+ * read of the first half would be significantly slower than the read of
+ * the second half.
+ *
+ * Return: 0. Waiter on waitqueue will be woken on completion.
+ */
+static int measure_cycles_lat_fn(void *_plr)
+{
+	struct pseudo_lock_region *plr = _plr;
+	unsigned long i;
+	u64 start, end;
+#ifdef CONFIG_KASAN
+	/*
+	 * The registers used for local register variables are also used
+	 * when KASAN is active. When KASAN is active we use a regular
+	 * variable to ensure we always use a valid pointer to access memory.
+	 * The cost is that accessing this pointer, which could be in
+	 * cache, will be included in the measurement of memory read latency.
+	 */
+	void *mem_r;
+#else
+#ifdef CONFIG_X86_64
+	register void *mem_r asm("rbx");
+#else
+	register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+	local_irq_disable();
+	/*
+	 * The wrmsr call may be reordered with the assignment below it.
+	 * Call wrmsr as directly as possible to avoid tracing clobbering
+	 * local register variable used for memory pointer.
+	 */
+	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	mem_r = plr->kmem;
+	/*
+	 * Dummy execute of the time measurement to load the needed
+	 * instructions into the L1 instruction cache.
+	 */
+	start = rdtsc_ordered();
+	for (i = 0; i < plr->size; i += 32) {
+		start = rdtsc_ordered();
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			     :
+			     : "r" (mem_r), "r" (i)
+			     : "%eax", "memory");
+		end = rdtsc_ordered();
+		trace_pseudo_lock_mem_latency((u32)(end - start));
+	}
+	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	local_irq_enable();
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
+static int measure_cycles_perf_fn(void *_plr)
+{
+	unsigned long long l3_hits = 0, l3_miss = 0;
+	u64 l3_hit_bits = 0, l3_miss_bits = 0;
+	struct pseudo_lock_region *plr = _plr;
+	unsigned long long l2_hits, l2_miss;
+	u64 l2_hit_bits, l2_miss_bits;
+	unsigned long i;
+#ifdef CONFIG_KASAN
+	/*
+	 * The registers used for local register variables are also used
+	 * when KASAN is active. When KASAN is active we use regular variables
+	 * at the cost of including cache access latency to these variables
+	 * in the measurements.
+	 */
+	unsigned int line_size;
+	unsigned int size;
+	void *mem_r;
+#else
+	register unsigned int line_size asm("esi");
+	register unsigned int size asm("edi");
+#ifdef CONFIG_X86_64
+	register void *mem_r asm("rbx");
+#else
+	register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+	/*
+	 * Non-architectural event for the Goldmont Microarchitecture
+	 * from Intel x86 Architecture Software Developer Manual (SDM):
+	 * MEM_LOAD_UOPS_RETIRED D1H (event number)
+	 * Umask values:
+	 *     L1_HIT   01H
+	 *     L2_HIT   02H
+	 *     L1_MISS  08H
+	 *     L2_MISS  10H
+	 *
+	 * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
+	 * has two "no fix" errata associated with it: BDM35 and BDM100. On
+	 * this platform we use the following events instead:
+	 *  L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/)
+	 *       REFERENCES FFH
+	 *       MISS       3FH
+	 *  LONGEST_LAT_CACHE 2EH (Documented in SDM)
+	 *       REFERENCE 4FH
+	 *       MISS      41H
+	 */
+
+	/*
+	 * Start by setting flags for IA32_PERFEVTSELx:
+	 *     OS  (Operating system mode)  0x2
+	 *     INT (APIC interrupt enable)  0x10
+	 *     EN  (Enable counter)         0x40
+	 *
+	 * Then add the Umask value and event number to select performance
+	 * event.
+	 */
+
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+		l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1;
+		l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1;
+		break;
+	case INTEL_FAM6_BROADWELL_X:
+		/* On BDW the l2_hit_bits count references, not hits */
+		l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24;
+		l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24;
+		/* On BDW the l3_hit_bits count references, not hits */
+		l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e;
+		l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e;
+		break;
+	default:
+		goto out;
+	}
+
+	local_irq_disable();
+	/*
+	 * Call wrmsr direcly to avoid the local register variables from
+	 * being overwritten due to reordering of their assignment with
+	 * the wrmsr calls.
+	 */
+	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	/* Disable events and reset counters */
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0);
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0);
+	}
+	/* Set and enable the L2 counters */
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits);
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+				      l3_hit_bits);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+				      l3_miss_bits);
+	}
+	mem_r = plr->kmem;
+	size = plr->size;
+	line_size = plr->line_size;
+	for (i = 0; i < size; i += line_size) {
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			     :
+			     : "r" (mem_r), "r" (i)
+			     : "%eax", "memory");
+	}
+	/*
+	 * Call wrmsr directly (no tracing) to not influence
+	 * the cache access counters as they are disabled.
+	 */
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0,
+			      l2_hit_bits & ~(0x40ULL << 16));
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1,
+			      l2_miss_bits & ~(0x40ULL << 16));
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+				      l3_hit_bits & ~(0x40ULL << 16));
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+				      l3_miss_bits & ~(0x40ULL << 16));
+	}
+	l2_hits = native_read_pmc(0);
+	l2_miss = native_read_pmc(1);
+	if (l3_hit_bits > 0) {
+		l3_hits = native_read_pmc(2);
+		l3_miss = native_read_pmc(3);
+	}
+	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	local_irq_enable();
+	/*
+	 * On BDW we count references and misses, need to adjust. Sometimes
+	 * the "hits" counter is a bit more than the references, for
+	 * example, x references but x + 1 hits. To not report invalid
+	 * hit values in this case we treat that as misses eaqual to
+	 * references.
+	 */
+	if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+		l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss);
+	trace_pseudo_lock_l2(l2_hits, l2_miss);
+	if (l3_hit_bits > 0) {
+		if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+			l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss);
+		trace_pseudo_lock_l3(l3_hits, l3_miss);
+	}
+
+out:
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
+/**
+ * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
+ *
+ * The measurement of latency to access a pseudo-locked region should be
+ * done from a cpu that is associated with that pseudo-locked region.
+ * Determine which cpu is associated with this region and start a thread on
+ * that cpu to perform the measurement, wait for that thread to complete.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct task_struct *thread;
+	unsigned int cpu;
+	int ret = -1;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	if (rdtgrp->flags & RDT_DELETED) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	plr->thread_done = 0;
+	cpu = cpumask_first(&plr->d->cpu_mask);
+	if (!cpu_online(cpu)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (sel == 1)
+		thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
+						cpu_to_node(cpu),
+						"pseudo_lock_measure/%u",
+						cpu);
+	else if (sel == 2)
+		thread = kthread_create_on_node(measure_cycles_perf_fn, plr,
+						cpu_to_node(cpu),
+						"pseudo_lock_measure/%u",
+						cpu);
+	else
+		goto out;
+
+	if (IS_ERR(thread)) {
+		ret = PTR_ERR(thread);
+		goto out;
+	}
+	kthread_bind(thread, cpu);
+	wake_up_process(thread);
+
+	ret = wait_event_interruptible(plr->lock_thread_wq,
+				       plr->thread_done == 1);
+	if (ret < 0)
+		goto out;
+
+	ret = 0;
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+	return ret;
+}
+
+static ssize_t pseudo_lock_measure_trigger(struct file *file,
+					   const char __user *user_buf,
+					   size_t count, loff_t *ppos)
+{
+	struct rdtgroup *rdtgrp = file->private_data;
+	size_t buf_size;
+	char buf[32];
+	int ret;
+	int sel;
+
+	buf_size = min(count, (sizeof(buf) - 1));
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	ret = kstrtoint(buf, 10, &sel);
+	if (ret == 0) {
+		if (sel != 1)
+			return -EINVAL;
+		ret = debugfs_file_get(file->f_path.dentry);
+		if (ret)
+			return ret;
+		ret = pseudo_lock_measure_cycles(rdtgrp, sel);
+		if (ret == 0)
+			ret = count;
+		debugfs_file_put(file->f_path.dentry);
+	}
+
+	return ret;
+}
+
+static const struct file_operations pseudo_measure_fops = {
+	.write = pseudo_lock_measure_trigger,
+	.open = simple_open,
+	.llseek = default_llseek,
+};
+
+/**
+ * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-lock region belongs
+ *
+ * Called when a resource group in the pseudo-locksetup mode receives a
+ * valid schemata that should be pseudo-locked. Since the resource group is
+ * in pseudo-locksetup mode the &struct pseudo_lock_region has already been
+ * allocated and initialized with the essential information. If a failure
+ * occurs the resource group remains in the pseudo-locksetup mode with the
+ * &struct pseudo_lock_region associated with it, but cleared from all
+ * information and ready for the user to re-attempt pseudo-locking by
+ * writing the schemata again.
+ *
+ * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0
+ * on failure. Descriptive error will be written to last_cmd_status buffer.
+ */
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct task_struct *thread;
+	unsigned int new_minor;
+	struct device *dev;
+	int ret;
+
+	ret = pseudo_lock_region_alloc(plr);
+	if (ret < 0)
+		return ret;
+
+	ret = pseudo_lock_cstates_constrain(plr);
+	if (ret < 0) {
+		ret = -EINVAL;
+		goto out_region;
+	}
+
+	plr->thread_done = 0;
+
+	thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp,
+					cpu_to_node(plr->cpu),
+					"pseudo_lock/%u", plr->cpu);
+	if (IS_ERR(thread)) {
+		ret = PTR_ERR(thread);
+		rdt_last_cmd_printf("locking thread returned error %d\n", ret);
+		goto out_cstates;
+	}
+
+	kthread_bind(thread, plr->cpu);
+	wake_up_process(thread);
+
+	ret = wait_event_interruptible(plr->lock_thread_wq,
+				       plr->thread_done == 1);
+	if (ret < 0) {
+		/*
+		 * If the thread does not get on the CPU for whatever
+		 * reason and the process which sets up the region is
+		 * interrupted then this will leave the thread in runnable
+		 * state and once it gets on the CPU it will derefence
+		 * the cleared, but not freed, plr struct resulting in an
+		 * empty pseudo-locking loop.
+		 */
+		rdt_last_cmd_puts("locking thread interrupted\n");
+		goto out_cstates;
+	}
+
+	ret = pseudo_lock_minor_get(&new_minor);
+	if (ret < 0) {
+		rdt_last_cmd_puts("unable to obtain a new minor number\n");
+		goto out_cstates;
+	}
+
+	/*
+	 * Unlock access but do not release the reference. The
+	 * pseudo-locked region will still be here on return.
+	 *
+	 * The mutex has to be released temporarily to avoid a potential
+	 * deadlock with the mm->mmap_sem semaphore which is obtained in
+	 * the device_create() and debugfs_create_dir() callpath below
+	 * as well as before the mmap() callback is called.
+	 */
+	mutex_unlock(&rdtgroup_mutex);
+
+	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
+		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
+						      debugfs_resctrl);
+		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
+			debugfs_create_file("pseudo_lock_measure", 0200,
+					    plr->debugfs_dir, rdtgrp,
+					    &pseudo_measure_fops);
+	}
+
+	dev = device_create(pseudo_lock_class, NULL,
+			    MKDEV(pseudo_lock_major, new_minor),
+			    rdtgrp, "%s", rdtgrp->kn->name);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		rdt_last_cmd_printf("failed to create character device: %d\n",
+				    ret);
+		goto out_debugfs;
+	}
+
+	/* We released the mutex - check if group was removed while we did so */
+	if (rdtgrp->flags & RDT_DELETED) {
+		ret = -ENODEV;
+		goto out_device;
+	}
+
+	plr->minor = new_minor;
+
+	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
+	closid_free(rdtgrp->closid);
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444);
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444);
+
+	ret = 0;
+	goto out;
+
+out_device:
+	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
+out_debugfs:
+	debugfs_remove_recursive(plr->debugfs_dir);
+	pseudo_lock_minor_release(new_minor);
+out_cstates:
+	pseudo_lock_cstates_relax(plr);
+out_region:
+	pseudo_lock_region_clear(plr);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region
+ * @rdtgrp: resource group to which the pseudo-locked region belongs
+ *
+ * The removal of a pseudo-locked region can be initiated when the resource
+ * group is removed from user space via a "rmdir" from userspace or the
+ * unmount of the resctrl filesystem. On removal the resource group does
+ * not go back to pseudo-locksetup mode before it is removed, instead it is
+ * removed directly. There is thus assymmetry with the creation where the
+ * &struct pseudo_lock_region is removed here while it was not created in
+ * rdtgroup_pseudo_lock_create().
+ *
+ * Return: void
+ */
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		/*
+		 * Default group cannot be a pseudo-locked region so we can
+		 * free closid here.
+		 */
+		closid_free(rdtgrp->closid);
+		goto free;
+	}
+
+	pseudo_lock_cstates_relax(plr);
+	debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
+	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
+	pseudo_lock_minor_release(plr->minor);
+
+free:
+	pseudo_lock_free(rdtgrp);
+}
+
+static int pseudo_lock_dev_open(struct inode *inode, struct file *filp)
+{
+	struct rdtgroup *rdtgrp;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgrp = region_find_by_minor(iminor(inode));
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
+	filp->private_data = rdtgrp;
+	atomic_inc(&rdtgrp->waitcount);
+	/* Perform a non-seekable open - llseek is not supported */
+	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
+{
+	struct rdtgroup *rdtgrp;
+
+	mutex_lock(&rdtgroup_mutex);
+	rdtgrp = filp->private_data;
+	WARN_ON(!rdtgrp);
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+	filp->private_data = NULL;
+	atomic_dec(&rdtgrp->waitcount);
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
+static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
+{
+	/* Not supported */
+	return -EINVAL;
+}
+
+static const struct vm_operations_struct pseudo_mmap_ops = {
+	.mremap = pseudo_lock_dev_mremap,
+};
+
+static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	unsigned long vsize = vma->vm_end - vma->vm_start;
+	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
+	struct pseudo_lock_region *plr;
+	struct rdtgroup *rdtgrp;
+	unsigned long physical;
+	unsigned long psize;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgrp = filp->private_data;
+	WARN_ON(!rdtgrp);
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
+	plr = rdtgrp->plr;
+
+	/*
+	 * Task is required to run with affinity to the cpus associated
+	 * with the pseudo-locked region. If this is not the case the task
+	 * may be scheduled elsewhere and invalidate entries in the
+	 * pseudo-locked region.
+	 */
+	if (!cpumask_subset(&current->cpus_allowed, &plr->d->cpu_mask)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EINVAL;
+	}
+
+	physical = __pa(plr->kmem) >> PAGE_SHIFT;
+	psize = plr->size - off;
+
+	if (off > plr->size) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENOSPC;
+	}
+
+	/*
+	 * Ensure changes are carried directly to the memory being mapped,
+	 * do not allow copy-on-write mapping.
+	 */
+	if (!(vma->vm_flags & VM_SHARED)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EINVAL;
+	}
+
+	if (vsize > psize) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENOSPC;
+	}
+
+	memset(plr->kmem + off, 0, vsize);
+
+	if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
+			    vsize, vma->vm_page_prot)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EAGAIN;
+	}
+	vma->vm_ops = &pseudo_mmap_ops;
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
+static const struct file_operations pseudo_lock_dev_fops = {
+	.owner =	THIS_MODULE,
+	.llseek =	no_llseek,
+	.read =		NULL,
+	.write =	NULL,
+	.open =		pseudo_lock_dev_open,
+	.release =	pseudo_lock_dev_release,
+	.mmap =		pseudo_lock_dev_mmap,
+};
+
+static char *pseudo_lock_devnode(struct device *dev, umode_t *mode)
+{
+	struct rdtgroup *rdtgrp;
+
+	rdtgrp = dev_get_drvdata(dev);
+	if (mode)
+		*mode = 0600;
+	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
+}
+
+int rdt_pseudo_lock_init(void)
+{
+	int ret;
+
+	ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops);
+	if (ret < 0)
+		return ret;
+
+	pseudo_lock_major = ret;
+
+	pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock");
+	if (IS_ERR(pseudo_lock_class)) {
+		ret = PTR_ERR(pseudo_lock_class);
+		unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+		return ret;
+	}
+
+	pseudo_lock_class->devnode = pseudo_lock_devnode;
+	return 0;
+}
+
+void rdt_pseudo_lock_release(void)
+{
+	class_destroy(pseudo_lock_class);
+	pseudo_lock_class = NULL;
+	unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+	pseudo_lock_major = 0;
+}
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
new file mode 100644
index 000000000000..2c041e6d9f05
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM resctrl
+
+#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PSEUDO_LOCK_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(pseudo_lock_mem_latency,
+	    TP_PROTO(u32 latency),
+	    TP_ARGS(latency),
+	    TP_STRUCT__entry(__field(u32, latency)),
+	    TP_fast_assign(__entry->latency = latency),
+	    TP_printk("latency=%u", __entry->latency)
+	   );
+
+TRACE_EVENT(pseudo_lock_l2,
+	    TP_PROTO(u64 l2_hits, u64 l2_miss),
+	    TP_ARGS(l2_hits, l2_miss),
+	    TP_STRUCT__entry(__field(u64, l2_hits)
+			     __field(u64, l2_miss)),
+	    TP_fast_assign(__entry->l2_hits = l2_hits;
+			   __entry->l2_miss = l2_miss;),
+	    TP_printk("hits=%llu miss=%llu",
+		      __entry->l2_hits, __entry->l2_miss));
+
+TRACE_EVENT(pseudo_lock_l3,
+	    TP_PROTO(u64 l3_hits, u64 l3_miss),
+	    TP_ARGS(l3_hits, l3_miss),
+	    TP_STRUCT__entry(__field(u64, l3_hits)
+			     __field(u64, l3_miss)),
+	    TP_fast_assign(__entry->l3_hits = l3_hits;
+			   __entry->l3_miss = l3_miss;),
+	    TP_printk("hits=%llu miss=%llu",
+		      __entry->l3_hits, __entry->l3_miss));
+
+#endif /* _TRACE_PSEUDO_LOCK_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event
+#include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 749856a2e736..d6d7ea7349d0 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -20,7 +20,9 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/cacheinfo.h>
 #include <linux/cpu.h>
+#include <linux/debugfs.h>
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
@@ -55,6 +57,8 @@ static struct kernfs_node *kn_mondata;
 static struct seq_buf last_cmd_status;
 static char last_cmd_status_buf[512];
 
+struct dentry *debugfs_resctrl;
+
 void rdt_last_cmd_clear(void)
 {
 	lockdep_assert_held(&rdtgroup_mutex);
@@ -121,11 +125,65 @@ static int closid_alloc(void)
 	return closid;
 }
 
-static void closid_free(int closid)
+void closid_free(int closid)
 {
 	closid_free_map |= 1 << closid;
 }
 
+/**
+ * closid_allocated - test if provided closid is in use
+ * @closid: closid to be tested
+ *
+ * Return: true if @closid is currently associated with a resource group,
+ * false if @closid is free
+ */
+static bool closid_allocated(unsigned int closid)
+{
+	return (closid_free_map & (1 << closid)) == 0;
+}
+
+/**
+ * rdtgroup_mode_by_closid - Return mode of resource group with closid
+ * @closid: closid if the resource group
+ *
+ * Each resource group is associated with a @closid. Here the mode
+ * of a resource group can be queried by searching for it using its closid.
+ *
+ * Return: mode as &enum rdtgrp_mode of resource group with closid @closid
+ */
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
+{
+	struct rdtgroup *rdtgrp;
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (rdtgrp->closid == closid)
+			return rdtgrp->mode;
+	}
+
+	return RDT_NUM_MODES;
+}
+
+static const char * const rdt_mode_str[] = {
+	[RDT_MODE_SHAREABLE]		= "shareable",
+	[RDT_MODE_EXCLUSIVE]		= "exclusive",
+	[RDT_MODE_PSEUDO_LOCKSETUP]	= "pseudo-locksetup",
+	[RDT_MODE_PSEUDO_LOCKED]	= "pseudo-locked",
+};
+
+/**
+ * rdtgroup_mode_str - Return the string representation of mode
+ * @mode: the resource group mode as &enum rdtgroup_mode
+ *
+ * Return: string representation of valid mode, "unknown" otherwise
+ */
+static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
+{
+	if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
+		return "unknown";
+
+	return rdt_mode_str[mode];
+}
+
 /* set uid and gid of rdtgroup dirs and files to that of the creator */
 static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
 {
@@ -207,8 +265,12 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 
 	if (rdtgrp) {
-		seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
-			   cpumask_pr_args(&rdtgrp->cpu_mask));
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+				   cpumask_pr_args(&rdtgrp->plr->d->cpu_mask));
+		else
+			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+				   cpumask_pr_args(&rdtgrp->cpu_mask));
 	} else {
 		ret = -ENOENT;
 	}
@@ -394,6 +456,13 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		goto unlock;
 	}
 
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		goto unlock;
+	}
+
 	if (is_cpu_list(of))
 		ret = cpulist_parse(buf, newmask);
 	else
@@ -509,6 +578,32 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	return ret;
 }
 
+/**
+ * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
+ * @r: Resource group
+ *
+ * Return: 1 if tasks have been assigned to @r, 0 otherwise
+ */
+int rdtgroup_tasks_assigned(struct rdtgroup *r)
+{
+	struct task_struct *p, *t;
+	int ret = 0;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	rcu_read_lock();
+	for_each_process_thread(p, t) {
+		if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
+		    (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) {
+			ret = 1;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static int rdtgroup_task_write_permission(struct task_struct *task,
 					  struct kernfs_open_file *of)
 {
@@ -570,13 +665,22 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
 	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
 		return -EINVAL;
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
 	rdt_last_cmd_clear();
 
-	if (rdtgrp)
-		ret = rdtgroup_move_task(pid, rdtgrp, of);
-	else
-		ret = -ENOENT;
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		goto unlock;
+	}
 
+	ret = rdtgroup_move_task(pid, rdtgrp, of);
+
+unlock:
 	rdtgroup_kn_unlock(of->kn);
 
 	return ret ?: nbytes;
@@ -662,6 +766,94 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+/**
+ * rdt_bit_usage_show - Display current usage of resources
+ *
+ * A domain is a shared resource that can now be allocated differently. Here
+ * we display the current regions of the domain as an annotated bitmask.
+ * For each domain of this resource its allocation bitmask
+ * is annotated as below to indicate the current usage of the corresponding bit:
+ *   0 - currently unused
+ *   X - currently available for sharing and used by software and hardware
+ *   H - currently used by hardware only but available for software use
+ *   S - currently used and shareable by software only
+ *   E - currently used exclusively by one resource group
+ *   P - currently pseudo-locked by one resource group
+ */
+static int rdt_bit_usage_show(struct kernfs_open_file *of,
+			      struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+	u32 sw_shareable = 0, hw_shareable = 0;
+	u32 exclusive = 0, pseudo_locked = 0;
+	struct rdt_domain *dom;
+	int i, hwb, swb, excl, psl;
+	enum rdtgrp_mode mode;
+	bool sep = false;
+	u32 *ctrl;
+
+	mutex_lock(&rdtgroup_mutex);
+	hw_shareable = r->cache.shareable_bits;
+	list_for_each_entry(dom, &r->domains, list) {
+		if (sep)
+			seq_putc(seq, ';');
+		ctrl = dom->ctrl_val;
+		sw_shareable = 0;
+		exclusive = 0;
+		seq_printf(seq, "%d=", dom->id);
+		for (i = 0; i < r->num_closid; i++, ctrl++) {
+			if (!closid_allocated(i))
+				continue;
+			mode = rdtgroup_mode_by_closid(i);
+			switch (mode) {
+			case RDT_MODE_SHAREABLE:
+				sw_shareable |= *ctrl;
+				break;
+			case RDT_MODE_EXCLUSIVE:
+				exclusive |= *ctrl;
+				break;
+			case RDT_MODE_PSEUDO_LOCKSETUP:
+			/*
+			 * RDT_MODE_PSEUDO_LOCKSETUP is possible
+			 * here but not included since the CBM
+			 * associated with this CLOSID in this mode
+			 * is not initialized and no task or cpu can be
+			 * assigned this CLOSID.
+			 */
+				break;
+			case RDT_MODE_PSEUDO_LOCKED:
+			case RDT_NUM_MODES:
+				WARN(1,
+				     "invalid mode for closid %d\n", i);
+				break;
+			}
+		}
+		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
+			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
+			hwb = test_bit(i, (unsigned long *)&hw_shareable);
+			swb = test_bit(i, (unsigned long *)&sw_shareable);
+			excl = test_bit(i, (unsigned long *)&exclusive);
+			psl = test_bit(i, (unsigned long *)&pseudo_locked);
+			if (hwb && swb)
+				seq_putc(seq, 'X');
+			else if (hwb && !swb)
+				seq_putc(seq, 'H');
+			else if (!hwb && swb)
+				seq_putc(seq, 'S');
+			else if (excl)
+				seq_putc(seq, 'E');
+			else if (psl)
+				seq_putc(seq, 'P');
+			else /* Unused bits remain */
+				seq_putc(seq, '0');
+		}
+		sep = true;
+	}
+	seq_putc(seq, '\n');
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
 static int rdt_min_bw_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
@@ -740,6 +932,269 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+/*
+ * rdtgroup_mode_show - Display mode of this resource group
+ */
+static int rdtgroup_mode_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));
+
+	rdtgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+/**
+ * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
+ * @r: Resource to which domain instance @d belongs.
+ * @d: The domain instance for which @closid is being tested.
+ * @cbm: Capacity bitmask being tested.
+ * @closid: Intended closid for @cbm.
+ * @exclusive: Only check if overlaps with exclusive resource groups
+ *
+ * Checks if provided @cbm intended to be used for @closid on domain
+ * @d overlaps with any other closids or other hardware usage associated
+ * with this domain. If @exclusive is true then only overlaps with
+ * resource groups in exclusive mode will be considered. If @exclusive
+ * is false then overlaps with any resource group or hardware entities
+ * will be considered.
+ *
+ * Return: false if CBM does not overlap, true if it does.
+ */
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+			   u32 _cbm, int closid, bool exclusive)
+{
+	unsigned long *cbm = (unsigned long *)&_cbm;
+	unsigned long *ctrl_b;
+	enum rdtgrp_mode mode;
+	u32 *ctrl;
+	int i;
+
+	/* Check for any overlap with regions used by hardware directly */
+	if (!exclusive) {
+		if (bitmap_intersects(cbm,
+				      (unsigned long *)&r->cache.shareable_bits,
+				      r->cache.cbm_len))
+			return true;
+	}
+
+	/* Check for overlap with other resource groups */
+	ctrl = d->ctrl_val;
+	for (i = 0; i < r->num_closid; i++, ctrl++) {
+		ctrl_b = (unsigned long *)ctrl;
+		mode = rdtgroup_mode_by_closid(i);
+		if (closid_allocated(i) && i != closid &&
+		    mode != RDT_MODE_PSEUDO_LOCKSETUP) {
+			if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) {
+				if (exclusive) {
+					if (mode == RDT_MODE_EXCLUSIVE)
+						return true;
+					continue;
+				}
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+/**
+ * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
+ *
+ * An exclusive resource group implies that there should be no sharing of
+ * its allocated resources. At the time this group is considered to be
+ * exclusive this test can determine if its current schemata supports this
+ * setting by testing for overlap with all other resource groups.
+ *
+ * Return: true if resource group can be exclusive, false if there is overlap
+ * with allocations of other resource groups and thus this resource group
+ * cannot be exclusive.
+ */
+static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
+{
+	int closid = rdtgrp->closid;
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		list_for_each_entry(d, &r->domains, list) {
+			if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
+						  rdtgrp->closid, false))
+				return false;
+		}
+	}
+
+	return true;
+}
+
+/**
+ * rdtgroup_mode_write - Modify the resource group's mode
+ *
+ */
+static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
+				   char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	enum rdtgrp_mode mode;
+	int ret = 0;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	rdt_last_cmd_clear();
+
+	mode = rdtgrp->mode;
+
+	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
+	    (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) ||
+	    (!strcmp(buf, "pseudo-locksetup") &&
+	     mode == RDT_MODE_PSEUDO_LOCKSETUP) ||
+	    (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED))
+		goto out;
+
+	if (mode == RDT_MODE_PSEUDO_LOCKED) {
+		rdt_last_cmd_printf("cannot change pseudo-locked group\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (!strcmp(buf, "shareable")) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			ret = rdtgroup_locksetup_exit(rdtgrp);
+			if (ret)
+				goto out;
+		}
+		rdtgrp->mode = RDT_MODE_SHAREABLE;
+	} else if (!strcmp(buf, "exclusive")) {
+		if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
+			rdt_last_cmd_printf("schemata overlaps\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			ret = rdtgroup_locksetup_exit(rdtgrp);
+			if (ret)
+				goto out;
+		}
+		rdtgrp->mode = RDT_MODE_EXCLUSIVE;
+	} else if (!strcmp(buf, "pseudo-locksetup")) {
+		ret = rdtgroup_locksetup_enter(rdtgrp);
+		if (ret)
+			goto out;
+		rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
+	} else {
+		rdt_last_cmd_printf("unknown/unsupported mode\n");
+		ret = -EINVAL;
+	}
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+	return ret ?: nbytes;
+}
+
+/**
+ * rdtgroup_cbm_to_size - Translate CBM to size in bytes
+ * @r: RDT resource to which @d belongs.
+ * @d: RDT domain instance.
+ * @cbm: bitmask for which the size should be computed.
+ *
+ * The bitmask provided associated with the RDT domain instance @d will be
+ * translated into how many bytes it represents. The size in bytes is
+ * computed by first dividing the total cache size by the CBM length to
+ * determine how many bytes each bit in the bitmask represents. The result
+ * is multiplied with the number of bits set in the bitmask.
+ */
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
+				  struct rdt_domain *d, u32 cbm)
+{
+	struct cpu_cacheinfo *ci;
+	unsigned int size = 0;
+	int num_b, i;
+
+	num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len);
+	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == r->cache_level) {
+			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
+			break;
+		}
+	}
+
+	return size;
+}
+
+/**
+ * rdtgroup_size_show - Display size in bytes of allocated regions
+ *
+ * The "size" file mirrors the layout of the "schemata" file, printing the
+ * size in bytes of each region instead of the capacity bitmask.
+ *
+ */
+static int rdtgroup_size_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+	unsigned int size;
+	bool sep = false;
+	u32 cbm;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+		seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name);
+		size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+					    rdtgrp->plr->d,
+					    rdtgrp->plr->cbm);
+		seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+		goto out;
+	}
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		seq_printf(s, "%*s:", max_name_width, r->name);
+		list_for_each_entry(d, &r->domains, list) {
+			if (sep)
+				seq_putc(s, ';');
+			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+				size = 0;
+			} else {
+				cbm = d->ctrl_val[rdtgrp->closid];
+				size = rdtgroup_cbm_to_size(r, d, cbm);
+			}
+			seq_printf(s, "%d=%u", d->id, size);
+			sep = true;
+		}
+		seq_putc(s, '\n');
+	}
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+
+	return 0;
+}
+
 /* rdtgroup information files for one cache resource. */
 static struct rftype res_common_files[] = {
 	{
@@ -792,6 +1247,13 @@ static struct rftype res_common_files[] = {
 		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
 	},
 	{
+		.name		= "bit_usage",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_bit_usage_show,
+		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
+	},
+	{
 		.name		= "min_bandwidth",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -853,6 +1315,22 @@ static struct rftype res_common_files[] = {
 		.seq_show	= rdtgroup_schemata_show,
 		.fflags		= RF_CTRL_BASE,
 	},
+	{
+		.name		= "mode",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_mode_write,
+		.seq_show	= rdtgroup_mode_show,
+		.fflags		= RF_CTRL_BASE,
+	},
+	{
+		.name		= "size",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdtgroup_size_show,
+		.fflags		= RF_CTRL_BASE,
+	},
+
 };
 
 static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
@@ -883,6 +1361,103 @@ error:
 	return ret;
 }
 
+/**
+ * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ *
+ * The permissions of named resctrl file, directory, or link are modified
+ * to not allow read, write, or execute by any user.
+ *
+ * WARNING: This function is intended to communicate to the user that the
+ * resctrl file has been locked down - that it is not relevant to the
+ * particular state the system finds itself in. It should not be relied
+ * on to protect from user access because after the file's permissions
+ * are restricted the user can still change the permissions using chmod
+ * from the command line.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
+{
+	struct iattr iattr = {.ia_valid = ATTR_MODE,};
+	struct kernfs_node *kn;
+	int ret = 0;
+
+	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+	if (!kn)
+		return -ENOENT;
+
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		iattr.ia_mode = S_IFDIR;
+		break;
+	case KERNFS_FILE:
+		iattr.ia_mode = S_IFREG;
+		break;
+	case KERNFS_LINK:
+		iattr.ia_mode = S_IFLNK;
+		break;
+	}
+
+	ret = kernfs_setattr(kn, &iattr);
+	kernfs_put(kn);
+	return ret;
+}
+
+/**
+ * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ * @mask: Mask of permissions that should be restored
+ *
+ * Restore the permissions of the named file. If @name is a directory the
+ * permissions of its parent will be used.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+			     umode_t mask)
+{
+	struct iattr iattr = {.ia_valid = ATTR_MODE,};
+	struct kernfs_node *kn, *parent;
+	struct rftype *rfts, *rft;
+	int ret, len;
+
+	rfts = res_common_files;
+	len = ARRAY_SIZE(res_common_files);
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		if (!strcmp(rft->name, name))
+			iattr.ia_mode = rft->mode & mask;
+	}
+
+	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+	if (!kn)
+		return -ENOENT;
+
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		parent = kernfs_get_parent(kn);
+		if (parent) {
+			iattr.ia_mode |= parent->mode;
+			kernfs_put(parent);
+		}
+		iattr.ia_mode |= S_IFDIR;
+		break;
+	case KERNFS_FILE:
+		iattr.ia_mode |= S_IFREG;
+		break;
+	case KERNFS_LINK:
+		iattr.ia_mode |= S_IFLNK;
+		break;
+	}
+
+	ret = kernfs_setattr(kn, &iattr);
+	kernfs_put(kn);
+	return ret;
+}
+
 static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
 				      unsigned long fflags)
 {
@@ -1224,6 +1799,9 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 
 	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
 	    (rdtgrp->flags & RDT_DELETED)) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
 		kernfs_unbreak_active_protection(kn);
 		kernfs_put(rdtgrp->kn);
 		kfree(rdtgrp);
@@ -1289,10 +1867,16 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 		rdtgroup_default.mon.mon_data_kn = kn_mondata;
 	}
 
+	ret = rdt_pseudo_lock_init();
+	if (ret) {
+		dentry = ERR_PTR(ret);
+		goto out_mondata;
+	}
+
 	dentry = kernfs_mount(fs_type, flags, rdt_root,
 			      RDTGROUP_SUPER_MAGIC, NULL);
 	if (IS_ERR(dentry))
-		goto out_mondata;
+		goto out_psl;
 
 	if (rdt_alloc_capable)
 		static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
@@ -1310,6 +1894,8 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 
 	goto out;
 
+out_psl:
+	rdt_pseudo_lock_release();
 out_mondata:
 	if (rdt_mon_capable)
 		kernfs_remove(kn_mondata);
@@ -1447,6 +2033,10 @@ static void rmdir_all_sub(void)
 		if (rdtgrp == &rdtgroup_default)
 			continue;
 
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
+
 		/*
 		 * Give any CPUs back to the default group. We cannot copy
 		 * cpu_online_mask because a CPU might have executed the
@@ -1483,6 +2073,8 @@ static void rdt_kill_sb(struct super_block *sb)
 		reset_all_ctrls(r);
 	cdp_disable_all();
 	rmdir_all_sub();
+	rdt_pseudo_lock_release();
+	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
 	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
 	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
 	static_branch_disable_cpuslocked(&rdt_enable_key);
@@ -1682,6 +2274,114 @@ out_destroy:
 	return ret;
 }
 
+/**
+ * cbm_ensure_valid - Enforce validity on provided CBM
+ * @_val:	Candidate CBM
+ * @r:		RDT resource to which the CBM belongs
+ *
+ * The provided CBM represents all cache portions available for use. This
+ * may be represented by a bitmap that does not consist of contiguous ones
+ * and thus be an invalid CBM.
+ * Here the provided CBM is forced to be a valid CBM by only considering
+ * the first set of contiguous bits as valid and clearing all bits.
+ * The intention here is to provide a valid default CBM with which a new
+ * resource group is initialized. The user can follow this with a
+ * modification to the CBM if the default does not satisfy the
+ * requirements.
+ */
+static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
+{
+	/*
+	 * Convert the u32 _val to an unsigned long required by all the bit
+	 * operations within this function. No more than 32 bits of this
+	 * converted value can be accessed because all bit operations are
+	 * additionally provided with cbm_len that is initialized during
+	 * hardware enumeration using five bits from the EAX register and
+	 * thus never can exceed 32 bits.
+	 */
+	unsigned long *val = (unsigned long *)_val;
+	unsigned int cbm_len = r->cache.cbm_len;
+	unsigned long first_bit, zero_bit;
+
+	if (*val == 0)
+		return;
+
+	first_bit = find_first_bit(val, cbm_len);
+	zero_bit = find_next_zero_bit(val, cbm_len, first_bit);
+
+	/* Clear any remaining bits to ensure contiguous region */
+	bitmap_clear(val, zero_bit, cbm_len - zero_bit);
+}
+
+/**
+ * rdtgroup_init_alloc - Initialize the new RDT group's allocations
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations. That is, all shareable and unused bits.
+ *
+ * All-zero CBM is invalid. If there are no more shareable bits available
+ * on any domain then the entire allocation will fail.
+ */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+	u32 used_b = 0, unused_b = 0;
+	u32 closid = rdtgrp->closid;
+	struct rdt_resource *r;
+	enum rdtgrp_mode mode;
+	struct rdt_domain *d;
+	int i, ret;
+	u32 *ctrl;
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		list_for_each_entry(d, &r->domains, list) {
+			d->have_new_ctrl = false;
+			d->new_ctrl = r->cache.shareable_bits;
+			used_b = r->cache.shareable_bits;
+			ctrl = d->ctrl_val;
+			for (i = 0; i < r->num_closid; i++, ctrl++) {
+				if (closid_allocated(i) && i != closid) {
+					mode = rdtgroup_mode_by_closid(i);
+					if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+						break;
+					used_b |= *ctrl;
+					if (mode == RDT_MODE_SHAREABLE)
+						d->new_ctrl |= *ctrl;
+				}
+			}
+			if (d->plr && d->plr->cbm > 0)
+				used_b |= d->plr->cbm;
+			unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+			unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+			d->new_ctrl |= unused_b;
+			/*
+			 * Force the initial CBM to be valid, user can
+			 * modify the CBM based on system availability.
+			 */
+			cbm_ensure_valid(&d->new_ctrl, r);
+			if (bitmap_weight((unsigned long *) &d->new_ctrl,
+					  r->cache.cbm_len) <
+					r->cache.min_cbm_bits) {
+				rdt_last_cmd_printf("no space on %s:%d\n",
+						    r->name, d->id);
+				return -ENOSPC;
+			}
+			d->have_new_ctrl = true;
+		}
+	}
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		ret = update_domains(r, rdtgrp->closid);
+		if (ret < 0) {
+			rdt_last_cmd_puts("failed to initialize allocations\n");
+			return ret;
+		}
+		rdtgrp->mode = RDT_MODE_SHAREABLE;
+	}
+
+	return 0;
+}
+
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 			     struct kernfs_node *prgrp_kn,
 			     const char *name, umode_t mode,
@@ -1700,6 +2400,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 		goto out_unlock;
 	}
 
+	if (rtype == RDTMON_GROUP &&
+	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		goto out_unlock;
+	}
+
 	/* allocate the rdtgroup. */
 	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
 	if (!rdtgrp) {
@@ -1840,6 +2548,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 	ret = 0;
 
 	rdtgrp->closid = closid;
+	ret = rdtgroup_init_alloc(rdtgrp);
+	if (ret < 0)
+		goto out_id_free;
+
 	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
 
 	if (rdt_mon_capable) {
@@ -1850,15 +2562,16 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 		ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL);
 		if (ret) {
 			rdt_last_cmd_puts("kernfs subdir error\n");
-			goto out_id_free;
+			goto out_del_list;
 		}
 	}
 
 	goto out_unlock;
 
+out_del_list:
+	list_del(&rdtgrp->rdtgroup_list);
 out_id_free:
 	closid_free(closid);
-	list_del(&rdtgrp->rdtgroup_list);
 out_common_fail:
 	mkdir_rdt_prepare_clean(rdtgrp);
 out_unlock:
@@ -1945,6 +2658,21 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	return 0;
 }
 
+static int rdtgroup_ctrl_remove(struct kernfs_node *kn,
+				struct rdtgroup *rdtgrp)
+{
+	rdtgrp->flags = RDT_DELETED;
+	list_del(&rdtgrp->rdtgroup_list);
+
+	/*
+	 * one extra hold on this, will drop when we kfree(rdtgrp)
+	 * in rdtgroup_kn_unlock()
+	 */
+	kernfs_get(kn);
+	kernfs_remove(rdtgrp->kn);
+	return 0;
+}
+
 static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 			       cpumask_var_t tmpmask)
 {
@@ -1970,7 +2698,6 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
 	update_closid_rmid(tmpmask, NULL);
 
-	rdtgrp->flags = RDT_DELETED;
 	closid_free(rdtgrp->closid);
 	free_rmid(rdtgrp->mon.rmid);
 
@@ -1979,14 +2706,7 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	 */
 	free_all_child_rdtgrp(rdtgrp);
 
-	list_del(&rdtgrp->rdtgroup_list);
-
-	/*
-	 * one extra hold on this, will drop when we kfree(rdtgrp)
-	 * in rdtgroup_kn_unlock()
-	 */
-	kernfs_get(kn);
-	kernfs_remove(rdtgrp->kn);
+	rdtgroup_ctrl_remove(kn, rdtgrp);
 
 	return 0;
 }
@@ -2014,13 +2734,19 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	 * If the rdtgroup is a mon group and parent directory
 	 * is a valid "mon_groups" directory, remove the mon group.
 	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn)
-		ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
-	else if (rdtgrp->type == RDTMON_GROUP &&
-		 is_mon_groups(parent_kn, kn->name))
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			ret = rdtgroup_ctrl_remove(kn, rdtgrp);
+		} else {
+			ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
+		}
+	} else if (rdtgrp->type == RDTMON_GROUP &&
+		 is_mon_groups(parent_kn, kn->name)) {
 		ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask);
-	else
+	} else {
 		ret = -EPERM;
+	}
 
 out:
 	rdtgroup_kn_unlock(kn);
@@ -2046,7 +2772,8 @@ static int __init rdtgroup_setup_root(void)
 	int ret;
 
 	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
-				      KERNFS_ROOT_CREATE_DEACTIVATED,
+				      KERNFS_ROOT_CREATE_DEACTIVATED |
+				      KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
 				      &rdtgroup_default);
 	if (IS_ERR(rdt_root))
 		return PTR_ERR(rdt_root);
@@ -2102,6 +2829,29 @@ int __init rdtgroup_init(void)
 	if (ret)
 		goto cleanup_mountpoint;
 
+	/*
+	 * Adding the resctrl debugfs directory here may not be ideal since
+	 * it would let the resctrl debugfs directory appear on the debugfs
+	 * filesystem before the resctrl filesystem is mounted.
+	 * It may also be ok since that would enable debugging of RDT before
+	 * resctrl is mounted.
+	 * The reason why the debugfs directory is created here and not in
+	 * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and
+	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
+	 * (the lockdep class of inode->i_rwsem). Other filesystem
+	 * interactions (eg. SyS_getdents) have the lock ordering:
+	 * &sb->s_type->i_mutex_key --> &mm->mmap_sem
+	 * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex
+	 * is taken, thus creating dependency:
+	 * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause
+	 * issues considering the other two lock dependencies.
+	 * By creating the debugfs directory here we avoid a dependency
+	 * that may cause deadlock (even though file operations cannot
+	 * occur until the filesystem is mounted, but I do not know how to
+	 * tell lockdep that).
+	 */
+	debugfs_resctrl = debugfs_create_dir("resctrl", NULL);
+
 	return 0;
 
 cleanup_mountpoint:
@@ -2111,3 +2861,11 @@ cleanup_root:
 
 	return ret;
 }
+
+void __exit rdtgroup_exit(void)
+{
+	debugfs_remove_recursive(debugfs_resctrl);
+	unregister_filesystem(&rdt_fs_type);
+	sysfs_remove_mount_point(fs_kobj, "resctrl");
+	kernfs_destroy_root(rdt_root);
+}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8c50754c09c1..4b767284b7f5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -123,8 +123,8 @@ void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
-	/* We hope get_seconds stays lockless */
-	m->time = get_seconds();
+	/* need the internal __ version to avoid deadlocks */
+	m->time = __ktime_get_real_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
 	m->cpuid = cpuid_eax(1);
 	m->socketid = cpu_data(m->extcpu).phys_proc_id;
@@ -1104,6 +1104,101 @@ static void mce_unmap_kpfn(unsigned long pfn)
 }
 #endif
 
+
+/*
+ * Cases where we avoid rendezvous handler timeout:
+ * 1) If this CPU is offline.
+ *
+ * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+ *  skip those CPUs which remain looping in the 1st kernel - see
+ *  crash_nmi_callback().
+ *
+ * Note: there still is a small window between kexec-ing and the new,
+ * kdump kernel establishing a new #MC handler where a broadcasted MCE
+ * might not get handled properly.
+ */
+static bool __mc_check_crashing_cpu(int cpu)
+{
+	if (cpu_is_offline(cpu) ||
+	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
+		u64 mcgstatus;
+
+		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+		if (mcgstatus & MCG_STATUS_RIPV) {
+			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+			return true;
+		}
+	}
+	return false;
+}
+
+static void __mc_scan_banks(struct mce *m, struct mce *final,
+			    unsigned long *toclear, unsigned long *valid_banks,
+			    int no_way_out, int *worst)
+{
+	struct mca_config *cfg = &mca_cfg;
+	int severity, i;
+
+	for (i = 0; i < cfg->banks; i++) {
+		__clear_bit(i, toclear);
+		if (!test_bit(i, valid_banks))
+			continue;
+
+		if (!mce_banks[i].ctl)
+			continue;
+
+		m->misc = 0;
+		m->addr = 0;
+		m->bank = i;
+
+		m->status = mce_rdmsrl(msr_ops.status(i));
+		if (!(m->status & MCI_STATUS_VAL))
+			continue;
+
+		/*
+		 * Corrected or non-signaled errors are handled by
+		 * machine_check_poll(). Leave them alone, unless this panics.
+		 */
+		if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
+			!no_way_out)
+			continue;
+
+		/* Set taint even when machine check was not enabled. */
+		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
+		severity = mce_severity(m, cfg->tolerant, NULL, true);
+
+		/*
+		 * When machine check was for corrected/deferred handler don't
+		 * touch, unless we're panicking.
+		 */
+		if ((severity == MCE_KEEP_SEVERITY ||
+		     severity == MCE_UCNA_SEVERITY) && !no_way_out)
+			continue;
+
+		__set_bit(i, toclear);
+
+		/* Machine check event was not enabled. Clear, but ignore. */
+		if (severity == MCE_NO_SEVERITY)
+			continue;
+
+		mce_read_aux(m, i);
+
+		/* assuming valid severity level != 0 */
+		m->severity = severity;
+
+		mce_log(m);
+
+		if (severity > *worst) {
+			*final = *m;
+			*worst = severity;
+		}
+	}
+
+	/* mce_clear_state will clear *final, save locally for use later */
+	*m = *final;
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1118,68 +1213,45 @@ static void mce_unmap_kpfn(unsigned long pfn)
  */
 void do_machine_check(struct pt_regs *regs, long error_code)
 {
+	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
+	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	struct mca_config *cfg = &mca_cfg;
+	int cpu = smp_processor_id();
+	char *msg = "Unknown";
 	struct mce m, *final;
-	int i;
 	int worst = 0;
-	int severity;
 
 	/*
 	 * Establish sequential order between the CPUs entering the machine
 	 * check handler.
 	 */
 	int order = -1;
+
 	/*
 	 * If no_way_out gets set, there is no safe way to recover from this
 	 * MCE.  If mca_cfg.tolerant is cranked up, we'll try anyway.
 	 */
 	int no_way_out = 0;
+
 	/*
 	 * If kill_it gets set, there might be a way to recover from this
 	 * error.
 	 */
 	int kill_it = 0;
-	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
-	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
-	char *msg = "Unknown";
 
 	/*
 	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
 	 * on Intel.
 	 */
 	int lmce = 1;
-	int cpu = smp_processor_id();
 
-	/*
-	 * Cases where we avoid rendezvous handler timeout:
-	 * 1) If this CPU is offline.
-	 *
-	 * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
-	 *  skip those CPUs which remain looping in the 1st kernel - see
-	 *  crash_nmi_callback().
-	 *
-	 * Note: there still is a small window between kexec-ing and the new,
-	 * kdump kernel establishing a new #MC handler where a broadcasted MCE
-	 * might not get handled properly.
-	 */
-	if (cpu_is_offline(cpu) ||
-	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
-		u64 mcgstatus;
-
-		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
-		if (mcgstatus & MCG_STATUS_RIPV) {
-			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
-			return;
-		}
-	}
+	if (__mc_check_crashing_cpu(cpu))
+		return;
 
 	ist_enter(regs);
 
 	this_cpu_inc(mce_exception_count);
 
-	if (!cfg->banks)
-		goto out;
-
 	mce_gather_info(&m, regs);
 	m.tsc = rdtsc();
 
@@ -1220,67 +1292,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		order = mce_start(&no_way_out);
 	}
 
-	for (i = 0; i < cfg->banks; i++) {
-		__clear_bit(i, toclear);
-		if (!test_bit(i, valid_banks))
-			continue;
-		if (!mce_banks[i].ctl)
-			continue;
-
-		m.misc = 0;
-		m.addr = 0;
-		m.bank = i;
-
-		m.status = mce_rdmsrl(msr_ops.status(i));
-		if ((m.status & MCI_STATUS_VAL) == 0)
-			continue;
-
-		/*
-		 * Non uncorrected or non signaled errors are handled by
-		 * machine_check_poll. Leave them alone, unless this panics.
-		 */
-		if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
-			!no_way_out)
-			continue;
-
-		/*
-		 * Set taint even when machine check was not enabled.
-		 */
-		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
-
-		severity = mce_severity(&m, cfg->tolerant, NULL, true);
-
-		/*
-		 * When machine check was for corrected/deferred handler don't
-		 * touch, unless we're panicing.
-		 */
-		if ((severity == MCE_KEEP_SEVERITY ||
-		     severity == MCE_UCNA_SEVERITY) && !no_way_out)
-			continue;
-		__set_bit(i, toclear);
-		if (severity == MCE_NO_SEVERITY) {
-			/*
-			 * Machine check event was not enabled. Clear, but
-			 * ignore.
-			 */
-			continue;
-		}
-
-		mce_read_aux(&m, i);
-
-		/* assuming valid severity level != 0 */
-		m.severity = severity;
-
-		mce_log(&m);
-
-		if (severity > worst) {
-			*final = m;
-			worst = severity;
-		}
-	}
-
-	/* mce_clear_state will clear *final, save locally for use later */
-	m = *final;
+	__mc_scan_banks(&m, final, toclear, valid_banks, no_way_out, &worst);
 
 	if (!no_way_out)
 		mce_clear_state(toclear);
@@ -1319,7 +1331,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	if (worst > 0)
 		mce_report_event(regs);
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
-out:
+
 	sync_core();
 
 	if (worst != MCE_AR_SEVERITY && !kill_it)
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 08286269fd24..b9bc8a1a584e 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -509,12 +509,20 @@ static struct platform_device	*microcode_pdev;
 
 static int check_online_cpus(void)
 {
-	if (num_online_cpus() == num_present_cpus())
-		return 0;
+	unsigned int cpu;
 
-	pr_err("Not all CPUs online, aborting microcode update.\n");
+	/*
+	 * Make sure all CPUs are online.  It's fine for SMT to be disabled if
+	 * all the primary threads are still online.
+	 */
+	for_each_present_cpu(cpu) {
+		if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) {
+			pr_err("Not all CPUs online, aborting microcode update.\n");
+			return -EINVAL;
+		}
+	}
 
-	return -EINVAL;
+	return 0;
 }
 
 static atomic_t late_cpus_in;
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 81c0afb39d0a..71ca064e3794 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -22,18 +22,10 @@
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 #define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
 
-/*
- * Check for extended topology enumeration cpuid leaf 0xb and if it
- * exists, use it for populating initial_apicid and cpu topology
- * detection.
- */
-int detect_extended_topology(struct cpuinfo_x86 *c)
+int detect_extended_topology_early(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
-	unsigned int eax, ebx, ecx, edx, sub_index;
-	unsigned int ht_mask_width, core_plus_mask_width;
-	unsigned int core_select_mask, core_level_siblings;
-	static bool printed;
+	unsigned int eax, ebx, ecx, edx;
 
 	if (c->cpuid_level < 0xb)
 		return -1;
@@ -52,10 +44,30 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	 * initial apic id, which also represents 32-bit extended x2apic id.
 	 */
 	c->initial_apicid = edx;
+	smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+#endif
+	return 0;
+}
+
+/*
+ * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * exists, use it for populating initial_apicid and cpu topology
+ * detection.
+ */
+int detect_extended_topology(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int eax, ebx, ecx, edx, sub_index;
+	unsigned int ht_mask_width, core_plus_mask_width;
+	unsigned int core_select_mask, core_level_siblings;
+
+	if (detect_extended_topology_early(c) < 0)
+		return -1;
 
 	/*
 	 * Populate HT related information from sub-leaf level 0.
 	 */
+	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
@@ -86,15 +98,6 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 
 	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
-
-	if (!printed) {
-		pr_info("CPU: Physical Processor ID: %d\n",
-		       c->phys_proc_id);
-		if (c->x86_max_cores > 1)
-			pr_info("CPU: Processor Core ID: %d\n",
-			       c->cpu_core_id);
-		printed = 1;
-	}
 #endif
 	return 0;
 }
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 666a284116ac..9c8652974f8e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -22,8 +22,6 @@
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
-#define OPCODE_BUFSIZE 64
-
 int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
 static int die_counter;
@@ -93,26 +91,18 @@ static void printk_stack_address(unsigned long address, int reliable,
  */
 void show_opcodes(u8 *rip, const char *loglvl)
 {
-	unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3;
+#define PROLOGUE_SIZE 42
+#define EPILOGUE_SIZE 21
+#define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
 	u8 opcodes[OPCODE_BUFSIZE];
-	u8 *ip;
-	int i;
-
-	printk("%sCode: ", loglvl);
-
-	ip = (u8 *)rip - code_prologue;
-	if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) {
-		pr_cont("Bad RIP value.\n");
-		return;
-	}
 
-	for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) {
-		if (ip == rip)
-			pr_cont("<%02x> ", opcodes[i]);
-		else
-			pr_cont("%02x ", opcodes[i]);
+	if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) {
+		printk("%sCode: Bad RIP value.\n", loglvl);
+	} else {
+		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
+		       __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes,
+		       opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1);
 	}
-	pr_cont("\n");
 }
 
 void show_ip(struct pt_regs *regs, const char *loglvl)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index f92a6593de1e..2ea85b32421a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -10,6 +10,7 @@
 #include <asm/fpu/signal.h>
 #include <asm/fpu/types.h>
 #include <asm/traps.h>
+#include <asm/irq_regs.h>
 
 #include <linux/hardirq.h>
 #include <linux/pkeys.h>
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index abe6df15a8fb..30f9cb2c0b55 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -512,11 +512,18 @@ ENTRY(initial_code)
 ENTRY(setup_once_ref)
 	.long setup_once
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#define	PGD_ALIGN	(2 * PAGE_SIZE)
+#define PTI_USER_PGD_FILL	1024
+#else
+#define	PGD_ALIGN	(PAGE_SIZE)
+#define PTI_USER_PGD_FILL	0
+#endif
 /*
  * BSS section
  */
 __PAGE_ALIGNED_BSS
-	.align PAGE_SIZE
+	.align PGD_ALIGN
 #ifdef CONFIG_X86_PAE
 .globl initial_pg_pmd
 initial_pg_pmd:
@@ -526,14 +533,17 @@ initial_pg_pmd:
 initial_page_table:
 	.fill 1024,4,0
 #endif
+	.align PGD_ALIGN
 initial_pg_fixmap:
 	.fill 1024,4,0
-.globl empty_zero_page
-empty_zero_page:
-	.fill 4096,1,0
 .globl swapper_pg_dir
+	.align PGD_ALIGN
 swapper_pg_dir:
 	.fill 1024,4,0
+	.fill PTI_USER_PGD_FILL,4,0
+.globl empty_zero_page
+empty_zero_page:
+	.fill 4096,1,0
 EXPORT_SYMBOL(empty_zero_page)
 
 /*
@@ -542,7 +552,7 @@ EXPORT_SYMBOL(empty_zero_page)
 #ifdef CONFIG_X86_PAE
 __PAGE_ALIGNED_DATA
 	/* Page-aligned for the benefit of paravirt? */
-	.align PAGE_SIZE
+	.align PGD_ALIGN
 ENTRY(initial_page_table)
 	.long	pa(initial_pg_pmd+PGD_IDENT_ATTR),0	/* low identity map */
 # if KPMDS == 3
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 8344dd2f310a..15ebc2fc166e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -235,7 +235,7 @@ ENTRY(secondary_startup_64)
 	 *		address given in m16:64.
 	 */
 	pushq	$.Lafter_lret	# put return address on stack for unwinder
-	xorq	%rbp, %rbp	# clear frame pointer
+	xorl	%ebp, %ebp	# clear frame pointer
 	movq	initial_code(%rip), %rax
 	pushq	$__KERNEL_CS	# set correct cs
 	pushq	%rax		# target address in negative space
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 346b24883911..b0acb22e5a46 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1,6 +1,7 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 8771766d46b6..34a5c1715148 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -169,28 +169,29 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 		set_dr_addr_mask(0, i);
 }
 
-/*
- * Check for virtual address in kernel space.
- */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+static int arch_bp_generic_len(int x86_len)
 {
-	unsigned int len;
-	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	va = info->address;
-	len = bp->attr.bp_len;
-
-	/*
-	 * We don't need to worry about va + len - 1 overflowing:
-	 * we already require that va is aligned to a multiple of len.
-	 */
-	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+	switch (x86_len) {
+	case X86_BREAKPOINT_LEN_1:
+		return HW_BREAKPOINT_LEN_1;
+	case X86_BREAKPOINT_LEN_2:
+		return HW_BREAKPOINT_LEN_2;
+	case X86_BREAKPOINT_LEN_4:
+		return HW_BREAKPOINT_LEN_4;
+#ifdef CONFIG_X86_64
+	case X86_BREAKPOINT_LEN_8:
+		return HW_BREAKPOINT_LEN_8;
+#endif
+	default:
+		return -EINVAL;
+	}
 }
 
 int arch_bp_generic_fields(int x86_len, int x86_type,
 			   int *gen_len, int *gen_type)
 {
+	int len;
+
 	/* Type */
 	switch (x86_type) {
 	case X86_BREAKPOINT_EXECUTE:
@@ -211,42 +212,47 @@ int arch_bp_generic_fields(int x86_len, int x86_type,
 	}
 
 	/* Len */
-	switch (x86_len) {
-	case X86_BREAKPOINT_LEN_1:
-		*gen_len = HW_BREAKPOINT_LEN_1;
-		break;
-	case X86_BREAKPOINT_LEN_2:
-		*gen_len = HW_BREAKPOINT_LEN_2;
-		break;
-	case X86_BREAKPOINT_LEN_4:
-		*gen_len = HW_BREAKPOINT_LEN_4;
-		break;
-#ifdef CONFIG_X86_64
-	case X86_BREAKPOINT_LEN_8:
-		*gen_len = HW_BREAKPOINT_LEN_8;
-		break;
-#endif
-	default:
+	len = arch_bp_generic_len(x86_len);
+	if (len < 0)
 		return -EINVAL;
-	}
+	*gen_len = len;
 
 	return 0;
 }
 
-
-static int arch_build_bp_info(struct perf_event *bp)
+/*
+ * Check for virtual address in kernel space.
+ */
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	unsigned long va;
+	int len;
 
-	info->address = bp->attr.bp_addr;
+	va = hw->address;
+	len = arch_bp_generic_len(hw->len);
+	WARN_ON_ONCE(len < 0);
+
+	/*
+	 * We don't need to worry about va + len - 1 overflowing:
+	 * we already require that va is aligned to a multiple of len.
+	 */
+	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+}
+
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
+{
+	hw->address = attr->bp_addr;
+	hw->mask = 0;
 
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_W:
-		info->type = X86_BREAKPOINT_WRITE;
+		hw->type = X86_BREAKPOINT_WRITE;
 		break;
 	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
-		info->type = X86_BREAKPOINT_RW;
+		hw->type = X86_BREAKPOINT_RW;
 		break;
 	case HW_BREAKPOINT_X:
 		/*
@@ -254,23 +260,23 @@ static int arch_build_bp_info(struct perf_event *bp)
 		 * acceptable for kprobes.  On non-kprobes kernels, we don't
 		 * allow kernel breakpoints at all.
 		 */
-		if (bp->attr.bp_addr >= TASK_SIZE_MAX) {
+		if (attr->bp_addr >= TASK_SIZE_MAX) {
 #ifdef CONFIG_KPROBES
-			if (within_kprobe_blacklist(bp->attr.bp_addr))
+			if (within_kprobe_blacklist(attr->bp_addr))
 				return -EINVAL;
 #else
 			return -EINVAL;
 #endif
 		}
 
-		info->type = X86_BREAKPOINT_EXECUTE;
+		hw->type = X86_BREAKPOINT_EXECUTE;
 		/*
 		 * x86 inst breakpoints need to have a specific undefined len.
 		 * But we still need to check userspace is not trying to setup
 		 * an unsupported length, to get a range breakpoint for example.
 		 */
-		if (bp->attr.bp_len == sizeof(long)) {
-			info->len = X86_BREAKPOINT_LEN_X;
+		if (attr->bp_len == sizeof(long)) {
+			hw->len = X86_BREAKPOINT_LEN_X;
 			return 0;
 		}
 	default:
@@ -278,28 +284,26 @@ static int arch_build_bp_info(struct perf_event *bp)
 	}
 
 	/* Len */
-	info->mask = 0;
-
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->len = X86_BREAKPOINT_LEN_1;
+		hw->len = X86_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->len = X86_BREAKPOINT_LEN_2;
+		hw->len = X86_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->len = X86_BREAKPOINT_LEN_4;
+		hw->len = X86_BREAKPOINT_LEN_4;
 		break;
 #ifdef CONFIG_X86_64
 	case HW_BREAKPOINT_LEN_8:
-		info->len = X86_BREAKPOINT_LEN_8;
+		hw->len = X86_BREAKPOINT_LEN_8;
 		break;
 #endif
 	default:
 		/* AMD range breakpoint */
-		if (!is_power_of_2(bp->attr.bp_len))
+		if (!is_power_of_2(attr->bp_len))
 			return -EINVAL;
-		if (bp->attr.bp_addr & (bp->attr.bp_len - 1))
+		if (attr->bp_addr & (attr->bp_len - 1))
 			return -EINVAL;
 
 		if (!boot_cpu_has(X86_FEATURE_BPEXT))
@@ -312,8 +316,8 @@ static int arch_build_bp_info(struct perf_event *bp)
 		 * breakpoints, then we'll have to check for kprobe-blacklisted
 		 * addresses anywhere in the range.
 		 */
-		info->mask = bp->attr.bp_len - 1;
-		info->len = X86_BREAKPOINT_LEN_1;
+		hw->mask = attr->bp_len - 1;
+		hw->len = X86_BREAKPOINT_LEN_1;
 	}
 
 	return 0;
@@ -322,22 +326,23 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
 	int ret;
 
 
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
-	switch (info->len) {
+	switch (hw->len) {
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
-		if (info->mask)
-			align = info->mask;
+		if (hw->mask)
+			align = hw->mask;
 		break;
 	case X86_BREAKPOINT_LEN_2:
 		align = 1;
@@ -358,7 +363,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
 	 */
-	if (info->address & align)
+	if (hw->address & align)
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 86c4439f9d74..519649ddf100 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/timex.h>
 #include <linux/random.h>
 #include <linux/init.h>
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 74383a3780dc..01adea278a71 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -8,6 +8,7 @@
 #include <asm/traps.h>
 #include <asm/proto.h>
 #include <asm/desc.h>
+#include <asm/hw_irq.h>
 
 struct idt_data {
 	unsigned int	vector;
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 328d027d829d..59b5f2ea7c2f 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -10,6 +10,7 @@
 #include <linux/ftrace.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/irq.h>
 
 #include <asm/apic.h>
 #include <asm/io_apic.h>
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index c1bdbd3d3232..95600a99ae93 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -11,6 +11,7 @@
 
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kernel_stat.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index d86e344f5b3d..0469cd078db1 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -11,6 +11,7 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/delay.h>
 #include <linux/ftrace.h>
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 772196c1b8c4..a0693b71cfc1 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/timex.h>
 #include <linux/random.h>
 #include <linux/kprobes.h>
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index e56c95be2808..eeea935e9bb5 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -37,15 +37,18 @@ static void bug_at(unsigned char *ip, int line)
 	BUG();
 }
 
-static void __jump_label_transform(struct jump_entry *entry,
-				   enum jump_label_type type,
-				   void *(*poker)(void *, const void *, size_t),
-				   int init)
+static void __ref __jump_label_transform(struct jump_entry *entry,
+					 enum jump_label_type type,
+					 void *(*poker)(void *, const void *, size_t),
+					 int init)
 {
 	union jump_code_union code;
 	const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
 	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
 
+	if (early_boot_irqs_disabled)
+		poker = text_poke_early;
+
 	if (type == JUMP_LABEL_JMP) {
 		if (init) {
 			/*
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index ae38dccf0c8f..2b949f4fd4d8 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -105,14 +105,4 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig
 }
 #endif
 
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			   struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				  struct kprobe_ctlblk *kcb)
-{
-	return 0;
-}
-#endif
 #endif
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6f4d42377fe5..b0d1e81c96bb 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -66,8 +66,6 @@
 
 #include "common.h"
 
-void jprobe_return_end(void);
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -395,8 +393,6 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 			  - (u8 *) real;
 		if ((s64) (s32) newdisp != newdisp) {
 			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
-			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n",
-				src, real, insn->displacement.value);
 			return 0;
 		}
 		disp = (u8 *) dest + insn_offset_displacement(insn);
@@ -596,7 +592,6 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 		 * stepping.
 		 */
 		regs->ip = (unsigned long)p->ainsn.insn;
-		preempt_enable_no_resched();
 		return;
 	}
 #endif
@@ -640,8 +635,7 @@ static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
 		 * Raise a BUG or we'll continue in an endless reentering loop
 		 * and eventually a stack overflow.
 		 */
-		printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
-		       p->addr);
+		pr_err("Unrecoverable kprobe detected.\n");
 		dump_kprobe(p);
 		BUG();
 	default:
@@ -669,12 +663,10 @@ int kprobe_int3_handler(struct pt_regs *regs)
 
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
 	/*
-	 * We don't want to be preempted for the entire
-	 * duration of kprobe processing. We conditionally
-	 * re-enable preemption at the end of this function,
-	 * and also in reenter_kprobe() and setup_singlestep().
+	 * We don't want to be preempted for the entire duration of kprobe
+	 * processing. Since int3 and debug trap disables irqs and we clear
+	 * IF while singlestepping, it must be no preemptible.
 	 */
-	preempt_disable();
 
 	kcb = get_kprobe_ctlblk();
 	p = get_kprobe(addr);
@@ -690,13 +682,14 @@ int kprobe_int3_handler(struct pt_regs *regs)
 			/*
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry
-			 * for jprobe processing, so get out doing nothing
-			 * more here.
+			 * pre-handler and it returned non-zero, that means
+			 * user handler setup registers to exit to another
+			 * instruction, we must skip the single stepping.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs))
 				setup_singlestep(p, regs, kcb, 0);
+			else
+				reset_current_kprobe();
 			return 1;
 		}
 	} else if (*addr != BREAKPOINT_INSTRUCTION) {
@@ -710,18 +703,9 @@ int kprobe_int3_handler(struct pt_regs *regs)
 		 * the original instruction.
 		 */
 		regs->ip = (unsigned long)addr;
-		preempt_enable_no_resched();
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			if (!skip_singlestep(p, regs, kcb))
-				setup_singlestep(p, regs, kcb, 0);
-			return 1;
-		}
 	} /* else: not a kprobe fault; let the kernel handle it */
 
-	preempt_enable_no_resched();
 	return 0;
 }
 NOKPROBE_SYMBOL(kprobe_int3_handler);
@@ -972,8 +956,6 @@ int kprobe_debug_handler(struct pt_regs *regs)
 	}
 	reset_current_kprobe();
 out:
-	preempt_enable_no_resched();
-
 	/*
 	 * if somebody else is singlestepping across a probe point, flags
 	 * will have TF set, in which case, continue the remaining processing
@@ -1020,7 +1002,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 			restore_previous_kprobe(kcb);
 		else
 			reset_current_kprobe();
-		preempt_enable_no_resched();
 	} else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
 		   kcb->kprobe_status == KPROBE_HIT_SSDONE) {
 		/*
@@ -1083,93 +1064,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
 }
 NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_sp = stack_addr(regs);
-	addr = (unsigned long)(kcb->jprobe_saved_sp);
-
-	/*
-	 * As Linus pointed out, gcc assumes that the callee
-	 * owns the argument space and could overwrite it, e.g.
-	 * tailcall optimization. So, to be absolutely safe
-	 * we also save and restore enough stack bytes to cover
-	 * the argument area.
-	 * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy
-	 * raw stack chunk with redzones:
-	 */
-	__memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
-	regs->ip = (unsigned long)(jp->entry);
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer to get messed up.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	/* Unpoison stack redzones in the frames we are going to jump over. */
-	kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp);
-
-	asm volatile (
-#ifdef CONFIG_X86_64
-			"       xchg   %%rbx,%%rsp	\n"
-#else
-			"       xchgl   %%ebx,%%esp	\n"
-#endif
-			"       int3			\n"
-			"       .globl jprobe_return_end\n"
-			"       jprobe_return_end:	\n"
-			"       nop			\n"::"b"
-			(kcb->jprobe_saved_sp):"memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-NOKPROBE_SYMBOL(jprobe_return_end);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	u8 *addr = (u8 *) (regs->ip - 1);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	void *saved_sp = kcb->jprobe_saved_sp;
-
-	if ((addr > (u8 *) jprobe_return) &&
-	    (addr < (u8 *) jprobe_return_end)) {
-		if (stack_addr(regs) != saved_sp) {
-			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
-			printk(KERN_ERR
-			       "current sp %p does not match saved sp %p\n",
-			       stack_addr(regs), saved_sp);
-			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk(KERN_ERR "Current registers\n");
-			show_regs(regs);
-			BUG();
-		}
-		/* It's OK to start function graph tracing again */
-		unpause_graph_tracing();
-		*regs = kcb->jprobe_saved_regs;
-		__memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	bool is_in_entry_trampoline_section = false;
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 8dc0161cec8f..ef819e19650b 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -25,36 +25,6 @@
 
 #include "common.h"
 
-static nokprobe_inline
-void __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		      struct kprobe_ctlblk *kcb, unsigned long orig_ip)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->ip)
-	 * as if there is a 5byte nop
-	 */
-	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-	if (orig_ip)
-		regs->ip = orig_ip;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		    struct kprobe_ctlblk *kcb)
-{
-	if (kprobe_ftrace(p)) {
-		__skip_singlestep(p, regs, kcb, 0);
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
 /* Ftrace callback handler for kprobes -- called under preepmt disabed */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 			   struct ftrace_ops *ops, struct pt_regs *regs)
@@ -75,18 +45,25 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
 		regs->ip = ip + sizeof(kprobe_opcode_t);
 
-		/* To emulate trap based kprobes, preempt_disable here */
-		preempt_disable();
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
-			__skip_singlestep(p, regs, kcb, orig_ip);
-			preempt_enable_no_resched();
+			/*
+			 * Emulate singlestep (and also recover regs->ip)
+			 * as if there is a 5byte nop
+			 */
+			regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
+			regs->ip = orig_ip;
 		}
 		/*
-		 * If pre_handler returns !0, it sets regs->ip and
-		 * resets current kprobe, and keep preempt count +1.
+		 * If pre_handler returns !0, it changes regs->ip. We have to
+		 * skip emulating post_handler.
 		 */
+		__this_cpu_write(current_kprobe, NULL);
 	}
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 203d398802a3..eaf02f2e7300 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -491,7 +491,6 @@ int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
 		if (!reenter)
 			reset_current_kprobe();
-		preempt_enable_no_resched();
 		return 1;
 	}
 	return 0;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5b2300b818af..09aaabb2bbf1 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -45,7 +45,6 @@
 #include <asm/apic.h>
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
-#include <asm/kvm_guest.h>
 
 static int kvmapf = 1;
 
@@ -66,15 +65,6 @@ static int __init parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
-static int kvmclock_vsyscall = 1;
-static int __init parse_no_kvmclock_vsyscall(char *arg)
-{
-        kvmclock_vsyscall = 0;
-        return 0;
-}
-
-early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
-
 static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
 static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64);
 static int has_steal_clock = 0;
@@ -154,7 +144,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
 
 	for (;;) {
 		if (!n.halted)
-			prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+			prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
 		if (hlist_unhashed(&n.link))
 			break;
 
@@ -188,7 +178,7 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
 	else if (swq_has_sleeper(&n->wq))
-		swake_up(&n->wq);
+		swake_up_one(&n->wq);
 }
 
 static void apf_task_wake_all(void)
@@ -560,9 +550,6 @@ static void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
 		apic_set_eoi_write(kvm_guest_apic_eoi_write);
 
-	if (kvmclock_vsyscall)
-		kvm_setup_vsyscall_timeinfo();
-
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
@@ -628,6 +615,7 @@ const __initconst struct hypervisor_x86 x86_hyper_kvm = {
 	.name			= "KVM",
 	.detect			= kvm_detect,
 	.type			= X86_HYPER_KVM,
+	.init.init_platform	= kvmclock_init,
 	.init.guest_late_init	= kvm_guest_init,
 	.init.x2apic_available	= kvm_para_available,
 };
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 3b8e7c13c614..1e6764648af3 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -23,30 +23,57 @@
 #include <asm/apic.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
-#include <linux/memblock.h>
+#include <linux/cpuhotplug.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
 
+#include <asm/hypervisor.h>
 #include <asm/mem_encrypt.h>
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 #include <asm/kvmclock.h>
 
-static int kvmclock __ro_after_init = 1;
-static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
-static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
-static u64 kvm_sched_clock_offset;
+static int kvmclock __initdata = 1;
+static int kvmclock_vsyscall __initdata = 1;
+static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
+static u64 kvm_sched_clock_offset __ro_after_init;
 
-static int parse_no_kvmclock(char *arg)
+static int __init parse_no_kvmclock(char *arg)
 {
 	kvmclock = 0;
 	return 0;
 }
 early_param("no-kvmclock", parse_no_kvmclock);
 
-/* The hypervisor will put information about time periodically here */
-static struct pvclock_vsyscall_time_info *hv_clock;
-static struct pvclock_wall_clock *wall_clock;
+static int __init parse_no_kvmclock_vsyscall(char *arg)
+{
+	kvmclock_vsyscall = 0;
+	return 0;
+}
+early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
+
+/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
+#define HV_CLOCK_SIZE	(sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
+#define HVC_BOOT_ARRAY_SIZE \
+	(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
+
+static struct pvclock_vsyscall_time_info
+			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE);
+static struct pvclock_wall_clock wall_clock;
+static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+
+static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+{
+	return &this_cpu_read(hv_clock_per_cpu)->pvti;
+}
+
+static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
+{
+	return this_cpu_read(hv_clock_per_cpu);
+}
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
@@ -55,21 +82,10 @@ static struct pvclock_wall_clock *wall_clock;
  */
 static void kvm_get_wallclock(struct timespec64 *now)
 {
-	struct pvclock_vcpu_time_info *vcpu_time;
-	int low, high;
-	int cpu;
-
-	low = (int)slow_virt_to_phys(wall_clock);
-	high = ((u64)slow_virt_to_phys(wall_clock) >> 32);
-
-	native_write_msr(msr_kvm_wall_clock, low, high);
-
-	cpu = get_cpu();
-
-	vcpu_time = &hv_clock[cpu].pvti;
-	pvclock_read_wallclock(wall_clock, vcpu_time, now);
-
-	put_cpu();
+	wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
+	preempt_disable();
+	pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now);
+	preempt_enable();
 }
 
 static int kvm_set_wallclock(const struct timespec64 *now)
@@ -79,14 +95,10 @@ static int kvm_set_wallclock(const struct timespec64 *now)
 
 static u64 kvm_clock_read(void)
 {
-	struct pvclock_vcpu_time_info *src;
 	u64 ret;
-	int cpu;
 
 	preempt_disable_notrace();
-	cpu = smp_processor_id();
-	src = &hv_clock[cpu].pvti;
-	ret = pvclock_clocksource_read(src);
+	ret = pvclock_clocksource_read(this_cpu_pvti());
 	preempt_enable_notrace();
 	return ret;
 }
@@ -112,11 +124,11 @@ static inline void kvm_sched_clock_init(bool stable)
 	kvm_sched_clock_offset = kvm_clock_read();
 	pv_time_ops.sched_clock = kvm_sched_clock_read;
 
-	printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
-			kvm_sched_clock_offset);
+	pr_info("kvm-clock: using sched offset of %llu cycles",
+		kvm_sched_clock_offset);
 
 	BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) >
-	         sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
+		sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
 }
 
 /*
@@ -130,19 +142,11 @@ static inline void kvm_sched_clock_init(bool stable)
  */
 static unsigned long kvm_get_tsc_khz(void)
 {
-	struct pvclock_vcpu_time_info *src;
-	int cpu;
-	unsigned long tsc_khz;
-
-	cpu = get_cpu();
-	src = &hv_clock[cpu].pvti;
-	tsc_khz = pvclock_tsc_khz(src);
-	put_cpu();
 	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	return tsc_khz;
+	return pvclock_tsc_khz(this_cpu_pvti());
 }
 
-static void kvm_get_preset_lpj(void)
+static void __init kvm_get_preset_lpj(void)
 {
 	unsigned long khz;
 	u64 lpj;
@@ -156,49 +160,40 @@ static void kvm_get_preset_lpj(void)
 
 bool kvm_check_and_clear_guest_paused(void)
 {
+	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
 	bool ret = false;
-	struct pvclock_vcpu_time_info *src;
-	int cpu = smp_processor_id();
 
-	if (!hv_clock)
+	if (!src)
 		return ret;
 
-	src = &hv_clock[cpu].pvti;
-	if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
-		src->flags &= ~PVCLOCK_GUEST_STOPPED;
+	if ((src->pvti.flags & PVCLOCK_GUEST_STOPPED) != 0) {
+		src->pvti.flags &= ~PVCLOCK_GUEST_STOPPED;
 		pvclock_touch_watchdogs();
 		ret = true;
 	}
-
 	return ret;
 }
 
 struct clocksource kvm_clock = {
-	.name = "kvm-clock",
-	.read = kvm_clock_get_cycles,
-	.rating = 400,
-	.mask = CLOCKSOURCE_MASK(64),
-	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
+	.name	= "kvm-clock",
+	.read	= kvm_clock_get_cycles,
+	.rating	= 400,
+	.mask	= CLOCKSOURCE_MASK(64),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 EXPORT_SYMBOL_GPL(kvm_clock);
 
-int kvm_register_clock(char *txt)
+static void kvm_register_clock(char *txt)
 {
-	int cpu = smp_processor_id();
-	int low, high, ret;
-	struct pvclock_vcpu_time_info *src;
-
-	if (!hv_clock)
-		return 0;
+	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
+	u64 pa;
 
-	src = &hv_clock[cpu].pvti;
-	low = (int)slow_virt_to_phys(src) | 1;
-	high = ((u64)slow_virt_to_phys(src) >> 32);
-	ret = native_write_msr_safe(msr_kvm_system_time, low, high);
-	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
-	       cpu, high, low, txt);
+	if (!src)
+		return;
 
-	return ret;
+	pa = slow_virt_to_phys(&src->pvti) | 0x01ULL;
+	wrmsrl(msr_kvm_system_time, pa);
+	pr_info("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt);
 }
 
 static void kvm_save_sched_clock_state(void)
@@ -213,11 +208,7 @@ static void kvm_restore_sched_clock_state(void)
 #ifdef CONFIG_X86_LOCAL_APIC
 static void kvm_setup_secondary_clock(void)
 {
-	/*
-	 * Now that the first cpu already had this clocksource initialized,
-	 * we shouldn't fail.
-	 */
-	WARN_ON(kvm_register_clock("secondary cpu clock"));
+	kvm_register_clock("secondary cpu clock");
 }
 #endif
 
@@ -245,100 +236,84 @@ static void kvm_shutdown(void)
 	native_machine_shutdown();
 }
 
-static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size,
-					     phys_addr_t align)
+static int __init kvm_setup_vsyscall_timeinfo(void)
 {
-	phys_addr_t mem;
+#ifdef CONFIG_X86_64
+	u8 flags;
 
-	mem = memblock_alloc(size, align);
-	if (!mem)
+	if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
 		return 0;
 
-	if (sev_active()) {
-		if (early_set_memory_decrypted((unsigned long)__va(mem), size))
-			goto e_free;
-	}
+	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+		return 0;
 
-	return mem;
-e_free:
-	memblock_free(mem, size);
+	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
+#endif
 	return 0;
 }
+early_initcall(kvm_setup_vsyscall_timeinfo);
 
-static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size)
+static int kvmclock_setup_percpu(unsigned int cpu)
 {
-	if (sev_active())
-		early_set_memory_encrypted((unsigned long)__va(addr), size);
+	struct pvclock_vsyscall_time_info *p = per_cpu(hv_clock_per_cpu, cpu);
 
-	memblock_free(addr, size);
+	/*
+	 * The per cpu area setup replicates CPU0 data to all cpu
+	 * pointers. So carefully check. CPU0 has been set up in init
+	 * already.
+	 */
+	if (!cpu || (p && p != per_cpu(hv_clock_per_cpu, 0)))
+		return 0;
+
+	/* Use the static page for the first CPUs, allocate otherwise */
+	if (cpu < HVC_BOOT_ARRAY_SIZE)
+		p = &hv_clock_boot[cpu];
+	else
+		p = kzalloc(sizeof(*p), GFP_KERNEL);
+
+	per_cpu(hv_clock_per_cpu, cpu) = p;
+	return p ? 0 : -ENOMEM;
 }
 
 void __init kvmclock_init(void)
 {
-	struct pvclock_vcpu_time_info *vcpu_time;
-	unsigned long mem, mem_wall_clock;
-	int size, cpu, wall_clock_size;
 	u8 flags;
 
-	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
-	if (!kvm_para_available())
+	if (!kvm_para_available() || !kvmclock)
 		return;
 
-	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
 		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
 		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
-	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
-		return;
-
-	wall_clock_size = PAGE_ALIGN(sizeof(struct pvclock_wall_clock));
-	mem_wall_clock = kvm_memblock_alloc(wall_clock_size, PAGE_SIZE);
-	if (!mem_wall_clock)
-		return;
-
-	wall_clock = __va(mem_wall_clock);
-	memset(wall_clock, 0, wall_clock_size);
-
-	mem = kvm_memblock_alloc(size, PAGE_SIZE);
-	if (!mem) {
-		kvm_memblock_free(mem_wall_clock, wall_clock_size);
-		wall_clock = NULL;
+	} else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
 		return;
 	}
 
-	hv_clock = __va(mem);
-	memset(hv_clock, 0, size);
-
-	if (kvm_register_clock("primary cpu clock")) {
-		hv_clock = NULL;
-		kvm_memblock_free(mem, size);
-		kvm_memblock_free(mem_wall_clock, wall_clock_size);
-		wall_clock = NULL;
+	if (cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "kvmclock:setup_percpu",
+			      kvmclock_setup_percpu, NULL) < 0) {
 		return;
 	}
 
-	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+	pr_info("kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
-	pvclock_set_pvti_cpu0_va(hv_clock);
+	this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]);
+	kvm_register_clock("primary cpu clock");
+	pvclock_set_pvti_cpu0_va(hv_clock_boot);
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
 		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 
-	cpu = get_cpu();
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-
+	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
 	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
-	put_cpu();
 
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
 	x86_platform.calibrate_cpu = kvm_get_tsc_khz;
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-	x86_cpuinit.early_percpu_clock_init =
-		kvm_setup_secondary_clock;
+	x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock;
 #endif
 	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
 	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
@@ -350,31 +325,3 @@ void __init kvmclock_init(void)
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
 	pv_info.name = "KVM";
 }
-
-int __init kvm_setup_vsyscall_timeinfo(void)
-{
-#ifdef CONFIG_X86_64
-	int cpu;
-	u8 flags;
-	struct pvclock_vcpu_time_info *vcpu_time;
-	unsigned int size;
-
-	if (!hv_clock)
-		return 0;
-
-	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
-	cpu = get_cpu();
-
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-
-	put_cpu();
-
-	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
-		return 1;
-
-	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
-#endif
-	return 0;
-}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c9b14020f4dd..733e6ace0fa4 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -100,6 +100,102 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 	return new_ldt;
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+static void do_sanity_check(struct mm_struct *mm,
+			    bool had_kernel_mapping,
+			    bool had_user_mapping)
+{
+	if (mm->context.ldt) {
+		/*
+		 * We already had an LDT.  The top-level entry should already
+		 * have been allocated and synchronized with the usermode
+		 * tables.
+		 */
+		WARN_ON(!had_kernel_mapping);
+		if (static_cpu_has(X86_FEATURE_PTI))
+			WARN_ON(!had_user_mapping);
+	} else {
+		/*
+		 * This is the first time we're mapping an LDT for this process.
+		 * Sync the pgd to the usermode tables.
+		 */
+		WARN_ON(had_kernel_mapping);
+		if (static_cpu_has(X86_FEATURE_PTI))
+			WARN_ON(had_user_mapping);
+	}
+}
+
+#ifdef CONFIG_X86_PAE
+
+static pmd_t *pgd_to_pmd_walk(pgd_t *pgd, unsigned long va)
+{
+	p4d_t *p4d;
+	pud_t *pud;
+
+	if (pgd->pgd == 0)
+		return NULL;
+
+	p4d = p4d_offset(pgd, va);
+	if (p4d_none(*p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, va);
+	if (pud_none(*pud))
+		return NULL;
+
+	return pmd_offset(pud, va);
+}
+
+static void map_ldt_struct_to_user(struct mm_struct *mm)
+{
+	pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	pmd_t *k_pmd, *u_pmd;
+
+	k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
+	u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
+
+	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+		set_pmd(u_pmd, *k_pmd);
+}
+
+static void sanity_check_ldt_mapping(struct mm_struct *mm)
+{
+	pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	bool had_kernel, had_user;
+	pmd_t *k_pmd, *u_pmd;
+
+	k_pmd      = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
+	u_pmd      = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
+	had_kernel = (k_pmd->pmd != 0);
+	had_user   = (u_pmd->pmd != 0);
+
+	do_sanity_check(mm, had_kernel, had_user);
+}
+
+#else /* !CONFIG_X86_PAE */
+
+static void map_ldt_struct_to_user(struct mm_struct *mm)
+{
+	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
+
+	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+		set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+}
+
+static void sanity_check_ldt_mapping(struct mm_struct *mm)
+{
+	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	bool had_kernel = (pgd->pgd != 0);
+	bool had_user   = (kernel_to_user_pgdp(pgd)->pgd != 0);
+
+	do_sanity_check(mm, had_kernel, had_user);
+}
+
+#endif /* CONFIG_X86_PAE */
+
 /*
  * If PTI is enabled, this maps the LDT into the kernelmode and
  * usermode tables for the given mm.
@@ -115,9 +211,8 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 static int
 map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 {
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-	bool is_vmalloc, had_top_level_entry;
 	unsigned long va;
+	bool is_vmalloc;
 	spinlock_t *ptl;
 	pgd_t *pgd;
 	int i;
@@ -131,13 +226,15 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	 */
 	WARN_ON(ldt->slot != -1);
 
+	/* Check if the current mappings are sane */
+	sanity_check_ldt_mapping(mm);
+
 	/*
 	 * Did we already have the top level entry allocated?  We can't
 	 * use pgd_none() for this because it doens't do anything on
 	 * 4-level page table kernels.
 	 */
 	pgd = pgd_offset(mm, LDT_BASE_ADDR);
-	had_top_level_entry = (pgd->pgd != 0);
 
 	is_vmalloc = is_vmalloc_addr(ldt->entries);
 
@@ -172,41 +269,31 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 		pte_unmap_unlock(ptep, ptl);
 	}
 
-	if (mm->context.ldt) {
-		/*
-		 * We already had an LDT.  The top-level entry should already
-		 * have been allocated and synchronized with the usermode
-		 * tables.
-		 */
-		WARN_ON(!had_top_level_entry);
-		if (static_cpu_has(X86_FEATURE_PTI))
-			WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
-	} else {
-		/*
-		 * This is the first time we're mapping an LDT for this process.
-		 * Sync the pgd to the usermode tables.
-		 */
-		WARN_ON(had_top_level_entry);
-		if (static_cpu_has(X86_FEATURE_PTI)) {
-			WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
-			set_pgd(kernel_to_user_pgdp(pgd), *pgd);
-		}
-	}
+	/* Propagate LDT mapping to the user page-table */
+	map_ldt_struct_to_user(mm);
 
 	va = (unsigned long)ldt_slot_va(slot);
 	flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
 
 	ldt->slot = slot;
-#endif
 	return 0;
 }
 
+#else /* !CONFIG_PAGE_TABLE_ISOLATION */
+
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+	return 0;
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
 static void free_ldt_pgtables(struct mm_struct *mm)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 	struct mmu_gather tlb;
 	unsigned long start = LDT_BASE_ADDR;
-	unsigned long end = start + (1UL << PGDIR_SHIFT);
+	unsigned long end = LDT_END_ADDR;
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return;
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index d1ab07ec8c9a..5409c2800ab5 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -56,7 +56,7 @@ static void load_segments(void)
 
 static void machine_kexec_free_page_tables(struct kimage *image)
 {
-	free_page((unsigned long)image->arch.pgd);
+	free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
 	image->arch.pgd = NULL;
 #ifdef CONFIG_X86_PAE
 	free_page((unsigned long)image->arch.pmd0);
@@ -72,7 +72,8 @@ static void machine_kexec_free_page_tables(struct kimage *image)
 
 static int machine_kexec_alloc_page_tables(struct kimage *image)
 {
-	image->arch.pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+	image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						    PGD_ALLOCATION_ORDER);
 #ifdef CONFIG_X86_PAE
 	image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
 	image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 99dc79e76bdc..930c88341e4e 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -88,10 +88,12 @@ unsigned paravirt_patch_call(void *insnbuf,
 	struct branch *b = insnbuf;
 	unsigned long delta = (unsigned long)target - (addr+5);
 
-	if (tgt_clobbers & ~site_clobbers)
-		return len;	/* target would clobber too much for this site */
-	if (len < 5)
+	if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+		WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+#endif
 		return len;	/* call too long for patch site */
+	}
 
 	b->opcode = 0xe8; /* call */
 	b->delta = delta;
@@ -106,8 +108,12 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
 	struct branch *b = insnbuf;
 	unsigned long delta = (unsigned long)target - (addr+5);
 
-	if (len < 5)
+	if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+		WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+#endif
 		return len;	/* call too long for patch site */
+	}
 
 	b->opcode = 0xe9;	/* jmp */
 	b->delta = delta;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 9edadabf04f6..9cb98f7b07c9 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -20,7 +20,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
 #endif
 
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index ab5d9dd668d2..80f9fe8d27d0 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -175,7 +175,7 @@ rootfs_initcall(pci_iommu_init);
 
 static int via_no_dac_cb(struct pci_dev *pdev, void *data)
 {
-	pdev->dev.dma_32bit_limit = true;
+	pdev->dev.bus_dma_mask = DMA_BIT_MASK(32);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
index 4dfd90a75e63..2e9006c1e240 100644
--- a/arch/x86/kernel/pci-iommu_table.c
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -60,7 +60,7 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
 			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
 			       p->detect, q->detect);
 			/* Heavy handed way..*/
-			x->depend = 0;
+			x->depend = NULL;
 		}
 	}
 
diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c
index da5190a1ea16..4a710ffffd9a 100644
--- a/arch/x86/kernel/pcspeaker.c
+++ b/arch/x86/kernel/pcspeaker.c
@@ -9,6 +9,6 @@ static __init int add_pcspkr(void)
 
 	pd = platform_device_register_simple("pcspkr", -1, NULL, 0);
 
-	return IS_ERR(pd) ? PTR_ERR(pd) : 0;
+	return PTR_ERR_OR_ZERO(pd);
 }
 device_initcall(add_pcspkr);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 30ca2d1a9231..c93fcfdf1673 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -57,14 +57,12 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
 		 */
 		.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
 
-#ifdef CONFIG_X86_64
 		/*
 		 * .sp1 is cpu_current_top_of_stack.  The init task never
 		 * runs user code, but cpu_current_top_of_stack should still
 		 * be well defined before the first context switch.
 		 */
 		.sp1 = TOP_OF_INIT_STACK,
-#endif
 
 #ifdef CONFIG_X86_32
 		.ss0 = __KERNEL_DS,
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0ae659de21eb..2924fd447e61 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -285,7 +285,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
-	update_sp0(next_p);
+	update_task_stack(next_p);
 	refresh_sysenter_cs(next);
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 12bb445fb98d..476e3ddf8890 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -478,7 +478,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	/* Reload sp0. */
-	update_sp0(next_p);
+	update_task_stack(next_p);
 
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2f86d883dd95..8fe740e22030 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -823,6 +823,12 @@ void __init setup_arch(char **cmdline_p)
 	memblock_reserve(__pa_symbol(_text),
 			 (unsigned long)__bss_stop - (unsigned long)_text);
 
+	/*
+	 * Make sure page 0 is always reserved because on systems with
+	 * L1TF its contents can be leaked to user processes.
+	 */
+	memblock_reserve(0, PAGE_SIZE);
+
 	early_reserve_initrd();
 
 	/*
@@ -866,6 +872,8 @@ void __init setup_arch(char **cmdline_p)
 
 	idt_setup_early_traps();
 	early_cpu_init();
+	arch_init_ideal_nops();
+	jump_label_init();
 	early_ioremap_init();
 
 	setup_olpc_ofw_pgd();
@@ -1012,6 +1020,7 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	init_hypervisor_platform();
 
+	tsc_early_init();
 	x86_init.resources.probe_roms();
 
 	/* after parse_early_param, so could debug it */
@@ -1197,11 +1206,6 @@ void __init setup_arch(char **cmdline_p)
 
 	memblock_find_dma_reserve();
 
-#ifdef CONFIG_KVM_GUEST
-	kvmclock_init();
-#endif
-
-	tsc_early_delay_calibrate();
 	if (!early_xdbc_setup_hardware())
 		early_xdbc_register_console();
 
@@ -1272,8 +1276,6 @@ void __init setup_arch(char **cmdline_p)
 
 	mcheck_init();
 
-	arch_init_ideal_nops();
-
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 5c574dff4c1a..04adc8d60aed 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -261,6 +261,7 @@ __visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	inc_irq_stat(irq_resched_count);
+	kvm_set_cpu_l1tf_flush_l1d();
 
 	if (trace_resched_ipi_enabled()) {
 		/*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index db9656e13ea0..f02ecaf97904 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -80,6 +80,7 @@
 #include <asm/intel-family.h>
 #include <asm/cpu_device_id.h>
 #include <asm/spec-ctrl.h>
+#include <asm/hw_irq.h>
 
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
@@ -271,6 +272,23 @@ static void notrace start_secondary(void *unused)
 }
 
 /**
+ * topology_is_primary_thread - Check whether CPU is the primary SMT thread
+ * @cpu:	CPU to check
+ */
+bool topology_is_primary_thread(unsigned int cpu)
+{
+	return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu));
+}
+
+/**
+ * topology_smt_supported - Check whether SMT is supported by the CPUs
+ */
+bool topology_smt_supported(void)
+{
+	return smp_num_siblings > 1;
+}
+
+/**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
  *
  * Returns logical package id or -1 if not found
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 093f2ea5dd56..7627455047c2 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -81,16 +81,6 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 #ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
 
-#define STACKTRACE_DUMP_ONCE(task) ({				\
-	static bool __section(.data.unlikely) __dumped;		\
-								\
-	if (!__dumped) {					\
-		__dumped = true;				\
-		WARN_ON(1);					\
-		show_stack(task, NULL);				\
-	}							\
-})
-
 static int __always_inline
 __save_stack_trace_reliable(struct stack_trace *trace,
 			    struct task_struct *task)
@@ -99,30 +89,25 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 	struct pt_regs *regs;
 	unsigned long addr;
 
-	for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
+	for (unwind_start(&state, task, NULL, NULL);
+	     !unwind_done(&state) && !unwind_error(&state);
 	     unwind_next_frame(&state)) {
 
 		regs = unwind_get_entry_regs(&state, NULL);
 		if (regs) {
+			/* Success path for user tasks */
+			if (user_mode(regs))
+				goto success;
+
 			/*
 			 * Kernel mode registers on the stack indicate an
 			 * in-kernel interrupt or exception (e.g., preemption
 			 * or a page fault), which can make frame pointers
 			 * unreliable.
 			 */
-			if (!user_mode(regs))
-				return -EINVAL;
 
-			/*
-			 * The last frame contains the user mode syscall
-			 * pt_regs.  Skip it and finish the unwind.
-			 */
-			unwind_next_frame(&state);
-			if (!unwind_done(&state)) {
-				STACKTRACE_DUMP_ONCE(task);
+			if (IS_ENABLED(CONFIG_FRAME_POINTER))
 				return -EINVAL;
-			}
-			break;
 		}
 
 		addr = unwind_get_return_address(&state);
@@ -132,21 +117,22 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 		 * generated code which __kernel_text_address() doesn't know
 		 * about.
 		 */
-		if (!addr) {
-			STACKTRACE_DUMP_ONCE(task);
+		if (!addr)
 			return -EINVAL;
-		}
 
 		if (save_stack_address(trace, addr, false))
 			return -EINVAL;
 	}
 
 	/* Check for stack corruption */
-	if (unwind_error(&state)) {
-		STACKTRACE_DUMP_ONCE(task);
+	if (unwind_error(&state))
+		return -EINVAL;
+
+	/* Success path for non-user tasks, i.e. kthreads and idle tasks */
+	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
 		return -EINVAL;
-	}
 
+success:
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 774ebafa97c4..be01328eb755 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -12,6 +12,7 @@
 
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/i8253.h>
 #include <linux/time.h>
 #include <linux/export.h>
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 74392d9d51e0..1463468ba9a0 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -33,16 +33,13 @@ EXPORT_SYMBOL(cpu_khz);
 unsigned int __read_mostly tsc_khz;
 EXPORT_SYMBOL(tsc_khz);
 
+#define KHZ	1000
+
 /*
  * TSC can be unstable due to cpufreq or due to unsynced TSCs
  */
 static int __read_mostly tsc_unstable;
 
-/* native_sched_clock() is called before tsc_init(), so
-   we must start with the TSC soft disabled to prevent
-   erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */
-static int __read_mostly tsc_disabled = -1;
-
 static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
@@ -106,23 +103,6 @@ void cyc2ns_read_end(void)
  *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
  */
 
-static void cyc2ns_data_init(struct cyc2ns_data *data)
-{
-	data->cyc2ns_mul = 0;
-	data->cyc2ns_shift = 0;
-	data->cyc2ns_offset = 0;
-}
-
-static void __init cyc2ns_init(int cpu)
-{
-	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
-
-	cyc2ns_data_init(&c2n->data[0]);
-	cyc2ns_data_init(&c2n->data[1]);
-
-	seqcount_init(&c2n->seq);
-}
-
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
 	struct cyc2ns_data data;
@@ -138,18 +118,11 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 	return ns;
 }
 
-static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+static void __set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
 {
 	unsigned long long ns_now;
 	struct cyc2ns_data data;
 	struct cyc2ns *c2n;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	sched_clock_idle_sleep_event();
-
-	if (!khz)
-		goto done;
 
 	ns_now = cycles_2_ns(tsc_now);
 
@@ -181,13 +154,56 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_
 	c2n->data[0] = data;
 	raw_write_seqcount_latch(&c2n->seq);
 	c2n->data[1] = data;
+}
+
+static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	sched_clock_idle_sleep_event();
+
+	if (khz)
+		__set_cyc2ns_scale(khz, cpu, tsc_now);
 
-done:
 	sched_clock_idle_wakeup_event();
 	local_irq_restore(flags);
 }
 
 /*
+ * Initialize cyc2ns for boot cpu
+ */
+static void __init cyc2ns_init_boot_cpu(void)
+{
+	struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+
+	seqcount_init(&c2n->seq);
+	__set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc());
+}
+
+/*
+ * Secondary CPUs do not run through tsc_init(), so set up
+ * all the scale factors for all CPUs, assuming the same
+ * speed as the bootup CPU. (cpufreq notifiers will fix this
+ * up if their speed diverges)
+ */
+static void __init cyc2ns_init_secondary_cpus(void)
+{
+	unsigned int cpu, this_cpu = smp_processor_id();
+	struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+	struct cyc2ns_data *data = c2n->data;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu != this_cpu) {
+			seqcount_init(&c2n->seq);
+			c2n = per_cpu_ptr(&cyc2ns, cpu);
+			c2n->data[0] = data[0];
+			c2n->data[1] = data[1];
+		}
+	}
+}
+
+/*
  * Scheduler clock - returns current time in nanosec units.
  */
 u64 native_sched_clock(void)
@@ -248,8 +264,7 @@ EXPORT_SYMBOL_GPL(check_tsc_unstable);
 #ifdef CONFIG_X86_TSC
 int __init notsc_setup(char *str)
 {
-	pr_warn("Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely\n");
-	tsc_disabled = 1;
+	mark_tsc_unstable("boot parameter notsc");
 	return 1;
 }
 #else
@@ -665,30 +680,17 @@ static unsigned long cpu_khz_from_cpuid(void)
 	return eax_base_mhz * 1000;
 }
 
-/**
- * native_calibrate_cpu - calibrate the cpu on boot
+/*
+ * calibrate cpu using pit, hpet, and ptimer methods. They are available
+ * later in boot after acpi is initialized.
  */
-unsigned long native_calibrate_cpu(void)
+static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 {
 	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags, latch, ms, fast_calibrate;
+	unsigned long flags, latch, ms;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
-	fast_calibrate = cpu_khz_from_cpuid();
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	fast_calibrate = cpu_khz_from_msr();
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	local_irq_save(flags);
-	fast_calibrate = quick_pit_calibrate();
-	local_irq_restore(flags);
-	if (fast_calibrate)
-		return fast_calibrate;
-
 	/*
 	 * Run 5 calibration loops to get the lowest frequency value
 	 * (the best estimate). We use two different calibration modes
@@ -831,6 +833,37 @@ unsigned long native_calibrate_cpu(void)
 	return tsc_pit_min;
 }
 
+/**
+ * native_calibrate_cpu_early - can calibrate the cpu early in boot
+ */
+unsigned long native_calibrate_cpu_early(void)
+{
+	unsigned long flags, fast_calibrate = cpu_khz_from_cpuid();
+
+	if (!fast_calibrate)
+		fast_calibrate = cpu_khz_from_msr();
+	if (!fast_calibrate) {
+		local_irq_save(flags);
+		fast_calibrate = quick_pit_calibrate();
+		local_irq_restore(flags);
+	}
+	return fast_calibrate;
+}
+
+
+/**
+ * native_calibrate_cpu - calibrate the cpu
+ */
+static unsigned long native_calibrate_cpu(void)
+{
+	unsigned long tsc_freq = native_calibrate_cpu_early();
+
+	if (!tsc_freq)
+		tsc_freq = pit_hpet_ptimer_calibrate_cpu();
+
+	return tsc_freq;
+}
+
 void recalibrate_cpu_khz(void)
 {
 #ifndef CONFIG_SMP
@@ -1307,7 +1340,7 @@ unreg:
 
 static int __init init_tsc_clocksource(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
+	if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz)
 		return 0;
 
 	if (tsc_unstable)
@@ -1341,40 +1374,22 @@ unreg:
  */
 device_initcall(init_tsc_clocksource);
 
-void __init tsc_early_delay_calibrate(void)
+static bool __init determine_cpu_tsc_frequencies(bool early)
 {
-	unsigned long lpj;
-
-	if (!boot_cpu_has(X86_FEATURE_TSC))
-		return;
-
-	cpu_khz = x86_platform.calibrate_cpu();
-	tsc_khz = x86_platform.calibrate_tsc();
-
-	tsc_khz = tsc_khz ? : cpu_khz;
-	if (!tsc_khz)
-		return;
-
-	lpj = tsc_khz * 1000;
-	do_div(lpj, HZ);
-	loops_per_jiffy = lpj;
-}
-
-void __init tsc_init(void)
-{
-	u64 lpj, cyc;
-	int cpu;
-
-	if (!boot_cpu_has(X86_FEATURE_TSC)) {
-		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
-		return;
+	/* Make sure that cpu and tsc are not already calibrated */
+	WARN_ON(cpu_khz || tsc_khz);
+
+	if (early) {
+		cpu_khz = x86_platform.calibrate_cpu();
+		tsc_khz = x86_platform.calibrate_tsc();
+	} else {
+		/* We should not be here with non-native cpu calibration */
+		WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu);
+		cpu_khz = pit_hpet_ptimer_calibrate_cpu();
 	}
 
-	cpu_khz = x86_platform.calibrate_cpu();
-	tsc_khz = x86_platform.calibrate_tsc();
-
 	/*
-	 * Trust non-zero tsc_khz as authorative,
+	 * Trust non-zero tsc_khz as authoritative,
 	 * and use it to sanity check cpu_khz,
 	 * which will be off if system timer is off.
 	 */
@@ -1383,52 +1398,78 @@ void __init tsc_init(void)
 	else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz)
 		cpu_khz = tsc_khz;
 
-	if (!tsc_khz) {
-		mark_tsc_unstable("could not calculate TSC khz");
-		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
-		return;
-	}
+	if (tsc_khz == 0)
+		return false;
 
 	pr_info("Detected %lu.%03lu MHz processor\n",
-		(unsigned long)cpu_khz / 1000,
-		(unsigned long)cpu_khz % 1000);
+		(unsigned long)cpu_khz / KHZ,
+		(unsigned long)cpu_khz % KHZ);
 
 	if (cpu_khz != tsc_khz) {
 		pr_info("Detected %lu.%03lu MHz TSC",
-			(unsigned long)tsc_khz / 1000,
-			(unsigned long)tsc_khz % 1000);
+			(unsigned long)tsc_khz / KHZ,
+			(unsigned long)tsc_khz % KHZ);
 	}
+	return true;
+}
+
+static unsigned long __init get_loops_per_jiffy(void)
+{
+	unsigned long lpj = tsc_khz * KHZ;
 
+	do_div(lpj, HZ);
+	return lpj;
+}
+
+static void __init tsc_enable_sched_clock(void)
+{
 	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
 	tsc_store_and_check_tsc_adjust(true);
+	cyc2ns_init_boot_cpu();
+	static_branch_enable(&__use_tsc);
+}
+
+void __init tsc_early_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_TSC))
+		return;
+	if (!determine_cpu_tsc_frequencies(true))
+		return;
+	loops_per_jiffy = get_loops_per_jiffy();
 
+	tsc_enable_sched_clock();
+}
+
+void __init tsc_init(void)
+{
 	/*
-	 * Secondary CPUs do not run through tsc_init(), so set up
-	 * all the scale factors for all CPUs, assuming the same
-	 * speed as the bootup CPU. (cpufreq notifiers will fix this
-	 * up if their speed diverges)
+	 * native_calibrate_cpu_early can only calibrate using methods that are
+	 * available early in boot.
 	 */
-	cyc = rdtsc();
-	for_each_possible_cpu(cpu) {
-		cyc2ns_init(cpu);
-		set_cyc2ns_scale(tsc_khz, cpu, cyc);
-	}
+	if (x86_platform.calibrate_cpu == native_calibrate_cpu_early)
+		x86_platform.calibrate_cpu = native_calibrate_cpu;
 
-	if (tsc_disabled > 0)
+	if (!boot_cpu_has(X86_FEATURE_TSC)) {
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
+	}
 
-	/* now allow native_sched_clock() to use rdtsc */
+	if (!tsc_khz) {
+		/* We failed to determine frequencies earlier, try again */
+		if (!determine_cpu_tsc_frequencies(false)) {
+			mark_tsc_unstable("could not calculate TSC khz");
+			setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
+			return;
+		}
+		tsc_enable_sched_clock();
+	}
 
-	tsc_disabled = 0;
-	static_branch_enable(&__use_tsc);
+	cyc2ns_init_secondary_cpus();
 
 	if (!no_sched_irq_time)
 		enable_sched_clock_irqtime();
 
-	lpj = ((u64)tsc_khz * 1000);
-	do_div(lpj, HZ);
-	lpj_fine = lpj;
-
+	lpj_fine = get_loops_per_jiffy();
 	use_tsc_delay();
 
 	check_system_tsc_reliable();
@@ -1455,7 +1496,7 @@ unsigned long calibrate_delay_is_known(void)
 	int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC);
 	const struct cpumask *mask = topology_core_cpumask(cpu);
 
-	if (tsc_disabled || !constant_tsc || !mask)
+	if (!constant_tsc || !mask)
 		return 0;
 
 	sibling = cpumask_any_but(mask, cpu);
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 19afdbd7d0a7..27ef714d886c 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -1,17 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * tsc_msr.c - TSC frequency enumeration via MSR
+ * TSC frequency enumeration via MSR
  *
- * Copyright (C) 2013 Intel Corporation
+ * Copyright (C) 2013, 2018 Intel Corporation
  * Author: Bin Gao <bin.gao@intel.com>
- *
- * This file is released under the GPLv2.
  */
 
 #include <linux/kernel.h>
-#include <asm/processor.h>
-#include <asm/setup.h>
+
 #include <asm/apic.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include <asm/msr.h>
 #include <asm/param.h>
+#include <asm/tsc.h>
 
 #define MAX_NUM_FREQS	9
 
@@ -23,44 +25,48 @@
  * field msr_plat does.
  */
 struct freq_desc {
-	u8 x86_family;	/* CPU family */
-	u8 x86_model;	/* model */
 	u8 msr_plat;	/* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */
 	u32 freqs[MAX_NUM_FREQS];
 };
 
-static struct freq_desc freq_desc_tables[] = {
-	/* PNW */
-	{ 6, 0x27, 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 } },
-	/* CLV+ */
-	{ 6, 0x35, 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 } },
-	/* TNG - Intel Atom processor Z3400 series */
-	{ 6, 0x4a, 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 } },
-	/* VLV2 - Intel Atom processor E3000, Z3600, Z3700 series */
-	{ 6, 0x37, 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 } },
-	/* ANN - Intel Atom processor Z3500 series */
-	{ 6, 0x5a, 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } },
-	/* AMT - Intel Atom processor X7-Z8000 and X5-Z8000 series */
-	{ 6, 0x4c, 1, { 83300, 100000, 133300, 116700,
-			80000, 93300, 90000, 88900, 87500 } },
+/*
+ * Penwell and Clovertrail use spread spectrum clock,
+ * so the freq number is not exactly the same as reported
+ * by MSR based on SDM.
+ */
+static const struct freq_desc freq_desc_pnw = {
+	0, { 0, 0, 0, 0, 0, 99840, 0, 83200 }
 };
 
-static int match_cpu(u8 family, u8 model)
-{
-	int i;
+static const struct freq_desc freq_desc_clv = {
+	0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 }
+};
 
-	for (i = 0; i < ARRAY_SIZE(freq_desc_tables); i++) {
-		if ((family == freq_desc_tables[i].x86_family) &&
-			(model == freq_desc_tables[i].x86_model))
-			return i;
-	}
+static const struct freq_desc freq_desc_byt = {
+	1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 }
+};
 
-	return -1;
-}
+static const struct freq_desc freq_desc_cht = {
+	1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 }
+};
 
-/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
-#define id_to_freq(cpu_index, freq_id) \
-	(freq_desc_tables[cpu_index].freqs[freq_id])
+static const struct freq_desc freq_desc_tng = {
+	1, { 0, 100000, 133300, 0, 0, 0, 0, 0 }
+};
+
+static const struct freq_desc freq_desc_ann = {
+	1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 }
+};
+
+static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
+	INTEL_CPU_FAM6(ATOM_PENWELL,		freq_desc_pnw),
+	INTEL_CPU_FAM6(ATOM_CLOVERVIEW,		freq_desc_clv),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT1,	freq_desc_byt),
+	INTEL_CPU_FAM6(ATOM_AIRMONT,		freq_desc_cht),
+	INTEL_CPU_FAM6(ATOM_MERRIFIELD,		freq_desc_tng),
+	INTEL_CPU_FAM6(ATOM_MOOREFIELD,		freq_desc_ann),
+	{}
+};
 
 /*
  * MSR-based CPU/TSC frequency discovery for certain CPUs.
@@ -70,18 +76,17 @@ static int match_cpu(u8 family, u8 model)
  */
 unsigned long cpu_khz_from_msr(void)
 {
-	u32 lo, hi, ratio, freq_id, freq;
+	u32 lo, hi, ratio, freq;
+	const struct freq_desc *freq_desc;
+	const struct x86_cpu_id *id;
 	unsigned long res;
-	int cpu_index;
-
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
-		return 0;
 
-	cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model);
-	if (cpu_index < 0)
+	id = x86_match_cpu(tsc_msr_cpu_ids);
+	if (!id)
 		return 0;
 
-	if (freq_desc_tables[cpu_index].msr_plat) {
+	freq_desc = (struct freq_desc *)id->driver_data;
+	if (freq_desc->msr_plat) {
 		rdmsr(MSR_PLATFORM_INFO, lo, hi);
 		ratio = (lo >> 8) & 0xff;
 	} else {
@@ -91,8 +96,9 @@ unsigned long cpu_khz_from_msr(void)
 
 	/* Get FSB FREQ ID */
 	rdmsr(MSR_FSB_FREQ, lo, hi);
-	freq_id = lo & 0x7;
-	freq = id_to_freq(cpu_index, freq_id);
+
+	/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
+	freq = freq_desc->freqs[lo & 0x7];
 
 	/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
 	res = freq * ratio;
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index feb28fee6cea..26038eacf74a 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -198,7 +198,7 @@ static int orc_sort_cmp(const void *_a, const void *_b)
 	 * whitelisted .o files which didn't get objtool generation.
 	 */
 	orc_a = cur_orc_table + (a - cur_orc_ip_table);
-	return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1;
+	return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1;
 }
 
 #ifdef CONFIG_MODULES
@@ -352,7 +352,7 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 
 bool unwind_next_frame(struct unwind_state *state)
 {
-	unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
+	unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
 	bool indirect = false;
@@ -363,9 +363,9 @@ bool unwind_next_frame(struct unwind_state *state)
 	/* Don't let modules unload while we're reading their ORC data. */
 	preempt_disable();
 
-	/* Have we reached the end? */
+	/* End-of-stack check for user tasks: */
 	if (state->regs && user_mode(state->regs))
-		goto done;
+		goto the_end;
 
 	/*
 	 * Find the orc_entry associated with the text address.
@@ -374,9 +374,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	 * calls and calls to noreturn functions.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
-	if (!orc || orc->sp_reg == ORC_REG_UNDEFINED)
-		goto done;
-	orig_ip = state->ip;
+	if (!orc)
+		goto err;
+
+	/* End-of-stack check for kernel threads: */
+	if (orc->sp_reg == ORC_REG_UNDEFINED) {
+		if (!orc->end)
+			goto err;
+
+		goto the_end;
+	}
 
 	/* Find the previous frame's stack: */
 	switch (orc->sp_reg) {
@@ -402,7 +409,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg R10 at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->r10;
 		break;
@@ -411,7 +418,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg R13 at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->r13;
 		break;
@@ -420,7 +427,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg DI at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->di;
 		break;
@@ -429,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg DX at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->dx;
 		break;
@@ -437,12 +444,12 @@ bool unwind_next_frame(struct unwind_state *state)
 	default:
 		orc_warn("unknown SP base reg %d for ip %pB\n",
 			 orc->sp_reg, (void *)state->ip);
-		goto done;
+		goto err;
 	}
 
 	if (indirect) {
 		if (!deref_stack_reg(state, sp, &sp))
-			goto done;
+			goto err;
 	}
 
 	/* Find IP, SP and possibly regs: */
@@ -451,7 +458,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		ip_p = sp - sizeof(long);
 
 		if (!deref_stack_reg(state, ip_p, &state->ip))
-			goto done;
+			goto err;
 
 		state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
 						  state->ip, (void *)ip_p);
@@ -465,7 +472,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
-			goto done;
+			goto err;
 		}
 
 		state->regs = (struct pt_regs *)sp;
@@ -477,7 +484,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference iret registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
-			goto done;
+			goto err;
 		}
 
 		state->regs = (void *)sp - IRET_FRAME_OFFSET;
@@ -500,18 +507,18 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_REG_PREV_SP:
 		if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp))
-			goto done;
+			goto err;
 		break;
 
 	case ORC_REG_BP:
 		if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp))
-			goto done;
+			goto err;
 		break;
 
 	default:
 		orc_warn("unknown BP base reg %d for ip %pB\n",
 			 orc->bp_reg, (void *)orig_ip);
-		goto done;
+		goto err;
 	}
 
 	/* Prevent a recursive loop due to bad ORC data: */
@@ -520,13 +527,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	    state->sp <= prev_sp) {
 		orc_warn("stack going in the wrong direction? ip=%pB\n",
 			 (void *)orig_ip);
-		goto done;
+		goto err;
 	}
 
 	preempt_enable();
 	return true;
 
-done:
+err:
+	state->error = true;
+
+the_end:
 	preempt_enable();
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 9d0b5af7db91..1c03e4aa6474 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -149,7 +149,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 	preempt_disable();
 	tsk->thread.sp0 = vm86->saved_sp0;
 	tsk->thread.sysenter_cs = __KERNEL_CS;
-	update_sp0(tsk);
+	update_task_stack(tsk);
 	refresh_sysenter_cs(&tsk->thread);
 	vm86->saved_sp0 = 0;
 	preempt_enable();
@@ -374,7 +374,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 		refresh_sysenter_cs(&tsk->thread);
 	}
 
-	update_sp0(tsk);
+	update_task_stack(tsk);
 	preempt_enable();
 
 	if (vm86->flags & VM86_SCREEN_BITMAP)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 5e1458f609a1..8bde0a419f86 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -55,19 +55,22 @@ jiffies_64 = jiffies;
  * so we can enable protection checks as well as retain 2MB large page
  * mappings for kernel text.
  */
-#define X64_ALIGN_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
+#define X86_ALIGN_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
 
-#define X64_ALIGN_RODATA_END					\
+#define X86_ALIGN_RODATA_END					\
 		. = ALIGN(HPAGE_SIZE);				\
-		__end_rodata_hpage_align = .;
+		__end_rodata_hpage_align = .;			\
+		__end_rodata_aligned = .;
 
 #define ALIGN_ENTRY_TEXT_BEGIN	. = ALIGN(PMD_SIZE);
 #define ALIGN_ENTRY_TEXT_END	. = ALIGN(PMD_SIZE);
 
 #else
 
-#define X64_ALIGN_RODATA_BEGIN
-#define X64_ALIGN_RODATA_END
+#define X86_ALIGN_RODATA_BEGIN
+#define X86_ALIGN_RODATA_END					\
+		. = ALIGN(PAGE_SIZE);				\
+		__end_rodata_aligned = .;
 
 #define ALIGN_ENTRY_TEXT_BEGIN
 #define ALIGN_ENTRY_TEXT_END
@@ -141,9 +144,9 @@ SECTIONS
 
 	/* .text should occupy whole number of pages */
 	. = ALIGN(PAGE_SIZE);
-	X64_ALIGN_RODATA_BEGIN
+	X86_ALIGN_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
-	X64_ALIGN_RODATA_END
+	X86_ALIGN_RODATA_END
 
 	/* Data */
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 3ab867603e81..2792b5573818 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -109,7 +109,7 @@ struct x86_cpuinit_ops x86_cpuinit = {
 static void default_nmi_init(void) { };
 
 struct x86_platform_ops x86_platform __ro_after_init = {
-	.calibrate_cpu			= native_calibrate_cpu,
+	.calibrate_cpu			= native_calibrate_cpu_early,
 	.calibrate_tsc			= native_calibrate_tsc,
 	.get_wallclock			= mach_get_cmos_time,
 	.set_wallclock			= mach_set_rtc_mmss,
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b5cd8465d44f..d536d457517b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1379,7 +1379,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	 * using swait_active() is safe.
 	 */
 	if (swait_active(q))
-		swake_up(q);
+		swake_up_one(q);
 
 	if (apic_lvtt_tscdeadline(apic))
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 6b8f11521c41..a44e568363a4 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3840,6 +3840,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 {
 	int r = 1;
 
+	vcpu->arch.l1tf_flush_l1d = true;
 	switch (vcpu->arch.apf.host_apf_reason) {
 	default:
 		trace_kvm_page_fault(fault_address, error_code);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5d8e317c2b04..46b428c0990e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -188,6 +188,150 @@ module_param(ple_window_max, uint, 0444);
 
 extern const ulong vmx_return;
 
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
+static DEFINE_MUTEX(vmx_l1d_flush_mutex);
+
+/* Storage for pre module init parameter parsing */
+static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO;
+
+static const struct {
+	const char *option;
+	enum vmx_l1d_flush_state cmd;
+} vmentry_l1d_param[] = {
+	{"auto",	VMENTER_L1D_FLUSH_AUTO},
+	{"never",	VMENTER_L1D_FLUSH_NEVER},
+	{"cond",	VMENTER_L1D_FLUSH_COND},
+	{"always",	VMENTER_L1D_FLUSH_ALWAYS},
+};
+
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
+{
+	struct page *page;
+	unsigned int i;
+
+	if (!enable_ept) {
+		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
+		return 0;
+	}
+
+       if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
+	       u64 msr;
+
+	       rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
+	       if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
+		       l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+		       return 0;
+	       }
+       }
+
+	/* If set to auto use the default l1tf mitigation method */
+	if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+			l1tf = VMENTER_L1D_FLUSH_NEVER;
+			break;
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+			l1tf = VMENTER_L1D_FLUSH_COND;
+			break;
+		case L1TF_MITIGATION_FULL:
+		case L1TF_MITIGATION_FULL_FORCE:
+			l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+			break;
+		}
+	} else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) {
+		l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+	}
+
+	if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
+	    !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+		if (!page)
+			return -ENOMEM;
+		vmx_l1d_flush_pages = page_address(page);
+
+		/*
+		 * Initialize each page with a different pattern in
+		 * order to protect against KSM in the nested
+		 * virtualization case.
+		 */
+		for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) {
+			memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1,
+			       PAGE_SIZE);
+		}
+	}
+
+	l1tf_vmx_mitigation = l1tf;
+
+	if (l1tf != VMENTER_L1D_FLUSH_NEVER)
+		static_branch_enable(&vmx_l1d_should_flush);
+	else
+		static_branch_disable(&vmx_l1d_should_flush);
+
+	if (l1tf == VMENTER_L1D_FLUSH_COND)
+		static_branch_enable(&vmx_l1d_flush_cond);
+	else
+		static_branch_disable(&vmx_l1d_flush_cond);
+	return 0;
+}
+
+static int vmentry_l1d_flush_parse(const char *s)
+{
+	unsigned int i;
+
+	if (s) {
+		for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
+			if (sysfs_streq(s, vmentry_l1d_param[i].option))
+				return vmentry_l1d_param[i].cmd;
+		}
+	}
+	return -EINVAL;
+}
+
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+	int l1tf, ret;
+
+	if (!boot_cpu_has(X86_BUG_L1TF))
+		return 0;
+
+	l1tf = vmentry_l1d_flush_parse(s);
+	if (l1tf < 0)
+		return l1tf;
+
+	/*
+	 * Has vmx_init() run already? If not then this is the pre init
+	 * parameter parsing. In that case just store the value and let
+	 * vmx_init() do the proper setup after enable_ept has been
+	 * established.
+	 */
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) {
+		vmentry_l1d_flush_param = l1tf;
+		return 0;
+	}
+
+	mutex_lock(&vmx_l1d_flush_mutex);
+	ret = vmx_setup_l1d_flush(l1tf);
+	mutex_unlock(&vmx_l1d_flush_mutex);
+	return ret;
+}
+
+static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
+{
+	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
+}
+
+static const struct kernel_param_ops vmentry_l1d_flush_ops = {
+	.set = vmentry_l1d_flush_set,
+	.get = vmentry_l1d_flush_get,
+};
+module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);
+
 struct kvm_vmx {
 	struct kvm kvm;
 
@@ -757,6 +901,11 @@ static inline int pi_test_sn(struct pi_desc *pi_desc)
 			(unsigned long *)&pi_desc->control);
 }
 
+struct vmx_msrs {
+	unsigned int		nr;
+	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
+};
+
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
@@ -790,9 +939,8 @@ struct vcpu_vmx {
 	struct loaded_vmcs   *loaded_vmcs;
 	bool                  __launched; /* temporary, used in vmx_vcpu_run */
 	struct msr_autoload {
-		unsigned nr;
-		struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
-		struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+		struct vmx_msrs guest;
+		struct vmx_msrs host;
 	} msr_autoload;
 	struct {
 		int           loaded;
@@ -2377,9 +2525,20 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 	vm_exit_controls_clearbit(vmx, exit);
 }
 
+static int find_msr(struct vmx_msrs *m, unsigned int msr)
+{
+	unsigned int i;
+
+	for (i = 0; i < m->nr; ++i) {
+		if (m->val[i].index == msr)
+			return i;
+	}
+	return -ENOENT;
+}
+
 static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 {
-	unsigned i;
+	int i;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {
@@ -2400,18 +2559,21 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 		}
 		break;
 	}
+	i = find_msr(&m->guest, msr);
+	if (i < 0)
+		goto skip_guest;
+	--m->guest.nr;
+	m->guest.val[i] = m->guest.val[m->guest.nr];
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
 
-	for (i = 0; i < m->nr; ++i)
-		if (m->guest[i].index == msr)
-			break;
-
-	if (i == m->nr)
+skip_guest:
+	i = find_msr(&m->host, msr);
+	if (i < 0)
 		return;
-	--m->nr;
-	m->guest[i] = m->guest[m->nr];
-	m->host[i] = m->host[m->nr];
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+
+	--m->host.nr;
+	m->host.val[i] = m->host.val[m->host.nr];
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
 }
 
 static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
@@ -2426,9 +2588,9 @@ static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 }
 
 static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
-				  u64 guest_val, u64 host_val)
+				  u64 guest_val, u64 host_val, bool entry_only)
 {
-	unsigned i;
+	int i, j = 0;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {
@@ -2463,24 +2625,31 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	for (i = 0; i < m->nr; ++i)
-		if (m->guest[i].index == msr)
-			break;
+	i = find_msr(&m->guest, msr);
+	if (!entry_only)
+		j = find_msr(&m->host, msr);
 
-	if (i == NR_AUTOLOAD_MSRS) {
+	if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
-	} else if (i == m->nr) {
-		++m->nr;
-		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
-		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
 	}
+	if (i < 0) {
+		i = m->guest.nr++;
+		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+	}
+	m->guest.val[i].index = msr;
+	m->guest.val[i].value = guest_val;
+
+	if (entry_only)
+		return;
 
-	m->guest[i].index = msr;
-	m->guest[i].value = guest_val;
-	m->host[i].index = msr;
-	m->host[i].value = host_val;
+	if (j < 0) {
+		j = m->host.nr++;
+		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
+	}
+	m->host.val[j].index = msr;
+	m->host.val[j].value = host_val;
 }
 
 static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
@@ -2524,7 +2693,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 			guest_efer &= ~EFER_LME;
 		if (guest_efer != host_efer)
 			add_atomic_switch_msr(vmx, MSR_EFER,
-					      guest_efer, host_efer);
+					      guest_efer, host_efer, false);
 		return false;
 	} else {
 		guest_efer &= ~ignore_bits;
@@ -3987,7 +4156,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.ia32_xss = data;
 		if (vcpu->arch.ia32_xss != host_xss)
 			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
-				vcpu->arch.ia32_xss, host_xss);
+				vcpu->arch.ia32_xss, host_xss, false);
 		else
 			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
 		break;
@@ -6274,9 +6443,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
 	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
@@ -6296,8 +6465,7 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities);
+	vmx->arch_capabilities = kvm_get_arch_capabilities();
 
 	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
 
@@ -9548,6 +9716,79 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	}
 }
 
+/*
+ * Software based L1D cache flush which is used when microcode providing
+ * the cache control MSR is not loaded.
+ *
+ * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to
+ * flush it is required to read in 64 KiB because the replacement algorithm
+ * is not exactly LRU. This could be sized at runtime via topology
+ * information but as all relevant affected CPUs have 32KiB L1D cache size
+ * there is no point in doing so.
+ */
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
+{
+	int size = PAGE_SIZE << L1D_CACHE_ORDER;
+
+	/*
+	 * This code is only executed when the the flush mode is 'cond' or
+	 * 'always'
+	 */
+	if (static_branch_likely(&vmx_l1d_flush_cond)) {
+		bool flush_l1d;
+
+		/*
+		 * Clear the per-vcpu flush bit, it gets set again
+		 * either from vcpu_run() or from one of the unsafe
+		 * VMEXIT handlers.
+		 */
+		flush_l1d = vcpu->arch.l1tf_flush_l1d;
+		vcpu->arch.l1tf_flush_l1d = false;
+
+		/*
+		 * Clear the per-cpu flush bit, it gets set again from
+		 * the interrupt handlers.
+		 */
+		flush_l1d |= kvm_get_cpu_l1tf_flush_l1d();
+		kvm_clear_cpu_l1tf_flush_l1d();
+
+		if (!flush_l1d)
+			return;
+	}
+
+	vcpu->stat.l1d_flush++;
+
+	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		return;
+	}
+
+	asm volatile(
+		/* First ensure the pages are in the TLB */
+		"xorl	%%eax, %%eax\n"
+		".Lpopulate_tlb:\n\t"
+		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$4096, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lpopulate_tlb\n\t"
+		"xorl	%%eax, %%eax\n\t"
+		"cpuid\n\t"
+		/* Now fill the cache */
+		"xorl	%%eax, %%eax\n"
+		".Lfill_cache:\n"
+		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$64, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lfill_cache\n\t"
+		"lfence\n"
+		:: [flush_pages] "r" (vmx_l1d_flush_pages),
+		    [size] "r" (size)
+		: "eax", "ebx", "ecx", "edx");
+}
+
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -9949,7 +10190,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 			clear_atomic_switch_msr(vmx, msrs[i].msr);
 		else
 			add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
-					msrs[i].host);
+					msrs[i].host, false);
 }
 
 static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
@@ -10044,6 +10285,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	evmcs_rsp = static_branch_unlikely(&enable_evmcs) ?
 		(unsigned long)&current_evmcs->host_rsp : 0;
 
+	if (static_branch_unlikely(&vmx_l1d_should_flush))
+		vmx_l1d_flush(vcpu);
+
 	asm(
 		/* Store host registers */
 		"push %%" _ASM_DX "; push %%" _ASM_BP ";"
@@ -10403,10 +10647,37 @@ free_vcpu:
 	return ERR_PTR(err);
 }
 
+#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+
 static int vmx_vm_init(struct kvm *kvm)
 {
 	if (!ple_gap)
 		kvm->arch.pause_in_guest = true;
+
+	if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+			/* 'I explicitly don't care' is set */
+			break;
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+		case L1TF_MITIGATION_FULL:
+			/*
+			 * Warn upon starting the first VM in a potentially
+			 * insecure environment.
+			 */
+			if (cpu_smt_control == CPU_SMT_ENABLED)
+				pr_warn_once(L1TF_MSG_SMT);
+			if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER)
+				pr_warn_once(L1TF_MSG_L1D);
+			break;
+		case L1TF_MITIGATION_FULL_FORCE:
+			/* Flush is enforced */
+			break;
+		}
+	}
 	return 0;
 }
 
@@ -11260,10 +11531,10 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	 * Set the MSR load/store lists to match L0's settings.
 	 */
 	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
 	set_cr4_guest_host_mask(vmx);
 
@@ -11899,6 +12170,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return ret;
 	}
 
+	/* Hide L1D cache contents from the nested guest.  */
+	vmx->vcpu.arch.l1tf_flush_l1d = true;
+
 	/*
 	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
 	 * by event injection, halt vcpu.
@@ -12419,8 +12693,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vmx_segment_cache_clear(vmx);
 
 	/* Update any VMCS fields that might have changed while L2 ran */
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 	if (vmx->hv_deadline_tsc == -1)
 		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
@@ -13137,6 +13411,51 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.enable_smi_window = enable_smi_window,
 };
 
+static void vmx_cleanup_l1d_flush(void)
+{
+	if (vmx_l1d_flush_pages) {
+		free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
+		vmx_l1d_flush_pages = NULL;
+	}
+	/* Restore state so sysfs ignores VMX */
+	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
+}
+
+static void vmx_exit(void)
+{
+#ifdef CONFIG_KEXEC_CORE
+	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
+	synchronize_rcu();
+#endif
+
+	kvm_exit();
+
+#if IS_ENABLED(CONFIG_HYPERV)
+	if (static_branch_unlikely(&enable_evmcs)) {
+		int cpu;
+		struct hv_vp_assist_page *vp_ap;
+		/*
+		 * Reset everything to support using non-enlightened VMCS
+		 * access later (e.g. when we reload the module with
+		 * enlightened_vmcs=0)
+		 */
+		for_each_online_cpu(cpu) {
+			vp_ap =	hv_get_vp_assist_page(cpu);
+
+			if (!vp_ap)
+				continue;
+
+			vp_ap->current_nested_vmcs = 0;
+			vp_ap->enlighten_vmentry = 0;
+		}
+
+		static_branch_disable(&enable_evmcs);
+	}
+#endif
+	vmx_cleanup_l1d_flush();
+}
+module_exit(vmx_exit);
+
 static int __init vmx_init(void)
 {
 	int r;
@@ -13171,10 +13490,25 @@ static int __init vmx_init(void)
 #endif
 
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
-                     __alignof__(struct vcpu_vmx), THIS_MODULE);
+		     __alignof__(struct vcpu_vmx), THIS_MODULE);
 	if (r)
 		return r;
 
+	/*
+	 * Must be called after kvm_init() so enable_ept is properly set
+	 * up. Hand the parameter mitigation value in which was stored in
+	 * the pre module init parser. If no parameter was given, it will
+	 * contain 'auto' which will be turned into the default 'cond'
+	 * mitigation mode.
+	 */
+	if (boot_cpu_has(X86_BUG_L1TF)) {
+		r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
+		if (r) {
+			vmx_exit();
+			return r;
+		}
+	}
+
 #ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);
@@ -13183,39 +13517,4 @@ static int __init vmx_init(void)
 
 	return 0;
 }
-
-static void __exit vmx_exit(void)
-{
-#ifdef CONFIG_KEXEC_CORE
-	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
-	synchronize_rcu();
-#endif
-
-	kvm_exit();
-
-#if IS_ENABLED(CONFIG_HYPERV)
-	if (static_branch_unlikely(&enable_evmcs)) {
-		int cpu;
-		struct hv_vp_assist_page *vp_ap;
-		/*
-		 * Reset everything to support using non-enlightened VMCS
-		 * access later (e.g. when we reload the module with
-		 * enlightened_vmcs=0)
-		 */
-		for_each_online_cpu(cpu) {
-			vp_ap =	hv_get_vp_assist_page(cpu);
-
-			if (!vp_ap)
-				continue;
-
-			vp_ap->current_nested_vmcs = 0;
-			vp_ap->enlighten_vmentry = 0;
-		}
-
-		static_branch_disable(&enable_evmcs);
-	}
-#endif
-}
-
-module_init(vmx_init)
-module_exit(vmx_exit)
+module_init(vmx_init);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2b812b3c5088..a5caa5e5480c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -195,6 +195,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "irq_injections", VCPU_STAT(irq_injections) },
 	{ "nmi_injections", VCPU_STAT(nmi_injections) },
 	{ "req_event", VCPU_STAT(req_event) },
+	{ "l1d_flush", VCPU_STAT(l1d_flush) },
 	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
 	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
 	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
@@ -1102,11 +1103,35 @@ static u32 msr_based_features[] = {
 
 static unsigned int num_msr_based_features;
 
+u64 kvm_get_arch_capabilities(void)
+{
+	u64 data;
+
+	rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
+
+	/*
+	 * If we're doing cache flushes (either "always" or "cond")
+	 * we will do one whenever the guest does a vmlaunch/vmresume.
+	 * If an outer hypervisor is doing the cache flush for us
+	 * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that
+	 * capability to the guest too, and if EPT is disabled we're not
+	 * vulnerable.  Overall, only VMENTER_L1D_FLUSH_NEVER will
+	 * require a nested hypervisor to do a flush of its own.
+	 */
+	if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
+		data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;
+
+	return data;
+}
+EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
+
 static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
 {
 	switch (msr->index) {
-	case MSR_IA32_UCODE_REV:
 	case MSR_IA32_ARCH_CAPABILITIES:
+		msr->data = kvm_get_arch_capabilities();
+		break;
+	case MSR_IA32_UCODE_REV:
 		rdmsrl_safe(msr->index, &msr->data);
 		break;
 	default:
@@ -4876,6 +4901,9 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v
 int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
 				unsigned int bytes, struct x86_exception *exception)
 {
+	/* kvm_write_guest_virt_system can pull in tons of pages. */
+	vcpu->arch.l1tf_flush_l1d = true;
+
 	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
 					   PFERR_WRITE_MASK, exception);
 }
@@ -6052,6 +6080,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 	bool writeback = true;
 	bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 
+	vcpu->arch.l1tf_flush_l1d = true;
+
 	/*
 	 * Clear write_fault_to_shadow_pgtable here to ensure it is
 	 * never reused.
@@ -7581,6 +7611,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
 		if (kvm_vcpu_running(vcpu)) {
@@ -8700,6 +8731,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
+	vcpu->arch.l1tf_flush_l1d = true;
 	kvm_x86_ops->sched_in(vcpu, cpu);
 }
 
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 298ef1479240..3b24dc05251c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -256,7 +256,7 @@ ENTRY(__memcpy_mcsafe)
 
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
-	xorq %rax, %rax
+	xorl %eax, %eax
 	ret
 ENDPROC(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 2f3c9196b834..a12afff146d1 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -111,6 +111,8 @@ static struct addr_marker address_markers[] = {
 	[END_OF_SPACE_NR]	= { -1,			NULL }
 };
 
+#define INIT_PGD	((pgd_t *) &init_top_pgt)
+
 #else /* CONFIG_X86_64 */
 
 enum address_markers_idx {
@@ -121,6 +123,9 @@ enum address_markers_idx {
 #ifdef CONFIG_HIGHMEM
 	PKMAP_BASE_NR,
 #endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	LDT_NR,
+#endif
 	CPU_ENTRY_AREA_NR,
 	FIXADDR_START_NR,
 	END_OF_SPACE_NR,
@@ -134,11 +139,16 @@ static struct addr_marker address_markers[] = {
 #ifdef CONFIG_HIGHMEM
 	[PKMAP_BASE_NR]		= { 0UL,		"Persistent kmap() Area" },
 #endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	[LDT_NR]		= { 0UL,		"LDT remap" },
+#endif
 	[CPU_ENTRY_AREA_NR]	= { 0UL,		"CPU entry area" },
 	[FIXADDR_START_NR]	= { 0UL,		"Fixmap area" },
 	[END_OF_SPACE_NR]	= { -1,			NULL }
 };
 
+#define INIT_PGD	(swapper_pg_dir)
+
 #endif /* !CONFIG_X86_64 */
 
 /* Multipliers for offsets within the PTEs */
@@ -496,11 +506,7 @@ static inline bool is_hypervisor_range(int idx)
 static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 				       bool checkwx, bool dmesg)
 {
-#ifdef CONFIG_X86_64
-	pgd_t *start = (pgd_t *) &init_top_pgt;
-#else
-	pgd_t *start = swapper_pg_dir;
-#endif
+	pgd_t *start = INIT_PGD;
 	pgprotval_t prot, eff;
 	int i;
 	struct pg_state st = {};
@@ -563,12 +569,13 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
 }
 EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
 
-static void ptdump_walk_user_pgd_level_checkwx(void)
+void ptdump_walk_user_pgd_level_checkwx(void)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
-	pgd_t *pgd = (pgd_t *) &init_top_pgt;
+	pgd_t *pgd = INIT_PGD;
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!(__supported_pte_mask & _PAGE_NX) ||
+	    !static_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pr_info("x86/mm: Checking user space page tables\n");
@@ -580,7 +587,6 @@ static void ptdump_walk_user_pgd_level_checkwx(void)
 void ptdump_walk_pgd_level_checkwx(void)
 {
 	ptdump_walk_pgd_level_core(NULL, NULL, true, false);
-	ptdump_walk_user_pgd_level_checkwx();
 }
 
 static int __init pt_dump_init(void)
@@ -609,6 +615,9 @@ static int __init pt_dump_init(void)
 # endif
 	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
 	address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
+# ifdef CONFIG_MODIFY_LDT_SYSCALL
+	address_markers[LDT_NR].start_address = LDT_BASE_ADDR;
+# endif
 #endif
 	return 0;
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2aafa6ab6103..db1c042e9853 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -317,8 +317,6 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
-	WARN_ON_ONCE(in_nmi());
-
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index cee58a972cb2..156ed8154af8 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -4,6 +4,8 @@
 #include <linux/swap.h>
 #include <linux/memblock.h>
 #include <linux/bootmem.h>	/* for max_low_pfn */
+#include <linux/swapfile.h>
+#include <linux/swapops.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -773,13 +775,44 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	}
 }
 
+/*
+ * begin/end can be in the direct map or the "high kernel mapping"
+ * used for the kernel image only.  free_init_pages() will do the
+ * right thing for either kind of address.
+ */
+void free_kernel_image_pages(void *begin, void *end)
+{
+	unsigned long begin_ul = (unsigned long)begin;
+	unsigned long end_ul = (unsigned long)end;
+	unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT;
+
+
+	free_init_pages("unused kernel image", begin_ul, end_ul);
+
+	/*
+	 * PTI maps some of the kernel into userspace.  For performance,
+	 * this includes some kernel areas that do not contain secrets.
+	 * Those areas might be adjacent to the parts of the kernel image
+	 * being freed, which may contain secrets.  Remove the "high kernel
+	 * image mapping" for these freed areas, ensuring they are not even
+	 * potentially vulnerable to Meltdown regardless of the specific
+	 * optimizations PTI is currently using.
+	 *
+	 * The "noalias" prevents unmapping the direct map alias which is
+	 * needed to access the freed pages.
+	 *
+	 * This is only valid for 64bit kernels. 32bit has only one mapping
+	 * which can't be treated in this way for obvious reasons.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI))
+		set_memory_np_noalias(begin_ul, len_pages);
+}
+
 void __ref free_initmem(void)
 {
 	e820__reallocate_tables();
 
-	free_init_pages("unused kernel",
-			(unsigned long)(&__init_begin),
-			(unsigned long)(&__init_end));
+	free_kernel_image_pages(&__init_begin, &__init_end);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -880,3 +913,24 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
 	__cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
 	__pte2cachemode_tbl[entry] = cache;
 }
+
+unsigned long max_swapfile_size(void)
+{
+	unsigned long pages;
+
+	pages = generic_max_swapfile_size();
+
+	if (boot_cpu_has_bug(X86_BUG_L1TF)) {
+		/* Limit the swap file size to MAX_PA/2 for L1TF workaround */
+		unsigned long l1tf_limit = l1tf_pfn_limit() + 1;
+		/*
+		 * We encode swap offsets also with 3 bits below those for pfn
+		 * which makes the usable limit higher.
+		 */
+#if CONFIG_PGTABLE_LEVELS > 2
+		l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
+#endif
+		pages = min_t(unsigned long, l1tf_limit, pages);
+	}
+	return pages;
+}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a688617c727e..dd519f372169 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1283,20 +1283,10 @@ void mark_rodata_ro(void)
 	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
 #endif
 
-	free_init_pages("unused kernel",
-			(unsigned long) __va(__pa_symbol(text_end)),
-			(unsigned long) __va(__pa_symbol(rodata_start)));
-	free_init_pages("unused kernel",
-			(unsigned long) __va(__pa_symbol(rodata_end)),
-			(unsigned long) __va(__pa_symbol(_sdata)));
+	free_kernel_image_pages((void *)text_end, (void *)rodata_start);
+	free_kernel_image_pages((void *)rodata_end, (void *)_sdata);
 
 	debug_checkwx();
-
-	/*
-	 * Do this after all of the manipulation of the
-	 * kernel text page tables are complete.
-	 */
-	pti_clone_kernel_text();
 }
 
 int kern_addr_valid(unsigned long addr)
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 7c8686709636..79eb55ce69a9 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -126,24 +126,29 @@ static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr)
 
 static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old)
 {
+	pmd_t new_pmd;
 	pmdval_t v = pmd_val(*pmd);
 	if (clear) {
-		*old = v & _PAGE_PRESENT;
-		v &= ~_PAGE_PRESENT;
-	} else	/* presume this has been called with clear==true previously */
-		v |= *old;
-	set_pmd(pmd, __pmd(v));
+		*old = v;
+		new_pmd = pmd_mknotpresent(*pmd);
+	} else {
+		/* Presume this has been called with clear==true previously */
+		new_pmd = __pmd(*old);
+	}
+	set_pmd(pmd, new_pmd);
 }
 
 static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
 {
 	pteval_t v = pte_val(*pte);
 	if (clear) {
-		*old = v & _PAGE_PRESENT;
-		v &= ~_PAGE_PRESENT;
-	} else	/* presume this has been called with clear==true previously */
-		v |= *old;
-	set_pte_atomic(pte, __pte(v));
+		*old = v;
+		/* Nothing should care about address */
+		pte_clear(&init_mm, 0, pte);
+	} else {
+		/* Presume this has been called with clear==true previously */
+		set_pte_atomic(pte, __pte(*old));
+	}
 }
 
 static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 48c591251600..f40ab8185d94 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -240,3 +240,24 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t count)
 
 	return phys_addr_valid(addr + count - 1);
 }
+
+/*
+ * Only allow root to set high MMIO mappings to PROT_NONE.
+ * This prevents an unpriv. user to set them to PROT_NONE and invert
+ * them, then pointing to valid memory for L1TF speculation.
+ *
+ * Note: for locked down kernels may want to disable the root override.
+ */
+bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return true;
+	if (!__pte_needs_invert(pgprot_val(prot)))
+		return true;
+	/* If it's real memory always allow */
+	if (pfn_valid(pfn))
+		return true;
+	if (pfn > l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN))
+		return false;
+	return true;
+}
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 34a2a3bfde9c..b54d52a2d00a 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -61,7 +61,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
 	eb->nid = nid;
 
 	if (emu_nid_to_phys[nid] == NUMA_NO_NODE)
-		emu_nid_to_phys[nid] = nid;
+		emu_nid_to_phys[nid] = pb->nid;
 
 	pb->start += size;
 	if (pb->start >= pb->end) {
@@ -198,40 +198,73 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 	return end;
 }
 
+static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes)
+{
+	unsigned long max_pfn = PHYS_PFN(max_addr);
+	unsigned long base_pfn = PHYS_PFN(base);
+	unsigned long hole_pfns = PHYS_PFN(hole);
+
+	return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes);
+}
+
 /*
  * Sets up fake nodes of `size' interleaved over physical nodes ranging from
  * `addr' to `max_addr'.
  *
  * Returns zero on success or negative on error.
  */
-static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
 					      struct numa_meminfo *pi,
-					      u64 addr, u64 max_addr, u64 size)
+					      u64 addr, u64 max_addr, u64 size,
+					      int nr_nodes, struct numa_memblk *pblk,
+					      int nid)
 {
 	nodemask_t physnode_mask = numa_nodes_parsed;
+	int i, ret, uniform = 0;
 	u64 min_size;
-	int nid = 0;
-	int i, ret;
 
-	if (!size)
+	if ((!size && !nr_nodes) || (nr_nodes && !pblk))
 		return -1;
+
 	/*
-	 * The limit on emulated nodes is MAX_NUMNODES, so the size per node is
-	 * increased accordingly if the requested size is too small.  This
-	 * creates a uniform distribution of node sizes across the entire
-	 * machine (but not necessarily over physical nodes).
+	 * In the 'uniform' case split the passed in physical node by
+	 * nr_nodes, in the non-uniform case, ignore the passed in
+	 * physical block and try to create nodes of at least size
+	 * @size.
+	 *
+	 * In the uniform case, split the nodes strictly by physical
+	 * capacity, i.e. ignore holes. In the non-uniform case account
+	 * for holes and treat @size as a minimum floor.
 	 */
-	min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES;
-	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
-	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
-		min_size = (min_size + FAKE_NODE_MIN_SIZE) &
-						FAKE_NODE_MIN_HASH_MASK;
+	if (!nr_nodes)
+		nr_nodes = MAX_NUMNODES;
+	else {
+		nodes_clear(physnode_mask);
+		node_set(pblk->nid, physnode_mask);
+		uniform = 1;
+	}
+
+	if (uniform) {
+		min_size = uniform_size(max_addr, addr, 0, nr_nodes);
+		size = min_size;
+	} else {
+		/*
+		 * The limit on emulated nodes is MAX_NUMNODES, so the
+		 * size per node is increased accordingly if the
+		 * requested size is too small.  This creates a uniform
+		 * distribution of node sizes across the entire machine
+		 * (but not necessarily over physical nodes).
+		 */
+		min_size = uniform_size(max_addr, addr,
+				mem_hole_size(addr, max_addr), nr_nodes);
+	}
+	min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE);
 	if (size < min_size) {
 		pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
 			size >> 20, min_size >> 20);
 		size = min_size;
 	}
-	size &= FAKE_NODE_MIN_HASH_MASK;
+	size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE);
 
 	/*
 	 * Fill physical nodes with fake nodes of size until there is no memory
@@ -248,10 +281,14 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 				node_clear(i, physnode_mask);
 				continue;
 			}
+
 			start = pi->blk[phys_blk].start;
 			limit = pi->blk[phys_blk].end;
 
-			end = find_end_of_node(start, limit, size);
+			if (uniform)
+				end = start + size;
+			else
+				end = find_end_of_node(start, limit, size);
 			/*
 			 * If there won't be at least FAKE_NODE_MIN_SIZE of
 			 * non-reserved memory in ZONE_DMA32 for the next node,
@@ -266,7 +303,8 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 			 * next node, this one must extend to the end of the
 			 * physical node.
 			 */
-			if (limit - end - mem_hole_size(end, limit) < size)
+			if ((limit - end - mem_hole_size(end, limit) < size)
+					&& !uniform)
 				end = limit;
 
 			ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
@@ -276,7 +314,15 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 				return ret;
 		}
 	}
-	return 0;
+	return nid;
+}
+
+static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+					      struct numa_meminfo *pi,
+					      u64 addr, u64 max_addr, u64 size)
+{
+	return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
+			0, NULL, NUMA_NO_NODE);
 }
 
 int __init setup_emu2phys_nid(int *dfl_phys_nid)
@@ -346,7 +392,28 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	 * the fixed node size.  Otherwise, if it is just a single number N,
 	 * split the system RAM into N fake nodes.
 	 */
-	if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
+	if (strchr(emu_cmdline, 'U')) {
+		nodemask_t physnode_mask = numa_nodes_parsed;
+		unsigned long n;
+		int nid = 0;
+
+		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
+		ret = -1;
+		for_each_node_mask(i, physnode_mask) {
+			ret = split_nodes_size_interleave_uniform(&ei, &pi,
+					pi.blk[i].start, pi.blk[i].end, 0,
+					n, &pi.blk[i], nid);
+			if (ret < 0)
+				break;
+			if (ret < n) {
+				pr_info("%s: phys: %d only got %d of %ld nodes, failing\n",
+						__func__, i, ret, n);
+				ret = -1;
+				break;
+			}
+			nid = ret;
+		}
+	} else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
 		u64 size;
 
 		size = memparse(emu_cmdline, &emu_cmdline);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 3bded76e8d5c..8d6c34fe49be 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -53,6 +53,7 @@ static DEFINE_SPINLOCK(cpa_lock);
 #define CPA_FLUSHTLB 1
 #define CPA_ARRAY 2
 #define CPA_PAGES_ARRAY 4
+#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
 
 #ifdef CONFIG_PROC_FS
 static unsigned long direct_pages_count[PG_LEVEL_NUM];
@@ -1014,8 +1015,8 @@ static long populate_pmd(struct cpa_data *cpa,
 
 		pmd = pmd_offset(pud, start);
 
-		set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
-				   massage_pgprot(pmd_pgprot)));
+		set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn,
+					canon_pgprot(pmd_pgprot))));
 
 		start	  += PMD_SIZE;
 		cpa->pfn  += PMD_SIZE >> PAGE_SHIFT;
@@ -1087,8 +1088,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d,
 	 * Map everything starting from the Gb boundary, possibly with 1G pages
 	 */
 	while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) {
-		set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
-				   massage_pgprot(pud_pgprot)));
+		set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn,
+				   canon_pgprot(pud_pgprot))));
 
 		start	  += PUD_SIZE;
 		cpa->pfn  += PUD_SIZE >> PAGE_SHIFT;
@@ -1486,6 +1487,9 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	/* No alias checking for _NX bit modifications */
 	checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;
+	/* Has caller explicitly disabled alias checking? */
+	if (in_flag & CPA_NO_CHECK_ALIAS)
+		checkalias = 0;
 
 	ret = __change_page_attr_set_clr(&cpa, checkalias);
 
@@ -1772,6 +1776,15 @@ int set_memory_np(unsigned long addr, int numpages)
 	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
 }
 
+int set_memory_np_noalias(unsigned long addr, int numpages)
+{
+	int cpa_flags = CPA_NO_CHECK_ALIAS;
+
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+					__pgprot(_PAGE_PRESENT), 0,
+					cpa_flags, NULL);
+}
+
 int set_memory_4k(unsigned long addr, int numpages)
 {
 	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
@@ -1784,6 +1797,12 @@ int set_memory_nonglobal(unsigned long addr, int numpages)
 				      __pgprot(_PAGE_GLOBAL), 0);
 }
 
+int set_memory_global(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages,
+				    __pgprot(_PAGE_GLOBAL), 0);
+}
+
 static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 {
 	struct cpa_data cpa;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 47b5951e592b..3ef095c70ae3 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -182,6 +182,14 @@ static void pgd_dtor(pgd_t *pgd)
  */
 #define PREALLOCATED_PMDS	UNSHARED_PTRS_PER_PGD
 
+/*
+ * We allocate separate PMDs for the kernel part of the user page-table
+ * when PTI is enabled. We need them to map the per-process LDT into the
+ * user-space page-table.
+ */
+#define PREALLOCATED_USER_PMDS	 (static_cpu_has(X86_FEATURE_PTI) ? \
+					KERNEL_PGD_PTRS : 0)
+
 void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 {
 	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
@@ -202,14 +210,14 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 
 /* No need to prepopulate any pagetable entries in non-PAE modes. */
 #define PREALLOCATED_PMDS	0
-
+#define PREALLOCATED_USER_PMDS	 0
 #endif	/* CONFIG_X86_PAE */
 
-static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
+static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
 {
 	int i;
 
-	for(i = 0; i < PREALLOCATED_PMDS; i++)
+	for (i = 0; i < count; i++)
 		if (pmds[i]) {
 			pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
 			free_page((unsigned long)pmds[i]);
@@ -217,7 +225,7 @@ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
 		}
 }
 
-static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
+static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
 {
 	int i;
 	bool failed = false;
@@ -226,7 +234,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
 	if (mm == &init_mm)
 		gfp &= ~__GFP_ACCOUNT;
 
-	for(i = 0; i < PREALLOCATED_PMDS; i++) {
+	for (i = 0; i < count; i++) {
 		pmd_t *pmd = (pmd_t *)__get_free_page(gfp);
 		if (!pmd)
 			failed = true;
@@ -241,7 +249,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
 	}
 
 	if (failed) {
-		free_pmds(mm, pmds);
+		free_pmds(mm, pmds, count);
 		return -ENOMEM;
 	}
 
@@ -254,23 +262,38 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
  * preallocate which never got a corresponding vma will need to be
  * freed manually.
  */
+static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp)
+{
+	pgd_t pgd = *pgdp;
+
+	if (pgd_val(pgd) != 0) {
+		pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+
+		*pgdp = native_make_pgd(0);
+
+		paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
+		pmd_free(mm, pmd);
+		mm_dec_nr_pmds(mm);
+	}
+}
+
 static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
 {
 	int i;
 
-	for(i = 0; i < PREALLOCATED_PMDS; i++) {
-		pgd_t pgd = pgdp[i];
+	for (i = 0; i < PREALLOCATED_PMDS; i++)
+		mop_up_one_pmd(mm, &pgdp[i]);
 
-		if (pgd_val(pgd) != 0) {
-			pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
 
-			pgdp[i] = native_make_pgd(0);
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
 
-			paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
-			pmd_free(mm, pmd);
-			mm_dec_nr_pmds(mm);
-		}
-	}
+	pgdp = kernel_to_user_pgdp(pgdp);
+
+	for (i = 0; i < PREALLOCATED_USER_PMDS; i++)
+		mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]);
+#endif
 }
 
 static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
@@ -296,6 +319,38 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
 	}
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+				     pgd_t *k_pgd, pmd_t *pmds[])
+{
+	pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	p4d_t *u_p4d;
+	pud_t *u_pud;
+	int i;
+
+	u_p4d = p4d_offset(u_pgd, 0);
+	u_pud = pud_offset(u_p4d, 0);
+
+	s_pgd += KERNEL_PGD_BOUNDARY;
+	u_pud += KERNEL_PGD_BOUNDARY;
+
+	for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) {
+		pmd_t *pmd = pmds[i];
+
+		memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd),
+		       sizeof(pmd_t) * PTRS_PER_PMD);
+
+		pud_populate(mm, u_pud, pmd);
+	}
+
+}
+#else
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+				     pgd_t *k_pgd, pmd_t *pmds[])
+{
+}
+#endif
 /*
  * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also
  * assumes that pgd should be in one page.
@@ -329,9 +384,6 @@ static int __init pgd_cache_init(void)
 	 */
 	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
 				      SLAB_PANIC, NULL);
-	if (!pgd_cache)
-		return -ENOMEM;
-
 	return 0;
 }
 core_initcall(pgd_cache_init);
@@ -343,7 +395,8 @@ static inline pgd_t *_pgd_alloc(void)
 	 * We allocate one page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return (pgd_t *)__get_free_page(PGALLOC_GFP);
+		return (pgd_t *)__get_free_pages(PGALLOC_GFP,
+						 PGD_ALLOCATION_ORDER);
 
 	/*
 	 * Now PAE kernel is not running as a Xen domain. We can allocate
@@ -355,7 +408,7 @@ static inline pgd_t *_pgd_alloc(void)
 static inline void _pgd_free(pgd_t *pgd)
 {
 	if (!SHARED_KERNEL_PMD)
-		free_page((unsigned long)pgd);
+		free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
 	else
 		kmem_cache_free(pgd_cache, pgd);
 }
@@ -375,6 +428,7 @@ static inline void _pgd_free(pgd_t *pgd)
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd;
+	pmd_t *u_pmds[PREALLOCATED_USER_PMDS];
 	pmd_t *pmds[PREALLOCATED_PMDS];
 
 	pgd = _pgd_alloc();
@@ -384,12 +438,15 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	mm->pgd = pgd;
 
-	if (preallocate_pmds(mm, pmds) != 0)
+	if (preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0)
 		goto out_free_pgd;
 
-	if (paravirt_pgd_alloc(mm) != 0)
+	if (preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0)
 		goto out_free_pmds;
 
+	if (paravirt_pgd_alloc(mm) != 0)
+		goto out_free_user_pmds;
+
 	/*
 	 * Make sure that pre-populating the pmds is atomic with
 	 * respect to anything walking the pgd_list, so that they
@@ -399,13 +456,16 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	pgd_ctor(mm, pgd);
 	pgd_prepopulate_pmd(mm, pgd, pmds);
+	pgd_prepopulate_user_pmd(mm, pgd, u_pmds);
 
 	spin_unlock(&pgd_lock);
 
 	return pgd;
 
+out_free_user_pmds:
+	free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS);
 out_free_pmds:
-	free_pmds(mm, pmds);
+	free_pmds(mm, pmds, PREALLOCATED_PMDS);
 out_free_pgd:
 	_pgd_free(pgd);
 out:
@@ -719,28 +779,50 @@ int pmd_clear_huge(pmd_t *pmd)
 	return 0;
 }
 
+#ifdef CONFIG_X86_64
 /**
  * pud_free_pmd_page - Clear pud entry and free pmd page.
  * @pud: Pointer to a PUD.
+ * @addr: Virtual address associated with pud.
  *
- * Context: The pud range has been unmaped and TLB purged.
+ * Context: The pud range has been unmapped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ *
+ * NOTE: Callers must allow a single page allocation.
  */
-int pud_free_pmd_page(pud_t *pud)
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
-	pmd_t *pmd;
+	pmd_t *pmd, *pmd_sv;
+	pte_t *pte;
 	int i;
 
 	if (pud_none(*pud))
 		return 1;
 
 	pmd = (pmd_t *)pud_page_vaddr(*pud);
+	pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL);
+	if (!pmd_sv)
+		return 0;
 
-	for (i = 0; i < PTRS_PER_PMD; i++)
-		if (!pmd_free_pte_page(&pmd[i]))
-			return 0;
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd_sv[i] = pmd[i];
+		if (!pmd_none(pmd[i]))
+			pmd_clear(&pmd[i]);
+	}
 
 	pud_clear(pud);
+
+	/* INVLPG to clear all paging-structure caches */
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(pmd_sv[i])) {
+			pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
+			free_page((unsigned long)pte);
+		}
+	}
+
+	free_page((unsigned long)pmd_sv);
 	free_page((unsigned long)pmd);
 
 	return 1;
@@ -749,11 +831,12 @@ int pud_free_pmd_page(pud_t *pud)
 /**
  * pmd_free_pte_page - Clear pmd entry and free pte page.
  * @pmd: Pointer to a PMD.
+ * @addr: Virtual address associated with pmd.
  *
- * Context: The pmd range has been unmaped and TLB purged.
+ * Context: The pmd range has been unmapped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
  */
-int pmd_free_pte_page(pmd_t *pmd)
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	pte_t *pte;
 
@@ -762,8 +845,30 @@ int pmd_free_pte_page(pmd_t *pmd)
 
 	pte = (pte_t *)pmd_page_vaddr(*pmd);
 	pmd_clear(pmd);
+
+	/* INVLPG to clear all paging-structure caches */
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
 	free_page((unsigned long)pte);
 
 	return 1;
 }
+
+#else /* !CONFIG_X86_64 */
+
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
+{
+	return pud_none(*pud);
+}
+
+/*
+ * Disable free page handling on x86-PAE. This assures that ioremap()
+ * does not update sync'd pmd entries. See vmalloc_sync_one().
+ */
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+{
+	return pmd_none(*pmd);
+}
+
+#endif /* CONFIG_X86_64 */
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 4d418e705878..31341ae7309f 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -45,6 +45,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
+#include <asm/sections.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt)     "Kernel/User page tables isolation: " fmt
@@ -54,6 +55,16 @@
 #define __GFP_NOTRACK	0
 #endif
 
+/*
+ * Define the page-table levels we clone for user-space on 32
+ * and 64 bit.
+ */
+#ifdef CONFIG_X86_64
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PMD
+#else
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PTE
+#endif
+
 static void __init pti_print_if_insecure(const char *reason)
 {
 	if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
@@ -117,7 +128,7 @@ enable:
 	setup_force_cpu_cap(X86_FEATURE_PTI);
 }
 
-pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 {
 	/*
 	 * Changes to the high (kernel) portion of the kernelmode page
@@ -176,7 +187,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
 
 	if (pgd_none(*pgd)) {
 		unsigned long new_p4d_page = __get_free_page(gfp);
-		if (!new_p4d_page)
+		if (WARN_ON_ONCE(!new_p4d_page))
 			return NULL;
 
 		set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
@@ -195,13 +206,17 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
 static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 {
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
-	p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
+	p4d_t *p4d;
 	pud_t *pud;
 
+	p4d = pti_user_pagetable_walk_p4d(address);
+	if (!p4d)
+		return NULL;
+
 	BUILD_BUG_ON(p4d_large(*p4d) != 0);
 	if (p4d_none(*p4d)) {
 		unsigned long new_pud_page = __get_free_page(gfp);
-		if (!new_pud_page)
+		if (WARN_ON_ONCE(!new_pud_page))
 			return NULL;
 
 		set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
@@ -215,7 +230,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	}
 	if (pud_none(*pud)) {
 		unsigned long new_pmd_page = __get_free_page(gfp);
-		if (!new_pmd_page)
+		if (WARN_ON_ONCE(!new_pmd_page))
 			return NULL;
 
 		set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
@@ -224,7 +239,6 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	return pmd_offset(pud, address);
 }
 
-#ifdef CONFIG_X86_VSYSCALL_EMULATION
 /*
  * Walk the shadow copy of the page tables (optionally) trying to allocate
  * page table pages on the way down.  Does not support large pages.
@@ -237,9 +251,13 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 {
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
-	pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
+	pmd_t *pmd;
 	pte_t *pte;
 
+	pmd = pti_user_pagetable_walk_pmd(address);
+	if (!pmd)
+		return NULL;
+
 	/* We can't do anything sensible if we hit a large mapping. */
 	if (pmd_large(*pmd)) {
 		WARN_ON(1);
@@ -262,6 +280,7 @@ static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 	return pte;
 }
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 static void __init pti_setup_vsyscall(void)
 {
 	pte_t *pte, *target_pte;
@@ -282,8 +301,14 @@ static void __init pti_setup_vsyscall(void)
 static void __init pti_setup_vsyscall(void) { }
 #endif
 
+enum pti_clone_level {
+	PTI_CLONE_PMD,
+	PTI_CLONE_PTE,
+};
+
 static void
-pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+pti_clone_pgtable(unsigned long start, unsigned long end,
+		  enum pti_clone_level level)
 {
 	unsigned long addr;
 
@@ -291,59 +316,105 @@ pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
 	 * Clone the populated PMDs which cover start to end. These PMD areas
 	 * can have holes.
 	 */
-	for (addr = start; addr < end; addr += PMD_SIZE) {
+	for (addr = start; addr < end;) {
+		pte_t *pte, *target_pte;
 		pmd_t *pmd, *target_pmd;
 		pgd_t *pgd;
 		p4d_t *p4d;
 		pud_t *pud;
 
+		/* Overflow check */
+		if (addr < start)
+			break;
+
 		pgd = pgd_offset_k(addr);
 		if (WARN_ON(pgd_none(*pgd)))
 			return;
 		p4d = p4d_offset(pgd, addr);
 		if (WARN_ON(p4d_none(*p4d)))
 			return;
+
 		pud = pud_offset(p4d, addr);
-		if (pud_none(*pud))
+		if (pud_none(*pud)) {
+			addr += PUD_SIZE;
 			continue;
+		}
+
 		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd))
+		if (pmd_none(*pmd)) {
+			addr += PMD_SIZE;
 			continue;
+		}
 
-		target_pmd = pti_user_pagetable_walk_pmd(addr);
-		if (WARN_ON(!target_pmd))
-			return;
-
-		/*
-		 * Only clone present PMDs.  This ensures only setting
-		 * _PAGE_GLOBAL on present PMDs.  This should only be
-		 * called on well-known addresses anyway, so a non-
-		 * present PMD would be a surprise.
-		 */
-		if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
-			return;
-
-		/*
-		 * Setting 'target_pmd' below creates a mapping in both
-		 * the user and kernel page tables.  It is effectively
-		 * global, so set it as global in both copies.  Note:
-		 * the X86_FEATURE_PGE check is not _required_ because
-		 * the CPU ignores _PAGE_GLOBAL when PGE is not
-		 * supported.  The check keeps consistentency with
-		 * code that only set this bit when supported.
-		 */
-		if (boot_cpu_has(X86_FEATURE_PGE))
-			*pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
-
-		/*
-		 * Copy the PMD.  That is, the kernelmode and usermode
-		 * tables will share the last-level page tables of this
-		 * address range
-		 */
-		*target_pmd = pmd_clear_flags(*pmd, clear);
+		if (pmd_large(*pmd) || level == PTI_CLONE_PMD) {
+			target_pmd = pti_user_pagetable_walk_pmd(addr);
+			if (WARN_ON(!target_pmd))
+				return;
+
+			/*
+			 * Only clone present PMDs.  This ensures only setting
+			 * _PAGE_GLOBAL on present PMDs.  This should only be
+			 * called on well-known addresses anyway, so a non-
+			 * present PMD would be a surprise.
+			 */
+			if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
+				return;
+
+			/*
+			 * Setting 'target_pmd' below creates a mapping in both
+			 * the user and kernel page tables.  It is effectively
+			 * global, so set it as global in both copies.  Note:
+			 * the X86_FEATURE_PGE check is not _required_ because
+			 * the CPU ignores _PAGE_GLOBAL when PGE is not
+			 * supported.  The check keeps consistentency with
+			 * code that only set this bit when supported.
+			 */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
+
+			/*
+			 * Copy the PMD.  That is, the kernelmode and usermode
+			 * tables will share the last-level page tables of this
+			 * address range
+			 */
+			*target_pmd = *pmd;
+
+			addr += PMD_SIZE;
+
+		} else if (level == PTI_CLONE_PTE) {
+
+			/* Walk the page-table down to the pte level */
+			pte = pte_offset_kernel(pmd, addr);
+			if (pte_none(*pte)) {
+				addr += PAGE_SIZE;
+				continue;
+			}
+
+			/* Only clone present PTEs */
+			if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT)))
+				return;
+
+			/* Allocate PTE in the user page-table */
+			target_pte = pti_user_pagetable_walk_pte(addr);
+			if (WARN_ON(!target_pte))
+				return;
+
+			/* Set GLOBAL bit in both PTEs */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pte = pte_set_flags(*pte, _PAGE_GLOBAL);
+
+			/* Clone the PTE */
+			*target_pte = *pte;
+
+			addr += PAGE_SIZE;
+
+		} else {
+			BUG();
+		}
 	}
 }
 
+#ifdef CONFIG_X86_64
 /*
  * Clone a single p4d (i.e. a top-level entry on 4-level systems and a
  * next-level entry on 5-level systems.
@@ -354,6 +425,9 @@ static void __init pti_clone_p4d(unsigned long addr)
 	pgd_t *kernel_pgd;
 
 	user_p4d = pti_user_pagetable_walk_p4d(addr);
+	if (!user_p4d)
+		return;
+
 	kernel_pgd = pgd_offset_k(addr);
 	kernel_p4d = p4d_offset(kernel_pgd, addr);
 	*user_p4d = *kernel_p4d;
@@ -367,6 +441,25 @@ static void __init pti_clone_user_shared(void)
 	pti_clone_p4d(CPU_ENTRY_AREA_BASE);
 }
 
+#else /* CONFIG_X86_64 */
+
+/*
+ * On 32 bit PAE systems with 1GB of Kernel address space there is only
+ * one pgd/p4d for the whole kernel. Cloning that would map the whole
+ * address space into the user page-tables, making PTI useless. So clone
+ * the page-table on the PMD level to prevent that.
+ */
+static void __init pti_clone_user_shared(void)
+{
+	unsigned long start, end;
+
+	start = CPU_ENTRY_AREA_BASE;
+	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
+
+	pti_clone_pgtable(start, end, PTI_CLONE_PMD);
+}
+#endif /* CONFIG_X86_64 */
+
 /*
  * Clone the ESPFIX P4D into the user space visible page table
  */
@@ -380,11 +473,11 @@ static void __init pti_setup_espfix64(void)
 /*
  * Clone the populated PMDs of the entry and irqentry text and force it RO.
  */
-static void __init pti_clone_entry_text(void)
+static void pti_clone_entry_text(void)
 {
-	pti_clone_pmds((unsigned long) __entry_text_start,
-			(unsigned long) __irqentry_text_end,
-		       _PAGE_RW);
+	pti_clone_pgtable((unsigned long) __entry_text_start,
+			  (unsigned long) __irqentry_text_end,
+			  PTI_CLONE_PMD);
 }
 
 /*
@@ -435,10 +528,17 @@ static inline bool pti_kernel_image_global_ok(void)
 }
 
 /*
+ * This is the only user for these and it is not arch-generic
+ * like the other set_memory.h functions.  Just extern them.
+ */
+extern int set_memory_nonglobal(unsigned long addr, int numpages);
+extern int set_memory_global(unsigned long addr, int numpages);
+
+/*
  * For some configurations, map all of kernel text into the user page
  * tables.  This reduces TLB misses, especially on non-PCID systems.
  */
-void pti_clone_kernel_text(void)
+static void pti_clone_kernel_text(void)
 {
 	/*
 	 * rodata is part of the kernel image and is normally
@@ -446,7 +546,8 @@ void pti_clone_kernel_text(void)
 	 * clone the areas past rodata, they might contain secrets.
 	 */
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = (unsigned long)__end_rodata_hpage_align;
+	unsigned long end_clone  = (unsigned long)__end_rodata_aligned;
+	unsigned long end_global = PFN_ALIGN((unsigned long)__stop___ex_table);
 
 	if (!pti_kernel_image_global_ok())
 		return;
@@ -458,14 +559,18 @@ void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pmds(start, end, _PAGE_RW);
+	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE);
+
+	/*
+	 * pti_clone_pgtable() will set the global bit in any PMDs
+	 * that it clones, but we also need to get any PTEs in
+	 * the last level for areas that are not huge-page-aligned.
+	 */
+
+	/* Set the global bit for normal non-__init kernel text: */
+	set_memory_global(start, (end_global - start) >> PAGE_SHIFT);
 }
 
-/*
- * This is the only user for it and it is not arch-generic like
- * the other set_memory.h functions.  Just extern it.
- */
-extern int set_memory_nonglobal(unsigned long addr, int numpages);
 void pti_set_kernel_image_nonglobal(void)
 {
 	/*
@@ -477,9 +582,11 @@ void pti_set_kernel_image_nonglobal(void)
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
 
-	if (pti_kernel_image_global_ok())
-		return;
-
+	/*
+	 * This clears _PAGE_GLOBAL from the entire kernel image.
+	 * pti_clone_kernel_text() map put _PAGE_GLOBAL back for
+	 * areas that are mapped to userspace.
+	 */
 	set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT);
 }
 
@@ -493,6 +600,28 @@ void __init pti_init(void)
 
 	pr_info("enabled\n");
 
+#ifdef CONFIG_X86_32
+	/*
+	 * We check for X86_FEATURE_PCID here. But the init-code will
+	 * clear the feature flag on 32 bit because the feature is not
+	 * supported on 32 bit anyway. To print the warning we need to
+	 * check with cpuid directly again.
+	 */
+	if (cpuid_ecx(0x1) & BIT(17)) {
+		/* Use printk to work around pr_fmt() */
+		printk(KERN_WARNING "\n");
+		printk(KERN_WARNING "************************************************************\n");
+		printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!  **\n");
+		printk(KERN_WARNING "**                                                        **\n");
+		printk(KERN_WARNING "** You are using 32-bit PTI on a 64-bit PCID-capable CPU. **\n");
+		printk(KERN_WARNING "** Your performance will increase dramatically if you     **\n");
+		printk(KERN_WARNING "** switch to a 64-bit kernel!                             **\n");
+		printk(KERN_WARNING "**                                                        **\n");
+		printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!  **\n");
+		printk(KERN_WARNING "************************************************************\n");
+	}
+#endif
+
 	pti_clone_user_shared();
 
 	/* Undo all global bits from the init pagetables in head_64.S: */
@@ -502,3 +631,22 @@ void __init pti_init(void)
 	pti_setup_espfix64();
 	pti_setup_vsyscall();
 }
+
+/*
+ * Finalize the kernel mappings in the userspace page-table. Some of the
+ * mappings for the kernel image might have changed since pti_init()
+ * cloned them. This is because parts of the kernel image have been
+ * mapped RO and/or NX.  These changes need to be cloned again to the
+ * userspace page-table.
+ */
+void pti_finalize(void)
+{
+	/*
+	 * We need to clone everything (again) that maps parts of the
+	 * kernel image.
+	 */
+	pti_clone_entry_text();
+	pti_clone_kernel_text();
+
+	debug_checkwx_user();
+}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6eb1f34c3c85..752dbf4e0e50 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
+#include <linux/gfp.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -35,7 +36,7 @@
  * necessary invalidation by clearing out the 'ctx_id' which
  * forces a TLB flush when the context is loaded.
  */
-void clear_asid_other(void)
+static void clear_asid_other(void)
 {
 	u16 asid;
 
@@ -185,8 +186,11 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 {
 	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy);
 	unsigned cpu = smp_processor_id();
 	u64 next_tlb_gen;
+	bool need_flush;
+	u16 new_asid;
 
 	/*
 	 * NB: The scheduler will call us with prev == next when switching
@@ -240,20 +244,41 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			   next->context.ctx_id);
 
 		/*
-		 * We don't currently support having a real mm loaded without
-		 * our cpu set in mm_cpumask().  We have all the bookkeeping
-		 * in place to figure out whether we would need to flush
-		 * if our cpu were cleared in mm_cpumask(), but we don't
-		 * currently use it.
+		 * Even in lazy TLB mode, the CPU should stay set in the
+		 * mm_cpumask. The TLB shootdown code can figure out from
+		 * from cpu_tlbstate.is_lazy whether or not to send an IPI.
 		 */
 		if (WARN_ON_ONCE(real_prev != &init_mm &&
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 
-		return;
+		/*
+		 * If the CPU is not in lazy TLB mode, we are just switching
+		 * from one thread in a process to another thread in the same
+		 * process. No TLB flush required.
+		 */
+		if (!was_lazy)
+			return;
+
+		/*
+		 * Read the tlb_gen to check whether a flush is needed.
+		 * If the TLB is up to date, just use it.
+		 * The barrier synchronizes with the tlb_gen increment in
+		 * the TLB shootdown code.
+		 */
+		smp_mb();
+		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+		if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) ==
+				next_tlb_gen)
+			return;
+
+		/*
+		 * TLB contents went out of date while we were in lazy
+		 * mode. Fall through to the TLB switching code below.
+		 */
+		new_asid = prev_asid;
+		need_flush = true;
 	} else {
-		u16 new_asid;
-		bool need_flush;
 		u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
 
 		/*
@@ -285,53 +310,60 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			sync_current_stack_to_mm(next);
 		}
 
-		/* Stop remote flushes for the previous mm */
-		VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
-				real_prev != &init_mm);
-		cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+		/*
+		 * Stop remote flushes for the previous mm.
+		 * Skip kernel threads; we never send init_mm TLB flushing IPIs,
+		 * but the bitmap manipulation can cause cache line contention.
+		 */
+		if (real_prev != &init_mm) {
+			VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
+						mm_cpumask(real_prev)));
+			cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+		}
 
 		/*
 		 * Start remote flushes and then read tlb_gen.
 		 */
-		cpumask_set_cpu(cpu, mm_cpumask(next));
+		if (next != &init_mm)
+			cpumask_set_cpu(cpu, mm_cpumask(next));
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
 		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+	}
 
-		if (need_flush) {
-			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
-			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-			load_new_mm_cr3(next->pgd, new_asid, true);
-
-			/*
-			 * NB: This gets called via leave_mm() in the idle path
-			 * where RCU functions differently.  Tracing normally
-			 * uses RCU, so we need to use the _rcuidle variant.
-			 *
-			 * (There is no good reason for this.  The idle code should
-			 *  be rearranged to call this before rcu_idle_enter().)
-			 */
-			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-		} else {
-			/* The new ASID is already up to date. */
-			load_new_mm_cr3(next->pgd, new_asid, false);
-
-			/* See above wrt _rcuidle. */
-			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
-		}
+	if (need_flush) {
+		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
+		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
+		load_new_mm_cr3(next->pgd, new_asid, true);
 
 		/*
-		 * Record last user mm's context id, so we can avoid
-		 * flushing branch buffer with IBPB if we switch back
-		 * to the same user.
+		 * NB: This gets called via leave_mm() in the idle path
+		 * where RCU functions differently.  Tracing normally
+		 * uses RCU, so we need to use the _rcuidle variant.
+		 *
+		 * (There is no good reason for this.  The idle code should
+		 *  be rearranged to call this before rcu_idle_enter().)
 		 */
-		if (next != &init_mm)
-			this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+	} else {
+		/* The new ASID is already up to date. */
+		load_new_mm_cr3(next->pgd, new_asid, false);
 
-		this_cpu_write(cpu_tlbstate.loaded_mm, next);
-		this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+		/* See above wrt _rcuidle. */
+		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
 
+	/*
+	 * Record last user mm's context id, so we can avoid
+	 * flushing branch buffer with IBPB if we switch back
+	 * to the same user.
+	 */
+	if (next != &init_mm)
+		this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+
+	this_cpu_write(cpu_tlbstate.loaded_mm, next);
+	this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+
 	load_mm_cr4(next);
 	switch_ldt(real_prev, next);
 }
@@ -354,20 +386,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
 		return;
 
-	if (tlb_defer_switch_to_init_mm()) {
-		/*
-		 * There's a significant optimization that may be possible
-		 * here.  We have accurate enough TLB flush tracking that we
-		 * don't need to maintain coherence of TLB per se when we're
-		 * lazy.  We do, however, need to maintain coherence of
-		 * paging-structure caches.  We could, in principle, leave our
-		 * old mm loaded and only switch to init_mm when
-		 * tlb_remove_page() happens.
-		 */
-		this_cpu_write(cpu_tlbstate.is_lazy, true);
-	} else {
-		switch_mm(NULL, &init_mm, NULL);
-	}
+	this_cpu_write(cpu_tlbstate.is_lazy, true);
 }
 
 /*
@@ -454,6 +473,9 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 		 * paging-structure cache to avoid speculatively reading
 		 * garbage into our TLB.  Since switching to init_mm is barely
 		 * slower than a minimal flush, just switch to init_mm.
+		 *
+		 * This should be rare, with native_flush_tlb_others skipping
+		 * IPIs to lazy TLB mode CPUs.
 		 */
 		switch_mm_irqs_off(NULL, &init_mm, NULL);
 		return;
@@ -560,6 +582,9 @@ static void flush_tlb_func_remote(void *info)
 void native_flush_tlb_others(const struct cpumask *cpumask,
 			     const struct flush_tlb_info *info)
 {
+	cpumask_var_t lazymask;
+	unsigned int cpu;
+
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (info->end == TLB_FLUSH_ALL)
 		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
@@ -583,8 +608,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 		 * that UV should be updated so that smp_call_function_many(),
 		 * etc, are optimal on UV.
 		 */
-		unsigned int cpu;
-
 		cpu = smp_processor_id();
 		cpumask = uv_flush_tlb_others(cpumask, info);
 		if (cpumask)
@@ -592,8 +615,29 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 					       (void *)info, 1);
 		return;
 	}
-	smp_call_function_many(cpumask, flush_tlb_func_remote,
+
+	/*
+	 * A temporary cpumask is used in order to skip sending IPIs
+	 * to CPUs in lazy TLB state, while keeping them in mm_cpumask(mm).
+	 * If the allocation fails, simply IPI every CPU in mm_cpumask.
+	 */
+	if (!alloc_cpumask_var(&lazymask, GFP_ATOMIC)) {
+		smp_call_function_many(cpumask, flush_tlb_func_remote,
 			       (void *)info, 1);
+		return;
+	}
+
+	cpumask_copy(lazymask, cpumask);
+
+	for_each_cpu(cpu, lazymask) {
+		if (per_cpu(cpu_tlbstate.is_lazy, cpu))
+			cpumask_clear_cpu(cpu, lazymask);
+	}
+
+	smp_call_function_many(lazymask, flush_tlb_func_remote,
+			       (void *)info, 1);
+
+	free_cpumask_var(lazymask);
 }
 
 /*
@@ -646,6 +690,68 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	put_cpu();
 }
 
+void tlb_flush_remove_tables_local(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm &&
+			this_cpu_read(cpu_tlbstate.is_lazy)) {
+		/*
+		 * We're in lazy mode.  We need to at least flush our
+		 * paging-structure cache to avoid speculatively reading
+		 * garbage into our TLB.  Since switching to init_mm is barely
+		 * slower than a minimal flush, just switch to init_mm.
+		 */
+		switch_mm_irqs_off(NULL, &init_mm, NULL);
+	}
+}
+
+static void mm_fill_lazy_tlb_cpu_mask(struct mm_struct *mm,
+				      struct cpumask *lazy_cpus)
+{
+	int cpu;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		if (!per_cpu(cpu_tlbstate.is_lazy, cpu))
+			cpumask_set_cpu(cpu, lazy_cpus);
+	}
+}
+
+void tlb_flush_remove_tables(struct mm_struct *mm)
+{
+	int cpu = get_cpu();
+	cpumask_var_t lazy_cpus;
+
+	if (cpumask_any_but(mm_cpumask(mm), cpu) >= nr_cpu_ids) {
+		put_cpu();
+		return;
+	}
+
+	if (!zalloc_cpumask_var(&lazy_cpus, GFP_ATOMIC)) {
+		/*
+		 * If the cpumask allocation fails, do a brute force flush
+		 * on all the CPUs that have this mm loaded.
+		 */
+		smp_call_function_many(mm_cpumask(mm),
+				tlb_flush_remove_tables_local, (void *)mm, 1);
+		put_cpu();
+		return;
+	}
+
+	/*
+	 * CPUs with !is_lazy either received a TLB flush IPI while the user
+	 * pages in this address range were unmapped, or have context switched
+	 * and reloaded %CR3 since then.
+	 *
+	 * Shootdown IPIs at page table freeing time only need to be sent to
+	 * CPUs that may have out of date TLB contents.
+	 */
+	mm_fill_lazy_tlb_cpu_mask(mm, lazy_cpus);
+	smp_call_function_many(lazy_cpus,
+				tlb_flush_remove_tables_local, (void *)mm, 1);
+	free_cpumask_var(lazy_cpus);
+	put_cpu();
+}
 
 static void do_flush_tlb_all(void *info)
 {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 5f2eb3231607..ee5d08f25ce4 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -636,6 +636,8 @@ void efi_switch_mm(struct mm_struct *mm)
 #ifdef CONFIG_EFI_MIXED
 extern efi_status_t efi64_thunk(u32, ...);
 
+static DEFINE_SPINLOCK(efi_runtime_lock);
+
 #define runtime_service32(func)						 \
 ({									 \
 	u32 table = (u32)(unsigned long)efi.systab;			 \
@@ -657,17 +659,14 @@ extern efi_status_t efi64_thunk(u32, ...);
 #define efi_thunk(f, ...)						\
 ({									\
 	efi_status_t __s;						\
-	unsigned long __flags;						\
 	u32 __func;							\
 									\
-	local_irq_save(__flags);					\
 	arch_efi_call_virt_setup();					\
 									\
 	__func = runtime_service32(f);					\
 	__s = efi64_thunk(__func, __VA_ARGS__);				\
 									\
 	arch_efi_call_virt_teardown();					\
-	local_irq_restore(__flags);					\
 									\
 	__s;								\
 })
@@ -702,14 +701,17 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	efi_status_t status;
 	u32 phys_tm, phys_tc;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_tm = virt_to_phys_or_null(tm);
 	phys_tc = virt_to_phys_or_null(tc);
 
 	status = efi_thunk(get_time, phys_tm, phys_tc);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -719,13 +721,16 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm)
 {
 	efi_status_t status;
 	u32 phys_tm;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_time, phys_tm);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -737,8 +742,10 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
 {
 	efi_status_t status;
 	u32 phys_enabled, phys_pending, phys_tm;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_enabled = virt_to_phys_or_null(enabled);
 	phys_pending = virt_to_phys_or_null(pending);
@@ -747,6 +754,7 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
 	status = efi_thunk(get_wakeup_time, phys_enabled,
 			     phys_pending, phys_tm);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -757,13 +765,16 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 {
 	efi_status_t status;
 	u32 phys_tm;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_wakeup_time, enabled, phys_tm);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -781,6 +792,9 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 	efi_status_t status;
 	u32 phys_name, phys_vendor, phys_attr;
 	u32 phys_data_size, phys_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_data_size = virt_to_phys_or_null(data_size);
 	phys_vendor = virt_to_phys_or_null(vendor);
@@ -791,6 +805,8 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 	status = efi_thunk(get_variable, phys_name, phys_vendor,
 			   phys_attr, phys_data_size, phys_data);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -800,6 +816,34 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 {
 	u32 phys_name, phys_vendor, phys_data;
 	efi_status_t status;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_data = virt_to_phys_or_null_size(data, data_size);
+
+	/* If data_size is > sizeof(u32) we've got problems */
+	status = efi_thunk(set_variable, phys_name, phys_vendor,
+			   attr, data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
+				   u32 attr, unsigned long data_size,
+				   void *data)
+{
+	u32 phys_name, phys_vendor, phys_data;
+	efi_status_t status;
+	unsigned long flags;
+
+	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+		return EFI_NOT_READY;
 
 	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
 	phys_vendor = virt_to_phys_or_null(vendor);
@@ -809,6 +853,8 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	status = efi_thunk(set_variable, phys_name, phys_vendor,
 			   attr, data_size, phys_data);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -819,6 +865,9 @@ efi_thunk_get_next_variable(unsigned long *name_size,
 {
 	efi_status_t status;
 	u32 phys_name_size, phys_name, phys_vendor;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_name_size = virt_to_phys_or_null(name_size);
 	phys_vendor = virt_to_phys_or_null(vendor);
@@ -827,6 +876,8 @@ efi_thunk_get_next_variable(unsigned long *name_size,
 	status = efi_thunk(get_next_variable, phys_name_size,
 			   phys_name, phys_vendor);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -835,10 +886,15 @@ efi_thunk_get_next_high_mono_count(u32 *count)
 {
 	efi_status_t status;
 	u32 phys_count;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_count = virt_to_phys_or_null(count);
 	status = efi_thunk(get_next_high_mono_count, phys_count);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -847,10 +903,15 @@ efi_thunk_reset_system(int reset_type, efi_status_t status,
 		       unsigned long data_size, efi_char16_t *data)
 {
 	u32 phys_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_data = virt_to_phys_or_null_size(data, data_size);
 
 	efi_thunk(reset_system, reset_type, status, data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 }
 
 static efi_status_t
@@ -872,10 +933,13 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
 {
 	efi_status_t status;
 	u32 phys_storage, phys_remaining, phys_max;
+	unsigned long flags;
 
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
 	phys_storage = virt_to_phys_or_null(storage_space);
 	phys_remaining = virt_to_phys_or_null(remaining_space);
 	phys_max = virt_to_phys_or_null(max_variable_size);
@@ -883,6 +947,35 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
 	status = efi_thunk(query_variable_info, attr, phys_storage,
 			   phys_remaining, phys_max);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_query_variable_info_nonblocking(u32 attr, u64 *storage_space,
+					  u64 *remaining_space,
+					  u64 *max_variable_size)
+{
+	efi_status_t status;
+	u32 phys_storage, phys_remaining, phys_max;
+	unsigned long flags;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+		return EFI_NOT_READY;
+
+	phys_storage = virt_to_phys_or_null(storage_space);
+	phys_remaining = virt_to_phys_or_null(remaining_space);
+	phys_max = virt_to_phys_or_null(max_variable_size);
+
+	status = efi_thunk(query_variable_info, attr, phys_storage,
+			   phys_remaining, phys_max);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -908,9 +1001,11 @@ void efi_thunk_runtime_setup(void)
 	efi.get_variable = efi_thunk_get_variable;
 	efi.get_next_variable = efi_thunk_get_next_variable;
 	efi.set_variable = efi_thunk_set_variable;
+	efi.set_variable_nonblocking = efi_thunk_set_variable_nonblocking;
 	efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count;
 	efi.reset_system = efi_thunk_reset_system;
 	efi.query_variable_info = efi_thunk_query_variable_info;
+	efi.query_variable_info_nonblocking = efi_thunk_query_variable_info_nonblocking;
 	efi.update_capsule = efi_thunk_update_capsule;
 	efi.query_capsule_caps = efi_thunk_query_capsule_caps;
 }
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 36c1f8b9f7e0..844d31cb8a0c 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -105,12 +105,11 @@ early_param("efi_no_storage_paranoia", setup_storage_paranoia);
 */
 void efi_delete_dummy_variable(void)
 {
-	efi.set_variable((efi_char16_t *)efi_dummy_name,
-			 &EFI_DUMMY_GUID,
-			 EFI_VARIABLE_NON_VOLATILE |
-			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
-			 EFI_VARIABLE_RUNTIME_ACCESS,
-			 0, NULL);
+	efi.set_variable_nonblocking((efi_char16_t *)efi_dummy_name,
+				     &EFI_DUMMY_GUID,
+				     EFI_VARIABLE_NON_VOLATILE |
+				     EFI_VARIABLE_BOOTSERVICE_ACCESS |
+				     EFI_VARIABLE_RUNTIME_ACCESS, 0, NULL);
 }
 
 /*
@@ -249,7 +248,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 	int num_entries;
 	void *new;
 
-	if (efi_mem_desc_lookup(addr, &md)) {
+	if (efi_mem_desc_lookup(addr, &md) ||
+	    md.type != EFI_BOOT_SERVICES_DATA) {
 		pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr);
 		return;
 	}
diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile
index fa021dfab088..5cf886c867c2 100644
--- a/arch/x86/platform/intel-mid/Makefile
+++ b/arch/x86/platform/intel-mid/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o mfld.o mrfld.o pwr.o
+obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o pwr.o
 
 # SFI specific code
 ifdef CONFIG_X86_INTEL_MID
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 4f5fa65a1011..2acd6be13375 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
@@ -18,6 +18,7 @@
 #include <asm/intel-mid.h>
 #include <asm/intel_scu_ipc.h>
 #include <asm/io_apic.h>
+#include <asm/hw_irq.h>
 
 #define TANGIER_EXT_TIMER0_MSI 12
 
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 2ebdf31d9996..56f66eafb94f 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -36,8 +36,6 @@
 #include <asm/apb_timer.h>
 #include <asm/reboot.h>
 
-#include "intel_mid_weak_decls.h"
-
 /*
  * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
  * cmdline option x86_intel_mid_timer can be used to override the configuration
@@ -61,10 +59,6 @@
 
 enum intel_mid_timer_options intel_mid_timer_options;
 
-/* intel_mid_ops to store sub arch ops */
-static struct intel_mid_ops *intel_mid_ops;
-/* getter function for sub arch ops*/
-static void *(*get_intel_mid_ops[])(void) = INTEL_MID_OPS_INIT;
 enum intel_mid_cpu_type __intel_mid_cpu_chip;
 EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip);
 
@@ -82,11 +76,6 @@ static void intel_mid_reboot(void)
 	intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
 }
 
-static unsigned long __init intel_mid_calibrate_tsc(void)
-{
-	return 0;
-}
-
 static void __init intel_mid_setup_bp_timer(void)
 {
 	apbt_time_init();
@@ -133,6 +122,7 @@ static void intel_mid_arch_setup(void)
 	case 0x3C:
 	case 0x4A:
 		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_TANGIER;
+		x86_platform.legacy.rtc = 1;
 		break;
 	case 0x27:
 	default:
@@ -140,17 +130,7 @@ static void intel_mid_arch_setup(void)
 		break;
 	}
 
-	if (__intel_mid_cpu_chip < MAX_CPU_OPS(get_intel_mid_ops))
-		intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
-	else {
-		intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
-		pr_info("ARCH: Unknown SoC, assuming Penwell!\n");
-	}
-
 out:
-	if (intel_mid_ops->arch_setup)
-		intel_mid_ops->arch_setup();
-
 	/*
 	 * Intel MID platforms are using explicitly defined regulators.
 	 *
@@ -191,7 +171,6 @@ void __init x86_intel_mid_early_setup(void)
 
 	x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock;
 
-	x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
 	x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
 
 	x86_init.pci.arch_init = intel_mid_pci_init;
diff --git a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
deleted file mode 100644
index 3c1c3866d82b..000000000000
--- a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * intel_mid_weak_decls.h: Weak declarations of intel-mid.c
- *
- * (C) Copyright 2013 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.
- */
-
-
-/* For every CPU addition a new get_<cpuname>_ops interface needs
- * to be added.
- */
-extern void *get_penwell_ops(void);
-extern void *get_cloverview_ops(void);
-extern void *get_tangier_ops(void);
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
deleted file mode 100644
index e42978d4deaf..000000000000
--- a/arch/x86/platform/intel-mid/mfld.c
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * mfld.c: Intel Medfield platform setup code
- *
- * (C) Copyright 2013 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.
- */
-
-#include <linux/init.h>
-
-#include <asm/apic.h>
-#include <asm/intel-mid.h>
-#include <asm/intel_mid_vrtc.h>
-
-#include "intel_mid_weak_decls.h"
-
-static unsigned long __init mfld_calibrate_tsc(void)
-{
-	unsigned long fast_calibrate;
-	u32 lo, hi, ratio, fsb;
-
-	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
-	pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
-	ratio = (hi >> 8) & 0x1f;
-	pr_debug("ratio is %d\n", ratio);
-	if (!ratio) {
-		pr_err("read a zero ratio, should be incorrect!\n");
-		pr_err("force tsc ratio to 16 ...\n");
-		ratio = 16;
-	}
-	rdmsr(MSR_FSB_FREQ, lo, hi);
-	if ((lo & 0x7) == 0x7)
-		fsb = FSB_FREQ_83SKU;
-	else
-		fsb = FSB_FREQ_100SKU;
-	fast_calibrate = ratio * fsb;
-	pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
-	lapic_timer_frequency = fsb * 1000 / HZ;
-
-	/*
-	 * TSC on Intel Atom SoCs is reliable and of known frequency.
-	 * See tsc_msr.c for details.
-	 */
-	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-
-	return fast_calibrate;
-}
-
-static void __init penwell_arch_setup(void)
-{
-	x86_platform.calibrate_tsc = mfld_calibrate_tsc;
-}
-
-static struct intel_mid_ops penwell_ops = {
-	.arch_setup = penwell_arch_setup,
-};
-
-void *get_penwell_ops(void)
-{
-	return &penwell_ops;
-}
-
-void *get_cloverview_ops(void)
-{
-	return &penwell_ops;
-}
diff --git a/arch/x86/platform/intel-mid/mrfld.c b/arch/x86/platform/intel-mid/mrfld.c
deleted file mode 100644
index ae7bdeb0e507..000000000000
--- a/arch/x86/platform/intel-mid/mrfld.c
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * Intel Merrifield platform specific setup code
- *
- * (C) Copyright 2013 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.
- */
-
-#include <linux/init.h>
-
-#include <asm/apic.h>
-#include <asm/intel-mid.h>
-
-#include "intel_mid_weak_decls.h"
-
-static unsigned long __init tangier_calibrate_tsc(void)
-{
-	unsigned long fast_calibrate;
-	u32 lo, hi, ratio, fsb, bus_freq;
-
-	/* *********************** */
-	/* Compute TSC:Ratio * FSB */
-	/* *********************** */
-
-	/* Compute Ratio */
-	rdmsr(MSR_PLATFORM_INFO, lo, hi);
-	pr_debug("IA32 PLATFORM_INFO is 0x%x : %x\n", hi, lo);
-
-	ratio = (lo >> 8) & 0xFF;
-	pr_debug("ratio is %d\n", ratio);
-	if (!ratio) {
-		pr_err("Read a zero ratio, force tsc ratio to 4 ...\n");
-		ratio = 4;
-	}
-
-	/* Compute FSB */
-	rdmsr(MSR_FSB_FREQ, lo, hi);
-	pr_debug("Actual FSB frequency detected by SOC 0x%x : %x\n",
-			hi, lo);
-
-	bus_freq = lo & 0x7;
-	pr_debug("bus_freq = 0x%x\n", bus_freq);
-
-	if (bus_freq == 0)
-		fsb = FSB_FREQ_100SKU;
-	else if (bus_freq == 1)
-		fsb = FSB_FREQ_100SKU;
-	else if (bus_freq == 2)
-		fsb = FSB_FREQ_133SKU;
-	else if (bus_freq == 3)
-		fsb = FSB_FREQ_167SKU;
-	else if (bus_freq == 4)
-		fsb = FSB_FREQ_83SKU;
-	else if (bus_freq == 5)
-		fsb = FSB_FREQ_400SKU;
-	else if (bus_freq == 6)
-		fsb = FSB_FREQ_267SKU;
-	else if (bus_freq == 7)
-		fsb = FSB_FREQ_333SKU;
-	else {
-		BUG();
-		pr_err("Invalid bus_freq! Setting to minimal value!\n");
-		fsb = FSB_FREQ_100SKU;
-	}
-
-	/* TSC = FSB Freq * Resolved HFM Ratio */
-	fast_calibrate = ratio * fsb;
-	pr_debug("calculate tangier tsc %lu KHz\n", fast_calibrate);
-
-	/* ************************************ */
-	/* Calculate Local APIC Timer Frequency */
-	/* ************************************ */
-	lapic_timer_frequency = (fsb * 1000) / HZ;
-
-	pr_debug("Setting lapic_timer_frequency = %d\n",
-			lapic_timer_frequency);
-
-	/*
-	 * TSC on Intel Atom SoCs is reliable and of known frequency.
-	 * See tsc_msr.c for details.
-	 */
-	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-
-	return fast_calibrate;
-}
-
-static void __init tangier_arch_setup(void)
-{
-	x86_platform.calibrate_tsc = tangier_calibrate_tsc;
-	x86_platform.legacy.rtc = 1;
-}
-
-/* tangier arch ops */
-static struct intel_mid_ops tangier_ops = {
-	.arch_setup = tangier_arch_setup,
-};
-
-void *get_tangier_ops(void)
-{
-	return &tangier_ops;
-}
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index 7c3077e58fa0..f0e920fb98ad 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -311,10 +311,8 @@ static int __init add_xo1_platform_devices(void)
 		return PTR_ERR(pdev);
 
 	pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 static int olpc_xo1_ec_probe(struct platform_device *pdev)
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index ca446da48fd2..a4130b84d1ff 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1285,6 +1285,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 	struct msg_desc msgdesc;
 
 	ack_APIC_irq();
+	kvm_set_cpu_l1tf_flush_l1d();
 	time_start = get_cycles();
 
 	bcp = &per_cpu(bau_control, smp_processor_id());
@@ -1607,8 +1608,6 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr,
 				*tunables[cnt].tunp = val;
 			continue;
 		}
-		if (q == p)
-			break;
 	}
 	return 0;
 }
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index ce8da3a0412c..fd369a6e9ff8 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -137,7 +137,7 @@ ENTRY(restore_registers)
 	/* Saved in save_processor_state. */
 	lgdt	saved_context_gdt_desc(%rax)
 
-	xorq	%rax, %rax
+	xorl	%eax, %eax
 
 	/* tell the hibernation core that we've just restored the memory */
 	movq	%rax, in_suspend(%rip)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 220e97841e49..3a6c8ebc8032 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -67,6 +67,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 	"__tracedata_(start|end)|"
 	"__(start|stop)_notes|"
 	"__end_rodata|"
+	"__end_rodata_aligned|"
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
diff --git a/arch/x86/um/vdso/.gitignore b/arch/x86/um/vdso/.gitignore
index 9cac6d072199..f8b69d84238e 100644
--- a/arch/x86/um/vdso/.gitignore
+++ b/arch/x86/um/vdso/.gitignore
@@ -1,2 +1 @@
-vdso-syms.lds
 vdso.lds
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index b2d6967262b2..822ccdba93ad 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -53,22 +53,6 @@ $(vobjs): KBUILD_CFLAGS += $(CFL)
 CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage
 CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage
 
-targets += vdso-syms.lds
-extra-$(VDSO64-y)			+= vdso-syms.lds
-
-#
-# Match symbols in the DSO that look like VDSO*; produce a file of constants.
-#
-sed-vdsosym := -e 's/^00*/0/' \
-	-e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p'
-quiet_cmd_vdsosym = VDSOSYM $@
-define cmd_vdsosym
-	$(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@
-endef
-
-$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE
-	$(call if_changed,vdsosym)
-
 #
 # The DSO images are built using a special linker script.
 #
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 3b5318505c69..2eeddd814653 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -3,6 +3,7 @@
 #endif
 #include <linux/cpu.h>
 #include <linux/kexec.h>
+#include <linux/slab.h>
 
 #include <xen/features.h>
 #include <xen/page.h>
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 439a94bf89ad..105a57d73701 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -119,6 +119,27 @@ static void __init xen_banner(void)
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
+
+static void __init xen_pv_init_platform(void)
+{
+	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
+	HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
+
+	/* xen clock uses per-cpu vcpu_info, need to init it for boot cpu */
+	xen_vcpu_info_reset(0);
+
+	/* pvclock is in shared info area */
+	xen_init_time_ops();
+}
+
+static void __init xen_pv_guest_late_init(void)
+{
+#ifndef CONFIG_SMP
+	/* Setup shared vcpu info for non-smp configurations */
+	xen_setup_vcpu_info_placement();
+#endif
+}
+
 /* Check if running on Xen version (major, minor) or later */
 bool
 xen_running_on_version_or_later(unsigned int major, unsigned int minor)
@@ -947,34 +968,8 @@ static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
 	xen_write_msr_safe(msr, low, high);
 }
 
-void xen_setup_shared_info(void)
-{
-	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
-
-	HYPERVISOR_shared_info =
-		(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
-
-	xen_setup_mfn_list_list();
-
-	if (system_state == SYSTEM_BOOTING) {
-#ifndef CONFIG_SMP
-		/*
-		 * In UP this is as good a place as any to set up shared info.
-		 * Limit this to boot only, at restore vcpu setup is done via
-		 * xen_vcpu_restore().
-		 */
-		xen_setup_vcpu_info_placement();
-#endif
-		/*
-		 * Now that shared info is set up we can start using routines
-		 * that point to pvclock area.
-		 */
-		xen_init_time_ops();
-	}
-}
-
 /* This is called once we have the cpu_possible_mask */
-void __ref xen_setup_vcpu_info_placement(void)
+void __init xen_setup_vcpu_info_placement(void)
 {
 	int cpu;
 
@@ -1228,6 +1223,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	x86_init.irqs.intr_mode_init	= x86_init_noop;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
+	x86_init.hyper.init_platform = xen_pv_init_platform;
+	x86_init.hyper.guest_late_init = xen_pv_guest_late_init;
 
 	/*
 	 * Set up some pagetable state before starting to set any ptes.
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2c30cabfda90..52206ad81e4b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1230,8 +1230,7 @@ static void __init xen_pagetable_p2m_free(void)
 	 * We roundup to the PMD, which means that if anybody at this stage is
 	 * using the __ka address of xen_start_info or
 	 * xen_start_info->shared_info they are in going to crash. Fortunatly
-	 * we have already revectored in xen_setup_kernel_pagetable and in
-	 * xen_setup_shared_info.
+	 * we have already revectored in xen_setup_kernel_pagetable.
 	 */
 	size = roundup(size, PMD_SIZE);
 
@@ -1292,8 +1291,7 @@ static void __init xen_pagetable_init(void)
 
 	/* Remap memory freed due to conflicts with E820 map */
 	xen_remap_memory();
-
-	xen_setup_shared_info();
+	xen_setup_mfn_list_list();
 }
 static void xen_write_cr2(unsigned long cr2)
 {
diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c
index a2e0f110af56..8303b58c79a9 100644
--- a/arch/x86/xen/suspend_pv.c
+++ b/arch/x86/xen/suspend_pv.c
@@ -27,8 +27,9 @@ void xen_pv_pre_suspend(void)
 void xen_pv_post_suspend(int suspend_cancelled)
 {
 	xen_build_mfn_list_list();
-
-	xen_setup_shared_info();
+	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
+	HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
+	xen_setup_mfn_list_list();
 
 	if (suspend_cancelled) {
 		xen_start_info->store_mfn =
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index e0f1bcf01d63..c84f1e039d84 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -31,6 +31,8 @@
 /* Xen may fire a timer up to this many ns early */
 #define TIMER_SLOP	100000
 
+static u64 xen_sched_clock_offset __read_mostly;
+
 /* Get the TSC speed from Xen */
 static unsigned long xen_tsc_khz(void)
 {
@@ -40,7 +42,7 @@ static unsigned long xen_tsc_khz(void)
 	return pvclock_tsc_khz(info);
 }
 
-u64 xen_clocksource_read(void)
+static u64 xen_clocksource_read(void)
 {
         struct pvclock_vcpu_time_info *src;
 	u64 ret;
@@ -57,6 +59,11 @@ static u64 xen_clocksource_get_cycles(struct clocksource *cs)
 	return xen_clocksource_read();
 }
 
+static u64 xen_sched_clock(void)
+{
+	return xen_clocksource_read() - xen_sched_clock_offset;
+}
+
 static void xen_read_wallclock(struct timespec64 *ts)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
@@ -367,7 +374,7 @@ void xen_timer_resume(void)
 }
 
 static const struct pv_time_ops xen_time_ops __initconst = {
-	.sched_clock = xen_clocksource_read,
+	.sched_clock = xen_sched_clock,
 	.steal_clock = xen_steal_clock,
 };
 
@@ -503,8 +510,9 @@ static void __init xen_time_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 }
 
-void __ref xen_init_time_ops(void)
+void __init xen_init_time_ops(void)
 {
+	xen_sched_clock_offset = xen_clocksource_read();
 	pv_time_ops = xen_time_ops;
 
 	x86_init.timers.timer_init = xen_time_init;
@@ -542,11 +550,11 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
-		printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
-				"disable pv timer\n");
+		pr_info("Xen doesn't support pvclock on HVM, disable pv timer");
 		return;
 	}
 
+	xen_sched_clock_offset = xen_clocksource_read();
 	pv_time_ops = xen_time_ops;
 	x86_init.timers.setup_percpu_clockev = xen_time_init;
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 3b34745d0a52..e78684597f57 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -31,7 +31,6 @@ extern struct shared_info xen_dummy_shared_info;
 extern struct shared_info *HYPERVISOR_shared_info;
 
 void xen_setup_mfn_list_list(void);
-void xen_setup_shared_info(void);
 void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
@@ -68,12 +67,11 @@ void xen_init_irq_ops(void);
 void xen_setup_timer(int cpu);
 void xen_setup_runstate_info(int cpu);
 void xen_teardown_timer(int cpu);
-u64 xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);
 void xen_save_time_memory_area(void);
 void xen_restore_time_memory_area(void);
-void __ref xen_init_time_ops(void);
-void __init xen_hvm_init_time_ops(void);
+void xen_init_time_ops(void);
+void xen_hvm_init_time_ops(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index e7a23f2a519a..7de0149e1cf7 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -197,107 +197,9 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0)
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1,(v))
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1,(v))
-
-/**
- * atomic_dec_return - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1,(v)) == 0)
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_add_return(1,(v)) == 0)
-
-/**
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i,v) (atomic_add_return((i),(v)) < 0)
-
 #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #endif /* __KERNEL__ */
 
 #endif /* _XTENSA_ATOMIC_H */
diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index dbe3053b284a..9f119c1ca0b5 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -30,13 +30,16 @@ struct arch_hw_breakpoint {
 	u16 type;
 };
 
+struct perf_event_attr;
 struct perf_event;
 struct pt_regs;
 struct task_struct;
 
 int hw_breakpoint_slots(int type);
-int arch_check_bp_in_kernelspace(struct perf_event *bp);
-int arch_validate_hwbkpt_settings(struct perf_event *bp);
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw);
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data);
 
diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c
index b35656ab7dbd..c2e387c19cda 100644
--- a/arch/xtensa/kernel/hw_breakpoint.c
+++ b/arch/xtensa/kernel/hw_breakpoint.c
@@ -33,14 +33,13 @@ int hw_breakpoint_slots(int type)
 	}
 }
 
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = bp->attr.bp_len;
+	va = hw->address;
+	len = hw->len;
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -48,50 +47,41 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->type = XTENSA_BREAKPOINT_EXECUTE;
+		hw->type = XTENSA_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->type = XTENSA_BREAKPOINT_LOAD;
+		hw->type = XTENSA_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->type = XTENSA_BREAKPOINT_STORE;
+		hw->type = XTENSA_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
+		hw->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	info->len = bp->attr.bp_len;
-	if (info->len < 1 || info->len > 64 || !is_power_of_2(info->len))
+	hw->len = attr->bp_len;
+	if (hw->len < 1 || hw->len > 64 || !is_power_of_2(hw->len))
 		return -EINVAL;
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
-	if (info->address & (info->len - 1))
+	hw->address = attr->bp_addr;
+	if (hw->address & (hw->len - 1))
 		return -EINVAL;
 
 	return 0;
 }
 
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
-{
-	int ret;
-
-	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
-	return ret;
-}
-
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data)
 {
diff --git a/block/Kconfig b/block/Kconfig
index eb50fd4977c2..1f2469a0123c 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -149,6 +149,18 @@ config BLK_WBT
 	dynamically on an algorithm loosely based on CoDel, factoring in
 	the realtime performance of the disk.
 
+config BLK_CGROUP_IOLATENCY
+	bool "Enable support for latency based cgroup IO protection"
+	depends on BLK_CGROUP=y
+	default n
+	---help---
+	Enabling this option enables the .latency interface for IO throttling.
+	The IO controller will attempt to maintain average IO latencies below
+	the configured latency target, throttling anybody with a higher latency
+	target than the victimized group.
+
+	Note, this is an experimental interface and could be changed someday.
+
 config BLK_WBT_SQ
 	bool "Single queue writeback throttling"
 	default n
@@ -177,6 +189,10 @@ config BLK_DEBUG_FS
 	Unless you are building a kernel for a tiny system, you should
 	say Y here.
 
+config BLK_DEBUG_FS_ZONED
+       bool
+       default BLK_DEBUG_FS && BLK_DEV_ZONED
+
 config BLK_SED_OPAL
 	bool "Logic for interfacing with Opal enabled SEDs"
 	---help---
diff --git a/block/Makefile b/block/Makefile
index 6a56303b9925..572b33f32c07 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o partition-generic.o ioprio.o \
-			badblocks.o partitions/
+			badblocks.o partitions/ blk-rq-qos.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
@@ -17,6 +17,7 @@ obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
+obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
@@ -34,4 +35,5 @@ obj-$(CONFIG_BLK_MQ_RDMA)	+= blk-mq-rdma.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
+obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 495b9ddb3355..41d9036b1822 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -634,7 +634,7 @@ static bool bfq_differentiated_weights(struct bfq_data *bfqd)
  * The following function returns true if every queue must receive the
  * same share of the throughput (this condition is used when deciding
  * whether idling may be disabled, see the comments in the function
- * bfq_bfqq_may_idle()).
+ * bfq_better_to_idle()).
  *
  * Such a scenario occurs when:
  * 1) all active queues have the same weight,
@@ -742,8 +742,9 @@ inc_counter:
  * See the comments to the function bfq_weights_tree_add() for considerations
  * about overhead.
  */
-void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
-			     struct rb_root *root)
+void __bfq_weights_tree_remove(struct bfq_data *bfqd,
+			       struct bfq_entity *entity,
+			       struct rb_root *root)
 {
 	if (!entity->weight_counter)
 		return;
@@ -760,6 +761,43 @@ reset_entity_pointer:
 }
 
 /*
+ * Invoke __bfq_weights_tree_remove on bfqq and all its inactive
+ * parent entities.
+ */
+void bfq_weights_tree_remove(struct bfq_data *bfqd,
+			     struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = bfqq->entity.parent;
+
+	__bfq_weights_tree_remove(bfqd, &bfqq->entity,
+				  &bfqd->queue_weights_tree);
+
+	for_each_entity(entity) {
+		struct bfq_sched_data *sd = entity->my_sched_data;
+
+		if (sd->next_in_service || sd->in_service_entity) {
+			/*
+			 * entity is still active, because either
+			 * next_in_service or in_service_entity is not
+			 * NULL (see the comments on the definition of
+			 * next_in_service for details on why
+			 * in_service_entity must be checked too).
+			 *
+			 * As a consequence, the weight of entity is
+			 * not to be removed. In addition, if entity
+			 * is active, then its parent entities are
+			 * active as well, and thus their weights are
+			 * not to be removed either. In the end, this
+			 * loop must stop here.
+			 */
+			break;
+		}
+		__bfq_weights_tree_remove(bfqd, entity,
+					  &bfqd->group_weights_tree);
+	}
+}
+
+/*
  * Return expired entry, or NULL to just start from scratch in rbtree.
  */
 static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
@@ -1344,18 +1382,30 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
 		 * remain unchanged after such an expiration, and the
 		 * following statement therefore assigns to
 		 * entity->budget the remaining budget on such an
-		 * expiration. For clarity, entity->service is not
-		 * updated on expiration in any case, and, in normal
-		 * operation, is reset only when bfqq is selected for
-		 * service (see bfq_get_next_queue).
+		 * expiration.
 		 */
 		entity->budget = min_t(unsigned long,
 				       bfq_bfqq_budget_left(bfqq),
 				       bfqq->max_budget);
 
+		/*
+		 * At this point, we have used entity->service to get
+		 * the budget left (needed for updating
+		 * entity->budget). Thus we finally can, and have to,
+		 * reset entity->service. The latter must be reset
+		 * because bfqq would otherwise be charged again for
+		 * the service it has received during its previous
+		 * service slot(s).
+		 */
+		entity->service = 0;
+
 		return true;
 	}
 
+	/*
+	 * We can finally complete expiration, by setting service to 0.
+	 */
+	entity->service = 0;
 	entity->budget = max_t(unsigned long, bfqq->max_budget,
 			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
 	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
@@ -3233,11 +3283,21 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	ref = bfqq->ref;
 	__bfq_bfqq_expire(bfqd, bfqq);
 
+	if (ref == 1) /* bfqq is gone, no more actions on it */
+		return;
+
 	/* mark bfqq as waiting a request only if a bic still points to it */
-	if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
+	if (!bfq_bfqq_busy(bfqq) &&
 	    reason != BFQQE_BUDGET_TIMEOUT &&
-	    reason != BFQQE_BUDGET_EXHAUSTED)
+	    reason != BFQQE_BUDGET_EXHAUSTED) {
 		bfq_mark_bfqq_non_blocking_wait_rq(bfqq);
+		/*
+		 * Not setting service to 0, because, if the next rq
+		 * arrives in time, the queue will go on receiving
+		 * service with this same budget (as if it never expired)
+		 */
+	} else
+		entity->service = 0;
 }
 
 /*
@@ -3295,7 +3355,7 @@ static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
  * issues taken into account are not trivial. We discuss these issues
  * individually while introducing the variables.
  */
-static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
+static bool bfq_better_to_idle(struct bfq_queue *bfqq)
 {
 	struct bfq_data *bfqd = bfqq->bfqd;
 	bool rot_without_queueing =
@@ -3528,19 +3588,19 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 }
 
 /*
- * If the in-service queue is empty but the function bfq_bfqq_may_idle
+ * If the in-service queue is empty but the function bfq_better_to_idle
  * returns true, then:
  * 1) the queue must remain in service and cannot be expired, and
  * 2) the device must be idled to wait for the possible arrival of a new
  *    request for the queue.
- * See the comments on the function bfq_bfqq_may_idle for the reasons
+ * See the comments on the function bfq_better_to_idle for the reasons
  * why performing device idling is the best choice to boost the throughput
- * and preserve service guarantees when bfq_bfqq_may_idle itself
+ * and preserve service guarantees when bfq_better_to_idle itself
  * returns true.
  */
 static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
 {
-	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_may_idle(bfqq);
+	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq);
 }
 
 /*
@@ -3559,8 +3619,14 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 
 	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
 
+	/*
+	 * Do not expire bfqq for budget timeout if bfqq may be about
+	 * to enjoy device idling. The reason why, in this case, we
+	 * prevent bfqq from expiring is the same as in the comments
+	 * on the case where bfq_bfqq_must_idle() returns true, in
+	 * bfq_completed_request().
+	 */
 	if (bfq_may_expire_for_budg_timeout(bfqq) &&
-	    !bfq_bfqq_wait_request(bfqq) &&
 	    !bfq_bfqq_must_idle(bfqq))
 		goto expire;
 
@@ -3620,7 +3686,7 @@ check_queue:
 	 * may idle after their completion, then keep it anyway.
 	 */
 	if (bfq_bfqq_wait_request(bfqq) ||
-	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
+	    (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) {
 		bfqq = NULL;
 		goto keep_queue;
 	}
@@ -4582,8 +4648,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 		 */
 		bfqq->budget_timeout = jiffies;
 
-		bfq_weights_tree_remove(bfqd, &bfqq->entity,
-					&bfqd->queue_weights_tree);
+		bfq_weights_tree_remove(bfqd, bfqq);
 	}
 
 	now_ns = ktime_get_ns();
@@ -4637,15 +4702,39 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 	 * or if we want to idle in case it has no pending requests.
 	 */
 	if (bfqd->in_service_queue == bfqq) {
-		if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
-			bfq_arm_slice_timer(bfqd);
+		if (bfq_bfqq_must_idle(bfqq)) {
+			if (bfqq->dispatched == 0)
+				bfq_arm_slice_timer(bfqd);
+			/*
+			 * If we get here, we do not expire bfqq, even
+			 * if bfqq was in budget timeout or had no
+			 * more requests (as controlled in the next
+			 * conditional instructions). The reason for
+			 * not expiring bfqq is as follows.
+			 *
+			 * Here bfqq->dispatched > 0 holds, but
+			 * bfq_bfqq_must_idle() returned true. This
+			 * implies that, even if no request arrives
+			 * for bfqq before bfqq->dispatched reaches 0,
+			 * bfqq will, however, not be expired on the
+			 * completion event that causes bfqq->dispatch
+			 * to reach zero. In contrast, on this event,
+			 * bfqq will start enjoying device idling
+			 * (I/O-dispatch plugging).
+			 *
+			 * But, if we expired bfqq here, bfqq would
+			 * not have the chance to enjoy device idling
+			 * when bfqq->dispatched finally reaches
+			 * zero. This would expose bfqq to violation
+			 * of its reserved service guarantees.
+			 */
 			return;
 		} else if (bfq_may_expire_for_budg_timeout(bfqq))
 			bfq_bfqq_expire(bfqd, bfqq, false,
 					BFQQE_BUDGET_TIMEOUT);
 		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
 			 (bfqq->dispatched == 0 ||
-			  !bfq_bfqq_may_idle(bfqq)))
+			  !bfq_better_to_idle(bfqq)))
 			bfq_bfqq_expire(bfqd, bfqq, false,
 					BFQQE_NO_MORE_REQUESTS);
 	}
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 0f712e03b035..a8a2e5aca4d4 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -827,8 +827,11 @@ struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
 void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
 			  struct rb_root *root);
-void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
-			     struct rb_root *root);
+void __bfq_weights_tree_remove(struct bfq_data *bfqd,
+			       struct bfq_entity *entity,
+			       struct rb_root *root);
+void bfq_weights_tree_remove(struct bfq_data *bfqd,
+			     struct bfq_queue *bfqq);
 void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		     bool compensate, enum bfqq_expiration reason);
 void bfq_put_queue(struct bfq_queue *bfqq);
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 4498c43245e2..dbc07b456059 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -499,9 +499,6 @@ static void bfq_active_insert(struct bfq_service_tree *st,
 	if (bfqq)
 		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	else /* bfq_group */
-		bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
-
 	if (bfqg != bfqd->root_group)
 		bfqg->active_entities++;
 #endif
@@ -601,10 +598,6 @@ static void bfq_active_extract(struct bfq_service_tree *st,
 	if (bfqq)
 		list_del(&bfqq->bfqq_list);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	else /* bfq_group */
-		bfq_weights_tree_remove(bfqd, entity,
-					&bfqd->group_weights_tree);
-
 	if (bfqg != bfqd->root_group)
 		bfqg->active_entities--;
 #endif
@@ -799,7 +792,7 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		if (prev_weight != new_weight) {
 			root = bfqq ? &bfqd->queue_weights_tree :
 				      &bfqd->group_weights_tree;
-			bfq_weights_tree_remove(bfqd, entity, root);
+			__bfq_weights_tree_remove(bfqd, entity, root);
 		}
 		entity->weight = new_weight;
 		/*
@@ -971,7 +964,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
  * one of its children receives a new request.
  *
  * Basically, this function updates the timestamps of entity and
- * inserts entity into its active tree, ater possibly extracting it
+ * inserts entity into its active tree, after possibly extracting it
  * from its idle tree.
  */
 static void __bfq_activate_entity(struct bfq_entity *entity,
@@ -1015,6 +1008,16 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
 		entity->on_st = true;
 	}
 
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_weights_tree_add(bfqg->bfqd, entity,
+				     &bfqd->group_weights_tree);
+	}
+#endif
+
 	bfq_update_fin_time_enqueue(entity, st, backshifted);
 }
 
@@ -1542,12 +1545,6 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 		sd->in_service_entity = entity;
 
 		/*
-		 * Reset the accumulator of the amount of service that
-		 * the entity is about to receive.
-		 */
-		entity->service = 0;
-
-		/*
 		 * If entity is no longer a candidate for next
 		 * service, then it must be extracted from its active
 		 * tree, so as to make sure that it won't be
@@ -1664,8 +1661,7 @@ void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	bfqd->busy_queues--;
 
 	if (!bfqq->dispatched)
-		bfq_weights_tree_remove(bfqd, &bfqq->entity,
-					&bfqd->queue_weights_tree);
+		bfq_weights_tree_remove(bfqd, bfqq);
 
 	if (bfqq->wr_coeff > 1)
 		bfqd->wr_busy_queues--;
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index add7c7c85335..67b5fb861a51 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -160,28 +160,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL(bio_integrity_add_page);
 
 /**
- * bio_integrity_intervals - Return number of integrity intervals for a bio
- * @bi:		blk_integrity profile for device
- * @sectors:	Size of the bio in 512-byte sectors
- *
- * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the data integrity
- * interval size of the storage device.  Convert the block layer sectors
- * to the appropriate number of integrity intervals.
- */
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
-						   unsigned int sectors)
-{
-	return sectors >> (bi->interval_exp - 9);
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
-					       unsigned int sectors)
-{
-	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
-}
-
-/**
  * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
  * @proc_iter:  iterator to process
diff --git a/block/bio.c b/block/bio.c
index 047c5dca6d90..b12966e415d3 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -28,9 +28,11 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
+#include <linux/blk-cgroup.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
+#include "blk-rq-qos.h"
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
@@ -156,7 +158,7 @@ out:
 
 unsigned int bvec_nr_vecs(unsigned short idx)
 {
-	return bvec_slabs[idx].nr_vecs;
+	return bvec_slabs[--idx].nr_vecs;
 }
 
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
@@ -645,83 +647,6 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 EXPORT_SYMBOL(bio_clone_fast);
 
 /**
- * 	bio_clone_bioset - clone a bio
- * 	@bio_src: bio to clone
- *	@gfp_mask: allocation priority
- *	@bs: bio_set to allocate from
- *
- *	Clone bio. Caller will own the returned bio, but not the actual data it
- *	points to. Reference count of returned bio will be one.
- */
-struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
-			     struct bio_set *bs)
-{
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	struct bio *bio;
-
-	/*
-	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
-	 * bio_src->bi_io_vec to bio->bi_io_vec.
-	 *
-	 * We can't do that anymore, because:
-	 *
-	 *  - The point of cloning the biovec is to produce a bio with a biovec
-	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
-	 *
-	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
-	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
-	 *    But the clone should succeed as long as the number of biovecs we
-	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
-	 *
-	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
-	 *    that does not own the bio - reason being drivers don't use it for
-	 *    iterating over the biovec anymore, so expecting it to be kept up
-	 *    to date (i.e. for clones that share the parent biovec) is just
-	 *    asking for trouble and would force extra work on
-	 *    __bio_clone_fast() anyways.
-	 */
-
-	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
-	if (!bio)
-		return NULL;
-	bio->bi_disk		= bio_src->bi_disk;
-	bio->bi_opf		= bio_src->bi_opf;
-	bio->bi_write_hint	= bio_src->bi_write_hint;
-	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
-	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
-
-	switch (bio_op(bio)) {
-	case REQ_OP_DISCARD:
-	case REQ_OP_SECURE_ERASE:
-	case REQ_OP_WRITE_ZEROES:
-		break;
-	case REQ_OP_WRITE_SAME:
-		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
-		break;
-	default:
-		bio_for_each_segment(bv, bio_src, iter)
-			bio->bi_io_vec[bio->bi_vcnt++] = bv;
-		break;
-	}
-
-	if (bio_integrity(bio_src)) {
-		int ret;
-
-		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
-		if (ret < 0) {
-			bio_put(bio);
-			return NULL;
-		}
-	}
-
-	bio_clone_blkcg_association(bio, bio_src);
-
-	return bio;
-}
-EXPORT_SYMBOL(bio_clone_bioset);
-
-/**
  *	bio_add_pc_page	-	attempt to add page to bio
  *	@q: the target queue
  *	@bio: destination bio
@@ -1661,10 +1586,8 @@ void bio_set_pages_dirty(struct bio *bio)
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page && !PageCompound(page))
-			set_page_dirty_lock(page);
+		if (!PageCompound(bvec->bv_page))
+			set_page_dirty_lock(bvec->bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
@@ -1674,19 +1597,15 @@ static void bio_release_pages(struct bio *bio)
 	struct bio_vec *bvec;
 	int i;
 
-	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page)
-			put_page(page);
-	}
+	bio_for_each_segment_all(bvec, bio, i)
+		put_page(bvec->bv_page);
 }
 
 /*
  * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
  * If they are, then fine.  If, however, some pages are clean then they must
  * have been written out during the direct-IO read.  So we take another ref on
- * the BIO and the offending pages and re-dirty the pages in process context.
+ * the BIO and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
  * here on.  It will run one put_page() against each page and will run one
@@ -1704,78 +1623,70 @@ static struct bio *bio_dirty_list;
  */
 static void bio_dirty_fn(struct work_struct *work)
 {
-	unsigned long flags;
-	struct bio *bio;
+	struct bio *bio, *next;
 
-	spin_lock_irqsave(&bio_dirty_lock, flags);
-	bio = bio_dirty_list;
+	spin_lock_irq(&bio_dirty_lock);
+	next = bio_dirty_list;
 	bio_dirty_list = NULL;
-	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	spin_unlock_irq(&bio_dirty_lock);
 
-	while (bio) {
-		struct bio *next = bio->bi_private;
+	while ((bio = next) != NULL) {
+		next = bio->bi_private;
 
 		bio_set_pages_dirty(bio);
 		bio_release_pages(bio);
 		bio_put(bio);
-		bio = next;
 	}
 }
 
 void bio_check_pages_dirty(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int nr_clean_pages = 0;
+	unsigned long flags;
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (PageDirty(page) || PageCompound(page)) {
-			put_page(page);
-			bvec->bv_page = NULL;
-		} else {
-			nr_clean_pages++;
-		}
+		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
+			goto defer;
 	}
 
-	if (nr_clean_pages) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&bio_dirty_lock, flags);
-		bio->bi_private = bio_dirty_list;
-		bio_dirty_list = bio;
-		spin_unlock_irqrestore(&bio_dirty_lock, flags);
-		schedule_work(&bio_dirty_work);
-	} else {
-		bio_put(bio);
-	}
+	bio_release_pages(bio);
+	bio_put(bio);
+	return;
+defer:
+	spin_lock_irqsave(&bio_dirty_lock, flags);
+	bio->bi_private = bio_dirty_list;
+	bio_dirty_list = bio;
+	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	schedule_work(&bio_dirty_work);
 }
 EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
 
-void generic_start_io_acct(struct request_queue *q, int rw,
+void generic_start_io_acct(struct request_queue *q, int op,
 			   unsigned long sectors, struct hd_struct *part)
 {
+	const int sgrp = op_stat_group(op);
 	int cpu = part_stat_lock();
 
 	part_round_stats(q, cpu, part);
-	part_stat_inc(cpu, part, ios[rw]);
-	part_stat_add(cpu, part, sectors[rw], sectors);
-	part_inc_in_flight(q, part, rw);
+	part_stat_inc(cpu, part, ios[sgrp]);
+	part_stat_add(cpu, part, sectors[sgrp], sectors);
+	part_inc_in_flight(q, part, op_is_write(op));
 
 	part_stat_unlock();
 }
 EXPORT_SYMBOL(generic_start_io_acct);
 
-void generic_end_io_acct(struct request_queue *q, int rw,
+void generic_end_io_acct(struct request_queue *q, int req_op,
 			 struct hd_struct *part, unsigned long start_time)
 {
 	unsigned long duration = jiffies - start_time;
+	const int sgrp = op_stat_group(req_op);
 	int cpu = part_stat_lock();
 
-	part_stat_add(cpu, part, ticks[rw], duration);
+	part_stat_add(cpu, part, ticks[sgrp], duration);
 	part_round_stats(q, cpu, part);
-	part_dec_in_flight(q, part, rw);
+	part_dec_in_flight(q, part, op_is_write(req_op));
 
 	part_stat_unlock();
 }
@@ -1834,6 +1745,9 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
+	if (bio->bi_disk)
+		rq_qos_done_bio(bio->bi_disk->queue, bio);
+
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that
@@ -2042,6 +1956,30 @@ EXPORT_SYMBOL(bioset_init_from_src);
 
 #ifdef CONFIG_BLK_CGROUP
 
+#ifdef CONFIG_MEMCG
+/**
+ * bio_associate_blkcg_from_page - associate a bio with the page's blkcg
+ * @bio: target bio
+ * @page: the page to lookup the blkcg from
+ *
+ * Associate @bio with the blkcg from @page's owning memcg.  This works like
+ * every other associate function wrt references.
+ */
+int bio_associate_blkcg_from_page(struct bio *bio, struct page *page)
+{
+	struct cgroup_subsys_state *blkcg_css;
+
+	if (unlikely(bio->bi_css))
+		return -EBUSY;
+	if (!page->mem_cgroup)
+		return 0;
+	blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup,
+				     &io_cgrp_subsys);
+	bio->bi_css = blkcg_css;
+	return 0;
+}
+#endif /* CONFIG_MEMCG */
+
 /**
  * bio_associate_blkcg - associate a bio with the specified blkcg
  * @bio: target bio
@@ -2065,6 +2003,24 @@ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
 EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
 /**
+ * bio_associate_blkg - associate a bio with the specified blkg
+ * @bio: target bio
+ * @blkg: the blkg to associate
+ *
+ * Associate @bio with the blkg specified by @blkg.  This is the queue specific
+ * blkcg information associated with the @bio, a reference will be taken on the
+ * @blkg and will be freed when the bio is freed.
+ */
+int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
+{
+	if (unlikely(bio->bi_blkg))
+		return -EBUSY;
+	blkg_get(blkg);
+	bio->bi_blkg = blkg;
+	return 0;
+}
+
+/**
  * bio_disassociate_task - undo bio_associate_current()
  * @bio: target bio
  */
@@ -2078,6 +2034,10 @@ void bio_disassociate_task(struct bio *bio)
 		css_put(bio->bi_css);
 		bio->bi_css = NULL;
 	}
+	if (bio->bi_blkg) {
+		blkg_put(bio->bi_blkg);
+		bio->bi_blkg = NULL;
+	}
 }
 
 /**
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index eb85cb87c40f..694595b29b8f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -27,6 +27,7 @@
 #include <linux/atomic.h>
 #include <linux/ctype.h>
 #include <linux/blk-cgroup.h>
+#include <linux/tracehook.h>
 #include "blk.h"
 
 #define MAX_KEY_LEN 100
@@ -50,6 +51,8 @@ static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
 static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
 
+static bool blkcg_debug_stats = false;
+
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -564,6 +567,7 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
 		[BLKG_RWSTAT_WRITE]	= "Write",
 		[BLKG_RWSTAT_SYNC]	= "Sync",
 		[BLKG_RWSTAT_ASYNC]	= "Async",
+		[BLKG_RWSTAT_DISCARD]	= "Discard",
 	};
 	const char *dname = blkg_dev_name(pd->blkg);
 	u64 v;
@@ -577,7 +581,8 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
 			   (unsigned long long)atomic64_read(&rwstat->aux_cnt[i]));
 
 	v = atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_READ]) +
-		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]);
+		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]) +
+		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_DISCARD]);
 	seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v);
 	return v;
 }
@@ -954,30 +959,77 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
 		const char *dname;
+		char *buf;
 		struct blkg_rwstat rwstat;
-		u64 rbytes, wbytes, rios, wios;
+		u64 rbytes, wbytes, rios, wios, dbytes, dios;
+		size_t size = seq_get_buf(sf, &buf), off = 0;
+		int i;
+		bool has_stats = false;
 
 		dname = blkg_dev_name(blkg);
 		if (!dname)
 			continue;
 
+		/*
+		 * Hooray string manipulation, count is the size written NOT
+		 * INCLUDING THE \0, so size is now count+1 less than what we
+		 * had before, but we want to start writing the next bit from
+		 * the \0 so we only add count to buf.
+		 */
+		off += scnprintf(buf+off, size-off, "%s ", dname);
+
 		spin_lock_irq(blkg->q->queue_lock);
 
 		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
 					offsetof(struct blkcg_gq, stat_bytes));
 		rbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
 		wbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
+		dbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]);
 
 		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
 					offsetof(struct blkcg_gq, stat_ios));
 		rios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
 		wios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
+		dios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]);
 
 		spin_unlock_irq(blkg->q->queue_lock);
 
-		if (rbytes || wbytes || rios || wios)
-			seq_printf(sf, "%s rbytes=%llu wbytes=%llu rios=%llu wios=%llu\n",
-				   dname, rbytes, wbytes, rios, wios);
+		if (rbytes || wbytes || rios || wios) {
+			has_stats = true;
+			off += scnprintf(buf+off, size-off,
+					 "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu",
+					 rbytes, wbytes, rios, wios,
+					 dbytes, dios);
+		}
+
+		if (!blkcg_debug_stats)
+			goto next;
+
+		if (atomic_read(&blkg->use_delay)) {
+			has_stats = true;
+			off += scnprintf(buf+off, size-off,
+					 " use_delay=%d delay_nsec=%llu",
+					 atomic_read(&blkg->use_delay),
+					(unsigned long long)atomic64_read(&blkg->delay_nsec));
+		}
+
+		for (i = 0; i < BLKCG_MAX_POLS; i++) {
+			struct blkcg_policy *pol = blkcg_policy[i];
+			size_t written;
+
+			if (!blkg->pd[i] || !pol->pd_stat_fn)
+				continue;
+
+			written = pol->pd_stat_fn(blkg->pd[i], buf+off, size-off);
+			if (written)
+				has_stats = true;
+			off += written;
+		}
+next:
+		if (has_stats) {
+			off += scnprintf(buf+off, size-off, "\n");
+			seq_commit(sf, off);
+		}
 	}
 
 	rcu_read_unlock();
@@ -1191,6 +1243,14 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
+	ret = blk_iolatency_init(q);
+	if (ret) {
+		spin_lock_irq(q->queue_lock);
+		blkg_destroy_all(q);
+		spin_unlock_irq(q->queue_lock);
+		return ret;
+	}
+
 	ret = blk_throtl_init(q);
 	if (ret) {
 		spin_lock_irq(q->queue_lock);
@@ -1288,6 +1348,13 @@ static void blkcg_bind(struct cgroup_subsys_state *root_css)
 	mutex_unlock(&blkcg_pol_mutex);
 }
 
+static void blkcg_exit(struct task_struct *tsk)
+{
+	if (tsk->throttle_queue)
+		blk_put_queue(tsk->throttle_queue);
+	tsk->throttle_queue = NULL;
+}
+
 struct cgroup_subsys io_cgrp_subsys = {
 	.css_alloc = blkcg_css_alloc,
 	.css_offline = blkcg_css_offline,
@@ -1297,6 +1364,7 @@ struct cgroup_subsys io_cgrp_subsys = {
 	.dfl_cftypes = blkcg_files,
 	.legacy_cftypes = blkcg_legacy_files,
 	.legacy_name = "blkio",
+	.exit = blkcg_exit,
 #ifdef CONFIG_MEMCG
 	/*
 	 * This ensures that, if available, memcg is automatically enabled
@@ -1547,3 +1615,209 @@ out_unlock:
 	mutex_unlock(&blkcg_pol_register_mutex);
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
+
+/*
+ * Scale the accumulated delay based on how long it has been since we updated
+ * the delay.  We only call this when we are adding delay, in case it's been a
+ * while since we added delay, and when we are checking to see if we need to
+ * delay a task, to account for any delays that may have occurred.
+ */
+static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
+{
+	u64 old = atomic64_read(&blkg->delay_start);
+
+	/*
+	 * We only want to scale down every second.  The idea here is that we
+	 * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain
+	 * time window.  We only want to throttle tasks for recent delay that
+	 * has occurred, in 1 second time windows since that's the maximum
+	 * things can be throttled.  We save the current delay window in
+	 * blkg->last_delay so we know what amount is still left to be charged
+	 * to the blkg from this point onward.  blkg->last_use keeps track of
+	 * the use_delay counter.  The idea is if we're unthrottling the blkg we
+	 * are ok with whatever is happening now, and we can take away more of
+	 * the accumulated delay as we've already throttled enough that
+	 * everybody is happy with their IO latencies.
+	 */
+	if (time_before64(old + NSEC_PER_SEC, now) &&
+	    atomic64_cmpxchg(&blkg->delay_start, old, now) == old) {
+		u64 cur = atomic64_read(&blkg->delay_nsec);
+		u64 sub = min_t(u64, blkg->last_delay, now - old);
+		int cur_use = atomic_read(&blkg->use_delay);
+
+		/*
+		 * We've been unthrottled, subtract a larger chunk of our
+		 * accumulated delay.
+		 */
+		if (cur_use < blkg->last_use)
+			sub = max_t(u64, sub, blkg->last_delay >> 1);
+
+		/*
+		 * This shouldn't happen, but handle it anyway.  Our delay_nsec
+		 * should only ever be growing except here where we subtract out
+		 * min(last_delay, 1 second), but lord knows bugs happen and I'd
+		 * rather not end up with negative numbers.
+		 */
+		if (unlikely(cur < sub)) {
+			atomic64_set(&blkg->delay_nsec, 0);
+			blkg->last_delay = 0;
+		} else {
+			atomic64_sub(sub, &blkg->delay_nsec);
+			blkg->last_delay = cur - sub;
+		}
+		blkg->last_use = cur_use;
+	}
+}
+
+/*
+ * This is called when we want to actually walk up the hierarchy and check to
+ * see if we need to throttle, and then actually throttle if there is some
+ * accumulated delay.  This should only be called upon return to user space so
+ * we're not holding some lock that would induce a priority inversion.
+ */
+static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
+{
+	u64 now = ktime_to_ns(ktime_get());
+	u64 exp;
+	u64 delay_nsec = 0;
+	int tok;
+
+	while (blkg->parent) {
+		if (atomic_read(&blkg->use_delay)) {
+			blkcg_scale_delay(blkg, now);
+			delay_nsec = max_t(u64, delay_nsec,
+					   atomic64_read(&blkg->delay_nsec));
+		}
+		blkg = blkg->parent;
+	}
+
+	if (!delay_nsec)
+		return;
+
+	/*
+	 * Let's not sleep for all eternity if we've amassed a huge delay.
+	 * Swapping or metadata IO can accumulate 10's of seconds worth of
+	 * delay, and we want userspace to be able to do _something_ so cap the
+	 * delays at 1 second.  If there's 10's of seconds worth of delay then
+	 * the tasks will be delayed for 1 second for every syscall.
+	 */
+	delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
+
+	/*
+	 * TODO: the use_memdelay flag is going to be for the upcoming psi stuff
+	 * that hasn't landed upstream yet.  Once that stuff is in place we need
+	 * to do a psi_memstall_enter/leave if memdelay is set.
+	 */
+
+	exp = ktime_add_ns(now, delay_nsec);
+	tok = io_schedule_prepare();
+	do {
+		__set_current_state(TASK_KILLABLE);
+		if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS))
+			break;
+	} while (!fatal_signal_pending(current));
+	io_schedule_finish(tok);
+}
+
+/**
+ * blkcg_maybe_throttle_current - throttle the current task if it has been marked
+ *
+ * This is only called if we've been marked with set_notify_resume().  Obviously
+ * we can be set_notify_resume() for reasons other than blkcg throttling, so we
+ * check to see if current->throttle_queue is set and if not this doesn't do
+ * anything.  This should only ever be called by the resume code, it's not meant
+ * to be called by people willy-nilly as it will actually do the work to
+ * throttle the task if it is setup for throttling.
+ */
+void blkcg_maybe_throttle_current(void)
+{
+	struct request_queue *q = current->throttle_queue;
+	struct cgroup_subsys_state *css;
+	struct blkcg *blkcg;
+	struct blkcg_gq *blkg;
+	bool use_memdelay = current->use_memdelay;
+
+	if (!q)
+		return;
+
+	current->throttle_queue = NULL;
+	current->use_memdelay = false;
+
+	rcu_read_lock();
+	css = kthread_blkcg();
+	if (css)
+		blkcg = css_to_blkcg(css);
+	else
+		blkcg = css_to_blkcg(task_css(current, io_cgrp_id));
+
+	if (!blkcg)
+		goto out;
+	blkg = blkg_lookup(blkcg, q);
+	if (!blkg)
+		goto out;
+	blkg = blkg_try_get(blkg);
+	if (!blkg)
+		goto out;
+	rcu_read_unlock();
+
+	blkcg_maybe_throttle_blkg(blkg, use_memdelay);
+	blkg_put(blkg);
+	blk_put_queue(q);
+	return;
+out:
+	rcu_read_unlock();
+	blk_put_queue(q);
+}
+EXPORT_SYMBOL_GPL(blkcg_maybe_throttle_current);
+
+/**
+ * blkcg_schedule_throttle - this task needs to check for throttling
+ * @q - the request queue IO was submitted on
+ * @use_memdelay - do we charge this to memory delay for PSI
+ *
+ * This is called by the IO controller when we know there's delay accumulated
+ * for the blkg for this task.  We do not pass the blkg because there are places
+ * we call this that may not have that information, the swapping code for
+ * instance will only have a request_queue at that point.  This set's the
+ * notify_resume for the task to check and see if it requires throttling before
+ * returning to user space.
+ *
+ * We will only schedule once per syscall.  You can call this over and over
+ * again and it will only do the check once upon return to user space, and only
+ * throttle once.  If the task needs to be throttled again it'll need to be
+ * re-set at the next time we see the task.
+ */
+void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay)
+{
+	if (unlikely(current->flags & PF_KTHREAD))
+		return;
+
+	if (!blk_get_queue(q))
+		return;
+
+	if (current->throttle_queue)
+		blk_put_queue(current->throttle_queue);
+	current->throttle_queue = q;
+	if (use_memdelay)
+		current->use_memdelay = use_memdelay;
+	set_notify_resume(current);
+}
+EXPORT_SYMBOL_GPL(blkcg_schedule_throttle);
+
+/**
+ * blkcg_add_delay - add delay to this blkg
+ * @now - the current time in nanoseconds
+ * @delta - how many nanoseconds of delay to add
+ *
+ * Charge @delta to the blkg's current delay accumulation.  This is used to
+ * throttle tasks if an IO controller thinks we need more throttling.
+ */
+void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
+{
+	blkcg_scale_delay(blkg, now);
+	atomic64_add(delta, &blkg->delay_nsec);
+}
+EXPORT_SYMBOL_GPL(blkcg_add_delay);
+
+module_param(blkcg_debug_stats, bool, 0644);
+MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not");
diff --git a/block/blk-core.c b/block/blk-core.c
index ee33590f54eb..12550340418d 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -42,7 +42,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-sched.h"
-#include "blk-wbt.h"
+#include "blk-rq-qos.h"
 
 #ifdef CONFIG_DEBUG_FS
 struct dentry *blk_debugfs_root;
@@ -715,6 +715,35 @@ void blk_set_queue_dying(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
 
+/* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
+void blk_exit_queue(struct request_queue *q)
+{
+	/*
+	 * Since the I/O scheduler exit code may access cgroup information,
+	 * perform I/O scheduler exit before disassociating from the block
+	 * cgroup controller.
+	 */
+	if (q->elevator) {
+		ioc_clear_queue(q);
+		elevator_exit(q, q->elevator);
+		q->elevator = NULL;
+	}
+
+	/*
+	 * Remove all references to @q from the block cgroup controller before
+	 * restoring @q->queue_lock to avoid that restoring this pointer causes
+	 * e.g. blkcg_print_blkgs() to crash.
+	 */
+	blkcg_exit_queue(q);
+
+	/*
+	 * Since the cgroup code may dereference the @q->backing_dev_info
+	 * pointer, only decrease its reference count after having removed the
+	 * association with the block cgroup controller.
+	 */
+	bdi_put(q->backing_dev_info);
+}
+
 /**
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
@@ -762,9 +791,13 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * make sure all in-progress dispatch are completed because
 	 * blk_freeze_queue() can only complete all requests, and
 	 * dispatch may still be in-progress since we dispatch requests
-	 * from more than one contexts
+	 * from more than one contexts.
+	 *
+	 * No need to quiesce queue if it isn't initialized yet since
+	 * blk_freeze_queue() should be enough for cases of passthrough
+	 * request.
 	 */
-	if (q->mq_ops)
+	if (q->mq_ops && blk_queue_init_done(q))
 		blk_mq_quiesce_queue(q);
 
 	/* for synchronous bio-based driver finish in-flight integrity i/o */
@@ -780,30 +813,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	 */
 	WARN_ON_ONCE(q->kobj.state_in_sysfs);
 
-	/*
-	 * Since the I/O scheduler exit code may access cgroup information,
-	 * perform I/O scheduler exit before disassociating from the block
-	 * cgroup controller.
-	 */
-	if (q->elevator) {
-		ioc_clear_queue(q);
-		elevator_exit(q, q->elevator);
-		q->elevator = NULL;
-	}
-
-	/*
-	 * Remove all references to @q from the block cgroup controller before
-	 * restoring @q->queue_lock to avoid that restoring this pointer causes
-	 * e.g. blkcg_print_blkgs() to crash.
-	 */
-	blkcg_exit_queue(q);
-
-	/*
-	 * Since the cgroup code may dereference the @q->backing_dev_info
-	 * pointer, only decrease its reference count after having removed the
-	 * association with the block cgroup controller.
-	 */
-	bdi_put(q->backing_dev_info);
+	blk_exit_queue(q);
 
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
@@ -1180,6 +1190,7 @@ out_exit_flush_rq:
 		q->exit_rq_fn(q, q->fq->flush_rq);
 out_free_flush_queue:
 	blk_free_flush_queue(q->fq);
+	q->fq = NULL;
 	return -ENOMEM;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -1641,7 +1652,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 	blk_delete_timer(rq);
 	blk_clear_rq_complete(rq);
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, rq);
+	rq_qos_requeue(q, rq);
 
 	if (rq->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, rq);
@@ -1748,7 +1759,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	/* this is a bio leak */
 	WARN_ON(req->bio != NULL);
 
-	wbt_done(q->rq_wb, req);
+	rq_qos_done(q, req);
 
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
@@ -1982,7 +1993,6 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	int where = ELEVATOR_INSERT_SORT;
 	struct request *req, *free;
 	unsigned int request_count = 0;
-	unsigned int wb_acct;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -2040,7 +2050,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 get_rq:
-	wb_acct = wbt_wait(q->rq_wb, bio, q->queue_lock);
+	rq_qos_throttle(q, bio, q->queue_lock);
 
 	/*
 	 * Grab a free request. This is might sleep but can not fail.
@@ -2050,7 +2060,7 @@ get_rq:
 	req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
 	if (IS_ERR(req)) {
 		blk_queue_exit(q);
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, bio);
 		if (PTR_ERR(req) == -ENOMEM)
 			bio->bi_status = BLK_STS_RESOURCE;
 		else
@@ -2059,7 +2069,7 @@ get_rq:
 		goto out_unlock;
 	}
 
-	wbt_track(req, wb_acct);
+	rq_qos_track(q, req, bio);
 
 	/*
 	 * After dropping the lock and possibly sleeping here, our request
@@ -2700,13 +2710,13 @@ EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (blk_do_io_stat(req)) {
-		const int rw = rq_data_dir(req);
+		const int sgrp = op_stat_group(req_op(req));
 		struct hd_struct *part;
 		int cpu;
 
 		cpu = part_stat_lock();
 		part = req->part;
-		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+		part_stat_add(cpu, part, sectors[sgrp], bytes >> 9);
 		part_stat_unlock();
 	}
 }
@@ -2720,7 +2730,7 @@ void blk_account_io_done(struct request *req, u64 now)
 	 */
 	if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
 		unsigned long duration;
-		const int rw = rq_data_dir(req);
+		const int sgrp = op_stat_group(req_op(req));
 		struct hd_struct *part;
 		int cpu;
 
@@ -2728,10 +2738,10 @@ void blk_account_io_done(struct request *req, u64 now)
 		cpu = part_stat_lock();
 		part = req->part;
 
-		part_stat_inc(cpu, part, ios[rw]);
-		part_stat_add(cpu, part, ticks[rw], duration);
+		part_stat_inc(cpu, part, ios[sgrp]);
+		part_stat_add(cpu, part, ticks[sgrp], duration);
 		part_round_stats(req->q, cpu, part);
-		part_dec_in_flight(req->q, part, rw);
+		part_dec_in_flight(req->q, part, rq_data_dir(req));
 
 		hd_struct_put(part);
 		part_stat_unlock();
@@ -2751,9 +2761,9 @@ static bool blk_pm_allow_request(struct request *rq)
 		return rq->rq_flags & RQF_PM;
 	case RPM_SUSPENDED:
 		return false;
+	default:
+		return true;
 	}
-
-	return true;
 }
 #else
 static bool blk_pm_allow_request(struct request *rq)
@@ -2980,7 +2990,7 @@ void blk_start_request(struct request *req)
 		req->throtl_size = blk_rq_sectors(req);
 #endif
 		req->rq_flags |= RQF_STATS;
-		wbt_issue(req->q->rq_wb, req);
+		rq_qos_issue(req->q, req);
 	}
 
 	BUG_ON(blk_rq_is_complete(req));
@@ -3053,6 +3063,10 @@ EXPORT_SYMBOL_GPL(blk_steal_bios);
  *     Passing the result of blk_rq_bytes() as @nr_bytes guarantees
  *     %false return from this function.
  *
+ * Note:
+ *	The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in both
+ *	blk_rq_bytes() and in blk_update_request().
+ *
  * Return:
  *     %false - this request doesn't have any more data
  *     %true  - this request has more data
@@ -3200,7 +3214,7 @@ void blk_finish_request(struct request *req, blk_status_t error)
 	blk_account_io_done(req, now);
 
 	if (req->end_io) {
-		wbt_done(req->q->rq_wb, req);
+		rq_qos_done(q, req);
 		req->end_io(req, error);
 	} else {
 		if (blk_bidi_rq(req))
@@ -3763,9 +3777,11 @@ EXPORT_SYMBOL(blk_finish_plug);
  */
 void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
 {
-	/* not support for RQF_PM and ->rpm_status in blk-mq yet */
-	if (q->mq_ops)
+	/* Don't enable runtime PM for blk-mq until it is ready */
+	if (q->mq_ops) {
+		pm_runtime_disable(dev);
 		return;
+	}
 
 	q->dev = dev;
 	q->rpm_status = RPM_ACTIVE;
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index f23311e4b201..01580f88fcb3 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -278,7 +278,7 @@ int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
 	atomic_set(&ioc->nr_tasks, 1);
 	atomic_set(&ioc->active_ref, 1);
 	spin_lock_init(&ioc->lock);
-	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC | __GFP_HIGH);
+	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC);
 	INIT_HLIST_HEAD(&ioc->icq_list);
 	INIT_WORK(&ioc->release_work, ioc_release_fn);
 
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
new file mode 100644
index 000000000000..19923f8a029d
--- /dev/null
+++ b/block/blk-iolatency.c
@@ -0,0 +1,955 @@
+/*
+ * Block rq-qos base io controller
+ *
+ * This works similar to wbt with a few exceptions
+ *
+ * - It's bio based, so the latency covers the whole block layer in addition to
+ *   the actual io.
+ * - We will throttle all IO that comes in here if we need to.
+ * - We use the mean latency over the 100ms window.  This is because writes can
+ *   be particularly fast, which could give us a false sense of the impact of
+ *   other workloads on our protected workload.
+ * - By default there's no throttling, we set the queue_depth to UINT_MAX so
+ *   that we can have as many outstanding bio's as we're allowed to.  Only at
+ *   throttle time do we pay attention to the actual queue depth.
+ *
+ * The hierarchy works like the cpu controller does, we track the latency at
+ * every configured node, and each configured node has it's own independent
+ * queue depth.  This means that we only care about our latency targets at the
+ * peer level.  Some group at the bottom of the hierarchy isn't going to affect
+ * a group at the end of some other path if we're only configred at leaf level.
+ *
+ * Consider the following
+ *
+ *                   root blkg
+ *             /                     \
+ *        fast (target=5ms)     slow (target=10ms)
+ *         /     \                  /        \
+ *       a        b          normal(15ms)   unloved
+ *
+ * "a" and "b" have no target, but their combined io under "fast" cannot exceed
+ * an average latency of 5ms.  If it does then we will throttle the "slow"
+ * group.  In the case of "normal", if it exceeds its 15ms target, we will
+ * throttle "unloved", but nobody else.
+ *
+ * In this example "fast", "slow", and "normal" will be the only groups actually
+ * accounting their io latencies.  We have to walk up the heirarchy to the root
+ * on every submit and complete so we can do the appropriate stat recording and
+ * adjust the queue depth of ourselves if needed.
+ *
+ * There are 2 ways we throttle IO.
+ *
+ * 1) Queue depth throttling.  As we throttle down we will adjust the maximum
+ * number of IO's we're allowed to have in flight.  This starts at (u64)-1 down
+ * to 1.  If the group is only ever submitting IO for itself then this is the
+ * only way we throttle.
+ *
+ * 2) Induced delay throttling.  This is for the case that a group is generating
+ * IO that has to be issued by the root cg to avoid priority inversion. So think
+ * REQ_META or REQ_SWAP.  If we are already at qd == 1 and we're getting a lot
+ * of work done for us on behalf of the root cg and are being asked to scale
+ * down more then we induce a latency at userspace return.  We accumulate the
+ * total amount of time we need to be punished by doing
+ *
+ * total_time += min_lat_nsec - actual_io_completion
+ *
+ * and then at throttle time will do
+ *
+ * throttle_time = min(total_time, NSEC_PER_SEC)
+ *
+ * This induced delay will throttle back the activity that is generating the
+ * root cg issued io's, wethere that's some metadata intensive operation or the
+ * group is using so much memory that it is pushing us into swap.
+ *
+ * Copyright (C) 2018 Josef Bacik
+ */
+#include <linux/kernel.h>
+#include <linux/blk_types.h>
+#include <linux/backing-dev.h>
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/memcontrol.h>
+#include <linux/sched/loadavg.h>
+#include <linux/sched/signal.h>
+#include <trace/events/block.h>
+#include "blk-rq-qos.h"
+#include "blk-stat.h"
+
+#define DEFAULT_SCALE_COOKIE 1000000U
+
+static struct blkcg_policy blkcg_policy_iolatency;
+struct iolatency_grp;
+
+struct blk_iolatency {
+	struct rq_qos rqos;
+	struct timer_list timer;
+	atomic_t enabled;
+};
+
+static inline struct blk_iolatency *BLKIOLATENCY(struct rq_qos *rqos)
+{
+	return container_of(rqos, struct blk_iolatency, rqos);
+}
+
+static inline bool blk_iolatency_enabled(struct blk_iolatency *blkiolat)
+{
+	return atomic_read(&blkiolat->enabled) > 0;
+}
+
+struct child_latency_info {
+	spinlock_t lock;
+
+	/* Last time we adjusted the scale of everybody. */
+	u64 last_scale_event;
+
+	/* The latency that we missed. */
+	u64 scale_lat;
+
+	/* Total io's from all of our children for the last summation. */
+	u64 nr_samples;
+
+	/* The guy who actually changed the latency numbers. */
+	struct iolatency_grp *scale_grp;
+
+	/* Cookie to tell if we need to scale up or down. */
+	atomic_t scale_cookie;
+};
+
+struct iolatency_grp {
+	struct blkg_policy_data pd;
+	struct blk_rq_stat __percpu *stats;
+	struct blk_iolatency *blkiolat;
+	struct rq_depth rq_depth;
+	struct rq_wait rq_wait;
+	atomic64_t window_start;
+	atomic_t scale_cookie;
+	u64 min_lat_nsec;
+	u64 cur_win_nsec;
+
+	/* total running average of our io latency. */
+	u64 lat_avg;
+
+	/* Our current number of IO's for the last summation. */
+	u64 nr_samples;
+
+	struct child_latency_info child_lat;
+};
+
+#define BLKIOLATENCY_MIN_WIN_SIZE (100 * NSEC_PER_MSEC)
+#define BLKIOLATENCY_MAX_WIN_SIZE NSEC_PER_SEC
+/*
+ * These are the constants used to fake the fixed-point moving average
+ * calculation just like load average.  The call to CALC_LOAD folds
+ * (FIXED_1 (2048) - exp_factor) * new_sample into lat_avg.  The sampling
+ * window size is bucketed to try to approximately calculate average
+ * latency such that 1/exp (decay rate) is [1 min, 2.5 min) when windows
+ * elapse immediately.  Note, windows only elapse with IO activity.  Idle
+ * periods extend the most recent window.
+ */
+#define BLKIOLATENCY_NR_EXP_FACTORS 5
+#define BLKIOLATENCY_EXP_BUCKET_SIZE (BLKIOLATENCY_MAX_WIN_SIZE / \
+				      (BLKIOLATENCY_NR_EXP_FACTORS - 1))
+static const u64 iolatency_exp_factors[BLKIOLATENCY_NR_EXP_FACTORS] = {
+	2045, // exp(1/600) - 600 samples
+	2039, // exp(1/240) - 240 samples
+	2031, // exp(1/120) - 120 samples
+	2023, // exp(1/80)  - 80 samples
+	2014, // exp(1/60)  - 60 samples
+};
+
+static inline struct iolatency_grp *pd_to_lat(struct blkg_policy_data *pd)
+{
+	return pd ? container_of(pd, struct iolatency_grp, pd) : NULL;
+}
+
+static inline struct iolatency_grp *blkg_to_lat(struct blkcg_gq *blkg)
+{
+	return pd_to_lat(blkg_to_pd(blkg, &blkcg_policy_iolatency));
+}
+
+static inline struct blkcg_gq *lat_to_blkg(struct iolatency_grp *iolat)
+{
+	return pd_to_blkg(&iolat->pd);
+}
+
+static inline bool iolatency_may_queue(struct iolatency_grp *iolat,
+				       wait_queue_entry_t *wait,
+				       bool first_block)
+{
+	struct rq_wait *rqw = &iolat->rq_wait;
+
+	if (first_block && waitqueue_active(&rqw->wait) &&
+	    rqw->wait.head.next != &wait->entry)
+		return false;
+	return rq_wait_inc_below(rqw, iolat->rq_depth.max_depth);
+}
+
+static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
+				       struct iolatency_grp *iolat,
+				       spinlock_t *lock, bool issue_as_root,
+				       bool use_memdelay)
+	__releases(lock)
+	__acquires(lock)
+{
+	struct rq_wait *rqw = &iolat->rq_wait;
+	unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay);
+	DEFINE_WAIT(wait);
+	bool first_block = true;
+
+	if (use_delay)
+		blkcg_schedule_throttle(rqos->q, use_memdelay);
+
+	/*
+	 * To avoid priority inversions we want to just take a slot if we are
+	 * issuing as root.  If we're being killed off there's no point in
+	 * delaying things, we may have been killed by OOM so throttling may
+	 * make recovery take even longer, so just let the IO's through so the
+	 * task can go away.
+	 */
+	if (issue_as_root || fatal_signal_pending(current)) {
+		atomic_inc(&rqw->inflight);
+		return;
+	}
+
+	if (iolatency_may_queue(iolat, &wait, first_block))
+		return;
+
+	do {
+		prepare_to_wait_exclusive(&rqw->wait, &wait,
+					  TASK_UNINTERRUPTIBLE);
+
+		if (iolatency_may_queue(iolat, &wait, first_block))
+			break;
+		first_block = false;
+
+		if (lock) {
+			spin_unlock_irq(lock);
+			io_schedule();
+			spin_lock_irq(lock);
+		} else {
+			io_schedule();
+		}
+	} while (1);
+
+	finish_wait(&rqw->wait, &wait);
+}
+
+#define SCALE_DOWN_FACTOR 2
+#define SCALE_UP_FACTOR 4
+
+static inline unsigned long scale_amount(unsigned long qd, bool up)
+{
+	return max(up ? qd >> SCALE_UP_FACTOR : qd >> SCALE_DOWN_FACTOR, 1UL);
+}
+
+/*
+ * We scale the qd down faster than we scale up, so we need to use this helper
+ * to adjust the scale_cookie accordingly so we don't prematurely get
+ * scale_cookie at DEFAULT_SCALE_COOKIE and unthrottle too much.
+ *
+ * Each group has their own local copy of the last scale cookie they saw, so if
+ * the global scale cookie goes up or down they know which way they need to go
+ * based on their last knowledge of it.
+ */
+static void scale_cookie_change(struct blk_iolatency *blkiolat,
+				struct child_latency_info *lat_info,
+				bool up)
+{
+	unsigned long qd = blk_queue_depth(blkiolat->rqos.q);
+	unsigned long scale = scale_amount(qd, up);
+	unsigned long old = atomic_read(&lat_info->scale_cookie);
+	unsigned long max_scale = qd << 1;
+	unsigned long diff = 0;
+
+	if (old < DEFAULT_SCALE_COOKIE)
+		diff = DEFAULT_SCALE_COOKIE - old;
+
+	if (up) {
+		if (scale + old > DEFAULT_SCALE_COOKIE)
+			atomic_set(&lat_info->scale_cookie,
+				   DEFAULT_SCALE_COOKIE);
+		else if (diff > qd)
+			atomic_inc(&lat_info->scale_cookie);
+		else
+			atomic_add(scale, &lat_info->scale_cookie);
+	} else {
+		/*
+		 * We don't want to dig a hole so deep that it takes us hours to
+		 * dig out of it.  Just enough that we don't throttle/unthrottle
+		 * with jagged workloads but can still unthrottle once pressure
+		 * has sufficiently dissipated.
+		 */
+		if (diff > qd) {
+			if (diff < max_scale)
+				atomic_dec(&lat_info->scale_cookie);
+		} else {
+			atomic_sub(scale, &lat_info->scale_cookie);
+		}
+	}
+}
+
+/*
+ * Change the queue depth of the iolatency_grp.  We add/subtract 1/16th of the
+ * queue depth at a time so we don't get wild swings and hopefully dial in to
+ * fairer distribution of the overall queue depth.
+ */
+static void scale_change(struct iolatency_grp *iolat, bool up)
+{
+	unsigned long qd = blk_queue_depth(iolat->blkiolat->rqos.q);
+	unsigned long scale = scale_amount(qd, up);
+	unsigned long old = iolat->rq_depth.max_depth;
+	bool changed = false;
+
+	if (old > qd)
+		old = qd;
+
+	if (up) {
+		if (old == 1 && blkcg_unuse_delay(lat_to_blkg(iolat)))
+			return;
+
+		if (old < qd) {
+			changed = true;
+			old += scale;
+			old = min(old, qd);
+			iolat->rq_depth.max_depth = old;
+			wake_up_all(&iolat->rq_wait.wait);
+		}
+	} else if (old > 1) {
+		old >>= 1;
+		changed = true;
+		iolat->rq_depth.max_depth = max(old, 1UL);
+	}
+}
+
+/* Check our parent and see if the scale cookie has changed. */
+static void check_scale_change(struct iolatency_grp *iolat)
+{
+	struct iolatency_grp *parent;
+	struct child_latency_info *lat_info;
+	unsigned int cur_cookie;
+	unsigned int our_cookie = atomic_read(&iolat->scale_cookie);
+	u64 scale_lat;
+	unsigned int old;
+	int direction = 0;
+
+	if (lat_to_blkg(iolat)->parent == NULL)
+		return;
+
+	parent = blkg_to_lat(lat_to_blkg(iolat)->parent);
+	if (!parent)
+		return;
+
+	lat_info = &parent->child_lat;
+	cur_cookie = atomic_read(&lat_info->scale_cookie);
+	scale_lat = READ_ONCE(lat_info->scale_lat);
+
+	if (cur_cookie < our_cookie)
+		direction = -1;
+	else if (cur_cookie > our_cookie)
+		direction = 1;
+	else
+		return;
+
+	old = atomic_cmpxchg(&iolat->scale_cookie, our_cookie, cur_cookie);
+
+	/* Somebody beat us to the punch, just bail. */
+	if (old != our_cookie)
+		return;
+
+	if (direction < 0 && iolat->min_lat_nsec) {
+		u64 samples_thresh;
+
+		if (!scale_lat || iolat->min_lat_nsec <= scale_lat)
+			return;
+
+		/*
+		 * Sometimes high priority groups are their own worst enemy, so
+		 * instead of taking it out on some poor other group that did 5%
+		 * or less of the IO's for the last summation just skip this
+		 * scale down event.
+		 */
+		samples_thresh = lat_info->nr_samples * 5;
+		samples_thresh = div64_u64(samples_thresh, 100);
+		if (iolat->nr_samples <= samples_thresh)
+			return;
+	}
+
+	/* We're as low as we can go. */
+	if (iolat->rq_depth.max_depth == 1 && direction < 0) {
+		blkcg_use_delay(lat_to_blkg(iolat));
+		return;
+	}
+
+	/* We're back to the default cookie, unthrottle all the things. */
+	if (cur_cookie == DEFAULT_SCALE_COOKIE) {
+		blkcg_clear_delay(lat_to_blkg(iolat));
+		iolat->rq_depth.max_depth = UINT_MAX;
+		wake_up_all(&iolat->rq_wait.wait);
+		return;
+	}
+
+	scale_change(iolat, direction > 0);
+}
+
+static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
+				     spinlock_t *lock)
+{
+	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
+	struct blkcg *blkcg;
+	struct blkcg_gq *blkg;
+	struct request_queue *q = rqos->q;
+	bool issue_as_root = bio_issue_as_root_blkg(bio);
+
+	if (!blk_iolatency_enabled(blkiolat))
+		return;
+
+	rcu_read_lock();
+	blkcg = bio_blkcg(bio);
+	bio_associate_blkcg(bio, &blkcg->css);
+	blkg = blkg_lookup(blkcg, q);
+	if (unlikely(!blkg)) {
+		if (!lock)
+			spin_lock_irq(q->queue_lock);
+		blkg = blkg_lookup_create(blkcg, q);
+		if (IS_ERR(blkg))
+			blkg = NULL;
+		if (!lock)
+			spin_unlock_irq(q->queue_lock);
+	}
+	if (!blkg)
+		goto out;
+
+	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
+	bio_associate_blkg(bio, blkg);
+out:
+	rcu_read_unlock();
+	while (blkg && blkg->parent) {
+		struct iolatency_grp *iolat = blkg_to_lat(blkg);
+		if (!iolat) {
+			blkg = blkg->parent;
+			continue;
+		}
+
+		check_scale_change(iolat);
+		__blkcg_iolatency_throttle(rqos, iolat, lock, issue_as_root,
+				     (bio->bi_opf & REQ_SWAP) == REQ_SWAP);
+		blkg = blkg->parent;
+	}
+	if (!timer_pending(&blkiolat->timer))
+		mod_timer(&blkiolat->timer, jiffies + HZ);
+}
+
+static void iolatency_record_time(struct iolatency_grp *iolat,
+				  struct bio_issue *issue, u64 now,
+				  bool issue_as_root)
+{
+	struct blk_rq_stat *rq_stat;
+	u64 start = bio_issue_time(issue);
+	u64 req_time;
+
+	/*
+	 * Have to do this so we are truncated to the correct time that our
+	 * issue is truncated to.
+	 */
+	now = __bio_issue_time(now);
+
+	if (now <= start)
+		return;
+
+	req_time = now - start;
+
+	/*
+	 * We don't want to count issue_as_root bio's in the cgroups latency
+	 * statistics as it could skew the numbers downwards.
+	 */
+	if (unlikely(issue_as_root && iolat->rq_depth.max_depth != UINT_MAX)) {
+		u64 sub = iolat->min_lat_nsec;
+		if (req_time < sub)
+			blkcg_add_delay(lat_to_blkg(iolat), now, sub - req_time);
+		return;
+	}
+
+	rq_stat = get_cpu_ptr(iolat->stats);
+	blk_rq_stat_add(rq_stat, req_time);
+	put_cpu_ptr(rq_stat);
+}
+
+#define BLKIOLATENCY_MIN_ADJUST_TIME (500 * NSEC_PER_MSEC)
+#define BLKIOLATENCY_MIN_GOOD_SAMPLES 5
+
+static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now)
+{
+	struct blkcg_gq *blkg = lat_to_blkg(iolat);
+	struct iolatency_grp *parent;
+	struct child_latency_info *lat_info;
+	struct blk_rq_stat stat;
+	unsigned long flags;
+	int cpu, exp_idx;
+
+	blk_rq_stat_init(&stat);
+	preempt_disable();
+	for_each_online_cpu(cpu) {
+		struct blk_rq_stat *s;
+		s = per_cpu_ptr(iolat->stats, cpu);
+		blk_rq_stat_sum(&stat, s);
+		blk_rq_stat_init(s);
+	}
+	preempt_enable();
+
+	parent = blkg_to_lat(blkg->parent);
+	if (!parent)
+		return;
+
+	lat_info = &parent->child_lat;
+
+	/*
+	 * CALC_LOAD takes in a number stored in fixed point representation.
+	 * Because we are using this for IO time in ns, the values stored
+	 * are significantly larger than the FIXED_1 denominator (2048).
+	 * Therefore, rounding errors in the calculation are negligible and
+	 * can be ignored.
+	 */
+	exp_idx = min_t(int, BLKIOLATENCY_NR_EXP_FACTORS - 1,
+			div64_u64(iolat->cur_win_nsec,
+				  BLKIOLATENCY_EXP_BUCKET_SIZE));
+	CALC_LOAD(iolat->lat_avg, iolatency_exp_factors[exp_idx], stat.mean);
+
+	/* Everything is ok and we don't need to adjust the scale. */
+	if (stat.mean <= iolat->min_lat_nsec &&
+	    atomic_read(&lat_info->scale_cookie) == DEFAULT_SCALE_COOKIE)
+		return;
+
+	/* Somebody beat us to the punch, just bail. */
+	spin_lock_irqsave(&lat_info->lock, flags);
+	lat_info->nr_samples -= iolat->nr_samples;
+	lat_info->nr_samples += stat.nr_samples;
+	iolat->nr_samples = stat.nr_samples;
+
+	if ((lat_info->last_scale_event >= now ||
+	    now - lat_info->last_scale_event < BLKIOLATENCY_MIN_ADJUST_TIME) &&
+	    lat_info->scale_lat <= iolat->min_lat_nsec)
+		goto out;
+
+	if (stat.mean <= iolat->min_lat_nsec &&
+	    stat.nr_samples >= BLKIOLATENCY_MIN_GOOD_SAMPLES) {
+		if (lat_info->scale_grp == iolat) {
+			lat_info->last_scale_event = now;
+			scale_cookie_change(iolat->blkiolat, lat_info, true);
+		}
+	} else if (stat.mean > iolat->min_lat_nsec) {
+		lat_info->last_scale_event = now;
+		if (!lat_info->scale_grp ||
+		    lat_info->scale_lat > iolat->min_lat_nsec) {
+			WRITE_ONCE(lat_info->scale_lat, iolat->min_lat_nsec);
+			lat_info->scale_grp = iolat;
+		}
+		scale_cookie_change(iolat->blkiolat, lat_info, false);
+	}
+out:
+	spin_unlock_irqrestore(&lat_info->lock, flags);
+}
+
+static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
+{
+	struct blkcg_gq *blkg;
+	struct rq_wait *rqw;
+	struct iolatency_grp *iolat;
+	u64 window_start;
+	u64 now = ktime_to_ns(ktime_get());
+	bool issue_as_root = bio_issue_as_root_blkg(bio);
+	bool enabled = false;
+
+	blkg = bio->bi_blkg;
+	if (!blkg)
+		return;
+
+	iolat = blkg_to_lat(bio->bi_blkg);
+	if (!iolat)
+		return;
+
+	enabled = blk_iolatency_enabled(iolat->blkiolat);
+	while (blkg && blkg->parent) {
+		iolat = blkg_to_lat(blkg);
+		if (!iolat) {
+			blkg = blkg->parent;
+			continue;
+		}
+		rqw = &iolat->rq_wait;
+
+		atomic_dec(&rqw->inflight);
+		if (!enabled || iolat->min_lat_nsec == 0)
+			goto next;
+		iolatency_record_time(iolat, &bio->bi_issue, now,
+				      issue_as_root);
+		window_start = atomic64_read(&iolat->window_start);
+		if (now > window_start &&
+		    (now - window_start) >= iolat->cur_win_nsec) {
+			if (atomic64_cmpxchg(&iolat->window_start,
+					window_start, now) == window_start)
+				iolatency_check_latencies(iolat, now);
+		}
+next:
+		wake_up(&rqw->wait);
+		blkg = blkg->parent;
+	}
+}
+
+static void blkcg_iolatency_cleanup(struct rq_qos *rqos, struct bio *bio)
+{
+	struct blkcg_gq *blkg;
+
+	blkg = bio->bi_blkg;
+	while (blkg && blkg->parent) {
+		struct rq_wait *rqw;
+		struct iolatency_grp *iolat;
+
+		iolat = blkg_to_lat(blkg);
+		if (!iolat)
+			goto next;
+
+		rqw = &iolat->rq_wait;
+		atomic_dec(&rqw->inflight);
+		wake_up(&rqw->wait);
+next:
+		blkg = blkg->parent;
+	}
+}
+
+static void blkcg_iolatency_exit(struct rq_qos *rqos)
+{
+	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
+
+	del_timer_sync(&blkiolat->timer);
+	blkcg_deactivate_policy(rqos->q, &blkcg_policy_iolatency);
+	kfree(blkiolat);
+}
+
+static struct rq_qos_ops blkcg_iolatency_ops = {
+	.throttle = blkcg_iolatency_throttle,
+	.cleanup = blkcg_iolatency_cleanup,
+	.done_bio = blkcg_iolatency_done_bio,
+	.exit = blkcg_iolatency_exit,
+};
+
+static void blkiolatency_timer_fn(struct timer_list *t)
+{
+	struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer);
+	struct blkcg_gq *blkg;
+	struct cgroup_subsys_state *pos_css;
+	u64 now = ktime_to_ns(ktime_get());
+
+	rcu_read_lock();
+	blkg_for_each_descendant_pre(blkg, pos_css,
+				     blkiolat->rqos.q->root_blkg) {
+		struct iolatency_grp *iolat;
+		struct child_latency_info *lat_info;
+		unsigned long flags;
+		u64 cookie;
+
+		/*
+		 * We could be exiting, don't access the pd unless we have a
+		 * ref on the blkg.
+		 */
+		if (!blkg_try_get(blkg))
+			continue;
+
+		iolat = blkg_to_lat(blkg);
+		if (!iolat)
+			goto next;
+
+		lat_info = &iolat->child_lat;
+		cookie = atomic_read(&lat_info->scale_cookie);
+
+		if (cookie >= DEFAULT_SCALE_COOKIE)
+			goto next;
+
+		spin_lock_irqsave(&lat_info->lock, flags);
+		if (lat_info->last_scale_event >= now)
+			goto next_lock;
+
+		/*
+		 * We scaled down but don't have a scale_grp, scale up and carry
+		 * on.
+		 */
+		if (lat_info->scale_grp == NULL) {
+			scale_cookie_change(iolat->blkiolat, lat_info, true);
+			goto next_lock;
+		}
+
+		/*
+		 * It's been 5 seconds since our last scale event, clear the
+		 * scale grp in case the group that needed the scale down isn't
+		 * doing any IO currently.
+		 */
+		if (now - lat_info->last_scale_event >=
+		    ((u64)NSEC_PER_SEC * 5))
+			lat_info->scale_grp = NULL;
+next_lock:
+		spin_unlock_irqrestore(&lat_info->lock, flags);
+next:
+		blkg_put(blkg);
+	}
+	rcu_read_unlock();
+}
+
+int blk_iolatency_init(struct request_queue *q)
+{
+	struct blk_iolatency *blkiolat;
+	struct rq_qos *rqos;
+	int ret;
+
+	blkiolat = kzalloc(sizeof(*blkiolat), GFP_KERNEL);
+	if (!blkiolat)
+		return -ENOMEM;
+
+	rqos = &blkiolat->rqos;
+	rqos->id = RQ_QOS_CGROUP;
+	rqos->ops = &blkcg_iolatency_ops;
+	rqos->q = q;
+
+	rq_qos_add(q, rqos);
+
+	ret = blkcg_activate_policy(q, &blkcg_policy_iolatency);
+	if (ret) {
+		rq_qos_del(q, rqos);
+		kfree(blkiolat);
+		return ret;
+	}
+
+	timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0);
+
+	return 0;
+}
+
+static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
+{
+	struct iolatency_grp *iolat = blkg_to_lat(blkg);
+	struct blk_iolatency *blkiolat = iolat->blkiolat;
+	u64 oldval = iolat->min_lat_nsec;
+
+	iolat->min_lat_nsec = val;
+	iolat->cur_win_nsec = max_t(u64, val << 4, BLKIOLATENCY_MIN_WIN_SIZE);
+	iolat->cur_win_nsec = min_t(u64, iolat->cur_win_nsec,
+				    BLKIOLATENCY_MAX_WIN_SIZE);
+
+	if (!oldval && val)
+		atomic_inc(&blkiolat->enabled);
+	if (oldval && !val)
+		atomic_dec(&blkiolat->enabled);
+}
+
+static void iolatency_clear_scaling(struct blkcg_gq *blkg)
+{
+	if (blkg->parent) {
+		struct iolatency_grp *iolat = blkg_to_lat(blkg->parent);
+		struct child_latency_info *lat_info;
+		if (!iolat)
+			return;
+
+		lat_info = &iolat->child_lat;
+		spin_lock(&lat_info->lock);
+		atomic_set(&lat_info->scale_cookie, DEFAULT_SCALE_COOKIE);
+		lat_info->last_scale_event = 0;
+		lat_info->scale_grp = NULL;
+		lat_info->scale_lat = 0;
+		spin_unlock(&lat_info->lock);
+	}
+}
+
+static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
+			     size_t nbytes, loff_t off)
+{
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
+	struct blkcg_gq *blkg;
+	struct blk_iolatency *blkiolat;
+	struct blkg_conf_ctx ctx;
+	struct iolatency_grp *iolat;
+	char *p, *tok;
+	u64 lat_val = 0;
+	u64 oldval;
+	int ret;
+
+	ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx);
+	if (ret)
+		return ret;
+
+	iolat = blkg_to_lat(ctx.blkg);
+	blkiolat = iolat->blkiolat;
+	p = ctx.body;
+
+	ret = -EINVAL;
+	while ((tok = strsep(&p, " "))) {
+		char key[16];
+		char val[21];	/* 18446744073709551616 */
+
+		if (sscanf(tok, "%15[^=]=%20s", key, val) != 2)
+			goto out;
+
+		if (!strcmp(key, "target")) {
+			u64 v;
+
+			if (!strcmp(val, "max"))
+				lat_val = 0;
+			else if (sscanf(val, "%llu", &v) == 1)
+				lat_val = v * NSEC_PER_USEC;
+			else
+				goto out;
+		} else {
+			goto out;
+		}
+	}
+
+	/* Walk up the tree to see if our new val is lower than it should be. */
+	blkg = ctx.blkg;
+	oldval = iolat->min_lat_nsec;
+
+	iolatency_set_min_lat_nsec(blkg, lat_val);
+	if (oldval != iolat->min_lat_nsec) {
+		iolatency_clear_scaling(blkg);
+	}
+
+	ret = 0;
+out:
+	blkg_conf_finish(&ctx);
+	return ret ?: nbytes;
+}
+
+static u64 iolatency_prfill_limit(struct seq_file *sf,
+				  struct blkg_policy_data *pd, int off)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	const char *dname = blkg_dev_name(pd->blkg);
+
+	if (!dname || !iolat->min_lat_nsec)
+		return 0;
+	seq_printf(sf, "%s target=%llu\n",
+		   dname, div_u64(iolat->min_lat_nsec, NSEC_PER_USEC));
+	return 0;
+}
+
+static int iolatency_print_limit(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  iolatency_prfill_limit,
+			  &blkcg_policy_iolatency, seq_cft(sf)->private, false);
+	return 0;
+}
+
+static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf,
+				size_t size)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	unsigned long long avg_lat = div64_u64(iolat->lat_avg, NSEC_PER_USEC);
+	unsigned long long cur_win = div64_u64(iolat->cur_win_nsec, NSEC_PER_MSEC);
+
+	if (iolat->rq_depth.max_depth == UINT_MAX)
+		return scnprintf(buf, size, " depth=max avg_lat=%llu win=%llu",
+				 avg_lat, cur_win);
+
+	return scnprintf(buf, size, " depth=%u avg_lat=%llu win=%llu",
+			 iolat->rq_depth.max_depth, avg_lat, cur_win);
+}
+
+
+static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, int node)
+{
+	struct iolatency_grp *iolat;
+
+	iolat = kzalloc_node(sizeof(*iolat), gfp, node);
+	if (!iolat)
+		return NULL;
+	iolat->stats = __alloc_percpu_gfp(sizeof(struct blk_rq_stat),
+				       __alignof__(struct blk_rq_stat), gfp);
+	if (!iolat->stats) {
+		kfree(iolat);
+		return NULL;
+	}
+	return &iolat->pd;
+}
+
+static void iolatency_pd_init(struct blkg_policy_data *pd)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	struct blkcg_gq *blkg = lat_to_blkg(iolat);
+	struct rq_qos *rqos = blkcg_rq_qos(blkg->q);
+	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
+	u64 now = ktime_to_ns(ktime_get());
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct blk_rq_stat *stat;
+		stat = per_cpu_ptr(iolat->stats, cpu);
+		blk_rq_stat_init(stat);
+	}
+
+	rq_wait_init(&iolat->rq_wait);
+	spin_lock_init(&iolat->child_lat.lock);
+	iolat->rq_depth.queue_depth = blk_queue_depth(blkg->q);
+	iolat->rq_depth.max_depth = UINT_MAX;
+	iolat->rq_depth.default_depth = iolat->rq_depth.queue_depth;
+	iolat->blkiolat = blkiolat;
+	iolat->cur_win_nsec = 100 * NSEC_PER_MSEC;
+	atomic64_set(&iolat->window_start, now);
+
+	/*
+	 * We init things in list order, so the pd for the parent may not be
+	 * init'ed yet for whatever reason.
+	 */
+	if (blkg->parent && blkg_to_pd(blkg->parent, &blkcg_policy_iolatency)) {
+		struct iolatency_grp *parent = blkg_to_lat(blkg->parent);
+		atomic_set(&iolat->scale_cookie,
+			   atomic_read(&parent->child_lat.scale_cookie));
+	} else {
+		atomic_set(&iolat->scale_cookie, DEFAULT_SCALE_COOKIE);
+	}
+
+	atomic_set(&iolat->child_lat.scale_cookie, DEFAULT_SCALE_COOKIE);
+}
+
+static void iolatency_pd_offline(struct blkg_policy_data *pd)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	struct blkcg_gq *blkg = lat_to_blkg(iolat);
+
+	iolatency_set_min_lat_nsec(blkg, 0);
+	iolatency_clear_scaling(blkg);
+}
+
+static void iolatency_pd_free(struct blkg_policy_data *pd)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	free_percpu(iolat->stats);
+	kfree(iolat);
+}
+
+static struct cftype iolatency_files[] = {
+	{
+		.name = "latency",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = iolatency_print_limit,
+		.write = iolatency_set_limit,
+	},
+	{}
+};
+
+static struct blkcg_policy blkcg_policy_iolatency = {
+	.dfl_cftypes	= iolatency_files,
+	.pd_alloc_fn	= iolatency_pd_alloc,
+	.pd_init_fn	= iolatency_pd_init,
+	.pd_offline_fn	= iolatency_pd_offline,
+	.pd_free_fn	= iolatency_pd_free,
+	.pd_stat_fn	= iolatency_pd_stat,
+};
+
+static int __init iolatency_init(void)
+{
+	return blkcg_policy_register(&blkcg_policy_iolatency);
+}
+
+static void __exit iolatency_exit(void)
+{
+	return blkcg_policy_unregister(&blkcg_policy_iolatency);
+}
+
+module_init(iolatency_init);
+module_exit(iolatency_exit);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 8faa70f26fcd..d1b9dd03da25 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -68,6 +68,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		 */
 		req_sects = min_t(sector_t, nr_sects,
 					q->limits.max_discard_sectors);
+		if (!req_sects)
+			goto fail;
 		if (req_sects > UINT_MAX >> 9)
 			req_sects = UINT_MAX >> 9;
 
@@ -105,6 +107,14 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	*biop = bio;
 	return 0;
+
+fail:
+	if (bio) {
+		submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	*biop = NULL;
+	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL(__blkdev_issue_discard);
 
diff --git a/block/blk-mq-debugfs-zoned.c b/block/blk-mq-debugfs-zoned.c
new file mode 100644
index 000000000000..fb2c82c351e4
--- /dev/null
+++ b/block/blk-mq-debugfs-zoned.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/blkdev.h>
+#include "blk-mq-debugfs.h"
+
+int queue_zone_wlock_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	unsigned int i;
+
+	if (!q->seq_zones_wlock)
+		return 0;
+
+	for (i = 0; i < q->nr_zones; i++)
+		if (test_bit(i, q->seq_zones_wlock))
+			seq_printf(m, "%u\n", i);
+
+	return 0;
+}
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 1c4532e92938..cb1e6cf7ac48 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -206,21 +206,6 @@ static ssize_t queue_write_hint_store(void *data, const char __user *buf,
 	return count;
 }
 
-static int queue_zone_wlock_show(void *data, struct seq_file *m)
-{
-	struct request_queue *q = data;
-	unsigned int i;
-
-	if (!q->seq_zones_wlock)
-		return 0;
-
-	for (i = 0; i < blk_queue_nr_zones(q); i++)
-		if (test_bit(i, q->seq_zones_wlock))
-			seq_printf(m, "%u\n", i);
-
-	return 0;
-}
-
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
 	{ "poll_stat", 0400, queue_poll_stat_show },
 	{ "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops },
@@ -637,6 +622,14 @@ static int hctx_active_show(void *data, struct seq_file *m)
 	return 0;
 }
 
+static int hctx_dispatch_busy_show(void *data, struct seq_file *m)
+{
+	struct blk_mq_hw_ctx *hctx = data;
+
+	seq_printf(m, "%u\n", hctx->dispatch_busy);
+	return 0;
+}
+
 static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
 	__acquires(&ctx->lock)
 {
@@ -798,6 +791,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"queued", 0600, hctx_queued_show, hctx_queued_write},
 	{"run", 0600, hctx_run_show, hctx_run_write},
 	{"active", 0400, hctx_active_show},
+	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
 	{},
 };
 
diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h
index b9d366e57097..a9160be12be0 100644
--- a/block/blk-mq-debugfs.h
+++ b/block/blk-mq-debugfs.h
@@ -80,4 +80,13 @@ static inline void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hc
 }
 #endif
 
+#ifdef CONFIG_BLK_DEBUG_FS_ZONED
+int queue_zone_wlock_show(void *data, struct seq_file *m);
+#else
+static inline int queue_zone_wlock_show(void *data, struct seq_file *m)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c
index e233996bb76f..db644ec624f5 100644
--- a/block/blk-mq-pci.c
+++ b/block/blk-mq-pci.c
@@ -17,6 +17,8 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 
+#include "blk-mq.h"
+
 /**
  * blk_mq_pci_map_queues - provide a default queue mapping for PCI device
  * @set:	tagset to provide the mapping for
@@ -48,8 +50,7 @@ int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
 
 fallback:
 	WARN_ON_ONCE(set->nr_hw_queues > 1);
-	for_each_possible_cpu(cpu)
-		set->mq_map[cpu] = 0;
+	blk_mq_clear_mq_map(set);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 56c493c6cd90..cf9c66c6d35a 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -59,29 +59,16 @@ static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
 	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
 		return;
 
-	if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-		struct request_queue *q = hctx->queue;
-
-		if (!test_and_set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-			atomic_inc(&q->shared_hctx_restart);
-	} else
-		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+	set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 }
 
-static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 {
 	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-		return false;
-
-	if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-		struct request_queue *q = hctx->queue;
-
-		if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-			atomic_dec(&q->shared_hctx_restart);
-	} else
-		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		return;
+	clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
-	return blk_mq_run_hw_queue(hctx, true);
+	blk_mq_run_hw_queue(hctx, true);
 }
 
 /*
@@ -219,15 +206,8 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 		}
 	} else if (has_sched_dispatch) {
 		blk_mq_do_dispatch_sched(hctx);
-	} else if (q->mq_ops->get_budget) {
-		/*
-		 * If we need to get budget before queuing request, we
-		 * dequeue request one by one from sw queue for avoiding
-		 * to mess up I/O merge when dispatch runs out of resource.
-		 *
-		 * TODO: get more budgets, and dequeue more requests in
-		 * one time.
-		 */
+	} else if (hctx->dispatch_busy) {
+		/* dequeue request one by one from sw queue if queue is busy */
 		blk_mq_do_dispatch_ctx(hctx);
 	} else {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
@@ -339,7 +319,8 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 		return e->type->ops.mq.bio_merge(hctx, bio);
 	}
 
-	if (hctx->flags & BLK_MQ_F_SHOULD_MERGE) {
+	if ((hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
+			!list_empty_careful(&ctx->rq_list)) {
 		/* default per sw-queue merge */
 		spin_lock(&ctx->lock);
 		ret = blk_mq_attempt_merge(q, ctx, bio);
@@ -380,68 +361,6 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
 	return false;
 }
 
-/**
- * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
- * @pos:    loop cursor.
- * @skip:   the list element that will not be examined. Iteration starts at
- *          @skip->next.
- * @head:   head of the list to examine. This list must have at least one
- *          element, namely @skip.
- * @member: name of the list_head structure within typeof(*pos).
- */
-#define list_for_each_entry_rcu_rr(pos, skip, head, member)		\
-	for ((pos) = (skip);						\
-	     (pos = (pos)->member.next != (head) ? list_entry_rcu(	\
-			(pos)->member.next, typeof(*pos), member) :	\
-	      list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
-	     (pos) != (skip); )
-
-/*
- * Called after a driver tag has been freed to check whether a hctx needs to
- * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
- * queues in a round-robin fashion if the tag set of @hctx is shared with other
- * hardware queues.
- */
-void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
-{
-	struct blk_mq_tags *const tags = hctx->tags;
-	struct blk_mq_tag_set *const set = hctx->queue->tag_set;
-	struct request_queue *const queue = hctx->queue, *q;
-	struct blk_mq_hw_ctx *hctx2;
-	unsigned int i, j;
-
-	if (set->flags & BLK_MQ_F_TAG_SHARED) {
-		/*
-		 * If this is 0, then we know that no hardware queues
-		 * have RESTART marked. We're done.
-		 */
-		if (!atomic_read(&queue->shared_hctx_restart))
-			return;
-
-		rcu_read_lock();
-		list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
-					   tag_set_list) {
-			queue_for_each_hw_ctx(q, hctx2, i)
-				if (hctx2->tags == tags &&
-				    blk_mq_sched_restart_hctx(hctx2))
-					goto done;
-		}
-		j = hctx->queue_num + 1;
-		for (i = 0; i < queue->nr_hw_queues; i++, j++) {
-			if (j == queue->nr_hw_queues)
-				j = 0;
-			hctx2 = queue->queue_hw_ctx[j];
-			if (hctx2->tags == tags &&
-			    blk_mq_sched_restart_hctx(hctx2))
-				break;
-		}
-done:
-		rcu_read_unlock();
-	} else {
-		blk_mq_sched_restart_hctx(hctx);
-	}
-}
-
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 				 bool run_queue, bool async)
 {
@@ -486,8 +405,19 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 
 	if (e && e->type->ops.mq.insert_requests)
 		e->type->ops.mq.insert_requests(hctx, list, false);
-	else
+	else {
+		/*
+		 * try to issue requests directly if the hw queue isn't
+		 * busy in case of 'none' scheduler, and this way may save
+		 * us one extra enqueue & dequeue to sw queue.
+		 */
+		if (!hctx->dispatch_busy && !e && !run_queue_async) {
+			blk_mq_try_issue_list_directly(hctx, list);
+			if (list_empty(list))
+				return;
+		}
 		blk_mq_insert_requests(hctx, ctx, list);
+	}
 
 	blk_mq_run_hw_queue(hctx, run_queue_async);
 }
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 3de0836163c2..816923bf874d 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -23,6 +23,9 @@ bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
 
 /*
  * If a previously inactive queue goes active, bump the active user count.
+ * We need to do this before try to allocate driver tag, then even if fail
+ * to get tag when first time, the other shared-tag users could reserve
+ * budget for it.
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
@@ -399,8 +402,6 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 	if (tdepth <= tags->nr_reserved_tags)
 		return -EINVAL;
 
-	tdepth -= tags->nr_reserved_tags;
-
 	/*
 	 * If we are allowed to grow beyond the original size, allocate
 	 * a new set of tags before freeing the old one.
@@ -420,7 +421,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 		if (tdepth > 16 * BLKDEV_MAX_RQ)
 			return -EINVAL;
 
-		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, 0);
+		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth,
+				tags->nr_reserved_tags);
 		if (!new)
 			return -ENOMEM;
 		ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth);
@@ -437,7 +439,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 		 * Don't need (or can't) update reserved tags here, they
 		 * remain static and should never need resizing.
 		 */
-		sbitmap_queue_resize(&tags->bitmap_tags, tdepth);
+		sbitmap_queue_resize(&tags->bitmap_tags,
+				tdepth - tags->nr_reserved_tags);
 	}
 
 	return 0;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 654b0dc7e001..72a0033ccee9 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -34,8 +34,8 @@
 #include "blk-mq-debugfs.h"
 #include "blk-mq-tag.h"
 #include "blk-stat.h"
-#include "blk-wbt.h"
 #include "blk-mq-sched.h"
+#include "blk-rq-qos.h"
 
 static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
 static void blk_mq_poll_stats_start(struct request_queue *q);
@@ -285,7 +285,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 		rq->tag = -1;
 		rq->internal_tag = tag;
 	} else {
-		if (blk_mq_tag_busy(data->hctx)) {
+		if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
 			rq_flags = RQF_MQ_INFLIGHT;
 			atomic_inc(&data->hctx->nr_active);
 		}
@@ -367,6 +367,8 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 		if (!op_is_flush(op) && e->type->ops.mq.limit_depth &&
 		    !(data->flags & BLK_MQ_REQ_RESERVED))
 			e->type->ops.mq.limit_depth(op, data);
+	} else {
+		blk_mq_tag_busy(data->hctx);
 	}
 
 	tag = blk_mq_get_tag(data);
@@ -504,7 +506,7 @@ void blk_mq_free_request(struct request *rq)
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
 
-	wbt_done(q->rq_wb, rq);
+	rq_qos_done(q, rq);
 
 	if (blk_rq_rl(rq))
 		blk_put_rl(blk_rq_rl(rq));
@@ -527,7 +529,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 	blk_account_io_done(rq, now);
 
 	if (rq->end_io) {
-		wbt_done(rq->q->rq_wb, rq);
+		rq_qos_done(rq->q, rq);
 		rq->end_io(rq, error);
 	} else {
 		if (unlikely(blk_bidi_rq(rq)))
@@ -639,7 +641,7 @@ void blk_mq_start_request(struct request *rq)
 		rq->throtl_size = blk_rq_sectors(rq);
 #endif
 		rq->rq_flags |= RQF_STATS;
-		wbt_issue(q->rq_wb, rq);
+		rq_qos_issue(q, rq);
 	}
 
 	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
@@ -665,7 +667,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 	blk_mq_put_driver_tag(rq);
 
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, rq);
+	rq_qos_requeue(q, rq);
 
 	if (blk_mq_request_started(rq)) {
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
@@ -962,16 +964,14 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
-bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
-			   bool wait)
+bool blk_mq_get_driver_tag(struct request *rq)
 {
 	struct blk_mq_alloc_data data = {
 		.q = rq->q,
 		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
-		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
+		.flags = BLK_MQ_REQ_NOWAIT,
 	};
-
-	might_sleep_if(wait);
+	bool shared;
 
 	if (rq->tag != -1)
 		goto done;
@@ -979,9 +979,10 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
 		data.flags |= BLK_MQ_REQ_RESERVED;
 
+	shared = blk_mq_tag_busy(data.hctx);
 	rq->tag = blk_mq_get_tag(&data);
 	if (rq->tag >= 0) {
-		if (blk_mq_tag_busy(data.hctx)) {
+		if (shared) {
 			rq->rq_flags |= RQF_MQ_INFLIGHT;
 			atomic_inc(&data.hctx->nr_active);
 		}
@@ -989,8 +990,6 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 	}
 
 done:
-	if (hctx)
-		*hctx = data.hctx;
 	return rq->tag != -1;
 }
 
@@ -1001,7 +1000,10 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 
 	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
 
+	spin_lock(&hctx->dispatch_wait_lock);
 	list_del_init(&wait->entry);
+	spin_unlock(&hctx->dispatch_wait_lock);
+
 	blk_mq_run_hw_queue(hctx, true);
 	return 1;
 }
@@ -1012,17 +1014,16 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
  * restart. For both cases, take care to check the condition again after
  * marking us as waiting.
  */
-static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
+static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 				 struct request *rq)
 {
-	struct blk_mq_hw_ctx *this_hctx = *hctx;
-	struct sbq_wait_state *ws;
+	struct wait_queue_head *wq;
 	wait_queue_entry_t *wait;
 	bool ret;
 
-	if (!(this_hctx->flags & BLK_MQ_F_TAG_SHARED)) {
-		if (!test_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state))
-			set_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state);
+	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
+		if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+			set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
 		/*
 		 * It's possible that a tag was freed in the window between the
@@ -1032,30 +1033,35 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 		 * Don't clear RESTART here, someone else could have set it.
 		 * At most this will cost an extra queue run.
 		 */
-		return blk_mq_get_driver_tag(rq, hctx, false);
+		return blk_mq_get_driver_tag(rq);
 	}
 
-	wait = &this_hctx->dispatch_wait;
+	wait = &hctx->dispatch_wait;
 	if (!list_empty_careful(&wait->entry))
 		return false;
 
-	spin_lock(&this_hctx->lock);
+	wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait;
+
+	spin_lock_irq(&wq->lock);
+	spin_lock(&hctx->dispatch_wait_lock);
 	if (!list_empty(&wait->entry)) {
-		spin_unlock(&this_hctx->lock);
+		spin_unlock(&hctx->dispatch_wait_lock);
+		spin_unlock_irq(&wq->lock);
 		return false;
 	}
 
-	ws = bt_wait_ptr(&this_hctx->tags->bitmap_tags, this_hctx);
-	add_wait_queue(&ws->wait, wait);
+	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue(wq, wait);
 
 	/*
 	 * It's possible that a tag was freed in the window between the
 	 * allocation failure and adding the hardware queue to the wait
 	 * queue.
 	 */
-	ret = blk_mq_get_driver_tag(rq, hctx, false);
+	ret = blk_mq_get_driver_tag(rq);
 	if (!ret) {
-		spin_unlock(&this_hctx->lock);
+		spin_unlock(&hctx->dispatch_wait_lock);
+		spin_unlock_irq(&wq->lock);
 		return false;
 	}
 
@@ -1063,14 +1069,42 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 	 * We got a tag, remove ourselves from the wait queue to ensure
 	 * someone else gets the wakeup.
 	 */
-	spin_lock_irq(&ws->wait.lock);
 	list_del_init(&wait->entry);
-	spin_unlock_irq(&ws->wait.lock);
-	spin_unlock(&this_hctx->lock);
+	spin_unlock(&hctx->dispatch_wait_lock);
+	spin_unlock_irq(&wq->lock);
 
 	return true;
 }
 
+#define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT  8
+#define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR  4
+/*
+ * Update dispatch busy with the Exponential Weighted Moving Average(EWMA):
+ * - EWMA is one simple way to compute running average value
+ * - weight(7/8 and 1/8) is applied so that it can decrease exponentially
+ * - take 4 as factor for avoiding to get too small(0) result, and this
+ *   factor doesn't matter because EWMA decreases exponentially
+ */
+static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
+{
+	unsigned int ewma;
+
+	if (hctx->queue->elevator)
+		return;
+
+	ewma = hctx->dispatch_busy;
+
+	if (!ewma && !busy)
+		return;
+
+	ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1;
+	if (busy)
+		ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR;
+	ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT;
+
+	hctx->dispatch_busy = ewma;
+}
+
 #define BLK_MQ_RESOURCE_DELAY	3		/* ms units */
 
 /*
@@ -1103,7 +1137,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
 			break;
 
-		if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+		if (!blk_mq_get_driver_tag(rq)) {
 			/*
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed. The
@@ -1111,7 +1145,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			 * before we add this entry back on the dispatch list,
 			 * we'll re-run it below.
 			 */
-			if (!blk_mq_mark_tag_wait(&hctx, rq)) {
+			if (!blk_mq_mark_tag_wait(hctx, rq)) {
 				blk_mq_put_dispatch_budget(hctx);
 				/*
 				 * For non-shared tags, the RESTART check
@@ -1135,7 +1169,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			bd.last = true;
 		else {
 			nxt = list_first_entry(list, struct request, queuelist);
-			bd.last = !blk_mq_get_driver_tag(nxt, NULL, false);
+			bd.last = !blk_mq_get_driver_tag(nxt);
 		}
 
 		ret = q->mq_ops->queue_rq(hctx, &bd);
@@ -1207,8 +1241,10 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		else if (needs_restart && (ret == BLK_STS_RESOURCE))
 			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
 
+		blk_mq_update_dispatch_busy(hctx, true);
 		return false;
-	}
+	} else
+		blk_mq_update_dispatch_busy(hctx, false);
 
 	/*
 	 * If the host/device is unable to accept more work, inform the
@@ -1542,19 +1578,19 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 			    struct list_head *list)
 
 {
+	struct request *rq;
+
 	/*
 	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
 	 * offline now
 	 */
-	spin_lock(&ctx->lock);
-	while (!list_empty(list)) {
-		struct request *rq;
-
-		rq = list_first_entry(list, struct request, queuelist);
+	list_for_each_entry(rq, list, queuelist) {
 		BUG_ON(rq->mq_ctx != ctx);
-		list_del_init(&rq->queuelist);
-		__blk_mq_insert_req_list(hctx, rq, false);
+		trace_block_rq_insert(hctx->queue, rq);
 	}
+
+	spin_lock(&ctx->lock);
+	list_splice_tail_init(list, &ctx->rq_list);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
 }
@@ -1657,13 +1693,16 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 	ret = q->mq_ops->queue_rq(hctx, &bd);
 	switch (ret) {
 	case BLK_STS_OK:
+		blk_mq_update_dispatch_busy(hctx, false);
 		*cookie = new_cookie;
 		break;
 	case BLK_STS_RESOURCE:
 	case BLK_STS_DEV_RESOURCE:
+		blk_mq_update_dispatch_busy(hctx, true);
 		__blk_mq_requeue_request(rq);
 		break;
 	default:
+		blk_mq_update_dispatch_busy(hctx, false);
 		*cookie = BLK_QC_T_NONE;
 		break;
 	}
@@ -1698,7 +1737,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (!blk_mq_get_dispatch_budget(hctx))
 		goto insert;
 
-	if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+	if (!blk_mq_get_driver_tag(rq)) {
 		blk_mq_put_dispatch_budget(hctx);
 		goto insert;
 	}
@@ -1746,6 +1785,27 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq)
 	return ret;
 }
 
+void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+		struct list_head *list)
+{
+	while (!list_empty(list)) {
+		blk_status_t ret;
+		struct request *rq = list_first_entry(list, struct request,
+				queuelist);
+
+		list_del_init(&rq->queuelist);
+		ret = blk_mq_request_issue_directly(rq);
+		if (ret != BLK_STS_OK) {
+			if (ret == BLK_STS_RESOURCE ||
+					ret == BLK_STS_DEV_RESOURCE) {
+				list_add(&rq->queuelist, list);
+				break;
+			}
+			blk_mq_end_request(rq, ret);
+		}
+	}
+}
+
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
@@ -1756,7 +1816,6 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	blk_qc_t cookie;
-	unsigned int wb_acct;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1772,19 +1831,19 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	if (blk_mq_sched_bio_merge(q, bio))
 		return BLK_QC_T_NONE;
 
-	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
+	rq_qos_throttle(q, bio, NULL);
 
 	trace_block_getrq(q, bio, bio->bi_opf);
 
 	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, bio);
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
 		return BLK_QC_T_NONE;
 	}
 
-	wbt_track(rq, wb_acct);
+	rq_qos_track(q, rq, bio);
 
 	cookie = request_to_qc_t(data.hctx, rq);
 
@@ -1847,7 +1906,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
 					&cookie);
 		}
-	} else if (q->nr_hw_queues > 1 && is_sync) {
+	} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
+			!data.hctx->dispatch_busy)) {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
@@ -2146,6 +2206,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 
 	hctx->nr_ctx = 0;
 
+	spin_lock_init(&hctx->dispatch_wait_lock);
 	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
 	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
 
@@ -2331,15 +2392,10 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		if (shared) {
-			if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-				atomic_inc(&q->shared_hctx_restart);
+		if (shared)
 			hctx->flags |= BLK_MQ_F_TAG_SHARED;
-		} else {
-			if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-				atomic_dec(&q->shared_hctx_restart);
+		else
 			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
-		}
 	}
 }
 
@@ -2370,7 +2426,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 		blk_mq_update_tag_set_depth(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
-	synchronize_rcu();
 	INIT_LIST_HEAD(&q->tag_set_list);
 }
 
@@ -2685,7 +2740,6 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 {
 	if (set->ops->map_queues) {
-		int cpu;
 		/*
 		 * transport .map_queues is usually done in the following
 		 * way:
@@ -2700,8 +2754,7 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 		 * killing stale mapping since one CPU may not be mapped
 		 * to any hw queue.
 		 */
-		for_each_possible_cpu(cpu)
-			set->mq_map[cpu] = 0;
+		blk_mq_clear_mq_map(set);
 
 		return set->ops->map_queues(set);
 	} else
@@ -2711,7 +2764,7 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
- * requested depth down, if if it too large. In that case, the set
+ * requested depth down, if it's too large. In that case, the set
  * value will be stored in set->queue_depth.
  */
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 89231e439b2f..9497b47e2526 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -36,8 +36,7 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
-bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
-				bool wait);
+bool blk_mq_get_driver_tag(struct request *rq);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);
 
@@ -65,6 +64,8 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 
 /* Used by blk_insert_cloned_request() to issue request directly */
 blk_status_t blk_mq_request_issue_directly(struct request *rq);
+void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+				    struct list_head *list);
 
 /*
  * CPU -> queue mappings
@@ -203,4 +204,12 @@ static inline void blk_mq_put_driver_tag(struct request *rq)
 	__blk_mq_put_driver_tag(hctx, rq);
 }
 
+static inline void blk_mq_clear_mq_map(struct blk_mq_tag_set *set)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		set->mq_map[cpu] = 0;
+}
+
 #endif
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
new file mode 100644
index 000000000000..0005dfd568dd
--- /dev/null
+++ b/block/blk-rq-qos.c
@@ -0,0 +1,194 @@
+#include "blk-rq-qos.h"
+
+/*
+ * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
+ * false if 'v' + 1 would be bigger than 'below'.
+ */
+static bool atomic_inc_below(atomic_t *v, unsigned int below)
+{
+	unsigned int cur = atomic_read(v);
+
+	for (;;) {
+		unsigned int old;
+
+		if (cur >= below)
+			return false;
+		old = atomic_cmpxchg(v, cur, cur + 1);
+		if (old == cur)
+			break;
+		cur = old;
+	}
+
+	return true;
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit)
+{
+	return atomic_inc_below(&rq_wait->inflight, limit);
+}
+
+void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->cleanup)
+			rqos->ops->cleanup(rqos, bio);
+	}
+}
+
+void rq_qos_done(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->done)
+			rqos->ops->done(rqos, rq);
+	}
+}
+
+void rq_qos_issue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->issue)
+			rqos->ops->issue(rqos, rq);
+	}
+}
+
+void rq_qos_requeue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->requeue)
+			rqos->ops->requeue(rqos, rq);
+	}
+}
+
+void rq_qos_throttle(struct request_queue *q, struct bio *bio,
+		     spinlock_t *lock)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->throttle)
+			rqos->ops->throttle(rqos, bio, lock);
+	}
+}
+
+void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->track)
+			rqos->ops->track(rqos, rq, bio);
+	}
+}
+
+void rq_qos_done_bio(struct request_queue *q, struct bio *bio)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->done_bio)
+			rqos->ops->done_bio(rqos, bio);
+	}
+}
+
+/*
+ * Return true, if we can't increase the depth further by scaling
+ */
+bool rq_depth_calc_max_depth(struct rq_depth *rqd)
+{
+	unsigned int depth;
+	bool ret = false;
+
+	/*
+	 * For QD=1 devices, this is a special case. It's important for those
+	 * to have one request ready when one completes, so force a depth of
+	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
+	 * since the device can't have more than that in flight. If we're
+	 * scaling down, then keep a setting of 1/1/1.
+	 */
+	if (rqd->queue_depth == 1) {
+		if (rqd->scale_step > 0)
+			rqd->max_depth = 1;
+		else {
+			rqd->max_depth = 2;
+			ret = true;
+		}
+	} else {
+		/*
+		 * scale_step == 0 is our default state. If we have suffered
+		 * latency spikes, step will be > 0, and we shrink the
+		 * allowed write depths. If step is < 0, we're only doing
+		 * writes, and we allow a temporarily higher depth to
+		 * increase performance.
+		 */
+		depth = min_t(unsigned int, rqd->default_depth,
+			      rqd->queue_depth);
+		if (rqd->scale_step > 0)
+			depth = 1 + ((depth - 1) >> min(31, rqd->scale_step));
+		else if (rqd->scale_step < 0) {
+			unsigned int maxd = 3 * rqd->queue_depth / 4;
+
+			depth = 1 + ((depth - 1) << -rqd->scale_step);
+			if (depth > maxd) {
+				depth = maxd;
+				ret = true;
+			}
+		}
+
+		rqd->max_depth = depth;
+	}
+
+	return ret;
+}
+
+void rq_depth_scale_up(struct rq_depth *rqd)
+{
+	/*
+	 * Hit max in previous round, stop here
+	 */
+	if (rqd->scaled_max)
+		return;
+
+	rqd->scale_step--;
+
+	rqd->scaled_max = rq_depth_calc_max_depth(rqd);
+}
+
+/*
+ * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
+ * had a latency violation.
+ */
+void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
+{
+	/*
+	 * Stop scaling down when we've hit the limit. This also prevents
+	 * ->scale_step from going to crazy values, if the device can't
+	 * keep up.
+	 */
+	if (rqd->max_depth == 1)
+		return;
+
+	if (rqd->scale_step < 0 && hard_throttle)
+		rqd->scale_step = 0;
+	else
+		rqd->scale_step++;
+
+	rqd->scaled_max = false;
+	rq_depth_calc_max_depth(rqd);
+}
+
+void rq_qos_exit(struct request_queue *q)
+{
+	while (q->rq_qos) {
+		struct rq_qos *rqos = q->rq_qos;
+		q->rq_qos = rqos->next;
+		rqos->ops->exit(rqos);
+	}
+}
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
new file mode 100644
index 000000000000..32b02efbfa66
--- /dev/null
+++ b/block/blk-rq-qos.h
@@ -0,0 +1,109 @@
+#ifndef RQ_QOS_H
+#define RQ_QOS_H
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blk_types.h>
+#include <linux/atomic.h>
+#include <linux/wait.h>
+
+enum rq_qos_id {
+	RQ_QOS_WBT,
+	RQ_QOS_CGROUP,
+};
+
+struct rq_wait {
+	wait_queue_head_t wait;
+	atomic_t inflight;
+};
+
+struct rq_qos {
+	struct rq_qos_ops *ops;
+	struct request_queue *q;
+	enum rq_qos_id id;
+	struct rq_qos *next;
+};
+
+struct rq_qos_ops {
+	void (*throttle)(struct rq_qos *, struct bio *, spinlock_t *);
+	void (*track)(struct rq_qos *, struct request *, struct bio *);
+	void (*issue)(struct rq_qos *, struct request *);
+	void (*requeue)(struct rq_qos *, struct request *);
+	void (*done)(struct rq_qos *, struct request *);
+	void (*done_bio)(struct rq_qos *, struct bio *);
+	void (*cleanup)(struct rq_qos *, struct bio *);
+	void (*exit)(struct rq_qos *);
+};
+
+struct rq_depth {
+	unsigned int max_depth;
+
+	int scale_step;
+	bool scaled_max;
+
+	unsigned int queue_depth;
+	unsigned int default_depth;
+};
+
+static inline struct rq_qos *rq_qos_id(struct request_queue *q,
+				       enum rq_qos_id id)
+{
+	struct rq_qos *rqos;
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->id == id)
+			break;
+	}
+	return rqos;
+}
+
+static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_WBT);
+}
+
+static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_CGROUP);
+}
+
+static inline void rq_wait_init(struct rq_wait *rq_wait)
+{
+	atomic_set(&rq_wait->inflight, 0);
+	init_waitqueue_head(&rq_wait->wait);
+}
+
+static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
+{
+	rqos->next = q->rq_qos;
+	q->rq_qos = rqos;
+}
+
+static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
+{
+	struct rq_qos *cur, *prev = NULL;
+	for (cur = q->rq_qos; cur; cur = cur->next) {
+		if (cur == rqos) {
+			if (prev)
+				prev->next = rqos->next;
+			else
+				q->rq_qos = cur;
+			break;
+		}
+		prev = cur;
+	}
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit);
+void rq_depth_scale_up(struct rq_depth *rqd);
+void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
+bool rq_depth_calc_max_depth(struct rq_depth *rqd);
+
+void rq_qos_cleanup(struct request_queue *, struct bio *);
+void rq_qos_done(struct request_queue *, struct request *);
+void rq_qos_issue(struct request_queue *, struct request *);
+void rq_qos_requeue(struct request_queue *, struct request *);
+void rq_qos_done_bio(struct request_queue *q, struct bio *bio);
+void rq_qos_throttle(struct request_queue *, struct bio *, spinlock_t *);
+void rq_qos_track(struct request_queue *q, struct request *, struct bio *);
+void rq_qos_exit(struct request_queue *);
+#endif
diff --git a/block/blk-settings.c b/block/blk-settings.c
index d1de71124656..ffd459969689 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -128,7 +128,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 
 	/* Inherit limits from component devices */
 	lim->max_segments = USHRT_MAX;
-	lim->max_discard_segments = 1;
+	lim->max_discard_segments = USHRT_MAX;
 	lim->max_hw_sectors = UINT_MAX;
 	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
@@ -875,7 +875,7 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
 void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 	q->queue_depth = depth;
-	wbt_set_queue_depth(q->rq_wb, depth);
+	wbt_set_queue_depth(q, depth);
 }
 EXPORT_SYMBOL(blk_set_queue_depth);
 
@@ -900,7 +900,7 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 		queue_flag_clear(QUEUE_FLAG_FUA, q);
 	spin_unlock_irq(q->queue_lock);
 
-	wbt_set_write_cache(q->rq_wb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
+	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 175c143ac5b9..7587b1c3caaf 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -17,7 +17,7 @@ struct blk_queue_stats {
 	bool enable_accounting;
 };
 
-static void blk_stat_init(struct blk_rq_stat *stat)
+void blk_rq_stat_init(struct blk_rq_stat *stat)
 {
 	stat->min = -1ULL;
 	stat->max = stat->nr_samples = stat->mean = 0;
@@ -25,7 +25,7 @@ static void blk_stat_init(struct blk_rq_stat *stat)
 }
 
 /* src is a per-cpu stat, mean isn't initialized */
-static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
+void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 {
 	if (!src->nr_samples)
 		return;
@@ -39,7 +39,7 @@ static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 	dst->nr_samples += src->nr_samples;
 }
 
-static void __blk_stat_add(struct blk_rq_stat *stat, u64 value)
+void blk_rq_stat_add(struct blk_rq_stat *stat, u64 value)
 {
 	stat->min = min(stat->min, value);
 	stat->max = max(stat->max, value);
@@ -69,7 +69,7 @@ void blk_stat_add(struct request *rq, u64 now)
 			continue;
 
 		stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
-		__blk_stat_add(stat, value);
+		blk_rq_stat_add(stat, value);
 		put_cpu_ptr(cb->cpu_stat);
 	}
 	rcu_read_unlock();
@@ -82,15 +82,15 @@ static void blk_stat_timer_fn(struct timer_list *t)
 	int cpu;
 
 	for (bucket = 0; bucket < cb->buckets; bucket++)
-		blk_stat_init(&cb->stat[bucket]);
+		blk_rq_stat_init(&cb->stat[bucket]);
 
 	for_each_online_cpu(cpu) {
 		struct blk_rq_stat *cpu_stat;
 
 		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
 		for (bucket = 0; bucket < cb->buckets; bucket++) {
-			blk_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
-			blk_stat_init(&cpu_stat[bucket]);
+			blk_rq_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
+			blk_rq_stat_init(&cpu_stat[bucket]);
 		}
 	}
 
@@ -143,7 +143,7 @@ void blk_stat_add_callback(struct request_queue *q,
 
 		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
 		for (bucket = 0; bucket < cb->buckets; bucket++)
-			blk_stat_init(&cpu_stat[bucket]);
+			blk_rq_stat_init(&cpu_stat[bucket]);
 	}
 
 	spin_lock(&q->stats->lock);
diff --git a/block/blk-stat.h b/block/blk-stat.h
index 78399cdde9c9..f4a1568e81a4 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -159,4 +159,8 @@ static inline void blk_stat_activate_msecs(struct blk_stat_callback *cb,
 	mod_timer(&cb->timer, jiffies + msecs_to_jiffies(msecs));
 }
 
+void blk_rq_stat_add(struct blk_rq_stat *, u64);
+void blk_rq_stat_sum(struct blk_rq_stat *, struct blk_rq_stat *);
+void blk_rq_stat_init(struct blk_rq_stat *);
+
 #endif
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 94987b1f69e1..bb109bb0a055 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -422,16 +422,16 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 
 static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
 {
-	if (!q->rq_wb)
+	if (!wbt_rq_qos(q))
 		return -EINVAL;
 
-	return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000));
+	return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
 }
 
 static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 				  size_t count)
 {
-	struct rq_wb *rwb;
+	struct rq_qos *rqos;
 	ssize_t ret;
 	s64 val;
 
@@ -441,23 +441,21 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 	if (val < -1)
 		return -EINVAL;
 
-	rwb = q->rq_wb;
-	if (!rwb) {
+	rqos = wbt_rq_qos(q);
+	if (!rqos) {
 		ret = wbt_init(q);
 		if (ret)
 			return ret;
 	}
 
-	rwb = q->rq_wb;
 	if (val == -1)
-		rwb->min_lat_nsec = wbt_default_latency_nsec(q);
+		val = wbt_default_latency_nsec(q);
 	else if (val >= 0)
-		rwb->min_lat_nsec = val * 1000ULL;
+		val *= 1000ULL;
 
-	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
-		rwb->enable_state = WBT_STATE_ON_MANUAL;
+	wbt_set_min_lat(q, val);
 
-	wbt_update_limits(rwb);
+	wbt_update_limits(q);
 	return count;
 }
 
@@ -804,6 +802,21 @@ static void __blk_release_queue(struct work_struct *work)
 		blk_stat_remove_callback(q, q->poll_cb);
 	blk_stat_free_callback(q->poll_cb);
 
+	if (!blk_queue_dead(q)) {
+		/*
+		 * Last reference was dropped without having called
+		 * blk_cleanup_queue().
+		 */
+		WARN_ONCE(blk_queue_init_done(q),
+			  "request queue %p has been registered but blk_cleanup_queue() has not been called for that queue\n",
+			  q);
+		blk_exit_queue(q);
+	}
+
+	WARN(blk_queue_root_blkg(q),
+	     "request queue %p is being released but it has not yet been removed from the blkcg controller\n",
+	     q);
+
 	blk_free_queue_stats(q->stats);
 
 	blk_exit_rl(q, &q->root_rl);
@@ -964,7 +977,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
-	wbt_exit(q);
+	rq_qos_exit(q);
 
 	mutex_lock(&q->sysfs_lock);
 	if (q->request_fn || (q->mq_ops && q->elevator))
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 82282e6fdcf8..a3eede00d302 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -579,8 +579,10 @@ static void blk_throtl_update_limit_valid(struct throtl_data *td)
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 
 		if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
-		    tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+		    tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) {
 			low_valid = true;
+			break;
+		}
 	}
 	rcu_read_unlock();
 
@@ -920,12 +922,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	}
 
 	/* Calc approx time to dispatch */
-	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ) / tg_iops_limit(tg, rw) + 1;
-
-	if (jiffy_wait > jiffy_elapsed)
-		jiffy_wait = jiffy_wait - jiffy_elapsed;
-	else
-		jiffy_wait = 1;
+	jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed;
 
 	if (wait)
 		*wait = jiffy_wait;
@@ -2132,12 +2129,8 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td)
 static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
 {
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	if (bio->bi_css) {
-		if (bio->bi_cg_private)
-			blkg_put(tg_to_blkg(bio->bi_cg_private));
-		bio->bi_cg_private = tg;
-		blkg_get(tg_to_blkg(tg));
-	}
+	if (bio->bi_css)
+		bio_associate_blkg(bio, tg_to_blkg(tg));
 	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
 #endif
 }
@@ -2285,6 +2278,7 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns)
 
 void blk_throtl_bio_endio(struct bio *bio)
 {
+	struct blkcg_gq *blkg;
 	struct throtl_grp *tg;
 	u64 finish_time_ns;
 	unsigned long finish_time;
@@ -2292,20 +2286,18 @@ void blk_throtl_bio_endio(struct bio *bio)
 	unsigned long lat;
 	int rw = bio_data_dir(bio);
 
-	tg = bio->bi_cg_private;
-	if (!tg)
+	blkg = bio->bi_blkg;
+	if (!blkg)
 		return;
-	bio->bi_cg_private = NULL;
+	tg = blkg_to_tg(blkg);
 
 	finish_time_ns = ktime_get_ns();
 	tg->last_finish_time = finish_time_ns >> 10;
 
 	start_time = bio_issue_time(&bio->bi_issue) >> 10;
 	finish_time = __bio_issue_time(finish_time_ns) >> 10;
-	if (!start_time || finish_time <= start_time) {
-		blkg_put(tg_to_blkg(tg));
+	if (!start_time || finish_time <= start_time)
 		return;
-	}
 
 	lat = finish_time - start_time;
 	/* this is only for bio based driver */
@@ -2334,8 +2326,6 @@ void blk_throtl_bio_endio(struct bio *bio)
 		tg->bio_cnt /= 2;
 		tg->bad_bio_cnt /= 2;
 	}
-
-	blkg_put(tg_to_blkg(tg));
 }
 #endif
 
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 4f89b28fa652..1d94a20374fc 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -25,6 +25,7 @@
 #include <linux/swap.h>
 
 #include "blk-wbt.h"
+#include "blk-rq-qos.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/wbt.h>
@@ -78,28 +79,6 @@ static inline bool rwb_enabled(struct rq_wb *rwb)
 	return rwb && rwb->wb_normal != 0;
 }
 
-/*
- * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
- * false if 'v' + 1 would be bigger than 'below'.
- */
-static bool atomic_inc_below(atomic_t *v, int below)
-{
-	int cur = atomic_read(v);
-
-	for (;;) {
-		int old;
-
-		if (cur >= below)
-			return false;
-		old = atomic_cmpxchg(v, cur, cur + 1);
-		if (old == cur)
-			break;
-		cur = old;
-	}
-
-	return true;
-}
-
 static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
 {
 	if (rwb_enabled(rwb)) {
@@ -116,7 +95,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb;
+	struct bdi_writeback *wb = &rwb->rqos.q->backing_dev_info->wb;
 
 	return time_before(jiffies, wb->dirty_sleep + HZ);
 }
@@ -144,8 +123,9 @@ static void rwb_wake_all(struct rq_wb *rwb)
 	}
 }
 
-void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
+static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	struct rq_wait *rqw;
 	int inflight, limit;
 
@@ -186,7 +166,7 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
 		int diff = limit - inflight;
 
 		if (!inflight || diff >= rwb->wb_background / 2)
-			wake_up_all(&rqw->wait);
+			wake_up(&rqw->wait);
 	}
 }
 
@@ -194,10 +174,9 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
  * Called on completion of a request. Note that it's also called when
  * a request is merged, when the request gets freed.
  */
-void wbt_done(struct rq_wb *rwb, struct request *rq)
+static void wbt_done(struct rq_qos *rqos, struct request *rq)
 {
-	if (!rwb)
-		return;
+	struct rq_wb *rwb = RQWB(rqos);
 
 	if (!wbt_is_tracked(rq)) {
 		if (rwb->sync_cookie == rq) {
@@ -209,72 +188,11 @@ void wbt_done(struct rq_wb *rwb, struct request *rq)
 			wb_timestamp(rwb, &rwb->last_comp);
 	} else {
 		WARN_ON_ONCE(rq == rwb->sync_cookie);
-		__wbt_done(rwb, wbt_flags(rq));
+		__wbt_done(rqos, wbt_flags(rq));
 	}
 	wbt_clear_state(rq);
 }
 
-/*
- * Return true, if we can't increase the depth further by scaling
- */
-static bool calc_wb_limits(struct rq_wb *rwb)
-{
-	unsigned int depth;
-	bool ret = false;
-
-	if (!rwb->min_lat_nsec) {
-		rwb->wb_max = rwb->wb_normal = rwb->wb_background = 0;
-		return false;
-	}
-
-	/*
-	 * For QD=1 devices, this is a special case. It's important for those
-	 * to have one request ready when one completes, so force a depth of
-	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
-	 * since the device can't have more than that in flight. If we're
-	 * scaling down, then keep a setting of 1/1/1.
-	 */
-	if (rwb->queue_depth == 1) {
-		if (rwb->scale_step > 0)
-			rwb->wb_max = rwb->wb_normal = 1;
-		else {
-			rwb->wb_max = rwb->wb_normal = 2;
-			ret = true;
-		}
-		rwb->wb_background = 1;
-	} else {
-		/*
-		 * scale_step == 0 is our default state. If we have suffered
-		 * latency spikes, step will be > 0, and we shrink the
-		 * allowed write depths. If step is < 0, we're only doing
-		 * writes, and we allow a temporarily higher depth to
-		 * increase performance.
-		 */
-		depth = min_t(unsigned int, RWB_DEF_DEPTH, rwb->queue_depth);
-		if (rwb->scale_step > 0)
-			depth = 1 + ((depth - 1) >> min(31, rwb->scale_step));
-		else if (rwb->scale_step < 0) {
-			unsigned int maxd = 3 * rwb->queue_depth / 4;
-
-			depth = 1 + ((depth - 1) << -rwb->scale_step);
-			if (depth > maxd) {
-				depth = maxd;
-				ret = true;
-			}
-		}
-
-		/*
-		 * Set our max/normal/bg queue depths based on how far
-		 * we have scaled down (->scale_step).
-		 */
-		rwb->wb_max = depth;
-		rwb->wb_normal = (rwb->wb_max + 1) / 2;
-		rwb->wb_background = (rwb->wb_max + 3) / 4;
-	}
-
-	return ret;
-}
-
 static inline bool stat_sample_valid(struct blk_rq_stat *stat)
 {
 	/*
@@ -307,7 +225,8 @@ enum {
 
 static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 {
-	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info;
+	struct rq_depth *rqd = &rwb->rq_depth;
 	u64 thislat;
 
 	/*
@@ -351,7 +270,7 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 		return LAT_EXCEEDED;
 	}
 
-	if (rwb->scale_step)
+	if (rqd->scale_step)
 		trace_wbt_stat(bdi, stat);
 
 	return LAT_OK;
@@ -359,58 +278,48 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 
 static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
 {
-	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info;
+	struct rq_depth *rqd = &rwb->rq_depth;
 
-	trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec,
-			rwb->wb_background, rwb->wb_normal, rwb->wb_max);
+	trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec,
+			rwb->wb_background, rwb->wb_normal, rqd->max_depth);
 }
 
-static void scale_up(struct rq_wb *rwb)
+static void calc_wb_limits(struct rq_wb *rwb)
 {
-	/*
-	 * Hit max in previous round, stop here
-	 */
-	if (rwb->scaled_max)
-		return;
+	if (rwb->min_lat_nsec == 0) {
+		rwb->wb_normal = rwb->wb_background = 0;
+	} else if (rwb->rq_depth.max_depth <= 2) {
+		rwb->wb_normal = rwb->rq_depth.max_depth;
+		rwb->wb_background = 1;
+	} else {
+		rwb->wb_normal = (rwb->rq_depth.max_depth + 1) / 2;
+		rwb->wb_background = (rwb->rq_depth.max_depth + 3) / 4;
+	}
+}
 
-	rwb->scale_step--;
+static void scale_up(struct rq_wb *rwb)
+{
+	rq_depth_scale_up(&rwb->rq_depth);
+	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
-
-	rwb->scaled_max = calc_wb_limits(rwb);
-
-	rwb_wake_all(rwb);
-
-	rwb_trace_step(rwb, "step up");
+	rwb_trace_step(rwb, "scale up");
 }
 
-/*
- * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
- * had a latency violation.
- */
 static void scale_down(struct rq_wb *rwb, bool hard_throttle)
 {
-	/*
-	 * Stop scaling down when we've hit the limit. This also prevents
-	 * ->scale_step from going to crazy values, if the device can't
-	 * keep up.
-	 */
-	if (rwb->wb_max == 1)
-		return;
-
-	if (rwb->scale_step < 0 && hard_throttle)
-		rwb->scale_step = 0;
-	else
-		rwb->scale_step++;
-
-	rwb->scaled_max = false;
-	rwb->unknown_cnt = 0;
+	rq_depth_scale_down(&rwb->rq_depth, hard_throttle);
 	calc_wb_limits(rwb);
-	rwb_trace_step(rwb, "step down");
+	rwb->unknown_cnt = 0;
+	rwb_wake_all(rwb);
+	rwb_trace_step(rwb, "scale down");
 }
 
 static void rwb_arm_timer(struct rq_wb *rwb)
 {
-	if (rwb->scale_step > 0) {
+	struct rq_depth *rqd = &rwb->rq_depth;
+
+	if (rqd->scale_step > 0) {
 		/*
 		 * We should speed this up, using some variant of a fast
 		 * integer inverse square root calculation. Since we only do
@@ -418,7 +327,7 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 		 * though.
 		 */
 		rwb->cur_win_nsec = div_u64(rwb->win_nsec << 4,
-					int_sqrt((rwb->scale_step + 1) << 8));
+					int_sqrt((rqd->scale_step + 1) << 8));
 	} else {
 		/*
 		 * For step < 0, we don't want to increase/decrease the
@@ -433,12 +342,13 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 static void wb_timer_fn(struct blk_stat_callback *cb)
 {
 	struct rq_wb *rwb = cb->data;
+	struct rq_depth *rqd = &rwb->rq_depth;
 	unsigned int inflight = wbt_inflight(rwb);
 	int status;
 
 	status = latency_exceeded(rwb, cb->stat);
 
-	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
+	trace_wbt_timer(rwb->rqos.q->backing_dev_info, status, rqd->scale_step,
 			inflight);
 
 	/*
@@ -469,9 +379,9 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
 		 * currently don't have a valid read/write sample. For that
 		 * case, slowly return to center state (step == 0).
 		 */
-		if (rwb->scale_step > 0)
+		if (rqd->scale_step > 0)
 			scale_up(rwb);
-		else if (rwb->scale_step < 0)
+		else if (rqd->scale_step < 0)
 			scale_down(rwb, false);
 		break;
 	default:
@@ -481,19 +391,50 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
 	/*
 	 * Re-arm timer, if we have IO in flight
 	 */
-	if (rwb->scale_step || inflight)
+	if (rqd->scale_step || inflight)
 		rwb_arm_timer(rwb);
 }
 
-void wbt_update_limits(struct rq_wb *rwb)
+static void __wbt_update_limits(struct rq_wb *rwb)
 {
-	rwb->scale_step = 0;
-	rwb->scaled_max = false;
+	struct rq_depth *rqd = &rwb->rq_depth;
+
+	rqd->scale_step = 0;
+	rqd->scaled_max = false;
+
+	rq_depth_calc_max_depth(rqd);
 	calc_wb_limits(rwb);
 
 	rwb_wake_all(rwb);
 }
 
+void wbt_update_limits(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return;
+	__wbt_update_limits(RQWB(rqos));
+}
+
+u64 wbt_get_min_lat(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return 0;
+	return RQWB(rqos)->min_lat_nsec;
+}
+
+void wbt_set_min_lat(struct request_queue *q, u64 val)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return;
+	RQWB(rqos)->min_lat_nsec = val;
+	RQWB(rqos)->enable_state = WBT_STATE_ON_MANUAL;
+	__wbt_update_limits(RQWB(rqos));
+}
+
+
 static bool close_io(struct rq_wb *rwb)
 {
 	const unsigned long now = jiffies;
@@ -520,7 +461,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 	 * IO for a bit.
 	 */
 	if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
-		limit = rwb->wb_max;
+		limit = rwb->rq_depth.max_depth;
 	else if ((rw & REQ_BACKGROUND) || close_io(rwb)) {
 		/*
 		 * If less than 100ms since we completed unrelated IO,
@@ -533,30 +474,6 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 	return limit;
 }
 
-static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
-			     wait_queue_entry_t *wait, unsigned long rw)
-{
-	/*
-	 * inc it here even if disabled, since we'll dec it at completion.
-	 * this only happens if the task was sleeping in __wbt_wait(),
-	 * and someone turned it off at the same time.
-	 */
-	if (!rwb_enabled(rwb)) {
-		atomic_inc(&rqw->inflight);
-		return true;
-	}
-
-	/*
-	 * If the waitqueue is already active and we are not the next
-	 * in line to be woken up, wait for our turn.
-	 */
-	if (waitqueue_active(&rqw->wait) &&
-	    rqw->wait.head.next != &wait->entry)
-		return false;
-
-	return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw));
-}
-
 /*
  * Block if we will exceed our limit, or if we are currently waiting for
  * the timer to kick off queuing again.
@@ -567,16 +484,32 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
 	__acquires(lock)
 {
 	struct rq_wait *rqw = get_rq_wait(rwb, wb_acct);
-	DEFINE_WAIT(wait);
+	DECLARE_WAITQUEUE(wait, current);
 
-	if (may_queue(rwb, rqw, &wait, rw))
+	/*
+	* inc it here even if disabled, since we'll dec it at completion.
+	* this only happens if the task was sleeping in __wbt_wait(),
+	* and someone turned it off at the same time.
+	*/
+	if (!rwb_enabled(rwb)) {
+		atomic_inc(&rqw->inflight);
 		return;
+	}
 
+	if (!waitqueue_active(&rqw->wait)
+		&& rq_wait_inc_below(rqw, get_limit(rwb, rw)))
+		return;
+
+	add_wait_queue_exclusive(&rqw->wait, &wait);
 	do {
-		prepare_to_wait_exclusive(&rqw->wait, &wait,
-						TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE);
 
-		if (may_queue(rwb, rqw, &wait, rw))
+		if (!rwb_enabled(rwb)) {
+			atomic_inc(&rqw->inflight);
+			break;
+		}
+
+		if (rq_wait_inc_below(rqw, get_limit(rwb, rw)))
 			break;
 
 		if (lock) {
@@ -587,7 +520,8 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
 			io_schedule();
 	} while (1);
 
-	finish_wait(&rqw->wait, &wait);
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&rqw->wait, &wait);
 }
 
 static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
@@ -608,43 +542,72 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
 	}
 }
 
+static enum wbt_flags bio_to_wbt_flags(struct rq_wb *rwb, struct bio *bio)
+{
+	enum wbt_flags flags = 0;
+
+	if (bio_op(bio) == REQ_OP_READ) {
+		flags = WBT_READ;
+	} else if (wbt_should_throttle(rwb, bio)) {
+		if (current_is_kswapd())
+			flags |= WBT_KSWAPD;
+		if (bio_op(bio) == REQ_OP_DISCARD)
+			flags |= WBT_DISCARD;
+		flags |= WBT_TRACKED;
+	}
+	return flags;
+}
+
+static void wbt_cleanup(struct rq_qos *rqos, struct bio *bio)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	enum wbt_flags flags = bio_to_wbt_flags(rwb, bio);
+	__wbt_done(rqos, flags);
+}
+
 /*
  * Returns true if the IO request should be accounted, false if not.
  * May sleep, if we have exceeded the writeback limits. Caller can pass
  * in an irq held spinlock, if it holds one when calling this function.
  * If we do sleep, we'll release and re-grab it.
  */
-enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
+static void wbt_wait(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock)
 {
-	enum wbt_flags ret = 0;
+	struct rq_wb *rwb = RQWB(rqos);
+	enum wbt_flags flags;
 
 	if (!rwb_enabled(rwb))
-		return 0;
+		return;
 
-	if (bio_op(bio) == REQ_OP_READ)
-		ret = WBT_READ;
+	flags = bio_to_wbt_flags(rwb, bio);
 
 	if (!wbt_should_throttle(rwb, bio)) {
-		if (ret & WBT_READ)
+		if (flags & WBT_READ)
 			wb_timestamp(rwb, &rwb->last_issue);
-		return ret;
+		return;
 	}
 
 	if (current_is_kswapd())
-		ret |= WBT_KSWAPD;
+		flags |= WBT_KSWAPD;
 	if (bio_op(bio) == REQ_OP_DISCARD)
-		ret |= WBT_DISCARD;
+		flags |= WBT_DISCARD;
 
-	__wbt_wait(rwb, ret, bio->bi_opf, lock);
+	__wbt_wait(rwb, flags, bio->bi_opf, lock);
 
 	if (!blk_stat_is_active(rwb->cb))
 		rwb_arm_timer(rwb);
+}
 
-	return ret | WBT_TRACKED;
+static void wbt_track(struct rq_qos *rqos, struct request *rq, struct bio *bio)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	rq->wbt_flags |= bio_to_wbt_flags(rwb, bio);
 }
 
-void wbt_issue(struct rq_wb *rwb, struct request *rq)
+void wbt_issue(struct rq_qos *rqos, struct request *rq)
 {
+	struct rq_wb *rwb = RQWB(rqos);
+
 	if (!rwb_enabled(rwb))
 		return;
 
@@ -661,8 +624,9 @@ void wbt_issue(struct rq_wb *rwb, struct request *rq)
 	}
 }
 
-void wbt_requeue(struct rq_wb *rwb, struct request *rq)
+void wbt_requeue(struct rq_qos *rqos, struct request *rq)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	if (!rwb_enabled(rwb))
 		return;
 	if (rq == rwb->sync_cookie) {
@@ -671,39 +635,30 @@ void wbt_requeue(struct rq_wb *rwb, struct request *rq)
 	}
 }
 
-void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
-	if (rwb) {
-		rwb->queue_depth = depth;
-		wbt_update_limits(rwb);
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (rqos) {
+		RQWB(rqos)->rq_depth.queue_depth = depth;
+		__wbt_update_limits(RQWB(rqos));
 	}
 }
 
-void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on)
+void wbt_set_write_cache(struct request_queue *q, bool write_cache_on)
 {
-	if (rwb)
-		rwb->wc = write_cache_on;
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (rqos)
+		RQWB(rqos)->wc = write_cache_on;
 }
 
 /*
- * Disable wbt, if enabled by default.
- */
-void wbt_disable_default(struct request_queue *q)
-{
-	struct rq_wb *rwb = q->rq_wb;
-
-	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT)
-		wbt_exit(q);
-}
-EXPORT_SYMBOL_GPL(wbt_disable_default);
-
-/*
  * Enable wbt if defaults are configured that way
  */
 void wbt_enable_default(struct request_queue *q)
 {
+	struct rq_qos *rqos = wbt_rq_qos(q);
 	/* Throttling already enabled? */
-	if (q->rq_wb)
+	if (rqos)
 		return;
 
 	/* Queue not registered? Maybe shutting down... */
@@ -741,6 +696,42 @@ static int wbt_data_dir(const struct request *rq)
 	return -1;
 }
 
+static void wbt_exit(struct rq_qos *rqos)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	struct request_queue *q = rqos->q;
+
+	blk_stat_remove_callback(q, rwb->cb);
+	blk_stat_free_callback(rwb->cb);
+	kfree(rwb);
+}
+
+/*
+ * Disable wbt, if enabled by default.
+ */
+void wbt_disable_default(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	struct rq_wb *rwb;
+	if (!rqos)
+		return;
+	rwb = RQWB(rqos);
+	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
+		rwb->wb_normal = 0;
+}
+EXPORT_SYMBOL_GPL(wbt_disable_default);
+
+
+static struct rq_qos_ops wbt_rqos_ops = {
+	.throttle = wbt_wait,
+	.issue = wbt_issue,
+	.track = wbt_track,
+	.requeue = wbt_requeue,
+	.done = wbt_done,
+	.cleanup = wbt_cleanup,
+	.exit = wbt_exit,
+};
+
 int wbt_init(struct request_queue *q)
 {
 	struct rq_wb *rwb;
@@ -756,39 +747,29 @@ int wbt_init(struct request_queue *q)
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < WBT_NUM_RWQ; i++) {
-		atomic_set(&rwb->rq_wait[i].inflight, 0);
-		init_waitqueue_head(&rwb->rq_wait[i].wait);
-	}
+	for (i = 0; i < WBT_NUM_RWQ; i++)
+		rq_wait_init(&rwb->rq_wait[i]);
 
+	rwb->rqos.id = RQ_QOS_WBT;
+	rwb->rqos.ops = &wbt_rqos_ops;
+	rwb->rqos.q = q;
 	rwb->last_comp = rwb->last_issue = jiffies;
-	rwb->queue = q;
 	rwb->win_nsec = RWB_WINDOW_NSEC;
 	rwb->enable_state = WBT_STATE_ON_DEFAULT;
-	wbt_update_limits(rwb);
+	rwb->wc = 1;
+	rwb->rq_depth.default_depth = RWB_DEF_DEPTH;
+	__wbt_update_limits(rwb);
 
 	/*
 	 * Assign rwb and add the stats callback.
 	 */
-	q->rq_wb = rwb;
+	rq_qos_add(q, &rwb->rqos);
 	blk_stat_add_callback(q, rwb->cb);
 
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
 
-	wbt_set_queue_depth(rwb, blk_queue_depth(q));
-	wbt_set_write_cache(rwb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
+	wbt_set_queue_depth(q, blk_queue_depth(q));
+	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 
 	return 0;
 }
-
-void wbt_exit(struct request_queue *q)
-{
-	struct rq_wb *rwb = q->rq_wb;
-
-	if (rwb) {
-		blk_stat_remove_callback(q, rwb->cb);
-		blk_stat_free_callback(rwb->cb);
-		q->rq_wb = NULL;
-		kfree(rwb);
-	}
-}
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index 300df531d0a6..f47218d5b3b2 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -9,6 +9,7 @@
 #include <linux/ktime.h>
 
 #include "blk-stat.h"
+#include "blk-rq-qos.h"
 
 enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
@@ -35,20 +36,12 @@ enum {
 	WBT_STATE_ON_MANUAL	= 2,
 };
 
-struct rq_wait {
-	wait_queue_head_t wait;
-	atomic_t inflight;
-};
-
 struct rq_wb {
 	/*
 	 * Settings that govern how we throttle
 	 */
 	unsigned int wb_background;		/* background writeback */
 	unsigned int wb_normal;			/* normal writeback */
-	unsigned int wb_max;			/* max throughput writeback */
-	int scale_step;
-	bool scaled_max;
 
 	short enable_state;			/* WBT_STATE_* */
 
@@ -67,15 +60,20 @@ struct rq_wb {
 	void *sync_cookie;
 
 	unsigned int wc;
-	unsigned int queue_depth;
 
 	unsigned long last_issue;		/* last non-throttled issue */
 	unsigned long last_comp;		/* last non-throttled comp */
 	unsigned long min_lat_nsec;
-	struct request_queue *queue;
+	struct rq_qos rqos;
 	struct rq_wait rq_wait[WBT_NUM_RWQ];
+	struct rq_depth rq_depth;
 };
 
+static inline struct rq_wb *RQWB(struct rq_qos *rqos)
+{
+	return container_of(rqos, struct rq_wb, rqos);
+}
+
 static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 {
 	unsigned int i, ret = 0;
@@ -86,26 +84,19 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 	return ret;
 }
 
-#ifdef CONFIG_BLK_WBT
 
-static inline void wbt_track(struct request *rq, enum wbt_flags flags)
-{
-	rq->wbt_flags |= flags;
-}
+#ifdef CONFIG_BLK_WBT
 
-void __wbt_done(struct rq_wb *, enum wbt_flags);
-void wbt_done(struct rq_wb *, struct request *);
-enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *);
 int wbt_init(struct request_queue *);
-void wbt_exit(struct request_queue *);
-void wbt_update_limits(struct rq_wb *);
-void wbt_requeue(struct rq_wb *, struct request *);
-void wbt_issue(struct rq_wb *, struct request *);
+void wbt_update_limits(struct request_queue *);
 void wbt_disable_default(struct request_queue *);
 void wbt_enable_default(struct request_queue *);
 
-void wbt_set_queue_depth(struct rq_wb *, unsigned int);
-void wbt_set_write_cache(struct rq_wb *, bool);
+u64 wbt_get_min_lat(struct request_queue *q);
+void wbt_set_min_lat(struct request_queue *q, u64 val);
+
+void wbt_set_queue_depth(struct request_queue *, unsigned int);
+void wbt_set_write_cache(struct request_queue *, bool);
 
 u64 wbt_default_latency_nsec(struct request_queue *);
 
@@ -114,43 +105,30 @@ u64 wbt_default_latency_nsec(struct request_queue *);
 static inline void wbt_track(struct request *rq, enum wbt_flags flags)
 {
 }
-static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
-{
-}
-static inline void wbt_done(struct rq_wb *rwb, struct request *rq)
-{
-}
-static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio,
-				      spinlock_t *lock)
-{
-	return 0;
-}
 static inline int wbt_init(struct request_queue *q)
 {
 	return -EINVAL;
 }
-static inline void wbt_exit(struct request_queue *q)
-{
-}
-static inline void wbt_update_limits(struct rq_wb *rwb)
+static inline void wbt_update_limits(struct request_queue *q)
 {
 }
-static inline void wbt_requeue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_disable_default(struct request_queue *q)
 {
 }
-static inline void wbt_issue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_enable_default(struct request_queue *q)
 {
 }
-static inline void wbt_disable_default(struct request_queue *q)
+static inline void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 }
-static inline void wbt_enable_default(struct request_queue *q)
+static inline void wbt_set_write_cache(struct request_queue *q, bool wc)
 {
 }
-static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+static inline u64 wbt_get_min_lat(struct request_queue *q)
 {
+	return 0;
 }
-static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc)
+static inline void wbt_set_min_lat(struct request_queue *q, u64 val)
 {
 }
 static inline u64 wbt_default_latency_nsec(struct request_queue *q)
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 51000914e23f..c461cf63f1f4 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -200,7 +200,7 @@ int blkdev_report_zones(struct block_device *bdev,
 		/* Get header in the first page */
 		ofst = 0;
 		if (!nr_rep) {
-			hdr = (struct blk_zone_report_hdr *) addr;
+			hdr = addr;
 			nr_rep = hdr->nr_zones;
 			ofst = sizeof(struct blk_zone_report_hdr);
 		}
diff --git a/block/blk.h b/block/blk.h
index 8d23aea96ce9..d4d67e948920 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -130,6 +130,7 @@ void blk_free_flush_queue(struct blk_flush_queue *q);
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask);
 void blk_exit_rl(struct request_queue *q, struct request_list *rl);
+void blk_exit_queue(struct request_queue *q);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
 void blk_queue_bypass_start(struct request_queue *q);
@@ -412,4 +413,10 @@ static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
 
 extern void blk_drain_queue(struct request_queue *q);
 
+#ifdef CONFIG_BLK_CGROUP_IOLATENCY
+extern int blk_iolatency_init(struct request_queue *q);
+#else
+static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
+#endif
+
 #endif /* BLK_INTERNAL_H */
diff --git a/block/bounce.c b/block/bounce.c
index fd31347b7836..bc63b3a2d18c 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -195,6 +195,73 @@ static void bounce_end_io_read_isa(struct bio *bio)
 	__bounce_end_io_read(bio, &isa_page_pool);
 }
 
+static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask,
+		struct bio_set *bs)
+{
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	struct bio *bio;
+
+	/*
+	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
+	 * bio_src->bi_io_vec to bio->bi_io_vec.
+	 *
+	 * We can't do that anymore, because:
+	 *
+	 *  - The point of cloning the biovec is to produce a bio with a biovec
+	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
+	 *
+	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
+	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
+	 *    But the clone should succeed as long as the number of biovecs we
+	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
+	 *
+	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
+	 *    that does not own the bio - reason being drivers don't use it for
+	 *    iterating over the biovec anymore, so expecting it to be kept up
+	 *    to date (i.e. for clones that share the parent biovec) is just
+	 *    asking for trouble and would force extra work on
+	 *    __bio_clone_fast() anyways.
+	 */
+
+	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
+	if (!bio)
+		return NULL;
+	bio->bi_disk		= bio_src->bi_disk;
+	bio->bi_opf		= bio_src->bi_opf;
+	bio->bi_write_hint	= bio_src->bi_write_hint;
+	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
+	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
+
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_ZEROES:
+		break;
+	case REQ_OP_WRITE_SAME:
+		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
+		break;
+	default:
+		bio_for_each_segment(bv, bio_src, iter)
+			bio->bi_io_vec[bio->bi_vcnt++] = bv;
+		break;
+	}
+
+	if (bio_integrity(bio_src)) {
+		int ret;
+
+		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
+		if (ret < 0) {
+			bio_put(bio);
+			return NULL;
+		}
+	}
+
+	bio_clone_blkcg_association(bio, bio_src);
+
+	return bio;
+}
+
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 			       mempool_t *pool)
 {
@@ -222,7 +289,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 		generic_make_request(*bio_orig);
 		*bio_orig = bio;
 	}
-	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
+	bio = bounce_clone_bio(*bio_orig, GFP_NOIO, passthrough ? NULL :
 			&bounce_bio_set);
 
 	bio_for_each_segment_all(to, bio, i) {
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 9419def8c017..f3501cdaf1a6 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -48,9 +48,8 @@ static int bsg_transport_fill_hdr(struct request *rq, struct sg_io_v4 *hdr,
 
 	job->request_len = hdr->request_len;
 	job->request = memdup_user(uptr64(hdr->request), hdr->request_len);
-	if (IS_ERR(job->request))
-		return PTR_ERR(job->request);
-	return 0;
+
+	return PTR_ERR_OR_ZERO(job->request);
 }
 
 static int bsg_transport_complete_rq(struct request *rq, struct sg_io_v4 *hdr)
diff --git a/block/bsg.c b/block/bsg.c
index 3da540faf673..db588add6ba6 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -13,11 +13,9 @@
 #include <linux/init.h>
 #include <linux/file.h>
 #include <linux/blkdev.h>
-#include <linux/poll.h>
 #include <linux/cdev.h>
 #include <linux/jiffies.h>
 #include <linux/percpu.h>
-#include <linux/uio.h>
 #include <linux/idr.h>
 #include <linux/bsg.h>
 #include <linux/slab.h>
@@ -38,21 +36,10 @@
 struct bsg_device {
 	struct request_queue *queue;
 	spinlock_t lock;
-	struct list_head busy_list;
-	struct list_head done_list;
 	struct hlist_node dev_list;
 	atomic_t ref_count;
-	int queued_cmds;
-	int done_cmds;
-	wait_queue_head_t wq_done;
-	wait_queue_head_t wq_free;
 	char name[20];
 	int max_queue;
-	unsigned long flags;
-};
-
-enum {
-	BSG_F_BLOCK		= 1,
 };
 
 #define BSG_DEFAULT_CMDS	64
@@ -67,64 +54,6 @@ static struct hlist_head bsg_device_list[BSG_LIST_ARRAY_SIZE];
 static struct class *bsg_class;
 static int bsg_major;
 
-static struct kmem_cache *bsg_cmd_cachep;
-
-/*
- * our internal command type
- */
-struct bsg_command {
-	struct bsg_device *bd;
-	struct list_head list;
-	struct request *rq;
-	struct bio *bio;
-	struct bio *bidi_bio;
-	int err;
-	struct sg_io_v4 hdr;
-};
-
-static void bsg_free_command(struct bsg_command *bc)
-{
-	struct bsg_device *bd = bc->bd;
-	unsigned long flags;
-
-	kmem_cache_free(bsg_cmd_cachep, bc);
-
-	spin_lock_irqsave(&bd->lock, flags);
-	bd->queued_cmds--;
-	spin_unlock_irqrestore(&bd->lock, flags);
-
-	wake_up(&bd->wq_free);
-}
-
-static struct bsg_command *bsg_alloc_command(struct bsg_device *bd)
-{
-	struct bsg_command *bc = ERR_PTR(-EINVAL);
-
-	spin_lock_irq(&bd->lock);
-
-	if (bd->queued_cmds >= bd->max_queue)
-		goto out;
-
-	bd->queued_cmds++;
-	spin_unlock_irq(&bd->lock);
-
-	bc = kmem_cache_zalloc(bsg_cmd_cachep, GFP_KERNEL);
-	if (unlikely(!bc)) {
-		spin_lock_irq(&bd->lock);
-		bd->queued_cmds--;
-		bc = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	bc->bd = bd;
-	INIT_LIST_HEAD(&bc->list);
-	bsg_dbg(bd, "returning free cmd %p\n", bc);
-	return bc;
-out:
-	spin_unlock_irq(&bd->lock);
-	return bc;
-}
-
 static inline struct hlist_head *bsg_dev_idx_hash(int index)
 {
 	return &bsg_device_list[index & (BSG_LIST_ARRAY_SIZE - 1)];
@@ -285,101 +214,6 @@ out:
 	return ERR_PTR(ret);
 }
 
-/*
- * async completion call-back from the block layer, when scsi/ide/whatever
- * calls end_that_request_last() on a request
- */
-static void bsg_rq_end_io(struct request *rq, blk_status_t status)
-{
-	struct bsg_command *bc = rq->end_io_data;
-	struct bsg_device *bd = bc->bd;
-	unsigned long flags;
-
-	bsg_dbg(bd, "finished rq %p bc %p, bio %p\n",
-		rq, bc, bc->bio);
-
-	bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration);
-
-	spin_lock_irqsave(&bd->lock, flags);
-	list_move_tail(&bc->list, &bd->done_list);
-	bd->done_cmds++;
-	spin_unlock_irqrestore(&bd->lock, flags);
-
-	wake_up(&bd->wq_done);
-}
-
-/*
- * do final setup of a 'bc' and submit the matching 'rq' to the block
- * layer for io
- */
-static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
-			    struct bsg_command *bc, struct request *rq)
-{
-	int at_head = (0 == (bc->hdr.flags & BSG_FLAG_Q_AT_TAIL));
-
-	/*
-	 * add bc command to busy queue and submit rq for io
-	 */
-	bc->rq = rq;
-	bc->bio = rq->bio;
-	if (rq->next_rq)
-		bc->bidi_bio = rq->next_rq->bio;
-	bc->hdr.duration = jiffies;
-	spin_lock_irq(&bd->lock);
-	list_add_tail(&bc->list, &bd->busy_list);
-	spin_unlock_irq(&bd->lock);
-
-	bsg_dbg(bd, "queueing rq %p, bc %p\n", rq, bc);
-
-	rq->end_io_data = bc;
-	blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io);
-}
-
-static struct bsg_command *bsg_next_done_cmd(struct bsg_device *bd)
-{
-	struct bsg_command *bc = NULL;
-
-	spin_lock_irq(&bd->lock);
-	if (bd->done_cmds) {
-		bc = list_first_entry(&bd->done_list, struct bsg_command, list);
-		list_del(&bc->list);
-		bd->done_cmds--;
-	}
-	spin_unlock_irq(&bd->lock);
-
-	return bc;
-}
-
-/*
- * Get a finished command from the done list
- */
-static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd)
-{
-	struct bsg_command *bc;
-	int ret;
-
-	do {
-		bc = bsg_next_done_cmd(bd);
-		if (bc)
-			break;
-
-		if (!test_bit(BSG_F_BLOCK, &bd->flags)) {
-			bc = ERR_PTR(-EAGAIN);
-			break;
-		}
-
-		ret = wait_event_interruptible(bd->wq_done, bd->done_cmds);
-		if (ret) {
-			bc = ERR_PTR(-ERESTARTSYS);
-			break;
-		}
-	} while (1);
-
-	bsg_dbg(bd, "returning done %p\n", bc);
-
-	return bc;
-}
-
 static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 				    struct bio *bio, struct bio *bidi_bio)
 {
@@ -398,234 +232,6 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	return ret;
 }
 
-static bool bsg_complete(struct bsg_device *bd)
-{
-	bool ret = false;
-	bool spin;
-
-	do {
-		spin_lock_irq(&bd->lock);
-
-		BUG_ON(bd->done_cmds > bd->queued_cmds);
-
-		/*
-		 * All commands consumed.
-		 */
-		if (bd->done_cmds == bd->queued_cmds)
-			ret = true;
-
-		spin = !test_bit(BSG_F_BLOCK, &bd->flags);
-
-		spin_unlock_irq(&bd->lock);
-	} while (!ret && spin);
-
-	return ret;
-}
-
-static int bsg_complete_all_commands(struct bsg_device *bd)
-{
-	struct bsg_command *bc;
-	int ret, tret;
-
-	bsg_dbg(bd, "entered\n");
-
-	/*
-	 * wait for all commands to complete
-	 */
-	io_wait_event(bd->wq_done, bsg_complete(bd));
-
-	/*
-	 * discard done commands
-	 */
-	ret = 0;
-	do {
-		spin_lock_irq(&bd->lock);
-		if (!bd->queued_cmds) {
-			spin_unlock_irq(&bd->lock);
-			break;
-		}
-		spin_unlock_irq(&bd->lock);
-
-		bc = bsg_get_done_cmd(bd);
-		if (IS_ERR(bc))
-			break;
-
-		tret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio,
-						bc->bidi_bio);
-		if (!ret)
-			ret = tret;
-
-		bsg_free_command(bc);
-	} while (1);
-
-	return ret;
-}
-
-static int
-__bsg_read(char __user *buf, size_t count, struct bsg_device *bd,
-	   const struct iovec *iov, ssize_t *bytes_read)
-{
-	struct bsg_command *bc;
-	int nr_commands, ret;
-
-	if (count % sizeof(struct sg_io_v4))
-		return -EINVAL;
-
-	ret = 0;
-	nr_commands = count / sizeof(struct sg_io_v4);
-	while (nr_commands) {
-		bc = bsg_get_done_cmd(bd);
-		if (IS_ERR(bc)) {
-			ret = PTR_ERR(bc);
-			break;
-		}
-
-		/*
-		 * this is the only case where we need to copy data back
-		 * after completing the request. so do that here,
-		 * bsg_complete_work() cannot do that for us
-		 */
-		ret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio,
-					       bc->bidi_bio);
-
-		if (copy_to_user(buf, &bc->hdr, sizeof(bc->hdr)))
-			ret = -EFAULT;
-
-		bsg_free_command(bc);
-
-		if (ret)
-			break;
-
-		buf += sizeof(struct sg_io_v4);
-		*bytes_read += sizeof(struct sg_io_v4);
-		nr_commands--;
-	}
-
-	return ret;
-}
-
-static inline void bsg_set_block(struct bsg_device *bd, struct file *file)
-{
-	if (file->f_flags & O_NONBLOCK)
-		clear_bit(BSG_F_BLOCK, &bd->flags);
-	else
-		set_bit(BSG_F_BLOCK, &bd->flags);
-}
-
-/*
- * Check if the error is a "real" error that we should return.
- */
-static inline int err_block_err(int ret)
-{
-	if (ret && ret != -ENOSPC && ret != -ENODATA && ret != -EAGAIN)
-		return 1;
-
-	return 0;
-}
-
-static ssize_t
-bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
-{
-	struct bsg_device *bd = file->private_data;
-	int ret;
-	ssize_t bytes_read;
-
-	bsg_dbg(bd, "read %zd bytes\n", count);
-
-	bsg_set_block(bd, file);
-
-	bytes_read = 0;
-	ret = __bsg_read(buf, count, bd, NULL, &bytes_read);
-	*ppos = bytes_read;
-
-	if (!bytes_read || err_block_err(ret))
-		bytes_read = ret;
-
-	return bytes_read;
-}
-
-static int __bsg_write(struct bsg_device *bd, const char __user *buf,
-		       size_t count, ssize_t *bytes_written, fmode_t mode)
-{
-	struct bsg_command *bc;
-	struct request *rq;
-	int ret, nr_commands;
-
-	if (count % sizeof(struct sg_io_v4))
-		return -EINVAL;
-
-	nr_commands = count / sizeof(struct sg_io_v4);
-	rq = NULL;
-	bc = NULL;
-	ret = 0;
-	while (nr_commands) {
-		struct request_queue *q = bd->queue;
-
-		bc = bsg_alloc_command(bd);
-		if (IS_ERR(bc)) {
-			ret = PTR_ERR(bc);
-			bc = NULL;
-			break;
-		}
-
-		if (copy_from_user(&bc->hdr, buf, sizeof(bc->hdr))) {
-			ret = -EFAULT;
-			break;
-		}
-
-		/*
-		 * get a request, fill in the blanks, and add to request queue
-		 */
-		rq = bsg_map_hdr(bd->queue, &bc->hdr, mode);
-		if (IS_ERR(rq)) {
-			ret = PTR_ERR(rq);
-			rq = NULL;
-			break;
-		}
-
-		bsg_add_command(bd, q, bc, rq);
-		bc = NULL;
-		rq = NULL;
-		nr_commands--;
-		buf += sizeof(struct sg_io_v4);
-		*bytes_written += sizeof(struct sg_io_v4);
-	}
-
-	if (bc)
-		bsg_free_command(bc);
-
-	return ret;
-}
-
-static ssize_t
-bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
-{
-	struct bsg_device *bd = file->private_data;
-	ssize_t bytes_written;
-	int ret;
-
-	bsg_dbg(bd, "write %zd bytes\n", count);
-
-	if (unlikely(uaccess_kernel()))
-		return -EINVAL;
-
-	bsg_set_block(bd, file);
-
-	bytes_written = 0;
-	ret = __bsg_write(bd, buf, count, &bytes_written, file->f_mode);
-
-	*ppos = bytes_written;
-
-	/*
-	 * return bytes written on non-fatal errors
-	 */
-	if (!bytes_written || err_block_err(ret))
-		bytes_written = ret;
-
-	bsg_dbg(bd, "returning %zd\n", bytes_written);
-	return bytes_written;
-}
-
 static struct bsg_device *bsg_alloc_device(void)
 {
 	struct bsg_device *bd;
@@ -635,29 +241,20 @@ static struct bsg_device *bsg_alloc_device(void)
 		return NULL;
 
 	spin_lock_init(&bd->lock);
-
 	bd->max_queue = BSG_DEFAULT_CMDS;
-
-	INIT_LIST_HEAD(&bd->busy_list);
-	INIT_LIST_HEAD(&bd->done_list);
 	INIT_HLIST_NODE(&bd->dev_list);
-
-	init_waitqueue_head(&bd->wq_free);
-	init_waitqueue_head(&bd->wq_done);
 	return bd;
 }
 
 static int bsg_put_device(struct bsg_device *bd)
 {
-	int ret = 0, do_free;
 	struct request_queue *q = bd->queue;
 
 	mutex_lock(&bsg_mutex);
 
-	do_free = atomic_dec_and_test(&bd->ref_count);
-	if (!do_free) {
+	if (!atomic_dec_and_test(&bd->ref_count)) {
 		mutex_unlock(&bsg_mutex);
-		goto out;
+		return 0;
 	}
 
 	hlist_del(&bd->dev_list);
@@ -668,20 +265,9 @@ static int bsg_put_device(struct bsg_device *bd)
 	/*
 	 * close can always block
 	 */
-	set_bit(BSG_F_BLOCK, &bd->flags);
-
-	/*
-	 * correct error detection baddies here again. it's the responsibility
-	 * of the app to properly reap commands before close() if it wants
-	 * fool-proof error detection
-	 */
-	ret = bsg_complete_all_commands(bd);
-
 	kfree(bd);
-out:
-	if (do_free)
-		blk_put_queue(q);
-	return ret;
+	blk_put_queue(q);
+	return 0;
 }
 
 static struct bsg_device *bsg_add_device(struct inode *inode,
@@ -704,8 +290,6 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 
 	bd->queue = rq;
 
-	bsg_set_block(bd, file);
-
 	atomic_set(&bd->ref_count, 1);
 	hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
 
@@ -779,24 +363,6 @@ static int bsg_release(struct inode *inode, struct file *file)
 	return bsg_put_device(bd);
 }
 
-static __poll_t bsg_poll(struct file *file, poll_table *wait)
-{
-	struct bsg_device *bd = file->private_data;
-	__poll_t mask = 0;
-
-	poll_wait(file, &bd->wq_done, wait);
-	poll_wait(file, &bd->wq_free, wait);
-
-	spin_lock_irq(&bd->lock);
-	if (!list_empty(&bd->done_list))
-		mask |= EPOLLIN | EPOLLRDNORM;
-	if (bd->queued_cmds < bd->max_queue)
-		mask |= EPOLLOUT;
-	spin_unlock_irq(&bd->lock);
-
-	return mask;
-}
-
 static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct bsg_device *bd = file->private_data;
@@ -870,9 +436,6 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 }
 
 static const struct file_operations bsg_fops = {
-	.read		=	bsg_read,
-	.write		=	bsg_write,
-	.poll		=	bsg_poll,
 	.open		=	bsg_open,
 	.release	=	bsg_release,
 	.unlocked_ioctl	=	bsg_ioctl,
@@ -977,21 +540,12 @@ static int __init bsg_init(void)
 	int ret, i;
 	dev_t devid;
 
-	bsg_cmd_cachep = kmem_cache_create("bsg_cmd",
-				sizeof(struct bsg_command), 0, 0, NULL);
-	if (!bsg_cmd_cachep) {
-		printk(KERN_ERR "bsg: failed creating slab cache\n");
-		return -ENOMEM;
-	}
-
 	for (i = 0; i < BSG_LIST_ARRAY_SIZE; i++)
 		INIT_HLIST_HEAD(&bsg_device_list[i]);
 
 	bsg_class = class_create(THIS_MODULE, "bsg");
-	if (IS_ERR(bsg_class)) {
-		ret = PTR_ERR(bsg_class);
-		goto destroy_kmemcache;
-	}
+	if (IS_ERR(bsg_class))
+		return PTR_ERR(bsg_class);
 	bsg_class->devnode = bsg_devnode;
 
 	ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg");
@@ -1012,8 +566,6 @@ unregister_chrdev:
 	unregister_chrdev_region(MKDEV(bsg_major, 0), BSG_MAX_DEVS);
 destroy_bsg_class:
 	class_destroy(bsg_class);
-destroy_kmemcache:
-	kmem_cache_destroy(bsg_cmd_cachep);
 	return ret;
 }
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 82b6c27b3245..2eb87444b157 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3666,6 +3666,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct cfq_io_cq *cic)
 	switch (ioprio_class) {
 	default:
 		printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
+		/* fall through */
 	case IOPRIO_CLASS_NONE:
 		/*
 		 * no prio set, inherit CPU scheduling settings
@@ -4735,12 +4736,13 @@ USEC_SHOW_FUNCTION(cfq_target_latency_us_show, cfqd->cfq_target_latency);
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
-	unsigned int __data;						\
+	unsigned int __data, __min = (MIN), __max = (MAX);		\
+									\
 	cfq_var_store(&__data, (page));					\
-	if (__data < (MIN))						\
-		__data = (MIN);						\
-	else if (__data > (MAX))					\
-		__data = (MAX);						\
+	if (__data < __min)						\
+		__data = __min;						\
+	else if (__data > __max)					\
+		__data = __max;						\
 	if (__CONV)							\
 		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
 	else								\
@@ -4769,12 +4771,13 @@ STORE_FUNCTION(cfq_target_latency_store, &cfqd->cfq_target_latency, 1, UINT_MAX,
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
-	unsigned int __data;						\
+	unsigned int __data, __min = (MIN), __max = (MAX);		\
+									\
 	cfq_var_store(&__data, (page));					\
-	if (__data < (MIN))						\
-		__data = (MIN);						\
-	else if (__data > (MAX))					\
-		__data = (MAX);						\
+	if (__data < __min)						\
+		__data = __min;						\
+	else if (__data > __max)					\
+		__data = __max;						\
 	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
 	return count;							\
 }
diff --git a/block/genhd.c b/block/genhd.c
index f1543a45e73b..8cc719a37b32 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1333,21 +1333,28 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 		part_round_stats(gp->queue, cpu, hd);
 		part_stat_unlock();
 		part_in_flight(gp->queue, hd, inflight);
-		seq_printf(seqf, "%4d %7d %s %lu %lu %lu "
-			   "%u %lu %lu %lu %u %u %u %u\n",
+		seq_printf(seqf, "%4d %7d %s "
+			   "%lu %lu %lu %u "
+			   "%lu %lu %lu %u "
+			   "%u %u %u "
+			   "%lu %lu %lu %u\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
-			   part_stat_read(hd, ios[READ]),
-			   part_stat_read(hd, merges[READ]),
-			   part_stat_read(hd, sectors[READ]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[READ])),
-			   part_stat_read(hd, ios[WRITE]),
-			   part_stat_read(hd, merges[WRITE]),
-			   part_stat_read(hd, sectors[WRITE]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])),
+			   part_stat_read(hd, ios[STAT_READ]),
+			   part_stat_read(hd, merges[STAT_READ]),
+			   part_stat_read(hd, sectors[STAT_READ]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])),
+			   part_stat_read(hd, ios[STAT_WRITE]),
+			   part_stat_read(hd, merges[STAT_WRITE]),
+			   part_stat_read(hd, sectors[STAT_WRITE]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])),
 			   inflight[0],
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
-			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
+			   jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
+			   part_stat_read(hd, ios[STAT_DISCARD]),
+			   part_stat_read(hd, merges[STAT_DISCARD]),
+			   part_stat_read(hd, sectors[STAT_DISCARD]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD]))
 			);
 	}
 	disk_part_iter_exit(&piter);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 3dcfd4ec0e11..5a8975a1201c 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -130,19 +130,24 @@ ssize_t part_stat_show(struct device *dev,
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
-		"%8u %8u %8u"
+		"%8u %8u %8u "
+		"%8lu %8lu %8llu %8u"
 		"\n",
-		part_stat_read(p, ios[READ]),
-		part_stat_read(p, merges[READ]),
-		(unsigned long long)part_stat_read(p, sectors[READ]),
-		jiffies_to_msecs(part_stat_read(p, ticks[READ])),
-		part_stat_read(p, ios[WRITE]),
-		part_stat_read(p, merges[WRITE]),
-		(unsigned long long)part_stat_read(p, sectors[WRITE]),
-		jiffies_to_msecs(part_stat_read(p, ticks[WRITE])),
+		part_stat_read(p, ios[STAT_READ]),
+		part_stat_read(p, merges[STAT_READ]),
+		(unsigned long long)part_stat_read(p, sectors[STAT_READ]),
+		jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])),
+		part_stat_read(p, ios[STAT_WRITE]),
+		part_stat_read(p, merges[STAT_WRITE]),
+		(unsigned long long)part_stat_read(p, sectors[STAT_WRITE]),
+		jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])),
 		inflight[0],
 		jiffies_to_msecs(part_stat_read(p, io_ticks)),
-		jiffies_to_msecs(part_stat_read(p, time_in_queue)));
+		jiffies_to_msecs(part_stat_read(p, time_in_queue)),
+		part_stat_read(p, ios[STAT_DISCARD]),
+		part_stat_read(p, merges[STAT_DISCARD]),
+		(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
+		jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD])));
 }
 
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
diff --git a/block/partitions/aix.c b/block/partitions/aix.c
index 007f95eea0e1..903f3ed175d0 100644
--- a/block/partitions/aix.c
+++ b/block/partitions/aix.c
@@ -178,7 +178,7 @@ int aix_partition(struct parsed_partitions *state)
 	u32 vgda_sector = 0;
 	u32 vgda_len = 0;
 	int numlvs = 0;
-	struct pvd *pvd;
+	struct pvd *pvd = NULL;
 	struct lv_info {
 		unsigned short pps_per_lv;
 		unsigned short pps_found;
@@ -232,10 +232,11 @@ int aix_partition(struct parsed_partitions *state)
 				if (lvip[i].pps_per_lv)
 					foundlvs += 1;
 			}
+			/* pvd loops depend on n[].name and lvip[].pps_per_lv */
+			pvd = alloc_pvd(state, vgda_sector + 17);
 		}
 		put_dev_sector(sect);
 	}
-	pvd = alloc_pvd(state, vgda_sector + 17);
 	if (pvd) {
 		int numpps = be16_to_cpu(pvd->pp_count);
 		int psn_part1 = be32_to_cpu(pvd->psn_part1);
@@ -282,10 +283,14 @@ int aix_partition(struct parsed_partitions *state)
 				next_lp_ix += 1;
 		}
 		for (i = 0; i < state->limit; i += 1)
-			if (lvip[i].pps_found && !lvip[i].lv_is_contiguous)
+			if (lvip[i].pps_found && !lvip[i].lv_is_contiguous) {
+				char tmp[sizeof(n[i].name) + 1]; // null char
+
+				snprintf(tmp, sizeof(tmp), "%s", n[i].name);
 				pr_warn("partition %s (%u pp's found) is "
 					"not contiguous\n",
-					n[i].name, lvip[i].pps_found);
+					tmp, lvip[i].pps_found);
+			}
 		kfree(pvd);
 	}
 	kfree(n);
diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c
index 0417937dfe99..16766f267559 100644
--- a/block/partitions/ldm.c
+++ b/block/partitions/ldm.c
@@ -830,7 +830,6 @@ static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb)
 {
 	char buf[64];
 	int r_objid, r_name, r_id1, r_id2, len;
-	struct vblk_dgrp *dgrp;
 
 	BUG_ON (!buffer || !vb);
 
@@ -853,8 +852,6 @@ static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb)
 	if (len != get_unaligned_be32(buffer + 0x14))
 		return false;
 
-	dgrp = &vb->vblk.dgrp;
-
 	ldm_get_vstr (buffer + 0x18 + r_objid, buf, sizeof (buf));
 	return true;
 }
diff --git a/block/t10-pi.c b/block/t10-pi.c
index a98db384048f..62aed77d0bb9 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -184,3 +184,113 @@ const struct blk_integrity_profile t10_pi_type3_ip = {
 	.verify_fn		= t10_pi_type3_verify_ip,
 };
 EXPORT_SYMBOL(t10_pi_type3_ip);
+
+/**
+ * t10_pi_prepare - prepare PI prior submitting request to device
+ * @rq:              request with PI that should be prepared
+ * @protection_type: PI type (Type 1/Type 2/Type 3)
+ *
+ * For Type 1/Type 2, the virtual start sector is the one that was
+ * originally submitted by the block layer for the ref_tag usage. Due to
+ * partitioning, MD/DM cloning, etc. the actual physical start sector is
+ * likely to be different. Remap protection information to match the
+ * physical LBA.
+ *
+ * Type 3 does not have a reference tag so no remapping is required.
+ */
+void t10_pi_prepare(struct request *rq, u8 protection_type)
+{
+	const int tuple_sz = rq->q->integrity.tuple_size;
+	u32 ref_tag = t10_pi_ref_tag(rq);
+	struct bio *bio;
+
+	if (protection_type == T10_PI_TYPE3_PROTECTION)
+		return;
+
+	__rq_for_each_bio(bio, rq) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
+		u32 virt = bip_get_seed(bip) & 0xffffffff;
+		struct bio_vec iv;
+		struct bvec_iter iter;
+
+		/* Already remapped? */
+		if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
+			break;
+
+		bip_for_each_vec(iv, bip, iter) {
+			void *p, *pmap;
+			unsigned int j;
+
+			pmap = kmap_atomic(iv.bv_page);
+			p = pmap + iv.bv_offset;
+			for (j = 0; j < iv.bv_len; j += tuple_sz) {
+				struct t10_pi_tuple *pi = p;
+
+				if (be32_to_cpu(pi->ref_tag) == virt)
+					pi->ref_tag = cpu_to_be32(ref_tag);
+				virt++;
+				ref_tag++;
+				p += tuple_sz;
+			}
+
+			kunmap_atomic(pmap);
+		}
+
+		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
+	}
+}
+EXPORT_SYMBOL(t10_pi_prepare);
+
+/**
+ * t10_pi_complete - prepare PI prior returning request to the block layer
+ * @rq:              request with PI that should be prepared
+ * @protection_type: PI type (Type 1/Type 2/Type 3)
+ * @intervals:       total elements to prepare
+ *
+ * For Type 1/Type 2, the virtual start sector is the one that was
+ * originally submitted by the block layer for the ref_tag usage. Due to
+ * partitioning, MD/DM cloning, etc. the actual physical start sector is
+ * likely to be different. Since the physical start sector was submitted
+ * to the device, we should remap it back to virtual values expected by the
+ * block layer.
+ *
+ * Type 3 does not have a reference tag so no remapping is required.
+ */
+void t10_pi_complete(struct request *rq, u8 protection_type,
+		     unsigned int intervals)
+{
+	const int tuple_sz = rq->q->integrity.tuple_size;
+	u32 ref_tag = t10_pi_ref_tag(rq);
+	struct bio *bio;
+
+	if (protection_type == T10_PI_TYPE3_PROTECTION)
+		return;
+
+	__rq_for_each_bio(bio, rq) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
+		u32 virt = bip_get_seed(bip) & 0xffffffff;
+		struct bio_vec iv;
+		struct bvec_iter iter;
+
+		bip_for_each_vec(iv, bip, iter) {
+			void *p, *pmap;
+			unsigned int j;
+
+			pmap = kmap_atomic(iv.bv_page);
+			p = pmap + iv.bv_offset;
+			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
+				struct t10_pi_tuple *pi = p;
+
+				if (be32_to_cpu(pi->ref_tag) == ref_tag)
+					pi->ref_tag = cpu_to_be32(virt);
+				virt++;
+				ref_tag++;
+				intervals--;
+				p += tuple_sz;
+			}
+
+			kunmap_atomic(pmap);
+		}
+	}
+}
+EXPORT_SYMBOL(t10_pi_complete);
diff --git a/drivers/Makefile b/drivers/Makefile
index 24cd47014657..a6abd7a856c6 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -76,7 +76,7 @@ obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= macintosh/
 obj-$(CONFIG_IDE)		+= ide/
-obj-$(CONFIG_SCSI)		+= scsi/
+obj-y				+= scsi/
 obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 7a3a541046ed..08f26db2da7e 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -947,6 +947,24 @@ static int nc_dma_get_range(struct device *dev, u64 *size)
 	return 0;
 }
 
+static int rc_dma_get_range(struct device *dev, u64 *size)
+{
+	struct acpi_iort_node *node;
+	struct acpi_iort_root_complex *rc;
+
+	node = iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX,
+			      iort_match_node_callback, dev);
+	if (!node || node->revision < 1)
+		return -ENODEV;
+
+	rc = (struct acpi_iort_root_complex *)node->node_data;
+
+	*size = rc->memory_address_limit >= 64 ? U64_MAX :
+			1ULL<<rc->memory_address_limit;
+
+	return 0;
+}
+
 /**
  * iort_dma_setup() - Set-up device DMA parameters.
  *
@@ -960,25 +978,28 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	int ret, msb;
 
 	/*
-	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to
-	 * setup the correct supported mask.
+	 * If @dev is expected to be DMA-capable then the bus code that created
+	 * it should have initialised its dma_mask pointer by this point. For
+	 * now, we'll continue the legacy behaviour of coercing it to the
+	 * coherent mask if not, but we'll no longer do so quietly.
 	 */
-	if (!dev->coherent_dma_mask)
-		dev->coherent_dma_mask = DMA_BIT_MASK(32);
-
-	/*
-	 * Set it to coherent_dma_mask by default if the architecture
-	 * code has not set it.
-	 */
-	if (!dev->dma_mask)
+	if (!dev->dma_mask) {
+		dev_warn(dev, "DMA mask not set\n");
 		dev->dma_mask = &dev->coherent_dma_mask;
+	}
 
-	size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	if (dev->coherent_dma_mask)
+		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	else
+		size = 1ULL << 32;
 
-	if (dev_is_pci(dev))
+	if (dev_is_pci(dev)) {
 		ret = acpi_dma_get_range(dev, &dmaaddr, &offset, &size);
-	else
+		if (ret == -ENODEV)
+			ret = rc_dma_get_range(dev, &size);
+	} else {
 		ret = nc_dma_get_range(dev, &size);
+	}
 
 	if (!ret) {
 		msb = fls64(dmaaddr + size - 1);
@@ -993,6 +1014,7 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 		 * Limit coherent and dma mask based on size
 		 * retrieved from firmware.
 		 */
+		dev->bus_dma_mask = mask;
 		dev->coherent_dma_mask = mask;
 		*dev->dma_mask = mask;
 	}
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index aad1b01447de..8e270962b2f3 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -597,8 +597,9 @@ static int ata_get_identity(struct ata_port *ap, struct scsi_device *sdev,
 int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 {
 	int rc = 0;
+	u8 sensebuf[SCSI_SENSE_BUFFERSIZE];
 	u8 scsi_cmd[MAX_COMMAND_SIZE];
-	u8 args[4], *argbuf = NULL, *sensebuf = NULL;
+	u8 args[4], *argbuf = NULL;
 	int argsize = 0;
 	enum dma_data_direction data_dir;
 	struct scsi_sense_hdr sshdr;
@@ -610,10 +611,7 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	if (copy_from_user(args, arg, sizeof(args)))
 		return -EFAULT;
 
-	sensebuf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
-	if (!sensebuf)
-		return -ENOMEM;
-
+	memset(sensebuf, 0, sizeof(sensebuf));
 	memset(scsi_cmd, 0, sizeof(scsi_cmd));
 
 	if (args[3]) {
@@ -685,7 +683,6 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	 && copy_to_user(arg + sizeof(args), argbuf, argsize))
 		rc = -EFAULT;
 error:
-	kfree(sensebuf);
 	kfree(argbuf);
 	return rc;
 }
@@ -704,8 +701,9 @@ error:
 int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 {
 	int rc = 0;
+	u8 sensebuf[SCSI_SENSE_BUFFERSIZE];
 	u8 scsi_cmd[MAX_COMMAND_SIZE];
-	u8 args[7], *sensebuf = NULL;
+	u8 args[7];
 	struct scsi_sense_hdr sshdr;
 	int cmd_result;
 
@@ -715,10 +713,7 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	if (copy_from_user(args, arg, sizeof(args)))
 		return -EFAULT;
 
-	sensebuf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
-	if (!sensebuf)
-		return -ENOMEM;
-
+	memset(sensebuf, 0, sizeof(sensebuf));
 	memset(scsi_cmd, 0, sizeof(scsi_cmd));
 	scsi_cmd[0]  = ATA_16;
 	scsi_cmd[1]  = (3 << 1); /* Non-data */
@@ -769,7 +764,6 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	}
 
  error:
-	kfree(sensebuf);
 	return rc;
 }
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 30cc9c877ebb..eb9443d5bae1 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -540,16 +540,24 @@ ssize_t __weak cpu_show_spec_store_bypass(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_l1tf(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
 static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
+static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
 	&dev_attr_spectre_v1.attr,
 	&dev_attr_spectre_v2.attr,
 	&dev_attr_spec_store_bypass.attr,
+	&dev_attr_l1tf.attr,
 	NULL
 };
 
diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index cb0f1aad20b7..b9558ff20830 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -30,6 +30,7 @@ config BCMA_HOST_PCI
 
 config BCMA_HOST_SOC
 	bool "Support for BCMA in a SoC"
+	depends on HAS_IOMEM
 	help
 	  Host interface for a Broadcom AIX bus directly mapped into
 	  the memory. This only works with the Broadcom SoCs from the
@@ -61,7 +62,7 @@ config BCMA_DRIVER_PCI_HOSTMODE
 
 config BCMA_DRIVER_MIPS
 	bool "BCMA Broadcom MIPS core driver"
-	depends on MIPS
+	depends on MIPS || COMPILE_TEST
 	help
 	  Driver for the Broadcom MIPS core attached to Broadcom specific
 	  Advanced Microcontroller Bus.
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index f6518067aa7d..f99e5c883368 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -21,6 +21,7 @@
 #define DAC960_DriverDate			"21 Aug 2007"
 
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
@@ -6426,7 +6427,7 @@ static bool DAC960_V2_ExecuteUserCommand(DAC960_Controller_T *Controller,
   return true;
 }
 
-static int dac960_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_proc_show(struct seq_file *m, void *v)
 {
   unsigned char *StatusMessage = "OK\n";
   int ControllerNumber;
@@ -6446,14 +6447,16 @@ static int dac960_proc_show(struct seq_file *m, void *v)
   return 0;
 }
 
-static int dac960_initial_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_initial_status_proc_show(struct seq_file *m,
+							  void *v)
 {
 	DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private;
 	seq_printf(m, "%.*s", Controller->InitialStatusLength, Controller->CombinedStatusBuffer);
 	return 0;
 }
 
-static int dac960_current_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_current_status_proc_show(struct seq_file *m,
+							  void *v)
 {
   DAC960_Controller_T *Controller = (DAC960_Controller_T *) m->private;
   unsigned char *StatusMessage =
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index ad9b687a236a..d4913516823f 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -74,12 +74,12 @@ config AMIGA_Z2RAM
 
 config CDROM
 	tristate
+	select BLK_SCSI_REQUEST
 
 config GDROM
 	tristate "SEGA Dreamcast GD-ROM drive"
 	depends on SH_DREAMCAST
 	select CDROM
-	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	help
 	  A standard SEGA Dreamcast comes with a modified CD ROM drive called a
 	  "GD-ROM" by SEGA to signify it is capable of reading special disks
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index dc061158b403..8566b188368b 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -36,8 +36,11 @@ obj-$(CONFIG_BLK_DEV_RBD)     += rbd.o
 obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX)	+= mtip32xx/
 
 obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
-obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
 obj-$(CONFIG_ZRAM) += zram/
 
+obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
+null_blk-objs	:= null_blk_main.o
+null_blk-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
+
 skd-y		:= skd_main.o
 swim_mod-y	:= swim.o swim_asm.o
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 096882e54095..136dc507d020 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1137,6 +1137,7 @@ noskb:		if (buf)
 			break;
 		}
 		bvcpy(skb, f->buf->bio, f->iter, n);
+		/* fall through */
 	case ATA_CMD_PIO_WRITE:
 	case ATA_CMD_PIO_WRITE_EXT:
 		spin_lock_irq(&d->lock);
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 697f735b07a4..41060e9cedf2 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -284,8 +284,8 @@ freedev(struct aoedev *d)
 	e = t + d->ntargets;
 	for (; t < e && *t; t++)
 		freetgt(d, *t);
-	if (d->bufpool)
-		mempool_destroy(d->bufpool);
+
+	mempool_destroy(d->bufpool);
 	skbpoolfree(d);
 	minor_free(d->sysminor);
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index bb976598ee43..df8103dd40ac 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -254,20 +254,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  * Process a single bvec of a bio.
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	void *mem;
 	int err = 0;
 
-	if (is_write) {
+	if (op_is_write(op)) {
 		err = copy_to_brd_setup(brd, sector, len);
 		if (err)
 			goto out;
 	}
 
 	mem = kmap_atomic(page);
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		copy_from_brd(mem + off, brd, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -296,7 +296,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		int err;
 
 		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
-					op_is_write(bio_op(bio)), sector);
+				  bio_op(bio), sector);
 		if (err)
 			goto io_error;
 		sector += len >> SECTOR_SHIFT;
@@ -310,15 +310,15 @@ io_error:
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	int err;
 
 	if (PageTransHuge(page))
 		return -ENOTSUPP;
-	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
-	page_endio(page, is_write, err);
+	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+	page_endio(page, op_is_write(op), err);
 	return err;
 }
 
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index bc4ed2ed40a2..e35a234b0a8f 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -55,12 +55,10 @@
 # define __protected_by(x)       __attribute__((require_context(x,1,999,"rdwr")))
 # define __protected_read_by(x)  __attribute__((require_context(x,1,999,"read")))
 # define __protected_write_by(x) __attribute__((require_context(x,1,999,"write")))
-# define __must_hold(x)       __attribute__((context(x,1,1), require_context(x,1,999,"call")))
 #else
 # define __protected_by(x)
 # define __protected_read_by(x)
 # define __protected_write_by(x)
-# define __must_hold(x)
 #endif
 
 /* shared module parameters, defined in drbd_main.c */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index a80809bd3057..ef8212a4b73e 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2103,14 +2103,10 @@ static void drbd_destroy_mempools(void)
 	mempool_exit(&drbd_md_io_page_pool);
 	mempool_exit(&drbd_ee_mempool);
 	mempool_exit(&drbd_request_mempool);
-	if (drbd_ee_cache)
-		kmem_cache_destroy(drbd_ee_cache);
-	if (drbd_request_cache)
-		kmem_cache_destroy(drbd_request_cache);
-	if (drbd_bm_ext_cache)
-		kmem_cache_destroy(drbd_bm_ext_cache);
-	if (drbd_al_ext_cache)
-		kmem_cache_destroy(drbd_al_ext_cache);
+	kmem_cache_destroy(drbd_ee_cache);
+	kmem_cache_destroy(drbd_request_cache);
+	kmem_cache_destroy(drbd_bm_ext_cache);
+	kmem_cache_destroy(drbd_al_ext_cache);
 
 	drbd_ee_cache        = NULL;
 	drbd_request_cache   = NULL;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index be9450f5ad1c..75f6b47169e6 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2674,8 +2674,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 	if (c_min_rate == 0)
 		return false;
 
-	curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
-		      (int)part_stat_read(&disk->part0, sectors[1]) -
+	curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
@@ -2790,6 +2789,7 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 		   then we would do something smarter here than reading
 		   the block... */
 		peer_req->flags |= EE_RS_THIN_REQ;
+		/* fall through */
 	case P_RS_DATA_REQUEST:
 		peer_req->w.cb = w_e_end_rsdata_req;
 		fault_type = DRBD_FAULT_RS_RD;
@@ -2968,6 +2968,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		/* Else fall through to one of the other strategies... */
 		drbd_warn(device, "Discard younger/older primary did not find a decision\n"
 		     "Using discard-least-changes instead\n");
+		/* fall through */
 	case ASB_DISCARD_ZERO_CHG:
 		if (ch_peer == 0 && ch_self == 0) {
 			rv = test_bit(RESOLVE_CONFLICTS, &peer_device->connection->flags)
@@ -2979,6 +2980,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		}
 		if (after_sb_0p == ASB_DISCARD_ZERO_CHG)
 			break;
+		/* else: fall through */
 	case ASB_DISCARD_LEAST_CHG:
 		if	(ch_self < ch_peer)
 			rv = -1;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index d146fedc38bb..19cac36e9737 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -38,7 +38,7 @@ static void _drbd_start_io_acct(struct drbd_device *device, struct drbd_request
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_start_io_acct(q, bio_data_dir(req->master_bio),
+	generic_start_io_acct(q, bio_op(req->master_bio),
 				req->i.size >> 9, &device->vdisk->part0);
 }
 
@@ -47,7 +47,7 @@ static void _drbd_end_io_acct(struct drbd_device *device, struct drbd_request *r
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_end_io_acct(q, bio_data_dir(req->master_bio),
+	generic_end_io_acct(q, bio_op(req->master_bio),
 			    &device->vdisk->part0, req->start_jif);
 }
 
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 5e793dd7adfb..b8f77e83d456 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1690,9 +1690,7 @@ void drbd_rs_controller_reset(struct drbd_device *device)
 	atomic_set(&device->rs_sect_in, 0);
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
-	device->rs_last_events =
-		(int)part_stat_read(&disk->part0, sectors[0]) +
-		(int)part_stat_read(&disk->part0, sectors[1]);
+	device->rs_last_events = (int)part_stat_read_accum(&disk->part0, sectors);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 8871b5044d9e..48f622728ce6 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -1461,7 +1461,6 @@ static void setup_rw_floppy(void)
 	int i;
 	int r;
 	int flags;
-	int dflags;
 	unsigned long ready_date;
 	void (*function)(void);
 
@@ -1485,8 +1484,6 @@ static void setup_rw_floppy(void)
 		if (fd_wait_for_completion(ready_date, function))
 			return;
 	}
-	dflags = DRS->flags;
-
 	if ((flags & FD_RAW_READ) || (flags & FD_RAW_WRITE))
 		setup_DMA();
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 4cb1d1be3cfb..ea9debf59b22 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -690,7 +690,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 			  unsigned int arg)
 {
 	struct file	*file, *old_file;
-	struct inode	*inode;
 	int		error;
 
 	error = -ENXIO;
@@ -711,7 +710,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (error)
 		goto out_putf;
 
-	inode = file->f_mapping->host;
 	old_file = lo->lo_backing_file;
 
 	error = -EINVAL;
@@ -1611,6 +1609,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_GET_STATUS64:
 	case LOOP_SET_STATUS64:
 		arg = (unsigned long) compat_ptr(arg);
+		/* fall through */
 	case LOOP_SET_FD:
 	case LOOP_CHANGE_FD:
 	case LOOP_SET_BLOCK_SIZE:
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index c73626decb46..db253cd5b32a 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2575,8 +2575,7 @@ static int mtip_hw_debugfs_init(struct driver_data *dd)
 
 static void mtip_hw_debugfs_exit(struct driver_data *dd)
 {
-	if (dd->dfs_node)
-		debugfs_remove_recursive(dd->dfs_node);
+	debugfs_remove_recursive(dd->dfs_node);
 }
 
 /*
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
new file mode 100644
index 000000000000..d81781f22dba
--- /dev/null
+++ b/drivers/block/null_blk.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BLK_NULL_BLK_H
+#define __BLK_NULL_BLK_H
+
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/blk-mq.h>
+#include <linux/hrtimer.h>
+#include <linux/configfs.h>
+#include <linux/badblocks.h>
+#include <linux/fault-inject.h>
+
+struct nullb_cmd {
+	struct list_head list;
+	struct llist_node ll_list;
+	struct __call_single_data csd;
+	struct request *rq;
+	struct bio *bio;
+	unsigned int tag;
+	blk_status_t error;
+	struct nullb_queue *nq;
+	struct hrtimer timer;
+};
+
+struct nullb_queue {
+	unsigned long *tag_map;
+	wait_queue_head_t wait;
+	unsigned int queue_depth;
+	struct nullb_device *dev;
+	unsigned int requeue_selection;
+
+	struct nullb_cmd *cmds;
+};
+
+struct nullb_device {
+	struct nullb *nullb;
+	struct config_item item;
+	struct radix_tree_root data; /* data stored in the disk */
+	struct radix_tree_root cache; /* disk cache data */
+	unsigned long flags; /* device flags */
+	unsigned int curr_cache;
+	struct badblocks badblocks;
+
+	unsigned int nr_zones;
+	struct blk_zone *zones;
+	sector_t zone_size_sects;
+
+	unsigned long size; /* device size in MB */
+	unsigned long completion_nsec; /* time in ns to complete a request */
+	unsigned long cache_size; /* disk cache size in MB */
+	unsigned long zone_size; /* zone size in MB if device is zoned */
+	unsigned int submit_queues; /* number of submission queues */
+	unsigned int home_node; /* home node for the device */
+	unsigned int queue_mode; /* block interface */
+	unsigned int blocksize; /* block size */
+	unsigned int irqmode; /* IRQ completion handler */
+	unsigned int hw_queue_depth; /* queue depth */
+	unsigned int index; /* index of the disk, only valid with a disk */
+	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
+	bool blocking; /* blocking blk-mq device */
+	bool use_per_node_hctx; /* use per-node allocation for hardware context */
+	bool power; /* power on/off the device */
+	bool memory_backed; /* if data is stored in memory */
+	bool discard; /* if support discard */
+	bool zoned; /* if device is zoned */
+};
+
+struct nullb {
+	struct nullb_device *dev;
+	struct list_head list;
+	unsigned int index;
+	struct request_queue *q;
+	struct gendisk *disk;
+	struct blk_mq_tag_set *tag_set;
+	struct blk_mq_tag_set __tag_set;
+	unsigned int queue_depth;
+	atomic_long_t cur_bytes;
+	struct hrtimer bw_timer;
+	unsigned long cache_flush_pos;
+	spinlock_t lock;
+
+	struct nullb_queue *queues;
+	unsigned int nr_queues;
+	char disk_name[DISK_NAME_LEN];
+};
+
+#ifdef CONFIG_BLK_DEV_ZONED
+int null_zone_init(struct nullb_device *dev);
+void null_zone_exit(struct nullb_device *dev);
+blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd);
+void null_zone_write(struct nullb_cmd *cmd);
+void null_zone_reset(struct nullb_cmd *cmd);
+#else
+static inline int null_zone_init(struct nullb_device *dev)
+{
+	return -EINVAL;
+}
+static inline void null_zone_exit(struct nullb_device *dev) {}
+static inline blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd)
+{
+	return BLK_STS_NOTSUPP;
+}
+static inline void null_zone_write(struct nullb_cmd *cmd) {}
+static inline void null_zone_reset(struct nullb_cmd *cmd) {}
+#endif /* CONFIG_BLK_DEV_ZONED */
+#endif /* __NULL_BLK_H */
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk_main.c
index 042c778e5a4e..6127e3ff7b4b 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk_main.c
@@ -7,14 +7,8 @@
 #include <linux/moduleparam.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
-#include <linux/blkdev.h>
 #include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/blk-mq.h>
-#include <linux/hrtimer.h>
-#include <linux/configfs.h>
-#include <linux/badblocks.h>
-#include <linux/fault-inject.h>
+#include "null_blk.h"
 
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
@@ -35,28 +29,6 @@ static inline u64 mb_per_tick(int mbps)
 	return (1 << 20) / TICKS_PER_SEC * ((u64) mbps);
 }
 
-struct nullb_cmd {
-	struct list_head list;
-	struct llist_node ll_list;
-	struct __call_single_data csd;
-	struct request *rq;
-	struct bio *bio;
-	unsigned int tag;
-	blk_status_t error;
-	struct nullb_queue *nq;
-	struct hrtimer timer;
-};
-
-struct nullb_queue {
-	unsigned long *tag_map;
-	wait_queue_head_t wait;
-	unsigned int queue_depth;
-	struct nullb_device *dev;
-	unsigned int requeue_selection;
-
-	struct nullb_cmd *cmds;
-};
-
 /*
  * Status flags for nullb_device.
  *
@@ -92,52 +64,6 @@ struct nullb_page {
 #define NULLB_PAGE_LOCK (MAP_SZ - 1)
 #define NULLB_PAGE_FREE (MAP_SZ - 2)
 
-struct nullb_device {
-	struct nullb *nullb;
-	struct config_item item;
-	struct radix_tree_root data; /* data stored in the disk */
-	struct radix_tree_root cache; /* disk cache data */
-	unsigned long flags; /* device flags */
-	unsigned int curr_cache;
-	struct badblocks badblocks;
-
-	unsigned long size; /* device size in MB */
-	unsigned long completion_nsec; /* time in ns to complete a request */
-	unsigned long cache_size; /* disk cache size in MB */
-	unsigned int submit_queues; /* number of submission queues */
-	unsigned int home_node; /* home node for the device */
-	unsigned int queue_mode; /* block interface */
-	unsigned int blocksize; /* block size */
-	unsigned int irqmode; /* IRQ completion handler */
-	unsigned int hw_queue_depth; /* queue depth */
-	unsigned int index; /* index of the disk, only valid with a disk */
-	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
-	bool blocking; /* blocking blk-mq device */
-	bool use_per_node_hctx; /* use per-node allocation for hardware context */
-	bool power; /* power on/off the device */
-	bool memory_backed; /* if data is stored in memory */
-	bool discard; /* if support discard */
-};
-
-struct nullb {
-	struct nullb_device *dev;
-	struct list_head list;
-	unsigned int index;
-	struct request_queue *q;
-	struct gendisk *disk;
-	struct blk_mq_tag_set *tag_set;
-	struct blk_mq_tag_set __tag_set;
-	unsigned int queue_depth;
-	atomic_long_t cur_bytes;
-	struct hrtimer bw_timer;
-	unsigned long cache_flush_pos;
-	spinlock_t lock;
-
-	struct nullb_queue *queues;
-	unsigned int nr_queues;
-	char disk_name[DISK_NAME_LEN];
-};
-
 static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
@@ -254,6 +180,14 @@ static bool g_use_per_node_hctx;
 module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
 MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
 
+static bool g_zoned;
+module_param_named(zoned, g_zoned, bool, S_IRUGO);
+MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false");
+
+static unsigned long g_zone_size = 256;
+module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
+MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -357,6 +291,8 @@ NULLB_DEVICE_ATTR(memory_backed, bool);
 NULLB_DEVICE_ATTR(discard, bool);
 NULLB_DEVICE_ATTR(mbps, uint);
 NULLB_DEVICE_ATTR(cache_size, ulong);
+NULLB_DEVICE_ATTR(zoned, bool);
+NULLB_DEVICE_ATTR(zone_size, ulong);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -390,6 +326,7 @@ static ssize_t nullb_device_power_store(struct config_item *item,
 		null_del_dev(dev->nullb);
 		mutex_unlock(&lock);
 		clear_bit(NULLB_DEV_FL_UP, &dev->flags);
+		clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 	}
 
 	return count;
@@ -468,6 +405,8 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_mbps,
 	&nullb_device_attr_cache_size,
 	&nullb_device_attr_badblocks,
+	&nullb_device_attr_zoned,
+	&nullb_device_attr_zone_size,
 	NULL,
 };
 
@@ -520,7 +459,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks\n");
+	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -579,6 +518,8 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->hw_queue_depth = g_hw_queue_depth;
 	dev->blocking = g_blocking;
 	dev->use_per_node_hctx = g_use_per_node_hctx;
+	dev->zoned = g_zoned;
+	dev->zone_size = g_zone_size;
 	return dev;
 }
 
@@ -587,6 +528,7 @@ static void null_free_dev(struct nullb_device *dev)
 	if (!dev)
 		return;
 
+	null_zone_exit(dev);
 	badblocks_exit(&dev->badblocks);
 	kfree(dev);
 }
@@ -862,7 +804,9 @@ static struct nullb_page *null_lookup_page(struct nullb *nullb,
 }
 
 static struct nullb_page *null_insert_page(struct nullb *nullb,
-	sector_t sector, bool ignore_cache)
+					   sector_t sector, bool ignore_cache)
+	__releases(&nullb->lock)
+	__acquires(&nullb->lock)
 {
 	u64 idx;
 	struct nullb_page *t_page;
@@ -1219,6 +1163,11 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 	struct nullb *nullb = dev->nullb;
 	int err = 0;
 
+	if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) {
+		cmd->error = null_zone_report(nullb, cmd);
+		goto out;
+	}
+
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
 		struct request *rq = cmd->rq;
 
@@ -1283,6 +1232,13 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 		}
 	}
 	cmd->error = errno_to_blk_status(err);
+
+	if (!cmd->error && dev->zoned) {
+		if (req_op(cmd->rq) == REQ_OP_WRITE)
+			null_zone_write(cmd);
+		else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET)
+			null_zone_reset(cmd);
+	}
 out:
 	/* Complete IO by inline, softirq or timer */
 	switch (dev->irqmode) {
@@ -1810,6 +1766,15 @@ static int null_add_dev(struct nullb_device *dev)
 		blk_queue_flush_queueable(nullb->q, true);
 	}
 
+	if (dev->zoned) {
+		rv = null_zone_init(dev);
+		if (rv)
+			goto out_cleanup_blk_queue;
+
+		blk_queue_chunk_sectors(nullb->q, dev->zone_size_sects);
+		nullb->q->limits.zoned = BLK_ZONED_HM;
+	}
+
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q);
@@ -1828,13 +1793,16 @@ static int null_add_dev(struct nullb_device *dev)
 
 	rv = null_gendisk_register(nullb);
 	if (rv)
-		goto out_cleanup_blk_queue;
+		goto out_cleanup_zone;
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
 	mutex_unlock(&lock);
 
 	return 0;
+out_cleanup_zone:
+	if (dev->zoned)
+		null_zone_exit(dev);
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
@@ -1861,6 +1829,11 @@ static int __init null_init(void)
 		g_bs = PAGE_SIZE;
 	}
 
+	if (!is_power_of_2(g_zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
 	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
 		if (g_submit_queues != nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.\n",
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
new file mode 100644
index 000000000000..a979ca00d7be
--- /dev/null
+++ b/drivers/block/null_blk_zoned.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/vmalloc.h>
+#include "null_blk.h"
+
+/* zone_size in MBs to sectors. */
+#define ZONE_SIZE_SHIFT		11
+
+static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
+{
+	return sect >> ilog2(dev->zone_size_sects);
+}
+
+int null_zone_init(struct nullb_device *dev)
+{
+	sector_t dev_size = (sector_t)dev->size * 1024 * 1024;
+	sector_t sector = 0;
+	unsigned int i;
+
+	if (!is_power_of_2(dev->zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
+	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
+	dev->nr_zones = dev_size >>
+				(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
+	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct blk_zone),
+			GFP_KERNEL | __GFP_ZERO);
+	if (!dev->zones)
+		return -ENOMEM;
+
+	for (i = 0; i < dev->nr_zones; i++) {
+		struct blk_zone *zone = &dev->zones[i];
+
+		zone->start = zone->wp = sector;
+		zone->len = dev->zone_size_sects;
+		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
+		zone->cond = BLK_ZONE_COND_EMPTY;
+
+		sector += dev->zone_size_sects;
+	}
+
+	return 0;
+}
+
+void null_zone_exit(struct nullb_device *dev)
+{
+	kvfree(dev->zones);
+}
+
+static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq,
+			      unsigned int zno, unsigned int nr_zones)
+{
+	struct blk_zone_report_hdr *hdr = NULL;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	void *addr;
+	unsigned int zones_to_cpy;
+
+	bio_for_each_segment(bvec, rq->bio, iter) {
+		addr = kmap_atomic(bvec.bv_page);
+
+		zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone);
+
+		if (!hdr) {
+			hdr = (struct blk_zone_report_hdr *)addr;
+			hdr->nr_zones = nr_zones;
+			zones_to_cpy--;
+			addr += sizeof(struct blk_zone_report_hdr);
+		}
+
+		zones_to_cpy = min_t(unsigned int, zones_to_cpy, nr_zones);
+
+		memcpy(addr, &dev->zones[zno],
+				zones_to_cpy * sizeof(struct blk_zone));
+
+		kunmap_atomic(addr);
+
+		nr_zones -= zones_to_cpy;
+		zno += zones_to_cpy;
+
+		if (!nr_zones)
+			break;
+	}
+}
+
+blk_status_t null_zone_report(struct nullb *nullb,
+				     struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = nullb->dev;
+	struct request *rq = cmd->rq;
+	unsigned int zno = null_zone_no(dev, blk_rq_pos(rq));
+	unsigned int nr_zones = dev->nr_zones - zno;
+	unsigned int max_zones = (blk_rq_bytes(rq) /
+					sizeof(struct blk_zone)) - 1;
+
+	nr_zones = min_t(unsigned int, nr_zones, max_zones);
+
+	null_zone_fill_rq(nullb->dev, rq, zno, nr_zones);
+
+	return BLK_STS_OK;
+}
+
+void null_zone_write(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct request *rq = cmd->rq;
+	sector_t sector = blk_rq_pos(rq);
+	unsigned int rq_sectors = blk_rq_sectors(rq);
+	unsigned int zno = null_zone_no(dev, sector);
+	struct blk_zone *zone = &dev->zones[zno];
+
+	switch (zone->cond) {
+	case BLK_ZONE_COND_FULL:
+		/* Cannot write to a full zone */
+		cmd->error = BLK_STS_IOERR;
+		break;
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_IMP_OPEN:
+		/* Writes must be at the write pointer position */
+		if (blk_rq_pos(rq) != zone->wp) {
+			cmd->error = BLK_STS_IOERR;
+			break;
+		}
+
+		if (zone->cond == BLK_ZONE_COND_EMPTY)
+			zone->cond = BLK_ZONE_COND_IMP_OPEN;
+
+		zone->wp += rq_sectors;
+		if (zone->wp == zone->start + zone->len)
+			zone->cond = BLK_ZONE_COND_FULL;
+		break;
+	default:
+		/* Invalid zone condition */
+		cmd->error = BLK_STS_IOERR;
+		break;
+	}
+}
+
+void null_zone_reset(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct request *rq = cmd->rq;
+	unsigned int zno = null_zone_no(dev, blk_rq_pos(rq));
+	struct blk_zone *zone = &dev->zones[zno];
+
+	zone->cond = BLK_ZONE_COND_EMPTY;
+	zone->wp = zone->start;
+}
diff --git a/drivers/block/paride/bpck.c b/drivers/block/paride/bpck.c
index 4f27e7392e38..f5f63ca2889d 100644
--- a/drivers/block/paride/bpck.c
+++ b/drivers/block/paride/bpck.c
@@ -347,7 +347,7 @@ static int bpck_test_proto( PIA *pi, char * scratch, int verbose )
 
 static void bpck_read_eeprom ( PIA *pi, char * buf )
 
-{       int i,j,k,n,p,v,f, om, od;
+{       int i, j, k, p, v, f, om, od;
 
 	bpck_force_spp(pi);
 
@@ -356,7 +356,6 @@ static void bpck_read_eeprom ( PIA *pi, char * buf )
 
 	bpck_connect(pi);
 	
-	n = 0;
 	WR(4,0);
 	for (i=0;i<64;i++) {
 	    WR(6,8);  
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 8961b190e256..7cf947586fe4 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -426,6 +426,7 @@ static void run_fsm(void)
 				pd_claimed = 1;
 				if (!pi_schedule_claimed(pi_current, run_fsm))
 					return;
+				/* fall through */
 			case 1:
 				pd_claimed = 2;
 				pi_current->proto->connect(pi_current);
@@ -445,6 +446,7 @@ static void run_fsm(void)
 				spin_unlock_irqrestore(&pd_lock, saved_flags);
 				if (stop)
 					return;
+				/* fall through */
 			case Hold:
 				schedule_fsm();
 				return;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index b3f83cd96f33..e285413d4a75 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -67,7 +67,7 @@
 #include <scsi/scsi.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
-
+#include <linux/nospec.h>
 #include <linux/uaccess.h>
 
 #define DRIVER_NAME	"pktcdvd"
@@ -748,13 +748,13 @@ static const char *sense_key_string(__u8 index)
 static void pkt_dump_sense(struct pktcdvd_device *pd,
 			   struct packet_command *cgc)
 {
-	struct request_sense *sense = cgc->sense;
+	struct scsi_sense_hdr *sshdr = cgc->sshdr;
 
-	if (sense)
+	if (sshdr)
 		pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
 			CDROM_PACKET_SIZE, cgc->cmd,
-			sense->sense_key, sense->asc, sense->ascq,
-			sense_key_string(sense->sense_key));
+			sshdr->sense_key, sshdr->asc, sshdr->ascq,
+			sense_key_string(sshdr->sense_key));
 	else
 		pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
 }
@@ -787,18 +787,19 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
 				unsigned write_speed, unsigned read_speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int ret;
 
 	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_SET_SPEED;
 	cgc.cmd[2] = (read_speed >> 8) & 0xff;
 	cgc.cmd[3] = read_speed & 0xff;
 	cgc.cmd[4] = (write_speed >> 8) & 0xff;
 	cgc.cmd[5] = write_speed & 0xff;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		pkt_dump_sense(pd, &cgc);
 
 	return ret;
@@ -1562,7 +1563,8 @@ static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
 	cgc.cmd[8] = cgc.buflen = 2;
 	cgc.quiet = 1;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		return ret;
 
 	/* not all drives have the same disc_info length, so requeue
@@ -1591,7 +1593,8 @@ static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type,
 	cgc.cmd[8] = 8;
 	cgc.quiet = 1;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		return ret;
 
 	cgc.buflen = be16_to_cpu(ti->track_information_length) +
@@ -1612,17 +1615,20 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
 	__u32 last_track;
 	int ret = -1;
 
-	if ((ret = pkt_get_disc_info(pd, &di)))
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret)
 		return ret;
 
 	last_track = (di.last_track_msb << 8) | di.last_track_lsb;
-	if ((ret = pkt_get_track_info(pd, last_track, 1, &ti)))
+	ret = pkt_get_track_info(pd, last_track, 1, &ti);
+	if (ret)
 		return ret;
 
 	/* if this track is blank, try the previous. */
 	if (ti.blank) {
 		last_track--;
-		if ((ret = pkt_get_track_info(pd, last_track, 1, &ti)))
+		ret = pkt_get_track_info(pd, last_track, 1, &ti);
+		if (ret)
 			return ret;
 	}
 
@@ -1645,7 +1651,7 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
 static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	write_param_page *wp;
 	char buffer[128];
 	int ret, size;
@@ -1656,8 +1662,9 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 
 	memset(buffer, 0, sizeof(buffer));
 	init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
-	cgc.sense = &sense;
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
+	cgc.sshdr = &sshdr;
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1671,8 +1678,9 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	 * now get it all
 	 */
 	init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
-	cgc.sense = &sense;
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
+	cgc.sshdr = &sshdr;
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1714,7 +1722,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
 
 	cgc.buflen = cgc.cmd[8] = size;
-	if ((ret = pkt_mode_select(pd, &cgc))) {
+	ret = pkt_mode_select(pd, &cgc);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1819,7 +1828,8 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	memset(&di, 0, sizeof(disc_information));
 	memset(&ti, 0, sizeof(track_information));
 
-	if ((ret = pkt_get_disc_info(pd, &di))) {
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret) {
 		pkt_err(pd, "failed get_disc\n");
 		return ret;
 	}
@@ -1830,7 +1840,8 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;
 
 	track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
-	if ((ret = pkt_get_track_info(pd, track, 1, &ti))) {
+	ret = pkt_get_track_info(pd, track, 1, &ti);
+	if (ret) {
 		pkt_err(pd, "failed get_track\n");
 		return ret;
 	}
@@ -1905,12 +1916,12 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 						int set)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[64];
 	int ret;
 
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.buflen = pd->mode_offset + 12;
 
 	/*
@@ -1918,7 +1929,8 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 	 */
 	cgc.quiet = 1;
 
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0)))
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
+	if (ret)
 		return ret;
 
 	buf[pd->mode_offset + 10] |= (!!set << 2);
@@ -1950,14 +1962,14 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
 						unsigned *write_speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[256+18];
 	unsigned char *cap_buf;
 	int ret, offset;
 
 	cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 
 	ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
 	if (ret) {
@@ -2011,13 +2023,13 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 						unsigned *speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[64];
 	unsigned int size, st, sp;
 	int ret;
 
 	init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
 	cgc.cmd[1] = 2;
 	cgc.cmd[2] = 4; /* READ ATIP */
@@ -2032,7 +2044,7 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 		size = sizeof(buf);
 
 	init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
 	cgc.cmd[1] = 2;
 	cgc.cmd[2] = 4;
@@ -2083,17 +2095,18 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int ret;
 
 	pkt_dbg(2, pd, "Performing OPC\n");
 
 	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.timeout = 60*HZ;
 	cgc.cmd[0] = GPCMD_SEND_OPC;
 	cgc.cmd[1] = 1;
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		pkt_dump_sense(pd, &cgc);
 	return ret;
 }
@@ -2103,19 +2116,22 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 	int ret;
 	unsigned int write_speed, media_write_speed, read_speed;
 
-	if ((ret = pkt_probe_settings(pd))) {
+	ret = pkt_probe_settings(pd);
+	if (ret) {
 		pkt_dbg(2, pd, "failed probe\n");
 		return ret;
 	}
 
-	if ((ret = pkt_set_write_settings(pd))) {
+	ret = pkt_set_write_settings(pd);
+	if (ret) {
 		pkt_dbg(1, pd, "failed saving write settings\n");
 		return -EIO;
 	}
 
 	pkt_write_caching(pd, USE_WCACHING);
 
-	if ((ret = pkt_get_max_speed(pd, &write_speed)))
+	ret = pkt_get_max_speed(pd, &write_speed);
+	if (ret)
 		write_speed = 16 * 177;
 	switch (pd->mmc3_profile) {
 		case 0x13: /* DVD-RW */
@@ -2124,7 +2140,8 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 			pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
 			break;
 		default:
-			if ((ret = pkt_media_speed(pd, &media_write_speed)))
+			ret = pkt_media_speed(pd, &media_write_speed);
+			if (ret)
 				media_write_speed = 16;
 			write_speed = min(write_speed, media_write_speed * 177);
 			pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
@@ -2132,14 +2149,16 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 	}
 	read_speed = write_speed;
 
-	if ((ret = pkt_set_speed(pd, write_speed, read_speed))) {
+	ret = pkt_set_speed(pd, write_speed, read_speed);
+	if (ret) {
 		pkt_dbg(1, pd, "couldn't set write speed\n");
 		return -EIO;
 	}
 	pd->write_speed = write_speed;
 	pd->read_speed = read_speed;
 
-	if ((ret = pkt_perform_opc(pd))) {
+	ret = pkt_perform_opc(pd);
+	if (ret) {
 		pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
 	}
 
@@ -2161,10 +2180,12 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 	 * so bdget() can't fail.
 	 */
 	bdget(pd->bdev->bd_dev);
-	if ((ret = blkdev_get(pd->bdev, FMODE_READ | FMODE_EXCL, pd)))
+	ret = blkdev_get(pd->bdev, FMODE_READ | FMODE_EXCL, pd);
+	if (ret)
 		goto out;
 
-	if ((ret = pkt_get_last_written(pd, &lba))) {
+	ret = pkt_get_last_written(pd, &lba);
+	if (ret) {
 		pkt_err(pd, "pkt_get_last_written failed\n");
 		goto out_putdev;
 	}
@@ -2175,7 +2196,8 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 
 	q = bdev_get_queue(pd->bdev);
 	if (write) {
-		if ((ret = pkt_open_write(pd)))
+		ret = pkt_open_write(pd);
+		if (ret)
 			goto out_putdev;
 		/*
 		 * Some CDRW drives can not handle writes larger than one packet,
@@ -2190,7 +2212,8 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 		clear_bit(PACKET_WRITABLE, &pd->flags);
 	}
 
-	if ((ret = pkt_set_segment_merging(pd, q)))
+	ret = pkt_set_segment_merging(pd, q);
+	if (ret)
 		goto out_putdev;
 
 	if (write) {
@@ -2231,6 +2254,8 @@ static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
 {
 	if (dev_minor >= MAX_WRITERS)
 		return NULL;
+
+	dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
 	return pkt_devs[dev_minor];
 }
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index fa0729c1e776..d81c653b9bf6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -61,7 +61,7 @@ static int atomic_inc_return_safe(atomic_t *v)
 {
 	unsigned int counter;
 
-	counter = (unsigned int)__atomic_add_unless(v, 1, 0);
+	counter = (unsigned int)atomic_fetch_add_unless(v, 1, 0);
 	if (counter <= (unsigned int)INT_MAX)
 		return (int)counter;
 
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index dddb3f2490b6..1a92f9e65937 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -112,7 +112,7 @@ static const struct block_device_operations rsxx_fops = {
 
 static void disk_stats_start(struct rsxx_cardinfo *card, struct bio *bio)
 {
-	generic_start_io_acct(card->queue, bio_data_dir(bio), bio_sectors(bio),
+	generic_start_io_acct(card->queue, bio_op(bio), bio_sectors(bio),
 			     &card->gendisk->part0);
 }
 
@@ -120,8 +120,8 @@ static void disk_stats_complete(struct rsxx_cardinfo *card,
 				struct bio *bio,
 				unsigned long start_time)
 {
-	generic_end_io_acct(card->queue, bio_data_dir(bio),
-				&card->gendisk->part0, start_time);
+	generic_end_io_acct(card->queue, bio_op(bio),
+			    &card->gendisk->part0, start_time);
 }
 
 static void bio_dma_done_cb(struct rsxx_cardinfo *card,
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index bc7aea6d7b7c..87b9e7fbf062 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -657,8 +657,8 @@ static bool skd_preop_sg_list(struct skd_device *skdev,
 
 	if (unlikely(skdev->dbg_level > 1)) {
 		dev_dbg(&skdev->pdev->dev,
-			"skreq=%x sksg_list=%p sksg_dma=%llx\n",
-			skreq->id, skreq->sksg_list, skreq->sksg_dma_address);
+			"skreq=%x sksg_list=%p sksg_dma=%pad\n",
+			skreq->id, skreq->sksg_list, &skreq->sksg_dma_address);
 		for (i = 0; i < n_sg; i++) {
 			struct fit_sg_descriptor *sgd = &skreq->sksg_list[i];
 
@@ -1190,8 +1190,8 @@ static void skd_send_fitmsg(struct skd_device *skdev,
 {
 	u64 qcmd;
 
-	dev_dbg(&skdev->pdev->dev, "dma address 0x%llx, busy=%d\n",
-		skmsg->mb_dma_address, skd_in_flight(skdev));
+	dev_dbg(&skdev->pdev->dev, "dma address %pad, busy=%d\n",
+		&skmsg->mb_dma_address, skd_in_flight(skdev));
 	dev_dbg(&skdev->pdev->dev, "msg_buf %p\n", skmsg->msg_buf);
 
 	qcmd = skmsg->mb_dma_address;
@@ -1250,9 +1250,9 @@ static void skd_send_special_fitmsg(struct skd_device *skdev,
 		}
 
 		dev_dbg(&skdev->pdev->dev,
-			"skspcl=%p id=%04x sksg_list=%p sksg_dma=%llx\n",
+			"skspcl=%p id=%04x sksg_list=%p sksg_dma=%pad\n",
 			skspcl, skspcl->req.id, skspcl->req.sksg_list,
-			skspcl->req.sksg_dma_address);
+			&skspcl->req.sksg_dma_address);
 		for (i = 0; i < skspcl->req.n_sg; i++) {
 			struct fit_sg_descriptor *sgd =
 				&skspcl->req.sksg_list[i];
@@ -2685,8 +2685,8 @@ static int skd_cons_skmsg(struct skd_device *skdev)
 
 		WARN(((uintptr_t)skmsg->msg_buf | skmsg->mb_dma_address) &
 		     (FIT_QCMD_ALIGN - 1),
-		     "not aligned: msg_buf %p mb_dma_address %#llx\n",
-		     skmsg->msg_buf, skmsg->mb_dma_address);
+		     "not aligned: msg_buf %p mb_dma_address %pad\n",
+		     skmsg->msg_buf, &skmsg->mb_dma_address);
 		memset(skmsg->msg_buf, 0, SKD_N_FITMSG_BYTES);
 	}
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index b5cedccb5d7d..8986adab9bf5 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -251,14 +251,9 @@ static DEFINE_SPINLOCK(minor_lock);
 #define GRANTS_PER_INDIRECT_FRAME \
 	(XEN_PAGE_SIZE / sizeof(struct blkif_request_segment))
 
-#define PSEGS_PER_INDIRECT_FRAME	\
-	(GRANTS_INDIRECT_FRAME / GRANTS_PSEGS)
-
 #define INDIRECT_GREFS(_grants)		\
 	DIV_ROUND_UP(_grants, GRANTS_PER_INDIRECT_FRAME)
 
-#define GREFS(_psegs)	((_psegs) * GRANTS_PER_PSEG)
-
 static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo);
 static void blkfront_gather_backend_features(struct blkfront_info *info);
 static int negotiate_mq(struct blkfront_info *info);
@@ -1441,7 +1436,7 @@ static bool blkif_completion(unsigned long *id,
 
 		/* Wait the second response if not yet here. */
 		if (s2->status == REQ_WAITING)
-			return 0;
+			return false;
 
 		bret->status = blkif_get_final_status(s->status,
 						      s2->status);
@@ -1542,7 +1537,7 @@ static bool blkif_completion(unsigned long *id,
 		}
 	}
 
-	return 1;
+	return true;
 }
 
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 7436b2d27fa3..c7acf74253a1 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -298,7 +298,8 @@ static void reset_bdev(struct zram *zram)
 	zram->backing_dev = NULL;
 	zram->old_block_size = 0;
 	zram->bdev = NULL;
-
+	zram->disk->queue->backing_dev_info->capabilities |=
+				BDI_CAP_SYNCHRONOUS_IO;
 	kvfree(zram->bitmap);
 	zram->bitmap = NULL;
 }
@@ -400,6 +401,18 @@ static ssize_t backing_dev_store(struct device *dev,
 	zram->backing_dev = backing_dev;
 	zram->bitmap = bitmap;
 	zram->nr_pages = nr_pages;
+	/*
+	 * With writeback feature, zram does asynchronous IO so it's no longer
+	 * synchronous device so let's remove synchronous io flag. Othewise,
+	 * upper layer(e.g., swap) could wait IO completion rather than
+	 * (submit and return), which will cause system sluggish.
+	 * Furthermore, when the IO function returns(e.g., swap_readpage),
+	 * upper layer expects IO was done so it could deallocate the page
+	 * freely but in fact, IO is going on so finally could cause
+	 * use-after-free when the IO is really done.
+	 */
+	zram->disk->queue->backing_dev_info->capabilities &=
+			~BDI_CAP_SYNCHRONOUS_IO;
 	up_write(&zram->init_lock);
 
 	pr_info("setup backing device %s\n", file_name);
@@ -1274,17 +1287,16 @@ static void zram_bio_discard(struct zram *zram, u32 index,
  * Returns 1 if IO request was successfully submitted.
  */
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, bool is_write, struct bio *bio)
+			int offset, unsigned int op, struct bio *bio)
 {
 	unsigned long start_time = jiffies;
-	int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
 	struct request_queue *q = zram->disk->queue;
 	int ret;
 
-	generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT,
+	generic_start_io_acct(q, op, bvec->bv_len >> SECTOR_SHIFT,
 			&zram->disk->part0);
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		atomic64_inc(&zram->stats.num_reads);
 		ret = zram_bvec_read(zram, bvec, index, offset, bio);
 		flush_dcache_page(bvec->bv_page);
@@ -1293,14 +1305,14 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 		ret = zram_bvec_write(zram, bvec, index, offset, bio);
 	}
 
-	generic_end_io_acct(q, rw_acct, &zram->disk->part0, start_time);
+	generic_end_io_acct(q, op, &zram->disk->part0, start_time);
 
 	zram_slot_lock(zram, index);
 	zram_accessed(zram, index);
 	zram_slot_unlock(zram, index);
 
 	if (unlikely(ret < 0)) {
-		if (!is_write)
+		if (!op_is_write(op))
 			atomic64_inc(&zram->stats.failed_reads);
 		else
 			atomic64_inc(&zram->stats.failed_writes);
@@ -1338,7 +1350,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
 							unwritten);
 			if (zram_bvec_rw(zram, &bv, index, offset,
-					op_is_write(bio_op(bio)), bio) < 0)
+					 bio_op(bio), bio) < 0)
 				goto out;
 
 			bv.bv_offset += bv.bv_len;
@@ -1390,7 +1402,7 @@ static void zram_slot_free_notify(struct block_device *bdev,
 }
 
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	int offset, ret;
 	u32 index;
@@ -1414,7 +1426,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_len = PAGE_SIZE;
 	bv.bv_offset = 0;
 
-	ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
+	ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL);
 out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
@@ -1429,7 +1441,7 @@ out:
 
 	switch (ret) {
 	case 0:
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 		break;
 	case 1:
 		ret = 0;
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index a78b8e7085e9..113fc6edb2b0 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -282,6 +282,7 @@
 #include <linux/blkdev.h>
 #include <linux/times.h>
 #include <linux/uaccess.h>
+#include <scsi/scsi_common.h>
 #include <scsi/scsi_request.h>
 
 /* used to tell the module to turn on full debugging messages */
@@ -345,10 +346,10 @@ static LIST_HEAD(cdrom_list);
 int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
 			       struct packet_command *cgc)
 {
-	if (cgc->sense) {
-		cgc->sense->sense_key = 0x05;
-		cgc->sense->asc = 0x20;
-		cgc->sense->ascq = 0x00;
+	if (cgc->sshdr) {
+		cgc->sshdr->sense_key = 0x05;
+		cgc->sshdr->asc = 0x20;
+		cgc->sshdr->ascq = 0x00;
 	}
 
 	cgc->stat = -EIO;
@@ -2222,9 +2223,12 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 
 		blk_execute_rq(q, cdi->disk, rq, 0);
 		if (scsi_req(rq)->result) {
-			struct request_sense *s = req->sense;
+			struct scsi_sense_hdr sshdr;
+
 			ret = -EIO;
-			cdi->last_sense = s->sense_key;
+			scsi_normalize_sense(req->sense, req->sense_len,
+					     &sshdr);
+			cdi->last_sense = sshdr.sense_key;
 		}
 
 		if (blk_rq_unmap_user(bio))
@@ -2943,7 +2947,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 					      struct packet_command *cgc,
 					      int cmd)
 {
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	struct cdrom_msf msf;
 	int blocksize = 0, format = 0, lba;
 	int ret;
@@ -2971,13 +2975,13 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 	if (cgc->buffer == NULL)
 		return -ENOMEM;
 
-	memset(&sense, 0, sizeof(sense));
-	cgc->sense = &sense;
+	memset(&sshdr, 0, sizeof(sshdr));
+	cgc->sshdr = &sshdr;
 	cgc->data_direction = CGC_DATA_READ;
 	ret = cdrom_read_block(cdi, cgc, lba, 1, format, blocksize);
-	if (ret && sense.sense_key == 0x05 &&
-	    sense.asc == 0x20 &&
-	    sense.ascq == 0x00) {
+	if (ret && sshdr.sense_key == 0x05 &&
+	    sshdr.asc == 0x20 &&
+	    sshdr.ascq == 0x00) {
 		/*
 		 * SCSI-II devices are not required to support
 		 * READ_CD, so let's try switching block size
@@ -2986,7 +2990,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 		ret = cdrom_switch_blocksize(cdi, blocksize);
 		if (ret)
 			goto out;
-		cgc->sense = NULL;
+		cgc->sshdr = NULL;
 		ret = cdrom_read_cd(cdi, cgc, lba, blocksize, 1);
 		ret |= cdrom_switch_blocksize(cdi, blocksize);
 	}
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 7513411140b6..9ab3db8b3988 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -35,9 +35,6 @@ static struct clk *__of_clk_get(struct device_node *np, int index,
 	struct clk *clk;
 	int rc;
 
-	if (index < 0)
-		return ERR_PTR(-EINVAL);
-
 	rc = of_parse_phandle_with_args(np, "clocks", "#clock-cells", index,
 					&clkspec);
 	if (rc)
@@ -199,7 +196,7 @@ struct clk *clk_get(struct device *dev, const char *con_id)
 	const char *dev_id = dev ? dev_name(dev) : NULL;
 	struct clk *clk;
 
-	if (dev) {
+	if (dev && dev->of_node) {
 		clk = __of_clk_get_by_name(dev->of_node, dev_id, con_id);
 		if (!IS_ERR(clk) || PTR_ERR(clk) == -EPROBE_DEFER)
 			return clk;
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 00caf37e52f9..c070cc7992e9 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -49,7 +49,7 @@ obj-$(CONFIG_CLKSRC_SAMSUNG_PWM)	+= samsung_pwm_timer.o
 obj-$(CONFIG_FSL_FTM_TIMER)	+= fsl_ftm_timer.o
 obj-$(CONFIG_VF_PIT_TIMER)	+= vf_pit_timer.o
 obj-$(CONFIG_CLKSRC_QCOM)	+= qcom-timer.o
-obj-$(CONFIG_MTK_TIMER)		+= mtk_timer.o
+obj-$(CONFIG_MTK_TIMER)		+= timer-mediatek.o
 obj-$(CONFIG_CLKSRC_PISTACHIO)	+= time-pistachio.o
 obj-$(CONFIG_CLKSRC_TI_32K)	+= timer-ti-32k.o
 obj-$(CONFIG_CLKSRC_NPS)	+= timer-nps.o
diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c
deleted file mode 100644
index f9b724fd9950..000000000000
--- a/drivers/clocksource/mtk_timer.c
+++ /dev/null
@@ -1,268 +0,0 @@
-/*
- * Mediatek SoCs General-Purpose Timer handling.
- *
- * Copyright (C) 2014 Matthias Brugger
- *
- * Matthias Brugger <matthias.bgg@gmail.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.
- *
- * 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.
- */
-
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
-
-#include <linux/clk.h>
-#include <linux/clockchips.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqreturn.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/sched_clock.h>
-#include <linux/slab.h>
-
-#define GPT_IRQ_EN_REG		0x00
-#define GPT_IRQ_ENABLE(val)	BIT((val) - 1)
-#define GPT_IRQ_ACK_REG		0x08
-#define GPT_IRQ_ACK(val)	BIT((val) - 1)
-
-#define TIMER_CTRL_REG(val)	(0x10 * (val))
-#define TIMER_CTRL_OP(val)	(((val) & 0x3) << 4)
-#define TIMER_CTRL_OP_ONESHOT	(0)
-#define TIMER_CTRL_OP_REPEAT	(1)
-#define TIMER_CTRL_OP_FREERUN	(3)
-#define TIMER_CTRL_CLEAR	(2)
-#define TIMER_CTRL_ENABLE	(1)
-#define TIMER_CTRL_DISABLE	(0)
-
-#define TIMER_CLK_REG(val)	(0x04 + (0x10 * (val)))
-#define TIMER_CLK_SRC(val)	(((val) & 0x1) << 4)
-#define TIMER_CLK_SRC_SYS13M	(0)
-#define TIMER_CLK_SRC_RTC32K	(1)
-#define TIMER_CLK_DIV1		(0x0)
-#define TIMER_CLK_DIV2		(0x1)
-
-#define TIMER_CNT_REG(val)	(0x08 + (0x10 * (val)))
-#define TIMER_CMP_REG(val)	(0x0C + (0x10 * (val)))
-
-#define GPT_CLK_EVT	1
-#define GPT_CLK_SRC	2
-
-struct mtk_clock_event_device {
-	void __iomem *gpt_base;
-	u32 ticks_per_jiffy;
-	struct clock_event_device dev;
-};
-
-static void __iomem *gpt_sched_reg __read_mostly;
-
-static u64 notrace mtk_read_sched_clock(void)
-{
-	return readl_relaxed(gpt_sched_reg);
-}
-
-static inline struct mtk_clock_event_device *to_mtk_clk(
-				struct clock_event_device *c)
-{
-	return container_of(c, struct mtk_clock_event_device, dev);
-}
-
-static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer)
-{
-	u32 val;
-
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-	writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base +
-			TIMER_CTRL_REG(timer));
-}
-
-static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt,
-				unsigned long delay, u8 timer)
-{
-	writel(delay, evt->gpt_base + TIMER_CMP_REG(timer));
-}
-
-static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt,
-		bool periodic, u8 timer)
-{
-	u32 val;
-
-	/* Acknowledge interrupt */
-	writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG);
-
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-
-	/* Clear 2 bit timer operation mode field */
-	val &= ~TIMER_CTRL_OP(0x3);
-
-	if (periodic)
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT);
-	else
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT);
-
-	writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR,
-	       evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static int mtk_clkevt_shutdown(struct clock_event_device *clk)
-{
-	mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT);
-	return 0;
-}
-
-static int mtk_clkevt_set_periodic(struct clock_event_device *clk)
-{
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, true, GPT_CLK_EVT);
-	return 0;
-}
-
-static int mtk_clkevt_next_event(unsigned long event,
-				   struct clock_event_device *clk)
-{
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, false, GPT_CLK_EVT);
-
-	return 0;
-}
-
-static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id)
-{
-	struct mtk_clock_event_device *evt = dev_id;
-
-	/* Acknowledge timer0 irq */
-	writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG);
-	evt->dev.event_handler(&evt->dev);
-
-	return IRQ_HANDLED;
-}
-
-static void
-__init mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option)
-{
-	writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE,
-		evt->gpt_base + TIMER_CTRL_REG(timer));
-
-	writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1,
-			evt->gpt_base + TIMER_CLK_REG(timer));
-
-	writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer));
-
-	writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE,
-			evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
-{
-	u32 val;
-
-	/* Disable all interrupts */
-	writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG);
-
-	/* Acknowledge all spurious pending interrupts */
-	writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG);
-
-	val = readl(evt->gpt_base + GPT_IRQ_EN_REG);
-	writel(val | GPT_IRQ_ENABLE(timer),
-			evt->gpt_base + GPT_IRQ_EN_REG);
-}
-
-static int __init mtk_timer_init(struct device_node *node)
-{
-	struct mtk_clock_event_device *evt;
-	struct resource res;
-	unsigned long rate = 0;
-	struct clk *clk;
-
-	evt = kzalloc(sizeof(*evt), GFP_KERNEL);
-	if (!evt)
-		return -ENOMEM;
-
-	evt->dev.name = "mtk_tick";
-	evt->dev.rating = 300;
-	evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	evt->dev.set_state_shutdown = mtk_clkevt_shutdown;
-	evt->dev.set_state_periodic = mtk_clkevt_set_periodic;
-	evt->dev.set_state_oneshot = mtk_clkevt_shutdown;
-	evt->dev.tick_resume = mtk_clkevt_shutdown;
-	evt->dev.set_next_event = mtk_clkevt_next_event;
-	evt->dev.cpumask = cpu_possible_mask;
-
-	evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer");
-	if (IS_ERR(evt->gpt_base)) {
-		pr_err("Can't get resource\n");
-		goto err_kzalloc;
-	}
-
-	evt->dev.irq = irq_of_parse_and_map(node, 0);
-	if (evt->dev.irq <= 0) {
-		pr_err("Can't parse IRQ\n");
-		goto err_mem;
-	}
-
-	clk = of_clk_get(node, 0);
-	if (IS_ERR(clk)) {
-		pr_err("Can't get timer clock\n");
-		goto err_irq;
-	}
-
-	if (clk_prepare_enable(clk)) {
-		pr_err("Can't prepare clock\n");
-		goto err_clk_put;
-	}
-	rate = clk_get_rate(clk);
-
-	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
-			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
-		pr_err("failed to setup irq %d\n", evt->dev.irq);
-		goto err_clk_disable;
-	}
-
-	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
-
-	/* Configure clock source */
-	mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
-	clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
-			node->name, rate, 300, 32, clocksource_mmio_readl_up);
-	gpt_sched_reg = evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC);
-	sched_clock_register(mtk_read_sched_clock, 32, rate);
-
-	/* Configure clock event */
-	mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
-	clockevents_config_and_register(&evt->dev, rate, 0x3,
-					0xffffffff);
-
-	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
-
-	return 0;
-
-err_clk_disable:
-	clk_disable_unprepare(clk);
-err_clk_put:
-	clk_put(clk);
-err_irq:
-	irq_dispose_mapping(evt->dev.irq);
-err_mem:
-	iounmap(evt->gpt_base);
-	of_address_to_resource(node, 0, &res);
-	release_mem_region(res.start, resource_size(&res));
-err_kzalloc:
-	kfree(evt);
-
-	return -EINVAL;
-}
-TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init);
diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index c337a8100a7b..aa624885e0e2 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -230,7 +230,7 @@ static int __init tegra20_init_timer(struct device_node *np)
 		return ret;
 	}
 
-	tegra_clockevent.cpumask = cpu_all_mask;
+	tegra_clockevent.cpumask = cpu_possible_mask;
 	tegra_clockevent.irq = tegra_timer_irq.irq;
 	clockevents_config_and_register(&tegra_clockevent, 1000000,
 					0x1, 0x1fffffff);
@@ -259,6 +259,6 @@ static int __init tegra20_init_rtc(struct device_node *np)
 	else
 		clk_prepare_enable(clk);
 
-	return register_persistent_clock(NULL, tegra_read_persistent_clock64);
+	return register_persistent_clock(tegra_read_persistent_clock64);
 }
 TIMER_OF_DECLARE(tegra20_rtc, "nvidia,tegra20-rtc", tegra20_init_rtc);
diff --git a/drivers/clocksource/timer-atcpit100.c b/drivers/clocksource/timer-atcpit100.c
index 5e23d7b4a722..b4bd2f5b801d 100644
--- a/drivers/clocksource/timer-atcpit100.c
+++ b/drivers/clocksource/timer-atcpit100.c
@@ -185,7 +185,7 @@ static struct timer_of to = {
 		.set_state_oneshot = atcpit100_clkevt_set_oneshot,
 		.tick_resume = atcpit100_clkevt_shutdown,
 		.set_next_event = atcpit100_clkevt_next_event,
-		.cpumask = cpu_all_mask,
+		.cpumask = cpu_possible_mask,
 	},
 
 	.of_irq = {
diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c
index 0eee03250cfc..f5b2eda30bf3 100644
--- a/drivers/clocksource/timer-keystone.c
+++ b/drivers/clocksource/timer-keystone.c
@@ -211,7 +211,7 @@ static int __init keystone_timer_init(struct device_node *np)
 	event_dev->set_state_shutdown = keystone_shutdown;
 	event_dev->set_state_periodic = keystone_set_periodic;
 	event_dev->set_state_oneshot = keystone_shutdown;
-	event_dev->cpumask = cpu_all_mask;
+	event_dev->cpumask = cpu_possible_mask;
 	event_dev->owner = THIS_MODULE;
 	event_dev->name = TIMER_NAME;
 	event_dev->irq = irq;
diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
new file mode 100644
index 000000000000..eb10321f8517
--- /dev/null
+++ b/drivers/clocksource/timer-mediatek.c
@@ -0,0 +1,328 @@
+/*
+ * Mediatek SoCs General-Purpose Timer handling.
+ *
+ * Copyright (C) 2014 Matthias Brugger
+ *
+ * Matthias Brugger <matthias.bgg@gmail.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.
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/irqreturn.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+#include "timer-of.h"
+
+#define TIMER_CLK_EVT           (1)
+#define TIMER_CLK_SRC           (2)
+
+#define TIMER_SYNC_TICKS        (3)
+
+/* gpt */
+#define GPT_IRQ_EN_REG          0x00
+#define GPT_IRQ_ENABLE(val)     BIT((val) - 1)
+#define GPT_IRQ_ACK_REG	        0x08
+#define GPT_IRQ_ACK(val)        BIT((val) - 1)
+
+#define GPT_CTRL_REG(val)       (0x10 * (val))
+#define GPT_CTRL_OP(val)        (((val) & 0x3) << 4)
+#define GPT_CTRL_OP_ONESHOT     (0)
+#define GPT_CTRL_OP_REPEAT      (1)
+#define GPT_CTRL_OP_FREERUN     (3)
+#define GPT_CTRL_CLEAR          (2)
+#define GPT_CTRL_ENABLE         (1)
+#define GPT_CTRL_DISABLE        (0)
+
+#define GPT_CLK_REG(val)        (0x04 + (0x10 * (val)))
+#define GPT_CLK_SRC(val)        (((val) & 0x1) << 4)
+#define GPT_CLK_SRC_SYS13M      (0)
+#define GPT_CLK_SRC_RTC32K      (1)
+#define GPT_CLK_DIV1            (0x0)
+#define GPT_CLK_DIV2            (0x1)
+
+#define GPT_CNT_REG(val)        (0x08 + (0x10 * (val)))
+#define GPT_CMP_REG(val)        (0x0C + (0x10 * (val)))
+
+/* system timer */
+#define SYST_BASE               (0x40)
+
+#define SYST_CON                (SYST_BASE + 0x0)
+#define SYST_VAL                (SYST_BASE + 0x4)
+
+#define SYST_CON_REG(to)        (timer_of_base(to) + SYST_CON)
+#define SYST_VAL_REG(to)        (timer_of_base(to) + SYST_VAL)
+
+/*
+ * SYST_CON_EN: Clock enable. Shall be set to
+ *   - Start timer countdown.
+ *   - Allow timeout ticks being updated.
+ *   - Allow changing interrupt functions.
+ *
+ * SYST_CON_IRQ_EN: Set to allow interrupt.
+ *
+ * SYST_CON_IRQ_CLR: Set to clear interrupt.
+ */
+#define SYST_CON_EN              BIT(0)
+#define SYST_CON_IRQ_EN          BIT(1)
+#define SYST_CON_IRQ_CLR         BIT(4)
+
+static void __iomem *gpt_sched_reg __read_mostly;
+
+static void mtk_syst_ack_irq(struct timer_of *to)
+{
+	/* Clear and disable interrupt */
+	writel(SYST_CON_IRQ_CLR | SYST_CON_EN, SYST_CON_REG(to));
+}
+
+static irqreturn_t mtk_syst_handler(int irq, void *dev_id)
+{
+	struct clock_event_device *clkevt = dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
+
+	mtk_syst_ack_irq(to);
+	clkevt->event_handler(clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static int mtk_syst_clkevt_next_event(unsigned long ticks,
+				      struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	/* Enable clock to allow timeout tick update later */
+	writel(SYST_CON_EN, SYST_CON_REG(to));
+
+	/*
+	 * Write new timeout ticks. Timer shall start countdown
+	 * after timeout ticks are updated.
+	 */
+	writel(ticks, SYST_VAL_REG(to));
+
+	/* Enable interrupt */
+	writel(SYST_CON_EN | SYST_CON_IRQ_EN, SYST_CON_REG(to));
+
+	return 0;
+}
+
+static int mtk_syst_clkevt_shutdown(struct clock_event_device *clkevt)
+{
+	/* Disable timer */
+	writel(0, SYST_CON_REG(to_timer_of(clkevt)));
+
+	return 0;
+}
+
+static int mtk_syst_clkevt_resume(struct clock_event_device *clkevt)
+{
+	return mtk_syst_clkevt_shutdown(clkevt);
+}
+
+static int mtk_syst_clkevt_oneshot(struct clock_event_device *clkevt)
+{
+	return 0;
+}
+
+static u64 notrace mtk_gpt_read_sched_clock(void)
+{
+	return readl_relaxed(gpt_sched_reg);
+}
+
+static void mtk_gpt_clkevt_time_stop(struct timer_of *to, u8 timer)
+{
+	u32 val;
+
+	val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
+	writel(val & ~GPT_CTRL_ENABLE, timer_of_base(to) +
+	       GPT_CTRL_REG(timer));
+}
+
+static void mtk_gpt_clkevt_time_setup(struct timer_of *to,
+				      unsigned long delay, u8 timer)
+{
+	writel(delay, timer_of_base(to) + GPT_CMP_REG(timer));
+}
+
+static void mtk_gpt_clkevt_time_start(struct timer_of *to,
+				      bool periodic, u8 timer)
+{
+	u32 val;
+
+	/* Acknowledge interrupt */
+	writel(GPT_IRQ_ACK(timer), timer_of_base(to) + GPT_IRQ_ACK_REG);
+
+	val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
+
+	/* Clear 2 bit timer operation mode field */
+	val &= ~GPT_CTRL_OP(0x3);
+
+	if (periodic)
+		val |= GPT_CTRL_OP(GPT_CTRL_OP_REPEAT);
+	else
+		val |= GPT_CTRL_OP(GPT_CTRL_OP_ONESHOT);
+
+	writel(val | GPT_CTRL_ENABLE | GPT_CTRL_CLEAR,
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
+}
+
+static int mtk_gpt_clkevt_shutdown(struct clock_event_device *clk)
+{
+	mtk_gpt_clkevt_time_stop(to_timer_of(clk), TIMER_CLK_EVT);
+
+	return 0;
+}
+
+static int mtk_gpt_clkevt_set_periodic(struct clock_event_device *clk)
+{
+	struct timer_of *to = to_timer_of(clk);
+
+	mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(to, to->of_clk.period, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(to, true, TIMER_CLK_EVT);
+
+	return 0;
+}
+
+static int mtk_gpt_clkevt_next_event(unsigned long event,
+				     struct clock_event_device *clk)
+{
+	struct timer_of *to = to_timer_of(clk);
+
+	mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(to, event, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(to, false, TIMER_CLK_EVT);
+
+	return 0;
+}
+
+static irqreturn_t mtk_gpt_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *clkevt = (struct clock_event_device *)dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
+
+	/* Acknowledge timer0 irq */
+	writel(GPT_IRQ_ACK(TIMER_CLK_EVT), timer_of_base(to) + GPT_IRQ_ACK_REG);
+	clkevt->event_handler(clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static void
+__init mtk_gpt_setup(struct timer_of *to, u8 timer, u8 option)
+{
+	writel(GPT_CTRL_CLEAR | GPT_CTRL_DISABLE,
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
+
+	writel(GPT_CLK_SRC(GPT_CLK_SRC_SYS13M) | GPT_CLK_DIV1,
+	       timer_of_base(to) + GPT_CLK_REG(timer));
+
+	writel(0x0, timer_of_base(to) + GPT_CMP_REG(timer));
+
+	writel(GPT_CTRL_OP(option) | GPT_CTRL_ENABLE,
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
+}
+
+static void mtk_gpt_enable_irq(struct timer_of *to, u8 timer)
+{
+	u32 val;
+
+	/* Disable all interrupts */
+	writel(0x0, timer_of_base(to) + GPT_IRQ_EN_REG);
+
+	/* Acknowledge all spurious pending interrupts */
+	writel(0x3f, timer_of_base(to) + GPT_IRQ_ACK_REG);
+
+	val = readl(timer_of_base(to) + GPT_IRQ_EN_REG);
+	writel(val | GPT_IRQ_ENABLE(timer),
+	       timer_of_base(to) + GPT_IRQ_EN_REG);
+}
+
+static struct timer_of to = {
+	.flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+	.clkevt = {
+		.name = "mtk-clkevt",
+		.rating = 300,
+		.cpumask = cpu_possible_mask,
+	},
+
+	.of_irq = {
+		.flags = IRQF_TIMER | IRQF_IRQPOLL,
+	},
+};
+
+static int __init mtk_syst_init(struct device_node *node)
+{
+	int ret;
+
+	to.clkevt.features = CLOCK_EVT_FEAT_DYNIRQ | CLOCK_EVT_FEAT_ONESHOT;
+	to.clkevt.set_state_shutdown = mtk_syst_clkevt_shutdown;
+	to.clkevt.set_state_oneshot = mtk_syst_clkevt_oneshot;
+	to.clkevt.tick_resume = mtk_syst_clkevt_resume;
+	to.clkevt.set_next_event = mtk_syst_clkevt_next_event;
+	to.of_irq.handler = mtk_syst_handler;
+
+	ret = timer_of_init(node, &to);
+	if (ret)
+		goto err;
+
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					TIMER_SYNC_TICKS, 0xffffffff);
+
+	return 0;
+err:
+	timer_of_cleanup(&to);
+	return ret;
+}
+
+static int __init mtk_gpt_init(struct device_node *node)
+{
+	int ret;
+
+	to.clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	to.clkevt.set_state_shutdown = mtk_gpt_clkevt_shutdown;
+	to.clkevt.set_state_periodic = mtk_gpt_clkevt_set_periodic;
+	to.clkevt.set_state_oneshot = mtk_gpt_clkevt_shutdown;
+	to.clkevt.tick_resume = mtk_gpt_clkevt_shutdown;
+	to.clkevt.set_next_event = mtk_gpt_clkevt_next_event;
+	to.of_irq.handler = mtk_gpt_interrupt;
+
+	ret = timer_of_init(node, &to);
+	if (ret)
+		goto err;
+
+	/* Configure clock source */
+	mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
+	clocksource_mmio_init(timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC),
+			      node->name, timer_of_rate(&to), 300, 32,
+			      clocksource_mmio_readl_up);
+	gpt_sched_reg = timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC);
+	sched_clock_register(mtk_gpt_read_sched_clock, 32, timer_of_rate(&to));
+
+	/* Configure clock event */
+	mtk_gpt_setup(&to, TIMER_CLK_EVT, GPT_CTRL_OP_REPEAT);
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					TIMER_SYNC_TICKS, 0xffffffff);
+
+	mtk_gpt_enable_irq(&to, TIMER_CLK_EVT);
+
+	return 0;
+err:
+	timer_of_cleanup(&to);
+	return ret;
+}
+TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
+TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init);
diff --git a/drivers/clocksource/timer-sprd.c b/drivers/clocksource/timer-sprd.c
index ef9ebeafb3ed..430cb99d8d79 100644
--- a/drivers/clocksource/timer-sprd.c
+++ b/drivers/clocksource/timer-sprd.c
@@ -156,4 +156,54 @@ static int __init sprd_timer_init(struct device_node *np)
 	return 0;
 }
 
+static struct timer_of suspend_to = {
+	.flags = TIMER_OF_BASE | TIMER_OF_CLOCK,
+};
+
+static u64 sprd_suspend_timer_read(struct clocksource *cs)
+{
+	return ~(u64)readl_relaxed(timer_of_base(&suspend_to) +
+				   TIMER_VALUE_SHDW_LO) & cs->mask;
+}
+
+static int sprd_suspend_timer_enable(struct clocksource *cs)
+{
+	sprd_timer_update_counter(timer_of_base(&suspend_to),
+				  TIMER_VALUE_LO_MASK);
+	sprd_timer_enable(timer_of_base(&suspend_to), TIMER_CTL_PERIOD_MODE);
+
+	return 0;
+}
+
+static void sprd_suspend_timer_disable(struct clocksource *cs)
+{
+	sprd_timer_disable(timer_of_base(&suspend_to));
+}
+
+static struct clocksource suspend_clocksource = {
+	.name	= "sprd_suspend_timer",
+	.rating	= 200,
+	.read	= sprd_suspend_timer_read,
+	.enable = sprd_suspend_timer_enable,
+	.disable = sprd_suspend_timer_disable,
+	.mask	= CLOCKSOURCE_MASK(32),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_SUSPEND_NONSTOP,
+};
+
+static int __init sprd_suspend_timer_init(struct device_node *np)
+{
+	int ret;
+
+	ret = timer_of_init(np, &suspend_to);
+	if (ret)
+		return ret;
+
+	clocksource_register_hz(&suspend_clocksource,
+				timer_of_rate(&suspend_to));
+
+	return 0;
+}
+
 TIMER_OF_DECLARE(sc9860_timer, "sprd,sc9860-timer", sprd_timer_init);
+TIMER_OF_DECLARE(sc9860_persistent_timer, "sprd,sc9860-suspend-timer",
+		 sprd_suspend_timer_init);
diff --git a/drivers/clocksource/timer-ti-32k.c b/drivers/clocksource/timer-ti-32k.c
index 880a861ab3c8..29e2e1a78a43 100644
--- a/drivers/clocksource/timer-ti-32k.c
+++ b/drivers/clocksource/timer-ti-32k.c
@@ -78,8 +78,7 @@ static struct ti_32k ti_32k_timer = {
 		.rating		= 250,
 		.read		= ti_32k_read_cycles,
 		.mask		= CLOCKSOURCE_MASK(32),
-		.flags		= CLOCK_SOURCE_IS_CONTINUOUS |
-				CLOCK_SOURCE_SUSPEND_NONSTOP,
+		.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 	},
 };
 
diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c
index a6a0338eea77..f74689334f7c 100644
--- a/drivers/clocksource/zevio-timer.c
+++ b/drivers/clocksource/zevio-timer.c
@@ -162,7 +162,7 @@ static int __init zevio_timer_add(struct device_node *node)
 		timer->clkevt.set_state_oneshot = zevio_timer_set_oneshot;
 		timer->clkevt.tick_resume	= zevio_timer_set_oneshot;
 		timer->clkevt.rating		= 200;
-		timer->clkevt.cpumask		= cpu_all_mask;
+		timer->clkevt.cpumask		= cpu_possible_mask;
 		timer->clkevt.features		= CLOCK_EVT_FEAT_ONESHOT;
 		timer->clkevt.irq		= irqnr;
 
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 781a4a337557..d8e159feb573 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -87,6 +87,18 @@ config EFI_RUNTIME_WRAPPERS
 config EFI_ARMSTUB
 	bool
 
+config EFI_ARMSTUB_DTB_LOADER
+	bool "Enable the DTB loader"
+	depends on EFI_ARMSTUB
+	help
+	  Select this config option to add support for the dtb= command
+	  line parameter, allowing a device tree blob to be loaded into
+	  memory from the EFI System Partition by the stub.
+
+	  The device tree is typically provided by the platform or by
+	  the bootloader, so this option is mostly for development
+	  purposes only.
+
 config EFI_BOOTLOADER_CONTROL
 	tristate "EFI Bootloader Control"
 	depends on EFI_VARS
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 3bf0dca378a6..a7902fccdcfa 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -48,8 +48,21 @@ u64 cper_next_record_id(void)
 {
 	static atomic64_t seq;
 
-	if (!atomic64_read(&seq))
-		atomic64_set(&seq, ((u64)get_seconds()) << 32);
+	if (!atomic64_read(&seq)) {
+		time64_t time = ktime_get_real_seconds();
+
+		/*
+		 * This code is unlikely to still be needed in year 2106,
+		 * but just in case, let's use a few more bits for timestamps
+		 * after y2038 to be sure they keep increasing monotonically
+		 * for the next few hundred years...
+		 */
+		if (time < 0x80000000)
+			atomic64_set(&seq, (ktime_get_real_seconds()) << 32);
+		else
+			atomic64_set(&seq, 0x8000000000000000ull |
+					   ktime_get_real_seconds() << 24);
+	}
 
 	return atomic64_inc_return(&seq);
 }
@@ -459,7 +472,7 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		else
 			goto err_section_too_small;
 #if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
-	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_ARM)) {
+	} else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 		struct cper_sec_proc_arm *arm_err = acpi_hest_get_payload(gdata);
 
 		printk("%ssection_type: ARM processor error\n", newpfx);
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 232f4915223b..2a29dd9c986d 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -82,8 +82,11 @@ struct mm_struct efi_mm = {
 	.mmap_sem		= __RWSEM_INITIALIZER(efi_mm.mmap_sem),
 	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
+	.cpu_bitmap		= { [BITS_TO_LONGS(NR_CPUS)] = 0},
 };
 
+struct workqueue_struct *efi_rts_wq;
+
 static bool disable_runtime;
 static int __init setup_noefi(char *arg)
 {
@@ -337,6 +340,18 @@ static int __init efisubsys_init(void)
 	if (!efi_enabled(EFI_BOOT))
 		return 0;
 
+	/*
+	 * Since we process only one efi_runtime_service() at a time, an
+	 * ordered workqueue (which creates only one execution context)
+	 * should suffice all our needs.
+	 */
+	efi_rts_wq = alloc_ordered_workqueue("efi_rts_wq", 0);
+	if (!efi_rts_wq) {
+		pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return 0;
+	}
+
 	/* We register the efi directory at /sys/firmware/efi */
 	efi_kobj = kobject_create_and_add("efi", firmware_kobj);
 	if (!efi_kobj) {
@@ -388,7 +403,7 @@ subsys_initcall(efisubsys_init);
  * and if so, populate the supplied memory descriptor with the appropriate
  * data.
  */
-int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
+int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 {
 	efi_memory_desc_t *md;
 
@@ -406,12 +421,6 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 		u64 size;
 		u64 end;
 
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_DATA &&
-		    md->type != EFI_RUNTIME_SERVICES_DATA) {
-			continue;
-		}
-
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
 		if (phys_addr >= md->phys_addr && phys_addr < end) {
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 1ab80e06e7c5..5d06bd247d07 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -250,7 +250,10 @@ void __init efi_esrt_init(void)
 		return;
 
 	rc = efi_mem_desc_lookup(efi.esrt, &md);
-	if (rc < 0) {
+	if (rc < 0 ||
+	    (!(md.attribute & EFI_MEMORY_RUNTIME) &&
+	     md.type != EFI_BOOT_SERVICES_DATA &&
+	     md.type != EFI_RUNTIME_SERVICES_DATA)) {
 		pr_warn("ESRT header is not in the memory map.\n");
 		return;
 	}
@@ -326,7 +329,8 @@ void __init efi_esrt_init(void)
 
 	end = esrt_data + size;
 	pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end);
-	efi_mem_reserve(esrt_data, esrt_data_size);
+	if (md.type == EFI_BOOT_SERVICES_DATA)
+		efi_mem_reserve(esrt_data, esrt_data_size);
 
 	pr_debug("esrt-init: loaded.\n");
 }
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 01a9d78ee415..6920033de6d4 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -40,31 +40,6 @@
 
 static u64 virtmap_base = EFI_RT_VIRTUAL_BASE;
 
-efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
-			     void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_t *image = __image;
-	efi_file_handle_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-
-	status = sys_table_arg->boottime->handle_protocol(handle,
-				 &fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	status = io->open_volume(io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table_arg, "Failed to open volume\n");
-
-	*__fh = fh;
-	return status;
-}
-
 void efi_char16_printk(efi_system_table_t *sys_table_arg,
 			      efi_char16_t *str)
 {
@@ -202,9 +177,10 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 	 * 'dtb=' unless UEFI Secure Boot is disabled.  We assume that secure
 	 * boot is enabled if we can't determine its state.
 	 */
-	if (secure_boot != efi_secureboot_mode_disabled &&
-	    strstr(cmdline_ptr, "dtb=")) {
-		pr_efi(sys_table, "Ignoring DTB from command line.\n");
+	if (!IS_ENABLED(CONFIG_EFI_ARMSTUB_DTB_LOADER) ||
+	     secure_boot != efi_secureboot_mode_disabled) {
+		if (strstr(cmdline_ptr, "dtb="))
+			pr_efi(sys_table, "Ignoring DTB from command line.\n");
 	} else {
 		status = handle_cmdline_files(sys_table, image, cmdline_ptr,
 					      "dtb=",
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 50a9cab5a834..e94975f4655b 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -413,6 +413,34 @@ static efi_status_t efi_file_close(void *handle)
 	return efi_call_proto(efi_file_handle, close, handle);
 }
 
+static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
+				    efi_loaded_image_t *image,
+				    efi_file_handle_t **__fh)
+{
+	efi_file_io_interface_t *io;
+	efi_file_handle_t *fh;
+	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+	efi_status_t status;
+	void *handle = (void *)(unsigned long)efi_table_attr(efi_loaded_image,
+							     device_handle,
+							     image);
+
+	status = efi_call_early(handle_protocol, handle,
+				&fs_proto, (void **)&io);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
+		return status;
+	}
+
+	status = efi_call_proto(efi_file_io_interface, open_volume, io, &fh);
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table_arg, "Failed to open volume\n");
+	else
+		*__fh = fh;
+
+	return status;
+}
+
 /*
  * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi=
  * option, e.g. efi=nochunk.
@@ -563,8 +591,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
 
 		/* Only open the volume once. */
 		if (!i) {
-			status = efi_open_volume(sys_table_arg, image,
-						 (void **)&fh);
+			status = efi_open_volume(sys_table_arg, image, &fh);
 			if (status != EFI_SUCCESS)
 				goto free_files;
 		}
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index f59564b72ddc..32799cf039ef 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -36,9 +36,6 @@ extern int __pure is_quiet(void);
 
 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);
-
 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/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index ae54870b2788..aa66cbf23512 100644
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -1,6 +1,15 @@
 /*
  * runtime-wrappers.c - Runtime Services function call wrappers
  *
+ * Implementation summary:
+ * -----------------------
+ * 1. When user/kernel thread requests to execute efi_runtime_service(),
+ * enqueue work to efi_rts_wq.
+ * 2. Caller thread waits for completion until the work is finished
+ * because it's dependent on the return status and execution of
+ * efi_runtime_service().
+ * For instance, get_variable() and get_next_variable().
+ *
  * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  * Split off from arch/x86/platform/efi/efi.c
@@ -22,6 +31,9 @@
 #include <linux/mutex.h>
 #include <linux/semaphore.h>
 #include <linux/stringify.h>
+#include <linux/workqueue.h>
+#include <linux/completion.h>
+
 #include <asm/efi.h>
 
 /*
@@ -33,6 +45,76 @@
 #define __efi_call_virt(f, args...) \
 	__efi_call_virt_pointer(efi.systab->runtime, f, args)
 
+/* efi_runtime_service() function identifiers */
+enum efi_rts_ids {
+	GET_TIME,
+	SET_TIME,
+	GET_WAKEUP_TIME,
+	SET_WAKEUP_TIME,
+	GET_VARIABLE,
+	GET_NEXT_VARIABLE,
+	SET_VARIABLE,
+	QUERY_VARIABLE_INFO,
+	GET_NEXT_HIGH_MONO_COUNT,
+	UPDATE_CAPSULE,
+	QUERY_CAPSULE_CAPS,
+};
+
+/*
+ * efi_runtime_work:	Details of EFI Runtime Service work
+ * @arg<1-5>:		EFI Runtime Service function arguments
+ * @status:		Status of executing EFI Runtime Service
+ * @efi_rts_id:		EFI Runtime Service function identifier
+ * @efi_rts_comp:	Struct used for handling completions
+ */
+struct efi_runtime_work {
+	void *arg1;
+	void *arg2;
+	void *arg3;
+	void *arg4;
+	void *arg5;
+	efi_status_t status;
+	struct work_struct work;
+	enum efi_rts_ids efi_rts_id;
+	struct completion efi_rts_comp;
+};
+
+/*
+ * efi_queue_work:	Queue efi_runtime_service() and wait until it's done
+ * @rts:		efi_runtime_service() function identifier
+ * @rts_arg<1-5>:	efi_runtime_service() function arguments
+ *
+ * Accesses to efi_runtime_services() are serialized by a binary
+ * semaphore (efi_runtime_lock) and caller waits until the work is
+ * finished, hence _only_ one work is queued at a time and the caller
+ * thread waits for completion.
+ */
+#define efi_queue_work(_rts, _arg1, _arg2, _arg3, _arg4, _arg5)		\
+({									\
+	struct efi_runtime_work efi_rts_work;				\
+	efi_rts_work.status = EFI_ABORTED;				\
+									\
+	init_completion(&efi_rts_work.efi_rts_comp);			\
+	INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts);		\
+	efi_rts_work.arg1 = _arg1;					\
+	efi_rts_work.arg2 = _arg2;					\
+	efi_rts_work.arg3 = _arg3;					\
+	efi_rts_work.arg4 = _arg4;					\
+	efi_rts_work.arg5 = _arg5;					\
+	efi_rts_work.efi_rts_id = _rts;					\
+									\
+	/*								\
+	 * queue_work() returns 0 if work was already on queue,         \
+	 * _ideally_ this should never happen.                          \
+	 */								\
+	if (queue_work(efi_rts_wq, &efi_rts_work.work))			\
+		wait_for_completion(&efi_rts_work.efi_rts_comp);	\
+	else								\
+		pr_err("Failed to queue work to efi_rts_wq.\n");	\
+									\
+	efi_rts_work.status;						\
+})
+
 void efi_call_virt_check_flags(unsigned long flags, const char *call)
 {
 	unsigned long cur_flags, mismatch;
@@ -90,13 +172,98 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call)
  */
 static DEFINE_SEMAPHORE(efi_runtime_lock);
 
+/*
+ * Calls the appropriate efi_runtime_service() with the appropriate
+ * arguments.
+ *
+ * Semantics followed by efi_call_rts() to understand efi_runtime_work:
+ * 1. If argument was a pointer, recast it from void pointer to original
+ * pointer type.
+ * 2. If argument was a value, recast it from void pointer to original
+ * pointer type and dereference it.
+ */
+static void efi_call_rts(struct work_struct *work)
+{
+	struct efi_runtime_work *efi_rts_work;
+	void *arg1, *arg2, *arg3, *arg4, *arg5;
+	efi_status_t status = EFI_NOT_FOUND;
+
+	efi_rts_work = container_of(work, struct efi_runtime_work, work);
+	arg1 = efi_rts_work->arg1;
+	arg2 = efi_rts_work->arg2;
+	arg3 = efi_rts_work->arg3;
+	arg4 = efi_rts_work->arg4;
+	arg5 = efi_rts_work->arg5;
+
+	switch (efi_rts_work->efi_rts_id) {
+	case GET_TIME:
+		status = efi_call_virt(get_time, (efi_time_t *)arg1,
+				       (efi_time_cap_t *)arg2);
+		break;
+	case SET_TIME:
+		status = efi_call_virt(set_time, (efi_time_t *)arg1);
+		break;
+	case GET_WAKEUP_TIME:
+		status = efi_call_virt(get_wakeup_time, (efi_bool_t *)arg1,
+				       (efi_bool_t *)arg2, (efi_time_t *)arg3);
+		break;
+	case SET_WAKEUP_TIME:
+		status = efi_call_virt(set_wakeup_time, *(efi_bool_t *)arg1,
+				       (efi_time_t *)arg2);
+		break;
+	case GET_VARIABLE:
+		status = efi_call_virt(get_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, (u32 *)arg3,
+				       (unsigned long *)arg4, (void *)arg5);
+		break;
+	case GET_NEXT_VARIABLE:
+		status = efi_call_virt(get_next_variable, (unsigned long *)arg1,
+				       (efi_char16_t *)arg2,
+				       (efi_guid_t *)arg3);
+		break;
+	case SET_VARIABLE:
+		status = efi_call_virt(set_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, *(u32 *)arg3,
+				       *(unsigned long *)arg4, (void *)arg5);
+		break;
+	case QUERY_VARIABLE_INFO:
+		status = efi_call_virt(query_variable_info, *(u32 *)arg1,
+				       (u64 *)arg2, (u64 *)arg3, (u64 *)arg4);
+		break;
+	case GET_NEXT_HIGH_MONO_COUNT:
+		status = efi_call_virt(get_next_high_mono_count, (u32 *)arg1);
+		break;
+	case UPDATE_CAPSULE:
+		status = efi_call_virt(update_capsule,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2,
+				       *(unsigned long *)arg3);
+		break;
+	case QUERY_CAPSULE_CAPS:
+		status = efi_call_virt(query_capsule_caps,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2, (u64 *)arg3,
+				       (int *)arg4);
+		break;
+	default:
+		/*
+		 * Ideally, we should never reach here because a caller of this
+		 * function should have put the right efi_runtime_service()
+		 * function identifier into efi_rts_work->efi_rts_id
+		 */
+		pr_err("Requested executing invalid EFI Runtime Service.\n");
+	}
+	efi_rts_work->status = status;
+	complete(&efi_rts_work->efi_rts_comp);
+}
+
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	efi_status_t status;
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_time, tm, tc);
+	status = efi_queue_work(GET_TIME, tm, tc, NULL, NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -107,7 +274,7 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_time, tm);
+	status = efi_queue_work(SET_TIME, tm, NULL, NULL, NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -120,7 +287,8 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
+	status = efi_queue_work(GET_WAKEUP_TIME, enabled, pending, tm, NULL,
+				NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -131,7 +299,8 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_wakeup_time, enabled, tm);
+	status = efi_queue_work(SET_WAKEUP_TIME, &enabled, tm, NULL, NULL,
+				NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -146,8 +315,8 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_variable, name, vendor, attr, data_size,
-			       data);
+	status = efi_queue_work(GET_VARIABLE, name, vendor, attr, data_size,
+				data);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -160,7 +329,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_next_variable, name_size, name, vendor);
+	status = efi_queue_work(GET_NEXT_VARIABLE, name_size, name, vendor,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -175,8 +345,8 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
-			       data);
+	status = efi_queue_work(SET_VARIABLE, name, vendor, &attr, &data_size,
+				data);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -210,8 +380,8 @@ static efi_status_t virt_efi_query_variable_info(u32 attr,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(query_variable_info, attr, storage_space,
-			       remaining_space, max_variable_size);
+	status = efi_queue_work(QUERY_VARIABLE_INFO, &attr, storage_space,
+				remaining_space, max_variable_size, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -242,7 +412,8 @@ static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_next_high_mono_count, count);
+	status = efi_queue_work(GET_NEXT_HIGH_MONO_COUNT, count, NULL, NULL,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -272,7 +443,8 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(update_capsule, capsules, count, sg_list);
+	status = efi_queue_work(UPDATE_CAPSULE, capsules, &count, &sg_list,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -289,8 +461,8 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(query_capsule_caps, capsules, count, max_size,
-			       reset_type);
+	status = efi_queue_work(QUERY_CAPSULE_CAPS, capsules, &count,
+				max_size, reset_type, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index e2232cbcec8b..addd9fecc198 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -25,6 +25,7 @@
 
 struct acpi_gpio_event {
 	struct list_head node;
+	struct list_head initial_sync_list;
 	acpi_handle handle;
 	unsigned int pin;
 	unsigned int irq;
@@ -50,6 +51,9 @@ struct acpi_gpio_chip {
 	struct list_head events;
 };
 
+static LIST_HEAD(acpi_gpio_initial_sync_list);
+static DEFINE_MUTEX(acpi_gpio_initial_sync_list_lock);
+
 static int acpi_gpiochip_find(struct gpio_chip *gc, void *data)
 {
 	if (!gc->parent)
@@ -85,6 +89,21 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin)
 	return gpiochip_get_desc(chip, pin);
 }
 
+static void acpi_gpio_add_to_initial_sync_list(struct acpi_gpio_event *event)
+{
+	mutex_lock(&acpi_gpio_initial_sync_list_lock);
+	list_add(&event->initial_sync_list, &acpi_gpio_initial_sync_list);
+	mutex_unlock(&acpi_gpio_initial_sync_list_lock);
+}
+
+static void acpi_gpio_del_from_initial_sync_list(struct acpi_gpio_event *event)
+{
+	mutex_lock(&acpi_gpio_initial_sync_list_lock);
+	if (!list_empty(&event->initial_sync_list))
+		list_del_init(&event->initial_sync_list);
+	mutex_unlock(&acpi_gpio_initial_sync_list_lock);
+}
+
 static irqreturn_t acpi_gpio_irq_handler(int irq, void *data)
 {
 	struct acpi_gpio_event *event = data;
@@ -136,7 +155,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 	irq_handler_t handler = NULL;
 	struct gpio_desc *desc;
 	unsigned long irqflags;
-	int ret, pin, irq;
+	int ret, pin, irq, value;
 
 	if (!acpi_gpio_get_irq_resource(ares, &agpio))
 		return AE_OK;
@@ -167,6 +186,8 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 
 	gpiod_direction_input(desc);
 
+	value = gpiod_get_value(desc);
+
 	ret = gpiochip_lock_as_irq(chip, pin);
 	if (ret) {
 		dev_err(chip->parent, "Failed to lock GPIO as interrupt\n");
@@ -208,6 +229,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 	event->irq = irq;
 	event->pin = pin;
 	event->desc = desc;
+	INIT_LIST_HEAD(&event->initial_sync_list);
 
 	ret = request_threaded_irq(event->irq, NULL, handler, irqflags,
 				   "ACPI:Event", event);
@@ -222,6 +244,18 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares,
 		enable_irq_wake(irq);
 
 	list_add_tail(&event->node, &acpi_gpio->events);
+
+	/*
+	 * Make sure we trigger the initial state of the IRQ when using RISING
+	 * or FALLING.  Note we run the handlers on late_init, the AML code
+	 * may refer to OperationRegions from other (builtin) drivers which
+	 * may be probed after us.
+	 */
+	if (handler == acpi_gpio_irq_handler &&
+	    (((irqflags & IRQF_TRIGGER_RISING) && value == 1) ||
+	     ((irqflags & IRQF_TRIGGER_FALLING) && value == 0)))
+		acpi_gpio_add_to_initial_sync_list(event);
+
 	return AE_OK;
 
 fail_free_event:
@@ -294,6 +328,8 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip)
 	list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) {
 		struct gpio_desc *desc;
 
+		acpi_gpio_del_from_initial_sync_list(event);
+
 		if (irqd_is_wakeup_set(irq_get_irq_data(event->irq)))
 			disable_irq_wake(event->irq);
 
@@ -1158,3 +1194,21 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id)
 
 	return con_id == NULL;
 }
+
+/* Sync the initial state of handlers after all builtin drivers have probed */
+static int acpi_gpio_initial_sync(void)
+{
+	struct acpi_gpio_event *event, *ep;
+
+	mutex_lock(&acpi_gpio_initial_sync_list_lock);
+	list_for_each_entry_safe(event, ep, &acpi_gpio_initial_sync_list,
+				 initial_sync_list) {
+		acpi_evaluate_object(event->handle, NULL, NULL, NULL);
+		list_del_init(&event->initial_sync_list);
+	}
+	mutex_unlock(&acpi_gpio_initial_sync_list_lock);
+
+	return 0;
+}
+/* We must use _sync so that this runs after the first deferred_probe run */
+late_initcall_sync(acpi_gpio_initial_sync);
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index d638c0fb3418..b54fb78a283c 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -553,7 +553,7 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 
 	/* Clone the lessor file to create a new file for us */
 	DRM_DEBUG_LEASE("Allocating lease file\n");
-	lessee_file = filp_clone_open(lessor_file);
+	lessee_file = file_clone_open(lessor_file);
 	if (IS_ERR(lessee_file)) {
 		ret = PTR_ERR(lessee_file);
 		goto out_lessee;
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index dc87797db500..b50b74053664 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -4,6 +4,7 @@
  * Copyright © 2017-2018 Intel Corporation
  */
 
+#include <linux/irq.h>
 #include "i915_pmu.h"
 #include "intel_ringbuffer.h"
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c
index 6269750e2b54..b4941101f21a 100644
--- a/drivers/gpu/drm/i915/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/intel_lpe_audio.c
@@ -62,6 +62,7 @@
 
 #include <linux/acpi.h>
 #include <linux/device.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index f10840ad465c..ccf42663a908 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -937,6 +937,18 @@ config SENSORS_MCP3021
 	  This driver can also be built as a module.  If so, the module
 	  will be called mcp3021.
 
+config SENSORS_MLXREG_FAN
+	tristate "Mellanox Mellanox FAN driver"
+	depends on MELLANOX_PLATFORM
+	imply THERMAL
+	select REGMAP
+	help
+	  This option enables support for the FAN control on the Mellanox
+	  Ethernet and InfiniBand switches. The driver can be activated by the
+	  platform device add call. Say Y to enable these. To compile this
+	  driver as a module, choose 'M' here: the module will be called
+	  mlxreg-fan.
+
 config SENSORS_TC654
 	tristate "Microchip TC654/TC655 and compatibles"
 	depends on I2C
@@ -1256,6 +1268,16 @@ config SENSORS_NCT7904
 	  This driver can also be built as a module.  If so, the module
 	  will be called nct7904.
 
+config SENSORS_NPCM7XX
+	tristate "Nuvoton NPCM750 and compatible PWM and Fan controllers"
+	imply THERMAL
+	help
+	  This driver provides support for Nuvoton NPCM750/730/715/705 PWM
+          and Fan controllers.
+
+          This driver can also be built as a module. If so, the module
+          will be called npcm750-pwm-fan.
+
 config SENSORS_NSA320
 	tristate "ZyXEL NSA320 and compatible fan speed and temperature sensors"
 	depends on GPIOLIB && OF
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index e7d52a36e6c4..842c92f83ce6 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -129,11 +129,13 @@ obj-$(CONFIG_SENSORS_MAX31790)	+= max31790.o
 obj-$(CONFIG_SENSORS_MC13783_ADC)+= mc13783-adc.o
 obj-$(CONFIG_SENSORS_MCP3021)	+= mcp3021.o
 obj-$(CONFIG_SENSORS_TC654)	+= tc654.o
+obj-$(CONFIG_SENSORS_MLXREG_FAN) += mlxreg-fan.o
 obj-$(CONFIG_SENSORS_MENF21BMC_HWMON) += menf21bmc_hwmon.o
 obj-$(CONFIG_SENSORS_NCT6683)	+= nct6683.o
 obj-$(CONFIG_SENSORS_NCT6775)	+= nct6775.o
 obj-$(CONFIG_SENSORS_NCT7802)	+= nct7802.o
 obj-$(CONFIG_SENSORS_NCT7904)	+= nct7904.o
+obj-$(CONFIG_SENSORS_NPCM7XX)	+= npcm750-pwm-fan.o
 obj-$(CONFIG_SENSORS_NSA320)	+= nsa320-hwmon.o
 obj-$(CONFIG_SENSORS_NTC_THERMISTOR)	+= ntc_thermistor.o
 obj-$(CONFIG_SENSORS_PC87360)	+= pc87360.o
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index 9ef84998c7f3..90837f7c7d0f 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -194,8 +194,7 @@ struct adt7475_data {
 	struct mutex lock;
 
 	unsigned long measure_updated;
-	unsigned long limits_updated;
-	char valid;
+	bool valid;
 
 	u8 config4;
 	u8 config5;
@@ -326,6 +325,9 @@ static ssize_t show_voltage(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	unsigned short val;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	switch (sattr->nr) {
 	case ALARM:
 		return sprintf(buf, "%d\n",
@@ -381,6 +383,9 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	switch (sattr->nr) {
 	case HYSTERSIS:
 		mutex_lock(&data->lock);
@@ -625,6 +630,9 @@ static ssize_t show_point2(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out, val;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	mutex_lock(&data->lock);
 	out = (data->range[sattr->index] >> 4) & 0x0F;
 	val = reg2temp(data, data->temp[AUTOMIN][sattr->index]);
@@ -683,6 +691,9 @@ static ssize_t show_tach(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	if (sattr->nr == ALARM)
 		out = (data->alarms >> (sattr->index + 10)) & 1;
 	else
@@ -720,6 +731,9 @@ static ssize_t show_pwm(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwm[sattr->nr][sattr->index]);
 }
 
@@ -729,6 +743,9 @@ static ssize_t show_pwmchan(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwmchan[sattr->index]);
 }
 
@@ -738,6 +755,9 @@ static ssize_t show_pwmctrl(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwmctl[sattr->index]);
 }
 
@@ -945,6 +965,9 @@ static ssize_t show_pwmfreq(struct device *dev, struct device_attribute *attr,
 	int i = clamp_val(data->range[sattr->index] & 0xf, 0,
 			  ARRAY_SIZE(pwmfreq_table) - 1);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", pwmfreq_table[i]);
 }
 
@@ -1035,6 +1058,10 @@ static ssize_t cpu0_vid_show(struct device *dev,
 			     struct device_attribute *devattr, char *buf)
 {
 	struct adt7475_data *data = adt7475_update_device(dev);
+
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
 
@@ -1385,6 +1412,121 @@ static void adt7475_remove_files(struct i2c_client *client,
 		sysfs_remove_group(&client->dev.kobj, &vid_attr_group);
 }
 
+static int adt7475_update_limits(struct i2c_client *client)
+{
+	struct adt7475_data *data = i2c_get_clientdata(client);
+	int i;
+	int ret;
+
+	ret = adt7475_read(REG_CONFIG4);
+	if (ret < 0)
+		return ret;
+	data->config4 = ret;
+
+	ret = adt7475_read(REG_CONFIG5);
+	if (ret < 0)
+		return ret;
+	data->config5 = ret;
+
+	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+		if (!(data->has_voltage & (1 << i)))
+			continue;
+		/* Adjust values so they match the input precision */
+		ret = adt7475_read(VOLTAGE_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[MIN][i] = ret << 2;
+
+		ret = adt7475_read(VOLTAGE_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[MAX][i] = ret << 2;
+	}
+
+	if (data->has_voltage & (1 << 5)) {
+		ret = adt7475_read(REG_VTT_MIN);
+		if (ret < 0)
+			return ret;
+		data->voltage[MIN][5] = ret << 2;
+
+		ret = adt7475_read(REG_VTT_MAX);
+		if (ret < 0)
+			return ret;
+		data->voltage[MAX][5] = ret << 2;
+	}
+
+	for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+		/* Adjust values so they match the input precision */
+		ret = adt7475_read(TEMP_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[MIN][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[MAX][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_TMIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[AUTOMIN][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_THERM_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[THERM][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_OFFSET_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[OFFSET][i] = ret;
+	}
+	adt7475_read_hystersis(client);
+
+	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+		if (i == 3 && !data->has_fan4)
+			continue;
+		ret = adt7475_read_word(client, TACH_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->tach[MIN][i] = ret;
+	}
+
+	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+		if (i == 1 && !data->has_pwm2)
+			continue;
+		ret = adt7475_read(PWM_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[MAX][i] = ret;
+
+		ret = adt7475_read(PWM_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[MIN][i] = ret;
+		/* Set the channel and control information */
+		adt7475_read_pwm(client, i);
+	}
+
+	ret = adt7475_read(TEMP_TRANGE_REG(0));
+	if (ret < 0)
+		return ret;
+	data->range[0] = ret;
+
+	ret = adt7475_read(TEMP_TRANGE_REG(1));
+	if (ret < 0)
+		return ret;
+	data->range[1] = ret;
+
+	ret = adt7475_read(TEMP_TRANGE_REG(2));
+	if (ret < 0)
+		return ret;
+	data->range[2] = ret;
+
+	return 0;
+}
+
 static int adt7475_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
@@ -1562,6 +1704,11 @@ static int adt7475_probe(struct i2c_client *client,
 			 (data->bypass_attn & (1 << 3)) ? " in3" : "",
 			 (data->bypass_attn & (1 << 4)) ? " in4" : "");
 
+	/* Limits and settings, should never change update more than once */
+	ret = adt7475_update_limits(client);
+	if (ret)
+		goto eremove;
+
 	return 0;
 
 eremove:
@@ -1658,121 +1805,122 @@ static void adt7475_read_pwm(struct i2c_client *client, int index)
 	}
 }
 
-static struct adt7475_data *adt7475_update_device(struct device *dev)
+static int adt7475_update_measure(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adt7475_data *data = i2c_get_clientdata(client);
 	u16 ext;
 	int i;
+	int ret;
 
-	mutex_lock(&data->lock);
+	ret = adt7475_read(REG_STATUS2);
+	if (ret < 0)
+		return ret;
+	data->alarms = ret << 8;
 
-	/* Measurement values update every 2 seconds */
-	if (time_after(jiffies, data->measure_updated + HZ * 2) ||
-	    !data->valid) {
-		data->alarms = adt7475_read(REG_STATUS2) << 8;
-		data->alarms |= adt7475_read(REG_STATUS1);
-
-		ext = (adt7475_read(REG_EXTEND2) << 8) |
-			adt7475_read(REG_EXTEND1);
-		for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
-			if (!(data->has_voltage & (1 << i)))
-				continue;
-			data->voltage[INPUT][i] =
-				(adt7475_read(VOLTAGE_REG(i)) << 2) |
-				((ext >> (i * 2)) & 3);
-		}
+	ret = adt7475_read(REG_STATUS1);
+	if (ret < 0)
+		return ret;
+	data->alarms |= ret;
 
-		for (i = 0; i < ADT7475_TEMP_COUNT; i++)
-			data->temp[INPUT][i] =
-				(adt7475_read(TEMP_REG(i)) << 2) |
-				((ext >> ((i + 5) * 2)) & 3);
+	ret = adt7475_read(REG_EXTEND2);
+	if (ret < 0)
+		return ret;
 
-		if (data->has_voltage & (1 << 5)) {
-			data->alarms |= adt7475_read(REG_STATUS4) << 24;
-			ext = adt7475_read(REG_EXTEND3);
-			data->voltage[INPUT][5] = adt7475_read(REG_VTT) << 2 |
-				((ext >> 4) & 3);
-		}
+	ext = (ret << 8);
 
-		for (i = 0; i < ADT7475_TACH_COUNT; i++) {
-			if (i == 3 && !data->has_fan4)
-				continue;
-			data->tach[INPUT][i] =
-				adt7475_read_word(client, TACH_REG(i));
-		}
+	ret = adt7475_read(REG_EXTEND1);
+	if (ret < 0)
+		return ret;
 
-		/* Updated by hw when in auto mode */
-		for (i = 0; i < ADT7475_PWM_COUNT; i++) {
-			if (i == 1 && !data->has_pwm2)
-				continue;
-			data->pwm[INPUT][i] = adt7475_read(PWM_REG(i));
-		}
+	ext |= ret;
+
+	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+		if (!(data->has_voltage & (1 << i)))
+			continue;
+		ret = adt7475_read(VOLTAGE_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[INPUT][i] =
+			(ret << 2) |
+			((ext >> (i * 2)) & 3);
+	}
 
-		if (data->has_vid)
-			data->vid = adt7475_read(REG_VID) & 0x3f;
+	for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+		ret = adt7475_read(TEMP_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[INPUT][i] =
+			(ret << 2) |
+			((ext >> ((i + 5) * 2)) & 3);
+	}
 
-		data->measure_updated = jiffies;
+	if (data->has_voltage & (1 << 5)) {
+		ret = adt7475_read(REG_STATUS4);
+		if (ret < 0)
+			return ret;
+		data->alarms |= ret << 24;
+
+		ret = adt7475_read(REG_EXTEND3);
+		if (ret < 0)
+			return ret;
+		ext = ret;
+
+		ret = adt7475_read(REG_VTT);
+		if (ret < 0)
+			return ret;
+		data->voltage[INPUT][5] = ret << 2 |
+			((ext >> 4) & 3);
 	}
 
-	/* Limits and settings, should never change update every 60 seconds */
-	if (time_after(jiffies, data->limits_updated + HZ * 60) ||
-	    !data->valid) {
-		data->config4 = adt7475_read(REG_CONFIG4);
-		data->config5 = adt7475_read(REG_CONFIG5);
-
-		for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
-			if (!(data->has_voltage & (1 << i)))
-				continue;
-			/* Adjust values so they match the input precision */
-			data->voltage[MIN][i] =
-				adt7475_read(VOLTAGE_MIN_REG(i)) << 2;
-			data->voltage[MAX][i] =
-				adt7475_read(VOLTAGE_MAX_REG(i)) << 2;
-		}
+	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+		if (i == 3 && !data->has_fan4)
+			continue;
+		ret = adt7475_read_word(client, TACH_REG(i));
+		if (ret < 0)
+			return ret;
+		data->tach[INPUT][i] = ret;
+	}
 
-		if (data->has_voltage & (1 << 5)) {
-			data->voltage[MIN][5] = adt7475_read(REG_VTT_MIN) << 2;
-			data->voltage[MAX][5] = adt7475_read(REG_VTT_MAX) << 2;
-		}
+	/* Updated by hw when in auto mode */
+	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+		if (i == 1 && !data->has_pwm2)
+			continue;
+		ret = adt7475_read(PWM_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[INPUT][i] = ret;
+	}
 
-		for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
-			/* Adjust values so they match the input precision */
-			data->temp[MIN][i] =
-				adt7475_read(TEMP_MIN_REG(i)) << 2;
-			data->temp[MAX][i] =
-				adt7475_read(TEMP_MAX_REG(i)) << 2;
-			data->temp[AUTOMIN][i] =
-				adt7475_read(TEMP_TMIN_REG(i)) << 2;
-			data->temp[THERM][i] =
-				adt7475_read(TEMP_THERM_REG(i)) << 2;
-			data->temp[OFFSET][i] =
-				adt7475_read(TEMP_OFFSET_REG(i));
-		}
-		adt7475_read_hystersis(client);
+	if (data->has_vid) {
+		ret = adt7475_read(REG_VID);
+		if (ret < 0)
+			return ret;
+		data->vid = ret & 0x3f;
+	}
 
-		for (i = 0; i < ADT7475_TACH_COUNT; i++) {
-			if (i == 3 && !data->has_fan4)
-				continue;
-			data->tach[MIN][i] =
-				adt7475_read_word(client, TACH_MIN_REG(i));
-		}
+	return 0;
+}
 
-		for (i = 0; i < ADT7475_PWM_COUNT; i++) {
-			if (i == 1 && !data->has_pwm2)
-				continue;
-			data->pwm[MAX][i] = adt7475_read(PWM_MAX_REG(i));
-			data->pwm[MIN][i] = adt7475_read(PWM_MIN_REG(i));
-			/* Set the channel and control information */
-			adt7475_read_pwm(client, i);
-		}
+static struct adt7475_data *adt7475_update_device(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct adt7475_data *data = i2c_get_clientdata(client);
+	int ret;
 
-		data->range[0] = adt7475_read(TEMP_TRANGE_REG(0));
-		data->range[1] = adt7475_read(TEMP_TRANGE_REG(1));
-		data->range[2] = adt7475_read(TEMP_TRANGE_REG(2));
+	mutex_lock(&data->lock);
 
-		data->limits_updated = jiffies;
-		data->valid = 1;
+	/* Measurement values update every 2 seconds */
+	if (time_after(jiffies, data->measure_updated + HZ * 2) ||
+	    !data->valid) {
+		ret = adt7475_update_measure(dev);
+		if (ret) {
+			data->valid = false;
+			mutex_unlock(&data->lock);
+			return ERR_PTR(ret);
+		}
+		data->measure_updated = jiffies;
+		data->valid = true;
 	}
 
 	mutex_unlock(&data->lock);
diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c
index 1ea7ca510f84..aaebeb726d6a 100644
--- a/drivers/hwmon/emc1403.c
+++ b/drivers/hwmon/emc1403.c
@@ -443,8 +443,10 @@ static int emc1403_probe(struct i2c_client *client,
 	switch (id->driver_data) {
 	case emc1404:
 		data->groups[2] = &emc1404_group;
+		/* fall through */
 	case emc1403:
 		data->groups[1] = &emc1403_group;
+		/* fall through */
 	case emc1402:
 		data->groups[0] = &emc1402_group;
 	}
diff --git a/drivers/hwmon/iio_hwmon.c b/drivers/hwmon/iio_hwmon.c
index 69031a0f7ed2..2f3f875c06ac 100644
--- a/drivers/hwmon/iio_hwmon.c
+++ b/drivers/hwmon/iio_hwmon.c
@@ -22,7 +22,6 @@
  * struct iio_hwmon_state - device instance state
  * @channels:		filled with array of channels from iio
  * @num_channels:	number of channels in channels (saves counting twice)
- * @hwmon_dev:		associated hwmon device
  * @attr_group:		the group of attributes
  * @groups:		null terminated array of attribute groups
  * @attrs:		null terminated array of attribute pointers.
@@ -30,7 +29,6 @@
 struct iio_hwmon_state {
 	struct iio_channel *channels;
 	int num_channels;
-	struct device *hwmon_dev;
 	struct attribute_group attr_group;
 	const struct attribute_group *groups[2];
 	struct attribute **attrs;
@@ -68,12 +66,13 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	enum iio_chan_type type;
 	struct iio_channel *channels;
 	const char *name = "iio_hwmon";
+	struct device *hwmon_dev;
 	char *sname;
 
 	if (dev->of_node && dev->of_node->name)
 		name = dev->of_node->name;
 
-	channels = iio_channel_get_all(dev);
+	channels = devm_iio_channel_get_all(dev);
 	if (IS_ERR(channels)) {
 		if (PTR_ERR(channels) == -ENODEV)
 			return -EPROBE_DEFER;
@@ -81,10 +80,8 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	}
 
 	st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL);
-	if (st == NULL) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (st == NULL)
+		return -ENOMEM;
 
 	st->channels = channels;
 
@@ -95,22 +92,18 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	st->attrs = devm_kcalloc(dev,
 				 st->num_channels + 1, sizeof(*st->attrs),
 				 GFP_KERNEL);
-	if (st->attrs == NULL) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (st->attrs == NULL)
+		return -ENOMEM;
 
 	for (i = 0; i < st->num_channels; i++) {
 		a = devm_kzalloc(dev, sizeof(*a), GFP_KERNEL);
-		if (a == NULL) {
-			ret = -ENOMEM;
-			goto error_release_channels;
-		}
+		if (a == NULL)
+			return -ENOMEM;
 
 		sysfs_attr_init(&a->dev_attr.attr);
 		ret = iio_get_channel_type(&st->channels[i], &type);
 		if (ret < 0)
-			goto error_release_channels;
+			return ret;
 
 		switch (type) {
 		case IIO_VOLTAGE:
@@ -134,13 +127,11 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 							       humidity_i++);
 			break;
 		default:
-			ret = -EINVAL;
-			goto error_release_channels;
-		}
-		if (a->dev_attr.attr.name == NULL) {
-			ret = -ENOMEM;
-			goto error_release_channels;
+			return -EINVAL;
 		}
+		if (a->dev_attr.attr.name == NULL)
+			return -ENOMEM;
+
 		a->dev_attr.show = iio_hwmon_read_val;
 		a->dev_attr.attr.mode = S_IRUGO;
 		a->index = i;
@@ -151,34 +142,13 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	st->groups[0] = &st->attr_group;
 
 	sname = devm_kstrdup(dev, name, GFP_KERNEL);
-	if (!sname) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (!sname)
+		return -ENOMEM;
 
 	strreplace(sname, '-', '_');
-	st->hwmon_dev = hwmon_device_register_with_groups(dev, sname, st,
-							  st->groups);
-	if (IS_ERR(st->hwmon_dev)) {
-		ret = PTR_ERR(st->hwmon_dev);
-		goto error_release_channels;
-	}
-	platform_set_drvdata(pdev, st);
-	return 0;
-
-error_release_channels:
-	iio_channel_release_all(channels);
-	return ret;
-}
-
-static int iio_hwmon_remove(struct platform_device *pdev)
-{
-	struct iio_hwmon_state *st = platform_get_drvdata(pdev);
-
-	hwmon_device_unregister(st->hwmon_dev);
-	iio_channel_release_all(st->channels);
-
-	return 0;
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, sname, st,
+							   st->groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static const struct of_device_id iio_hwmon_of_match[] = {
@@ -193,7 +163,6 @@ static struct platform_driver __refdata iio_hwmon_driver = {
 		.of_match_table = iio_hwmon_of_match,
 	},
 	.probe = iio_hwmon_probe,
-	.remove = iio_hwmon_remove,
 };
 
 module_platform_driver(iio_hwmon_driver);
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 17c6460ae351..bb15d7816a29 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -99,12 +99,8 @@ static const struct tctl_offset tctl_offset_table[] = {
 	{ 0x17, "AMD Ryzen 7 1700X", 20000 },
 	{ 0x17, "AMD Ryzen 7 1800X", 20000 },
 	{ 0x17, "AMD Ryzen 7 2700X", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1950X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1920X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1900X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1950", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1920", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1910", 10000 },
+	{ 0x17, "AMD Ryzen Threadripper 19", 27000 }, /* 19{00,20,50}X */
+	{ 0x17, "AMD Ryzen Threadripper 29", 27000 }, /* 29{20,50,70,90}[W]X */
 };
 
 static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c
new file mode 100644
index 000000000000..de46577c7d5a
--- /dev/null
+++ b/drivers/hwmon/mlxreg-fan.c
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+//
+// Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+// Copyright (c) 2018 Vadim Pasternak <vadimp@mellanox.com>
+
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/module.h>
+#include <linux/platform_data/mlxreg.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/thermal.h>
+
+#define MLXREG_FAN_MAX_TACHO		12
+#define MLXREG_FAN_MAX_STATE		10
+#define MLXREG_FAN_MIN_DUTY		51	/* 20% */
+#define MLXREG_FAN_MAX_DUTY		255	/* 100% */
+/*
+ * Minimum and maximum FAN allowed speed in percent: from 20% to 100%. Values
+ * MLXREG_FAN_MAX_STATE + x, where x is between 2 and 10 are used for
+ * setting FAN speed dynamic minimum. For example, if value is set to 14 (40%)
+ * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to
+ * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100.
+ */
+#define MLXREG_FAN_SPEED_MIN			(MLXREG_FAN_MAX_STATE + 2)
+#define MLXREG_FAN_SPEED_MAX			(MLXREG_FAN_MAX_STATE * 2)
+#define MLXREG_FAN_SPEED_MIN_LEVEL		2	/* 20 percent */
+#define MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF	44
+#define MLXREG_FAN_TACHO_DIVIDER_DEF		1132
+/*
+ * FAN datasheet defines the formula for RPM calculations as RPM = 15/t-high.
+ * The logic in a programmable device measures the time t-high by sampling the
+ * tachometer every t-sample (with the default value 11.32 uS) and increment
+ * a counter (N) as long as the pulse has not change:
+ * RPM = 15 / (t-sample * (K + Regval)), where:
+ * Regval: is the value read from the programmable device register;
+ *  - 0xff - represents tachometer fault;
+ *  - 0xfe - represents tachometer minimum value , which is 4444 RPM;
+ *  - 0x00 - represents tachometer maximum value , which is 300000 RPM;
+ * K: is 44 and it represents the minimum allowed samples per pulse;
+ * N: is equal K + Regval;
+ * In order to calculate RPM from the register value the following formula is
+ * used: RPM = 15 / ((Regval + K) * 11.32) * 10^(-6)), which in  the
+ * default case is modified to:
+ * RPM = 15000000 * 100 / ((Regval + 44) * 1132);
+ * - for Regval 0x00, RPM will be 15000000 * 100 / (44 * 1132) = 30115;
+ * - for Regval 0xfe, RPM will be 15000000 * 100 / ((254 + 44) * 1132) = 4446;
+ * In common case the formula is modified to:
+ * RPM = 15000000 * 100 / ((Regval + samples) * divider).
+ */
+#define MLXREG_FAN_GET_RPM(rval, d, s)	(DIV_ROUND_CLOSEST(15000000 * 100, \
+					 ((rval) + (s)) * (d)))
+#define MLXREG_FAN_GET_FAULT(val, mask) (!!((val) ^ (mask)))
+#define MLXREG_FAN_PWM_DUTY2STATE(duty)	(DIV_ROUND_CLOSEST((duty) *	\
+					 MLXREG_FAN_MAX_STATE,		\
+					 MLXREG_FAN_MAX_DUTY))
+#define MLXREG_FAN_PWM_STATE2DUTY(stat)	(DIV_ROUND_CLOSEST((stat) *	\
+					 MLXREG_FAN_MAX_DUTY,		\
+					 MLXREG_FAN_MAX_STATE))
+
+/*
+ * struct mlxreg_fan_tacho - tachometer data (internal use):
+ *
+ * @connected: indicates if tachometer is connected;
+ * @reg: register offset;
+ * @mask: fault mask;
+ */
+struct mlxreg_fan_tacho {
+	bool connected;
+	u32 reg;
+	u32 mask;
+};
+
+/*
+ * struct mlxreg_fan_pwm - PWM data (internal use):
+ *
+ * @connected: indicates if PWM is connected;
+ * @reg: register offset;
+ */
+struct mlxreg_fan_pwm {
+	bool connected;
+	u32 reg;
+};
+
+/*
+ * struct mlxreg_fan - private data (internal use):
+ *
+ * @dev: basic device;
+ * @regmap: register map of parent device;
+ * @tacho: tachometer data;
+ * @pwm: PWM data;
+ * @samples: minimum allowed samples per pulse;
+ * @divider: divider value for tachometer RPM calculation;
+ * @cooling: cooling device levels;
+ * @cdev: cooling device;
+ */
+struct mlxreg_fan {
+	struct device *dev;
+	void *regmap;
+	struct mlxreg_core_platform_data *pdata;
+	struct mlxreg_fan_tacho tacho[MLXREG_FAN_MAX_TACHO];
+	struct mlxreg_fan_pwm pwm;
+	int samples;
+	int divider;
+	u8 cooling_levels[MLXREG_FAN_MAX_STATE + 1];
+	struct thermal_cooling_device *cdev;
+};
+
+static int
+mlxreg_fan_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+		int channel, long *val)
+{
+	struct mlxreg_fan *fan = dev_get_drvdata(dev);
+	struct mlxreg_fan_tacho *tacho;
+	u32 regval;
+	int err;
+
+	switch (type) {
+	case hwmon_fan:
+		tacho = &fan->tacho[channel];
+		switch (attr) {
+		case hwmon_fan_input:
+			err = regmap_read(fan->regmap, tacho->reg, &regval);
+			if (err)
+				return err;
+
+			*val = MLXREG_FAN_GET_RPM(regval, fan->divider,
+						  fan->samples);
+			break;
+
+		case hwmon_fan_fault:
+			err = regmap_read(fan->regmap, tacho->reg, &regval);
+			if (err)
+				return err;
+
+			*val = MLXREG_FAN_GET_FAULT(regval, tacho->mask);
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+			if (err)
+				return err;
+
+			*val = regval;
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+mlxreg_fan_write(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+		 int channel, long val)
+{
+	struct mlxreg_fan *fan = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			if (val < MLXREG_FAN_MIN_DUTY ||
+			    val > MLXREG_FAN_MAX_DUTY)
+				return -EINVAL;
+			return regmap_write(fan->regmap, fan->pwm.reg, val);
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static umode_t
+mlxreg_fan_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
+		      int channel)
+{
+	switch (type) {
+	case hwmon_fan:
+		if (!(((struct mlxreg_fan *)data)->tacho[channel].connected))
+			return 0;
+
+		switch (attr) {
+		case hwmon_fan_input:
+		case hwmon_fan_fault:
+			return 0444;
+		default:
+			break;
+		}
+		break;
+
+	case hwmon_pwm:
+		if (!(((struct mlxreg_fan *)data)->pwm.connected))
+			return 0;
+
+		switch (attr) {
+		case hwmon_pwm_input:
+			return 0644;
+		default:
+			break;
+		}
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const u32 mlxreg_fan_hwmon_fan_config[] = {
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_fan = {
+	.type = hwmon_fan,
+	.config = mlxreg_fan_hwmon_fan_config,
+};
+
+static const u32 mlxreg_fan_hwmon_pwm_config[] = {
+	HWMON_PWM_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_pwm = {
+	.type = hwmon_pwm,
+	.config = mlxreg_fan_hwmon_pwm_config,
+};
+
+static const struct hwmon_channel_info *mlxreg_fan_hwmon_info[] = {
+	&mlxreg_fan_hwmon_fan,
+	&mlxreg_fan_hwmon_pwm,
+	NULL
+};
+
+static const struct hwmon_ops mlxreg_fan_hwmon_hwmon_ops = {
+	.is_visible = mlxreg_fan_is_visible,
+	.read = mlxreg_fan_read,
+	.write = mlxreg_fan_write,
+};
+
+static const struct hwmon_chip_info mlxreg_fan_hwmon_chip_info = {
+	.ops = &mlxreg_fan_hwmon_hwmon_ops,
+	.info = mlxreg_fan_hwmon_info,
+};
+
+static int mlxreg_fan_get_max_state(struct thermal_cooling_device *cdev,
+				    unsigned long *state)
+{
+	*state = MLXREG_FAN_MAX_STATE;
+	return 0;
+}
+
+static int mlxreg_fan_get_cur_state(struct thermal_cooling_device *cdev,
+				    unsigned long *state)
+
+{
+	struct mlxreg_fan *fan = cdev->devdata;
+	u32 regval;
+	int err;
+
+	err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+	if (err) {
+		dev_err(fan->dev, "Failed to query PWM duty\n");
+		return err;
+	}
+
+	*state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+
+	return 0;
+}
+
+static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev,
+				    unsigned long state)
+
+{
+	struct mlxreg_fan *fan = cdev->devdata;
+	unsigned long cur_state;
+	u32 regval;
+	int i;
+	int err;
+
+	/*
+	 * Verify if this request is for changing allowed FAN dynamical
+	 * minimum. If it is - update cooling levels accordingly and update
+	 * state, if current state is below the newly requested minimum state.
+	 * For example, if current state is 5, and minimal state is to be
+	 * changed from 4 to 6, fan->cooling_levels[0 to 5] will be changed all
+	 * from 4 to 6. And state 5 (fan->cooling_levels[4]) should be
+	 * overwritten.
+	 */
+	if (state >= MLXREG_FAN_SPEED_MIN && state <= MLXREG_FAN_SPEED_MAX) {
+		state -= MLXREG_FAN_MAX_STATE;
+		for (i = 0; i < state; i++)
+			fan->cooling_levels[i] = state;
+		for (i = state; i <= MLXREG_FAN_MAX_STATE; i++)
+			fan->cooling_levels[i] = i;
+
+		err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+		if (err) {
+			dev_err(fan->dev, "Failed to query PWM duty\n");
+			return err;
+		}
+
+		cur_state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+		if (state < cur_state)
+			return 0;
+
+		state = cur_state;
+	}
+
+	if (state > MLXREG_FAN_MAX_STATE)
+		return -EINVAL;
+
+	/* Normalize the state to the valid speed range. */
+	state = fan->cooling_levels[state];
+	err = regmap_write(fan->regmap, fan->pwm.reg,
+			   MLXREG_FAN_PWM_STATE2DUTY(state));
+	if (err) {
+		dev_err(fan->dev, "Failed to write PWM duty\n");
+		return err;
+	}
+	return 0;
+}
+
+static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = {
+	.get_max_state	= mlxreg_fan_get_max_state,
+	.get_cur_state	= mlxreg_fan_get_cur_state,
+	.set_cur_state	= mlxreg_fan_set_cur_state,
+};
+
+static int mlxreg_fan_config(struct mlxreg_fan *fan,
+			     struct mlxreg_core_platform_data *pdata)
+{
+	struct mlxreg_core_data *data = pdata->data;
+	bool configured = false;
+	int tacho_num = 0, i;
+
+	fan->samples = MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF;
+	fan->divider = MLXREG_FAN_TACHO_DIVIDER_DEF;
+	for (i = 0; i < pdata->counter; i++, data++) {
+		if (strnstr(data->label, "tacho", sizeof(data->label))) {
+			if (tacho_num == MLXREG_FAN_MAX_TACHO) {
+				dev_err(fan->dev, "too many tacho entries: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->tacho[tacho_num].reg = data->reg;
+			fan->tacho[tacho_num].mask = data->mask;
+			fan->tacho[tacho_num++].connected = true;
+		} else if (strnstr(data->label, "pwm", sizeof(data->label))) {
+			if (fan->pwm.connected) {
+				dev_err(fan->dev, "duplicate pwm entry: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->pwm.reg = data->reg;
+			fan->pwm.connected = true;
+		} else if (strnstr(data->label, "conf", sizeof(data->label))) {
+			if (configured) {
+				dev_err(fan->dev, "duplicate conf entry: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			/* Validate that conf parameters are not zeros. */
+			if (!data->mask || !data->bit) {
+				dev_err(fan->dev, "invalid conf entry params: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->samples = data->mask;
+			fan->divider = data->bit;
+			configured = true;
+		} else {
+			dev_err(fan->dev, "invalid label: %s\n", data->label);
+			return -EINVAL;
+		}
+	}
+
+	/* Init cooling levels per PWM state. */
+	for (i = 0; i < MLXREG_FAN_SPEED_MIN_LEVEL; i++)
+		fan->cooling_levels[i] = MLXREG_FAN_SPEED_MIN_LEVEL;
+	for (i = MLXREG_FAN_SPEED_MIN_LEVEL; i <= MLXREG_FAN_MAX_STATE; i++)
+		fan->cooling_levels[i] = i;
+
+	return 0;
+}
+
+static int mlxreg_fan_probe(struct platform_device *pdev)
+{
+	struct mlxreg_core_platform_data *pdata;
+	struct mlxreg_fan *fan;
+	struct device *hwm;
+	int err;
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata) {
+		dev_err(&pdev->dev, "Failed to get platform data.\n");
+		return -EINVAL;
+	}
+
+	fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL);
+	if (!fan)
+		return -ENOMEM;
+
+	fan->dev = &pdev->dev;
+	fan->regmap = pdata->regmap;
+	platform_set_drvdata(pdev, fan);
+
+	err = mlxreg_fan_config(fan, pdata);
+	if (err)
+		return err;
+
+	hwm = devm_hwmon_device_register_with_info(&pdev->dev, "mlxreg_fan",
+						   fan,
+						   &mlxreg_fan_hwmon_chip_info,
+						   NULL);
+	if (IS_ERR(hwm)) {
+		dev_err(&pdev->dev, "Failed to register hwmon device\n");
+		return PTR_ERR(hwm);
+	}
+
+	if (IS_REACHABLE(CONFIG_THERMAL)) {
+		fan->cdev = thermal_cooling_device_register("mlxreg_fan", fan,
+						&mlxreg_fan_cooling_ops);
+		if (IS_ERR(fan->cdev)) {
+			dev_err(&pdev->dev, "Failed to register cooling device\n");
+			return PTR_ERR(fan->cdev);
+		}
+	}
+
+	return 0;
+}
+
+static int mlxreg_fan_remove(struct platform_device *pdev)
+{
+	struct mlxreg_fan *fan = platform_get_drvdata(pdev);
+
+	if (IS_REACHABLE(CONFIG_THERMAL))
+		thermal_cooling_device_unregister(fan->cdev);
+
+	return 0;
+}
+
+static struct platform_driver mlxreg_fan_driver = {
+	.driver = {
+	    .name = "mlxreg-fan",
+	},
+	.probe = mlxreg_fan_probe,
+	.remove = mlxreg_fan_remove,
+};
+
+module_platform_driver(mlxreg_fan_driver);
+
+MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox FAN driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mlxreg-fan");
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index f9d1349c3286..c6bd61e4695a 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -1050,8 +1050,8 @@ struct nct6775_data {
 	u64 beeps;
 
 	u8 pwm_num;	/* number of pwm */
-	u8 pwm_mode[NUM_FAN];	/* 1->DC variable voltage,
-				 * 0->PWM variable duty cycle
+	u8 pwm_mode[NUM_FAN];	/* 0->DC variable voltage,
+				 * 1->PWM variable duty cycle
 				 */
 	enum pwm_enable pwm_enable[NUM_FAN];
 			/* 0->off
@@ -2541,7 +2541,7 @@ static void pwm_update_registers(struct nct6775_data *data, int nr)
 	case thermal_cruise:
 		nct6775_write_value(data, data->REG_TARGET[nr],
 				    data->target_temp[nr]);
-		/* intentional */
+		/* fall through  */
 	default:
 		reg = nct6775_read_value(data, data->REG_FAN_MODE[nr]);
 		reg = (reg & ~data->tolerance_mask) |
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index 95a68ab175c7..7815ddf149f6 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -77,7 +77,7 @@ struct nct7904_data {
 };
 
 /* Access functions */
-static int nct7904_bank_lock(struct nct7904_data *data, unsigned bank)
+static int nct7904_bank_lock(struct nct7904_data *data, unsigned int bank)
 {
 	int ret;
 
@@ -99,7 +99,7 @@ static inline void nct7904_bank_release(struct nct7904_data *data)
 
 /* Read 1-byte register. Returns unsigned reg or -ERRNO on error. */
 static int nct7904_read_reg(struct nct7904_data *data,
-			    unsigned bank, unsigned reg)
+			    unsigned int bank, unsigned int reg)
 {
 	struct i2c_client *client = data->client;
 	int ret;
@@ -117,7 +117,7 @@ static int nct7904_read_reg(struct nct7904_data *data,
  * -ERRNO on error.
  */
 static int nct7904_read_reg16(struct nct7904_data *data,
-			      unsigned bank, unsigned reg)
+			      unsigned int bank, unsigned int reg)
 {
 	struct i2c_client *client = data->client;
 	int ret, hi;
@@ -139,7 +139,7 @@ static int nct7904_read_reg16(struct nct7904_data *data,
 
 /* Write 1-byte register. Returns 0 or -ERRNO on error. */
 static int nct7904_write_reg(struct nct7904_data *data,
-			     unsigned bank, unsigned reg, u8 val)
+			     unsigned int bank, unsigned int reg, u8 val)
 {
 	struct i2c_client *client = data->client;
 	int ret;
@@ -159,7 +159,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel,
 	unsigned int cnt, rpm;
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_fan_input:
 		ret = nct7904_read_reg16(data, BANK_0,
 					 FANIN1_HV_REG + channel * 2);
@@ -200,7 +200,7 @@ static int nct7904_read_in(struct device *dev, u32 attr, int channel,
 
 	index = nct7904_chan_to_index[channel];
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_in_input:
 		ret = nct7904_read_reg16(data, BANK_0,
 					 VSEN1_HV_REG + index * 2);
@@ -236,7 +236,7 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret, temp;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_temp_input:
 		if (channel == 0)
 			ret = nct7904_read_reg16(data, BANK_0, LTD_HV_REG);
@@ -276,7 +276,7 @@ static int nct7904_read_pwm(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 		ret = nct7904_read_reg(data, BANK_3, FANCTL1_OUT_REG + channel);
 		if (ret < 0)
@@ -301,7 +301,7 @@ static int nct7904_write_pwm(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 		if (val < 0 || val > 255)
 			return -EINVAL;
@@ -322,7 +322,7 @@ static int nct7904_write_pwm(struct device *dev, u32 attr, int channel,
 
 static umode_t nct7904_pwm_is_visible(const void *_data, u32 attr, int channel)
 {
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 	case hwmon_pwm_enable:
 		return S_IRUGO | S_IWUSR;
@@ -431,15 +431,15 @@ static const struct hwmon_channel_info nct7904_in = {
 };
 
 static const u32 nct7904_fan_config[] = {
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-	    0
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_fan = {
@@ -448,11 +448,11 @@ static const struct hwmon_channel_info nct7904_fan = {
 };
 
 static const u32 nct7904_pwm_config[] = {
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	    0
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_pwm = {
@@ -461,16 +461,16 @@ static const struct hwmon_channel_info nct7904_pwm = {
 };
 
 static const u32 nct7904_temp_config[] = {
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-	    0
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_temp = {
diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c
new file mode 100644
index 000000000000..8474d601aa63
--- /dev/null
+++ b/drivers/hwmon/npcm750-pwm-fan.c
@@ -0,0 +1,1057 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2014-2018 Nuvoton Technology corporation.
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
+#include <linux/thermal.h>
+
+/* NPCM7XX PWM registers */
+#define NPCM7XX_PWM_REG_BASE(base, n)    ((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_PWM_REG_PR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_PWM_REG_CSR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_PWM_REG_CR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_PWM_REG_CNRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x0C + (12 * (ch)))
+#define NPCM7XX_PWM_REG_CMRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x10 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PDRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x14 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PIER(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x3C)
+#define NPCM7XX_PWM_REG_PIIR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x40)
+
+#define NPCM7XX_PWM_CTRL_CH0_MODE_BIT		BIT(3)
+#define NPCM7XX_PWM_CTRL_CH1_MODE_BIT		BIT(11)
+#define NPCM7XX_PWM_CTRL_CH2_MODE_BIT		BIT(15)
+#define NPCM7XX_PWM_CTRL_CH3_MODE_BIT		BIT(19)
+
+#define NPCM7XX_PWM_CTRL_CH0_INV_BIT		BIT(2)
+#define NPCM7XX_PWM_CTRL_CH1_INV_BIT		BIT(10)
+#define NPCM7XX_PWM_CTRL_CH2_INV_BIT		BIT(14)
+#define NPCM7XX_PWM_CTRL_CH3_INV_BIT		BIT(18)
+
+#define NPCM7XX_PWM_CTRL_CH0_EN_BIT		BIT(0)
+#define NPCM7XX_PWM_CTRL_CH1_EN_BIT		BIT(8)
+#define NPCM7XX_PWM_CTRL_CH2_EN_BIT		BIT(12)
+#define NPCM7XX_PWM_CTRL_CH3_EN_BIT		BIT(16)
+
+/* Define the maximum PWM channel number */
+#define NPCM7XX_PWM_MAX_CHN_NUM			8
+#define NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE	4
+#define NPCM7XX_PWM_MAX_MODULES                 2
+
+/* Define the Counter Register, value = 100 for match 100% */
+#define NPCM7XX_PWM_COUNTER_DEFAULT_NUM		255
+#define NPCM7XX_PWM_CMR_DEFAULT_NUM		127
+#define NPCM7XX_PWM_CMR_MAX			255
+
+/* default all PWM channels PRESCALE2 = 1 */
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0	0x4
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1	0x40
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2	0x400
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3	0x4000
+
+#define PWM_OUTPUT_FREQ_25KHZ			25000
+#define PWN_CNT_DEFAULT				256
+#define MIN_PRESCALE1				2
+#define NPCM7XX_PWM_PRESCALE_SHIFT_CH01		8
+
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT	(NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3)
+
+#define NPCM7XX_PWM_CTRL_MODE_DEFAULT	(NPCM7XX_PWM_CTRL_CH0_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH1_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH2_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH3_MODE_BIT)
+
+/* NPCM7XX FAN Tacho registers */
+#define NPCM7XX_FAN_REG_BASE(base, n)	((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_FAN_REG_TCNT1(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_FAN_REG_TCRA(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x02)
+#define NPCM7XX_FAN_REG_TCRB(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_FAN_REG_TCNT2(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x06)
+#define NPCM7XX_FAN_REG_TPRSC(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_FAN_REG_TCKC(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x0A)
+#define NPCM7XX_FAN_REG_TMCTRL(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x0C)
+#define NPCM7XX_FAN_REG_TICTRL(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x0E)
+#define NPCM7XX_FAN_REG_TICLR(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x10)
+#define NPCM7XX_FAN_REG_TIEN(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x12)
+#define NPCM7XX_FAN_REG_TCPA(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x14)
+#define NPCM7XX_FAN_REG_TCPB(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x16)
+#define NPCM7XX_FAN_REG_TCPCFG(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x18)
+#define NPCM7XX_FAN_REG_TINASEL(base, n)  (NPCM7XX_FAN_REG_BASE(base, n) + 0x1A)
+#define NPCM7XX_FAN_REG_TINBSEL(base, n)  (NPCM7XX_FAN_REG_BASE(base, n) + 0x1C)
+
+#define NPCM7XX_FAN_TCKC_CLKX_NONE	0
+#define NPCM7XX_FAN_TCKC_CLK1_APB	BIT(0)
+#define NPCM7XX_FAN_TCKC_CLK2_APB	BIT(3)
+
+#define NPCM7XX_FAN_TMCTRL_TBEN		BIT(6)
+#define NPCM7XX_FAN_TMCTRL_TAEN		BIT(5)
+#define NPCM7XX_FAN_TMCTRL_TBEDG	BIT(4)
+#define NPCM7XX_FAN_TMCTRL_TAEDG	BIT(3)
+#define NPCM7XX_FAN_TMCTRL_MODE_5	BIT(2)
+
+#define NPCM7XX_FAN_TICLR_CLEAR_ALL	GENMASK(5, 0)
+#define NPCM7XX_FAN_TICLR_TFCLR		BIT(5)
+#define NPCM7XX_FAN_TICLR_TECLR		BIT(4)
+#define NPCM7XX_FAN_TICLR_TDCLR		BIT(3)
+#define NPCM7XX_FAN_TICLR_TCCLR		BIT(2)
+#define NPCM7XX_FAN_TICLR_TBCLR		BIT(1)
+#define NPCM7XX_FAN_TICLR_TACLR		BIT(0)
+
+#define NPCM7XX_FAN_TIEN_ENABLE_ALL	GENMASK(5, 0)
+#define NPCM7XX_FAN_TIEN_TFIEN		BIT(5)
+#define NPCM7XX_FAN_TIEN_TEIEN		BIT(4)
+#define NPCM7XX_FAN_TIEN_TDIEN		BIT(3)
+#define NPCM7XX_FAN_TIEN_TCIEN		BIT(2)
+#define NPCM7XX_FAN_TIEN_TBIEN		BIT(1)
+#define NPCM7XX_FAN_TIEN_TAIEN		BIT(0)
+
+#define NPCM7XX_FAN_TICTRL_TFPND	BIT(5)
+#define NPCM7XX_FAN_TICTRL_TEPND	BIT(4)
+#define NPCM7XX_FAN_TICTRL_TDPND	BIT(3)
+#define NPCM7XX_FAN_TICTRL_TCPND	BIT(2)
+#define NPCM7XX_FAN_TICTRL_TBPND	BIT(1)
+#define NPCM7XX_FAN_TICTRL_TAPND	BIT(0)
+
+#define NPCM7XX_FAN_TCPCFG_HIBEN	BIT(7)
+#define NPCM7XX_FAN_TCPCFG_EQBEN	BIT(6)
+#define NPCM7XX_FAN_TCPCFG_LOBEN	BIT(5)
+#define NPCM7XX_FAN_TCPCFG_CPBSEL	BIT(4)
+#define NPCM7XX_FAN_TCPCFG_HIAEN	BIT(3)
+#define NPCM7XX_FAN_TCPCFG_EQAEN	BIT(2)
+#define NPCM7XX_FAN_TCPCFG_LOAEN	BIT(1)
+#define NPCM7XX_FAN_TCPCFG_CPASEL	BIT(0)
+
+/* FAN General Definition */
+/* Define the maximum FAN channel number */
+#define NPCM7XX_FAN_MAX_MODULE			8
+#define NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE	2
+#define NPCM7XX_FAN_MAX_CHN_NUM			16
+
+/*
+ * Get Fan Tach Timeout (base on clock 214843.75Hz, 1 cnt = 4.654us)
+ * Timeout 94ms ~= 0x5000
+ * (The minimum FAN speed could to support ~640RPM/pulse 1,
+ * 320RPM/pulse 2, ...-- 10.6Hz)
+ */
+#define NPCM7XX_FAN_TIMEOUT	0x5000
+#define NPCM7XX_FAN_TCNT	0xFFFF
+#define NPCM7XX_FAN_TCPA	(NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+#define NPCM7XX_FAN_TCPB	(NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+
+#define NPCM7XX_FAN_POLL_TIMER_200MS			200
+#define NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION	2
+#define NPCM7XX_FAN_TINASEL_FANIN_DEFAULT		0
+#define NPCM7XX_FAN_CLK_PRESCALE			255
+
+#define NPCM7XX_FAN_CMPA				0
+#define NPCM7XX_FAN_CMPB				1
+
+/* Obtain the fan number */
+#define NPCM7XX_FAN_INPUT(fan, cmp)		(((fan) << 1) + (cmp))
+
+/* fan sample status */
+#define FAN_DISABLE				0xFF
+#define FAN_INIT				0x00
+#define FAN_PREPARE_TO_GET_FIRST_CAPTURE	0x01
+#define FAN_ENOUGH_SAMPLE			0x02
+
+struct npcm7xx_fan_dev {
+	u8 fan_st_flg;
+	u8 fan_pls_per_rev;
+	u16 fan_cnt;
+	u32 fan_cnt_tmp;
+};
+
+struct npcm7xx_cooling_device {
+	char name[THERMAL_NAME_LENGTH];
+	struct npcm7xx_pwm_fan_data *data;
+	struct thermal_cooling_device *tcdev;
+	int pwm_port;
+	u8 *cooling_levels;
+	u8 max_state;
+	u8 cur_state;
+};
+
+struct npcm7xx_pwm_fan_data {
+	void __iomem *pwm_base;
+	void __iomem *fan_base;
+	unsigned long pwm_clk_freq;
+	unsigned long fan_clk_freq;
+	struct clk *pwm_clk;
+	struct clk *fan_clk;
+	struct mutex pwm_lock[NPCM7XX_PWM_MAX_MODULES];
+	spinlock_t fan_lock[NPCM7XX_FAN_MAX_MODULE];
+	int fan_irq[NPCM7XX_FAN_MAX_MODULE];
+	bool pwm_present[NPCM7XX_PWM_MAX_CHN_NUM];
+	bool fan_present[NPCM7XX_FAN_MAX_CHN_NUM];
+	u32 input_clk_freq;
+	struct timer_list fan_timer;
+	struct npcm7xx_fan_dev fan_dev[NPCM7XX_FAN_MAX_CHN_NUM];
+	struct npcm7xx_cooling_device *cdev[NPCM7XX_PWM_MAX_CHN_NUM];
+	u8 fan_select;
+};
+
+static int npcm7xx_pwm_config_set(struct npcm7xx_pwm_fan_data *data,
+				  int channel, u16 val)
+{
+	u32 pwm_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 tmp_buf, ctrl_en_bit, env_bit;
+
+	/*
+	 * Config PWM Comparator register for setting duty cycle
+	 */
+	mutex_lock(&data->pwm_lock[module]);
+
+	/* write new CMR value  */
+	iowrite32(val, NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pwm_ch));
+	tmp_buf = ioread32(NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+
+	switch (pwm_ch) {
+	case 0:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH0_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH0_INV_BIT;
+		break;
+	case 1:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH1_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH1_INV_BIT;
+		break;
+	case 2:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH2_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH2_INV_BIT;
+		break;
+	case 3:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH3_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH3_INV_BIT;
+		break;
+	default:
+		mutex_unlock(&data->pwm_lock[module]);
+		return -ENODEV;
+	}
+
+	if (val == 0) {
+		/* Disable PWM */
+		tmp_buf &= ~ctrl_en_bit;
+		tmp_buf |= env_bit;
+	} else {
+		/* Enable PWM */
+		tmp_buf |= ctrl_en_bit;
+		tmp_buf &= ~env_bit;
+	}
+
+	iowrite32(tmp_buf, NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+	mutex_unlock(&data->pwm_lock[module]);
+
+	return 0;
+}
+
+static inline void npcm7xx_fan_start_capture(struct npcm7xx_pwm_fan_data *data,
+					     u8 fan, u8 cmp)
+{
+	u8 fan_id;
+	u8 reg_mode;
+	u8 reg_int;
+	unsigned long flags;
+
+	fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+	/* to check whether any fan tach is enable */
+	if (data->fan_dev[fan_id].fan_st_flg != FAN_DISABLE) {
+		/* reset status */
+		spin_lock_irqsave(&data->fan_lock[fan], flags);
+
+		data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+		reg_int = ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/*
+		 * the interrupt enable bits do not need to be cleared before
+		 * it sets, the interrupt enable bits are cleared only on reset.
+		 * the clock unit control register is behaving in the same
+		 * manner that the interrupt enable register behave.
+		 */
+		if (cmp == NPCM7XX_FAN_CMPA) {
+			/* enable interrupt */
+			iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TAIEN |
+					    NPCM7XX_FAN_TIEN_TEIEN),
+				 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+			reg_mode = NPCM7XX_FAN_TCKC_CLK1_APB
+				| ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+							       fan));
+
+			/* start to Capture */
+			iowrite8(reg_mode, NPCM7XX_FAN_REG_TCKC(data->fan_base,
+								fan));
+		} else {
+			/* enable interrupt */
+			iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TBIEN |
+					    NPCM7XX_FAN_TIEN_TFIEN),
+				 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+			reg_mode =
+				NPCM7XX_FAN_TCKC_CLK2_APB
+				| ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+							       fan));
+
+			/* start to Capture */
+			iowrite8(reg_mode,
+				 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+		}
+
+		spin_unlock_irqrestore(&data->fan_lock[fan], flags);
+	}
+}
+
+/*
+ * Enable a background timer to poll fan tach value, (200ms * 4)
+ * to polling all fan
+ */
+static void npcm7xx_fan_polling(struct timer_list *t)
+{
+	struct npcm7xx_pwm_fan_data *data;
+	int i;
+
+	data = from_timer(data, t, fan_timer);
+
+	/*
+	 * Polling two module per one round,
+	 * FAN01 & FAN89 / FAN23 & FAN1011 / FAN45 & FAN1213 / FAN67 & FAN1415
+	 */
+	for (i = data->fan_select; i < NPCM7XX_FAN_MAX_MODULE;
+	      i = i + 4) {
+		/* clear the flag and reset the counter (TCNT) */
+		iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, i));
+
+		if (data->fan_present[i * 2]) {
+			iowrite16(NPCM7XX_FAN_TCNT,
+				  NPCM7XX_FAN_REG_TCNT1(data->fan_base, i));
+			npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPA);
+		}
+		if (data->fan_present[(i * 2) + 1]) {
+			iowrite16(NPCM7XX_FAN_TCNT,
+				  NPCM7XX_FAN_REG_TCNT2(data->fan_base, i));
+			npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPB);
+		}
+	}
+
+	data->fan_select++;
+	data->fan_select &= 0x3;
+
+	/* reset the timer interval */
+	data->fan_timer.expires = jiffies +
+		msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+	add_timer(&data->fan_timer);
+}
+
+static inline void npcm7xx_fan_compute(struct npcm7xx_pwm_fan_data *data,
+				       u8 fan, u8 cmp, u8 fan_id, u8 flag_int,
+				       u8 flag_mode, u8 flag_clear)
+{
+	u8  reg_int;
+	u8  reg_mode;
+	u16 fan_cap;
+
+	if (cmp == NPCM7XX_FAN_CMPA)
+		fan_cap = ioread16(NPCM7XX_FAN_REG_TCRA(data->fan_base, fan));
+	else
+		fan_cap = ioread16(NPCM7XX_FAN_REG_TCRB(data->fan_base, fan));
+
+	/* clear capature flag, H/W will auto reset the NPCM7XX_FAN_TCNTx */
+	iowrite8(flag_clear, NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+	if (data->fan_dev[fan_id].fan_st_flg == FAN_INIT) {
+		/* First capture, drop it */
+		data->fan_dev[fan_id].fan_st_flg =
+			FAN_PREPARE_TO_GET_FIRST_CAPTURE;
+
+		/* reset counter */
+		data->fan_dev[fan_id].fan_cnt_tmp = 0;
+	} else if (data->fan_dev[fan_id].fan_st_flg < FAN_ENOUGH_SAMPLE) {
+		/*
+		 * collect the enough sample,
+		 * (ex: 2 pulse fan need to get 2 sample)
+		 */
+		data->fan_dev[fan_id].fan_cnt_tmp +=
+			(NPCM7XX_FAN_TCNT - fan_cap);
+
+		data->fan_dev[fan_id].fan_st_flg++;
+	} else {
+		/* get enough sample or fan disable */
+		if (data->fan_dev[fan_id].fan_st_flg == FAN_ENOUGH_SAMPLE) {
+			data->fan_dev[fan_id].fan_cnt_tmp +=
+				(NPCM7XX_FAN_TCNT - fan_cap);
+
+			/* compute finial average cnt per pulse */
+			data->fan_dev[fan_id].fan_cnt =
+				data->fan_dev[fan_id].fan_cnt_tmp /
+				FAN_ENOUGH_SAMPLE;
+
+			data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+		}
+
+		reg_int =  ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* disable interrupt */
+		iowrite8((reg_int & ~flag_int),
+			 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+		reg_mode =  ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/* stop capturing */
+		iowrite8((reg_mode & ~flag_mode),
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+	}
+}
+
+static inline void npcm7xx_check_cmp(struct npcm7xx_pwm_fan_data *data,
+				     u8 fan, u8 cmp, u8 flag)
+{
+	u8 reg_int;
+	u8 reg_mode;
+	u8 flag_timeout;
+	u8 flag_cap;
+	u8 flag_clear;
+	u8 flag_int;
+	u8 flag_mode;
+	u8 fan_id;
+
+	fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+	if (cmp == NPCM7XX_FAN_CMPA) {
+		flag_cap = NPCM7XX_FAN_TICTRL_TAPND;
+		flag_timeout = NPCM7XX_FAN_TICTRL_TEPND;
+		flag_int = NPCM7XX_FAN_TIEN_TAIEN | NPCM7XX_FAN_TIEN_TEIEN;
+		flag_mode = NPCM7XX_FAN_TCKC_CLK1_APB;
+		flag_clear = NPCM7XX_FAN_TICLR_TACLR | NPCM7XX_FAN_TICLR_TECLR;
+	} else {
+		flag_cap = NPCM7XX_FAN_TICTRL_TBPND;
+		flag_timeout = NPCM7XX_FAN_TICTRL_TFPND;
+		flag_int = NPCM7XX_FAN_TIEN_TBIEN | NPCM7XX_FAN_TIEN_TFIEN;
+		flag_mode = NPCM7XX_FAN_TCKC_CLK2_APB;
+		flag_clear = NPCM7XX_FAN_TICLR_TBCLR | NPCM7XX_FAN_TICLR_TFCLR;
+	}
+
+	if (flag & flag_timeout) {
+		reg_int =  ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* disable interrupt */
+		iowrite8((reg_int & ~flag_int),
+			 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* clear interrupt flag */
+		iowrite8(flag_clear,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+		reg_mode =  ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/* stop capturing */
+		iowrite8((reg_mode & ~flag_mode),
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/*
+		 *  If timeout occurs (NPCM7XX_FAN_TIMEOUT), the fan doesn't
+		 *  connect or speed is lower than 10.6Hz (320RPM/pulse2).
+		 *  In these situation, the RPM output should be zero.
+		 */
+		data->fan_dev[fan_id].fan_cnt = 0;
+	} else {
+	    /* input capture is occurred */
+		if (flag & flag_cap)
+			npcm7xx_fan_compute(data, fan, cmp, fan_id, flag_int,
+					    flag_mode, flag_clear);
+	}
+}
+
+static irqreturn_t npcm7xx_fan_isr(int irq, void *dev_id)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_id;
+	unsigned long flags;
+	int module;
+	u8 flag;
+
+	module = irq - data->fan_irq[0];
+	spin_lock_irqsave(&data->fan_lock[module], flags);
+
+	flag = ioread8(NPCM7XX_FAN_REG_TICTRL(data->fan_base, module));
+	if (flag > 0) {
+		npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPA, flag);
+		npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPB, flag);
+		spin_unlock_irqrestore(&data->fan_lock[module], flags);
+		return IRQ_HANDLED;
+	}
+
+	spin_unlock_irqrestore(&data->fan_lock[module], flags);
+
+	return IRQ_NONE;
+}
+
+static int npcm7xx_read_pwm(struct device *dev, u32 attr, int channel,
+			    long *val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+	u32 pmw_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		*val = ioread32
+			(NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pmw_ch));
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int npcm7xx_write_pwm(struct device *dev, u32 attr, int channel,
+			     long val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+	int err;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		if (val < 0 || val > NPCM7XX_PWM_CMR_MAX)
+			return -EINVAL;
+		err = npcm7xx_pwm_config_set(data, channel, (u16)val);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static umode_t npcm7xx_pwm_is_visible(const void *_data, u32 attr, int channel)
+{
+	const struct npcm7xx_pwm_fan_data *data = _data;
+
+	if (!data->pwm_present[channel])
+		return 0;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		return 0644;
+	default:
+		return 0;
+	}
+}
+
+static int npcm7xx_read_fan(struct device *dev, u32 attr, int channel,
+			    long *val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+
+	switch (attr) {
+	case hwmon_fan_input:
+		*val = 0;
+		if (data->fan_dev[channel].fan_cnt <= 0)
+			return data->fan_dev[channel].fan_cnt;
+
+		/* Convert the raw reading to RPM */
+		if (data->fan_dev[channel].fan_cnt > 0 &&
+		    data->fan_dev[channel].fan_pls_per_rev > 0)
+			*val = ((data->input_clk_freq * 60) /
+				(data->fan_dev[channel].fan_cnt *
+				 data->fan_dev[channel].fan_pls_per_rev));
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t npcm7xx_fan_is_visible(const void *_data, u32 attr, int channel)
+{
+	const struct npcm7xx_pwm_fan_data *data = _data;
+
+	if (!data->fan_present[channel])
+		return 0;
+
+	switch (attr) {
+	case hwmon_fan_input:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static int npcm7xx_read(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long *val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_read_pwm(dev, attr, channel, val);
+	case hwmon_fan:
+		return npcm7xx_read_fan(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int npcm7xx_write(struct device *dev, enum hwmon_sensor_types type,
+			 u32 attr, int channel, long val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_write_pwm(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t npcm7xx_is_visible(const void *data,
+				  enum hwmon_sensor_types type,
+				  u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_pwm_is_visible(data, attr, channel);
+	case hwmon_fan:
+		return npcm7xx_fan_is_visible(data, attr, channel);
+	default:
+		return 0;
+	}
+}
+
+static const u32 npcm7xx_pwm_config[] = {
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info npcm7xx_pwm = {
+	.type = hwmon_pwm,
+	.config = npcm7xx_pwm_config,
+};
+
+static const u32 npcm7xx_fan_config[] = {
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info npcm7xx_fan = {
+	.type = hwmon_fan,
+	.config = npcm7xx_fan_config,
+};
+
+static const struct hwmon_channel_info *npcm7xx_info[] = {
+	&npcm7xx_pwm,
+	&npcm7xx_fan,
+	NULL
+};
+
+static const struct hwmon_ops npcm7xx_hwmon_ops = {
+	.is_visible = npcm7xx_is_visible,
+	.read = npcm7xx_read,
+	.write = npcm7xx_write,
+};
+
+static const struct hwmon_chip_info npcm7xx_chip_info = {
+	.ops = &npcm7xx_hwmon_ops,
+	.info = npcm7xx_info,
+};
+
+static u32 npcm7xx_pwm_init(struct npcm7xx_pwm_fan_data *data)
+{
+	int m, ch;
+	u32 prescale_val, output_freq;
+
+	data->pwm_clk_freq = clk_get_rate(data->pwm_clk);
+
+	/* Adjust NPCM7xx PWMs output frequency to ~25Khz */
+	output_freq = data->pwm_clk_freq / PWN_CNT_DEFAULT;
+	prescale_val = DIV_ROUND_CLOSEST(output_freq, PWM_OUTPUT_FREQ_25KHZ);
+
+	/* If prescale_val = 0, then the prescale output clock is stopped */
+	if (prescale_val < MIN_PRESCALE1)
+		prescale_val = MIN_PRESCALE1;
+	/*
+	 * prescale_val need to decrement in one because in the PWM Prescale
+	 * register the Prescale value increment by one
+	 */
+	prescale_val--;
+
+	/* Setting PWM Prescale Register value register to both modules */
+	prescale_val |= (prescale_val << NPCM7XX_PWM_PRESCALE_SHIFT_CH01);
+
+	for (m = 0; m < NPCM7XX_PWM_MAX_MODULES  ; m++) {
+		iowrite32(prescale_val, NPCM7XX_PWM_REG_PR(data->pwm_base, m));
+		iowrite32(NPCM7XX_PWM_PRESCALE2_DEFAULT,
+			  NPCM7XX_PWM_REG_CSR(data->pwm_base, m));
+		iowrite32(NPCM7XX_PWM_CTRL_MODE_DEFAULT,
+			  NPCM7XX_PWM_REG_CR(data->pwm_base, m));
+
+		for (ch = 0; ch < NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE; ch++) {
+			iowrite32(NPCM7XX_PWM_COUNTER_DEFAULT_NUM,
+				  NPCM7XX_PWM_REG_CNRx(data->pwm_base, m, ch));
+		}
+	}
+
+	return output_freq / ((prescale_val & 0xf) + 1);
+}
+
+static void npcm7xx_fan_init(struct npcm7xx_pwm_fan_data *data)
+{
+	int md;
+	int ch;
+	int i;
+	u32 apb_clk_freq;
+
+	for (md = 0; md < NPCM7XX_FAN_MAX_MODULE; md++) {
+		/* stop FAN0~7 clock */
+		iowrite8(NPCM7XX_FAN_TCKC_CLKX_NONE,
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, md));
+
+		/* disable all interrupt */
+		iowrite8(0x00, NPCM7XX_FAN_REG_TIEN(data->fan_base, md));
+
+		/* clear all interrupt */
+		iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, md));
+
+		/* set FAN0~7 clock prescaler */
+		iowrite8(NPCM7XX_FAN_CLK_PRESCALE,
+			 NPCM7XX_FAN_REG_TPRSC(data->fan_base, md));
+
+		/* set FAN0~7 mode (high-to-low transition) */
+		iowrite8((NPCM7XX_FAN_TMCTRL_MODE_5 | NPCM7XX_FAN_TMCTRL_TBEN |
+			  NPCM7XX_FAN_TMCTRL_TAEN),
+			 NPCM7XX_FAN_REG_TMCTRL(data->fan_base, md));
+
+		/* set FAN0~7 Initial Count/Cap */
+		iowrite16(NPCM7XX_FAN_TCNT,
+			  NPCM7XX_FAN_REG_TCNT1(data->fan_base, md));
+		iowrite16(NPCM7XX_FAN_TCNT,
+			  NPCM7XX_FAN_REG_TCNT2(data->fan_base, md));
+
+		/* set FAN0~7 compare (equal to count) */
+		iowrite8((NPCM7XX_FAN_TCPCFG_EQAEN | NPCM7XX_FAN_TCPCFG_EQBEN),
+			 NPCM7XX_FAN_REG_TCPCFG(data->fan_base, md));
+
+		/* set FAN0~7 compare value */
+		iowrite16(NPCM7XX_FAN_TCPA,
+			  NPCM7XX_FAN_REG_TCPA(data->fan_base, md));
+		iowrite16(NPCM7XX_FAN_TCPB,
+			  NPCM7XX_FAN_REG_TCPB(data->fan_base, md));
+
+		/* set FAN0~7 fan input FANIN 0~15 */
+		iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+			 NPCM7XX_FAN_REG_TINASEL(data->fan_base, md));
+		iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+			 NPCM7XX_FAN_REG_TINBSEL(data->fan_base, md));
+
+		for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE; i++) {
+			ch = md * NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE + i;
+			data->fan_dev[ch].fan_st_flg = FAN_DISABLE;
+			data->fan_dev[ch].fan_pls_per_rev =
+				NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION;
+			data->fan_dev[ch].fan_cnt = 0;
+		}
+	}
+
+	apb_clk_freq = clk_get_rate(data->fan_clk);
+
+	/* Fan tach input clock = APB clock / prescalar, default is 255. */
+	data->input_clk_freq = apb_clk_freq / (NPCM7XX_FAN_CLK_PRESCALE + 1);
+}
+
+static int
+npcm7xx_pwm_cz_get_max_state(struct thermal_cooling_device *tcdev,
+			     unsigned long *state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+	*state = cdev->max_state;
+
+	return 0;
+}
+
+static int
+npcm7xx_pwm_cz_get_cur_state(struct thermal_cooling_device *tcdev,
+			     unsigned long *state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+	*state = cdev->cur_state;
+
+	return 0;
+}
+
+static int
+npcm7xx_pwm_cz_set_cur_state(struct thermal_cooling_device *tcdev,
+			     unsigned long state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+	int ret;
+
+	if (state > cdev->max_state)
+		return -EINVAL;
+
+	cdev->cur_state = state;
+	ret = npcm7xx_pwm_config_set(cdev->data, cdev->pwm_port,
+				     cdev->cooling_levels[cdev->cur_state]);
+
+	return ret;
+}
+
+static const struct thermal_cooling_device_ops npcm7xx_pwm_cool_ops = {
+	.get_max_state = npcm7xx_pwm_cz_get_max_state,
+	.get_cur_state = npcm7xx_pwm_cz_get_cur_state,
+	.set_cur_state = npcm7xx_pwm_cz_set_cur_state,
+};
+
+static int npcm7xx_create_pwm_cooling(struct device *dev,
+				      struct device_node *child,
+				      struct npcm7xx_pwm_fan_data *data,
+				      u32 pwm_port, u8 num_levels)
+{
+	int ret;
+	struct npcm7xx_cooling_device *cdev;
+
+	cdev = devm_kzalloc(dev, sizeof(*cdev), GFP_KERNEL);
+	if (!cdev)
+		return -ENOMEM;
+
+	cdev->cooling_levels = devm_kzalloc(dev, num_levels, GFP_KERNEL);
+	if (!cdev->cooling_levels)
+		return -ENOMEM;
+
+	cdev->max_state = num_levels - 1;
+	ret = of_property_read_u8_array(child, "cooling-levels",
+					cdev->cooling_levels,
+					num_levels);
+	if (ret) {
+		dev_err(dev, "Property 'cooling-levels' cannot be read.\n");
+		return ret;
+	}
+	snprintf(cdev->name, THERMAL_NAME_LENGTH, "%s%d", child->name,
+		 pwm_port);
+
+	cdev->tcdev = thermal_of_cooling_device_register(child,
+							 cdev->name,
+							 cdev,
+							 &npcm7xx_pwm_cool_ops);
+	if (IS_ERR(cdev->tcdev))
+		return PTR_ERR(cdev->tcdev);
+
+	cdev->data = data;
+	cdev->pwm_port = pwm_port;
+
+	data->cdev[pwm_port] = cdev;
+
+	return 0;
+}
+
+static int npcm7xx_en_pwm_fan(struct device *dev,
+			      struct device_node *child,
+			      struct npcm7xx_pwm_fan_data *data)
+{
+	u8 *fan_ch;
+	u32 pwm_port;
+	int ret, fan_cnt;
+	u8 index, ch;
+
+	ret = of_property_read_u32(child, "reg", &pwm_port);
+	if (ret)
+		return ret;
+
+	data->pwm_present[pwm_port] = true;
+	ret = npcm7xx_pwm_config_set(data, pwm_port,
+				     NPCM7XX_PWM_CMR_DEFAULT_NUM);
+
+	ret = of_property_count_u8_elems(child, "cooling-levels");
+	if (ret > 0) {
+		ret = npcm7xx_create_pwm_cooling(dev, child, data, pwm_port,
+						 ret);
+		if (ret)
+			return ret;
+	}
+
+	fan_cnt = of_property_count_u8_elems(child, "fan-tach-ch");
+	if (fan_cnt < 1)
+		return -EINVAL;
+
+	fan_ch = devm_kzalloc(dev, sizeof(*fan_ch) * fan_cnt, GFP_KERNEL);
+	if (!fan_ch)
+		return -ENOMEM;
+
+	ret = of_property_read_u8_array(child, "fan-tach-ch", fan_ch, fan_cnt);
+	if (ret)
+		return ret;
+
+	for (ch = 0; ch < fan_cnt; ch++) {
+		index = fan_ch[ch];
+		data->fan_present[index] = true;
+		data->fan_dev[index].fan_st_flg = FAN_INIT;
+	}
+
+	return 0;
+}
+
+static int npcm7xx_pwm_fan_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np, *child;
+	struct npcm7xx_pwm_fan_data *data;
+	struct resource *res;
+	struct device *hwmon;
+	char name[20];
+	int ret, cnt;
+	u32 output_freq;
+	u32 i;
+
+	np = dev->of_node;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm");
+	if (!res) {
+		dev_err(dev, "pwm resource not found\n");
+		return -ENODEV;
+	}
+
+	data->pwm_base = devm_ioremap_resource(dev, res);
+	dev_dbg(dev, "pwm base resource is %pR\n", res);
+	if (IS_ERR(data->pwm_base))
+		return PTR_ERR(data->pwm_base);
+
+	data->pwm_clk = devm_clk_get(dev, "pwm");
+	if (IS_ERR(data->pwm_clk)) {
+		dev_err(dev, "couldn't get pwm clock\n");
+		return PTR_ERR(data->pwm_clk);
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "fan");
+	if (!res) {
+		dev_err(dev, "fan resource not found\n");
+		return -ENODEV;
+	}
+
+	data->fan_base = devm_ioremap_resource(dev, res);
+	dev_dbg(dev, "fan base resource is %pR\n", res);
+	if (IS_ERR(data->fan_base))
+		return PTR_ERR(data->fan_base);
+
+	data->fan_clk = devm_clk_get(dev, "fan");
+	if (IS_ERR(data->fan_clk)) {
+		dev_err(dev, "couldn't get fan clock\n");
+		return PTR_ERR(data->fan_clk);
+	}
+
+	output_freq = npcm7xx_pwm_init(data);
+	npcm7xx_fan_init(data);
+
+	for (cnt = 0; cnt < NPCM7XX_PWM_MAX_MODULES  ; cnt++)
+		mutex_init(&data->pwm_lock[cnt]);
+
+	for (i = 0; i < NPCM7XX_FAN_MAX_MODULE; i++) {
+		spin_lock_init(&data->fan_lock[i]);
+
+		data->fan_irq[i] = platform_get_irq(pdev, i);
+		if (data->fan_irq[i] < 0) {
+			dev_err(dev, "get IRQ fan%d failed\n", i);
+			return data->fan_irq[i];
+		}
+
+		sprintf(name, "NPCM7XX-FAN-MD%d", i);
+		ret = devm_request_irq(dev, data->fan_irq[i], npcm7xx_fan_isr,
+				       0, name, (void *)data);
+		if (ret) {
+			dev_err(dev, "register IRQ fan%d failed\n", i);
+			return ret;
+		}
+	}
+
+	for_each_child_of_node(np, child) {
+		ret = npcm7xx_en_pwm_fan(dev, child, data);
+		if (ret) {
+			dev_err(dev, "enable pwm and fan failed\n");
+			of_node_put(child);
+			return ret;
+		}
+	}
+
+	hwmon = devm_hwmon_device_register_with_info(dev, "npcm7xx_pwm_fan",
+						     data, &npcm7xx_chip_info,
+						     NULL);
+	if (IS_ERR(hwmon)) {
+		dev_err(dev, "unable to register hwmon device\n");
+		return PTR_ERR(hwmon);
+	}
+
+	for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM; i++) {
+		if (data->fan_present[i]) {
+			/* fan timer initialization */
+			data->fan_timer.expires = jiffies +
+				msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+			timer_setup(&data->fan_timer,
+				    npcm7xx_fan_polling, 0);
+			add_timer(&data->fan_timer);
+			break;
+		}
+	}
+
+	pr_info("NPCM7XX PWM-FAN Driver probed, output Freq %dHz[PWM], input Freq %dHz[FAN]\n",
+		output_freq, data->input_clk_freq);
+
+	return 0;
+}
+
+static const struct of_device_id of_pwm_fan_match_table[] = {
+	{ .compatible = "nuvoton,npcm750-pwm-fan", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_pwm_fan_match_table);
+
+static struct platform_driver npcm7xx_pwm_fan_driver = {
+	.probe		= npcm7xx_pwm_fan_probe,
+	.driver		= {
+		.name	= "npcm7xx_pwm_fan",
+		.of_match_table = of_pwm_fan_match_table,
+	},
+};
+
+module_platform_driver(npcm7xx_pwm_fan_driver);
+
+MODULE_DESCRIPTION("Nuvoton NPCM7XX PWM and Fan Tacho driver");
+MODULE_AUTHOR("Tomer Maimon <tomer.maimon@nuvoton.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index e71aec69e76e..a82018aaf473 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -130,7 +130,7 @@ config SENSORS_MAX34440
 	default n
 	help
 	  If you say yes here you get hardware monitoring support for Maxim
-	  MAX34440, MAX34441, MAX34446, MAX34460, and MAX34461.
+	  MAX34440, MAX34441, MAX34446, MAX34451, MAX34460, and MAX34461.
 
 	  This driver can also be built as a module. If so, the module will
 	  be called max34440.
diff --git a/drivers/hwmon/pmbus/max34440.c b/drivers/hwmon/pmbus/max34440.c
index 74a1f6f68fb3..47576c460010 100644
--- a/drivers/hwmon/pmbus/max34440.c
+++ b/drivers/hwmon/pmbus/max34440.c
@@ -27,7 +27,7 @@
 #include <linux/i2c.h>
 #include "pmbus.h"
 
-enum chips { max34440, max34441, max34446, max34460, max34461 };
+enum chips { max34440, max34441, max34446, max34451, max34460, max34461 };
 
 #define MAX34440_MFR_VOUT_PEAK		0xd4
 #define MAX34440_MFR_IOUT_PEAK		0xd5
@@ -44,6 +44,9 @@ enum chips { max34440, max34441, max34446, max34460, max34461 };
 #define MAX34440_STATUS_OT_FAULT	BIT(5)
 #define MAX34440_STATUS_OT_WARN		BIT(6)
 
+#define MAX34451_MFR_CHANNEL_CONFIG	0xe4
+#define MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK	0x3f
+
 struct max34440_data {
 	int id;
 	struct pmbus_driver_info info;
@@ -67,7 +70,7 @@ static int max34440_read_word_data(struct i2c_client *client, int page, int reg)
 					   MAX34440_MFR_VOUT_PEAK);
 		break;
 	case PMBUS_VIRT_READ_IOUT_AVG:
-		if (data->id != max34446)
+		if (data->id != max34446 && data->id != max34451)
 			return -ENXIO;
 		ret = pmbus_read_word_data(client, page,
 					   MAX34446_MFR_IOUT_AVG);
@@ -143,7 +146,7 @@ static int max34440_write_word_data(struct i2c_client *client, int page,
 	case PMBUS_VIRT_RESET_IOUT_HISTORY:
 		ret = pmbus_write_word_data(client, page,
 					    MAX34440_MFR_IOUT_PEAK, 0);
-		if (!ret && data->id == max34446)
+		if (!ret && (data->id == max34446 || data->id == max34451))
 			ret = pmbus_write_word_data(client, page,
 					MAX34446_MFR_IOUT_AVG, 0);
 
@@ -202,6 +205,58 @@ static int max34440_read_byte_data(struct i2c_client *client, int page, int reg)
 	return ret;
 }
 
+static int max34451_set_supported_funcs(struct i2c_client *client,
+					 struct max34440_data *data)
+{
+	/*
+	 * Each of the channel 0-15 can be configured to monitor the following
+	 * functions based on MFR_CHANNEL_CONFIG[5:0]
+	 * 0x10: Sequencing + voltage monitoring (only valid for PAGES 0–11)
+	 * 0x20: Voltage monitoring (no sequencing)
+	 * 0x21: Voltage read only
+	 * 0x22: Current monitoring
+	 * 0x23: Current read only
+	 * 0x30: General-purpose input active low
+	 * 0x34: General-purpose input active high
+	 * 0x00:  Disabled
+	 */
+
+	int page, rv;
+
+	for (page = 0; page < 16; page++) {
+		rv = i2c_smbus_write_byte_data(client, PMBUS_PAGE, page);
+		if (rv < 0)
+			return rv;
+
+		rv = i2c_smbus_read_word_data(client,
+					      MAX34451_MFR_CHANNEL_CONFIG);
+		if (rv < 0)
+			return rv;
+
+		switch (rv & MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK) {
+		case 0x10:
+		case 0x20:
+			data->info.func[page] = PMBUS_HAVE_VOUT |
+				PMBUS_HAVE_STATUS_VOUT;
+			break;
+		case 0x21:
+			data->info.func[page] = PMBUS_HAVE_VOUT;
+			break;
+		case 0x22:
+			data->info.func[page] = PMBUS_HAVE_IOUT |
+				PMBUS_HAVE_STATUS_IOUT;
+			break;
+		case 0x23:
+			data->info.func[page] = PMBUS_HAVE_IOUT;
+			break;
+		default:
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static struct pmbus_driver_info max34440_info[] = {
 	[max34440] = {
 		.pages = 14,
@@ -325,6 +380,30 @@ static struct pmbus_driver_info max34440_info[] = {
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
 	},
+	[max34451] = {
+		.pages = 21,
+		.format[PSC_VOLTAGE_OUT] = direct,
+		.format[PSC_TEMPERATURE] = direct,
+		.format[PSC_CURRENT_OUT] = direct,
+		.m[PSC_VOLTAGE_OUT] = 1,
+		.b[PSC_VOLTAGE_OUT] = 0,
+		.R[PSC_VOLTAGE_OUT] = 3,
+		.m[PSC_CURRENT_OUT] = 1,
+		.b[PSC_CURRENT_OUT] = 0,
+		.R[PSC_CURRENT_OUT] = 2,
+		.m[PSC_TEMPERATURE] = 1,
+		.b[PSC_TEMPERATURE] = 0,
+		.R[PSC_TEMPERATURE] = 2,
+		/* func 0-15 is set dynamically before probing */
+		.func[16] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[17] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[19] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[20] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.read_byte_data = max34440_read_byte_data,
+		.read_word_data = max34440_read_word_data,
+		.write_word_data = max34440_write_word_data,
+	},
 	[max34460] = {
 		.pages = 18,
 		.format[PSC_VOLTAGE_OUT] = direct,
@@ -398,6 +477,7 @@ static int max34440_probe(struct i2c_client *client,
 			  const struct i2c_device_id *id)
 {
 	struct max34440_data *data;
+	int rv;
 
 	data = devm_kzalloc(&client->dev, sizeof(struct max34440_data),
 			    GFP_KERNEL);
@@ -406,6 +486,12 @@ static int max34440_probe(struct i2c_client *client,
 	data->id = id->driver_data;
 	data->info = max34440_info[id->driver_data];
 
+	if (data->id == max34451) {
+		rv = max34451_set_supported_funcs(client, data);
+		if (rv)
+			return rv;
+	}
+
 	return pmbus_do_probe(client, id, &data->info);
 }
 
@@ -413,6 +499,7 @@ static const struct i2c_device_id max34440_id[] = {
 	{"max34440", max34440},
 	{"max34441", max34441},
 	{"max34446", max34446},
+	{"max34451", max34451},
 	{"max34460", max34460},
 	{"max34461", max34461},
 	{}
diff --git a/drivers/i2c/busses/i2c-xlp9xx.c b/drivers/i2c/busses/i2c-xlp9xx.c
index 1f41a4f89c08..8a873975cf12 100644
--- a/drivers/i2c/busses/i2c-xlp9xx.c
+++ b/drivers/i2c/busses/i2c-xlp9xx.c
@@ -191,28 +191,43 @@ static void xlp9xx_i2c_drain_rx_fifo(struct xlp9xx_i2c_dev *priv)
 	if (priv->len_recv) {
 		/* read length byte */
 		rlen = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO);
+
+		/*
+		 * We expect at least 2 interrupts for I2C_M_RECV_LEN
+		 * transactions. The length is updated during the first
+		 * interrupt, and the buffer contents are only copied
+		 * during subsequent interrupts. If in case the interrupts
+		 * get merged we would complete the transaction without
+		 * copying out the bytes from RX fifo. To avoid this now we
+		 * drain the fifo as and when data is available.
+		 * We drained the rlen byte already, decrement total length
+		 * by one.
+		 */
+
+		len--;
 		if (rlen > I2C_SMBUS_BLOCK_MAX || rlen == 0) {
 			rlen = 0;	/*abort transfer */
 			priv->msg_buf_remaining = 0;
 			priv->msg_len = 0;
-		} else {
-			*buf++ = rlen;
-			if (priv->client_pec)
-				++rlen; /* account for error check byte */
-			/* update remaining bytes and message length */
-			priv->msg_buf_remaining = rlen;
-			priv->msg_len = rlen + 1;
+			xlp9xx_i2c_update_rlen(priv);
+			return;
 		}
+
+		*buf++ = rlen;
+		if (priv->client_pec)
+			++rlen; /* account for error check byte */
+		/* update remaining bytes and message length */
+		priv->msg_buf_remaining = rlen;
+		priv->msg_len = rlen + 1;
 		xlp9xx_i2c_update_rlen(priv);
 		priv->len_recv = false;
-	} else {
-		len = min(priv->msg_buf_remaining, len);
-		for (i = 0; i < len; i++, buf++)
-			*buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO);
-
-		priv->msg_buf_remaining -= len;
 	}
 
+	len = min(priv->msg_buf_remaining, len);
+	for (i = 0; i < len; i++, buf++)
+		*buf = xlp9xx_read_i2c_reg(priv, XLP9XX_I2C_MRXFIFO);
+
+	priv->msg_buf_remaining -= len;
 	priv->msg_buf = buf;
 
 	if (priv->msg_buf_remaining)
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 5f178384876f..44a7a255ef74 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -419,10 +419,11 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd)
 
 int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		    int write, void *buffer, unsigned *bufflen,
-		    struct request_sense *sense, int timeout,
+		    struct scsi_sense_hdr *sshdr, int timeout,
 		    req_flags_t rq_flags)
 {
 	struct cdrom_info *info = drive->driver_data;
+	struct scsi_sense_hdr local_sshdr;
 	int retries = 10;
 	bool failed;
 
@@ -430,6 +431,9 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 				  "rq_flags: 0x%x",
 				  cmd[0], write, timeout, rq_flags);
 
+	if (!sshdr)
+		sshdr = &local_sshdr;
+
 	/* start of retry loop */
 	do {
 		struct request *rq;
@@ -456,8 +460,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 
 		if (buffer)
 			*bufflen = scsi_req(rq)->resid_len;
-		if (sense)
-			memcpy(sense, scsi_req(rq)->sense, sizeof(*sense));
+		scsi_normalize_sense(scsi_req(rq)->sense,
+				     scsi_req(rq)->sense_len, sshdr);
 
 		/*
 		 * FIXME: we should probably abort/retry or something in case of
@@ -469,12 +473,10 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 			 * The request failed.  Retry if it was due to a unit
 			 * attention status (usually means media was changed).
 			 */
-			struct request_sense *reqbuf = scsi_req(rq)->sense;
-
-			if (reqbuf->sense_key == UNIT_ATTENTION)
+			if (sshdr->sense_key == UNIT_ATTENTION)
 				cdrom_saw_media_change(drive);
-			else if (reqbuf->sense_key == NOT_READY &&
-				 reqbuf->asc == 4 && reqbuf->ascq != 4) {
+			else if (sshdr->sense_key == NOT_READY &&
+				 sshdr->asc == 4 && sshdr->ascq != 4) {
 				/*
 				 * The drive is in the process of loading
 				 * a disk.  Retry, but wait a little to give
@@ -864,7 +866,7 @@ static void msf_from_bcd(struct atapi_msf *msf)
 	msf->frame  = bcd2bin(msf->frame);
 }
 
-int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense)
+int cdrom_check_status(ide_drive_t *drive, struct scsi_sense_hdr *sshdr)
 {
 	struct cdrom_info *info = drive->driver_data;
 	struct cdrom_device_info *cdi;
@@ -886,12 +888,11 @@ int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense)
 	 */
 	cmd[7] = cdi->sanyo_slot % 3;
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, RQF_QUIET);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sshdr, 0, RQF_QUIET);
 }
 
 static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
-			       unsigned long *sectors_per_frame,
-			       struct request_sense *sense)
+			       unsigned long *sectors_per_frame)
 {
 	struct {
 		__be32 lba;
@@ -908,7 +909,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 	memset(cmd, 0, BLK_MAX_CDB);
 	cmd[0] = GPCMD_READ_CDVD_CAPACITY;
 
-	stat = ide_cd_queue_pc(drive, cmd, 0, &capbuf, &len, sense, 0,
+	stat = ide_cd_queue_pc(drive, cmd, 0, &capbuf, &len, NULL, 0,
 			       RQF_QUIET);
 	if (stat)
 		return stat;
@@ -944,8 +945,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 }
 
 static int cdrom_read_tocentry(ide_drive_t *drive, int trackno, int msf_flag,
-				int format, char *buf, int buflen,
-				struct request_sense *sense)
+				int format, char *buf, int buflen)
 {
 	unsigned char cmd[BLK_MAX_CDB];
 
@@ -962,11 +962,11 @@ static int cdrom_read_tocentry(ide_drive_t *drive, int trackno, int msf_flag,
 	if (msf_flag)
 		cmd[1] = 2;
 
-	return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, sense, 0, RQF_QUIET);
+	return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, NULL, 0, RQF_QUIET);
 }
 
 /* Try to read the entire TOC for the disk into our internal buffer. */
-int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
+int ide_cd_read_toc(ide_drive_t *drive)
 {
 	int stat, ntracks, i;
 	struct cdrom_info *info = drive->driver_data;
@@ -996,14 +996,13 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	 * Check to see if the existing data is still valid. If it is,
 	 * just return.
 	 */
-	(void) cdrom_check_status(drive, sense);
+	(void) cdrom_check_status(drive, NULL);
 
 	if (drive->atapi_flags & IDE_AFLAG_TOC_VALID)
 		return 0;
 
 	/* try to get the total cdrom capacity and sector size */
-	stat = cdrom_read_capacity(drive, &toc->capacity, &sectors_per_frame,
-				   sense);
+	stat = cdrom_read_capacity(drive, &toc->capacity, &sectors_per_frame);
 	if (stat)
 		toc->capacity = 0x1fffff;
 
@@ -1016,7 +1015,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 
 	/* first read just the header, so we know how long the TOC is */
 	stat = cdrom_read_tocentry(drive, 0, 1, 0, (char *) &toc->hdr,
-				    sizeof(struct atapi_toc_header), sense);
+				    sizeof(struct atapi_toc_header));
 	if (stat)
 		return stat;
 
@@ -1036,7 +1035,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 				  (char *)&toc->hdr,
 				   sizeof(struct atapi_toc_header) +
 				   (ntracks + 1) *
-				   sizeof(struct atapi_toc_entry), sense);
+				   sizeof(struct atapi_toc_entry));
 
 	if (stat && toc->hdr.first_track > 1) {
 		/*
@@ -1056,8 +1055,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 					   (char *)&toc->hdr,
 					   sizeof(struct atapi_toc_header) +
 					   (ntracks + 1) *
-					   sizeof(struct atapi_toc_entry),
-					   sense);
+					   sizeof(struct atapi_toc_entry));
 		if (stat)
 			return stat;
 
@@ -1094,7 +1092,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	if (toc->hdr.first_track != CDROM_LEADOUT) {
 		/* read the multisession information */
 		stat = cdrom_read_tocentry(drive, 0, 0, 1, (char *)&ms_tmp,
-					   sizeof(ms_tmp), sense);
+					   sizeof(ms_tmp));
 		if (stat)
 			return stat;
 
@@ -1108,7 +1106,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	if (drive->atapi_flags & IDE_AFLAG_TOCADDR_AS_BCD) {
 		/* re-read multisession information using MSF format */
 		stat = cdrom_read_tocentry(drive, 0, 1, 1, (char *)&ms_tmp,
-					   sizeof(ms_tmp), sense);
+					   sizeof(ms_tmp));
 		if (stat)
 			return stat;
 
@@ -1412,7 +1410,7 @@ static sector_t ide_cdrom_capacity(ide_drive_t *drive)
 {
 	unsigned long capacity, sectors_per_frame;
 
-	if (cdrom_read_capacity(drive, &capacity, &sectors_per_frame, NULL))
+	if (cdrom_read_capacity(drive, &capacity, &sectors_per_frame))
 		return 0;
 
 	return capacity * sectors_per_frame;
@@ -1710,9 +1708,8 @@ static unsigned int idecd_check_events(struct gendisk *disk,
 static int idecd_revalidate_disk(struct gendisk *disk)
 {
 	struct cdrom_info *info = ide_drv_g(disk, cdrom_info);
-	struct request_sense sense;
 
-	ide_cd_read_toc(info->drive, &sense);
+	ide_cd_read_toc(info->drive);
 
 	return  0;
 }
@@ -1736,7 +1733,6 @@ static int ide_cd_probe(ide_drive_t *drive)
 {
 	struct cdrom_info *info;
 	struct gendisk *g;
-	struct request_sense sense;
 
 	ide_debug_log(IDE_DBG_PROBE, "driver_req: %s, media: 0x%x",
 				     drive->driver_req, drive->media);
@@ -1785,7 +1781,7 @@ static int ide_cd_probe(ide_drive_t *drive)
 		goto failed;
 	}
 
-	ide_cd_read_toc(drive, &sense);
+	ide_cd_read_toc(drive);
 	g->fops = &idecd_ops;
 	g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
 	device_add_disk(&drive->gendev, g);
diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h
index 04f0f310a856..a69dc7f61c4d 100644
--- a/drivers/ide/ide-cd.h
+++ b/drivers/ide/ide-cd.h
@@ -98,11 +98,11 @@ void ide_cd_log_error(const char *, struct request *, struct request_sense *);
 
 /* ide-cd.c functions used by ide-cd_ioctl.c */
 int ide_cd_queue_pc(ide_drive_t *, const unsigned char *, int, void *,
-		    unsigned *, struct request_sense *, int, req_flags_t);
-int ide_cd_read_toc(ide_drive_t *, struct request_sense *);
+		    unsigned *, struct scsi_sense_hdr *, int, req_flags_t);
+int ide_cd_read_toc(ide_drive_t *);
 int ide_cdrom_get_capabilities(ide_drive_t *, u8 *);
 void ide_cdrom_update_speed(ide_drive_t *, u8 *);
-int cdrom_check_status(ide_drive_t *, struct request_sense *);
+int cdrom_check_status(ide_drive_t *, struct scsi_sense_hdr *);
 
 /* ide-cd_ioctl.c */
 int ide_cdrom_open_real(struct cdrom_device_info *, int);
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index b1322400887b..4a6e1a413ead 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -43,14 +43,14 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct media_event_desc med;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int stat;
 
 	if (slot_nr != CDSL_CURRENT)
 		return -EINVAL;
 
-	stat = cdrom_check_status(drive, &sense);
-	if (!stat || sense.sense_key == UNIT_ATTENTION)
+	stat = cdrom_check_status(drive, &sshdr);
+	if (!stat || sshdr.sense_key == UNIT_ATTENTION)
 		return CDS_DISC_OK;
 
 	if (!cdrom_get_media_event(cdi, &med)) {
@@ -62,8 +62,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 			return CDS_NO_DISC;
 	}
 
-	if (sense.sense_key == NOT_READY && sense.asc == 0x04
-			&& sense.ascq == 0x04)
+	if (sshdr.sense_key == NOT_READY && sshdr.asc == 0x04
+			&& sshdr.ascq == 0x04)
 		return CDS_DISC_OK;
 
 	/*
@@ -71,8 +71,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 	 * just return TRAY_OPEN since ATAPI doesn't provide
 	 * any other way to detect this...
 	 */
-	if (sense.sense_key == NOT_READY) {
-		if (sense.asc == 0x3a && sense.ascq == 1)
+	if (sshdr.sense_key == NOT_READY) {
+		if (sshdr.asc == 0x3a && sshdr.ascq == 1)
 			return CDS_NO_DISC;
 		else
 			return CDS_TRAY_OPEN;
@@ -105,8 +105,7 @@ unsigned int ide_cdrom_check_events_real(struct cdrom_device_info *cdi,
 /* Eject the disk if EJECTFLAG is 0.
    If EJECTFLAG is 1, try to reload the disk. */
 static
-int cdrom_eject(ide_drive_t *drive, int ejectflag,
-		struct request_sense *sense)
+int cdrom_eject(ide_drive_t *drive, int ejectflag)
 {
 	struct cdrom_info *cd = drive->driver_data;
 	struct cdrom_device_info *cdi = &cd->devinfo;
@@ -129,20 +128,16 @@ int cdrom_eject(ide_drive_t *drive, int ejectflag,
 	cmd[0] = GPCMD_START_STOP_UNIT;
 	cmd[4] = loej | (ejectflag != 0);
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, 0);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 }
 
 /* Lock the door if LOCKFLAG is nonzero; unlock it otherwise. */
 static
-int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
-		    struct request_sense *sense)
+int ide_cd_lockdoor(ide_drive_t *drive, int lockflag)
 {
-	struct request_sense my_sense;
+	struct scsi_sense_hdr sshdr;
 	int stat;
 
-	if (sense == NULL)
-		sense = &my_sense;
-
 	/* If the drive cannot lock the door, just pretend. */
 	if ((drive->dev_flags & IDE_DFLAG_DOORLOCKING) == 0) {
 		stat = 0;
@@ -155,14 +150,14 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 		cmd[4] = lockflag ? 1 : 0;
 
 		stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL,
-				       sense, 0, 0);
+				       &sshdr, 0, 0);
 	}
 
 	/* If we got an illegal field error, the drive
 	   probably cannot lock the door. */
 	if (stat != 0 &&
-	    sense->sense_key == ILLEGAL_REQUEST &&
-	    (sense->asc == 0x24 || sense->asc == 0x20)) {
+	    sshdr.sense_key == ILLEGAL_REQUEST &&
+	    (sshdr.asc == 0x24 || sshdr.asc == 0x20)) {
 		printk(KERN_ERR "%s: door locking not supported\n",
 			drive->name);
 		drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING;
@@ -170,7 +165,7 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 	}
 
 	/* no medium, that's alright. */
-	if (stat != 0 && sense->sense_key == NOT_READY && sense->asc == 0x3a)
+	if (stat != 0 && sshdr.sense_key == NOT_READY && sshdr.asc == 0x3a)
 		stat = 0;
 
 	if (stat == 0) {
@@ -186,23 +181,22 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 int ide_cdrom_tray_move(struct cdrom_device_info *cdi, int position)
 {
 	ide_drive_t *drive = cdi->handle;
-	struct request_sense sense;
 
 	if (position) {
-		int stat = ide_cd_lockdoor(drive, 0, &sense);
+		int stat = ide_cd_lockdoor(drive, 0);
 
 		if (stat)
 			return stat;
 	}
 
-	return cdrom_eject(drive, !position, &sense);
+	return cdrom_eject(drive, !position);
 }
 
 int ide_cdrom_lock_door(struct cdrom_device_info *cdi, int lock)
 {
 	ide_drive_t *drive = cdi->handle;
 
-	return ide_cd_lockdoor(drive, lock, NULL);
+	return ide_cd_lockdoor(drive, lock);
 }
 
 /*
@@ -213,7 +207,6 @@ int ide_cdrom_select_speed(struct cdrom_device_info *cdi, int speed)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *cd = drive->driver_data;
-	struct request_sense sense;
 	u8 buf[ATAPI_CAPABILITIES_PAGE_SIZE];
 	int stat;
 	unsigned char cmd[BLK_MAX_CDB];
@@ -236,7 +229,7 @@ int ide_cdrom_select_speed(struct cdrom_device_info *cdi, int speed)
 		cmd[5] = speed & 0xff;
 	}
 
-	stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, &sense, 0, 0);
+	stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 
 	if (!ide_cdrom_get_capabilities(drive, buf)) {
 		ide_cdrom_update_speed(drive, buf);
@@ -252,11 +245,10 @@ int ide_cdrom_get_last_session(struct cdrom_device_info *cdi,
 	struct atapi_toc *toc;
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *info = drive->driver_data;
-	struct request_sense sense;
 	int ret;
 
 	if ((drive->atapi_flags & IDE_AFLAG_TOC_VALID) == 0 || !info->toc) {
-		ret = ide_cd_read_toc(drive, &sense);
+		ret = ide_cd_read_toc(drive);
 		if (ret)
 			return ret;
 	}
@@ -300,7 +292,6 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *cd = drive->driver_data;
-	struct request_sense sense;
 	struct request *rq;
 	int ret;
 
@@ -315,7 +306,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	 * lock it again.
 	 */
 	if (drive->atapi_flags & IDE_AFLAG_DOOR_LOCKED)
-		(void)ide_cd_lockdoor(drive, 1, &sense);
+		(void)ide_cd_lockdoor(drive, 1);
 
 	return ret;
 }
@@ -355,7 +346,6 @@ static int ide_cd_fake_play_trkind(ide_drive_t *drive, void *arg)
 	struct atapi_toc_entry *first_toc, *last_toc;
 	unsigned long lba_start, lba_end;
 	int stat;
-	struct request_sense sense;
 	unsigned char cmd[BLK_MAX_CDB];
 
 	stat = ide_cd_get_toc_entry(drive, ti->cdti_trk0, &first_toc);
@@ -380,7 +370,7 @@ static int ide_cd_fake_play_trkind(ide_drive_t *drive, void *arg)
 	lba_to_msf(lba_start,   &cmd[3], &cmd[4], &cmd[5]);
 	lba_to_msf(lba_end - 1, &cmd[6], &cmd[7], &cmd[8]);
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, &sense, 0, 0);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 }
 
 static int ide_cd_read_tochdr(ide_drive_t *drive, void *arg)
@@ -391,7 +381,7 @@ static int ide_cd_read_tochdr(ide_drive_t *drive, void *arg)
 	int stat;
 
 	/* Make sure our saved TOC is valid. */
-	stat = ide_cd_read_toc(drive, NULL);
+	stat = ide_cd_read_toc(drive);
 	if (stat)
 		return stat;
 
@@ -461,8 +451,8 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi,
 	   layer. the packet must be complete, as we do not
 	   touch it at all. */
 
-	if (cgc->sense)
-		memset(cgc->sense, 0, sizeof(struct request_sense));
+	if (cgc->sshdr)
+		memset(cgc->sshdr, 0, sizeof(*cgc->sshdr));
 
 	if (cgc->quiet)
 		flags |= RQF_QUIET;
@@ -470,7 +460,7 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi,
 	cgc->stat = ide_cd_queue_pc(drive, cgc->cmd,
 				    cgc->data_direction == CGC_DATA_WRITE,
 				    cgc->buffer, &len,
-				    cgc->sense, cgc->timeout, flags);
+				    cgc->sshdr, cgc->timeout, flags);
 	if (!cgc->stat)
 		cgc->buflen -= len;
 	return cgc->stat;
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index a6e904973ba8..475910ffbcb6 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -121,7 +121,7 @@ static int uverbs_try_lock_object(struct ib_uobject *uobj, bool exclusive)
 	 * this lock.
 	 */
 	if (!exclusive)
-		return __atomic_add_unless(&uobj->usecnt, 1, -1) == -1 ?
+		return atomic_fetch_add_unless(&uobj->usecnt, 1, -1) == -1 ?
 			-EBUSY : 0;
 
 	/* lock is either WRITE or DESTROY - should be exclusive */
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index ca844a926e6a..130bf163f066 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -311,7 +311,7 @@ iser_set_dif_domain(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs,
 {
 	domain->sig_type = IB_SIG_TYPE_T10_DIF;
 	domain->sig.dif.pi_interval = scsi_prot_interval(sc);
-	domain->sig.dif.ref_tag = scsi_prot_ref_tag(sc);
+	domain->sig.dif.ref_tag = t10_pi_ref_tag(sc->request);
 	/*
 	 * At the moment we hard code those, but in the future
 	 * we will take them from sc.
diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c
index a4e404aaf64b..5c7afdec192c 100644
--- a/drivers/input/keyboard/hilkbd.c
+++ b/drivers/input/keyboard/hilkbd.c
@@ -57,8 +57,8 @@ MODULE_LICENSE("GPL v2");
  #define HIL_DATA		0x1
  #define HIL_CMD		0x3
  #define HIL_IRQ		2
- #define hil_readb(p)		readb(p)
- #define hil_writeb(v,p)	writeb((v),(p))
+ #define hil_readb(p)		readb((const volatile void __iomem *)(p))
+ #define hil_writeb(v, p)	writeb((v), (volatile void __iomem *)(p))
 
 #else
 #error "HIL is not supported on this platform"
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index ddcbbdb5d658..511ff9a1d6d9 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -367,6 +367,9 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
 		iova_len = roundup_pow_of_two(iova_len);
 
+	if (dev->bus_dma_mask)
+		dma_limit &= dev->bus_dma_mask;
+
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, domain->geometry.aperture_end);
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index e9233db16e03..d564d21245c5 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -8,7 +8,7 @@ config ARM_GIC
 	bool
 	select IRQ_DOMAIN
 	select IRQ_DOMAIN_HIERARCHY
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
 config ARM_GIC_PM
@@ -34,7 +34,7 @@ config GIC_NON_BANKED
 config ARM_GIC_V3
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select IRQ_DOMAIN_HIERARCHY
 	select PARTITION_PERCPU
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
@@ -66,7 +66,7 @@ config ARM_NVIC
 config ARM_VIC
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config ARM_VIC_NR
 	int
@@ -93,14 +93,14 @@ config ATMEL_AIC_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config ATMEL_AIC5_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config I8259
@@ -137,7 +137,7 @@ config DW_APB_ICTL
 config FARADAY_FTINTC010
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config HISILICON_IRQ_MBIGEN
@@ -162,7 +162,7 @@ config CLPS711X_IRQCHIP
 	bool
 	depends on ARCH_CLPS711X
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 	default y
 
@@ -181,7 +181,7 @@ config OMAP_IRQCHIP
 config ORION_IRQCHIP
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config PIC32_EVIC
 	bool
diff --git a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
index 4eca5c763766..606efa64adff 100644
--- a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
@@ -45,6 +45,9 @@ static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain,
 	 */
 	info->scratchpad[0].ul = mc_bus_dev->icid;
 	msi_info = msi_get_domain_info(msi_domain->parent);
+
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(msi_domain->parent, dev, nvec, info);
 }
 
diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
index 25a98de5cfb2..8d6d009d1d58 100644
--- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
@@ -66,7 +66,7 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 {
 	struct pci_dev *pdev, *alias_dev;
 	struct msi_domain_info *msi_info;
-	int alias_count = 0;
+	int alias_count = 0, minnvec = 1;
 
 	if (!dev_is_pci(dev))
 		return -EINVAL;
@@ -86,8 +86,18 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev);
 
-	return msi_info->ops->msi_prepare(domain->parent,
-					  dev, max(nvec, alias_count), info);
+	/*
+	 * Always allocate a power of 2, and special case device 0 for
+	 * broken systems where the DevID is not wired (and all devices
+	 * appear as DevID 0). For that reason, we generously allocate a
+	 * minimum of 32 MSIs for DevID 0. If you want more because all
+	 * your devices are aliasing to DevID 0, consider fixing your HW.
+	 */
+	nvec = max(nvec, alias_count);
+	if (!info->scratchpad[0].ul)
+		minnvec = 32;
+	nvec = max_t(int, minnvec, roundup_pow_of_two(nvec));
+	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
 }
 
 static struct msi_domain_ops its_pci_msi_ops = {
diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
index 8881a053c173..7b8e87b493fe 100644
--- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
@@ -73,6 +73,8 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = dev_id;
 
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(domain->parent,
 					  dev, nvec, info);
 }
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d7842d312d3e..316a57530f6d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -23,6 +23,8 @@
 #include <linux/dma-iommu.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
+#include <linux/list.h>
+#include <linux/list_sort.h>
 #include <linux/log2.h>
 #include <linux/mm.h>
 #include <linux/msi.h>
@@ -160,7 +162,7 @@ static struct {
 } vpe_proxy;
 
 static LIST_HEAD(its_nodes);
-static DEFINE_SPINLOCK(its_lock);
+static DEFINE_RAW_SPINLOCK(its_lock);
 static struct rdists *gic_rdists;
 static struct irq_domain *its_parent;
 
@@ -1421,112 +1423,176 @@ static struct irq_chip its_irq_chip = {
 	.irq_set_vcpu_affinity	= its_irq_set_vcpu_affinity,
 };
 
+
 /*
  * How we allocate LPIs:
  *
- * The GIC has id_bits bits for interrupt identifiers. From there, we
- * must subtract 8192 which are reserved for SGIs/PPIs/SPIs. Then, as
- * we allocate LPIs by chunks of 32, we can shift the whole thing by 5
- * bits to the right.
+ * lpi_range_list contains ranges of LPIs that are to available to
+ * allocate from. To allocate LPIs, just pick the first range that
+ * fits the required allocation, and reduce it by the required
+ * amount. Once empty, remove the range from the list.
+ *
+ * To free a range of LPIs, add a free range to the list, sort it and
+ * merge the result if the new range happens to be adjacent to an
+ * already free block.
  *
- * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations.
+ * The consequence of the above is that allocation is cost is low, but
+ * freeing is expensive. We assumes that freeing rarely occurs.
  */
-#define IRQS_PER_CHUNK_SHIFT	5
-#define IRQS_PER_CHUNK		(1UL << IRQS_PER_CHUNK_SHIFT)
-#define ITS_MAX_LPI_NRBITS	16 /* 64K LPIs */
 
-static unsigned long *lpi_bitmap;
-static u32 lpi_chunks;
-static DEFINE_SPINLOCK(lpi_lock);
+static DEFINE_MUTEX(lpi_range_lock);
+static LIST_HEAD(lpi_range_list);
+
+struct lpi_range {
+	struct list_head	entry;
+	u32			base_id;
+	u32			span;
+};
 
-static int its_lpi_to_chunk(int lpi)
+static struct lpi_range *mk_lpi_range(u32 base, u32 span)
 {
-	return (lpi - 8192) >> IRQS_PER_CHUNK_SHIFT;
+	struct lpi_range *range;
+
+	range = kzalloc(sizeof(*range), GFP_KERNEL);
+	if (range) {
+		INIT_LIST_HEAD(&range->entry);
+		range->base_id = base;
+		range->span = span;
+	}
+
+	return range;
 }
 
-static int its_chunk_to_lpi(int chunk)
+static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
-	return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192;
+	struct lpi_range *ra, *rb;
+
+	ra = container_of(a, struct lpi_range, entry);
+	rb = container_of(b, struct lpi_range, entry);
+
+	return rb->base_id - ra->base_id;
 }
 
-static int __init its_lpi_init(u32 id_bits)
+static void merge_lpi_ranges(void)
 {
-	lpi_chunks = its_lpi_to_chunk(1UL << id_bits);
+	struct lpi_range *range, *tmp;
 
-	lpi_bitmap = kcalloc(BITS_TO_LONGS(lpi_chunks), sizeof(long),
-			     GFP_KERNEL);
-	if (!lpi_bitmap) {
-		lpi_chunks = 0;
-		return -ENOMEM;
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (!list_is_last(&range->entry, &lpi_range_list) &&
+		    (tmp->base_id == (range->base_id + range->span))) {
+			tmp->base_id = range->base_id;
+			tmp->span += range->span;
+			list_del(&range->entry);
+			kfree(range);
+		}
 	}
+}
 
-	pr_info("ITS: Allocated %d chunks for LPIs\n", (int)lpi_chunks);
-	return 0;
+static int alloc_lpi_range(u32 nr_lpis, u32 *base)
+{
+	struct lpi_range *range, *tmp;
+	int err = -ENOSPC;
+
+	mutex_lock(&lpi_range_lock);
+
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (range->span >= nr_lpis) {
+			*base = range->base_id;
+			range->base_id += nr_lpis;
+			range->span -= nr_lpis;
+
+			if (range->span == 0) {
+				list_del(&range->entry);
+				kfree(range);
+			}
+
+			err = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&lpi_range_lock);
+
+	pr_debug("ITS: alloc %u:%u\n", *base, nr_lpis);
+	return err;
 }
 
-static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids)
+static int free_lpi_range(u32 base, u32 nr_lpis)
 {
-	unsigned long *bitmap = NULL;
-	int chunk_id;
-	int nr_chunks;
-	int i;
+	struct lpi_range *new;
+	int err = 0;
+
+	mutex_lock(&lpi_range_lock);
+
+	new = mk_lpi_range(base, nr_lpis);
+	if (!new) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	list_add(&new->entry, &lpi_range_list);
+	list_sort(NULL, &lpi_range_list, lpi_range_cmp);
+	merge_lpi_ranges();
+out:
+	mutex_unlock(&lpi_range_lock);
+	return err;
+}
+
+static int __init its_lpi_init(u32 id_bits)
+{
+	u32 lpis = (1UL << id_bits) - 8192;
+	u32 numlpis;
+	int err;
+
+	numlpis = 1UL << GICD_TYPER_NUM_LPIS(gic_rdists->gicd_typer);
+
+	if (numlpis > 2 && !WARN_ON(numlpis > lpis)) {
+		lpis = numlpis;
+		pr_info("ITS: Using hypervisor restricted LPI range [%u]\n",
+			lpis);
+	}
 
-	nr_chunks = DIV_ROUND_UP(nr_irqs, IRQS_PER_CHUNK);
+	/*
+	 * Initializing the allocator is just the same as freeing the
+	 * full range of LPIs.
+	 */
+	err = free_lpi_range(8192, lpis);
+	pr_debug("ITS: Allocator initialized for %u LPIs\n", lpis);
+	return err;
+}
 
-	spin_lock(&lpi_lock);
+static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids)
+{
+	unsigned long *bitmap = NULL;
+	int err = 0;
 
 	do {
-		chunk_id = bitmap_find_next_zero_area(lpi_bitmap, lpi_chunks,
-						      0, nr_chunks, 0);
-		if (chunk_id < lpi_chunks)
+		err = alloc_lpi_range(nr_irqs, base);
+		if (!err)
 			break;
 
-		nr_chunks--;
-	} while (nr_chunks > 0);
+		nr_irqs /= 2;
+	} while (nr_irqs > 0);
 
-	if (!nr_chunks)
+	if (err)
 		goto out;
 
-	bitmap = kcalloc(BITS_TO_LONGS(nr_chunks * IRQS_PER_CHUNK),
-			 sizeof(long),
-			 GFP_ATOMIC);
+	bitmap = kcalloc(BITS_TO_LONGS(nr_irqs), sizeof (long), GFP_ATOMIC);
 	if (!bitmap)
 		goto out;
 
-	for (i = 0; i < nr_chunks; i++)
-		set_bit(chunk_id + i, lpi_bitmap);
-
-	*base = its_chunk_to_lpi(chunk_id);
-	*nr_ids = nr_chunks * IRQS_PER_CHUNK;
+	*nr_ids = nr_irqs;
 
 out:
-	spin_unlock(&lpi_lock);
-
 	if (!bitmap)
 		*base = *nr_ids = 0;
 
 	return bitmap;
 }
 
-static void its_lpi_free_chunks(unsigned long *bitmap, int base, int nr_ids)
+static void its_lpi_free(unsigned long *bitmap, u32 base, u32 nr_ids)
 {
-	int lpi;
-
-	spin_lock(&lpi_lock);
-
-	for (lpi = base; lpi < (base + nr_ids); lpi += IRQS_PER_CHUNK) {
-		int chunk = its_lpi_to_chunk(lpi);
-
-		BUG_ON(chunk > lpi_chunks);
-		if (test_bit(chunk, lpi_bitmap)) {
-			clear_bit(chunk, lpi_bitmap);
-		} else {
-			pr_err("Bad LPI chunk %d\n", chunk);
-		}
-	}
-
-	spin_unlock(&lpi_lock);
-
+	WARN_ON(free_lpi_range(base, nr_ids));
 	kfree(bitmap);
 }
 
@@ -1559,7 +1625,7 @@ static int __init its_alloc_lpi_tables(void)
 {
 	phys_addr_t paddr;
 
-	lpi_id_bits = min_t(u32, gic_rdists->id_bits, ITS_MAX_LPI_NRBITS);
+	lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer);
 	gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT);
 	if (!gic_rdists->prop_page) {
 		pr_err("Failed to allocate PROPBASE\n");
@@ -1997,12 +2063,12 @@ static void its_cpu_init_collections(void)
 {
 	struct its_node *its;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 
 	list_for_each_entry(its, &its_nodes, entry)
 		its_cpu_init_collection(its);
 
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
@@ -2134,17 +2200,20 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	if (!its_alloc_device_table(its, dev_id))
 		return NULL;
 
+	if (WARN_ON(!is_power_of_2(nvecs)))
+		nvecs = roundup_pow_of_two(nvecs);
+
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	/*
-	 * We allocate at least one chunk worth of LPIs bet device,
-	 * and thus that many ITEs. The device may require less though.
+	 * Even if the device wants a single LPI, the ITT must be
+	 * sized as a power of two (and you need at least one bit...).
 	 */
-	nr_ites = max(IRQS_PER_CHUNK, roundup_pow_of_two(nvecs));
+	nr_ites = max(2, nvecs);
 	sz = nr_ites * its->ite_size;
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
 	itt = kzalloc(sz, GFP_KERNEL);
 	if (alloc_lpis) {
-		lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis);
+		lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
 		if (lpi_map)
 			col_map = kcalloc(nr_lpis, sizeof(*col_map),
 					  GFP_KERNEL);
@@ -2379,9 +2448,9 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 	/* If all interrupts have been freed, start mopping the floor */
 	if (bitmap_empty(its_dev->event_map.lpi_map,
 			 its_dev->event_map.nr_lpis)) {
-		its_lpi_free_chunks(its_dev->event_map.lpi_map,
-				    its_dev->event_map.lpi_base,
-				    its_dev->event_map.nr_lpis);
+		its_lpi_free(its_dev->event_map.lpi_map,
+			     its_dev->event_map.lpi_base,
+			     its_dev->event_map.nr_lpis);
 		kfree(its_dev->event_map.col_map);
 
 		/* Unmap device/itt */
@@ -2780,7 +2849,7 @@ static void its_vpe_irq_domain_free(struct irq_domain *domain,
 	}
 
 	if (bitmap_empty(vm->db_bitmap, vm->nr_db_lpis)) {
-		its_lpi_free_chunks(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
+		its_lpi_free(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
 		its_free_prop_table(vm->vprop_page);
 	}
 }
@@ -2795,18 +2864,18 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 
 	BUG_ON(!vm);
 
-	bitmap = its_lpi_alloc_chunks(nr_irqs, &base, &nr_ids);
+	bitmap = its_lpi_alloc(roundup_pow_of_two(nr_irqs), &base, &nr_ids);
 	if (!bitmap)
 		return -ENOMEM;
 
 	if (nr_ids < nr_irqs) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
 	vprop_page = its_allocate_prop_table(GFP_KERNEL);
 	if (!vprop_page) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
@@ -2833,7 +2902,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 		if (i > 0)
 			its_vpe_irq_domain_free(domain, virq, i - 1);
 
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		its_free_prop_table(vprop_page);
 	}
 
@@ -3070,7 +3139,7 @@ static int its_save_disable(void)
 	struct its_node *its;
 	int err = 0;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 
@@ -3102,7 +3171,7 @@ err:
 			writel_relaxed(its->ctlr_save, base + GITS_CTLR);
 		}
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return err;
 }
@@ -3112,7 +3181,7 @@ static void its_restore_enable(void)
 	struct its_node *its;
 	int ret;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 		int i;
@@ -3164,7 +3233,7 @@ static void its_restore_enable(void)
 		    GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER)))
 			its_cpu_init_collection(its);
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct syscore_ops its_syscore_ops = {
@@ -3398,9 +3467,9 @@ static int __init its_probe_one(struct resource *res,
 	if (err)
 		goto out_free_tables;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_add(&its->entry, &its_nodes);
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return 0;
 
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 76ea56d779a1..e214181b77b7 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -877,7 +877,7 @@ static struct irq_chip gic_eoimode1_chip = {
 	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
-#define GIC_ID_NR		(1U << gic_data.rdists.id_bits)
+#define GIC_ID_NR	(1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
 
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hw)
@@ -1091,7 +1091,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
 	 */
 	typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
-	gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
+	gic_data.rdists.gicd_typer = typer;
 	gic_irqs = GICD_TYPER_IRQS(typer);
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;
diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c
index fc5953dea509..2ff08986b536 100644
--- a/drivers/irqchip/irq-ingenic.c
+++ b/drivers/irqchip/irq-ingenic.c
@@ -165,6 +165,7 @@ static int __init intc_1chip_of_init(struct device_node *node,
 	return ingenic_intc_of_init(node, 1);
 }
 IRQCHIP_DECLARE(jz4740_intc, "ingenic,jz4740-intc", intc_1chip_of_init);
+IRQCHIP_DECLARE(jz4725b_intc, "ingenic,jz4725b-intc", intc_1chip_of_init);
 
 static int __init intc_2chip_of_init(struct device_node *node,
 	struct device_node *parent)
diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 3a7e8905a97e..3df527fcf4e1 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -159,6 +159,7 @@ static const struct stm32_exti_bank *stm32mp1_exti_banks[] = {
 };
 
 static const struct stm32_desc_irq stm32mp1_desc_irq[] = {
+	{ .exti = 0, .irq_parent = 6 },
 	{ .exti = 1, .irq_parent = 7 },
 	{ .exti = 2, .irq_parent = 8 },
 	{ .exti = 3, .irq_parent = 9 },
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 9c03f35d9df1..439bf90d084d 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -17,23 +17,25 @@ menuconfig NVM
 
 if NVM
 
-config NVM_DEBUG
-	bool "Open-Channel SSD debugging support"
-	default n
-	---help---
-	Exposes a debug management interface to create/remove targets at:
+config NVM_PBLK
+	tristate "Physical Block Device Open-Channel SSD target"
+	help
+	  Allows an open-channel SSD to be exposed as a block device to the
+	  host. The target assumes the device exposes raw flash and must be
+	  explicitly managed by the host.
 
-	  /sys/module/lnvm/parameters/configure_debug
+	  Please note the disk format is considered EXPERIMENTAL for now.
 
-	It is required to create/remove targets without IOCTLs.
+if NVM_PBLK
 
-config NVM_PBLK
-	tristate "Physical Block Device Open-Channel SSD target"
-	---help---
-	Allows an open-channel SSD to be exposed as a block device to the
-	host. The target assumes the device exposes raw flash and must be
-	explicitly managed by the host.
+config NVM_PBLK_DEBUG
+	bool "PBlk Debug Support"
+	default n
+	help
+	  Enables debug support for pblk. This includes extra checks, more
+	  vocal error messages, and extra tracking fields in the pblk sysfs
+	  entries.
 
-	Please note the disk format is considered EXPERIMENTAL for now.
+endif # NVM_PBLK_DEBUG
 
 endif # NVM
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
index b1c6d7eb6115..f565a56b898a 100644
--- a/drivers/lightnvm/pblk-cache.c
+++ b/drivers/lightnvm/pblk-cache.c
@@ -27,7 +27,8 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
 	int nr_entries = pblk_get_secs(bio);
 	int i, ret;
 
-	generic_start_io_acct(q, WRITE, bio_sectors(bio), &pblk->disk->part0);
+	generic_start_io_acct(q, REQ_OP_WRITE, bio_sectors(bio),
+			      &pblk->disk->part0);
 
 	/* Update the write buffer head (mem) with the entries that we can
 	 * write. The write in itself cannot fail, so there is no need to
@@ -67,7 +68,7 @@ retry:
 
 	atomic64_add(nr_entries, &pblk->user_wa);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(nr_entries, &pblk->inflight_writes);
 	atomic_long_add(nr_entries, &pblk->req_writes);
 #endif
@@ -75,7 +76,7 @@ retry:
 	pblk_rl_inserted(&pblk->rl, nr_entries);
 
 out:
-	generic_end_io_acct(q, WRITE, &pblk->disk->part0, start_time);
+	generic_end_io_acct(q, REQ_OP_WRITE, &pblk->disk->part0, start_time);
 	pblk_write_should_kick(pblk);
 	return ret;
 }
@@ -123,7 +124,7 @@ retry:
 
 	atomic64_add(valid_entries, &pblk->gc_wa);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(valid_entries, &pblk->inflight_writes);
 	atomic_long_add(valid_entries, &pblk->recov_gc_writes);
 #endif
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index ed9cc977c8b3..00984b486fea 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -35,7 +35,7 @@ static void pblk_line_mark_bb(struct work_struct *work)
 		line = &pblk->lines[pblk_ppa_to_line(*ppa)];
 		pos = pblk_ppa_to_pos(&dev->geo, *ppa);
 
-		pr_err("pblk: failed to mark bb, line:%d, pos:%d\n",
+		pblk_err(pblk, "failed to mark bb, line:%d, pos:%d\n",
 				line->id, pos);
 	}
 
@@ -51,12 +51,12 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
 	struct ppa_addr *ppa;
 	int pos = pblk_ppa_to_pos(geo, ppa_addr);
 
-	pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
+	pblk_debug(pblk, "erase failed: line:%d, pos:%d\n", line->id, pos);
 	atomic_long_inc(&pblk->erase_failed);
 
 	atomic_dec(&line->blk_in_line);
 	if (test_and_set_bit(pos, line->blk_bitmap))
-		pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
+		pblk_err(pblk, "attempted to erase bb: line:%d, pos:%d\n",
 							line->id, pos);
 
 	/* Not necessary to mark bad blocks on 2.0 spec. */
@@ -194,7 +194,7 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
 	u64 paddr;
 	int line_id;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a device address */
 	BUG_ON(pblk_addr_in_cache(ppa));
 	BUG_ON(pblk_ppa_empty(ppa));
@@ -264,6 +264,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 	switch (type) {
 	case PBLK_WRITE:
 		kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap);
+		/* fall through */
 	case PBLK_WRITE_INT:
 		pool = &pblk->w_rq_pool;
 		break;
@@ -274,7 +275,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 		pool = &pblk->e_rq_pool;
 		break;
 	default:
-		pr_err("pblk: trying to free unknown rqd type\n");
+		pblk_err(pblk, "trying to free unknown rqd type\n");
 		return;
 	}
 
@@ -310,7 +311,7 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
 
 		ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
 		if (ret != PBLK_EXPOSED_PAGE_SIZE) {
-			pr_err("pblk: could not add page to bio\n");
+			pblk_err(pblk, "could not add page to bio\n");
 			mempool_free(page, &pblk->page_bio_pool);
 			goto err;
 		}
@@ -410,7 +411,7 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
 		line->state = PBLK_LINESTATE_CORRUPT;
 		line->gc_group = PBLK_LINEGC_NONE;
 		move_list =  &l_mg->corrupt_list;
-		pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
+		pblk_err(pblk, "corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
 						line->id, vsc,
 						line->sec_in_line,
 						lm->high_thrs, lm->mid_thrs);
@@ -430,7 +431,7 @@ void pblk_discard(struct pblk *pblk, struct bio *bio)
 void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	atomic_long_inc(&pblk->write_failed);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pblk_print_failed_rqd(pblk, rqd, rqd->error);
 #endif
 }
@@ -452,9 +453,9 @@ void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
 		atomic_long_inc(&pblk->read_failed);
 		break;
 	default:
-		pr_err("pblk: unknown read error:%d\n", rqd->error);
+		pblk_err(pblk, "unknown read error:%d\n", rqd->error);
 	}
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pblk_print_failed_rqd(pblk, rqd, rqd->error);
 #endif
 }
@@ -470,7 +471,7 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
 
 	atomic_inc(&pblk->inflight_io);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (pblk_check_io(pblk, rqd))
 		return NVM_IO_ERR;
 #endif
@@ -484,7 +485,7 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
 
 	atomic_inc(&pblk->inflight_io);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (pblk_check_io(pblk, rqd))
 		return NVM_IO_ERR;
 #endif
@@ -517,7 +518,7 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 	for (i = 0; i < nr_secs; i++) {
 		page = vmalloc_to_page(kaddr);
 		if (!page) {
-			pr_err("pblk: could not map vmalloc bio\n");
+			pblk_err(pblk, "could not map vmalloc bio\n");
 			bio_put(bio);
 			bio = ERR_PTR(-ENOMEM);
 			goto out;
@@ -525,7 +526,7 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 
 		ret = bio_add_pc_page(dev->q, bio, page, PAGE_SIZE, 0);
 		if (ret != PAGE_SIZE) {
-			pr_err("pblk: could not add page to bio\n");
+			pblk_err(pblk, "could not add page to bio\n");
 			bio_put(bio);
 			bio = ERR_PTR(-ENOMEM);
 			goto out;
@@ -711,7 +712,7 @@ next_rq:
 			while (test_bit(pos, line->blk_bitmap)) {
 				paddr += min;
 				if (pblk_boundary_paddr_checks(pblk, paddr)) {
-					pr_err("pblk: corrupt emeta line:%d\n",
+					pblk_err(pblk, "corrupt emeta line:%d\n",
 								line->id);
 					bio_put(bio);
 					ret = -EINTR;
@@ -723,7 +724,7 @@ next_rq:
 			}
 
 			if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
-				pr_err("pblk: corrupt emeta line:%d\n",
+				pblk_err(pblk, "corrupt emeta line:%d\n",
 								line->id);
 				bio_put(bio);
 				ret = -EINTR;
@@ -738,7 +739,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, &rqd);
 	if (ret) {
-		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		goto free_rqd_dma;
 	}
@@ -843,7 +844,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	 */
 	ret = pblk_submit_io_sync(pblk, &rqd);
 	if (ret) {
-		pr_err("pblk: smeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "smeta I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		goto free_ppa_list;
 	}
@@ -905,7 +906,7 @@ static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_tgt_dev *dev = pblk->dev;
 		struct nvm_geo *geo = &dev->geo;
 
-		pr_err("pblk: could not sync erase line:%d,blk:%d\n",
+		pblk_err(pblk, "could not sync erase line:%d,blk:%d\n",
 					pblk_ppa_to_line(ppa),
 					pblk_ppa_to_pos(geo, ppa));
 
@@ -945,7 +946,7 @@ int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
 
 		ret = pblk_blk_erase_sync(pblk, ppa);
 		if (ret) {
-			pr_err("pblk: failed to erase line %d\n", line->id);
+			pblk_err(pblk, "failed to erase line %d\n", line->id);
 			return ret;
 		}
 	} while (1);
@@ -1012,7 +1013,7 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
 		list_add_tail(&line->list, &l_mg->bad_list);
 		spin_unlock(&l_mg->free_lock);
 
-		pr_debug("pblk: line %d is bad\n", line->id);
+		pblk_debug(pblk, "line %d is bad\n", line->id);
 
 		return 0;
 	}
@@ -1122,7 +1123,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 	line->cur_sec = off + lm->smeta_sec;
 
 	if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) {
-		pr_debug("pblk: line smeta I/O failed. Retry\n");
+		pblk_debug(pblk, "line smeta I/O failed. Retry\n");
 		return 0;
 	}
 
@@ -1154,7 +1155,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 		spin_unlock(&line->lock);
 
 		list_add_tail(&line->list, &l_mg->bad_list);
-		pr_err("pblk: unexpected line %d is bad\n", line->id);
+		pblk_err(pblk, "unexpected line %d is bad\n", line->id);
 
 		return 0;
 	}
@@ -1299,7 +1300,7 @@ struct pblk_line *pblk_line_get(struct pblk *pblk)
 
 retry:
 	if (list_empty(&l_mg->free_list)) {
-		pr_err("pblk: no free lines\n");
+		pblk_err(pblk, "no free lines\n");
 		return NULL;
 	}
 
@@ -1315,7 +1316,7 @@ retry:
 
 		list_add_tail(&line->list, &l_mg->bad_list);
 
-		pr_debug("pblk: line %d is bad\n", line->id);
+		pblk_debug(pblk, "line %d is bad\n", line->id);
 		goto retry;
 	}
 
@@ -1329,7 +1330,7 @@ retry:
 			list_add(&line->list, &l_mg->corrupt_list);
 			goto retry;
 		default:
-			pr_err("pblk: failed to prepare line %d\n", line->id);
+			pblk_err(pblk, "failed to prepare line %d\n", line->id);
 			list_add(&line->list, &l_mg->free_list);
 			l_mg->nr_free_lines++;
 			return NULL;
@@ -1477,7 +1478,7 @@ static void pblk_line_close_meta_sync(struct pblk *pblk)
 
 			ret = pblk_submit_meta_io(pblk, line);
 			if (ret) {
-				pr_err("pblk: sync meta line %d failed (%d)\n",
+				pblk_err(pblk, "sync meta line %d failed (%d)\n",
 							line->id, ret);
 				return;
 			}
@@ -1507,7 +1508,7 @@ void __pblk_pipeline_flush(struct pblk *pblk)
 
 	ret = pblk_recov_pad(pblk);
 	if (ret) {
-		pr_err("pblk: could not close data on teardown(%d)\n", ret);
+		pblk_err(pblk, "could not close data on teardown(%d)\n", ret);
 		return;
 	}
 
@@ -1687,7 +1688,7 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_tgt_dev *dev = pblk->dev;
 		struct nvm_geo *geo = &dev->geo;
 
-		pr_err("pblk: could not async erase line:%d,blk:%d\n",
+		pblk_err(pblk, "could not async erase line:%d,blk:%d\n",
 					pblk_ppa_to_line(ppa),
 					pblk_ppa_to_pos(geo, ppa));
 	}
@@ -1726,7 +1727,7 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
 	struct list_head *move_list;
 	int i;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN(!bitmap_full(line->map_bitmap, lm->sec_per_line),
 				"pblk: corrupt closed line %d\n", line->id);
 #endif
@@ -1856,7 +1857,7 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list,
 	 * Only send one inflight I/O per LUN. Since we map at a page
 	 * granurality, all ppas in the I/O will map to the same LUN
 	 */
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	int i;
 
 	for (i = 1; i < nr_ppas; i++)
@@ -1866,7 +1867,8 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list,
 
 	ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(30000));
 	if (ret == -ETIME || ret == -EINTR)
-		pr_err("pblk: taking lun semaphore timed out: err %d\n", -ret);
+		pblk_err(pblk, "taking lun semaphore timed out: err %d\n",
+				-ret);
 }
 
 void pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas)
@@ -1901,7 +1903,7 @@ void pblk_up_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas)
 	struct pblk_lun *rlun;
 	int pos = pblk_ppa_to_pos(geo, ppa_list[0]);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	int i;
 
 	for (i = 1; i < nr_ppas; i++)
@@ -1951,7 +1953,7 @@ void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
 void pblk_update_map_cache(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
 {
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(!pblk_addr_in_cache(ppa));
 	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
@@ -1966,7 +1968,7 @@ int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa_new,
 	struct ppa_addr ppa_l2p, ppa_gc;
 	int ret = 1;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(!pblk_addr_in_cache(ppa_new));
 	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa_new)));
@@ -2003,14 +2005,14 @@ void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
 {
 	struct ppa_addr ppa_l2p;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a device address */
 	BUG_ON(pblk_addr_in_cache(ppa_mapped));
 #endif
 	/* Invalidate and discard padded entries */
 	if (lba == ADDR_EMPTY) {
 		atomic64_inc(&pblk->pad_wa);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		atomic_long_inc(&pblk->padded_wb);
 #endif
 		if (!pblk_ppa_empty(ppa_mapped))
@@ -2036,7 +2038,7 @@ void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
 		goto out;
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN_ON(!pblk_addr_in_cache(ppa_l2p) && !pblk_ppa_empty(ppa_l2p));
 #endif
 
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 080469d90b40..157c2567c9e8 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -90,7 +90,7 @@ static void pblk_gc_line_ws(struct work_struct *work)
 
 	gc_rq->data = vmalloc(array_size(gc_rq->nr_secs, geo->csecs));
 	if (!gc_rq->data) {
-		pr_err("pblk: could not GC line:%d (%d/%d)\n",
+		pblk_err(pblk, "could not GC line:%d (%d/%d)\n",
 					line->id, *line->vsc, gc_rq->nr_secs);
 		goto out;
 	}
@@ -98,7 +98,7 @@ static void pblk_gc_line_ws(struct work_struct *work)
 	/* Read from GC victim block */
 	ret = pblk_submit_read_gc(pblk, gc_rq);
 	if (ret) {
-		pr_err("pblk: failed GC read in line:%d (err:%d)\n",
+		pblk_err(pblk, "failed GC read in line:%d (err:%d)\n",
 								line->id, ret);
 		goto out;
 	}
@@ -146,7 +146,7 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
 
 	ret = pblk_line_read_emeta(pblk, line, emeta_buf);
 	if (ret) {
-		pr_err("pblk: line %d read emeta failed (%d)\n",
+		pblk_err(pblk, "line %d read emeta failed (%d)\n",
 				line->id, ret);
 		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 		return NULL;
@@ -160,7 +160,7 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
 
 	ret = pblk_recov_check_emeta(pblk, emeta_buf);
 	if (ret) {
-		pr_err("pblk: inconsistent emeta (line %d)\n",
+		pblk_err(pblk, "inconsistent emeta (line %d)\n",
 				line->id);
 		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 		return NULL;
@@ -201,7 +201,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	} else {
 		lba_list = get_lba_list_from_emeta(pblk, line);
 		if (!lba_list) {
-			pr_err("pblk: could not interpret emeta (line %d)\n",
+			pblk_err(pblk, "could not interpret emeta (line %d)\n",
 					line->id);
 			goto fail_free_invalid_bitmap;
 		}
@@ -213,7 +213,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	spin_unlock(&line->lock);
 
 	if (sec_left < 0) {
-		pr_err("pblk: corrupted GC line (%d)\n", line->id);
+		pblk_err(pblk, "corrupted GC line (%d)\n", line->id);
 		goto fail_free_lba_list;
 	}
 
@@ -289,7 +289,7 @@ fail_free_ws:
 	kref_put(&line->ref, pblk_line_put);
 	atomic_dec(&gc->read_inflight_gc);
 
-	pr_err("pblk: Failed to GC line %d\n", line->id);
+	pblk_err(pblk, "failed to GC line %d\n", line->id);
 }
 
 static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
@@ -297,7 +297,7 @@ static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
 	struct pblk_gc *gc = &pblk->gc;
 	struct pblk_line_ws *line_ws;
 
-	pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
+	pblk_debug(pblk, "line '%d' being reclaimed for GC\n", line->id);
 
 	line_ws = kmalloc(sizeof(struct pblk_line_ws), GFP_KERNEL);
 	if (!line_ws)
@@ -351,7 +351,7 @@ static int pblk_gc_read(struct pblk *pblk)
 	pblk_gc_kick(pblk);
 
 	if (pblk_gc_line(pblk, line))
-		pr_err("pblk: failed to GC line %d\n", line->id);
+		pblk_err(pblk, "failed to GC line %d\n", line->id);
 
 	return 0;
 }
@@ -522,8 +522,8 @@ static int pblk_gc_reader_ts(void *data)
 		io_schedule();
 	}
 
-#ifdef CONFIG_NVM_DEBUG
-	pr_info("pblk: flushing gc pipeline, %d lines left\n",
+#ifdef CONFIG_NVM_PBLK_DEBUG
+	pblk_info(pblk, "flushing gc pipeline, %d lines left\n",
 		atomic_read(&gc->pipeline_gc));
 #endif
 
@@ -540,7 +540,7 @@ static int pblk_gc_reader_ts(void *data)
 static void pblk_gc_start(struct pblk *pblk)
 {
 	pblk->gc.gc_active = 1;
-	pr_debug("pblk: gc start\n");
+	pblk_debug(pblk, "gc start\n");
 }
 
 void pblk_gc_should_start(struct pblk *pblk)
@@ -605,14 +605,14 @@ int pblk_gc_init(struct pblk *pblk)
 
 	gc->gc_ts = kthread_create(pblk_gc_ts, pblk, "pblk-gc-ts");
 	if (IS_ERR(gc->gc_ts)) {
-		pr_err("pblk: could not allocate GC main kthread\n");
+		pblk_err(pblk, "could not allocate GC main kthread\n");
 		return PTR_ERR(gc->gc_ts);
 	}
 
 	gc->gc_writer_ts = kthread_create(pblk_gc_writer_ts, pblk,
 							"pblk-gc-writer-ts");
 	if (IS_ERR(gc->gc_writer_ts)) {
-		pr_err("pblk: could not allocate GC writer kthread\n");
+		pblk_err(pblk, "could not allocate GC writer kthread\n");
 		ret = PTR_ERR(gc->gc_writer_ts);
 		goto fail_free_main_kthread;
 	}
@@ -620,7 +620,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_reader_ts = kthread_create(pblk_gc_reader_ts, pblk,
 							"pblk-gc-reader-ts");
 	if (IS_ERR(gc->gc_reader_ts)) {
-		pr_err("pblk: could not allocate GC reader kthread\n");
+		pblk_err(pblk, "could not allocate GC reader kthread\n");
 		ret = PTR_ERR(gc->gc_reader_ts);
 		goto fail_free_writer_kthread;
 	}
@@ -641,7 +641,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_line_reader_wq = alloc_workqueue("pblk-gc-line-reader-wq",
 			WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_GC_MAX_READERS);
 	if (!gc->gc_line_reader_wq) {
-		pr_err("pblk: could not allocate GC line reader workqueue\n");
+		pblk_err(pblk, "could not allocate GC line reader workqueue\n");
 		ret = -ENOMEM;
 		goto fail_free_reader_kthread;
 	}
@@ -650,7 +650,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_reader_wq = alloc_workqueue("pblk-gc-line_wq",
 					WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
 	if (!gc->gc_reader_wq) {
-		pr_err("pblk: could not allocate GC reader workqueue\n");
+		pblk_err(pblk, "could not allocate GC reader workqueue\n");
 		ret = -ENOMEM;
 		goto fail_free_reader_line_wq;
 	}
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index b57f764d6a16..537e98f2b24a 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -91,7 +91,7 @@ static size_t pblk_trans_map_size(struct pblk *pblk)
 	return entry_size * pblk->rl.nr_secs;
 }
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static u32 pblk_l2p_crc(struct pblk *pblk)
 {
 	size_t map_size;
@@ -117,13 +117,13 @@ static int pblk_l2p_recover(struct pblk *pblk, bool factory_init)
 	} else {
 		line = pblk_recov_l2p(pblk);
 		if (IS_ERR(line)) {
-			pr_err("pblk: could not recover l2p table\n");
+			pblk_err(pblk, "could not recover l2p table\n");
 			return -EFAULT;
 		}
 	}
 
-#ifdef CONFIG_NVM_DEBUG
-	pr_info("pblk init: L2P CRC: %x\n", pblk_l2p_crc(pblk));
+#ifdef CONFIG_NVM_PBLK_DEBUG
+	pblk_info(pblk, "init: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
 	/* Free full lines directly as GC has not been started yet */
@@ -166,7 +166,7 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init)
 static void pblk_rwb_free(struct pblk *pblk)
 {
 	if (pblk_rb_tear_down_check(&pblk->rwb))
-		pr_err("pblk: write buffer error on tear down\n");
+		pblk_err(pblk, "write buffer error on tear down\n");
 
 	pblk_rb_data_free(&pblk->rwb);
 	vfree(pblk_rb_entries_ref(&pblk->rwb));
@@ -179,11 +179,14 @@ static int pblk_rwb_init(struct pblk *pblk)
 	struct pblk_rb_entry *entries;
 	unsigned long nr_entries, buffer_size;
 	unsigned int power_size, power_seg_sz;
+	int pgs_in_buffer;
 
-	if (write_buffer_size && (write_buffer_size > pblk->pgs_in_buffer))
+	pgs_in_buffer = max(geo->mw_cunits, geo->ws_opt) * geo->all_luns;
+
+	if (write_buffer_size && (write_buffer_size > pgs_in_buffer))
 		buffer_size = write_buffer_size;
 	else
-		buffer_size = pblk->pgs_in_buffer;
+		buffer_size = pgs_in_buffer;
 
 	nr_entries = pblk_rb_calculate_size(buffer_size);
 
@@ -200,7 +203,8 @@ static int pblk_rwb_init(struct pblk *pblk)
 /* Minimum pages needed within a lun */
 #define ADDR_POOL_SIZE 64
 
-static int pblk_set_addrf_12(struct nvm_geo *geo, struct nvm_addrf_12 *dst)
+static int pblk_set_addrf_12(struct pblk *pblk, struct nvm_geo *geo,
+			     struct nvm_addrf_12 *dst)
 {
 	struct nvm_addrf_12 *src = (struct nvm_addrf_12 *)&geo->addrf;
 	int power_len;
@@ -208,14 +212,14 @@ static int pblk_set_addrf_12(struct nvm_geo *geo, struct nvm_addrf_12 *dst)
 	/* Re-calculate channel and lun format to adapt to configuration */
 	power_len = get_count_order(geo->num_ch);
 	if (1 << power_len != geo->num_ch) {
-		pr_err("pblk: supports only power-of-two channel config.\n");
+		pblk_err(pblk, "supports only power-of-two channel config.\n");
 		return -EINVAL;
 	}
 	dst->ch_len = power_len;
 
 	power_len = get_count_order(geo->num_lun);
 	if (1 << power_len != geo->num_lun) {
-		pr_err("pblk: supports only power-of-two LUN config.\n");
+		pblk_err(pblk, "supports only power-of-two LUN config.\n");
 		return -EINVAL;
 	}
 	dst->lun_len = power_len;
@@ -282,18 +286,19 @@ static int pblk_set_addrf(struct pblk *pblk)
 	case NVM_OCSSD_SPEC_12:
 		div_u64_rem(geo->clba, pblk->min_write_pgs, &mod);
 		if (mod) {
-			pr_err("pblk: bad configuration of sectors/pages\n");
+			pblk_err(pblk, "bad configuration of sectors/pages\n");
 			return -EINVAL;
 		}
 
-		pblk->addrf_len = pblk_set_addrf_12(geo, (void *)&pblk->addrf);
+		pblk->addrf_len = pblk_set_addrf_12(pblk, geo,
+							(void *)&pblk->addrf);
 		break;
 	case NVM_OCSSD_SPEC_20:
 		pblk->addrf_len = pblk_set_addrf_20(geo, (void *)&pblk->addrf,
-								&pblk->uaddrf);
+							&pblk->uaddrf);
 		break;
 	default:
-		pr_err("pblk: OCSSD revision not supported (%d)\n",
+		pblk_err(pblk, "OCSSD revision not supported (%d)\n",
 								geo->version);
 		return -EINVAL;
 	}
@@ -366,15 +371,13 @@ static int pblk_core_init(struct pblk *pblk)
 	atomic64_set(&pblk->nr_flush, 0);
 	pblk->nr_flush_rst = 0;
 
-	pblk->pgs_in_buffer = geo->mw_cunits * geo->all_luns;
-
 	pblk->min_write_pgs = geo->ws_opt * (geo->csecs / PAGE_SIZE);
 	max_write_ppas = pblk->min_write_pgs * geo->all_luns;
 	pblk->max_write_pgs = min_t(int, max_write_ppas, NVM_MAX_VLBA);
 	pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
 
 	if (pblk->max_write_pgs > PBLK_MAX_REQ_ADDRS) {
-		pr_err("pblk: vector list too big(%u > %u)\n",
+		pblk_err(pblk, "vector list too big(%u > %u)\n",
 				pblk->max_write_pgs, PBLK_MAX_REQ_ADDRS);
 		return -EINVAL;
 	}
@@ -607,7 +610,7 @@ static int pblk_luns_init(struct pblk *pblk)
 
 	/* TODO: Implement unbalanced LUN support */
 	if (geo->num_lun < 0) {
-		pr_err("pblk: unbalanced LUN config.\n");
+		pblk_err(pblk, "unbalanced LUN config.\n");
 		return -EINVAL;
 	}
 
@@ -716,10 +719,11 @@ static int pblk_setup_line_meta_12(struct pblk *pblk, struct pblk_line *line,
 
 		/*
 		 * In 1.2 spec. chunk state is not persisted by the device. Thus
-		 * some of the values are reset each time pblk is instantiated.
+		 * some of the values are reset each time pblk is instantiated,
+		 * so we have to assume that the block is closed.
 		 */
 		if (lun_bb_meta[line->id] == NVM_BLK_T_FREE)
-			chunk->state =  NVM_CHK_ST_FREE;
+			chunk->state =  NVM_CHK_ST_CLOSED;
 		else
 			chunk->state = NVM_CHK_ST_OFFLINE;
 
@@ -1026,7 +1030,7 @@ add_emeta_page:
 					lm->emeta_sec[0], geo->clba);
 
 	if (lm->min_blk_line > lm->blk_per_line) {
-		pr_err("pblk: config. not supported. Min. LUN in line:%d\n",
+		pblk_err(pblk, "config. not supported. Min. LUN in line:%d\n",
 							lm->blk_per_line);
 		return -EINVAL;
 	}
@@ -1078,7 +1082,7 @@ static int pblk_lines_init(struct pblk *pblk)
 	}
 
 	if (!nr_free_chks) {
-		pr_err("pblk: too many bad blocks prevent for sane instance\n");
+		pblk_err(pblk, "too many bad blocks prevent for sane instance\n");
 		return -EINTR;
 	}
 
@@ -1108,7 +1112,7 @@ static int pblk_writer_init(struct pblk *pblk)
 		int err = PTR_ERR(pblk->writer_ts);
 
 		if (err != -EINTR)
-			pr_err("pblk: could not allocate writer kthread (%d)\n",
+			pblk_err(pblk, "could not allocate writer kthread (%d)\n",
 					err);
 		return err;
 	}
@@ -1154,7 +1158,7 @@ static void pblk_tear_down(struct pblk *pblk, bool graceful)
 	pblk_rb_sync_l2p(&pblk->rwb);
 	pblk_rl_free(&pblk->rl);
 
-	pr_debug("pblk: consistent tear down (graceful:%d)\n", graceful);
+	pblk_debug(pblk, "consistent tear down (graceful:%d)\n", graceful);
 }
 
 static void pblk_exit(void *private, bool graceful)
@@ -1165,8 +1169,8 @@ static void pblk_exit(void *private, bool graceful)
 	pblk_gc_exit(pblk, graceful);
 	pblk_tear_down(pblk, graceful);
 
-#ifdef CONFIG_NVM_DEBUG
-	pr_info("pblk exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
+#ifdef CONFIG_NVM_PBLK_DEBUG
+	pblk_info(pblk, "exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
 	pblk_free(pblk);
@@ -1189,34 +1193,35 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	struct pblk *pblk;
 	int ret;
 
-	/* pblk supports 1.2 and 2.0 versions */
+	pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
+	if (!pblk)
+		return ERR_PTR(-ENOMEM);
+
+	pblk->dev = dev;
+	pblk->disk = tdisk;
+	pblk->state = PBLK_STATE_RUNNING;
+	pblk->gc.gc_enabled = 0;
+
 	if (!(geo->version == NVM_OCSSD_SPEC_12 ||
 					geo->version == NVM_OCSSD_SPEC_20)) {
-		pr_err("pblk: OCSSD version not supported (%u)\n",
+		pblk_err(pblk, "OCSSD version not supported (%u)\n",
 							geo->version);
+		kfree(pblk);
 		return ERR_PTR(-EINVAL);
 	}
 
 	if (geo->version == NVM_OCSSD_SPEC_12 && geo->dom & NVM_RSP_L2P) {
-		pr_err("pblk: host-side L2P table not supported. (%x)\n",
+		pblk_err(pblk, "host-side L2P table not supported. (%x)\n",
 							geo->dom);
+		kfree(pblk);
 		return ERR_PTR(-EINVAL);
 	}
 
-	pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
-	if (!pblk)
-		return ERR_PTR(-ENOMEM);
-
-	pblk->dev = dev;
-	pblk->disk = tdisk;
-	pblk->state = PBLK_STATE_RUNNING;
-	pblk->gc.gc_enabled = 0;
-
 	spin_lock_init(&pblk->resubmit_lock);
 	spin_lock_init(&pblk->trans_lock);
 	spin_lock_init(&pblk->lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_set(&pblk->inflight_writes, 0);
 	atomic_long_set(&pblk->padded_writes, 0);
 	atomic_long_set(&pblk->padded_wb, 0);
@@ -1241,38 +1246,38 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 
 	ret = pblk_core_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize core\n");
+		pblk_err(pblk, "could not initialize core\n");
 		goto fail;
 	}
 
 	ret = pblk_lines_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize lines\n");
+		pblk_err(pblk, "could not initialize lines\n");
 		goto fail_free_core;
 	}
 
 	ret = pblk_rwb_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize write buffer\n");
+		pblk_err(pblk, "could not initialize write buffer\n");
 		goto fail_free_lines;
 	}
 
 	ret = pblk_l2p_init(pblk, flags & NVM_TARGET_FACTORY);
 	if (ret) {
-		pr_err("pblk: could not initialize maps\n");
+		pblk_err(pblk, "could not initialize maps\n");
 		goto fail_free_rwb;
 	}
 
 	ret = pblk_writer_init(pblk);
 	if (ret) {
 		if (ret != -EINTR)
-			pr_err("pblk: could not initialize write thread\n");
+			pblk_err(pblk, "could not initialize write thread\n");
 		goto fail_free_l2p;
 	}
 
 	ret = pblk_gc_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize gc\n");
+		pblk_err(pblk, "could not initialize gc\n");
 		goto fail_stop_writer;
 	}
 
@@ -1287,8 +1292,7 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	blk_queue_max_discard_sectors(tqueue, UINT_MAX >> 9);
 	blk_queue_flag_set(QUEUE_FLAG_DISCARD, tqueue);
 
-	pr_info("pblk(%s): luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
-			tdisk->disk_name,
+	pblk_info(pblk, "luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
 			geo->all_luns, pblk->l_mg.nr_lines,
 			(unsigned long long)pblk->rl.nr_secs,
 			pblk->rwb.nr_entries);
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 55e9442a99e2..f6eec0212dfc 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -111,7 +111,7 @@ int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
 	} while (iter > 0);
 	up_write(&pblk_rb_lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_set(&rb->inflight_flush_point, 0);
 #endif
 
@@ -308,7 +308,7 @@ void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
 
 	entry = &rb->entries[ring_pos];
 	flags = READ_ONCE(entry->w_ctx.flags);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must guarantee that the entry is free */
 	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
 #endif
@@ -332,7 +332,7 @@ void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
 
 	entry = &rb->entries[ring_pos];
 	flags = READ_ONCE(entry->w_ctx.flags);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must guarantee that the entry is free */
 	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
 #endif
@@ -362,7 +362,7 @@ static int pblk_rb_flush_point_set(struct pblk_rb *rb, struct bio *bio,
 		return 0;
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_inc(&rb->inflight_flush_point);
 #endif
 
@@ -547,7 +547,7 @@ try:
 
 		page = virt_to_page(entry->data);
 		if (!page) {
-			pr_err("pblk: could not allocate write bio page\n");
+			pblk_err(pblk, "could not allocate write bio page\n");
 			flags &= ~PBLK_WRITTEN_DATA;
 			flags |= PBLK_SUBMITTED_ENTRY;
 			/* Release flags on context. Protect from writes */
@@ -557,7 +557,7 @@ try:
 
 		if (bio_add_pc_page(q, bio, page, rb->seg_size, 0) !=
 								rb->seg_size) {
-			pr_err("pblk: could not add page to write bio\n");
+			pblk_err(pblk, "could not add page to write bio\n");
 			flags &= ~PBLK_WRITTEN_DATA;
 			flags |= PBLK_SUBMITTED_ENTRY;
 			/* Release flags on context. Protect from writes */
@@ -576,19 +576,19 @@ try:
 
 	if (pad) {
 		if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, pad)) {
-			pr_err("pblk: could not pad page in write bio\n");
+			pblk_err(pblk, "could not pad page in write bio\n");
 			return NVM_IO_ERR;
 		}
 
 		if (pad < pblk->min_write_pgs)
 			atomic64_inc(&pblk->pad_dist[pad - 1]);
 		else
-			pr_warn("pblk: padding more than min. sectors\n");
+			pblk_warn(pblk, "padding more than min. sectors\n");
 
 		atomic64_add(pad, &pblk->pad_wa);
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(pad, &pblk->padded_writes);
 #endif
 
@@ -613,7 +613,7 @@ int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
 	int ret = 1;
 
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must ensure that the access will not cause an overflow */
 	BUG_ON(pos >= rb->nr_entries);
 #endif
@@ -820,7 +820,7 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
 			rb->subm,
 			rb->sync,
 			rb->l2p_update,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_read(&rb->inflight_flush_point),
 #else
 			0,
@@ -838,7 +838,7 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
 			rb->subm,
 			rb->sync,
 			rb->l2p_update,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_read(&rb->inflight_flush_point),
 #else
 			0,
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 18694694e5f0..5a46d7f9302f 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -28,7 +28,7 @@ static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
 				sector_t lba, struct ppa_addr ppa,
 				int bio_iter, bool advanced_bio)
 {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(pblk_ppa_empty(ppa));
 	BUG_ON(!pblk_addr_in_cache(ppa));
@@ -79,7 +79,7 @@ retry:
 			WARN_ON(test_and_set_bit(i, read_bitmap));
 			meta_list[i].lba = cpu_to_le64(lba);
 			advanced_bio = true;
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_long_inc(&pblk->cache_reads);
 #endif
 		} else {
@@ -97,7 +97,7 @@ next:
 	else
 		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(nr_secs, &pblk->inflight_reads);
 #endif
 }
@@ -117,13 +117,13 @@ static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
 			continue;
 
 		if (lba != blba + i) {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			struct ppa_addr *p;
 
 			p = (nr_lbas == 1) ? &rqd->ppa_list[i] : &rqd->ppa_addr;
-			print_ppa(&pblk->dev->geo, p, "seq", i);
+			print_ppa(pblk, p, "seq", i);
 #endif
-			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
 							lba, (u64)blba + i);
 			WARN_ON(1);
 		}
@@ -149,14 +149,14 @@ static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
 		meta_lba = le64_to_cpu(meta_lba_list[j].lba);
 
 		if (lba != meta_lba) {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			struct ppa_addr *p;
 			int nr_ppas = rqd->nr_ppas;
 
 			p = (nr_ppas == 1) ? &rqd->ppa_list[j] : &rqd->ppa_addr;
-			print_ppa(&pblk->dev->geo, p, "seq", j);
+			print_ppa(pblk, p, "seq", j);
 #endif
-			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
 								lba, meta_lba);
 			WARN_ON(1);
 		}
@@ -185,7 +185,7 @@ static void pblk_read_put_rqd_kref(struct pblk *pblk, struct nvm_rq *rqd)
 
 static void pblk_end_user_read(struct bio *bio)
 {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN_ONCE(bio->bi_status, "pblk: corrupted read bio\n");
 #endif
 	bio_endio(bio);
@@ -199,7 +199,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 	struct bio *int_bio = rqd->bio;
 	unsigned long start_time = r_ctx->start_time;
 
-	generic_end_io_acct(dev->q, READ, &pblk->disk->part0, start_time);
+	generic_end_io_acct(dev->q, REQ_OP_READ, &pblk->disk->part0, start_time);
 
 	if (rqd->error)
 		pblk_log_read_err(pblk, rqd);
@@ -212,7 +212,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 	if (put_line)
 		pblk_read_put_rqd_kref(pblk, rqd);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(rqd->nr_ppas, &pblk->sync_reads);
 	atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads);
 #endif
@@ -231,74 +231,36 @@ static void pblk_end_io_read(struct nvm_rq *rqd)
 	__pblk_end_io_read(pblk, rqd, true);
 }
 
-static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
-			     struct bio *orig_bio, unsigned int bio_init_idx,
-			     unsigned long *read_bitmap)
+static void pblk_end_partial_read(struct nvm_rq *rqd)
 {
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
-	struct bio *new_bio;
+	struct pblk *pblk = rqd->private;
+	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_pr_ctx *pr_ctx = r_ctx->private;
+	struct bio *new_bio = rqd->bio;
+	struct bio *bio = pr_ctx->orig_bio;
 	struct bio_vec src_bv, dst_bv;
-	void *ppa_ptr = NULL;
-	void *src_p, *dst_p;
-	dma_addr_t dma_ppa_list = 0;
-	__le64 *lba_list_mem, *lba_list_media;
-	int nr_secs = rqd->nr_ppas;
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	int bio_init_idx = pr_ctx->bio_init_idx;
+	unsigned long *read_bitmap = pr_ctx->bitmap;
+	int nr_secs = pr_ctx->orig_nr_secs;
 	int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
-	int i, ret, hole;
-
-	/* Re-use allocated memory for intermediate lbas */
-	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
-	lba_list_media = (((void *)rqd->ppa_list) + 2 * pblk_dma_ppa_size);
-
-	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
-
-	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
-		goto fail_add_pages;
-
-	if (nr_holes != new_bio->bi_vcnt) {
-		pr_err("pblk: malformed bio\n");
-		goto fail;
-	}
-
-	for (i = 0; i < nr_secs; i++)
-		lba_list_mem[i] = meta_list[i].lba;
-
-	new_bio->bi_iter.bi_sector = 0; /* internal bio */
-	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
-
-	rqd->bio = new_bio;
-	rqd->nr_ppas = nr_holes;
-	rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
-
-	if (unlikely(nr_holes == 1)) {
-		ppa_ptr = rqd->ppa_list;
-		dma_ppa_list = rqd->dma_ppa_list;
-		rqd->ppa_addr = rqd->ppa_list[0];
-	}
-
-	ret = pblk_submit_io_sync(pblk, rqd);
-	if (ret) {
-		bio_put(rqd->bio);
-		pr_err("pblk: sync read IO submission failed\n");
-		goto fail;
-	}
-
-	if (rqd->error) {
-		atomic_long_inc(&pblk->read_failed);
-#ifdef CONFIG_NVM_DEBUG
-		pblk_print_failed_rqd(pblk, rqd, rqd->error);
-#endif
-	}
+	__le64 *lba_list_mem, *lba_list_media;
+	void *src_p, *dst_p;
+	int hole, i;
 
 	if (unlikely(nr_holes == 1)) {
 		struct ppa_addr ppa;
 
 		ppa = rqd->ppa_addr;
-		rqd->ppa_list = ppa_ptr;
-		rqd->dma_ppa_list = dma_ppa_list;
+		rqd->ppa_list = pr_ctx->ppa_ptr;
+		rqd->dma_ppa_list = pr_ctx->dma_ppa_list;
 		rqd->ppa_list[0] = ppa;
 	}
 
+	/* Re-use allocated memory for intermediate lbas */
+	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
+	lba_list_media = (((void *)rqd->ppa_list) + 2 * pblk_dma_ppa_size);
+
 	for (i = 0; i < nr_secs; i++) {
 		lba_list_media[i] = meta_list[i].lba;
 		meta_list[i].lba = lba_list_mem[i];
@@ -316,7 +278,7 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 		meta_list[hole].lba = lba_list_media[i];
 
 		src_bv = new_bio->bi_io_vec[i++];
-		dst_bv = orig_bio->bi_io_vec[bio_init_idx + hole];
+		dst_bv = bio->bi_io_vec[bio_init_idx + hole];
 
 		src_p = kmap_atomic(src_bv.bv_page);
 		dst_p = kmap_atomic(dst_bv.bv_page);
@@ -334,19 +296,107 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 	} while (hole < nr_secs);
 
 	bio_put(new_bio);
+	kfree(pr_ctx);
 
 	/* restore original request */
 	rqd->bio = NULL;
 	rqd->nr_ppas = nr_secs;
 
+	bio_endio(bio);
 	__pblk_end_io_read(pblk, rqd, false);
-	return NVM_IO_DONE;
+}
 
-fail:
-	/* Free allocated pages in new bio */
+static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
+			    unsigned int bio_init_idx,
+			    unsigned long *read_bitmap,
+			    int nr_holes)
+{
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_pr_ctx *pr_ctx;
+	struct bio *new_bio, *bio = r_ctx->private;
+	__le64 *lba_list_mem;
+	int nr_secs = rqd->nr_ppas;
+	int i;
+
+	/* Re-use allocated memory for intermediate lbas */
+	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
+
+	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
+
+	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
+		goto fail_bio_put;
+
+	if (nr_holes != new_bio->bi_vcnt) {
+		WARN_ONCE(1, "pblk: malformed bio\n");
+		goto fail_free_pages;
+	}
+
+	pr_ctx = kmalloc(sizeof(struct pblk_pr_ctx), GFP_KERNEL);
+	if (!pr_ctx)
+		goto fail_free_pages;
+
+	for (i = 0; i < nr_secs; i++)
+		lba_list_mem[i] = meta_list[i].lba;
+
+	new_bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
+
+	rqd->bio = new_bio;
+	rqd->nr_ppas = nr_holes;
+	rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
+	pr_ctx->ppa_ptr = NULL;
+	pr_ctx->orig_bio = bio;
+	bitmap_copy(pr_ctx->bitmap, read_bitmap, NVM_MAX_VLBA);
+	pr_ctx->bio_init_idx = bio_init_idx;
+	pr_ctx->orig_nr_secs = nr_secs;
+	r_ctx->private = pr_ctx;
+
+	if (unlikely(nr_holes == 1)) {
+		pr_ctx->ppa_ptr = rqd->ppa_list;
+		pr_ctx->dma_ppa_list = rqd->dma_ppa_list;
+		rqd->ppa_addr = rqd->ppa_list[0];
+	}
+	return 0;
+
+fail_free_pages:
 	pblk_bio_free_pages(pblk, new_bio, 0, new_bio->bi_vcnt);
-fail_add_pages:
-	pr_err("pblk: failed to perform partial read\n");
+fail_bio_put:
+	bio_put(new_bio);
+
+	return -ENOMEM;
+}
+
+static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
+				 unsigned int bio_init_idx,
+				 unsigned long *read_bitmap, int nr_secs)
+{
+	int nr_holes;
+	int ret;
+
+	nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
+
+	if (pblk_setup_partial_read(pblk, rqd, bio_init_idx, read_bitmap,
+				    nr_holes))
+		return NVM_IO_ERR;
+
+	rqd->end_io = pblk_end_partial_read;
+
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		bio_put(rqd->bio);
+		pblk_err(pblk, "partial read IO submission failed\n");
+		goto err;
+	}
+
+	return NVM_IO_OK;
+
+err:
+	pblk_err(pblk, "failed to perform partial read\n");
+
+	/* Free allocated pages in new bio */
+	pblk_bio_free_pages(pblk, rqd->bio, 0, rqd->bio->bi_vcnt);
 	__pblk_end_io_read(pblk, rqd, false);
 	return NVM_IO_ERR;
 }
@@ -359,7 +409,7 @@ static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
 
 	pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_inc(&pblk->inflight_reads);
 #endif
 
@@ -382,7 +432,7 @@ retry:
 		WARN_ON(test_and_set_bit(0, read_bitmap));
 		meta_list[0].lba = cpu_to_le64(lba);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		atomic_long_inc(&pblk->cache_reads);
 #endif
 	} else {
@@ -401,7 +451,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	struct pblk_g_ctx *r_ctx;
 	struct nvm_rq *rqd;
 	unsigned int bio_init_idx;
-	unsigned long read_bitmap; /* Max 64 ppas per request */
+	DECLARE_BITMAP(read_bitmap, NVM_MAX_VLBA);
 	int ret = NVM_IO_ERR;
 
 	/* logic error: lba out-of-bounds. Ignore read request */
@@ -411,9 +461,10 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		return NVM_IO_ERR;
 	}
 
-	generic_start_io_acct(q, READ, bio_sectors(bio), &pblk->disk->part0);
+	generic_start_io_acct(q, REQ_OP_READ, bio_sectors(bio),
+			      &pblk->disk->part0);
 
-	bitmap_zero(&read_bitmap, nr_secs);
+	bitmap_zero(read_bitmap, nr_secs);
 
 	rqd = pblk_alloc_rqd(pblk, PBLK_READ);
 
@@ -436,7 +487,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
 							&rqd->dma_meta_list);
 	if (!rqd->meta_list) {
-		pr_err("pblk: not able to allocate ppa list\n");
+		pblk_err(pblk, "not able to allocate ppa list\n");
 		goto fail_rqd_free;
 	}
 
@@ -444,32 +495,32 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
 		rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
 
-		pblk_read_ppalist_rq(pblk, rqd, bio, blba, &read_bitmap);
+		pblk_read_ppalist_rq(pblk, rqd, bio, blba, read_bitmap);
 	} else {
-		pblk_read_rq(pblk, rqd, bio, blba, &read_bitmap);
+		pblk_read_rq(pblk, rqd, bio, blba, read_bitmap);
 	}
 
-	if (bitmap_full(&read_bitmap, nr_secs)) {
+	if (bitmap_full(read_bitmap, nr_secs)) {
 		atomic_inc(&pblk->inflight_io);
 		__pblk_end_io_read(pblk, rqd, false);
 		return NVM_IO_DONE;
 	}
 
 	/* All sectors are to be read from the device */
-	if (bitmap_empty(&read_bitmap, rqd->nr_ppas)) {
+	if (bitmap_empty(read_bitmap, rqd->nr_ppas)) {
 		struct bio *int_bio = NULL;
 
 		/* Clone read bio to deal with read errors internally */
 		int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);
 		if (!int_bio) {
-			pr_err("pblk: could not clone read bio\n");
+			pblk_err(pblk, "could not clone read bio\n");
 			goto fail_end_io;
 		}
 
 		rqd->bio = int_bio;
 
 		if (pblk_submit_io(pblk, rqd)) {
-			pr_err("pblk: read IO submission failed\n");
+			pblk_err(pblk, "read IO submission failed\n");
 			ret = NVM_IO_ERR;
 			goto fail_end_io;
 		}
@@ -480,8 +531,15 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	/* The read bio request could be partially filled by the write buffer,
 	 * but there are some holes that need to be read from the drive.
 	 */
-	return pblk_partial_read(pblk, rqd, bio, bio_init_idx, &read_bitmap);
+	ret = pblk_partial_read_bio(pblk, rqd, bio_init_idx, read_bitmap,
+				    nr_secs);
+	if (ret)
+		goto fail_meta_free;
+
+	return NVM_IO_OK;
 
+fail_meta_free:
+	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 fail_rqd_free:
 	pblk_free_rqd(pblk, rqd, PBLK_READ);
 	return ret;
@@ -514,7 +572,7 @@ static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
 		rqd->ppa_list[valid_secs++] = ppa_list_l2p[i];
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(valid_secs, &pblk->inflight_reads);
 #endif
 
@@ -548,7 +606,7 @@ static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
 	rqd->ppa_addr = ppa_l2p;
 	valid_secs = 1;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_inc(&pblk->inflight_reads);
 #endif
 
@@ -595,7 +653,8 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 	bio = pblk_bio_map_addr(pblk, gc_rq->data, gc_rq->secs_to_gc, data_len,
 						PBLK_VMALLOC_META, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		pr_err("pblk: could not allocate GC bio (%lu)\n", PTR_ERR(bio));
+		pblk_err(pblk, "could not allocate GC bio (%lu)\n",
+				PTR_ERR(bio));
 		goto err_free_dma;
 	}
 
@@ -609,7 +668,7 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 
 	if (pblk_submit_io_sync(pblk, &rqd)) {
 		ret = -EIO;
-		pr_err("pblk: GC read request failed\n");
+		pblk_err(pblk, "GC read request failed\n");
 		goto err_free_bio;
 	}
 
@@ -619,12 +678,12 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 
 	if (rqd.error) {
 		atomic_long_inc(&pblk->read_failed_gc);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		pblk_print_failed_rqd(pblk, &rqd, rqd.error);
 #endif
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(gc_rq->secs_to_gc, &pblk->sync_reads);
 	atomic_long_add(gc_rq->secs_to_gc, &pblk->recov_gc_reads);
 	atomic_long_sub(gc_rq->secs_to_gc, &pblk->inflight_reads);
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 3a5069183859..e232e47e1353 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -77,7 +77,7 @@ static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
 	}
 
 	if (nr_valid_lbas != nr_lbas)
-		pr_err("pblk: line %d - inconsistent lba list(%llu/%llu)\n",
+		pblk_err(pblk, "line %d - inconsistent lba list(%llu/%llu)\n",
 				line->id, nr_valid_lbas, nr_lbas);
 
 	line->left_msecs = 0;
@@ -184,7 +184,7 @@ next_read_rq:
 	/* If read fails, more padding is needed */
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		return ret;
 	}
 
@@ -194,7 +194,7 @@ next_read_rq:
 	 * we cannot recover from here. Need FTL log.
 	 */
 	if (rqd->error && rqd->error != NVM_RSP_WARN_HIGHECC) {
-		pr_err("pblk: L2P recovery failed (%d)\n", rqd->error);
+		pblk_err(pblk, "L2P recovery failed (%d)\n", rqd->error);
 		return -EINTR;
 	}
 
@@ -273,7 +273,7 @@ static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
 next_pad_rq:
 	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
 	if (rq_ppas < pblk->min_write_pgs) {
-		pr_err("pblk: corrupted pad line %d\n", line->id);
+		pblk_err(pblk, "corrupted pad line %d\n", line->id);
 		goto fail_free_pad;
 	}
 
@@ -342,7 +342,7 @@ next_pad_rq:
 
 	ret = pblk_submit_io(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		pblk_up_page(pblk, rqd->ppa_list, rqd->nr_ppas);
 		goto fail_free_bio;
 	}
@@ -356,12 +356,12 @@ next_pad_rq:
 
 	if (!wait_for_completion_io_timeout(&pad_rq->wait,
 				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
-		pr_err("pblk: pad write timed out\n");
+		pblk_err(pblk, "pad write timed out\n");
 		ret = -ETIME;
 	}
 
 	if (!pblk_line_is_full(line))
-		pr_err("pblk: corrupted padded line: %d\n", line->id);
+		pblk_err(pblk, "corrupted padded line: %d\n", line->id);
 
 	vfree(data);
 free_rq:
@@ -461,7 +461,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		return ret;
 	}
 
@@ -501,11 +501,11 @@ next_rq:
 
 		ret = pblk_recov_pad_oob(pblk, line, pad_secs);
 		if (ret)
-			pr_err("pblk: OOB padding failed (err:%d)\n", ret);
+			pblk_err(pblk, "OOB padding failed (err:%d)\n", ret);
 
 		ret = pblk_recov_read_oob(pblk, line, p, r_ptr);
 		if (ret)
-			pr_err("pblk: OOB read failed (err:%d)\n", ret);
+			pblk_err(pblk, "OOB read failed (err:%d)\n", ret);
 
 		left_ppas = 0;
 	}
@@ -592,7 +592,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		return ret;
 	}
@@ -671,14 +671,14 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
 
 	ret = pblk_recov_scan_oob(pblk, line, p, &done);
 	if (ret) {
-		pr_err("pblk: could not recover L2P from OOB\n");
+		pblk_err(pblk, "could not recover L2P from OOB\n");
 		goto out;
 	}
 
 	if (!done) {
 		ret = pblk_recov_scan_all_oob(pblk, line, p);
 		if (ret) {
-			pr_err("pblk: could not recover L2P from OOB\n");
+			pblk_err(pblk, "could not recover L2P from OOB\n");
 			goto out;
 		}
 	}
@@ -737,14 +737,15 @@ static int pblk_recov_check_line_version(struct pblk *pblk,
 	struct line_header *header = &emeta->header;
 
 	if (header->version_major != EMETA_VERSION_MAJOR) {
-		pr_err("pblk: line major version mismatch: %d, expected: %d\n",
-		       header->version_major, EMETA_VERSION_MAJOR);
+		pblk_err(pblk, "line major version mismatch: %d, expected: %d\n",
+			 header->version_major, EMETA_VERSION_MAJOR);
 		return 1;
 	}
 
-#ifdef NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (header->version_minor > EMETA_VERSION_MINOR)
-		pr_info("pblk: newer line minor version found: %d\n", line_v);
+		pblk_info(pblk, "newer line minor version found: %d\n",
+				header->version_minor);
 #endif
 
 	return 0;
@@ -851,7 +852,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 			continue;
 
 		if (smeta_buf->header.version_major != SMETA_VERSION_MAJOR) {
-			pr_err("pblk: found incompatible line version %u\n",
+			pblk_err(pblk, "found incompatible line version %u\n",
 					smeta_buf->header.version_major);
 			return ERR_PTR(-EINVAL);
 		}
@@ -863,7 +864,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 		}
 
 		if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) {
-			pr_debug("pblk: ignore line %u due to uuid mismatch\n",
+			pblk_debug(pblk, "ignore line %u due to uuid mismatch\n",
 					i);
 			continue;
 		}
@@ -887,7 +888,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 
 		pblk_recov_line_add_ordered(&recov_list, line);
 		found_lines++;
-		pr_debug("pblk: recovering data line %d, seq:%llu\n",
+		pblk_debug(pblk, "recovering data line %d, seq:%llu\n",
 						line->id, smeta_buf->seq_nr);
 	}
 
@@ -947,7 +948,7 @@ next:
 			line->emeta = NULL;
 		} else {
 			if (open_lines > 1)
-				pr_err("pblk: failed to recover L2P\n");
+				pblk_err(pblk, "failed to recover L2P\n");
 
 			open_lines++;
 			line->meta_line = meta_line;
@@ -976,7 +977,7 @@ next:
 
 out:
 	if (found_lines != recovered_lines)
-		pr_err("pblk: failed to recover all found lines %d/%d\n",
+		pblk_err(pblk, "failed to recover all found lines %d/%d\n",
 						found_lines, recovered_lines);
 
 	return data_line;
@@ -999,7 +1000,7 @@ int pblk_recov_pad(struct pblk *pblk)
 
 	ret = pblk_recov_pad_oob(pblk, line, left_msecs);
 	if (ret) {
-		pr_err("pblk: Tear down padding failed (%d)\n", ret);
+		pblk_err(pblk, "tear down padding failed (%d)\n", ret);
 		return ret;
 	}
 
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
index 88a0a7c407aa..9fc3dfa168b4 100644
--- a/drivers/lightnvm/pblk-sysfs.c
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -268,7 +268,7 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
 	spin_unlock(&l_mg->free_lock);
 
 	if (nr_free_lines != free_line_cnt)
-		pr_err("pblk: corrupted free line list:%d/%d\n",
+		pblk_err(pblk, "corrupted free line list:%d/%d\n",
 						nr_free_lines, free_line_cnt);
 
 	sz = snprintf(page, PAGE_SIZE - sz,
@@ -421,7 +421,7 @@ static ssize_t pblk_sysfs_get_padding_dist(struct pblk *pblk, char *page)
 	return sz;
 }
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
 {
 	return snprintf(page, PAGE_SIZE,
@@ -598,7 +598,7 @@ static struct attribute sys_padding_dist = {
 	.mode = 0644,
 };
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static struct attribute sys_stats_debug_attr = {
 	.name = "stats",
 	.mode = 0444,
@@ -619,7 +619,7 @@ static struct attribute *pblk_attrs[] = {
 	&sys_write_amp_mileage,
 	&sys_write_amp_trip,
 	&sys_padding_dist,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	&sys_stats_debug_attr,
 #endif
 	NULL,
@@ -654,7 +654,7 @@ static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr,
 		return pblk_sysfs_get_write_amp_trip(pblk, buf);
 	else if (strcmp(attr->name, "padding_dist") == 0)
 		return pblk_sysfs_get_padding_dist(pblk, buf);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	else if (strcmp(attr->name, "stats") == 0)
 		return pblk_sysfs_stats_debug(pblk, buf);
 #endif
@@ -697,8 +697,7 @@ int pblk_sysfs_init(struct gendisk *tdisk)
 					kobject_get(&parent_dev->kobj),
 					"%s", "pblk");
 	if (ret) {
-		pr_err("pblk: could not register %s/pblk\n",
-						tdisk->disk_name);
+		pblk_err(pblk, "could not register\n");
 		return ret;
 	}
 
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index f353e52941f5..ee774a86cf1e 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -38,7 +38,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 			/* Release flags on context. Protect from writes */
 			smp_store_release(&w_ctx->flags, flags);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_dec(&rwb->inflight_flush_point);
 #endif
 		}
@@ -51,7 +51,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 		pblk_bio_free_pages(pblk, rqd->bio, c_ctx->nr_valid,
 							c_ctx->nr_padded);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(rqd->nr_ppas, &pblk->sync_writes);
 #endif
 
@@ -78,7 +78,7 @@ static void pblk_complete_write(struct pblk *pblk, struct nvm_rq *rqd,
 	unsigned long flags;
 	unsigned long pos;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_sub(c_ctx->nr_valid, &pblk->inflight_writes);
 #endif
 
@@ -196,7 +196,7 @@ static void pblk_queue_resubmit(struct pblk *pblk, struct pblk_c_ctx *c_ctx)
 	list_add_tail(&r_ctx->list, &pblk->resubmit_list);
 	spin_unlock(&pblk->resubmit_lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(c_ctx->nr_valid, &pblk->recov_writes);
 #endif
 }
@@ -238,7 +238,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
 
 	recovery = mempool_alloc(&pblk->rec_pool, GFP_ATOMIC);
 	if (!recovery) {
-		pr_err("pblk: could not allocate recovery work\n");
+		pblk_err(pblk, "could not allocate recovery work\n");
 		return;
 	}
 
@@ -258,7 +258,7 @@ static void pblk_end_io_write(struct nvm_rq *rqd)
 		pblk_end_w_fail(pblk, rqd);
 		return;
 	}
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	else
 		WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n");
 #endif
@@ -279,7 +279,7 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 
 	if (rqd->error) {
 		pblk_log_write_err(pblk, rqd);
-		pr_err("pblk: metadata I/O failed. Line %d\n", line->id);
+		pblk_err(pblk, "metadata I/O failed. Line %d\n", line->id);
 		line->w_err_gc->has_write_err = 1;
 	}
 
@@ -356,11 +356,11 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
 
 	secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if ((!secs_to_sync && secs_to_flush)
 			|| (secs_to_sync < 0)
 			|| (secs_to_sync > secs_avail && !secs_to_flush)) {
-		pr_err("pblk: bad sector calculation (a:%d,s:%d,f:%d)\n",
+		pblk_err(pblk, "bad sector calculation (a:%d,s:%d,f:%d)\n",
 				secs_avail, secs_to_sync, secs_to_flush);
 	}
 #endif
@@ -397,7 +397,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 	bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
 					l_mg->emeta_alloc_type, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		pr_err("pblk: failed to map emeta io");
+		pblk_err(pblk, "failed to map emeta io");
 		ret = PTR_ERR(bio);
 		goto fail_free_rqd;
 	}
@@ -428,7 +428,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 
 	ret = pblk_submit_io(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
 		goto fail_rollback;
 	}
 
@@ -518,7 +518,7 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 	/* Assign lbas to ppas and populate request structure */
 	err = pblk_setup_w_rq(pblk, rqd, &erase_ppa);
 	if (err) {
-		pr_err("pblk: could not setup write request: %d\n", err);
+		pblk_err(pblk, "could not setup write request: %d\n", err);
 		return NVM_IO_ERR;
 	}
 
@@ -527,7 +527,7 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 	/* Submit data write for current data line */
 	err = pblk_submit_io(pblk, rqd);
 	if (err) {
-		pr_err("pblk: data I/O submission failed: %d\n", err);
+		pblk_err(pblk, "data I/O submission failed: %d\n", err);
 		return NVM_IO_ERR;
 	}
 
@@ -549,7 +549,8 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 		/* Submit metadata write for previous data line */
 		err = pblk_submit_meta_io(pblk, meta_line);
 		if (err) {
-			pr_err("pblk: metadata I/O submission failed: %d", err);
+			pblk_err(pblk, "metadata I/O submission failed: %d",
+					err);
 			return NVM_IO_ERR;
 		}
 	}
@@ -614,7 +615,7 @@ static int pblk_submit_write(struct pblk *pblk)
 		secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
 					secs_to_flush);
 		if (secs_to_sync > pblk->max_write_pgs) {
-			pr_err("pblk: bad buffer sync calculation\n");
+			pblk_err(pblk, "bad buffer sync calculation\n");
 			return 1;
 		}
 
@@ -633,14 +634,14 @@ static int pblk_submit_write(struct pblk *pblk)
 
 	if (pblk_rb_read_to_bio(&pblk->rwb, rqd, pos, secs_to_sync,
 								secs_avail)) {
-		pr_err("pblk: corrupted write bio\n");
+		pblk_err(pblk, "corrupted write bio\n");
 		goto fail_put_bio;
 	}
 
 	if (pblk_submit_io_set(pblk, rqd))
 		goto fail_free_bio;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(secs_to_sync, &pblk->sub_writes);
 #endif
 
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 34cc1d64a9d4..4760af7b6499 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -119,6 +119,16 @@ struct pblk_g_ctx {
 	u64 lba;
 };
 
+/* partial read context */
+struct pblk_pr_ctx {
+	struct bio *orig_bio;
+	DECLARE_BITMAP(bitmap, NVM_MAX_VLBA);
+	unsigned int orig_nr_secs;
+	unsigned int bio_init_idx;
+	void *ppa_ptr;
+	dma_addr_t dma_ppa_list;
+};
+
 /* Pad context */
 struct pblk_pad_rq {
 	struct pblk *pblk;
@@ -193,7 +203,7 @@ struct pblk_rb {
 	spinlock_t w_lock;		/* Write lock */
 	spinlock_t s_lock;		/* Sync lock */
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_t inflight_flush_point;	/* Not served REQ_FLUSH | REQ_FUA */
 #endif
 };
@@ -608,9 +618,6 @@ struct pblk {
 
 	int min_write_pgs; /* Minimum amount of pages required by controller */
 	int max_write_pgs; /* Maximum amount of pages supported by controller */
-	int pgs_in_buffer; /* Number of pages that need to be held in buffer to
-			    * guarantee successful reads.
-			    */
 
 	sector_t capacity; /* Device capacity when bad blocks are subtracted */
 
@@ -639,7 +646,7 @@ struct pblk {
 	u64 nr_flush_rst;		/* Flushes reset value for pad dist.*/
 	atomic64_t nr_flush;		/* Number of flush/fua I/O */
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Non-persistent debug counters, 4kb sector I/Os */
 	atomic_long_t inflight_writes;	/* Inflight writes (user and gc) */
 	atomic_long_t padded_writes;	/* Sectors padded due to flush/fua */
@@ -706,6 +713,15 @@ struct pblk_line_ws {
 #define pblk_g_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_g_ctx))
 #define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx))
 
+#define pblk_err(pblk, fmt, ...)			\
+	pr_err("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_info(pblk, fmt, ...)			\
+	pr_info("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_warn(pblk, fmt, ...)			\
+	pr_warn("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_debug(pblk, fmt, ...)			\
+	pr_debug("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+
 /*
  * pblk ring buffer operations
  */
@@ -1282,20 +1298,22 @@ static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs)
 	return !(nr_secs % pblk->min_write_pgs);
 }
 
-#ifdef CONFIG_NVM_DEBUG
-static inline void print_ppa(struct nvm_geo *geo, struct ppa_addr *p,
+#ifdef CONFIG_NVM_PBLK_DEBUG
+static inline void print_ppa(struct pblk *pblk, struct ppa_addr *p,
 			     char *msg, int error)
 {
+	struct nvm_geo *geo = &pblk->dev->geo;
+
 	if (p->c.is_cached) {
-		pr_err("ppa: (%s: %x) cache line: %llu\n",
+		pblk_err(pblk, "ppa: (%s: %x) cache line: %llu\n",
 				msg, error, (u64)p->c.line);
 	} else if (geo->version == NVM_OCSSD_SPEC_12) {
-		pr_err("ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
+		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
 			msg, error,
 			p->g.ch, p->g.lun, p->g.blk,
 			p->g.pg, p->g.pl, p->g.sec);
 	} else {
-		pr_err("ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n",
+		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n",
 			msg, error,
 			p->m.grp, p->m.pu, p->m.chk, p->m.sec);
 	}
@@ -1307,16 +1325,16 @@ static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd,
 	int bit = -1;
 
 	if (rqd->nr_ppas ==  1) {
-		print_ppa(&pblk->dev->geo, &rqd->ppa_addr, "rqd", error);
+		print_ppa(pblk, &rqd->ppa_addr, "rqd", error);
 		return;
 	}
 
 	while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas,
 						bit + 1)) < rqd->nr_ppas) {
-		print_ppa(&pblk->dev->geo, &rqd->ppa_list[bit], "rqd", error);
+		print_ppa(pblk, &rqd->ppa_list[bit], "rqd", error);
 	}
 
-	pr_err("error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
+	pblk_err(pblk, "error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
 }
 
 static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
@@ -1347,7 +1365,7 @@ static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
 				continue;
 		}
 
-		print_ppa(geo, ppa, "boundary", i);
+		print_ppa(tgt_dev->q->queuedata, ppa, "boundary", i);
 
 		return 1;
 	}
@@ -1377,7 +1395,7 @@ static inline int pblk_check_io(struct pblk *pblk, struct nvm_rq *rqd)
 
 			spin_lock(&line->lock);
 			if (line->state != PBLK_LINESTATE_OPEN) {
-				pr_err("pblk: bad ppa: line:%d,state:%d\n",
+				pblk_err(pblk, "bad ppa: line:%d,state:%d\n",
 							line->id, line->state);
 				WARN_ON(1);
 				spin_unlock(&line->lock);
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index d6bf294f3907..05f82ff6f016 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -328,13 +328,6 @@ struct cached_dev {
 	 */
 	atomic_t		has_dirty;
 
-	/*
-	 * Set to zero by things that touch the backing volume-- except
-	 * writeback.  Incremented by writeback.  Used to determine when to
-	 * accelerate idle writeback.
-	 */
-	atomic_t		backing_idle;
-
 	struct bch_ratelimit	writeback_rate;
 	struct delayed_work	writeback_rate_update;
 
@@ -423,9 +416,9 @@ struct cache {
 	/*
 	 * When allocating new buckets, prio_write() gets first dibs - since we
 	 * may not be allocate at all without writing priorities and gens.
-	 * prio_buckets[] contains the last buckets we wrote priorities to (so
-	 * gc can mark them as metadata), prio_next[] contains the buckets
-	 * allocated for the next prio write.
+	 * prio_last_buckets[] contains the last buckets we wrote priorities to
+	 * (so gc can mark them as metadata), prio_buckets[] contains the
+	 * buckets allocated for the next prio write.
 	 */
 	uint64_t		*prio_buckets;
 	uint64_t		*prio_last_buckets;
@@ -474,6 +467,7 @@ struct cache {
 
 struct gc_stat {
 	size_t			nodes;
+	size_t			nodes_pre;
 	size_t			key_bytes;
 
 	size_t			nkeys;
@@ -514,6 +508,8 @@ struct cache_set {
 	struct cache_accounting accounting;
 
 	unsigned long		flags;
+	atomic_t		idle_counter;
+	atomic_t		at_max_writeback_rate;
 
 	struct cache_sb		sb;
 
@@ -523,8 +519,10 @@ struct cache_set {
 
 	struct bcache_device	**devices;
 	unsigned		devices_max_used;
+	atomic_t		attached_dev_nr;
 	struct list_head	cached_devs;
 	uint64_t		cached_dev_sectors;
+	atomic_long_t		flash_dev_dirty_sectors;
 	struct closure		caching;
 
 	struct closure		sb_write;
@@ -603,6 +601,10 @@ struct cache_set {
 	 */
 	atomic_t		rescale;
 	/*
+	 * used for GC, identify if any front side I/Os is inflight
+	 */
+	atomic_t		search_inflight;
+	/*
 	 * When we invalidate buckets, we use both the priority and the amount
 	 * of good data to determine which buckets to reuse first - to weight
 	 * those together consistently we keep track of the smallest nonzero
@@ -995,7 +997,7 @@ void bch_open_buckets_free(struct cache_set *);
 int bch_cache_allocator_start(struct cache *ca);
 
 void bch_debug_exit(void);
-int bch_debug_init(struct kobject *);
+void bch_debug_init(struct kobject *kobj);
 void bch_request_exit(void);
 int bch_request_init(void);
 
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index f3403b45bc28..596c93b44e9b 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -366,6 +366,10 @@ EXPORT_SYMBOL(bch_btree_keys_init);
 
 /* Binary tree stuff for auxiliary search trees */
 
+/*
+ * return array index next to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
 static unsigned inorder_next(unsigned j, unsigned size)
 {
 	if (j * 2 + 1 < size) {
@@ -379,6 +383,10 @@ static unsigned inorder_next(unsigned j, unsigned size)
 	return j;
 }
 
+/*
+ * return array index previous to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
 static unsigned inorder_prev(unsigned j, unsigned size)
 {
 	if (j * 2 < size) {
@@ -421,6 +429,10 @@ static unsigned __to_inorder(unsigned j, unsigned size, unsigned extra)
 	return j;
 }
 
+/*
+ * Return the cacheline index in bset_tree->data, where j is index
+ * from a linear array which stores the auxiliar binary tree
+ */
 static unsigned to_inorder(unsigned j, struct bset_tree *t)
 {
 	return __to_inorder(j, t->size, t->extra);
@@ -441,6 +453,10 @@ static unsigned __inorder_to_tree(unsigned j, unsigned size, unsigned extra)
 	return j;
 }
 
+/*
+ * Return an index from a linear array which stores the auxiliar binary
+ * tree, j is the cacheline index of t->data.
+ */
 static unsigned inorder_to_tree(unsigned j, struct bset_tree *t)
 {
 	return __inorder_to_tree(j, t->size, t->extra);
@@ -546,6 +562,20 @@ static inline uint64_t shrd128(uint64_t high, uint64_t low, uint8_t shift)
 	return low;
 }
 
+/*
+ * Calculate mantissa value for struct bkey_float.
+ * If most significant bit of f->exponent is not set, then
+ *  - f->exponent >> 6 is 0
+ *  - p[0] points to bkey->low
+ *  - p[-1] borrows bits from KEY_INODE() of bkey->high
+ * if most isgnificant bits of f->exponent is set, then
+ *  - f->exponent >> 6 is 1
+ *  - p[0] points to bits from KEY_INODE() of bkey->high
+ *  - p[-1] points to other bits from KEY_INODE() of
+ *    bkey->high too.
+ * See make_bfloat() to check when most significant bit of f->exponent
+ * is set or not.
+ */
 static inline unsigned bfloat_mantissa(const struct bkey *k,
 				       struct bkey_float *f)
 {
@@ -570,6 +600,16 @@ static void make_bfloat(struct bset_tree *t, unsigned j)
 	BUG_ON(m < l || m > r);
 	BUG_ON(bkey_next(p) != m);
 
+	/*
+	 * If l and r have different KEY_INODE values (different backing
+	 * device), f->exponent records how many least significant bits
+	 * are different in KEY_INODE values and sets most significant
+	 * bits to 1 (by +64).
+	 * If l and r have same KEY_INODE value, f->exponent records
+	 * how many different bits in least significant bits of bkey->low.
+	 * See bfloat_mantiss() how the most significant bit of
+	 * f->exponent is used to calculate bfloat mantissa value.
+	 */
 	if (KEY_INODE(l) != KEY_INODE(r))
 		f->exponent = fls64(KEY_INODE(r) ^ KEY_INODE(l)) + 64;
 	else
@@ -633,6 +673,15 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic)
 }
 EXPORT_SYMBOL(bch_bset_init_next);
 
+/*
+ * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to
+ * accelerate bkey search in a btree node (pointed by bset_tree->data in
+ * memory). After search in the auxiliar tree by calling bset_search_tree(),
+ * a struct bset_search_iter is returned which indicates range [l, r] from
+ * bset_tree->data where the searching bkey might be inside. Then a followed
+ * linear comparison does the exact search, see __bch_bset_search() for how
+ * the auxiliary tree is used.
+ */
 void bch_bset_build_written_tree(struct btree_keys *b)
 {
 	struct bset_tree *t = bset_tree_last(b);
@@ -898,6 +947,17 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
 	unsigned inorder, j, n = 1;
 
 	do {
+		/*
+		 * A bit trick here.
+		 * If p < t->size, (int)(p - t->size) is a minus value and
+		 * the most significant bit is set, right shifting 31 bits
+		 * gets 1. If p >= t->size, the most significant bit is
+		 * not set, right shifting 31 bits gets 0.
+		 * So the following 2 lines equals to
+		 *	if (p >= t->size)
+		 *		p = 0;
+		 * but a branch instruction is avoided.
+		 */
 		unsigned p = n << 4;
 		p &= ((int) (p - t->size)) >> 31;
 
@@ -907,6 +967,9 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
 		f = &t->tree[j];
 
 		/*
+		 * Similar bit trick, use subtract operation to avoid a branch
+		 * instruction.
+		 *
 		 * n = (f->mantissa > bfloat_mantissa())
 		 *	? j * 2
 		 *	: j * 2 + 1;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 547c9eedc2f4..c19f7716df88 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -90,6 +90,9 @@
 
 #define MAX_NEED_GC		64
 #define MAX_SAVE_PRIO		72
+#define MAX_GC_TIMES		100
+#define MIN_GC_NODES		100
+#define GC_SLEEP_MS		100
 
 #define PTR_DIRTY_BIT		(((uint64_t) 1 << 36))
 
@@ -1008,6 +1011,13 @@ retry:
 		BUG_ON(b->level != level);
 	}
 
+	if (btree_node_io_error(b)) {
+		rw_unlock(write, b);
+		return ERR_PTR(-EIO);
+	}
+
+	BUG_ON(!b->written);
+
 	b->parent = parent;
 	b->accessed = 1;
 
@@ -1019,13 +1029,6 @@ retry:
 	for (; i <= b->keys.nsets; i++)
 		prefetch(b->keys.set[i].data);
 
-	if (btree_node_io_error(b)) {
-		rw_unlock(write, b);
-		return ERR_PTR(-EIO);
-	}
-
-	BUG_ON(!b->written);
-
 	return b;
 }
 
@@ -1520,6 +1523,32 @@ static unsigned btree_gc_count_keys(struct btree *b)
 	return ret;
 }
 
+static size_t btree_gc_min_nodes(struct cache_set *c)
+{
+	size_t min_nodes;
+
+	/*
+	 * Since incremental GC would stop 100ms when front
+	 * side I/O comes, so when there are many btree nodes,
+	 * if GC only processes constant (100) nodes each time,
+	 * GC would last a long time, and the front side I/Os
+	 * would run out of the buckets (since no new bucket
+	 * can be allocated during GC), and be blocked again.
+	 * So GC should not process constant nodes, but varied
+	 * nodes according to the number of btree nodes, which
+	 * realized by dividing GC into constant(100) times,
+	 * so when there are many btree nodes, GC can process
+	 * more nodes each time, otherwise, GC will process less
+	 * nodes each time (but no less than MIN_GC_NODES)
+	 */
+	min_nodes = c->gc_stats.nodes / MAX_GC_TIMES;
+	if (min_nodes < MIN_GC_NODES)
+		min_nodes = MIN_GC_NODES;
+
+	return min_nodes;
+}
+
+
 static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 			    struct closure *writes, struct gc_stat *gc)
 {
@@ -1585,6 +1614,13 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 		memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1));
 		r->b = NULL;
 
+		if (atomic_read(&b->c->search_inflight) &&
+		    gc->nodes >= gc->nodes_pre + btree_gc_min_nodes(b->c)) {
+			gc->nodes_pre =  gc->nodes;
+			ret = -EAGAIN;
+			break;
+		}
+
 		if (need_resched()) {
 			ret = -EAGAIN;
 			break;
@@ -1753,7 +1789,10 @@ static void bch_btree_gc(struct cache_set *c)
 		closure_sync(&writes);
 		cond_resched();
 
-		if (ret && ret != -EAGAIN)
+		if (ret == -EAGAIN)
+			schedule_timeout_interruptible(msecs_to_jiffies
+						       (GC_SLEEP_MS));
+		else if (ret)
 			pr_warn("gc failed!");
 	} while (ret && !test_bit(CACHE_SET_IO_DISABLE, &c->flags));
 
@@ -1834,8 +1873,14 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 		do {
 			k = bch_btree_iter_next_filter(&iter, &b->keys,
 						       bch_ptr_bad);
-			if (k)
+			if (k) {
 				btree_node_prefetch(b, k);
+				/*
+				 * initiallize c->gc_stats.nodes
+				 * for incremental GC
+				 */
+				b->c->gc_stats.nodes++;
+			}
 
 			if (p)
 				ret = btree(check_recurse, p, b, op);
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index d211e2c25b6b..68e9d926134d 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -152,7 +152,7 @@ static inline bool btree_node_ ## flag(struct btree *b)			\
 {	return test_bit(BTREE_NODE_ ## flag, &b->flags); }		\
 									\
 static inline void set_btree_node_ ## flag(struct btree *b)		\
-{	set_bit(BTREE_NODE_ ## flag, &b->flags); }			\
+{	set_bit(BTREE_NODE_ ## flag, &b->flags); }
 
 enum btree_flags {
 	BTREE_NODE_io_error,
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 0e14969182c6..618253683d40 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -199,11 +199,16 @@ static const struct file_operations debug_ops = {
 	.release	= single_release
 };
 
-int __init closure_debug_init(void)
+void  __init closure_debug_init(void)
 {
-	closure_debug = debugfs_create_file("closures",
-				0400, bcache_debug, NULL, &debug_ops);
-	return IS_ERR_OR_NULL(closure_debug);
+	if (!IS_ERR_OR_NULL(bcache_debug))
+		/*
+		 * it is unnecessary to check return value of
+		 * debugfs_create_file(), we should not care
+		 * about this.
+		 */
+		closure_debug = debugfs_create_file(
+			"closures", 0400, bcache_debug, NULL, &debug_ops);
 }
 #endif
 
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 71427eb5fdae..7c2c5bc7c88b 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -186,13 +186,13 @@ static inline void closure_sync(struct closure *cl)
 
 #ifdef CONFIG_BCACHE_CLOSURES_DEBUG
 
-int closure_debug_init(void);
+void closure_debug_init(void);
 void closure_debug_create(struct closure *cl);
 void closure_debug_destroy(struct closure *cl);
 
 #else
 
-static inline int closure_debug_init(void) { return 0; }
+static inline void closure_debug_init(void) {}
 static inline void closure_debug_create(struct closure *cl) {}
 static inline void closure_debug_destroy(struct closure *cl) {}
 
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index d030ce3025a6..12034c07257b 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -110,11 +110,15 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 	struct bio_vec bv, cbv;
 	struct bvec_iter iter, citer = { 0 };
 
-	check = bio_clone_kmalloc(bio, GFP_NOIO);
+	check = bio_kmalloc(GFP_NOIO, bio_segments(bio));
 	if (!check)
 		return;
+	check->bi_disk = bio->bi_disk;
 	check->bi_opf = REQ_OP_READ;
+	check->bi_iter.bi_sector = bio->bi_iter.bi_sector;
+	check->bi_iter.bi_size = bio->bi_iter.bi_size;
 
+	bch_bio_map(check, NULL);
 	if (bch_bio_alloc_pages(check, GFP_NOIO))
 		goto out_put;
 
@@ -248,11 +252,12 @@ void bch_debug_exit(void)
 		debugfs_remove_recursive(bcache_debug);
 }
 
-int __init bch_debug_init(struct kobject *kobj)
+void __init bch_debug_init(struct kobject *kobj)
 {
-	if (!IS_ENABLED(CONFIG_DEBUG_FS))
-		return 0;
-
+	/*
+	 * it is unnecessary to check return value of
+	 * debugfs_create_file(), we should not care
+	 * about this.
+	 */
 	bcache_debug = debugfs_create_dir("bcache", NULL);
-	return IS_ERR_OR_NULL(bcache_debug);
 }
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 18f1b5239620..10748c626a1d 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -828,6 +828,7 @@ void bch_journal_free(struct cache_set *c)
 	free_pages((unsigned long) c->journal.w[1].data, JSET_BITS);
 	free_pages((unsigned long) c->journal.w[0].data, JSET_BITS);
 	free_fifo(&c->journal.pin);
+	free_heap(&c->flush_btree);
 }
 
 int bch_journal_alloc(struct cache_set *c)
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index ae67f5fa8047..7dbe8b6316a0 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -107,7 +107,7 @@ static int bch_keylist_realloc(struct keylist *l, unsigned u64s,
 	/*
 	 * The journalling code doesn't handle the case where the keys to insert
 	 * is bigger than an empty write: If we just return -ENOMEM here,
-	 * bio_insert() and bio_invalidate() will insert the keys created so far
+	 * bch_data_insert_keys() will insert the keys created so far
 	 * and finish the rest when the keylist is empty.
 	 */
 	if (newsize * sizeof(uint64_t) > block_bytes(c) - sizeof(struct jset))
@@ -667,8 +667,7 @@ static void backing_request_endio(struct bio *bio)
 static void bio_complete(struct search *s)
 {
 	if (s->orig_bio) {
-		generic_end_io_acct(s->d->disk->queue,
-				    bio_data_dir(s->orig_bio),
+		generic_end_io_acct(s->d->disk->queue, bio_op(s->orig_bio),
 				    &s->d->disk->part0, s->start_time);
 
 		trace_bcache_request_end(s->d, s->orig_bio);
@@ -702,6 +701,8 @@ static void search_free(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 
+	atomic_dec(&s->d->c->search_inflight);
+
 	if (s->iop.bio)
 		bio_put(s->iop.bio);
 
@@ -719,6 +720,7 @@ static inline struct search *search_alloc(struct bio *bio,
 
 	closure_init(&s->cl, NULL);
 	do_bio_hook(s, bio, request_endio);
+	atomic_inc(&d->c->search_inflight);
 
 	s->orig_bio		= bio;
 	s->cache_miss		= NULL;
@@ -1062,8 +1064,7 @@ static void detached_dev_end_io(struct bio *bio)
 	bio->bi_end_io = ddip->bi_end_io;
 	bio->bi_private = ddip->bi_private;
 
-	generic_end_io_acct(ddip->d->disk->queue,
-			    bio_data_dir(bio),
+	generic_end_io_acct(ddip->d->disk->queue, bio_op(bio),
 			    &ddip->d->disk->part0, ddip->start_time);
 
 	if (bio->bi_status) {
@@ -1102,6 +1103,44 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
 		generic_make_request(bio);
 }
 
+static void quit_max_writeback_rate(struct cache_set *c,
+				    struct cached_dev *this_dc)
+{
+	int i;
+	struct bcache_device *d;
+	struct cached_dev *dc;
+
+	/*
+	 * mutex bch_register_lock may compete with other parallel requesters,
+	 * or attach/detach operations on other backing device. Waiting to
+	 * the mutex lock may increase I/O request latency for seconds or more.
+	 * To avoid such situation, if mutext_trylock() failed, only writeback
+	 * rate of current cached device is set to 1, and __update_write_back()
+	 * will decide writeback rate of other cached devices (remember now
+	 * c->idle_counter is 0 already).
+	 */
+	if (mutex_trylock(&bch_register_lock)) {
+		for (i = 0; i < c->devices_max_used; i++) {
+			if (!c->devices[i])
+				continue;
+
+			if (UUID_FLASH_ONLY(&c->uuids[i]))
+				continue;
+
+			d = c->devices[i];
+			dc = container_of(d, struct cached_dev, disk);
+			/*
+			 * set writeback rate to default minimum value,
+			 * then let update_writeback_rate() to decide the
+			 * upcoming rate.
+			 */
+			atomic_long_set(&dc->writeback_rate.rate, 1);
+		}
+		mutex_unlock(&bch_register_lock);
+	} else
+		atomic_long_set(&this_dc->writeback_rate.rate, 1);
+}
+
 /* Cached devices - read & write stuff */
 
 static blk_qc_t cached_dev_make_request(struct request_queue *q,
@@ -1119,8 +1158,25 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
 		return BLK_QC_T_NONE;
 	}
 
-	atomic_set(&dc->backing_idle, 0);
-	generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0);
+	if (likely(d->c)) {
+		if (atomic_read(&d->c->idle_counter))
+			atomic_set(&d->c->idle_counter, 0);
+		/*
+		 * If at_max_writeback_rate of cache set is true and new I/O
+		 * comes, quit max writeback rate of all cached devices
+		 * attached to this cache set, and set at_max_writeback_rate
+		 * to false.
+		 */
+		if (unlikely(atomic_read(&d->c->at_max_writeback_rate) == 1)) {
+			atomic_set(&d->c->at_max_writeback_rate, 0);
+			quit_max_writeback_rate(d->c, dc);
+		}
+	}
+
+	generic_start_io_acct(q,
+			      bio_op(bio),
+			      bio_sectors(bio),
+			      &d->disk->part0);
 
 	bio_set_dev(bio, dc->bdev);
 	bio->bi_iter.bi_sector += dc->sb.data_offset;
@@ -1229,7 +1285,6 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 	struct search *s;
 	struct closure *cl;
 	struct bcache_device *d = bio->bi_disk->private_data;
-	int rw = bio_data_dir(bio);
 
 	if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) {
 		bio->bi_status = BLK_STS_IOERR;
@@ -1237,7 +1292,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 		return BLK_QC_T_NONE;
 	}
 
-	generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0);
+	generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0);
 
 	s = search_alloc(bio, d);
 	cl = &s->cl;
@@ -1254,7 +1309,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 				      flash_dev_nodata,
 				      bcache_wq);
 		return BLK_QC_T_NONE;
-	} else if (rw) {
+	} else if (bio_data_dir(bio)) {
 		bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
 					&KEY(d->id, bio->bi_iter.bi_sector, 0),
 					&KEY(d->id, bio_end_sector(bio), 0));
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index fa4058e43202..55a37641aa95 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -181,7 +181,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 		goto err;
 	}
 
-	sb->last_mount = get_seconds();
+	sb->last_mount = (u32)ktime_get_real_seconds();
 	err = NULL;
 
 	get_page(bh->b_page);
@@ -696,12 +696,14 @@ static void bcache_device_detach(struct bcache_device *d)
 {
 	lockdep_assert_held(&bch_register_lock);
 
+	atomic_dec(&d->c->attached_dev_nr);
+
 	if (test_bit(BCACHE_DEV_DETACHING, &d->flags)) {
 		struct uuid_entry *u = d->c->uuids + d->id;
 
 		SET_UUID_FLASH_ONLY(u, 0);
 		memcpy(u->uuid, invalid_uuid, 16);
-		u->invalidated = cpu_to_le32(get_seconds());
+		u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
 		bch_uuid_write(d->c);
 	}
 
@@ -796,11 +798,12 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 		return idx;
 
 	if (bioset_init(&d->bio_split, 4, offsetof(struct bbio, bio),
-			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
-	    !(d->disk = alloc_disk(BCACHE_MINORS))) {
-		ida_simple_remove(&bcache_device_idx, idx);
-		return -ENOMEM;
-	}
+			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
+		goto err;
+
+	d->disk = alloc_disk(BCACHE_MINORS);
+	if (!d->disk)
+		goto err;
 
 	set_capacity(d->disk, sectors);
 	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
@@ -834,6 +837,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	blk_queue_write_cache(q, true, true);
 
 	return 0;
+
+err:
+	ida_simple_remove(&bcache_device_idx, idx);
+	return -ENOMEM;
+
 }
 
 /* Cached device */
@@ -1027,7 +1035,7 @@ void bch_cached_dev_detach(struct cached_dev *dc)
 int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 			  uint8_t *set_uuid)
 {
-	uint32_t rtime = cpu_to_le32(get_seconds());
+	uint32_t rtime = cpu_to_le32((u32)ktime_get_real_seconds());
 	struct uuid_entry *u;
 	struct cached_dev *exist_dc, *t;
 
@@ -1070,7 +1078,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	    (BDEV_STATE(&dc->sb) == BDEV_STATE_STALE ||
 	     BDEV_STATE(&dc->sb) == BDEV_STATE_NONE)) {
 		memcpy(u->uuid, invalid_uuid, 16);
-		u->invalidated = cpu_to_le32(get_seconds());
+		u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
 		u = NULL;
 	}
 
@@ -1138,6 +1146,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 
 	bch_cached_dev_run(dc);
 	bcache_device_link(&dc->disk, c, "bdev");
+	atomic_inc(&c->attached_dev_nr);
 
 	/* Allow the writeback thread to proceed */
 	up_write(&dc->writeback_lock);
@@ -1285,6 +1294,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 	pr_info("registered backing device %s", dc->backing_dev_name);
 
 	list_add(&dc->list, &uncached_devices);
+	/* attach to a matched cache set if it exists */
 	list_for_each_entry(c, &bch_cache_sets, list)
 		bch_cached_dev_attach(dc, c, NULL);
 
@@ -1311,6 +1321,8 @@ static void flash_dev_free(struct closure *cl)
 {
 	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
 	mutex_lock(&bch_register_lock);
+	atomic_long_sub(bcache_dev_sectors_dirty(d),
+			&d->c->flash_dev_dirty_sectors);
 	bcache_device_free(d);
 	mutex_unlock(&bch_register_lock);
 	kobject_put(&d->kobj);
@@ -1390,7 +1402,7 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size)
 
 	get_random_bytes(u->uuid, 16);
 	memset(u->label, 0, 32);
-	u->first_reg = u->last_reg = cpu_to_le32(get_seconds());
+	u->first_reg = u->last_reg = cpu_to_le32((u32)ktime_get_real_seconds());
 
 	SET_UUID_FLASH_ONLY(u, 1);
 	u->sectors = size >> 9;
@@ -1687,6 +1699,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	c->block_bits		= ilog2(sb->block_size);
 	c->nr_uuids		= bucket_bytes(c) / sizeof(struct uuid_entry);
 	c->devices_max_used	= 0;
+	atomic_set(&c->attached_dev_nr, 0);
 	c->btree_pages		= bucket_pages(c);
 	if (c->btree_pages > BTREE_MAX_PAGES)
 		c->btree_pages = max_t(int, c->btree_pages / 4,
@@ -1894,7 +1907,7 @@ static void run_cache_set(struct cache_set *c)
 		goto err;
 
 	closure_sync(&cl);
-	c->sb.last_mount = get_seconds();
+	c->sb.last_mount = (u32)ktime_get_real_seconds();
 	bcache_write_super(c);
 
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
@@ -2163,8 +2176,12 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (!try_module_get(THIS_MODULE))
 		return -EBUSY;
 
-	if (!(path = kstrndup(buffer, size, GFP_KERNEL)) ||
-	    !(sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL)))
+	path = kstrndup(buffer, size, GFP_KERNEL);
+	if (!path)
+		goto err;
+
+	sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL);
+	if (!sb)
 		goto err;
 
 	err = "failed to open device";
@@ -2324,13 +2341,21 @@ static int __init bcache_init(void)
 		return bcache_major;
 	}
 
-	if (!(bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0)) ||
-	    !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
-	    bch_request_init() ||
-	    bch_debug_init(bcache_kobj) || closure_debug_init() ||
+	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
+	if (!bcache_wq)
+		goto err;
+
+	bcache_kobj = kobject_create_and_add("bcache", fs_kobj);
+	if (!bcache_kobj)
+		goto err;
+
+	if (bch_request_init() ||
 	    sysfs_create_files(bcache_kobj, files))
 		goto err;
 
+	bch_debug_init(bcache_kobj);
+	closure_debug_init();
+
 	return 0;
 err:
 	bcache_exit();
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 225b15aa0340..81d3520b0702 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -149,6 +149,7 @@ SHOW(__bch_cached_dev)
 	struct cached_dev *dc = container_of(kobj, struct cached_dev,
 					     disk.kobj);
 	const char *states[] = { "no cache", "clean", "dirty", "inconsistent" };
+	int wb = dc->writeback_running;
 
 #define var(stat)		(dc->stat)
 
@@ -170,7 +171,8 @@ SHOW(__bch_cached_dev)
 	var_printf(writeback_running,	"%i");
 	var_print(writeback_delay);
 	var_print(writeback_percent);
-	sysfs_hprint(writeback_rate,	dc->writeback_rate.rate << 9);
+	sysfs_hprint(writeback_rate,
+		     wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0);
 	sysfs_hprint(io_errors,		atomic_read(&dc->io_errors));
 	sysfs_printf(io_error_limit,	"%i", dc->error_limit);
 	sysfs_printf(io_disable,	"%i", dc->io_disable);
@@ -188,15 +190,22 @@ SHOW(__bch_cached_dev)
 		char change[20];
 		s64 next_io;
 
-		bch_hprint(rate,	dc->writeback_rate.rate << 9);
-		bch_hprint(dirty,	bcache_dev_sectors_dirty(&dc->disk) << 9);
-		bch_hprint(target,	dc->writeback_rate_target << 9);
-		bch_hprint(proportional,dc->writeback_rate_proportional << 9);
-		bch_hprint(integral,	dc->writeback_rate_integral_scaled << 9);
-		bch_hprint(change,	dc->writeback_rate_change << 9);
-
-		next_io = div64_s64(dc->writeback_rate.next - local_clock(),
-				    NSEC_PER_MSEC);
+		/*
+		 * Except for dirty and target, other values should
+		 * be 0 if writeback is not running.
+		 */
+		bch_hprint(rate,
+			   wb ? atomic_long_read(&dc->writeback_rate.rate) << 9
+			      : 0);
+		bch_hprint(dirty, bcache_dev_sectors_dirty(&dc->disk) << 9);
+		bch_hprint(target, dc->writeback_rate_target << 9);
+		bch_hprint(proportional,
+			   wb ? dc->writeback_rate_proportional << 9 : 0);
+		bch_hprint(integral,
+			   wb ? dc->writeback_rate_integral_scaled << 9 : 0);
+		bch_hprint(change, wb ? dc->writeback_rate_change << 9 : 0);
+		next_io = wb ? div64_s64(dc->writeback_rate.next-local_clock(),
+					 NSEC_PER_MSEC) : 0;
 
 		return sprintf(buf,
 			       "rate:\t\t%s/sec\n"
@@ -255,8 +264,19 @@ STORE(__cached_dev)
 
 	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40);
 
-	sysfs_strtoul_clamp(writeback_rate,
-			    dc->writeback_rate.rate, 1, INT_MAX);
+	if (attr == &sysfs_writeback_rate) {
+		ssize_t ret;
+		long int v = atomic_long_read(&dc->writeback_rate.rate);
+
+		ret = strtoul_safe_clamp(buf, v, 1, INT_MAX);
+
+		if (!ret) {
+			atomic_long_set(&dc->writeback_rate.rate, v);
+			ret = size;
+		}
+
+		return ret;
+	}
 
 	sysfs_strtoul_clamp(writeback_rate_update_seconds,
 			    dc->writeback_rate_update_seconds,
@@ -338,8 +358,8 @@ STORE(__cached_dev)
 			if (!v)
 				return size;
 		}
-
-		pr_err("Can't attach %s: cache set not found", buf);
+		if (v == -ENOENT)
+			pr_err("Can't attach %s: cache set not found", buf);
 		return v;
 	}
 
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index fc479b026d6d..b15256bcf0e7 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -200,7 +200,7 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
 {
 	uint64_t now = local_clock();
 
-	d->next += div_u64(done * NSEC_PER_SEC, d->rate);
+	d->next += div_u64(done * NSEC_PER_SEC, atomic_long_read(&d->rate));
 
 	/* Bound the time.  Don't let us fall further than 2 seconds behind
 	 * (this prevents unnecessary backlog that would make it impossible
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index cced87f8eb27..f7b0133c9d2f 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -442,7 +442,7 @@ struct bch_ratelimit {
 	 * Rate at which we want to do work, in units per second
 	 * The units here correspond to the units passed to bch_next_delay()
 	 */
-	uint32_t		rate;
+	atomic_long_t		rate;
 };
 
 static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index ad45ebe1a74b..481d4cf38ac0 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -27,7 +27,7 @@ static uint64_t __calc_target_rate(struct cached_dev *dc)
 	 * flash-only devices
 	 */
 	uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size -
-				bcache_flash_devs_sectors_dirty(c);
+				atomic_long_read(&c->flash_dev_dirty_sectors);
 
 	/*
 	 * Unfortunately there is no control of global dirty data.  If the
@@ -104,11 +104,56 @@ static void __update_writeback_rate(struct cached_dev *dc)
 
 	dc->writeback_rate_proportional = proportional_scaled;
 	dc->writeback_rate_integral_scaled = integral_scaled;
-	dc->writeback_rate_change = new_rate - dc->writeback_rate.rate;
-	dc->writeback_rate.rate = new_rate;
+	dc->writeback_rate_change = new_rate -
+			atomic_long_read(&dc->writeback_rate.rate);
+	atomic_long_set(&dc->writeback_rate.rate, new_rate);
 	dc->writeback_rate_target = target;
 }
 
+static bool set_at_max_writeback_rate(struct cache_set *c,
+				       struct cached_dev *dc)
+{
+	/*
+	 * Idle_counter is increased everytime when update_writeback_rate() is
+	 * called. If all backing devices attached to the same cache set have
+	 * identical dc->writeback_rate_update_seconds values, it is about 6
+	 * rounds of update_writeback_rate() on each backing device before
+	 * c->at_max_writeback_rate is set to 1, and then max wrteback rate set
+	 * to each dc->writeback_rate.rate.
+	 * In order to avoid extra locking cost for counting exact dirty cached
+	 * devices number, c->attached_dev_nr is used to calculate the idle
+	 * throushold. It might be bigger if not all cached device are in write-
+	 * back mode, but it still works well with limited extra rounds of
+	 * update_writeback_rate().
+	 */
+	if (atomic_inc_return(&c->idle_counter) <
+	    atomic_read(&c->attached_dev_nr) * 6)
+		return false;
+
+	if (atomic_read(&c->at_max_writeback_rate) != 1)
+		atomic_set(&c->at_max_writeback_rate, 1);
+
+	atomic_long_set(&dc->writeback_rate.rate, INT_MAX);
+
+	/* keep writeback_rate_target as existing value */
+	dc->writeback_rate_proportional = 0;
+	dc->writeback_rate_integral_scaled = 0;
+	dc->writeback_rate_change = 0;
+
+	/*
+	 * Check c->idle_counter and c->at_max_writeback_rate agagain in case
+	 * new I/O arrives during before set_at_max_writeback_rate() returns.
+	 * Then the writeback rate is set to 1, and its new value should be
+	 * decided via __update_writeback_rate().
+	 */
+	if ((atomic_read(&c->idle_counter) <
+	     atomic_read(&c->attached_dev_nr) * 6) ||
+	    !atomic_read(&c->at_max_writeback_rate))
+		return false;
+
+	return true;
+}
+
 static void update_writeback_rate(struct work_struct *work)
 {
 	struct cached_dev *dc = container_of(to_delayed_work(work),
@@ -136,13 +181,20 @@ static void update_writeback_rate(struct work_struct *work)
 		return;
 	}
 
-	down_read(&dc->writeback_lock);
-
-	if (atomic_read(&dc->has_dirty) &&
-	    dc->writeback_percent)
-		__update_writeback_rate(dc);
+	if (atomic_read(&dc->has_dirty) && dc->writeback_percent) {
+		/*
+		 * If the whole cache set is idle, set_at_max_writeback_rate()
+		 * will set writeback rate to a max number. Then it is
+		 * unncessary to update writeback rate for an idle cache set
+		 * in maximum writeback rate number(s).
+		 */
+		if (!set_at_max_writeback_rate(c, dc)) {
+			down_read(&dc->writeback_lock);
+			__update_writeback_rate(dc);
+			up_read(&dc->writeback_lock);
+		}
+	}
 
-	up_read(&dc->writeback_lock);
 
 	/*
 	 * CACHE_SET_IO_DISABLE might be set via sysfs interface,
@@ -422,27 +474,6 @@ static void read_dirty(struct cached_dev *dc)
 
 		delay = writeback_delay(dc, size);
 
-		/* If the control system would wait for at least half a
-		 * second, and there's been no reqs hitting the backing disk
-		 * for awhile: use an alternate mode where we have at most
-		 * one contiguous set of writebacks in flight at a time.  If
-		 * someone wants to do IO it will be quick, as it will only
-		 * have to contend with one operation in flight, and we'll
-		 * be round-tripping data to the backing disk as quickly as
-		 * it can accept it.
-		 */
-		if (delay >= HZ / 2) {
-			/* 3 means at least 1.5 seconds, up to 7.5 if we
-			 * have slowed way down.
-			 */
-			if (atomic_inc_return(&dc->backing_idle) >= 3) {
-				/* Wait for current I/Os to finish */
-				closure_sync(&cl);
-				/* And immediately launch a new set. */
-				delay = 0;
-			}
-		}
-
 		while (!kthread_should_stop() &&
 		       !test_bit(CACHE_SET_IO_DISABLE, &dc->disk.c->flags) &&
 		       delay) {
@@ -476,6 +507,9 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
 	if (!d)
 		return;
 
+	if (UUID_FLASH_ONLY(&c->uuids[inode]))
+		atomic_long_add(nr_sectors, &c->flash_dev_dirty_sectors);
+
 	stripe = offset_to_stripe(d, offset);
 	stripe_offset = offset & (d->stripe_size - 1);
 
@@ -673,10 +707,14 @@ static int bch_writeback_thread(void *arg)
 }
 
 /* Init */
+#define INIT_KEYS_EACH_TIME	500000
+#define INIT_KEYS_SLEEP_MS	100
 
 struct sectors_dirty_init {
 	struct btree_op	op;
 	unsigned	inode;
+	size_t		count;
+	struct bkey	start;
 };
 
 static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
@@ -691,18 +729,37 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
 		bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k),
 					     KEY_START(k), KEY_SIZE(k));
 
+	op->count++;
+	if (atomic_read(&b->c->search_inflight) &&
+	    !(op->count % INIT_KEYS_EACH_TIME)) {
+		bkey_copy_key(&op->start, k);
+		return -EAGAIN;
+	}
+
 	return MAP_CONTINUE;
 }
 
 void bch_sectors_dirty_init(struct bcache_device *d)
 {
 	struct sectors_dirty_init op;
+	int ret;
 
 	bch_btree_op_init(&op.op, -1);
 	op.inode = d->id;
-
-	bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0),
-			   sectors_dirty_init_fn, 0);
+	op.count = 0;
+	op.start = KEY(op.inode, 0, 0);
+
+	do {
+		ret = bch_btree_map_keys(&op.op, d->c, &op.start,
+					 sectors_dirty_init_fn, 0);
+		if (ret == -EAGAIN)
+			schedule_timeout_interruptible(
+				msecs_to_jiffies(INIT_KEYS_SLEEP_MS));
+		else if (ret < 0) {
+			pr_warn("sectors dirty init failed, ret=%d!", ret);
+			break;
+		}
+	} while (ret == -EAGAIN);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
@@ -715,7 +772,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 	dc->writeback_running		= true;
 	dc->writeback_percent		= 10;
 	dc->writeback_delay		= 30;
-	dc->writeback_rate.rate		= 1024;
+	atomic_long_set(&dc->writeback_rate.rate, 1024);
 	dc->writeback_rate_minimum	= 8;
 
 	dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 610fb01de629..3745d7004c47 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -28,25 +28,6 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
 	return ret;
 }
 
-static inline uint64_t  bcache_flash_devs_sectors_dirty(struct cache_set *c)
-{
-	uint64_t i, ret = 0;
-
-	mutex_lock(&bch_register_lock);
-
-	for (i = 0; i < c->devices_max_used; i++) {
-		struct bcache_device *d = c->devices[i];
-
-		if (!d || !UUID_FLASH_ONLY(&c->uuids[i]))
-			continue;
-		ret += bcache_dev_sectors_dirty(d);
-	}
-
-	mutex_unlock(&bch_register_lock);
-
-	return ret;
-}
-
 static inline unsigned offset_to_stripe(struct bcache_device *d,
 					uint64_t offset)
 {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b0dd7027848b..20f7e4ef5342 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -609,7 +609,8 @@ static void start_io_acct(struct dm_io *io)
 
 	io->start_time = jiffies;
 
-	generic_start_io_acct(md->queue, rw, bio_sectors(bio), &dm_disk(md)->part0);
+	generic_start_io_acct(md->queue, bio_op(bio), bio_sectors(bio),
+			      &dm_disk(md)->part0);
 
 	atomic_set(&dm_disk(md)->part0.in_flight[rw],
 		   atomic_inc_return(&md->pending[rw]));
@@ -628,7 +629,8 @@ static void end_io_acct(struct dm_io *io)
 	int pending;
 	int rw = bio_data_dir(bio);
 
-	generic_end_io_acct(md->queue, rw, &dm_disk(md)->part0, io->start_time);
+	generic_end_io_acct(md->queue, bio_op(bio), &dm_disk(md)->part0,
+			    io->start_time);
 
 	if (unlikely(dm_stats_used(&md->stats)))
 		dm_stats_account_io(&md->stats, bio_data_dir(bio),
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 021cbf9ef1bf..e8a74e92be30 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -304,15 +304,6 @@ static void recover_bitmaps(struct md_thread *thread)
 	while (cinfo->recovery_map) {
 		slot = fls64((u64)cinfo->recovery_map) - 1;
 
-		/* Clear suspend_area associated with the bitmap */
-		spin_lock_irq(&cinfo->suspend_lock);
-		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
-			if (slot == s->slot) {
-				list_del(&s->list);
-				kfree(s);
-			}
-		spin_unlock_irq(&cinfo->suspend_lock);
-
 		snprintf(str, 64, "bitmap%04d", slot);
 		bm_lockres = lockres_init(mddev, str, NULL, 1);
 		if (!bm_lockres) {
@@ -331,14 +322,30 @@ static void recover_bitmaps(struct md_thread *thread)
 			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
 			goto clear_bit;
 		}
+
+		/* Clear suspend_area associated with the bitmap */
+		spin_lock_irq(&cinfo->suspend_lock);
+		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
+			if (slot == s->slot) {
+				list_del(&s->list);
+				kfree(s);
+			}
+		spin_unlock_irq(&cinfo->suspend_lock);
+
 		if (hi > 0) {
 			if (lo < mddev->recovery_cp)
 				mddev->recovery_cp = lo;
 			/* wake up thread to continue resync in case resync
 			 * is not finished */
 			if (mddev->recovery_cp != MaxSector) {
-			    set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			    md_wakeup_thread(mddev->thread);
+				/*
+				 * clear the REMOTE flag since we will launch
+				 * resync thread in current node.
+				 */
+				clear_bit(MD_RESYNCING_REMOTE,
+					  &mddev->recovery);
+				set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+				md_wakeup_thread(mddev->thread);
 			}
 		}
 clear_bit:
@@ -457,6 +464,11 @@ static void process_suspend_info(struct mddev *mddev,
 	struct suspend_info *s;
 
 	if (!hi) {
+		/*
+		 * clear the REMOTE flag since resync or recovery is finished
+		 * in remote node.
+		 */
+		clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 		remove_suspend_info(mddev, slot);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
@@ -585,6 +597,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 		revalidate_disk(mddev->gendisk);
 		break;
 	case RESYNCING:
+		set_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 		process_suspend_info(mddev, le32_to_cpu(msg->slot),
 				     le64_to_cpu(msg->low),
 				     le64_to_cpu(msg->high));
@@ -1265,8 +1278,18 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
 static int resync_finish(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
+
+	clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 	dlm_unlock_sync(cinfo->resync_lockres);
-	return resync_info_update(mddev, 0, 0);
+
+	/*
+	 * If resync thread is interrupted so we can't say resync is finished,
+	 * another node will launch resync thread to continue.
+	 */
+	if (test_bit(MD_CLOSING, &mddev->flags))
+		return 0;
+	else
+		return resync_info_update(mddev, 0, 0);
 }
 
 static int area_resyncing(struct mddev *mddev, int direction,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 994aed2f9dff..724def2f9eaa 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -204,10 +204,6 @@ static int start_readonly;
  */
 static bool create_on_open = true;
 
-/* bio_clone_mddev
- * like bio_clone_bioset, but with a local bio set
- */
-
 struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 			    struct mddev *mddev)
 {
@@ -335,6 +331,7 @@ EXPORT_SYMBOL(md_handle_request);
 static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
+	const int sgrp = op_stat_group(bio_op(bio));
 	struct mddev *mddev = q->queuedata;
 	unsigned int sectors;
 	int cpu;
@@ -363,8 +360,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 	md_handle_request(mddev, bio);
 
 	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
+	part_stat_inc(cpu, &mddev->gendisk->part0, ios[sgrp]);
+	part_stat_add(cpu, &mddev->gendisk->part0, sectors[sgrp], sectors);
 	part_stat_unlock();
 
 	return BLK_QC_T_NONE;
@@ -7680,6 +7677,23 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 		resync -= atomic_read(&mddev->recovery_active);
 
 	if (resync == 0) {
+		if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery)) {
+			struct md_rdev *rdev;
+
+			rdev_for_each(rdev, mddev)
+				if (rdev->raid_disk >= 0 &&
+				    !test_bit(Faulty, &rdev->flags) &&
+				    rdev->recovery_offset != MaxSector &&
+				    rdev->recovery_offset) {
+					seq_printf(seq, "\trecover=REMOTE");
+					return 1;
+				}
+			if (mddev->reshape_position != MaxSector)
+				seq_printf(seq, "\treshape=REMOTE");
+			else
+				seq_printf(seq, "\tresync=REMOTE");
+			return 1;
+		}
 		if (mddev->recovery_cp < MaxSector) {
 			seq_printf(seq, "\tresync=PENDING");
 			return 1;
@@ -8046,8 +8060,7 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_contains->bd_disk;
-		curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
-			      (int)part_stat_read(&disk->part0, sectors[1]) -
+		curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2d148bdaba74..8afd6bfdbfb9 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -496,6 +496,7 @@ enum recovery_flags {
 	MD_RECOVERY_FROZEN,	/* User request to abort, and not restart, any action */
 	MD_RECOVERY_ERROR,	/* sync-action interrupted because io-error */
 	MD_RECOVERY_WAIT,	/* waiting for pers->start() to finish */
+	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
 static inline int __must_check mddev_lock(struct mddev *mddev)
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 2b775abf377b..7416db70c6cc 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -717,7 +717,6 @@ static void r5c_disable_writeback_async(struct work_struct *work)
 static void r5l_submit_current_io(struct r5l_log *log)
 {
 	struct r5l_io_unit *io = log->current_io;
-	struct bio *bio;
 	struct r5l_meta_block *block;
 	unsigned long flags;
 	u32 crc;
@@ -730,7 +729,6 @@ static void r5l_submit_current_io(struct r5l_log *log)
 	block->meta_size = cpu_to_le32(io->meta_offset);
 	crc = crc32c_le(log->uuid_checksum, block, PAGE_SIZE);
 	block->checksum = cpu_to_le32(crc);
-	bio = io->current_bio;
 
 	log->current_io = NULL;
 	spin_lock_irqsave(&log->io_list_lock, flags);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2031506a0ecd..81eaa221216c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -409,16 +409,14 @@ void raid5_release_stripe(struct stripe_head *sh)
 		md_wakeup_thread(conf->mddev->thread);
 	return;
 slow_path:
-	local_irq_save(flags);
 	/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
-	if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
+	if (atomic_dec_and_lock_irqsave(&sh->count, &conf->device_lock, flags)) {
 		INIT_LIST_HEAD(&list);
 		hash = sh->hash_lock_index;
 		do_release_stripe(conf, sh, &list);
-		spin_unlock(&conf->device_lock);
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		release_inactive_stripe_list(conf, &list, hash);
 	}
-	local_irq_restore(flags);
 }
 
 static inline void remove_hash(struct stripe_head *sh)
@@ -4521,6 +4519,12 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			s->failed++;
 			if (rdev && !test_bit(Faulty, &rdev->flags))
 				do_recovery = 1;
+			else if (!rdev) {
+				rdev = rcu_dereference(
+				    conf->disks[i].replacement);
+				if (rdev && !test_bit(Faulty, &rdev->flags))
+					do_recovery = 1;
+			}
 		}
 
 		if (test_bit(R5_InJournal, &dev->flags))
diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index 8d731d6c3e54..63389f075f1d 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -116,12 +116,14 @@ config FSL_CORENET_CF
 
 config FSL_IFC
 	bool
-	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
+	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+	depends on HAS_IOMEM
 
 config JZ4780_NEMC
 	bool "Ingenic JZ4780 SoC NEMC driver"
 	default y
-	depends on MACH_JZ4780
+	depends on MACH_JZ4780 || COMPILE_TEST
+	depends on HAS_IOMEM && OF
 	help
 	  This driver is for the NAND/External Memory Controller (NEMC) in
 	  the Ingenic JZ4780. This controller is used to handle external
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 6b16946f9b05..8fd5ec4d6042 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -67,10 +67,8 @@ static struct file *cxl_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	/* strongly inspired by anon_inode_getfile() */
@@ -91,23 +89,11 @@ static struct file *cxl_getfile(const char *name,
 		goto err_fs;
 	}
 
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(cxl_vfs_mount->mnt_sb, &this);
-	if (!path.dentry)
+	file = alloc_file_pseudo(inode, cxl_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
+	if (IS_ERR(file))
 		goto err_inode;
 
-	path.mnt = mntget(cxl_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
-	if (IS_ERR(file)) {
-		path_put(&path);
-		goto err_fs;
-	}
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index 46ab7feec6b6..c77f537323ec 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -24,7 +24,7 @@ config MTD_TESTS
 
 config MTD_REDBOOT_PARTS
 	tristate "RedBoot partition table parsing"
-	---help---
+	help
 	  RedBoot is a ROM monitor and bootloader which deals with multiple
 	  'images' in flash devices by putting a table one of the erase
 	  blocks on the device, similar to a partition table, which gives
@@ -45,7 +45,7 @@ if MTD_REDBOOT_PARTS
 config MTD_REDBOOT_DIRECTORY_BLOCK
 	int "Location of RedBoot partition table"
 	default "-1"
-	---help---
+	help
 	  This option is the Linux counterpart to the
 	  CYGNUM_REDBOOT_FIS_DIRECTORY_BLOCK RedBoot compile time
 	  option.
@@ -75,7 +75,7 @@ endif # MTD_REDBOOT_PARTS
 config MTD_CMDLINE_PARTS
 	tristate "Command line partition table parsing"
 	depends on MTD
-	---help---
+	help
 	  Allow generic configuration of the MTD partition tables via the kernel
 	  command line. Multiple flash resources are supported for hardware where
 	  different kinds of flash memory are available.
@@ -112,7 +112,7 @@ config MTD_CMDLINE_PARTS
 config MTD_AFS_PARTS
 	tristate "ARM Firmware Suite partition parsing"
 	depends on (ARM || ARM64)
-	---help---
+	help
 	  The ARM Firmware Suite allows the user to divide flash devices into
 	  multiple 'images'. Each such image has a header containing its name
 	  and offset/size etc.
@@ -136,7 +136,7 @@ config MTD_OF_PARTS
 
 config MTD_AR7_PARTS
 	tristate "TI AR7 partitioning support"
-	---help---
+	help
 	  TI AR7 partitioning support
 
 config MTD_BCM63XX_PARTS
@@ -170,7 +170,7 @@ config MTD_BLOCK
 	tristate "Caching block device access to MTD devices"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  Although most flash chips have an erase size too large to be useful
 	  as block devices, it is possible to use MTD devices which are based
 	  on RAM chips in this manner. This block device is a user of MTD
@@ -205,7 +205,7 @@ config FTL
 	tristate "FTL (Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the original Flash Translation Layer which
 	  is part of the PCMCIA specification. It uses a kind of pseudo-
 	  file system on a flash device to emulate a block device with
@@ -222,7 +222,7 @@ config NFTL
 	tristate "NFTL (NAND Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the NAND Flash Translation Layer which is
 	  used on M-Systems' DiskOnChip devices. It uses a kind of pseudo-
 	  file system on a flash device to emulate a block device with
@@ -246,7 +246,7 @@ config INFTL
 	tristate "INFTL (Inverse NAND Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the Inverse NAND Flash Translation
 	  Layer which is used on M-Systems' newer DiskOnChip devices. It
 	  uses a kind of pseudo-file system on a flash device to emulate
@@ -261,10 +261,10 @@ config INFTL
 	  not use it.
 
 config RFD_FTL
-        tristate "Resident Flash Disk (Flash Translation Layer) support"
+	tristate "Resident Flash Disk (Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the flash translation layer known
 	  as the Resident Flash Disk (RFD), as used by the Embedded BIOS
 	  of General Software. There is a blurb at:
@@ -308,7 +308,7 @@ config MTD_SWAP
 	select MTD_BLKDEVS
 	help
 	  Provides volatile block device driver on top of mtd partition
-          suitable for swapping.  The mapping of written blocks is not saved.
+	  suitable for swapping.  The mapping of written blocks is not saved.
 	  The driver provides wear leveling by storing erase counter into the
 	  OOB.
 
diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig
index bbfa1f129266..39ec32a29051 100644
--- a/drivers/mtd/chips/Kconfig
+++ b/drivers/mtd/chips/Kconfig
@@ -44,7 +44,7 @@ choice
 	prompt "Flash cmd/query data swapping"
 	depends on MTD_CFI_ADV_OPTIONS
 	default MTD_CFI_NOSWAP
-	---help---
+	help
 	  This option defines the way in which the CPU attempts to arrange
 	  data bits when writing the 'magic' commands to the chips. Saying
 	  'NO', which is the default when CONFIG_MTD_CFI_ADV_OPTIONS isn't
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 1b64ac8c5bc8..72428b6bfc47 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -1216,7 +1216,6 @@ static inline int do_read_secsi_onechip(struct map_info *map,
 					size_t grouplen)
 {
 	DECLARE_WAITQUEUE(wait, current);
-	unsigned long timeo = jiffies + HZ;
 
  retry:
 	mutex_lock(&chip->mutex);
@@ -1229,7 +1228,6 @@ static inline int do_read_secsi_onechip(struct map_info *map,
 
 		schedule();
 		remove_wait_queue(&chip->wq, &wait);
-		timeo = jiffies + HZ;
 
 		goto retry;
 	}
diff --git a/drivers/mtd/chips/gen_probe.c b/drivers/mtd/chips/gen_probe.c
index b57ceea21513..837b04ab96a9 100644
--- a/drivers/mtd/chips/gen_probe.c
+++ b/drivers/mtd/chips/gen_probe.c
@@ -202,16 +202,19 @@ static inline struct mtd_info *cfi_cmdset_unknown(struct map_info *map,
 	struct cfi_private *cfi = map->fldrv_priv;
 	__u16 type = primary?cfi->cfiq->P_ID:cfi->cfiq->A_ID;
 #ifdef CONFIG_MODULES
-	char probename[sizeof(VMLINUX_SYMBOL_STR(cfi_cmdset_%4.4X))];
 	cfi_cmdset_fn_t *probe_function;
+	char *probename;
 
-	sprintf(probename, VMLINUX_SYMBOL_STR(cfi_cmdset_%4.4X), type);
+	probename = kasprintf(GFP_KERNEL, "cfi_cmdset_%4.4X", type);
+	if (!probename)
+		return NULL;
 
 	probe_function = __symbol_get(probename);
 	if (!probe_function) {
 		request_module("cfi_cmdset_%4.4X", type);
 		probe_function = __symbol_get(probename);
 	}
+	kfree(probename);
 
 	if (probe_function) {
 		struct mtd_info *mtd;
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 57b02c4b3f63..e514d57a0419 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -5,7 +5,7 @@ menu "Self-contained MTD device drivers"
 config MTD_PMC551
 	tristate "Ramix PMC551 PCI Mezzanine RAM card support"
 	depends on PCI
-	---help---
+	help
 	  This provides a MTD device driver for the Ramix PMC551 RAM PCI card
 	  from Ramix Inc. <http://www.ramix.com/products/memory/pmc551.html>.
 	  These devices come in memory configurations from 32M - 1G.  If you
@@ -209,7 +209,7 @@ config MTD_DOCG3
 	select BCH
 	select BCH_CONST_PARAMS
 	select BITREVERSE
-	---help---
+	help
 	  This provides an MTD device driver for the M-Systems DiskOnChip
 	  G3 devices.
 
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index e84563d2067f..fe260ccb2d7d 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -28,11 +28,9 @@
 #include <linux/spi/flash.h>
 #include <linux/mtd/spi-nor.h>
 
-#define	MAX_CMD_SIZE		6
 struct m25p {
 	struct spi_mem		*spimem;
 	struct spi_nor		spi_nor;
-	u8			command[MAX_CMD_SIZE];
 };
 
 static int m25p80_read_reg(struct spi_nor *nor, u8 code, u8 *val, int len)
@@ -70,7 +68,7 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 1),
 				   SPI_MEM_OP_ADDR(nor->addr_width, to, 1),
-				   SPI_MEM_OP_DUMMY(0, 1),
+				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_OUT(len, buf, 1));
 	size_t remaining = len;
 	int ret;
@@ -78,7 +76,6 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	/* get transfer protocols. */
 	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->write_proto);
 	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->write_proto);
-	op.dummy.buswidth = op.addr.buswidth;
 	op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->write_proto);
 
 	if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c
index c1312b141ae0..33593122e49b 100644
--- a/drivers/mtd/devices/powernv_flash.c
+++ b/drivers/mtd/devices/powernv_flash.c
@@ -223,6 +223,7 @@ static int powernv_flash_set_driver_info(struct device *dev,
 	mtd->_read = powernv_flash_read;
 	mtd->_write = powernv_flash_write;
 	mtd->dev.parent = dev;
+	mtd_set_of_node(mtd, dev->of_node);
 	return 0;
 }
 
diff --git a/drivers/mtd/devices/sst25l.c b/drivers/mtd/devices/sst25l.c
index 1897f33fe3e7..10d24efb4629 100644
--- a/drivers/mtd/devices/sst25l.c
+++ b/drivers/mtd/devices/sst25l.c
@@ -394,9 +394,8 @@ static int sst25l_probe(struct spi_device *spi)
 	      flash->mtd.numeraseregions);
 
 
-	ret = mtd_device_parse_register(&flash->mtd, NULL, NULL,
-					data ? data->parts : NULL,
-					data ? data->nr_parts : 0);
+	ret = mtd_device_register(&flash->mtd, data ? data->parts : NULL,
+				  data ? data->nr_parts : 0);
 	if (ret)
 		return -ENODEV;
 
diff --git a/drivers/mtd/lpddr/Kconfig b/drivers/mtd/lpddr/Kconfig
index 3a19cbee24d7..a5a332fbd593 100644
--- a/drivers/mtd/lpddr/Kconfig
+++ b/drivers/mtd/lpddr/Kconfig
@@ -13,10 +13,10 @@ config MTD_QINFO_PROBE
 	depends on MTD_LPDDR
 	tristate "Detect flash chips by QINFO probe"
 	help
-	    Device Information for LPDDR chips is offered through the Overlay
-	    Window QINFO interface, permits software to be used for entire
-	    families of devices. This serves similar purpose of CFI on legacy
-	    Flash products
+	  Device Information for LPDDR chips is offered through the Overlay
+	  Window QINFO interface, permits software to be used for entire
+	  families of devices. This serves similar purpose of CFI on legacy
+	  Flash products
 
 config MTD_LPDDR2_NVM
 	# ARM dependency is only for writel_relaxed()
diff --git a/drivers/mtd/lpddr/lpddr2_nvm.c b/drivers/mtd/lpddr/lpddr2_nvm.c
index 5d73db2a496d..c950c880ad59 100644
--- a/drivers/mtd/lpddr/lpddr2_nvm.c
+++ b/drivers/mtd/lpddr/lpddr2_nvm.c
@@ -476,7 +476,7 @@ static int lpddr2_nvm_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 	/* Parse partitions and register the MTD device */
-	return mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+	return mtd_device_register(mtd, NULL, 0);
 }
 
 /*
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index bdc1283f30fb..afb36bff13a7 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -207,13 +207,13 @@ config MTD_ICHXROM
 	  BE VERY CAREFUL.
 
 config MTD_ESB2ROM
-        tristate "BIOS flash chip on Intel ESB Controller Hub 2"
-        depends on X86 && MTD_JEDECPROBE && PCI
-        help
-          Support for treating the BIOS flash chip on ESB2 motherboards
-          as an MTD device - with this you can reprogram your BIOS.
+	tristate "BIOS flash chip on Intel ESB Controller Hub 2"
+	depends on X86 && MTD_JEDECPROBE && PCI
+	help
+	  Support for treating the BIOS flash chip on ESB2 motherboards
+	  as an MTD device - with this you can reprogram your BIOS.
 
-          BE VERY CAREFUL.
+	  BE VERY CAREFUL.
 
 config MTD_CK804XROM
 	tristate "BIOS flash chip on Nvidia CK804"
@@ -401,12 +401,12 @@ config MTD_PISMO
 	  When built as a module, it will be called pismo.ko
 
 config MTD_LATCH_ADDR
-        tristate "Latch-assisted Flash Chip Support"
-        depends on MTD_COMPLEX_MAPPINGS
-        help
-          Map driver which allows flashes to be partially physically addressed
-          and have the upper address lines set by a board specific code.
+	tristate "Latch-assisted Flash Chip Support"
+	depends on MTD_COMPLEX_MAPPINGS
+	help
+	  Map driver which allows flashes to be partially physically addressed
+	  and have the upper address lines set by a board specific code.
 
-          If compiled as a module, it will be called latch-addr-flash.
+	  If compiled as a module, it will be called latch-addr-flash.
 
 endmenu
diff --git a/drivers/mtd/maps/gpio-addr-flash.c b/drivers/mtd/maps/gpio-addr-flash.c
index 385305e66fd1..9d9723693217 100644
--- a/drivers/mtd/maps/gpio-addr-flash.c
+++ b/drivers/mtd/maps/gpio-addr-flash.c
@@ -239,6 +239,9 @@ static int gpio_flash_probe(struct platform_device *pdev)
 	state->map.bankwidth  = pdata->width;
 	state->map.size       = state->win_size * (1 << state->gpio_count);
 	state->map.virt       = ioremap_nocache(memory->start, state->map.size);
+	if (!state->map.virt)
+		return -ENOMEM;
+
 	state->map.phys       = NO_XIP;
 	state->map.map_priv_1 = (unsigned long)state;
 
diff --git a/drivers/mtd/maps/impa7.c b/drivers/mtd/maps/impa7.c
index a0b8fa7849a9..815e2db87955 100644
--- a/drivers/mtd/maps/impa7.c
+++ b/drivers/mtd/maps/impa7.c
@@ -88,9 +88,8 @@ static int __init init_impa7(void)
 		if (impa7_mtd[i]) {
 			impa7_mtd[i]->owner = THIS_MODULE;
 			devicesfound++;
-			mtd_device_parse_register(impa7_mtd[i], NULL, NULL,
-						  partitions,
-						  ARRAY_SIZE(partitions));
+			mtd_device_register(impa7_mtd[i], partitions,
+					    ARRAY_SIZE(partitions));
 		} else {
 			iounmap((void __iomem *)impa7_map[i].virt);
 		}
diff --git a/drivers/mtd/maps/intel_vr_nor.c b/drivers/mtd/maps/intel_vr_nor.c
index dd5d6855f543..69503aef981e 100644
--- a/drivers/mtd/maps/intel_vr_nor.c
+++ b/drivers/mtd/maps/intel_vr_nor.c
@@ -71,7 +71,7 @@ static int vr_nor_init_partitions(struct vr_nor_mtd *p)
 {
 	/* register the flash bank */
 	/* partition the flash bank */
-	return mtd_device_parse_register(p->info, NULL, NULL, NULL, 0);
+	return mtd_device_register(p->info, NULL, 0);
 }
 
 static void vr_nor_destroy_mtd_setup(struct vr_nor_mtd *p)
diff --git a/drivers/mtd/maps/latch-addr-flash.c b/drivers/mtd/maps/latch-addr-flash.c
index 6dc97aa667dc..51db24b7f88d 100644
--- a/drivers/mtd/maps/latch-addr-flash.c
+++ b/drivers/mtd/maps/latch-addr-flash.c
@@ -197,9 +197,8 @@ static int latch_addr_flash_probe(struct platform_device *dev)
 	}
 	info->mtd->dev.parent = &dev->dev;
 
-	mtd_device_parse_register(info->mtd, NULL, NULL,
-				  latch_addr_data->parts,
-				  latch_addr_data->nr_parts);
+	mtd_device_register(info->mtd, latch_addr_data->parts,
+			    latch_addr_data->nr_parts);
 	return 0;
 
 iounmap:
diff --git a/drivers/mtd/maps/rbtx4939-flash.c b/drivers/mtd/maps/rbtx4939-flash.c
index 3a06ecfc55ff..80a187167c92 100644
--- a/drivers/mtd/maps/rbtx4939-flash.c
+++ b/drivers/mtd/maps/rbtx4939-flash.c
@@ -97,8 +97,7 @@ static int rbtx4939_flash_probe(struct platform_device *dev)
 		goto err_out;
 	}
 	info->mtd->dev.parent = &dev->dev;
-	err = mtd_device_parse_register(info->mtd, NULL, NULL, pdata->parts,
-					pdata->nr_parts);
+	err = mtd_device_register(info->mtd, pdata->parts, pdata->nr_parts);
 
 	if (err)
 		goto err_out;
diff --git a/drivers/mtd/maps/solutionengine.c b/drivers/mtd/maps/solutionengine.c
index bb580bc16445..c07f21b20463 100644
--- a/drivers/mtd/maps/solutionengine.c
+++ b/drivers/mtd/maps/solutionengine.c
@@ -59,9 +59,9 @@ static int __init init_soleng_maps(void)
 			return -ENXIO;
 		}
 	}
-	printk(KERN_NOTICE "Solution Engine: Flash at 0x%08lx, EPROM at 0x%08lx\n",
-	       soleng_flash_map.phys & 0x1fffffff,
-	       soleng_eprom_map.phys & 0x1fffffff);
+	printk(KERN_NOTICE "Solution Engine: Flash at 0x%pap, EPROM at 0x%pap\n",
+	       &soleng_flash_map.phys,
+	       &soleng_eprom_map.phys);
 	flash_mtd->owner = THIS_MODULE;
 
 	eprom_mtd = do_map_probe("map_rom", &soleng_eprom_map);
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index cd67c85cc87d..02389528f622 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -160,8 +160,12 @@ static ssize_t mtdchar_read(struct file *file, char __user *buf, size_t count,
 
 	pr_debug("MTD_read\n");
 
-	if (*ppos + count > mtd->size)
-		count = mtd->size - *ppos;
+	if (*ppos + count > mtd->size) {
+		if (*ppos < mtd->size)
+			count = mtd->size - *ppos;
+		else
+			count = 0;
+	}
 
 	if (!count)
 		return 0;
@@ -246,7 +250,7 @@ static ssize_t mtdchar_write(struct file *file, const char __user *buf, size_t c
 
 	pr_debug("MTD_write\n");
 
-	if (*ppos == mtd->size)
+	if (*ppos >= mtd->size)
 		return -ENOSPC;
 
 	if (*ppos + count > mtd->size)
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 42395df06be9..97ac219c082e 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1155,21 +1155,29 @@ int mtd_read_oob(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops)
 {
 	int ret_code;
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->_read_oob)
-		return -EOPNOTSUPP;
 
 	ret_code = mtd_check_oob_ops(mtd, from, ops);
 	if (ret_code)
 		return ret_code;
 
 	ledtrig_mtd_activity();
+
+	/* Check the validity of a potential fallback on mtd->_read */
+	if (!mtd->_read_oob && (!mtd->_read || ops->oobbuf))
+		return -EOPNOTSUPP;
+
+	if (mtd->_read_oob)
+		ret_code = mtd->_read_oob(mtd, from, ops);
+	else
+		ret_code = mtd->_read(mtd, from, ops->len, &ops->retlen,
+				      ops->datbuf);
+
 	/*
 	 * In cases where ops->datbuf != NULL, mtd->_read_oob() has semantics
 	 * similar to mtd->_read(), returning a non-negative integer
 	 * representing max bitflips. In other cases, mtd->_read_oob() may
 	 * return -EUCLEAN. In all cases, perform similar logic to mtd_read().
 	 */
-	ret_code = mtd->_read_oob(mtd, from, ops);
 	if (unlikely(ret_code < 0))
 		return ret_code;
 	if (mtd->ecc_strength == 0)
@@ -1184,8 +1192,7 @@ int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 	int ret;
 
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->_write_oob)
-		return -EOPNOTSUPP;
+
 	if (!(mtd->flags & MTD_WRITEABLE))
 		return -EROFS;
 
@@ -1194,7 +1201,16 @@ int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 		return ret;
 
 	ledtrig_mtd_activity();
-	return mtd->_write_oob(mtd, to, ops);
+
+	/* Check the validity of a potential fallback on mtd->_write */
+	if (!mtd->_write_oob && (!mtd->_write || ops->oobbuf))
+		return -EOPNOTSUPP;
+
+	if (mtd->_write_oob)
+		return mtd->_write_oob(mtd, to, ops);
+	else
+		return mtd->_write(mtd, to, ops->len, &ops->retlen,
+				   ops->datbuf);
 }
 EXPORT_SYMBOL_GPL(mtd_write_oob);
 
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index f8d3a015cdad..52e2cb35fc79 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -322,22 +322,6 @@ static inline void free_partition(struct mtd_part *p)
 	kfree(p);
 }
 
-/**
- * mtd_parse_part - parse MTD partition looking for subpartitions
- *
- * @slave: part that is supposed to be a container and should be parsed
- * @types: NULL-terminated array with names of partition parsers to try
- *
- * Some partitions are kind of containers with extra subpartitions (volumes).
- * There can be various formats of such containers. This function tries to use
- * specified parsers to analyze given partition and registers found
- * subpartitions on success.
- */
-static int mtd_parse_part(struct mtd_part *slave, const char *const *types)
-{
-	return parse_mtd_partitions(&slave->mtd, types, NULL);
-}
-
 static struct mtd_part *allocate_partition(struct mtd_info *parent,
 			const struct mtd_partition *part, int partno,
 			uint64_t cur_offset)
@@ -735,8 +719,8 @@ int add_mtd_partitions(struct mtd_info *master,
 
 		add_mtd_device(&slave->mtd);
 		mtd_add_partition_attrs(slave);
-		if (parts[i].types)
-			mtd_parse_part(slave, parts[i].types);
+		/* Look for subpartitions */
+		parse_mtd_partitions(&slave->mtd, parts[i].types, NULL);
 
 		cur_offset = slave->offset + slave->mtd.size;
 	}
@@ -812,6 +796,12 @@ static const char * const default_mtd_part_types[] = {
 	NULL
 };
 
+/* Check DT only when looking for subpartitions. */
+static const char * const default_subpartition_types[] = {
+	"ofpart",
+	NULL
+};
+
 static int mtd_part_do_parse(struct mtd_part_parser *parser,
 			     struct mtd_info *master,
 			     struct mtd_partitions *pparts,
@@ -882,7 +872,9 @@ static int mtd_part_of_parse(struct mtd_info *master,
 	const char *fixed = "fixed-partitions";
 	int ret, err = 0;
 
-	np = of_get_child_by_name(mtd_get_of_node(master), "partitions");
+	np = mtd_get_of_node(master);
+	if (!mtd_is_partition(master))
+		np = of_get_child_by_name(np, "partitions");
 	of_property_for_each_string(np, "compatible", prop, compat) {
 		parser = mtd_part_get_compatible_parser(compat);
 		if (!parser)
@@ -945,7 +937,8 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types,
 	int ret, err = 0;
 
 	if (!types)
-		types = default_mtd_part_types;
+		types = mtd_is_partition(master) ? default_subpartition_types :
+			default_mtd_part_types;
 
 	for ( ; *types; types++) {
 		/*
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 88c7d3b4ff8b..9033215e62ea 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -4,3 +4,4 @@ config MTD_NAND_CORE
 source "drivers/mtd/nand/onenand/Kconfig"
 
 source "drivers/mtd/nand/raw/Kconfig"
+source "drivers/mtd/nand/spi/Kconfig"
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 3f0cb87f1a57..7ecd80c0a66e 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -5,3 +5,4 @@ obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o
 
 obj-y	+= onenand/
 obj-y	+= raw/
+obj-y	+= spi/
diff --git a/drivers/mtd/nand/onenand/generic.c b/drivers/mtd/nand/onenand/generic.c
index d5ccaf943b91..acad17ec6581 100644
--- a/drivers/mtd/nand/onenand/generic.c
+++ b/drivers/mtd/nand/onenand/generic.c
@@ -66,9 +66,8 @@ static int generic_onenand_probe(struct platform_device *pdev)
 		goto out_iounmap;
 	}
 
-	err = mtd_device_parse_register(&info->mtd, NULL, NULL,
-					pdata ? pdata->parts : NULL,
-					pdata ? pdata->nr_parts : 0);
+	err = mtd_device_register(&info->mtd, pdata ? pdata->parts : NULL,
+				  pdata ? pdata->nr_parts : 0);
 
 	platform_set_drvdata(pdev, info);
 
diff --git a/drivers/mtd/nand/onenand/samsung.c b/drivers/mtd/nand/onenand/samsung.c
index 4cce4c0311ca..e64d0fdf7eb5 100644
--- a/drivers/mtd/nand/onenand/samsung.c
+++ b/drivers/mtd/nand/onenand/samsung.c
@@ -933,9 +933,8 @@ static int s3c_onenand_probe(struct platform_device *pdev)
 	if (s3c_read_reg(MEM_CFG_OFFSET) & ONENAND_SYS_CFG1_SYNC_READ)
 		dev_info(&onenand->pdev->dev, "OneNAND Sync. Burst Read enabled\n");
 
-	err = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata ? pdata->parts : NULL,
-					pdata ? pdata->nr_parts : 0);
+	err = mtd_device_register(mtd, pdata ? pdata->parts : NULL,
+				  pdata ? pdata->nr_parts : 0);
 	if (err) {
 		dev_err(&pdev->dev, "failed to parse partitions and register the MTD device\n");
 		onenand_release(mtd);
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 6871ff0fd300..5fc9a1bde4ac 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -44,12 +44,12 @@ config MTD_NAND_DENALI
 	tristate
 
 config MTD_NAND_DENALI_PCI
-        tristate "Support Denali NAND controller on Intel Moorestown"
+	tristate "Support Denali NAND controller on Intel Moorestown"
 	select MTD_NAND_DENALI
 	depends on PCI
-        help
-          Enable the driver for NAND flash on Intel Moorestown, using the
-          Denali NAND controller core.
+	help
+	  Enable the driver for NAND flash on Intel Moorestown, using the
+	  Denali NAND controller core.
 
 config MTD_NAND_DENALI_DT
 	tristate "Support Denali NAND controller as a DT device"
@@ -77,9 +77,10 @@ config MTD_NAND_AMS_DELTA
 
 config MTD_NAND_OMAP2
 	tristate "NAND Flash device on OMAP2, OMAP3, OMAP4 and Keystone"
-	depends on (ARCH_OMAP2PLUS || ARCH_KEYSTONE)
+	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
-          Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4
+	  Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4
 	  and Keystone platforms.
 
 config MTD_NAND_OMAP_BCH
@@ -137,7 +138,7 @@ config MTD_NAND_NDFC
 	depends on 4xx
 	select MTD_NAND_ECC_SMC
 	help
-	 NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs
+	  NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs
 
 config MTD_NAND_S3C2410_CLKSTOP
 	bool "Samsung S3C NAND IDLE clock stop"
@@ -152,6 +153,7 @@ config MTD_NAND_S3C2410_CLKSTOP
 config MTD_NAND_TANGO
 	tristate "NAND Flash support for Tango chips"
 	depends on ARCH_TANGO || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables the NAND Flash controller on Tango chips.
 
@@ -168,40 +170,40 @@ config MTD_NAND_DISKONCHIP
 	  these devices.
 
 config MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        bool "Advanced detection options for DiskOnChip"
-        depends on MTD_NAND_DISKONCHIP
-        help
-          This option allows you to specify nonstandard address at which to
-          probe for a DiskOnChip, or to change the detection options.  You
-          are unlikely to need any of this unless you are using LinuxBIOS.
-          Say 'N'.
+	bool "Advanced detection options for DiskOnChip"
+	depends on MTD_NAND_DISKONCHIP
+	help
+	  This option allows you to specify nonstandard address at which to
+	  probe for a DiskOnChip, or to change the detection options.  You
+	  are unlikely to need any of this unless you are using LinuxBIOS.
+	  Say 'N'.
 
 config MTD_NAND_DISKONCHIP_PROBE_ADDRESS
-        hex "Physical address of DiskOnChip" if MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        depends on MTD_NAND_DISKONCHIP
-        default "0"
-        ---help---
-        By default, the probe for DiskOnChip devices will look for a
-        DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
-        This option allows you to specify a single address at which to probe
-        for the device, which is useful if you have other devices in that
-        range which get upset when they are probed.
-
-        (Note that on PowerPC, the normal probe will only check at
-        0xE4000000.)
-
-        Normally, you should leave this set to zero, to allow the probe at
-        the normal addresses.
+	hex "Physical address of DiskOnChip" if MTD_NAND_DISKONCHIP_PROBE_ADVANCED
+	depends on MTD_NAND_DISKONCHIP
+	default "0"
+	help
+	  By default, the probe for DiskOnChip devices will look for a
+	  DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
+	  This option allows you to specify a single address at which to probe
+	  for the device, which is useful if you have other devices in that
+	  range which get upset when they are probed.
+
+	  (Note that on PowerPC, the normal probe will only check at
+	  0xE4000000.)
+
+	  Normally, you should leave this set to zero, to allow the probe at
+	  the normal addresses.
 
 config MTD_NAND_DISKONCHIP_PROBE_HIGH
-        bool "Probe high addresses"
-        depends on MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        help
-          By default, the probe for DiskOnChip devices will look for a
-          DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
-          This option changes to make it probe between 0xFFFC8000 and
-          0xFFFEE000.  Unless you are using LinuxBIOS, this is unlikely to be
-          useful to you.  Say 'N'.
+	bool "Probe high addresses"
+	depends on MTD_NAND_DISKONCHIP_PROBE_ADVANCED
+	help
+	  By default, the probe for DiskOnChip devices will look for a
+	  DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
+	  This option changes to make it probe between 0xFFFC8000 and
+	  0xFFFEE000.  Unless you are using LinuxBIOS, this is unlikely to be
+	  useful to you.  Say 'N'.
 
 config MTD_NAND_DISKONCHIP_BBTWRITE
 	bool "Allow BBT writes on DiskOnChip Millennium and 2000TSOP"
@@ -247,7 +249,8 @@ config MTD_NAND_DOCG4
 
 config MTD_NAND_SHARPSL
 	tristate "Support for NAND Flash on Sharp SL Series (C7xx + others)"
-	depends on ARCH_PXA
+	depends on ARCH_PXA || COMPILE_TEST
+	depends on HAS_IOMEM
 
 config MTD_NAND_CAFE
 	tristate "NAND support for OLPC CAFÉ chip"
@@ -274,7 +277,9 @@ config MTD_NAND_CS553X
 
 config MTD_NAND_ATMEL
 	tristate "Support for NAND Flash / SmartMedia on AT91"
-	depends on ARCH_AT91
+	depends on ARCH_AT91 || COMPILE_TEST
+	depends on HAS_IOMEM
+	select GENERIC_ALLOCATOR
 	select MFD_ATMEL_SMC
 	help
 	  Enables support for NAND Flash / Smart Media Card interface
@@ -294,7 +299,8 @@ config MTD_NAND_MARVELL
 
 config MTD_NAND_SLC_LPC32XX
 	tristate "NXP LPC32xx SLC Controller"
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NXP's LPC32XX SLC (i.e. for Single Level Cell
 	  chips) NAND controller. This is the default for the PHYTEC 3250
@@ -305,7 +311,8 @@ config MTD_NAND_SLC_LPC32XX
 
 config MTD_NAND_MLC_LPC32XX
 	tristate "NXP LPC32xx MLC Controller"
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Uses the LPC32XX MLC (i.e. for Multi Level Cell chips) NAND
 	  controller. This is the default for the WORK92105 controller
@@ -339,17 +346,18 @@ config MTD_NAND_NANDSIM
 	  MTD nand layer.
 
 config MTD_NAND_GPMI_NAND
-        tristate "GPMI NAND Flash Controller driver"
-        depends on MTD_NAND && MXS_DMA
-        help
-	 Enables NAND Flash support for IMX23, IMX28 or IMX6.
-	 The GPMI controller is very powerful, with the help of BCH
-	 module, it can do the hardware ECC. The GPMI supports several
-	 NAND flashs at the same time.
+	tristate "GPMI NAND Flash Controller driver"
+	depends on MXS_DMA
+	help
+	  Enables NAND Flash support for IMX23, IMX28 or IMX6.
+	  The GPMI controller is very powerful, with the help of BCH
+	  module, it can do the hardware ECC. The GPMI supports several
+	  NAND flashs at the same time.
 
 config MTD_NAND_BRCMNAND
 	tristate "Broadcom STB NAND controller"
-	depends on ARM || ARM64 || MIPS
+	depends on ARM || ARM64 || MIPS || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables the Broadcom NAND controller driver. The controller was
 	  originally designed for Set-Top Box but is used on various BCM7xxx,
@@ -358,6 +366,7 @@ config MTD_NAND_BRCMNAND
 config MTD_NAND_BCM47XXNFLASH
 	tristate "Support for NAND flash on BCM4706 BCMA bus"
 	depends on BCMA_NFLASH
+	depends on BCMA
 	help
 	  BCMA bus can have various flash memories attached, they are
 	  registered by bcma as platform devices. This enables driver for
@@ -399,7 +408,8 @@ config MTD_NAND_FSL_ELBC
 
 config MTD_NAND_FSL_IFC
 	tristate "NAND support for Freescale IFC controller"
-	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
+	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+	depends on HAS_IOMEM
 	select FSL_IFC
 	select MEMORY
 	help
@@ -437,7 +447,8 @@ config MTD_NAND_VF610_NFC
 
 config MTD_NAND_MXC
 	tristate "MXC NAND support"
-	depends on ARCH_MXC
+	depends on ARCH_MXC || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the driver for the NAND flash controller on the
 	  MXC processors.
@@ -451,15 +462,17 @@ config MTD_NAND_SH_FLCTL
 	  for NAND Flash using FLCTL.
 
 config MTD_NAND_DAVINCI
-        tristate "Support NAND on DaVinci/Keystone SoC"
-        depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF)
-        help
+	tristate "Support NAND on DaVinci/Keystone SoC"
+	depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF) || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
 	  Enable the driver for NAND flash chips on Texas Instruments
 	  DaVinci/Keystone processors.
 
 config MTD_NAND_TXX9NDFMC
 	tristate "NAND Flash support for TXx9 SoC"
-	depends on SOC_TX4938 || SOC_TX4939
+	depends on SOC_TX4938 || SOC_TX4939 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the NAND flash controller on the TXx9 SoCs.
 
@@ -471,28 +484,31 @@ config MTD_NAND_SOCRATES
 
 config MTD_NAND_NUC900
 	tristate "Support for NAND on Nuvoton NUC9xx/w90p910 evaluation boards."
-	depends on ARCH_W90X900
+	depends on ARCH_W90X900 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the driver for the NAND Flash on evaluation board based
 	  on w90p910 / NUC9xx.
 
 config MTD_NAND_JZ4740
 	tristate "Support for JZ4740 SoC NAND controller"
-	depends on MACH_JZ4740
+	depends on MACH_JZ4740 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
-		Enables support for NAND Flash on JZ4740 SoC based boards.
+	  Enables support for NAND Flash on JZ4740 SoC based boards.
 
 config MTD_NAND_JZ4780
 	tristate "Support for NAND on JZ4780 SoC"
-	depends on MACH_JZ4780 && JZ4780_NEMC
+	depends on JZ4780_NEMC
 	help
 	  Enables support for NAND Flash connected to the NEMC on JZ4780 SoC
 	  based boards, using the BCH controller for hardware error correction.
 
 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
+	depends on OF && HAS_IOMEM
+	depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300 || \
+		   COMPILE_TEST
 	help
 	  Enables support for NAND Flash chips on the ST Microelectronics
 	  Flexible Static Memory Controller (FSMC)
@@ -506,19 +522,22 @@ config MTD_NAND_XWAY
 
 config MTD_NAND_SUNXI
 	tristate "Support for NAND on Allwinner SoCs"
-	depends on ARCH_SUNXI
+	depends on ARCH_SUNXI || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND Flash chips on Allwinner SoCs.
 
 config MTD_NAND_HISI504
 	tristate "Support for NAND controller on Hisilicon SoC Hip04"
 	depends on ARCH_HISI || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND controller on Hisilicon SoC Hip04.
 
 config MTD_NAND_QCOM
 	tristate "Support for NAND on QCOM SoCs"
-	depends on ARCH_QCOM
+	depends on ARCH_QCOM || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND flash chips on SoCs containing the EBI2 NAND
 	  controller. This controller is found on IPQ806x SoC.
@@ -526,8 +545,20 @@ config MTD_NAND_QCOM
 config MTD_NAND_MTK
 	tristate "Support for NAND controller on MTK SoCs"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND controller on MTK SoCs.
 	  This controller is found on mt27xx, mt81xx, mt65xx SoCs.
 
+config MTD_NAND_TEGRA
+	tristate "Support for NAND controller on NVIDIA Tegra"
+	depends on ARCH_TEGRA || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
+	  Enables support for NAND flash controller on NVIDIA Tegra SoC.
+	  The driver has been developed and tested on a Tegra 2 SoC. DMA
+	  support, raw read/write page as well as HW ECC read/write page
+	  is supported. Extra OOB bytes when using HW ECC are currently
+	  not supported.
+
 endif # MTD_NAND
diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile
index 165b7ef9e9a1..d5a5f9832b88 100644
--- a/drivers/mtd/nand/raw/Makefile
+++ b/drivers/mtd/nand/raw/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_MTD_NAND_HISI504)	        += hisi504_nand.o
 obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= brcmnand/
 obj-$(CONFIG_MTD_NAND_QCOM)		+= qcom_nandc.o
 obj-$(CONFIG_MTD_NAND_MTK)		+= mtk_ecc.o mtk_nand.o
+obj-$(CONFIG_MTD_NAND_TEGRA)		+= tegra_nand.o
 
 nand-objs := nand_base.o nand_bbt.o nand_timings.o nand_ids.o
 nand-objs += nand_amd.o
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 12f6753d47ae..a068b214ebaa 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -52,7 +52,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/genalloc.h>
-#include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/mfd/syscon.h>
@@ -129,6 +128,11 @@
 #define DEFAULT_TIMEOUT_MS			1000
 #define MIN_DMA_LEN				128
 
+static bool atmel_nand_avoid_dma __read_mostly;
+
+MODULE_PARM_DESC(avoiddma, "Avoid using DMA");
+module_param_named(avoiddma, atmel_nand_avoid_dma, bool, 0400);
+
 enum atmel_nand_rb_type {
 	ATMEL_NAND_NO_RB,
 	ATMEL_NAND_NATIVE_RB,
@@ -197,7 +201,7 @@ struct atmel_nand_controller_ops {
 	int (*remove)(struct atmel_nand_controller *nc);
 	void (*nand_init)(struct atmel_nand_controller *nc,
 			  struct atmel_nand *nand);
-	int (*ecc_init)(struct atmel_nand *nand);
+	int (*ecc_init)(struct nand_chip *chip);
 	int (*setup_data_interface)(struct atmel_nand *nand, int csline,
 				    const struct nand_data_interface *conf);
 };
@@ -211,7 +215,7 @@ struct atmel_nand_controller_caps {
 };
 
 struct atmel_nand_controller {
-	struct nand_hw_control base;
+	struct nand_controller base;
 	const struct atmel_nand_controller_caps *caps;
 	struct device *dev;
 	struct regmap *smc;
@@ -222,7 +226,7 @@ struct atmel_nand_controller {
 };
 
 static inline struct atmel_nand_controller *
-to_nand_controller(struct nand_hw_control *ctl)
+to_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(ctl, struct atmel_nand_controller, base);
 }
@@ -234,7 +238,7 @@ struct atmel_smc_nand_controller {
 };
 
 static inline struct atmel_smc_nand_controller *
-to_smc_nand_controller(struct nand_hw_control *ctl)
+to_smc_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(to_nand_controller(ctl),
 			    struct atmel_smc_nand_controller, base);
@@ -258,7 +262,7 @@ struct atmel_hsmc_nand_controller {
 };
 
 static inline struct atmel_hsmc_nand_controller *
-to_hsmc_nand_controller(struct nand_hw_control *ctl)
+to_hsmc_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(to_nand_controller(ctl),
 			    struct atmel_hsmc_nand_controller, base);
@@ -1128,9 +1132,8 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 	return 0;
 }
 
-static int atmel_nand_ecc_init(struct atmel_nand *nand)
+static int atmel_nand_ecc_init(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->base;
 	struct atmel_nand_controller *nc;
 	int ret;
 
@@ -1165,12 +1168,11 @@ static int atmel_nand_ecc_init(struct atmel_nand *nand)
 	return 0;
 }
 
-static int atmel_hsmc_nand_ecc_init(struct atmel_nand *nand)
+static int atmel_hsmc_nand_ecc_init(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->base;
 	int ret;
 
-	ret = atmel_nand_ecc_init(nand);
+	ret = atmel_nand_ecc_init(chip);
 	if (ret)
 		return ret;
 
@@ -1553,23 +1555,7 @@ static void atmel_hsmc_nand_init(struct atmel_nand_controller *nc,
 	chip->select_chip = atmel_hsmc_nand_select_chip;
 }
 
-static int atmel_nand_detect(struct atmel_nand *nand)
-{
-	struct nand_chip *chip = &nand->base;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	struct atmel_nand_controller *nc;
-	int ret;
-
-	nc = to_nand_controller(chip->controller);
-
-	ret = nand_scan_ident(mtd, nand->numcs, NULL);
-	if (ret)
-		dev_err(nc->dev, "nand_scan_ident() failed: %d\n", ret);
-
-	return ret;
-}
-
-static int atmel_nand_unregister(struct atmel_nand *nand)
+static int atmel_nand_controller_remove_nand(struct atmel_nand *nand)
 {
 	struct nand_chip *chip = &nand->base;
 	struct mtd_info *mtd = nand_to_mtd(chip);
@@ -1585,60 +1571,6 @@ static int atmel_nand_unregister(struct atmel_nand *nand)
 	return 0;
 }
 
-static int atmel_nand_register(struct atmel_nand *nand)
-{
-	struct nand_chip *chip = &nand->base;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	struct atmel_nand_controller *nc;
-	int ret;
-
-	nc = to_nand_controller(chip->controller);
-
-	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
-		/*
-		 * We keep the MTD name unchanged to avoid breaking platforms
-		 * where the MTD cmdline parser is used and the bootloader
-		 * has not been updated to use the new naming scheme.
-		 */
-		mtd->name = "atmel_nand";
-	} else if (!mtd->name) {
-		/*
-		 * If the new bindings are used and the bootloader has not been
-		 * updated to pass a new mtdparts parameter on the cmdline, you
-		 * should define the following property in your nand node:
-		 *
-		 *	label = "atmel_nand";
-		 *
-		 * This way, mtd->name will be set by the core when
-		 * nand_set_flash_node() is called.
-		 */
-		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
-					   "%s:nand.%d", dev_name(nc->dev),
-					   nand->cs[0].id);
-		if (!mtd->name) {
-			dev_err(nc->dev, "Failed to allocate mtd->name\n");
-			return -ENOMEM;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(nc->dev, "nand_scan_tail() failed: %d\n", ret);
-		return ret;
-	}
-
-	ret = mtd_device_register(mtd, NULL, 0);
-	if (ret) {
-		dev_err(nc->dev, "Failed to register mtd device: %d\n", ret);
-		nand_cleanup(chip);
-		return ret;
-	}
-
-	list_add_tail(&nand->node, &nc->chips);
-
-	return 0;
-}
-
 static struct atmel_nand *atmel_nand_create(struct atmel_nand_controller *nc,
 					    struct device_node *np,
 					    int reg_cells)
@@ -1750,6 +1682,8 @@ static int
 atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
 			       struct atmel_nand *nand)
 {
+	struct nand_chip *chip = &nand->base;
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
 
 	/* No card inserted, skip this NAND. */
@@ -1760,15 +1694,22 @@ atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
 
 	nc->caps->ops->nand_init(nc, nand);
 
-	ret = atmel_nand_detect(nand);
-	if (ret)
+	ret = nand_scan(mtd, nand->numcs);
+	if (ret) {
+		dev_err(nc->dev, "NAND scan failed: %d\n", ret);
 		return ret;
+	}
 
-	ret = nc->caps->ops->ecc_init(nand);
-	if (ret)
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(nc->dev, "Failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
 		return ret;
+	}
+
+	list_add_tail(&nand->node, &nc->chips);
 
-	return atmel_nand_register(nand);
+	return 0;
 }
 
 static int
@@ -1778,7 +1719,7 @@ atmel_nand_controller_remove_nands(struct atmel_nand_controller *nc)
 	int ret;
 
 	list_for_each_entry_safe(nand, tmp, &nc->chips, node) {
-		ret = atmel_nand_unregister(nand);
+		ret = atmel_nand_controller_remove_nand(nand);
 		if (ret)
 			return ret;
 	}
@@ -1953,6 +1894,51 @@ static const struct of_device_id atmel_matrix_of_ids[] = {
 	{ /* sentinel */ },
 };
 
+static int atmel_nand_attach_chip(struct nand_chip *chip)
+{
+	struct atmel_nand_controller *nc = to_nand_controller(chip->controller);
+	struct atmel_nand *nand = to_atmel_nand(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ret;
+
+	ret = nc->caps->ops->ecc_init(chip);
+	if (ret)
+		return ret;
+
+	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
+		/*
+		 * We keep the MTD name unchanged to avoid breaking platforms
+		 * where the MTD cmdline parser is used and the bootloader
+		 * has not been updated to use the new naming scheme.
+		 */
+		mtd->name = "atmel_nand";
+	} else if (!mtd->name) {
+		/*
+		 * If the new bindings are used and the bootloader has not been
+		 * updated to pass a new mtdparts parameter on the cmdline, you
+		 * should define the following property in your nand node:
+		 *
+		 *	label = "atmel_nand";
+		 *
+		 * This way, mtd->name will be set by the core when
+		 * nand_set_flash_node() is called.
+		 */
+		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
+					   "%s:nand.%d", dev_name(nc->dev),
+					   nand->cs[0].id);
+		if (!mtd->name) {
+			dev_err(nc->dev, "Failed to allocate mtd->name\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops atmel_nand_controller_ops = {
+	.attach_chip = atmel_nand_attach_chip,
+};
+
 static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 				struct platform_device *pdev,
 				const struct atmel_nand_controller_caps *caps)
@@ -1961,7 +1947,8 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 	struct device_node *np = dev->of_node;
 	int ret;
 
-	nand_hw_control_init(&nc->base);
+	nand_controller_init(&nc->base);
+	nc->base.ops = &atmel_nand_controller_ops;
 	INIT_LIST_HEAD(&nc->chips);
 	nc->dev = dev;
 	nc->caps = caps;
@@ -1977,7 +1964,7 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 		return ret;
 	}
 
-	if (nc->caps->has_dma) {
+	if (nc->caps->has_dma && !atmel_nand_avoid_dma) {
 		dma_cap_mask_t mask;
 
 		dma_cap_zero(mask);
@@ -2045,7 +2032,7 @@ atmel_smc_nand_controller_init(struct atmel_smc_nand_controller *nc)
 		return ret;
 	}
 
-	nc->ebi_csa_offs = (unsigned int)match->data;
+	nc->ebi_csa_offs = (uintptr_t)match->data;
 
 	/*
 	 * The at91sam9263 has 2 EBIs, if the NAND controller is under EBI1
@@ -2214,9 +2201,9 @@ atmel_hsmc_nand_controller_init(struct atmel_hsmc_nand_controller *nc)
 		return -ENOMEM;
 	}
 
-	nc->sram.virt = gen_pool_dma_alloc(nc->sram.pool,
-					    ATMEL_NFC_SRAM_SIZE,
-					    &nc->sram.dma);
+	nc->sram.virt = (void __iomem *)gen_pool_dma_alloc(nc->sram.pool,
+							   ATMEL_NFC_SRAM_SIZE,
+							   &nc->sram.dma);
 	if (!nc->sram.virt) {
 		dev_err(nc->base.dev,
 			"Could not allocate memory from the NFC SRAM pool\n");
diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c
index df0ef1f1e2f5..35f5c84cd331 100644
--- a/drivers/mtd/nand/raw/au1550nd.c
+++ b/drivers/mtd/nand/raw/au1550nd.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/slab.h>
-#include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/mtd/mtd.h>
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 1306aaa7a8bf..4b90d5b380c2 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -114,7 +114,7 @@ enum {
 
 struct brcmnand_controller {
 	struct device		*dev;
-	struct nand_hw_control	controller;
+	struct nand_controller	controller;
 	void __iomem		*nand_base;
 	void __iomem		*nand_fc; /* flash cache */
 	void __iomem		*flash_dma_base;
@@ -2208,6 +2208,40 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 	return 0;
 }
 
+static int brcmnand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct brcmnand_host *host = nand_get_controller_data(chip);
+	int ret;
+
+	chip->options |= NAND_NO_SUBPAGE_WRITE;
+	/*
+	 * Avoid (for instance) kmap()'d buffers from JFFS2, which we can't DMA
+	 * to/from, and have nand_base pass us a bounce buffer instead, as
+	 * needed.
+	 */
+	chip->options |= NAND_USE_BOUNCE_BUFFER;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	if (brcmnand_setup_dev(host))
+		return -ENXIO;
+
+	chip->ecc.size = host->hwcfg.sector_size_1k ? 1024 : 512;
+
+	/* only use our internal HW threshold */
+	mtd->bitflip_threshold = 1;
+
+	ret = brcmstb_choose_ecc_layout(host);
+
+	return ret;
+}
+
+static const struct nand_controller_ops brcmnand_controller_ops = {
+	.attach_chip = brcmnand_attach_chip,
+};
+
 static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 {
 	struct brcmnand_controller *ctrl = host->ctrl;
@@ -2267,33 +2301,7 @@ static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 	nand_writereg(ctrl, cfg_offs,
 		      nand_readreg(ctrl, cfg_offs) & ~CFG_BUS_WIDTH);
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	chip->options |= NAND_NO_SUBPAGE_WRITE;
-	/*
-	 * Avoid (for instance) kmap()'d buffers from JFFS2, which we can't DMA
-	 * to/from, and have nand_base pass us a bounce buffer instead, as
-	 * needed.
-	 */
-	chip->options |= NAND_USE_BOUNCE_BUFFER;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH)
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-	if (brcmnand_setup_dev(host))
-		return -ENXIO;
-
-	chip->ecc.size = host->hwcfg.sector_size_1k ? 1024 : 512;
-	/* only use our internal HW threshold */
-	mtd->bitflip_threshold = 1;
-
-	ret = brcmstb_choose_ecc_layout(host);
-	if (ret)
-		return ret;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
@@ -2433,7 +2441,8 @@ int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc)
 
 	init_completion(&ctrl->done);
 	init_completion(&ctrl->dma_done);
-	nand_hw_control_init(&ctrl->controller);
+	nand_controller_init(&ctrl->controller);
+	ctrl->controller.ops = &brcmnand_controller_ops;
 	INIT_LIST_HEAD(&ctrl->host_list);
 
 	/* NAND register range */
diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index d721f489b38b..1dbe43adcfe7 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -67,6 +67,7 @@ struct cafe_priv {
 	int nr_data;
 	int data_pos;
 	int page_addr;
+	bool usedma;
 	dma_addr_t dmaaddr;
 	unsigned char *dmabuf;
 };
@@ -121,7 +122,7 @@ static void cafe_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct cafe_priv *cafe = nand_get_controller_data(chip);
 
-	if (usedma)
+	if (cafe->usedma)
 		memcpy(cafe->dmabuf + cafe->datalen, buf, len);
 	else
 		memcpy_toio(cafe->mmio + CAFE_NAND_WRITE_DATA + cafe->datalen, buf, len);
@@ -137,7 +138,7 @@ static void cafe_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct cafe_priv *cafe = nand_get_controller_data(chip);
 
-	if (usedma)
+	if (cafe->usedma)
 		memcpy(buf, cafe->dmabuf + cafe->datalen, len);
 	else
 		memcpy_fromio(buf, cafe->mmio + CAFE_NAND_READ_DATA + cafe->datalen, len);
@@ -253,7 +254,7 @@ static void cafe_nand_cmdfunc(struct mtd_info *mtd, unsigned command,
 	/* NB: The datasheet lies -- we really should be subtracting 1 here */
 	cafe_writel(cafe, cafe->datalen, NAND_DATA_LEN);
 	cafe_writel(cafe, 0x90000000, NAND_IRQ);
-	if (usedma && (ctl1 & (3<<25))) {
+	if (cafe->usedma && (ctl1 & (3<<25))) {
 		uint32_t dmactl = 0xc0000000 + cafe->datalen;
 		/* If WR or RD bits set, set up DMA */
 		if (ctl1 & (1<<26)) {
@@ -345,11 +346,6 @@ static irqreturn_t cafe_nand_interrupt(int irq, void *id)
 	return IRQ_HANDLED;
 }
 
-static void cafe_nand_bug(struct mtd_info *mtd)
-{
-	BUG();
-}
-
 static int cafe_nand_write_oob(struct mtd_info *mtd,
 			       struct nand_chip *chip, int page)
 {
@@ -598,6 +594,76 @@ static int cafe_mul(int x)
 	return gf4096_mul(x, 0xe01);
 }
 
+static int cafe_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct cafe_priv *cafe = nand_get_controller_data(chip);
+	int err = 0;
+
+	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev, 2112,
+					  &cafe->dmaaddr, GFP_KERNEL);
+	if (!cafe->dmabuf)
+		return -ENOMEM;
+
+	/* Set up DMA address */
+	cafe_writel(cafe, lower_32_bits(cafe->dmaaddr), NAND_DMA_ADDR0);
+	cafe_writel(cafe, upper_32_bits(cafe->dmaaddr), NAND_DMA_ADDR1);
+
+	cafe_dev_dbg(&cafe->pdev->dev, "Set DMA address to %x (virt %p)\n",
+		     cafe_readl(cafe, NAND_DMA_ADDR0), cafe->dmabuf);
+
+	/* Restore the DMA flag */
+	cafe->usedma = usedma;
+
+	cafe->ctl2 = BIT(27); /* Reed-Solomon ECC */
+	if (mtd->writesize == 2048)
+		cafe->ctl2 |= BIT(29); /* 2KiB page size */
+
+	/* Set up ECC according to the type of chip we found */
+	mtd_set_ooblayout(mtd, &cafe_ooblayout_ops);
+	if (mtd->writesize == 2048) {
+		cafe->nand.bbt_td = &cafe_bbt_main_descr_2048;
+		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_2048;
+	} else if (mtd->writesize == 512) {
+		cafe->nand.bbt_td = &cafe_bbt_main_descr_512;
+		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_512;
+	} else {
+		dev_warn(&cafe->pdev->dev,
+			 "Unexpected NAND flash writesize %d. Aborting\n",
+			 mtd->writesize);
+		err = -ENOTSUPP;
+		goto out_free_dma;
+	}
+
+	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
+	cafe->nand.ecc.size = mtd->writesize;
+	cafe->nand.ecc.bytes = 14;
+	cafe->nand.ecc.strength = 4;
+	cafe->nand.ecc.write_page = cafe_nand_write_page_lowlevel;
+	cafe->nand.ecc.write_oob = cafe_nand_write_oob;
+	cafe->nand.ecc.read_page = cafe_nand_read_page;
+	cafe->nand.ecc.read_oob = cafe_nand_read_oob;
+
+	return 0;
+
+ out_free_dma:
+	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
+
+	return err;
+}
+
+static void cafe_nand_detach_chip(struct nand_chip *chip)
+{
+	struct cafe_priv *cafe = nand_get_controller_data(chip);
+
+	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
+}
+
+static const struct nand_controller_ops cafe_nand_controller_ops = {
+	.attach_chip = cafe_nand_attach_chip,
+	.detach_chip = cafe_nand_detach_chip,
+};
+
 static int cafe_nand_probe(struct pci_dev *pdev,
 				     const struct pci_device_id *ent)
 {
@@ -605,7 +671,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	struct cafe_priv *cafe;
 	uint32_t ctrl;
 	int err = 0;
-	int old_dma;
 
 	/* Very old versions shared the same PCI ident for all three
 	   functions on the chip. Verify the class too... */
@@ -713,65 +778,15 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 		cafe_readl(cafe, GLOBAL_CTRL),
 		cafe_readl(cafe, GLOBAL_IRQ_MASK));
 
-	/* Do not use the DMA for the nand_scan_ident() */
-	old_dma = usedma;
-	usedma = 0;
+	/* Do not use the DMA during the NAND identification */
+	cafe->usedma = 0;
 
 	/* Scan to find existence of the device */
-	err = nand_scan_ident(mtd, 2, NULL);
+	cafe->nand.dummy_controller.ops = &cafe_nand_controller_ops;
+	err = nand_scan(mtd, 2);
 	if (err)
 		goto out_irq;
 
-	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev, 2112,
-					  &cafe->dmaaddr, GFP_KERNEL);
-	if (!cafe->dmabuf) {
-		err = -ENOMEM;
-		goto out_irq;
-	}
-
-	/* Set up DMA address */
-	cafe_writel(cafe, lower_32_bits(cafe->dmaaddr), NAND_DMA_ADDR0);
-	cafe_writel(cafe, upper_32_bits(cafe->dmaaddr), NAND_DMA_ADDR1);
-
-	cafe_dev_dbg(&cafe->pdev->dev, "Set DMA address to %x (virt %p)\n",
-		cafe_readl(cafe, NAND_DMA_ADDR0), cafe->dmabuf);
-
-	/* Restore the DMA flag */
-	usedma = old_dma;
-
-	cafe->ctl2 = 1<<27; /* Reed-Solomon ECC */
-	if (mtd->writesize == 2048)
-		cafe->ctl2 |= 1<<29; /* 2KiB page size */
-
-	/* Set up ECC according to the type of chip we found */
-	mtd_set_ooblayout(mtd, &cafe_ooblayout_ops);
-	if (mtd->writesize == 2048) {
-		cafe->nand.bbt_td = &cafe_bbt_main_descr_2048;
-		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_2048;
-	} else if (mtd->writesize == 512) {
-		cafe->nand.bbt_td = &cafe_bbt_main_descr_512;
-		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_512;
-	} else {
-		pr_warn("Unexpected NAND flash writesize %d. Aborting\n",
-			mtd->writesize);
-		goto out_free_dma;
-	}
-	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
-	cafe->nand.ecc.size = mtd->writesize;
-	cafe->nand.ecc.bytes = 14;
-	cafe->nand.ecc.strength = 4;
-	cafe->nand.ecc.hwctl  = (void *)cafe_nand_bug;
-	cafe->nand.ecc.calculate = (void *)cafe_nand_bug;
-	cafe->nand.ecc.correct  = (void *)cafe_nand_bug;
-	cafe->nand.ecc.write_page = cafe_nand_write_page_lowlevel;
-	cafe->nand.ecc.write_oob = cafe_nand_write_oob;
-	cafe->nand.ecc.read_page = cafe_nand_read_page;
-	cafe->nand.ecc.read_oob = cafe_nand_read_oob;
-
-	err = nand_scan_tail(mtd);
-	if (err)
-		goto out_free_dma;
-
 	pci_set_drvdata(pdev, mtd);
 
 	mtd->name = "cafe_nand";
@@ -783,8 +798,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 
  out_cleanup_nand:
 	nand_cleanup(&cafe->nand);
- out_free_dma:
-	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
  out_irq:
 	/* Disable NAND IRQ in global IRQ mask register */
 	cafe_writel(cafe, ~1 & cafe_readl(cafe, GLOBAL_IRQ_MASK), GLOBAL_IRQ_MASK);
diff --git a/drivers/mtd/nand/raw/cmx270_nand.c b/drivers/mtd/nand/raw/cmx270_nand.c
index 02d6751e9efe..b66e254b6802 100644
--- a/drivers/mtd/nand/raw/cmx270_nand.c
+++ b/drivers/mtd/nand/raw/cmx270_nand.c
@@ -200,8 +200,8 @@ static int __init cmx270_init(void)
 	}
 
 	/* Register the partitions */
-	ret = mtd_device_parse_register(cmx270_nand_mtd, NULL, NULL,
-					partition_info, NUM_PARTITIONS);
+	ret = mtd_device_register(cmx270_nand_mtd, partition_info,
+				  NUM_PARTITIONS);
 	if (ret)
 		goto err_scan;
 
diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c
index 82269fde9e66..beafad62e7d5 100644
--- a/drivers/mtd/nand/raw/cs553x_nand.c
+++ b/drivers/mtd/nand/raw/cs553x_nand.c
@@ -310,8 +310,7 @@ static int __init cs553x_init(void)
 	for (i = 0; i < NR_CS553X_CONTROLLERS; i++) {
 		if (cs553x_mtd[i]) {
 			/* If any devices registered, return success. Else the last error. */
-			mtd_device_parse_register(cs553x_mtd[i], NULL, NULL,
-						  NULL, 0);
+			mtd_device_register(cs553x_mtd[i], NULL, 0);
 			err = 0;
 		}
 	}
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index cd12e5abafde..40145e206a6b 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -53,15 +53,14 @@
 struct davinci_nand_info {
 	struct nand_chip	chip;
 
-	struct device		*dev;
+	struct platform_device	*pdev;
 
 	bool			is_readmode;
 
 	void __iomem		*base;
 	void __iomem		*vaddr;
 
-	uint32_t		ioaddr;
-	uint32_t		current_cs;
+	void __iomem		*current_cs;
 
 	uint32_t		mask_chipsel;
 	uint32_t		mask_ale;
@@ -102,17 +101,17 @@ static void nand_davinci_hwcontrol(struct mtd_info *mtd, int cmd,
 				   unsigned int ctrl)
 {
 	struct davinci_nand_info	*info = to_davinci_nand(mtd);
-	uint32_t			addr = info->current_cs;
+	void __iomem			*addr = info->current_cs;
 	struct nand_chip		*nand = mtd_to_nand(mtd);
 
 	/* Did the control lines change? */
 	if (ctrl & NAND_CTRL_CHANGE) {
 		if ((ctrl & NAND_CTRL_CLE) == NAND_CTRL_CLE)
-			addr |= info->mask_cle;
+			addr += info->mask_cle;
 		else if ((ctrl & NAND_CTRL_ALE) == NAND_CTRL_ALE)
-			addr |= info->mask_ale;
+			addr += info->mask_ale;
 
-		nand->IO_ADDR_W = (void __iomem __force *)addr;
+		nand->IO_ADDR_W = addr;
 	}
 
 	if (cmd != NAND_CMD_NONE)
@@ -122,14 +121,14 @@ static void nand_davinci_hwcontrol(struct mtd_info *mtd, int cmd,
 static void nand_davinci_select_chip(struct mtd_info *mtd, int chip)
 {
 	struct davinci_nand_info	*info = to_davinci_nand(mtd);
-	uint32_t			addr = info->ioaddr;
+
+	info->current_cs = info->vaddr;
 
 	/* maybe kick in a second chipselect */
 	if (chip > 0)
-		addr |= info->mask_chipsel;
-	info->current_cs = addr;
+		info->current_cs += info->mask_chipsel;
 
-	info->chip.IO_ADDR_W = (void __iomem __force *)addr;
+	info->chip.IO_ADDR_W = info->current_cs;
 	info->chip.IO_ADDR_R = info->chip.IO_ADDR_W;
 }
 
@@ -319,7 +318,7 @@ static int nand_davinci_correct_4bit(struct mtd_info *mtd,
 	/* Unpack ten bytes into eight 10 bit values.  We know we're
 	 * little-endian, and use type punning for less shifting/masking.
 	 */
-	if (WARN_ON(0x01 & (unsigned) ecc_code))
+	if (WARN_ON(0x01 & (uintptr_t)ecc_code))
 		return -EINVAL;
 	ecc16 = (unsigned short *)ecc_code;
 
@@ -441,9 +440,9 @@ static void nand_davinci_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if ((0x03 & ((unsigned)buf)) == 0 && (0x03 & len) == 0)
+	if ((0x03 & ((uintptr_t)buf)) == 0 && (0x03 & len) == 0)
 		ioread32_rep(chip->IO_ADDR_R, buf, len >> 2);
-	else if ((0x01 & ((unsigned)buf)) == 0 && (0x01 & len) == 0)
+	else if ((0x01 & ((uintptr_t)buf)) == 0 && (0x01 & len) == 0)
 		ioread16_rep(chip->IO_ADDR_R, buf, len >> 1);
 	else
 		ioread8_rep(chip->IO_ADDR_R, buf, len);
@@ -454,9 +453,9 @@ static void nand_davinci_write_buf(struct mtd_info *mtd,
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if ((0x03 & ((unsigned)buf)) == 0 && (0x03 & len) == 0)
+	if ((0x03 & ((uintptr_t)buf)) == 0 && (0x03 & len) == 0)
 		iowrite32_rep(chip->IO_ADDR_R, buf, len >> 2);
-	else if ((0x01 & ((unsigned)buf)) == 0 && (0x01 & len) == 0)
+	else if ((0x01 & ((uintptr_t)buf)) == 0 && (0x01 & len) == 0)
 		iowrite16_rep(chip->IO_ADDR_R, buf, len >> 1);
 	else
 		iowrite8_rep(chip->IO_ADDR_R, buf, len);
@@ -606,6 +605,104 @@ static struct davinci_nand_pdata
 }
 #endif
 
+static int davinci_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct davinci_nand_info *info = to_davinci_nand(mtd);
+	struct davinci_nand_pdata *pdata = nand_davinci_get_pdata(info->pdev);
+	int ret = 0;
+
+	if (IS_ERR(pdata))
+		return PTR_ERR(pdata);
+
+	switch (info->chip.ecc.mode) {
+	case NAND_ECC_NONE:
+		pdata->ecc_bits = 0;
+		break;
+	case NAND_ECC_SOFT:
+		pdata->ecc_bits = 0;
+		/*
+		 * This driver expects Hamming based ECC when ecc_mode is set
+		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
+		 * avoid adding an extra ->ecc_algo field to
+		 * davinci_nand_pdata.
+		 */
+		info->chip.ecc.algo = NAND_ECC_HAMMING;
+		break;
+	case NAND_ECC_HW:
+		if (pdata->ecc_bits == 4) {
+			/*
+			 * No sanity checks:  CPUs must support this,
+			 * and the chips may not use NAND_BUSWIDTH_16.
+			 */
+
+			/* No sharing 4-bit hardware between chipselects yet */
+			spin_lock_irq(&davinci_nand_lock);
+			if (ecc4_busy)
+				ret = -EBUSY;
+			else
+				ecc4_busy = true;
+			spin_unlock_irq(&davinci_nand_lock);
+
+			if (ret == -EBUSY)
+				return ret;
+
+			info->chip.ecc.calculate = nand_davinci_calculate_4bit;
+			info->chip.ecc.correct = nand_davinci_correct_4bit;
+			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
+			info->chip.ecc.bytes = 10;
+			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
+			info->chip.ecc.algo = NAND_ECC_BCH;
+		} else {
+			/* 1bit ecc hamming */
+			info->chip.ecc.calculate = nand_davinci_calculate_1bit;
+			info->chip.ecc.correct = nand_davinci_correct_1bit;
+			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
+			info->chip.ecc.bytes = 3;
+			info->chip.ecc.algo = NAND_ECC_HAMMING;
+		}
+		info->chip.ecc.size = 512;
+		info->chip.ecc.strength = pdata->ecc_bits;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * Update ECC layout if needed ... for 1-bit HW ECC, the default
+	 * is OK, but it allocates 6 bytes when only 3 are needed (for
+	 * each 512 bytes).  For the 4-bit HW ECC, that default is not
+	 * usable:  10 bytes are needed, not 6.
+	 */
+	if (pdata->ecc_bits == 4) {
+		int chunks = mtd->writesize / 512;
+
+		if (!chunks || mtd->oobsize < 16) {
+			dev_dbg(&info->pdev->dev, "too small\n");
+			return -EINVAL;
+		}
+
+		/* For small page chips, preserve the manufacturer's
+		 * badblock marking data ... and make sure a flash BBT
+		 * table marker fits in the free bytes.
+		 */
+		if (chunks == 1) {
+			mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops);
+		} else if (chunks == 4 || chunks == 8) {
+			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+			info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
+		} else {
+			return -EIO;
+		}
+	}
+
+	return ret;
+}
+
+static const struct nand_controller_ops davinci_nand_controller_ops = {
+	.attach_chip = davinci_nand_attach_chip,
+};
+
 static int nand_davinci_probe(struct platform_device *pdev)
 {
 	struct davinci_nand_pdata	*pdata;
@@ -659,7 +756,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 		return -EADDRNOTAVAIL;
 	}
 
-	info->dev		= &pdev->dev;
+	info->pdev		= pdev;
 	info->base		= base;
 	info->vaddr		= vaddr;
 
@@ -680,9 +777,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	info->chip.bbt_md	= pdata->bbt_md;
 	info->timing		= pdata->timing;
 
-	info->ioaddr		= (uint32_t __force) vaddr;
-
-	info->current_cs	= info->ioaddr;
+	info->current_cs	= info->vaddr;
 	info->core_chipsel	= pdata->core_chipsel;
 	info->mask_chipsel	= pdata->mask_chipsel;
 
@@ -711,100 +806,15 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	spin_unlock_irq(&davinci_nand_lock);
 
 	/* Scan to find existence of the device(s) */
-	ret = nand_scan_ident(mtd, pdata->mask_chipsel ? 2 : 1, NULL);
+	info->chip.dummy_controller.ops = &davinci_nand_controller_ops;
+	ret = nand_scan(mtd, pdata->mask_chipsel ? 2 : 1);
 	if (ret < 0) {
 		dev_dbg(&pdev->dev, "no NAND chip(s) found\n");
 		return ret;
 	}
 
-	switch (info->chip.ecc.mode) {
-	case NAND_ECC_NONE:
-		pdata->ecc_bits = 0;
-		break;
-	case NAND_ECC_SOFT:
-		pdata->ecc_bits = 0;
-		/*
-		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
-		 * avoid adding an extra ->ecc_algo field to
-		 * davinci_nand_pdata.
-		 */
-		info->chip.ecc.algo = NAND_ECC_HAMMING;
-		break;
-	case NAND_ECC_HW:
-		if (pdata->ecc_bits == 4) {
-			/* No sanity checks:  CPUs must support this,
-			 * and the chips may not use NAND_BUSWIDTH_16.
-			 */
-
-			/* No sharing 4-bit hardware between chipselects yet */
-			spin_lock_irq(&davinci_nand_lock);
-			if (ecc4_busy)
-				ret = -EBUSY;
-			else
-				ecc4_busy = true;
-			spin_unlock_irq(&davinci_nand_lock);
-
-			if (ret == -EBUSY)
-				return ret;
-
-			info->chip.ecc.calculate = nand_davinci_calculate_4bit;
-			info->chip.ecc.correct = nand_davinci_correct_4bit;
-			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
-			info->chip.ecc.bytes = 10;
-			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
-			info->chip.ecc.algo = NAND_ECC_BCH;
-		} else {
-			/* 1bit ecc hamming */
-			info->chip.ecc.calculate = nand_davinci_calculate_1bit;
-			info->chip.ecc.correct = nand_davinci_correct_1bit;
-			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
-			info->chip.ecc.bytes = 3;
-			info->chip.ecc.algo = NAND_ECC_HAMMING;
-		}
-		info->chip.ecc.size = 512;
-		info->chip.ecc.strength = pdata->ecc_bits;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* Update ECC layout if needed ... for 1-bit HW ECC, the default
-	 * is OK, but it allocates 6 bytes when only 3 are needed (for
-	 * each 512 bytes).  For the 4-bit HW ECC, that default is not
-	 * usable:  10 bytes are needed, not 6.
-	 */
-	if (pdata->ecc_bits == 4) {
-		int	chunks = mtd->writesize / 512;
-
-		if (!chunks || mtd->oobsize < 16) {
-			dev_dbg(&pdev->dev, "too small\n");
-			ret = -EINVAL;
-			goto err;
-		}
-
-		/* For small page chips, preserve the manufacturer's
-		 * badblock marking data ... and make sure a flash BBT
-		 * table marker fits in the free bytes.
-		 */
-		if (chunks == 1) {
-			mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops);
-		} else if (chunks == 4 || chunks == 8) {
-			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
-			info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
-		} else {
-			ret = -EIO;
-			goto err;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret < 0)
-		goto err;
-
 	if (pdata->parts)
-		ret = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata->parts, pdata->nr_parts);
+		ret = mtd_device_register(mtd, pdata->parts, pdata->nr_parts);
 	else
 		ret = mtd_device_register(mtd, NULL, 0);
 	if (ret < 0)
@@ -819,11 +829,6 @@ static int nand_davinci_probe(struct platform_device *pdev)
 err_cleanup_nand:
 	nand_cleanup(&info->chip);
 
-err:
-	spin_lock_irq(&davinci_nand_lock);
-	if (info->chip.ecc.mode == NAND_ECC_HW_SYNDROME)
-		ecc4_busy = false;
-	spin_unlock_irq(&davinci_nand_lock);
 	return ret;
 }
 
diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 2a302a1d1430..ca18612c4201 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -51,14 +51,6 @@ MODULE_LICENSE("GPL");
 #define DENALI_INVALID_BANK	-1
 #define DENALI_NR_BANKS		4
 
-/*
- * The bus interface clock, clk_x, is phase aligned with the core clock.  The
- * clk_x is an integral multiple N of the core clk.  The value N is configured
- * at IP delivery time, and its available value is 4, 5, or 6.  We need to align
- * to the largest value to make it work with any possible configuration.
- */
-#define DENALI_CLK_X_MULT	6
-
 static inline struct denali_nand_info *mtd_to_denali(struct mtd_info *mtd)
 {
 	return container_of(mtd_to_nand(mtd), struct denali_nand_info, nand);
@@ -954,7 +946,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	const struct nand_sdr_timings *timings;
-	unsigned long t_clk;
+	unsigned long t_x, mult_x;
 	int acc_clks, re_2_we, re_2_re, we_2_re, addr_2_data;
 	int rdwr_en_lo, rdwr_en_hi, rdwr_en_lo_hi, cs_setup;
 	int addr_2_data_mask;
@@ -965,15 +957,24 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 		return PTR_ERR(timings);
 
 	/* clk_x period in picoseconds */
-	t_clk = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate);
-	if (!t_clk)
+	t_x = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate);
+	if (!t_x)
+		return -EINVAL;
+
+	/*
+	 * The bus interface clock, clk_x, is phase aligned with the core clock.
+	 * The clk_x is an integral multiple N of the core clk.  The value N is
+	 * configured at IP delivery time, and its available value is 4, 5, 6.
+	 */
+	mult_x = DIV_ROUND_CLOSEST_ULL(denali->clk_x_rate, denali->clk_rate);
+	if (mult_x < 4 || mult_x > 6)
 		return -EINVAL;
 
 	if (chipnr == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	/* tREA -> ACC_CLKS */
-	acc_clks = DIV_ROUND_UP(timings->tREA_max, t_clk);
+	acc_clks = DIV_ROUND_UP(timings->tREA_max, t_x);
 	acc_clks = min_t(int, acc_clks, ACC_CLKS__VALUE);
 
 	tmp = ioread32(denali->reg + ACC_CLKS);
@@ -982,7 +983,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + ACC_CLKS);
 
 	/* tRWH -> RE_2_WE */
-	re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_clk);
+	re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_x);
 	re_2_we = min_t(int, re_2_we, RE_2_WE__VALUE);
 
 	tmp = ioread32(denali->reg + RE_2_WE);
@@ -991,7 +992,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RE_2_WE);
 
 	/* tRHZ -> RE_2_RE */
-	re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_clk);
+	re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_x);
 	re_2_re = min_t(int, re_2_re, RE_2_RE__VALUE);
 
 	tmp = ioread32(denali->reg + RE_2_RE);
@@ -1005,8 +1006,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	 * With WE_2_RE properly set, the Denali controller automatically takes
 	 * care of the delay; the driver need not set NAND_WAIT_TCCS.
 	 */
-	we_2_re = DIV_ROUND_UP(max(timings->tCCS_min, timings->tWHR_min),
-			       t_clk);
+	we_2_re = DIV_ROUND_UP(max(timings->tCCS_min, timings->tWHR_min), t_x);
 	we_2_re = min_t(int, we_2_re, TWHR2_AND_WE_2_RE__WE_2_RE);
 
 	tmp = ioread32(denali->reg + TWHR2_AND_WE_2_RE);
@@ -1021,7 +1021,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	if (denali->revision < 0x0501)
 		addr_2_data_mask >>= 1;
 
-	addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_clk);
+	addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_x);
 	addr_2_data = min_t(int, addr_2_data, addr_2_data_mask);
 
 	tmp = ioread32(denali->reg + TCWAW_AND_ADDR_2_DATA);
@@ -1031,7 +1031,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 
 	/* tREH, tWH -> RDWR_EN_HI_CNT */
 	rdwr_en_hi = DIV_ROUND_UP(max(timings->tREH_min, timings->tWH_min),
-				  t_clk);
+				  t_x);
 	rdwr_en_hi = min_t(int, rdwr_en_hi, RDWR_EN_HI_CNT__VALUE);
 
 	tmp = ioread32(denali->reg + RDWR_EN_HI_CNT);
@@ -1040,11 +1040,10 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RDWR_EN_HI_CNT);
 
 	/* tRP, tWP -> RDWR_EN_LO_CNT */
-	rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min),
-				  t_clk);
+	rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min), t_x);
 	rdwr_en_lo_hi = DIV_ROUND_UP(max(timings->tRC_min, timings->tWC_min),
-				     t_clk);
-	rdwr_en_lo_hi = max(rdwr_en_lo_hi, DENALI_CLK_X_MULT);
+				     t_x);
+	rdwr_en_lo_hi = max_t(int, rdwr_en_lo_hi, mult_x);
 	rdwr_en_lo = max(rdwr_en_lo, rdwr_en_lo_hi - rdwr_en_hi);
 	rdwr_en_lo = min_t(int, rdwr_en_lo, RDWR_EN_LO_CNT__VALUE);
 
@@ -1054,8 +1053,8 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RDWR_EN_LO_CNT);
 
 	/* tCS, tCEA -> CS_SETUP_CNT */
-	cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_clk) - rdwr_en_lo,
-			(int)DIV_ROUND_UP(timings->tCEA_max, t_clk) - acc_clks,
+	cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_x) - rdwr_en_lo,
+			(int)DIV_ROUND_UP(timings->tCEA_max, t_x) - acc_clks,
 			0);
 	cs_setup = min_t(int, cs_setup, CS_SETUP_CNT__VALUE);
 
@@ -1120,33 +1119,6 @@ int denali_calc_ecc_bytes(int step_size, int strength)
 }
 EXPORT_SYMBOL(denali_calc_ecc_bytes);
 
-static int denali_ecc_setup(struct mtd_info *mtd, struct nand_chip *chip,
-			    struct denali_nand_info *denali)
-{
-	int oobavail = mtd->oobsize - denali->oob_skip_bytes;
-	int ret;
-
-	/*
-	 * If .size and .strength are already set (usually by DT),
-	 * check if they are supported by this controller.
-	 */
-	if (chip->ecc.size && chip->ecc.strength)
-		return nand_check_ecc_caps(chip, denali->ecc_caps, oobavail);
-
-	/*
-	 * We want .size and .strength closest to the chip's requirement
-	 * unless NAND_ECC_MAXIMIZE is requested.
-	 */
-	if (!(chip->ecc.options & NAND_ECC_MAXIMIZE)) {
-		ret = nand_match_ecc_req(chip, denali->ecc_caps, oobavail);
-		if (!ret)
-			return 0;
-	}
-
-	/* Max ECC strength is the last thing we can do */
-	return nand_maximize_ecc(chip, denali->ecc_caps, oobavail);
-}
-
 static int denali_ooblayout_ecc(struct mtd_info *mtd, int section,
 				struct mtd_oob_region *oobregion)
 {
@@ -1233,62 +1205,12 @@ static int denali_multidev_fixup(struct denali_nand_info *denali)
 	return 0;
 }
 
-int denali_init(struct denali_nand_info *denali)
+static int denali_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &denali->nand;
 	struct mtd_info *mtd = nand_to_mtd(chip);
-	u32 features = ioread32(denali->reg + FEATURES);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	int ret;
 
-	mtd->dev.parent = denali->dev;
-	denali_hw_init(denali);
-
-	init_completion(&denali->complete);
-	spin_lock_init(&denali->irq_lock);
-
-	denali_clear_irq_all(denali);
-
-	ret = devm_request_irq(denali->dev, denali->irq, denali_isr,
-			       IRQF_SHARED, DENALI_NAND_NAME, denali);
-	if (ret) {
-		dev_err(denali->dev, "Unable to request IRQ\n");
-		return ret;
-	}
-
-	denali_enable_irq(denali);
-	denali_reset_banks(denali);
-
-	denali->active_bank = DENALI_INVALID_BANK;
-
-	nand_set_flash_node(chip, denali->dev->of_node);
-	/* Fallback to the default name if DT did not give "label" property */
-	if (!mtd->name)
-		mtd->name = "denali-nand";
-
-	chip->select_chip = denali_select_chip;
-	chip->read_byte = denali_read_byte;
-	chip->write_byte = denali_write_byte;
-	chip->read_word = denali_read_word;
-	chip->cmd_ctrl = denali_cmd_ctrl;
-	chip->dev_ready = denali_dev_ready;
-	chip->waitfunc = denali_waitfunc;
-
-	if (features & FEATURES__INDEX_ADDR) {
-		denali->host_read = denali_indexed_read;
-		denali->host_write = denali_indexed_write;
-	} else {
-		denali->host_read = denali_direct_read;
-		denali->host_write = denali_direct_write;
-	}
-
-	/* clk rate info is needed for setup_data_interface */
-	if (denali->clk_x_rate)
-		chip->setup_data_interface = denali_setup_data_interface;
-
-	ret = nand_scan_ident(mtd, denali->max_banks, NULL);
-	if (ret)
-		goto disable_irq;
-
 	if (ioread32(denali->reg + FEATURES) & FEATURES__DMA)
 		denali->dma_avail = 1;
 
@@ -1317,10 +1239,11 @@ int denali_init(struct denali_nand_info *denali)
 	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
-	ret = denali_ecc_setup(mtd, chip, denali);
+	ret = nand_ecc_choose_conf(chip, denali->ecc_caps,
+				   mtd->oobsize - denali->oob_skip_bytes);
 	if (ret) {
 		dev_err(denali->dev, "Failed to setup ECC settings.\n");
-		goto disable_irq;
+		return ret;
 	}
 
 	dev_dbg(denali->dev,
@@ -1364,7 +1287,7 @@ int denali_init(struct denali_nand_info *denali)
 
 	ret = denali_multidev_fixup(denali);
 	if (ret)
-		goto disable_irq;
+		return ret;
 
 	/*
 	 * This buffer is DMA-mapped by denali_{read,write}_page_raw.  Do not
@@ -1372,26 +1295,92 @@ int denali_init(struct denali_nand_info *denali)
 	 * guarantee DMA-safe alignment.
 	 */
 	denali->buf = kmalloc(mtd->writesize + mtd->oobsize, GFP_KERNEL);
-	if (!denali->buf) {
-		ret = -ENOMEM;
-		goto disable_irq;
+	if (!denali->buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void denali_detach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+
+	kfree(denali->buf);
+}
+
+static const struct nand_controller_ops denali_controller_ops = {
+	.attach_chip = denali_attach_chip,
+	.detach_chip = denali_detach_chip,
+};
+
+int denali_init(struct denali_nand_info *denali)
+{
+	struct nand_chip *chip = &denali->nand;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u32 features = ioread32(denali->reg + FEATURES);
+	int ret;
+
+	mtd->dev.parent = denali->dev;
+	denali_hw_init(denali);
+
+	init_completion(&denali->complete);
+	spin_lock_init(&denali->irq_lock);
+
+	denali_clear_irq_all(denali);
+
+	ret = devm_request_irq(denali->dev, denali->irq, denali_isr,
+			       IRQF_SHARED, DENALI_NAND_NAME, denali);
+	if (ret) {
+		dev_err(denali->dev, "Unable to request IRQ\n");
+		return ret;
 	}
 
-	ret = nand_scan_tail(mtd);
+	denali_enable_irq(denali);
+	denali_reset_banks(denali);
+
+	denali->active_bank = DENALI_INVALID_BANK;
+
+	nand_set_flash_node(chip, denali->dev->of_node);
+	/* Fallback to the default name if DT did not give "label" property */
+	if (!mtd->name)
+		mtd->name = "denali-nand";
+
+	chip->select_chip = denali_select_chip;
+	chip->read_byte = denali_read_byte;
+	chip->write_byte = denali_write_byte;
+	chip->read_word = denali_read_word;
+	chip->cmd_ctrl = denali_cmd_ctrl;
+	chip->dev_ready = denali_dev_ready;
+	chip->waitfunc = denali_waitfunc;
+
+	if (features & FEATURES__INDEX_ADDR) {
+		denali->host_read = denali_indexed_read;
+		denali->host_write = denali_indexed_write;
+	} else {
+		denali->host_read = denali_direct_read;
+		denali->host_write = denali_direct_write;
+	}
+
+	/* clk rate info is needed for setup_data_interface */
+	if (denali->clk_rate && denali->clk_x_rate)
+		chip->setup_data_interface = denali_setup_data_interface;
+
+	chip->dummy_controller.ops = &denali_controller_ops;
+	ret = nand_scan(mtd, denali->max_banks);
 	if (ret)
-		goto free_buf;
+		goto disable_irq;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(denali->dev, "Failed to register MTD: %d\n", ret);
 		goto cleanup_nand;
 	}
+
 	return 0;
 
 cleanup_nand:
 	nand_cleanup(chip);
-free_buf:
-	kfree(denali->buf);
 disable_irq:
 	denali_disable_irq(denali);
 
@@ -1404,7 +1393,6 @@ void denali_remove(struct denali_nand_info *denali)
 	struct mtd_info *mtd = nand_to_mtd(&denali->nand);
 
 	nand_release(mtd);
-	kfree(denali->buf);
 	denali_disable_irq(denali);
 }
 EXPORT_SYMBOL(denali_remove);
diff --git a/drivers/mtd/nand/raw/denali.h b/drivers/mtd/nand/raw/denali.h
index 9ad33d237378..1f8feaf924eb 100644
--- a/drivers/mtd/nand/raw/denali.h
+++ b/drivers/mtd/nand/raw/denali.h
@@ -300,6 +300,7 @@
 
 struct denali_nand_info {
 	struct nand_chip nand;
+	unsigned long clk_rate;		/* core clock rate */
 	unsigned long clk_x_rate;	/* bus interface clock rate */
 	int active_bank;		/* currently selected bank */
 	struct device *dev;
diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c
index 5869e90cc14b..0faaad032e5f 100644
--- a/drivers/mtd/nand/raw/denali_dt.c
+++ b/drivers/mtd/nand/raw/denali_dt.c
@@ -27,7 +27,9 @@
 
 struct denali_dt {
 	struct denali_nand_info	denali;
-	struct clk		*clk;
+	struct clk *clk;	/* core clock */
+	struct clk *clk_x;	/* bus interface clock */
+	struct clk *clk_ecc;	/* ECC circuit clock */
 };
 
 struct denali_dt_data {
@@ -79,63 +81,99 @@ MODULE_DEVICE_TABLE(of, denali_nand_dt_ids);
 
 static int denali_dt_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct denali_dt *dt;
 	const struct denali_dt_data *data;
 	struct denali_nand_info *denali;
 	int ret;
 
-	dt = devm_kzalloc(&pdev->dev, sizeof(*dt), GFP_KERNEL);
+	dt = devm_kzalloc(dev, sizeof(*dt), GFP_KERNEL);
 	if (!dt)
 		return -ENOMEM;
 	denali = &dt->denali;
 
-	data = of_device_get_match_data(&pdev->dev);
+	data = of_device_get_match_data(dev);
 	if (data) {
 		denali->revision = data->revision;
 		denali->caps = data->caps;
 		denali->ecc_caps = data->ecc_caps;
 	}
 
-	denali->dev = &pdev->dev;
+	denali->dev = dev;
 	denali->irq = platform_get_irq(pdev, 0);
 	if (denali->irq < 0) {
-		dev_err(&pdev->dev, "no irq defined\n");
+		dev_err(dev, "no irq defined\n");
 		return denali->irq;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg");
-	denali->reg = devm_ioremap_resource(&pdev->dev, res);
+	denali->reg = devm_ioremap_resource(dev, res);
 	if (IS_ERR(denali->reg))
 		return PTR_ERR(denali->reg);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data");
-	denali->host = devm_ioremap_resource(&pdev->dev, res);
+	denali->host = devm_ioremap_resource(dev, res);
 	if (IS_ERR(denali->host))
 		return PTR_ERR(denali->host);
 
-	dt->clk = devm_clk_get(&pdev->dev, NULL);
+	/*
+	 * A single anonymous clock is supported for the backward compatibility.
+	 * New platforms should support all the named clocks.
+	 */
+	dt->clk = devm_clk_get(dev, "nand");
+	if (IS_ERR(dt->clk))
+		dt->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(dt->clk)) {
-		dev_err(&pdev->dev, "no clk available\n");
+		dev_err(dev, "no clk available\n");
 		return PTR_ERR(dt->clk);
 	}
+
+	dt->clk_x = devm_clk_get(dev, "nand_x");
+	if (IS_ERR(dt->clk_x))
+		dt->clk_x = NULL;
+
+	dt->clk_ecc = devm_clk_get(dev, "ecc");
+	if (IS_ERR(dt->clk_ecc))
+		dt->clk_ecc = NULL;
+
 	ret = clk_prepare_enable(dt->clk);
 	if (ret)
 		return ret;
 
-	/*
-	 * Hardcode the clock rate for the backward compatibility.
-	 * This works for both SOCFPGA and UniPhier.
-	 */
-	denali->clk_x_rate = 200000000;
+	ret = clk_prepare_enable(dt->clk_x);
+	if (ret)
+		goto out_disable_clk;
+
+	ret = clk_prepare_enable(dt->clk_ecc);
+	if (ret)
+		goto out_disable_clk_x;
+
+	if (dt->clk_x) {
+		denali->clk_rate = clk_get_rate(dt->clk);
+		denali->clk_x_rate = clk_get_rate(dt->clk_x);
+	} else {
+		/*
+		 * Hardcode the clock rates for the backward compatibility.
+		 * This works for both SOCFPGA and UniPhier.
+		 */
+		dev_notice(dev,
+			   "necessary clock is missing. default clock rates are used.\n");
+		denali->clk_rate = 50000000;
+		denali->clk_x_rate = 200000000;
+	}
 
 	ret = denali_init(denali);
 	if (ret)
-		goto out_disable_clk;
+		goto out_disable_clk_ecc;
 
 	platform_set_drvdata(pdev, dt);
 	return 0;
 
+out_disable_clk_ecc:
+	clk_disable_unprepare(dt->clk_ecc);
+out_disable_clk_x:
+	clk_disable_unprepare(dt->clk_x);
 out_disable_clk:
 	clk_disable_unprepare(dt->clk);
 
@@ -147,6 +185,8 @@ static int denali_dt_remove(struct platform_device *pdev)
 	struct denali_dt *dt = platform_get_drvdata(pdev);
 
 	denali_remove(&dt->denali);
+	clk_disable_unprepare(dt->clk_ecc);
+	clk_disable_unprepare(dt->clk_x);
 	clk_disable_unprepare(dt->clk);
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/denali_pci.c b/drivers/mtd/nand/raw/denali_pci.c
index 49cb3e1f8bd0..7c8efc4c7bdf 100644
--- a/drivers/mtd/nand/raw/denali_pci.c
+++ b/drivers/mtd/nand/raw/denali_pci.c
@@ -73,6 +73,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	denali->irq = dev->irq;
 	denali->ecc_caps = &denali_pci_ecc_caps;
 	denali->nand.ecc.options |= NAND_ECC_MAXIMIZE;
+	denali->clk_rate = 50000000;		/* 50 MHz */
 	denali->clk_x_rate = 200000000;		/* 200 MHz */
 
 	ret = pci_request_regions(dev, DENALI_NAND_NAME);
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 8d10061abb4b..3c46188dd6d2 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1291,7 +1291,7 @@ static int __init nftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md = NULL;
 	}
 
-	ret = this->scan_bbt(mtd);
+	ret = nand_create_bbt(this);
 	if (ret)
 		return ret;
 
@@ -1338,7 +1338,7 @@ static int __init inftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md->pattern = "TBB_SYSM";
 	}
 
-	ret = this->scan_bbt(mtd);
+	ret = nand_create_bbt(this);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/nand/raw/docg4.c b/drivers/mtd/nand/raw/docg4.c
index 1314aa99b9ab..a3f04315c05c 100644
--- a/drivers/mtd/nand/raw/docg4.c
+++ b/drivers/mtd/nand/raw/docg4.c
@@ -1227,10 +1227,9 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	 * required within a nand driver because they are performed by the nand
 	 * infrastructure code as part of nand_scan().  In this case they need
 	 * to be initialized here because we skip call to nand_scan_ident() (the
-	 * first half of nand_scan()).  The call to nand_scan_ident() is skipped
-	 * because for this device the chip id is not read in the manner of a
-	 * standard nand device.  Unfortunately, nand_scan_ident() does other
-	 * things as well, such as call nand_set_defaults().
+	 * first half of nand_scan()).  The call to nand_scan_ident() could be
+	 * skipped because for this device the chip id is not read in the manner
+	 * of a standard nand device.
 	 */
 
 	struct nand_chip *nand = mtd_to_nand(mtd);
@@ -1257,8 +1256,8 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	nand->ecc.strength = DOCG4_T;
 	nand->options = NAND_BUSWIDTH_16 | NAND_NO_SUBPAGE_WRITE;
 	nand->IO_ADDR_R = nand->IO_ADDR_W = doc->virtadr + DOC_IOSPACE_DATA;
-	nand->controller = &nand->hwcontrol;
-	nand_hw_control_init(nand->controller);
+	nand->controller = &nand->dummy_controller;
+	nand_controller_init(nand->controller);
 
 	/* methods */
 	nand->cmdfunc = docg4_command;
@@ -1315,6 +1314,40 @@ static int __init read_id_reg(struct mtd_info *mtd)
 
 static char const *part_probes[] = { "cmdlinepart", "saftlpart", NULL };
 
+static int docg4_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct docg4_priv *doc = (struct docg4_priv *)(chip + 1);
+	int ret;
+
+	init_mtd_structs(mtd);
+
+	/* Initialize kernel BCH algorithm */
+	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
+	if (!doc->bch)
+		return -EINVAL;
+
+	reset(mtd);
+
+	ret = read_id_reg(mtd);
+	if (ret)
+		free_bch(doc->bch);
+
+	return ret;
+}
+
+static void docg4_detach_chip(struct nand_chip *chip)
+{
+	struct docg4_priv *doc = (struct docg4_priv *)(chip + 1);
+
+	free_bch(doc->bch);
+}
+
+static const struct nand_controller_ops docg4_controller_ops = {
+	.attach_chip = docg4_attach_chip,
+	.detach_chip = docg4_detach_chip,
+};
+
 static int __init probe_docg4(struct platform_device *pdev)
 {
 	struct mtd_info *mtd;
@@ -1341,7 +1374,7 @@ static int __init probe_docg4(struct platform_device *pdev)
 	nand = kzalloc(len, GFP_KERNEL);
 	if (nand == NULL) {
 		retval = -ENOMEM;
-		goto fail_unmap;
+		goto unmap;
 	}
 
 	mtd = nand_to_mtd(nand);
@@ -1350,46 +1383,35 @@ static int __init probe_docg4(struct platform_device *pdev)
 	mtd->dev.parent = &pdev->dev;
 	doc->virtadr = virtadr;
 	doc->dev = dev;
-
-	init_mtd_structs(mtd);
-
-	/* initialize kernel bch algorithm */
-	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
-	if (doc->bch == NULL) {
-		retval = -EINVAL;
-		goto fail;
-	}
-
 	platform_set_drvdata(pdev, doc);
 
-	reset(mtd);
-	retval = read_id_reg(mtd);
-	if (retval == -ENODEV) {
-		dev_warn(dev, "No diskonchip G4 device found.\n");
-		goto fail;
-	}
-
-	retval = nand_scan_tail(mtd);
+	/*
+	 * Running nand_scan() with maxchips == 0 will skip nand_scan_ident(),
+	 * which is a specific operation with this driver and done in the
+	 * ->attach_chip callback.
+	 */
+	nand->dummy_controller.ops = &docg4_controller_ops;
+	retval = nand_scan(mtd, 0);
 	if (retval)
-		goto fail;
+		goto free_nand;
 
 	retval = read_factory_bbt(mtd);
 	if (retval)
-		goto fail;
+		goto cleanup_nand;
 
 	retval = mtd_device_parse_register(mtd, part_probes, NULL, NULL, 0);
 	if (retval)
-		goto fail;
+		goto cleanup_nand;
 
 	doc->mtd = mtd;
+
 	return 0;
 
-fail:
-	nand_release(mtd); /* deletes partitions and mtd devices */
-	free_bch(doc->bch);
+cleanup_nand:
+	nand_cleanup(nand);
+free_nand:
 	kfree(nand);
-
-fail_unmap:
+unmap:
 	iounmap(virtadr);
 
 	return retval;
@@ -1399,7 +1421,6 @@ static int __exit cleanup_docg4(struct platform_device *pdev)
 {
 	struct docg4_priv *doc = platform_get_drvdata(pdev);
 	nand_release(doc->mtd);
-	free_bch(doc->bch);
 	kfree(mtd_to_nand(doc->mtd));
 	iounmap(doc->virtadr);
 	return 0;
diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index 51f0b340bc0d..55f449b711fd 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -61,7 +61,7 @@ struct fsl_elbc_mtd {
 /* Freescale eLBC FCM controller information */
 
 struct fsl_elbc_fcm_ctrl {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct fsl_elbc_mtd *chips[MAX_BANKS];
 
 	u8 __iomem *addr;        /* Address of assigned FCM buffer        */
@@ -637,9 +637,9 @@ static int fsl_elbc_wait(struct mtd_info *mtd, struct nand_chip *chip)
 	return (elbc_fcm_ctrl->mdr & 0xff) | NAND_STATUS_WP;
 }
 
-static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
+static int fsl_elbc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct fsl_elbc_mtd *priv = nand_get_controller_data(chip);
 	struct fsl_lbc_ctrl *ctrl = priv->ctrl;
 	struct fsl_lbc_regs __iomem *lbc = ctrl->regs;
@@ -700,12 +700,16 @@ static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
 		dev_err(priv->dev,
 		        "fsl_elbc_init: page size %d is not supported\n",
 		        mtd->writesize);
-		return -1;
+		return -ENOTSUPP;
 	}
 
 	return 0;
 }
 
+static const struct nand_controller_ops fsl_elbc_controller_ops = {
+	.attach_chip = fsl_elbc_attach_chip,
+};
+
 static int fsl_elbc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 			      uint8_t *buf, int oob_required, int page)
 {
@@ -879,7 +883,7 @@ static int fsl_elbc_nand_probe(struct platform_device *pdev)
 		}
 		elbc_fcm_ctrl->counter++;
 
-		nand_hw_control_init(&elbc_fcm_ctrl->controller);
+		nand_controller_init(&elbc_fcm_ctrl->controller);
 		fsl_lbc_ctrl_dev->nand = elbc_fcm_ctrl;
 	} else {
 		elbc_fcm_ctrl = fsl_lbc_ctrl_dev->nand;
@@ -910,15 +914,8 @@ static int fsl_elbc_nand_probe(struct platform_device *pdev)
 	if (ret)
 		goto err;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		goto err;
-
-	ret = fsl_elbc_chip_init_tail(mtd);
-	if (ret)
-		goto err;
-
-	ret = nand_scan_tail(mtd);
+	priv->chip.controller->ops = &fsl_elbc_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto err;
 
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 382b67e97174..24f59d0066af 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -51,7 +51,7 @@ struct fsl_ifc_mtd {
 
 /* overview of the fsl ifc controller */
 struct fsl_ifc_nand_ctrl {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct fsl_ifc_mtd *chips[FSL_IFC_BANK_COUNT];
 
 	void __iomem *addr;	/* Address of assigned IFC buffer	*/
@@ -225,7 +225,7 @@ static void fsl_ifc_run_command(struct mtd_info *mtd)
 		int bufnum = nctrl->page & priv->bufnum_mask;
 		int sector_start = bufnum * chip->ecc.steps;
 		int sector_end = sector_start + chip->ecc.steps - 1;
-		__be32 *eccstat_regs;
+		__be32 __iomem *eccstat_regs;
 
 		eccstat_regs = ifc->ifc_nand.nand_eccstat;
 		eccstat = ifc_in32(&eccstat_regs[sector_start / 4]);
@@ -714,9 +714,9 @@ static int fsl_ifc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return nand_prog_page_end_op(chip);
 }
 
-static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
+static int fsl_ifc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
 
 	dev_dbg(priv->dev, "%s: nand->numchips = %d\n", __func__,
@@ -757,6 +757,10 @@ static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
 	return 0;
 }
 
+static const struct nand_controller_ops fsl_ifc_controller_ops = {
+	.attach_chip = fsl_ifc_attach_chip,
+};
+
 static void fsl_ifc_sram_init(struct fsl_ifc_mtd *priv)
 {
 	struct fsl_ifc_ctrl *ctrl = priv->ctrl;
@@ -1004,7 +1008,7 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
 		ifc_nand_ctrl->addr = NULL;
 		fsl_ifc_ctrl_dev->nand = ifc_nand_ctrl;
 
-		nand_hw_control_init(&ifc_nand_ctrl->controller);
+		nand_controller_init(&ifc_nand_ctrl->controller);
 	} else {
 		ifc_nand_ctrl = fsl_ifc_ctrl_dev->nand;
 	}
@@ -1046,15 +1050,8 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
 	if (ret)
 		goto err;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		goto err;
-
-	ret = fsl_ifc_chip_init_tail(mtd);
-	if (ret)
-		goto err;
-
-	ret = nand_scan_tail(mtd);
+	priv->chip.controller->ops = &fsl_ifc_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto err;
 
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index f4a5a317d4ae..f418236fa020 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -62,7 +62,7 @@
 						reg)
 
 /* fsmc controller registers for NAND flash */
-#define PC			0x00
+#define FSMC_PC			0x00
 	/* pc register definitions */
 	#define FSMC_RESET		(1 << 0)
 	#define FSMC_WAITON		(1 << 1)
@@ -273,12 +273,13 @@ static void fsmc_nand_setup(struct fsmc_nand_data *host,
 	tset = (tims->tset & FSMC_TSET_MASK) << FSMC_TSET_SHIFT;
 
 	if (host->nand.options & NAND_BUSWIDTH_16)
-		writel_relaxed(value | FSMC_DEVWID_16, host->regs_va + PC);
+		writel_relaxed(value | FSMC_DEVWID_16,
+			       host->regs_va + FSMC_PC);
 	else
-		writel_relaxed(value | FSMC_DEVWID_8, host->regs_va + PC);
+		writel_relaxed(value | FSMC_DEVWID_8, host->regs_va + FSMC_PC);
 
-	writel_relaxed(readl(host->regs_va + PC) | tclr | tar,
-		       host->regs_va + PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) | tclr | tar,
+		       host->regs_va + FSMC_PC);
 	writel_relaxed(thiz | thold | twait | tset, host->regs_va + COMM);
 	writel_relaxed(thiz | thold | twait | tset, host->regs_va + ATTRIB);
 }
@@ -371,12 +372,12 @@ static void fsmc_enable_hwecc(struct mtd_info *mtd, int mode)
 {
 	struct fsmc_nand_data *host = mtd_to_fsmc(mtd);
 
-	writel_relaxed(readl(host->regs_va + PC) & ~FSMC_ECCPLEN_256,
-		       host->regs_va + PC);
-	writel_relaxed(readl(host->regs_va + PC) & ~FSMC_ECCEN,
-		       host->regs_va + PC);
-	writel_relaxed(readl(host->regs_va + PC) | FSMC_ECCEN,
-		       host->regs_va + PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) & ~FSMC_ECCPLEN_256,
+		       host->regs_va + FSMC_PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) & ~FSMC_ECCEN,
+		       host->regs_va + FSMC_PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) | FSMC_ECCEN,
+		       host->regs_va + FSMC_PC);
 }
 
 /*
@@ -546,7 +547,7 @@ static void fsmc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	struct fsmc_nand_data *host  = mtd_to_fsmc(mtd);
 	int i;
 
-	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+	if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) &&
 			IS_ALIGNED(len, sizeof(uint32_t))) {
 		uint32_t *p = (uint32_t *)buf;
 		len = len >> 2;
@@ -569,7 +570,7 @@ static void fsmc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	struct fsmc_nand_data *host  = mtd_to_fsmc(mtd);
 	int i;
 
-	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+	if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) &&
 			IS_ALIGNED(len, sizeof(uint32_t))) {
 		uint32_t *p = (uint32_t *)buf;
 		len = len >> 2;
@@ -618,11 +619,11 @@ static void fsmc_select_chip(struct mtd_info *mtd, int chipnr)
 	if (chipnr > 0)
 		return;
 
-	pc = readl(host->regs_va + PC);
+	pc = readl(host->regs_va + FSMC_PC);
 	if (chipnr < 0)
-		writel_relaxed(pc & ~FSMC_ENABLE, host->regs_va + PC);
+		writel_relaxed(pc & ~FSMC_ENABLE, host->regs_va + FSMC_PC);
 	else
-		writel_relaxed(pc | FSMC_ENABLE, host->regs_va + PC);
+		writel_relaxed(pc | FSMC_ENABLE, host->regs_va + FSMC_PC);
 
 	/* nCE line must be asserted before starting any operation */
 	mb();
@@ -740,7 +741,7 @@ static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
 	for (i = 0, s = 0; s < eccsteps; s++, i += eccbytes, p += eccsize) {
 		nand_read_page_op(chip, page, s * eccsize, NULL, 0);
 		chip->ecc.hwctl(mtd, NAND_ECC_READ);
-		chip->read_buf(mtd, p, eccsize);
+		nand_read_data_op(chip, p, eccsize, false);
 
 		for (j = 0; j < eccbytes;) {
 			struct mtd_oob_region oobregion;
@@ -918,6 +919,82 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
 	return 0;
 }
 
+static int fsmc_nand_attach_chip(struct nand_chip *nand)
+{
+	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct fsmc_nand_data *host = mtd_to_fsmc(mtd);
+
+	if (AMBA_REV_BITS(host->pid) >= 8) {
+		switch (mtd->oobsize) {
+		case 16:
+		case 64:
+		case 128:
+		case 224:
+		case 256:
+			break;
+		default:
+			dev_warn(host->dev,
+				 "No oob scheme defined for oobsize %d\n",
+				 mtd->oobsize);
+			return -EINVAL;
+		}
+
+		mtd_set_ooblayout(mtd, &fsmc_ecc4_ooblayout_ops);
+
+		return 0;
+	}
+
+	switch (nand->ecc.mode) {
+	case NAND_ECC_HW:
+		dev_info(host->dev, "Using 1-bit HW ECC scheme\n");
+		nand->ecc.calculate = fsmc_read_hwecc_ecc1;
+		nand->ecc.correct = nand_correct_data;
+		nand->ecc.bytes = 3;
+		nand->ecc.strength = 1;
+		break;
+
+	case NAND_ECC_SOFT:
+		if (nand->ecc.algo == NAND_ECC_BCH) {
+			dev_info(host->dev,
+				 "Using 4-bit SW BCH ECC scheme\n");
+			break;
+		}
+
+	case NAND_ECC_ON_DIE:
+		break;
+
+	default:
+		dev_err(host->dev, "Unsupported ECC mode!\n");
+		return -ENOTSUPP;
+	}
+
+	/*
+	 * Don't set layout for BCH4 SW ECC. This will be
+	 * generated later in nand_bch_init() later.
+	 */
+	if (nand->ecc.mode == NAND_ECC_HW) {
+		switch (mtd->oobsize) {
+		case 16:
+		case 64:
+		case 128:
+			mtd_set_ooblayout(mtd,
+					  &fsmc_ecc1_ooblayout_ops);
+			break;
+		default:
+			dev_warn(host->dev,
+				 "No oob scheme defined for oobsize %d\n",
+				 mtd->oobsize);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops fsmc_nand_controller_ops = {
+	.attach_chip = fsmc_nand_attach_chip,
+};
+
 /*
  * fsmc_nand_probe - Probe function
  * @pdev:       platform device structure
@@ -1047,76 +1124,8 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	/*
 	 * Scan to find existence of the device
 	 */
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret) {
-		dev_err(&pdev->dev, "No NAND Device found!\n");
-		goto release_dma_write_chan;
-	}
-
-	if (AMBA_REV_BITS(host->pid) >= 8) {
-		switch (mtd->oobsize) {
-		case 16:
-		case 64:
-		case 128:
-		case 224:
-		case 256:
-			break;
-		default:
-			dev_warn(&pdev->dev, "No oob scheme defined for oobsize %d\n",
-				 mtd->oobsize);
-			ret = -EINVAL;
-			goto release_dma_write_chan;
-		}
-
-		mtd_set_ooblayout(mtd, &fsmc_ecc4_ooblayout_ops);
-	} else {
-		switch (nand->ecc.mode) {
-		case NAND_ECC_HW:
-			dev_info(&pdev->dev, "Using 1-bit HW ECC scheme\n");
-			nand->ecc.calculate = fsmc_read_hwecc_ecc1;
-			nand->ecc.correct = nand_correct_data;
-			nand->ecc.bytes = 3;
-			nand->ecc.strength = 1;
-			break;
-
-		case NAND_ECC_SOFT:
-			if (nand->ecc.algo == NAND_ECC_BCH) {
-				dev_info(&pdev->dev, "Using 4-bit SW BCH ECC scheme\n");
-				break;
-			}
-
-		case NAND_ECC_ON_DIE:
-			break;
-
-		default:
-			dev_err(&pdev->dev, "Unsupported ECC mode!\n");
-			goto release_dma_write_chan;
-		}
-
-		/*
-		 * Don't set layout for BCH4 SW ECC. This will be
-		 * generated later in nand_bch_init() later.
-		 */
-		if (nand->ecc.mode == NAND_ECC_HW) {
-			switch (mtd->oobsize) {
-			case 16:
-			case 64:
-			case 128:
-				mtd_set_ooblayout(mtd,
-						  &fsmc_ecc1_ooblayout_ops);
-				break;
-			default:
-				dev_warn(&pdev->dev,
-					 "No oob scheme defined for oobsize %d\n",
-					 mtd->oobsize);
-				ret = -EINVAL;
-				goto release_dma_write_chan;
-			}
-		}
-	}
-
-	/* Second stage of scan to fill MTD data-structures */
-	ret = nand_scan_tail(mtd);
+	nand->dummy_controller.ops = &fsmc_nand_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto release_dma_write_chan;
 
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
index 83697b8df871..88ea2203e263 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * 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, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #include <linux/delay.h>
 #include <linux/clk.h>
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index f6aa358a3452..1c1ebbc82824 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2010-2015 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * 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, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #include <linux/clk.h>
 #include <linux/slab.h>
@@ -757,9 +744,9 @@ static int gpmi_alloc_dma_buffer(struct gpmi_nand_data *this)
 	 * [2] Allocate a read/write data buffer.
 	 *     The gpmi_alloc_dma_buffer can be called twice.
 	 *     We allocate a PAGE_SIZE length buffer if gpmi_alloc_dma_buffer
-	 *     is called before the nand_scan_ident; and we allocate a buffer
-	 *     of the real NAND page size when the gpmi_alloc_dma_buffer is
-	 *     called after the nand_scan_ident.
+	 *     is called before the NAND identification; and we allocate a
+	 *     buffer of the real NAND page size when the gpmi_alloc_dma_buffer
+	 *     is called after.
 	 */
 	this->data_buffer_dma = kzalloc(mtd->writesize ?: PAGE_SIZE,
 					GFP_DMA | GFP_KERNEL);
@@ -957,7 +944,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 	struct gpmi_nand_data *this = nand_get_controller_data(chip);
 	struct bch_geometry *nfc_geo = &this->bch_geometry;
 	struct mtd_info *mtd = nand_to_mtd(chip);
-	void          *payload_virt;
 	dma_addr_t    payload_phys;
 	unsigned int  i;
 	unsigned char *status;
@@ -967,7 +953,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 
 	dev_dbg(this->dev, "page number is : %d\n", page);
 
-	payload_virt = this->payload_virt;
 	payload_phys = this->payload_phys;
 
 	if (virt_addr_valid(buf)) {
@@ -976,7 +961,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 		dest_phys = dma_map_single(this->dev, buf, nfc_geo->payload_size,
 					   DMA_FROM_DEVICE);
 		if (!dma_mapping_error(this->dev, dest_phys)) {
-			payload_virt = buf;
 			payload_phys = dest_phys;
 			direct = true;
 		}
@@ -1881,6 +1865,34 @@ static int gpmi_init_last(struct gpmi_nand_data *this)
 	return 0;
 }
 
+static int gpmi_nand_attach_chip(struct nand_chip *chip)
+{
+	struct gpmi_nand_data *this = nand_get_controller_data(chip);
+	int ret;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+		if (of_property_read_bool(this->dev->of_node,
+					  "fsl,no-blockmark-swap"))
+			this->swap_block_mark = false;
+	}
+	dev_dbg(this->dev, "Blockmark swapping %sabled\n",
+		this->swap_block_mark ? "en" : "dis");
+
+	ret = gpmi_init_last(this);
+	if (ret)
+		return ret;
+
+	chip->options |= NAND_SKIP_BBTSCAN;
+
+	return 0;
+}
+
+static const struct nand_controller_ops gpmi_nand_controller_ops = {
+	.attach_chip = gpmi_nand_attach_chip,
+};
+
 static int gpmi_nand_init(struct gpmi_nand_data *this)
 {
 	struct nand_chip *chip = &this->nand;
@@ -1921,33 +1933,15 @@ static int gpmi_nand_init(struct gpmi_nand_data *this)
 	if (ret)
 		goto err_out;
 
-	ret = nand_scan_ident(mtd, GPMI_IS_MX6(this) ? 2 : 1, NULL);
-	if (ret)
-		goto err_out;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-		if (of_property_read_bool(this->dev->of_node,
-						"fsl,no-blockmark-swap"))
-			this->swap_block_mark = false;
-	}
-	dev_dbg(this->dev, "Blockmark swapping %sabled\n",
-		this->swap_block_mark ? "en" : "dis");
-
-	ret = gpmi_init_last(this);
-	if (ret)
-		goto err_out;
-
-	chip->options |= NAND_SKIP_BBTSCAN;
-	ret = nand_scan_tail(mtd);
+	chip->dummy_controller.ops = &gpmi_nand_controller_ops;
+	ret = nand_scan(mtd, GPMI_IS_MX6(this) ? 2 : 1);
 	if (ret)
 		goto err_out;
 
 	ret = nand_boot_init(this);
 	if (ret)
 		goto err_nand_cleanup;
-	ret = chip->scan_bbt(mtd);
+	ret = nand_create_bbt(chip);
 	if (ret)
 		goto err_nand_cleanup;
 
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
index 6aa10d6962d6..69cd0cbde4f2 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
@@ -1,18 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2010-2011 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * 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.
  */
 #ifndef __DRIVERS_MTD_NAND_GPMI_NAND_H
 #define __DRIVERS_MTD_NAND_GPMI_NAND_H
diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c
index a1e009c8e556..950dc7789296 100644
--- a/drivers/mtd/nand/raw/hisi504_nand.c
+++ b/drivers/mtd/nand/raw/hisi504_nand.c
@@ -709,9 +709,50 @@ static int hisi_nfc_ecc_probe(struct hinfc_host *host)
 	return 0;
 }
 
+static int hisi_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct hinfc_host *host = nand_get_controller_data(chip);
+	int flag;
+
+	host->buffer = dmam_alloc_coherent(host->dev,
+					   mtd->writesize + mtd->oobsize,
+					   &host->dma_buffer, GFP_KERNEL);
+	if (!host->buffer)
+		return -ENOMEM;
+
+	host->dma_oob = host->dma_buffer + mtd->writesize;
+	memset(host->buffer, 0xff, mtd->writesize + mtd->oobsize);
+
+	flag = hinfc_read(host, HINFC504_CON);
+	flag &= ~(HINFC504_CON_PAGESIZE_MASK << HINFC504_CON_PAGEISZE_SHIFT);
+	switch (mtd->writesize) {
+	case 2048:
+		flag |= (0x001 << HINFC504_CON_PAGEISZE_SHIFT);
+		break;
+	/*
+	 * TODO: add more pagesize support,
+	 * default pagesize has been set in hisi_nfc_host_init
+	 */
+	default:
+		dev_err(host->dev, "NON-2KB page size nand flash\n");
+		return -EINVAL;
+	}
+	hinfc_write(host, flag, HINFC504_CON);
+
+	if (chip->ecc.mode == NAND_ECC_HW)
+		hisi_nfc_ecc_probe(host);
+
+	return 0;
+}
+
+static const struct nand_controller_ops hisi_nfc_controller_ops = {
+	.attach_chip = hisi_nfc_attach_chip,
+};
+
 static int hisi_nfc_probe(struct platform_device *pdev)
 {
-	int ret = 0, irq, flag, max_chips = HINFC504_MAX_CHIP;
+	int ret = 0, irq, max_chips = HINFC504_MAX_CHIP;
 	struct device *dev = &pdev->dev;
 	struct hinfc_host *host;
 	struct nand_chip  *chip;
@@ -769,42 +810,11 @@ static int hisi_nfc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = nand_scan_ident(mtd, max_chips, NULL);
+	chip->dummy_controller.ops = &hisi_nfc_controller_ops;
+	ret = nand_scan(mtd, max_chips);
 	if (ret)
 		return ret;
 
-	host->buffer = dmam_alloc_coherent(dev, mtd->writesize + mtd->oobsize,
-		&host->dma_buffer, GFP_KERNEL);
-	if (!host->buffer)
-		return -ENOMEM;
-
-	host->dma_oob = host->dma_buffer + mtd->writesize;
-	memset(host->buffer, 0xff, mtd->writesize + mtd->oobsize);
-
-	flag = hinfc_read(host, HINFC504_CON);
-	flag &= ~(HINFC504_CON_PAGESIZE_MASK << HINFC504_CON_PAGEISZE_SHIFT);
-	switch (mtd->writesize) {
-	case 2048:
-		flag |= (0x001 << HINFC504_CON_PAGEISZE_SHIFT); break;
-	/*
-	 * TODO: add more pagesize support,
-	 * default pagesize has been set in hisi_nfc_host_init
-	 */
-	default:
-		dev_err(dev, "NON-2KB page size nand flash\n");
-		return -EINVAL;
-	}
-	hinfc_write(host, flag, HINFC504_CON);
-
-	if (chip->ecc.mode == NAND_ECC_HW)
-		hisi_nfc_ecc_probe(host);
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
-		return ret;
-	}
-
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "Err MTD partition=%d\n", ret);
diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index 613b00a9604b..a7515452bc59 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -23,9 +24,9 @@
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
-#include <asm/mach-jz4740/jz4740_nand.h>
+#include <linux/platform_data/jz4740/jz4740_nand.h>
 
 #define JZ_REG_NAND_CTRL	0x50
 #define JZ_REG_NAND_ECC_CTRL	0x100
@@ -330,7 +331,7 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 
 	if (chipnr == 0) {
 		/* Detect first chip. */
-		ret = nand_scan_ident(mtd, 1, NULL);
+		ret = nand_scan(mtd, 1);
 		if (ret)
 			goto notfound_id;
 
@@ -355,7 +356,7 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 		mtd->size += chip->chipsize;
 	}
 
-	dev_info(&pdev->dev, "Found chip %i on bank %i\n", chipnr, bank);
+	dev_info(&pdev->dev, "Found chip %zu on bank %i\n", chipnr, bank);
 	return 0;
 
 notfound_id:
@@ -367,6 +368,24 @@ notfound_id:
 	return ret;
 }
 
+static int jz_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct device *dev = mtd->dev.parent;
+	struct jz_nand_platform_data *pdata = dev_get_platdata(dev);
+	struct platform_device *pdev = to_platform_device(dev);
+
+	if (pdata && pdata->ident_callback)
+		pdata->ident_callback(pdev, mtd, &pdata->partitions,
+				      &pdata->num_partitions);
+
+	return 0;
+}
+
+static const struct nand_controller_ops jz_nand_controller_ops = {
+	.attach_chip = jz_nand_attach_chip,
+};
+
 static int jz_nand_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -410,6 +429,7 @@ static int jz_nand_probe(struct platform_device *pdev)
 	chip->chip_delay = 50;
 	chip->cmd_ctrl = jz_nand_cmd_ctrl;
 	chip->select_chip = jz_nand_select_chip;
+	chip->dummy_controller.ops = &jz_nand_controller_ops;
 
 	if (nand->busy_gpio)
 		chip->dev_ready = jz_nand_dev_ready;
@@ -455,33 +475,20 @@ static int jz_nand_probe(struct platform_device *pdev)
 		goto err_iounmap_mmio;
 	}
 
-	if (pdata && pdata->ident_callback) {
-		pdata->ident_callback(pdev, mtd, &pdata->partitions,
-					&pdata->num_partitions);
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(&pdev->dev,  "Failed to scan NAND\n");
-		goto err_unclaim_banks;
-	}
-
-	ret = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata ? pdata->partitions : NULL,
-					pdata ? pdata->num_partitions : 0);
+	ret = mtd_device_register(mtd, pdata ? pdata->partitions : NULL,
+				  pdata ? pdata->num_partitions : 0);
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to add mtd device\n");
-		goto err_nand_release;
+		goto err_cleanup_nand;
 	}
 
 	dev_info(&pdev->dev, "Successfully registered JZ4740 NAND driver\n");
 
 	return 0;
 
-err_nand_release:
-	nand_release(mtd);
-err_unclaim_banks:
+err_cleanup_nand:
+	nand_cleanup(chip);
 	while (chipnr--) {
 		unsigned char bank = nand->banks[chipnr];
 		jz_nand_iounmap_resource(nand->bank_mem[bank - 1],
diff --git a/drivers/mtd/nand/raw/jz4780_nand.c b/drivers/mtd/nand/raw/jz4780_nand.c
index e69f6ae4c539..db4fa60bd52a 100644
--- a/drivers/mtd/nand/raw/jz4780_nand.c
+++ b/drivers/mtd/nand/raw/jz4780_nand.c
@@ -44,7 +44,7 @@ struct jz4780_nand_cs {
 struct jz4780_nand_controller {
 	struct device *dev;
 	struct jz4780_bch *bch;
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	unsigned int num_banks;
 	struct list_head chips;
 	int selected;
@@ -65,7 +65,8 @@ static inline struct jz4780_nand_chip *to_jz4780_nand_chip(struct mtd_info *mtd)
 	return container_of(mtd_to_nand(mtd), struct jz4780_nand_chip, chip);
 }
 
-static inline struct jz4780_nand_controller *to_jz4780_nand_controller(struct nand_hw_control *ctrl)
+static inline struct jz4780_nand_controller
+*to_jz4780_nand_controller(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct jz4780_nand_controller, controller);
 }
@@ -157,9 +158,8 @@ static int jz4780_nand_ecc_correct(struct mtd_info *mtd, u8 *dat,
 	return jz4780_bch_correct(nfc->bch, &params, dat, read_ecc);
 }
 
-static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *dev)
+static int jz4780_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct jz4780_nand_controller *nfc = to_jz4780_nand_controller(chip->controller);
 	int eccbytes;
@@ -170,7 +170,8 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	switch (chip->ecc.mode) {
 	case NAND_ECC_HW:
 		if (!nfc->bch) {
-			dev_err(dev, "HW BCH selected, but BCH controller not found\n");
+			dev_err(nfc->dev,
+				"HW BCH selected, but BCH controller not found\n");
 			return -ENODEV;
 		}
 
@@ -179,15 +180,16 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 		chip->ecc.correct = jz4780_nand_ecc_correct;
 		/* fall through */
 	case NAND_ECC_SOFT:
-		dev_info(dev, "using %s (strength %d, size %d, bytes %d)\n",
-			(nfc->bch) ? "hardware BCH" : "software ECC",
-			chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
+		dev_info(nfc->dev, "using %s (strength %d, size %d, bytes %d)\n",
+			 (nfc->bch) ? "hardware BCH" : "software ECC",
+			 chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
 		break;
 	case NAND_ECC_NONE:
-		dev_info(dev, "not using ECC\n");
+		dev_info(nfc->dev, "not using ECC\n");
 		break;
 	default:
-		dev_err(dev, "ECC mode %d not supported\n", chip->ecc.mode);
+		dev_err(nfc->dev, "ECC mode %d not supported\n",
+			chip->ecc.mode);
 		return -EINVAL;
 	}
 
@@ -199,7 +201,7 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	eccbytes = mtd->writesize / chip->ecc.size * chip->ecc.bytes;
 
 	if (eccbytes > mtd->oobsize - 2) {
-		dev_err(dev,
+		dev_err(nfc->dev,
 			"invalid ECC config: required %d ECC bytes, but only %d are available",
 			eccbytes, mtd->oobsize - 2);
 		return -EINVAL;
@@ -210,6 +212,10 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	return 0;
 }
 
+static const struct nand_controller_ops jz4780_nand_controller_ops = {
+	.attach_chip = jz4780_nand_attach_chip,
+};
+
 static int jz4780_nand_init_chip(struct platform_device *pdev,
 				struct jz4780_nand_controller *nfc,
 				struct device_node *np,
@@ -279,15 +285,8 @@ static int jz4780_nand_init_chip(struct platform_device *pdev,
 	chip->controller = &nfc->controller;
 	nand_set_flash_node(chip, np);
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	ret = jz4780_nand_init_ecc(nand, dev);
-	if (ret)
-		return ret;
-
-	ret = nand_scan_tail(mtd);
+	chip->controller->ops = &jz4780_nand_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
@@ -368,7 +367,7 @@ static int jz4780_nand_probe(struct platform_device *pdev)
 	nfc->dev = dev;
 	nfc->num_banks = num_banks;
 
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
 	INIT_LIST_HEAD(&nfc->chips);
 
 	ret = jz4780_nand_init_chips(nfc, pdev);
diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 052d123a8304..e82abada130a 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -184,6 +184,7 @@ static struct nand_bbt_descr lpc32xx_nand_bbt_mirror = {
 };
 
 struct lpc32xx_nand_host {
+	struct platform_device	*pdev;
 	struct nand_chip	nand_chip;
 	struct lpc32xx_mlc_platform_data *pdata;
 	struct clk		*clk;
@@ -653,6 +654,32 @@ static struct lpc32xx_nand_cfg_mlc *lpc32xx_parse_dt(struct device *dev)
 	return ncfg;
 }
 
+static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
+	struct device *dev = &host->pdev->dev;
+
+	host->dma_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL);
+	if (!host->dma_buf)
+		return -ENOMEM;
+
+	host->dummy_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL);
+	if (!host->dummy_buf)
+		return -ENOMEM;
+
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.size = 512;
+	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
+	host->mlcsubpages = mtd->writesize / 512;
+
+	return 0;
+}
+
+static const struct nand_controller_ops lpc32xx_nand_controller_ops = {
+	.attach_chip = lpc32xx_nand_attach_chip,
+};
+
 /*
  * Probe for NAND controller
  */
@@ -669,6 +696,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	if (!host)
 		return -ENOMEM;
 
+	host->pdev = pdev;
+
 	rc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->io_base = devm_ioremap_resource(&pdev->dev, rc);
 	if (IS_ERR(host->io_base))
@@ -748,31 +777,6 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 		}
 	}
 
-	/*
-	 * Scan to find existance of the device and
-	 * Get the type of NAND device SMALL block or LARGE block
-	 */
-	res = nand_scan_ident(mtd, 1, NULL);
-	if (res)
-		goto release_dma_chan;
-
-	host->dma_buf = devm_kzalloc(&pdev->dev, mtd->writesize, GFP_KERNEL);
-	if (!host->dma_buf) {
-		res = -ENOMEM;
-		goto release_dma_chan;
-	}
-
-	host->dummy_buf = devm_kzalloc(&pdev->dev, mtd->writesize, GFP_KERNEL);
-	if (!host->dummy_buf) {
-		res = -ENOMEM;
-		goto release_dma_chan;
-	}
-
-	nand_chip->ecc.mode = NAND_ECC_HW;
-	nand_chip->ecc.size = 512;
-	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
-	host->mlcsubpages = mtd->writesize / 512;
-
 	/* initially clear interrupt status */
 	readb(MLC_IRQ_SR(host->io_base));
 
@@ -794,10 +798,11 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	}
 
 	/*
-	 * Fills out all the uninitialized function pointers with the defaults
-	 * And scans for a bad block table if appropriate.
+	 * Scan to find existence of the device and get the type of NAND device:
+	 * SMALL block or LARGE block.
 	 */
-	res = nand_scan_tail(mtd);
+	nand_chip->dummy_controller.ops = &lpc32xx_nand_controller_ops;
+	res = nand_scan(mtd, 1);
 	if (res)
 		goto free_irq;
 
diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index 42820aa1abab..a4e8b7e75135 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -779,6 +779,46 @@ static struct lpc32xx_nand_cfg_slc *lpc32xx_parse_dt(struct device *dev)
 	return ncfg;
 }
 
+static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
+
+	/* OOB and ECC CPU and DMA work areas */
+	host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE);
+
+	/*
+	 * Small page FLASH has a unique OOB layout, but large and huge
+	 * page FLASH use the standard layout. Small page FLASH uses a
+	 * custom BBT marker layout.
+	 */
+	if (mtd->writesize <= 512)
+		mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
+
+	/* These sizes remain the same regardless of page size */
+	chip->ecc.size = 256;
+	chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
+	chip->ecc.prepad = 0;
+	chip->ecc.postpad = 0;
+
+	/*
+	 * Use a custom BBT marker setup for small page FLASH that
+	 * won't interfere with the ECC layout. Large and huge page
+	 * FLASH use the standard layout.
+	 */
+	if ((chip->bbt_options & NAND_BBT_USE_FLASH) &&
+	    mtd->writesize <= 512) {
+		chip->bbt_td = &bbt_smallpage_main_descr;
+		chip->bbt_md = &bbt_smallpage_mirror_descr;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops lpc32xx_nand_controller_ops = {
+	.attach_chip = lpc32xx_nand_attach_chip,
+};
+
 /*
  * Probe for NAND controller
  */
@@ -884,41 +924,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	}
 
 	/* Find NAND device */
-	res = nand_scan_ident(mtd, 1, NULL);
-	if (res)
-		goto release_dma;
-
-	/* OOB and ECC CPU and DMA work areas */
-	host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE);
-
-	/*
-	 * Small page FLASH has a unique OOB layout, but large and huge
-	 * page FLASH use the standard layout. Small page FLASH uses a
-	 * custom BBT marker layout.
-	 */
-	if (mtd->writesize <= 512)
-		mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
-
-	/* These sizes remain the same regardless of page size */
-	chip->ecc.size = 256;
-	chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
-	chip->ecc.prepad = chip->ecc.postpad = 0;
-
-	/*
-	 * Use a custom BBT marker setup for small page FLASH that
-	 * won't interfere with the ECC layout. Large and huge page
-	 * FLASH use the standard layout.
-	 */
-	if ((chip->bbt_options & NAND_BBT_USE_FLASH) &&
-	    mtd->writesize <= 512) {
-		chip->bbt_td = &bbt_smallpage_main_descr;
-		chip->bbt_md = &bbt_smallpage_mirror_descr;
-	}
-
-	/*
-	 * Fills out all the uninitialized function pointers with the defaults
-	 */
-	res = nand_scan_tail(mtd);
+	chip->dummy_controller.ops = &lpc32xx_nand_controller_ops;
+	res = nand_scan(mtd, 1);
 	if (res)
 		goto release_dma;
 
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index ebb1d141b900..218e09431d3d 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -318,7 +318,7 @@ struct marvell_nfc_caps {
  * @dma_buf:		32-bit aligned buffer for DMA transfers (NFCv1 only)
  */
 struct marvell_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct device *dev;
 	void __iomem *regs;
 	struct clk *core_clk;
@@ -335,7 +335,7 @@ struct marvell_nfc {
 	u8 *dma_buf;
 };
 
-static inline struct marvell_nfc *to_marvell_nfc(struct nand_hw_control *ctrl)
+static inline struct marvell_nfc *to_marvell_nfc(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct marvell_nfc, controller);
 }
@@ -650,11 +650,6 @@ static void marvell_nfc_select_chip(struct mtd_info *mtd, int die_nr)
 		return;
 	}
 
-	/*
-	 * Do not change the timing registers when using the DT property
-	 * marvell,nand-keep-config; in that case ->ndtr0 and ->ndtr1 from the
-	 * marvell_nand structure are supposedly empty.
-	 */
 	writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
 	writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
 
@@ -2157,6 +2152,7 @@ static int marvell_nand_ecc_init(struct mtd_info *mtd,
 		break;
 	case NAND_ECC_NONE:
 	case NAND_ECC_SOFT:
+	case NAND_ECC_ON_DIE:
 		if (!nfc->caps->is_nfcv2 && mtd->writesize != SZ_512 &&
 		    mtd->writesize != SZ_2K) {
 			dev_err(nfc->dev, "NFCv1 cannot write %d bytes pages\n",
@@ -2294,6 +2290,111 @@ static int marvell_nfc_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	return 0;
 }
 
+static int marvell_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip);
+	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
+	struct pxa3xx_nand_platform_data *pdata = dev_get_platdata(nfc->dev);
+	int ret;
+
+	if (pdata && pdata->flash_bbt)
+		chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		/*
+		 * We'll use a bad block table stored in-flash and don't
+		 * allow writing the bad block marker to the flash.
+		 */
+		chip->bbt_options |= NAND_BBT_NO_OOB_BBM;
+		chip->bbt_td = &bbt_main_descr;
+		chip->bbt_md = &bbt_mirror_descr;
+	}
+
+	/* Save the chip-specific fields of NDCR */
+	marvell_nand->ndcr = NDCR_PAGE_SZ(mtd->writesize);
+	if (chip->options & NAND_BUSWIDTH_16)
+		marvell_nand->ndcr |= NDCR_DWIDTH_M | NDCR_DWIDTH_C;
+
+	/*
+	 * On small page NANDs, only one cycle is needed to pass the
+	 * column address.
+	 */
+	if (mtd->writesize <= 512) {
+		marvell_nand->addr_cyc = 1;
+	} else {
+		marvell_nand->addr_cyc = 2;
+		marvell_nand->ndcr |= NDCR_RA_START;
+	}
+
+	/*
+	 * Now add the number of cycles needed to pass the row
+	 * address.
+	 *
+	 * Addressing a chip using CS 2 or 3 should also need the third row
+	 * cycle but due to inconsistance in the documentation and lack of
+	 * hardware to test this situation, this case is not supported.
+	 */
+	if (chip->options & NAND_ROW_ADDR_3)
+		marvell_nand->addr_cyc += 3;
+	else
+		marvell_nand->addr_cyc += 2;
+
+	if (pdata) {
+		chip->ecc.size = pdata->ecc_step_size;
+		chip->ecc.strength = pdata->ecc_strength;
+	}
+
+	ret = marvell_nand_ecc_init(mtd, &chip->ecc);
+	if (ret) {
+		dev_err(nfc->dev, "ECC init failed: %d\n", ret);
+		return ret;
+	}
+
+	if (chip->ecc.mode == NAND_ECC_HW) {
+		/*
+		 * Subpage write not available with hardware ECC, prohibit also
+		 * subpage read as in userspace subpage access would still be
+		 * allowed and subpage write, if used, would lead to numerous
+		 * uncorrectable ECC errors.
+		 */
+		chip->options |= NAND_NO_SUBPAGE_WRITE;
+	}
+
+	if (pdata || nfc->caps->legacy_of_bindings) {
+		/*
+		 * We keep the MTD name unchanged to avoid breaking platforms
+		 * where the MTD cmdline parser is used and the bootloader
+		 * has not been updated to use the new naming scheme.
+		 */
+		mtd->name = "pxa3xx_nand-0";
+	} else if (!mtd->name) {
+		/*
+		 * If the new bindings are used and the bootloader has not been
+		 * updated to pass a new mtdparts parameter on the cmdline, you
+		 * should define the following property in your NAND node, ie:
+		 *
+		 *	label = "main-storage";
+		 *
+		 * This way, mtd->name will be set by the core when
+		 * nand_set_flash_node() is called.
+		 */
+		mtd->name = devm_kasprintf(nfc->dev, GFP_KERNEL,
+					   "%s:nand.%d", dev_name(nfc->dev),
+					   marvell_nand->sels[0].cs);
+		if (!mtd->name) {
+			dev_err(nfc->dev, "Failed to allocate mtd->name\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops marvell_nand_controller_ops = {
+	.attach_chip = marvell_nand_attach_chip,
+};
+
 static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 				  struct device_node *np)
 {
@@ -2436,105 +2537,10 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 	marvell_nand->ndtr1 = readl_relaxed(nfc->regs + NDTR1);
 
 	chip->options |= NAND_BUSWIDTH_AUTO;
-	ret = nand_scan_ident(mtd, marvell_nand->nsels, NULL);
-	if (ret) {
-		dev_err(dev, "could not identify the nand chip\n");
-		return ret;
-	}
-
-	if (pdata && pdata->flash_bbt)
-		chip->bbt_options |= NAND_BBT_USE_FLASH;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
-		/*
-		 * We'll use a bad block table stored in-flash and don't
-		 * allow writing the bad block marker to the flash.
-		 */
-		chip->bbt_options |= NAND_BBT_NO_OOB_BBM;
-		chip->bbt_td = &bbt_main_descr;
-		chip->bbt_md = &bbt_mirror_descr;
-	}
-
-	/* Save the chip-specific fields of NDCR */
-	marvell_nand->ndcr = NDCR_PAGE_SZ(mtd->writesize);
-	if (chip->options & NAND_BUSWIDTH_16)
-		marvell_nand->ndcr |= NDCR_DWIDTH_M | NDCR_DWIDTH_C;
-
-	/*
-	 * On small page NANDs, only one cycle is needed to pass the
-	 * column address.
-	 */
-	if (mtd->writesize <= 512) {
-		marvell_nand->addr_cyc = 1;
-	} else {
-		marvell_nand->addr_cyc = 2;
-		marvell_nand->ndcr |= NDCR_RA_START;
-	}
-
-	/*
-	 * Now add the number of cycles needed to pass the row
-	 * address.
-	 *
-	 * Addressing a chip using CS 2 or 3 should also need the third row
-	 * cycle but due to inconsistance in the documentation and lack of
-	 * hardware to test this situation, this case is not supported.
-	 */
-	if (chip->options & NAND_ROW_ADDR_3)
-		marvell_nand->addr_cyc += 3;
-	else
-		marvell_nand->addr_cyc += 2;
-
-	if (pdata) {
-		chip->ecc.size = pdata->ecc_step_size;
-		chip->ecc.strength = pdata->ecc_strength;
-	}
 
-	ret = marvell_nand_ecc_init(mtd, &chip->ecc);
+	ret = nand_scan(mtd, marvell_nand->nsels);
 	if (ret) {
-		dev_err(dev, "ECC init failed: %d\n", ret);
-		return ret;
-	}
-
-	if (chip->ecc.mode == NAND_ECC_HW) {
-		/*
-		 * Subpage write not available with hardware ECC, prohibit also
-		 * subpage read as in userspace subpage access would still be
-		 * allowed and subpage write, if used, would lead to numerous
-		 * uncorrectable ECC errors.
-		 */
-		chip->options |= NAND_NO_SUBPAGE_WRITE;
-	}
-
-	if (pdata || nfc->caps->legacy_of_bindings) {
-		/*
-		 * We keep the MTD name unchanged to avoid breaking platforms
-		 * where the MTD cmdline parser is used and the bootloader
-		 * has not been updated to use the new naming scheme.
-		 */
-		mtd->name = "pxa3xx_nand-0";
-	} else if (!mtd->name) {
-		/*
-		 * If the new bindings are used and the bootloader has not been
-		 * updated to pass a new mtdparts parameter on the cmdline, you
-		 * should define the following property in your NAND node, ie:
-		 *
-		 *	label = "main-storage";
-		 *
-		 * This way, mtd->name will be set by the core when
-		 * nand_set_flash_node() is called.
-		 */
-		mtd->name = devm_kasprintf(nfc->dev, GFP_KERNEL,
-					   "%s:nand.%d", dev_name(nfc->dev),
-					   marvell_nand->sels[0].cs);
-		if (!mtd->name) {
-			dev_err(nfc->dev, "Failed to allocate mtd->name\n");
-			return -ENOMEM;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
+		dev_err(dev, "could not scan the nand chip\n");
 		return ret;
 	}
 
@@ -2677,6 +2683,21 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 	return 0;
 }
 
+static void marvell_nfc_reset(struct marvell_nfc *nfc)
+{
+	/*
+	 * ECC operations and interruptions are only enabled when specifically
+	 * needed. ECC shall not be activated in the early stages (fails probe).
+	 * Arbiter flag, even if marked as "reserved", must be set (empirical).
+	 * SPARE_EN bit must always be set or ECC bytes will not be at the same
+	 * offset in the read page and this will fail the protection.
+	 */
+	writel_relaxed(NDCR_ALL_INT | NDCR_ND_ARB_EN | NDCR_SPARE_EN |
+		       NDCR_RD_ID_CNT(NFCV1_READID_LEN), nfc->regs + NDCR);
+	writel_relaxed(0xFFFFFFFF, nfc->regs + NDSR);
+	writel_relaxed(0, nfc->regs + NDECCCTRL);
+}
+
 static int marvell_nfc_init(struct marvell_nfc *nfc)
 {
 	struct device_node *np = nfc->dev->of_node;
@@ -2715,17 +2736,7 @@ static int marvell_nfc_init(struct marvell_nfc *nfc)
 	if (!nfc->caps->is_nfcv2)
 		marvell_nfc_init_dma(nfc);
 
-	/*
-	 * ECC operations and interruptions are only enabled when specifically
-	 * needed. ECC shall not be activated in the early stages (fails probe).
-	 * Arbiter flag, even if marked as "reserved", must be set (empirical).
-	 * SPARE_EN bit must always be set or ECC bytes will not be at the same
-	 * offset in the read page and this will fail the protection.
-	 */
-	writel_relaxed(NDCR_ALL_INT | NDCR_ND_ARB_EN | NDCR_SPARE_EN |
-		       NDCR_RD_ID_CNT(NFCV1_READID_LEN), nfc->regs + NDCR);
-	writel_relaxed(0xFFFFFFFF, nfc->regs + NDSR);
-	writel_relaxed(0, nfc->regs + NDECCCTRL);
+	marvell_nfc_reset(nfc);
 
 	return 0;
 }
@@ -2744,7 +2755,8 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	nfc->dev = dev;
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
+	nfc->controller.ops = &marvell_nand_controller_ops;
 	INIT_LIST_HEAD(&nfc->chips);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -2772,17 +2784,19 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return ret;
 
 	nfc->reg_clk = devm_clk_get(&pdev->dev, "reg");
-	if (PTR_ERR(nfc->reg_clk) != -ENOENT) {
-		if (!IS_ERR(nfc->reg_clk)) {
-			ret = clk_prepare_enable(nfc->reg_clk);
-			if (ret)
-				goto unprepare_core_clk;
-		} else {
+	if (IS_ERR(nfc->reg_clk)) {
+		if (PTR_ERR(nfc->reg_clk) != -ENOENT) {
 			ret = PTR_ERR(nfc->reg_clk);
 			goto unprepare_core_clk;
 		}
+
+		nfc->reg_clk = NULL;
 	}
 
+	ret = clk_prepare_enable(nfc->reg_clk);
+	if (ret)
+		goto unprepare_core_clk;
+
 	marvell_nfc_disable_int(nfc, NDCR_ALL_INT);
 	marvell_nfc_clear_int(nfc, NDCR_ALL_INT);
 	ret = devm_request_irq(dev, irq, marvell_nfc_isr,
@@ -2840,6 +2854,49 @@ static int marvell_nfc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused marvell_nfc_suspend(struct device *dev)
+{
+	struct marvell_nfc *nfc = dev_get_drvdata(dev);
+	struct marvell_nand_chip *chip;
+
+	list_for_each_entry(chip, &nfc->chips, node)
+		marvell_nfc_wait_ndrun(&chip->chip);
+
+	clk_disable_unprepare(nfc->reg_clk);
+	clk_disable_unprepare(nfc->core_clk);
+
+	return 0;
+}
+
+static int __maybe_unused marvell_nfc_resume(struct device *dev)
+{
+	struct marvell_nfc *nfc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(nfc->core_clk);
+	if (ret < 0)
+		return ret;
+
+	ret = clk_prepare_enable(nfc->reg_clk);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Reset nfc->selected_chip so the next command will cause the timing
+	 * registers to be restored in marvell_nfc_select_chip().
+	 */
+	nfc->selected_chip = NULL;
+
+	/* Reset registers that have lost their contents */
+	marvell_nfc_reset(nfc);
+
+	return 0;
+}
+
+static const struct dev_pm_ops marvell_nfc_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(marvell_nfc_suspend, marvell_nfc_resume)
+};
+
 static const struct marvell_nfc_caps marvell_armada_8k_nfc_caps = {
 	.max_cs_nb = 4,
 	.max_rb_nb = 2,
@@ -2924,6 +2981,7 @@ static struct platform_driver marvell_nfc_driver = {
 	.driver	= {
 		.name		= "marvell-nfc",
 		.of_match_table = marvell_nfc_of_ids,
+		.pm		= &marvell_nfc_pm_ops,
 	},
 	.id_table = marvell_nfc_platform_ids,
 	.probe = marvell_nfc_probe,
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index 75c845adb050..57b5ed1699e3 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -145,7 +145,7 @@ struct mtk_nfc_clk {
 };
 
 struct mtk_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct mtk_ecc_config ecc_cfg;
 	struct mtk_nfc_clk clk;
 	struct mtk_ecc *ecc;
@@ -1250,13 +1250,54 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
 	return 0;
 }
 
+static int mtk_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct device *dev = mtd->dev.parent;
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	int len;
+	int ret;
+
+	if (chip->options & NAND_BUSWIDTH_16) {
+		dev_err(dev, "16bits buswidth not supported");
+		return -EINVAL;
+	}
+
+	/* store bbt magic in page, cause OOB is not protected */
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	ret = mtk_nfc_ecc_init(dev, mtd);
+	if (ret)
+		return ret;
+
+	ret = mtk_nfc_set_spare_per_sector(&mtk_nand->spare_per_sector, mtd);
+	if (ret)
+		return ret;
+
+	mtk_nfc_set_fdm(&mtk_nand->fdm, mtd);
+	mtk_nfc_set_bad_mark_ctl(&mtk_nand->bad_mark, mtd);
+
+	len = mtd->writesize + mtd->oobsize;
+	nfc->buffer = devm_kzalloc(dev, len, GFP_KERNEL);
+	if (!nfc->buffer)
+		return  -ENOMEM;
+
+	return 0;
+}
+
+static const struct nand_controller_ops mtk_nfc_controller_ops = {
+	.attach_chip = mtk_nfc_attach_chip,
+};
+
 static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 				  struct device_node *np)
 {
 	struct mtk_nfc_nand_chip *chip;
 	struct nand_chip *nand;
 	struct mtd_info *mtd;
-	int nsels, len;
+	int nsels;
 	u32 tmp;
 	int ret;
 	int i;
@@ -1324,40 +1365,11 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 
 	mtk_nfc_hw_init(nfc);
 
-	ret = nand_scan_ident(mtd, nsels, NULL);
-	if (ret)
-		return ret;
-
-	/* store bbt magic in page, cause OOB is not protected */
-	if (nand->bbt_options & NAND_BBT_USE_FLASH)
-		nand->bbt_options |= NAND_BBT_NO_OOB;
-
-	ret = mtk_nfc_ecc_init(dev, mtd);
-	if (ret)
-		return -EINVAL;
-
-	if (nand->options & NAND_BUSWIDTH_16) {
-		dev_err(dev, "16bits buswidth not supported");
-		return -EINVAL;
-	}
-
-	ret = mtk_nfc_set_spare_per_sector(&chip->spare_per_sector, mtd);
-	if (ret)
-		return ret;
-
-	mtk_nfc_set_fdm(&chip->fdm, mtd);
-	mtk_nfc_set_bad_mark_ctl(&chip->bad_mark, mtd);
-
-	len = mtd->writesize + mtd->oobsize;
-	nfc->buffer = devm_kzalloc(dev, len, GFP_KERNEL);
-	if (!nfc->buffer)
-		return  -ENOMEM;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, nsels);
 	if (ret)
 		return ret;
 
-	ret = mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "mtd parse partition error\n");
 		nand_release(mtd);
@@ -1443,6 +1455,7 @@ static int mtk_nfc_probe(struct platform_device *pdev)
 	spin_lock_init(&nfc->controller.lock);
 	init_waitqueue_head(&nfc->controller.wq);
 	INIT_LIST_HEAD(&nfc->chips);
+	nfc->controller.ops = &mtk_nfc_controller_ops;
 
 	/* probe defer if not ready */
 	nfc->ecc = of_mtk_ecc_get(np);
diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 26cef218bb43..4c9214dea424 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
  * Copyright 2008 Sascha Hauer, kernel@pengutronix.de
- *
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
  */
 
 #include <linux/delay.h>
@@ -34,8 +21,6 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-
-#include <asm/mach/flash.h>
 #include <linux/platform_data/mtd-mxc_nand.h>
 
 #define DRIVER_NAME "mxc_nand"
@@ -1686,7 +1671,7 @@ static const struct of_device_id mxcnd_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, mxcnd_dt_ids);
 
-static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
+static int mxcnd_probe_dt(struct mxc_nand_host *host)
 {
 	struct device_node *np = host->dev->of_node;
 	const struct of_device_id *of_id =
@@ -1700,12 +1685,80 @@ static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
 	return 0;
 }
 #else
-static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
+static int mxcnd_probe_dt(struct mxc_nand_host *host)
 {
 	return 1;
 }
 #endif
 
+static int mxcnd_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct mxc_nand_host *host = nand_get_controller_data(chip);
+	struct device *dev = mtd->dev.parent;
+
+	switch (chip->ecc.mode) {
+	case NAND_ECC_HW:
+		chip->ecc.read_page = mxc_nand_read_page;
+		chip->ecc.read_page_raw = mxc_nand_read_page_raw;
+		chip->ecc.read_oob = mxc_nand_read_oob;
+		chip->ecc.write_page = mxc_nand_write_page_ecc;
+		chip->ecc.write_page_raw = mxc_nand_write_page_raw;
+		chip->ecc.write_oob = mxc_nand_write_oob;
+		break;
+
+	case NAND_ECC_SOFT:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		chip->bbt_td = &bbt_main_descr;
+		chip->bbt_md = &bbt_mirror_descr;
+	}
+
+	/* Allocate the right size buffer now */
+	devm_kfree(dev, (void *)host->data_buf);
+	host->data_buf = devm_kzalloc(dev, mtd->writesize + mtd->oobsize,
+				      GFP_KERNEL);
+	if (!host->data_buf)
+		return -ENOMEM;
+
+	/* Call preset again, with correct writesize chip time */
+	host->devtype_data->preset(mtd);
+
+	if (!chip->ecc.bytes) {
+		if (host->eccsize == 8)
+			chip->ecc.bytes = 18;
+		else if (host->eccsize == 4)
+			chip->ecc.bytes = 9;
+	}
+
+	/*
+	 * Experimentation shows that i.MX NFC can only handle up to 218 oob
+	 * bytes. Limit used_oobsize to 218 so as to not confuse copy_spare()
+	 * into copying invalid data to/from the spare IO buffer, as this
+	 * might cause ECC data corruption when doing sub-page write to a
+	 * partially written page.
+	 */
+	host->used_oobsize = min(mtd->oobsize, 218U);
+
+	if (chip->ecc.mode == NAND_ECC_HW) {
+		if (is_imx21_nfc(host) || is_imx27_nfc(host))
+			chip->ecc.strength = 1;
+		else
+			chip->ecc.strength = (host->eccsize == 4) ? 4 : 8;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops mxcnd_controller_ops = {
+	.attach_chip = mxcnd_attach_chip,
+};
+
 static int mxcnd_probe(struct platform_device *pdev)
 {
 	struct nand_chip *this;
@@ -1845,71 +1898,9 @@ static int mxcnd_probe(struct platform_device *pdev)
 		host->devtype_data->irq_control(host, 1);
 	}
 
-	/* first scan to find the device and get the page size */
-	err = nand_scan_ident(mtd, is_imx25_nfc(host) ? 4 : 1, NULL);
-	if (err)
-		goto escan;
-
-	switch (this->ecc.mode) {
-	case NAND_ECC_HW:
-		this->ecc.read_page = mxc_nand_read_page;
-		this->ecc.read_page_raw = mxc_nand_read_page_raw;
-		this->ecc.read_oob = mxc_nand_read_oob;
-		this->ecc.write_page = mxc_nand_write_page_ecc;
-		this->ecc.write_page_raw = mxc_nand_write_page_raw;
-		this->ecc.write_oob = mxc_nand_write_oob;
-		break;
-
-	case NAND_ECC_SOFT:
-		break;
-
-	default:
-		err = -EINVAL;
-		goto escan;
-	}
-
-	if (this->bbt_options & NAND_BBT_USE_FLASH) {
-		this->bbt_td = &bbt_main_descr;
-		this->bbt_md = &bbt_mirror_descr;
-	}
-
-	/* allocate the right size buffer now */
-	devm_kfree(&pdev->dev, (void *)host->data_buf);
-	host->data_buf = devm_kzalloc(&pdev->dev, mtd->writesize + mtd->oobsize,
-					GFP_KERNEL);
-	if (!host->data_buf) {
-		err = -ENOMEM;
-		goto escan;
-	}
-
-	/* Call preset again, with correct writesize this time */
-	host->devtype_data->preset(mtd);
-
-	if (!this->ecc.bytes) {
-		if (host->eccsize == 8)
-			this->ecc.bytes = 18;
-		else if (host->eccsize == 4)
-			this->ecc.bytes = 9;
-	}
-
-	/*
-	 * Experimentation shows that i.MX NFC can only handle up to 218 oob
-	 * bytes. Limit used_oobsize to 218 so as to not confuse copy_spare()
-	 * into copying invalid data to/from the spare IO buffer, as this
-	 * might cause ECC data corruption when doing sub-page write to a
-	 * partially written page.
-	 */
-	host->used_oobsize = min(mtd->oobsize, 218U);
-
-	if (this->ecc.mode == NAND_ECC_HW) {
-		if (is_imx21_nfc(host) || is_imx27_nfc(host))
-			this->ecc.strength = 1;
-		else
-			this->ecc.strength = (host->eccsize == 4) ? 4 : 8;
-	}
-
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	/* Scan the NAND device */
+	this->dummy_controller.ops = &mxcnd_controller_ops;
+	err = nand_scan(mtd, is_imx25_nfc(host) ? 4 : 1);
 	if (err)
 		goto escan;
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index b01d15ec4c56..d527e448ce19 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -2668,8 +2668,8 @@ static bool nand_subop_instr_is_valid(const struct nand_subop *subop,
 	return subop && instr_idx < subop->ninstrs;
 }
 
-static int nand_subop_get_start_off(const struct nand_subop *subop,
-				    unsigned int instr_idx)
+static unsigned int nand_subop_get_start_off(const struct nand_subop *subop,
+					     unsigned int instr_idx)
 {
 	if (instr_idx)
 		return 0;
@@ -2688,12 +2688,12 @@ static int nand_subop_get_start_off(const struct nand_subop *subop,
  *
  * Given an address instruction, returns the offset of the first cycle to issue.
  */
-int nand_subop_get_addr_start_off(const struct nand_subop *subop,
-				  unsigned int instr_idx)
+unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop,
+					   unsigned int instr_idx)
 {
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR))
+		return 0;
 
 	return nand_subop_get_start_off(subop, instr_idx);
 }
@@ -2710,14 +2710,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_addr_start_off);
  *
  * Given an address instruction, returns the number of address cycle to issue.
  */
-int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
-				unsigned int instr_idx)
+unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
+					 unsigned int instr_idx)
 {
 	int start_off, end_off;
 
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR))
+		return 0;
 
 	start_off = nand_subop_get_addr_start_off(subop, instr_idx);
 
@@ -2742,12 +2742,12 @@ EXPORT_SYMBOL_GPL(nand_subop_get_num_addr_cyc);
  *
  * Given a data instruction, returns the offset to start from.
  */
-int nand_subop_get_data_start_off(const struct nand_subop *subop,
-				  unsigned int instr_idx)
+unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop,
+					   unsigned int instr_idx)
 {
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    !nand_instr_is_data(&subop->instrs[instr_idx]))
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    !nand_instr_is_data(&subop->instrs[instr_idx])))
+		return 0;
 
 	return nand_subop_get_start_off(subop, instr_idx);
 }
@@ -2764,14 +2764,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_data_start_off);
  *
  * Returns the length of the chunk of data to send/receive.
  */
-int nand_subop_get_data_len(const struct nand_subop *subop,
-			    unsigned int instr_idx)
+unsigned int nand_subop_get_data_len(const struct nand_subop *subop,
+				     unsigned int instr_idx)
 {
 	int start_off = 0, end_off;
 
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    !nand_instr_is_data(&subop->instrs[instr_idx]))
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    !nand_instr_is_data(&subop->instrs[instr_idx])))
+		return 0;
 
 	start_off = nand_subop_get_data_start_off(subop, instr_idx);
 
@@ -2967,6 +2967,23 @@ int nand_check_erased_ecc_chunk(void *data, int datalen,
 EXPORT_SYMBOL(nand_check_erased_ecc_chunk);
 
 /**
+ * nand_read_page_raw_notsupp - dummy read raw page function
+ * @mtd: mtd info structure
+ * @chip: nand chip info structure
+ * @buf: buffer to store read data
+ * @oob_required: caller requires OOB data read to chip->oob_poi
+ * @page: page number to read
+ *
+ * Returns -ENOTSUPP unconditionally.
+ */
+int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+			       u8 *buf, int oob_required, int page)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_read_page_raw_notsupp);
+
+/**
  * nand_read_page_raw - [INTERN] read raw page data without ecc
  * @mtd: mtd info structure
  * @chip: nand chip info structure
@@ -3960,6 +3977,22 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from,
 	return ret;
 }
 
+/**
+ * nand_write_page_raw_notsupp - dummy raw page write function
+ * @mtd: mtd info structure
+ * @chip: nand chip info structure
+ * @buf: data buffer
+ * @oob_required: must write chip->oob_poi to OOB
+ * @page: page number to write
+ *
+ * Returns -ENOTSUPP unconditionally.
+ */
+int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+				const u8 *buf, int oob_required, int page)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_write_page_raw_notsupp);
 
 /**
  * nand_write_page_raw - [INTERN] raw page write function
@@ -4965,12 +4998,10 @@ static void nand_set_defaults(struct nand_chip *chip)
 		chip->write_byte = busw ? nand_write_byte16 : nand_write_byte;
 	if (!chip->read_buf || chip->read_buf == nand_read_buf)
 		chip->read_buf = busw ? nand_read_buf16 : nand_read_buf;
-	if (!chip->scan_bbt)
-		chip->scan_bbt = nand_default_bbt;
 
 	if (!chip->controller) {
-		chip->controller = &chip->hwcontrol;
-		nand_hw_control_init(chip->controller);
+		chip->controller = &chip->dummy_controller;
+		nand_controller_init(chip->controller);
 	}
 
 	if (!chip->buf_align)
@@ -5120,6 +5151,8 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_onfi_params *p;
+	struct onfi_params *onfi;
+	int onfi_version = 0;
 	char id[4];
 	int i, ret, val;
 
@@ -5168,30 +5201,35 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 		}
 	}
 
+	if (chip->manufacturer.desc && chip->manufacturer.desc->ops &&
+	    chip->manufacturer.desc->ops->fixup_onfi_param_page)
+		chip->manufacturer.desc->ops->fixup_onfi_param_page(chip, p);
+
 	/* Check version */
 	val = le16_to_cpu(p->revision);
-	if (val & (1 << 5))
-		chip->parameters.onfi.version = 23;
-	else if (val & (1 << 4))
-		chip->parameters.onfi.version = 22;
-	else if (val & (1 << 3))
-		chip->parameters.onfi.version = 21;
-	else if (val & (1 << 2))
-		chip->parameters.onfi.version = 20;
-	else if (val & (1 << 1))
-		chip->parameters.onfi.version = 10;
-
-	if (!chip->parameters.onfi.version) {
+	if (val & ONFI_VERSION_2_3)
+		onfi_version = 23;
+	else if (val & ONFI_VERSION_2_2)
+		onfi_version = 22;
+	else if (val & ONFI_VERSION_2_1)
+		onfi_version = 21;
+	else if (val & ONFI_VERSION_2_0)
+		onfi_version = 20;
+	else if (val & ONFI_VERSION_1_0)
+		onfi_version = 10;
+
+	if (!onfi_version) {
 		pr_info("unsupported ONFI version: %d\n", val);
 		goto free_onfi_param_page;
-	} else {
-		ret = 1;
 	}
 
 	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
 	sanitize_string(p->model, sizeof(p->model));
-	strncpy(chip->parameters.model, p->model,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(p->model, GFP_KERNEL);
+	if (!chip->parameters.model) {
+		ret = -ENOMEM;
+		goto free_onfi_param_page;
+	}
 
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
 
@@ -5219,7 +5257,7 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 	if (p->ecc_bits != 0xff) {
 		chip->ecc_strength_ds = p->ecc_bits;
 		chip->ecc_step_ds = 512;
-	} else if (chip->parameters.onfi.version >= 21 &&
+	} else if (onfi_version >= 21 &&
 		(le16_to_cpu(p->features) & ONFI_FEATURE_EXT_PARAM_PAGE)) {
 
 		/*
@@ -5246,19 +5284,33 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 		bitmap_set(chip->parameters.set_feature_list,
 			   ONFI_FEATURE_ADDR_TIMING_MODE, 1);
 	}
-	chip->parameters.onfi.tPROG = le16_to_cpu(p->t_prog);
-	chip->parameters.onfi.tBERS = le16_to_cpu(p->t_bers);
-	chip->parameters.onfi.tR = le16_to_cpu(p->t_r);
-	chip->parameters.onfi.tCCS = le16_to_cpu(p->t_ccs);
-	chip->parameters.onfi.async_timing_mode =
-		le16_to_cpu(p->async_timing_mode);
-	chip->parameters.onfi.vendor_revision =
-		le16_to_cpu(p->vendor_revision);
-	memcpy(chip->parameters.onfi.vendor, p->vendor,
-	       sizeof(p->vendor));
 
+	onfi = kzalloc(sizeof(*onfi), GFP_KERNEL);
+	if (!onfi) {
+		ret = -ENOMEM;
+		goto free_model;
+	}
+
+	onfi->version = onfi_version;
+	onfi->tPROG = le16_to_cpu(p->t_prog);
+	onfi->tBERS = le16_to_cpu(p->t_bers);
+	onfi->tR = le16_to_cpu(p->t_r);
+	onfi->tCCS = le16_to_cpu(p->t_ccs);
+	onfi->async_timing_mode = le16_to_cpu(p->async_timing_mode);
+	onfi->vendor_revision = le16_to_cpu(p->vendor_revision);
+	memcpy(onfi->vendor, p->vendor, sizeof(p->vendor));
+	chip->parameters.onfi = onfi;
+
+	/* Identification done, free the full ONFI parameter page and exit */
+	kfree(p);
+
+	return 1;
+
+free_model:
+	kfree(chip->parameters.model);
 free_onfi_param_page:
 	kfree(p);
+
 	return ret;
 }
 
@@ -5321,8 +5373,11 @@ static int nand_flash_detect_jedec(struct nand_chip *chip)
 
 	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
 	sanitize_string(p->model, sizeof(p->model));
-	strncpy(chip->parameters.model, p->model,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(p->model, GFP_KERNEL);
+	if (!chip->parameters.model) {
+		ret = -ENOMEM;
+		goto free_jedec_param_page;
+	}
 
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
 
@@ -5511,8 +5566,9 @@ static bool find_full_id_nand(struct nand_chip *chip,
 		chip->onfi_timing_mode_default =
 					type->onfi_timing_mode_default;
 
-		strncpy(chip->parameters.model, type->name,
-			sizeof(chip->parameters.model) - 1);
+		chip->parameters.model = kstrdup(type->name, GFP_KERNEL);
+		if (!chip->parameters.model)
+			return false;
 
 		return true;
 	}
@@ -5651,7 +5707,6 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 		}
 	}
 
-	chip->parameters.onfi.version = 0;
 	if (!type->name || !type->pagesize) {
 		/* Check if the chip is ONFI compliant */
 		ret = nand_flash_detect_onfi(chip);
@@ -5671,8 +5726,9 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 	if (!type->name)
 		return -ENODEV;
 
-	strncpy(chip->parameters.model, type->name,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(type->name, GFP_KERNEL);
+	if (!chip->parameters.model)
+		return -ENOMEM;
 
 	chip->chipsize = (uint64_t)type->chipsize << 20;
 
@@ -5702,7 +5758,9 @@ ident_done:
 			mtd->name);
 		pr_warn("bus width %d instead of %d bits\n", busw ? 16 : 8,
 			(chip->options & NAND_BUSWIDTH_16) ? 16 : 8);
-		return -EINVAL;
+		ret = -EINVAL;
+
+		goto free_detect_allocation;
 	}
 
 	nand_decode_bbm_options(chip);
@@ -5739,6 +5797,11 @@ ident_done:
 		(int)(chip->chipsize >> 20), nand_is_slc(chip) ? "SLC" : "MLC",
 		mtd->erasesize >> 10, mtd->writesize, mtd->oobsize);
 	return 0;
+
+free_detect_allocation:
+	kfree(chip->parameters.model);
+
+	return ret;
 }
 
 static const char * const nand_ecc_modes[] = {
@@ -5777,6 +5840,7 @@ static int of_get_nand_ecc_mode(struct device_node *np)
 static const char * const nand_ecc_algos[] = {
 	[NAND_ECC_HAMMING]	= "hamming",
 	[NAND_ECC_BCH]		= "bch",
+	[NAND_ECC_RS]		= "rs",
 };
 
 static int of_get_nand_ecc_algo(struct device_node *np)
@@ -5858,6 +5922,9 @@ static int nand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_bus_width(dn) == 16)
 		chip->options |= NAND_BUSWIDTH_16;
 
+	if (of_property_read_bool(dn, "nand-is-boot-medium"))
+		chip->options |= NAND_IS_BOOT_MEDIUM;
+
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
@@ -5885,7 +5952,7 @@ static int nand_dt_init(struct nand_chip *chip)
 }
 
 /**
- * nand_scan_ident - [NAND Interface] Scan for the NAND device
+ * nand_scan_ident - Scan for the NAND device
  * @mtd: MTD device structure
  * @maxchips: number of chips to scan for
  * @table: alternative NAND ID table
@@ -5893,9 +5960,13 @@ static int nand_dt_init(struct nand_chip *chip)
  * This is the first phase of the normal nand_scan() function. It reads the
  * flash ID and sets up MTD fields accordingly.
  *
+ * This helper used to be called directly from controller drivers that needed
+ * to tweak some ECC-related parameters before nand_scan_tail(). This separation
+ * prevented dynamic allocations during this phase which was unconvenient and
+ * as been banned for the benefit of the ->init_ecc()/cleanup_ecc() hooks.
  */
-int nand_scan_ident(struct mtd_info *mtd, int maxchips,
-		    struct nand_flash_dev *table)
+static int nand_scan_ident(struct mtd_info *mtd, int maxchips,
+			   struct nand_flash_dev *table)
 {
 	int i, nand_maf_id, nand_dev_id;
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -5969,7 +6040,12 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 
 	return 0;
 }
-EXPORT_SYMBOL(nand_scan_ident);
+
+static void nand_scan_ident_cleanup(struct nand_chip *chip)
+{
+	kfree(chip->parameters.model);
+	kfree(chip->parameters.onfi);
+}
 
 static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
 {
@@ -6077,24 +6153,17 @@ static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
  * by the controller and the calculated ECC bytes fit within the chip's OOB.
  * On success, the calculated ECC bytes is set.
  */
-int nand_check_ecc_caps(struct nand_chip *chip,
-			const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_check_ecc_caps(struct nand_chip *chip,
+		    const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
 	int preset_step = chip->ecc.size;
 	int preset_strength = chip->ecc.strength;
-	int nsteps, ecc_bytes;
+	int ecc_bytes, nsteps = mtd->writesize / preset_step;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
-	if (!preset_step || !preset_strength)
-		return -ENODATA;
-
-	nsteps = mtd->writesize / preset_step;
-
 	for (i = 0; i < caps->nstepinfos; i++) {
 		stepinfo = &caps->stepinfos[i];
 
@@ -6127,7 +6196,6 @@ int nand_check_ecc_caps(struct nand_chip *chip,
 
 	return -ENOTSUPP;
 }
-EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
 
 /**
  * nand_match_ecc_req - meet the chip's requirement with least ECC bytes
@@ -6139,8 +6207,9 @@ EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
  * number of ECC bytes (i.e. with the largest number of OOB-free bytes).
  * On success, the chosen ECC settings are set.
  */
-int nand_match_ecc_req(struct nand_chip *chip,
-		       const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_match_ecc_req(struct nand_chip *chip,
+		   const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
@@ -6151,9 +6220,6 @@ int nand_match_ecc_req(struct nand_chip *chip,
 	int best_ecc_bytes_total = INT_MAX;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
 	/* No information provided by the NAND chip */
 	if (!req_step || !req_strength)
 		return -ENOTSUPP;
@@ -6212,7 +6278,6 @@ int nand_match_ecc_req(struct nand_chip *chip,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nand_match_ecc_req);
 
 /**
  * nand_maximize_ecc - choose the max ECC strength available
@@ -6223,8 +6288,9 @@ EXPORT_SYMBOL_GPL(nand_match_ecc_req);
  * Choose the max ECC strength that is supported on the controller, and can fit
  * within the chip's OOB.  On success, the chosen ECC settings are set.
  */
-int nand_maximize_ecc(struct nand_chip *chip,
-		      const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_maximize_ecc(struct nand_chip *chip,
+		  const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
@@ -6234,9 +6300,6 @@ int nand_maximize_ecc(struct nand_chip *chip,
 	int best_strength, best_ecc_bytes;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
 	for (i = 0; i < caps->nstepinfos; i++) {
 		stepinfo = &caps->stepinfos[i];
 		step_size = stepinfo->stepsize;
@@ -6285,7 +6348,44 @@ int nand_maximize_ecc(struct nand_chip *chip,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nand_maximize_ecc);
+
+/**
+ * nand_ecc_choose_conf - Set the ECC strength and ECC step size
+ * @chip: nand chip info structure
+ * @caps: ECC engine caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * Choose the ECC configuration according to following logic
+ *
+ * 1. If both ECC step size and ECC strength are already set (usually by DT)
+ *    then check if it is supported by this controller.
+ * 2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength.
+ * 3. Otherwise, try to match the ECC step size and ECC strength closest
+ *    to the chip's requirement. If available OOB size can't fit the chip
+ *    requirement then fallback to the maximum ECC step size and ECC strength.
+ *
+ * On success, the chosen ECC settings are set.
+ */
+int nand_ecc_choose_conf(struct nand_chip *chip,
+			 const struct nand_ecc_caps *caps, int oobavail)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	if (WARN_ON(oobavail < 0 || oobavail > mtd->oobsize))
+		return -EINVAL;
+
+	if (chip->ecc.size && chip->ecc.strength)
+		return nand_check_ecc_caps(chip, caps, oobavail);
+
+	if (chip->ecc.options & NAND_ECC_MAXIMIZE)
+		return nand_maximize_ecc(chip, caps, oobavail);
+
+	if (!nand_match_ecc_req(chip, caps, oobavail))
+		return 0;
+
+	return nand_maximize_ecc(chip, caps, oobavail);
+}
+EXPORT_SYMBOL_GPL(nand_ecc_choose_conf);
 
 /*
  * Check if the chip configuration meet the datasheet requirements.
@@ -6322,14 +6422,14 @@ static bool nand_ecc_strength_good(struct mtd_info *mtd)
 }
 
 /**
- * nand_scan_tail - [NAND Interface] Scan for the NAND device
+ * nand_scan_tail - Scan for the NAND device
  * @mtd: MTD device structure
  *
  * This is the second phase of the normal nand_scan() function. It fills out
  * all the uninitialized function pointers with the defaults and scans for a
  * bad block table if appropriate.
  */
-int nand_scan_tail(struct mtd_info *mtd)
+static int nand_scan_tail(struct mtd_info *mtd)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
@@ -6636,7 +6736,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 		return 0;
 
 	/* Build bad block table */
-	ret = chip->scan_bbt(mtd);
+	ret = nand_create_bbt(chip);
 	if (ret)
 		goto err_nand_manuf_cleanup;
 
@@ -6653,24 +6753,27 @@ err_free_buf:
 
 	return ret;
 }
-EXPORT_SYMBOL(nand_scan_tail);
 
-/*
- * is_module_text_address() isn't exported, and it's mostly a pointless
- * test if this is a module _anyway_ -- they'd have to try _really_ hard
- * to call us from in-kernel code if the core NAND support is modular.
- */
-#ifdef MODULE
-#define caller_is_module() (1)
-#else
-#define caller_is_module() \
-	is_module_text_address((unsigned long)__builtin_return_address(0))
-#endif
+static int nand_attach(struct nand_chip *chip)
+{
+	if (chip->controller->ops && chip->controller->ops->attach_chip)
+		return chip->controller->ops->attach_chip(chip);
+
+	return 0;
+}
+
+static void nand_detach(struct nand_chip *chip)
+{
+	if (chip->controller->ops && chip->controller->ops->detach_chip)
+		chip->controller->ops->detach_chip(chip);
+}
 
 /**
  * nand_scan_with_ids - [NAND Interface] Scan for the NAND device
  * @mtd: MTD device structure
- * @maxchips: number of chips to scan for
+ * @maxchips: number of chips to scan for. @nand_scan_ident() will not be run if
+ *	      this parameter is zero (useful for specific drivers that must
+ *	      handle this part of the process themselves, e.g docg4).
  * @ids: optional flash IDs table
  *
  * This fills out all the uninitialized function pointers with the defaults.
@@ -6680,11 +6783,30 @@ EXPORT_SYMBOL(nand_scan_tail);
 int nand_scan_with_ids(struct mtd_info *mtd, int maxchips,
 		       struct nand_flash_dev *ids)
 {
+	struct nand_chip *chip = mtd_to_nand(mtd);
 	int ret;
 
-	ret = nand_scan_ident(mtd, maxchips, ids);
-	if (!ret)
-		ret = nand_scan_tail(mtd);
+	if (maxchips) {
+		ret = nand_scan_ident(mtd, maxchips, ids);
+		if (ret)
+			return ret;
+	}
+
+	ret = nand_attach(chip);
+	if (ret)
+		goto cleanup_ident;
+
+	ret = nand_scan_tail(mtd);
+	if (ret)
+		goto detach_chip;
+
+	return 0;
+
+detach_chip:
+	nand_detach(chip);
+cleanup_ident:
+	nand_scan_ident_cleanup(chip);
+
 	return ret;
 }
 EXPORT_SYMBOL(nand_scan_with_ids);
@@ -6712,7 +6834,14 @@ void nand_cleanup(struct nand_chip *chip)
 
 	/* Free manufacturer priv data. */
 	nand_manufacturer_cleanup(chip);
+
+	/* Free controller specific allocations after chip identification */
+	nand_detach(chip);
+
+	/* Free identification phase allocations */
+	nand_scan_ident_cleanup(chip);
 }
+
 EXPORT_SYMBOL_GPL(nand_cleanup);
 
 /**
diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c
index d9f4ceff2568..39db352f8757 100644
--- a/drivers/mtd/nand/raw/nand_bbt.c
+++ b/drivers/mtd/nand/raw/nand_bbt.c
@@ -1349,15 +1349,14 @@ static int nand_create_badblock_pattern(struct nand_chip *this)
 }
 
 /**
- * nand_default_bbt - [NAND Interface] Select a default bad block table for the device
- * @mtd: MTD device structure
+ * nand_create_bbt - [NAND Interface] Select a default bad block table for the device
+ * @this: NAND chip object
  *
  * This function selects the default bad block table support for the device and
  * calls the nand_scan_bbt function.
  */
-int nand_default_bbt(struct mtd_info *mtd)
+int nand_create_bbt(struct nand_chip *this)
 {
-	struct nand_chip *this = mtd_to_nand(mtd);
 	int ret;
 
 	/* Is a flash based bad block table requested? */
@@ -1383,8 +1382,9 @@ int nand_default_bbt(struct mtd_info *mtd)
 			return ret;
 	}
 
-	return nand_scan_bbt(mtd, this->badblock_pattern);
+	return nand_scan_bbt(nand_to_mtd(this), this->badblock_pattern);
 }
+EXPORT_SYMBOL(nand_create_bbt);
 
 /**
  * nand_isreserved_bbt - [NAND Interface] Check if a block is reserved
diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c
index d542908a0ebb..4ffbb26e76d6 100644
--- a/drivers/mtd/nand/raw/nand_hynix.c
+++ b/drivers/mtd/nand/raw/nand_hynix.c
@@ -100,6 +100,16 @@ static int hynix_nand_reg_write_op(struct nand_chip *chip, u8 addr, u8 val)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	u16 column = ((u16)addr << 8) | addr;
 
+	if (chip->exec_op) {
+		struct nand_op_instr instrs[] = {
+			NAND_OP_ADDR(1, &addr, 0),
+			NAND_OP_8BIT_DATA_OUT(1, &val, 0),
+		};
+		struct nand_operation op = NAND_OPERATION(instrs);
+
+		return nand_exec_op(chip, &op);
+	}
+
 	chip->cmdfunc(mtd, NAND_CMD_NONE, column, -1);
 	chip->write_byte(mtd, val);
 
@@ -473,6 +483,19 @@ static void hynix_nand_extract_oobsize(struct nand_chip *chip,
 			WARN(1, "Invalid OOB size");
 			break;
 		}
+
+		/*
+		 * The datasheet of H27UCG8T2BTR mentions that the "Redundant
+		 * Area Size" is encoded "per 8KB" (page size). This chip uses
+		 * a page size of 16KiB. The datasheet mentions an OOB size of
+		 * 1.280 bytes, but the OOB size encoded in the ID bytes (using
+		 * the existing logic above) is 640 bytes.
+		 * Update the OOB size for this chip by taking the value
+		 * determined above and scaling it to the actual page size (so
+		 * the actual OOB size for this chip is: 640 * 16k / 8k).
+		 */
+		if (chip->id.data[1] == 0xde)
+			mtd->oobsize *= mtd->writesize / SZ_8K;
 	}
 }
 
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 5ec4c90a637d..f5dc0a7a2456 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -16,12 +16,33 @@
  */
 
 #include <linux/mtd/rawnand.h>
+#include <linux/slab.h>
 
 /*
- * Special Micron status bit that indicates when the block has been
- * corrected by on-die ECC and should be rewritten
+ * Special Micron status bit 3 indicates that the block has been
+ * corrected by on-die ECC and should be rewritten.
  */
-#define NAND_STATUS_WRITE_RECOMMENDED	BIT(3)
+#define NAND_ECC_STATUS_WRITE_RECOMMENDED	BIT(3)
+
+/*
+ * On chips with 8-bit ECC and additional bit can be used to distinguish
+ * cases where a errors were corrected without needing a rewrite
+ *
+ * Bit 4 Bit 3 Bit 0 Description
+ * ----- ----- ----- -----------
+ * 0     0     0     No Errors
+ * 0     0     1     Multiple uncorrected errors
+ * 0     1     0     4 - 6 errors corrected, recommend rewrite
+ * 0     1     1     Reserved
+ * 1     0     0     1 - 3 errors corrected
+ * 1     0     1     Reserved
+ * 1     1     0     7 - 8 errors corrected, recommend rewrite
+ */
+#define NAND_ECC_STATUS_MASK		(BIT(4) | BIT(3) | BIT(0))
+#define NAND_ECC_STATUS_UNCORRECTABLE	BIT(0)
+#define NAND_ECC_STATUS_4_6_CORRECTED	BIT(3)
+#define NAND_ECC_STATUS_1_3_CORRECTED	BIT(4)
+#define NAND_ECC_STATUS_7_8_CORRECTED	(BIT(4) | BIT(3))
 
 struct nand_onfi_vendor_micron {
 	u8 two_plane_read;
@@ -43,6 +64,16 @@ struct nand_onfi_vendor_micron {
 	u8 param_revision;
 } __packed;
 
+struct micron_on_die_ecc {
+	bool forced;
+	bool enabled;
+	void *rawbuf;
+};
+
+struct micron_nand {
+	struct micron_on_die_ecc ecc;
+};
+
 static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -57,9 +88,10 @@ static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
 static int micron_nand_onfi_init(struct nand_chip *chip)
 {
 	struct nand_parameters *p = &chip->parameters;
-	struct nand_onfi_vendor_micron *micron = (void *)p->onfi.vendor;
 
-	if (chip->parameters.onfi.version && p->onfi.vendor_revision) {
+	if (p->onfi) {
+		struct nand_onfi_vendor_micron *micron = (void *)p->onfi->vendor;
+
 		chip->read_retries = micron->read_retry_options;
 		chip->setup_read_retry = micron_nand_setup_read_retry;
 	}
@@ -74,8 +106,9 @@ static int micron_nand_onfi_init(struct nand_chip *chip)
 	return 0;
 }
 
-static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
-					    struct mtd_oob_region *oobregion)
+static int micron_nand_on_die_4_ooblayout_ecc(struct mtd_info *mtd,
+					      int section,
+					      struct mtd_oob_region *oobregion)
 {
 	if (section >= 4)
 		return -ERANGE;
@@ -86,8 +119,9 @@ static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
 	return 0;
 }
 
-static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
-					     struct mtd_oob_region *oobregion)
+static int micron_nand_on_die_4_ooblayout_free(struct mtd_info *mtd,
+					       int section,
+					       struct mtd_oob_region *oobregion)
 {
 	if (section >= 4)
 		return -ERANGE;
@@ -98,19 +132,161 @@ static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
 	return 0;
 }
 
-static const struct mtd_ooblayout_ops micron_nand_on_die_ooblayout_ops = {
-	.ecc = micron_nand_on_die_ooblayout_ecc,
-	.free = micron_nand_on_die_ooblayout_free,
+static const struct mtd_ooblayout_ops micron_nand_on_die_4_ooblayout_ops = {
+	.ecc = micron_nand_on_die_4_ooblayout_ecc,
+	.free = micron_nand_on_die_4_ooblayout_free,
+};
+
+static int micron_nand_on_die_8_ooblayout_ecc(struct mtd_info *mtd,
+					      int section,
+					      struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = mtd->oobsize - chip->ecc.total;
+	oobregion->length = chip->ecc.total;
+
+	return 0;
+}
+
+static int micron_nand_on_die_8_ooblayout_free(struct mtd_info *mtd,
+					       int section,
+					       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = 2;
+	oobregion->length = mtd->oobsize - chip->ecc.total - 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops micron_nand_on_die_8_ooblayout_ops = {
+	.ecc = micron_nand_on_die_8_ooblayout_ecc,
+	.free = micron_nand_on_die_8_ooblayout_free,
 };
 
 static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
 {
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
 	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	int ret;
+
+	if (micron->ecc.forced)
+		return 0;
+
+	if (micron->ecc.enabled == enable)
+		return 0;
 
 	if (enable)
 		feature[0] |= ONFI_FEATURE_ON_DIE_ECC_EN;
 
-	return nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
+	ret = nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
+	if (!ret)
+		micron->ecc.enabled = enable;
+
+	return ret;
+}
+
+static int micron_nand_on_die_ecc_status_4(struct nand_chip *chip, u8 status,
+					   void *buf, int page,
+					   int oob_required)
+{
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	unsigned int step, max_bitflips = 0;
+	int ret;
+
+	if (!(status & NAND_ECC_STATUS_WRITE_RECOMMENDED)) {
+		if (status & NAND_STATUS_FAIL)
+			mtd->ecc_stats.failed++;
+
+		return 0;
+	}
+
+	/*
+	 * The internal ECC doesn't tell us the number of bitflips that have
+	 * been corrected, but tells us if it recommends to rewrite the block.
+	 * If it's the case, we need to read the page in raw mode and compare
+	 * its content to the corrected version to extract the actual number of
+	 * bitflips.
+	 * But before we do that, we must make sure we have all OOB bytes read
+	 * in non-raw mode, even if the user did not request those bytes.
+	 */
+	if (!oob_required) {
+		ret = nand_read_data_op(chip, chip->oob_poi, mtd->oobsize,
+					false);
+		if (ret)
+			return ret;
+	}
+
+	micron_nand_on_die_ecc_setup(chip, false);
+
+	ret = nand_read_page_op(chip, page, 0, micron->ecc.rawbuf,
+				mtd->writesize + mtd->oobsize);
+	if (ret)
+		return ret;
+
+	for (step = 0; step < chip->ecc.steps; step++) {
+		unsigned int offs, i, nbitflips = 0;
+		u8 *rawbuf, *corrbuf;
+
+		offs = step * chip->ecc.size;
+		rawbuf = micron->ecc.rawbuf + offs;
+		corrbuf = buf + offs;
+
+		for (i = 0; i < chip->ecc.size; i++)
+			nbitflips += hweight8(corrbuf[i] ^ rawbuf[i]);
+
+		offs = (step * 16) + 4;
+		rawbuf = micron->ecc.rawbuf + mtd->writesize + offs;
+		corrbuf = chip->oob_poi + offs;
+
+		for (i = 0; i < chip->ecc.bytes + 4; i++)
+			nbitflips += hweight8(corrbuf[i] ^ rawbuf[i]);
+
+		if (WARN_ON(nbitflips > chip->ecc.strength))
+			return -EINVAL;
+
+		max_bitflips = max(nbitflips, max_bitflips);
+		mtd->ecc_stats.corrected += nbitflips;
+	}
+
+	return max_bitflips;
+}
+
+static int micron_nand_on_die_ecc_status_8(struct nand_chip *chip, u8 status)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	/*
+	 * With 8/512 we have more information but still don't know precisely
+	 * how many bit-flips were seen.
+	 */
+	switch (status & NAND_ECC_STATUS_MASK) {
+	case NAND_ECC_STATUS_UNCORRECTABLE:
+		mtd->ecc_stats.failed++;
+		return 0;
+	case NAND_ECC_STATUS_1_3_CORRECTED:
+		mtd->ecc_stats.corrected += 3;
+		return 3;
+	case NAND_ECC_STATUS_4_6_CORRECTED:
+		mtd->ecc_stats.corrected += 6;
+		/* rewrite recommended */
+		return 6;
+	case NAND_ECC_STATUS_7_8_CORRECTED:
+		mtd->ecc_stats.corrected += 8;
+		/* rewrite recommended */
+		return 8;
+	default:
+		return 0;
+	}
 }
 
 static int
@@ -137,24 +313,18 @@ micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
 	if (ret)
 		goto out;
 
-	if (status & NAND_STATUS_FAIL)
-		mtd->ecc_stats.failed++;
-
-	/*
-	 * The internal ECC doesn't tell us the number of bitflips
-	 * that have been corrected, but tells us if it recommends to
-	 * rewrite the block. If it's the case, then we pretend we had
-	 * a number of bitflips equal to the ECC strength, which will
-	 * hint the NAND core to rewrite the block.
-	 */
-	else if (status & NAND_STATUS_WRITE_RECOMMENDED)
-		max_bitflips = chip->ecc.strength;
-
 	ret = nand_read_data_op(chip, buf, mtd->writesize, false);
 	if (!ret && oob_required)
 		ret = nand_read_data_op(chip, chip->oob_poi, mtd->oobsize,
 					false);
 
+	if (chip->ecc.strength == 4)
+		max_bitflips = micron_nand_on_die_ecc_status_4(chip, status,
+							       buf, page,
+							       oob_required);
+	else
+		max_bitflips = micron_nand_on_die_ecc_status_8(chip, status);
+
 out:
 	micron_nand_on_die_ecc_setup(chip, false);
 
@@ -195,6 +365,9 @@ enum {
 	MICRON_ON_DIE_MANDATORY,
 };
 
+#define MICRON_ID_INTERNAL_ECC_MASK	GENMASK(1, 0)
+#define MICRON_ID_ECC_ENABLED		BIT(7)
+
 /*
  * Try to detect if the NAND support on-die ECC. To do this, we enable
  * the feature, and read back if it has been enabled as expected. We
@@ -207,42 +380,52 @@ enum {
  */
 static int micron_supports_on_die_ecc(struct nand_chip *chip)
 {
-	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	u8 id[5];
 	int ret;
 
-	if (!chip->parameters.onfi.version)
+	if (!chip->parameters.onfi)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	if (chip->bits_per_cell != 1)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
+	/*
+	 * We only support on-die ECC of 4/512 or 8/512
+	 */
+	if  (chip->ecc_strength_ds != 4 && chip->ecc_strength_ds != 8)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	/* 0x2 means on-die ECC is available. */
+	if (chip->id.len != 5 ||
+	    (chip->id.data[4] & MICRON_ID_INTERNAL_ECC_MASK) != 0x2)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
 	ret = micron_nand_on_die_ecc_setup(chip, true);
 	if (ret)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
-	ret = nand_get_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
-	if (ret < 0)
-		return ret;
+	ret = nand_readid_op(chip, 0, id, sizeof(id));
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
 
-	if ((feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN) == 0)
+	if (!(id[4] & MICRON_ID_ECC_ENABLED))
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	ret = micron_nand_on_die_ecc_setup(chip, false);
 	if (ret)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
-	ret = nand_get_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
-	if (ret < 0)
-		return ret;
+	ret = nand_readid_op(chip, 0, id, sizeof(id));
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
 
-	if (feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN)
+	if (id[4] & MICRON_ID_ECC_ENABLED)
 		return MICRON_ON_DIE_MANDATORY;
 
 	/*
-	 * Some Micron NANDs have an on-die ECC of 4/512, some other
-	 * 8/512. We only support the former.
+	 * We only support on-die ECC of 4/512 or 8/512
 	 */
-	if (chip->ecc_strength_ds != 4)
+	if  (chip->ecc_strength_ds != 4 && chip->ecc_strength_ds != 8)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	return MICRON_ON_DIE_SUPPORTED;
@@ -251,44 +434,116 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip)
 static int micron_nand_init(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct micron_nand *micron;
 	int ondie;
 	int ret;
 
+	micron = kzalloc(sizeof(*micron), GFP_KERNEL);
+	if (!micron)
+		return -ENOMEM;
+
+	nand_set_manufacturer_data(chip, micron);
+
 	ret = micron_nand_onfi_init(chip);
 	if (ret)
-		return ret;
+		goto err_free_manuf_data;
 
 	if (mtd->writesize == 2048)
 		chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
 
 	ondie = micron_supports_on_die_ecc(chip);
 
-	if (ondie == MICRON_ON_DIE_MANDATORY) {
+	if (ondie == MICRON_ON_DIE_MANDATORY &&
+	    chip->ecc.mode != NAND_ECC_ON_DIE) {
 		pr_err("On-die ECC forcefully enabled, not supported\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_free_manuf_data;
 	}
 
 	if (chip->ecc.mode == NAND_ECC_ON_DIE) {
 		if (ondie == MICRON_ON_DIE_UNSUPPORTED) {
 			pr_err("On-die ECC selected but not supported\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_free_manuf_data;
+		}
+
+		if (ondie == MICRON_ON_DIE_MANDATORY) {
+			micron->ecc.forced = true;
+			micron->ecc.enabled = true;
+		}
+
+		/*
+		 * In case of 4bit on-die ECC, we need a buffer to store a
+		 * page dumped in raw mode so that we can compare its content
+		 * to the same page after ECC correction happened and extract
+		 * the real number of bitflips from this comparison.
+		 * That's not needed for 8-bit ECC, because the status expose
+		 * a better approximation of the number of bitflips in a page.
+		 */
+		if (chip->ecc_strength_ds == 4) {
+			micron->ecc.rawbuf = kmalloc(mtd->writesize +
+						     mtd->oobsize,
+						     GFP_KERNEL);
+			if (!micron->ecc.rawbuf) {
+				ret = -ENOMEM;
+				goto err_free_manuf_data;
+			}
 		}
 
-		chip->ecc.bytes = 8;
+		if (chip->ecc_strength_ds == 4)
+			mtd_set_ooblayout(mtd,
+					  &micron_nand_on_die_4_ooblayout_ops);
+		else
+			mtd_set_ooblayout(mtd,
+					  &micron_nand_on_die_8_ooblayout_ops);
+
+		chip->ecc.bytes = chip->ecc_strength_ds * 2;
 		chip->ecc.size = 512;
-		chip->ecc.strength = 4;
+		chip->ecc.strength = chip->ecc_strength_ds;
 		chip->ecc.algo = NAND_ECC_BCH;
 		chip->ecc.read_page = micron_nand_read_page_on_die_ecc;
 		chip->ecc.write_page = micron_nand_write_page_on_die_ecc;
-		chip->ecc.read_page_raw = nand_read_page_raw;
-		chip->ecc.write_page_raw = nand_write_page_raw;
 
-		mtd_set_ooblayout(mtd, &micron_nand_on_die_ooblayout_ops);
+		if (ondie == MICRON_ON_DIE_MANDATORY) {
+			chip->ecc.read_page_raw = nand_read_page_raw_notsupp;
+			chip->ecc.write_page_raw = nand_write_page_raw_notsupp;
+		} else {
+			chip->ecc.read_page_raw = nand_read_page_raw;
+			chip->ecc.write_page_raw = nand_write_page_raw;
+		}
 	}
 
 	return 0;
+
+err_free_manuf_data:
+	kfree(micron->ecc.rawbuf);
+	kfree(micron);
+
+	return ret;
+}
+
+static void micron_nand_cleanup(struct nand_chip *chip)
+{
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
+
+	kfree(micron->ecc.rawbuf);
+	kfree(micron);
+}
+
+static void micron_fixup_onfi_param_page(struct nand_chip *chip,
+					 struct nand_onfi_params *p)
+{
+	/*
+	 * MT29F1G08ABAFAWP-ITE:F and possibly others report 00 00 for the
+	 * revision number field of the ONFI parameter page. Assume ONFI
+	 * version 1.0 if the revision number is 00 00.
+	 */
+	if (le16_to_cpu(p->revision) == 0)
+		p->revision = cpu_to_le16(ONFI_VERSION_1_0);
 }
 
 const struct nand_manufacturer_ops micron_nand_manuf_ops = {
 	.init = micron_nand_init,
+	.cleanup = micron_nand_cleanup,
+	.fixup_onfi_param_page = micron_fixup_onfi_param_page,
 };
diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c
index 7c4e4a371bbc..ebc7b5f76f77 100644
--- a/drivers/mtd/nand/raw/nand_timings.c
+++ b/drivers/mtd/nand/raw/nand_timings.c
@@ -13,6 +13,8 @@
 #include <linux/export.h>
 #include <linux/mtd/rawnand.h>
 
+#define ONFI_DYN_TIMING_MAX U16_MAX
+
 static const struct nand_data_interface onfi_sdr_timings[] = {
 	/* Mode 0 */
 	{
@@ -292,6 +294,7 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 			     int timing_mode)
 {
 	struct nand_data_interface *iface = &chip->data_interface;
+	struct onfi_params *onfi = chip->parameters.onfi;
 
 	if (type != NAND_SDR_IFACE)
 		return -EINVAL;
@@ -303,20 +306,35 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 
 	/*
 	 * Initialize timings that cannot be deduced from timing mode:
-	 * tR, tPROG, tCCS, ...
+	 * tPROG, tBERS, tR and tCCS.
 	 * These information are part of the ONFI parameter page.
 	 */
-	if (chip->parameters.onfi.version) {
-		struct nand_parameters *params = &chip->parameters;
+	if (onfi) {
+		struct nand_sdr_timings *timings = &iface->timings.sdr;
+
+		/* microseconds -> picoseconds */
+		timings->tPROG_max = 1000000ULL * onfi->tPROG;
+		timings->tBERS_max = 1000000ULL * onfi->tBERS;
+		timings->tR_max = 1000000ULL * onfi->tR;
+
+		/* nanoseconds -> picoseconds */
+		timings->tCCS_min = 1000UL * onfi->tCCS;
+	} else {
 		struct nand_sdr_timings *timings = &iface->timings.sdr;
+		/*
+		 * For non-ONFI chips we use the highest possible value for
+		 * tPROG and tBERS. tR and tCCS will take the default values
+		 * precised in the ONFI specification for timing mode 0,
+		 * respectively 200us and 500ns.
+		 */
 
 		/* microseconds -> picoseconds */
-		timings->tPROG_max = 1000000ULL * params->onfi.tPROG;
-		timings->tBERS_max = 1000000ULL * params->onfi.tBERS;
-		timings->tR_max = 1000000ULL * params->onfi.tR;
+		timings->tPROG_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
+		timings->tBERS_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
+		timings->tR_max = 1000000ULL * 200000000ULL;
 
 		/* nanoseconds -> picoseconds */
-		timings->tCCS_min = 1000UL * params->onfi.tCCS;
+		timings->tCCS_min = 1000UL * 500000;
 	}
 
 	return 0;
diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index f8edacde49ab..71ac034aee9c 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -2192,6 +2192,48 @@ static void ns_nand_read_buf(struct mtd_info *mtd, u_char *buf, int len)
 	return;
 }
 
+static int ns_attach_chip(struct nand_chip *chip)
+{
+	unsigned int eccsteps, eccbytes;
+
+	if (!bch)
+		return 0;
+
+	if (!mtd_nand_has_bch()) {
+		NS_ERR("BCH ECC support is disabled\n");
+		return -EINVAL;
+	}
+
+	/* Use 512-byte ecc blocks */
+	eccsteps = nsmtd->writesize / 512;
+	eccbytes = ((bch * 13) + 7) / 8;
+
+	/* Do not bother supporting small page devices */
+	if (nsmtd->oobsize < 64 || !eccsteps) {
+		NS_ERR("BCH not available on small page devices\n");
+		return -EINVAL;
+	}
+
+	if (((eccbytes * eccsteps) + 2) > nsmtd->oobsize) {
+		NS_ERR("Invalid BCH value %u\n", bch);
+		return -EINVAL;
+	}
+
+	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.algo = NAND_ECC_BCH;
+	chip->ecc.size = 512;
+	chip->ecc.strength = bch;
+	chip->ecc.bytes = eccbytes;
+
+	NS_INFO("Using %u-bit/%u bytes BCH ECC\n", bch, chip->ecc.size);
+
+	return 0;
+}
+
+static const struct nand_controller_ops ns_controller_ops = {
+	.attach_chip = ns_attach_chip,
+};
+
 /*
  * Module initialization function
  */
@@ -2276,44 +2318,10 @@ static int __init ns_init_module(void)
 	if ((retval = parse_gravepages()) != 0)
 		goto error;
 
-	retval = nand_scan_ident(nsmtd, 1, NULL);
-	if (retval) {
-		NS_ERR("cannot scan NAND Simulator device\n");
-		goto error;
-	}
-
-	if (bch) {
-		unsigned int eccsteps, eccbytes;
-		if (!mtd_nand_has_bch()) {
-			NS_ERR("BCH ECC support is disabled\n");
-			retval = -EINVAL;
-			goto error;
-		}
-		/* use 512-byte ecc blocks */
-		eccsteps = nsmtd->writesize/512;
-		eccbytes = (bch*13+7)/8;
-		/* do not bother supporting small page devices */
-		if ((nsmtd->oobsize < 64) || !eccsteps) {
-			NS_ERR("bch not available on small page devices\n");
-			retval = -EINVAL;
-			goto error;
-		}
-		if ((eccbytes*eccsteps+2) > nsmtd->oobsize) {
-			NS_ERR("invalid bch value %u\n", bch);
-			retval = -EINVAL;
-			goto error;
-		}
-		chip->ecc.mode = NAND_ECC_SOFT;
-		chip->ecc.algo = NAND_ECC_BCH;
-		chip->ecc.size = 512;
-		chip->ecc.strength = bch;
-		chip->ecc.bytes = eccbytes;
-		NS_INFO("using %u-bit/%u bytes BCH ECC\n", bch, chip->ecc.size);
-	}
-
-	retval = nand_scan_tail(nsmtd);
+	chip->dummy_controller.ops = &ns_controller_ops;
+	retval = nand_scan(nsmtd, 1);
 	if (retval) {
-		NS_ERR("can't register NAND Simulator\n");
+		NS_ERR("Could not scan NAND Simulator device\n");
 		goto error;
 	}
 
@@ -2337,7 +2345,7 @@ static int __init ns_init_module(void)
 	if ((retval = init_nandsim(nsmtd)) != 0)
 		goto err_exit;
 
-	if ((retval = chip->scan_bbt(nsmtd)) != 0)
+	if ((retval = nand_create_bbt(chip)) != 0)
 		goto err_exit;
 
 	if ((retval = parse_badblocks(nand, nsmtd)) != 0)
diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c
index d8a806894937..540fa1a0ea24 100644
--- a/drivers/mtd/nand/raw/ndfc.c
+++ b/drivers/mtd/nand/raw/ndfc.c
@@ -39,7 +39,7 @@ struct ndfc_controller {
 	void __iomem *ndfcbase;
 	struct nand_chip chip;
 	int chip_select;
-	struct nand_hw_control ndfc_control;
+	struct nand_controller ndfc_control;
 };
 
 static struct ndfc_controller ndfc_ctrl[NDFC_MAX_CS];
@@ -218,7 +218,7 @@ static int ndfc_probe(struct platform_device *ofdev)
 	ndfc = &ndfc_ctrl[cs];
 	ndfc->chip_select = cs;
 
-	nand_hw_control_init(&ndfc->ndfc_control);
+	nand_controller_init(&ndfc->ndfc_control);
 	ndfc->ofdev = ofdev;
 	dev_set_drvdata(&ofdev->dev, ndfc);
 
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index e50c64adc3c8..4546ac0bed4a 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -144,12 +144,6 @@ static u_char bch8_vector[] = {0xf3, 0xdb, 0x14, 0x16, 0x8b, 0xd2, 0xbe, 0xcc,
 	0xac, 0x6b, 0xff, 0x99, 0x7b};
 static u_char bch4_vector[] = {0x00, 0x6b, 0x31, 0xdd, 0x41, 0xbc, 0x10};
 
-/* Shared among all NAND instances to synchronize access to the ECC Engine */
-static struct nand_hw_control omap_gpmc_controller = {
-	.lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock),
-	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq),
-};
-
 struct omap_nand_info {
 	struct nand_chip		nand;
 	struct platform_device		*pdev;
@@ -1915,106 +1909,26 @@ static const struct mtd_ooblayout_ops omap_sw_ooblayout_ops = {
 	.free = omap_sw_ooblayout_free,
 };
 
-static int omap_nand_probe(struct platform_device *pdev)
+static int omap_nand_attach_chip(struct nand_chip *chip)
 {
-	struct omap_nand_info		*info;
-	struct mtd_info			*mtd;
-	struct nand_chip		*nand_chip;
-	int				err;
-	dma_cap_mask_t			mask;
-	struct resource			*res;
-	struct device			*dev = &pdev->dev;
-	int				min_oobbytes = BADBLOCK_MARKER_LENGTH;
-	int				oobbytes_per_step;
-
-	info = devm_kzalloc(&pdev->dev, sizeof(struct omap_nand_info),
-				GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info->pdev = pdev;
-
-	err = omap_get_dt_info(dev, info);
-	if (err)
-		return err;
-
-	info->ops = gpmc_omap_get_nand_ops(&info->reg, info->gpmc_cs);
-	if (!info->ops) {
-		dev_err(&pdev->dev, "Failed to get GPMC->NAND interface\n");
-		return -ENODEV;
-	}
-
-	nand_chip		= &info->nand;
-	mtd			= nand_to_mtd(nand_chip);
-	mtd->dev.parent		= &pdev->dev;
-	nand_chip->ecc.priv	= NULL;
-	nand_set_flash_node(nand_chip, dev->of_node);
-
-	if (!mtd->name) {
-		mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-					   "omap2-nand.%d", info->gpmc_cs);
-		if (!mtd->name) {
-			dev_err(&pdev->dev, "Failed to set MTD name\n");
-			return -ENOMEM;
-		}
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(nand_chip->IO_ADDR_R))
-		return PTR_ERR(nand_chip->IO_ADDR_R);
-
-	info->phys_base = res->start;
-
-	nand_chip->controller = &omap_gpmc_controller;
-
-	nand_chip->IO_ADDR_W = nand_chip->IO_ADDR_R;
-	nand_chip->cmd_ctrl  = omap_hwcontrol;
-
-	info->ready_gpiod = devm_gpiod_get_optional(&pdev->dev, "rb",
-						    GPIOD_IN);
-	if (IS_ERR(info->ready_gpiod)) {
-		dev_err(dev, "failed to get ready gpio\n");
-		return PTR_ERR(info->ready_gpiod);
-	}
-
-	/*
-	 * If RDY/BSY line is connected to OMAP then use the omap ready
-	 * function and the generic nand_wait function which reads the status
-	 * register after monitoring the RDY/BSY line. Otherwise use a standard
-	 * chip delay which is slightly more than tR (AC Timing) of the NAND
-	 * device and read status register until you get a failure or success
-	 */
-	if (info->ready_gpiod) {
-		nand_chip->dev_ready = omap_dev_ready;
-		nand_chip->chip_delay = 0;
-	} else {
-		nand_chip->waitfunc = omap_wait;
-		nand_chip->chip_delay = 50;
-	}
-
-	if (info->flash_bbt)
-		nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
-
-	/* scan NAND device connected to chip controller */
-	nand_chip->options |= info->devsize & NAND_BUSWIDTH_16;
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err) {
-		dev_err(&info->pdev->dev,
-			"scan failed, may be bus-width mismatch\n");
-		goto return_error;
-	}
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct omap_nand_info *info = mtd_to_omap(mtd);
+	struct device *dev = &info->pdev->dev;
+	int min_oobbytes = BADBLOCK_MARKER_LENGTH;
+	int oobbytes_per_step;
+	dma_cap_mask_t mask;
+	int err;
 
-	if (nand_chip->bbt_options & NAND_BBT_USE_FLASH)
-		nand_chip->bbt_options |= NAND_BBT_NO_OOB;
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
 	else
-		nand_chip->options |= NAND_SKIP_BBTSCAN;
+		chip->options |= NAND_SKIP_BBTSCAN;
 
-	/* re-populate low-level callbacks based on xfer modes */
+	/* Re-populate low-level callbacks based on xfer modes */
 	switch (info->xfer_type) {
 	case NAND_OMAP_PREFETCH_POLLED:
-		nand_chip->read_buf   = omap_read_buf_pref;
-		nand_chip->write_buf  = omap_write_buf_pref;
+		chip->read_buf = omap_read_buf_pref;
+		chip->write_buf = omap_write_buf_pref;
 		break;
 
 	case NAND_OMAP_POLLED:
@@ -2024,12 +1938,11 @@ static int omap_nand_probe(struct platform_device *pdev)
 	case NAND_OMAP_PREFETCH_DMA:
 		dma_cap_zero(mask);
 		dma_cap_set(DMA_SLAVE, mask);
-		info->dma = dma_request_chan(pdev->dev.parent, "rxtx");
+		info->dma = dma_request_chan(dev, "rxtx");
 
 		if (IS_ERR(info->dma)) {
-			dev_err(&pdev->dev, "DMA engine request failed\n");
-			err = PTR_ERR(info->dma);
-			goto return_error;
+			dev_err(dev, "DMA engine request failed\n");
+			return PTR_ERR(info->dma);
 		} else {
 			struct dma_slave_config cfg;
 
@@ -2042,222 +1955,306 @@ static int omap_nand_probe(struct platform_device *pdev)
 			cfg.dst_maxburst = 16;
 			err = dmaengine_slave_config(info->dma, &cfg);
 			if (err) {
-				dev_err(&pdev->dev, "DMA engine slave config failed: %d\n",
+				dev_err(dev,
+					"DMA engine slave config failed: %d\n",
 					err);
-				goto return_error;
+				return err;
 			}
-			nand_chip->read_buf   = omap_read_buf_dma_pref;
-			nand_chip->write_buf  = omap_write_buf_dma_pref;
+			chip->read_buf = omap_read_buf_dma_pref;
+			chip->write_buf = omap_write_buf_dma_pref;
 		}
 		break;
 
 	case NAND_OMAP_PREFETCH_IRQ:
-		info->gpmc_irq_fifo = platform_get_irq(pdev, 0);
+		info->gpmc_irq_fifo = platform_get_irq(info->pdev, 0);
 		if (info->gpmc_irq_fifo <= 0) {
-			dev_err(&pdev->dev, "error getting fifo irq\n");
-			err = -ENODEV;
-			goto return_error;
+			dev_err(dev, "Error getting fifo IRQ\n");
+			return -ENODEV;
 		}
-		err = devm_request_irq(&pdev->dev, info->gpmc_irq_fifo,
-					omap_nand_irq, IRQF_SHARED,
-					"gpmc-nand-fifo", info);
+		err = devm_request_irq(dev, info->gpmc_irq_fifo,
+				       omap_nand_irq, IRQF_SHARED,
+				       "gpmc-nand-fifo", info);
 		if (err) {
-			dev_err(&pdev->dev, "requesting irq(%d) error:%d",
-						info->gpmc_irq_fifo, err);
+			dev_err(dev, "Requesting IRQ %d, error %d\n",
+				info->gpmc_irq_fifo, err);
 			info->gpmc_irq_fifo = 0;
-			goto return_error;
+			return err;
 		}
 
-		info->gpmc_irq_count = platform_get_irq(pdev, 1);
+		info->gpmc_irq_count = platform_get_irq(info->pdev, 1);
 		if (info->gpmc_irq_count <= 0) {
-			dev_err(&pdev->dev, "error getting count irq\n");
-			err = -ENODEV;
-			goto return_error;
+			dev_err(dev, "Error getting IRQ count\n");
+			return -ENODEV;
 		}
-		err = devm_request_irq(&pdev->dev, info->gpmc_irq_count,
-					omap_nand_irq, IRQF_SHARED,
-					"gpmc-nand-count", info);
+		err = devm_request_irq(dev, info->gpmc_irq_count,
+				       omap_nand_irq, IRQF_SHARED,
+				       "gpmc-nand-count", info);
 		if (err) {
-			dev_err(&pdev->dev, "requesting irq(%d) error:%d",
-						info->gpmc_irq_count, err);
+			dev_err(dev, "Requesting IRQ %d, error %d\n",
+				info->gpmc_irq_count, err);
 			info->gpmc_irq_count = 0;
-			goto return_error;
+			return err;
 		}
 
-		nand_chip->read_buf  = omap_read_buf_irq_pref;
-		nand_chip->write_buf = omap_write_buf_irq_pref;
+		chip->read_buf = omap_read_buf_irq_pref;
+		chip->write_buf = omap_write_buf_irq_pref;
 
 		break;
 
 	default:
-		dev_err(&pdev->dev,
-			"xfer_type(%d) not supported!\n", info->xfer_type);
-		err = -EINVAL;
-		goto return_error;
+		dev_err(dev, "xfer_type %d not supported!\n", info->xfer_type);
+		return -EINVAL;
 	}
 
-	if (!omap2_nand_ecc_check(info)) {
-		err = -EINVAL;
-		goto return_error;
-	}
+	if (!omap2_nand_ecc_check(info))
+		return -EINVAL;
 
 	/*
 	 * Bail out earlier to let NAND_ECC_SOFT code create its own
 	 * ooblayout instead of using ours.
 	 */
 	if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW) {
-		nand_chip->ecc.mode = NAND_ECC_SOFT;
-		nand_chip->ecc.algo = NAND_ECC_HAMMING;
-		goto scan_tail;
+		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.algo = NAND_ECC_HAMMING;
+		return 0;
 	}
 
-	/* populate MTD interface based on ECC scheme */
+	/* Populate MTD interface based on ECC scheme */
 	switch (info->ecc_opt) {
 	case OMAP_ECC_HAM1_CODE_HW:
-		pr_info("nand: using OMAP_ECC_HAM1_CODE_HW\n");
-		nand_chip->ecc.mode             = NAND_ECC_HW;
-		nand_chip->ecc.bytes            = 3;
-		nand_chip->ecc.size             = 512;
-		nand_chip->ecc.strength         = 1;
-		nand_chip->ecc.calculate        = omap_calculate_ecc;
-		nand_chip->ecc.hwctl            = omap_enable_hwecc;
-		nand_chip->ecc.correct          = omap_correct_data;
+		dev_info(dev, "nand: using OMAP_ECC_HAM1_CODE_HW\n");
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.bytes		= 3;
+		chip->ecc.size		= 512;
+		chip->ecc.strength	= 1;
+		chip->ecc.calculate	= omap_calculate_ecc;
+		chip->ecc.hwctl		= omap_enable_hwecc;
+		chip->ecc.correct	= omap_correct_data;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
-		if (!(nand_chip->options & NAND_BUSWIDTH_16))
-			min_oobbytes		= 1;
+		if (!(chip->options & NAND_BUSWIDTH_16))
+			min_oobbytes	= 1;
 
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW_DETECTION_SW\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 7;
-		nand_chip->ecc.strength		= 4;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= nand_bch_correct_data;
-		nand_chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 7;
+		chip->ecc.strength	= 4;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
-		oobbytes_per_step		= nand_chip->ecc.bytes + 1;
-		/* software bch library is used for locating errors */
-		nand_chip->ecc.priv		= nand_bch_init(mtd);
-		if (!nand_chip->ecc.priv) {
-			dev_err(&info->pdev->dev, "unable to use BCH library\n");
-			err = -EINVAL;
-			goto return_error;
+		oobbytes_per_step	= chip->ecc.bytes + 1;
+		/* Software BCH library is used for locating errors */
+		chip->ecc.priv		= nand_bch_init(mtd);
+		if (!chip->ecc.priv) {
+			dev_err(dev, "Unable to use BCH library\n");
+			return -EINVAL;
 		}
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
-		nand_chip->ecc.bytes		= 7 + 1;
-		nand_chip->ecc.strength		= 4;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		chip->ecc.bytes		= 7 + 1;
+		chip->ecc.strength	= 4;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH4_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 		break;
 
 	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW_DETECTION_SW\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 13;
-		nand_chip->ecc.strength		= 8;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= nand_bch_correct_data;
-		nand_chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 13;
+		chip->ecc.strength	= 8;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
-		oobbytes_per_step		= nand_chip->ecc.bytes + 1;
-		/* software bch library is used for locating errors */
-		nand_chip->ecc.priv		= nand_bch_init(mtd);
-		if (!nand_chip->ecc.priv) {
-			dev_err(&info->pdev->dev, "unable to use BCH library\n");
-			err = -EINVAL;
-			goto return_error;
+		oobbytes_per_step	= chip->ecc.bytes + 1;
+		/* Software BCH library is used for locating errors */
+		chip->ecc.priv		= nand_bch_init(mtd);
+		if (!chip->ecc.priv) {
+			dev_err(dev, "unable to use BCH library\n");
+			return -EINVAL;
 		}
 		break;
 
 	case OMAP_ECC_BCH8_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
-		nand_chip->ecc.bytes		= 13 + 1;
-		nand_chip->ecc.strength		= 8;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		chip->ecc.bytes		= 13 + 1;
+		chip->ecc.strength	= 8;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH8_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 
 		break;
 
 	case OMAP_ECC_BCH16_CODE_HW:
-		pr_info("using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 26;
-		nand_chip->ecc.strength		= 16;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		pr_info("Using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 26;
+		chip->ecc.strength	= 16;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH16_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 
 		break;
 	default:
-		dev_err(&info->pdev->dev, "invalid or unsupported ECC scheme\n");
-		err = -EINVAL;
-		goto return_error;
+		dev_err(dev, "Invalid or unsupported ECC scheme\n");
+		return -EINVAL;
 	}
 
-	/* check if NAND device's OOB is enough to store ECC signatures */
+	/* Check if NAND device's OOB is enough to store ECC signatures */
 	min_oobbytes += (oobbytes_per_step *
-			 (mtd->writesize / nand_chip->ecc.size));
+			 (mtd->writesize / chip->ecc.size));
 	if (mtd->oobsize < min_oobbytes) {
-		dev_err(&info->pdev->dev,
-			"not enough OOB bytes required = %d, available=%d\n",
+		dev_err(dev,
+			"Not enough OOB bytes: required = %d, available=%d\n",
 			min_oobbytes, mtd->oobsize);
-		err = -EINVAL;
-		goto return_error;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops omap_nand_controller_ops = {
+	.attach_chip = omap_nand_attach_chip,
+};
+
+/* Shared among all NAND instances to synchronize access to the ECC Engine */
+static struct nand_controller omap_gpmc_controller = {
+	.lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock),
+	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq),
+	.ops = &omap_nand_controller_ops,
+};
+
+static int omap_nand_probe(struct platform_device *pdev)
+{
+	struct omap_nand_info		*info;
+	struct mtd_info			*mtd;
+	struct nand_chip		*nand_chip;
+	int				err;
+	struct resource			*res;
+	struct device			*dev = &pdev->dev;
+
+	info = devm_kzalloc(&pdev->dev, sizeof(struct omap_nand_info),
+				GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->pdev = pdev;
+
+	err = omap_get_dt_info(dev, info);
+	if (err)
+		return err;
+
+	info->ops = gpmc_omap_get_nand_ops(&info->reg, info->gpmc_cs);
+	if (!info->ops) {
+		dev_err(&pdev->dev, "Failed to get GPMC->NAND interface\n");
+		return -ENODEV;
 	}
 
-scan_tail:
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	nand_chip		= &info->nand;
+	mtd			= nand_to_mtd(nand_chip);
+	mtd->dev.parent		= &pdev->dev;
+	nand_chip->ecc.priv	= NULL;
+	nand_set_flash_node(nand_chip, dev->of_node);
+
+	if (!mtd->name) {
+		mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+					   "omap2-nand.%d", info->gpmc_cs);
+		if (!mtd->name) {
+			dev_err(&pdev->dev, "Failed to set MTD name\n");
+			return -ENOMEM;
+		}
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(nand_chip->IO_ADDR_R))
+		return PTR_ERR(nand_chip->IO_ADDR_R);
+
+	info->phys_base = res->start;
+
+	nand_chip->controller = &omap_gpmc_controller;
+
+	nand_chip->IO_ADDR_W = nand_chip->IO_ADDR_R;
+	nand_chip->cmd_ctrl  = omap_hwcontrol;
+
+	info->ready_gpiod = devm_gpiod_get_optional(&pdev->dev, "rb",
+						    GPIOD_IN);
+	if (IS_ERR(info->ready_gpiod)) {
+		dev_err(dev, "failed to get ready gpio\n");
+		return PTR_ERR(info->ready_gpiod);
+	}
+
+	/*
+	 * If RDY/BSY line is connected to OMAP then use the omap ready
+	 * function and the generic nand_wait function which reads the status
+	 * register after monitoring the RDY/BSY line. Otherwise use a standard
+	 * chip delay which is slightly more than tR (AC Timing) of the NAND
+	 * device and read status register until you get a failure or success
+	 */
+	if (info->ready_gpiod) {
+		nand_chip->dev_ready = omap_dev_ready;
+		nand_chip->chip_delay = 0;
+	} else {
+		nand_chip->waitfunc = omap_wait;
+		nand_chip->chip_delay = 50;
+	}
+
+	if (info->flash_bbt)
+		nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+	/* scan NAND device connected to chip controller */
+	nand_chip->options |= info->devsize & NAND_BUSWIDTH_16;
+
+	err = nand_scan(mtd, 1);
 	if (err)
 		goto return_error;
 
diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index 7825fd3ce66b..52d435285a3f 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -18,7 +18,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
 #include <linux/platform_data/mtd-orion_nand.h>
 
 struct orion_nand_info {
@@ -52,7 +52,7 @@ static void orion_nand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	void __iomem *io_base = chip->IO_ADDR_R;
-#if __LINUX_ARM_ARCH__ >= 5
+#if defined(__LINUX_ARM_ARCH__) && __LINUX_ARM_ARCH__ >= 5
 	uint64_t *buf64;
 #endif
 	int i = 0;
@@ -61,7 +61,7 @@ static void orion_nand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 		*buf++ = readb(io_base);
 		len--;
 	}
-#if __LINUX_ARM_ARCH__ >= 5
+#if defined(__LINUX_ARM_ARCH__) && __LINUX_ARM_ARCH__ >= 5
 	buf64 = (uint64_t *)buf;
 	while (i < len/8) {
 		/*
@@ -153,9 +153,6 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	if (board->width == 16)
 		nc->options |= NAND_BUSWIDTH_16;
 
-	if (board->dev_ready)
-		nc->dev_ready = board->dev_ready;
-
 	platform_set_drvdata(pdev, info);
 
 	/* Not all platforms can gate the clock, so it is not
diff --git a/drivers/mtd/nand/raw/oxnas_nand.c b/drivers/mtd/nand/raw/oxnas_nand.c
index d649d5944826..01b00bb69c1e 100644
--- a/drivers/mtd/nand/raw/oxnas_nand.c
+++ b/drivers/mtd/nand/raw/oxnas_nand.c
@@ -32,7 +32,7 @@
 #define OXNAS_NAND_MAX_CHIPS	1
 
 struct oxnas_nand_ctrl {
-	struct nand_hw_control base;
+	struct nand_controller base;
 	void __iomem *io_base;
 	struct clk *clk;
 	struct nand_chip *chips[OXNAS_NAND_MAX_CHIPS];
@@ -96,7 +96,7 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 	if (!oxnas)
 		return -ENOMEM;
 
-	nand_hw_control_init(&oxnas->base);
+	nand_controller_init(&oxnas->base);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	oxnas->io_base = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c
index 925a1323604d..222626df4b96 100644
--- a/drivers/mtd/nand/raw/plat_nand.c
+++ b/drivers/mtd/nand/raw/plat_nand.c
@@ -67,12 +67,10 @@ static int plat_nand_probe(struct platform_device *pdev)
 	data->chip.select_chip = pdata->ctrl.select_chip;
 	data->chip.write_buf = pdata->ctrl.write_buf;
 	data->chip.read_buf = pdata->ctrl.read_buf;
-	data->chip.read_byte = pdata->ctrl.read_byte;
 	data->chip.chip_delay = pdata->chip.chip_delay;
 	data->chip.options |= pdata->chip.options;
 	data->chip.bbt_options |= pdata->chip.bbt_options;
 
-	data->chip.ecc.hwctl = pdata->ctrl.hwcontrol;
 	data->chip.ecc.mode = NAND_ECC_SOFT;
 	data->chip.ecc.algo = NAND_ECC_HAMMING;
 
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 6a5519f0ff25..d1d470bb32e4 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -213,6 +213,8 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
 #define QPIC_PER_CW_CMD_SGL		32
 #define QPIC_PER_CW_DATA_SGL		8
 
+#define QPIC_NAND_COMPLETION_TIMEOUT	msecs_to_jiffies(2000)
+
 /*
  * Flags used in DMA descriptor preparation helper functions
  * (i.e. read_reg_dma/write_reg_dma/read_data_dma/write_data_dma)
@@ -245,6 +247,11 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
  * @tx_sgl_start - start index in data sgl for tx.
  * @rx_sgl_pos - current index in data sgl for rx.
  * @rx_sgl_start - start index in data sgl for rx.
+ * @wait_second_completion - wait for second DMA desc completion before making
+ *			     the NAND transfer completion.
+ * @txn_done - completion for NAND transfer.
+ * @last_data_desc - last DMA desc in data channel (tx/rx).
+ * @last_cmd_desc - last DMA desc in command channel.
  */
 struct bam_transaction {
 	struct bam_cmd_element *bam_ce;
@@ -258,6 +265,10 @@ struct bam_transaction {
 	u32 tx_sgl_start;
 	u32 rx_sgl_pos;
 	u32 rx_sgl_start;
+	bool wait_second_completion;
+	struct completion txn_done;
+	struct dma_async_tx_descriptor *last_data_desc;
+	struct dma_async_tx_descriptor *last_cmd_desc;
 };
 
 /*
@@ -354,7 +365,7 @@ struct nandc_regs {
  *				from all connected NAND devices pagesize
  */
 struct qcom_nand_controller {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct list_head host_list;
 
 	struct device *dev;
@@ -504,6 +515,8 @@ alloc_bam_transaction(struct qcom_nand_controller *nandc)
 
 	bam_txn->data_sgl = bam_txn_buf;
 
+	init_completion(&bam_txn->txn_done);
+
 	return bam_txn;
 }
 
@@ -523,11 +536,33 @@ static void clear_bam_transaction(struct qcom_nand_controller *nandc)
 	bam_txn->tx_sgl_start = 0;
 	bam_txn->rx_sgl_pos = 0;
 	bam_txn->rx_sgl_start = 0;
+	bam_txn->last_data_desc = NULL;
+	bam_txn->wait_second_completion = false;
 
 	sg_init_table(bam_txn->cmd_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_CMD_SGL);
 	sg_init_table(bam_txn->data_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_DATA_SGL);
+
+	reinit_completion(&bam_txn->txn_done);
+}
+
+/* Callback for DMA descriptor completion */
+static void qpic_bam_dma_done(void *data)
+{
+	struct bam_transaction *bam_txn = data;
+
+	/*
+	 * In case of data transfer with NAND, 2 callbacks will be generated.
+	 * One for command channel and another one for data channel.
+	 * If current transaction has data descriptors
+	 * (i.e. wait_second_completion is true), then set this to false
+	 * and wait for second DMA descriptor completion.
+	 */
+	if (bam_txn->wait_second_completion)
+		bam_txn->wait_second_completion = false;
+	else
+		complete(&bam_txn->txn_done);
 }
 
 static inline struct qcom_nand_host *to_qcom_nand_host(struct nand_chip *chip)
@@ -756,6 +791,12 @@ static int prepare_bam_async_desc(struct qcom_nand_controller *nandc,
 
 	desc->dma_desc = dma_desc;
 
+	/* update last data/command descriptor */
+	if (chan == nandc->cmd_chan)
+		bam_txn->last_cmd_desc = dma_desc;
+	else
+		bam_txn->last_data_desc = dma_desc;
+
 	list_add_tail(&desc->node, &nandc->desc_list);
 
 	return 0;
@@ -1055,7 +1096,8 @@ static void config_nand_page_read(struct qcom_nand_controller *nandc)
  * Helper to prepare DMA descriptors for configuring registers
  * before reading each codeword in NAND page.
  */
-static void config_nand_cw_read(struct qcom_nand_controller *nandc)
+static void
+config_nand_cw_read(struct qcom_nand_controller *nandc, bool use_ecc)
 {
 	if (nandc->props->is_bam)
 		write_reg_dma(nandc, NAND_READ_LOCATION_0, 4,
@@ -1064,19 +1106,25 @@ static void config_nand_cw_read(struct qcom_nand_controller *nandc)
 	write_reg_dma(nandc, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL);
 	write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL);
 
-	read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0);
-	read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1,
-		     NAND_BAM_NEXT_SGL);
+	if (use_ecc) {
+		read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0);
+		read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1,
+			     NAND_BAM_NEXT_SGL);
+	} else {
+		read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL);
+	}
 }
 
 /*
  * Helper to prepare dma descriptors to configure registers needed for reading a
  * single codeword in page
  */
-static void config_nand_single_cw_page_read(struct qcom_nand_controller *nandc)
+static void
+config_nand_single_cw_page_read(struct qcom_nand_controller *nandc,
+				bool use_ecc)
 {
 	config_nand_page_read(nandc);
-	config_nand_cw_read(nandc);
+	config_nand_cw_read(nandc, use_ecc);
 }
 
 /*
@@ -1157,7 +1205,7 @@ static int nandc_param(struct qcom_nand_host *host)
 	nandc->buf_count = 512;
 	memset(nandc->data_buffer, 0xff, nandc->buf_count);
 
-	config_nand_single_cw_page_read(nandc);
+	config_nand_single_cw_page_read(nandc, false);
 
 	read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer,
 		      nandc->buf_count, 0);
@@ -1273,10 +1321,20 @@ static int submit_descs(struct qcom_nand_controller *nandc)
 		cookie = dmaengine_submit(desc->dma_desc);
 
 	if (nandc->props->is_bam) {
+		bam_txn->last_cmd_desc->callback = qpic_bam_dma_done;
+		bam_txn->last_cmd_desc->callback_param = bam_txn;
+		if (bam_txn->last_data_desc) {
+			bam_txn->last_data_desc->callback = qpic_bam_dma_done;
+			bam_txn->last_data_desc->callback_param = bam_txn;
+			bam_txn->wait_second_completion = true;
+		}
+
 		dma_async_issue_pending(nandc->tx_chan);
 		dma_async_issue_pending(nandc->rx_chan);
+		dma_async_issue_pending(nandc->cmd_chan);
 
-		if (dma_sync_wait(nandc->cmd_chan, cookie) != DMA_COMPLETE)
+		if (!wait_for_completion_timeout(&bam_txn->txn_done,
+						 QPIC_NAND_COMPLETION_TIMEOUT))
 			return -ETIMEDOUT;
 	} else {
 		if (dma_sync_wait(nandc->chan, cookie) != DMA_COMPLETE)
@@ -1512,20 +1570,180 @@ struct read_stats {
 	__le32 erased_cw;
 };
 
+/* reads back FLASH_STATUS register set by the controller */
+static int check_flash_errors(struct qcom_nand_host *host, int cw_cnt)
+{
+	struct nand_chip *chip = &host->chip;
+	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
+	int i;
+
+	for (i = 0; i < cw_cnt; i++) {
+		u32 flash = le32_to_cpu(nandc->reg_read_buf[i]);
+
+		if (flash & (FS_OP_ERR | FS_MPU_ERR))
+			return -EIO;
+	}
+
+	return 0;
+}
+
+/* performs raw read for one codeword */
+static int
+qcom_nandc_read_cw_raw(struct mtd_info *mtd, struct nand_chip *chip,
+		       u8 *data_buf, u8 *oob_buf, int page, int cw)
+{
+	struct qcom_nand_host *host = to_qcom_nand_host(chip);
+	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	int data_size1, data_size2, oob_size1, oob_size2;
+	int ret, reg_off = FLASH_BUF_ACC, read_loc = 0;
+
+	nand_read_page_op(chip, page, 0, NULL, 0);
+	host->use_ecc = false;
+
+	clear_bam_transaction(nandc);
+	set_address(host, host->cw_size * cw, page);
+	update_rw_regs(host, 1, true);
+	config_nand_page_read(nandc);
+
+	data_size1 = mtd->writesize - host->cw_size * (ecc->steps - 1);
+	oob_size1 = host->bbm_size;
+
+	if (cw == (ecc->steps - 1)) {
+		data_size2 = ecc->size - data_size1 -
+			     ((ecc->steps - 1) * 4);
+		oob_size2 = (ecc->steps * 4) + host->ecc_bytes_hw +
+			    host->spare_bytes;
+	} else {
+		data_size2 = host->cw_data - data_size1;
+		oob_size2 = host->ecc_bytes_hw + host->spare_bytes;
+	}
+
+	if (nandc->props->is_bam) {
+		nandc_set_read_loc(nandc, 0, read_loc, data_size1, 0);
+		read_loc += data_size1;
+
+		nandc_set_read_loc(nandc, 1, read_loc, oob_size1, 0);
+		read_loc += oob_size1;
+
+		nandc_set_read_loc(nandc, 2, read_loc, data_size2, 0);
+		read_loc += data_size2;
+
+		nandc_set_read_loc(nandc, 3, read_loc, oob_size2, 1);
+	}
+
+	config_nand_cw_read(nandc, false);
+
+	read_data_dma(nandc, reg_off, data_buf, data_size1, 0);
+	reg_off += data_size1;
+
+	read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0);
+	reg_off += oob_size1;
+
+	read_data_dma(nandc, reg_off, data_buf + data_size1, data_size2, 0);
+	reg_off += data_size2;
+
+	read_data_dma(nandc, reg_off, oob_buf + oob_size1, oob_size2, 0);
+
+	ret = submit_descs(nandc);
+	free_descs(nandc);
+	if (ret) {
+		dev_err(nandc->dev, "failure to read raw cw %d\n", cw);
+		return ret;
+	}
+
+	return check_flash_errors(host, 1);
+}
+
+/*
+ * Bitflips can happen in erased codewords also so this function counts the
+ * number of 0 in each CW for which ECC engine returns the uncorrectable
+ * error. The page will be assumed as erased if this count is less than or
+ * equal to the ecc->strength for each CW.
+ *
+ * 1. Both DATA and OOB need to be checked for number of 0. The
+ *    top-level API can be called with only data buf or OOB buf so use
+ *    chip->data_buf if data buf is null and chip->oob_poi if oob buf
+ *    is null for copying the raw bytes.
+ * 2. Perform raw read for all the CW which has uncorrectable errors.
+ * 3. For each CW, check the number of 0 in cw_data and usable OOB bytes.
+ *    The BBM and spare bytes bit flip won’t affect the ECC so don’t check
+ *    the number of bitflips in this area.
+ */
+static int
+check_for_erased_page(struct qcom_nand_host *host, u8 *data_buf,
+		      u8 *oob_buf, unsigned long uncorrectable_cws,
+		      int page, unsigned int max_bitflips)
+{
+	struct nand_chip *chip = &host->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	u8 *cw_data_buf, *cw_oob_buf;
+	int cw, data_size, oob_size, ret = 0;
+
+	if (!data_buf) {
+		data_buf = chip->data_buf;
+		chip->pagebuf = -1;
+	}
+
+	if (!oob_buf) {
+		oob_buf = chip->oob_poi;
+		chip->pagebuf = -1;
+	}
+
+	for_each_set_bit(cw, &uncorrectable_cws, ecc->steps) {
+		if (cw == (ecc->steps - 1)) {
+			data_size = ecc->size - ((ecc->steps - 1) * 4);
+			oob_size = (ecc->steps * 4) + host->ecc_bytes_hw;
+		} else {
+			data_size = host->cw_data;
+			oob_size = host->ecc_bytes_hw;
+		}
+
+		/* determine starting buffer address for current CW */
+		cw_data_buf = data_buf + (cw * host->cw_data);
+		cw_oob_buf = oob_buf + (cw * ecc->bytes);
+
+		ret = qcom_nandc_read_cw_raw(mtd, chip, cw_data_buf,
+					     cw_oob_buf, page, cw);
+		if (ret)
+			return ret;
+
+		/*
+		 * make sure it isn't an erased page reported
+		 * as not-erased by HW because of a few bitflips
+		 */
+		ret = nand_check_erased_ecc_chunk(cw_data_buf, data_size,
+						  cw_oob_buf + host->bbm_size,
+						  oob_size, NULL,
+						  0, ecc->strength);
+		if (ret < 0) {
+			mtd->ecc_stats.failed++;
+		} else {
+			mtd->ecc_stats.corrected += ret;
+			max_bitflips = max_t(unsigned int, max_bitflips, ret);
+		}
+	}
+
+	return max_bitflips;
+}
+
 /*
  * reads back status registers set by the controller to notify page read
  * errors. this is equivalent to what 'ecc->correct()' would do.
  */
 static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
-			     u8 *oob_buf)
+			     u8 *oob_buf, int page)
 {
 	struct nand_chip *chip = &host->chip;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	unsigned int max_bitflips = 0;
+	unsigned int max_bitflips = 0, uncorrectable_cws = 0;
 	struct read_stats *buf;
+	bool flash_op_err = false, erased;
 	int i;
+	u8 *data_buf_start = data_buf, *oob_buf_start = oob_buf;
 
 	buf = (struct read_stats *)nandc->reg_read_buf;
 	nandc_read_buffer_sync(nandc, true);
@@ -1546,48 +1764,49 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 		buffer = le32_to_cpu(buf->buffer);
 		erased_cw = le32_to_cpu(buf->erased_cw);
 
-		if (flash & (FS_OP_ERR | FS_MPU_ERR)) {
-			bool erased;
-
-			/* ignore erased codeword errors */
+		/*
+		 * Check ECC failure for each codeword. ECC failure can
+		 * happen in either of the following conditions
+		 * 1. If number of bitflips are greater than ECC engine
+		 *    capability.
+		 * 2. If this codeword contains all 0xff for which erased
+		 *    codeword detection check will be done.
+		 */
+		if ((flash & FS_OP_ERR) && (buffer & BS_UNCORRECTABLE_BIT)) {
+			/*
+			 * For BCH ECC, ignore erased codeword errors, if
+			 * ERASED_CW bits are set.
+			 */
 			if (host->bch_enabled) {
 				erased = (erased_cw & ERASED_CW) == ERASED_CW ?
 					 true : false;
-			} else {
+			/*
+			 * For RS ECC, HW reports the erased CW by placing
+			 * special characters at certain offsets in the buffer.
+			 * These special characters will be valid only if
+			 * complete page is read i.e. data_buf is not NULL.
+			 */
+			} else if (data_buf) {
 				erased = erased_chunk_check_and_fixup(data_buf,
 								      data_len);
+			} else {
+				erased = false;
 			}
 
-			if (erased) {
-				data_buf += data_len;
-				if (oob_buf)
-					oob_buf += oob_len + ecc->bytes;
-				continue;
-			}
-
-			if (buffer & BS_UNCORRECTABLE_BIT) {
-				int ret, ecclen, extraooblen;
-				void *eccbuf;
-
-				eccbuf = oob_buf ? oob_buf + oob_len : NULL;
-				ecclen = oob_buf ? host->ecc_bytes_hw : 0;
-				extraooblen = oob_buf ? oob_len : 0;
-
-				/*
-				 * make sure it isn't an erased page reported
-				 * as not-erased by HW because of a few bitflips
-				 */
-				ret = nand_check_erased_ecc_chunk(data_buf,
-					data_len, eccbuf, ecclen, oob_buf,
-					extraooblen, ecc->strength);
-				if (ret < 0) {
-					mtd->ecc_stats.failed++;
-				} else {
-					mtd->ecc_stats.corrected += ret;
-					max_bitflips =
-						max_t(unsigned int, max_bitflips, ret);
-				}
-			}
+			if (!erased)
+				uncorrectable_cws |= BIT(i);
+		/*
+		 * Check if MPU or any other operational error (timeout,
+		 * device failure, etc.) happened for this codeword and
+		 * make flash_op_err true. If flash_op_err is set, then
+		 * EIO will be returned for page read.
+		 */
+		} else if (flash & (FS_OP_ERR | FS_MPU_ERR)) {
+			flash_op_err = true;
+		/*
+		 * No ECC or operational errors happened. Check the number of
+		 * bits corrected and update the ecc_stats.corrected.
+		 */
 		} else {
 			unsigned int stat;
 
@@ -1596,12 +1815,21 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 			max_bitflips = max(max_bitflips, stat);
 		}
 
-		data_buf += data_len;
+		if (data_buf)
+			data_buf += data_len;
 		if (oob_buf)
 			oob_buf += oob_len + ecc->bytes;
 	}
 
-	return max_bitflips;
+	if (flash_op_err)
+		return -EIO;
+
+	if (!uncorrectable_cws)
+		return max_bitflips;
+
+	return check_for_erased_page(host, data_buf_start, oob_buf_start,
+				     uncorrectable_cws, page,
+				     max_bitflips);
 }
 
 /*
@@ -1609,11 +1837,12 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
  * ecc->read_oob()
  */
 static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
-			 u8 *oob_buf)
+			 u8 *oob_buf, int page)
 {
 	struct nand_chip *chip = &host->chip;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	u8 *data_buf_start = data_buf, *oob_buf_start = oob_buf;
 	int i, ret;
 
 	config_nand_page_read(nandc);
@@ -1644,7 +1873,7 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 			}
 		}
 
-		config_nand_cw_read(nandc);
+		config_nand_cw_read(nandc, true);
 
 		if (data_buf)
 			read_data_dma(nandc, FLASH_BUF_ACC, data_buf,
@@ -1674,12 +1903,14 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 	}
 
 	ret = submit_descs(nandc);
-	if (ret)
-		dev_err(nandc->dev, "failure to read page/oob\n");
-
 	free_descs(nandc);
 
-	return ret;
+	if (ret) {
+		dev_err(nandc->dev, "failure to read page/oob\n");
+		return ret;
+	}
+
+	return parse_read_errors(host, data_buf_start, oob_buf_start, page);
 }
 
 /*
@@ -1704,7 +1935,7 @@ static int copy_last_cw(struct qcom_nand_host *host, int page)
 	set_address(host, host->cw_size * (ecc->steps - 1), page);
 	update_rw_regs(host, 1, true);
 
-	config_nand_single_cw_page_read(nandc);
+	config_nand_single_cw_page_read(nandc, host->use_ecc);
 
 	read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer, size, 0);
 
@@ -1724,20 +1955,14 @@ static int qcom_nandc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	u8 *data_buf, *oob_buf = NULL;
-	int ret;
 
 	nand_read_page_op(chip, page, 0, NULL, 0);
 	data_buf = buf;
 	oob_buf = oob_required ? chip->oob_poi : NULL;
 
 	clear_bam_transaction(nandc);
-	ret = read_page_ecc(host, data_buf, oob_buf);
-	if (ret) {
-		dev_err(nandc->dev, "failure to read page\n");
-		return ret;
-	}
 
-	return parse_read_errors(host, data_buf, oob_buf);
+	return read_page_ecc(host, data_buf, oob_buf, page);
 }
 
 /* implements ecc->read_page_raw() */
@@ -1746,77 +1971,20 @@ static int qcom_nandc_read_page_raw(struct mtd_info *mtd,
 				    int oob_required, int page)
 {
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
-	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
-	u8 *data_buf, *oob_buf;
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int i, ret;
-	int read_loc;
-
-	nand_read_page_op(chip, page, 0, NULL, 0);
-	data_buf = buf;
-	oob_buf = chip->oob_poi;
-
-	host->use_ecc = false;
+	int cw, ret;
+	u8 *data_buf = buf, *oob_buf = chip->oob_poi;
 
-	clear_bam_transaction(nandc);
-	update_rw_regs(host, ecc->steps, true);
-	config_nand_page_read(nandc);
-
-	for (i = 0; i < ecc->steps; i++) {
-		int data_size1, data_size2, oob_size1, oob_size2;
-		int reg_off = FLASH_BUF_ACC;
-
-		data_size1 = mtd->writesize - host->cw_size * (ecc->steps - 1);
-		oob_size1 = host->bbm_size;
-
-		if (i == (ecc->steps - 1)) {
-			data_size2 = ecc->size - data_size1 -
-				     ((ecc->steps - 1) << 2);
-			oob_size2 = (ecc->steps << 2) + host->ecc_bytes_hw +
-				    host->spare_bytes;
-		} else {
-			data_size2 = host->cw_data - data_size1;
-			oob_size2 = host->ecc_bytes_hw + host->spare_bytes;
-		}
-
-		if (nandc->props->is_bam) {
-			read_loc = 0;
-			nandc_set_read_loc(nandc, 0, read_loc, data_size1, 0);
-			read_loc += data_size1;
-
-			nandc_set_read_loc(nandc, 1, read_loc, oob_size1, 0);
-			read_loc += oob_size1;
-
-			nandc_set_read_loc(nandc, 2, read_loc, data_size2, 0);
-			read_loc += data_size2;
-
-			nandc_set_read_loc(nandc, 3, read_loc, oob_size2, 1);
-		}
-
-		config_nand_cw_read(nandc);
-
-		read_data_dma(nandc, reg_off, data_buf, data_size1, 0);
-		reg_off += data_size1;
-		data_buf += data_size1;
-
-		read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0);
-		reg_off += oob_size1;
-		oob_buf += oob_size1;
-
-		read_data_dma(nandc, reg_off, data_buf, data_size2, 0);
-		reg_off += data_size2;
-		data_buf += data_size2;
+	for (cw = 0; cw < ecc->steps; cw++) {
+		ret = qcom_nandc_read_cw_raw(mtd, chip, data_buf, oob_buf,
+					     page, cw);
+		if (ret)
+			return ret;
 
-		read_data_dma(nandc, reg_off, oob_buf, oob_size2, 0);
-		oob_buf += oob_size2;
+		data_buf += host->cw_data;
+		oob_buf += ecc->bytes;
 	}
 
-	ret = submit_descs(nandc);
-	if (ret)
-		dev_err(nandc->dev, "failure to read raw page\n");
-
-	free_descs(nandc);
-
 	return 0;
 }
 
@@ -1827,7 +1995,6 @@ static int qcom_nandc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int ret;
 
 	clear_read_regs(nandc);
 	clear_bam_transaction(nandc);
@@ -1836,11 +2003,7 @@ static int qcom_nandc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	set_address(host, 0, page);
 	update_rw_regs(host, ecc->steps, true);
 
-	ret = read_page_ecc(host, NULL, chip->oob_poi);
-	if (ret)
-		dev_err(nandc->dev, "failure to read oob\n");
-
-	return ret;
+	return read_page_ecc(host, NULL, chip->oob_poi, page);
 }
 
 /* implements ecc->write_page() */
@@ -1988,11 +2151,9 @@ static int qcom_nandc_write_page_raw(struct mtd_info *mtd,
 /*
  * implements ecc->write_oob()
  *
- * the NAND controller cannot write only data or only oob within a codeword,
- * since ecc is calculated for the combined codeword. we first copy the
- * entire contents for the last codeword(data + oob), replace the old oob
- * with the new one in chip->oob_poi, and then write the entire codeword.
- * this read-copy-write operation results in a slight performance loss.
+ * the NAND controller cannot write only data or only OOB within a codeword
+ * since ECC is calculated for the combined codeword. So update the OOB from
+ * chip->oob_poi, and pad the data area with OxFF before writing.
  */
 static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
 				int page)
@@ -2005,19 +2166,13 @@ static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	int ret;
 
 	host->use_ecc = true;
-
-	clear_bam_transaction(nandc);
-	ret = copy_last_cw(host, page);
-	if (ret)
-		return ret;
-
-	clear_read_regs(nandc);
 	clear_bam_transaction(nandc);
 
 	/* calculate the data and oob size for the last codeword/step */
 	data_size = ecc->size - ((ecc->steps - 1) << 2);
 	oob_size = mtd->oobavail;
 
+	memset(nandc->data_buffer, 0xff, host->cw_data);
 	/* override new oob content to last codeword */
 	mtd_ooblayout_get_databytes(mtd, nandc->data_buffer + data_size, oob,
 				    0, mtd->oobavail);
@@ -2049,7 +2204,6 @@ static int qcom_nandc_block_bad(struct mtd_info *mtd, loff_t ofs)
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	int page, ret, bbpos, bad = 0;
-	u32 flash_status;
 
 	page = (int)(ofs >> chip->page_shift) & chip->pagemask;
 
@@ -2066,9 +2220,7 @@ static int qcom_nandc_block_bad(struct mtd_info *mtd, loff_t ofs)
 	if (ret)
 		goto err;
 
-	flash_status = le32_to_cpu(nandc->reg_read_buf[0]);
-
-	if (flash_status & (FS_OP_ERR | FS_MPU_ERR)) {
+	if (check_flash_errors(host, 1)) {
 		dev_warn(nandc->dev, "error when trying to read BBM\n");
 		goto err;
 	}
@@ -2315,27 +2467,40 @@ static const struct mtd_ooblayout_ops qcom_nand_ooblayout_ops = {
 	.free = qcom_nand_ooblayout_free,
 };
 
-static int qcom_nand_host_setup(struct qcom_nand_host *host)
+static int
+qcom_nandc_calc_ecc_bytes(int step_size, int strength)
+{
+	return strength == 4 ? 12 : 16;
+}
+NAND_ECC_CAPS_SINGLE(qcom_nandc_ecc_caps, qcom_nandc_calc_ecc_bytes,
+		     NANDC_STEP_SIZE, 4, 8);
+
+static int qcom_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &host->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
-	int cwperpage, bad_block_byte;
+	int cwperpage, bad_block_byte, ret;
 	bool wide_bus;
 	int ecc_mode = 1;
 
+	/* controller only supports 512 bytes data steps */
+	ecc->size = NANDC_STEP_SIZE;
+	wide_bus = chip->options & NAND_BUSWIDTH_16 ? true : false;
+	cwperpage = mtd->writesize / NANDC_STEP_SIZE;
+
 	/*
-	 * the controller requires each step consists of 512 bytes of data.
-	 * bail out if DT has populated a wrong step size.
+	 * Each CW has 4 available OOB bytes which will be protected with ECC
+	 * so remaining bytes can be used for ECC.
 	 */
-	if (ecc->size != NANDC_STEP_SIZE) {
-		dev_err(nandc->dev, "invalid ecc size\n");
-		return -EINVAL;
+	ret = nand_ecc_choose_conf(chip, &qcom_nandc_ecc_caps,
+				   mtd->oobsize - (cwperpage * 4));
+	if (ret) {
+		dev_err(nandc->dev, "No valid ECC settings possible\n");
+		return ret;
 	}
 
-	wide_bus = chip->options & NAND_BUSWIDTH_16 ? true : false;
-
 	if (ecc->strength >= 8) {
 		/* 8 bit ECC defaults to BCH ECC on all platforms */
 		host->bch_enabled = true;
@@ -2403,7 +2568,6 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 
 	mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops);
 
-	cwperpage = mtd->writesize / ecc->size;
 	nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage,
 				     cwperpage);
 
@@ -2419,12 +2583,6 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 	 * for 8 bit ECC
 	 */
 	host->cw_size = host->cw_data + ecc->bytes;
-
-	if (ecc->bytes * (mtd->writesize / ecc->size) > mtd->oobsize) {
-		dev_err(nandc->dev, "ecc data doesn't fit in OOB area\n");
-		return -EINVAL;
-	}
-
 	bad_block_byte = mtd->writesize - host->cw_size * (cwperpage - 1) + 1;
 
 	host->cfg0 = (cwperpage - 1) << CW_PER_PAGE
@@ -2482,6 +2640,10 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 	return 0;
 }
 
+static const struct nand_controller_ops qcom_nandc_ops = {
+	.attach_chip = qcom_nand_attach_chip,
+};
+
 static int qcom_nandc_alloc(struct qcom_nand_controller *nandc)
 {
 	int ret;
@@ -2570,7 +2732,8 @@ static int qcom_nandc_alloc(struct qcom_nand_controller *nandc)
 	INIT_LIST_HEAD(&nandc->desc_list);
 	INIT_LIST_HEAD(&nandc->host_list);
 
-	nand_hw_control_init(&nandc->controller);
+	nand_controller_init(&nandc->controller);
+	nandc->controller.ops = &qcom_nandc_ops;
 
 	return 0;
 }
@@ -2623,9 +2786,9 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc)
 	return 0;
 }
 
-static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
-			       struct qcom_nand_host *host,
-			       struct device_node *dn)
+static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc,
+					    struct qcom_nand_host *host,
+					    struct device_node *dn)
 {
 	struct nand_chip *chip = &host->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
@@ -2672,30 +2835,13 @@ static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
 	/* set up initial status value */
 	host->status = NAND_STATUS_READY | NAND_STATUS_WP;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	ret = qcom_nand_host_setup(host);
-
-	return ret;
-}
-
-static int qcom_nand_mtd_register(struct qcom_nand_controller *nandc,
-				  struct qcom_nand_host *host,
-				  struct device_node *dn)
-{
-	struct nand_chip *chip = &host->chip;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	int ret;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret)
-		nand_cleanup(mtd_to_nand(mtd));
+		nand_cleanup(chip);
 
 	return ret;
 }
@@ -2704,28 +2850,9 @@ static int qcom_probe_nand_devices(struct qcom_nand_controller *nandc)
 {
 	struct device *dev = nandc->dev;
 	struct device_node *dn = dev->of_node, *child;
-	struct qcom_nand_host *host, *tmp;
+	struct qcom_nand_host *host;
 	int ret;
 
-	for_each_available_child_of_node(dn, child) {
-		host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
-		if (!host) {
-			of_node_put(child);
-			return -ENOMEM;
-		}
-
-		ret = qcom_nand_host_init(nandc, host, child);
-		if (ret) {
-			devm_kfree(dev, host);
-			continue;
-		}
-
-		list_add_tail(&host->node, &nandc->host_list);
-	}
-
-	if (list_empty(&nandc->host_list))
-		return -ENODEV;
-
 	if (nandc->props->is_bam) {
 		free_bam_transaction(nandc);
 		nandc->bam_txn = alloc_bam_transaction(nandc);
@@ -2736,12 +2863,20 @@ static int qcom_probe_nand_devices(struct qcom_nand_controller *nandc)
 		}
 	}
 
-	list_for_each_entry_safe(host, tmp, &nandc->host_list, node) {
-		ret = qcom_nand_mtd_register(nandc, host, child);
+	for_each_available_child_of_node(dn, child) {
+		host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+		if (!host) {
+			of_node_put(child);
+			return -ENOMEM;
+		}
+
+		ret = qcom_nand_host_init_and_register(nandc, host, child);
 		if (ret) {
-			list_del(&host->node);
 			devm_kfree(dev, host);
+			continue;
 		}
+
+		list_add_tail(&host->node, &nandc->host_list);
 	}
 
 	if (list_empty(&nandc->host_list))
@@ -2799,14 +2934,6 @@ static int qcom_nandc_probe(struct platform_device *pdev)
 
 	nandc->props = dev_data;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	nandc->base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(nandc->base))
-		return PTR_ERR(nandc->base);
-
-	nandc->base_phys = res->start;
-	nandc->base_dma = phys_to_dma(dev, (phys_addr_t)res->start);
-
 	nandc->core_clk = devm_clk_get(dev, "core");
 	if (IS_ERR(nandc->core_clk))
 		return PTR_ERR(nandc->core_clk);
@@ -2819,9 +2946,21 @@ static int qcom_nandc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	nandc->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(nandc->base))
+		return PTR_ERR(nandc->base);
+
+	nandc->base_phys = res->start;
+	nandc->base_dma = dma_map_resource(dev, res->start,
+					   resource_size(res),
+					   DMA_BIDIRECTIONAL, 0);
+	if (!nandc->base_dma)
+		return -ENXIO;
+
 	ret = qcom_nandc_alloc(nandc);
 	if (ret)
-		goto err_core_clk;
+		goto err_nandc_alloc;
 
 	ret = clk_prepare_enable(nandc->core_clk);
 	if (ret)
@@ -2847,6 +2986,9 @@ err_aon_clk:
 	clk_disable_unprepare(nandc->core_clk);
 err_core_clk:
 	qcom_nandc_unalloc(nandc);
+err_nandc_alloc:
+	dma_unmap_resource(dev, res->start, resource_size(res),
+			   DMA_BIDIRECTIONAL, 0);
 
 	return ret;
 }
@@ -2854,16 +2996,21 @@ err_core_clk:
 static int qcom_nandc_remove(struct platform_device *pdev)
 {
 	struct qcom_nand_controller *nandc = platform_get_drvdata(pdev);
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	struct qcom_nand_host *host;
 
 	list_for_each_entry(host, &nandc->host_list, node)
 		nand_release(nand_to_mtd(&host->chip));
 
+
 	qcom_nandc_unalloc(nandc);
 
 	clk_disable_unprepare(nandc->aon_clk);
 	clk_disable_unprepare(nandc->core_clk);
 
+	dma_unmap_resource(&pdev->dev, nandc->base_dma, resource_size(res),
+			   DMA_BIDIRECTIONAL, 0);
+
 	return 0;
 }
 
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 19661c5d3220..c21e8892394a 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -162,7 +162,7 @@ enum s3c_nand_clk_state {
  */
 struct s3c2410_nand_info {
 	/* mtd info */
-	struct nand_hw_control		controller;
+	struct nand_controller		controller;
 	struct s3c2410_nand_mtd		*mtds;
 	struct s3c2410_platform_nand	*platform;
 
@@ -802,8 +802,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 
 		mtdinfo->name = set->name;
 
-		return mtd_device_parse_register(mtdinfo, NULL, NULL,
-					 set->partitions, set->nr_partitions);
+		return mtd_device_register(mtdinfo, set->partitions,
+					   set->nr_partitions);
 	}
 
 	return -ENODEV;
@@ -915,20 +915,19 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info,
 }
 
 /**
- * s3c2410_nand_update_chip - post probe update
- * @info: The controller instance.
- * @nmtd: The driver version of the MTD instance.
+ * s3c2410_nand_attach_chip - Init the ECC engine after NAND scan
+ * @chip: The NAND chip
  *
- * This routine is called after the chip probe has successfully completed
- * and the relevant per-chip information updated. This call ensure that
+ * This hook is called by the core after the identification of the NAND chip,
+ * once the relevant per-chip information is up to date.. This call ensure that
  * we update the internal state accordingly.
  *
  * The internal state is currently limited to the ECC state information.
 */
-static int s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
-				    struct s3c2410_nand_mtd *nmtd)
+static int s3c2410_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nmtd->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd);
 
 	switch (chip->ecc.mode) {
 
@@ -998,6 +997,10 @@ static int s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
 	return 0;
 }
 
+static const struct nand_controller_ops s3c24xx_nand_controller_ops = {
+	.attach_chip = s3c2410_nand_attach_chip,
+};
+
 static const struct of_device_id s3c24xx_nand_dt_ids[] = {
 	{
 		.compatible = "samsung,s3c2410-nand",
@@ -1094,7 +1097,8 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, info);
 
-	nand_hw_control_init(&info->controller);
+	nand_controller_init(&info->controller);
+	info->controller.ops = &s3c24xx_nand_controller_ops;
 
 	/* get the clock source and enable it */
 
@@ -1134,8 +1138,13 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "mapped registers at %p\n", info->regs);
 
-	sets = (plat != NULL) ? plat->sets : NULL;
-	nr_sets = (plat != NULL) ? plat->nr_sets : 1;
+	if (!plat->sets || plat->nr_sets < 1) {
+		err = -EINVAL;
+		goto exit_error;
+	}
+
+	sets = plat->sets;
+	nr_sets = plat->nr_sets;
 
 	info->mtd_count = nr_sets;
 
@@ -1152,7 +1161,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	nmtd = info->mtds;
 
-	for (setno = 0; setno < nr_sets; setno++, nmtd++) {
+	for (setno = 0; setno < nr_sets; setno++, nmtd++, sets++) {
 		struct mtd_info *mtd = nand_to_mtd(&nmtd->chip);
 
 		pr_debug("initialising set %d (%p, info %p)\n",
@@ -1161,22 +1170,11 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 		mtd->dev.parent = &pdev->dev;
 		s3c2410_nand_init_chip(info, nmtd, sets);
 
-		err = nand_scan_ident(mtd, (sets) ? sets->nr_chips : 1, NULL);
-		if (err)
-			goto exit_error;
-
-		err = s3c2410_nand_update_chip(info, nmtd);
-		if (err < 0)
-			goto exit_error;
-
-		err = nand_scan_tail(mtd);
+		err = nand_scan(mtd, sets ? sets->nr_chips : 1);
 		if (err)
 			goto exit_error;
 
 		s3c2410_nand_add_partition(info, nmtd, sets);
-
-		if (sets != NULL)
-			sets++;
 	}
 
 	/* initialise the hardware */
diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c
index c7abceffcc40..bb8866e05ff7 100644
--- a/drivers/mtd/nand/raw/sh_flctl.c
+++ b/drivers/mtd/nand/raw/sh_flctl.c
@@ -1002,10 +1002,17 @@ static void flctl_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	flctl->index += len;
 }
 
-static int flctl_chip_init_tail(struct mtd_info *mtd)
+static int flctl_chip_attach_chip(struct nand_chip *chip)
 {
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
-	struct nand_chip *chip = &flctl->chip;
+
+	/*
+	 * NAND_BUSWIDTH_16 may have been set by nand_scan_ident().
+	 * Add the SEL_16BIT flag in flctl->flcmncr_base.
+	 */
+	if (chip->options & NAND_BUSWIDTH_16)
+		flctl->flcmncr_base |= SEL_16BIT;
 
 	if (mtd->writesize == 512) {
 		flctl->page_size = 0;
@@ -1063,6 +1070,10 @@ static int flctl_chip_init_tail(struct mtd_info *mtd)
 	return 0;
 }
 
+static const struct nand_controller_ops flctl_nand_controller_ops = {
+	.attach_chip = flctl_chip_attach_chip,
+};
+
 static irqreturn_t flctl_handle_flste(int irq, void *dev_id)
 {
 	struct sh_flctl *flctl = dev_id;
@@ -1191,25 +1202,8 @@ static int flctl_probe(struct platform_device *pdev)
 
 	flctl_setup_dma(flctl);
 
-	ret = nand_scan_ident(flctl_mtd, 1, NULL);
-	if (ret)
-		goto err_chip;
-
-	if (nand->options & NAND_BUSWIDTH_16) {
-		/*
-		 * NAND_BUSWIDTH_16 may have been set by nand_scan_ident().
-		 * Add the SEL_16BIT flag in pdata->flcmncr_val and re-assign
-		 * flctl->flcmncr_base to pdata->flcmncr_val.
-		 */
-		pdata->flcmncr_val |= SEL_16BIT;
-		flctl->flcmncr_base = pdata->flcmncr_val;
-	}
-
-	ret = flctl_chip_init_tail(flctl_mtd);
-	if (ret)
-		goto err_chip;
-
-	ret = nand_scan_tail(flctl_mtd);
+	nand->dummy_controller.ops = &flctl_nand_controller_ops;
+	ret = nand_scan(flctl_mtd, 1);
 	if (ret)
 		goto err_chip;
 
diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index e93df02c825e..fc171b17a39b 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -21,10 +21,7 @@
 #include <linux/mtd/sharpsl.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
-
-#include <asm/io.h>
-#include <mach/hardware.h>
-#include <asm/mach-types.h>
+#include <linux/io.h>
 
 struct sharpsl_nand {
 	struct nand_chip	chip;
diff --git a/drivers/mtd/nand/raw/sm_common.c b/drivers/mtd/nand/raw/sm_common.c
index 7f5044a79f01..73aafe8c3ef3 100644
--- a/drivers/mtd/nand/raw/sm_common.c
+++ b/drivers/mtd/nand/raw/sm_common.c
@@ -160,19 +160,9 @@ static struct nand_flash_dev nand_xd_flash_ids[] = {
 	{NULL}
 };
 
-int sm_register_device(struct mtd_info *mtd, int smartmedia)
+static int sm_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	int ret;
-
-	chip->options |= NAND_SKIP_BBTSCAN;
-
-	/* Scan for card properties */
-	ret = nand_scan_ident(mtd, 1, smartmedia ?
-		nand_smartmedia_flash_ids : nand_xd_flash_ids);
-
-	if (ret)
-		return ret;
+	struct mtd_info *mtd = nand_to_mtd(chip);
 
 	/* Bad block marker position */
 	chip->badblockpos = 0x05;
@@ -187,12 +177,33 @@ int sm_register_device(struct mtd_info *mtd, int smartmedia)
 	else
 		return -ENODEV;
 
-	ret = nand_scan_tail(mtd);
+	return 0;
+}
+
+static const struct nand_controller_ops sm_controller_ops = {
+	.attach_chip = sm_attach_chip,
+};
+
+int sm_register_device(struct mtd_info *mtd, int smartmedia)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct nand_flash_dev *flash_ids;
+	int ret;
+
+	chip->options |= NAND_SKIP_BBTSCAN;
 
+	/* Scan for card properties */
+	chip->dummy_controller.ops = &sm_controller_ops;
+	flash_ids = smartmedia ? nand_smartmedia_flash_ids : nand_xd_flash_ids;
+	ret = nand_scan_with_ids(mtd, 1, flash_ids);
 	if (ret)
 		return ret;
 
-	return mtd_device_register(mtd, NULL, 0);
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret)
+		nand_cleanup(chip);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(sm_register_device);
 
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index d831a141a196..1f0b7ee38df5 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -29,14 +29,12 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/reset.h>
@@ -127,7 +125,7 @@
 #define NFC_CMD_TYPE_MSK	GENMASK(31, 30)
 #define NFC_NORMAL_OP		(0 << 30)
 #define NFC_ECC_OP		(1 << 30)
-#define NFC_PAGE_OP		(2 << 30)
+#define NFC_PAGE_OP		(2U << 30)
 
 /* define bit use in NFC_RCMD_SET */
 #define NFC_READ_CMD_MSK	GENMASK(7, 0)
@@ -234,7 +232,7 @@ static inline struct sunxi_nand_chip *to_sunxi_nand(struct nand_chip *nand)
  *			controller events
  */
 struct sunxi_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct device *dev;
 	void __iomem *regs;
 	struct clk *ahb_clk;
@@ -247,7 +245,7 @@ struct sunxi_nfc {
 	struct dma_chan *dmac;
 };
 
-static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_hw_control *ctrl)
+static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct sunxi_nfc, controller);
 }
@@ -544,7 +542,7 @@ static void sunxi_nfc_write_buf(struct mtd_info *mtd, const uint8_t *buf,
 
 static uint8_t sunxi_nfc_read_byte(struct mtd_info *mtd)
 {
-	uint8_t ret;
+	uint8_t ret = 0;
 
 	sunxi_nfc_read_buf(mtd, &ret, 1);
 
@@ -1816,12 +1814,21 @@ static void sunxi_nand_ecc_cleanup(struct nand_ecc_ctrl *ecc)
 	}
 }
 
-static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
-			       struct device_node *np)
+static int sunxi_nand_attach_chip(struct nand_chip *nand)
 {
-	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct nand_ecc_ctrl *ecc = &nand->ecc;
+	struct device_node *np = nand_get_flash_node(nand);
 	int ret;
 
+	if (nand->bbt_options & NAND_BBT_USE_FLASH)
+		nand->bbt_options |= NAND_BBT_NO_OOB;
+
+	if (nand->options & NAND_NEED_SCRAMBLING)
+		nand->options |= NAND_NO_SUBPAGE_WRITE;
+
+	nand->options |= NAND_SUBPAGE_READ;
+
 	if (!ecc->size) {
 		ecc->size = nand->ecc_step_ds;
 		ecc->strength = nand->ecc_strength_ds;
@@ -1846,6 +1853,10 @@ static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
 	return 0;
 }
 
+static const struct nand_controller_ops sunxi_nand_controller_ops = {
+	.attach_chip = sunxi_nand_attach_chip,
+};
+
 static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 				struct device_node *np)
 {
@@ -1911,6 +1922,8 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	/* Default tR value specified in the ONFI spec (chapter 4.15.1) */
 	nand->chip_delay = 200;
 	nand->controller = &nfc->controller;
+	nand->controller->ops = &sunxi_nand_controller_ops;
+
 	/*
 	 * Set the ECC mode to the default value in case nothing is specified
 	 * in the DT.
@@ -1927,30 +1940,10 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	mtd = nand_to_mtd(nand);
 	mtd->dev.parent = dev;
 
-	ret = nand_scan_ident(mtd, nsels, NULL);
+	ret = nand_scan(mtd, nsels);
 	if (ret)
 		return ret;
 
-	if (nand->bbt_options & NAND_BBT_USE_FLASH)
-		nand->bbt_options |= NAND_BBT_NO_OOB;
-
-	if (nand->options & NAND_NEED_SCRAMBLING)
-		nand->options |= NAND_NO_SUBPAGE_WRITE;
-
-	nand->options |= NAND_SUBPAGE_READ;
-
-	ret = sunxi_nand_ecc_init(mtd, &nand->ecc, np);
-	if (ret) {
-		dev_err(dev, "ECC init failed: %d\n", ret);
-		return ret;
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
-		return ret;
-	}
-
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "failed to register mtd device: %d\n", ret);
@@ -2012,7 +2005,7 @@ static int sunxi_nfc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	nfc->dev = dev;
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
 	INIT_LIST_HEAD(&nfc->chips);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index f2052fae21c7..72698691727d 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -83,7 +83,7 @@
 #define MAX_CS		4
 
 struct tango_nfc {
-	struct nand_hw_control hw;
+	struct nand_controller hw;
 	void __iomem *reg_base;
 	void __iomem *mem_base;
 	void __iomem *pbus_base;
@@ -517,6 +517,28 @@ static int tango_set_timings(struct mtd_info *mtd, int csline,
 	return 0;
 }
 
+static int tango_attach_chip(struct nand_chip *chip)
+{
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+
+	ecc->mode = NAND_ECC_HW;
+	ecc->algo = NAND_ECC_BCH;
+	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
+
+	ecc->read_page_raw = tango_read_page_raw;
+	ecc->write_page_raw = tango_write_page_raw;
+	ecc->read_page = tango_read_page;
+	ecc->write_page = tango_write_page;
+	ecc->read_oob = tango_read_oob;
+	ecc->write_oob = tango_write_oob;
+
+	return 0;
+}
+
+static const struct nand_controller_ops tango_controller_ops = {
+	.attach_chip = tango_attach_chip,
+};
+
 static int chip_init(struct device *dev, struct device_node *np)
 {
 	u32 cs;
@@ -566,22 +588,7 @@ static int chip_init(struct device *dev, struct device_node *np)
 	mtd_set_ooblayout(mtd, &tango_nand_ooblayout_ops);
 	mtd->dev.parent = dev;
 
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err)
-		return err;
-
-	ecc->mode = NAND_ECC_HW;
-	ecc->algo = NAND_ECC_BCH;
-	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
-
-	ecc->read_page_raw = tango_read_page_raw;
-	ecc->write_page_raw = tango_write_page_raw;
-	ecc->read_page = tango_read_page;
-	ecc->write_page = tango_write_page;
-	ecc->read_oob = tango_read_oob;
-	ecc->write_oob = tango_write_oob;
-
-	err = nand_scan_tail(mtd);
+	err = nand_scan(mtd, 1);
 	if (err)
 		return err;
 
@@ -654,7 +661,8 @@ static int tango_nand_probe(struct platform_device *pdev)
 		return PTR_ERR(nfc->chan);
 
 	platform_set_drvdata(pdev, nfc);
-	nand_hw_control_init(&nfc->hw);
+	nand_controller_init(&nfc->hw);
+	nfc->hw.ops = &tango_controller_ops;
 	nfc->freq_kHz = clk_get_rate(clk) / 1000;
 
 	for_each_child_of_node(pdev->dev.of_node, np) {
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
new file mode 100644
index 000000000000..79da1efc88d1
--- /dev/null
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -0,0 +1,1246 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Stefan Agner <stefan@agner.ch>
+ * Copyright (C) 2014-2015 Lucas Stach <dev@lynxeye.de>
+ * Copyright (C) 2012 Avionic Design GmbH
+ */
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/rawnand.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#define COMMAND					0x00
+#define   COMMAND_GO				BIT(31)
+#define   COMMAND_CLE				BIT(30)
+#define   COMMAND_ALE				BIT(29)
+#define   COMMAND_PIO				BIT(28)
+#define   COMMAND_TX				BIT(27)
+#define   COMMAND_RX				BIT(26)
+#define   COMMAND_SEC_CMD			BIT(25)
+#define   COMMAND_AFT_DAT			BIT(24)
+#define   COMMAND_TRANS_SIZE(size)		((((size) - 1) & 0xf) << 20)
+#define   COMMAND_A_VALID			BIT(19)
+#define   COMMAND_B_VALID			BIT(18)
+#define   COMMAND_RD_STATUS_CHK			BIT(17)
+#define   COMMAND_RBSY_CHK			BIT(16)
+#define   COMMAND_CE(x)				BIT(8 + ((x) & 0x7))
+#define   COMMAND_CLE_SIZE(size)		((((size) - 1) & 0x3) << 4)
+#define   COMMAND_ALE_SIZE(size)		((((size) - 1) & 0xf) << 0)
+
+#define STATUS					0x04
+
+#define ISR					0x08
+#define   ISR_CORRFAIL_ERR			BIT(24)
+#define   ISR_UND				BIT(7)
+#define   ISR_OVR				BIT(6)
+#define   ISR_CMD_DONE				BIT(5)
+#define   ISR_ECC_ERR				BIT(4)
+
+#define IER					0x0c
+#define   IER_ERR_TRIG_VAL(x)			(((x) & 0xf) << 16)
+#define   IER_UND				BIT(7)
+#define   IER_OVR				BIT(6)
+#define   IER_CMD_DONE				BIT(5)
+#define   IER_ECC_ERR				BIT(4)
+#define   IER_GIE				BIT(0)
+
+#define CONFIG					0x10
+#define   CONFIG_HW_ECC				BIT(31)
+#define   CONFIG_ECC_SEL			BIT(30)
+#define   CONFIG_ERR_COR			BIT(29)
+#define   CONFIG_PIPE_EN			BIT(28)
+#define   CONFIG_TVAL_4				(0 << 24)
+#define   CONFIG_TVAL_6				(1 << 24)
+#define   CONFIG_TVAL_8				(2 << 24)
+#define   CONFIG_SKIP_SPARE			BIT(23)
+#define   CONFIG_BUS_WIDTH_16			BIT(21)
+#define   CONFIG_COM_BSY			BIT(20)
+#define   CONFIG_PS_256				(0 << 16)
+#define   CONFIG_PS_512				(1 << 16)
+#define   CONFIG_PS_1024			(2 << 16)
+#define   CONFIG_PS_2048			(3 << 16)
+#define   CONFIG_PS_4096			(4 << 16)
+#define   CONFIG_SKIP_SPARE_SIZE_4		(0 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_8		(1 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_12		(2 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_16		(3 << 14)
+#define   CONFIG_TAG_BYTE_SIZE(x)			((x) & 0xff)
+
+#define TIMING_1				0x14
+#define   TIMING_TRP_RESP(x)			(((x) & 0xf) << 28)
+#define   TIMING_TWB(x)				(((x) & 0xf) << 24)
+#define   TIMING_TCR_TAR_TRR(x)			(((x) & 0xf) << 20)
+#define   TIMING_TWHR(x)			(((x) & 0xf) << 16)
+#define   TIMING_TCS(x)				(((x) & 0x3) << 14)
+#define   TIMING_TWH(x)				(((x) & 0x3) << 12)
+#define   TIMING_TWP(x)				(((x) & 0xf) <<  8)
+#define   TIMING_TRH(x)				(((x) & 0x3) <<  4)
+#define   TIMING_TRP(x)				(((x) & 0xf) <<  0)
+
+#define RESP					0x18
+
+#define TIMING_2				0x1c
+#define   TIMING_TADL(x)			((x) & 0xf)
+
+#define CMD_REG1				0x20
+#define CMD_REG2				0x24
+#define ADDR_REG1				0x28
+#define ADDR_REG2				0x2c
+
+#define DMA_MST_CTRL				0x30
+#define   DMA_MST_CTRL_GO			BIT(31)
+#define   DMA_MST_CTRL_IN			(0 << 30)
+#define   DMA_MST_CTRL_OUT			BIT(30)
+#define   DMA_MST_CTRL_PERF_EN			BIT(29)
+#define   DMA_MST_CTRL_IE_DONE			BIT(28)
+#define   DMA_MST_CTRL_REUSE			BIT(27)
+#define   DMA_MST_CTRL_BURST_1			(2 << 24)
+#define   DMA_MST_CTRL_BURST_4			(3 << 24)
+#define   DMA_MST_CTRL_BURST_8			(4 << 24)
+#define   DMA_MST_CTRL_BURST_16			(5 << 24)
+#define   DMA_MST_CTRL_IS_DONE			BIT(20)
+#define   DMA_MST_CTRL_EN_A			BIT(2)
+#define   DMA_MST_CTRL_EN_B			BIT(1)
+
+#define DMA_CFG_A				0x34
+#define DMA_CFG_B				0x38
+
+#define FIFO_CTRL				0x3c
+#define   FIFO_CTRL_CLR_ALL			BIT(3)
+
+#define DATA_PTR				0x40
+#define TAG_PTR					0x44
+#define ECC_PTR					0x48
+
+#define DEC_STATUS				0x4c
+#define   DEC_STATUS_A_ECC_FAIL			BIT(1)
+#define   DEC_STATUS_ERR_COUNT_MASK		0x00ff0000
+#define   DEC_STATUS_ERR_COUNT_SHIFT		16
+
+#define HWSTATUS_CMD				0x50
+#define HWSTATUS_MASK				0x54
+#define   HWSTATUS_RDSTATUS_MASK(x)		(((x) & 0xff) << 24)
+#define   HWSTATUS_RDSTATUS_VALUE(x)		(((x) & 0xff) << 16)
+#define   HWSTATUS_RBSY_MASK(x)			(((x) & 0xff) << 8)
+#define   HWSTATUS_RBSY_VALUE(x)		(((x) & 0xff) << 0)
+
+#define BCH_CONFIG				0xcc
+#define   BCH_ENABLE				BIT(0)
+#define   BCH_TVAL_4				(0 << 4)
+#define   BCH_TVAL_8				(1 << 4)
+#define   BCH_TVAL_14				(2 << 4)
+#define   BCH_TVAL_16				(3 << 4)
+
+#define DEC_STAT_RESULT				0xd0
+#define DEC_STAT_BUF				0xd4
+#define   DEC_STAT_BUF_FAIL_SEC_FLAG_MASK	0xff000000
+#define   DEC_STAT_BUF_FAIL_SEC_FLAG_SHIFT	24
+#define   DEC_STAT_BUF_CORR_SEC_FLAG_MASK	0x00ff0000
+#define   DEC_STAT_BUF_CORR_SEC_FLAG_SHIFT	16
+#define   DEC_STAT_BUF_MAX_CORR_CNT_MASK	0x00001f00
+#define   DEC_STAT_BUF_MAX_CORR_CNT_SHIFT	8
+
+#define OFFSET(val, off)	((val) < (off) ? 0 : (val) - (off))
+
+#define SKIP_SPARE_BYTES	4
+#define BITS_PER_STEP_RS	18
+#define BITS_PER_STEP_BCH	13
+
+#define INT_MASK		(IER_UND | IER_OVR | IER_CMD_DONE | IER_GIE)
+#define HWSTATUS_CMD_DEFAULT	NAND_STATUS_READY
+#define HWSTATUS_MASK_DEFAULT	(HWSTATUS_RDSTATUS_MASK(1) | \
+				HWSTATUS_RDSTATUS_VALUE(0) | \
+				HWSTATUS_RBSY_MASK(NAND_STATUS_READY) | \
+				HWSTATUS_RBSY_VALUE(NAND_STATUS_READY))
+
+struct tegra_nand_controller {
+	struct nand_controller controller;
+	struct device *dev;
+	void __iomem *regs;
+	int irq;
+	struct clk *clk;
+	struct completion command_complete;
+	struct completion dma_complete;
+	bool last_read_error;
+	int cur_cs;
+	struct nand_chip *chip;
+};
+
+struct tegra_nand_chip {
+	struct nand_chip chip;
+	struct gpio_desc *wp_gpio;
+	struct mtd_oob_region ecc;
+	u32 config;
+	u32 config_ecc;
+	u32 bch_config;
+	int cs[1];
+};
+
+static inline struct tegra_nand_controller *
+			to_tegra_ctrl(struct nand_controller *hw_ctrl)
+{
+	return container_of(hw_ctrl, struct tegra_nand_controller, controller);
+}
+
+static inline struct tegra_nand_chip *to_tegra_chip(struct nand_chip *chip)
+{
+	return container_of(chip, struct tegra_nand_chip, chip);
+}
+
+static int tegra_nand_ooblayout_rs_ecc(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	int bytes_per_step = DIV_ROUND_UP(BITS_PER_STEP_RS * chip->ecc.strength,
+					  BITS_PER_BYTE);
+
+	if (section > 0)
+		return -ERANGE;
+
+	oobregion->offset = SKIP_SPARE_BYTES;
+	oobregion->length = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+	return 0;
+}
+
+static int tegra_nand_ooblayout_no_free(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *oobregion)
+{
+	return -ERANGE;
+}
+
+static const struct mtd_ooblayout_ops tegra_nand_oob_rs_ops = {
+	.ecc = tegra_nand_ooblayout_rs_ecc,
+	.free = tegra_nand_ooblayout_no_free,
+};
+
+static int tegra_nand_ooblayout_bch_ecc(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	int bytes_per_step = DIV_ROUND_UP(BITS_PER_STEP_BCH * chip->ecc.strength,
+					  BITS_PER_BYTE);
+
+	if (section > 0)
+		return -ERANGE;
+
+	oobregion->offset = SKIP_SPARE_BYTES;
+	oobregion->length = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops tegra_nand_oob_bch_ops = {
+	.ecc = tegra_nand_ooblayout_bch_ecc,
+	.free = tegra_nand_ooblayout_no_free,
+};
+
+static irqreturn_t tegra_nand_irq(int irq, void *data)
+{
+	struct tegra_nand_controller *ctrl = data;
+	u32 isr, dma;
+
+	isr = readl_relaxed(ctrl->regs + ISR);
+	dma = readl_relaxed(ctrl->regs + DMA_MST_CTRL);
+	dev_dbg(ctrl->dev, "isr %08x\n", isr);
+
+	if (!isr && !(dma & DMA_MST_CTRL_IS_DONE))
+		return IRQ_NONE;
+
+	/*
+	 * The bit name is somewhat missleading: This is also set when
+	 * HW ECC was successful. The data sheet states:
+	 * Correctable OR Un-correctable errors occurred in the DMA transfer...
+	 */
+	if (isr & ISR_CORRFAIL_ERR)
+		ctrl->last_read_error = true;
+
+	if (isr & ISR_CMD_DONE)
+		complete(&ctrl->command_complete);
+
+	if (isr & ISR_UND)
+		dev_err(ctrl->dev, "FIFO underrun\n");
+
+	if (isr & ISR_OVR)
+		dev_err(ctrl->dev, "FIFO overrun\n");
+
+	/* handle DMA interrupts */
+	if (dma & DMA_MST_CTRL_IS_DONE) {
+		writel_relaxed(dma, ctrl->regs + DMA_MST_CTRL);
+		complete(&ctrl->dma_complete);
+	}
+
+	/* clear interrupts */
+	writel_relaxed(isr, ctrl->regs + ISR);
+
+	return IRQ_HANDLED;
+}
+
+static const char * const tegra_nand_reg_names[] = {
+	"COMMAND",
+	"STATUS",
+	"ISR",
+	"IER",
+	"CONFIG",
+	"TIMING",
+	NULL,
+	"TIMING2",
+	"CMD_REG1",
+	"CMD_REG2",
+	"ADDR_REG1",
+	"ADDR_REG2",
+	"DMA_MST_CTRL",
+	"DMA_CFG_A",
+	"DMA_CFG_B",
+	"FIFO_CTRL",
+};
+
+static void tegra_nand_dump_reg(struct tegra_nand_controller *ctrl)
+{
+	u32 reg;
+	int i;
+
+	dev_err(ctrl->dev, "Tegra NAND controller register dump\n");
+	for (i = 0; i < ARRAY_SIZE(tegra_nand_reg_names); i++) {
+		const char *reg_name = tegra_nand_reg_names[i];
+
+		if (!reg_name)
+			continue;
+
+		reg = readl_relaxed(ctrl->regs + (i * 4));
+		dev_err(ctrl->dev, "%s: 0x%08x\n", reg_name, reg);
+	}
+}
+
+static void tegra_nand_controller_abort(struct tegra_nand_controller *ctrl)
+{
+	u32 isr, dma;
+
+	disable_irq(ctrl->irq);
+
+	/* Abort current command/DMA operation */
+	writel_relaxed(0, ctrl->regs + DMA_MST_CTRL);
+	writel_relaxed(0, ctrl->regs + COMMAND);
+
+	/* clear interrupts */
+	isr = readl_relaxed(ctrl->regs + ISR);
+	writel_relaxed(isr, ctrl->regs + ISR);
+	dma = readl_relaxed(ctrl->regs + DMA_MST_CTRL);
+	writel_relaxed(dma, ctrl->regs + DMA_MST_CTRL);
+
+	reinit_completion(&ctrl->command_complete);
+	reinit_completion(&ctrl->dma_complete);
+
+	enable_irq(ctrl->irq);
+}
+
+static int tegra_nand_cmd(struct nand_chip *chip,
+			  const struct nand_subop *subop)
+{
+	const struct nand_op_instr *instr;
+	const struct nand_op_instr *instr_data_in = NULL;
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	unsigned int op_id, size = 0, offset = 0;
+	bool first_cmd = true;
+	u32 reg, cmd = 0;
+	int ret;
+
+	for (op_id = 0; op_id < subop->ninstrs; op_id++) {
+		unsigned int naddrs, i;
+		const u8 *addrs;
+		u32 addr1 = 0, addr2 = 0;
+
+		instr = &subop->instrs[op_id];
+
+		switch (instr->type) {
+		case NAND_OP_CMD_INSTR:
+			if (first_cmd) {
+				cmd |= COMMAND_CLE;
+				writel_relaxed(instr->ctx.cmd.opcode,
+					       ctrl->regs + CMD_REG1);
+			} else {
+				cmd |= COMMAND_SEC_CMD;
+				writel_relaxed(instr->ctx.cmd.opcode,
+					       ctrl->regs + CMD_REG2);
+			}
+			first_cmd = false;
+			break;
+
+		case NAND_OP_ADDR_INSTR:
+			offset = nand_subop_get_addr_start_off(subop, op_id);
+			naddrs = nand_subop_get_num_addr_cyc(subop, op_id);
+			addrs = &instr->ctx.addr.addrs[offset];
+
+			cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(naddrs);
+			for (i = 0; i < min_t(unsigned int, 4, naddrs); i++)
+				addr1 |= *addrs++ << (BITS_PER_BYTE * i);
+			naddrs -= i;
+			for (i = 0; i < min_t(unsigned int, 4, naddrs); i++)
+				addr2 |= *addrs++ << (BITS_PER_BYTE * i);
+
+			writel_relaxed(addr1, ctrl->regs + ADDR_REG1);
+			writel_relaxed(addr2, ctrl->regs + ADDR_REG2);
+			break;
+
+		case NAND_OP_DATA_IN_INSTR:
+			size = nand_subop_get_data_len(subop, op_id);
+			offset = nand_subop_get_data_start_off(subop, op_id);
+
+			cmd |= COMMAND_TRANS_SIZE(size) | COMMAND_PIO |
+				COMMAND_RX | COMMAND_A_VALID;
+
+			instr_data_in = instr;
+			break;
+
+		case NAND_OP_DATA_OUT_INSTR:
+			size = nand_subop_get_data_len(subop, op_id);
+			offset = nand_subop_get_data_start_off(subop, op_id);
+
+			cmd |= COMMAND_TRANS_SIZE(size) | COMMAND_PIO |
+				COMMAND_TX | COMMAND_A_VALID;
+			memcpy(&reg, instr->ctx.data.buf.out + offset, size);
+
+			writel_relaxed(reg, ctrl->regs + RESP);
+			break;
+
+		case NAND_OP_WAITRDY_INSTR:
+			cmd |= COMMAND_RBSY_CHK;
+			break;
+		}
+	}
+
+	cmd |= COMMAND_GO | COMMAND_CE(ctrl->cur_cs);
+	writel_relaxed(cmd, ctrl->regs + COMMAND);
+	ret = wait_for_completion_timeout(&ctrl->command_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "COMMAND timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		return -ETIMEDOUT;
+	}
+
+	if (instr_data_in) {
+		reg = readl_relaxed(ctrl->regs + RESP);
+		memcpy(instr_data_in->ctx.data.buf.in + offset, &reg, size);
+	}
+
+	return 0;
+}
+
+static const struct nand_op_parser tegra_nand_op_parser = NAND_OP_PARSER(
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(true, 8),
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(true)),
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_DATA_OUT_ELEM(false, 4)),
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(true, 8),
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(true),
+		NAND_OP_PARSER_PAT_DATA_IN_ELEM(true, 4)),
+	);
+
+static int tegra_nand_exec_op(struct nand_chip *chip,
+			      const struct nand_operation *op,
+			      bool check_only)
+{
+	return nand_op_parser_exec_op(chip, &tegra_nand_op_parser, op,
+				      check_only);
+}
+
+static void tegra_nand_select_chip(struct mtd_info *mtd, int die_nr)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+
+	WARN_ON(die_nr >= (int)ARRAY_SIZE(nand->cs));
+
+	if (die_nr < 0 || die_nr > 0) {
+		ctrl->cur_cs = -1;
+		return;
+	}
+
+	ctrl->cur_cs = nand->cs[die_nr];
+}
+
+static void tegra_nand_hw_ecc(struct tegra_nand_controller *ctrl,
+			      struct nand_chip *chip, bool enable)
+{
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+
+	if (chip->ecc.algo == NAND_ECC_BCH && enable)
+		writel_relaxed(nand->bch_config, ctrl->regs + BCH_CONFIG);
+	else
+		writel_relaxed(0, ctrl->regs + BCH_CONFIG);
+
+	if (enable)
+		writel_relaxed(nand->config_ecc, ctrl->regs + CONFIG);
+	else
+		writel_relaxed(nand->config, ctrl->regs + CONFIG);
+}
+
+static int tegra_nand_page_xfer(struct mtd_info *mtd, struct nand_chip *chip,
+				void *buf, void *oob_buf, int oob_len, int page,
+				bool read)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	dma_addr_t dma_addr = 0, dma_addr_oob = 0;
+	u32 addr1, cmd, dma_ctrl;
+	int ret;
+
+	if (read) {
+		writel_relaxed(NAND_CMD_READ0, ctrl->regs + CMD_REG1);
+		writel_relaxed(NAND_CMD_READSTART, ctrl->regs + CMD_REG2);
+	} else {
+		writel_relaxed(NAND_CMD_SEQIN, ctrl->regs + CMD_REG1);
+		writel_relaxed(NAND_CMD_PAGEPROG, ctrl->regs + CMD_REG2);
+	}
+	cmd = COMMAND_CLE | COMMAND_SEC_CMD;
+
+	/* Lower 16-bits are column, by default 0 */
+	addr1 = page << 16;
+
+	if (!buf)
+		addr1 |= mtd->writesize;
+	writel_relaxed(addr1, ctrl->regs + ADDR_REG1);
+
+	if (chip->options & NAND_ROW_ADDR_3) {
+		writel_relaxed(page >> 16, ctrl->regs + ADDR_REG2);
+		cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(5);
+	} else {
+		cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(4);
+	}
+
+	if (buf) {
+		dma_addr = dma_map_single(ctrl->dev, buf, mtd->writesize, dir);
+		ret = dma_mapping_error(ctrl->dev, dma_addr);
+		if (ret) {
+			dev_err(ctrl->dev, "dma mapping error\n");
+			return -EINVAL;
+		}
+
+		writel_relaxed(mtd->writesize - 1, ctrl->regs + DMA_CFG_A);
+		writel_relaxed(dma_addr, ctrl->regs + DATA_PTR);
+	}
+
+	if (oob_buf) {
+		dma_addr_oob = dma_map_single(ctrl->dev, oob_buf, mtd->oobsize,
+					      dir);
+		ret = dma_mapping_error(ctrl->dev, dma_addr_oob);
+		if (ret) {
+			dev_err(ctrl->dev, "dma mapping error\n");
+			ret = -EINVAL;
+			goto err_unmap_dma_page;
+		}
+
+		writel_relaxed(oob_len - 1, ctrl->regs + DMA_CFG_B);
+		writel_relaxed(dma_addr_oob, ctrl->regs + TAG_PTR);
+	}
+
+	dma_ctrl = DMA_MST_CTRL_GO | DMA_MST_CTRL_PERF_EN |
+		   DMA_MST_CTRL_IE_DONE | DMA_MST_CTRL_IS_DONE |
+		   DMA_MST_CTRL_BURST_16;
+
+	if (buf)
+		dma_ctrl |= DMA_MST_CTRL_EN_A;
+	if (oob_buf)
+		dma_ctrl |= DMA_MST_CTRL_EN_B;
+
+	if (read)
+		dma_ctrl |= DMA_MST_CTRL_IN | DMA_MST_CTRL_REUSE;
+	else
+		dma_ctrl |= DMA_MST_CTRL_OUT;
+
+	writel_relaxed(dma_ctrl, ctrl->regs + DMA_MST_CTRL);
+
+	cmd |= COMMAND_GO | COMMAND_RBSY_CHK | COMMAND_TRANS_SIZE(9) |
+	       COMMAND_CE(ctrl->cur_cs);
+
+	if (buf)
+		cmd |= COMMAND_A_VALID;
+	if (oob_buf)
+		cmd |= COMMAND_B_VALID;
+
+	if (read)
+		cmd |= COMMAND_RX;
+	else
+		cmd |= COMMAND_TX | COMMAND_AFT_DAT;
+
+	writel_relaxed(cmd, ctrl->regs + COMMAND);
+
+	ret = wait_for_completion_timeout(&ctrl->command_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "COMMAND timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		ret = -ETIMEDOUT;
+		goto err_unmap_dma;
+	}
+
+	ret = wait_for_completion_timeout(&ctrl->dma_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "DMA timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		ret = -ETIMEDOUT;
+		goto err_unmap_dma;
+	}
+	ret = 0;
+
+err_unmap_dma:
+	if (oob_buf)
+		dma_unmap_single(ctrl->dev, dma_addr_oob, mtd->oobsize, dir);
+err_unmap_dma_page:
+	if (buf)
+		dma_unmap_single(ctrl->dev, dma_addr, mtd->writesize, dir);
+
+	return ret;
+}
+
+static int tegra_nand_read_page_raw(struct mtd_info *mtd,
+				    struct nand_chip *chip, u8 *buf,
+				    int oob_required, int page)
+{
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+
+	return tegra_nand_page_xfer(mtd, chip, buf, oob_buf,
+				    mtd->oobsize, page, true);
+}
+
+static int tegra_nand_write_page_raw(struct mtd_info *mtd,
+				     struct nand_chip *chip, const u8 *buf,
+				     int oob_required, int page)
+{
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+
+	return tegra_nand_page_xfer(mtd, chip, (void *)buf, oob_buf,
+				     mtd->oobsize, page, false);
+}
+
+static int tegra_nand_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
+			       int page)
+{
+	return tegra_nand_page_xfer(mtd, chip, NULL, chip->oob_poi,
+				    mtd->oobsize, page, true);
+}
+
+static int tegra_nand_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
+				int page)
+{
+	return tegra_nand_page_xfer(mtd, chip, NULL, chip->oob_poi,
+				    mtd->oobsize, page, false);
+}
+
+static int tegra_nand_read_page_hwecc(struct mtd_info *mtd,
+				      struct nand_chip *chip, u8 *buf,
+				      int oob_required, int page)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+	u32 dec_stat, max_corr_cnt;
+	unsigned long fail_sec_flag;
+	int ret;
+
+	tegra_nand_hw_ecc(ctrl, chip, true);
+	ret = tegra_nand_page_xfer(mtd, chip, buf, oob_buf, 0, page, true);
+	tegra_nand_hw_ecc(ctrl, chip, false);
+	if (ret)
+		return ret;
+
+	/* No correctable or un-correctable errors, page must have 0 bitflips */
+	if (!ctrl->last_read_error)
+		return 0;
+
+	/*
+	 * Correctable or un-correctable errors occurred. Use DEC_STAT_BUF
+	 * which contains information for all ECC selections.
+	 *
+	 * Note that since we do not use Command Queues DEC_RESULT does not
+	 * state the number of pages we can read from the DEC_STAT_BUF. But
+	 * since CORRFAIL_ERR did occur during page read we do have a valid
+	 * result in DEC_STAT_BUF.
+	 */
+	ctrl->last_read_error = false;
+	dec_stat = readl_relaxed(ctrl->regs + DEC_STAT_BUF);
+
+	fail_sec_flag = (dec_stat & DEC_STAT_BUF_FAIL_SEC_FLAG_MASK) >>
+			DEC_STAT_BUF_FAIL_SEC_FLAG_SHIFT;
+
+	max_corr_cnt = (dec_stat & DEC_STAT_BUF_MAX_CORR_CNT_MASK) >>
+		       DEC_STAT_BUF_MAX_CORR_CNT_SHIFT;
+
+	if (fail_sec_flag) {
+		int bit, max_bitflips = 0;
+
+		/*
+		 * Since we do not support subpage writes, a complete page
+		 * is either written or not. We can take a shortcut here by
+		 * checking wheather any of the sector has been successful
+		 * read. If at least one sectors has been read successfully,
+		 * the page must have been a written previously. It cannot
+		 * be an erased page.
+		 *
+		 * E.g. controller might return fail_sec_flag with 0x4, which
+		 * would mean only the third sector failed to correct. The
+		 * page must have been written and the third sector is really
+		 * not correctable anymore.
+		 */
+		if (fail_sec_flag ^ GENMASK(chip->ecc.steps - 1, 0)) {
+			mtd->ecc_stats.failed += hweight8(fail_sec_flag);
+			return max_corr_cnt;
+		}
+
+		/*
+		 * All sectors failed to correct, but the ECC isn't smart
+		 * enough to figure out if a page is really just erased.
+		 * Read OOB data and check whether data/OOB is completely
+		 * erased or if error correction just failed for all sub-
+		 * pages.
+		 */
+		ret = tegra_nand_read_oob(mtd, chip, page);
+		if (ret < 0)
+			return ret;
+
+		for_each_set_bit(bit, &fail_sec_flag, chip->ecc.steps) {
+			u8 *data = buf + (chip->ecc.size * bit);
+			u8 *oob = chip->oob_poi + nand->ecc.offset +
+				  (chip->ecc.bytes * bit);
+
+			ret = nand_check_erased_ecc_chunk(data, chip->ecc.size,
+							  oob, chip->ecc.bytes,
+							  NULL, 0,
+							  chip->ecc.strength);
+			if (ret < 0) {
+				mtd->ecc_stats.failed++;
+			} else {
+				mtd->ecc_stats.corrected += ret;
+				max_bitflips = max(ret, max_bitflips);
+			}
+		}
+
+		return max_t(unsigned int, max_corr_cnt, max_bitflips);
+	} else {
+		int corr_sec_flag;
+
+		corr_sec_flag = (dec_stat & DEC_STAT_BUF_CORR_SEC_FLAG_MASK) >>
+				DEC_STAT_BUF_CORR_SEC_FLAG_SHIFT;
+
+		/*
+		 * The value returned in the register is the maximum of
+		 * bitflips encountered in any of the ECC regions. As there is
+		 * no way to get the number of bitflips in a specific regions
+		 * we are not able to deliver correct stats but instead
+		 * overestimate the number of corrected bitflips by assuming
+		 * that all regions where errors have been corrected
+		 * encountered the maximum number of bitflips.
+		 */
+		mtd->ecc_stats.corrected += max_corr_cnt * hweight8(corr_sec_flag);
+
+		return max_corr_cnt;
+	}
+}
+
+static int tegra_nand_write_page_hwecc(struct mtd_info *mtd,
+				       struct nand_chip *chip, const u8 *buf,
+				       int oob_required, int page)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+	int ret;
+
+	tegra_nand_hw_ecc(ctrl, chip, true);
+	ret = tegra_nand_page_xfer(mtd, chip, (void *)buf, oob_buf,
+				   0, page, false);
+	tegra_nand_hw_ecc(ctrl, chip, false);
+
+	return ret;
+}
+
+static void tegra_nand_setup_timing(struct tegra_nand_controller *ctrl,
+				    const struct nand_sdr_timings *timings)
+{
+	/*
+	 * The period (and all other timings in this function) is in ps,
+	 * so need to take care here to avoid integer overflows.
+	 */
+	unsigned int rate = clk_get_rate(ctrl->clk) / 1000000;
+	unsigned int period = DIV_ROUND_UP(1000000, rate);
+	u32 val, reg = 0;
+
+	val = DIV_ROUND_UP(max3(timings->tAR_min, timings->tRR_min,
+				timings->tRC_min), period);
+	reg |= TIMING_TCR_TAR_TRR(OFFSET(val, 3));
+
+	val = DIV_ROUND_UP(max(max(timings->tCS_min, timings->tCH_min),
+			       max(timings->tALS_min, timings->tALH_min)),
+			   period);
+	reg |= TIMING_TCS(OFFSET(val, 2));
+
+	val = DIV_ROUND_UP(max(timings->tRP_min, timings->tREA_max) + 6000,
+			   period);
+	reg |= TIMING_TRP(OFFSET(val, 1)) | TIMING_TRP_RESP(OFFSET(val, 1));
+
+	reg |= TIMING_TWB(OFFSET(DIV_ROUND_UP(timings->tWB_max, period), 1));
+	reg |= TIMING_TWHR(OFFSET(DIV_ROUND_UP(timings->tWHR_min, period), 1));
+	reg |= TIMING_TWH(OFFSET(DIV_ROUND_UP(timings->tWH_min, period), 1));
+	reg |= TIMING_TWP(OFFSET(DIV_ROUND_UP(timings->tWP_min, period), 1));
+	reg |= TIMING_TRH(OFFSET(DIV_ROUND_UP(timings->tREH_min, period), 1));
+
+	writel_relaxed(reg, ctrl->regs + TIMING_1);
+
+	val = DIV_ROUND_UP(timings->tADL_min, period);
+	reg = TIMING_TADL(OFFSET(val, 3));
+
+	writel_relaxed(reg, ctrl->regs + TIMING_2);
+}
+
+static int tegra_nand_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	const struct nand_sdr_timings *timings;
+
+	timings = nand_get_sdr_timings(conf);
+	if (IS_ERR(timings))
+		return PTR_ERR(timings);
+
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
+		return 0;
+
+	tegra_nand_setup_timing(ctrl, timings);
+
+	return 0;
+}
+
+static const int rs_strength_bootable[] = { 4 };
+static const int rs_strength[] = { 4, 6, 8 };
+static const int bch_strength_bootable[] = { 8, 16 };
+static const int bch_strength[] = { 4, 8, 14, 16 };
+
+static int tegra_nand_get_strength(struct nand_chip *chip, const int *strength,
+				   int strength_len, int bits_per_step,
+				   int oobsize)
+{
+	bool maximize = chip->ecc.options & NAND_ECC_MAXIMIZE;
+	int i;
+
+	/*
+	 * Loop through available strengths. Backwards in case we try to
+	 * maximize the BCH strength.
+	 */
+	for (i = 0; i < strength_len; i++) {
+		int strength_sel, bytes_per_step, bytes_per_page;
+
+		if (maximize) {
+			strength_sel = strength[strength_len - i - 1];
+		} else {
+			strength_sel = strength[i];
+
+			if (strength_sel < chip->ecc_strength_ds)
+				continue;
+		}
+
+		bytes_per_step = DIV_ROUND_UP(bits_per_step * strength_sel,
+					      BITS_PER_BYTE);
+		bytes_per_page = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+		/* Check whether strength fits OOB */
+		if (bytes_per_page < (oobsize - SKIP_SPARE_BYTES))
+			return strength_sel;
+	}
+
+	return -EINVAL;
+}
+
+static int tegra_nand_select_strength(struct nand_chip *chip, int oobsize)
+{
+	const int *strength;
+	int strength_len, bits_per_step;
+
+	switch (chip->ecc.algo) {
+	case NAND_ECC_RS:
+		bits_per_step = BITS_PER_STEP_RS;
+		if (chip->options & NAND_IS_BOOT_MEDIUM) {
+			strength = rs_strength_bootable;
+			strength_len = ARRAY_SIZE(rs_strength_bootable);
+		} else {
+			strength = rs_strength;
+			strength_len = ARRAY_SIZE(rs_strength);
+		}
+		break;
+	case NAND_ECC_BCH:
+		bits_per_step = BITS_PER_STEP_BCH;
+		if (chip->options & NAND_IS_BOOT_MEDIUM) {
+			strength = bch_strength_bootable;
+			strength_len = ARRAY_SIZE(bch_strength_bootable);
+		} else {
+			strength = bch_strength;
+			strength_len = ARRAY_SIZE(bch_strength);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return tegra_nand_get_strength(chip, strength, strength_len,
+				       bits_per_step, oobsize);
+}
+
+static int tegra_nand_attach_chip(struct nand_chip *chip)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int bits_per_step;
+	int ret;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.size = 512;
+	chip->ecc.steps = mtd->writesize / chip->ecc.size;
+	if (chip->ecc_step_ds != 512) {
+		dev_err(ctrl->dev, "Unsupported step size %d\n",
+			chip->ecc_step_ds);
+		return -EINVAL;
+	}
+
+	chip->ecc.read_page = tegra_nand_read_page_hwecc;
+	chip->ecc.write_page = tegra_nand_write_page_hwecc;
+	chip->ecc.read_page_raw = tegra_nand_read_page_raw;
+	chip->ecc.write_page_raw = tegra_nand_write_page_raw;
+	chip->ecc.read_oob = tegra_nand_read_oob;
+	chip->ecc.write_oob = tegra_nand_write_oob;
+
+	if (chip->options & NAND_BUSWIDTH_16)
+		nand->config |= CONFIG_BUS_WIDTH_16;
+
+	if (chip->ecc.algo == NAND_ECC_UNKNOWN) {
+		if (mtd->writesize < 2048)
+			chip->ecc.algo = NAND_ECC_RS;
+		else
+			chip->ecc.algo = NAND_ECC_BCH;
+	}
+
+	if (chip->ecc.algo == NAND_ECC_BCH && mtd->writesize < 2048) {
+		dev_err(ctrl->dev, "BCH supports 2K or 4K page size only\n");
+		return -EINVAL;
+	}
+
+	if (!chip->ecc.strength) {
+		ret = tegra_nand_select_strength(chip, mtd->oobsize);
+		if (ret < 0) {
+			dev_err(ctrl->dev,
+				"No valid strength found, minimum %d\n",
+				chip->ecc_strength_ds);
+			return ret;
+		}
+
+		chip->ecc.strength = ret;
+	}
+
+	nand->config_ecc = CONFIG_PIPE_EN | CONFIG_SKIP_SPARE |
+			   CONFIG_SKIP_SPARE_SIZE_4;
+
+	switch (chip->ecc.algo) {
+	case NAND_ECC_RS:
+		bits_per_step = BITS_PER_STEP_RS * chip->ecc.strength;
+		mtd_set_ooblayout(mtd, &tegra_nand_oob_rs_ops);
+		nand->config_ecc |= CONFIG_HW_ECC | CONFIG_ECC_SEL |
+				    CONFIG_ERR_COR;
+		switch (chip->ecc.strength) {
+		case 4:
+			nand->config_ecc |= CONFIG_TVAL_4;
+			break;
+		case 6:
+			nand->config_ecc |= CONFIG_TVAL_6;
+			break;
+		case 8:
+			nand->config_ecc |= CONFIG_TVAL_8;
+			break;
+		default:
+			dev_err(ctrl->dev, "ECC strength %d not supported\n",
+				chip->ecc.strength);
+			return -EINVAL;
+		}
+		break;
+	case NAND_ECC_BCH:
+		bits_per_step = BITS_PER_STEP_BCH * chip->ecc.strength;
+		mtd_set_ooblayout(mtd, &tegra_nand_oob_bch_ops);
+		nand->bch_config = BCH_ENABLE;
+		switch (chip->ecc.strength) {
+		case 4:
+			nand->bch_config |= BCH_TVAL_4;
+			break;
+		case 8:
+			nand->bch_config |= BCH_TVAL_8;
+			break;
+		case 14:
+			nand->bch_config |= BCH_TVAL_14;
+			break;
+		case 16:
+			nand->bch_config |= BCH_TVAL_16;
+			break;
+		default:
+			dev_err(ctrl->dev, "ECC strength %d not supported\n",
+				chip->ecc.strength);
+			return -EINVAL;
+		}
+		break;
+	default:
+		dev_err(ctrl->dev, "ECC algorithm not supported\n");
+		return -EINVAL;
+	}
+
+	dev_info(ctrl->dev, "Using %s with strength %d per 512 byte step\n",
+		 chip->ecc.algo == NAND_ECC_BCH ? "BCH" : "RS",
+		 chip->ecc.strength);
+
+	chip->ecc.bytes = DIV_ROUND_UP(bits_per_step, BITS_PER_BYTE);
+
+	switch (mtd->writesize) {
+	case 256:
+		nand->config |= CONFIG_PS_256;
+		break;
+	case 512:
+		nand->config |= CONFIG_PS_512;
+		break;
+	case 1024:
+		nand->config |= CONFIG_PS_1024;
+		break;
+	case 2048:
+		nand->config |= CONFIG_PS_2048;
+		break;
+	case 4096:
+		nand->config |= CONFIG_PS_4096;
+		break;
+	default:
+		dev_err(ctrl->dev, "Unsupported writesize %d\n",
+			mtd->writesize);
+		return -ENODEV;
+	}
+
+	/* Store complete configuration for HW ECC in config_ecc */
+	nand->config_ecc |= nand->config;
+
+	/* Non-HW ECC read/writes complete OOB */
+	nand->config |= CONFIG_TAG_BYTE_SIZE(mtd->oobsize - 1);
+	writel_relaxed(nand->config, ctrl->regs + CONFIG);
+
+	return 0;
+}
+
+static const struct nand_controller_ops tegra_nand_controller_ops = {
+	.attach_chip = &tegra_nand_attach_chip,
+};
+
+static int tegra_nand_chips_init(struct device *dev,
+				 struct tegra_nand_controller *ctrl)
+{
+	struct device_node *np = dev->of_node;
+	struct device_node *np_nand;
+	int nsels, nchips = of_get_child_count(np);
+	struct tegra_nand_chip *nand;
+	struct mtd_info *mtd;
+	struct nand_chip *chip;
+	int ret;
+	u32 cs;
+
+	if (nchips != 1) {
+		dev_err(dev, "Currently only one NAND chip supported\n");
+		return -EINVAL;
+	}
+
+	np_nand = of_get_next_child(np, NULL);
+
+	nsels = of_property_count_elems_of_size(np_nand, "reg", sizeof(u32));
+	if (nsels != 1) {
+		dev_err(dev, "Missing/invalid reg property\n");
+		return -EINVAL;
+	}
+
+	/* Retrieve CS id, currently only single die NAND supported */
+	ret = of_property_read_u32(np_nand, "reg", &cs);
+	if (ret) {
+		dev_err(dev, "could not retrieve reg property: %d\n", ret);
+		return ret;
+	}
+
+	nand = devm_kzalloc(dev, sizeof(*nand), GFP_KERNEL);
+	if (!nand)
+		return -ENOMEM;
+
+	nand->cs[0] = cs;
+
+	nand->wp_gpio = devm_gpiod_get_optional(dev, "wp", GPIOD_OUT_LOW);
+
+	if (IS_ERR(nand->wp_gpio)) {
+		ret = PTR_ERR(nand->wp_gpio);
+		dev_err(dev, "Failed to request WP GPIO: %d\n", ret);
+		return ret;
+	}
+
+	chip = &nand->chip;
+	chip->controller = &ctrl->controller;
+
+	mtd = nand_to_mtd(chip);
+
+	mtd->dev.parent = dev;
+	mtd->owner = THIS_MODULE;
+
+	nand_set_flash_node(chip, np_nand);
+
+	if (!mtd->name)
+		mtd->name = "tegra_nand";
+
+	chip->options = NAND_NO_SUBPAGE_WRITE | NAND_USE_BOUNCE_BUFFER;
+	chip->exec_op = tegra_nand_exec_op;
+	chip->select_chip = tegra_nand_select_chip;
+	chip->setup_data_interface = tegra_nand_setup_data_interface;
+
+	ret = nand_scan(mtd, 1);
+	if (ret)
+		return ret;
+
+	mtd_ooblayout_ecc(mtd, 0, &nand->ecc);
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(dev, "Failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
+		return ret;
+	}
+
+	ctrl->chip = chip;
+
+	return 0;
+}
+
+static int tegra_nand_probe(struct platform_device *pdev)
+{
+	struct reset_control *rst;
+	struct tegra_nand_controller *ctrl;
+	struct resource *res;
+	int err = 0;
+
+	ctrl = devm_kzalloc(&pdev->dev, sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return -ENOMEM;
+
+	ctrl->dev = &pdev->dev;
+	nand_controller_init(&ctrl->controller);
+	ctrl->controller.ops = &tegra_nand_controller_ops;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctrl->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ctrl->regs))
+		return PTR_ERR(ctrl->regs);
+
+	rst = devm_reset_control_get(&pdev->dev, "nand");
+	if (IS_ERR(rst))
+		return PTR_ERR(rst);
+
+	ctrl->clk = devm_clk_get(&pdev->dev, "nand");
+	if (IS_ERR(ctrl->clk))
+		return PTR_ERR(ctrl->clk);
+
+	err = clk_prepare_enable(ctrl->clk);
+	if (err)
+		return err;
+
+	err = reset_control_reset(rst);
+	if (err) {
+		dev_err(ctrl->dev, "Failed to reset HW: %d\n", err);
+		goto err_disable_clk;
+	}
+
+	writel_relaxed(HWSTATUS_CMD_DEFAULT, ctrl->regs + HWSTATUS_CMD);
+	writel_relaxed(HWSTATUS_MASK_DEFAULT, ctrl->regs + HWSTATUS_MASK);
+	writel_relaxed(INT_MASK, ctrl->regs + IER);
+
+	init_completion(&ctrl->command_complete);
+	init_completion(&ctrl->dma_complete);
+
+	ctrl->irq = platform_get_irq(pdev, 0);
+	err = devm_request_irq(&pdev->dev, ctrl->irq, tegra_nand_irq, 0,
+			       dev_name(&pdev->dev), ctrl);
+	if (err) {
+		dev_err(ctrl->dev, "Failed to get IRQ: %d\n", err);
+		goto err_disable_clk;
+	}
+
+	writel_relaxed(DMA_MST_CTRL_IS_DONE, ctrl->regs + DMA_MST_CTRL);
+
+	err = tegra_nand_chips_init(ctrl->dev, ctrl);
+	if (err)
+		goto err_disable_clk;
+
+	platform_set_drvdata(pdev, ctrl);
+
+	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(ctrl->clk);
+	return err;
+}
+
+static int tegra_nand_remove(struct platform_device *pdev)
+{
+	struct tegra_nand_controller *ctrl = platform_get_drvdata(pdev);
+	struct nand_chip *chip = ctrl->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ret;
+
+	ret = mtd_device_unregister(mtd);
+	if (ret)
+		return ret;
+
+	nand_cleanup(chip);
+
+	clk_disable_unprepare(ctrl->clk);
+
+	return 0;
+}
+
+static const struct of_device_id tegra_nand_of_match[] = {
+	{ .compatible = "nvidia,tegra20-nand" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, tegra_nand_of_match);
+
+static struct platform_driver tegra_nand_driver = {
+	.driver = {
+		.name = "tegra-nand",
+		.of_match_table = tegra_nand_of_match,
+	},
+	.probe = tegra_nand_probe,
+	.remove = tegra_nand_remove,
+};
+module_platform_driver(tegra_nand_driver);
+
+MODULE_DESCRIPTION("NVIDIA Tegra NAND driver");
+MODULE_AUTHOR("Thierry Reding <thierry.reding@nvidia.com>");
+MODULE_AUTHOR("Lucas Stach <dev@lynxeye.de>");
+MODULE_AUTHOR("Stefan Agner <stefan@agner.ch>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index b567d212fe7d..4d61a14fcb65 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -20,7 +20,7 @@
 #include <linux/mtd/nand_ecc.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
-#include <asm/txx9/ndfmc.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 
 /* TXX9 NDFMC Registers */
 #define TXX9_NDFDTR	0x00
@@ -73,7 +73,7 @@ struct txx9ndfmc_drvdata {
 	void __iomem *base;
 	unsigned char hold;	/* in gbusclock */
 	unsigned char spw;	/* in gbusclock */
-	struct nand_hw_control hw_control;
+	struct nand_controller controller;
 };
 
 static struct platform_device *mtd_to_platdev(struct mtd_info *mtd)
@@ -254,23 +254,25 @@ static void txx9ndfmc_initialize(struct platform_device *dev)
 #define TXX9NDFMC_NS_TO_CYC(gbusclk, ns) \
 	DIV_ROUND_UP((ns) * DIV_ROUND_UP(gbusclk, 1000), 1000000)
 
-static int txx9ndfmc_nand_scan(struct mtd_info *mtd)
+static int txx9ndfmc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	int ret;
-
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (!ret) {
-		if (mtd->writesize >= 512) {
-			/* Hardware ECC 6 byte ECC per 512 Byte data */
-			chip->ecc.size = 512;
-			chip->ecc.bytes = 6;
-		}
-		ret = nand_scan_tail(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	if (mtd->writesize >= 512) {
+		chip->ecc.size = 512;
+		chip->ecc.bytes = 6;
+	} else {
+		chip->ecc.size = 256;
+		chip->ecc.bytes = 3;
 	}
-	return ret;
+
+	return 0;
 }
 
+static const struct nand_controller_ops txx9ndfmc_controller_ops = {
+	.attach_chip = txx9ndfmc_attach_chip,
+};
+
 static int __init txx9ndfmc_probe(struct platform_device *dev)
 {
 	struct txx9ndfmc_platform_data *plat = dev_get_platdata(&dev->dev);
@@ -303,7 +305,8 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 	dev_info(&dev->dev, "CLK:%ldMHz HOLD:%d SPW:%d\n",
 		 (gbusclk + 500000) / 1000000, hold, spw);
 
-	nand_hw_control_init(&drvdata->hw_control);
+	nand_controller_init(&drvdata->controller);
+	drvdata->controller.ops = &txx9ndfmc_controller_ops;
 
 	platform_set_drvdata(dev, drvdata);
 	txx9ndfmc_initialize(dev);
@@ -332,12 +335,9 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		chip->ecc.correct = txx9ndfmc_correct_data;
 		chip->ecc.hwctl = txx9ndfmc_enable_hwecc;
 		chip->ecc.mode = NAND_ECC_HW;
-		/* txx9ndfmc_nand_scan will overwrite ecc.size and ecc.bytes */
-		chip->ecc.size = 256;
-		chip->ecc.bytes = 3;
 		chip->ecc.strength = 1;
 		chip->chip_delay = 100;
-		chip->controller = &drvdata->hw_control;
+		chip->controller = &drvdata->controller;
 
 		nand_set_controller_data(chip, txx9_priv);
 		txx9_priv->dev = dev;
@@ -359,14 +359,14 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		if (plat->wide_mask & (1 << i))
 			chip->options |= NAND_BUSWIDTH_16;
 
-		if (txx9ndfmc_nand_scan(mtd)) {
+		if (nand_scan(mtd, 1)) {
 			kfree(txx9_priv->mtdname);
 			kfree(txx9_priv);
 			continue;
 		}
 		mtd->name = txx9_priv->mtdname;
 
-		mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+		mtd_device_register(mtd, NULL, 0);
 		drvdata->mtds[i] = mtd;
 	}
 
diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c
index d5a22fc96878..6f6dcbf9095b 100644
--- a/drivers/mtd/nand/raw/vf610_nfc.c
+++ b/drivers/mtd/nand/raw/vf610_nfc.c
@@ -747,6 +747,69 @@ static void vf610_nfc_init_controller(struct vf610_nfc *nfc)
 	}
 }
 
+static int vf610_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct vf610_nfc *nfc = mtd_to_nfc(mtd);
+
+	vf610_nfc_init_controller(nfc);
+
+	/* Bad block options. */
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	/* Single buffer only, max 256 OOB minus ECC status */
+	if (mtd->writesize + mtd->oobsize > PAGE_2K + OOB_MAX - 8) {
+		dev_err(nfc->dev, "Unsupported flash page size\n");
+		return -ENXIO;
+	}
+
+	if (chip->ecc.mode != NAND_ECC_HW)
+		return 0;
+
+	if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
+		dev_err(nfc->dev, "Unsupported flash with hwecc\n");
+		return -ENXIO;
+	}
+
+	if (chip->ecc.size != mtd->writesize) {
+		dev_err(nfc->dev, "Step size needs to be page size\n");
+		return -ENXIO;
+	}
+
+	/* Only 64 byte ECC layouts known */
+	if (mtd->oobsize > 64)
+		mtd->oobsize = 64;
+
+	/* Use default large page ECC layout defined in NAND core */
+	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	if (chip->ecc.strength == 32) {
+		nfc->ecc_mode = ECC_60_BYTE;
+		chip->ecc.bytes = 60;
+	} else if (chip->ecc.strength == 24) {
+		nfc->ecc_mode = ECC_45_BYTE;
+		chip->ecc.bytes = 45;
+	} else {
+		dev_err(nfc->dev, "Unsupported ECC strength\n");
+		return -ENXIO;
+	}
+
+	chip->ecc.read_page = vf610_nfc_read_page;
+	chip->ecc.write_page = vf610_nfc_write_page;
+	chip->ecc.read_page_raw = vf610_nfc_read_page_raw;
+	chip->ecc.write_page_raw = vf610_nfc_write_page_raw;
+	chip->ecc.read_oob = vf610_nfc_read_oob;
+	chip->ecc.write_oob = vf610_nfc_write_oob;
+
+	chip->ecc.size = PAGE_2K;
+
+	return 0;
+}
+
+static const struct nand_controller_ops vf610_nfc_controller_ops = {
+	.attach_chip = vf610_nfc_attach_chip,
+};
+
 static int vf610_nfc_probe(struct platform_device *pdev)
 {
 	struct vf610_nfc *nfc;
@@ -827,67 +890,9 @@ static int vf610_nfc_probe(struct platform_device *pdev)
 
 	vf610_nfc_preinit_controller(nfc);
 
-	/* first scan to find the device and get the page size */
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err)
-		goto err_disable_clk;
-
-	vf610_nfc_init_controller(nfc);
-
-	/* Bad block options. */
-	if (chip->bbt_options & NAND_BBT_USE_FLASH)
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-	/* Single buffer only, max 256 OOB minus ECC status */
-	if (mtd->writesize + mtd->oobsize > PAGE_2K + OOB_MAX - 8) {
-		dev_err(nfc->dev, "Unsupported flash page size\n");
-		err = -ENXIO;
-		goto err_disable_clk;
-	}
-
-	if (chip->ecc.mode == NAND_ECC_HW) {
-		if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
-			dev_err(nfc->dev, "Unsupported flash with hwecc\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		if (chip->ecc.size != mtd->writesize) {
-			dev_err(nfc->dev, "Step size needs to be page size\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		/* Only 64 byte ECC layouts known */
-		if (mtd->oobsize > 64)
-			mtd->oobsize = 64;
-
-		/* Use default large page ECC layout defined in NAND core */
-		mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
-		if (chip->ecc.strength == 32) {
-			nfc->ecc_mode = ECC_60_BYTE;
-			chip->ecc.bytes = 60;
-		} else if (chip->ecc.strength == 24) {
-			nfc->ecc_mode = ECC_45_BYTE;
-			chip->ecc.bytes = 45;
-		} else {
-			dev_err(nfc->dev, "Unsupported ECC strength\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		chip->ecc.read_page = vf610_nfc_read_page;
-		chip->ecc.write_page = vf610_nfc_write_page;
-		chip->ecc.read_page_raw = vf610_nfc_read_page_raw;
-		chip->ecc.write_page_raw = vf610_nfc_write_page_raw;
-		chip->ecc.read_oob = vf610_nfc_read_oob;
-		chip->ecc.write_oob = vf610_nfc_write_oob;
-
-		chip->ecc.size = PAGE_2K;
-	}
-
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	/* Scan the NAND chip */
+	chip->dummy_controller.ops = &vf610_nfc_controller_ops;
+	err = nand_scan(mtd, 1);
 	if (err)
 		goto err_disable_clk;
 
diff --git a/drivers/mtd/nand/spi/Kconfig b/drivers/mtd/nand/spi/Kconfig
new file mode 100644
index 000000000000..7c37d2929b68
--- /dev/null
+++ b/drivers/mtd/nand/spi/Kconfig
@@ -0,0 +1,7 @@
+menuconfig MTD_SPI_NAND
+	tristate "SPI NAND device Support"
+	select MTD_NAND_CORE
+	depends on SPI_MASTER
+	select SPI_MEM
+	help
+	  This is the framework for the SPI NAND device drivers.
diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile
new file mode 100644
index 000000000000..b74e074b363a
--- /dev/null
+++ b/drivers/mtd/nand/spi/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+spinand-objs := core.o macronix.o micron.o winbond.o
+obj-$(CONFIG_MTD_SPI_NAND) += spinand.o
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
new file mode 100644
index 000000000000..30f83649c481
--- /dev/null
+++ b/drivers/mtd/nand/spi/core.c
@@ -0,0 +1,1155 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016-2017 Micron Technology, Inc.
+ *
+ * Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#define pr_fmt(fmt)	"spi-nand: " fmt
+
+#include <linux/device.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mtd/spinand.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+static void spinand_cache_op_adjust_colum(struct spinand_device *spinand,
+					  const struct nand_page_io_req *req,
+					  u16 *column)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int shift;
+
+	if (nand->memorg.planes_per_lun < 2)
+		return;
+
+	/* The plane number is passed in MSB just above the column address */
+	shift = fls(nand->memorg.pagesize);
+	*column |= req->pos.plane << shift;
+}
+
+static int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val)
+{
+	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(reg,
+						      spinand->scratchbuf);
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (ret)
+		return ret;
+
+	*val = *spinand->scratchbuf;
+	return 0;
+}
+
+static int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val)
+{
+	struct spi_mem_op op = SPINAND_SET_FEATURE_OP(reg,
+						      spinand->scratchbuf);
+
+	*spinand->scratchbuf = val;
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_read_status(struct spinand_device *spinand, u8 *status)
+{
+	return spinand_read_reg_op(spinand, REG_STATUS, status);
+}
+
+static int spinand_get_cfg(struct spinand_device *spinand, u8 *cfg)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	if (WARN_ON(spinand->cur_target < 0 ||
+		    spinand->cur_target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	*cfg = spinand->cfg_cache[spinand->cur_target];
+	return 0;
+}
+
+static int spinand_set_cfg(struct spinand_device *spinand, u8 cfg)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	if (WARN_ON(spinand->cur_target < 0 ||
+		    spinand->cur_target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	if (spinand->cfg_cache[spinand->cur_target] == cfg)
+		return 0;
+
+	ret = spinand_write_reg_op(spinand, REG_CFG, cfg);
+	if (ret)
+		return ret;
+
+	spinand->cfg_cache[spinand->cur_target] = cfg;
+	return 0;
+}
+
+/**
+ * spinand_upd_cfg() - Update the configuration register
+ * @spinand: the spinand device
+ * @mask: the mask encoding the bits to update in the config reg
+ * @val: the new value to apply
+ *
+ * Update the configuration register.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val)
+{
+	int ret;
+	u8 cfg;
+
+	ret = spinand_get_cfg(spinand, &cfg);
+	if (ret)
+		return ret;
+
+	cfg &= ~mask;
+	cfg |= val;
+
+	return spinand_set_cfg(spinand, cfg);
+}
+
+/**
+ * spinand_select_target() - Select a specific NAND target/die
+ * @spinand: the spinand device
+ * @target: the target/die to select
+ *
+ * Select a new target/die. If chip only has one die, this function is a NOOP.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_select_target(struct spinand_device *spinand, unsigned int target)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	if (WARN_ON(target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	if (spinand->cur_target == target)
+		return 0;
+
+	if (nand->memorg.ntargets == 1) {
+		spinand->cur_target = target;
+		return 0;
+	}
+
+	ret = spinand->select_target(spinand, target);
+	if (ret)
+		return ret;
+
+	spinand->cur_target = target;
+	return 0;
+}
+
+static int spinand_init_cfg_cache(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct device *dev = &spinand->spimem->spi->dev;
+	unsigned int target;
+	int ret;
+
+	spinand->cfg_cache = devm_kcalloc(dev,
+					  nand->memorg.ntargets,
+					  sizeof(*spinand->cfg_cache),
+					  GFP_KERNEL);
+	if (!spinand->cfg_cache)
+		return -ENOMEM;
+
+	for (target = 0; target < nand->memorg.ntargets; target++) {
+		ret = spinand_select_target(spinand, target);
+		if (ret)
+			return ret;
+
+		/*
+		 * We use spinand_read_reg_op() instead of spinand_get_cfg()
+		 * here to bypass the config cache.
+		 */
+		ret = spinand_read_reg_op(spinand, REG_CFG,
+					  &spinand->cfg_cache[target]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int spinand_init_quad_enable(struct spinand_device *spinand)
+{
+	bool enable = false;
+
+	if (!(spinand->flags & SPINAND_HAS_QE_BIT))
+		return 0;
+
+	if (spinand->op_templates.read_cache->data.buswidth == 4 ||
+	    spinand->op_templates.write_cache->data.buswidth == 4 ||
+	    spinand->op_templates.update_cache->data.buswidth == 4)
+		enable = true;
+
+	return spinand_upd_cfg(spinand, CFG_QUAD_ENABLE,
+			       enable ? CFG_QUAD_ENABLE : 0);
+}
+
+static int spinand_ecc_enable(struct spinand_device *spinand,
+			      bool enable)
+{
+	return spinand_upd_cfg(spinand, CFG_ECC_ENABLE,
+			       enable ? CFG_ECC_ENABLE : 0);
+}
+
+static int spinand_write_enable_op(struct spinand_device *spinand)
+{
+	struct spi_mem_op op = SPINAND_WR_EN_DIS_OP(true);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_load_page_op(struct spinand_device *spinand,
+				const struct nand_page_io_req *req)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, &req->pos);
+	struct spi_mem_op op = SPINAND_PAGE_READ_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_read_from_cache_op(struct spinand_device *spinand,
+				      const struct nand_page_io_req *req)
+{
+	struct spi_mem_op op = *spinand->op_templates.read_cache;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_page_io_req adjreq = *req;
+	unsigned int nbytes = 0;
+	void *buf = NULL;
+	u16 column = 0;
+	int ret;
+
+	if (req->datalen) {
+		adjreq.datalen = nanddev_page_size(nand);
+		adjreq.dataoffs = 0;
+		adjreq.databuf.in = spinand->databuf;
+		buf = spinand->databuf;
+		nbytes = adjreq.datalen;
+	}
+
+	if (req->ooblen) {
+		adjreq.ooblen = nanddev_per_page_oobsize(nand);
+		adjreq.ooboffs = 0;
+		adjreq.oobbuf.in = spinand->oobbuf;
+		nbytes += nanddev_per_page_oobsize(nand);
+		if (!buf) {
+			buf = spinand->oobbuf;
+			column = nanddev_page_size(nand);
+		}
+	}
+
+	spinand_cache_op_adjust_colum(spinand, &adjreq, &column);
+	op.addr.val = column;
+
+	/*
+	 * Some controllers are limited in term of max RX data size. In this
+	 * case, just repeat the READ_CACHE operation after updating the
+	 * column.
+	 */
+	while (nbytes) {
+		op.data.buf.in = buf;
+		op.data.nbytes = nbytes;
+		ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		ret = spi_mem_exec_op(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		buf += op.data.nbytes;
+		nbytes -= op.data.nbytes;
+		op.addr.val += op.data.nbytes;
+	}
+
+	if (req->datalen)
+		memcpy(req->databuf.in, spinand->databuf + req->dataoffs,
+		       req->datalen);
+
+	if (req->ooblen) {
+		if (req->mode == MTD_OPS_AUTO_OOB)
+			mtd_ooblayout_get_databytes(mtd, req->oobbuf.in,
+						    spinand->oobbuf,
+						    req->ooboffs,
+						    req->ooblen);
+		else
+			memcpy(req->oobbuf.in, spinand->oobbuf + req->ooboffs,
+			       req->ooblen);
+	}
+
+	return 0;
+}
+
+static int spinand_write_to_cache_op(struct spinand_device *spinand,
+				     const struct nand_page_io_req *req)
+{
+	struct spi_mem_op op = *spinand->op_templates.write_cache;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_page_io_req adjreq = *req;
+	unsigned int nbytes = 0;
+	void *buf = NULL;
+	u16 column = 0;
+	int ret;
+
+	memset(spinand->databuf, 0xff,
+	       nanddev_page_size(nand) +
+	       nanddev_per_page_oobsize(nand));
+
+	if (req->datalen) {
+		memcpy(spinand->databuf + req->dataoffs, req->databuf.out,
+		       req->datalen);
+		adjreq.dataoffs = 0;
+		adjreq.datalen = nanddev_page_size(nand);
+		adjreq.databuf.out = spinand->databuf;
+		nbytes = adjreq.datalen;
+		buf = spinand->databuf;
+	}
+
+	if (req->ooblen) {
+		if (req->mode == MTD_OPS_AUTO_OOB)
+			mtd_ooblayout_set_databytes(mtd, req->oobbuf.out,
+						    spinand->oobbuf,
+						    req->ooboffs,
+						    req->ooblen);
+		else
+			memcpy(spinand->oobbuf + req->ooboffs, req->oobbuf.out,
+			       req->ooblen);
+
+		adjreq.ooblen = nanddev_per_page_oobsize(nand);
+		adjreq.ooboffs = 0;
+		nbytes += nanddev_per_page_oobsize(nand);
+		if (!buf) {
+			buf = spinand->oobbuf;
+			column = nanddev_page_size(nand);
+		}
+	}
+
+	spinand_cache_op_adjust_colum(spinand, &adjreq, &column);
+
+	op = *spinand->op_templates.write_cache;
+	op.addr.val = column;
+
+	/*
+	 * Some controllers are limited in term of max TX data size. In this
+	 * case, split the operation into one LOAD CACHE and one or more
+	 * LOAD RANDOM CACHE.
+	 */
+	while (nbytes) {
+		op.data.buf.out = buf;
+		op.data.nbytes = nbytes;
+
+		ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		ret = spi_mem_exec_op(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		buf += op.data.nbytes;
+		nbytes -= op.data.nbytes;
+		op.addr.val += op.data.nbytes;
+
+		/*
+		 * We need to use the RANDOM LOAD CACHE operation if there's
+		 * more than one iteration, because the LOAD operation resets
+		 * the cache to 0xff.
+		 */
+		if (nbytes) {
+			column = op.addr.val;
+			op = *spinand->op_templates.update_cache;
+			op.addr.val = column;
+		}
+	}
+
+	return 0;
+}
+
+static int spinand_program_op(struct spinand_device *spinand,
+			      const struct nand_page_io_req *req)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, &req->pos);
+	struct spi_mem_op op = SPINAND_PROG_EXEC_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_erase_op(struct spinand_device *spinand,
+			    const struct nand_pos *pos)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, pos);
+	struct spi_mem_op op = SPINAND_BLK_ERASE_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_wait(struct spinand_device *spinand, u8 *s)
+{
+	unsigned long timeo =  jiffies + msecs_to_jiffies(400);
+	u8 status;
+	int ret;
+
+	do {
+		ret = spinand_read_status(spinand, &status);
+		if (ret)
+			return ret;
+
+		if (!(status & STATUS_BUSY))
+			goto out;
+	} while (time_before(jiffies, timeo));
+
+	/*
+	 * Extra read, just in case the STATUS_READY bit has changed
+	 * since our last check
+	 */
+	ret = spinand_read_status(spinand, &status);
+	if (ret)
+		return ret;
+
+out:
+	if (s)
+		*s = status;
+
+	return status & STATUS_BUSY ? -ETIMEDOUT : 0;
+}
+
+static int spinand_read_id_op(struct spinand_device *spinand, u8 *buf)
+{
+	struct spi_mem_op op = SPINAND_READID_OP(0, spinand->scratchbuf,
+						 SPINAND_MAX_ID_LEN);
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (!ret)
+		memcpy(buf, spinand->scratchbuf, SPINAND_MAX_ID_LEN);
+
+	return ret;
+}
+
+static int spinand_reset_op(struct spinand_device *spinand)
+{
+	struct spi_mem_op op = SPINAND_RESET_OP;
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (ret)
+		return ret;
+
+	return spinand_wait(spinand, NULL);
+}
+
+static int spinand_lock_block(struct spinand_device *spinand, u8 lock)
+{
+	return spinand_write_reg_op(spinand, REG_BLOCK_LOCK, lock);
+}
+
+static int spinand_check_ecc_status(struct spinand_device *spinand, u8 status)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	if (spinand->eccinfo.get_status)
+		return spinand->eccinfo.get_status(spinand, status);
+
+	switch (status & STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_HAS_BITFLIPS:
+		/*
+		 * We have no way to know exactly how many bitflips have been
+		 * fixed, so let's return the maximum possible value so that
+		 * wear-leveling layers move the data immediately.
+		 */
+		return nand->eccreq.strength;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static int spinand_read_page(struct spinand_device *spinand,
+			     const struct nand_page_io_req *req,
+			     bool ecc_enabled)
+{
+	u8 status;
+	int ret;
+
+	ret = spinand_load_page_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (ret < 0)
+		return ret;
+
+	ret = spinand_read_from_cache_op(spinand, req);
+	if (ret)
+		return ret;
+
+	if (!ecc_enabled)
+		return 0;
+
+	return spinand_check_ecc_status(spinand, status);
+}
+
+static int spinand_write_page(struct spinand_device *spinand,
+			      const struct nand_page_io_req *req)
+{
+	u8 status;
+	int ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_to_cache_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_program_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (!ret && (status & STATUS_PROG_FAILED))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int spinand_mtd_read(struct mtd_info *mtd, loff_t from,
+			    struct mtd_oob_ops *ops)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int max_bitflips = 0;
+	struct nand_io_iter iter;
+	bool enable_ecc = false;
+	bool ecc_failed = false;
+	int ret = 0;
+
+	if (ops->mode != MTD_OPS_RAW && spinand->eccinfo.ooblayout)
+		enable_ecc = true;
+
+	mutex_lock(&spinand->lock);
+
+	nanddev_io_for_each_page(nand, from, ops, &iter) {
+		ret = spinand_select_target(spinand, iter.req.pos.target);
+		if (ret)
+			break;
+
+		ret = spinand_ecc_enable(spinand, enable_ecc);
+		if (ret)
+			break;
+
+		ret = spinand_read_page(spinand, &iter.req, enable_ecc);
+		if (ret < 0 && ret != -EBADMSG)
+			break;
+
+		if (ret == -EBADMSG) {
+			ecc_failed = true;
+			mtd->ecc_stats.failed++;
+			ret = 0;
+		} else {
+			mtd->ecc_stats.corrected += ret;
+			max_bitflips = max_t(unsigned int, max_bitflips, ret);
+		}
+
+		ops->retlen += iter.req.datalen;
+		ops->oobretlen += iter.req.ooblen;
+	}
+
+	mutex_unlock(&spinand->lock);
+
+	if (ecc_failed && !ret)
+		ret = -EBADMSG;
+
+	return ret ? ret : max_bitflips;
+}
+
+static int spinand_mtd_write(struct mtd_info *mtd, loff_t to,
+			     struct mtd_oob_ops *ops)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct nand_io_iter iter;
+	bool enable_ecc = false;
+	int ret = 0;
+
+	if (ops->mode != MTD_OPS_RAW && mtd->ooblayout)
+		enable_ecc = true;
+
+	mutex_lock(&spinand->lock);
+
+	nanddev_io_for_each_page(nand, to, ops, &iter) {
+		ret = spinand_select_target(spinand, iter.req.pos.target);
+		if (ret)
+			break;
+
+		ret = spinand_ecc_enable(spinand, enable_ecc);
+		if (ret)
+			break;
+
+		ret = spinand_write_page(spinand, &iter.req);
+		if (ret)
+			break;
+
+		ops->retlen += iter.req.datalen;
+		ops->oobretlen += iter.req.ooblen;
+	}
+
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static bool spinand_isbad(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_page_io_req req = {
+		.pos = *pos,
+		.ooblen = 2,
+		.ooboffs = 0,
+		.oobbuf.in = spinand->oobbuf,
+		.mode = MTD_OPS_RAW,
+	};
+
+	memset(spinand->oobbuf, 0, 2);
+	spinand_select_target(spinand, pos->target);
+	spinand_read_page(spinand, &req, false);
+	if (spinand->oobbuf[0] != 0xff || spinand->oobbuf[1] != 0xff)
+		return true;
+
+	return false;
+}
+
+static int spinand_mtd_block_isbad(struct mtd_info *mtd, loff_t offs)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_isbad(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_markbad(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_page_io_req req = {
+		.pos = *pos,
+		.ooboffs = 0,
+		.ooblen = 2,
+		.oobbuf.out = spinand->oobbuf,
+	};
+	int ret;
+
+	/* Erase block before marking it bad. */
+	ret = spinand_select_target(spinand, pos->target);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	spinand_erase_op(spinand, pos);
+
+	memset(spinand->oobbuf, 0, 2);
+	return spinand_write_page(spinand, &req);
+}
+
+static int spinand_mtd_block_markbad(struct mtd_info *mtd, loff_t offs)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_markbad(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_erase(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	u8 status;
+	int ret;
+
+	ret = spinand_select_target(spinand, pos->target);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_erase_op(spinand, pos);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (!ret && (status & STATUS_ERASE_FAILED))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int spinand_mtd_erase(struct mtd_info *mtd,
+			     struct erase_info *einfo)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	int ret;
+
+	mutex_lock(&spinand->lock);
+	ret = nanddev_mtd_erase(mtd, einfo);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_mtd_block_isreserved(struct mtd_info *mtd, loff_t offs)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_isreserved(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static const struct nand_ops spinand_ops = {
+	.erase = spinand_erase,
+	.markbad = spinand_markbad,
+	.isbad = spinand_isbad,
+};
+
+static const struct spinand_manufacturer *spinand_manufacturers[] = {
+	&macronix_spinand_manufacturer,
+	&micron_spinand_manufacturer,
+	&winbond_spinand_manufacturer,
+};
+
+static int spinand_manufacturer_detect(struct spinand_device *spinand)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(spinand_manufacturers); i++) {
+		ret = spinand_manufacturers[i]->ops->detect(spinand);
+		if (ret > 0) {
+			spinand->manufacturer = spinand_manufacturers[i];
+			return 0;
+		} else if (ret < 0) {
+			return ret;
+		}
+	}
+
+	return -ENOTSUPP;
+}
+
+static int spinand_manufacturer_init(struct spinand_device *spinand)
+{
+	if (spinand->manufacturer->ops->init)
+		return spinand->manufacturer->ops->init(spinand);
+
+	return 0;
+}
+
+static void spinand_manufacturer_cleanup(struct spinand_device *spinand)
+{
+	/* Release manufacturer private data */
+	if (spinand->manufacturer->ops->cleanup)
+		return spinand->manufacturer->ops->cleanup(spinand);
+}
+
+static const struct spi_mem_op *
+spinand_select_op_variant(struct spinand_device *spinand,
+			  const struct spinand_op_variants *variants)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	for (i = 0; i < variants->nops; i++) {
+		struct spi_mem_op op = variants->ops[i];
+		unsigned int nbytes;
+		int ret;
+
+		nbytes = nanddev_per_page_oobsize(nand) +
+			 nanddev_page_size(nand);
+
+		while (nbytes) {
+			op.data.nbytes = nbytes;
+			ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+			if (ret)
+				break;
+
+			if (!spi_mem_supports_op(spinand->spimem, &op))
+				break;
+
+			nbytes -= op.data.nbytes;
+		}
+
+		if (!nbytes)
+			return &variants->ops[i];
+	}
+
+	return NULL;
+}
+
+/**
+ * spinand_match_and_init() - Try to find a match between a device ID and an
+ *			      entry in a spinand_info table
+ * @spinand: SPI NAND object
+ * @table: SPI NAND device description table
+ * @table_size: size of the device description table
+ *
+ * Should be used by SPI NAND manufacturer drivers when they want to find a
+ * match between a device ID retrieved through the READ_ID command and an
+ * entry in the SPI NAND description table. If a match is found, the spinand
+ * object will be initialized with information provided by the matching
+ * spinand_info entry.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_match_and_init(struct spinand_device *spinand,
+			   const struct spinand_info *table,
+			   unsigned int table_size, u8 devid)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	for (i = 0; i < table_size; i++) {
+		const struct spinand_info *info = &table[i];
+		const struct spi_mem_op *op;
+
+		if (devid != info->devid)
+			continue;
+
+		nand->memorg = table[i].memorg;
+		nand->eccreq = table[i].eccreq;
+		spinand->eccinfo = table[i].eccinfo;
+		spinand->flags = table[i].flags;
+		spinand->select_target = table[i].select_target;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.read_cache);
+		if (!op)
+			return -ENOTSUPP;
+
+		spinand->op_templates.read_cache = op;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.write_cache);
+		if (!op)
+			return -ENOTSUPP;
+
+		spinand->op_templates.write_cache = op;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.update_cache);
+		spinand->op_templates.update_cache = op;
+
+		return 0;
+	}
+
+	return -ENOTSUPP;
+}
+
+static int spinand_detect(struct spinand_device *spinand)
+{
+	struct device *dev = &spinand->spimem->spi->dev;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	ret = spinand_reset_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_read_id_op(spinand, spinand->id.data);
+	if (ret)
+		return ret;
+
+	spinand->id.len = SPINAND_MAX_ID_LEN;
+
+	ret = spinand_manufacturer_detect(spinand);
+	if (ret) {
+		dev_err(dev, "unknown raw ID %*phN\n", SPINAND_MAX_ID_LEN,
+			spinand->id.data);
+		return ret;
+	}
+
+	if (nand->memorg.ntargets > 1 && !spinand->select_target) {
+		dev_err(dev,
+			"SPI NANDs with more than one die must implement ->select_target()\n");
+		return -EINVAL;
+	}
+
+	dev_info(&spinand->spimem->spi->dev,
+		 "%s SPI NAND was found.\n", spinand->manufacturer->name);
+	dev_info(&spinand->spimem->spi->dev,
+		 "%llu MiB, block size: %zu KiB, page size: %zu, OOB size: %u\n",
+		 nanddev_size(nand) >> 20, nanddev_eraseblock_size(nand) >> 10,
+		 nanddev_page_size(nand), nanddev_per_page_oobsize(nand));
+
+	return 0;
+}
+
+static int spinand_noecc_ooblayout_ecc(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *region)
+{
+	return -ERANGE;
+}
+
+static int spinand_noecc_ooblayout_free(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	/* Reserve 2 bytes for the BBM. */
+	region->offset = 2;
+	region->length = 62;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops spinand_noecc_ooblayout = {
+	.ecc = spinand_noecc_ooblayout_ecc,
+	.free = spinand_noecc_ooblayout_free,
+};
+
+static int spinand_init(struct spinand_device *spinand)
+{
+	struct device *dev = &spinand->spimem->spi->dev;
+	struct mtd_info *mtd = spinand_to_mtd(spinand);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	int ret, i;
+
+	/*
+	 * We need a scratch buffer because the spi_mem interface requires that
+	 * buf passed in spi_mem_op->data.buf be DMA-able.
+	 */
+	spinand->scratchbuf = kzalloc(SPINAND_MAX_ID_LEN, GFP_KERNEL);
+	if (!spinand->scratchbuf)
+		return -ENOMEM;
+
+	ret = spinand_detect(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	/*
+	 * Use kzalloc() instead of devm_kzalloc() here, because some drivers
+	 * may use this buffer for DMA access.
+	 * Memory allocated by devm_ does not guarantee DMA-safe alignment.
+	 */
+	spinand->databuf = kzalloc(nanddev_page_size(nand) +
+			       nanddev_per_page_oobsize(nand),
+			       GFP_KERNEL);
+	if (!spinand->databuf) {
+		ret = -ENOMEM;
+		goto err_free_bufs;
+	}
+
+	spinand->oobbuf = spinand->databuf + nanddev_page_size(nand);
+
+	ret = spinand_init_cfg_cache(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_init_quad_enable(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_upd_cfg(spinand, CFG_OTP_ENABLE, 0);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_manufacturer_init(spinand);
+	if (ret) {
+		dev_err(dev,
+			"Failed to initialize the SPI NAND chip (err = %d)\n",
+			ret);
+		goto err_free_bufs;
+	}
+
+	/* After power up, all blocks are locked, so unlock them here. */
+	for (i = 0; i < nand->memorg.ntargets; i++) {
+		ret = spinand_select_target(spinand, i);
+		if (ret)
+			goto err_free_bufs;
+
+		ret = spinand_lock_block(spinand, BL_ALL_UNLOCKED);
+		if (ret)
+			goto err_free_bufs;
+	}
+
+	ret = nanddev_init(nand, &spinand_ops, THIS_MODULE);
+	if (ret)
+		goto err_manuf_cleanup;
+
+	/*
+	 * Right now, we don't support ECC, so let the whole oob
+	 * area is available for user.
+	 */
+	mtd->_read_oob = spinand_mtd_read;
+	mtd->_write_oob = spinand_mtd_write;
+	mtd->_block_isbad = spinand_mtd_block_isbad;
+	mtd->_block_markbad = spinand_mtd_block_markbad;
+	mtd->_block_isreserved = spinand_mtd_block_isreserved;
+	mtd->_erase = spinand_mtd_erase;
+
+	if (spinand->eccinfo.ooblayout)
+		mtd_set_ooblayout(mtd, spinand->eccinfo.ooblayout);
+	else
+		mtd_set_ooblayout(mtd, &spinand_noecc_ooblayout);
+
+	ret = mtd_ooblayout_count_freebytes(mtd);
+	if (ret < 0)
+		goto err_cleanup_nanddev;
+
+	mtd->oobavail = ret;
+
+	return 0;
+
+err_cleanup_nanddev:
+	nanddev_cleanup(nand);
+
+err_manuf_cleanup:
+	spinand_manufacturer_cleanup(spinand);
+
+err_free_bufs:
+	kfree(spinand->databuf);
+	kfree(spinand->scratchbuf);
+	return ret;
+}
+
+static void spinand_cleanup(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	nanddev_cleanup(nand);
+	spinand_manufacturer_cleanup(spinand);
+	kfree(spinand->databuf);
+	kfree(spinand->scratchbuf);
+}
+
+static int spinand_probe(struct spi_mem *mem)
+{
+	struct spinand_device *spinand;
+	struct mtd_info *mtd;
+	int ret;
+
+	spinand = devm_kzalloc(&mem->spi->dev, sizeof(*spinand),
+			       GFP_KERNEL);
+	if (!spinand)
+		return -ENOMEM;
+
+	spinand->spimem = mem;
+	spi_mem_set_drvdata(mem, spinand);
+	spinand_set_of_node(spinand, mem->spi->dev.of_node);
+	mutex_init(&spinand->lock);
+	mtd = spinand_to_mtd(spinand);
+	mtd->dev.parent = &mem->spi->dev;
+
+	ret = spinand_init(spinand);
+	if (ret)
+		return ret;
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret)
+		goto err_spinand_cleanup;
+
+	return 0;
+
+err_spinand_cleanup:
+	spinand_cleanup(spinand);
+
+	return ret;
+}
+
+static int spinand_remove(struct spi_mem *mem)
+{
+	struct spinand_device *spinand;
+	struct mtd_info *mtd;
+	int ret;
+
+	spinand = spi_mem_get_drvdata(mem);
+	mtd = spinand_to_mtd(spinand);
+
+	ret = mtd_device_unregister(mtd);
+	if (ret)
+		return ret;
+
+	spinand_cleanup(spinand);
+
+	return 0;
+}
+
+static const struct spi_device_id spinand_ids[] = {
+	{ .name = "spi-nand" },
+	{ /* sentinel */ },
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id spinand_of_ids[] = {
+	{ .compatible = "spi-nand" },
+	{ /* sentinel */ },
+};
+#endif
+
+static struct spi_mem_driver spinand_drv = {
+	.spidrv = {
+		.id_table = spinand_ids,
+		.driver = {
+			.name = "spi-nand",
+			.of_match_table = of_match_ptr(spinand_of_ids),
+		},
+	},
+	.probe = spinand_probe,
+	.remove = spinand_remove,
+};
+module_spi_mem_driver(spinand_drv);
+
+MODULE_DESCRIPTION("SPI NAND framework");
+MODULE_AUTHOR("Peter Pan<peterpandong@micron.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c
new file mode 100644
index 000000000000..98f6b9c4b684
--- /dev/null
+++ b/drivers/mtd/nand/spi/macronix.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Macronix
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_MACRONIX		0xC2
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int mx35lfxge4ab_ooblayout_ecc(struct mtd_info *mtd, int section,
+				      struct mtd_oob_region *region)
+{
+	return -ERANGE;
+}
+
+static int mx35lfxge4ab_ooblayout_free(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 2;
+	region->length = mtd->oobsize - 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops mx35lfxge4ab_ooblayout = {
+	.ecc = mx35lfxge4ab_ooblayout_ecc,
+	.free = mx35lfxge4ab_ooblayout_free,
+};
+
+static int mx35lf1ge4ab_get_eccsr(struct spinand_device *spinand, u8 *eccsr)
+{
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0x7c, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_DUMMY(1, 1),
+					  SPI_MEM_OP_DATA_IN(1, eccsr, 1));
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int mx35lf1ge4ab_ecc_get_status(struct spinand_device *spinand,
+				       u8 status)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	u8 eccsr;
+
+	switch (status & STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	case STATUS_ECC_HAS_BITFLIPS:
+		/*
+		 * Let's try to retrieve the real maximum number of bitflips
+		 * in order to avoid forcing the wear-leveling layer to move
+		 * data around if it's not necessary.
+		 */
+		if (mx35lf1ge4ab_get_eccsr(spinand, &eccsr))
+			return nand->eccreq.strength;
+
+		if (WARN_ON(eccsr > nand->eccreq.strength || !eccsr))
+			return nand->eccreq.strength;
+
+		return eccsr;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct spinand_info macronix_spinand_table[] = {
+	SPINAND_INFO("MX35LF1GE4AB", 0x12,
+		     NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 1),
+		     NAND_ECCREQ(4, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout,
+				     mx35lf1ge4ab_ecc_get_status)),
+	SPINAND_INFO("MX35LF2GE4AB", 0x22,
+		     NAND_MEMORG(1, 2048, 64, 64, 2048, 2, 1, 1),
+		     NAND_ECCREQ(4, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL)),
+};
+
+static int macronix_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Macronix SPI NAND read ID needs a dummy byte, so the first byte in
+	 * raw_id is garbage.
+	 */
+	if (id[1] != SPINAND_MFR_MACRONIX)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, macronix_spinand_table,
+				     ARRAY_SIZE(macronix_spinand_table),
+				     id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static const struct spinand_manufacturer_ops macronix_spinand_manuf_ops = {
+	.detect = macronix_spinand_detect,
+};
+
+const struct spinand_manufacturer macronix_spinand_manufacturer = {
+	.id = SPINAND_MFR_MACRONIX,
+	.name = "Macronix",
+	.ops = &macronix_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/nand/spi/micron.c b/drivers/mtd/nand/spi/micron.c
new file mode 100644
index 000000000000..9c4381d6847b
--- /dev/null
+++ b/drivers/mtd/nand/spi/micron.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2017 Micron Technology, Inc.
+ *
+ * Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_MICRON		0x2c
+
+#define MICRON_STATUS_ECC_MASK		GENMASK(7, 4)
+#define MICRON_STATUS_ECC_NO_BITFLIPS	(0 << 4)
+#define MICRON_STATUS_ECC_1TO3_BITFLIPS	(1 << 4)
+#define MICRON_STATUS_ECC_4TO6_BITFLIPS	(3 << 4)
+#define MICRON_STATUS_ECC_7TO8_BITFLIPS	(5 << 4)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int mt29f2g01abagd_ooblayout_ecc(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 64;
+	region->length = 64;
+
+	return 0;
+}
+
+static int mt29f2g01abagd_ooblayout_free(struct mtd_info *mtd, int section,
+					 struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	/* Reserve 2 bytes for the BBM. */
+	region->offset = 2;
+	region->length = 62;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops mt29f2g01abagd_ooblayout = {
+	.ecc = mt29f2g01abagd_ooblayout_ecc,
+	.free = mt29f2g01abagd_ooblayout_free,
+};
+
+static int mt29f2g01abagd_ecc_get_status(struct spinand_device *spinand,
+					 u8 status)
+{
+	switch (status & MICRON_STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	case MICRON_STATUS_ECC_1TO3_BITFLIPS:
+		return 3;
+
+	case MICRON_STATUS_ECC_4TO6_BITFLIPS:
+		return 6;
+
+	case MICRON_STATUS_ECC_7TO8_BITFLIPS:
+		return 8;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct spinand_info micron_spinand_table[] = {
+	SPINAND_INFO("MT29F2G01ABAGD", 0x24,
+		     NAND_MEMORG(1, 2048, 128, 64, 2048, 2, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&mt29f2g01abagd_ooblayout,
+				     mt29f2g01abagd_ecc_get_status)),
+};
+
+static int micron_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Micron SPI NAND read ID need a dummy byte,
+	 * so the first byte in raw_id is dummy.
+	 */
+	if (id[1] != SPINAND_MFR_MICRON)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, micron_spinand_table,
+				     ARRAY_SIZE(micron_spinand_table), id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static const struct spinand_manufacturer_ops micron_spinand_manuf_ops = {
+	.detect = micron_spinand_detect,
+};
+
+const struct spinand_manufacturer micron_spinand_manufacturer = {
+	.id = SPINAND_MFR_MICRON,
+	.name = "Micron",
+	.ops = &micron_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
new file mode 100644
index 000000000000..67baa1b32c00
--- /dev/null
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017 exceet electronics GmbH
+ *
+ * Authors:
+ *	Frieder Schrempf <frieder.schrempf@exceet.de>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_WINBOND		0xEF
+
+#define WINBOND_CFG_BUF_READ		BIT(3)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int w25m02gv_ooblayout_ecc(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section) + 8;
+	region->length = 8;
+
+	return 0;
+}
+
+static int w25m02gv_ooblayout_free(struct mtd_info *mtd, int section,
+				   struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section) + 2;
+	region->length = 6;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops w25m02gv_ooblayout = {
+	.ecc = w25m02gv_ooblayout_ecc,
+	.free = w25m02gv_ooblayout_free,
+};
+
+static int w25m02gv_select_target(struct spinand_device *spinand,
+				  unsigned int target)
+{
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0xc2, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_NO_DUMMY,
+					  SPI_MEM_OP_DATA_OUT(1,
+							spinand->scratchbuf,
+							1));
+
+	*spinand->scratchbuf = target;
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static const struct spinand_info winbond_spinand_table[] = {
+	SPINAND_INFO("W25M02GV", 0xAB,
+		     NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 2),
+		     NAND_ECCREQ(1, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL),
+		     SPINAND_SELECT_TARGET(w25m02gv_select_target)),
+};
+
+/**
+ * winbond_spinand_detect - initialize device related part in spinand_device
+ * struct if it is a Winbond device.
+ * @spinand: SPI NAND device structure
+ */
+static int winbond_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Winbond SPI NAND read ID need a dummy byte,
+	 * so the first byte in raw_id is dummy.
+	 */
+	if (id[1] != SPINAND_MFR_WINBOND)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, winbond_spinand_table,
+				     ARRAY_SIZE(winbond_spinand_table), id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static int winbond_spinand_init(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	/*
+	 * Make sure all dies are in buffer read mode and not continuous read
+	 * mode.
+	 */
+	for (i = 0; i < nand->memorg.ntargets; i++) {
+		spinand_select_target(spinand, i);
+		spinand_upd_cfg(spinand, WINBOND_CFG_BUF_READ,
+				WINBOND_CFG_BUF_READ);
+	}
+
+	return 0;
+}
+
+static const struct spinand_manufacturer_ops winbond_spinand_manuf_ops = {
+	.detect = winbond_spinand_detect,
+	.init = winbond_spinand_init,
+};
+
+const struct spinand_manufacturer winbond_spinand_manufacturer = {
+	.id = SPINAND_MFR_WINBOND,
+	.name = "Winbond",
+	.ops = &winbond_spinand_manuf_ops,
+};
diff --git a/drivers/mtd/nftlmount.c b/drivers/mtd/nftlmount.c
index 27184e3874db..91b7fb326f9a 100644
--- a/drivers/mtd/nftlmount.c
+++ b/drivers/mtd/nftlmount.c
@@ -577,7 +577,7 @@ static int get_fold_mark(struct NFTLrecord *nftl, unsigned int block)
 int NFTL_mount(struct NFTLrecord *s)
 {
 	int i;
-	unsigned int first_logical_block, logical_block, rep_block, nb_erases, erase_mark;
+	unsigned int first_logical_block, logical_block, rep_block, erase_mark;
 	unsigned int block, first_block, is_first_block;
 	int chain_length, do_format_chain;
 	struct nftl_uci0 h0;
@@ -621,7 +621,6 @@ int NFTL_mount(struct NFTLrecord *s)
 
 				logical_block = le16_to_cpu ((h0.VirtUnitNum | h0.SpareVirtUnitNum));
 				rep_block = le16_to_cpu ((h0.ReplUnitNum | h0.SpareReplUnitNum));
-				nb_erases = le32_to_cpu (h1.WearInfo);
 				erase_mark = le16_to_cpu ((h1.EraseMark | h1.EraseMark1));
 
 				is_first_block = !(logical_block >> 15);
diff --git a/drivers/mtd/parsers/parser_trx.c b/drivers/mtd/parsers/parser_trx.c
index 17ac33599783..4a89a68622fe 100644
--- a/drivers/mtd/parsers/parser_trx.c
+++ b/drivers/mtd/parsers/parser_trx.c
@@ -116,9 +116,16 @@ static int parser_trx_parse(struct mtd_info *mtd,
 	return i;
 };
 
+static const struct of_device_id mtd_parser_trx_of_match_table[] = {
+	{ .compatible = "brcm,trx" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtd_parser_trx_of_match_table);
+
 static struct mtd_part_parser mtd_parser_trx = {
 	.parse_fn = parser_trx_parse,
 	.name = "trx",
+	.of_match_table = mtd_parser_trx_of_match_table,
 };
 module_mtd_part_parser(mtd_parser_trx);
 
diff --git a/drivers/mtd/spi-nor/atmel-quadspi.c b/drivers/mtd/spi-nor/atmel-quadspi.c
index 6c5708bacad8..820048726b4f 100644
--- a/drivers/mtd/spi-nor/atmel-quadspi.c
+++ b/drivers/mtd/spi-nor/atmel-quadspi.c
@@ -34,7 +34,7 @@
 #include <linux/of.h>
 
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 /* QSPI register offsets */
 #define QSPI_CR      0x0000  /* Control Register */
@@ -737,6 +737,26 @@ static int atmel_qspi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused atmel_qspi_suspend(struct device *dev)
+{
+	struct atmel_qspi *aq = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(aq->clk);
+
+	return 0;
+}
+
+static int __maybe_unused atmel_qspi_resume(struct device *dev)
+{
+	struct atmel_qspi *aq = dev_get_drvdata(dev);
+
+	clk_prepare_enable(aq->clk);
+
+	return atmel_qspi_init(aq);
+}
+
+static SIMPLE_DEV_PM_OPS(atmel_qspi_pm_ops, atmel_qspi_suspend,
+			 atmel_qspi_resume);
 
 static const struct of_device_id atmel_qspi_dt_ids[] = {
 	{ .compatible = "atmel,sama5d2-qspi" },
@@ -749,6 +769,7 @@ static struct platform_driver atmel_qspi_driver = {
 	.driver = {
 		.name	= "atmel_qspi",
 		.of_match_table	= atmel_qspi_dt_ids,
+		.pm	= &atmel_qspi_pm_ops,
 	},
 	.probe		= atmel_qspi_probe,
 	.remove		= atmel_qspi_remove,
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index d7e10b36a0b9..8e714fbfa521 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -525,15 +525,14 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor, u8 *rxbuf,
 	       reg_base + CQSPI_REG_INDIRECTRD);
 
 	while (remaining > 0) {
-		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
-						  msecs_to_jiffies
-						  (CQSPI_READ_TIMEOUT_MS));
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+				msecs_to_jiffies(CQSPI_READ_TIMEOUT_MS)))
+			ret = -ETIMEDOUT;
 
 		bytes_to_read = cqspi_get_rd_sram_level(cqspi);
 
-		if (!ret && bytes_to_read == 0) {
+		if (ret && bytes_to_read == 0) {
 			dev_err(nor->dev, "Indirect read timeout, no bytes\n");
-			ret = -ETIMEDOUT;
 			goto failrd;
 		}
 
@@ -649,10 +648,8 @@ static int cqspi_indirect_write_execute(struct spi_nor *nor, loff_t to_addr,
 		iowrite32_rep(cqspi->ahb_base, txbuf,
 			      DIV_ROUND_UP(write_bytes, 4));
 
-		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
-						  msecs_to_jiffies
-						  (CQSPI_TIMEOUT_MS));
-		if (!ret) {
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+					msecs_to_jiffies(CQSPI_TIMEOUT_MS))) {
 			dev_err(nor->dev, "Indirect write timeout\n");
 			ret = -ETIMEDOUT;
 			goto failwr;
@@ -988,9 +985,8 @@ static int cqspi_direct_read_execute(struct spi_nor *nor, u_char *buf,
 	}
 
 	dma_async_issue_pending(cqspi->rx_chan);
-	ret = wait_for_completion_timeout(&cqspi->rx_dma_complete,
-					  msecs_to_jiffies(len));
-	if (ret <= 0) {
+	if (!wait_for_completion_timeout(&cqspi->rx_dma_complete,
+					 msecs_to_jiffies(len))) {
 		dmaengine_terminate_sync(cqspi->rx_chan);
 		dev_err(nor->dev, "DMA wait_for_completion_timeout\n");
 		ret = -ETIMEDOUT;
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index d2cbfc27826e..af0a22019516 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -908,7 +908,7 @@ struct intel_spi *intel_spi_probe(struct device *dev,
 	if (!ispi->writeable || !writeable)
 		ispi->nor.mtd.flags &= ~MTD_WRITEABLE;
 
-	ret = mtd_device_parse_register(&ispi->nor.mtd, NULL, NULL, &part, 1);
+	ret = mtd_device_register(&ispi->nor.mtd, &part, 1);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c
index 15374216d4d9..0c9094ec5966 100644
--- a/drivers/mtd/spi-nor/nxp-spifi.c
+++ b/drivers/mtd/spi-nor/nxp-spifi.c
@@ -436,6 +436,7 @@ static int nxp_spifi_probe(struct platform_device *pdev)
 	}
 
 	ret = nxp_spifi_setup_flash(spifi, flash_np);
+	of_node_put(flash_np);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to setup flash chip\n");
 		goto dis_clks;
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index d9c368c44194..f028277fb1ce 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -2757,8 +2757,18 @@ static int spi_nor_init(struct spi_nor *nor)
 
 	if ((nor->addr_width == 4) &&
 	    (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) &&
-	    !(nor->info->flags & SPI_NOR_4B_OPCODES))
+	    !(nor->info->flags & SPI_NOR_4B_OPCODES)) {
+		/*
+		 * If the RESET# pin isn't hooked up properly, or the system
+		 * otherwise doesn't perform a reset command in the boot
+		 * sequence, it's impossible to 100% protect against unexpected
+		 * reboots (e.g., crashes). Warn the user (or hopefully, system
+		 * designer) that this is bad.
+		 */
+		WARN_ONCE(nor->flags & SNOR_F_BROKEN_RESET,
+			  "enabling reset hack; may not recover from unexpected reboots\n");
 		set_4byte(nor, nor->info, 1);
+	}
 
 	return 0;
 }
@@ -2781,7 +2791,8 @@ void spi_nor_restore(struct spi_nor *nor)
 	/* restore the addressing mode */
 	if ((nor->addr_width == 4) &&
 	    (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) &&
-	    !(nor->info->flags & SPI_NOR_4B_OPCODES))
+	    !(nor->info->flags & SPI_NOR_4B_OPCODES) &&
+	    (nor->flags & SNOR_F_BROKEN_RESET))
 		set_4byte(nor, nor->info, 0);
 }
 EXPORT_SYMBOL_GPL(spi_nor_restore);
@@ -2911,6 +2922,9 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 		params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
 	}
 
+	if (of_property_read_bool(np, "broken-flash-reset"))
+		nor->flags |= SNOR_F_BROKEN_RESET;
+
 	/* Some devices cannot do fast-read, no matter what DT tells us */
 	if (info->flags & SPI_NOR_NO_FR)
 		params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST;
diff --git a/drivers/mtd/spi-nor/stm32-quadspi.c b/drivers/mtd/spi-nor/stm32-quadspi.c
index 72553506a00b..13e9fc961d3b 100644
--- a/drivers/mtd/spi-nor/stm32-quadspi.c
+++ b/drivers/mtd/spi-nor/stm32-quadspi.c
@@ -355,7 +355,7 @@ static int stm32_qspi_read_reg(struct spi_nor *nor,
 	struct device *dev = flash->qspi->dev;
 	struct stm32_qspi_cmd cmd;
 
-	dev_dbg(dev, "read_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+	dev_dbg(dev, "read_reg: cmd:%#.2x buf:%pK len:%#x\n", opcode, buf, len);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode = opcode;
@@ -376,7 +376,7 @@ static int stm32_qspi_write_reg(struct spi_nor *nor, u8 opcode,
 	struct device *dev = flash->qspi->dev;
 	struct stm32_qspi_cmd cmd;
 
-	dev_dbg(dev, "write_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+	dev_dbg(dev, "write_reg: cmd:%#.2x buf:%pK len:%#x\n", opcode, buf, len);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode = opcode;
@@ -398,7 +398,7 @@ static ssize_t stm32_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
 	struct stm32_qspi_cmd cmd;
 	int err;
 
-	dev_dbg(qspi->dev, "read(%#.2x): buf:%p from:%#.8x len:%#zx\n",
+	dev_dbg(qspi->dev, "read(%#.2x): buf:%pK from:%#.8x len:%#zx\n",
 		nor->read_opcode, buf, (u32)from, len);
 
 	memset(&cmd, 0, sizeof(cmd));
diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index b6d735bf8011..342ae08ec3c2 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -153,9 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count,
 static void dayna_block_output(struct net_device *dev, int count,
 			       const unsigned char *buf, int start_page);
 
-#define memcpy_fromio(a, b, c)	memcpy((a), (void *)(b), (c))
-#define memcpy_toio(a, b, c)	memcpy((void *)(a), (b), (c))
-
 #define memcmp_withio(a, b, c)	memcmp((a), (void *)(b), (c))
 
 /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
@@ -239,7 +236,7 @@ static enum mac8390_access mac8390_testio(unsigned long membase)
 	unsigned long outdata = 0xA5A0B5B0;
 	unsigned long indata =  0x00000000;
 	/* Try writing 32 bits */
-	memcpy_toio(membase, &outdata, 4);
+	memcpy_toio((void __iomem *)membase, &outdata, 4);
 	/* Now compare them */
 	if (memcmp_withio(&outdata, membase, 4) == 0)
 		return ACCESS_32;
@@ -711,7 +708,7 @@ static void sane_get_8390_hdr(struct net_device *dev,
 			      struct e8390_pkt_hdr *hdr, int ring_page)
 {
 	unsigned long hdr_start = (ring_page - WD_START_PG)<<8;
-	memcpy_fromio(hdr, dev->mem_start + hdr_start, 4);
+	memcpy_fromio(hdr, (void __iomem *)dev->mem_start + hdr_start, 4);
 	/* Fix endianness */
 	hdr->count = swab16(hdr->count);
 }
@@ -725,13 +722,16 @@ static void sane_block_input(struct net_device *dev, int count,
 	if (xfer_start + count > ei_status.rmem_end) {
 		/* We must wrap the input move. */
 		int semi_count = ei_status.rmem_end - xfer_start;
-		memcpy_fromio(skb->data, dev->mem_start + xfer_base,
+		memcpy_fromio(skb->data,
+			      (void __iomem *)dev->mem_start + xfer_base,
 			      semi_count);
 		count -= semi_count;
-		memcpy_fromio(skb->data + semi_count, ei_status.rmem_start,
-			      count);
+		memcpy_fromio(skb->data + semi_count,
+			      (void __iomem *)ei_status.rmem_start, count);
 	} else {
-		memcpy_fromio(skb->data, dev->mem_start + xfer_base, count);
+		memcpy_fromio(skb->data,
+			      (void __iomem *)dev->mem_start + xfer_base,
+			      count);
 	}
 }
 
@@ -740,7 +740,7 @@ static void sane_block_output(struct net_device *dev, int count,
 {
 	long shmem = (start_page - WD_START_PG)<<8;
 
-	memcpy_toio(dev->mem_start + shmem, buf, count);
+	memcpy_toio((void __iomem *)dev->mem_start + shmem, buf, count);
 }
 
 /* dayna block input/output */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 956860a69797..3bdab972420b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -762,7 +762,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 
 	hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC));
 	hw_atl_rpfl2multicast_flr_en_set(self,
-					 IS_FILTER_ENABLED(IFF_MULTICAST), 0);
+					 IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
 
 	hw_atl_rpfl2_accept_all_mc_packets_set(self,
 					       IS_FILTER_ENABLED(IFF_ALLMULTI));
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 5d08d2aeb172..e337da6ba2a4 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1083,6 +1083,8 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 	lmac->dmacs_count = (RX_DMAC_COUNT / bgx->lmac_count);
 	lmac->dmacs = kcalloc(lmac->dmacs_count, sizeof(*lmac->dmacs),
 			      GFP_KERNEL);
+	if (!lmac->dmacs)
+		return -ENOMEM;
 
 	/* Enable lmac */
 	bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 00fc5f1afb1d..7dddb9e748b8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -1038,10 +1038,8 @@ static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb,
 	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, qid_filterid));
 	req->local_port = cpu_to_be16(f->fs.val.lport);
 	req->peer_port = cpu_to_be16(f->fs.val.fport);
-	req->local_ip = f->fs.val.lip[0] | f->fs.val.lip[1] << 8 |
-		f->fs.val.lip[2] << 16 | f->fs.val.lip[3] << 24;
-	req->peer_ip = f->fs.val.fip[0] | f->fs.val.fip[1] << 8 |
-		f->fs.val.fip[2] << 16 | f->fs.val.fip[3] << 24;
+	memcpy(&req->local_ip, f->fs.val.lip, 4);
+	memcpy(&req->peer_ip, f->fs.val.fip, 4);
 	req->opt0 = cpu_to_be64(NAGLE_V(f->fs.newvlan == VLAN_REMOVE ||
 					f->fs.newvlan == VLAN_REWRITE) |
 				DELACK_V(f->fs.hitcnts) |
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index eb9eb7aa953a..405236cf0b04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -858,8 +858,6 @@ struct mlx5e_profile {
 		mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 		mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
 	} rx_handlers;
-	void	(*netdev_registered_init)(struct mlx5e_priv *priv);
-	void    (*netdev_registered_remove)(struct mlx5e_priv *priv);
 	int	max_tc;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index e33afa8d2417..722998d68564 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -443,16 +443,12 @@ static int mlx5e_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app)
 	bool is_new;
 	int err;
 
-	if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
-		return -EINVAL;
-
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
-		return -EINVAL;
-
-	if (!MLX5_DSCP_SUPPORTED(priv->mdev))
-		return -EINVAL;
+	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) ||
+	    !MLX5_DSCP_SUPPORTED(priv->mdev))
+		return -EOPNOTSUPP;
 
-	if (app->protocol >= MLX5E_MAX_DSCP)
+	if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) ||
+	    (app->protocol >= MLX5E_MAX_DSCP))
 		return -EINVAL;
 
 	/* Save the old entry info */
@@ -500,16 +496,12 @@ static int mlx5e_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app)
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int err;
 
-	if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP)
-		return -EINVAL;
-
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
-		return -EINVAL;
-
-	if (!MLX5_DSCP_SUPPORTED(priv->mdev))
-		return -EINVAL;
+	if  (!MLX5_CAP_GEN(priv->mdev, vport_group_manager) ||
+	     !MLX5_DSCP_SUPPORTED(priv->mdev))
+		return -EOPNOTSUPP;
 
-	if (app->protocol >= MLX5E_MAX_DSCP)
+	if ((app->selector != IEEE_8021QAZ_APP_SEL_DSCP) ||
+	    (app->protocol >= MLX5E_MAX_DSCP))
 		return -EINVAL;
 
 	/* Skip if no dscp app entry */
@@ -1146,7 +1138,7 @@ static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state)
 {
 	int err;
 
-	err =  mlx5_set_trust_state(priv->mdev, trust_state);
+	err = mlx5_set_trust_state(priv->mdev, trust_state);
 	if (err)
 		return err;
 	priv->dcbx_dp.trust_state = trust_state;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3a2c4e548226..dfbcda0d0e08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1970,15 +1970,15 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
 {
 	struct mlx5_core_dev *fmdev, *pmdev;
-	u16 func_id, peer_id;
+	u64 fsystem_guid, psystem_guid;
 
 	fmdev = priv->mdev;
 	pmdev = peer_priv->mdev;
 
-	func_id = (u16)((fmdev->pdev->bus->number << 8) | PCI_SLOT(fmdev->pdev->devfn));
-	peer_id = (u16)((pmdev->pdev->bus->number << 8) | PCI_SLOT(pmdev->pdev->devfn));
+	mlx5_query_nic_vport_system_image_guid(fmdev, &fsystem_guid);
+	mlx5_query_nic_vport_system_image_guid(pmdev, &psystem_guid);
 
-	return (func_id == peer_id);
+	return (fsystem_guid == psystem_guid);
 }
 
 static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 358edab9e72e..3e34cb8ac1d3 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2086,14 +2086,16 @@ static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
 		int i;
 
 		for (i = 0; i < cpsw->data.slaves; i++) {
-			if (vid == cpsw->slaves[i].port_vlan)
-				return -EINVAL;
+			if (vid == cpsw->slaves[i].port_vlan) {
+				ret = -EINVAL;
+				goto err;
+			}
 		}
 	}
 
 	dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid);
 	ret = cpsw_add_vlan_ale_entry(priv, vid);
-
+err:
 	pm_runtime_put(cpsw->dev);
 	return ret;
 }
@@ -2119,22 +2121,17 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
 
 		for (i = 0; i < cpsw->data.slaves; i++) {
 			if (vid == cpsw->slaves[i].port_vlan)
-				return -EINVAL;
+				goto err;
 		}
 	}
 
 	dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid);
 	ret = cpsw_ale_del_vlan(cpsw->ale, vid, 0);
-	if (ret != 0)
-		return ret;
-
-	ret = cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
-				 HOST_PORT_NUM, ALE_VLAN, vid);
-	if (ret != 0)
-		return ret;
-
-	ret = cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
-				 0, ALE_VLAN, vid);
+	ret |= cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
+				  HOST_PORT_NUM, ALE_VLAN, vid);
+	ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
+				  0, ALE_VLAN, vid);
+err:
 	pm_runtime_put(cpsw->dev);
 	return ret;
 }
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 93dc05c194d3..5766225a4ce1 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -394,7 +394,7 @@ int cpsw_ale_del_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask,
 
 	idx = cpsw_ale_match_addr(ale, addr, (flags & ALE_VLAN) ? vid : 0);
 	if (idx < 0)
-		return -EINVAL;
+		return -ENOENT;
 
 	cpsw_ale_read(ale, idx, ale_entry);
 
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 2d8812dd1534..9dd2ca62d84a 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -894,7 +894,6 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 				  struct sk_buff *skb,
 				  struct sk_buff_head *list)
 {
-	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *nskb;
 
@@ -903,15 +902,16 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 			RING_GET_RESPONSE(&queue->rx, ++cons);
 		skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
 
-		if (shinfo->nr_frags == MAX_SKB_FRAGS) {
+		if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) {
 			unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 
 			BUG_ON(pull_to <= skb_headlen(skb));
 			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 		}
-		BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
+		BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS);
 
-		skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag),
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				skb_frag_page(nfrag),
 				rx->offset, rx->status, PAGE_SIZE);
 
 		skb_shinfo(nskb)->nr_frags = 0;
diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c
index a59b6c4bb5b8..ad3d17c42e23 100644
--- a/drivers/nubus/bus.c
+++ b/drivers/nubus/bus.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2017 Finn Thain
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/nubus.h>
 #include <linux/seq_file.h>
@@ -93,6 +94,8 @@ int nubus_device_register(struct nubus_board *board)
 	board->dev.release = nubus_device_release;
 	board->dev.bus = &nubus_bus_type;
 	dev_set_name(&board->dev, "slot.%X", board->slot);
+	board->dev.dma_mask = &board->dev.coherent_dma_mask;
+	dma_set_mask(&board->dev, DMA_BIT_MASK(32));
 	return device_register(&board->dev);
 }
 
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 85de8053aa34..0360c015f658 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1423,11 +1423,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 
 static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 			struct page *page, unsigned int len, unsigned int off,
-			bool is_write, sector_t sector)
+			unsigned int op, sector_t sector)
 {
 	int ret;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		ret = btt_read_pg(btt, bip, page, off, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -1464,7 +1464,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 		}
 
 		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
-				  op_is_write(bio_op(bio)), iter.bi_sector);
+				  bio_op(bio), iter.bi_sector);
 		if (err) {
 			dev_err(&btt->nd_btt->dev,
 					"io error in %s sector %lld, len %d,\n",
@@ -1483,16 +1483,16 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,
-		struct page *page, bool is_write)
+		struct page *page, unsigned int op)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 	int rc;
 	unsigned int len;
 
 	len = hpage_nr_pages(page) * PAGE_SIZE;
-	rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector);
+	rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector);
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return rc;
 }
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 32e0364b48b9..6ee7fd7e4bbd 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -396,16 +396,15 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
 		return false;
 
 	*start = jiffies;
-	generic_start_io_acct(disk->queue, bio_data_dir(bio),
-			      bio_sectors(bio), &disk->part0);
+	generic_start_io_acct(disk->queue, bio_op(bio), bio_sectors(bio),
+			      &disk->part0);
 	return true;
 }
 static inline void nd_iostat_end(struct bio *bio, unsigned long start)
 {
 	struct gendisk *disk = bio->bi_disk;
 
-	generic_end_io_acct(disk->queue, bio_data_dir(bio), &disk->part0,
-				start);
+	generic_end_io_acct(disk->queue, bio_op(bio), &disk->part0, start);
 }
 static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector,
 		unsigned int len)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 8b1fd7f1a224..dd17acd8fe68 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -120,7 +120,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 }
 
 static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	blk_status_t rc = BLK_STS_OK;
@@ -131,7 +131,7 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		if (unlikely(bad_pmem))
 			rc = BLK_STS_IOERR;
 		else {
@@ -180,8 +180,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, op_is_write(bio_op(bio)),
-				iter.bi_sector);
+				bvec.bv_offset, bio_op(bio), iter.bi_sector);
 		if (rc) {
 			bio->bi_status = rc;
 			break;
@@ -198,13 +197,13 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	blk_status_t rc;
 
 	rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
-			  0, is_write, sector);
+			  0, op, sector);
 
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
@@ -213,7 +212,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	 * caused by double completion.
 	 */
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return blk_status_to_errno(rc);
 }
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index bf65501e6ed6..dd8ec1dd9219 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -252,7 +252,8 @@ void nvme_complete_rq(struct request *req)
 	trace_nvme_complete_rq(req);
 
 	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
-		if (nvme_req_needs_failover(req, status)) {
+		if ((req->cmd_flags & REQ_NVME_MPATH) &&
+		    blk_path_error(status)) {
 			nvme_failover_req(req);
 			return;
 		}
@@ -617,6 +618,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))
 				return BLK_STS_NOTSUPP;
 			control |= NVME_RW_PRINFO_PRACT;
+		} else if (req_op(req) == REQ_OP_WRITE) {
+			t10_pi_prepare(req, ns->pi_type);
 		}
 
 		switch (ns->pi_type) {
@@ -627,8 +630,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					NVME_RW_PRINFO_PRCHK_REF;
-			cmnd->rw.reftag = cpu_to_le32(
-					nvme_block_nr(ns, blk_rq_pos(req)));
+			cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
 			break;
 		}
 	}
@@ -638,6 +640,22 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	return 0;
 }
 
+void nvme_cleanup_cmd(struct request *req)
+{
+	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
+	    nvme_req(req)->status == 0) {
+		struct nvme_ns *ns = req->rq_disk->private_data;
+
+		t10_pi_complete(req, ns->pi_type,
+				blk_rq_bytes(req) >> ns->lba_shift);
+	}
+	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		kfree(page_address(req->special_vec.bv_page) +
+		      req->special_vec.bv_offset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
+
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd)
 {
@@ -668,10 +686,7 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 	}
 
 	cmd->common.command_id = req->tag;
-	if (ns)
-		trace_nvme_setup_nvm_cmd(req->q->id, cmd);
-	else
-		trace_nvme_setup_admin_cmd(cmd);
+	trace_nvme_setup_cmd(req, cmd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_setup_cmd);
@@ -864,9 +879,6 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
-	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
-	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 
@@ -1056,7 +1068,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 #define NVME_AEN_SUPPORTED \
-	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT)
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | NVME_AEN_CFG_ANA_CHANGE)
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
@@ -1472,6 +1484,12 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 	set_capacity(disk, capacity);
 	nvme_config_discard(ns);
+
+	if (id->nsattr & (1 << 0))
+		set_disk_ro(disk, true);
+	else
+		set_disk_ro(disk, false);
+
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
@@ -2270,21 +2288,16 @@ out_unlock:
 	return ret;
 }
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		     u8 log_page, void *log,
-		     size_t size, u64 offset)
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset)
 {
 	struct nvme_command c = { };
 	unsigned long dwlen = size / 4 - 1;
 
 	c.get_log_page.opcode = nvme_admin_get_log_page;
-
-	if (ns)
-		c.get_log_page.nsid = cpu_to_le32(ns->head->ns_id);
-	else
-		c.get_log_page.nsid = cpu_to_le32(NVME_NSID_ALL);
-
+	c.get_log_page.nsid = cpu_to_le32(nsid);
 	c.get_log_page.lid = log_page;
+	c.get_log_page.lsp = lsp;
 	c.get_log_page.numdl = cpu_to_le16(dwlen & ((1 << 16) - 1));
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
 	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
@@ -2293,12 +2306,6 @@ int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static int nvme_get_log(struct nvme_ctrl *ctrl, u8 log_page, void *log,
-			size_t size)
-{
-	return nvme_get_log_ext(ctrl, NULL, log_page, log, size, 0);
-}
-
 static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 {
 	int ret;
@@ -2309,8 +2316,8 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 	if (!ctrl->effects)
 		return 0;
 
-	ret = nvme_get_log(ctrl, NVME_LOG_CMD_EFFECTS, ctrl->effects,
-					sizeof(*ctrl->effects));
+	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
+			ctrl->effects, sizeof(*ctrl->effects), 0);
 	if (ret) {
 		kfree(ctrl->effects);
 		ctrl->effects = NULL;
@@ -2401,6 +2408,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	nvme_set_queue_limits(ctrl, ctrl->admin_q);
 	ctrl->sgls = le32_to_cpu(id->sgls);
 	ctrl->kas = le16_to_cpu(id->kas);
+	ctrl->max_namespaces = le32_to_cpu(id->mnan);
 
 	if (id->rtd3e) {
 		/* us -> s */
@@ -2460,8 +2468,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
 	}
 
+	ret = nvme_mpath_init(ctrl, id);
 	kfree(id);
 
+	if (ret < 0)
+		return ret;
+
 	if (ctrl->apst_enabled && !prev_apst_enabled)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
@@ -2680,6 +2692,10 @@ static struct attribute *nvme_ns_id_attrs[] = {
 	&dev_attr_nguid.attr,
 	&dev_attr_eui.attr,
 	&dev_attr_nsid.attr,
+#ifdef CONFIG_NVME_MULTIPATH
+	&dev_attr_ana_grpid.attr,
+	&dev_attr_ana_state.attr,
+#endif
 	NULL,
 };
 
@@ -2702,6 +2718,14 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 		if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
 			return 0;
 	}
+#ifdef CONFIG_NVME_MULTIPATH
+	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
+		if (dev_to_disk(dev)->fops != &nvme_fops) /* per-path attr */
+			return 0;
+		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
+			return 0;
+	}
+#endif
 	return a->mode;
 }
 
@@ -3075,8 +3099,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	nvme_get_ctrl(ctrl);
 
-	kfree(id);
-
 	device_add_disk(ctrl->device, ns->disk);
 	if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_id_attr_group))
@@ -3086,8 +3108,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
 			ns->disk->disk_name);
 
-	nvme_mpath_add_disk(ns->head);
+	nvme_mpath_add_disk(ns, id);
 	nvme_fault_inject_init(ns);
+	kfree(id);
+
 	return;
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
@@ -3229,7 +3253,8 @@ static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 	 * raced with us in reading the log page, which could cause us to miss
 	 * updates.
 	 */
-	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
+			log_size, 0);
 	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
@@ -3346,9 +3371,9 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_LOG_FW_SLOT, log, sizeof(*log)))
-		dev_warn(ctrl->device,
-				"Get FW SLOT INFO log error\n");
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log,
+			sizeof(*log), 0))
+		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
 }
 
@@ -3394,6 +3419,13 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
 		queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
+#ifdef CONFIG_NVME_MULTIPATH
+	case NVME_AER_NOTICE_ANA:
+		if (!ctrl->ana_log_buf)
+			break;
+		queue_work(nvme_wq, &ctrl->ana_work);
+		break;
+#endif
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);
 	}
@@ -3426,6 +3458,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 
 void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 {
+	nvme_mpath_stop(ctrl);
 	nvme_stop_keep_alive(ctrl);
 	flush_work(&ctrl->async_event_work);
 	flush_work(&ctrl->scan_work);
@@ -3463,6 +3496,7 @@ static void nvme_free_ctrl(struct device *dev)
 
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 	kfree(ctrl->effects);
+	nvme_mpath_uninit(ctrl);
 
 	if (subsys) {
 		mutex_lock(&subsys->lock);
@@ -3499,6 +3533,10 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
 	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
 
+	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
+	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
+
 	ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto out;
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index f7efe5a58cc7..206d63cb1afc 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -474,7 +474,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
 
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
 {
-	if (ctrl->opts->max_reconnects != -1 &&
+	if (ctrl->opts->max_reconnects == -1 ||
 	    ctrl->nr_reconnects < ctrl->opts->max_reconnects)
 		return true;
 
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 9bac912173ba..611e70cae754 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1737,6 +1737,7 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq,
 	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;
 	struct nvme_fc_queue *queue = &ctrl->queues[queue_idx];
 
+	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	return __nvme_fc_init_request(ctrl, queue, op, rq, queue->rqcnt++);
 }
 
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 41279da799ed..6fe5923c95d4 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -414,12 +414,6 @@ static int nvme_nvm_setup_20(struct nvme_nvm_id20 *id,
 	/* Set compacted version for upper layers */
 	geo->version = NVM_OCSSD_SPEC_20;
 
-	if (!(geo->major_ver_id == 2 && geo->minor_ver_id == 0)) {
-		pr_err("nvm: OCSSD version not supported (v%d.%d)\n",
-				geo->major_ver_id, geo->minor_ver_id);
-		return -EINVAL;
-	}
-
 	geo->num_ch = le16_to_cpu(id->num_grp);
 	geo->num_lun = le16_to_cpu(id->num_pu);
 	geo->all_luns = geo->num_ch * geo->num_lun;
@@ -583,7 +577,13 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	struct ppa_addr ppa;
 	size_t left = nchks * sizeof(struct nvme_nvm_chk_meta);
 	size_t log_pos, offset, len;
-	int ret, i;
+	int ret, i, max_len;
+
+	/*
+	 * limit requests to maximum 256K to avoid issuing arbitrary large
+	 * requests when the device does not specific a maximum transfer size.
+	 */
+	max_len = min_t(unsigned int, ctrl->max_hw_sectors << 9, 256 * 1024);
 
 	/* Normalize lba address space to obtain log offset */
 	ppa.ppa = slba;
@@ -596,10 +596,11 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	offset = log_pos * sizeof(struct nvme_nvm_chk_meta);
 
 	while (left) {
-		len = min_t(unsigned int, left, ctrl->max_hw_sectors << 9);
+		len = min_t(unsigned int, left, max_len);
 
-		ret = nvme_get_log_ext(ctrl, ns, NVME_NVM_LOG_REPORT_CHUNK,
-				dev_meta, len, offset);
+		ret = nvme_get_log(ctrl, ns->head->ns_id,
+				NVME_NVM_LOG_REPORT_CHUNK, 0, dev_meta, len,
+				offset);
 		if (ret) {
 			dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
 			break;
@@ -662,12 +663,10 @@ static struct request *nvme_nvm_alloc_request(struct request_queue *q,
 
 	rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
 
-	if (rqd->bio) {
+	if (rqd->bio)
 		blk_init_request_from_bio(rq, rqd->bio);
-	} else {
+	else
 		rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
-		rq->__data_len = 0;
-	}
 
 	return rq;
 }
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 1ffd3e8b13a1..5a9562881d4e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017 Christoph Hellwig.
+ * Copyright (c) 2017-2018 Christoph Hellwig.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,11 @@ module_param(multipath, bool, 0444);
 MODULE_PARM_DESC(multipath,
 	"turn on native support for multiple controllers per subsystem");
 
+inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+	return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
+}
+
 /*
  * If multipathing is enabled we need to always use the subsystem instance
  * number for numbering our devices to avoid conflicts between subsystems that
@@ -45,6 +50,7 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
+	u16 status = nvme_req(req)->status;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ns->head->requeue_lock, flags);
@@ -52,15 +58,35 @@ void nvme_failover_req(struct request *req)
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
 	blk_mq_end_request(req, 0);
 
-	nvme_reset_ctrl(ns->ctrl);
-	kblockd_schedule_work(&ns->head->requeue_work);
-}
+	switch (status & 0x7ff) {
+	case NVME_SC_ANA_TRANSITION:
+	case NVME_SC_ANA_INACCESSIBLE:
+	case NVME_SC_ANA_PERSISTENT_LOSS:
+		/*
+		 * If we got back an ANA error we know the controller is alive,
+		 * but not ready to serve this namespaces.  The spec suggests
+		 * we should update our general state here, but due to the fact
+		 * that the admin and I/O queues are not serialized that is
+		 * fundamentally racy.  So instead just clear the current path,
+		 * mark the the path as pending and kick of a re-read of the ANA
+		 * log page ASAP.
+		 */
+		nvme_mpath_clear_current_path(ns);
+		if (ns->ctrl->ana_log_buf) {
+			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+			queue_work(nvme_wq, &ns->ctrl->ana_work);
+		}
+		break;
+	default:
+		/*
+		 * Reset the controller for any non-ANA error as we don't know
+		 * what caused the error.
+		 */
+		nvme_reset_ctrl(ns->ctrl);
+		break;
+	}
 
-bool nvme_req_needs_failover(struct request *req, blk_status_t error)
-{
-	if (!(req->cmd_flags & REQ_NVME_MPATH))
-		return false;
-	return blk_path_error(error);
+	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
@@ -75,25 +101,51 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 	up_read(&ctrl->namespaces_rwsem);
 }
 
+static const char *nvme_ana_state_names[] = {
+	[0]				= "invalid state",
+	[NVME_ANA_OPTIMIZED]		= "optimized",
+	[NVME_ANA_NONOPTIMIZED]		= "non-optimized",
+	[NVME_ANA_INACCESSIBLE]		= "inaccessible",
+	[NVME_ANA_PERSISTENT_LOSS]	= "persistent-loss",
+	[NVME_ANA_CHANGE]		= "change",
+};
+
 static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head)
 {
-	struct nvme_ns *ns;
+	struct nvme_ns *ns, *fallback = NULL;
 
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
-		if (ns->ctrl->state == NVME_CTRL_LIVE) {
+		if (ns->ctrl->state != NVME_CTRL_LIVE ||
+		    test_bit(NVME_NS_ANA_PENDING, &ns->flags))
+			continue;
+		switch (ns->ana_state) {
+		case NVME_ANA_OPTIMIZED:
 			rcu_assign_pointer(head->current_path, ns);
 			return ns;
+		case NVME_ANA_NONOPTIMIZED:
+			fallback = ns;
+			break;
+		default:
+			break;
 		}
 	}
 
-	return NULL;
+	if (fallback)
+		rcu_assign_pointer(head->current_path, fallback);
+	return fallback;
+}
+
+static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
+{
+	return ns->ctrl->state == NVME_CTRL_LIVE &&
+		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
 inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 {
 	struct nvme_ns *ns = srcu_dereference(head->current_path, &head->srcu);
 
-	if (unlikely(!ns || ns->ctrl->state != NVME_CTRL_LIVE))
+	if (unlikely(!ns || !nvme_path_is_optimized(ns)))
 		ns = __nvme_find_path(head);
 	return ns;
 }
@@ -142,7 +194,7 @@ static bool nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc)
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = srcu_dereference(head->current_path, &head->srcu);
-	if (likely(ns && ns->ctrl->state == NVME_CTRL_LIVE))
+	if (likely(ns && nvme_path_is_optimized(ns)))
 		found = ns->queue->poll_fn(q, qc);
 	srcu_read_unlock(&head->srcu, srcu_idx);
 	return found;
@@ -176,6 +228,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	struct request_queue *q;
 	bool vwc = false;
 
+	mutex_init(&head->lock);
 	bio_list_init(&head->requeue_list);
 	spin_lock_init(&head->requeue_lock);
 	INIT_WORK(&head->requeue_work, nvme_requeue_work);
@@ -220,29 +273,232 @@ out:
 	return -ENOMEM;
 }
 
-void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static void nvme_mpath_set_live(struct nvme_ns *ns)
 {
+	struct nvme_ns_head *head = ns->head;
+
+	lockdep_assert_held(&ns->head->lock);
+
 	if (!head->disk)
 		return;
 
-	mutex_lock(&head->subsys->lock);
 	if (!(head->disk->flags & GENHD_FL_UP)) {
 		device_add_disk(&head->subsys->dev, head->disk);
 		if (sysfs_create_group(&disk_to_dev(head->disk)->kobj,
 				&nvme_ns_id_attr_group))
-			pr_warn("%s: failed to create sysfs group for identification\n",
-				head->disk->disk_name);
+			dev_warn(&head->subsys->dev,
+				 "failed to create id group.\n");
+	}
+
+	kblockd_schedule_work(&ns->head->requeue_work);
+}
+
+static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
+		int (*cb)(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *,
+			void *))
+{
+	void *base = ctrl->ana_log_buf;
+	size_t offset = sizeof(struct nvme_ana_rsp_hdr);
+	int error, i;
+
+	lockdep_assert_held(&ctrl->ana_lock);
+
+	for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) {
+		struct nvme_ana_group_desc *desc = base + offset;
+		u32 nr_nsids = le32_to_cpu(desc->nnsids);
+		size_t nsid_buf_size = nr_nsids * sizeof(__le32);
+
+		if (WARN_ON_ONCE(desc->grpid == 0))
+			return -EINVAL;
+		if (WARN_ON_ONCE(le32_to_cpu(desc->grpid) > ctrl->anagrpmax))
+			return -EINVAL;
+		if (WARN_ON_ONCE(desc->state == 0))
+			return -EINVAL;
+		if (WARN_ON_ONCE(desc->state > NVME_ANA_CHANGE))
+			return -EINVAL;
+
+		offset += sizeof(*desc);
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - nsid_buf_size))
+			return -EINVAL;
+
+		error = cb(ctrl, desc, data);
+		if (error)
+			return error;
+
+		offset += nsid_buf_size;
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static inline bool nvme_state_is_live(enum nvme_ana_state state)
+{
+	return state == NVME_ANA_OPTIMIZED || state == NVME_ANA_NONOPTIMIZED;
+}
+
+static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
+		struct nvme_ns *ns)
+{
+	enum nvme_ana_state old;
+
+	mutex_lock(&ns->head->lock);
+	old = ns->ana_state;
+	ns->ana_grpid = le32_to_cpu(desc->grpid);
+	ns->ana_state = desc->state;
+	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
+
+	if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old))
+		nvme_mpath_set_live(ns);
+	mutex_unlock(&ns->head->lock);
+}
+
+static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
+		struct nvme_ana_group_desc *desc, void *data)
+{
+	u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
+	unsigned *nr_change_groups = data;
+	struct nvme_ns *ns;
+
+	dev_info(ctrl->device, "ANA group %d: %s.\n",
+			le32_to_cpu(desc->grpid),
+			nvme_ana_state_names[desc->state]);
+
+	if (desc->state == NVME_ANA_CHANGE)
+		(*nr_change_groups)++;
+
+	if (!nr_nsids)
+		return 0;
+
+	down_write(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		if (ns->head->ns_id != le32_to_cpu(desc->nsids[n]))
+			continue;
+		nvme_update_ns_ana_state(desc, ns);
+		if (++n == nr_nsids)
+			break;
+	}
+	up_write(&ctrl->namespaces_rwsem);
+	WARN_ON_ONCE(n < nr_nsids);
+	return 0;
+}
+
+static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only)
+{
+	u32 nr_change_groups = 0;
+	int error;
+
+	mutex_lock(&ctrl->ana_lock);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA,
+			groups_only ? NVME_ANA_LOG_RGO : 0,
+			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
+	if (error) {
+		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
+		goto out_unlock;
+	}
+
+	error = nvme_parse_ana_log(ctrl, &nr_change_groups,
+			nvme_update_ana_state);
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * In theory we should have an ANATT timer per group as they might enter
+	 * the change state at different times.  But that is a lot of overhead
+	 * just to protect against a target that keeps entering new changes
+	 * states while never finishing previous ones.  But we'll still
+	 * eventually time out once all groups are in change state, so this
+	 * isn't a big deal.
+	 *
+	 * We also double the ANATT value to provide some slack for transports
+	 * or AEN processing overhead.
+	 */
+	if (nr_change_groups)
+		mod_timer(&ctrl->anatt_timer, ctrl->anatt * HZ * 2 + jiffies);
+	else
+		del_timer_sync(&ctrl->anatt_timer);
+out_unlock:
+	mutex_unlock(&ctrl->ana_lock);
+	return error;
+}
+
+static void nvme_ana_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
+
+	nvme_read_ana_log(ctrl, false);
+}
+
+static void nvme_anatt_timeout(struct timer_list *t)
+{
+	struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
+
+	dev_info(ctrl->device, "ANATT timeout, resetting controller.\n");
+	nvme_reset_ctrl(ctrl);
+}
+
+void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+	if (!nvme_ctrl_use_ana(ctrl))
+		return;
+	del_timer_sync(&ctrl->anatt_timer);
+	cancel_work_sync(&ctrl->ana_work);
+}
+
+static ssize_t ana_grpid_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	return sprintf(buf, "%d\n", nvme_get_ns_from_dev(dev)->ana_grpid);
+}
+DEVICE_ATTR_RO(ana_grpid);
+
+static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+
+	return sprintf(buf, "%s\n", nvme_ana_state_names[ns->ana_state]);
+}
+DEVICE_ATTR_RO(ana_state);
+
+static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
+		struct nvme_ana_group_desc *desc, void *data)
+{
+	struct nvme_ns *ns = data;
+
+	if (ns->ana_grpid == le32_to_cpu(desc->grpid)) {
+		nvme_update_ns_ana_state(desc, ns);
+		return -ENXIO; /* just break out of the loop */
+	}
+
+	return 0;
+}
+
+void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	if (nvme_ctrl_use_ana(ns->ctrl)) {
+		mutex_lock(&ns->ctrl->ana_lock);
+		ns->ana_grpid = le32_to_cpu(id->anagrpid);
+		nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state);
+		mutex_unlock(&ns->ctrl->ana_lock);
+	} else {
+		mutex_lock(&ns->head->lock);
+		ns->ana_state = NVME_ANA_OPTIMIZED; 
+		nvme_mpath_set_live(ns);
+		mutex_unlock(&ns->head->lock);
 	}
-	mutex_unlock(&head->subsys->lock);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
-			   &nvme_ns_id_attr_group);
-	del_gendisk(head->disk);
+	if (head->disk->flags & GENHD_FL_UP) {
+		sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
+				   &nvme_ns_id_attr_group);
+		del_gendisk(head->disk);
+	}
 	blk_set_queue_dying(head->disk->queue);
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
@@ -250,3 +506,52 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	blk_cleanup_queue(head->disk->queue);
 	put_disk(head->disk);
 }
+
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+	int error;
+
+	if (!nvme_ctrl_use_ana(ctrl))
+		return 0;
+
+	ctrl->anacap = id->anacap;
+	ctrl->anatt = id->anatt;
+	ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);
+	ctrl->anagrpmax = le32_to_cpu(id->anagrpmax);
+
+	mutex_init(&ctrl->ana_lock);
+	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
+	ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
+		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc);
+	if (!(ctrl->anacap & (1 << 6)))
+		ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
+
+	if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
+		dev_err(ctrl->device,
+			"ANA log page size (%zd) larger than MDTS (%d).\n",
+			ctrl->ana_log_size,
+			ctrl->max_hw_sectors << SECTOR_SHIFT);
+		dev_err(ctrl->device, "disabling ANA support.\n");
+		return 0;
+	}
+
+	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
+	if (!ctrl->ana_log_buf)
+		goto out;
+
+	error = nvme_read_ana_log(ctrl, true);
+	if (error)
+		goto out_free_ana_log_buf;
+	return 0;
+out_free_ana_log_buf:
+	kfree(ctrl->ana_log_buf);
+out:
+	return -ENOMEM;
+}
+
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+	kfree(ctrl->ana_log_buf);
+}
+
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 0c4a33df3b2f..bb4a2003c097 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -102,6 +102,7 @@ struct nvme_request {
 	u8			retries;
 	u8			flags;
 	u16			status;
+	struct nvme_ctrl	*ctrl;
 };
 
 /*
@@ -119,6 +120,13 @@ static inline struct nvme_request *nvme_req(struct request *req)
 	return blk_mq_rq_to_pdu(req);
 }
 
+static inline u16 nvme_req_qid(struct request *req)
+{
+	if (!req->rq_disk)
+		return 0;
+	return blk_mq_unique_tag_to_hwq(blk_mq_unique_tag(req)) + 1;
+}
+
 /* The below value is the specific amount of delay needed before checking
  * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the
  * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
@@ -175,6 +183,7 @@ struct nvme_ctrl {
 	u16 oacs;
 	u16 nssa;
 	u16 nr_streams;
+	u32 max_namespaces;
 	atomic_t abort_limit;
 	u8 vwc;
 	u32 vs;
@@ -197,6 +206,19 @@ struct nvme_ctrl {
 	struct work_struct fw_act_work;
 	unsigned long events;
 
+#ifdef CONFIG_NVME_MULTIPATH
+	/* asymmetric namespace access: */
+	u8 anacap;
+	u8 anatt;
+	u32 anagrpmax;
+	u32 nanagrpid;
+	struct mutex ana_lock;
+	struct nvme_ana_rsp_hdr *ana_log_buf;
+	size_t ana_log_size;
+	struct timer_list anatt_timer;
+	struct work_struct ana_work;
+#endif
+
 	/* Power saving configuration */
 	u64 ps_max_latency_us;
 	bool apst_enabled;
@@ -261,6 +283,7 @@ struct nvme_ns_head {
 	struct bio_list		requeue_list;
 	spinlock_t		requeue_lock;
 	struct work_struct	requeue_work;
+	struct mutex		lock;
 #endif
 	struct list_head	list;
 	struct srcu_struct      srcu;
@@ -287,6 +310,10 @@ struct nvme_ns {
 	struct nvme_ctrl *ctrl;
 	struct request_queue *queue;
 	struct gendisk *disk;
+#ifdef CONFIG_NVME_MULTIPATH
+	enum nvme_ana_state ana_state;
+	u32 ana_grpid;
+#endif
 	struct list_head siblings;
 	struct nvm_dev *ndev;
 	struct kref kref;
@@ -299,8 +326,9 @@ struct nvme_ns {
 	bool ext;
 	u8 pi_type;
 	unsigned long flags;
-#define NVME_NS_REMOVING 0
-#define NVME_NS_DEAD     1
+#define NVME_NS_REMOVING	0
+#define NVME_NS_DEAD     	1
+#define NVME_NS_ANA_PENDING	2
 	u16 noiob;
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
@@ -356,14 +384,6 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
 	return (sector >> (ns->lba_shift - 9));
 }
 
-static inline void nvme_cleanup_cmd(struct request *req)
-{
-	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
-		kfree(page_address(req->special_vec.bv_page) +
-		      req->special_vec.bv_offset);
-	}
-}
-
 static inline void nvme_end_request(struct request *req, __le16 status,
 		union nvme_result result)
 {
@@ -420,6 +440,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl);
 #define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid);
+void nvme_cleanup_cmd(struct request *req);
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd);
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
@@ -435,21 +456,24 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl);
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		u8 log_page, void *log, size_t size, u64 offset);
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset);
 
 extern const struct attribute_group nvme_ns_id_attr_group;
 extern const struct block_device_operations nvme_ns_head_ops;
 
 #ifdef CONFIG_NVME_MULTIPATH
+bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl);
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
 void nvme_failover_req(struct request *req);
-bool nvme_req_needs_failover(struct request *req, blk_status_t error);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
-void nvme_mpath_add_disk(struct nvme_ns_head *head);
+void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
 void nvme_mpath_remove_disk(struct nvme_ns_head *head);
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
+void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 
 static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
@@ -468,7 +492,14 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 		kblockd_schedule_work(&head->requeue_work);
 }
 
+extern struct device_attribute dev_attr_ana_grpid;
+extern struct device_attribute dev_attr_ana_state;
+
 #else
+static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+	return false;
+}
 /*
  * Without the multipath code enabled, multiple controller per subsystems are
  * visible as devices and thus we cannot use the subsystem instance.
@@ -482,11 +513,6 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 static inline void nvme_failover_req(struct request *req)
 {
 }
-static inline bool nvme_req_needs_failover(struct request *req,
-					   blk_status_t error)
-{
-	return false;
-}
 static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 }
@@ -495,7 +521,8 @@ static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,
 {
 	return 0;
 }
-static inline void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static inline void nvme_mpath_add_disk(struct nvme_ns *ns,
+		struct nvme_id_ns *id)
 {
 }
 static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
@@ -507,6 +534,17 @@ static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 {
 }
+static inline int nvme_mpath_init(struct nvme_ctrl *ctrl,
+		struct nvme_id_ctrl *id)
+{
+	return 0;
+}
+static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+}
+static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 #ifdef CONFIG_NVM
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ddd441b1516a..1b9951d2067e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -418,6 +418,8 @@ static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req,
 
 	BUG_ON(!nvmeq);
 	iod->nvmeq = nvmeq;
+
+	nvme_req(req)->ctrl = &dev->ctrl;
 	return 0;
 }
 
@@ -535,73 +537,6 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
 		mempool_free(iod->sg, dev->iod_mempool);
 }
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-	if (be32_to_cpu(pi->ref_tag) == v)
-		pi->ref_tag = cpu_to_be32(p);
-}
-
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-	if (be32_to_cpu(pi->ref_tag) == p)
-		pi->ref_tag = cpu_to_be32(v);
-}
-
-/**
- * nvme_dif_remap - remaps ref tags to bip seed and physical lba
- *
- * The virtual start sector is the one that was originally submitted by the
- * block layer.	Due to partitioning, MD/DM cloning, etc. the actual physical
- * start sector may be different. Remap protection information to match the
- * physical LBA on writes, and back to the original seed on reads.
- *
- * Type 0 and 3 do not have a ref tag, so no remapping required.
- */
-static void nvme_dif_remap(struct request *req,
-			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
-	struct nvme_ns *ns = req->rq_disk->private_data;
-	struct bio_integrity_payload *bip;
-	struct t10_pi_tuple *pi;
-	void *p, *pmap;
-	u32 i, nlb, ts, phys, virt;
-
-	if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3)
-		return;
-
-	bip = bio_integrity(req->bio);
-	if (!bip)
-		return;
-
-	pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset;
-
-	p = pmap;
-	virt = bip_get_seed(bip);
-	phys = nvme_block_nr(ns, blk_rq_pos(req));
-	nlb = (blk_rq_bytes(req) >> ns->lba_shift);
-	ts = ns->disk->queue->integrity.tuple_size;
-
-	for (i = 0; i < nlb; i++, virt++, phys++) {
-		pi = (struct t10_pi_tuple *)p;
-		dif_swap(phys, virt, pi);
-		p += ts;
-	}
-	kunmap_atomic(pmap);
-}
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-static void nvme_dif_remap(struct request *req,
-			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
-}
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-#endif
-
 static void nvme_print_sgl(struct scatterlist *sgl, int nents)
 {
 	int i;
@@ -827,9 +762,6 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1)
 			goto out_unmap;
 
-		if (req_op(req) == REQ_OP_WRITE)
-			nvme_dif_remap(req, nvme_dif_prep);
-
 		if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir))
 			goto out_unmap;
 	}
@@ -852,11 +784,8 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 
 	if (iod->nents) {
 		dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
-		if (blk_integrity_rq(req)) {
-			if (req_op(req) == REQ_OP_READ)
-				nvme_dif_remap(req, nvme_dif_complete);
+		if (blk_integrity_rq(req))
 			dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir);
-		}
 	}
 
 	nvme_cleanup_cmd(req);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 66ec5985c9f3..0805fa6215ee 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -40,13 +40,14 @@
 
 #define NVME_RDMA_MAX_SEGMENTS		256
 
-#define NVME_RDMA_MAX_INLINE_SEGMENTS	1
+#define NVME_RDMA_MAX_INLINE_SEGMENTS	4
 
 struct nvme_rdma_device {
 	struct ib_device	*dev;
 	struct ib_pd		*pd;
 	struct kref		ref;
 	struct list_head	entry;
+	unsigned int		num_inline_segments;
 };
 
 struct nvme_rdma_qe {
@@ -117,6 +118,7 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
+	bool			use_inline_data;
 };
 
 static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
@@ -249,7 +251,7 @@ static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor)
 	/* +1 for drain */
 	init_attr.cap.max_recv_wr = queue->queue_size + 1;
 	init_attr.cap.max_recv_sge = 1;
-	init_attr.cap.max_send_sge = 1 + NVME_RDMA_MAX_INLINE_SEGMENTS;
+	init_attr.cap.max_send_sge = 1 + dev->num_inline_segments;
 	init_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
 	init_attr.qp_type = IB_QPT_RC;
 	init_attr.send_cq = queue->ib_cq;
@@ -286,6 +288,7 @@ static int nvme_rdma_init_request(struct blk_mq_tag_set *set,
 	struct ib_device *ibdev = dev->dev;
 	int ret;
 
+	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
 			DMA_TO_DEVICE);
 	if (ret)
@@ -374,6 +377,8 @@ nvme_rdma_find_get_device(struct rdma_cm_id *cm_id)
 		goto out_free_pd;
 	}
 
+	ndev->num_inline_segments = min(NVME_RDMA_MAX_INLINE_SEGMENTS,
+					ndev->dev->attrs.max_sge - 1);
 	list_add(&ndev->entry, &device_list);
 out_unlock:
 	mutex_unlock(&device_list_mutex);
@@ -868,6 +873,31 @@ out_free_io_queues:
 	return ret;
 }
 
+static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
+		bool remove)
+{
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_cancel_request,
+			&ctrl->ctrl);
+	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_destroy_admin_queue(ctrl, remove);
+}
+
+static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
+		bool remove)
+{
+	if (ctrl->ctrl.queue_count > 1) {
+		nvme_stop_queues(&ctrl->ctrl);
+		nvme_rdma_stop_io_queues(ctrl);
+		blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_cancel_request,
+				&ctrl->ctrl);
+		if (remove)
+			nvme_start_queues(&ctrl->ctrl);
+		nvme_rdma_destroy_io_queues(ctrl, remove);
+	}
+}
+
 static void nvme_rdma_stop_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
@@ -912,21 +942,44 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 	}
 }
 
-static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 {
-	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
-			struct nvme_rdma_ctrl, reconnect_work);
+	int ret = -EINVAL;
 	bool changed;
-	int ret;
 
-	++ctrl->ctrl.nr_reconnects;
-
-	ret = nvme_rdma_configure_admin_queue(ctrl, false);
+	ret = nvme_rdma_configure_admin_queue(ctrl, new);
 	if (ret)
-		goto requeue;
+		return ret;
+
+	if (ctrl->ctrl.icdoff) {
+		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
+		goto destroy_admin;
+	}
+
+	if (!(ctrl->ctrl.sgls & (1 << 2))) {
+		dev_err(ctrl->ctrl.device,
+			"Mandatory keyed sgls are not supported!\n");
+		goto destroy_admin;
+	}
+
+	if (ctrl->ctrl.opts->queue_size > ctrl->ctrl.sqsize + 1) {
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl sqsize %u, clamping down\n",
+			ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
+	}
+
+	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
+		dev_warn(ctrl->ctrl.device,
+			"sqsize %u > ctrl maxcmd %u, clamping down\n",
+			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
+		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
+	}
+
+	if (ctrl->ctrl.sgls & (1 << 20))
+		ctrl->use_inline_data = true;
 
 	if (ctrl->ctrl.queue_count > 1) {
-		ret = nvme_rdma_configure_io_queues(ctrl, false);
+		ret = nvme_rdma_configure_io_queues(ctrl, new);
 		if (ret)
 			goto destroy_admin;
 	}
@@ -935,10 +988,31 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	if (!changed) {
 		/* state change failure is ok if we're in DELETING state */
 		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
-		return;
+		ret = -EINVAL;
+		goto destroy_io;
 	}
 
 	nvme_start_ctrl(&ctrl->ctrl);
+	return 0;
+
+destroy_io:
+	if (ctrl->ctrl.queue_count > 1)
+		nvme_rdma_destroy_io_queues(ctrl, new);
+destroy_admin:
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	nvme_rdma_destroy_admin_queue(ctrl, new);
+	return ret;
+}
+
+static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvme_rdma_ctrl, reconnect_work);
+
+	++ctrl->ctrl.nr_reconnects;
+
+	if (nvme_rdma_setup_ctrl(ctrl, false))
+		goto requeue;
 
 	dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n",
 			ctrl->ctrl.nr_reconnects);
@@ -947,9 +1021,6 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 
 	return;
 
-destroy_admin:
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	nvme_rdma_destroy_admin_queue(ctrl, false);
 requeue:
 	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
 			ctrl->ctrl.nr_reconnects);
@@ -962,27 +1033,9 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 			struct nvme_rdma_ctrl, err_work);
 
 	nvme_stop_keep_alive(&ctrl->ctrl);
-
-	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		nvme_rdma_stop_io_queues(ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-					nvme_cancel_request, &ctrl->ctrl);
-		nvme_rdma_destroy_io_queues(ctrl, false);
-	}
-
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_cancel_request, &ctrl->ctrl);
-	nvme_rdma_destroy_admin_queue(ctrl, false);
-
-	/*
-	 * queues are not a live anymore, so restart the queues to fail fast
-	 * new IO
-	 */
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_teardown_io_queues(ctrl, false);
 	nvme_start_queues(&ctrl->ctrl);
+	nvme_rdma_teardown_admin_queue(ctrl, false);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we're in DELETING state */
@@ -1090,19 +1143,27 @@ static int nvme_rdma_set_sg_null(struct nvme_command *c)
 }
 
 static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue,
-		struct nvme_rdma_request *req, struct nvme_command *c)
+		struct nvme_rdma_request *req, struct nvme_command *c,
+		int count)
 {
 	struct nvme_sgl_desc *sg = &c->common.dptr.sgl;
+	struct scatterlist *sgl = req->sg_table.sgl;
+	struct ib_sge *sge = &req->sge[1];
+	u32 len = 0;
+	int i;
 
-	req->sge[1].addr = sg_dma_address(req->sg_table.sgl);
-	req->sge[1].length = sg_dma_len(req->sg_table.sgl);
-	req->sge[1].lkey = queue->device->pd->local_dma_lkey;
+	for (i = 0; i < count; i++, sgl++, sge++) {
+		sge->addr = sg_dma_address(sgl);
+		sge->length = sg_dma_len(sgl);
+		sge->lkey = queue->device->pd->local_dma_lkey;
+		len += sge->length;
+	}
 
 	sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff);
-	sg->length = cpu_to_le32(sg_dma_len(req->sg_table.sgl));
+	sg->length = cpu_to_le32(len);
 	sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET;
 
-	req->num_sge++;
+	req->num_sge += count;
 	return 0;
 }
 
@@ -1195,15 +1256,16 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 		goto out_free_table;
 	}
 
-	if (count == 1) {
+	if (count <= dev->num_inline_segments) {
 		if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) &&
+		    queue->ctrl->use_inline_data &&
 		    blk_rq_payload_bytes(rq) <=
 				nvme_rdma_inline_data_size(queue)) {
-			ret = nvme_rdma_map_sg_inline(queue, req, c);
+			ret = nvme_rdma_map_sg_inline(queue, req, c, count);
 			goto out;
 		}
 
-		if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
+		if (count == 1 && dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
 			ret = nvme_rdma_map_sg_single(queue, req, c);
 			goto out;
 		}
@@ -1574,6 +1636,7 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	case RDMA_CM_EVENT_UNREACHABLE:
 		nvme_rdma_destroy_queue_ib(queue);
+		/* fall through */
 	case RDMA_CM_EVENT_ADDR_ERROR:
 		dev_dbg(queue->ctrl->ctrl.device,
 			"CM error event %d\n", ev->event);
@@ -1736,25 +1799,12 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
 
 static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
 {
-	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		nvme_rdma_stop_io_queues(ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-					nvme_cancel_request, &ctrl->ctrl);
-		nvme_rdma_destroy_io_queues(ctrl, shutdown);
-	}
-
+	nvme_rdma_teardown_io_queues(ctrl, shutdown);
 	if (shutdown)
 		nvme_shutdown_ctrl(&ctrl->ctrl);
 	else
 		nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
-
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_cancel_request, &ctrl->ctrl);
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_destroy_admin_queue(ctrl, shutdown);
+	nvme_rdma_teardown_admin_queue(ctrl, shutdown);
 }
 
 static void nvme_rdma_delete_ctrl(struct nvme_ctrl *ctrl)
@@ -1766,8 +1816,6 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 {
 	struct nvme_rdma_ctrl *ctrl =
 		container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);
-	int ret;
-	bool changed;
 
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_rdma_shutdown_ctrl(ctrl, false);
@@ -1778,25 +1826,9 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 		return;
 	}
 
-	ret = nvme_rdma_configure_admin_queue(ctrl, false);
-	if (ret)
+	if (nvme_rdma_setup_ctrl(ctrl, false))
 		goto out_fail;
 
-	if (ctrl->ctrl.queue_count > 1) {
-		ret = nvme_rdma_configure_io_queues(ctrl, false);
-		if (ret)
-			goto out_fail;
-	}
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	if (!changed) {
-		/* state change failure is ok if we're in DELETING state */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
-		return;
-	}
-
-	nvme_start_ctrl(&ctrl->ctrl);
-
 	return;
 
 out_fail:
@@ -1959,49 +1991,10 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
 	WARN_ON_ONCE(!changed);
 
-	ret = nvme_rdma_configure_admin_queue(ctrl, true);
+	ret = nvme_rdma_setup_ctrl(ctrl, true);
 	if (ret)
 		goto out_uninit_ctrl;
 
-	/* sanity check icdoff */
-	if (ctrl->ctrl.icdoff) {
-		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
-		ret = -EINVAL;
-		goto out_remove_admin_queue;
-	}
-
-	/* sanity check keyed sgls */
-	if (!(ctrl->ctrl.sgls & (1 << 2))) {
-		dev_err(ctrl->ctrl.device,
-			"Mandatory keyed sgls are not supported!\n");
-		ret = -EINVAL;
-		goto out_remove_admin_queue;
-	}
-
-	/* only warn if argument is too large here, will clamp later */
-	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
-		dev_warn(ctrl->ctrl.device,
-			"queue_size %zu > ctrl sqsize %u, clamping down\n",
-			opts->queue_size, ctrl->ctrl.sqsize + 1);
-	}
-
-	/* warn if maxcmd is lower than sqsize+1 */
-	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
-		dev_warn(ctrl->ctrl.device,
-			"sqsize %u > ctrl maxcmd %u, clamping down\n",
-			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
-		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
-	}
-
-	if (opts->nr_io_queues) {
-		ret = nvme_rdma_configure_io_queues(ctrl, true);
-		if (ret)
-			goto out_remove_admin_queue;
-	}
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	WARN_ON_ONCE(!changed);
-
 	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
 		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
 
@@ -2011,13 +2004,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
 	mutex_unlock(&nvme_rdma_ctrl_mutex);
 
-	nvme_start_ctrl(&ctrl->ctrl);
-
 	return &ctrl->ctrl;
 
-out_remove_admin_queue:
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	nvme_rdma_destroy_admin_queue(ctrl, true);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 	nvme_put_ctrl(&ctrl->ctrl);
diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 41944bbef835..25b0e310f4a8 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -128,3 +128,14 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p,
 		return nvme_trace_common(p, cdw10);
 	}
 }
+
+const char *nvme_trace_disk_name(struct trace_seq *p, char *name)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+
+	if (*name)
+		trace_seq_printf(p, "disk=%s, ", name);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index 01390f0e1671..a490790d6691 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -50,13 +50,8 @@
 		nvme_admin_opcode_name(nvme_admin_security_recv),	\
 		nvme_admin_opcode_name(nvme_admin_sanitize_nvm))
 
-const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
-				       u8 *cdw10);
-#define __parse_nvme_admin_cmd(opcode, cdw10) \
-	nvme_trace_parse_admin_cmd(p, opcode, cdw10)
-
 #define nvme_opcode_name(opcode)	{ opcode, #opcode }
-#define show_opcode_name(val)					\
+#define show_nvm_opcode_name(val)				\
 	__print_symbolic(val,					\
 		nvme_opcode_name(nvme_cmd_flush),		\
 		nvme_opcode_name(nvme_cmd_write),		\
@@ -70,85 +65,92 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
 		nvme_opcode_name(nvme_cmd_resv_acquire),	\
 		nvme_opcode_name(nvme_cmd_resv_release))
 
-const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode,
-				     u8 *cdw10);
-#define __parse_nvme_cmd(opcode, cdw10) \
-	nvme_trace_parse_nvm_cmd(p, opcode, cdw10)
-
-TRACE_EVENT(nvme_setup_admin_cmd,
-	    TP_PROTO(struct nvme_command *cmd),
-	    TP_ARGS(cmd),
-	    TP_STRUCT__entry(
-		    __field(u8, opcode)
-		    __field(u8, flags)
-		    __field(u16, cid)
-		    __field(u64, metadata)
-		    __array(u8, cdw10, 24)
-	    ),
-	    TP_fast_assign(
-		    __entry->opcode = cmd->common.opcode;
-		    __entry->flags = cmd->common.flags;
-		    __entry->cid = cmd->common.command_id;
-		    __entry->metadata = le64_to_cpu(cmd->common.metadata);
-		    memcpy(__entry->cdw10, cmd->common.cdw10,
-			   sizeof(__entry->cdw10));
-	    ),
-	    TP_printk(" cmdid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->cid, __entry->flags, __entry->metadata,
-		      show_admin_opcode_name(__entry->opcode),
-		      __parse_nvme_admin_cmd(__entry->opcode, __entry->cdw10))
-);
-
+#define show_opcode_name(qid, opcode)					\
+	(qid ? show_nvm_opcode_name(opcode) : show_admin_opcode_name(opcode))
 
-TRACE_EVENT(nvme_setup_nvm_cmd,
-	    TP_PROTO(int qid, struct nvme_command *cmd),
-	    TP_ARGS(qid, cmd),
+const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
+		u8 *cdw10);
+const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode,
+		u8 *cdw10);
+
+#define parse_nvme_cmd(qid, opcode, cdw10) 			\
+	(qid ?							\
+	 nvme_trace_parse_nvm_cmd(p, opcode, cdw10) : 		\
+	 nvme_trace_parse_admin_cmd(p, opcode, cdw10))
+
+const char *nvme_trace_disk_name(struct trace_seq *p, char *name);
+#define __print_disk_name(name)				\
+	nvme_trace_disk_name(p, name)
+
+#ifndef TRACE_HEADER_MULTI_READ
+static inline void __assign_disk_name(char *name, struct gendisk *disk)
+{
+	if (disk)
+		memcpy(name, disk->disk_name, DISK_NAME_LEN);
+	else
+		memset(name, 0, DISK_NAME_LEN);
+}
+#endif
+
+TRACE_EVENT(nvme_setup_cmd,
+	    TP_PROTO(struct request *req, struct nvme_command *cmd),
+	    TP_ARGS(req, cmd),
 	    TP_STRUCT__entry(
-		    __field(int, qid)
-		    __field(u8, opcode)
-		    __field(u8, flags)
-		    __field(u16, cid)
-		    __field(u32, nsid)
-		    __field(u64, metadata)
-		    __array(u8, cdw10, 24)
+		__array(char, disk, DISK_NAME_LEN)
+		__field(int, ctrl_id)
+		__field(int, qid)
+		__field(u8, opcode)
+		__field(u8, flags)
+		__field(u16, cid)
+		__field(u32, nsid)
+		__field(u64, metadata)
+		__array(u8, cdw10, 24)
 	    ),
 	    TP_fast_assign(
-		    __entry->qid = qid;
-		    __entry->opcode = cmd->common.opcode;
-		    __entry->flags = cmd->common.flags;
-		    __entry->cid = cmd->common.command_id;
-		    __entry->nsid = le32_to_cpu(cmd->common.nsid);
-		    __entry->metadata = le64_to_cpu(cmd->common.metadata);
-		    memcpy(__entry->cdw10, cmd->common.cdw10,
-			   sizeof(__entry->cdw10));
+		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
+		__entry->qid = nvme_req_qid(req);
+		__entry->opcode = cmd->common.opcode;
+		__entry->flags = cmd->common.flags;
+		__entry->cid = cmd->common.command_id;
+		__entry->nsid = le32_to_cpu(cmd->common.nsid);
+		__entry->metadata = le64_to_cpu(cmd->common.metadata);
+		__assign_disk_name(__entry->disk, req->rq_disk);
+		memcpy(__entry->cdw10, cmd->common.cdw10,
+		       sizeof(__entry->cdw10));
 	    ),
-	    TP_printk("qid=%d, nsid=%u, cmdid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->qid, __entry->nsid, __entry->cid,
+	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
+		      __entry->ctrl_id, __print_disk_name(__entry->disk),
+		      __entry->qid, __entry->cid, __entry->nsid,
 		      __entry->flags, __entry->metadata,
-		      show_opcode_name(__entry->opcode),
-		      __parse_nvme_cmd(__entry->opcode, __entry->cdw10))
+		      show_opcode_name(__entry->qid, __entry->opcode),
+		      parse_nvme_cmd(__entry->qid, __entry->opcode, __entry->cdw10))
 );
 
 TRACE_EVENT(nvme_complete_rq,
 	    TP_PROTO(struct request *req),
 	    TP_ARGS(req),
 	    TP_STRUCT__entry(
-		    __field(int, qid)
-		    __field(int, cid)
-		    __field(u64, result)
-		    __field(u8, retries)
-		    __field(u8, flags)
-		    __field(u16, status)
+		__array(char, disk, DISK_NAME_LEN)
+		__field(int, ctrl_id)
+		__field(int, qid)
+		__field(int, cid)
+		__field(u64, result)
+		__field(u8, retries)
+		__field(u8, flags)
+		__field(u16, status)
 	    ),
 	    TP_fast_assign(
-		    __entry->qid = req->q->id;
-		    __entry->cid = req->tag;
-		    __entry->result = le64_to_cpu(nvme_req(req)->result.u64);
-		    __entry->retries = nvme_req(req)->retries;
-		    __entry->flags = nvme_req(req)->flags;
-		    __entry->status = nvme_req(req)->status;
+		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
+		__entry->qid = nvme_req_qid(req);
+		__entry->cid = req->tag;
+		__entry->result = le64_to_cpu(nvme_req(req)->result.u64);
+		__entry->retries = nvme_req(req)->retries;
+		__entry->flags = nvme_req(req)->flags;
+		__entry->status = nvme_req(req)->status;
+		__assign_disk_name(__entry->disk, req->rq_disk);
 	    ),
-	    TP_printk("qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+		      __entry->ctrl_id, __print_disk_name(__entry->disk),
 		      __entry->qid, __entry->cid, __entry->result,
 		      __entry->retries, __entry->flags, __entry->status)
 
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 38803576d5e1..a21caea1e080 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -19,6 +19,19 @@
 #include <asm/unaligned.h>
 #include "nvmet.h"
 
+/*
+ * This helper allows us to clear the AEN based on the RAE bit,
+ * Please use this helper when processing the log pages which are
+ * associated with the AEN.
+ */
+static inline void nvmet_clear_aen(struct nvmet_req *req, u32 aen_bit)
+{
+	int rae = le32_to_cpu(req->cmd->common.cdw10[0]) & 1 << 15;
+
+	if (!rae)
+		clear_bit(aen_bit, &req->sq->ctrl->aen_masked);
+}
+
 u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 {
 	u32 len = le16_to_cpu(cmd->get_log_page.numdu);
@@ -128,6 +141,36 @@ out:
 	nvmet_req_complete(req, status);
 }
 
+static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
+{
+	u16 status = NVME_SC_INTERNAL;
+	struct nvme_effects_log *log;
+
+	log = kzalloc(sizeof(*log), GFP_KERNEL);
+	if (!log)
+		goto out;
+
+	log->acs[nvme_admin_get_log_page]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_identify]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_abort_cmd]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_set_features]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_get_features]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_async_event]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_keep_alive]		= cpu_to_le32(1 << 0);
+
+	log->iocs[nvme_cmd_read]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_write]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_flush]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_dsm]			= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_write_zeroes]	= cpu_to_le32(1 << 0);
+
+	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+
+	kfree(log);
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -146,12 +189,76 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 	if (!status)
 		status = nvmet_zero_sgl(req, len, req->data_len - len);
 	ctrl->nr_changed_ns = 0;
-	clear_bit(NVME_AEN_CFG_NS_ATTR, &ctrl->aen_masked);
+	nvmet_clear_aen(req, NVME_AEN_CFG_NS_ATTR);
 	mutex_unlock(&ctrl->lock);
 out:
 	nvmet_req_complete(req, status);
 }
 
+static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
+		struct nvme_ana_group_desc *desc)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvmet_ns *ns;
+	u32 count = 0;
+
+	if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) {
+		rcu_read_lock();
+		list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+			if (ns->anagrpid == grpid)
+				desc->nsids[count++] = cpu_to_le32(ns->nsid);
+		rcu_read_unlock();
+	}
+
+	desc->grpid = cpu_to_le32(grpid);
+	desc->nnsids = cpu_to_le32(count);
+	desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	desc->state = req->port->ana_state[grpid];
+	memset(desc->rsvd17, 0, sizeof(desc->rsvd17));
+	return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32);
+}
+
+static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
+{
+	struct nvme_ana_rsp_hdr hdr = { 0, };
+	struct nvme_ana_group_desc *desc;
+	size_t offset = sizeof(struct nvme_ana_rsp_hdr); /* start beyond hdr */
+	size_t len;
+	u32 grpid;
+	u16 ngrps = 0;
+	u16 status;
+
+	status = NVME_SC_INTERNAL;
+	desc = kmalloc(sizeof(struct nvme_ana_group_desc) +
+			NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL);
+	if (!desc)
+		goto out;
+
+	down_read(&nvmet_ana_sem);
+	for (grpid = 1; grpid <= NVMET_MAX_ANAGRPS; grpid++) {
+		if (!nvmet_ana_group_enabled[grpid])
+			continue;
+		len = nvmet_format_ana_group(req, grpid, desc);
+		status = nvmet_copy_to_sgl(req, offset, desc, len);
+		if (status)
+			break;
+		offset += len;
+		ngrps++;
+	}
+
+	hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	hdr.ngrps = cpu_to_le16(ngrps);
+	nvmet_clear_aen(req, NVME_AEN_CFG_ANA_CHANGE);
+	up_read(&nvmet_ana_sem);
+
+	kfree(desc);
+
+	/* copy the header last once we know the number of groups */
+	status = nvmet_copy_to_sgl(req, 0, &hdr, sizeof(hdr));
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -183,8 +290,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	 * the safest is to leave it as zeroes.
 	 */
 
-	/* we support multiple ports and multiples hosts: */
-	id->cmic = (1 << 0) | (1 << 1);
+	/* we support multiple ports, multiples hosts and ANA: */
+	id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
 
 	/* no limit on data transfer sizes for now */
 	id->mdts = 0;
@@ -208,7 +315,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 
 	/* first slot is read-only, only one slot supported */
 	id->frmw = (1 << 0) | (1 << 1);
-	id->lpa = (1 << 0) | (1 << 2);
+	id->lpa = (1 << 0) | (1 << 1) | (1 << 2);
 	id->elpe = NVMET_ERROR_LOG_SLOTS - 1;
 	id->npss = 0;
 
@@ -222,6 +329,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
 
 	id->nn = cpu_to_le32(ctrl->subsys->max_nsid);
+	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
 			NVME_CTRL_ONCS_WRITE_ZEROES);
 
@@ -238,19 +346,24 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->has_keyed_sgls)
 		id->sgls |= cpu_to_le32(1 << 2);
-	if (ctrl->ops->sqe_inline_size)
+	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);
 
 	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
 
 	/* Max command capsule size is sqe + single page of in-capsule data */
 	id->ioccsz = cpu_to_le32((sizeof(struct nvme_command) +
-				  ctrl->ops->sqe_inline_size) / 16);
+				  req->port->inline_data_size) / 16);
 	/* Max response capsule size is cqe */
 	id->iorcsz = cpu_to_le32(sizeof(struct nvme_completion) / 16);
 
 	id->msdbd = ctrl->ops->msdbd;
 
+	id->anacap = (1 << 0) | (1 << 1) | (1 << 2) | (1 << 3) | (1 << 4);
+	id->anatt = 10; /* random value */
+	id->anagrpmax = cpu_to_le32(NVMET_MAX_ANAGRPS);
+	id->nanagrpid = cpu_to_le32(NVMET_MAX_ANAGRPS);
+
 	/*
 	 * Meh, we don't really support any power state.  Fake up the same
 	 * values that qemu does.
@@ -259,6 +372,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->psd[0].entry_lat = cpu_to_le32(0x10);
 	id->psd[0].exit_lat = cpu_to_le32(0x4);
 
+	id->nwpc = 1 << 0; /* write protect and no write protect */
+
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
 
 	kfree(id);
@@ -292,8 +407,15 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * nuse = ncap = nsze isn't always true, but we have no way to find
 	 * that out from the underlying device.
 	 */
-	id->ncap = id->nuse = id->nsze =
-		cpu_to_le64(ns->size >> ns->blksize_shift);
+	id->ncap = id->nsze = cpu_to_le64(ns->size >> ns->blksize_shift);
+	switch (req->port->ana_state[ns->anagrpid]) {
+	case NVME_ANA_INACCESSIBLE:
+	case NVME_ANA_PERSISTENT_LOSS:
+		break;
+	default:
+		id->nuse = id->nsze;
+		break;
+        }
 
 	/*
 	 * We just provide a single LBA format that matches what the
@@ -307,11 +429,14 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * controllers, but also with any other user of the block device.
 	 */
 	id->nmic = (1 << 0);
+	id->anagrpid = cpu_to_le32(ns->anagrpid);
 
-	memcpy(&id->nguid, &ns->nguid, sizeof(uuid_le));
+	memcpy(&id->nguid, &ns->nguid, sizeof(id->nguid));
 
 	id->lbaf[0].ds = ns->blksize_shift;
 
+	if (ns->readonly)
+		id->nsattr |= (1 << 0);
 	nvmet_put_namespace(ns);
 done:
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
@@ -424,6 +549,52 @@ static void nvmet_execute_abort(struct nvmet_req *req)
 	nvmet_req_complete(req, 0);
 }
 
+static u16 nvmet_write_protect_flush_sync(struct nvmet_req *req)
+{
+	u16 status;
+
+	if (req->ns->file)
+		status = nvmet_file_flush(req);
+	else
+		status = nvmet_bdev_flush(req);
+
+	if (status)
+		pr_err("write protect flush failed nsid: %u\n", req->ns->nsid);
+	return status;
+}
+
+static u16 nvmet_set_feat_write_protect(struct nvmet_req *req)
+{
+	u32 write_protect = le32_to_cpu(req->cmd->common.cdw10[1]);
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u16 status = NVME_SC_FEATURE_NOT_CHANGEABLE;
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->rw.nsid);
+	if (unlikely(!req->ns))
+		return status;
+
+	mutex_lock(&subsys->lock);
+	switch (write_protect) {
+	case NVME_NS_WRITE_PROTECT:
+		req->ns->readonly = true;
+		status = nvmet_write_protect_flush_sync(req);
+		if (status)
+			req->ns->readonly = false;
+		break;
+	case NVME_NS_NO_WRITE_PROTECT:
+		req->ns->readonly = false;
+		status = 0;
+		break;
+	default:
+		break;
+	}
+
+	if (!status)
+		nvmet_ns_changed(subsys, req->ns->nsid);
+	mutex_unlock(&subsys->lock);
+	return status;
+}
+
 static void nvmet_execute_set_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
@@ -454,6 +625,9 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 	case NVME_FEAT_HOST_ID:
 		status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 		break;
+	case NVME_FEAT_WRITE_PROTECT:
+		status = nvmet_set_feat_write_protect(req);
+		break;
 	default:
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
@@ -462,6 +636,26 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 	nvmet_req_complete(req, status);
 }
 
+static u16 nvmet_get_feat_write_protect(struct nvmet_req *req)
+{
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u32 result;
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->common.nsid);
+	if (!req->ns)
+		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+
+	mutex_lock(&subsys->lock);
+	if (req->ns->readonly == true)
+		result = NVME_NS_WRITE_PROTECT;
+	else
+		result = NVME_NS_NO_WRITE_PROTECT;
+	nvmet_set_result(req, result);
+	mutex_unlock(&subsys->lock);
+
+	return 0;
+}
+
 static void nvmet_execute_get_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
@@ -513,6 +707,9 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		status = nvmet_copy_to_sgl(req, 0, &req->sq->ctrl->hostid,
 				sizeof(req->sq->ctrl->hostid));
 		break;
+	case NVME_FEAT_WRITE_PROTECT:
+		status = nvmet_get_feat_write_protect(req);
+		break;
 	default:
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
@@ -586,6 +783,12 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 		case NVME_LOG_CHANGED_NS:
 			req->execute = nvmet_execute_get_log_changed_ns;
 			return 0;
+		case NVME_LOG_CMD_EFFECTS:
+			req->execute = nvmet_execute_get_log_cmd_effects_ns;
+			return 0;
+		case NVME_LOG_ANA:
+			req->execute = nvmet_execute_get_log_page_ana;
+			return 0;
 		}
 		break;
 	case nvme_admin_identify:
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index ebea1373d1b7..b37a8e3e3f80 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -218,6 +218,35 @@ static ssize_t nvmet_addr_trsvcid_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_, addr_trsvcid);
 
+static ssize_t nvmet_param_inline_data_size_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%d\n", port->inline_data_size);
+}
+
+static ssize_t nvmet_param_inline_data_size_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	int ret;
+
+	if (port->enabled) {
+		pr_err("Cannot modify inline_data_size while port enabled\n");
+		pr_err("Disable the port before modifying\n");
+		return -EACCES;
+	}
+	ret = kstrtoint(page, 0, &port->inline_data_size);
+	if (ret) {
+		pr_err("Invalid value '%s' for inline_data_size\n", page);
+		return -EINVAL;
+	}
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, param_inline_data_size);
+
 static ssize_t nvmet_addr_trtype_show(struct config_item *item,
 		char *page)
 {
@@ -387,6 +416,39 @@ out_unlock:
 
 CONFIGFS_ATTR(nvmet_ns_, device_nguid);
 
+static ssize_t nvmet_ns_ana_grpid_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%u\n", to_nvmet_ns(item)->anagrpid);
+}
+
+static ssize_t nvmet_ns_ana_grpid_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	u32 oldgrpid, newgrpid;
+	int ret;
+
+	ret = kstrtou32(page, 0, &newgrpid);
+	if (ret)
+		return ret;
+
+	if (newgrpid < 1 || newgrpid > NVMET_MAX_ANAGRPS)
+		return -EINVAL;
+
+	down_write(&nvmet_ana_sem);
+	oldgrpid = ns->anagrpid;
+	nvmet_ana_group_enabled[newgrpid]++;
+	ns->anagrpid = newgrpid;
+	nvmet_ana_group_enabled[oldgrpid]--;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_send_ana_event(ns->subsys, NULL);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, ana_grpid);
+
 static ssize_t nvmet_ns_enable_show(struct config_item *item, char *page)
 {
 	return sprintf(page, "%d\n", to_nvmet_ns(item)->enabled);
@@ -412,11 +474,41 @@ static ssize_t nvmet_ns_enable_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_ns_, enable);
 
+static ssize_t nvmet_ns_buffered_io_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%d\n", to_nvmet_ns(item)->buffered_io);
+}
+
+static ssize_t nvmet_ns_buffered_io_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	bool val;
+
+	if (strtobool(page, &val))
+		return -EINVAL;
+
+	mutex_lock(&ns->subsys->lock);
+	if (ns->enabled) {
+		pr_err("disable ns before setting buffered_io value.\n");
+		mutex_unlock(&ns->subsys->lock);
+		return -EINVAL;
+	}
+
+	ns->buffered_io = val;
+	mutex_unlock(&ns->subsys->lock);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, buffered_io);
+
 static struct configfs_attribute *nvmet_ns_attrs[] = {
 	&nvmet_ns_attr_device_path,
 	&nvmet_ns_attr_device_nguid,
 	&nvmet_ns_attr_device_uuid,
+	&nvmet_ns_attr_ana_grpid,
 	&nvmet_ns_attr_enable,
+	&nvmet_ns_attr_buffered_io,
 	NULL,
 };
 
@@ -863,6 +955,134 @@ static const struct config_item_type nvmet_referrals_type = {
 	.ct_group_ops	= &nvmet_referral_group_ops,
 };
 
+static struct {
+	enum nvme_ana_state	state;
+	const char		*name;
+} nvmet_ana_state_names[] = {
+	{ NVME_ANA_OPTIMIZED,		"optimized" },
+	{ NVME_ANA_NONOPTIMIZED,	"non-optimized" },
+	{ NVME_ANA_INACCESSIBLE,	"inaccessible" },
+	{ NVME_ANA_PERSISTENT_LOSS,	"persistent-loss" },
+	{ NVME_ANA_CHANGE,		"change" },
+};
+
+static ssize_t nvmet_ana_group_ana_state_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	enum nvme_ana_state state = grp->port->ana_state[grp->grpid];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (state != nvmet_ana_state_names[i].state)
+			continue;
+		return sprintf(page, "%s\n", nvmet_ana_state_names[i].name);
+	}
+
+	return sprintf(page, "\n");
+}
+
+static ssize_t nvmet_ana_group_ana_state_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (sysfs_streq(page, nvmet_ana_state_names[i].name))
+			goto found;
+	}
+
+	pr_err("Invalid value '%s' for ana_state\n", page);
+	return -EINVAL;
+
+found:
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = nvmet_ana_state_names[i].state;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ana_group_, ana_state);
+
+static struct configfs_attribute *nvmet_ana_group_attrs[] = {
+	&nvmet_ana_group_attr_ana_state,
+	NULL,
+};
+
+static void nvmet_ana_group_release(struct config_item *item)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+
+	if (grp == &grp->port->ana_default_group)
+		return;
+
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = NVME_ANA_INACCESSIBLE;
+	nvmet_ana_group_enabled[grp->grpid]--;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	kfree(grp);
+}
+
+static struct configfs_item_operations nvmet_ana_group_item_ops = {
+	.release		= nvmet_ana_group_release,
+};
+
+static const struct config_item_type nvmet_ana_group_type = {
+	.ct_item_ops		= &nvmet_ana_group_item_ops,
+	.ct_attrs		= nvmet_ana_group_attrs,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group *nvmet_ana_groups_make_group(
+		struct config_group *group, const char *name)
+{
+	struct nvmet_port *port = ana_groups_to_port(&group->cg_item);
+	struct nvmet_ana_group *grp;
+	u32 grpid;
+	int ret;
+
+	ret = kstrtou32(name, 0, &grpid);
+	if (ret)
+		goto out;
+
+	ret = -EINVAL;
+	if (grpid <= 1 || grpid > NVMET_MAX_ANAGRPS)
+		goto out;
+
+	ret = -ENOMEM;
+	grp = kzalloc(sizeof(*grp), GFP_KERNEL);
+	if (!grp)
+		goto out;
+	grp->port = port;
+	grp->grpid = grpid;
+
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[grpid]++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+
+	config_group_init_type_name(&grp->group, name, &nvmet_ana_group_type);
+	return &grp->group;
+out:
+	return ERR_PTR(ret);
+}
+
+static struct configfs_group_operations nvmet_ana_groups_group_ops = {
+	.make_group		= nvmet_ana_groups_make_group,
+};
+
+static const struct config_item_type nvmet_ana_groups_type = {
+	.ct_group_ops		= &nvmet_ana_groups_group_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
 /*
  * Ports definitions.
  */
@@ -870,6 +1090,7 @@ static void nvmet_port_release(struct config_item *item)
 {
 	struct nvmet_port *port = to_nvmet_port(item);
 
+	kfree(port->ana_state);
 	kfree(port);
 }
 
@@ -879,6 +1100,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_traddr,
 	&nvmet_attr_addr_trsvcid,
 	&nvmet_attr_addr_trtype,
+	&nvmet_attr_param_inline_data_size,
 	NULL,
 };
 
@@ -897,6 +1119,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 {
 	struct nvmet_port *port;
 	u16 portid;
+	u32 i;
 
 	if (kstrtou16(name, 0, &portid))
 		return ERR_PTR(-EINVAL);
@@ -905,9 +1128,24 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	if (!port)
 		return ERR_PTR(-ENOMEM);
 
+	port->ana_state = kcalloc(NVMET_MAX_ANAGRPS + 1,
+			sizeof(*port->ana_state), GFP_KERNEL);
+	if (!port->ana_state) {
+		kfree(port);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 1; i <= NVMET_MAX_ANAGRPS; i++) {
+		if (i == NVMET_DEFAULT_ANA_GRPID)
+			port->ana_state[1] = NVME_ANA_OPTIMIZED;
+		else
+			port->ana_state[i] = NVME_ANA_INACCESSIBLE;
+	}
+
 	INIT_LIST_HEAD(&port->entry);
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
+	port->inline_data_size = -1;	/* < 0 == let the transport choose */
 
 	port->disc_addr.portid = cpu_to_le16(portid);
 	config_group_init_type_name(&port->group, name, &nvmet_port_type);
@@ -920,6 +1158,18 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 			"referrals", &nvmet_referrals_type);
 	configfs_add_default_group(&port->referrals_group, &port->group);
 
+	config_group_init_type_name(&port->ana_groups_group,
+			"ana_groups", &nvmet_ana_groups_type);
+	configfs_add_default_group(&port->ana_groups_group, &port->group);
+
+	port->ana_default_group.port = port;
+	port->ana_default_group.grpid = NVMET_DEFAULT_ANA_GRPID;
+	config_group_init_type_name(&port->ana_default_group.group,
+			__stringify(NVMET_DEFAULT_ANA_GRPID),
+			&nvmet_ana_group_type);
+	configfs_add_default_group(&port->ana_default_group.group,
+			&port->ana_groups_group);
+
 	return &port->group;
 }
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 9838103f2d62..ebf3e7a6c49e 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -18,6 +18,7 @@
 
 #include "nvmet.h"
 
+struct workqueue_struct *buffered_io_wq;
 static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
 static DEFINE_IDA(cntlid_ida);
 
@@ -39,6 +40,10 @@ static DEFINE_IDA(cntlid_ida);
  */
 DECLARE_RWSEM(nvmet_config_sem);
 
+u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+u64 nvmet_ana_chgcnt;
+DECLARE_RWSEM(nvmet_ana_sem);
+
 static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
 		const char *subsysnqn);
 
@@ -175,7 +180,7 @@ out_unlock:
 	mutex_unlock(&ctrl->lock);
 }
 
-static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
+void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 {
 	struct nvmet_ctrl *ctrl;
 
@@ -189,6 +194,33 @@ static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 	}
 }
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port)
+{
+	struct nvmet_ctrl *ctrl;
+
+	mutex_lock(&subsys->lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		if (port && ctrl->port != port)
+			continue;
+		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_ANA_CHANGE))
+			continue;
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+				NVME_AER_NOTICE_ANA, NVME_LOG_ANA);
+	}
+	mutex_unlock(&subsys->lock);
+}
+
+void nvmet_port_send_ana_event(struct nvmet_port *port)
+{
+	struct nvmet_subsys_link *p;
+
+	down_read(&nvmet_config_sem);
+	list_for_each_entry(p, &port->subsystems, entry)
+		nvmet_send_ana_event(p->subsys, port);
+	up_read(&nvmet_config_sem);
+}
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops)
 {
 	int ret = 0;
@@ -241,6 +273,10 @@ int nvmet_enable_port(struct nvmet_port *port)
 		return ret;
 	}
 
+	/* If the transport didn't set inline_data_size, then disable it. */
+	if (port->inline_data_size < 0)
+		port->inline_data_size = 0;
+
 	port->enabled = true;
 	return 0;
 }
@@ -332,9 +368,13 @@ static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
 int nvmet_ns_enable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&subsys->lock);
+	ret = -EMFILE;
+	if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES)
+		goto out_unlock;
+	ret = 0;
 	if (ns->enabled)
 		goto out_unlock;
 
@@ -369,6 +409,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 
 		list_add_tail_rcu(&ns->dev_link, &old->dev_link);
 	}
+	subsys->nr_namespaces++;
 
 	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
@@ -409,6 +450,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	percpu_ref_exit(&ns->ref);
 
 	mutex_lock(&subsys->lock);
+	subsys->nr_namespaces--;
 	nvmet_ns_changed(subsys, ns->nsid);
 	nvmet_ns_dev_disable(ns);
 out_unlock:
@@ -419,6 +461,10 @@ void nvmet_ns_free(struct nvmet_ns *ns)
 {
 	nvmet_ns_disable(ns);
 
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[ns->anagrpid]--;
+	up_write(&nvmet_ana_sem);
+
 	kfree(ns->device_path);
 	kfree(ns);
 }
@@ -436,7 +482,14 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 
 	ns->nsid = nsid;
 	ns->subsys = subsys;
+
+	down_write(&nvmet_ana_sem);
+	ns->anagrpid = NVMET_DEFAULT_ANA_GRPID;
+	nvmet_ana_group_enabled[ns->anagrpid]++;
+	up_write(&nvmet_ana_sem);
+
 	uuid_gen(&ns->uuid);
+	ns->buffered_io = false;
 
 	return ns;
 }
@@ -542,6 +595,35 @@ int nvmet_sq_init(struct nvmet_sq *sq)
 }
 EXPORT_SYMBOL_GPL(nvmet_sq_init);
 
+static inline u16 nvmet_check_ana_state(struct nvmet_port *port,
+		struct nvmet_ns *ns)
+{
+	enum nvme_ana_state state = port->ana_state[ns->anagrpid];
+
+	if (unlikely(state == NVME_ANA_INACCESSIBLE))
+		return NVME_SC_ANA_INACCESSIBLE;
+	if (unlikely(state == NVME_ANA_PERSISTENT_LOSS))
+		return NVME_SC_ANA_PERSISTENT_LOSS;
+	if (unlikely(state == NVME_ANA_CHANGE))
+		return NVME_SC_ANA_TRANSITION;
+	return 0;
+}
+
+static inline u16 nvmet_io_cmd_check_access(struct nvmet_req *req)
+{
+	if (unlikely(req->ns->readonly)) {
+		switch (req->cmd->common.opcode) {
+		case nvme_cmd_read:
+		case nvme_cmd_flush:
+			break;
+		default:
+			return NVME_SC_NS_WRITE_PROTECTED;
+		}
+	}
+
+	return 0;
+}
+
 static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
@@ -554,6 +636,12 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
 	if (unlikely(!req->ns))
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+	ret = nvmet_check_ana_state(req->port, req->ns);
+	if (unlikely(ret))
+		return ret;
+	ret = nvmet_io_cmd_check_access(req);
+	if (unlikely(ret))
+		return ret;
 
 	if (req->ns->file)
 		return nvmet_file_parse_io_cmd(req);
@@ -870,6 +958,8 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	nvmet_init_cap(ctrl);
 
+	ctrl->port = req->port;
+
 	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
 	INIT_LIST_HEAD(&ctrl->async_events);
 
@@ -1109,6 +1199,15 @@ static int __init nvmet_init(void)
 {
 	int error;
 
+	nvmet_ana_group_enabled[NVMET_DEFAULT_ANA_GRPID] = 1;
+
+	buffered_io_wq = alloc_workqueue("nvmet-buffered-io-wq",
+			WQ_MEM_RECLAIM, 0);
+	if (!buffered_io_wq) {
+		error = -ENOMEM;
+		goto out;
+	}
+
 	error = nvmet_init_discovery();
 	if (error)
 		goto out;
@@ -1129,6 +1228,7 @@ static void __exit nvmet_exit(void)
 	nvmet_exit_configfs();
 	nvmet_exit_discovery();
 	ida_destroy(&cntlid_ida);
+	destroy_workqueue(buffered_io_wq);
 
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024);
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024);
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 08656b849bd6..eae29f493a07 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -171,7 +171,7 @@ static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req)
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->has_keyed_sgls)
 		id->sgls |= cpu_to_le32(1 << 2);
-	if (ctrl->ops->sqe_inline_size)
+	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);
 
 	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index e0b0f7df70c2..7bc9f6240432 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -124,6 +124,13 @@ static void nvmet_bdev_execute_flush(struct nvmet_req *req)
 	submit_bio(bio);
 }
 
+u16 nvmet_bdev_flush(struct nvmet_req *req)
+{
+	if (blkdev_issue_flush(req->ns->bdev, GFP_KERNEL, NULL))
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
+	return 0;
+}
+
 static u16 nvmet_bdev_discard_range(struct nvmet_ns *ns,
 		struct nvme_dsm_range *range, struct bio **bio)
 {
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 8c42b3a8c420..81a9dc5290a8 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -16,6 +16,8 @@
 void nvmet_file_ns_disable(struct nvmet_ns *ns)
 {
 	if (ns->file) {
+		if (ns->buffered_io)
+			flush_workqueue(buffered_io_wq);
 		mempool_destroy(ns->bvec_pool);
 		ns->bvec_pool = NULL;
 		kmem_cache_destroy(ns->bvec_cache);
@@ -27,11 +29,14 @@ void nvmet_file_ns_disable(struct nvmet_ns *ns)
 
 int nvmet_file_ns_enable(struct nvmet_ns *ns)
 {
-	int ret;
+	int flags = O_RDWR | O_LARGEFILE;
 	struct kstat stat;
+	int ret;
+
+	if (!ns->buffered_io)
+		flags |= O_DIRECT;
 
-	ns->file = filp_open(ns->device_path,
-			O_RDWR | O_LARGEFILE | O_DIRECT, 0);
+	ns->file = filp_open(ns->device_path, flags, 0);
 	if (IS_ERR(ns->file)) {
 		pr_err("failed to open file %s: (%ld)\n",
 				ns->device_path, PTR_ERR(ns->file));
@@ -100,7 +105,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
 
 	iocb->ki_pos = pos;
 	iocb->ki_filp = req->ns->file;
-	iocb->ki_flags = IOCB_DIRECT | ki_flags;
+	iocb->ki_flags = ki_flags | iocb_flags(req->ns->file);
 
 	ret = call_iter(iocb, &iter);
 
@@ -140,6 +145,12 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 		return;
 	}
 
+	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
+	if (unlikely(pos + req->data_len > req->ns->size)) {
+		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		return;
+	}
+
 	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
 		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
 				GFP_KERNEL);
@@ -155,8 +166,6 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 			is_sync = true;
 	}
 
-	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
-
 	memset(&req->f.iocb, 0, sizeof(struct kiocb));
 	for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) {
 		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter);
@@ -189,14 +198,31 @@ out:
 	nvmet_file_submit_bvec(req, pos, bv_cnt, total_len);
 }
 
-static void nvmet_file_flush_work(struct work_struct *w)
+static void nvmet_file_buffered_io_work(struct work_struct *w)
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
-	int ret;
 
-	ret = vfs_fsync(req->ns->file, 1);
+	nvmet_file_execute_rw(req);
+}
 
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+static void nvmet_file_execute_rw_buffered_io(struct nvmet_req *req)
+{
+	INIT_WORK(&req->f.work, nvmet_file_buffered_io_work);
+	queue_work(buffered_io_wq, &req->f.work);
+}
+
+u16 nvmet_file_flush(struct nvmet_req *req)
+{
+	if (vfs_fsync(req->ns->file, 1) < 0)
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
+	return 0;
+}
+
+static void nvmet_file_flush_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+
+	nvmet_req_complete(req, nvmet_file_flush(req));
 }
 
 static void nvmet_file_execute_flush(struct nvmet_req *req)
@@ -209,22 +235,30 @@ static void nvmet_file_execute_discard(struct nvmet_req *req)
 {
 	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	struct nvme_dsm_range range;
-	loff_t offset;
-	loff_t len;
-	int i, ret;
+	loff_t offset, len;
+	u16 ret;
+	int i;
 
 	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
-		if (nvmet_copy_from_sgl(req, i * sizeof(range), &range,
-					sizeof(range)))
+		ret = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+					sizeof(range));
+		if (ret)
 			break;
+
 		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
 		len = le32_to_cpu(range.nlb) << req->ns->blksize_shift;
-		ret = vfs_fallocate(req->ns->file, mode, offset, len);
-		if (ret)
+		if (offset + len > req->ns->size) {
+			ret = NVME_SC_LBA_RANGE | NVME_SC_DNR;
 			break;
+		}
+
+		if (vfs_fallocate(req->ns->file, mode, offset, len)) {
+			ret = NVME_SC_INTERNAL | NVME_SC_DNR;
+			break;
+		}
 	}
 
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	nvmet_req_complete(req, ret);
 }
 
 static void nvmet_file_dsm_work(struct work_struct *w)
@@ -263,6 +297,11 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w)
 	len = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
 			req->ns->blksize_shift);
 
+	if (unlikely(offset + len > req->ns->size)) {
+		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		return;
+	}
+
 	ret = vfs_fallocate(req->ns->file, mode, offset, len);
 	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
 }
@@ -280,7 +319,10 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	switch (cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
-		req->execute = nvmet_file_execute_rw;
+		if (req->ns->buffered_io)
+			req->execute = nvmet_file_execute_rw_buffered_io;
+		else
+			req->execute = nvmet_file_execute_rw;
 		req->data_len = nvmet_rw_len(req);
 		return 0;
 	case nvme_cmd_flush:
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index ae7586b8be07..9908082b32c4 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -227,6 +227,7 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set,
 {
 	struct nvme_loop_ctrl *ctrl = set->driver_data;
 
+	nvme_req(req)->ctrl = &ctrl->ctrl;
 	return nvme_loop_init_iod(ctrl, blk_mq_rq_to_pdu(req),
 			(set == &ctrl->tag_set) ? hctx_idx + 1 : 0);
 }
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 480dfe10fad9..ec9af4ee03b6 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -30,12 +30,11 @@
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
 
-
 /*
  * Supported optional AENs:
  */
 #define NVMET_AEN_CFG_OPTIONAL \
-	NVME_AEN_CFG_NS_ATTR
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_ANA_CHANGE)
 
 /*
  * Plus mandatory SMART AENs (we'll never send them, but allow enabling them):
@@ -59,12 +58,15 @@ struct nvmet_ns {
 	struct percpu_ref	ref;
 	struct block_device	*bdev;
 	struct file		*file;
+	bool			readonly;
 	u32			nsid;
 	u32			blksize_shift;
 	loff_t			size;
 	u8			nguid[16];
 	uuid_t			uuid;
+	u32			anagrpid;
 
+	bool			buffered_io;
 	bool			enabled;
 	struct nvmet_subsys	*subsys;
 	const char		*device_path;
@@ -97,6 +99,18 @@ struct nvmet_sq {
 	struct completion	confirm_done;
 };
 
+struct nvmet_ana_group {
+	struct config_group	group;
+	struct nvmet_port	*port;
+	u32			grpid;
+};
+
+static inline struct nvmet_ana_group *to_ana_group(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_ana_group,
+			group);
+}
+
 /**
  * struct nvmet_port -	Common structure to keep port
  *				information for the target.
@@ -114,8 +128,12 @@ struct nvmet_port {
 	struct list_head		subsystems;
 	struct config_group		referrals_group;
 	struct list_head		referrals;
+	struct config_group		ana_groups_group;
+	struct nvmet_ana_group		ana_default_group;
+	enum nvme_ana_state		*ana_state;
 	void				*priv;
 	bool				enabled;
+	int				inline_data_size;
 };
 
 static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
@@ -124,6 +142,13 @@ static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
 			group);
 }
 
+static inline struct nvmet_port *ana_groups_to_port(
+		struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_port,
+			ana_groups_group);
+}
+
 struct nvmet_ctrl {
 	struct nvmet_subsys	*subsys;
 	struct nvmet_cq		**cqs;
@@ -138,6 +163,8 @@ struct nvmet_ctrl {
 	u16			cntlid;
 	u32			kato;
 
+	struct nvmet_port	*port;
+
 	u32			aen_enabled;
 	unsigned long		aen_masked;
 	struct nvmet_req	*async_event_cmds[NVMET_ASYNC_EVENTS];
@@ -166,6 +193,7 @@ struct nvmet_subsys {
 	struct kref		ref;
 
 	struct list_head	namespaces;
+	unsigned int		nr_namespaces;
 	unsigned int		max_nsid;
 
 	struct list_head	ctrls;
@@ -225,7 +253,6 @@ struct nvmet_req;
 struct nvmet_fabrics_ops {
 	struct module *owner;
 	unsigned int type;
-	unsigned int sqe_inline_size;
 	unsigned int msdbd;
 	bool has_keyed_sgls : 1;
 	void (*queue_response)(struct nvmet_req *req);
@@ -269,6 +296,8 @@ struct nvmet_req {
 	const struct nvmet_fabrics_ops *ops;
 };
 
+extern struct workqueue_struct *buffered_io_wq;
+
 static inline void nvmet_set_status(struct nvmet_req *req, u16 status)
 {
 	req->rsp->status = cpu_to_le16(status << 1);
@@ -337,6 +366,10 @@ void nvmet_ns_disable(struct nvmet_ns *ns);
 struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid);
 void nvmet_ns_free(struct nvmet_ns *ns);
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port);
+void nvmet_port_send_ana_event(struct nvmet_port *port);
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops);
 void nvmet_unregister_transport(const struct nvmet_fabrics_ops *ops);
 
@@ -357,6 +390,22 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 #define NVMET_QUEUE_SIZE	1024
 #define NVMET_NR_QUEUES		128
 #define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
+
+/*
+ * Nice round number that makes a list of nsids fit into a page.
+ * Should become tunable at some point in the future.
+ */
+#define NVMET_MAX_NAMESPACES	1024
+
+/*
+ * 0 is not a valid ANA group ID, so we start numbering at 1.
+ *
+ * ANA Group 1 exists without manual intervention, has namespaces assigned to it
+ * by default, and is available in an optimized state through all ports.
+ */
+#define NVMET_MAX_ANAGRPS	128
+#define NVMET_DEFAULT_ANA_GRPID	1
+
 #define NVMET_KAS		10
 #define NVMET_DISC_KATO		120
 
@@ -370,6 +419,10 @@ extern struct nvmet_subsys *nvmet_disc_subsys;
 extern u64 nvmet_genctr;
 extern struct rw_semaphore nvmet_config_sem;
 
+extern u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+extern u64 nvmet_ana_chgcnt;
+extern struct rw_semaphore nvmet_ana_sem;
+
 bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
 		const char *hostnqn);
 
@@ -377,6 +430,9 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns);
 int nvmet_file_ns_enable(struct nvmet_ns *ns);
 void nvmet_bdev_ns_disable(struct nvmet_ns *ns);
 void nvmet_file_ns_disable(struct nvmet_ns *ns);
+u16 nvmet_bdev_flush(struct nvmet_req *req);
+u16 nvmet_file_flush(struct nvmet_req *req);
+void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid);
 
 static inline u32 nvmet_rw_len(struct nvmet_req *req)
 {
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 52e0c5d579a7..e7f43d1e1779 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -33,16 +33,17 @@
 #include "nvmet.h"
 
 /*
- * We allow up to a page of inline data to go with the SQE
+ * We allow at least 1 page, up to 4 SGEs, and up to 16KB of inline data
  */
-#define NVMET_RDMA_INLINE_DATA_SIZE	PAGE_SIZE
+#define NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE	PAGE_SIZE
+#define NVMET_RDMA_MAX_INLINE_SGE		4
+#define NVMET_RDMA_MAX_INLINE_DATA_SIZE		max_t(int, SZ_16K, PAGE_SIZE)
 
 struct nvmet_rdma_cmd {
-	struct ib_sge		sge[2];
+	struct ib_sge		sge[NVMET_RDMA_MAX_INLINE_SGE + 1];
 	struct ib_cqe		cqe;
 	struct ib_recv_wr	wr;
-	struct scatterlist	inline_sg;
-	struct page		*inline_page;
+	struct scatterlist	inline_sg[NVMET_RDMA_MAX_INLINE_SGE];
 	struct nvme_command     *nvme_cmd;
 	struct nvmet_rdma_queue	*queue;
 };
@@ -116,6 +117,8 @@ struct nvmet_rdma_device {
 	size_t			srq_size;
 	struct kref		ref;
 	struct list_head	entry;
+	int			inline_data_size;
+	int			inline_page_count;
 };
 
 static bool nvmet_rdma_use_srq;
@@ -138,6 +141,11 @@ static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);
 
 static const struct nvmet_fabrics_ops nvmet_rdma_ops;
 
+static int num_pages(int len)
+{
+	return 1 + (((len - 1) & PAGE_MASK) >> PAGE_SHIFT);
+}
+
 /* XXX: really should move to a generic header sooner or later.. */
 static inline u32 get_unaligned_le24(const u8 *p)
 {
@@ -184,6 +192,71 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
 	spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags);
 }
 
+static void nvmet_rdma_free_inline_pages(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_cmd *c)
+{
+	struct scatterlist *sg;
+	struct ib_sge *sge;
+	int i;
+
+	if (!ndev->inline_data_size)
+		return;
+
+	sg = c->inline_sg;
+	sge = &c->sge[1];
+
+	for (i = 0; i < ndev->inline_page_count; i++, sg++, sge++) {
+		if (sge->length)
+			ib_dma_unmap_page(ndev->device, sge->addr,
+					sge->length, DMA_FROM_DEVICE);
+		if (sg_page(sg))
+			__free_page(sg_page(sg));
+	}
+}
+
+static int nvmet_rdma_alloc_inline_pages(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_cmd *c)
+{
+	struct scatterlist *sg;
+	struct ib_sge *sge;
+	struct page *pg;
+	int len;
+	int i;
+
+	if (!ndev->inline_data_size)
+		return 0;
+
+	sg = c->inline_sg;
+	sg_init_table(sg, ndev->inline_page_count);
+	sge = &c->sge[1];
+	len = ndev->inline_data_size;
+
+	for (i = 0; i < ndev->inline_page_count; i++, sg++, sge++) {
+		pg = alloc_page(GFP_KERNEL);
+		if (!pg)
+			goto out_err;
+		sg_assign_page(sg, pg);
+		sge->addr = ib_dma_map_page(ndev->device,
+			pg, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+		if (ib_dma_mapping_error(ndev->device, sge->addr))
+			goto out_err;
+		sge->length = min_t(int, len, PAGE_SIZE);
+		sge->lkey = ndev->pd->local_dma_lkey;
+		len -= sge->length;
+	}
+
+	return 0;
+out_err:
+	for (; i >= 0; i--, sg--, sge--) {
+		if (sge->length)
+			ib_dma_unmap_page(ndev->device, sge->addr,
+					sge->length, DMA_FROM_DEVICE);
+		if (sg_page(sg))
+			__free_page(sg_page(sg));
+	}
+	return -ENOMEM;
+}
+
 static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
 			struct nvmet_rdma_cmd *c, bool admin)
 {
@@ -200,33 +273,17 @@ static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
 	c->sge[0].length = sizeof(*c->nvme_cmd);
 	c->sge[0].lkey = ndev->pd->local_dma_lkey;
 
-	if (!admin) {
-		c->inline_page = alloc_pages(GFP_KERNEL,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-		if (!c->inline_page)
-			goto out_unmap_cmd;
-		c->sge[1].addr = ib_dma_map_page(ndev->device,
-				c->inline_page, 0, NVMET_RDMA_INLINE_DATA_SIZE,
-				DMA_FROM_DEVICE);
-		if (ib_dma_mapping_error(ndev->device, c->sge[1].addr))
-			goto out_free_inline_page;
-		c->sge[1].length = NVMET_RDMA_INLINE_DATA_SIZE;
-		c->sge[1].lkey = ndev->pd->local_dma_lkey;
-	}
+	if (!admin && nvmet_rdma_alloc_inline_pages(ndev, c))
+		goto out_unmap_cmd;
 
 	c->cqe.done = nvmet_rdma_recv_done;
 
 	c->wr.wr_cqe = &c->cqe;
 	c->wr.sg_list = c->sge;
-	c->wr.num_sge = admin ? 1 : 2;
+	c->wr.num_sge = admin ? 1 : ndev->inline_page_count + 1;
 
 	return 0;
 
-out_free_inline_page:
-	if (!admin) {
-		__free_pages(c->inline_page,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-	}
 out_unmap_cmd:
 	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
 			sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
@@ -240,12 +297,8 @@ out:
 static void nvmet_rdma_free_cmd(struct nvmet_rdma_device *ndev,
 		struct nvmet_rdma_cmd *c, bool admin)
 {
-	if (!admin) {
-		ib_dma_unmap_page(ndev->device, c->sge[1].addr,
-				NVMET_RDMA_INLINE_DATA_SIZE, DMA_FROM_DEVICE);
-		__free_pages(c->inline_page,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-	}
+	if (!admin)
+		nvmet_rdma_free_inline_pages(ndev, c);
 	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
 				sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
 	kfree(c->nvme_cmd);
@@ -383,14 +436,21 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
 		struct nvmet_rdma_cmd *cmd)
 {
 	struct ib_recv_wr *bad_wr;
+	int ret;
 
 	ib_dma_sync_single_for_device(ndev->device,
 		cmd->sge[0].addr, cmd->sge[0].length,
 		DMA_FROM_DEVICE);
 
 	if (ndev->srq)
-		return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
-	return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
+		ret = ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
+	else
+		ret = ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
+
+	if (unlikely(ret))
+		pr_err("post_recv cmd failed\n");
+
+	return ret;
 }
 
 static void nvmet_rdma_process_wr_wait_list(struct nvmet_rdma_queue *queue)
@@ -429,7 +489,7 @@ static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp)
 				rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
 	}
 
-	if (rsp->req.sg != &rsp->cmd->inline_sg)
+	if (rsp->req.sg != rsp->cmd->inline_sg)
 		sgl_free(rsp->req.sg);
 
 	if (unlikely(!list_empty_careful(&queue->rsp_wr_wait_list)))
@@ -493,7 +553,7 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req)
 		rsp->send_sge.addr, rsp->send_sge.length,
 		DMA_TO_DEVICE);
 
-	if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) {
+	if (unlikely(ib_post_send(cm_id->qp, first_wr, &bad_wr))) {
 		pr_err("sending cmd response failed\n");
 		nvmet_rdma_release_rsp(rsp);
 	}
@@ -529,10 +589,25 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc)
 static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len,
 		u64 off)
 {
-	sg_init_table(&rsp->cmd->inline_sg, 1);
-	sg_set_page(&rsp->cmd->inline_sg, rsp->cmd->inline_page, len, off);
-	rsp->req.sg = &rsp->cmd->inline_sg;
-	rsp->req.sg_cnt = 1;
+	int sg_count = num_pages(len);
+	struct scatterlist *sg;
+	int i;
+
+	sg = rsp->cmd->inline_sg;
+	for (i = 0; i < sg_count; i++, sg++) {
+		if (i < sg_count - 1)
+			sg_unmark_end(sg);
+		else
+			sg_mark_end(sg);
+		sg->offset = off;
+		sg->length = min_t(int, len, PAGE_SIZE - off);
+		len -= sg->length;
+		if (!i)
+			off = 0;
+	}
+
+	rsp->req.sg = rsp->cmd->inline_sg;
+	rsp->req.sg_cnt = sg_count;
 }
 
 static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
@@ -544,7 +619,7 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
 	if (!nvme_is_write(rsp->req.cmd))
 		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 
-	if (off + len > NVMET_RDMA_INLINE_DATA_SIZE) {
+	if (off + len > rsp->queue->dev->inline_data_size) {
 		pr_err("invalid inline data offset!\n");
 		return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
 	}
@@ -743,7 +818,7 @@ static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
 	srq_size = 4095;	/* XXX: tune */
 
 	srq_attr.attr.max_wr = srq_size;
-	srq_attr.attr.max_sge = 2;
+	srq_attr.attr.max_sge = 1 + ndev->inline_page_count;
 	srq_attr.attr.srq_limit = 0;
 	srq_attr.srq_type = IB_SRQT_BASIC;
 	srq = ib_create_srq(ndev->pd, &srq_attr);
@@ -765,11 +840,16 @@ static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
 	ndev->srq = srq;
 	ndev->srq_size = srq_size;
 
-	for (i = 0; i < srq_size; i++)
-		nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
+	for (i = 0; i < srq_size; i++) {
+		ret = nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
+		if (ret)
+			goto out_free_cmds;
+	}
 
 	return 0;
 
+out_free_cmds:
+	nvmet_rdma_free_cmds(ndev, ndev->srq_cmds, ndev->srq_size, false);
 out_destroy_srq:
 	ib_destroy_srq(srq);
 	return ret;
@@ -793,7 +873,10 @@ static void nvmet_rdma_free_dev(struct kref *ref)
 static struct nvmet_rdma_device *
 nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 {
+	struct nvmet_port *port = cm_id->context;
 	struct nvmet_rdma_device *ndev;
+	int inline_page_count;
+	int inline_sge_count;
 	int ret;
 
 	mutex_lock(&device_list_mutex);
@@ -807,6 +890,18 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 	if (!ndev)
 		goto out_err;
 
+	inline_page_count = num_pages(port->inline_data_size);
+	inline_sge_count = max(cm_id->device->attrs.max_sge_rd,
+				cm_id->device->attrs.max_sge) - 1;
+	if (inline_page_count > inline_sge_count) {
+		pr_warn("inline_data_size %d cannot be supported by device %s. Reducing to %lu.\n",
+			port->inline_data_size, cm_id->device->name,
+			inline_sge_count * PAGE_SIZE);
+		port->inline_data_size = inline_sge_count * PAGE_SIZE;
+		inline_page_count = inline_sge_count;
+	}
+	ndev->inline_data_size = port->inline_data_size;
+	ndev->inline_page_count = inline_page_count;
 	ndev->device = cm_id->device;
 	kref_init(&ndev->ref);
 
@@ -881,7 +976,7 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 	} else {
 		/* +1 for drain */
 		qp_attr.cap.max_recv_wr = 1 + queue->recv_queue_size;
-		qp_attr.cap.max_recv_sge = 2;
+		qp_attr.cap.max_recv_sge = 1 + ndev->inline_page_count;
 	}
 
 	ret = rdma_create_qp(queue->cm_id, ndev->pd, &qp_attr);
@@ -899,13 +994,17 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 	if (!ndev->srq) {
 		for (i = 0; i < queue->recv_queue_size; i++) {
 			queue->cmds[i].queue = queue;
-			nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
+			ret = nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
+			if (ret)
+				goto err_destroy_qp;
 		}
 	}
 
 out:
 	return ret;
 
+err_destroy_qp:
+	rdma_destroy_qp(queue->cm_id);
 err_destroy_cq:
 	ib_free_cq(queue->cq);
 	goto out;
@@ -1379,6 +1478,15 @@ static int nvmet_rdma_add_port(struct nvmet_port *port)
 		return -EINVAL;
 	}
 
+	if (port->inline_data_size < 0) {
+		port->inline_data_size = NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE;
+	} else if (port->inline_data_size > NVMET_RDMA_MAX_INLINE_DATA_SIZE) {
+		pr_warn("inline_data_size %u is too large, reducing to %u\n",
+			port->inline_data_size,
+			NVMET_RDMA_MAX_INLINE_DATA_SIZE);
+		port->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
+	}
+
 	ret = inet_pton_with_scope(&init_net, af, port->disc_addr.traddr,
 			port->disc_addr.trsvcid, &addr);
 	if (ret) {
@@ -1456,7 +1564,6 @@ static void nvmet_rdma_disc_port_addr(struct nvmet_req *req,
 static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.owner			= THIS_MODULE,
 	.type			= NVMF_TRTYPE_RDMA,
-	.sqe_inline_size	= NVMET_RDMA_INLINE_DATA_SIZE,
 	.msdbd			= 1,
 	.has_keyed_sgls		= 1,
 	.add_port		= nvmet_rdma_add_port,
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 33d85511d790..5957cd4fa262 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -127,20 +127,20 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	}
 
 	/*
-	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to
-	 * setup the correct supported mask.
+	 * If @dev is expected to be DMA-capable then the bus code that created
+	 * it should have initialised its dma_mask pointer by this point. For
+	 * now, we'll continue the legacy behaviour of coercing it to the
+	 * coherent mask if not, but we'll no longer do so quietly.
 	 */
-	if (!dev->coherent_dma_mask)
-		dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	/*
-	 * Set it to coherent_dma_mask by default if the architecture
-	 * code has not set it.
-	 */
-	if (!dev->dma_mask)
+	if (!dev->dma_mask) {
+		dev_warn(dev, "DMA mask not set\n");
 		dev->dma_mask = &dev->coherent_dma_mask;
+	}
 
-	if (!size)
+	if (!size && dev->coherent_dma_mask)
 		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	else if (!size)
+		size = 1ULL << 32;
 
 	dev->dma_pfn_offset = offset;
 
@@ -149,6 +149,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	 * set by the driver.
 	 */
 	mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1);
+	dev->bus_dma_mask = mask;
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
 
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 6925d993e1f0..7ba90c290a42 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -185,6 +185,9 @@ static struct platform_device *of_platform_device_create_pdata(
 	if (!dev)
 		goto err_clear_flag;
 
+	dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	if (!dev->dev.dma_mask)
+		dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
 	dev->dev.bus = &platform_bus_type;
 	dev->dev.platform_data = platform_data;
 	of_msi_configure(&dev->dev, dev->dev.of_node);
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index f6325f1a89e8..d4d4a55f09f8 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -45,6 +45,7 @@
 #include <linux/irqdomain.h>
 #include <asm/irqdomain.h>
 #include <asm/apic.h>
+#include <linux/irq.h>
 #include <linux/msi.h>
 #include <linux/hyperv.h>
 #include <linux/refcount.h>
diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c
index 322de58eebaf..f66521c7f846 100644
--- a/drivers/platform/mips/cpu_hwmon.c
+++ b/drivers/platform/mips/cpu_hwmon.c
@@ -30,7 +30,8 @@ int loongson3_cpu_temp(int cpu)
 	case PRID_REV_LOONGSON3B_R2:
 		reg = ((reg >> 8) & 0xff) - 100;
 		break;
-	case PRID_REV_LOONGSON3A_R3:
+	case PRID_REV_LOONGSON3A_R3_0:
+	case PRID_REV_LOONGSON3A_R3_1:
 		reg = (reg & 0xffff)*731/0x4000 - 273;
 		break;
 	}
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index a9f60d0ee02e..a23e7d394a0a 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -73,8 +73,8 @@ static int  dasd_alloc_queue(struct dasd_block *);
 static void dasd_setup_queue(struct dasd_block *);
 static void dasd_free_queue(struct dasd_block *);
 static int dasd_flush_block_queue(struct dasd_block *);
-static void dasd_device_tasklet(struct dasd_device *);
-static void dasd_block_tasklet(struct dasd_block *);
+static void dasd_device_tasklet(unsigned long);
+static void dasd_block_tasklet(unsigned long);
 static void do_kick_device(struct work_struct *);
 static void do_restore_device(struct work_struct *);
 static void do_reload_device(struct work_struct *);
@@ -125,8 +125,7 @@ struct dasd_device *dasd_alloc_device(void)
 	dasd_init_chunklist(&device->erp_chunks, device->erp_mem, PAGE_SIZE);
 	spin_lock_init(&device->mem_lock);
 	atomic_set(&device->tasklet_scheduled, 0);
-	tasklet_init(&device->tasklet,
-		     (void (*)(unsigned long)) dasd_device_tasklet,
+	tasklet_init(&device->tasklet, dasd_device_tasklet,
 		     (unsigned long) device);
 	INIT_LIST_HEAD(&device->ccw_queue);
 	timer_setup(&device->timer, dasd_device_timeout, 0);
@@ -166,8 +165,7 @@ struct dasd_block *dasd_alloc_block(void)
 	atomic_set(&block->open_count, -1);
 
 	atomic_set(&block->tasklet_scheduled, 0);
-	tasklet_init(&block->tasklet,
-		     (void (*)(unsigned long)) dasd_block_tasklet,
+	tasklet_init(&block->tasklet, dasd_block_tasklet,
 		     (unsigned long) block);
 	INIT_LIST_HEAD(&block->ccw_queue);
 	spin_lock_init(&block->queue_lock);
@@ -2064,8 +2062,9 @@ EXPORT_SYMBOL_GPL(dasd_flush_device_queue);
 /*
  * Acquire the device lock and process queues for the device.
  */
-static void dasd_device_tasklet(struct dasd_device *device)
+static void dasd_device_tasklet(unsigned long data)
 {
+	struct dasd_device *device = (struct dasd_device *) data;
 	struct list_head final_queue;
 
 	atomic_set (&device->tasklet_scheduled, 0);
@@ -2783,8 +2782,9 @@ static void __dasd_block_start_head(struct dasd_block *block)
  * block layer request queue, creates ccw requests, enqueues them on
  * a dasd_device and processes ccw requests that have been returned.
  */
-static void dasd_block_tasklet(struct dasd_block *block)
+static void dasd_block_tasklet(unsigned long data)
 {
+	struct dasd_block *block = (struct dasd_block *) data;
 	struct list_head final_queue;
 	struct list_head *l, *n;
 	struct dasd_ccw_req *cqr;
@@ -3127,6 +3127,7 @@ static int dasd_alloc_queue(struct dasd_block *block)
 	block->tag_set.nr_hw_queues = nr_hw_queues;
 	block->tag_set.queue_depth = queue_depth;
 	block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	block->tag_set.numa_node = NUMA_NO_NODE;
 
 	rc = blk_mq_alloc_tag_set(&block->tag_set);
 	if (rc)
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index e36a114354fc..b9ce93e9df89 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -708,7 +708,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu,
 	struct ccw1 *ccw;
 
 	cqr = lcu->rsu_cqr;
-	strncpy((char *) &cqr->magic, "ECKD", 4);
+	memcpy((char *) &cqr->magic, "ECKD", 4);
 	ASCEBC((char *) &cqr->magic, 4);
 	ccw = cqr->cpaddr;
 	ccw->cmd_code = DASD_ECKD_CCW_RSCK;
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index b9ebb565ee2c..fab35c6170cc 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -426,7 +426,7 @@ dasd_add_busid(const char *bus_id, int features)
 	if (!devmap) {
 		/* This bus_id is new. */
 		new->devindex = dasd_max_devindex++;
-		strncpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
+		strlcpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
 		new->features = features;
 		new->device = NULL;
 		list_add(&new->list, &dasd_hashlists[hash]);
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index bbf95b78ef5d..4e7b55a14b1a 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1780,6 +1780,9 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device)
 	struct dasd_eckd_private *private = device->private;
 	int i;
 
+	if (!private)
+		return;
+
 	dasd_alias_disconnect_device_from_lcu(device);
 	private->ned = NULL;
 	private->sneq = NULL;
@@ -2035,8 +2038,11 @@ static int dasd_eckd_basic_to_ready(struct dasd_device *device)
 
 static int dasd_eckd_online_to_ready(struct dasd_device *device)
 {
-	cancel_work_sync(&device->reload_device);
-	cancel_work_sync(&device->kick_validate);
+	if (cancel_work_sync(&device->reload_device))
+		dasd_put_device(device);
+	if (cancel_work_sync(&device->kick_validate))
+		dasd_put_device(device);
+
 	return 0;
 };
 
@@ -3535,7 +3541,7 @@ static int prepare_itcw(struct itcw *itcw,
 
 	dcw = itcw_add_dcw(itcw, pfx_cmd, 0,
 		     &pfxdata, sizeof(pfxdata), total_data_size);
-	return PTR_RET(dcw);
+	return PTR_ERR_OR_ZERO(dcw);
 }
 
 static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index 6ef8714dc693..93bb09da7fdc 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -313,7 +313,7 @@ static void dasd_eer_write_standard_trigger(struct dasd_device *device,
 	ktime_get_real_ts64(&ts);
 	header.tv_sec = ts.tv_sec;
 	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-	strncpy(header.busid, dev_name(&device->cdev->dev),
+	strlcpy(header.busid, dev_name(&device->cdev->dev),
 		DASD_EER_BUSID_SIZE);
 
 	spin_lock_irqsave(&bufferlock, flags);
@@ -356,7 +356,7 @@ static void dasd_eer_write_snss_trigger(struct dasd_device *device,
 	ktime_get_real_ts64(&ts);
 	header.tv_sec = ts.tv_sec;
 	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-	strncpy(header.busid, dev_name(&device->cdev->dev),
+	strlcpy(header.busid, dev_name(&device->cdev->dev),
 		DASD_EER_BUSID_SIZE);
 
 	spin_lock_irqsave(&bufferlock, flags);
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index b1fcb76dd272..98f66b7b6794 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -455,6 +455,7 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 	bdev->tag_set.nr_hw_queues = nr_requests;
 	bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests;
 	bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	bdev->tag_set.numa_node = NUMA_NO_NODE;
 
 	ret = blk_mq_alloc_tag_set(&bdev->tag_set);
 	if (ret)
diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile
index 0a4c13e1e76e..c6ab34f94b1b 100644
--- a/drivers/s390/char/Makefile
+++ b/drivers/s390/char/Makefile
@@ -12,11 +12,6 @@ GCOV_PROFILE_sclp_early_core.o		:= n
 KCOV_INSTRUMENT_sclp_early_core.o	:= n
 UBSAN_SANITIZE_sclp_early_core.o	:= n
 
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_sclp_early_core.o		+= -march=z900
-endif
-
 CFLAGS_sclp_early_core.o		+= -D__NO_FORTIFY
 
 CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_EXPOLINE)
diff --git a/drivers/s390/char/keyboard.c b/drivers/s390/char/keyboard.c
index 79eb60958015..bbb3001b0961 100644
--- a/drivers/s390/char/keyboard.c
+++ b/drivers/s390/char/keyboard.c
@@ -334,37 +334,41 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 	      int cmd, int perm)
 {
 	struct kbentry tmp;
+	unsigned long kb_index, kb_table;
 	ushort *key_map, val, ov;
 
 	if (copy_from_user(&tmp, user_kbe, sizeof(struct kbentry)))
 		return -EFAULT;
+	kb_index = (unsigned long) tmp.kb_index;
 #if NR_KEYS < 256
-	if (tmp.kb_index >= NR_KEYS)
+	if (kb_index >= NR_KEYS)
 		return -EINVAL;
 #endif
+	kb_table = (unsigned long) tmp.kb_table;
 #if MAX_NR_KEYMAPS < 256
-	if (tmp.kb_table >= MAX_NR_KEYMAPS)
+	if (kb_table >= MAX_NR_KEYMAPS)
 		return -EINVAL;	
+	kb_table = array_index_nospec(kb_table , MAX_NR_KEYMAPS);
 #endif
 
 	switch (cmd) {
 	case KDGKBENT:
-		key_map = kbd->key_maps[tmp.kb_table];
+		key_map = kbd->key_maps[kb_table];
 		if (key_map) {
-		    val = U(key_map[tmp.kb_index]);
+		    val = U(key_map[kb_index]);
 		    if (KTYP(val) >= KBD_NR_TYPES)
 			val = K_HOLE;
 		} else
-		    val = (tmp.kb_index ? K_HOLE : K_NOSUCHMAP);
+		    val = (kb_index ? K_HOLE : K_NOSUCHMAP);
 		return put_user(val, &user_kbe->kb_value);
 	case KDSKBENT:
 		if (!perm)
 			return -EPERM;
-		if (!tmp.kb_index && tmp.kb_value == K_NOSUCHMAP) {
+		if (!kb_index && tmp.kb_value == K_NOSUCHMAP) {
 			/* disallocate map */
-			key_map = kbd->key_maps[tmp.kb_table];
+			key_map = kbd->key_maps[kb_table];
 			if (key_map) {
-			    kbd->key_maps[tmp.kb_table] = NULL;
+			    kbd->key_maps[kb_table] = NULL;
 			    kfree(key_map);
 			}
 			break;
@@ -375,18 +379,18 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 		if (KVAL(tmp.kb_value) > kbd_max_vals[KTYP(tmp.kb_value)])
 			return -EINVAL;
 
-		if (!(key_map = kbd->key_maps[tmp.kb_table])) {
+		if (!(key_map = kbd->key_maps[kb_table])) {
 			int j;
 
 			key_map = kmalloc(sizeof(plain_map),
 						     GFP_KERNEL);
 			if (!key_map)
 				return -ENOMEM;
-			kbd->key_maps[tmp.kb_table] = key_map;
+			kbd->key_maps[kb_table] = key_map;
 			for (j = 0; j < NR_KEYS; j++)
 				key_map[j] = U(K_HOLE);
 		}
-		ov = U(key_map[tmp.kb_index]);
+		ov = U(key_map[kb_index]);
 		if (tmp.kb_value == ov)
 			break;	/* nothing to do */
 		/*
@@ -395,7 +399,7 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 		if (((ov == K_SAK) || (tmp.kb_value == K_SAK)) &&
 		    !capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		key_map[tmp.kb_index] = U(tmp.kb_value);
+		key_map[kb_index] = U(tmp.kb_value);
 		break;
 	}
 	return 0;
diff --git a/drivers/s390/char/monwriter.c b/drivers/s390/char/monwriter.c
index 76c158c41510..4f1a69c9d81d 100644
--- a/drivers/s390/char/monwriter.c
+++ b/drivers/s390/char/monwriter.c
@@ -61,7 +61,7 @@ static int monwrite_diag(struct monwrite_hdr *myhdr, char *buffer, int fcn)
 	struct appldata_product_id id;
 	int rc;
 
-	strncpy(id.prod_nr, "LNXAPPL", 7);
+	memcpy(id.prod_nr, "LNXAPPL", 7);
 	id.prod_fn = myhdr->applid;
 	id.record_nr = myhdr->record_num;
 	id.version_nr = myhdr->version;
diff --git a/drivers/s390/char/sclp_async.c b/drivers/s390/char/sclp_async.c
index ee6f3b563728..e69b12a40636 100644
--- a/drivers/s390/char/sclp_async.c
+++ b/drivers/s390/char/sclp_async.c
@@ -64,42 +64,18 @@ static struct notifier_block call_home_panic_nb = {
 	.priority = INT_MAX,
 };
 
-static int proc_handler_callhome(struct ctl_table *ctl, int write,
-				 void __user *buffer, size_t *count,
-				 loff_t *ppos)
-{
-	unsigned long val;
-	int len, rc;
-	char buf[3];
-
-	if (!*count || (*ppos && !write)) {
-		*count = 0;
-		return 0;
-	}
-	if (!write) {
-		len = snprintf(buf, sizeof(buf), "%d\n", callhome_enabled);
-		rc = copy_to_user(buffer, buf, sizeof(buf));
-		if (rc != 0)
-			return -EFAULT;
-	} else {
-		len = *count;
-		rc = kstrtoul_from_user(buffer, len, 0, &val);
-		if (rc)
-			return rc;
-		if (val != 0 && val != 1)
-			return -EINVAL;
-		callhome_enabled = val;
-	}
-	*count = len;
-	*ppos += len;
-	return 0;
-}
+static int zero;
+static int one = 1;
 
 static struct ctl_table callhome_table[] = {
 	{
 		.procname	= "callhome",
+		.data		= &callhome_enabled,
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_handler_callhome,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 	{}
 };
diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c
index 37e65a05517f..cdcde18e7220 100644
--- a/drivers/s390/char/tape_3590.c
+++ b/drivers/s390/char/tape_3590.c
@@ -113,16 +113,16 @@ static int crypt_enabled(struct tape_device *device)
 static void ext_to_int_kekl(struct tape390_kekl *in,
 			    struct tape3592_kekl *out)
 {
-	int i;
+	int len;
 
 	memset(out, 0, sizeof(*out));
 	if (in->type == TAPE390_KEKL_TYPE_HASH)
 		out->flags |= 0x40;
 	if (in->type_on_tape == TAPE390_KEKL_TYPE_HASH)
 		out->flags |= 0x80;
-	strncpy(out->label, in->label, 64);
-	for (i = strlen(in->label); i < sizeof(out->label); i++)
-		out->label[i] = ' ';
+	len = min(sizeof(out->label), strlen(in->label));
+	memcpy(out->label, in->label, len);
+	memset(out->label + len, ' ', sizeof(out->label) - len);
 	ASCEBC(out->label, sizeof(out->label));
 }
 
diff --git a/drivers/s390/char/tape_class.c b/drivers/s390/char/tape_class.c
index a07102472ce9..b58df0dd0039 100644
--- a/drivers/s390/char/tape_class.c
+++ b/drivers/s390/char/tape_class.c
@@ -54,10 +54,10 @@ struct tape_class_device *register_tape_dev(
 	if (!tcd)
 		return ERR_PTR(-ENOMEM);
 
-	strncpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
+	strlcpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
 	for (s = strchr(tcd->device_name, '/'); s; s = strchr(s, '/'))
 		*s = '!';
-	strncpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
+	strlcpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
 	for (s = strchr(tcd->mode_name, '/'); s; s = strchr(s, '/'))
 		*s = '!';
 
@@ -77,7 +77,7 @@ struct tape_class_device *register_tape_dev(
 	tcd->class_device = device_create(tape_class, device,
 					  tcd->char_device->dev, NULL,
 					  "%s", tcd->device_name);
-	rc = PTR_RET(tcd->class_device);
+	rc = PTR_ERR_OR_ZERO(tcd->class_device);
 	if (rc)
 		goto fail_with_cdev;
 	rc = sysfs_create_link(
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index afbdee74147d..51038ec309c1 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -471,14 +471,17 @@ int chp_new(struct chp_id chpid)
 {
 	struct channel_subsystem *css = css_by_id(chpid.cssid);
 	struct channel_path *chp;
-	int ret;
+	int ret = 0;
 
+	mutex_lock(&css->mutex);
 	if (chp_is_registered(chpid))
-		return 0;
-	chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
-	if (!chp)
-		return -ENOMEM;
+		goto out;
 
+	chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
+	if (!chp) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	/* fill in status, etc. */
 	chp->chpid = chpid;
 	chp->state = 1;
@@ -505,21 +508,20 @@ int chp_new(struct chp_id chpid)
 		put_device(&chp->dev);
 		goto out;
 	}
-	mutex_lock(&css->mutex);
+
 	if (css->cm_enabled) {
 		ret = chp_add_cmg_attr(chp);
 		if (ret) {
 			device_unregister(&chp->dev);
-			mutex_unlock(&css->mutex);
 			goto out;
 		}
 	}
 	css->chps[chpid.id] = chp;
-	mutex_unlock(&css->mutex);
 	goto out;
 out_free:
 	kfree(chp);
 out:
+	mutex_unlock(&css->mutex);
 	return ret;
 }
 
@@ -585,8 +587,7 @@ static void chp_process_crw(struct crw *crw0, struct crw *crw1,
 	switch (crw0->erc) {
 	case CRW_ERC_IPARM: /* Path has come. */
 	case CRW_ERC_INIT:
-		if (!chp_is_registered(chpid))
-			chp_new(chpid);
+		chp_new(chpid);
 		chsc_chp_online(chpid);
 		break;
 	case CRW_ERC_PERRI: /* Path has gone. */
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 9029804dcd22..a0baee25134c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -91,7 +91,7 @@ struct chsc_ssd_area {
 	u16 sch;	  /* subchannel */
 	u8 chpid[8];	  /* chpids 0-7 */
 	u16 fla[8];	  /* full link addresses 0-7 */
-} __attribute__ ((packed));
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_get_ssd_info(struct subchannel_id schid, struct chsc_ssd_info *ssd)
 {
@@ -319,7 +319,7 @@ struct chsc_sei {
 		struct chsc_sei_nt2_area nt2_area;
 		u8 nt_area[PAGE_SIZE - 24];
 	} u;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 /*
  * Node Descriptor as defined in SA22-7204, "Common I/O-Device Commands"
@@ -841,7 +841,7 @@ int __chsc_do_secm(struct channel_subsystem *css, int enable)
 		u32 : 4;
 		u32 fmt : 4;
 		u32 : 16;
-	} __attribute__ ((packed)) *secm_area;
+	} *secm_area;
 	unsigned long flags;
 	int ret, ccode;
 
@@ -1014,7 +1014,7 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp)
 		u32 cmg : 8;
 		u32 zeroes3;
 		u32 data[NR_MEASUREMENT_CHARS];
-	} __attribute__ ((packed)) *scmc_area;
+	} *scmc_area;
 
 	chp->shared = -1;
 	chp->cmg = -1;
@@ -1142,7 +1142,7 @@ int __init chsc_get_cssid(int idx)
 			u8 cssid;
 			u32 : 24;
 		} list[0];
-	} __packed *sdcal_area;
+	} *sdcal_area;
 	int ret;
 
 	spin_lock_irq(&chsc_page_lock);
@@ -1192,7 +1192,7 @@ chsc_determine_css_characteristics(void)
 		u32 reserved4;
 		u32 general_char[510];
 		u32 chsc_char[508];
-	} __attribute__ ((packed)) *scsc_area;
+	} *scsc_area;
 
 	spin_lock_irqsave(&chsc_page_lock, flags);
 	memset(chsc_page, 0, PAGE_SIZE);
@@ -1236,7 +1236,7 @@ int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta)
 		unsigned int rsvd3[3];
 		u64 clock_delta;
 		unsigned int rsvd4[2];
-	} __attribute__ ((packed)) *rr;
+	} *rr;
 	int rc;
 
 	memset(page, 0, PAGE_SIZE);
@@ -1261,7 +1261,7 @@ int chsc_sstpi(void *page, void *result, size_t size)
 		unsigned int rsvd0[3];
 		struct chsc_header response;
 		char data[];
-	} __attribute__ ((packed)) *rr;
+	} *rr;
 	int rc;
 
 	memset(page, 0, PAGE_SIZE);
@@ -1284,7 +1284,7 @@ int chsc_siosl(struct subchannel_id schid)
 		u32 word3;
 		struct chsc_header response;
 		u32 word[11];
-	} __attribute__ ((packed)) *siosl_area;
+	} *siosl_area;
 	unsigned long flags;
 	int ccode;
 	int rc;
diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h
index 5c9f0dd33f4e..78aba8d94eec 100644
--- a/drivers/s390/cio/chsc.h
+++ b/drivers/s390/cio/chsc.h
@@ -15,12 +15,12 @@
 #define NR_MEASUREMENT_CHARS 5
 struct cmg_chars {
 	u32 values[NR_MEASUREMENT_CHARS];
-} __attribute__ ((packed));
+};
 
 #define NR_MEASUREMENT_ENTRIES 8
 struct cmg_entry {
 	u32 values[NR_MEASUREMENT_ENTRIES];
-} __attribute__ ((packed));
+};
 
 struct channel_path_desc_fmt1 {
 	u8 flags;
@@ -38,7 +38,7 @@ struct channel_path_desc_fmt1 {
 	u8 s:1;
 	u8 f:1;
 	u32 zeros[2];
-} __attribute__ ((packed));
+};
 
 struct channel_path_desc_fmt3 {
 	struct channel_path_desc_fmt1 fmt1_desc;
@@ -59,7 +59,7 @@ struct css_chsc_char {
 	u32:7;
 	u32 pnso:1; /* bit 116 */
 	u32:11;
-}__attribute__((packed));
+} __packed;
 
 extern struct css_chsc_char css_chsc_characteristics;
 
@@ -82,7 +82,7 @@ struct chsc_ssqd_area {
 	struct chsc_header response;
 	u32:32;
 	struct qdio_ssqd_desc qdio_ssqd;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_scssc_area {
 	struct chsc_header request;
@@ -102,7 +102,7 @@ struct chsc_scssc_area {
 	u32 reserved[1004];
 	struct chsc_header response;
 	u32:32;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_scpd {
 	struct chsc_header request;
@@ -120,7 +120,7 @@ struct chsc_scpd {
 	struct chsc_header response;
 	u32:32;
 	u8 data[0];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_sda_area {
 	struct chsc_header request;
@@ -199,7 +199,7 @@ struct chsc_scm_info {
 	u32 reserved2[10];
 	u64 restok;
 	struct sale scmal[248];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_scm_info(struct chsc_scm_info *scm_area, u64 token);
 
@@ -243,7 +243,7 @@ struct chsc_pnso_area {
 		struct qdio_brinfo_entry_l3_ipv4 l3_ipv4[0];
 		struct qdio_brinfo_entry_l2	 l2[0];
 	} entries;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_pnso_brinfo(struct subchannel_id schid,
 		struct chsc_pnso_area *brinfo_area,
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 5130d7c67239..de744ca158fd 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -526,76 +526,6 @@ int cio_disable_subchannel(struct subchannel *sch)
 }
 EXPORT_SYMBOL_GPL(cio_disable_subchannel);
 
-static int cio_check_devno_blacklisted(struct subchannel *sch)
-{
-	if (is_blacklisted(sch->schid.ssid, sch->schib.pmcw.dev)) {
-		/*
-		 * This device must not be known to Linux. So we simply
-		 * say that there is no device and return ENODEV.
-		 */
-		CIO_MSG_EVENT(6, "Blacklisted device detected "
-			      "at devno %04X, subchannel set %x\n",
-			      sch->schib.pmcw.dev, sch->schid.ssid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
-/**
- * cio_validate_subchannel - basic validation of subchannel
- * @sch: subchannel structure to be filled out
- * @schid: subchannel id
- *
- * Find out subchannel type and initialize struct subchannel.
- * Return codes:
- *   0 on success
- *   -ENXIO for non-defined subchannels
- *   -ENODEV for invalid subchannels or blacklisted devices
- *   -EIO for subchannels in an invalid subchannel set
- */
-int cio_validate_subchannel(struct subchannel *sch, struct subchannel_id schid)
-{
-	char dbf_txt[15];
-	int ccode;
-	int err;
-
-	sprintf(dbf_txt, "valsch%x", schid.sch_no);
-	CIO_TRACE_EVENT(4, dbf_txt);
-
-	/*
-	 * The first subchannel that is not-operational (ccode==3)
-	 * indicates that there aren't any more devices available.
-	 * If stsch gets an exception, it means the current subchannel set
-	 * is not valid.
-	 */
-	ccode = stsch(schid, &sch->schib);
-	if (ccode) {
-		err = (ccode == 3) ? -ENXIO : ccode;
-		goto out;
-	}
-	sch->st = sch->schib.pmcw.st;
-	sch->schid = schid;
-
-	switch (sch->st) {
-	case SUBCHANNEL_TYPE_IO:
-	case SUBCHANNEL_TYPE_MSG:
-		if (!css_sch_is_valid(&sch->schib))
-			err = -ENODEV;
-		else
-			err = cio_check_devno_blacklisted(sch);
-		break;
-	default:
-		err = 0;
-	}
-	if (err)
-		goto out;
-
-	CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
-		      sch->schid.ssid, sch->schid.sch_no, sch->st);
-out:
-	return err;
-}
-
 /*
  * do_cio_interrupt() handles all normal I/O device IRQ's
  */
@@ -719,6 +649,7 @@ struct subchannel *cio_probe_console(void)
 {
 	struct subchannel_id schid;
 	struct subchannel *sch;
+	struct schib schib;
 	int sch_no, ret;
 
 	sch_no = cio_get_console_sch_no();
@@ -728,7 +659,11 @@ struct subchannel *cio_probe_console(void)
 	}
 	init_subchannel_id(&schid);
 	schid.sch_no = sch_no;
-	sch = css_alloc_subchannel(schid);
+	ret = stsch(schid, &schib);
+	if (ret)
+		return ERR_PTR(-ENODEV);
+
+	sch = css_alloc_subchannel(schid, &schib);
 	if (IS_ERR(sch))
 		return sch;
 
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index 94cd813bdcfe..9811fd8a0c73 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -119,7 +119,6 @@ DECLARE_PER_CPU(struct irb, cio_irb);
 
 #define to_subchannel(n) container_of(n, struct subchannel, dev)
 
-extern int cio_validate_subchannel (struct subchannel *, struct subchannel_id);
 extern int cio_enable_subchannel(struct subchannel *, u32);
 extern int cio_disable_subchannel (struct subchannel *);
 extern int cio_cancel (struct subchannel *);
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 9263a0fb3858..aea502922646 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -25,6 +25,7 @@
 
 #include "css.h"
 #include "cio.h"
+#include "blacklist.h"
 #include "cio_debug.h"
 #include "ioasm.h"
 #include "chsc.h"
@@ -168,18 +169,53 @@ static void css_subchannel_release(struct device *dev)
 	kfree(sch);
 }
 
-struct subchannel *css_alloc_subchannel(struct subchannel_id schid)
+static int css_validate_subchannel(struct subchannel_id schid,
+				   struct schib *schib)
+{
+	int err;
+
+	switch (schib->pmcw.st) {
+	case SUBCHANNEL_TYPE_IO:
+	case SUBCHANNEL_TYPE_MSG:
+		if (!css_sch_is_valid(schib))
+			err = -ENODEV;
+		else if (is_blacklisted(schid.ssid, schib->pmcw.dev)) {
+			CIO_MSG_EVENT(6, "Blacklisted device detected "
+				      "at devno %04X, subchannel set %x\n",
+				      schib->pmcw.dev, schid.ssid);
+			err = -ENODEV;
+		} else
+			err = 0;
+		break;
+	default:
+		err = 0;
+	}
+	if (err)
+		goto out;
+
+	CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
+		      schid.ssid, schid.sch_no, schib->pmcw.st);
+out:
+	return err;
+}
+
+struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
+					struct schib *schib)
 {
 	struct subchannel *sch;
 	int ret;
 
+	ret = css_validate_subchannel(schid, schib);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
 	sch = kzalloc(sizeof(*sch), GFP_KERNEL | GFP_DMA);
 	if (!sch)
 		return ERR_PTR(-ENOMEM);
 
-	ret = cio_validate_subchannel(sch, schid);
-	if (ret < 0)
-		goto err;
+	sch->schid = schid;
+	sch->schib = *schib;
+	sch->st = schib->pmcw.st;
 
 	ret = css_sch_create_locks(sch);
 	if (ret)
@@ -244,8 +280,7 @@ static void ssd_register_chpids(struct chsc_ssd_info *ssd)
 	for (i = 0; i < 8; i++) {
 		mask = 0x80 >> i;
 		if (ssd->path_mask & mask)
-			if (!chp_is_registered(ssd->chpid[i]))
-				chp_new(ssd->chpid[i]);
+			chp_new(ssd->chpid[i]);
 	}
 }
 
@@ -382,12 +417,12 @@ int css_register_subchannel(struct subchannel *sch)
 	return ret;
 }
 
-static int css_probe_device(struct subchannel_id schid)
+static int css_probe_device(struct subchannel_id schid, struct schib *schib)
 {
 	struct subchannel *sch;
 	int ret;
 
-	sch = css_alloc_subchannel(schid);
+	sch = css_alloc_subchannel(schid, schib);
 	if (IS_ERR(sch))
 		return PTR_ERR(sch);
 
@@ -436,23 +471,23 @@ EXPORT_SYMBOL_GPL(css_sch_is_valid);
 static int css_evaluate_new_subchannel(struct subchannel_id schid, int slow)
 {
 	struct schib schib;
+	int ccode;
 
 	if (!slow) {
 		/* Will be done on the slow path. */
 		return -EAGAIN;
 	}
-	if (stsch(schid, &schib)) {
-		/* Subchannel is not provided. */
-		return -ENXIO;
-	}
-	if (!css_sch_is_valid(&schib)) {
-		/* Unusable - ignore. */
-		return 0;
-	}
-	CIO_MSG_EVENT(4, "event: sch 0.%x.%04x, new\n", schid.ssid,
-		      schid.sch_no);
+	/*
+	 * The first subchannel that is not-operational (ccode==3)
+	 * indicates that there aren't any more devices available.
+	 * If stsch gets an exception, it means the current subchannel set
+	 * is not valid.
+	 */
+	ccode = stsch(schid, &schib);
+	if (ccode)
+		return (ccode == 3) ? -ENXIO : ccode;
 
-	return css_probe_device(schid);
+	return css_probe_device(schid, &schib);
 }
 
 static int css_evaluate_known_subchannel(struct subchannel *sch, int slow)
@@ -1081,6 +1116,11 @@ static int __init channel_subsystem_init(void)
 	if (ret)
 		goto out_wq;
 
+	/* Register subchannels which are already in use. */
+	cio_register_early_subchannels();
+	/* Start initial subchannel evaluation. */
+	css_schedule_eval_all();
+
 	return ret;
 out_wq:
 	destroy_workqueue(cio_work_q);
@@ -1120,10 +1160,6 @@ int css_complete_work(void)
  */
 static int __init channel_subsystem_init_sync(void)
 {
-	/* Register subchannels which are already in use. */
-	cio_register_early_subchannels();
-	/* Start initial subchannel evaluation. */
-	css_schedule_eval_all();
 	css_complete_work();
 	return 0;
 }
diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h
index 30357cbf350a..8d832900a63d 100644
--- a/drivers/s390/cio/css.h
+++ b/drivers/s390/cio/css.h
@@ -103,7 +103,8 @@ extern void css_driver_unregister(struct css_driver *);
 
 extern void css_sch_device_unregister(struct subchannel *);
 extern int css_register_subchannel(struct subchannel *);
-extern struct subchannel *css_alloc_subchannel(struct subchannel_id);
+extern struct subchannel *css_alloc_subchannel(struct subchannel_id,
+					       struct schib *schib);
 extern struct subchannel *get_subchannel_by_schid(struct subchannel_id);
 extern int css_init_done;
 extern int max_ssid;
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index f4ca72dd862f..9c7d9da42ba0 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -631,21 +631,20 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q,
 	unsigned long phys_aob = 0;
 
 	if (!q->use_cq)
-		goto out;
+		return 0;
 
 	if (!q->aobs[bufnr]) {
 		struct qaob *aob = qdio_allocate_aob();
 		q->aobs[bufnr] = aob;
 	}
 	if (q->aobs[bufnr]) {
-		q->sbal_state[bufnr].flags = QDIO_OUTBUF_STATE_FLAG_NONE;
 		q->sbal_state[bufnr].aob = q->aobs[bufnr];
 		q->aobs[bufnr]->user1 = (u64) q->sbal_state[bufnr].user;
 		phys_aob = virt_to_phys(q->aobs[bufnr]);
 		WARN_ON_ONCE(phys_aob & 0xFF);
 	}
 
-out:
+	q->sbal_state[bufnr].flags = 0;
 	return phys_aob;
 }
 
diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h
index 1f8d1c1e566d..0ebb29b6fd6d 100644
--- a/drivers/s390/cio/trace.h
+++ b/drivers/s390/cio/trace.h
@@ -30,6 +30,17 @@ DECLARE_EVENT_CLASS(s390_class_schib,
 		__field(u16, schno)
 		__field(u16, devno)
 		__field_struct(struct schib, schib)
+		__field(u8, pmcw_ena)
+		__field(u8, pmcw_st)
+		__field(u8, pmcw_dnv)
+		__field(u16, pmcw_dev)
+		__field(u8, pmcw_lpm)
+		__field(u8, pmcw_pnom)
+		__field(u8, pmcw_lpum)
+		__field(u8, pmcw_pim)
+		__field(u8, pmcw_pam)
+		__field(u8, pmcw_pom)
+		__field(u64, pmcw_chpid)
 		__field(int, cc)
 	),
 	TP_fast_assign(
@@ -38,18 +49,29 @@ DECLARE_EVENT_CLASS(s390_class_schib,
 		__entry->schno = schid.sch_no;
 		__entry->devno = schib->pmcw.dev;
 		__entry->schib = *schib;
+		__entry->pmcw_ena = schib->pmcw.ena;
+		__entry->pmcw_st = schib->pmcw.ena;
+		__entry->pmcw_dnv = schib->pmcw.dnv;
+		__entry->pmcw_dev = schib->pmcw.dev;
+		__entry->pmcw_lpm = schib->pmcw.lpm;
+		__entry->pmcw_pnom = schib->pmcw.pnom;
+		__entry->pmcw_lpum = schib->pmcw.lpum;
+		__entry->pmcw_pim = schib->pmcw.pim;
+		__entry->pmcw_pam = schib->pmcw.pam;
+		__entry->pmcw_pom = schib->pmcw.pom;
+		memcpy(&__entry->pmcw_chpid, &schib->pmcw.chpid, 8);
 		__entry->cc = cc;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d ena=%d st=%d dnv=%d dev=%04x "
 		  "lpm=0x%02x pnom=0x%02x lpum=0x%02x pim=0x%02x pam=0x%02x "
 		  "pom=0x%02x chpids=%016llx",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  __entry->schib.pmcw.ena, __entry->schib.pmcw.st,
-		  __entry->schib.pmcw.dnv, __entry->schib.pmcw.dev,
-		  __entry->schib.pmcw.lpm, __entry->schib.pmcw.pnom,
-		  __entry->schib.pmcw.lpum, __entry->schib.pmcw.pim,
-		  __entry->schib.pmcw.pam, __entry->schib.pmcw.pom,
-		  *((u64 *) __entry->schib.pmcw.chpid)
+		  __entry->pmcw_ena, __entry->pmcw_st,
+		  __entry->pmcw_dnv, __entry->pmcw_dev,
+		  __entry->pmcw_lpm, __entry->pmcw_pnom,
+		  __entry->pmcw_lpum, __entry->pmcw_pim,
+		  __entry->pmcw_pam, __entry->pmcw_pom,
+		  __entry->pmcw_chpid
 	)
 );
 
@@ -89,6 +111,13 @@ TRACE_EVENT(s390_cio_tsch,
 		__field(u8, ssid)
 		__field(u16, schno)
 		__field_struct(struct irb, irb)
+		__field(u8, scsw_dcc)
+		__field(u8, scsw_pno)
+		__field(u8, scsw_fctl)
+		__field(u8, scsw_actl)
+		__field(u8, scsw_stctl)
+		__field(u8, scsw_dstat)
+		__field(u8, scsw_cstat)
 		__field(int, cc)
 	),
 	TP_fast_assign(
@@ -96,15 +125,22 @@ TRACE_EVENT(s390_cio_tsch,
 		__entry->ssid = schid.ssid;
 		__entry->schno = schid.sch_no;
 		__entry->irb = *irb;
+		__entry->scsw_dcc = scsw_cc(&irb->scsw);
+		__entry->scsw_pno = scsw_pno(&irb->scsw);
+		__entry->scsw_fctl = scsw_fctl(&irb->scsw);
+		__entry->scsw_actl = scsw_actl(&irb->scsw);
+		__entry->scsw_stctl = scsw_stctl(&irb->scsw);
+		__entry->scsw_dstat = scsw_dstat(&irb->scsw);
+		__entry->scsw_cstat = scsw_cstat(&irb->scsw);
 		__entry->cc = cc;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d dcc=%d pno=%d fctl=0x%x actl=0x%x "
 		  "stctl=0x%x dstat=0x%x cstat=0x%x",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  scsw_cc(&__entry->irb.scsw), scsw_pno(&__entry->irb.scsw),
-		  scsw_fctl(&__entry->irb.scsw), scsw_actl(&__entry->irb.scsw),
-		  scsw_stctl(&__entry->irb.scsw),
-		  scsw_dstat(&__entry->irb.scsw), scsw_cstat(&__entry->irb.scsw)
+		  __entry->scsw_dcc, __entry->scsw_pno,
+		  __entry->scsw_fctl, __entry->scsw_actl,
+		  __entry->scsw_stctl,
+		  __entry->scsw_dstat, __entry->scsw_cstat
 	)
 );
 
@@ -122,6 +158,9 @@ TRACE_EVENT(s390_cio_tpi,
 		__field(u8, cssid)
 		__field(u8, ssid)
 		__field(u16, schno)
+		__field(u8, adapter_IO)
+		__field(u8, isc)
+		__field(u8, type)
 	),
 	TP_fast_assign(
 		__entry->cc = cc;
@@ -136,11 +175,14 @@ TRACE_EVENT(s390_cio_tpi,
 		__entry->cssid = __entry->tpi_info.schid.cssid;
 		__entry->ssid = __entry->tpi_info.schid.ssid;
 		__entry->schno = __entry->tpi_info.schid.sch_no;
+		__entry->adapter_IO = __entry->tpi_info.adapter_IO;
+		__entry->isc = __entry->tpi_info.isc;
+		__entry->type = __entry->tpi_info.type;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d a=%d isc=%d type=%d",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  __entry->tpi_info.adapter_IO, __entry->tpi_info.isc,
-		  __entry->tpi_info.type
+		  __entry->adapter_IO, __entry->isc,
+		  __entry->type
 	)
 );
 
@@ -299,16 +341,20 @@ TRACE_EVENT(s390_cio_interrupt,
 		__field(u8, cssid)
 		__field(u8, ssid)
 		__field(u16, schno)
+		__field(u8, isc)
+		__field(u8, type)
 	),
 	TP_fast_assign(
 		__entry->tpi_info = *tpi_info;
-		__entry->cssid = __entry->tpi_info.schid.cssid;
-		__entry->ssid = __entry->tpi_info.schid.ssid;
-		__entry->schno = __entry->tpi_info.schid.sch_no;
+		__entry->cssid = tpi_info->schid.cssid;
+		__entry->ssid = tpi_info->schid.ssid;
+		__entry->schno = tpi_info->schid.sch_no;
+		__entry->isc = tpi_info->isc;
+		__entry->type = tpi_info->type;
 	),
 	TP_printk("schid=%x.%x.%04x isc=%d type=%d",
 		  __entry->cssid, __entry->ssid, __entry->schno,
-		  __entry->tpi_info.isc, __entry->tpi_info.type
+		  __entry->isc, __entry->type
 	)
 );
 
@@ -321,11 +367,13 @@ TRACE_EVENT(s390_cio_adapter_int,
 	TP_ARGS(tpi_info),
 	TP_STRUCT__entry(
 		__field_struct(struct tpi_info, tpi_info)
+		__field(u8, isc)
 	),
 	TP_fast_assign(
 		__entry->tpi_info = *tpi_info;
+		__entry->isc = tpi_info->isc;
 	),
-	TP_printk("isc=%d", __entry->tpi_info.isc)
+	TP_printk("isc=%d", __entry->isc)
 );
 
 /**
@@ -339,16 +387,30 @@ TRACE_EVENT(s390_cio_stcrw,
 	TP_STRUCT__entry(
 		__field_struct(struct crw, crw)
 		__field(int, cc)
+		__field(u8, slct)
+		__field(u8, oflw)
+		__field(u8, chn)
+		__field(u8, rsc)
+		__field(u8, anc)
+		__field(u8, erc)
+		__field(u16, rsid)
 	),
 	TP_fast_assign(
 		__entry->crw = *crw;
 		__entry->cc = cc;
+		__entry->slct = crw->slct;
+		__entry->oflw = crw->oflw;
+		__entry->chn = crw->chn;
+		__entry->rsc = crw->rsc;
+		__entry->anc = crw->anc;
+		__entry->erc = crw->erc;
+		__entry->rsid = crw->rsid;
 	),
 	TP_printk("cc=%d slct=%d oflw=%d chn=%d rsc=%d anc=%d erc=0x%x "
 		  "rsid=0x%x",
-		  __entry->cc, __entry->crw.slct, __entry->crw.oflw,
-		  __entry->crw.chn, __entry->crw.rsc,  __entry->crw.anc,
-		  __entry->crw.erc, __entry->crw.rsid
+		  __entry->cc, __entry->slct, __entry->oflw,
+		  __entry->chn, __entry->rsc,  __entry->anc,
+		  __entry->erc, __entry->rsid
 	)
 );
 
diff --git a/drivers/s390/crypto/ap_asm.h b/drivers/s390/crypto/ap_asm.h
deleted file mode 100644
index 16b59ce5e01d..000000000000
--- a/drivers/s390/crypto/ap_asm.h
+++ /dev/null
@@ -1,236 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright IBM Corp. 2016
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- *
- * Adjunct processor bus inline assemblies.
- */
-
-#ifndef _AP_ASM_H_
-#define _AP_ASM_H_
-
-#include <asm/isc.h>
-
-/**
- * ap_intructions_available() - Test if AP instructions are available.
- *
- * Returns 0 if the AP instructions are installed.
- */
-static inline int ap_instructions_available(void)
-{
-	register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
-	register unsigned long reg1 asm ("1") = -ENODEV;
-	register unsigned long reg2 asm ("2") = 0UL;
-
-	asm volatile(
-		"   .long 0xb2af0000\n"		/* PQAP(TAPQ) */
-		"0: la    %1,0\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+d" (reg0), "+d" (reg1), "+d" (reg2) : : "cc");
-	return reg1;
-}
-
-/**
- * ap_tapq(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
-{
-	register unsigned long reg0 asm ("0") = qid;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
-
-	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
-		     : "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
-	if (info)
-		*info = reg2;
-	return reg1;
-}
-
-/**
- * ap_pqap_rapq(): Reset adjunct processor queue.
- * @qid: The AP queue number
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
-{
-	register unsigned long reg0 asm ("0") = qid | 0x01000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(RAPQ) */
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
-	return reg1;
-}
-
-/**
- * ap_aqic(): Control interruption for a specific AP.
- * @qid: The AP queue number
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- */
-static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
-					     struct ap_qirq_ctrl qirqctrl,
-					     void *ind)
-{
-	register unsigned long reg0 asm ("0") = qid | (3UL << 24);
-	register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
-	register struct ap_queue_status reg1_out asm ("1");
-	register void *reg2 asm ("2") = ind;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(AQIC) */
-		: "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
-		:
-		: "cc");
-	return reg1_out;
-}
-
-/**
- * ap_qci(): Get AP configuration data
- *
- * Returns 0 on success, or -EOPNOTSUPP.
- */
-static inline int ap_qci(void *config)
-{
-	register unsigned long reg0 asm ("0") = 0x04000000UL;
-	register unsigned long reg1 asm ("1") = -EINVAL;
-	register void *reg2 asm ("2") = (void *) config;
-
-	asm volatile(
-		".long 0xb2af0000\n"		/* PQAP(QCI) */
-		"0: la    %1,0\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+d" (reg0), "+d" (reg1), "+d" (reg2)
-		:
-		: "cc", "memory");
-
-	return reg1;
-}
-
-/*
- * union ap_qact_ap_info - used together with the
- * ap_aqic() function to provide a convenient way
- * to handle the ap info needed by the qact function.
- */
-union ap_qact_ap_info {
-	unsigned long val;
-	struct {
-		unsigned int	  : 3;
-		unsigned int mode : 3;
-		unsigned int	  : 26;
-		unsigned int cat  : 8;
-		unsigned int	  : 8;
-		unsigned char ver[2];
-	};
-};
-
-/**
- * ap_qact(): Query AP combatibility type.
- * @qid: The AP queue number
- * @apinfo: On input the info about the AP queue. On output the
- *	    alternate AP queue info provided by the qact function
- *	    in GR2 is stored in.
- *
- * Returns AP queue status. Check response_code field for failures.
- */
-static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
-					     union ap_qact_ap_info *apinfo)
-{
-	register unsigned long reg0 asm ("0") = qid | (5UL << 24)
-		| ((ifbit & 0x01) << 22);
-	register unsigned long reg1_in asm ("1") = apinfo->val;
-	register struct ap_queue_status reg1_out asm ("1");
-	register unsigned long reg2 asm ("2") = 0;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(QACT) */
-		: "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
-		: : "cc");
-	apinfo->val = reg2;
-	return reg1_out;
-}
-
-/**
- * ap_nqap(): Send message to adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: The program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on NQAP can't happen because the L bit is 1.
- * Condition code 2 on NQAP also means the send is incomplete,
- * because a segment boundary was reached. The NQAP is repeated.
- */
-static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
-					     unsigned long long psmid,
-					     void *msg, size_t length)
-{
-	register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = (unsigned long) msg;
-	register unsigned long reg3 asm ("3") = (unsigned long) length;
-	register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
-	register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
-
-	asm volatile (
-		"0: .long 0xb2ad0042\n"		/* NQAP */
-		"   brc   2,0b"
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
-		: "d" (reg4), "d" (reg5)
-		: "cc", "memory");
-	return reg1;
-}
-
-/**
- * ap_dqap(): Receive message from adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: Pointer to program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on DQAP means the receive has taken place
- * but only partially.	The response is incomplete, hence the
- * DQAP is repeated.
- * Condition code 2 on DQAP also means the receive is incomplete,
- * this time because a segment boundary was reached. Again, the
- * DQAP is repeated.
- * Note that gpr2 is used by the DQAP instruction to keep track of
- * any 'residual' length, in case the instruction gets interrupted.
- * Hence it gets zeroed before the instruction.
- */
-static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
-					     unsigned long long *psmid,
-					     void *msg, size_t length)
-{
-	register unsigned long reg0 asm("0") = qid | 0x80000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm("2") = 0UL;
-	register unsigned long reg4 asm("4") = (unsigned long) msg;
-	register unsigned long reg5 asm("5") = (unsigned long) length;
-	register unsigned long reg6 asm("6") = 0UL;
-	register unsigned long reg7 asm("7") = 0UL;
-
-
-	asm volatile(
-		"0: .long 0xb2ae0064\n"		/* DQAP */
-		"   brc   6,0b\n"
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2),
-		  "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7)
-		: : "cc", "memory");
-	*psmid = (((unsigned long long) reg6) << 32) + reg7;
-	return reg1;
-}
-
-#endif /* _AP_ASM_H_ */
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 35a0c2b52f82..bf27fc4d1335 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -36,7 +36,6 @@
 #include <linux/debugfs.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
 #include "ap_debug.h"
 
 /*
@@ -174,24 +173,6 @@ static inline int ap_qact_available(void)
 	return 0;
 }
 
-/**
- * ap_test_queue(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @tbit: Test facilities bit
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-struct ap_queue_status ap_test_queue(ap_qid_t qid,
-				     int tbit,
-				     unsigned long *info)
-{
-	if (tbit)
-		qid |= 1UL << 23; /* set T bit*/
-	return ap_tapq(qid, info);
-}
-EXPORT_SYMBOL(ap_test_queue);
-
 /*
  * ap_query_configuration(): Fetch cryptographic config info
  *
@@ -200,7 +181,7 @@ EXPORT_SYMBOL(ap_test_queue);
  * is returned, e.g. if the PQAP(QCI) instruction is not
  * available, the return value will be -EOPNOTSUPP.
  */
-int ap_query_configuration(struct ap_config_info *info)
+static inline int ap_query_configuration(struct ap_config_info *info)
 {
 	if (!ap_configuration_available())
 		return -EOPNOTSUPP;
@@ -493,7 +474,7 @@ static int ap_poll_thread_start(void)
 		return 0;
 	mutex_lock(&ap_poll_thread_mutex);
 	ap_poll_kthread = kthread_run(ap_poll_thread, NULL, "appoll");
-	rc = PTR_RET(ap_poll_kthread);
+	rc = PTR_ERR_OR_ZERO(ap_poll_kthread);
 	if (rc)
 		ap_poll_kthread = NULL;
 	mutex_unlock(&ap_poll_thread_mutex);
@@ -1261,7 +1242,7 @@ static int __init ap_module_init(void)
 
 	/* Create /sys/devices/ap. */
 	ap_root_device = root_device_register("ap");
-	rc = PTR_RET(ap_root_device);
+	rc = PTR_ERR_OR_ZERO(ap_root_device);
 	if (rc)
 		goto out_bus;
 
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 6a273c5ebca5..936541937e15 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -15,6 +15,7 @@
 
 #include <linux/device.h>
 #include <linux/types.h>
+#include <asm/isc.h>
 #include <asm/ap.h>
 
 #define AP_DEVICES 256		/* Number of AP devices. */
diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c
index 2c726df210f6..c13e43292cb7 100644
--- a/drivers/s390/crypto/ap_card.c
+++ b/drivers/s390/crypto/ap_card.c
@@ -14,7 +14,6 @@
 #include <asm/facility.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
 
 /*
  * AP card related attributes.
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index ba3a2e13b0eb..e365171fe28f 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -14,26 +14,6 @@
 #include <asm/facility.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
-
-/**
- * ap_queue_irq_ctrl(): Control interruption on a AP queue.
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- *
- * Control interruption on the given AP queue.
- * Just a simple wrapper function for the low level PQAP(AQIC)
- * instruction available for other kernel modules.
- */
-struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid,
-					 struct ap_qirq_ctrl qirqctrl,
-					 void *ind)
-{
-	return ap_aqic(qid, qirqctrl, ind);
-}
-EXPORT_SYMBOL(ap_queue_irq_ctrl);
 
 /**
  * ap_queue_enable_interruption(): Enable interruption on an AP queue.
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 3929c8be8098..e663432395c1 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -699,7 +699,7 @@ static int query_crypto_facility(u16 cardnr, u16 domain,
 	/* fill request cprb param block with FQ request */
 	preqparm = (struct fqreqparm *) preqcblk->req_parmb;
 	memcpy(preqparm->subfunc_code, "FQ", 2);
-	strncpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
+	memcpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
 	preqparm->rule_array_len =
 		sizeof(preqparm->rule_array_len) + sizeof(preqparm->rule_array);
 	preqparm->lv1.len = sizeof(preqparm->lv1);
diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c
index 233e1e695208..da2c8dfd4d74 100644
--- a/drivers/s390/crypto/zcrypt_card.c
+++ b/drivers/s390/crypto/zcrypt_card.c
@@ -83,9 +83,21 @@ static ssize_t zcrypt_card_online_store(struct device *dev,
 static DEVICE_ATTR(online, 0644, zcrypt_card_online_show,
 		   zcrypt_card_online_store);
 
+static ssize_t zcrypt_card_load_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct zcrypt_card *zc = to_ap_card(dev)->private;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zc->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_card_load_show, NULL);
+
 static struct attribute *zcrypt_card_attrs[] = {
 	&dev_attr_type.attr,
 	&dev_attr_online.attr,
+	&dev_attr_load.attr,
 	NULL,
 };
 
diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h
index 011d61d8a4ae..1752622b95f7 100644
--- a/drivers/s390/crypto/zcrypt_cca_key.h
+++ b/drivers/s390/crypto/zcrypt_cca_key.h
@@ -99,7 +99,7 @@ struct cca_pvt_ext_CRT_sec {
  * @mex: pointer to user input data
  * @p: pointer to memory area for the key
  *
- * Returns the size of the key area or -EFAULT
+ * Returns the size of the key area or negative errno value.
  */
 static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
 {
@@ -118,6 +118,15 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
 	unsigned char *temp;
 	int i;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_modexpo(). However, do a plausibility check
+	 * here to make sure the following copy_from_user() can't be utilized
+	 * to compromise the system.
+	 */
+	if (WARN_ON_ONCE(mex->inputdatalength > 512))
+		return -EINVAL;
+
 	memset(key, 0, sizeof(*key));
 
 	key->pubHdr = static_pub_hdr;
@@ -178,6 +187,15 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p)
 	struct cca_public_sec *pub;
 	int short_len, long_len, pad_len, key_len, size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_crt(). However, do a plausibility check
+	 * here to make sure the following copy_from_user() can't be utilized
+	 * to compromise the system.
+	 */
+	if (WARN_ON_ONCE(crt->inputdatalength > 512))
+		return -EINVAL;
+
 	memset(key, 0, sizeof(*key));
 
 	short_len = (crt->inputdatalength + 1) / 2;
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index 97d4bacbc442..e70ae078c86b 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -246,7 +246,7 @@ int speed_idx_ep11(int req_type)
  * @ap_msg: pointer to AP message
  * @mex: pointer to user input data
  *
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
  */
 static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
 				       struct ap_message *ap_msg,
@@ -272,6 +272,14 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
 	} __packed * msg = ap_msg->message;
 	int size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_modexpo(). However, make sure the following
+	 * copy_from_user() never exceeds the allocated buffer space.
+	 */
+	if (WARN_ON_ONCE(mex->inputdatalength > PAGE_SIZE))
+		return -EINVAL;
+
 	/* VUD.ciphertext */
 	msg->length = mex->inputdatalength + 2;
 	if (copy_from_user(msg->text, mex->inputdata, mex->inputdatalength))
@@ -307,7 +315,7 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
  * @ap_msg: pointer to AP message
  * @crt: pointer to user input data
  *
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
  */
 static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
 				       struct ap_message *ap_msg,
@@ -334,6 +342,14 @@ static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
 	} __packed * msg = ap_msg->message;
 	int size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_crt(). However, make sure the following
+	 * copy_from_user() never exceeds the allocated buffer space.
+	 */
+	if (WARN_ON_ONCE(crt->inputdatalength > PAGE_SIZE))
+		return -EINVAL;
+
 	/* VUD.ciphertext */
 	msg->length = crt->inputdatalength + 2;
 	if (copy_from_user(msg->text, crt->inputdata, crt->inputdatalength))
diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c
index 720434e18007..91a52f268353 100644
--- a/drivers/s390/crypto/zcrypt_queue.c
+++ b/drivers/s390/crypto/zcrypt_queue.c
@@ -75,8 +75,20 @@ static ssize_t zcrypt_queue_online_store(struct device *dev,
 static DEVICE_ATTR(online, 0644, zcrypt_queue_online_show,
 		   zcrypt_queue_online_store);
 
+static ssize_t zcrypt_queue_load_show(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct zcrypt_queue *zq = to_ap_queue(dev)->private;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zq->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_queue_load_show, NULL);
+
 static struct attribute *zcrypt_queue_attrs[] = {
 	&dev_attr_online.attr,
+	&dev_attr_load.attr,
 	NULL,
 };
 
diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c
index a3a8c8d9d717..94f4d8fe85e0 100644
--- a/drivers/s390/scsi/zfcp_aux.c
+++ b/drivers/s390/scsi/zfcp_aux.c
@@ -101,7 +101,7 @@ static void __init zfcp_init_device_setup(char *devstr)
 	token = strsep(&str, ",");
 	if (!token || strlen(token) >= ZFCP_BUS_ID_SIZE)
 		goto err_out;
-	strncpy(busid, token, ZFCP_BUS_ID_SIZE);
+	strlcpy(busid, token, ZFCP_BUS_ID_SIZE);
 
 	token = strsep(&str, ",");
 	if (!token || kstrtoull(token, 0, (unsigned long long *) &wwpn))
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 80aca2456353..768953881c9e 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -21,6 +21,7 @@ CFLAGS_gdth.o    = # -DDEBUG_GDTH=2 -D__SERIAL__ -D__COM2__ -DGDTH_STATISTICS
 obj-$(CONFIG_PCMCIA)		+= pcmcia/
 
 obj-$(CONFIG_SCSI)		+= scsi_mod.o
+obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_common.o
 
 obj-$(CONFIG_RAID_ATTRS)	+= raid_class.o
 
@@ -156,7 +157,6 @@ obj-$(CONFIG_SCSI_HISI_SAS) += hisi_sas/
 obj-$(CONFIG_SCSI_DEBUG)	+= scsi_debug.o
 scsi_mod-y			+= scsi.o hosts.o scsi_ioctl.o \
 				   scsicam.o scsi_error.o scsi_lib.o
-scsi_mod-y			+= scsi_common.o
 scsi_mod-$(CONFIG_SCSI_CONSTANTS) += constants.o
 scsi_mod-$(CONFIG_SCSI_DMA)	+= scsi_lib_dma.o
 scsi_mod-y			+= scsi_scan.o scsi_sysfs.o scsi_devinfo.o
diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 497a68389461..a43d44e7e7dd 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -88,10 +88,8 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 				      const struct file_operations *fops,
 				      void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	if (fops->owner && !try_module_get(fops->owner)) {
@@ -116,29 +114,15 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		goto err3;
 	}
 
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(ocxlflash_vfs_mount->mnt_sb, &this);
-	if (!path.dentry) {
-		dev_err(dev, "%s: d_alloc_pseudo failed\n", __func__);
-		rc = -ENOMEM;
-		goto err4;
-	}
-
-	path.mnt = mntget(ocxlflash_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file_pseudo(inode, ocxlflash_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		dev_err(dev, "%s: alloc_file failed rc=%d\n",
 			__func__, rc);
-		path_put(&path);
-		goto err3;
+		goto err4;
 	}
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 out:
 	return file;
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index e489d89cbb45..379890c4500b 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -339,7 +339,6 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 	struct scsi_sense_hdr sshdr;
 	u8 *cmd_buf = NULL;
 	u8 *scsi_cmd = NULL;
-	u8 *sense_buf = NULL;
 	int rc = 0;
 	int result = 0;
 	int retry_cnt = 0;
@@ -348,8 +347,7 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 retry:
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
 	scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
-	sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-	if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
+	if (unlikely(!cmd_buf || !scsi_cmd)) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -364,7 +362,7 @@ retry:
 	/* Drop the ioctl read semahpore across lengthy call */
 	up_read(&cfg->ioctl_rwsem);
 	result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf,
-			      CMD_BUFSIZE, sense_buf, &sshdr, to, CMD_RETRIES,
+			      CMD_BUFSIZE, NULL, &sshdr, to, CMD_RETRIES,
 			      0, 0, NULL);
 	down_read(&cfg->ioctl_rwsem);
 	rc = check_state(cfg);
@@ -395,7 +393,6 @@ retry:
 					if (retry_cnt++ < 1) {
 						kfree(cmd_buf);
 						kfree(scsi_cmd);
-						kfree(sense_buf);
 						goto retry;
 					}
 				}
@@ -426,7 +423,6 @@ retry:
 out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
-	kfree(sense_buf);
 
 	dev_dbg(dev, "%s: maxlba=%lld blklen=%d rc=%d\n",
 		__func__, gli->max_lba, gli->blk_len, rc);
diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c
index 66e445a17d6c..2c904bf16b65 100644
--- a/drivers/scsi/cxlflash/vlun.c
+++ b/drivers/scsi/cxlflash/vlun.c
@@ -426,7 +426,6 @@ static int write_same16(struct scsi_device *sdev,
 {
 	u8 *cmd_buf = NULL;
 	u8 *scsi_cmd = NULL;
-	u8 *sense_buf = NULL;
 	int rc = 0;
 	int result = 0;
 	u64 offset = lba;
@@ -440,8 +439,7 @@ static int write_same16(struct scsi_device *sdev,
 
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
 	scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
-	sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-	if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
+	if (unlikely(!cmd_buf || !scsi_cmd)) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -457,7 +455,7 @@ static int write_same16(struct scsi_device *sdev,
 		/* Drop the ioctl read semahpore across lengthy call */
 		up_read(&cfg->ioctl_rwsem);
 		result = scsi_execute(sdev, scsi_cmd, DMA_TO_DEVICE, cmd_buf,
-				      CMD_BUFSIZE, sense_buf, NULL, to,
+				      CMD_BUFSIZE, NULL, NULL, to,
 				      CMD_RETRIES, 0, 0, NULL);
 		down_read(&cfg->ioctl_rwsem);
 		rc = check_state(cfg);
@@ -482,7 +480,6 @@ static int write_same16(struct scsi_device *sdev,
 out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
-	kfree(sense_buf);
 	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index ea23c8dffc25..ffec695e0bfb 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -754,9 +754,9 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 	case ELS_LOGO:
 		if (fip->mode == FIP_MODE_VN2VN) {
 			if (fip->state != FIP_ST_VNMP_UP)
-				return -EINVAL;
+				goto drop;
 			if (ntoh24(fh->fh_d_id) == FC_FID_FLOGI)
-				return -EINVAL;
+				goto drop;
 		} else {
 			if (fip->state != FIP_ST_ENABLED)
 				return 0;
@@ -799,9 +799,9 @@ int fcoe_ctlr_els_send(struct fcoe_ctlr *fip, struct fc_lport *lport,
 	fip->send(fip, skb);
 	return -EINPROGRESS;
 drop:
-	kfree_skb(skb);
 	LIBFCOE_FIP_DBG(fip, "drop els_send op %u d_id %x\n",
 			op, ntoh24(fh->fh_d_id));
+	kfree_skb(skb);
 	return -EINVAL;
 }
 EXPORT_SYMBOL(fcoe_ctlr_els_send);
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 31d31aad3de1..89b1f1af2fd4 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -2164,6 +2164,7 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 		FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n",
 			     fc_rport_state(rdata));
 
+		rdata->flags &= ~FC_RP_STARTED;
 		fc_rport_enter_delete(rdata, RPORT_EV_STOP);
 		mutex_unlock(&rdata->rp_mutex);
 		kref_put(&rdata->kref, fc_rport_destroy);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 569392d0d4c9..e44c91edf92d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3343,11 +3343,10 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 					spinlock_t *writeq_lock)
 {
 	unsigned long flags;
-	__u64 data_out = b;
 
 	spin_lock_irqsave(writeq_lock, flags);
-	writel((u32)(data_out), addr);
-	writel((u32)(data_out >> 32), (addr + 4));
+	__raw_writel((u32)(b), addr);
+	__raw_writel((u32)(b >> 32), (addr + 4));
 	mmiowb();
 	spin_unlock_irqrestore(writeq_lock, flags);
 }
@@ -3367,7 +3366,8 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 static inline void
 _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
 {
-	writeq(b, addr);
+	__raw_writeq(b, addr);
+	mmiowb();
 }
 #else
 static inline void
@@ -5268,7 +5268,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 
 	/* send message 32-bits at a time */
 	for (i = 0, failed = 0; i < request_bytes/4 && !failed; i++) {
-		writel((u32)(request[i]), &ioc->chip->Doorbell);
+		writel(cpu_to_le32(request[i]), &ioc->chip->Doorbell);
 		if ((_base_wait_for_doorbell_ack(ioc, 5)))
 			failed = 1;
 	}
@@ -5289,7 +5289,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 	}
 
 	/* read the first two 16-bits, it gives the total length of the reply */
-	reply[0] = (u16)(readl(&ioc->chip->Doorbell)
+	reply[0] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 	if ((_base_wait_for_doorbell_int(ioc, 5))) {
@@ -5298,7 +5298,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 			ioc->name, __LINE__);
 		return -EFAULT;
 	}
-	reply[1] = (u16)(readl(&ioc->chip->Doorbell)
+	reply[1] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 
@@ -5312,7 +5312,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 		if (i >=  reply_bytes/2) /* overflow case */
 			readl(&ioc->chip->Doorbell);
 		else
-			reply[i] = (u16)(readl(&ioc->chip->Doorbell)
+			reply[i] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 			    & MPI2_DOORBELL_DATA_MASK);
 		writel(0, &ioc->chip->HostInterruptStatus);
 	}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b8d131a455d0..dd738ae5c75b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -4568,7 +4568,7 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
 		    MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG |
 		    MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD;
 		mpi_request->CDB.EEDP32.PrimaryReferenceTag =
-		    cpu_to_be32(scsi_prot_ref_tag(scmd));
+		    cpu_to_be32(t10_pi_ref_tag(scmd->request));
 		break;
 
 	case SCSI_PROT_DIF_TYPE3:
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 091ec1207bea..cff83b9457f7 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -888,7 +888,7 @@ static void qedi_get_boot_tgt_info(struct nvm_iscsi_block *block,
 	ipv6_en = !!(block->generic.ctrl_flags &
 		     NVM_ISCSI_CFG_GEN_IPV6_ENABLED);
 
-	snprintf(tgt->iscsi_name, NVM_ISCSI_CFG_ISCSI_NAME_MAX_LEN, "%s\n",
+	snprintf(tgt->iscsi_name, sizeof(tgt->iscsi_name), "%s\n",
 		 block->target[index].target_name.byte);
 
 	tgt->ipv6_en = ipv6_en;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index a91cca52b5d5..dd93a22fe843 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2130,34 +2130,11 @@ __qla2x00_alloc_iocbs(struct qla_qpair *qpair, srb_t *sp)
 	req_cnt = 1;
 	handle = 0;
 
-	if (!sp)
-		goto skip_cmd_array;
-
-	/* Check for room in outstanding command list. */
-	handle = req->current_outstanding_cmd;
-	for (index = 1; index < req->num_outstanding_cmds; index++) {
-		handle++;
-		if (handle == req->num_outstanding_cmds)
-			handle = 1;
-		if (!req->outstanding_cmds[handle])
-			break;
-	}
-	if (index == req->num_outstanding_cmds) {
-		ql_log(ql_log_warn, vha, 0x700b,
-		    "No room on outstanding cmd array.\n");
-		goto queuing_error;
-	}
-
-	/* Prep command array. */
-	req->current_outstanding_cmd = handle;
-	req->outstanding_cmds[handle] = sp;
-	sp->handle = handle;
-
-	/* Adjust entry-counts as needed. */
-	if (sp->type != SRB_SCSI_CMD)
+	if (sp && (sp->type != SRB_SCSI_CMD)) {
+		/* Adjust entry-counts as needed. */
 		req_cnt = sp->iocbs;
+	}
 
-skip_cmd_array:
 	/* Check for room on request queue. */
 	if (req->cnt < req_cnt + 2) {
 		if (qpair->use_shadow_reg)
@@ -2183,6 +2160,28 @@ skip_cmd_array:
 	if (req->cnt < req_cnt + 2)
 		goto queuing_error;
 
+	if (sp) {
+		/* Check for room in outstanding command list. */
+		handle = req->current_outstanding_cmd;
+		for (index = 1; index < req->num_outstanding_cmds; index++) {
+			handle++;
+			if (handle == req->num_outstanding_cmds)
+				handle = 1;
+			if (!req->outstanding_cmds[handle])
+				break;
+		}
+		if (index == req->num_outstanding_cmds) {
+			ql_log(ql_log_warn, vha, 0x700b,
+			    "No room on outstanding cmd array.\n");
+			goto queuing_error;
+		}
+
+		/* Prep command array. */
+		req->current_outstanding_cmd = handle;
+		req->outstanding_cmds[handle] = sp;
+		sp->handle = handle;
+	}
+
 	/* Prep packet */
 	req->cnt -= req_cnt;
 	pkt = req->ring_ptr;
@@ -2195,6 +2194,8 @@ skip_cmd_array:
 		pkt->handle = handle;
 	}
 
+	return pkt;
+
 queuing_error:
 	qpair->tgt_counters.num_alloc_iocb_failed++;
 	return pkt;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 41e9ac9fc138..9cb9a166fa0c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -238,7 +238,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 
 
 /**
- * scsi_execute - insert request and wait for the result
+ * __scsi_execute - insert request and wait for the result
  * @sdev:	scsi device
  * @cmd:	scsi command
  * @data_direction: data direction
@@ -255,7 +255,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
  * Returns the scsi_cmnd result field if a command was executed, or a negative
  * Linux error code if we didn't get that far.
  */
-int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
 		 unsigned char *sense, struct scsi_sense_hdr *sshdr,
 		 int timeout, int retries, u64 flags, req_flags_t rq_flags,
@@ -309,7 +309,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 
 	return ret;
 }
-EXPORT_SYMBOL(scsi_execute);
+EXPORT_SYMBOL(__scsi_execute);
 
 /*
  * Function:    scsi_init_cmd_errh()
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 9421d9877730..bbebdc3769b0 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1119,7 +1119,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 		SCpnt->cmnd[0] = WRITE_6;
 
 		if (blk_integrity_rq(rq))
-			sd_dif_prepare(SCpnt);
+			t10_pi_prepare(SCpnt->request, sdkp->protection_type);
 
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
@@ -2047,8 +2047,10 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 					   "sd_done: completed %d of %d bytes\n",
 					   good_bytes, scsi_bufflen(SCpnt)));
 
-	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt))
-		sd_dif_complete(SCpnt, good_bytes);
+	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt) &&
+	    good_bytes)
+		t10_pi_complete(SCpnt->request, sdkp->protection_type,
+				good_bytes / scsi_prot_interval(SCpnt));
 
 	return good_bytes;
 }
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 392c7d078ae3..a7d4f50b67d4 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -254,21 +254,12 @@ static inline unsigned int sd_prot_flag_mask(unsigned int prot_op)
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 
 extern void sd_dif_config_host(struct scsi_disk *);
-extern void sd_dif_prepare(struct scsi_cmnd *scmd);
-extern void sd_dif_complete(struct scsi_cmnd *, unsigned int);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 static inline void sd_dif_config_host(struct scsi_disk *disk)
 {
 }
-static inline int sd_dif_prepare(struct scsi_cmnd *scmd)
-{
-	return 0;
-}
-static inline void sd_dif_complete(struct scsi_cmnd *cmd, unsigned int a)
-{
-}
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 9035380c0dda..db72c82486e3 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -95,116 +95,3 @@ out:
 	blk_integrity_register(disk, &bi);
 }
 
-/*
- * The virtual start sector is the one that was originally submitted
- * by the block layer.	Due to partitioning, MD/DM cloning, etc. the
- * actual physical start sector is likely to be different.  Remap
- * protection information to match the physical LBA.
- *
- * From a protocol perspective there's a slight difference between
- * Type 1 and 2.  The latter uses 32-byte CDBs exclusively, and the
- * reference tag is seeded in the CDB.  This gives us the potential to
- * avoid virt->phys remapping during write.  However, at read time we
- * don't know whether the virt sector is the same as when we wrote it
- * (we could be reading from real disk as opposed to MD/DM device.  So
- * we always remap Type 2 making it identical to Type 1.
- *
- * Type 3 does not have a reference tag so no remapping is required.
- */
-void sd_dif_prepare(struct scsi_cmnd *scmd)
-{
-	const int tuple_sz = sizeof(struct t10_pi_tuple);
-	struct bio *bio;
-	struct scsi_disk *sdkp;
-	struct t10_pi_tuple *pi;
-	u32 phys, virt;
-
-	sdkp = scsi_disk(scmd->request->rq_disk);
-
-	if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION)
-		return;
-
-	phys = scsi_prot_ref_tag(scmd);
-
-	__rq_for_each_bio(bio, scmd->request) {
-		struct bio_integrity_payload *bip = bio_integrity(bio);
-		struct bio_vec iv;
-		struct bvec_iter iter;
-		unsigned int j;
-
-		/* Already remapped? */
-		if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
-			break;
-
-		virt = bip_get_seed(bip) & 0xffffffff;
-
-		bip_for_each_vec(iv, bip, iter) {
-			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
-
-			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
-
-				if (be32_to_cpu(pi->ref_tag) == virt)
-					pi->ref_tag = cpu_to_be32(phys);
-
-				virt++;
-				phys++;
-			}
-
-			kunmap_atomic(pi);
-		}
-
-		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
-	}
-}
-
-/*
- * Remap physical sector values in the reference tag to the virtual
- * values expected by the block layer.
- */
-void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
-{
-	const int tuple_sz = sizeof(struct t10_pi_tuple);
-	struct scsi_disk *sdkp;
-	struct bio *bio;
-	struct t10_pi_tuple *pi;
-	unsigned int j, intervals;
-	u32 phys, virt;
-
-	sdkp = scsi_disk(scmd->request->rq_disk);
-
-	if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION || good_bytes == 0)
-		return;
-
-	intervals = good_bytes / scsi_prot_interval(scmd);
-	phys = scsi_prot_ref_tag(scmd);
-
-	__rq_for_each_bio(bio, scmd->request) {
-		struct bio_integrity_payload *bip = bio_integrity(bio);
-		struct bio_vec iv;
-		struct bvec_iter iter;
-
-		virt = bip_get_seed(bip) & 0xffffffff;
-
-		bip_for_each_vec(iv, bip, iter) {
-			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
-
-			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
-
-				if (intervals == 0) {
-					kunmap_atomic(pi);
-					return;
-				}
-
-				if (be32_to_cpu(pi->ref_tag) == phys)
-					pi->ref_tag = cpu_to_be32(virt);
-
-				virt++;
-				phys++;
-				intervals--;
-			}
-
-			kunmap_atomic(pi);
-		}
-	}
-}
-
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index ba9ba0e04f42..139e13c73b41 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1103,15 +1103,6 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 	case SCSI_IOCTL_SEND_COMMAND:
 		if (atomic_read(&sdp->detaching))
 			return -ENODEV;
-		if (read_only) {
-			unsigned char opcode = WRITE_6;
-			Scsi_Ioctl_Command __user *siocp = p;
-
-			if (copy_from_user(&opcode, siocp->data, 1))
-				return -EFAULT;
-			if (sg_allow_access(filp, &opcode))
-				return -EPERM;
-		}
 		return sg_scsi_ioctl(sdp->device->request_queue, NULL, filp->f_mode, p);
 	case SG_SET_DEBUG:
 		result = get_user(val, ip);
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 3f3cb72e0c0c..d0389b20574d 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -523,18 +523,26 @@ static int sr_init_command(struct scsi_cmnd *SCpnt)
 static int sr_block_open(struct block_device *bdev, fmode_t mode)
 {
 	struct scsi_cd *cd;
+	struct scsi_device *sdev;
 	int ret = -ENXIO;
 
+	cd = scsi_cd_get(bdev->bd_disk);
+	if (!cd)
+		goto out;
+
+	sdev = cd->device;
+	scsi_autopm_get_device(sdev);
 	check_disk_change(bdev);
 
 	mutex_lock(&sr_mutex);
-	cd = scsi_cd_get(bdev->bd_disk);
-	if (cd) {
-		ret = cdrom_open(&cd->cdi, bdev, mode);
-		if (ret)
-			scsi_cd_put(cd);
-	}
+	ret = cdrom_open(&cd->cdi, bdev, mode);
 	mutex_unlock(&sr_mutex);
+
+	scsi_autopm_put_device(sdev);
+	if (ret)
+		scsi_cd_put(cd);
+
+out:
 	return ret;
 }
 
@@ -562,6 +570,8 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	if (ret)
 		goto out;
 
+	scsi_autopm_get_device(sdev);
+
 	/*
 	 * Send SCSI addressing ioctls directly to mid level, send other
 	 * ioctls to cdrom/block level.
@@ -570,15 +580,18 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case SCSI_IOCTL_GET_IDLUN:
 	case SCSI_IOCTL_GET_BUS_NUMBER:
 		ret = scsi_ioctl(sdev, cmd, argp);
-		goto out;
+		goto put;
 	}
 
 	ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg);
 	if (ret != -ENOSYS)
-		goto out;
+		goto put;
 
 	ret = scsi_ioctl(sdev, cmd, argp);
 
+put:
+	scsi_autopm_put_device(sdev);
+
 out:
 	mutex_unlock(&sr_mutex);
 	return ret;
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 35fab1e18adc..ffcf902da390 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -186,14 +186,13 @@ static int sr_play_trkind(struct cdrom_device_info *cdi,
 int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 {
 	struct scsi_device *SDev;
-	struct scsi_sense_hdr sshdr;
+	struct scsi_sense_hdr local_sshdr, *sshdr = &local_sshdr;
 	int result, err = 0, retries = 0;
-	unsigned char sense_buffer[SCSI_SENSE_BUFFERSIZE], *senseptr = NULL;
 
 	SDev = cd->device;
 
-	if (cgc->sense)
-		senseptr = sense_buffer;
+	if (cgc->sshdr)
+		sshdr = cgc->sshdr;
 
       retry:
 	if (!scsi_block_when_processing_errors(SDev)) {
@@ -202,15 +201,12 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 	}
 
 	result = scsi_execute(SDev, cgc->cmd, cgc->data_direction,
-			      cgc->buffer, cgc->buflen, senseptr, &sshdr,
+			      cgc->buffer, cgc->buflen, NULL, sshdr,
 			      cgc->timeout, IOCTL_RETRIES, 0, 0, NULL);
 
-	if (cgc->sense)
-		memcpy(cgc->sense, sense_buffer, sizeof(*cgc->sense));
-
 	/* Minimal error checking.  Ignore cases we know about, and report the rest. */
 	if (driver_byte(result) != 0) {
-		switch (sshdr.sense_key) {
+		switch (sshdr->sense_key) {
 		case UNIT_ATTENTION:
 			SDev->changed = 1;
 			if (!cgc->quiet)
@@ -221,8 +217,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 			err = -ENOMEDIUM;
 			break;
 		case NOT_READY:	/* This happens if there is no disc in drive */
-			if (sshdr.asc == 0x04 &&
-			    sshdr.ascq == 0x01) {
+			if (sshdr->asc == 0x04 &&
+			    sshdr->ascq == 0x01) {
 				/* sense: Logical unit is in process of becoming ready */
 				if (!cgc->quiet)
 					sr_printk(KERN_INFO, cd,
@@ -245,8 +241,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 			break;
 		case ILLEGAL_REQUEST:
 			err = -EIO;
-			if (sshdr.asc == 0x20 &&
-			    sshdr.ascq == 0x00)
+			if (sshdr->asc == 0x20 &&
+			    sshdr->ascq == 0x00)
 				/* sense: Invalid command operation code */
 				err = -EDRIVE_CANT_DO_THIS;
 			break;
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 6dc8891ccb74..1c72db94270e 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -513,12 +513,12 @@ static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
 
 	if (sc->sc_data_direction == DMA_TO_DEVICE)
 		cmd_pi->pi_bytesout = cpu_to_virtio32(vdev,
-							blk_rq_sectors(rq) *
-							bi->tuple_size);
+						      bio_integrity_bytes(bi,
+							blk_rq_sectors(rq)));
 	else if (sc->sc_data_direction == DMA_FROM_DEVICE)
 		cmd_pi->pi_bytesin = cpu_to_virtio32(vdev,
-						       blk_rq_sectors(rq) *
-						       bi->tuple_size);
+						     bio_integrity_bytes(bi,
+							blk_rq_sectors(rq)));
 }
 #endif
 
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 777e5f1e52d1..0cd947f78b5b 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -561,9 +561,14 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter,
 	    (btstat == BTSTAT_SUCCESS ||
 	     btstat == BTSTAT_LINKED_COMMAND_COMPLETED ||
 	     btstat == BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG)) {
-		cmd->result = (DID_OK << 16) | sdstat;
-		if (sdstat == SAM_STAT_CHECK_CONDITION && cmd->sense_buffer)
-			cmd->result |= (DRIVER_SENSE << 24);
+		if (sdstat == SAM_STAT_COMMAND_TERMINATED) {
+			cmd->result = (DID_RESET << 16);
+		} else {
+			cmd->result = (DID_OK << 16) | sdstat;
+			if (sdstat == SAM_STAT_CHECK_CONDITION &&
+			    cmd->sense_buffer)
+				cmd->result |= (DRIVER_SENSE << 24);
+		}
 	} else
 		switch (btstat) {
 		case BTSTAT_SUCCESS:
diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index 2e45988d1259..e5d7fb81ad66 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -300,8 +300,8 @@ static void maple_send(void)
 	mutex_unlock(&maple_wlist_lock);
 	if (maple_packets > 0) {
 		for (i = 0; i < (1 << MAPLE_DMA_PAGES); i++)
-			sh_sync_dma_for_device(maple_sendbuf + i * PAGE_SIZE,
-				       PAGE_SIZE, DMA_BIDIRECTIONAL);
+			__flush_purge_region(maple_sendbuf + i * PAGE_SIZE,
+					PAGE_SIZE);
 	}
 
 finish:
@@ -642,7 +642,8 @@ static void maple_dma_handler(struct work_struct *work)
 		list_for_each_entry_safe(mq, nmq, &maple_sentq, list) {
 			mdev = mq->dev;
 			recvbuf = mq->recvbuf->buf;
-			sh_sync_dma_for_device(recvbuf, 0x400, DMA_FROM_DEVICE);
+			__flush_invalidate_region(sh_cacheop_vaddr(recvbuf),
+					0x400);
 			code = recvbuf[0];
 			kfree(mq->sendbuf);
 			list_del_init(&mq->list);
diff --git a/drivers/target/Kconfig b/drivers/target/Kconfig
index 4c44d7bed01a..cb6f32ce7de8 100644
--- a/drivers/target/Kconfig
+++ b/drivers/target/Kconfig
@@ -1,10 +1,10 @@
 
 menuconfig TARGET_CORE
 	tristate "Generic Target Core Mod (TCM) and ConfigFS Infrastructure"
-	depends on SCSI && BLOCK
+	depends on BLOCK
 	select CONFIGFS_FS
 	select CRC_T10DIF
-	select BLK_SCSI_REQUEST # only for scsi_command_size_tbl..
+	select BLK_SCSI_REQUEST
 	select SGL_ALLOC
 	default n
 	help
@@ -29,6 +29,7 @@ config TCM_FILEIO
 
 config TCM_PSCSI
 	tristate "TCM/pSCSI Subsystem Plugin for Linux/SCSI"
+	depends on SCSI
 	help
 	Say Y here to enable the TCM/pSCSI subsystem plugin for non-buffered
 	passthrough access to Linux/SCSI device
diff --git a/drivers/target/loopback/Kconfig b/drivers/target/loopback/Kconfig
index abe8ecbcdf06..158ee9d522f7 100644
--- a/drivers/target/loopback/Kconfig
+++ b/drivers/target/loopback/Kconfig
@@ -1,5 +1,6 @@
 config LOOPBACK_TARGET
 	tristate "TCM Virtual SAS target and Linux/SCSI LDD fabric loopback module"
+	depends on SCSI
 	help
 	  Say Y here to enable the TCM Virtual SAS target and Linux/SCSI LLD
 	  fabric loopback module.
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a502f1af4a21..ed3114556fda 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1560,9 +1560,12 @@ int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
 	d->iotlb = niotlb;
 
 	for (i = 0; i < d->nvqs; ++i) {
-		mutex_lock(&d->vqs[i]->mutex);
-		d->vqs[i]->iotlb = niotlb;
-		mutex_unlock(&d->vqs[i]->mutex);
+		struct vhost_virtqueue *vq = d->vqs[i];
+
+		mutex_lock(&vq->mutex);
+		vq->iotlb = niotlb;
+		__vhost_vq_meta_reset(vq);
+		mutex_unlock(&vq->mutex);
 	}
 
 	vhost_umem_clean(oiotlb);
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index 46a4484e3da7..c6f78d27947b 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -20,7 +20,7 @@
 #include <drm/drm_connector.h>  /* For DRM_MODE_PANEL_ORIENTATION_* */
 
 static bool request_mem_succeeded = false;
-static bool nowc = false;
+static u64 mem_flags = EFI_MEMORY_WC | EFI_MEMORY_UC;
 
 static struct fb_var_screeninfo efifb_defined = {
 	.activate		= FB_ACTIVATE_NOW,
@@ -68,8 +68,12 @@ static int efifb_setcolreg(unsigned regno, unsigned red, unsigned green,
 
 static void efifb_destroy(struct fb_info *info)
 {
-	if (info->screen_base)
-		iounmap(info->screen_base);
+	if (info->screen_base) {
+		if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+			iounmap(info->screen_base);
+		else
+			memunmap(info->screen_base);
+	}
 	if (request_mem_succeeded)
 		release_mem_region(info->apertures->ranges[0].base,
 				   info->apertures->ranges[0].size);
@@ -104,7 +108,7 @@ static int efifb_setup(char *options)
 			else if (!strncmp(this_opt, "width:", 6))
 				screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0);
 			else if (!strcmp(this_opt, "nowc"))
-				nowc = true;
+				mem_flags &= ~EFI_MEMORY_WC;
 		}
 	}
 
@@ -164,6 +168,7 @@ static int efifb_probe(struct platform_device *dev)
 	unsigned int size_remap;
 	unsigned int size_total;
 	char *option = NULL;
+	efi_memory_desc_t md;
 
 	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
 		return -ENODEV;
@@ -272,12 +277,35 @@ static int efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	if (nowc)
-		info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len);
-	else
-		info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len);
+	if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
+		if ((efifb_fix.smem_start + efifb_fix.smem_len) >
+		    (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) {
+			pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n",
+			       efifb_fix.smem_start);
+			err = -EIO;
+			goto err_release_fb;
+		}
+		/*
+		 * If the UEFI memory map covers the efifb region, we may only
+		 * remap it using the attributes the memory map prescribes.
+		 */
+		mem_flags |= EFI_MEMORY_WT | EFI_MEMORY_WB;
+		mem_flags &= md.attribute;
+	}
+	if (mem_flags & EFI_MEMORY_WC)
+		info->screen_base = ioremap_wc(efifb_fix.smem_start,
+					       efifb_fix.smem_len);
+	else if (mem_flags & EFI_MEMORY_UC)
+		info->screen_base = ioremap(efifb_fix.smem_start,
+					    efifb_fix.smem_len);
+	else if (mem_flags & EFI_MEMORY_WT)
+		info->screen_base = memremap(efifb_fix.smem_start,
+					     efifb_fix.smem_len, MEMREMAP_WT);
+	else if (mem_flags & EFI_MEMORY_WB)
+		info->screen_base = memremap(efifb_fix.smem_start,
+					     efifb_fix.smem_len, MEMREMAP_WB);
 	if (!info->screen_base) {
-		pr_err("efifb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n",
+		pr_err("efifb: abort, cannot remap video memory 0x%x @ 0x%lx\n",
 			efifb_fix.smem_len, efifb_fix.smem_start);
 		err = -EIO;
 		goto err_release_fb;
@@ -371,7 +399,10 @@ err_fb_dealoc:
 err_groups:
 	sysfs_remove_groups(&dev->dev.kobj, efifb_groups);
 err_unmap:
-	iounmap(info->screen_base);
+	if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+		iounmap(info->screen_base);
+	else
+		memunmap(info->screen_base);
 err_release_fb:
 	framebuffer_release(info);
 err_release_mem:
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 42e102e2e74a..85ff859d3af5 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -859,8 +859,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 
 static int
 v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
-		     struct file *file, unsigned flags, umode_t mode,
-		     int *opened)
+		     struct file *file, unsigned flags, umode_t mode)
 {
 	int err;
 	u32 perm;
@@ -917,7 +916,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		v9inode->writeback_fid = (void *) inode_fid;
 	}
 	mutex_unlock(&v9inode->v_mutex);
-	err = finish_open(file, dentry, generic_file_open, opened);
+	err = finish_open(file, dentry, generic_file_open);
 	if (err)
 		goto error;
 
@@ -925,7 +924,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(d_inode(dentry), file);
 
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 out:
 	dput(res);
 	return err;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 7f6ae21a27b3..4823e1c46999 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -241,8 +241,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 
 static int
 v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
-			  struct file *file, unsigned flags, umode_t omode,
-			  int *opened)
+			  struct file *file, unsigned flags, umode_t omode)
 {
 	int err = 0;
 	kgid_t gid;
@@ -352,13 +351,13 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	}
 	mutex_unlock(&v9inode->v_mutex);
 	/* Since we are opening a file, assign the open fid to the file */
-	err = finish_open(file, dentry, generic_file_open, opened);
+	err = finish_open(file, dentry, generic_file_open);
 	if (err)
 		goto err_clunk_old_fid;
 	file->private_data = ofid;
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(inode, file);
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 out:
 	v9fs_put_acl(dacl, pacl);
 	dput(res);
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index c836c425ca94..e91028d4340a 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -287,7 +287,7 @@ adfs_iget(struct super_block *sb, struct object_info *obj)
 		ADFS_I(inode)->mmu_private = inode->i_size;
 	}
 
-	insert_inode_hash(inode);
+	inode_fake_hash(inode);
 
 out:
 	return inode;
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 71fa525d63a0..7e099a7a4eb1 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -291,6 +291,7 @@ static void destroy_inodecache(void)
 static const struct super_operations adfs_sops = {
 	.alloc_inode	= adfs_alloc_inode,
 	.destroy_inode	= adfs_destroy_inode,
+	.drop_inode	= generic_delete_inode,
 	.write_inode	= adfs_write_inode,
 	.put_super	= adfs_put_super,
 	.statfs		= adfs_statfs,
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 7d623008157f..855bf2b79fed 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -822,6 +822,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 {
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct inode *inode;
+	struct dentry *d;
 	struct key *key;
 	int ret;
 
@@ -862,43 +863,17 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 
 	afs_stat_v(dvnode, n_lookup);
 	inode = afs_do_lookup(dir, dentry, key);
-	if (IS_ERR(inode)) {
-		ret = PTR_ERR(inode);
-		if (ret == -ENOENT) {
-			inode = afs_try_auto_mntpt(dentry, dir);
-			if (!IS_ERR(inode)) {
-				key_put(key);
-				goto success;
-			}
-
-			ret = PTR_ERR(inode);
-		}
-
-		key_put(key);
-		if (ret == -ENOENT) {
-			d_add(dentry, NULL);
-			_leave(" = NULL [negative]");
-			return NULL;
-		}
-		_leave(" = %d [do]", ret);
-		return ERR_PTR(ret);
-	}
-	dentry->d_fsdata = (void *)(unsigned long)dvnode->status.data_version;
-
-	/* instantiate the dentry */
 	key_put(key);
-	if (IS_ERR(inode)) {
-		_leave(" = %ld", PTR_ERR(inode));
-		return ERR_CAST(inode);
+	if (inode == ERR_PTR(-ENOENT)) {
+		inode = afs_try_auto_mntpt(dentry, dir);
+	} else {
+		dentry->d_fsdata =
+			(void *)(unsigned long)dvnode->status.data_version;
 	}
-
-success:
-	d_add(dentry, inode);
-	_leave(" = 0 { ino=%lu v=%u }",
-	       d_inode(dentry)->i_ino,
-	       d_inode(dentry)->i_generation);
-
-	return NULL;
+	d = d_splice_alias(inode, dentry);
+	if (!IS_ERR_OR_NULL(d))
+		d->d_fsdata = dentry->d_fsdata;
+	return d;
 }
 
 /*
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 174e843f0633..1cde710a8013 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -83,7 +83,7 @@ struct inode *afs_try_auto_mntpt(struct dentry *dentry, struct inode *dir)
 
 out:
 	_leave("= %d", ret);
-	return ERR_PTR(ret);
+	return ret == -ENOENT ? NULL : ERR_PTR(ret);
 }
 
 /*
@@ -141,12 +141,6 @@ out_p:
 static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
 					 unsigned int flags)
 {
-	struct afs_vnode *vnode;
-	struct inode *inode;
-	int ret;
-
-	vnode = AFS_FS_I(dir);
-
 	_enter("%pd", dentry);
 
 	ASSERTCMP(d_inode(dentry), ==, NULL);
@@ -160,22 +154,7 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr
 	    memcmp(dentry->d_name.name, "@cell", 5) == 0)
 		return afs_lookup_atcell(dentry);
 
-	inode = afs_try_auto_mntpt(dentry, dir);
-	if (IS_ERR(inode)) {
-		ret = PTR_ERR(inode);
-		if (ret == -ENOENT) {
-			d_add(dentry, NULL);
-			_leave(" = NULL [negative]");
-			return NULL;
-		}
-		_leave(" = %d [do]", ret);
-		return ERR_PTR(ret);
-	}
-
-	d_add(dentry, inode);
-	_leave(" = 0 { ino=%lu v=%u }",
-	       d_inode(dentry)->i_ino, d_inode(dentry)->i_generation);
-	return NULL;
+	return d_splice_alias(afs_try_auto_mntpt(dentry, dir), dentry);
 }
 
 const struct inode_operations afs_dynroot_inode_operations = {
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index a1b18082991b..183cc5418722 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -648,7 +648,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
 	trace_afs_notify_call(rxcall, call);
 	call->need_attention = true;
 
-	u = __atomic_add_unless(&call->usage, 1, 0);
+	u = atomic_fetch_add_unless(&call->usage, 1, 0);
 	if (u != 0) {
 		trace_afs_call(call, afs_call_trace_wake, u,
 			       atomic_read(&call->net->nr_outstanding_calls),
diff --git a/fs/aio.c b/fs/aio.c
index 27454594e37a..b9350f3360c6 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -5,6 +5,7 @@
  *	Implements an efficient asynchronous io interface.
  *
  *	Copyright 2000, 2001, 2002 Red Hat, Inc.  All Rights Reserved.
+ *	Copyright 2018 Christoph Hellwig.
  *
  *	See ../COPYING for licensing terms.
  */
@@ -18,6 +19,7 @@
 #include <linux/export.h>
 #include <linux/syscalls.h>
 #include <linux/backing-dev.h>
+#include <linux/refcount.h>
 #include <linux/uio.h>
 
 #include <linux/sched/signal.h>
@@ -164,10 +166,21 @@ struct fsync_iocb {
 	bool			datasync;
 };
 
+struct poll_iocb {
+	struct file		*file;
+	struct wait_queue_head	*head;
+	__poll_t		events;
+	bool			woken;
+	bool			cancelled;
+	struct wait_queue_entry	wait;
+	struct work_struct	work;
+};
+
 struct aio_kiocb {
 	union {
 		struct kiocb		rw;
 		struct fsync_iocb	fsync;
+		struct poll_iocb	poll;
 	};
 
 	struct kioctx		*ki_ctx;
@@ -178,6 +191,7 @@ struct aio_kiocb {
 
 	struct list_head	ki_list;	/* the aio core uses this
 						 * for cancellation */
+	refcount_t		ki_refcnt;
 
 	/*
 	 * If the aio_resfd field of the userspace iocb is not zero,
@@ -202,9 +216,7 @@ static const struct address_space_operations aio_ctx_aops;
 
 static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 {
-	struct qstr this = QSTR_INIT("[aio]", 5);
 	struct file *file;
-	struct path path;
 	struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
@@ -213,31 +225,17 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 	inode->i_mapping->private_data = ctx;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
-	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
-	if (!path.dentry) {
+	file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
+				O_RDWR, &aio_ring_fops);
+	if (IS_ERR(file))
 		iput(inode);
-		return ERR_PTR(-ENOMEM);
-	}
-	path.mnt = mntget(aio_mnt);
-
-	d_instantiate(path.dentry, inode);
-	file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops);
-	if (IS_ERR(file)) {
-		path_put(&path);
-		return file;
-	}
-
-	file->f_flags = O_RDWR;
 	return file;
 }
 
 static struct dentry *aio_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
-	static const struct dentry_operations ops = {
-		.d_dname	= simple_dname,
-	};
-	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, NULL,
 					   AIO_RING_MAGIC);
 
 	if (!IS_ERR(root))
@@ -1015,6 +1013,7 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 
 	percpu_ref_get(&ctx->reqs);
 	INIT_LIST_HEAD(&req->ki_list);
+	refcount_set(&req->ki_refcnt, 0);
 	req->ki_ctx = ctx;
 	return req;
 out_put:
@@ -1049,6 +1048,15 @@ out:
 	return ret;
 }
 
+static inline void iocb_put(struct aio_kiocb *iocb)
+{
+	if (refcount_read(&iocb->ki_refcnt) == 0 ||
+	    refcount_dec_and_test(&iocb->ki_refcnt)) {
+		percpu_ref_put(&iocb->ki_ctx->reqs);
+		kmem_cache_free(kiocb_cachep, iocb);
+	}
+}
+
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
@@ -1118,8 +1126,6 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 		eventfd_ctx_put(iocb->ki_eventfd);
 	}
 
-	kmem_cache_free(kiocb_cachep, iocb);
-
 	/*
 	 * We have to order our ring_info tail store above and test
 	 * of the wait list below outside the wait lock.  This is
@@ -1130,8 +1136,7 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
-
-	percpu_ref_put(&ctx->reqs);
+	iocb_put(iocb);
 }
 
 /* aio_read_events_ring
@@ -1592,6 +1597,182 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
 	return 0;
 }
 
+static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
+{
+	struct file *file = iocb->poll.file;
+
+	aio_complete(iocb, mangle_poll(mask), 0);
+	fput(file);
+}
+
+static void aio_poll_complete_work(struct work_struct *work)
+{
+	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
+	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+	struct poll_table_struct pt = { ._key = req->events };
+	struct kioctx *ctx = iocb->ki_ctx;
+	__poll_t mask = 0;
+
+	if (!READ_ONCE(req->cancelled))
+		mask = vfs_poll(req->file, &pt) & req->events;
+
+	/*
+	 * Note that ->ki_cancel callers also delete iocb from active_reqs after
+	 * calling ->ki_cancel.  We need the ctx_lock roundtrip here to
+	 * synchronize with them.  In the cancellation case the list_del_init
+	 * itself is not actually needed, but harmless so we keep it in to
+	 * avoid further branches in the fast path.
+	 */
+	spin_lock_irq(&ctx->ctx_lock);
+	if (!mask && !READ_ONCE(req->cancelled)) {
+		add_wait_queue(req->head, &req->wait);
+		spin_unlock_irq(&ctx->ctx_lock);
+		return;
+	}
+	list_del_init(&iocb->ki_list);
+	spin_unlock_irq(&ctx->ctx_lock);
+
+	aio_poll_complete(iocb, mask);
+}
+
+/* assumes we are called with irqs disabled */
+static int aio_poll_cancel(struct kiocb *iocb)
+{
+	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
+	struct poll_iocb *req = &aiocb->poll;
+
+	spin_lock(&req->head->lock);
+	WRITE_ONCE(req->cancelled, true);
+	if (!list_empty(&req->wait.entry)) {
+		list_del_init(&req->wait.entry);
+		schedule_work(&aiocb->poll.work);
+	}
+	spin_unlock(&req->head->lock);
+
+	return 0;
+}
+
+static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+		void *key)
+{
+	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
+	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+	__poll_t mask = key_to_poll(key);
+
+	req->woken = true;
+
+	/* for instances that support it check for an event match first: */
+	if (mask) {
+		if (!(mask & req->events))
+			return 0;
+
+		/* try to complete the iocb inline if we can: */
+		if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
+			list_del(&iocb->ki_list);
+			spin_unlock(&iocb->ki_ctx->ctx_lock);
+
+			list_del_init(&req->wait.entry);
+			aio_poll_complete(iocb, mask);
+			return 1;
+		}
+	}
+
+	list_del_init(&req->wait.entry);
+	schedule_work(&req->work);
+	return 1;
+}
+
+struct aio_poll_table {
+	struct poll_table_struct	pt;
+	struct aio_kiocb		*iocb;
+	int				error;
+};
+
+static void
+aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
+		struct poll_table_struct *p)
+{
+	struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt);
+
+	/* multiple wait queues per file are not supported */
+	if (unlikely(pt->iocb->poll.head)) {
+		pt->error = -EINVAL;
+		return;
+	}
+
+	pt->error = 0;
+	pt->iocb->poll.head = head;
+	add_wait_queue(head, &pt->iocb->poll.wait);
+}
+
+static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+{
+	struct kioctx *ctx = aiocb->ki_ctx;
+	struct poll_iocb *req = &aiocb->poll;
+	struct aio_poll_table apt;
+	__poll_t mask;
+
+	/* reject any unknown events outside the normal event mask. */
+	if ((u16)iocb->aio_buf != iocb->aio_buf)
+		return -EINVAL;
+	/* reject fields that are not defined for poll */
+	if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
+		return -EINVAL;
+
+	INIT_WORK(&req->work, aio_poll_complete_work);
+	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
+	req->file = fget(iocb->aio_fildes);
+	if (unlikely(!req->file))
+		return -EBADF;
+
+	apt.pt._qproc = aio_poll_queue_proc;
+	apt.pt._key = req->events;
+	apt.iocb = aiocb;
+	apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
+
+	/* initialized the list so that we can do list_empty checks */
+	INIT_LIST_HEAD(&req->wait.entry);
+	init_waitqueue_func_entry(&req->wait, aio_poll_wake);
+
+	/* one for removal from waitqueue, one for this function */
+	refcount_set(&aiocb->ki_refcnt, 2);
+
+	mask = vfs_poll(req->file, &apt.pt) & req->events;
+	if (unlikely(!req->head)) {
+		/* we did not manage to set up a waitqueue, done */
+		goto out;
+	}
+
+	spin_lock_irq(&ctx->ctx_lock);
+	spin_lock(&req->head->lock);
+	if (req->woken) {
+		/* wake_up context handles the rest */
+		mask = 0;
+		apt.error = 0;
+	} else if (mask || apt.error) {
+		/* if we get an error or a mask we are done */
+		WARN_ON_ONCE(list_empty(&req->wait.entry));
+		list_del_init(&req->wait.entry);
+	} else {
+		/* actually waiting for an event */
+		list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+		aiocb->ki_cancel = aio_poll_cancel;
+	}
+	spin_unlock(&req->head->lock);
+	spin_unlock_irq(&ctx->ctx_lock);
+
+out:
+	if (unlikely(apt.error)) {
+		fput(req->file);
+		return apt.error;
+	}
+
+	if (mask)
+		aio_poll_complete(aiocb, mask);
+	iocb_put(aiocb);
+	return 0;
+}
+
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 bool compat)
 {
@@ -1665,6 +1846,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	case IOCB_CMD_FDSYNC:
 		ret = aio_fsync(&req->fsync, &iocb, true);
 		break;
+	case IOCB_CMD_POLL:
+		ret = aio_poll(req, &iocb);
+		break;
 	default:
 		pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
 		ret = -EINVAL;
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 3168ee4e77f4..91262c34b797 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -71,8 +71,6 @@ struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
 
 	if (IS_ERR(anon_inode_inode))
@@ -82,39 +80,23 @@ struct file *anon_inode_getfile(const char *name,
 		return ERR_PTR(-ENOENT);
 
 	/*
-	 * Link the inode to a directory entry by creating a unique name
-	 * using the inode sequence number.
-	 */
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
-	if (!path.dentry)
-		goto err_module;
-
-	path.mnt = mntget(anon_inode_mnt);
-	/*
 	 * We know the anon_inode inode count is always greater than zero,
 	 * so ihold() is safe.
 	 */
 	ihold(anon_inode_inode);
-
-	d_instantiate(path.dentry, anon_inode_inode);
-
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file_pseudo(anon_inode_inode, anon_inode_mnt, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file))
-		goto err_dput;
+		goto err;
+
 	file->f_mapping = anon_inode_inode->i_mapping;
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
 
-err_dput:
-	path_put(&path);
-err_module:
+err:
+	iput(anon_inode_inode);
 	module_put(fops->owner);
 	return file;
 }
diff --git a/fs/attr.c b/fs/attr.c
index e3d53bf12240..d22e8187477f 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -120,7 +120,6 @@ EXPORT_SYMBOL(setattr_prepare);
  * inode_newsize_ok - may this inode be truncated to a given size
  * @inode:	the inode to be truncated
  * @offset:	the new size to assign to the inode
- * @Returns:	0 on success, -ve errno on failure
  *
  * inode_newsize_ok must be called with i_mutex held.
  *
@@ -130,6 +129,8 @@ EXPORT_SYMBOL(setattr_prepare);
  * returned. @inode must be a file (not directory), with appropriate
  * permissions to allow truncate (inode_newsize_ok does NOT check these
  * conditions).
+ *
+ * Return: 0 on success, -ve errno on failure
  */
 int inode_newsize_ok(const struct inode *inode, loff_t offset)
 {
@@ -205,7 +206,7 @@ EXPORT_SYMBOL(setattr_copy);
 /**
  * notify_change - modify attributes of a filesytem object
  * @dentry:	object affected
- * @iattr:	new attributes
+ * @attr:	new attributes
  * @delegated_inode: returns inode, if the inode is delegated
  *
  * The caller must hold the i_mutex on the affected object.
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 125e8bbd22a2..8035d2a44561 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -134,7 +134,7 @@ static int bad_inode_update_time(struct inode *inode, struct timespec64 *time,
 
 static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry,
 				 struct file *file, unsigned int open_flag,
-				 umode_t create_mode, int *opened)
+				 umode_t create_mode)
 {
 	return -EIO;
 }
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 816cc921cf36..efae2fb0930a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1751,7 +1751,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 		const struct user_regset *regset = &view->regsets[i];
 		do_thread_regset_writeback(t->task, regset);
 		if (regset->core_note_type && regset->get &&
-		    (!regset->active || regset->active(t->task, regset))) {
+		    (!regset->active || regset->active(t->task, regset) > 0)) {
 			int ret;
 			size_t size = regset_size(t->task, regset);
 			void *data = kmalloc(size, GFP_KERNEL);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 4b5fff31ef27..aa4a7a23ff99 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -205,7 +205,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		goto error;
 
 	if (fmt->flags & MISC_FMT_OPEN_FILE) {
-		interp_file = filp_clone_open(fmt->interp_file);
+		interp_file = file_clone_open(fmt->interp_file);
 		if (!IS_ERR(interp_file))
 			deny_write_access(interp_file);
 	} else {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index aba25414231a..38b8ce05cbc7 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -666,7 +666,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	result = blk_queue_enter(bdev->bd_queue, 0);
 	if (result)
 		return result;
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_READ);
 	blk_queue_exit(bdev->bd_queue);
 	return result;
 }
@@ -704,7 +705,8 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 		return result;
 
 	set_page_writeback(page);
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_WRITE);
 	if (result) {
 		end_page_writeback(page);
 	} else {
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 15e1dfef56a5..3b66c957ea6f 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -30,23 +30,22 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
-		BUG();
+		return ERR_PTR(-EINVAL);
 	}
 
-	size = btrfs_getxattr(inode, name, "", 0);
+	size = btrfs_getxattr(inode, name, NULL, 0);
 	if (size > 0) {
 		value = kzalloc(size, GFP_KERNEL);
 		if (!value)
 			return ERR_PTR(-ENOMEM);
 		size = btrfs_getxattr(inode, name, value, size);
 	}
-	if (size > 0) {
+	if (size > 0)
 		acl = posix_acl_from_xattr(&init_user_ns, value, size);
-	} else if (size == -ERANGE || size == -ENODATA || size == 0) {
+	else if (size == -ENODATA || size == 0)
 		acl = NULL;
-	} else {
-		acl = ERR_PTR(-EIO);
-	}
+	else
+		acl = ERR_PTR(size);
 	kfree(value);
 
 	return acl;
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 0a8e2e29a66b..ae750b1574a2 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -925,7 +925,7 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info,
 		type = btrfs_get_extent_inline_ref_type(leaf, iref,
 							BTRFS_REF_TYPE_ANY);
 		if (type == BTRFS_REF_TYPE_INVALID)
-			return -EINVAL;
+			return -EUCLEAN;
 
 		offset = btrfs_extent_inline_ref_offset(leaf, iref);
 
@@ -1793,7 +1793,7 @@ static int get_extent_inline_ref(unsigned long *ptr,
 	*out_type = btrfs_get_extent_inline_ref_type(eb, *out_eiref,
 						     BTRFS_REF_TYPE_ANY);
 	if (*out_type == BTRFS_REF_TYPE_INVALID)
-		return -EINVAL;
+		return -EUCLEAN;
 
 	*ptr += btrfs_extent_inline_ref_size(*out_type);
 	WARN_ON(*ptr > end);
@@ -2225,7 +2225,7 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 
 	fspath = init_data_container(total_bytes);
 	if (IS_ERR(fspath))
-		return (void *)fspath;
+		return ERR_CAST(fspath);
 
 	ifp = kmalloc(sizeof(*ifp), GFP_KERNEL);
 	if (!ifp) {
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 7e075343daa5..1343ac57b438 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -178,7 +178,7 @@ struct btrfs_inode {
 	struct btrfs_delayed_node *delayed_node;
 
 	/* File creation time. */
-	struct timespec i_otime;
+	struct timespec64 i_otime;
 
 	/* Hook into fs_info->delayed_iputs */
 	struct list_head delayed_iput;
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index a3fdb4fe967d..833cf3c35b4d 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1539,7 +1539,12 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
 	}
 
 	device = multi->stripes[0].dev;
-	block_ctx_out->dev = btrfsic_dev_state_lookup(device->bdev->bd_dev);
+	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state) ||
+	    !device->bdev || !device->name)
+		block_ctx_out->dev = NULL;
+	else
+		block_ctx_out->dev = btrfsic_dev_state_lookup(
+							device->bdev->bd_dev);
 	block_ctx_out->dev_bytenr = multi->stripes[0].physical;
 	block_ctx_out->start = bytenr;
 	block_ctx_out->len = len;
@@ -1624,7 +1629,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 		bio = btrfs_io_bio_alloc(num_pages - i);
 		bio_set_dev(bio, block_ctx->dev->bdev);
 		bio->bi_iter.bi_sector = dev_bytenr >> 9;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		for (j = i; j < num_pages; j++) {
 			ret = bio_add_page(bio, block_ctx->pagev[j],
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d3e447b45bf7..9bfa66592aa7 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -5,7 +5,6 @@
 
 #include <linux/kernel.h>
 #include <linux/bio.h>
-#include <linux/buffer_head.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
@@ -14,10 +13,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
-#include <linux/bit_spinlock.h>
 #include <linux/slab.h>
 #include <linux/sched/mm.h>
 #include <linux/log2.h>
@@ -303,7 +299,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	struct bio *bio = NULL;
 	struct compressed_bio *cb;
 	unsigned long bytes_left;
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	int pg_index = 0;
 	struct page *page;
 	u64 first_byte = disk_start;
@@ -342,9 +337,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		page = compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		if (bio->bi_iter.bi_size)
-			submit = io_tree->ops->merge_bio_hook(page, 0,
-							   PAGE_SIZE,
-							   bio, 0);
+			submit = btrfs_merge_bio_hook(page, 0, PAGE_SIZE, bio, 0);
 
 		page->mapping = NULL;
 		if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) <
@@ -613,7 +606,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	cb->len = bio->bi_iter.bi_size;
 
 	comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
-	bio_set_op_attrs (comp_bio, REQ_OP_READ, 0);
+	comp_bio->bi_opf = REQ_OP_READ;
 	comp_bio->bi_private = cb;
 	comp_bio->bi_end_io = end_compressed_bio_read;
 	refcount_set(&cb->pending_bios, 1);
@@ -626,9 +619,8 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		page->index = em_start >> PAGE_SHIFT;
 
 		if (comp_bio->bi_iter.bi_size)
-			submit = tree->ops->merge_bio_hook(page, 0,
-							PAGE_SIZE,
-							comp_bio, 0);
+			submit = btrfs_merge_bio_hook(page, 0, PAGE_SIZE,
+					comp_bio, 0);
 
 		page->mapping = NULL;
 		if (submit || bio_add_page(comp_bio, page, PAGE_SIZE, 0) <
@@ -660,7 +652,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			}
 
 			comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
-			bio_set_op_attrs(comp_bio, REQ_OP_READ, 0);
+			comp_bio->bi_opf = REQ_OP_READ;
 			comp_bio->bi_private = cb;
 			comp_bio->bi_end_io = end_compressed_bio_read;
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 4bc326df472e..d436fb4c002e 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -888,11 +888,7 @@ int btrfs_block_can_be_shared(struct btrfs_root *root,
 	     btrfs_root_last_snapshot(&root->root_item) ||
 	     btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
 		return 1;
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
-	    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
-		return 1;
-#endif
+
 	return 0;
 }
 
@@ -3128,8 +3124,7 @@ again:
  * higher levels
  *
  */
-static void fixup_low_keys(struct btrfs_fs_info *fs_info,
-			   struct btrfs_path *path,
+static void fixup_low_keys(struct btrfs_path *path,
 			   struct btrfs_disk_key *key, int level)
 {
 	int i;
@@ -3181,7 +3176,7 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
 	btrfs_set_item_key(eb, &disk_key, slot);
 	btrfs_mark_buffer_dirty(eb);
 	if (slot == 0)
-		fixup_low_keys(fs_info, path, &disk_key, 1);
+		fixup_low_keys(path, &disk_key, 1);
 }
 
 /*
@@ -3359,17 +3354,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 
 	root_add_used(root, fs_info->nodesize);
 
-	memzero_extent_buffer(c, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_nritems(c, 1);
-	btrfs_set_header_level(c, level);
-	btrfs_set_header_bytenr(c, c->start);
-	btrfs_set_header_generation(c, trans->transid);
-	btrfs_set_header_backref_rev(c, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(c, root->root_key.objectid);
-
-	write_extent_buffer_fsid(c, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(c, fs_info->chunk_tree_uuid);
-
 	btrfs_set_node_key(c, &lower_key, 0);
 	btrfs_set_node_blockptr(c, 0, lower->start);
 	lower_gen = btrfs_header_generation(lower);
@@ -3498,15 +3483,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 		return PTR_ERR(split);
 
 	root_add_used(root, fs_info->nodesize);
-
-	memzero_extent_buffer(split, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_level(split, btrfs_header_level(c));
-	btrfs_set_header_bytenr(split, split->start);
-	btrfs_set_header_generation(split, trans->transid);
-	btrfs_set_header_backref_rev(split, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(split, root->root_key.objectid);
-	write_extent_buffer_fsid(split, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(split, fs_info->chunk_tree_uuid);
+	ASSERT(btrfs_header_level(c) == level);
 
 	ret = tree_mod_log_eb_copy(fs_info, split, c, 0, mid, c_nritems - mid);
 	if (ret) {
@@ -3945,7 +3922,7 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info,
 		clean_tree_block(fs_info, right);
 
 	btrfs_item_key(right, &disk_key, 0);
-	fixup_low_keys(fs_info, path, &disk_key, 1);
+	fixup_low_keys(path, &disk_key, 1);
 
 	/* then fixup the leaf pointer in the path */
 	if (path->slots[0] < push_items) {
@@ -4292,15 +4269,6 @@ again:
 
 	root_add_used(root, fs_info->nodesize);
 
-	memzero_extent_buffer(right, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(right, right->start);
-	btrfs_set_header_generation(right, trans->transid);
-	btrfs_set_header_backref_rev(right, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(right, root->root_key.objectid);
-	btrfs_set_header_level(right, 0);
-	write_extent_buffer_fsid(right, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(right, fs_info->chunk_tree_uuid);
-
 	if (split == 0) {
 		if (mid <= slot) {
 			btrfs_set_header_nritems(right, 0);
@@ -4320,7 +4288,7 @@ again:
 			path->nodes[0] = right;
 			path->slots[0] = 0;
 			if (path->slots[1] == 0)
-				fixup_low_keys(fs_info, path, &disk_key, 1);
+				fixup_low_keys(path, &disk_key, 1);
 		}
 		/*
 		 * We create a new leaf 'right' for the required ins_len and
@@ -4642,7 +4610,7 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info,
 		btrfs_set_disk_key_offset(&disk_key, offset + size_diff);
 		btrfs_set_item_key(leaf, &disk_key, slot);
 		if (slot == 0)
-			fixup_low_keys(fs_info, path, &disk_key, 1);
+			fixup_low_keys(path, &disk_key, 1);
 	}
 
 	item = btrfs_item_nr(slot);
@@ -4744,7 +4712,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
 
 	if (path->slots[0] == 0) {
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
-		fixup_low_keys(fs_info, path, &disk_key, 1);
+		fixup_low_keys(path, &disk_key, 1);
 	}
 	btrfs_unlock_up_safe(path, 1);
 
@@ -4886,7 +4854,6 @@ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
 		    int level, int slot)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *parent = path->nodes[level];
 	u32 nritems;
 	int ret;
@@ -4919,7 +4886,7 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
 		struct btrfs_disk_key disk_key;
 
 		btrfs_node_key(parent, &disk_key, 0);
-		fixup_low_keys(fs_info, path, &disk_key, level + 1);
+		fixup_low_keys(path, &disk_key, level + 1);
 	}
 	btrfs_mark_buffer_dirty(parent);
 }
@@ -5022,7 +4989,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			struct btrfs_disk_key disk_key;
 
 			btrfs_item_key(leaf, &disk_key, 0);
-			fixup_low_keys(fs_info, path, &disk_key, 1);
+			fixup_low_keys(path, &disk_key, 1);
 		}
 
 		/* delete the leaf if it is mostly empty */
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 118346aceea9..318be7864072 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -55,8 +55,6 @@ struct btrfs_ordered_sum;
 
 #define BTRFS_OLDEST_GENERATION	0ULL
 
-#define BTRFS_COMPAT_EXTENT_TREE_V0
-
 /*
  * the max metadata block size.  This limit is somewhat artificial,
  * but the memmove costs go through the roof for larger blocks.
@@ -86,6 +84,14 @@ static const int btrfs_csum_sizes[] = { 4 };
 
 #define BTRFS_DIRTY_METADATA_THRESH	SZ_32M
 
+/*
+ * Use large batch size to reduce overhead of metadata updates.  On the reader
+ * side, we only read it when we are close to ENOSPC and the read overhead is
+ * mostly related to the number of CPUs, so it is OK to use arbitrary large
+ * value here.
+ */
+#define BTRFS_TOTAL_BYTES_PINNED_BATCH	SZ_128M
+
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
 
@@ -342,8 +348,8 @@ struct btrfs_path {
 					sizeof(struct btrfs_item))
 struct btrfs_dev_replace {
 	u64 replace_state;	/* see #define above */
-	u64 time_started;	/* seconds since 1-Jan-1970 */
-	u64 time_stopped;	/* seconds since 1-Jan-1970 */
+	time64_t time_started;	/* seconds since 1-Jan-1970 */
+	time64_t time_stopped;	/* seconds since 1-Jan-1970 */
 	atomic64_t num_write_errors;
 	atomic64_t num_uncorrectable_read_errors;
 
@@ -359,8 +365,6 @@ struct btrfs_dev_replace {
 	struct btrfs_device *srcdev;
 	struct btrfs_device *tgtdev;
 
-	pid_t lock_owner;
-	atomic_t nesting_level;
 	struct mutex lock_finishing_cancel_unmount;
 	rwlock_t lock;
 	atomic_t read_locks;
@@ -1213,7 +1217,6 @@ struct btrfs_root {
 	u64 defrag_trans_start;
 	struct btrfs_key defrag_progress;
 	struct btrfs_key defrag_max;
-	char *name;
 
 	/* the dirty list is only used by non-reference counted roots */
 	struct list_head dirty_list;
@@ -2428,32 +2431,6 @@ static inline u32 btrfs_file_extent_inline_item_len(
 	return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START;
 }
 
-/* this returns the number of file bytes represented by the inline item.
- * If an item is compressed, this is the uncompressed size
- */
-static inline u32 btrfs_file_extent_inline_len(const struct extent_buffer *eb,
-					int slot,
-					const struct btrfs_file_extent_item *fi)
-{
-	struct btrfs_map_token token;
-
-	btrfs_init_map_token(&token);
-	/*
-	 * return the space used on disk if this item isn't
-	 * compressed or encoded
-	 */
-	if (btrfs_token_file_extent_compression(eb, fi, &token) == 0 &&
-	    btrfs_token_file_extent_encryption(eb, fi, &token) == 0 &&
-	    btrfs_token_file_extent_other_encoding(eb, fi, &token) == 0) {
-		return btrfs_file_extent_inline_item_len(eb,
-							 btrfs_item_nr(slot));
-	}
-
-	/* otherwise use the ram bytes field */
-	return btrfs_token_file_extent_ram_bytes(eb, fi, &token);
-}
-
-
 /* btrfs_dev_stats_item */
 static inline u64 btrfs_dev_stats_value(const struct extent_buffer *eb,
 					const struct btrfs_dev_stats_item *ptr,
@@ -2676,7 +2653,6 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 				     u64 offset, u64 ram_bytes,
 				     struct btrfs_key *ins);
 int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   u64 root_objectid, u64 owner, u64 offset,
 				   struct btrfs_key *ins);
 int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes,
@@ -2716,15 +2692,14 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info);
 int btrfs_read_block_groups(struct btrfs_fs_info *info);
 int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr);
 int btrfs_make_block_group(struct btrfs_trans_handle *trans,
-			   struct btrfs_fs_info *fs_info, u64 bytes_used,
-			   u64 type, u64 chunk_offset, u64 size);
+			   u64 bytes_used, u64 type, u64 chunk_offset,
+			   u64 size);
 void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info);
 struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
 				const u64 chunk_offset);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info, u64 group_start,
-			     struct extent_map *em);
+			     u64 group_start, struct extent_map *em);
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
 void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
@@ -2786,7 +2761,6 @@ void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info,
 				   unsigned short type);
 void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
 			  struct btrfs_block_rsv *rsv);
-void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv);
 int btrfs_block_rsv_add(struct btrfs_root *root,
 			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
 			enum btrfs_reserve_flush_enum flush);
@@ -2803,8 +2777,7 @@ int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
 void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
 			     struct btrfs_block_rsv *block_rsv,
 			     u64 num_bytes);
-int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info,
-			     struct btrfs_block_group_cache *cache);
+int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
@@ -2812,8 +2785,7 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
 				   u64 start, u64 end);
 int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			 u64 num_bytes, u64 *actual_bytes);
-int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info, u64 type);
+int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
 int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
 
 int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
@@ -2822,10 +2794,10 @@ int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
 int btrfs_start_write_no_snapshotting(struct btrfs_root *root);
 void btrfs_end_write_no_snapshotting(struct btrfs_root *root);
 void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
-void check_system_chunk(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, const u64 type);
+void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
 u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 		       u64 start, u64 end);
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
 
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
@@ -3011,16 +2983,14 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq);
 
 /* root-item.c */
-int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 sequence,
-		       const char *name, int name_len);
-int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
-		       const char *name, int name_len);
+int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 sequence, const char *name,
+		       int name_len);
+int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 *sequence, const char *name,
+		       int name_len);
 int btrfs_del_root(struct btrfs_trans_handle *trans,
-		   struct btrfs_fs_info *fs_info, const struct btrfs_key *key);
+		   const struct btrfs_key *key);
 int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		      const struct btrfs_key *key,
 		      struct btrfs_root_item *item);
@@ -3196,7 +3166,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 			 size_t size, struct bio *bio,
 			 unsigned long bio_flags);
-void btrfs_set_range_writeback(void *private_data, u64 start, u64 end);
+void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end);
 vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
 int btrfs_readpage(struct file *file, struct page *page);
 void btrfs_evict_inode(struct inode *inode);
@@ -3452,7 +3422,7 @@ do {								\
 #ifdef CONFIG_BTRFS_ASSERT
 
 __cold
-static inline void assfail(char *expr, char *file, int line)
+static inline void assfail(const char *expr, const char *file, int line)
 {
 	pr_err("assertion failed: %s, file: %s, line: %d\n",
 	       expr, file, line);
@@ -3465,6 +3435,13 @@ static inline void assfail(char *expr, char *file, int line)
 #define ASSERT(expr)	((void)0)
 #endif
 
+__cold
+static inline void btrfs_print_v0_err(struct btrfs_fs_info *fs_info)
+{
+	btrfs_err(fs_info,
+"Unsupported V0 extent filesystem detected. Aborting. Please re-create your filesystem with a newer kernel");
+}
+
 __printf(5, 6)
 __cold
 void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index fe6caa7e698b..f51b509f2d9b 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1222,7 +1222,7 @@ int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
 
 int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
 	struct btrfs_path *path;
@@ -1418,7 +1418,6 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info)
 
 /* Will return 0 or -ENOMEM */
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
 				   struct btrfs_disk_key *disk_key, u8 type,
@@ -1458,11 +1457,10 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 	 */
 	BUG_ON(ret);
 
-
 	mutex_lock(&delayed_node->mutex);
 	ret = __btrfs_add_delayed_insertion_item(delayed_node, delayed_item);
 	if (unlikely(ret)) {
-		btrfs_err(fs_info,
+		btrfs_err(trans->fs_info,
 			  "err add delayed dir index item(name: %.*s) into the insertion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
 			  name_len, name, delayed_node->root->objectid,
 			  delayed_node->inode_id, ret);
@@ -1495,7 +1493,6 @@ static int btrfs_delete_delayed_insertion_item(struct btrfs_fs_info *fs_info,
 }
 
 int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   struct btrfs_inode *dir, u64 index)
 {
 	struct btrfs_delayed_node *node;
@@ -1511,7 +1508,8 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	item_key.type = BTRFS_DIR_INDEX_KEY;
 	item_key.offset = index;
 
-	ret = btrfs_delete_delayed_insertion_item(fs_info, node, &item_key);
+	ret = btrfs_delete_delayed_insertion_item(trans->fs_info, node,
+						  &item_key);
 	if (!ret)
 		goto end;
 
@@ -1533,7 +1531,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	mutex_lock(&node->mutex);
 	ret = __btrfs_add_delayed_deletion_item(node, item);
 	if (unlikely(ret)) {
-		btrfs_err(fs_info,
+		btrfs_err(trans->fs_info,
 			  "err add delayed dir index item(index: %llu) into the deletion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
 			  index, node->root->objectid, node->inode_id, ret);
 		BUG();
@@ -1837,7 +1835,7 @@ release_node:
 
 int btrfs_delayed_delete_inode_ref(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_delayed_node *delayed_node;
 
 	/*
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index ca7a97f3ab6b..33536cd681d4 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -86,14 +86,12 @@ static inline void btrfs_init_delayed_root(
 }
 
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
 				   struct btrfs_disk_key *disk_key, u8 type,
 				   u64 index);
 
 int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   struct btrfs_inode *dir, u64 index);
 
 int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 03dec673d12a..62ff545ba1f7 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -709,13 +709,13 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
  * to make sure the delayed ref is eventually processed before this
  * transaction commits.
  */
-int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root,  int level, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int *old_ref_mod, int *new_ref_mod)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_tree_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
@@ -730,27 +730,33 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	if (!ref)
 		return -ENOMEM;
 
+	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
+	if (!head_ref) {
+		kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+		return -ENOMEM;
+	}
+
+	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
+	    is_fstree(ref_root)) {
+		record = kmalloc(sizeof(*record), GFP_NOFS);
+		if (!record) {
+			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+			kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
+			return -ENOMEM;
+		}
+	}
+
 	if (parent)
 		ref_type = BTRFS_SHARED_BLOCK_REF_KEY;
 	else
 		ref_type = BTRFS_TREE_BLOCK_REF_KEY;
+
 	init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
 				ref_root, action, ref_type);
 	ref->root = ref_root;
 	ref->parent = parent;
 	ref->level = level;
 
-	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
-	if (!head_ref)
-		goto free_ref;
-
-	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
-	    is_fstree(ref_root)) {
-		record = kmalloc(sizeof(*record), GFP_NOFS);
-		if (!record)
-			goto free_head_ref;
-	}
-
 	init_delayed_ref_head(head_ref, record, bytenr, num_bytes,
 			      ref_root, 0, action, false, is_system);
 	head_ref->extent_op = extent_op;
@@ -779,25 +785,18 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 		btrfs_qgroup_trace_extent_post(fs_info, record);
 
 	return 0;
-
-free_head_ref:
-	kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
-free_ref:
-	kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
-
-	return -ENOMEM;
 }
 
 /*
  * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
  */
-int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, u64 reserved, int action,
 			       int *old_ref_mod, int *new_ref_mod)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_data_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index ea1aecb6a50d..d9f2a4ebd5db 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -234,14 +234,12 @@ static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *hea
 		kmem_cache_free(btrfs_delayed_ref_head_cachep, head);
 }
 
-int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root, int level, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int *old_ref_mod, int *new_ref_mod);
-int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, u64 reserved, int action,
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index e2ba0419297a..dec01970d8c5 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -6,14 +6,9 @@
 #include <linux/sched.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
-#include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/random.h>
-#include <linux/iocontext.h>
-#include <linux/capability.h>
 #include <linux/kthread.h>
 #include <linux/math64.h>
-#include <asm/div64.h>
 #include "ctree.h"
 #include "extent_map.h"
 #include "disk-io.h"
@@ -465,7 +460,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	 * go to the tgtdev as well (refer to btrfs_map_block()).
 	 */
 	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED;
-	dev_replace->time_started = get_seconds();
+	dev_replace->time_started = ktime_get_real_seconds();
 	dev_replace->cursor_left = 0;
 	dev_replace->committed_cursor_left = 0;
 	dev_replace->cursor_left_last_write_of_item = 0;
@@ -511,7 +506,7 @@ leave:
 	dev_replace->srcdev = NULL;
 	dev_replace->tgtdev = NULL;
 	btrfs_dev_replace_write_unlock(dev_replace);
-	btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+	btrfs_destroy_dev_replace_tgtdev(tgt_device);
 	return ret;
 }
 
@@ -618,7 +613,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 			  : BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED;
 	dev_replace->tgtdev = NULL;
 	dev_replace->srcdev = NULL;
-	dev_replace->time_stopped = get_seconds();
+	dev_replace->time_stopped = ktime_get_real_seconds();
 	dev_replace->item_needs_writeback = 1;
 
 	/* replace old device with new one in mapping tree */
@@ -637,7 +632,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		btrfs_rm_dev_replace_blocked(fs_info);
 		if (tgt_device)
-			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+			btrfs_destroy_dev_replace_tgtdev(tgt_device);
 		btrfs_rm_dev_replace_unblocked(fs_info);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 
@@ -663,7 +658,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	tgt_device->commit_total_bytes = src_device->commit_total_bytes;
 	tgt_device->commit_bytes_used = src_device->bytes_used;
 
-	btrfs_assign_next_active_device(fs_info, src_device, tgt_device);
+	btrfs_assign_next_active_device(src_device, tgt_device);
 
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 	fs_info->fs_devices->rw_devices++;
@@ -672,11 +667,17 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 
 	btrfs_rm_dev_replace_blocked(fs_info);
 
-	btrfs_rm_dev_replace_remove_srcdev(fs_info, src_device);
+	btrfs_rm_dev_replace_remove_srcdev(src_device);
 
 	btrfs_rm_dev_replace_unblocked(fs_info);
 
 	/*
+	 * Increment dev_stats_ccnt so that btrfs_run_dev_stats() will
+	 * update on-disk dev stats value during commit transaction
+	 */
+	atomic_inc(&tgt_device->dev_stats_ccnt);
+
+	/*
 	 * this is again a consistent state where no dev_replace procedure
 	 * is running, the target device is part of the filesystem, the
 	 * source device is not part of the filesystem anymore and its 1st
@@ -807,7 +808,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		break;
 	}
 	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED;
-	dev_replace->time_stopped = get_seconds();
+	dev_replace->time_stopped = ktime_get_real_seconds();
 	dev_replace->item_needs_writeback = 1;
 	btrfs_dev_replace_write_unlock(dev_replace);
 	btrfs_scrub_cancel(fs_info);
@@ -826,7 +827,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		btrfs_dev_name(tgt_device));
 
 	if (tgt_device)
-		btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+		btrfs_destroy_dev_replace_tgtdev(tgt_device);
 
 leave:
 	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
@@ -848,7 +849,7 @@ void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 		dev_replace->replace_state =
 			BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED;
-		dev_replace->time_stopped = get_seconds();
+		dev_replace->time_stopped = ktime_get_real_seconds();
 		dev_replace->item_needs_writeback = 1;
 		btrfs_info(fs_info, "suspending dev_replace for unmount");
 		break;
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 39e9766d1cbd..a678b07fcf01 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -160,8 +160,8 @@ second_insert:
 	}
 	btrfs_release_path(path);
 
-	ret2 = btrfs_insert_delayed_dir_index(trans, root->fs_info, name,
-			name_len, dir, &disk_key, type, index);
+	ret2 = btrfs_insert_delayed_dir_index(trans, name, name_len, dir,
+					      &disk_key, type, index);
 out_free:
 	btrfs_free_path(path);
 	if (ret)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 205092dc9390..5124c15705ce 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -5,8 +5,6 @@
 
 #include <linux/fs.h>
 #include <linux/blkdev.h>
-#include <linux/scatterlist.h>
-#include <linux/swap.h>
 #include <linux/radix-tree.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
@@ -54,7 +52,6 @@
 
 static const struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
-static void free_fs_root(struct btrfs_root *root);
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				      struct btrfs_fs_info *fs_info);
@@ -108,12 +105,9 @@ void __cold btrfs_end_io_wq_exit(void)
  */
 struct async_submit_bio {
 	void *private_data;
-	struct btrfs_fs_info *fs_info;
 	struct bio *bio;
 	extent_submit_bio_start_t *submit_bio_start;
-	extent_submit_bio_done_t *submit_bio_done;
 	int mirror_num;
-	unsigned long bio_flags;
 	/*
 	 * bio_offset is optional, can be used if the pages in the bio
 	 * can't tell us where in the file the bio should go
@@ -212,7 +206,7 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
@@ -615,8 +609,8 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != eb->start) {
-		btrfs_err_rl(fs_info, "bad tree block start %llu %llu",
-			     found_start, eb->start);
+		btrfs_err_rl(fs_info, "bad tree block start, want %llu have %llu",
+			     eb->start, found_start);
 		ret = -EIO;
 		goto err;
 	}
@@ -628,8 +622,8 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	}
 	found_level = btrfs_header_level(eb);
 	if (found_level >= BTRFS_MAX_LEVEL) {
-		btrfs_err(fs_info, "bad tree block level %d",
-			  (int)btrfs_header_level(eb));
+		btrfs_err(fs_info, "bad tree block level %d on %llu",
+			  (int)btrfs_header_level(eb), eb->start);
 		ret = -EIO;
 		goto err;
 	}
@@ -779,7 +773,7 @@ static void run_one_async_done(struct btrfs_work *work)
 		return;
 	}
 
-	async->submit_bio_done(async->private_data, async->bio, async->mirror_num);
+	btrfs_submit_bio_done(async->private_data, async->bio, async->mirror_num);
 }
 
 static void run_one_async_free(struct btrfs_work *work)
@@ -793,8 +787,7 @@ static void run_one_async_free(struct btrfs_work *work)
 blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags,
 				 u64 bio_offset, void *private_data,
-				 extent_submit_bio_start_t *submit_bio_start,
-				 extent_submit_bio_done_t *submit_bio_done)
+				 extent_submit_bio_start_t *submit_bio_start)
 {
 	struct async_submit_bio *async;
 
@@ -803,16 +796,13 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 		return BLK_STS_RESOURCE;
 
 	async->private_data = private_data;
-	async->fs_info = fs_info;
 	async->bio = bio;
 	async->mirror_num = mirror_num;
 	async->submit_bio_start = submit_bio_start;
-	async->submit_bio_done = submit_bio_done;
 
 	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
 			run_one_async_done, run_one_async_free);
 
-	async->bio_flags = bio_flags;
 	async->bio_offset = bio_offset;
 
 	async->status = 0;
@@ -851,24 +841,6 @@ static blk_status_t btree_submit_bio_start(void *private_data, struct bio *bio,
 	return btree_csum_one_bio(bio);
 }
 
-static blk_status_t btree_submit_bio_done(void *private_data, struct bio *bio,
-					    int mirror_num)
-{
-	struct inode *inode = private_data;
-	blk_status_t ret;
-
-	/*
-	 * when we're called for a write, we're already in the async
-	 * submission context.  Just jump into btrfs_map_bio
-	 */
-	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), bio, mirror_num, 1);
-	if (ret) {
-		bio->bi_status = ret;
-		bio_endio(bio);
-	}
-	return ret;
-}
-
 static int check_async_write(struct btrfs_inode *bi)
 {
 	if (atomic_read(&bi->sync_writers))
@@ -911,8 +883,7 @@ static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio,
 		 */
 		ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0,
 					  bio_offset, private_data,
-					  btree_submit_bio_start,
-					  btree_submit_bio_done);
+					  btree_submit_bio_start);
 	}
 
 	if (ret)
@@ -961,8 +932,9 @@ static int btree_writepages(struct address_space *mapping,
 
 		fs_info = BTRFS_I(mapping->host)->root->fs_info;
 		/* this is a bit racy, but that's ok */
-		ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes,
-					     BTRFS_DIRTY_METADATA_THRESH);
+		ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
+					     BTRFS_DIRTY_METADATA_THRESH,
+					     fs_info->dirty_metadata_batch);
 		if (ret < 0)
 			return 0;
 	}
@@ -1181,7 +1153,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->highest_objectid = 0;
 	root->nr_delalloc_inodes = 0;
 	root->nr_ordered_extents = 0;
-	root->name = NULL;
 	root->inode_tree = RB_ROOT;
 	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
 	root->block_rsv = NULL;
@@ -1292,15 +1263,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(leaf, leaf->start);
-	btrfs_set_header_generation(leaf, trans->transid);
-	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(leaf, objectid);
 	root->node = leaf;
-
-	write_extent_buffer_fsid(leaf, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(leaf, fs_info->chunk_tree_uuid);
 	btrfs_mark_buffer_dirty(leaf);
 
 	root->commit_root = btrfs_root_node(root);
@@ -1374,14 +1337,8 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 		return ERR_CAST(leaf);
 	}
 
-	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(leaf, leaf->start);
-	btrfs_set_header_generation(leaf, trans->transid);
-	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(leaf, BTRFS_TREE_LOG_OBJECTID);
 	root->node = leaf;
 
-	write_extent_buffer_fsid(root->node, fs_info->fsid);
 	btrfs_mark_buffer_dirty(root->node);
 	btrfs_tree_unlock(root->node);
 	return root;
@@ -1546,7 +1503,7 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 
 	return 0;
 fail:
-	/* the caller is responsible to call free_fs_root */
+	/* The caller is responsible to call btrfs_free_fs_root */
 	return ret;
 }
 
@@ -1651,14 +1608,14 @@ again:
 	ret = btrfs_insert_fs_root(fs_info, root);
 	if (ret) {
 		if (ret == -EEXIST) {
-			free_fs_root(root);
+			btrfs_free_fs_root(root);
 			goto again;
 		}
 		goto fail;
 	}
 	return root;
 fail:
-	free_fs_root(root);
+	btrfs_free_fs_root(root);
 	return ERR_PTR(ret);
 }
 
@@ -1803,7 +1760,7 @@ static int transaction_kthread(void *arg)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_transaction *cur;
 	u64 transid;
-	unsigned long now;
+	time64_t now;
 	unsigned long delay;
 	bool cannot_commit;
 
@@ -1819,7 +1776,7 @@ static int transaction_kthread(void *arg)
 			goto sleep;
 		}
 
-		now = get_seconds();
+		now = ktime_get_seconds();
 		if (cur->state < TRANS_STATE_BLOCKED &&
 		    !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
 		    (now < cur->start_time ||
@@ -2196,8 +2153,6 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
 
 static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
 {
-	fs_info->dev_replace.lock_owner = 0;
-	atomic_set(&fs_info->dev_replace.nesting_level, 0);
 	mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
 	rwlock_init(&fs_info->dev_replace.lock);
 	atomic_set(&fs_info->dev_replace.read_locks, 0);
@@ -3075,6 +3030,13 @@ retry_root_backup:
 	fs_info->generation = generation;
 	fs_info->last_trans_committed = generation;
 
+	ret = btrfs_verify_dev_extents(fs_info);
+	if (ret) {
+		btrfs_err(fs_info,
+			  "failed to verify dev extents against chunks: %d",
+			  ret);
+		goto fail_block_groups;
+	}
 	ret = btrfs_recover_balance(fs_info);
 	if (ret) {
 		btrfs_err(fs_info, "failed to recover balance: %d", ret);
@@ -3875,10 +3837,10 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 		__btrfs_remove_free_space_cache(root->free_ino_pinned);
 	if (root->free_ino_ctl)
 		__btrfs_remove_free_space_cache(root->free_ino_ctl);
-	free_fs_root(root);
+	btrfs_free_fs_root(root);
 }
 
-static void free_fs_root(struct btrfs_root *root)
+void btrfs_free_fs_root(struct btrfs_root *root)
 {
 	iput(root->ino_cache_inode);
 	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
@@ -3890,15 +3852,9 @@ static void free_fs_root(struct btrfs_root *root)
 	free_extent_buffer(root->commit_root);
 	kfree(root->free_ino_ctl);
 	kfree(root->free_ino_pinned);
-	kfree(root->name);
 	btrfs_put_fs_root(root);
 }
 
-void btrfs_free_fs_root(struct btrfs_root *root)
-{
-	free_fs_root(root);
-}
-
 int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 {
 	u64 root_objectid = 0;
@@ -4104,10 +4060,10 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	/*
 	 * This is a fast path so only do this check if we have sanity tests
-	 * enabled.  Normal people shouldn't be marking dummy buffers as dirty
+	 * enabled.  Normal people shouldn't be using umapped buffers as dirty
 	 * outside of the sanity tests.
 	 */
-	if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &buf->bflags)))
+	if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags)))
 		return;
 #endif
 	root = BTRFS_I(buf->pages[0]->mapping->host)->root;
@@ -4150,8 +4106,9 @@ static void __btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info,
 	if (flush_delayed)
 		btrfs_balance_delayed_items(fs_info);
 
-	ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes,
-				     BTRFS_DIRTY_METADATA_THRESH);
+	ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
+				     BTRFS_DIRTY_METADATA_THRESH,
+				     fs_info->dirty_metadata_batch);
 	if (ret > 0) {
 		balance_dirty_pages_ratelimited(fs_info->btree_inode->i_mapping);
 	}
@@ -4563,21 +4520,11 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
-static struct btrfs_fs_info *btree_fs_info(void *private_data)
-{
-	struct inode *inode = private_data;
-	return btrfs_sb(inode->i_sb);
-}
-
 static const struct extent_io_ops btree_extent_io_ops = {
 	/* mandatory callbacks */
 	.submit_bio_hook = btree_submit_bio_hook,
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
-	/* note we're sharing with inode.c for the merge bio hook */
-	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_io_failed_hook = btree_io_failed_hook,
-	.set_range_writeback = btrfs_set_range_writeback,
-	.tree_fs_info = btree_fs_info,
 
 	/* optional callbacks */
 };
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 1a3d277b027b..4cccba22640f 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -120,8 +120,9 @@ blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			int mirror_num, unsigned long bio_flags,
 			u64 bio_offset, void *private_data,
-			extent_submit_bio_start_t *submit_bio_start,
-			extent_submit_bio_done_t *submit_bio_done);
+			extent_submit_bio_start_t *submit_bio_start);
+blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
+			  int mirror_num);
 int btrfs_write_tree_block(struct extent_buffer *buf);
 void btrfs_wait_tree_block_writeback(struct extent_buffer *buf);
 int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3d9fe58c0080..de6f75f5547b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -52,24 +52,21 @@ enum {
 };
 
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info,
-				struct btrfs_delayed_ref_node *node, u64 parent,
-				u64 root_objectid, u64 owner_objectid,
-				u64 owner_offset, int refs_to_drop,
-				struct btrfs_delayed_extent_op *extra_op);
+			       struct btrfs_delayed_ref_node *node, u64 parent,
+			       u64 root_objectid, u64 owner_objectid,
+			       u64 owner_offset, int refs_to_drop,
+			       struct btrfs_delayed_extent_op *extra_op);
 static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
 				    struct extent_buffer *leaf,
 				    struct btrfs_extent_item *ei);
 static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
-				      struct btrfs_fs_info *fs_info,
 				      u64 parent, u64 root_objectid,
 				      u64 flags, u64 owner, u64 offset,
 				      struct btrfs_key *ins, int ref_mod);
 static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 				     struct btrfs_delayed_ref_node *node,
 				     struct btrfs_delayed_extent_op *extent_op);
-static int do_chunk_alloc(struct btrfs_trans_handle *trans,
-			  struct btrfs_fs_info *fs_info, u64 flags,
+static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 			  int force);
 static int find_next_key(struct btrfs_path *path, int level,
 			 struct btrfs_key *key);
@@ -220,9 +217,9 @@ static int add_excluded_extent(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-static void free_excluded_extents(struct btrfs_fs_info *fs_info,
-				  struct btrfs_block_group_cache *cache)
+static void free_excluded_extents(struct btrfs_block_group_cache *cache)
 {
+	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 start, end;
 
 	start = cache->key.objectid;
@@ -234,9 +231,9 @@ static void free_excluded_extents(struct btrfs_fs_info *fs_info,
 			  start, end, EXTENT_UPTODATE);
 }
 
-static int exclude_super_stripes(struct btrfs_fs_info *fs_info,
-				 struct btrfs_block_group_cache *cache)
+static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 {
+	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 bytenr;
 	u64 *logical;
 	int stripe_len;
@@ -558,7 +555,7 @@ static noinline void caching_thread(struct btrfs_work *work)
 	caching_ctl->progress = (u64)-1;
 
 	up_read(&fs_info->commit_root_sem);
-	free_excluded_extents(fs_info, block_group);
+	free_excluded_extents(block_group);
 	mutex_unlock(&caching_ctl->mutex);
 
 	wake_up(&caching_ctl->wait);
@@ -666,7 +663,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 		wake_up(&caching_ctl->wait);
 		if (ret == 1) {
 			put_caching_control(caching_ctl);
-			free_excluded_extents(fs_info, cache);
+			free_excluded_extents(cache);
 			return 0;
 		}
 	} else {
@@ -758,7 +755,8 @@ static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes,
 
 	space_info = __find_space_info(fs_info, flags);
 	ASSERT(space_info);
-	percpu_counter_add(&space_info->total_bytes_pinned, num_bytes);
+	percpu_counter_add_batch(&space_info->total_bytes_pinned, num_bytes,
+		    BTRFS_TOTAL_BYTES_PINNED_BATCH);
 }
 
 /*
@@ -870,18 +868,16 @@ search_again:
 			num_refs = btrfs_extent_refs(leaf, ei);
 			extent_flags = btrfs_extent_flags(leaf, ei);
 		} else {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-			struct btrfs_extent_item_v0 *ei0;
-			BUG_ON(item_size != sizeof(*ei0));
-			ei0 = btrfs_item_ptr(leaf, path->slots[0],
-					     struct btrfs_extent_item_v0);
-			num_refs = btrfs_extent_refs_v0(leaf, ei0);
-			/* FIXME: this isn't correct for data */
-			extent_flags = BTRFS_BLOCK_FLAG_FULL_BACKREF;
-#else
-			BUG();
-#endif
+			ret = -EINVAL;
+			btrfs_print_v0_err(fs_info);
+			if (trans)
+				btrfs_abort_transaction(trans, ret);
+			else
+				btrfs_handle_fs_error(fs_info, ret, NULL);
+
+			goto out_free;
 		}
+
 		BUG_ON(num_refs == 0);
 	} else {
 		num_refs = 0;
@@ -1039,89 +1035,6 @@ out_free:
  * tree block info structure.
  */
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
-				  struct btrfs_path *path,
-				  u64 owner, u32 extra_size)
-{
-	struct btrfs_root *root = fs_info->extent_root;
-	struct btrfs_extent_item *item;
-	struct btrfs_extent_item_v0 *ei0;
-	struct btrfs_extent_ref_v0 *ref0;
-	struct btrfs_tree_block_info *bi;
-	struct extent_buffer *leaf;
-	struct btrfs_key key;
-	struct btrfs_key found_key;
-	u32 new_size = sizeof(*item);
-	u64 refs;
-	int ret;
-
-	leaf = path->nodes[0];
-	BUG_ON(btrfs_item_size_nr(leaf, path->slots[0]) != sizeof(*ei0));
-
-	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-	ei0 = btrfs_item_ptr(leaf, path->slots[0],
-			     struct btrfs_extent_item_v0);
-	refs = btrfs_extent_refs_v0(leaf, ei0);
-
-	if (owner == (u64)-1) {
-		while (1) {
-			if (path->slots[0] >= btrfs_header_nritems(leaf)) {
-				ret = btrfs_next_leaf(root, path);
-				if (ret < 0)
-					return ret;
-				BUG_ON(ret > 0); /* Corruption */
-				leaf = path->nodes[0];
-			}
-			btrfs_item_key_to_cpu(leaf, &found_key,
-					      path->slots[0]);
-			BUG_ON(key.objectid != found_key.objectid);
-			if (found_key.type != BTRFS_EXTENT_REF_V0_KEY) {
-				path->slots[0]++;
-				continue;
-			}
-			ref0 = btrfs_item_ptr(leaf, path->slots[0],
-					      struct btrfs_extent_ref_v0);
-			owner = btrfs_ref_objectid_v0(leaf, ref0);
-			break;
-		}
-	}
-	btrfs_release_path(path);
-
-	if (owner < BTRFS_FIRST_FREE_OBJECTID)
-		new_size += sizeof(*bi);
-
-	new_size -= sizeof(*ei0);
-	ret = btrfs_search_slot(trans, root, &key, path,
-				new_size + extra_size, 1);
-	if (ret < 0)
-		return ret;
-	BUG_ON(ret); /* Corruption */
-
-	btrfs_extend_item(fs_info, path, new_size);
-
-	leaf = path->nodes[0];
-	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
-	btrfs_set_extent_refs(leaf, item, refs);
-	/* FIXME: get real generation */
-	btrfs_set_extent_generation(leaf, item, 0);
-	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		btrfs_set_extent_flags(leaf, item,
-				       BTRFS_EXTENT_FLAG_TREE_BLOCK |
-				       BTRFS_BLOCK_FLAG_FULL_BACKREF);
-		bi = (struct btrfs_tree_block_info *)(item + 1);
-		/* FIXME: get first key of the block */
-		memzero_extent_buffer(leaf, (unsigned long)bi, sizeof(*bi));
-		btrfs_set_tree_block_level(leaf, bi, (int)owner);
-	} else {
-		btrfs_set_extent_flags(leaf, item, BTRFS_EXTENT_FLAG_DATA);
-	}
-	btrfs_mark_buffer_dirty(leaf);
-	return 0;
-}
-#endif
-
 /*
  * is_data == BTRFS_REF_TYPE_BLOCK, tree block type is required,
  * is_data == BTRFS_REF_TYPE_DATA, data type is requried,
@@ -1216,13 +1129,12 @@ static int match_extent_data_ref(struct extent_buffer *leaf,
 }
 
 static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   u64 bytenr, u64 parent,
 					   u64 root_objectid,
 					   u64 owner, u64 offset)
 {
-	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *root = trans->fs_info->extent_root;
 	struct btrfs_key key;
 	struct btrfs_extent_data_ref *ref;
 	struct extent_buffer *leaf;
@@ -1251,17 +1163,6 @@ again:
 	if (parent) {
 		if (!ret)
 			return 0;
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		key.type = BTRFS_EXTENT_REF_V0_KEY;
-		btrfs_release_path(path);
-		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-		if (ret < 0) {
-			err = ret;
-			goto fail;
-		}
-		if (!ret)
-			return 0;
-#endif
 		goto fail;
 	}
 
@@ -1304,13 +1205,12 @@ fail:
 }
 
 static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   u64 bytenr, u64 parent,
 					   u64 root_objectid, u64 owner,
 					   u64 offset, int refs_to_add)
 {
-	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *root = trans->fs_info->extent_root;
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
 	u32 size;
@@ -1384,7 +1284,6 @@ fail:
 }
 
 static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   int refs_to_drop, int *last_ref)
 {
@@ -1406,13 +1305,10 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 		ref2 = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_shared_data_ref);
 		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
-		struct btrfs_extent_ref_v0 *ref0;
-		ref0 = btrfs_item_ptr(leaf, path->slots[0],
-				      struct btrfs_extent_ref_v0);
-		num_refs = btrfs_ref_count_v0(leaf, ref0);
-#endif
+	} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
+		btrfs_print_v0_err(trans->fs_info);
+		btrfs_abort_transaction(trans, -EINVAL);
+		return -EINVAL;
 	} else {
 		BUG();
 	}
@@ -1421,21 +1317,13 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 	num_refs -= refs_to_drop;
 
 	if (num_refs == 0) {
-		ret = btrfs_del_item(trans, fs_info->extent_root, path);
+		ret = btrfs_del_item(trans, trans->fs_info->extent_root, path);
 		*last_ref = 1;
 	} else {
 		if (key.type == BTRFS_EXTENT_DATA_REF_KEY)
 			btrfs_set_extent_data_ref_count(leaf, ref1, num_refs);
 		else if (key.type == BTRFS_SHARED_DATA_REF_KEY)
 			btrfs_set_shared_data_ref_count(leaf, ref2, num_refs);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		else {
-			struct btrfs_extent_ref_v0 *ref0;
-			ref0 = btrfs_item_ptr(leaf, path->slots[0],
-					struct btrfs_extent_ref_v0);
-			btrfs_set_ref_count_v0(leaf, ref0, num_refs);
-		}
-#endif
 		btrfs_mark_buffer_dirty(leaf);
 	}
 	return ret;
@@ -1453,6 +1341,8 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+
+	BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
 	if (iref) {
 		/*
 		 * If type is invalid, we should have bailed out earlier than
@@ -1475,13 +1365,6 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 		ref2 = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_shared_data_ref);
 		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
-		struct btrfs_extent_ref_v0 *ref0;
-		ref0 = btrfs_item_ptr(leaf, path->slots[0],
-				      struct btrfs_extent_ref_v0);
-		num_refs = btrfs_ref_count_v0(leaf, ref0);
-#endif
 	} else {
 		WARN_ON(1);
 	}
@@ -1489,12 +1372,11 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 }
 
 static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
-					  struct btrfs_fs_info *fs_info,
 					  struct btrfs_path *path,
 					  u64 bytenr, u64 parent,
 					  u64 root_objectid)
 {
-	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *root = trans->fs_info->extent_root;
 	struct btrfs_key key;
 	int ret;
 
@@ -1510,20 +1392,10 @@ static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret > 0)
 		ret = -ENOENT;
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (ret == -ENOENT && parent) {
-		btrfs_release_path(path);
-		key.type = BTRFS_EXTENT_REF_V0_KEY;
-		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-		if (ret > 0)
-			ret = -ENOENT;
-	}
-#endif
 	return ret;
 }
 
 static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
-					  struct btrfs_fs_info *fs_info,
 					  struct btrfs_path *path,
 					  u64 bytenr, u64 parent,
 					  u64 root_objectid)
@@ -1540,7 +1412,7 @@ static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
 		key.offset = root_objectid;
 	}
 
-	ret = btrfs_insert_empty_item(trans, fs_info->extent_root,
+	ret = btrfs_insert_empty_item(trans, trans->fs_info->extent_root,
 				      path, &key, 0);
 	btrfs_release_path(path);
 	return ret;
@@ -1599,13 +1471,13 @@ static int find_next_key(struct btrfs_path *path, int level,
  */
 static noinline_for_stack
 int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref **ref_ret,
 				 u64 bytenr, u64 num_bytes,
 				 u64 parent, u64 root_objectid,
 				 u64 owner, u64 offset, int insert)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
@@ -1635,8 +1507,8 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
 		extra_size = -1;
 
 	/*
-	 * Owner is our parent level, so we can just add one to get the level
-	 * for the block we are interested in.
+	 * Owner is our level, so we can just add one to get the level for the
+	 * block we are interested in.
 	 */
 	if (skinny_metadata && owner < BTRFS_FIRST_FREE_OBJECTID) {
 		key.type = BTRFS_METADATA_ITEM_KEY;
@@ -1684,23 +1556,12 @@ again:
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		if (!insert) {
-			err = -ENOENT;
-			goto out;
-		}
-		ret = convert_extent_item_v0(trans, fs_info, path, owner,
-					     extra_size);
-		if (ret < 0) {
-			err = ret;
-			goto out;
-		}
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+	if (unlikely(item_size < sizeof(*ei))) {
+		err = -EINVAL;
+		btrfs_print_v0_err(fs_info);
+		btrfs_abort_transaction(trans, err);
+		goto out;
 	}
-#endif
-	BUG_ON(item_size < sizeof(*ei));
 
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	flags = btrfs_extent_flags(leaf, ei);
@@ -1727,7 +1588,7 @@ again:
 		iref = (struct btrfs_extent_inline_ref *)ptr;
 		type = btrfs_get_extent_inline_ref_type(leaf, iref, needed);
 		if (type == BTRFS_REF_TYPE_INVALID) {
-			err = -EINVAL;
+			err = -EUCLEAN;
 			goto out;
 		}
 
@@ -1863,7 +1724,6 @@ void setup_inline_extent_backref(struct btrfs_fs_info *fs_info,
 }
 
 static int lookup_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref **ref_ret,
 				 u64 bytenr, u64 num_bytes, u64 parent,
@@ -1871,9 +1731,9 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 {
 	int ret;
 
-	ret = lookup_inline_extent_backref(trans, fs_info, path, ref_ret,
-					   bytenr, num_bytes, parent,
-					   root_objectid, owner, offset, 0);
+	ret = lookup_inline_extent_backref(trans, path, ref_ret, bytenr,
+					   num_bytes, parent, root_objectid,
+					   owner, offset, 0);
 	if (ret != -ENOENT)
 		return ret;
 
@@ -1881,12 +1741,11 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 	*ref_ret = NULL;
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = lookup_tree_block_ref(trans, fs_info, path, bytenr,
-					    parent, root_objectid);
+		ret = lookup_tree_block_ref(trans, path, bytenr, parent,
+					    root_objectid);
 	} else {
-		ret = lookup_extent_data_ref(trans, fs_info, path, bytenr,
-					     parent, root_objectid, owner,
-					     offset);
+		ret = lookup_extent_data_ref(trans, path, bytenr, parent,
+					     root_objectid, owner, offset);
 	}
 	return ret;
 }
@@ -1895,14 +1754,14 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
  * helper to update/remove inline back ref
  */
 static noinline_for_stack
-void update_inline_extent_backref(struct btrfs_fs_info *fs_info,
-				  struct btrfs_path *path,
+void update_inline_extent_backref(struct btrfs_path *path,
 				  struct btrfs_extent_inline_ref *iref,
 				  int refs_to_mod,
 				  struct btrfs_delayed_extent_op *extent_op,
 				  int *last_ref)
 {
-	struct extent_buffer *leaf;
+	struct extent_buffer *leaf = path->nodes[0];
+	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_extent_item *ei;
 	struct btrfs_extent_data_ref *dref = NULL;
 	struct btrfs_shared_data_ref *sref = NULL;
@@ -1913,7 +1772,6 @@ void update_inline_extent_backref(struct btrfs_fs_info *fs_info,
 	int type;
 	u64 refs;
 
-	leaf = path->nodes[0];
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	refs = btrfs_extent_refs(leaf, ei);
 	WARN_ON(refs_to_mod < 0 && refs + refs_to_mod <= 0);
@@ -1965,7 +1823,6 @@ void update_inline_extent_backref(struct btrfs_fs_info *fs_info,
 
 static noinline_for_stack
 int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 u64 bytenr, u64 num_bytes, u64 parent,
 				 u64 root_objectid, u64 owner,
@@ -1975,15 +1832,15 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 	struct btrfs_extent_inline_ref *iref;
 	int ret;
 
-	ret = lookup_inline_extent_backref(trans, fs_info, path, &iref,
-					   bytenr, num_bytes, parent,
-					   root_objectid, owner, offset, 1);
+	ret = lookup_inline_extent_backref(trans, path, &iref, bytenr,
+					   num_bytes, parent, root_objectid,
+					   owner, offset, 1);
 	if (ret == 0) {
 		BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
-		update_inline_extent_backref(fs_info, path, iref,
-					     refs_to_add, extent_op, NULL);
+		update_inline_extent_backref(path, iref, refs_to_add,
+					     extent_op, NULL);
 	} else if (ret == -ENOENT) {
-		setup_inline_extent_backref(fs_info, path, iref, parent,
+		setup_inline_extent_backref(trans->fs_info, path, iref, parent,
 					    root_objectid, owner, offset,
 					    refs_to_add, extent_op);
 		ret = 0;
@@ -1992,7 +1849,6 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 }
 
 static int insert_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 u64 bytenr, u64 parent, u64 root_objectid,
 				 u64 owner, u64 offset, int refs_to_add)
@@ -2000,18 +1856,17 @@ static int insert_extent_backref(struct btrfs_trans_handle *trans,
 	int ret;
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
 		BUG_ON(refs_to_add != 1);
-		ret = insert_tree_block_ref(trans, fs_info, path, bytenr,
-					    parent, root_objectid);
+		ret = insert_tree_block_ref(trans, path, bytenr, parent,
+					    root_objectid);
 	} else {
-		ret = insert_extent_data_ref(trans, fs_info, path, bytenr,
-					     parent, root_objectid,
-					     owner, offset, refs_to_add);
+		ret = insert_extent_data_ref(trans, path, bytenr, parent,
+					     root_objectid, owner, offset,
+					     refs_to_add);
 	}
 	return ret;
 }
 
 static int remove_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref *iref,
 				 int refs_to_drop, int is_data, int *last_ref)
@@ -2020,14 +1875,14 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 
 	BUG_ON(!is_data && refs_to_drop != 1);
 	if (iref) {
-		update_inline_extent_backref(fs_info, path, iref,
-					     -refs_to_drop, NULL, last_ref);
+		update_inline_extent_backref(path, iref, -refs_to_drop, NULL,
+					     last_ref);
 	} else if (is_data) {
-		ret = remove_extent_data_ref(trans, fs_info, path, refs_to_drop,
+		ret = remove_extent_data_ref(trans, path, refs_to_drop,
 					     last_ref);
 	} else {
 		*last_ref = 1;
-		ret = btrfs_del_item(trans, fs_info->extent_root, path);
+		ret = btrfs_del_item(trans, trans->fs_info->extent_root, path);
 	}
 	return ret;
 }
@@ -2185,13 +2040,13 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			   owner, offset, BTRFS_ADD_DELAYED_REF);
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_tree_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, (int)owner,
 						 BTRFS_ADD_DELAYED_REF, NULL,
 						 &old_ref_mod, &new_ref_mod);
 	} else {
-		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_data_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, owner, offset,
 						 0, BTRFS_ADD_DELAYED_REF,
@@ -2207,8 +2062,41 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+/*
+ * __btrfs_inc_extent_ref - insert backreference for a given extent
+ *
+ * @trans:	    Handle of transaction
+ *
+ * @node:	    The delayed ref node used to get the bytenr/length for
+ *		    extent whose references are incremented.
+ *
+ * @parent:	    If this is a shared extent (BTRFS_SHARED_DATA_REF_KEY/
+ *		    BTRFS_SHARED_BLOCK_REF_KEY) then it holds the logical
+ *		    bytenr of the parent block. Since new extents are always
+ *		    created with indirect references, this will only be the case
+ *		    when relocating a shared extent. In that case, root_objectid
+ *		    will be BTRFS_TREE_RELOC_OBJECTID. Otheriwse, parent must
+ *		    be 0
+ *
+ * @root_objectid:  The id of the root where this modification has originated,
+ *		    this can be either one of the well-known metadata trees or
+ *		    the subvolume id which references this extent.
+ *
+ * @owner:	    For data extents it is the inode number of the owning file.
+ *		    For metadata extents this parameter holds the level in the
+ *		    tree of the extent.
+ *
+ * @offset:	    For metadata extents the offset is ignored and is currently
+ *		    always passed as 0. For data extents it is the fileoffset
+ *		    this extent belongs to.
+ *
+ * @refs_to_add     Number of references to add
+ *
+ * @extent_op       Pointer to a structure, holding information necessary when
+ *                  updating a tree block's flags
+ *
+ */
 static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_delayed_ref_node *node,
 				  u64 parent, u64 root_objectid,
 				  u64 owner, u64 offset, int refs_to_add,
@@ -2230,10 +2118,9 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* this will setup the path even if it fails to insert the back ref */
-	ret = insert_inline_extent_backref(trans, fs_info, path, bytenr,
-					   num_bytes, parent, root_objectid,
-					   owner, offset,
-					   refs_to_add, extent_op);
+	ret = insert_inline_extent_backref(trans, path, bytenr, num_bytes,
+					   parent, root_objectid, owner,
+					   offset, refs_to_add, extent_op);
 	if ((ret < 0 && ret != -EAGAIN) || !ret)
 		goto out;
 
@@ -2256,8 +2143,8 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* now insert the actual backref */
-	ret = insert_extent_backref(trans, fs_info, path, bytenr, parent,
-				    root_objectid, owner, offset, refs_to_add);
+	ret = insert_extent_backref(trans, path, bytenr, parent, root_objectid,
+				    owner, offset, refs_to_add);
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
 out:
@@ -2266,7 +2153,6 @@ out:
 }
 
 static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_node *node,
 				struct btrfs_delayed_extent_op *extent_op,
 				int insert_reserved)
@@ -2283,7 +2169,7 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 	ins.type = BTRFS_EXTENT_ITEM_KEY;
 
 	ref = btrfs_delayed_node_to_data_ref(node);
-	trace_run_delayed_data_ref(fs_info, node, ref, node->action);
+	trace_run_delayed_data_ref(trans->fs_info, node, ref, node->action);
 
 	if (node->type == BTRFS_SHARED_DATA_REF_KEY)
 		parent = ref->parent;
@@ -2292,17 +2178,16 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
 		if (extent_op)
 			flags |= extent_op->flags_to_set;
-		ret = alloc_reserved_file_extent(trans, fs_info,
-						 parent, ref_root, flags,
-						 ref->objectid, ref->offset,
-						 &ins, node->ref_mod);
+		ret = alloc_reserved_file_extent(trans, parent, ref_root,
+						 flags, ref->objectid,
+						 ref->offset, &ins,
+						 node->ref_mod);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
-		ret = __btrfs_inc_extent_ref(trans, fs_info, node, parent,
-					     ref_root, ref->objectid,
-					     ref->offset, node->ref_mod,
-					     extent_op);
+		ret = __btrfs_inc_extent_ref(trans, node, parent, ref_root,
+					     ref->objectid, ref->offset,
+					     node->ref_mod, extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
-		ret = __btrfs_free_extent(trans, fs_info, node, parent,
+		ret = __btrfs_free_extent(trans, node, parent,
 					  ref_root, ref->objectid,
 					  ref->offset, node->ref_mod,
 					  extent_op);
@@ -2331,10 +2216,10 @@ static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
 }
 
 static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_delayed_ref_head *head,
 				 struct btrfs_delayed_extent_op *extent_op)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_key key;
 	struct btrfs_path *path;
 	struct btrfs_extent_item *ei;
@@ -2400,18 +2285,14 @@ again:
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		ret = convert_extent_item_v0(trans, fs_info, path, (u64)-1, 0);
-		if (ret < 0) {
-			err = ret;
-			goto out;
-		}
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+
+	if (unlikely(item_size < sizeof(*ei))) {
+		err = -EINVAL;
+		btrfs_print_v0_err(fs_info);
+		btrfs_abort_transaction(trans, err);
+		goto out;
 	}
-#endif
-	BUG_ON(item_size < sizeof(*ei));
+
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	__run_delayed_extent_op(extent_op, leaf, ei);
 
@@ -2422,7 +2303,6 @@ out:
 }
 
 static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_node *node,
 				struct btrfs_delayed_extent_op *extent_op,
 				int insert_reserved)
@@ -2433,14 +2313,14 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	u64 ref_root = 0;
 
 	ref = btrfs_delayed_node_to_tree_ref(node);
-	trace_run_delayed_tree_ref(fs_info, node, ref, node->action);
+	trace_run_delayed_tree_ref(trans->fs_info, node, ref, node->action);
 
 	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY)
 		parent = ref->parent;
 	ref_root = ref->root;
 
 	if (node->ref_mod != 1) {
-		btrfs_err(fs_info,
+		btrfs_err(trans->fs_info,
 	"btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu",
 			  node->bytenr, node->ref_mod, node->action, ref_root,
 			  parent);
@@ -2450,13 +2330,10 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		BUG_ON(!extent_op || !extent_op->update_flags);
 		ret = alloc_reserved_tree_block(trans, node, extent_op);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
-		ret = __btrfs_inc_extent_ref(trans, fs_info, node,
-					     parent, ref_root,
-					     ref->level, 0, 1,
-					     extent_op);
+		ret = __btrfs_inc_extent_ref(trans, node, parent, ref_root,
+					     ref->level, 0, 1, extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
-		ret = __btrfs_free_extent(trans, fs_info, node,
-					  parent, ref_root,
+		ret = __btrfs_free_extent(trans, node, parent, ref_root,
 					  ref->level, 0, 1, extent_op);
 	} else {
 		BUG();
@@ -2466,7 +2343,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 
 /* helper function to actually process a single delayed ref entry */
 static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info,
 			       struct btrfs_delayed_ref_node *node,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int insert_reserved)
@@ -2475,18 +2351,18 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 
 	if (trans->aborted) {
 		if (insert_reserved)
-			btrfs_pin_extent(fs_info, node->bytenr,
+			btrfs_pin_extent(trans->fs_info, node->bytenr,
 					 node->num_bytes, 1);
 		return 0;
 	}
 
 	if (node->type == BTRFS_TREE_BLOCK_REF_KEY ||
 	    node->type == BTRFS_SHARED_BLOCK_REF_KEY)
-		ret = run_delayed_tree_ref(trans, fs_info, node, extent_op,
+		ret = run_delayed_tree_ref(trans, node, extent_op,
 					   insert_reserved);
 	else if (node->type == BTRFS_EXTENT_DATA_REF_KEY ||
 		 node->type == BTRFS_SHARED_DATA_REF_KEY)
-		ret = run_delayed_data_ref(trans, fs_info, node, extent_op,
+		ret = run_delayed_data_ref(trans, node, extent_op,
 					   insert_reserved);
 	else
 		BUG();
@@ -2528,7 +2404,6 @@ static void unselect_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_ref
 }
 
 static int cleanup_extent_op(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info,
 			     struct btrfs_delayed_ref_head *head)
 {
 	struct btrfs_delayed_extent_op *extent_op = head->extent_op;
@@ -2542,21 +2417,22 @@ static int cleanup_extent_op(struct btrfs_trans_handle *trans,
 		return 0;
 	}
 	spin_unlock(&head->lock);
-	ret = run_delayed_extent_op(trans, fs_info, head, extent_op);
+	ret = run_delayed_extent_op(trans, head, extent_op);
 	btrfs_free_delayed_extent_op(extent_op);
 	return ret ? ret : 1;
 }
 
 static int cleanup_ref_head(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
 			    struct btrfs_delayed_ref_head *head)
 {
+
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int ret;
 
 	delayed_refs = &trans->transaction->delayed_refs;
 
-	ret = cleanup_extent_op(trans, fs_info, head);
+	ret = cleanup_extent_op(trans, head);
 	if (ret < 0) {
 		unselect_delayed_ref_head(delayed_refs, head);
 		btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret);
@@ -2598,8 +2474,9 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 			flags = BTRFS_BLOCK_GROUP_METADATA;
 		space_info = __find_space_info(fs_info, flags);
 		ASSERT(space_info);
-		percpu_counter_add(&space_info->total_bytes_pinned,
-				   -head->num_bytes);
+		percpu_counter_add_batch(&space_info->total_bytes_pinned,
+				   -head->num_bytes,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH);
 
 		if (head->is_data) {
 			spin_lock(&delayed_refs->lock);
@@ -2705,7 +2582,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		 * up and move on to the next ref_head.
 		 */
 		if (!ref) {
-			ret = cleanup_ref_head(trans, fs_info, locked_ref);
+			ret = cleanup_ref_head(trans, locked_ref);
 			if (ret > 0 ) {
 				/* We dropped our lock, we need to loop. */
 				ret = 0;
@@ -2752,7 +2629,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		locked_ref->extent_op = NULL;
 		spin_unlock(&locked_ref->lock);
 
-		ret = run_one_delayed_ref(trans, fs_info, ref, extent_op,
+		ret = run_one_delayed_ref(trans, ref, extent_op,
 					  must_insert_reserved);
 
 		btrfs_free_delayed_extent_op(extent_op);
@@ -3227,12 +3104,6 @@ static noinline int check_committed_ref(struct btrfs_root *root,
 
 	ret = 1;
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		WARN_ON(item_size != sizeof(struct btrfs_extent_item_v0));
-		goto out;
-	}
-#endif
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 
 	if (item_size != sizeof(*ei) +
@@ -4060,11 +3931,7 @@ static void update_space_info(struct btrfs_fs_info *info, u64 flags,
 	struct btrfs_space_info *found;
 	int factor;
 
-	if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
-		     BTRFS_BLOCK_GROUP_RAID10))
-		factor = 2;
-	else
-		factor = 1;
+	factor = btrfs_bg_type_to_factor(flags);
 
 	found = __find_space_info(info, flags);
 	ASSERT(found);
@@ -4289,7 +4156,7 @@ again:
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 
-			ret = do_chunk_alloc(trans, fs_info, alloc_target,
+			ret = do_chunk_alloc(trans, alloc_target,
 					     CHUNK_ALLOC_NO_FORCE);
 			btrfs_end_transaction(trans);
 			if (ret < 0) {
@@ -4309,9 +4176,10 @@ again:
 		 * allocation, and no removed chunk in current transaction,
 		 * don't bother committing the transaction.
 		 */
-		have_pinned_space = percpu_counter_compare(
+		have_pinned_space = __percpu_counter_compare(
 			&data_sinfo->total_bytes_pinned,
-			used + bytes - data_sinfo->total_bytes);
+			used + bytes - data_sinfo->total_bytes,
+			BTRFS_TOTAL_BYTES_PINNED_BATCH);
 		spin_unlock(&data_sinfo->lock);
 
 		/* commit the current transaction and try again */
@@ -4358,7 +4226,7 @@ commit_trans:
 				      data_sinfo->flags, bytes, 1);
 	spin_unlock(&data_sinfo->lock);
 
-	return ret;
+	return 0;
 }
 
 int btrfs_check_data_free_space(struct inode *inode,
@@ -4511,9 +4379,9 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
  * for allocating a chunk, otherwise if it's false, reserve space necessary for
  * removing a chunk.
  */
-void check_system_chunk(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 type)
+void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_space_info *info;
 	u64 left;
 	u64 thresh;
@@ -4552,7 +4420,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
 		 * the paths we visit in the chunk tree (they were already COWed
 		 * or created in the current transaction for example).
 		 */
-		ret = btrfs_alloc_chunk(trans, fs_info, flags);
+		ret = btrfs_alloc_chunk(trans, flags);
 	}
 
 	if (!ret) {
@@ -4573,11 +4441,13 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
  *    - return 1 if it successfully allocates a chunk,
  *    - return errors including -ENOSPC otherwise.
  */
-static int do_chunk_alloc(struct btrfs_trans_handle *trans,
-			  struct btrfs_fs_info *fs_info, u64 flags, int force)
+static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
+			  int force)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_space_info *space_info;
-	int wait_for_alloc = 0;
+	bool wait_for_alloc = false;
+	bool should_alloc = false;
 	int ret = 0;
 
 	/* Don't re-enter if we're already allocating a chunk */
@@ -4587,45 +4457,44 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 	space_info = __find_space_info(fs_info, flags);
 	ASSERT(space_info);
 
-again:
-	spin_lock(&space_info->lock);
-	if (force < space_info->force_alloc)
-		force = space_info->force_alloc;
-	if (space_info->full) {
-		if (should_alloc_chunk(fs_info, space_info, force))
-			ret = -ENOSPC;
-		else
-			ret = 0;
-		spin_unlock(&space_info->lock);
-		return ret;
-	}
-
-	if (!should_alloc_chunk(fs_info, space_info, force)) {
-		spin_unlock(&space_info->lock);
-		return 0;
-	} else if (space_info->chunk_alloc) {
-		wait_for_alloc = 1;
-	} else {
-		space_info->chunk_alloc = 1;
-	}
-
-	spin_unlock(&space_info->lock);
-
-	mutex_lock(&fs_info->chunk_mutex);
+	do {
+		spin_lock(&space_info->lock);
+		if (force < space_info->force_alloc)
+			force = space_info->force_alloc;
+		should_alloc = should_alloc_chunk(fs_info, space_info, force);
+		if (space_info->full) {
+			/* No more free physical space */
+			if (should_alloc)
+				ret = -ENOSPC;
+			else
+				ret = 0;
+			spin_unlock(&space_info->lock);
+			return ret;
+		} else if (!should_alloc) {
+			spin_unlock(&space_info->lock);
+			return 0;
+		} else if (space_info->chunk_alloc) {
+			/*
+			 * Someone is already allocating, so we need to block
+			 * until this someone is finished and then loop to
+			 * recheck if we should continue with our allocation
+			 * attempt.
+			 */
+			wait_for_alloc = true;
+			spin_unlock(&space_info->lock);
+			mutex_lock(&fs_info->chunk_mutex);
+			mutex_unlock(&fs_info->chunk_mutex);
+		} else {
+			/* Proceed with allocation */
+			space_info->chunk_alloc = 1;
+			wait_for_alloc = false;
+			spin_unlock(&space_info->lock);
+		}
 
-	/*
-	 * The chunk_mutex is held throughout the entirety of a chunk
-	 * allocation, so once we've acquired the chunk_mutex we know that the
-	 * other guy is done and we need to recheck and see if we should
-	 * allocate.
-	 */
-	if (wait_for_alloc) {
-		mutex_unlock(&fs_info->chunk_mutex);
-		wait_for_alloc = 0;
 		cond_resched();
-		goto again;
-	}
+	} while (wait_for_alloc);
 
+	mutex_lock(&fs_info->chunk_mutex);
 	trans->allocating_chunk = true;
 
 	/*
@@ -4651,9 +4520,9 @@ again:
 	 * Check if we have enough space in SYSTEM chunk because we may need
 	 * to update devices.
 	 */
-	check_system_chunk(trans, fs_info, flags);
+	check_system_chunk(trans, flags);
 
-	ret = btrfs_alloc_chunk(trans, fs_info, flags);
+	ret = btrfs_alloc_chunk(trans, flags);
 	trans->allocating_chunk = false;
 
 	spin_lock(&space_info->lock);
@@ -4703,6 +4572,7 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 	u64 space_size;
 	u64 avail;
 	u64 used;
+	int factor;
 
 	/* Don't overcommit when in mixed mode. */
 	if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
@@ -4737,10 +4607,8 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 	 * doesn't include the parity drive, so we don't have to
 	 * change the math
 	 */
-	if (profile & (BTRFS_BLOCK_GROUP_DUP |
-		       BTRFS_BLOCK_GROUP_RAID1 |
-		       BTRFS_BLOCK_GROUP_RAID10))
-		avail >>= 1;
+	factor = btrfs_bg_type_to_factor(profile);
+	avail = div_u64(avail, factor);
 
 	/*
 	 * If we aren't flushing all things, let us overcommit up to
@@ -4912,8 +4780,9 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 		return 0;
 
 	/* See if there is enough pinned space to make this reservation */
-	if (percpu_counter_compare(&space_info->total_bytes_pinned,
-				   bytes) >= 0)
+	if (__percpu_counter_compare(&space_info->total_bytes_pinned,
+				   bytes,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH) >= 0)
 		goto commit;
 
 	/*
@@ -4930,8 +4799,9 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 		bytes -= delayed_rsv->size;
 	spin_unlock(&delayed_rsv->lock);
 
-	if (percpu_counter_compare(&space_info->total_bytes_pinned,
-				   bytes) < 0) {
+	if (__percpu_counter_compare(&space_info->total_bytes_pinned,
+				   bytes,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH) < 0) {
 		return -ENOSPC;
 	}
 
@@ -4984,7 +4854,7 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 			ret = PTR_ERR(trans);
 			break;
 		}
-		ret = do_chunk_alloc(trans, fs_info,
+		ret = do_chunk_alloc(trans,
 				     btrfs_metadata_alloc_profile(fs_info),
 				     CHUNK_ALLOC_NO_FORCE);
 		btrfs_end_transaction(trans);
@@ -5659,11 +5529,6 @@ void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
 	kfree(rsv);
 }
 
-void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv)
-{
-	kfree(rsv);
-}
-
 int btrfs_block_rsv_add(struct btrfs_root *root,
 			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
 			enum btrfs_reserve_flush_enum flush)
@@ -6019,7 +5884,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	unsigned nr_extents;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
 	int ret = 0;
@@ -6092,7 +5957,7 @@ out_fail:
 void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 				     bool qgroup_free)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 	spin_lock(&inode->lock);
@@ -6121,7 +5986,7 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
 				    bool qgroup_free)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	unsigned num_extents;
 
 	spin_lock(&inode->lock);
@@ -6219,12 +6084,8 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		cache = btrfs_lookup_block_group(info, bytenr);
 		if (!cache)
 			return -ENOENT;
-		if (cache->flags & (BTRFS_BLOCK_GROUP_DUP |
-				    BTRFS_BLOCK_GROUP_RAID1 |
-				    BTRFS_BLOCK_GROUP_RAID10))
-			factor = 2;
-		else
-			factor = 1;
+		factor = btrfs_bg_type_to_factor(cache->flags);
+
 		/*
 		 * If this block group has free space cache written out, we
 		 * need to make sure to load it if we are removing space.  This
@@ -6268,8 +6129,9 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 			trace_btrfs_space_reservation(info, "pinned",
 						      cache->space_info->flags,
 						      num_bytes, 1);
-			percpu_counter_add(&cache->space_info->total_bytes_pinned,
-					   num_bytes);
+			percpu_counter_add_batch(&cache->space_info->total_bytes_pinned,
+					   num_bytes,
+					   BTRFS_TOTAL_BYTES_PINNED_BATCH);
 			set_extent_dirty(info->pinned_extents,
 					 bytenr, bytenr + num_bytes - 1,
 					 GFP_NOFS | __GFP_NOFAIL);
@@ -6279,7 +6141,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		if (list_empty(&cache->dirty_list)) {
 			list_add_tail(&cache->dirty_list,
 				      &trans->transaction->dirty_bgs);
-				trans->transaction->num_dirty_bgs++;
+			trans->transaction->num_dirty_bgs++;
 			btrfs_get_block_group(cache);
 		}
 		spin_unlock(&trans->transaction->dirty_bgs_lock);
@@ -6290,16 +6152,8 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		 * dirty list to avoid races between cleaner kthread and space
 		 * cache writeout.
 		 */
-		if (!alloc && old_val == 0) {
-			spin_lock(&info->unused_bgs_lock);
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &info->unused_bgs);
-			}
-			spin_unlock(&info->unused_bgs_lock);
-		}
+		if (!alloc && old_val == 0)
+			btrfs_mark_bg_unused(cache);
 
 		btrfs_put_block_group(cache);
 		total -= num_bytes;
@@ -6347,7 +6201,8 @@ static int pin_down_extent(struct btrfs_fs_info *fs_info,
 
 	trace_btrfs_space_reservation(fs_info, "pinned",
 				      cache->space_info->flags, num_bytes, 1);
-	percpu_counter_add(&cache->space_info->total_bytes_pinned, num_bytes);
+	percpu_counter_add_batch(&cache->space_info->total_bytes_pinned,
+		    num_bytes, BTRFS_TOTAL_BYTES_PINNED_BATCH);
 	set_extent_dirty(fs_info->pinned_extents, bytenr,
 			 bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL);
 	return 0;
@@ -6711,7 +6566,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 		trace_btrfs_space_reservation(fs_info, "pinned",
 					      space_info->flags, len, 0);
 		space_info->max_extent_size = 0;
-		percpu_counter_add(&space_info->total_bytes_pinned, -len);
+		percpu_counter_add_batch(&space_info->total_bytes_pinned,
+			    -len, BTRFS_TOTAL_BYTES_PINNED_BATCH);
 		if (cache->ro) {
 			space_info->bytes_readonly += len;
 			readonly = true;
@@ -6815,12 +6671,12 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 }
 
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *info,
-				struct btrfs_delayed_ref_node *node, u64 parent,
-				u64 root_objectid, u64 owner_objectid,
-				u64 owner_offset, int refs_to_drop,
-				struct btrfs_delayed_extent_op *extent_op)
+			       struct btrfs_delayed_ref_node *node, u64 parent,
+			       u64 root_objectid, u64 owner_objectid,
+			       u64 owner_offset, int refs_to_drop,
+			       struct btrfs_delayed_extent_op *extent_op)
 {
+	struct btrfs_fs_info *info = trans->fs_info;
 	struct btrfs_key key;
 	struct btrfs_path *path;
 	struct btrfs_root *extent_root = info->extent_root;
@@ -6852,9 +6708,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	if (is_data)
 		skinny_metadata = false;
 
-	ret = lookup_extent_backref(trans, info, path, &iref,
-				    bytenr, num_bytes, parent,
-				    root_objectid, owner_objectid,
+	ret = lookup_extent_backref(trans, path, &iref, bytenr, num_bytes,
+				    parent, root_objectid, owner_objectid,
 				    owner_offset);
 	if (ret == 0) {
 		extent_slot = path->slots[0];
@@ -6877,14 +6732,10 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				break;
 			extent_slot--;
 		}
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		item_size = btrfs_item_size_nr(path->nodes[0], extent_slot);
-		if (found_extent && item_size < sizeof(*ei))
-			found_extent = 0;
-#endif
+
 		if (!found_extent) {
 			BUG_ON(iref);
-			ret = remove_extent_backref(trans, info, path, NULL,
+			ret = remove_extent_backref(trans, path, NULL,
 						    refs_to_drop,
 						    is_data, &last_ref);
 			if (ret) {
@@ -6957,42 +6808,12 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, extent_slot);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		BUG_ON(found_extent || extent_slot != path->slots[0]);
-		ret = convert_extent_item_v0(trans, info, path, owner_objectid,
-					     0);
-		if (ret < 0) {
-			btrfs_abort_transaction(trans, ret);
-			goto out;
-		}
-
-		btrfs_release_path(path);
-		path->leave_spinning = 1;
-
-		key.objectid = bytenr;
-		key.type = BTRFS_EXTENT_ITEM_KEY;
-		key.offset = num_bytes;
-
-		ret = btrfs_search_slot(trans, extent_root, &key, path,
-					-1, 1);
-		if (ret) {
-			btrfs_err(info,
-				  "umm, got %d back from search, was looking for %llu",
-				ret, bytenr);
-			btrfs_print_leaf(path->nodes[0]);
-		}
-		if (ret < 0) {
-			btrfs_abort_transaction(trans, ret);
-			goto out;
-		}
-
-		extent_slot = path->slots[0];
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, extent_slot);
+	if (unlikely(item_size < sizeof(*ei))) {
+		ret = -EINVAL;
+		btrfs_print_v0_err(info);
+		btrfs_abort_transaction(trans, ret);
+		goto out;
 	}
-#endif
-	BUG_ON(item_size < sizeof(*ei));
 	ei = btrfs_item_ptr(leaf, extent_slot,
 			    struct btrfs_extent_item);
 	if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID &&
@@ -7028,9 +6849,9 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			btrfs_mark_buffer_dirty(leaf);
 		}
 		if (found_extent) {
-			ret = remove_extent_backref(trans, info, path,
-						    iref, refs_to_drop,
-						    is_data, &last_ref);
+			ret = remove_extent_backref(trans, path, iref,
+						    refs_to_drop, is_data,
+						    &last_ref);
 			if (ret) {
 				btrfs_abort_transaction(trans, ret);
 				goto out;
@@ -7172,7 +6993,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 				   root->root_key.objectid,
 				   btrfs_header_level(buf), 0,
 				   BTRFS_DROP_DELAYED_REF);
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, buf->start,
+		ret = btrfs_add_delayed_tree_ref(trans, buf->start,
 						 buf->len, parent,
 						 root->root_key.objectid,
 						 btrfs_header_level(buf),
@@ -7251,13 +7072,13 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		old_ref_mod = new_ref_mod = 0;
 		ret = 0;
 	} else if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_tree_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, (int)owner,
 						 BTRFS_DROP_DELAYED_REF, NULL,
 						 &old_ref_mod, &new_ref_mod);
 	} else {
-		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_data_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, owner, offset,
 						 0, BTRFS_DROP_DELAYED_REF,
@@ -7534,7 +7355,7 @@ search:
 		 * for the proper type.
 		 */
 		if (!block_group_bits(block_group, flags)) {
-		    u64 extra = BTRFS_BLOCK_GROUP_DUP |
+			u64 extra = BTRFS_BLOCK_GROUP_DUP |
 				BTRFS_BLOCK_GROUP_RAID1 |
 				BTRFS_BLOCK_GROUP_RAID5 |
 				BTRFS_BLOCK_GROUP_RAID6 |
@@ -7738,7 +7559,7 @@ unclustered_alloc:
 			goto loop;
 		}
 checks:
-		search_start = ALIGN(offset, fs_info->stripesize);
+		search_start = round_up(offset, fs_info->stripesize);
 
 		/* move on to the next group */
 		if (search_start + num_bytes >
@@ -7750,7 +7571,6 @@ checks:
 		if (offset < search_start)
 			btrfs_add_free_space(block_group, offset,
 					     search_start - offset);
-		BUG_ON(offset > search_start);
 
 		ret = btrfs_add_reserved_bytes(block_group, ram_bytes,
 				num_bytes, delalloc);
@@ -7826,8 +7646,7 @@ loop:
 				goto out;
 			}
 
-			ret = do_chunk_alloc(trans, fs_info, flags,
-					     CHUNK_ALLOC_FORCE);
+			ret = do_chunk_alloc(trans, flags, CHUNK_ALLOC_FORCE);
 
 			/*
 			 * If we can't allocate a new chunk we've already looped
@@ -8053,11 +7872,11 @@ int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
 }
 
 static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
-				      struct btrfs_fs_info *fs_info,
 				      u64 parent, u64 root_objectid,
 				      u64 flags, u64 owner, u64 offset,
 				      struct btrfs_key *ins, int ref_mod)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_extent_item *extent_item;
 	struct btrfs_extent_inline_ref *iref;
@@ -8231,7 +8050,6 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 				     u64 offset, u64 ram_bytes,
 				     struct btrfs_key *ins)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
 
 	BUG_ON(root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);
@@ -8240,7 +8058,7 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 			   root->root_key.objectid, owner, offset,
 			   BTRFS_ADD_DELAYED_EXTENT);
 
-	ret = btrfs_add_delayed_data_ref(fs_info, trans, ins->objectid,
+	ret = btrfs_add_delayed_data_ref(trans, ins->objectid,
 					 ins->offset, 0,
 					 root->root_key.objectid, owner,
 					 offset, ram_bytes,
@@ -8254,10 +8072,10 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
  * space cache bits as well
  */
 int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   u64 root_objectid, u64 owner, u64 offset,
 				   struct btrfs_key *ins)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_block_group_cache *block_group;
 	struct btrfs_space_info *space_info;
@@ -8285,15 +8103,15 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 	spin_unlock(&block_group->lock);
 	spin_unlock(&space_info->lock);
 
-	ret = alloc_reserved_file_extent(trans, fs_info, 0, root_objectid,
-					 0, owner, offset, ins, 1);
+	ret = alloc_reserved_file_extent(trans, 0, root_objectid, 0, owner,
+					 offset, ins, 1);
 	btrfs_put_block_group(block_group);
 	return ret;
 }
 
 static struct extent_buffer *
 btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		      u64 bytenr, int level)
+		      u64 bytenr, int level, u64 owner)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *buf;
@@ -8302,7 +8120,6 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	if (IS_ERR(buf))
 		return buf;
 
-	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
 	clean_tree_block(fs_info, buf);
@@ -8311,6 +8128,14 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	btrfs_set_lock_blocking(buf);
 	set_extent_buffer_uptodate(buf);
 
+	memzero_extent_buffer(buf, 0, sizeof(struct btrfs_header));
+	btrfs_set_header_level(buf, level);
+	btrfs_set_header_bytenr(buf, buf->start);
+	btrfs_set_header_generation(buf, trans->transid);
+	btrfs_set_header_backref_rev(buf, BTRFS_MIXED_BACKREF_REV);
+	btrfs_set_header_owner(buf, owner);
+	write_extent_buffer_fsid(buf, fs_info->fsid);
+	write_extent_buffer_chunk_tree_uuid(buf, fs_info->chunk_tree_uuid);
 	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
 		buf->log_index = root->log_transid % 2;
 		/*
@@ -8419,7 +8244,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	if (btrfs_is_testing(fs_info)) {
 		buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
-					    level);
+					    level, root_objectid);
 		if (!IS_ERR(buf))
 			root->alloc_bytenr += blocksize;
 		return buf;
@@ -8435,7 +8260,8 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out_unuse;
 
-	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level);
+	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level,
+				    root_objectid);
 	if (IS_ERR(buf)) {
 		ret = PTR_ERR(buf);
 		goto out_free_reserved;
@@ -8467,7 +8293,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		btrfs_ref_tree_mod(root, ins.objectid, ins.offset, parent,
 				   root_objectid, level, 0,
 				   BTRFS_ADD_DELAYED_EXTENT);
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, ins.objectid,
+		ret = btrfs_add_delayed_tree_ref(trans, ins.objectid,
 						 ins.offset, parent,
 						 root_objectid, level,
 						 BTRFS_ADD_DELAYED_EXTENT,
@@ -8499,7 +8325,6 @@ struct walk_control {
 	int keep_locks;
 	int reada_slot;
 	int reada_count;
-	int for_reloc;
 };
 
 #define DROP_REFERENCE	1
@@ -8819,7 +8644,7 @@ skip:
 		}
 
 		if (need_account) {
-			ret = btrfs_qgroup_trace_subtree(trans, root, next,
+			ret = btrfs_qgroup_trace_subtree(trans, next,
 							 generation, level - 1);
 			if (ret) {
 				btrfs_err_rl(fs_info,
@@ -8919,7 +8744,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			else
 				ret = btrfs_dec_ref(trans, root, eb, 0);
 			BUG_ON(ret); /* -ENOMEM */
-			ret = btrfs_qgroup_trace_leaf_items(trans, fs_info, eb);
+			ret = btrfs_qgroup_trace_leaf_items(trans, eb);
 			if (ret) {
 				btrfs_err_rl(fs_info,
 					     "error %d accounting leaf items. Quota is out of sync, rescan required.",
@@ -9136,7 +8961,6 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	wc->stage = DROP_REFERENCE;
 	wc->update_ref = update_ref;
 	wc->keep_locks = 0;
-	wc->for_reloc = for_reloc;
 	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info);
 
 	while (1) {
@@ -9199,7 +9023,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	if (err)
 		goto out_end_trans;
 
-	ret = btrfs_del_root(trans, fs_info, &root->root_key);
+	ret = btrfs_del_root(trans, &root->root_key);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		err = ret;
@@ -9302,7 +9126,6 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	wc->stage = DROP_REFERENCE;
 	wc->update_ref = 0;
 	wc->keep_locks = 1;
-	wc->for_reloc = 1;
 	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info);
 
 	while (1) {
@@ -9417,10 +9240,10 @@ out:
 	return ret;
 }
 
-int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info,
-			     struct btrfs_block_group_cache *cache)
+int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache)
 
 {
+	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_trans_handle *trans;
 	u64 alloc_flags;
 	int ret;
@@ -9454,7 +9277,7 @@ again:
 	 */
 	alloc_flags = update_block_group_flags(fs_info, cache->flags);
 	if (alloc_flags != cache->flags) {
-		ret = do_chunk_alloc(trans, fs_info, alloc_flags,
+		ret = do_chunk_alloc(trans, alloc_flags,
 				     CHUNK_ALLOC_FORCE);
 		/*
 		 * ENOSPC is allowed here, we may have enough space
@@ -9471,8 +9294,7 @@ again:
 	if (!ret)
 		goto out;
 	alloc_flags = get_alloc_profile(fs_info, cache->space_info->flags);
-	ret = do_chunk_alloc(trans, fs_info, alloc_flags,
-			     CHUNK_ALLOC_FORCE);
+	ret = do_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
 	if (ret < 0)
 		goto out;
 	ret = inc_block_group_ro(cache, 0);
@@ -9480,7 +9302,7 @@ out:
 	if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
 		alloc_flags = update_block_group_flags(fs_info, cache->flags);
 		mutex_lock(&fs_info->chunk_mutex);
-		check_system_chunk(trans, fs_info, alloc_flags);
+		check_system_chunk(trans, alloc_flags);
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
 	mutex_unlock(&fs_info->ro_block_group_mutex);
@@ -9489,12 +9311,11 @@ out:
 	return ret;
 }
 
-int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info, u64 type)
+int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type)
 {
-	u64 alloc_flags = get_alloc_profile(fs_info, type);
+	u64 alloc_flags = get_alloc_profile(trans->fs_info, type);
 
-	return do_chunk_alloc(trans, fs_info, alloc_flags, CHUNK_ALLOC_FORCE);
+	return do_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
 }
 
 /*
@@ -9520,13 +9341,7 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
 			continue;
 		}
 
-		if (block_group->flags & (BTRFS_BLOCK_GROUP_RAID1 |
-					  BTRFS_BLOCK_GROUP_RAID10 |
-					  BTRFS_BLOCK_GROUP_DUP))
-			factor = 2;
-		else
-			factor = 1;
-
+		factor = btrfs_bg_type_to_factor(block_group->flags);
 		free_bytes += (block_group->key.offset -
 			       btrfs_block_group_used(&block_group->item)) *
 			       factor;
@@ -9717,6 +9532,8 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
 	int ret = 0;
 	struct btrfs_key found_key;
 	struct extent_buffer *leaf;
+	struct btrfs_block_group_item bg;
+	u64 flags;
 	int slot;
 
 	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
@@ -9751,8 +9568,32 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
 			"logical %llu len %llu found bg but no related chunk",
 					  found_key.objectid, found_key.offset);
 				ret = -ENOENT;
+			} else if (em->start != found_key.objectid ||
+				   em->len != found_key.offset) {
+				btrfs_err(fs_info,
+		"block group %llu len %llu mismatch with chunk %llu len %llu",
+					  found_key.objectid, found_key.offset,
+					  em->start, em->len);
+				ret = -EUCLEAN;
 			} else {
-				ret = 0;
+				read_extent_buffer(leaf, &bg,
+					btrfs_item_ptr_offset(leaf, slot),
+					sizeof(bg));
+				flags = btrfs_block_group_flags(&bg) &
+					BTRFS_BLOCK_GROUP_TYPE_MASK;
+
+				if (flags != (em->map_lookup->type &
+					      BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+					btrfs_err(fs_info,
+"block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx",
+						found_key.objectid,
+						found_key.offset, flags,
+						(BTRFS_BLOCK_GROUP_TYPE_MASK &
+						 em->map_lookup->type));
+					ret = -EUCLEAN;
+				} else {
+					ret = 0;
+				}
 			}
 			free_extent_map(em);
 			goto out;
@@ -9847,7 +9688,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		 */
 		if (block_group->cached == BTRFS_CACHE_NO ||
 		    block_group->cached == BTRFS_CACHE_ERROR)
-			free_excluded_extents(info, block_group);
+			free_excluded_extents(block_group);
 
 		btrfs_remove_free_space_cache(block_group);
 		ASSERT(block_group->cached != BTRFS_CACHE_STARTED);
@@ -10003,6 +9844,62 @@ btrfs_create_block_group_cache(struct btrfs_fs_info *fs_info,
 	return cache;
 }
 
+
+/*
+ * Iterate all chunks and verify that each of them has the corresponding block
+ * group
+ */
+static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+	struct extent_map *em;
+	struct btrfs_block_group_cache *bg;
+	u64 start = 0;
+	int ret = 0;
+
+	while (1) {
+		read_lock(&map_tree->map_tree.lock);
+		/*
+		 * lookup_extent_mapping will return the first extent map
+		 * intersecting the range, so setting @len to 1 is enough to
+		 * get the first chunk.
+		 */
+		em = lookup_extent_mapping(&map_tree->map_tree, start, 1);
+		read_unlock(&map_tree->map_tree.lock);
+		if (!em)
+			break;
+
+		bg = btrfs_lookup_block_group(fs_info, em->start);
+		if (!bg) {
+			btrfs_err(fs_info,
+	"chunk start=%llu len=%llu doesn't have corresponding block group",
+				     em->start, em->len);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			break;
+		}
+		if (bg->key.objectid != em->start ||
+		    bg->key.offset != em->len ||
+		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
+		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+			btrfs_err(fs_info,
+"chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
+				em->start, em->len,
+				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
+				bg->key.objectid, bg->key.offset,
+				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			btrfs_put_block_group(bg);
+			break;
+		}
+		start = em->start + em->len;
+		free_extent_map(em);
+		btrfs_put_block_group(bg);
+	}
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_path *path;
@@ -10089,13 +9986,13 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		 * info has super bytes accounted for, otherwise we'll think
 		 * we have more space than we actually do.
 		 */
-		ret = exclude_super_stripes(info, cache);
+		ret = exclude_super_stripes(cache);
 		if (ret) {
 			/*
 			 * We may have excluded something, so call this just in
 			 * case.
 			 */
-			free_excluded_extents(info, cache);
+			free_excluded_extents(cache);
 			btrfs_put_block_group(cache);
 			goto error;
 		}
@@ -10110,14 +10007,14 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		if (found_key.offset == btrfs_block_group_used(&cache->item)) {
 			cache->last_byte_to_unpin = (u64)-1;
 			cache->cached = BTRFS_CACHE_FINISHED;
-			free_excluded_extents(info, cache);
+			free_excluded_extents(cache);
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
 			cache->last_byte_to_unpin = (u64)-1;
 			cache->cached = BTRFS_CACHE_FINISHED;
 			add_new_free_space(cache, found_key.objectid,
 					   found_key.objectid +
 					   found_key.offset);
-			free_excluded_extents(info, cache);
+			free_excluded_extents(cache);
 		}
 
 		ret = btrfs_add_block_group_cache(info, cache);
@@ -10140,15 +10037,8 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		if (btrfs_chunk_readonly(info, cache->key.objectid)) {
 			inc_block_group_ro(cache, 1);
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
-			spin_lock(&info->unused_bgs_lock);
-			/* Should always be true but just in case. */
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &info->unused_bgs);
-			}
-			spin_unlock(&info->unused_bgs_lock);
+			ASSERT(list_empty(&cache->bg_list));
+			btrfs_mark_bg_unused(cache);
 		}
 	}
 
@@ -10176,7 +10066,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 
 	btrfs_add_raid_kobjects(info);
 	init_global_block_rsv(info);
-	ret = 0;
+	ret = check_chunk_block_group_mappings(info);
 error:
 	btrfs_free_path(path);
 	return ret;
@@ -10206,8 +10096,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 					sizeof(item));
 		if (ret)
 			btrfs_abort_transaction(trans, ret);
-		ret = btrfs_finish_chunk_alloc(trans, fs_info, key.objectid,
-					       key.offset);
+		ret = btrfs_finish_chunk_alloc(trans, key.objectid, key.offset);
 		if (ret)
 			btrfs_abort_transaction(trans, ret);
 		add_block_group_free_space(trans, block_group);
@@ -10218,10 +10107,10 @@ next:
 	trans->can_flush_pending_bgs = can_flush_pending_bgs;
 }
 
-int btrfs_make_block_group(struct btrfs_trans_handle *trans,
-			   struct btrfs_fs_info *fs_info, u64 bytes_used,
+int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 			   u64 type, u64 chunk_offset, u64 size)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_block_group_cache *cache;
 	int ret;
 
@@ -10240,20 +10129,20 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
 	cache->needs_free_space = 1;
-	ret = exclude_super_stripes(fs_info, cache);
+	ret = exclude_super_stripes(cache);
 	if (ret) {
 		/*
 		 * We may have excluded something, so call this just in
 		 * case.
 		 */
-		free_excluded_extents(fs_info, cache);
+		free_excluded_extents(cache);
 		btrfs_put_block_group(cache);
 		return ret;
 	}
 
 	add_new_free_space(cache, chunk_offset, chunk_offset + size);
 
-	free_excluded_extents(fs_info, cache);
+	free_excluded_extents(cache);
 
 #ifdef CONFIG_BTRFS_DEBUG
 	if (btrfs_should_fragment_free_space(cache)) {
@@ -10311,9 +10200,9 @@ static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 }
 
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info, u64 group_start,
-			     struct extent_map *em)
+			     u64 group_start, struct extent_map *em)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_path *path;
 	struct btrfs_block_group_cache *block_group;
@@ -10337,18 +10226,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * Free the reserved super bytes from this block group before
 	 * remove it.
 	 */
-	free_excluded_extents(fs_info, block_group);
+	free_excluded_extents(block_group);
 	btrfs_free_ref_tree_range(fs_info, block_group->key.objectid,
 				  block_group->key.offset);
 
 	memcpy(&key, &block_group->key, sizeof(key));
 	index = btrfs_bg_flags_to_raid_index(block_group->flags);
-	if (block_group->flags & (BTRFS_BLOCK_GROUP_DUP |
-				  BTRFS_BLOCK_GROUP_RAID1 |
-				  BTRFS_BLOCK_GROUP_RAID10))
-		factor = 2;
-	else
-		factor = 1;
+	factor = btrfs_bg_type_to_factor(block_group->flags);
 
 	/* make sure this block group isn't part of an allocation cluster */
 	cluster = &fs_info->data_alloc_cluster;
@@ -10687,7 +10571,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		/* Don't want to race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
 		spin_lock(&block_group->lock);
-		if (block_group->reserved ||
+		if (block_group->reserved || block_group->pinned ||
 		    btrfs_block_group_used(&block_group->item) ||
 		    block_group->ro ||
 		    list_is_singular(&block_group->list)) {
@@ -10764,8 +10648,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 
 		space_info->bytes_pinned -= block_group->pinned;
 		space_info->bytes_readonly += block_group->pinned;
-		percpu_counter_add(&space_info->total_bytes_pinned,
-				   -block_group->pinned);
+		percpu_counter_add_batch(&space_info->total_bytes_pinned,
+				   -block_group->pinned,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH);
 		block_group->pinned = 0;
 
 		spin_unlock(&block_group->lock);
@@ -10782,8 +10667,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * Btrfs_remove_chunk will abort the transaction if things go
 		 * horribly wrong.
 		 */
-		ret = btrfs_remove_chunk(trans, fs_info,
-					 block_group->key.objectid);
+		ret = btrfs_remove_chunk(trans, block_group->key.objectid);
 
 		if (ret) {
 			if (trimming)
@@ -11066,3 +10950,16 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
 			       !atomic_read(&root->will_be_snapshotted));
 	}
 }
+
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+
+	spin_lock(&fs_info->unused_bgs_lock);
+	if (list_empty(&bg->bg_list)) {
+		btrfs_get_block_group(bg);
+		trace_btrfs_add_unused_block_group(bg);
+		list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
+	}
+	spin_unlock(&fs_info->unused_bgs_lock);
+}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index b3e45714d28f..628f1aef34b0 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -140,14 +140,6 @@ static int add_extent_changeset(struct extent_state *state, unsigned bits,
 
 static void flush_write_bio(struct extent_page_data *epd);
 
-static inline struct btrfs_fs_info *
-tree_fs_info(struct extent_io_tree *tree)
-{
-	if (tree->ops)
-		return tree->ops->tree_fs_info(tree->private_data);
-	return NULL;
-}
-
 int __init extent_io_init(void)
 {
 	extent_state_cache = kmem_cache_create("btrfs_extent_state",
@@ -564,8 +556,10 @@ alloc_extent_state_atomic(struct extent_state *prealloc)
 
 static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
 {
-	btrfs_panic(tree_fs_info(tree), err,
-		    "Locking error: Extent tree was modified by another thread while locked.");
+	struct inode *inode = tree->private_data;
+
+	btrfs_panic(btrfs_sb(inode->i_sb), err,
+	"locking error: extent tree was modified by another thread while locked");
 }
 
 /*
@@ -1386,14 +1380,6 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
 	}
 }
 
-/*
- * helper function to set both pages and extents in the tree writeback
- */
-static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	tree->ops->set_range_writeback(tree->private_data, start, end);
-}
-
 /* find the first state struct with 'bits' set after 'start', and
  * return it.  tree->lock must be held.  NULL will returned if
  * nothing was found after 'start'
@@ -2059,7 +2045,7 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
 			 struct extent_buffer *eb, int mirror_num)
 {
 	u64 start = eb->start;
-	unsigned long i, num_pages = num_extent_pages(eb->start, eb->len);
+	int i, num_pages = num_extent_pages(eb);
 	int ret = 0;
 
 	if (sb_rdonly(fs_info->sb))
@@ -2398,7 +2384,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 				      start - page_offset(page),
 				      (int)phy_offset, failed_bio->bi_end_io,
 				      NULL);
-	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
+	bio->bi_opf = REQ_OP_READ | read_mode;
 
 	btrfs_debug(btrfs_sb(inode->i_sb),
 		"Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d",
@@ -2790,8 +2776,8 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 		else
 			contig = bio_end_sector(bio) == sector;
 
-		if (tree->ops && tree->ops->merge_bio_hook(page, offset,
-					page_size, bio, bio_flags))
+		if (tree->ops && btrfs_merge_bio_hook(page, offset, page_size,
+						      bio, bio_flags))
 			can_merge = false;
 
 		if (prev_bio_flags != bio_flags || !contig || !can_merge ||
@@ -3422,7 +3408,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 			continue;
 		}
 
-		set_range_writeback(tree, cur, cur + iosize - 1);
+		btrfs_set_range_writeback(tree, cur, cur + iosize - 1);
 		if (!PageWriteback(page)) {
 			btrfs_err(BTRFS_I(inode)->root->fs_info,
 				   "page %lu not writeback, cur %llu end %llu",
@@ -3538,7 +3524,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 			  struct btrfs_fs_info *fs_info,
 			  struct extent_page_data *epd)
 {
-	unsigned long i, num_pages;
+	int i, num_pages;
 	int flush = 0;
 	int ret = 0;
 
@@ -3588,7 +3574,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 	if (!ret)
 		return ret;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
@@ -3712,13 +3698,13 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	u64 offset = eb->start;
 	u32 nritems;
-	unsigned long i, num_pages;
+	int i, num_pages;
 	unsigned long start, end;
 	unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
 	int ret = 0;
 
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	atomic_set(&eb->io_pages, num_pages);
 
 	/* set btree blocks beyond nritems with 0 to avoid stale content. */
@@ -4643,23 +4629,20 @@ int extent_buffer_under_io(struct extent_buffer *eb)
 }
 
 /*
- * Helper for releasing extent buffer page.
+ * Release all pages attached to the extent buffer.
  */
-static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
+static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb)
 {
-	unsigned long index;
-	struct page *page;
-	int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+	int i;
+	int num_pages;
+	int mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
 	BUG_ON(extent_buffer_under_io(eb));
 
-	index = num_extent_pages(eb->start, eb->len);
-	if (index == 0)
-		return;
+	num_pages = num_extent_pages(eb);
+	for (i = 0; i < num_pages; i++) {
+		struct page *page = eb->pages[i];
 
-	do {
-		index--;
-		page = eb->pages[index];
 		if (!page)
 			continue;
 		if (mapped)
@@ -4691,7 +4674,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 
 		/* One for when we allocated the page */
 		put_page(page);
-	} while (index != 0);
+	}
 }
 
 /*
@@ -4699,7 +4682,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
  */
 static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
 {
-	btrfs_release_extent_buffer_page(eb);
+	btrfs_release_extent_buffer_pages(eb);
 	__free_extent_buffer(eb);
 }
 
@@ -4743,10 +4726,10 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
 
 struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 {
-	unsigned long i;
+	int i;
 	struct page *p;
 	struct extent_buffer *new;
-	unsigned long num_pages = num_extent_pages(src->start, src->len);
+	int num_pages = num_extent_pages(src);
 
 	new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
 	if (new == NULL)
@@ -4766,7 +4749,7 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 	}
 
 	set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
-	set_bit(EXTENT_BUFFER_DUMMY, &new->bflags);
+	set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
 
 	return new;
 }
@@ -4775,15 +4758,14 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 						  u64 start, unsigned long len)
 {
 	struct extent_buffer *eb;
-	unsigned long num_pages;
-	unsigned long i;
-
-	num_pages = num_extent_pages(start, len);
+	int num_pages;
+	int i;
 
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
 		return NULL;
 
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		eb->pages[i] = alloc_page(GFP_NOFS);
 		if (!eb->pages[i])
@@ -4791,7 +4773,7 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 	}
 	set_extent_buffer_uptodate(eb);
 	btrfs_set_header_nritems(eb, 0);
-	set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+	set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
 	return eb;
 err:
@@ -4843,11 +4825,11 @@ static void check_buffer_tree_ref(struct extent_buffer *eb)
 static void mark_extent_buffer_accessed(struct extent_buffer *eb,
 		struct page *accessed)
 {
-	unsigned long num_pages, i;
+	int num_pages, i;
 
 	check_buffer_tree_ref(eb);
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
@@ -4944,8 +4926,8 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 					  u64 start)
 {
 	unsigned long len = fs_info->nodesize;
-	unsigned long num_pages = num_extent_pages(start, len);
-	unsigned long i;
+	int num_pages;
+	int i;
 	unsigned long index = start >> PAGE_SHIFT;
 	struct extent_buffer *eb;
 	struct extent_buffer *exists = NULL;
@@ -4967,6 +4949,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	if (!eb)
 		return ERR_PTR(-ENOMEM);
 
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++, index++) {
 		p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
 		if (!p) {
@@ -5009,8 +4992,11 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 			uptodate = 0;
 
 		/*
-		 * see below about how we avoid a nasty race with release page
-		 * and why we unlock later
+		 * We can't unlock the pages just yet since the extent buffer
+		 * hasn't been properly inserted in the radix tree, this
+		 * opens a race with btree_releasepage which can free a page
+		 * while we are still filling in all pages for the buffer and
+		 * we could crash.
 		 */
 	}
 	if (uptodate)
@@ -5039,21 +5025,12 @@ again:
 	set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
 
 	/*
-	 * there is a race where release page may have
-	 * tried to find this extent buffer in the radix
-	 * but failed.  It will tell the VM it is safe to
-	 * reclaim the, and it will clear the page private bit.
-	 * We must make sure to set the page private bit properly
-	 * after the extent buffer is in the radix tree so
-	 * it doesn't get lost
+	 * Now it's safe to unlock the pages because any calls to
+	 * btree_releasepage will correctly detect that a page belongs to a
+	 * live buffer and won't free them prematurely.
 	 */
-	SetPageChecked(eb->pages[0]);
-	for (i = 1; i < num_pages; i++) {
-		p = eb->pages[i];
-		ClearPageChecked(p);
-		unlock_page(p);
-	}
-	unlock_page(eb->pages[0]);
+	for (i = 0; i < num_pages; i++)
+		unlock_page(eb->pages[i]);
 	return eb;
 
 free_eb:
@@ -5075,9 +5052,10 @@ static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
 	__free_extent_buffer(eb);
 }
 
-/* Expects to have eb->eb_lock already held */
 static int release_extent_buffer(struct extent_buffer *eb)
 {
+	lockdep_assert_held(&eb->refs_lock);
+
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	if (atomic_dec_and_test(&eb->refs)) {
 		if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
@@ -5094,9 +5072,9 @@ static int release_extent_buffer(struct extent_buffer *eb)
 		}
 
 		/* Should be safe to release our pages at this point */
-		btrfs_release_extent_buffer_page(eb);
+		btrfs_release_extent_buffer_pages(eb);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-		if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) {
+		if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))) {
 			__free_extent_buffer(eb);
 			return 1;
 		}
@@ -5127,7 +5105,7 @@ void free_extent_buffer(struct extent_buffer *eb)
 
 	spin_lock(&eb->refs_lock);
 	if (atomic_read(&eb->refs) == 2 &&
-	    test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))
+	    test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))
 		atomic_dec(&eb->refs);
 
 	if (atomic_read(&eb->refs) == 2 &&
@@ -5159,11 +5137,11 @@ void free_extent_buffer_stale(struct extent_buffer *eb)
 
 void clear_extent_buffer_dirty(struct extent_buffer *eb)
 {
-	unsigned long i;
-	unsigned long num_pages;
+	int i;
+	int num_pages;
 	struct page *page;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
@@ -5189,15 +5167,15 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
 
 int set_extent_buffer_dirty(struct extent_buffer *eb)
 {
-	unsigned long i;
-	unsigned long num_pages;
+	int i;
+	int num_pages;
 	int was_dirty = 0;
 
 	check_buffer_tree_ref(eb);
 
 	was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
 
@@ -5208,12 +5186,12 @@ int set_extent_buffer_dirty(struct extent_buffer *eb)
 
 void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 {
-	unsigned long i;
+	int i;
 	struct page *page;
-	unsigned long num_pages;
+	int num_pages;
 
 	clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		if (page)
@@ -5223,12 +5201,12 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 
 void set_extent_buffer_uptodate(struct extent_buffer *eb)
 {
-	unsigned long i;
+	int i;
 	struct page *page;
-	unsigned long num_pages;
+	int num_pages;
 
 	set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		SetPageUptodate(page);
@@ -5238,13 +5216,13 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     struct extent_buffer *eb, int wait, int mirror_num)
 {
-	unsigned long i;
+	int i;
 	struct page *page;
 	int err;
 	int ret = 0;
 	int locked_pages = 0;
 	int all_uptodate = 1;
-	unsigned long num_pages;
+	int num_pages;
 	unsigned long num_reads = 0;
 	struct bio *bio = NULL;
 	unsigned long bio_flags = 0;
@@ -5252,7 +5230,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 		return 0;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		if (wait == WAIT_NONE) {
@@ -5576,11 +5554,11 @@ void copy_extent_buffer_full(struct extent_buffer *dst,
 			     struct extent_buffer *src)
 {
 	int i;
-	unsigned num_pages;
+	int num_pages;
 
 	ASSERT(dst->len == src->len);
 
-	num_pages = num_extent_pages(dst->start, dst->len);
+	num_pages = num_extent_pages(dst);
 	for (i = 0; i < num_pages; i++)
 		copy_page(page_address(dst->pages[i]),
 				page_address(src->pages[i]));
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0bfd4aeb822d..b4d03e677e1d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -46,7 +46,7 @@
 #define EXTENT_BUFFER_STALE 6
 #define EXTENT_BUFFER_WRITEBACK 7
 #define EXTENT_BUFFER_READ_ERR 8        /* read IO error */
-#define EXTENT_BUFFER_DUMMY 9
+#define EXTENT_BUFFER_UNMAPPED 9
 #define EXTENT_BUFFER_IN_TREE 10
 #define EXTENT_BUFFER_WRITE_ERR 11    /* write IO error */
 
@@ -92,9 +92,6 @@ typedef	blk_status_t (extent_submit_bio_hook_t)(void *private_data, struct bio *
 typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
 		struct bio *bio, u64 bio_offset);
 
-typedef blk_status_t (extent_submit_bio_done_t)(void *private_data,
-		struct bio *bio, int mirror_num);
-
 struct extent_io_ops {
 	/*
 	 * The following callbacks must be allways defined, the function
@@ -104,12 +101,7 @@ struct extent_io_ops {
 	int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
 				    struct page *page, u64 start, u64 end,
 				    int mirror);
-	int (*merge_bio_hook)(struct page *page, unsigned long offset,
-			      size_t size, struct bio *bio,
-			      unsigned long bio_flags);
 	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
-	struct btrfs_fs_info *(*tree_fs_info)(void *private_data);
-	void (*set_range_writeback)(void *private_data, u64 start, u64 end);
 
 	/*
 	 * Optional hooks, called if the pointer is not NULL
@@ -440,10 +432,10 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     int mirror_num);
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
 
-static inline unsigned long num_extent_pages(u64 start, u64 len)
+static inline int num_extent_pages(const struct extent_buffer *eb)
 {
-	return ((start + len + PAGE_SIZE - 1) >> PAGE_SHIFT) -
-		(start >> PAGE_SHIFT);
+	return (round_up(eb->start + eb->len, PAGE_SIZE) >> PAGE_SHIFT) -
+	       (eb->start >> PAGE_SHIFT);
 }
 
 static inline void extent_buffer_get(struct extent_buffer *eb)
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index f9dd6d1836a3..ba74827beb32 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -922,7 +922,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     const bool new_inline,
 				     struct extent_map *em)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf = path->nodes[0];
 	const int slot = path->slots[0];
@@ -942,7 +942,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 			btrfs_file_extent_num_bytes(leaf, fi);
 	} else if (type == BTRFS_FILE_EXTENT_INLINE) {
 		size_t size;
-		size = btrfs_file_extent_inline_len(leaf, slot, fi);
+		size = btrfs_file_extent_ram_bytes(leaf, fi);
 		extent_end = ALIGN(extent_start + size,
 				   fs_info->sectorsize);
 	}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 51e77d72068a..2be00e873e92 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -5,14 +5,11 @@
 
 #include <linux/fs.h>
 #include <linux/pagemap.h>
-#include <linux/highmem.h>
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
 #include <linux/falloc.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
 #include <linux/slab.h>
@@ -83,7 +80,7 @@ static int __compare_inode_defrag(struct inode_defrag *defrag1,
 static int __btrfs_add_inode_defrag(struct btrfs_inode *inode,
 				    struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct inode_defrag *entry;
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -135,8 +132,8 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info)
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 			   struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct inode_defrag *defrag;
 	u64 transid;
 	int ret;
@@ -185,7 +182,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode,
 				       struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret;
 
 	if (!__need_auto_defrag(fs_info))
@@ -833,8 +830,7 @@ next_slot:
 				btrfs_file_extent_num_bytes(leaf, fi);
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = key.offset +
-				btrfs_file_extent_inline_len(leaf,
-						     path->slots[0], fi);
+				btrfs_file_extent_ram_bytes(leaf, fi);
 		} else {
 			/* can't happen */
 			BUG();
@@ -1133,7 +1129,7 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 			      struct btrfs_inode *inode, u64 start, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
@@ -1470,7 +1466,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 				u64 *lockstart, u64 *lockend,
 				struct extent_state **cached_state)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 start_pos;
 	u64 last_pos;
 	int i;
@@ -1526,7 +1522,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 				    size_t *write_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct btrfs_ordered_extent *ordered;
 	u64 lockstart, lockend;
@@ -1569,10 +1565,11 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 	return ret;
 }
 
-static noinline ssize_t __btrfs_buffered_write(struct file *file,
-					       struct iov_iter *i,
-					       loff_t pos)
+static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
+					       struct iov_iter *i)
 {
+	struct file *file = iocb->ki_filp;
+	loff_t pos = iocb->ki_pos;
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -1804,7 +1801,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	loff_t pos = iocb->ki_pos;
+	loff_t pos;
 	ssize_t written;
 	ssize_t written_buffered;
 	loff_t endbyte;
@@ -1815,8 +1812,8 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	if (written < 0 || !iov_iter_count(from))
 		return written;
 
-	pos += written;
-	written_buffered = __btrfs_buffered_write(file, from, pos);
+	pos = iocb->ki_pos;
+	written_buffered = btrfs_buffered_write(iocb, from);
 	if (written_buffered < 0) {
 		err = written_buffered;
 		goto out;
@@ -1953,7 +1950,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		num_written = __btrfs_direct_write(iocb, from);
 	} else {
-		num_written = __btrfs_buffered_write(file, from, pos);
+		num_written = btrfs_buffered_write(iocb, from);
 		if (num_written > 0)
 			iocb->ki_pos = pos + num_written;
 		if (clean_page)
@@ -2042,7 +2039,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_log_ctx ctx;
 	int ret = 0, err;
-	bool full_sync = false;
 	u64 len;
 
 	/*
@@ -2066,96 +2062,21 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	inode_lock(inode);
 	atomic_inc(&root->log_batch);
-	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			     &BTRFS_I(inode)->runtime_flags);
+
 	/*
-	 * We might have have had more pages made dirty after calling
-	 * start_ordered_ops and before acquiring the inode's i_mutex.
+	 * We have to do this here to avoid the priority inversion of waiting on
+	 * IO of a lower priority task while holding a transaciton open.
 	 */
-	if (full_sync) {
-		/*
-		 * For a full sync, we need to make sure any ordered operations
-		 * start and finish before we start logging the inode, so that
-		 * all extents are persisted and the respective file extent
-		 * items are in the fs/subvol btree.
-		 */
-		ret = btrfs_wait_ordered_range(inode, start, len);
-	} else {
-		/*
-		 * Start any new ordered operations before starting to log the
-		 * inode. We will wait for them to finish in btrfs_sync_log().
-		 *
-		 * Right before acquiring the inode's mutex, we might have new
-		 * writes dirtying pages, which won't immediately start the
-		 * respective ordered operations - that is done through the
-		 * fill_delalloc callbacks invoked from the writepage and
-		 * writepages address space operations. So make sure we start
-		 * all ordered operations before starting to log our inode. Not
-		 * doing this means that while logging the inode, writeback
-		 * could start and invoke writepage/writepages, which would call
-		 * the fill_delalloc callbacks (cow_file_range,
-		 * submit_compressed_extents). These callbacks add first an
-		 * extent map to the modified list of extents and then create
-		 * the respective ordered operation, which means in
-		 * tree-log.c:btrfs_log_inode() we might capture all existing
-		 * ordered operations (with btrfs_get_logged_extents()) before
-		 * the fill_delalloc callback adds its ordered operation, and by
-		 * the time we visit the modified list of extent maps (with
-		 * btrfs_log_changed_extents()), we see and process the extent
-		 * map they created. We then use the extent map to construct a
-		 * file extent item for logging without waiting for the
-		 * respective ordered operation to finish - this file extent
-		 * item points to a disk location that might not have yet been
-		 * written to, containing random data - so after a crash a log
-		 * replay will make our inode have file extent items that point
-		 * to disk locations containing invalid data, as we returned
-		 * success to userspace without waiting for the respective
-		 * ordered operation to finish, because it wasn't captured by
-		 * btrfs_get_logged_extents().
-		 */
-		ret = start_ordered_ops(inode, start, end);
-	}
+	ret = btrfs_wait_ordered_range(inode, start, len);
 	if (ret) {
 		inode_unlock(inode);
 		goto out;
 	}
 	atomic_inc(&root->log_batch);
 
-	/*
-	 * If the last transaction that changed this file was before the current
-	 * transaction and we have the full sync flag set in our inode, we can
-	 * bail out now without any syncing.
-	 *
-	 * Note that we can't bail out if the full sync flag isn't set. This is
-	 * because when the full sync flag is set we start all ordered extents
-	 * and wait for them to fully complete - when they complete they update
-	 * the inode's last_trans field through:
-	 *
-	 *     btrfs_finish_ordered_io() ->
-	 *         btrfs_update_inode_fallback() ->
-	 *             btrfs_update_inode() ->
-	 *                 btrfs_set_inode_last_trans()
-	 *
-	 * So we are sure that last_trans is up to date and can do this check to
-	 * bail out safely. For the fast path, when the full sync flag is not
-	 * set in our inode, we can not do it because we start only our ordered
-	 * extents and don't wait for them to complete (that is when
-	 * btrfs_finish_ordered_io runs), so here at this point their last_trans
-	 * value might be less than or equals to fs_info->last_trans_committed,
-	 * and setting a speculative last_trans for an inode when a buffered
-	 * write is made (such as fs_info->generation + 1 for example) would not
-	 * be reliable since after setting the value and before fsync is called
-	 * any number of transactions can start and commit (transaction kthread
-	 * commits the current transaction periodically), and a transaction
-	 * commit does not start nor waits for ordered extents to complete.
-	 */
 	smp_mb();
 	if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) ||
-	    (full_sync && BTRFS_I(inode)->last_trans <=
-	     fs_info->last_trans_committed) ||
-	    (!btrfs_have_ordered_extents_in_range(inode, start, len) &&
-	     BTRFS_I(inode)->last_trans
-	     <= fs_info->last_trans_committed)) {
+	    BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed) {
 		/*
 		 * We've had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
@@ -2239,13 +2160,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 				goto out;
 			}
 		}
-		if (!full_sync) {
-			ret = btrfs_wait_ordered_range(inode, start, len);
-			if (ret) {
-				btrfs_end_transaction(trans);
-				goto out;
-			}
-		}
 		ret = btrfs_commit_transaction(trans);
 	} else {
 		ret = btrfs_end_transaction(trans);
@@ -2310,7 +2224,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		struct btrfs_inode *inode,
 		struct btrfs_path *path, u64 offset, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_file_extent_item *fi;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d5f80cb300be..0adf38b00fa0 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -71,10 +71,6 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	inode = btrfs_iget(fs_info->sb, &location, root, NULL);
 	if (IS_ERR(inode))
 		return inode;
-	if (is_bad_inode(inode)) {
-		iput(inode);
-		return ERR_PTR(-ENOENT);
-	}
 
 	mapping_set_gfp_mask(inode->i_mapping,
 			mapping_gfp_constraint(inode->i_mapping,
@@ -300,9 +296,9 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
 	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FREE_INO_OBJECTID)
 		check_crcs = 1;
 
-	/* Make sure we can fit our crcs into the first page */
+	/* Make sure we can fit our crcs and generation into the first page */
 	if (write && check_crcs &&
-	    (num_pages * sizeof(u32)) >= PAGE_SIZE)
+	    (num_pages * sizeof(u32) + sizeof(u64)) > PAGE_SIZE)
 		return -ENOSPC;
 
 	memset(io_ctl, 0, sizeof(struct btrfs_io_ctl));
@@ -547,7 +543,7 @@ static int io_ctl_add_bitmap(struct btrfs_io_ctl *io_ctl, void *bitmap)
 		io_ctl_map_page(io_ctl, 0);
 	}
 
-	memcpy(io_ctl->cur, bitmap, PAGE_SIZE);
+	copy_page(io_ctl->cur, bitmap);
 	io_ctl_set_crc(io_ctl, io_ctl->index - 1);
 	if (io_ctl->index < io_ctl->num_pages)
 		io_ctl_map_page(io_ctl, 0);
@@ -607,7 +603,7 @@ static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl,
 	if (ret)
 		return ret;
 
-	memcpy(entry->bitmap, io_ctl->cur, PAGE_SIZE);
+	copy_page(entry->bitmap, io_ctl->cur);
 	io_ctl_unmap_page(io_ctl);
 
 	return 0;
@@ -655,7 +651,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 				   struct btrfs_free_space_ctl *ctl,
 				   struct btrfs_path *path, u64 offset)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_free_space_header *header;
 	struct extent_buffer *leaf;
 	struct btrfs_io_ctl io_ctl;
@@ -1123,13 +1119,10 @@ static int __btrfs_wait_cache_io(struct btrfs_root *root,
 {
 	int ret;
 	struct inode *inode = io_ctl->inode;
-	struct btrfs_fs_info *fs_info;
 
 	if (!inode)
 		return 0;
 
-	fs_info = btrfs_sb(inode->i_sb);
-
 	/* Flush the dirty pages in the cache file. */
 	ret = flush_dirty_cache(inode);
 	if (ret)
@@ -1145,7 +1138,7 @@ out:
 		BTRFS_I(inode)->generation = 0;
 		if (block_group) {
 #ifdef DEBUG
-			btrfs_err(fs_info,
+			btrfs_err(root->fs_info,
 				  "failed to write free space cache for block group %llu",
 				  block_group->key.objectid);
 #endif
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index b5950aacd697..d6736595ec57 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1236,7 +1236,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
 	if (ret)
 		goto abort;
 
-	ret = btrfs_del_root(trans, fs_info, &free_space_root->root_key);
+	ret = btrfs_del_root(trans, &free_space_root->root_key);
 	if (ret)
 		goto abort;
 
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 12fcd8897c33..ffca2abf13d0 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2007 Oracle.  All rights reserved.
  */
 
-#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/pagemap.h>
 
@@ -244,8 +243,6 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 		return;
 
 	while (1) {
-		bool add_to_ctl = true;
-
 		spin_lock(rbroot_lock);
 		n = rb_first(rbroot);
 		if (!n) {
@@ -257,15 +254,14 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 		BUG_ON(info->bitmap); /* Logic error */
 
 		if (info->offset > root->ino_cache_progress)
-			add_to_ctl = false;
-		else if (info->offset + info->bytes > root->ino_cache_progress)
-			count = root->ino_cache_progress - info->offset + 1;
+			count = 0;
 		else
-			count = info->bytes;
+			count = min(root->ino_cache_progress - info->offset + 1,
+				    info->bytes);
 
 		rb_erase(&info->offset_index, rbroot);
 		spin_unlock(rbroot_lock);
-		if (add_to_ctl)
+		if (count)
 			__btrfs_add_free_space(root->fs_info, ctl,
 					       info->offset, count);
 		kmem_cache_free(btrfs_free_space_cachep, info);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index eba61bcb9bb3..9357a19d2bff 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -14,17 +14,13 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
-#include <linux/bit_spinlock.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/falloc.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
-#include <linux/mount.h>
 #include <linux/btrfs.h>
 #include <linux/blkdev.h>
 #include <linux/posix_acl_xattr.h>
@@ -1443,8 +1439,7 @@ next_slot:
 			nocow = 1;
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = found_key.offset +
-				btrfs_file_extent_inline_len(leaf,
-						     path->slots[0], fi);
+				btrfs_file_extent_ram_bytes(leaf, fi);
 			extent_end = ALIGN(extent_end,
 					   fs_info->sectorsize);
 		} else {
@@ -1752,7 +1747,7 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
 void __btrfs_del_delalloc_inode(struct btrfs_root *root,
 				struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (!list_empty(&inode->delalloc_inodes)) {
 		list_del_init(&inode->delalloc_inodes);
@@ -1903,8 +1898,8 @@ static void btrfs_clear_bit_hook(void *private_data,
 }
 
 /*
- * extent_io.c merge_bio_hook, this must check the chunk tree to make sure
- * we don't create bios that span stripes or chunks
+ * Merge bio hook, this must check the chunk tree to make sure we don't create
+ * bios that span stripes or chunks
  *
  * return 1 if page cannot be merged to bio
  * return 0 if page can be merged to bio
@@ -1962,7 +1957,7 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
+blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
 			  int mirror_num)
 {
 	struct inode *inode = private_data;
@@ -2035,8 +2030,7 @@ static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio,
 		/* we're doing a write, do the async checksumming */
 		ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags,
 					  bio_offset, inode,
-					  btrfs_submit_bio_start,
-					  btrfs_submit_bio_done);
+					  btrfs_submit_bio_start);
 		goto out;
 	} else if (!skip_sum) {
 		ret = btrfs_csum_one_bio(inode, bio, 0, 0);
@@ -3610,18 +3604,15 @@ static int btrfs_read_locked_inode(struct inode *inode)
 		filled = true;
 
 	path = btrfs_alloc_path();
-	if (!path) {
-		ret = -ENOMEM;
-		goto make_bad;
-	}
+	if (!path)
+		return -ENOMEM;
 
 	memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
 
 	ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
 	if (ret) {
-		if (ret > 0)
-			ret = -ENOENT;
-		goto make_bad;
+		btrfs_free_path(path);
+		return ret;
 	}
 
 	leaf = path->nodes[0];
@@ -3774,11 +3765,6 @@ cache_acl:
 
 	btrfs_sync_inode_flags_to_i_flags(inode);
 	return 0;
-
-make_bad:
-	btrfs_free_path(path);
-	make_bad_inode(inode);
-	return ret;
 }
 
 /*
@@ -3984,7 +3970,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		goto err;
 	}
 skip_backref:
-	ret = btrfs_delete_delayed_dir_index(trans, fs_info, dir, index);
+	ret = btrfs_delete_delayed_dir_index(trans, dir, index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto err;
@@ -4087,11 +4073,10 @@ out:
 }
 
 static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root,
-			struct inode *dir, u64 objectid,
-			const char *name, int name_len)
+			       struct inode *dir, u64 objectid,
+			       const char *name, int name_len)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_dir_item *di;
@@ -4124,9 +4109,8 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_del_root_ref(trans, fs_info, objectid,
-				 root->root_key.objectid, dir_ino,
-				 &index, name, name_len);
+	ret = btrfs_del_root_ref(trans, objectid, root->root_key.objectid,
+				 dir_ino, &index, name, name_len);
 	if (ret < 0) {
 		if (ret != -ENOENT) {
 			btrfs_abort_transaction(trans, ret);
@@ -4145,12 +4129,11 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-		btrfs_release_path(path);
 		index = key.offset;
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_delete_delayed_dir_index(trans, fs_info, BTRFS_I(dir), index);
+	ret = btrfs_delete_delayed_dir_index(trans, BTRFS_I(dir), index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -4243,9 +4226,9 @@ again:
 		prev = node;
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
 
-		if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		if (objectid < btrfs_ino(entry))
 			node = node->rb_left;
-		else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		else if (objectid > btrfs_ino(entry))
 			node = node->rb_right;
 		else
 			break;
@@ -4253,7 +4236,7 @@ again:
 	if (!node) {
 		while (prev) {
 			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) {
+			if (objectid <= btrfs_ino(entry)) {
 				node = prev;
 				break;
 			}
@@ -4262,7 +4245,7 @@ again:
 	}
 	while (node) {
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
-		objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1;
+		objectid = btrfs_ino(entry) + 1;
 		inode = igrab(&entry->vfs_inode);
 		if (inode) {
 			spin_unlock(&root->inode_lock);
@@ -4343,10 +4326,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
 
 	btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
 
-	ret = btrfs_unlink_subvol(trans, root, dir,
-				dest->root_key.objectid,
-				dentry->d_name.name,
-				dentry->d_name.len);
+	ret = btrfs_unlink_subvol(trans, dir, dest->root_key.objectid,
+				  dentry->d_name.name, dentry->d_name.len);
 	if (ret) {
 		err = ret;
 		btrfs_abort_transaction(trans, ret);
@@ -4441,7 +4422,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 		return PTR_ERR(trans);
 
 	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
-		err = btrfs_unlink_subvol(trans, root, dir,
+		err = btrfs_unlink_subvol(trans, dir,
 					  BTRFS_I(inode)->location.objectid,
 					  dentry->d_name.name,
 					  dentry->d_name.len);
@@ -4643,8 +4624,8 @@ search_again:
 					BTRFS_I(inode), leaf, fi,
 					found_key.offset);
 			} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
-				item_end += btrfs_file_extent_inline_len(leaf,
-							 path->slots[0], fi);
+				item_end += btrfs_file_extent_ram_bytes(leaf,
+									fi);
 
 				trace_btrfs_truncate_show_fi_inline(
 					BTRFS_I(inode), leaf, fi, path->slots[0],
@@ -5615,9 +5596,9 @@ static void inode_tree_add(struct inode *inode)
 		parent = *p;
 		entry = rb_entry(parent, struct btrfs_inode, rb_node);
 
-		if (ino < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		if (ino < btrfs_ino(entry))
 			p = &parent->rb_left;
-		else if (ino > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		else if (ino > btrfs_ino(entry))
 			p = &parent->rb_right;
 		else {
 			WARN_ON(!(entry->vfs_inode.i_state &
@@ -5708,16 +5689,21 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 		int ret;
 
 		ret = btrfs_read_locked_inode(inode);
-		if (!is_bad_inode(inode)) {
+		if (!ret) {
 			inode_tree_add(inode);
 			unlock_new_inode(inode);
 			if (new)
 				*new = 1;
 		} else {
-			unlock_new_inode(inode);
-			iput(inode);
-			ASSERT(ret < 0);
-			inode = ERR_PTR(ret < 0 ? ret : -ESTALE);
+			iget_failed(inode);
+			/*
+			 * ret > 0 can come from btrfs_search_slot called by
+			 * btrfs_read_locked_inode, this means the inode item
+			 * was not found.
+			 */
+			if (ret > 0)
+				ret = -ENOENT;
+			inode = ERR_PTR(ret);
 		}
 	}
 
@@ -5745,7 +5731,7 @@ static struct inode *new_simple_dir(struct super_block *s,
 	inode->i_mtime = current_time(inode);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
-	BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime);
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
 
 	return inode;
 }
@@ -6027,32 +6013,6 @@ err:
 	return ret;
 }
 
-int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
-{
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_trans_handle *trans;
-	int ret = 0;
-	bool nolock = false;
-
-	if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags))
-		return 0;
-
-	if (btrfs_fs_closing(root->fs_info) &&
-			btrfs_is_free_space_inode(BTRFS_I(inode)))
-		nolock = true;
-
-	if (wbc->sync_mode == WB_SYNC_ALL) {
-		if (nolock)
-			trans = btrfs_join_transaction_nolock(root);
-		else
-			trans = btrfs_join_transaction(root);
-		if (IS_ERR(trans))
-			return PTR_ERR(trans);
-		ret = btrfs_commit_transaction(trans);
-	}
-	return ret;
-}
-
 /*
  * This is somewhat expensive, updating the tree every time the
  * inode changes.  But, it is most likely to find the inode in cache.
@@ -6335,8 +6295,10 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	location->type = BTRFS_INODE_ITEM_KEY;
 
 	ret = btrfs_insert_inode_locked(inode);
-	if (ret < 0)
+	if (ret < 0) {
+		iput(inode);
 		goto fail;
+	}
 
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems);
@@ -6349,7 +6311,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	inode->i_mtime = current_time(inode);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
-	BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime);
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
 
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				  struct btrfs_inode_item);
@@ -6395,12 +6357,11 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	return inode;
 
 fail_unlock:
-	unlock_new_inode(inode);
+	discard_new_inode(inode);
 fail:
 	if (dir && name)
 		BTRFS_I(dir)->index_cnt--;
 	btrfs_free_path(path);
-	iput(inode);
 	return ERR_PTR(ret);
 }
 
@@ -6419,7 +6380,6 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret = 0;
 	struct btrfs_key key;
 	struct btrfs_root *root = parent_inode->root;
@@ -6435,7 +6395,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 	}
 
 	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
-		ret = btrfs_add_root_ref(trans, fs_info, key.objectid,
+		ret = btrfs_add_root_ref(trans, key.objectid,
 					 root->root_key.objectid, parent_ino,
 					 index, name, name_len);
 	} else if (add_backref) {
@@ -6471,7 +6431,7 @@ fail_dir_item:
 	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		u64 local_index;
 		int err;
-		err = btrfs_del_root_ref(trans, fs_info, key.objectid,
+		err = btrfs_del_root_ref(trans, key.objectid,
 					 root->root_key.objectid, parent_ino,
 					 &local_index, name, name_len);
 
@@ -6505,7 +6465,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = NULL;
 	int err;
-	int drop_inode = 0;
 	u64 objectid;
 	u64 index = 0;
 
@@ -6527,6 +6486,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 			mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_unlock;
 	}
 
@@ -6541,31 +6501,24 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
 			0, index);
-	if (err) {
-		goto out_unlock_inode;
-	} else {
-		btrfs_update_inode(trans, root, inode);
-		d_instantiate_new(dentry, inode);
-	}
+	if (err)
+		goto out_unlock;
+
+	btrfs_update_inode(trans, root, inode);
+	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
-	if (drop_inode) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	return err;
-
-out_unlock_inode:
-	drop_inode = 1;
-	unlock_new_inode(inode);
-	goto out_unlock;
-
 }
 
 static int btrfs_create(struct inode *dir, struct dentry *dentry,
@@ -6575,7 +6528,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = NULL;
-	int drop_inode_on_err = 0;
 	int err;
 	u64 objectid;
 	u64 index = 0;
@@ -6598,9 +6550,9 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 			mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_unlock;
 	}
-	drop_inode_on_err = 1;
 	/*
 	* If the active LSM wants to access the inode during
 	* d_instantiate it needs these. Smack checks to see
@@ -6613,33 +6565,28 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	err = btrfs_update_inode(trans, root, inode);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
 			0, index);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
-	if (err && drop_inode_on_err) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
-
-out_unlock_inode:
-	unlock_new_inode(inode);
-	goto out_unlock;
-
 }
 
 static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
@@ -6748,6 +6695,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 			S_IFDIR | mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_fail;
 	}
 
@@ -6758,34 +6706,30 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_fail_inode;
+		goto out_fail;
 
 	btrfs_i_size_write(BTRFS_I(inode), 0);
 	err = btrfs_update_inode(trans, root, inode);
 	if (err)
-		goto out_fail_inode;
+		goto out_fail;
 
 	err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 			dentry->d_name.name,
 			dentry->d_name.len, 0, index);
 	if (err)
-		goto out_fail_inode;
+		goto out_fail;
 
 	d_instantiate_new(dentry, inode);
 	drop_on_err = 0;
 
 out_fail:
 	btrfs_end_transaction(trans);
-	if (drop_on_err) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
-
-out_fail_inode:
-	unlock_new_inode(inode);
-	goto out_fail;
 }
 
 static noinline int uncompress_inline(struct btrfs_path *path,
@@ -6847,7 +6791,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 	    size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret;
 	int err = 0;
 	u64 extent_start = 0;
@@ -6943,7 +6887,8 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 						       extent_start);
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		size_t size;
-		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
+
+		size = btrfs_file_extent_ram_bytes(leaf, item);
 		extent_end = ALIGN(extent_start + size,
 				   fs_info->sectorsize);
 
@@ -6994,7 +6939,7 @@ next:
 		if (new_inline)
 			goto out;
 
-		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
+		size = btrfs_file_extent_ram_bytes(leaf, item);
 		extent_offset = page_offset(page) + pg_offset - extent_start;
 		copy_size = min_t(u64, PAGE_SIZE - pg_offset,
 				  size - extent_offset);
@@ -7865,7 +7810,7 @@ static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio,
 	isector >>= inode->i_sb->s_blocksize_bits;
 	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
 				pgoff, isector, repair_endio, repair_arg);
-	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
+	bio->bi_opf = REQ_OP_READ | read_mode;
 
 	btrfs_debug(BTRFS_I(inode)->root->fs_info,
 		    "repair DIO read error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d",
@@ -8299,8 +8244,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
 	if (write && async_submit) {
 		ret = btrfs_wq_submit_bio(fs_info, bio, 0, 0,
 					  file_offset, inode,
-					  btrfs_submit_bio_start_direct_io,
-					  btrfs_submit_bio_done);
+					  btrfs_submit_bio_start_direct_io);
 		goto err;
 	} else if (write) {
 		/*
@@ -9540,8 +9484,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	/* src is a subvolume */
 	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
 		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, root, old_dir,
-					  root_objectid,
+		ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
 					  old_dentry->d_name.name,
 					  old_dentry->d_name.len);
 	} else { /* src is an inode */
@@ -9560,8 +9503,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	/* dest is a subvolume */
 	if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
 		root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, dest, new_dir,
-					  root_objectid,
+		ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
 					  new_dentry->d_name.name,
 					  new_dentry->d_name.len);
 	} else { /* dest is an inode */
@@ -9821,7 +9763,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, root, old_dir, root_objectid,
+		ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
 					old_dentry->d_name.name,
 					old_dentry->d_name.len);
 	} else {
@@ -9843,8 +9785,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (unlikely(btrfs_ino(BTRFS_I(new_inode)) ==
 			     BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 			root_objectid = BTRFS_I(new_inode)->location.objectid;
-			ret = btrfs_unlink_subvol(trans, dest, new_dir,
-						root_objectid,
+			ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
 						new_dentry->d_name.name,
 						new_dentry->d_name.len);
 			BUG_ON(new_inode->i_nlink == 0);
@@ -10115,7 +10056,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	struct btrfs_key key;
 	struct inode *inode = NULL;
 	int err;
-	int drop_inode = 0;
 	u64 objectid;
 	u64 index = 0;
 	int name_len;
@@ -10148,6 +10088,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 				objectid, S_IFLNK|S_IRWXUGO, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_unlock;
 	}
 
@@ -10164,12 +10105,12 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	path = btrfs_alloc_path();
 	if (!path) {
 		err = -ENOMEM;
-		goto out_unlock_inode;
+		goto out_unlock;
 	}
 	key.objectid = btrfs_ino(BTRFS_I(inode));
 	key.offset = 0;
@@ -10179,7 +10120,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 				      datasize);
 	if (err) {
 		btrfs_free_path(path);
-		goto out_unlock_inode;
+		goto out_unlock;
 	}
 	leaf = path->nodes[0];
 	ei = btrfs_item_ptr(leaf, path->slots[0],
@@ -10211,26 +10152,19 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	if (!err)
 		err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
 				BTRFS_I(inode), 0, index);
-	if (err) {
-		drop_inode = 1;
-		goto out_unlock_inode;
-	}
+	if (err)
+		goto out_unlock;
 
 	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
-	if (drop_inode) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
-
-out_unlock_inode:
-	drop_inode = 1;
-	unlock_new_inode(inode);
-	goto out_unlock;
 }
 
 static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -10439,14 +10373,14 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	ret = btrfs_init_inode_security(trans, inode, dir, NULL);
 	if (ret)
-		goto out_inode;
+		goto out;
 
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret)
-		goto out_inode;
+		goto out;
 	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 	if (ret)
-		goto out_inode;
+		goto out;
 
 	/*
 	 * We set number of links to 0 in btrfs_new_inode(), and here we set
@@ -10456,21 +10390,15 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	 *    d_tmpfile() -> inode_dec_link_count() -> drop_nlink()
 	 */
 	set_nlink(inode, 1);
-	unlock_new_inode(inode);
 	d_tmpfile(dentry, inode);
+	unlock_new_inode(inode);
 	mark_inode_dirty(inode);
-
 out:
 	btrfs_end_transaction(trans);
-	if (ret)
-		iput(inode);
+	if (ret && inode)
+		discard_new_inode(inode);
 	btrfs_btree_balance_dirty(fs_info);
 	return ret;
-
-out_inode:
-	unlock_new_inode(inode);
-	goto out;
-
 }
 
 __attribute__((const))
@@ -10479,12 +10407,6 @@ static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror)
 	return -EAGAIN;
 }
 
-static struct btrfs_fs_info *iotree_fs_info(void *private_data)
-{
-	struct inode *inode = private_data;
-	return btrfs_sb(inode->i_sb);
-}
-
 static void btrfs_check_extent_io_range(void *private_data, const char *caller,
 					u64 start, u64 end)
 {
@@ -10499,9 +10421,9 @@ static void btrfs_check_extent_io_range(void *private_data, const char *caller,
 	}
 }
 
-void btrfs_set_range_writeback(void *private_data, u64 start, u64 end)
+void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 {
-	struct inode *inode = private_data;
+	struct inode *inode = tree->private_data;
 	unsigned long index = start >> PAGE_SHIFT;
 	unsigned long end_index = end >> PAGE_SHIFT;
 	struct page *page;
@@ -10557,10 +10479,7 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
 	/* mandatory callbacks */
 	.submit_bio_hook = btrfs_submit_bio_hook,
 	.readpage_end_io_hook = btrfs_readpage_end_io_hook,
-	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
-	.tree_fs_info = iotree_fs_info,
-	.set_range_writeback = btrfs_set_range_writeback,
 
 	/* optional callbacks */
 	.fill_delalloc = run_delalloc_range,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index b077544b5232..d3a5d2a41e5f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5,23 +5,18 @@
 
 #include <linux/kernel.h>
 #include <linux/bio.h>
-#include <linux/buffer_head.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/fsnotify.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/time.h>
-#include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mount.h>
-#include <linux/mpage.h>
 #include <linux/namei.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
-#include <linux/bit_spinlock.h>
 #include <linux/security.h>
 #include <linux/xattr.h>
 #include <linux/mm.h>
@@ -606,7 +601,7 @@ static noinline int create_subvol(struct inode *dir,
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 
-	ret = btrfs_qgroup_inherit(trans, fs_info, 0, objectid, inherit);
+	ret = btrfs_qgroup_inherit(trans, 0, objectid, inherit);
 	if (ret)
 		goto fail;
 
@@ -616,14 +611,6 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 	}
 
-	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(leaf, leaf->start);
-	btrfs_set_header_generation(leaf, trans->transid);
-	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(leaf, objectid);
-
-	write_extent_buffer_fsid(leaf, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(leaf, fs_info->chunk_tree_uuid);
 	btrfs_mark_buffer_dirty(leaf);
 
 	inode_item = &root_item->inode;
@@ -711,8 +698,7 @@ static noinline int create_subvol(struct inode *dir,
 	ret = btrfs_update_inode(trans, root, dir);
 	BUG_ON(ret);
 
-	ret = btrfs_add_root_ref(trans, fs_info,
-				 objectid, root->root_key.objectid,
+	ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid,
 				 btrfs_ino(BTRFS_I(dir)), index, name, namelen);
 	BUG_ON(ret);
 
@@ -2507,8 +2493,8 @@ out:
 static noinline int btrfs_ioctl_ino_lookup(struct file *file,
 					   void __user *argp)
 {
-	 struct btrfs_ioctl_ino_lookup_args *args;
-	 struct inode *inode;
+	struct btrfs_ioctl_ino_lookup_args *args;
+	struct inode *inode;
 	int ret = 0;
 
 	args = memdup_user(argp, sizeof(*args));
@@ -2941,8 +2927,14 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 		ret = btrfs_defrag_root(root);
 		break;
 	case S_IFREG:
-		if (!(file->f_mode & FMODE_WRITE)) {
-			ret = -EINVAL;
+		/*
+		 * Note that this does not check the file descriptor for write
+		 * access. This prevents defragmenting executables that are
+		 * running and allows defrag on files open in read-only mode.
+		 */
+		if (!capable(CAP_SYS_ADMIN) &&
+		    inode_permission(inode, MAY_WRITE)) {
+			ret = -EPERM;
 			goto out;
 		}
 
@@ -3165,10 +3157,8 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info,
 	di_args->total_bytes = btrfs_device_get_total_bytes(dev);
 	memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
 	if (dev->name) {
-		struct rcu_string *name;
-
-		name = rcu_dereference(dev->name);
-		strncpy(di_args->path, name->str, sizeof(di_args->path) - 1);
+		strncpy(di_args->path, rcu_str_deref(dev->name),
+				sizeof(di_args->path) - 1);
 		di_args->path[sizeof(di_args->path) - 1] = 0;
 	} else {
 		di_args->path[0] = '\0';
@@ -5118,9 +5108,7 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_quota_ctl_args *sa;
-	struct btrfs_trans_handle *trans = NULL;
 	int ret;
-	int err;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -5136,28 +5124,19 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
 	}
 
 	down_write(&fs_info->subvol_sem);
-	trans = btrfs_start_transaction(fs_info->tree_root, 2);
-	if (IS_ERR(trans)) {
-		ret = PTR_ERR(trans);
-		goto out;
-	}
 
 	switch (sa->cmd) {
 	case BTRFS_QUOTA_CTL_ENABLE:
-		ret = btrfs_quota_enable(trans, fs_info);
+		ret = btrfs_quota_enable(fs_info);
 		break;
 	case BTRFS_QUOTA_CTL_DISABLE:
-		ret = btrfs_quota_disable(trans, fs_info);
+		ret = btrfs_quota_disable(fs_info);
 		break;
 	default:
 		ret = -EINVAL;
 		break;
 	}
 
-	err = btrfs_commit_transaction(trans);
-	if (err && !ret)
-		ret = err;
-out:
 	kfree(sa);
 	up_write(&fs_info->subvol_sem);
 drop_write:
@@ -5195,15 +5174,13 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 	}
 
 	if (sa->assign) {
-		ret = btrfs_add_qgroup_relation(trans, fs_info,
-						sa->src, sa->dst);
+		ret = btrfs_add_qgroup_relation(trans, sa->src, sa->dst);
 	} else {
-		ret = btrfs_del_qgroup_relation(trans, fs_info,
-						sa->src, sa->dst);
+		ret = btrfs_del_qgroup_relation(trans, sa->src, sa->dst);
 	}
 
 	/* update qgroup status and info */
-	err = btrfs_run_qgroups(trans, fs_info);
+	err = btrfs_run_qgroups(trans);
 	if (err < 0)
 		btrfs_handle_fs_error(fs_info, err,
 				      "failed to update qgroup status and info");
@@ -5221,7 +5198,6 @@ drop_write:
 static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ioctl_qgroup_create_args *sa;
 	struct btrfs_trans_handle *trans;
@@ -5253,9 +5229,9 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 	}
 
 	if (sa->create) {
-		ret = btrfs_create_qgroup(trans, fs_info, sa->qgroupid);
+		ret = btrfs_create_qgroup(trans, sa->qgroupid);
 	} else {
-		ret = btrfs_remove_qgroup(trans, fs_info, sa->qgroupid);
+		ret = btrfs_remove_qgroup(trans, sa->qgroupid);
 	}
 
 	err = btrfs_end_transaction(trans);
@@ -5272,7 +5248,6 @@ drop_write:
 static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ioctl_qgroup_limit_args *sa;
 	struct btrfs_trans_handle *trans;
@@ -5305,7 +5280,7 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 		qgroupid = root->root_key.objectid;
 	}
 
-	ret = btrfs_limit_qgroup(trans, fs_info, qgroupid, &sa->lim);
+	ret = btrfs_limit_qgroup(trans, qgroupid, &sa->lim);
 
 	err = btrfs_end_transaction(trans);
 	if (err && !ret)
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 2e1a1694a33d..0c4ef208b8b9 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -6,7 +6,6 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
-#include <linux/pagevec.h>
 #include "ctree.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
@@ -421,129 +420,6 @@ out:
 	return ret == 0;
 }
 
-/* Needs to either be called under a log transaction or the log_mutex */
-void btrfs_get_logged_extents(struct btrfs_inode *inode,
-			      struct list_head *logged_list,
-			      const loff_t start,
-			      const loff_t end)
-{
-	struct btrfs_ordered_inode_tree *tree;
-	struct btrfs_ordered_extent *ordered;
-	struct rb_node *n;
-	struct rb_node *prev;
-
-	tree = &inode->ordered_tree;
-	spin_lock_irq(&tree->lock);
-	n = __tree_search(&tree->tree, end, &prev);
-	if (!n)
-		n = prev;
-	for (; n; n = rb_prev(n)) {
-		ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
-		if (ordered->file_offset > end)
-			continue;
-		if (entry_end(ordered) <= start)
-			break;
-		if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
-			continue;
-		list_add(&ordered->log_list, logged_list);
-		refcount_inc(&ordered->refs);
-	}
-	spin_unlock_irq(&tree->lock);
-}
-
-void btrfs_put_logged_extents(struct list_head *logged_list)
-{
-	struct btrfs_ordered_extent *ordered;
-
-	while (!list_empty(logged_list)) {
-		ordered = list_first_entry(logged_list,
-					   struct btrfs_ordered_extent,
-					   log_list);
-		list_del_init(&ordered->log_list);
-		btrfs_put_ordered_extent(ordered);
-	}
-}
-
-void btrfs_submit_logged_extents(struct list_head *logged_list,
-				 struct btrfs_root *log)
-{
-	int index = log->log_transid % 2;
-
-	spin_lock_irq(&log->log_extents_lock[index]);
-	list_splice_tail(logged_list, &log->logged_list[index]);
-	spin_unlock_irq(&log->log_extents_lock[index]);
-}
-
-void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *log, u64 transid)
-{
-	struct btrfs_ordered_extent *ordered;
-	int index = transid % 2;
-
-	spin_lock_irq(&log->log_extents_lock[index]);
-	while (!list_empty(&log->logged_list[index])) {
-		struct inode *inode;
-		ordered = list_first_entry(&log->logged_list[index],
-					   struct btrfs_ordered_extent,
-					   log_list);
-		list_del_init(&ordered->log_list);
-		inode = ordered->inode;
-		spin_unlock_irq(&log->log_extents_lock[index]);
-
-		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
-			u64 start = ordered->file_offset;
-			u64 end = ordered->file_offset + ordered->len - 1;
-
-			WARN_ON(!inode);
-			filemap_fdatawrite_range(inode->i_mapping, start, end);
-		}
-		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
-						   &ordered->flags));
-
-		/*
-		 * In order to keep us from losing our ordered extent
-		 * information when committing the transaction we have to make
-		 * sure that any logged extents are completed when we go to
-		 * commit the transaction.  To do this we simply increase the
-		 * current transactions pending_ordered counter and decrement it
-		 * when the ordered extent completes.
-		 */
-		if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
-			struct btrfs_ordered_inode_tree *tree;
-
-			tree = &BTRFS_I(inode)->ordered_tree;
-			spin_lock_irq(&tree->lock);
-			if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
-				set_bit(BTRFS_ORDERED_PENDING, &ordered->flags);
-				atomic_inc(&trans->transaction->pending_ordered);
-			}
-			spin_unlock_irq(&tree->lock);
-		}
-		btrfs_put_ordered_extent(ordered);
-		spin_lock_irq(&log->log_extents_lock[index]);
-	}
-	spin_unlock_irq(&log->log_extents_lock[index]);
-}
-
-void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid)
-{
-	struct btrfs_ordered_extent *ordered;
-	int index = transid % 2;
-
-	spin_lock_irq(&log->log_extents_lock[index]);
-	while (!list_empty(&log->logged_list[index])) {
-		ordered = list_first_entry(&log->logged_list[index],
-					   struct btrfs_ordered_extent,
-					   log_list);
-		list_del_init(&ordered->log_list);
-		spin_unlock_irq(&log->log_extents_lock[index]);
-		btrfs_put_ordered_extent(ordered);
-		spin_lock_irq(&log->log_extents_lock[index]);
-	}
-	spin_unlock_irq(&log->log_extents_lock[index]);
-}
-
 /*
  * used to drop a reference on an ordered extent.  This will free
  * the extent if the last reference is dropped
@@ -913,20 +789,6 @@ out:
 	return entry;
 }
 
-bool btrfs_have_ordered_extents_in_range(struct inode *inode,
-					 u64 file_offset,
-					 u64 len)
-{
-	struct btrfs_ordered_extent *oe;
-
-	oe = btrfs_lookup_ordered_range(BTRFS_I(inode), file_offset, len);
-	if (oe) {
-		btrfs_put_ordered_extent(oe);
-		return true;
-	}
-	return false;
-}
-
 /*
  * lookup and return any extent before 'file_offset'.  NULL is returned
  * if none is found
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 3be443fb3001..02d813aaa261 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -54,15 +54,11 @@ struct btrfs_ordered_sum {
 #define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates whether this ordered extent
 				       * has done its due diligence in updating
 				       * the isize. */
-#define BTRFS_ORDERED_LOGGED_CSUM 8 /* We've logged the csums on this ordered
-				       ordered extent */
-#define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */
+#define BTRFS_ORDERED_TRUNCATED 8 /* Set when we have to truncate an extent */
 
-#define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent
-				 * in the logging code. */
-#define BTRFS_ORDERED_PENDING 11 /* We are waiting for this ordered extent to
+#define BTRFS_ORDERED_PENDING 9 /* We are waiting for this ordered extent to
 				  * complete in the current transaction. */
-#define BTRFS_ORDERED_REGULAR 12 /* Regular IO for COW */
+#define BTRFS_ORDERED_REGULAR 10 /* Regular IO for COW */
 
 struct btrfs_ordered_extent {
 	/* logical offset in the file */
@@ -182,9 +178,6 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
 		struct btrfs_inode *inode,
 		u64 file_offset,
 		u64 len);
-bool btrfs_have_ordered_extents_in_range(struct inode *inode,
-					 u64 file_offset,
-					 u64 len);
 int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 				struct btrfs_ordered_extent *ordered);
 int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
@@ -193,16 +186,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 			       const u64 range_start, const u64 range_len);
 u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 			      const u64 range_start, const u64 range_len);
-void btrfs_get_logged_extents(struct btrfs_inode *inode,
-			      struct list_head *logged_list,
-			      const loff_t start,
-			      const loff_t end);
-void btrfs_put_logged_extents(struct list_head *logged_list);
-void btrfs_submit_logged_extents(struct list_head *logged_list,
-				 struct btrfs_root *log);
-void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *log, u64 transid);
-void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid);
 int __init ordered_data_init(void);
 void __cold ordered_data_exit(void);
 
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index a4e11cf04671..df49931ffe92 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -52,17 +52,9 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 	u64 offset;
 	int ref_index = 0;
 
-	if (item_size < sizeof(*ei)) {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		struct btrfs_extent_item_v0 *ei0;
-		BUG_ON(item_size != sizeof(*ei0));
-		ei0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_item_v0);
-		pr_info("\t\textent refs %u\n",
-		       btrfs_extent_refs_v0(eb, ei0));
-		return;
-#else
-		BUG();
-#endif
+	if (unlikely(item_size < sizeof(*ei))) {
+		btrfs_print_v0_err(eb->fs_info);
+		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
 	}
 
 	ei = btrfs_item_ptr(eb, slot, struct btrfs_extent_item);
@@ -133,20 +125,6 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 	WARN_ON(ptr > end);
 }
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static void print_extent_ref_v0(struct extent_buffer *eb, int slot)
-{
-	struct btrfs_extent_ref_v0 *ref0;
-
-	ref0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_ref_v0);
-	printk("\t\textent back ref root %llu gen %llu owner %llu num_refs %lu\n",
-		btrfs_ref_root_v0(eb, ref0),
-		btrfs_ref_generation_v0(eb, ref0),
-		btrfs_ref_objectid_v0(eb, ref0),
-		(unsigned long)btrfs_ref_count_v0(eb, ref0));
-}
-#endif
-
 static void print_uuid_item(struct extent_buffer *l, unsigned long offset,
 			    u32 item_size)
 {
@@ -267,8 +245,8 @@ void btrfs_print_leaf(struct extent_buffer *l)
 					    struct btrfs_file_extent_item);
 			if (btrfs_file_extent_type(l, fi) ==
 			    BTRFS_FILE_EXTENT_INLINE) {
-				pr_info("\t\tinline extent data size %u\n",
-				       btrfs_file_extent_inline_len(l, i, fi));
+				pr_info("\t\tinline extent data size %llu\n",
+				       btrfs_file_extent_ram_bytes(l, fi));
 				break;
 			}
 			pr_info("\t\textent data disk bytenr %llu nr %llu\n",
@@ -280,11 +258,8 @@ void btrfs_print_leaf(struct extent_buffer *l)
 			       btrfs_file_extent_ram_bytes(l, fi));
 			break;
 		case BTRFS_EXTENT_REF_V0_KEY:
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-			print_extent_ref_v0(l, i);
-#else
-			BUG();
-#endif
+			btrfs_print_v0_err(fs_info);
+			btrfs_handle_fs_error(fs_info, -EINVAL, NULL);
 			break;
 		case BTRFS_BLOCK_GROUP_ITEM_KEY:
 			bi = btrfs_item_ptr(l, i,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index c25dc47210a3..4353bb69bb86 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -530,11 +530,11 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
 	fs_info->qgroup_ulist = NULL;
 }
 
-static int add_qgroup_relation_item(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *quota_root,
-				    u64 src, u64 dst)
+static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src,
+				    u64 dst)
 {
 	int ret;
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 
@@ -554,11 +554,11 @@ static int add_qgroup_relation_item(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static int del_qgroup_relation_item(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *quota_root,
-				    u64 src, u64 dst)
+static int del_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src,
+				    u64 dst)
 {
 	int ret;
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 
@@ -653,10 +653,10 @@ out:
 	return ret;
 }
 
-static int del_qgroup_item(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *quota_root, u64 qgroupid)
+static int del_qgroup_item(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
 	int ret;
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 
@@ -700,9 +700,9 @@ out:
 }
 
 static int update_qgroup_limit_item(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *root,
 				    struct btrfs_qgroup *qgroup)
 {
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct extent_buffer *l;
@@ -718,7 +718,7 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1);
 	if (ret > 0)
 		ret = -ENOENT;
 
@@ -742,9 +742,10 @@ out:
 }
 
 static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
-				   struct btrfs_root *root,
 				   struct btrfs_qgroup *qgroup)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct extent_buffer *l;
@@ -752,7 +753,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
 	int ret;
 	int slot;
 
-	if (btrfs_is_testing(root->fs_info))
+	if (btrfs_is_testing(fs_info))
 		return 0;
 
 	key.objectid = 0;
@@ -763,7 +764,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1);
 	if (ret > 0)
 		ret = -ENOENT;
 
@@ -786,10 +787,10 @@ out:
 	return ret;
 }
 
-static int update_qgroup_status_item(struct btrfs_trans_handle *trans,
-				     struct btrfs_fs_info *fs_info,
-				    struct btrfs_root *root)
+static int update_qgroup_status_item(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct extent_buffer *l;
@@ -805,7 +806,7 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1);
 	if (ret > 0)
 		ret = -ENOENT;
 
@@ -875,8 +876,7 @@ out:
 	return ret;
 }
 
-int btrfs_quota_enable(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info)
+int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *quota_root;
 	struct btrfs_root *tree_root = fs_info->tree_root;
@@ -886,6 +886,7 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	struct btrfs_key found_key;
 	struct btrfs_qgroup *qgroup = NULL;
+	struct btrfs_trans_handle *trans = NULL;
 	int ret = 0;
 	int slot;
 
@@ -893,9 +894,25 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	if (fs_info->quota_root)
 		goto out;
 
+	/*
+	 * 1 for quota root item
+	 * 1 for BTRFS_QGROUP_STATUS item
+	 *
+	 * Yet we also need 2*n items for a QGROUP_INFO/QGROUP_LIMIT items
+	 * per subvolume. However those are not currently reserved since it
+	 * would be a lot of overkill.
+	 */
+	trans = btrfs_start_transaction(tree_root, 2);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		trans = NULL;
+		goto out;
+	}
+
 	fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
 	if (!fs_info->qgroup_ulist) {
 		ret = -ENOMEM;
+		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
@@ -906,12 +923,14 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 				       BTRFS_QUOTA_TREE_OBJECTID);
 	if (IS_ERR(quota_root)) {
 		ret =  PTR_ERR(quota_root);
+		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_root;
 	}
 
@@ -921,8 +940,10 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_insert_empty_item(trans, quota_root, path, &key,
 				      sizeof(*ptr));
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
+	}
 
 	leaf = path->nodes[0];
 	ptr = btrfs_item_ptr(leaf, path->slots[0],
@@ -944,9 +965,10 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot_for_read(tree_root, &key, path, 1, 0);
 	if (ret > 0)
 		goto out_add_root;
-	if (ret < 0)
+	if (ret < 0) {
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
-
+	}
 
 	while (1) {
 		slot = path->slots[0];
@@ -956,18 +978,23 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 		if (found_key.type == BTRFS_ROOT_REF_KEY) {
 			ret = add_qgroup_item(trans, quota_root,
 					      found_key.offset);
-			if (ret)
+			if (ret) {
+				btrfs_abort_transaction(trans, ret);
 				goto out_free_path;
+			}
 
 			qgroup = add_qgroup_rb(fs_info, found_key.offset);
 			if (IS_ERR(qgroup)) {
 				ret = PTR_ERR(qgroup);
+				btrfs_abort_transaction(trans, ret);
 				goto out_free_path;
 			}
 		}
 		ret = btrfs_next_item(tree_root, path);
-		if (ret < 0)
+		if (ret < 0) {
+			btrfs_abort_transaction(trans, ret);
 			goto out_free_path;
+		}
 		if (ret)
 			break;
 	}
@@ -975,18 +1002,28 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 out_add_root:
 	btrfs_release_path(path);
 	ret = add_qgroup_item(trans, quota_root, BTRFS_FS_TREE_OBJECTID);
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
+	}
 
 	qgroup = add_qgroup_rb(fs_info, BTRFS_FS_TREE_OBJECTID);
 	if (IS_ERR(qgroup)) {
 		ret = PTR_ERR(qgroup);
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
 	}
 	spin_lock(&fs_info->qgroup_lock);
 	fs_info->quota_root = quota_root;
 	set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 	spin_unlock(&fs_info->qgroup_lock);
+
+	ret = btrfs_commit_transaction(trans);
+	if (ret) {
+		trans = NULL;
+		goto out_free_path;
+	}
+
 	ret = qgroup_rescan_init(fs_info, 0, 1);
 	if (!ret) {
 	        qgroup_rescan_zero_tracking(fs_info);
@@ -1006,20 +1043,35 @@ out:
 	if (ret) {
 		ulist_free(fs_info->qgroup_ulist);
 		fs_info->qgroup_ulist = NULL;
+		if (trans)
+			btrfs_end_transaction(trans);
 	}
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;
 }
 
-int btrfs_quota_disable(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info)
+int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *quota_root;
+	struct btrfs_trans_handle *trans = NULL;
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	if (!fs_info->quota_root)
 		goto out;
+
+	/*
+	 * 1 For the root item
+	 *
+	 * We should also reserve enough items for the quota tree deletion in
+	 * btrfs_clean_quota_tree but this is not done.
+	 */
+	trans = btrfs_start_transaction(fs_info->tree_root, 1);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out;
+	}
+
 	clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 	btrfs_qgroup_wait_for_completion(fs_info, false);
 	spin_lock(&fs_info->qgroup_lock);
@@ -1031,12 +1083,16 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 	btrfs_free_qgroup_config(fs_info);
 
 	ret = btrfs_clean_quota_tree(trans, quota_root);
-	if (ret)
-		goto out;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto end_trans;
+	}
 
-	ret = btrfs_del_root(trans, fs_info, &quota_root->root_key);
-	if (ret)
-		goto out;
+	ret = btrfs_del_root(trans, &quota_root->root_key);
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto end_trans;
+	}
 
 	list_del(&quota_root->dirty_list);
 
@@ -1048,6 +1104,9 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 	free_extent_buffer(quota_root->node);
 	free_extent_buffer(quota_root->commit_root);
 	kfree(quota_root);
+
+end_trans:
+	ret = btrfs_end_transaction(trans);
 out:
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;
@@ -1177,9 +1236,10 @@ out:
 	return ret;
 }
 
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *parent;
 	struct btrfs_qgroup *member;
@@ -1216,13 +1276,13 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	ret = add_qgroup_relation_item(trans, quota_root, src, dst);
+	ret = add_qgroup_relation_item(trans, src, dst);
 	if (ret)
 		goto out;
 
-	ret = add_qgroup_relation_item(trans, quota_root, dst, src);
+	ret = add_qgroup_relation_item(trans, dst, src);
 	if (ret) {
-		del_qgroup_relation_item(trans, quota_root, src, dst);
+		del_qgroup_relation_item(trans, src, dst);
 		goto out;
 	}
 
@@ -1240,9 +1300,10 @@ out:
 	return ret;
 }
 
-static int __del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
+static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+				 u64 dst)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *parent;
 	struct btrfs_qgroup *member;
@@ -1276,8 +1337,8 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans,
 	ret = -ENOENT;
 	goto out;
 exist:
-	ret = del_qgroup_relation_item(trans, quota_root, src, dst);
-	err = del_qgroup_relation_item(trans, quota_root, dst, src);
+	ret = del_qgroup_relation_item(trans, src, dst);
+	err = del_qgroup_relation_item(trans, dst, src);
 	if (err && !ret)
 		ret = err;
 
@@ -1290,21 +1351,22 @@ out:
 	return ret;
 }
 
-int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
+int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
-	ret = __del_qgroup_relation(trans, fs_info, src, dst);
+	ret = __del_qgroup_relation(trans, src, dst);
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 
 	return ret;
 }
 
-int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid)
+int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	int ret = 0;
@@ -1336,9 +1398,9 @@ out:
 	return ret;
 }
 
-int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid)
+int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_qgroup_list *list;
@@ -1362,16 +1424,15 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 	}
-	ret = del_qgroup_item(trans, quota_root, qgroupid);
+	ret = del_qgroup_item(trans, qgroupid);
 	if (ret && ret != -ENOENT)
 		goto out;
 
 	while (!list_empty(&qgroup->groups)) {
 		list = list_first_entry(&qgroup->groups,
 					struct btrfs_qgroup_list, next_group);
-		ret = __del_qgroup_relation(trans, fs_info,
-					   qgroupid,
-					   list->group->qgroupid);
+		ret = __del_qgroup_relation(trans, qgroupid,
+					    list->group->qgroupid);
 		if (ret)
 			goto out;
 	}
@@ -1384,10 +1445,10 @@ out:
 	return ret;
 }
 
-int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 qgroupid,
+int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	int ret = 0;
@@ -1451,7 +1512,7 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
 
 	spin_unlock(&fs_info->qgroup_lock);
 
-	ret = update_qgroup_limit_item(trans, quota_root, qgroup);
+	ret = update_qgroup_limit_item(trans, qgroup);
 	if (ret) {
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 		btrfs_info(fs_info, "unable to update quota limit for %llu",
@@ -1519,10 +1580,10 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
-		struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
-		gfp_t gfp_flag)
+int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+			      u64 num_bytes, gfp_t gfp_flag)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_qgroup_extent_record *record;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int ret;
@@ -1530,8 +1591,6 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)
 	    || bytenr == 0 || num_bytes == 0)
 		return 0;
-	if (WARN_ON(trans == NULL))
-		return -EINVAL;
 	record = kmalloc(sizeof(*record), gfp_flag);
 	if (!record)
 		return -ENOMEM;
@@ -1552,9 +1611,9 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
 }
 
 int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct extent_buffer *eb)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int nr = btrfs_header_nritems(eb);
 	int i, extent_type, ret;
 	struct btrfs_key key;
@@ -1584,8 +1643,8 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
 
 		num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
 
-		ret = btrfs_qgroup_trace_extent(trans, fs_info, bytenr,
-						num_bytes, GFP_NOFS);
+		ret = btrfs_qgroup_trace_extent(trans, bytenr, num_bytes,
+						GFP_NOFS);
 		if (ret)
 			return ret;
 	}
@@ -1655,11 +1714,10 @@ static int adjust_slots_upwards(struct btrfs_path *path, int root_level)
 }
 
 int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root,
 			       struct extent_buffer *root_eb,
 			       u64 root_gen, int root_level)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret = 0;
 	int level;
 	struct extent_buffer *eb = root_eb;
@@ -1678,7 +1736,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 	}
 
 	if (root_level == 0) {
-		ret = btrfs_qgroup_trace_leaf_items(trans, fs_info, root_eb);
+		ret = btrfs_qgroup_trace_leaf_items(trans, root_eb);
 		goto out;
 	}
 
@@ -1736,8 +1794,7 @@ walk_down:
 			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 			path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
 
-			ret = btrfs_qgroup_trace_extent(trans, fs_info,
-							child_bytenr,
+			ret = btrfs_qgroup_trace_extent(trans, child_bytenr,
 							fs_info->nodesize,
 							GFP_NOFS);
 			if (ret)
@@ -1745,8 +1802,8 @@ walk_down:
 		}
 
 		if (level == 0) {
-			ret = btrfs_qgroup_trace_leaf_items(trans,fs_info,
-							   path->nodes[level]);
+			ret = btrfs_qgroup_trace_leaf_items(trans,
+							    path->nodes[level]);
 			if (ret)
 				goto out;
 
@@ -1981,12 +2038,11 @@ static int maybe_fs_roots(struct ulist *roots)
 	return is_fstree(unode->val);
 }
 
-int
-btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
-			    u64 bytenr, u64 num_bytes,
-			    struct ulist *old_roots, struct ulist *new_roots)
+int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+				u64 num_bytes, struct ulist *old_roots,
+				struct ulist *new_roots)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct ulist *qgroups = NULL;
 	struct ulist *tmp = NULL;
 	u64 seq;
@@ -2116,9 +2172,10 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 				ulist_del(record->old_roots, qgroup_to_skip,
 					  0);
 			}
-			ret = btrfs_qgroup_account_extent(trans, fs_info,
-					record->bytenr, record->num_bytes,
-					record->old_roots, new_roots);
+			ret = btrfs_qgroup_account_extent(trans, record->bytenr,
+							  record->num_bytes,
+							  record->old_roots,
+							  new_roots);
 			record->old_roots = NULL;
 			new_roots = NULL;
 		}
@@ -2136,9 +2193,9 @@ cleanup:
 /*
  * called from commit_transaction. Writes all changed qgroups to disk.
  */
-int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info)
+int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root = fs_info->quota_root;
 	int ret = 0;
 
@@ -2152,11 +2209,11 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 					  struct btrfs_qgroup, dirty);
 		list_del_init(&qgroup->dirty);
 		spin_unlock(&fs_info->qgroup_lock);
-		ret = update_qgroup_info_item(trans, quota_root, qgroup);
+		ret = update_qgroup_info_item(trans, qgroup);
 		if (ret)
 			fs_info->qgroup_flags |=
 					BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
-		ret = update_qgroup_limit_item(trans, quota_root, qgroup);
+		ret = update_qgroup_limit_item(trans, qgroup);
 		if (ret)
 			fs_info->qgroup_flags |=
 					BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
@@ -2168,7 +2225,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
 	spin_unlock(&fs_info->qgroup_lock);
 
-	ret = update_qgroup_status_item(trans, fs_info, quota_root);
+	ret = update_qgroup_status_item(trans);
 	if (ret)
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 
@@ -2181,13 +2238,13 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
  * cause a transaction abort so we take extra care here to only error
  * when a readonly fs is a reasonable outcome.
  */
-int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
-			 struct btrfs_qgroup_inherit *inherit)
+int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
+			 u64 objectid, struct btrfs_qgroup_inherit *inherit)
 {
 	int ret = 0;
 	int i;
 	u64 *i_qgroups;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_qgroup *srcgroup;
 	struct btrfs_qgroup *dstgroup;
@@ -2229,22 +2286,6 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	if (srcid) {
-		struct btrfs_root *srcroot;
-		struct btrfs_key srckey;
-
-		srckey.objectid = srcid;
-		srckey.type = BTRFS_ROOT_ITEM_KEY;
-		srckey.offset = (u64)-1;
-		srcroot = btrfs_read_fs_root_no_name(fs_info, &srckey);
-		if (IS_ERR(srcroot)) {
-			ret = PTR_ERR(srcroot);
-			goto out;
-		}
-
-		level_size = fs_info->nodesize;
-	}
-
 	/*
 	 * add qgroup to all inherited groups
 	 */
@@ -2253,12 +2294,12 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		for (i = 0; i < inherit->num_qgroups; ++i, ++i_qgroups) {
 			if (*i_qgroups == 0)
 				continue;
-			ret = add_qgroup_relation_item(trans, quota_root,
-						       objectid, *i_qgroups);
+			ret = add_qgroup_relation_item(trans, objectid,
+						       *i_qgroups);
 			if (ret && ret != -EEXIST)
 				goto out;
-			ret = add_qgroup_relation_item(trans, quota_root,
-						       *i_qgroups, objectid);
+			ret = add_qgroup_relation_item(trans, *i_qgroups,
+						       objectid);
 			if (ret && ret != -EEXIST)
 				goto out;
 		}
@@ -2281,7 +2322,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		dstgroup->rsv_rfer = inherit->lim.rsv_rfer;
 		dstgroup->rsv_excl = inherit->lim.rsv_excl;
 
-		ret = update_qgroup_limit_item(trans, quota_root, dstgroup);
+		ret = update_qgroup_limit_item(trans, dstgroup);
 		if (ret) {
 			fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 			btrfs_info(fs_info,
@@ -2301,6 +2342,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		 * our counts don't go crazy, so at this point the only
 		 * difference between the two roots should be the root node.
 		 */
+		level_size = fs_info->nodesize;
 		dstgroup->rfer = srcgroup->rfer;
 		dstgroup->rfer_cmpr = srcgroup->rfer_cmpr;
 		dstgroup->excl = level_size;
@@ -2598,10 +2640,10 @@ static bool is_last_leaf(struct btrfs_path *path)
  * returns < 0 on error, 0 when more leafs are to be scanned.
  * returns 1 when done.
  */
-static int
-qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
-		   struct btrfs_trans_handle *trans)
+static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans,
+			      struct btrfs_path *path)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_key found;
 	struct extent_buffer *scratch_leaf = NULL;
 	struct ulist *roots = NULL;
@@ -2669,8 +2711,8 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 		if (ret < 0)
 			goto out;
 		/* For rescan, just pass old_roots as NULL */
-		ret = btrfs_qgroup_account_extent(trans, fs_info,
-				found.objectid, num_bytes, NULL, roots);
+		ret = btrfs_qgroup_account_extent(trans, found.objectid,
+						  num_bytes, NULL, roots);
 		if (ret < 0)
 			goto out;
 	}
@@ -2716,7 +2758,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 		if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
 			err = -EINTR;
 		} else {
-			err = qgroup_rescan_leaf(fs_info, path, trans);
+			err = qgroup_rescan_leaf(trans, path);
 		}
 		if (err > 0)
 			btrfs_commit_transaction(trans);
@@ -2751,7 +2793,7 @@ out:
 			  err);
 		goto done;
 	}
-	ret = update_qgroup_status_item(trans, fs_info, fs_info->quota_root);
+	ret = update_qgroup_status_item(trans);
 	if (ret < 0) {
 		err = ret;
 		btrfs_err(fs_info, "fail to update qgroup status: %d", err);
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index d60dd06445ce..54b8bb282c0e 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -141,24 +141,19 @@ struct btrfs_qgroup {
 #define QGROUP_RELEASE		(1<<1)
 #define QGROUP_FREE		(1<<2)
 
-int btrfs_quota_enable(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info);
-int btrfs_quota_disable(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info);
+int btrfs_quota_enable(struct btrfs_fs_info *fs_info);
+int btrfs_quota_disable(struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
 void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
 				     bool interruptible);
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
-int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
-int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid);
-int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 qgroupid);
-int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 qgroupid,
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst);
+int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst);
+int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
+int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
+int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit);
 int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);
 void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
@@ -217,9 +212,8 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
  * Return <0 for error, like memory allocation failure or invalid parameter
  * (NULL trans)
  */
-int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
-		struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
-		gfp_t gfp_flag);
+int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+			      u64 num_bytes, gfp_t gfp_flag);
 
 /*
  * Inform qgroup to trace all leaf items of data
@@ -228,7 +222,6 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
  * Return <0 for error(ENOMEM)
  */
 int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct extent_buffer *eb);
 /*
  * Inform qgroup to trace a whole subtree, including all its child tree
@@ -241,20 +234,15 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
  * Return <0 for error(ENOMEM or tree search error)
  */
 int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root,
 			       struct extent_buffer *root_eb,
 			       u64 root_gen, int root_level);
-int
-btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
-			    u64 bytenr, u64 num_bytes,
-			    struct ulist *old_roots, struct ulist *new_roots);
+int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+				u64 num_bytes, struct ulist *old_roots,
+				struct ulist *new_roots);
 int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans);
-int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
-			 struct btrfs_qgroup_inherit *inherit);
+int btrfs_run_qgroups(struct btrfs_trans_handle *trans);
+int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
+			 u64 objectid, struct btrfs_qgroup_inherit *inherit);
 void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 			       u64 ref_root, u64 num_bytes,
 			       enum btrfs_qgroup_rsv_type type);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 5e4ad134b9ad..df41d7049936 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -5,32 +5,19 @@
  */
 
 #include <linux/sched.h>
-#include <linux/wait.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
-#include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/random.h>
-#include <linux/iocontext.h>
-#include <linux/capability.h>
-#include <linux/ratelimit.h>
-#include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/hash.h>
 #include <linux/list_sort.h>
 #include <linux/raid/xor.h>
 #include <linux/mm.h>
-#include <asm/div64.h>
 #include "ctree.h"
-#include "extent_map.h"
 #include "disk-io.h"
-#include "transaction.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "raid56.h"
 #include "async-thread.h"
-#include "check-integrity.h"
-#include "rcu-string.h"
 
 /* set when additional merges to this rbio are not allowed */
 #define RBIO_RMW_LOCKED_BIT	1
@@ -175,8 +162,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
 static noinline void finish_rmw(struct btrfs_raid_bio *rbio);
 static void rmw_work(struct btrfs_work *work);
 static void read_rebuild_work(struct btrfs_work *work);
-static void async_rmw_stripe(struct btrfs_raid_bio *rbio);
-static void async_read_rebuild(struct btrfs_raid_bio *rbio);
 static int fail_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio);
 static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed);
 static void __free_raid_bio(struct btrfs_raid_bio *rbio);
@@ -185,7 +170,13 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio);
 
 static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 					 int need_check);
-static void async_scrub_parity(struct btrfs_raid_bio *rbio);
+static void scrub_parity_work(struct btrfs_work *work);
+
+static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func)
+{
+	btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL);
+	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
+}
 
 /*
  * the stripe hash table is used for locking, and to collect
@@ -260,7 +251,7 @@ static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
 		s = kmap(rbio->bio_pages[i]);
 		d = kmap(rbio->stripe_pages[i]);
 
-		memcpy(d, s, PAGE_SIZE);
+		copy_page(d, s);
 
 		kunmap(rbio->bio_pages[i]);
 		kunmap(rbio->stripe_pages[i]);
@@ -516,32 +507,21 @@ static void run_xor(void **pages, int src_cnt, ssize_t len)
 }
 
 /*
- * returns true if the bio list inside this rbio
- * covers an entire stripe (no rmw required).
- * Must be called with the bio list lock held, or
- * at a time when you know it is impossible to add
- * new bios into the list
+ * Returns true if the bio list inside this rbio covers an entire stripe (no
+ * rmw required).
  */
-static int __rbio_is_full(struct btrfs_raid_bio *rbio)
+static int rbio_is_full(struct btrfs_raid_bio *rbio)
 {
+	unsigned long flags;
 	unsigned long size = rbio->bio_list_bytes;
 	int ret = 1;
 
+	spin_lock_irqsave(&rbio->bio_list_lock, flags);
 	if (size != rbio->nr_data * rbio->stripe_len)
 		ret = 0;
-
 	BUG_ON(size > rbio->nr_data * rbio->stripe_len);
-	return ret;
-}
-
-static int rbio_is_full(struct btrfs_raid_bio *rbio)
-{
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&rbio->bio_list_lock, flags);
-	ret = __rbio_is_full(rbio);
 	spin_unlock_irqrestore(&rbio->bio_list_lock, flags);
+
 	return ret;
 }
 
@@ -812,16 +792,16 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
 			spin_unlock_irqrestore(&h->lock, flags);
 
 			if (next->operation == BTRFS_RBIO_READ_REBUILD)
-				async_read_rebuild(next);
+				start_async_work(next, read_rebuild_work);
 			else if (next->operation == BTRFS_RBIO_REBUILD_MISSING) {
 				steal_rbio(rbio, next);
-				async_read_rebuild(next);
+				start_async_work(next, read_rebuild_work);
 			} else if (next->operation == BTRFS_RBIO_WRITE) {
 				steal_rbio(rbio, next);
-				async_rmw_stripe(next);
+				start_async_work(next, rmw_work);
 			} else if (next->operation == BTRFS_RBIO_PARITY_SCRUB) {
 				steal_rbio(rbio, next);
-				async_scrub_parity(next);
+				start_async_work(next, scrub_parity_work);
 			}
 
 			goto done_nolock;
@@ -1275,7 +1255,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 						pointers);
 		} else {
 			/* raid5 */
-			memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
+			copy_page(pointers[nr_data], pointers[0]);
 			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
 		}
 
@@ -1343,7 +1323,7 @@ write_data:
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 
 		submit_bio(bio);
 	}
@@ -1508,20 +1488,6 @@ cleanup:
 	rbio_orig_end_io(rbio, BLK_STS_IOERR);
 }
 
-static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
-{
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper, rmw_work, NULL, NULL);
-	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
-}
-
-static void async_read_rebuild(struct btrfs_raid_bio *rbio)
-{
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
-			read_rebuild_work, NULL, NULL);
-
-	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
-}
-
 /*
  * the stripe must be locked by the caller.  It will
  * unlock after all the writes are done
@@ -1599,7 +1565,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_rmw_end_io;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -1652,7 +1618,7 @@ static int partial_stripe_write(struct btrfs_raid_bio *rbio)
 
 	ret = lock_stripe_add(rbio);
 	if (ret == 0)
-		async_rmw_stripe(rbio);
+		start_async_work(rbio, rmw_work);
 	return 0;
 }
 
@@ -1720,8 +1686,11 @@ static void run_plug(struct btrfs_plug_cb *plug)
 		list_del_init(&cur->plug_list);
 
 		if (rbio_is_full(cur)) {
+			int ret;
+
 			/* we have a full stripe, send it down */
-			full_stripe_write(cur);
+			ret = full_stripe_write(cur);
+			BUG_ON(ret);
 			continue;
 		}
 		if (last) {
@@ -1941,9 +1910,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 			BUG_ON(failb != -1);
 pstripe:
 			/* Copy parity block into failed block to start with */
-			memcpy(pointers[faila],
-			       pointers[rbio->nr_data],
-			       PAGE_SIZE);
+			copy_page(pointers[faila], pointers[rbio->nr_data]);
 
 			/* rearrange the pointer array */
 			p = pointers[faila];
@@ -2145,7 +2112,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_recover_end_io;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -2448,7 +2415,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 						pointers);
 		} else {
 			/* raid5 */
-			memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
+			copy_page(pointers[nr_data], pointers[0]);
 			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
 		}
 
@@ -2456,7 +2423,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 		p = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
 		parity = kmap(p);
 		if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE))
-			memcpy(parity, pointers[rbio->scrubp], PAGE_SIZE);
+			copy_page(parity, pointers[rbio->scrubp]);
 		else
 			/* Parity is right, needn't writeback */
 			bitmap_clear(rbio->dbitmap, pagenr, 1);
@@ -2517,7 +2484,7 @@ submit_write:
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 
 		submit_bio(bio);
 	}
@@ -2699,7 +2666,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid56_parity_scrub_end_io;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -2728,18 +2695,10 @@ static void scrub_parity_work(struct btrfs_work *work)
 	raid56_parity_scrub_stripe(rbio);
 }
 
-static void async_scrub_parity(struct btrfs_raid_bio *rbio)
-{
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
-			scrub_parity_work, NULL, NULL);
-
-	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
-}
-
 void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio)
 {
 	if (!lock_stripe_add(rbio))
-		async_scrub_parity(rbio);
+		start_async_work(rbio, scrub_parity_work);
 }
 
 /* The following code is used for dev replace of a missing RAID 5/6 device. */
@@ -2781,5 +2740,5 @@ raid56_alloc_missing_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
 void raid56_submit_missing_rbio(struct btrfs_raid_bio *rbio)
 {
 	if (!lock_stripe_add(rbio))
-		async_read_rebuild(rbio);
+		start_async_work(rbio, read_rebuild_work);
 }
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 40f1bcef394d..dec14b739b10 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -7,7 +7,6 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
-#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 #include "ctree.h"
@@ -355,7 +354,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 		dev = bbio->stripes[nzones].dev;
 
 		/* cannot read ahead on missing device. */
-		 if (!dev->bdev)
+		if (!dev->bdev)
 			continue;
 
 		zone = reada_find_zone(dev, logical, bbio);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 879b76fa881a..8783a1776540 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -586,29 +586,6 @@ static struct btrfs_root *read_fs_root(struct btrfs_fs_info *fs_info,
 	return btrfs_get_fs_root(fs_info, &key, false);
 }
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static noinline_for_stack
-struct btrfs_root *find_tree_root(struct reloc_control *rc,
-				  struct extent_buffer *leaf,
-				  struct btrfs_extent_ref_v0 *ref0)
-{
-	struct btrfs_root *root;
-	u64 root_objectid = btrfs_ref_root_v0(leaf, ref0);
-	u64 generation = btrfs_ref_generation_v0(leaf, ref0);
-
-	BUG_ON(root_objectid == BTRFS_TREE_RELOC_OBJECTID);
-
-	root = read_fs_root(rc->extent_root->fs_info, root_objectid);
-	BUG_ON(IS_ERR(root));
-
-	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
-	    generation != btrfs_root_generation(&root->root_item))
-		return NULL;
-
-	return root;
-}
-#endif
-
 static noinline_for_stack
 int find_inline_backref(struct extent_buffer *leaf, int slot,
 			unsigned long *ptr, unsigned long *end)
@@ -621,12 +598,11 @@ int find_inline_backref(struct extent_buffer *leaf, int slot,
 	btrfs_item_key_to_cpu(leaf, &key, slot);
 
 	item_size = btrfs_item_size_nr(leaf, slot);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
 	if (item_size < sizeof(*ei)) {
-		WARN_ON(item_size != sizeof(struct btrfs_extent_item_v0));
+		btrfs_print_v0_err(leaf->fs_info);
+		btrfs_handle_fs_error(leaf->fs_info, -EINVAL, NULL);
 		return 1;
 	}
-#endif
 	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
 	WARN_ON(!(btrfs_extent_flags(leaf, ei) &
 		  BTRFS_EXTENT_FLAG_TREE_BLOCK));
@@ -792,7 +768,7 @@ again:
 			type = btrfs_get_extent_inline_ref_type(eb, iref,
 							BTRFS_REF_TYPE_BLOCK);
 			if (type == BTRFS_REF_TYPE_INVALID) {
-				err = -EINVAL;
+				err = -EUCLEAN;
 				goto out;
 			}
 			key.type = type;
@@ -811,29 +787,7 @@ again:
 			goto next;
 		}
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY ||
-		    key.type == BTRFS_EXTENT_REF_V0_KEY) {
-			if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
-				struct btrfs_extent_ref_v0 *ref0;
-				ref0 = btrfs_item_ptr(eb, path1->slots[0],
-						struct btrfs_extent_ref_v0);
-				if (key.objectid == key.offset) {
-					root = find_tree_root(rc, eb, ref0);
-					if (root && !should_ignore_root(root))
-						cur->root = root;
-					else
-						list_add(&cur->list, &useless);
-					break;
-				}
-				if (is_cowonly_root(btrfs_ref_root_v0(eb,
-								      ref0)))
-					cur->cowonly = 1;
-			}
-#else
-		ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
-#endif
 			if (key.objectid == key.offset) {
 				/*
 				 * only root blocks of reloc trees use
@@ -876,6 +830,12 @@ again:
 			edge->node[UPPER] = upper;
 
 			goto next;
+		} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
+			err = -EINVAL;
+			btrfs_print_v0_err(rc->extent_root->fs_info);
+			btrfs_handle_fs_error(rc->extent_root->fs_info, err,
+					      NULL);
+			goto out;
 		} else if (key.type != BTRFS_TREE_BLOCK_REF_KEY) {
 			goto next;
 		}
@@ -1321,18 +1281,19 @@ static void __del_reloc_root(struct btrfs_root *root)
 	struct mapping_node *node = NULL;
 	struct reloc_control *rc = fs_info->reloc_ctl;
 
-	spin_lock(&rc->reloc_root_tree.lock);
-	rb_node = tree_search(&rc->reloc_root_tree.rb_root,
-			      root->node->start);
-	if (rb_node) {
-		node = rb_entry(rb_node, struct mapping_node, rb_node);
-		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
+	if (rc) {
+		spin_lock(&rc->reloc_root_tree.lock);
+		rb_node = tree_search(&rc->reloc_root_tree.rb_root,
+				      root->node->start);
+		if (rb_node) {
+			node = rb_entry(rb_node, struct mapping_node, rb_node);
+			rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
+		}
+		spin_unlock(&rc->reloc_root_tree.lock);
+		if (!node)
+			return;
+		BUG_ON((struct btrfs_root *)node->data != root);
 	}
-	spin_unlock(&rc->reloc_root_tree.lock);
-
-	if (!node)
-		return;
-	BUG_ON((struct btrfs_root *)node->data != root);
 
 	spin_lock(&fs_info->trans_lock);
 	list_del_init(&root->root_list);
@@ -1918,13 +1879,12 @@ again:
 		 *    and tree block numbers, if current trans doesn't free
 		 *    data reloc tree inode.
 		 */
-		ret = btrfs_qgroup_trace_subtree(trans, src, parent,
+		ret = btrfs_qgroup_trace_subtree(trans, parent,
 				btrfs_header_generation(parent),
 				btrfs_header_level(parent));
 		if (ret < 0)
 			break;
-		ret = btrfs_qgroup_trace_subtree(trans, dest,
-				path->nodes[level],
+		ret = btrfs_qgroup_trace_subtree(trans, path->nodes[level],
 				btrfs_header_generation(path->nodes[level]),
 				btrfs_header_level(path->nodes[level]));
 		if (ret < 0)
@@ -3333,48 +3293,6 @@ int relocate_data_extent(struct inode *inode, struct btrfs_key *extent_key,
 	return 0;
 }
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static int get_ref_objectid_v0(struct reloc_control *rc,
-			       struct btrfs_path *path,
-			       struct btrfs_key *extent_key,
-			       u64 *ref_objectid, int *path_change)
-{
-	struct btrfs_key key;
-	struct extent_buffer *leaf;
-	struct btrfs_extent_ref_v0 *ref0;
-	int ret;
-	int slot;
-
-	leaf = path->nodes[0];
-	slot = path->slots[0];
-	while (1) {
-		if (slot >= btrfs_header_nritems(leaf)) {
-			ret = btrfs_next_leaf(rc->extent_root, path);
-			if (ret < 0)
-				return ret;
-			BUG_ON(ret > 0);
-			leaf = path->nodes[0];
-			slot = path->slots[0];
-			if (path_change)
-				*path_change = 1;
-		}
-		btrfs_item_key_to_cpu(leaf, &key, slot);
-		if (key.objectid != extent_key->objectid)
-			return -ENOENT;
-
-		if (key.type != BTRFS_EXTENT_REF_V0_KEY) {
-			slot++;
-			continue;
-		}
-		ref0 = btrfs_item_ptr(leaf, slot,
-				struct btrfs_extent_ref_v0);
-		*ref_objectid = btrfs_ref_objectid_v0(leaf, ref0);
-		break;
-	}
-	return 0;
-}
-#endif
-
 /*
  * helper to add a tree block to the list.
  * the major work is getting the generation and level of the block
@@ -3407,23 +3325,12 @@ static int add_tree_block(struct reloc_control *rc,
 			level = (int)extent_key->offset;
 		}
 		generation = btrfs_extent_generation(eb, ei);
+	} else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
+		btrfs_print_v0_err(eb->fs_info);
+		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
+		return -EINVAL;
 	} else {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		u64 ref_owner;
-		int ret;
-
-		BUG_ON(item_size != sizeof(struct btrfs_extent_item_v0));
-		ret = get_ref_objectid_v0(rc, path, extent_key,
-					  &ref_owner, NULL);
-		if (ret < 0)
-			return ret;
-		BUG_ON(ref_owner >= BTRFS_MAX_LEVEL);
-		level = (int)ref_owner;
-		/* FIXME: get real generation */
-		generation = 0;
-#else
 		BUG();
-#endif
 	}
 
 	btrfs_release_path(path);
@@ -3563,11 +3470,8 @@ static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
 	key.offset = 0;
 
 	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
-	if (IS_ERR(inode) || is_bad_inode(inode)) {
-		if (!IS_ERR(inode))
-			iput(inode);
+	if (IS_ERR(inode))
 		return -ENOENT;
-	}
 
 truncate:
 	ret = btrfs_check_trunc_cache_free_space(fs_info,
@@ -3781,12 +3685,7 @@ int add_data_references(struct reloc_control *rc,
 	eb = path->nodes[0];
 	ptr = btrfs_item_ptr_offset(eb, path->slots[0]);
 	end = ptr + btrfs_item_size_nr(eb, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (ptr + sizeof(struct btrfs_extent_item_v0) == end)
-		ptr = end;
-	else
-#endif
-		ptr += sizeof(struct btrfs_extent_item);
+	ptr += sizeof(struct btrfs_extent_item);
 
 	while (ptr < end) {
 		iref = (struct btrfs_extent_inline_ref *)ptr;
@@ -3801,7 +3700,7 @@ int add_data_references(struct reloc_control *rc,
 			ret = find_data_references(rc, extent_key,
 						   eb, dref, blocks);
 		} else {
-			ret = -EINVAL;
+			ret = -EUCLEAN;
 			btrfs_err(rc->extent_root->fs_info,
 		     "extent %llu slot %d has an invalid inline ref type",
 			     eb->start, path->slots[0]);
@@ -3832,13 +3731,7 @@ int add_data_references(struct reloc_control *rc,
 		if (key.objectid != extent_key->objectid)
 			break;
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		if (key.type == BTRFS_SHARED_DATA_REF_KEY ||
-		    key.type == BTRFS_EXTENT_REF_V0_KEY) {
-#else
-		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
-#endif
 			ret = __add_tree_block(rc, key.offset, blocksize,
 					       blocks);
 		} else if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
@@ -3846,6 +3739,10 @@ int add_data_references(struct reloc_control *rc,
 					      struct btrfs_extent_data_ref);
 			ret = find_data_references(rc, extent_key,
 						   eb, dref, blocks);
+		} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
+			btrfs_print_v0_err(eb->fs_info);
+			btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
+			ret = -EINVAL;
 		} else {
 			ret = 0;
 		}
@@ -4084,41 +3981,13 @@ restart:
 			flags = btrfs_extent_flags(path->nodes[0], ei);
 			ret = check_extent_flags(flags);
 			BUG_ON(ret);
-
+		} else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
+			err = -EINVAL;
+			btrfs_print_v0_err(trans->fs_info);
+			btrfs_abort_transaction(trans, err);
+			break;
 		} else {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-			u64 ref_owner;
-			int path_change = 0;
-
-			BUG_ON(item_size !=
-			       sizeof(struct btrfs_extent_item_v0));
-			ret = get_ref_objectid_v0(rc, path, &key, &ref_owner,
-						  &path_change);
-			if (ret < 0) {
-				err = ret;
-				break;
-			}
-			if (ref_owner < BTRFS_FIRST_FREE_OBJECTID)
-				flags = BTRFS_EXTENT_FLAG_TREE_BLOCK;
-			else
-				flags = BTRFS_EXTENT_FLAG_DATA;
-
-			if (path_change) {
-				btrfs_release_path(path);
-
-				path->search_commit_root = 1;
-				path->skip_locking = 1;
-				ret = btrfs_search_slot(NULL, rc->extent_root,
-							&key, path, 0, 0);
-				if (ret < 0) {
-					err = ret;
-					break;
-				}
-				BUG_ON(ret > 0);
-			}
-#else
 			BUG();
-#endif
 		}
 
 		if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
@@ -4169,8 +4038,7 @@ restart:
 		}
 	}
 	if (trans && progress && err == -ENOSPC) {
-		ret = btrfs_force_chunk_alloc(trans, fs_info,
-					      rc->block_group->flags);
+		ret = btrfs_force_chunk_alloc(trans, rc->block_group->flags);
 		if (ret == 1) {
 			err = 0;
 			progress = 0;
@@ -4284,7 +4152,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
-	BUG_ON(IS_ERR(inode) || is_bad_inode(inode));
+	BUG_ON(IS_ERR(inode));
 	BTRFS_I(inode)->index_cnt = group->key.objectid;
 
 	err = btrfs_orphan_add(trans, BTRFS_I(inode));
@@ -4375,7 +4243,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 	rc->block_group = btrfs_lookup_block_group(fs_info, group_start);
 	BUG_ON(!rc->block_group);
 
-	ret = btrfs_inc_block_group_ro(fs_info, rc->block_group);
+	ret = btrfs_inc_block_group_ro(rc->block_group);
 	if (ret) {
 		err = ret;
 		goto out;
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index c451285976ac..65bda0682928 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -320,9 +320,9 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info)
 
 /* drop the root item for 'key' from the tree root */
 int btrfs_del_root(struct btrfs_trans_handle *trans,
-		   struct btrfs_fs_info *fs_info, const struct btrfs_key *key)
+		   const struct btrfs_key *key)
 {
-	struct btrfs_root *root = fs_info->tree_root;
+	struct btrfs_root *root = trans->fs_info->tree_root;
 	struct btrfs_path *path;
 	int ret;
 
@@ -341,13 +341,12 @@ out:
 	return ret;
 }
 
-int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
-		       const char *name, int name_len)
+int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 *sequence, const char *name,
+		       int name_len)
 
 {
-	struct btrfs_root *tree_root = fs_info->tree_root;
+	struct btrfs_root *tree_root = trans->fs_info->tree_root;
 	struct btrfs_path *path;
 	struct btrfs_root_ref *ref;
 	struct extent_buffer *leaf;
@@ -413,12 +412,11 @@ out:
  *
  * Will return 0, -ENOMEM, or anything from the CoW path
  */
-int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 sequence,
-		       const char *name, int name_len)
+int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 sequence, const char *name,
+		       int name_len)
 {
-	struct btrfs_root *tree_root = fs_info->tree_root;
+	struct btrfs_root *tree_root = trans->fs_info->tree_root;
 	struct btrfs_key key;
 	int ret;
 	struct btrfs_path *path;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 6702896cdb8f..3be1456b5116 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -188,32 +188,6 @@ struct scrub_ctx {
 	refcount_t              refs;
 };
 
-struct scrub_fixup_nodatasum {
-	struct scrub_ctx	*sctx;
-	struct btrfs_device	*dev;
-	u64			logical;
-	struct btrfs_root	*root;
-	struct btrfs_work	work;
-	int			mirror_num;
-};
-
-struct scrub_nocow_inode {
-	u64			inum;
-	u64			offset;
-	u64			root;
-	struct list_head	list;
-};
-
-struct scrub_copy_nocow_ctx {
-	struct scrub_ctx	*sctx;
-	u64			logical;
-	u64			len;
-	int			mirror_num;
-	u64			physical_for_dev_replace;
-	struct list_head	inodes;
-	struct btrfs_work	work;
-};
-
 struct scrub_warning {
 	struct btrfs_path	*path;
 	u64			extent_item_size;
@@ -232,8 +206,6 @@ struct full_stripe_lock {
 
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
 static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
-static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx);
-static void scrub_pending_trans_workers_dec(struct scrub_ctx *sctx);
 static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
 static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 				     struct scrub_block *sblocks_for_recheck);
@@ -277,13 +249,6 @@ static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
 static void scrub_wr_submit(struct scrub_ctx *sctx);
 static void scrub_wr_bio_end_io(struct bio *bio);
 static void scrub_wr_bio_end_io_worker(struct btrfs_work *work);
-static int write_page_nocow(struct scrub_ctx *sctx,
-			    u64 physical_for_dev_replace, struct page *page);
-static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
-				      struct scrub_copy_nocow_ctx *ctx);
-static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
-			    int mirror_num, u64 physical_for_dev_replace);
-static void copy_nocow_pages_worker(struct btrfs_work *work);
 static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_put_ctx(struct scrub_ctx *sctx);
@@ -555,60 +520,6 @@ out:
 	return ret;
 }
 
-/*
- * used for workers that require transaction commits (i.e., for the
- * NOCOW case)
- */
-static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx)
-{
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-
-	refcount_inc(&sctx->refs);
-	/*
-	 * increment scrubs_running to prevent cancel requests from
-	 * completing as long as a worker is running. we must also
-	 * increment scrubs_paused to prevent deadlocking on pause
-	 * requests used for transactions commits (as the worker uses a
-	 * transaction context). it is safe to regard the worker
-	 * as paused for all matters practical. effectively, we only
-	 * avoid cancellation requests from completing.
-	 */
-	mutex_lock(&fs_info->scrub_lock);
-	atomic_inc(&fs_info->scrubs_running);
-	atomic_inc(&fs_info->scrubs_paused);
-	mutex_unlock(&fs_info->scrub_lock);
-
-	/*
-	 * check if @scrubs_running=@scrubs_paused condition
-	 * inside wait_event() is not an atomic operation.
-	 * which means we may inc/dec @scrub_running/paused
-	 * at any time. Let's wake up @scrub_pause_wait as
-	 * much as we can to let commit transaction blocked less.
-	 */
-	wake_up(&fs_info->scrub_pause_wait);
-
-	atomic_inc(&sctx->workers_pending);
-}
-
-/* used for workers that require transaction commits */
-static void scrub_pending_trans_workers_dec(struct scrub_ctx *sctx)
-{
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-
-	/*
-	 * see scrub_pending_trans_workers_inc() why we're pretending
-	 * to be paused in the scrub counters
-	 */
-	mutex_lock(&fs_info->scrub_lock);
-	atomic_dec(&fs_info->scrubs_running);
-	atomic_dec(&fs_info->scrubs_paused);
-	mutex_unlock(&fs_info->scrub_lock);
-	atomic_dec(&sctx->workers_pending);
-	wake_up(&fs_info->scrub_pause_wait);
-	wake_up(&sctx->list_wait);
-	scrub_put_ctx(sctx);
-}
-
 static void scrub_free_csums(struct scrub_ctx *sctx)
 {
 	while (!list_empty(&sctx->csum_list)) {
@@ -882,194 +793,6 @@ out:
 	btrfs_free_path(path);
 }
 
-static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
-{
-	struct page *page = NULL;
-	unsigned long index;
-	struct scrub_fixup_nodatasum *fixup = fixup_ctx;
-	int ret;
-	int corrected = 0;
-	struct btrfs_key key;
-	struct inode *inode = NULL;
-	struct btrfs_fs_info *fs_info;
-	u64 end = offset + PAGE_SIZE - 1;
-	struct btrfs_root *local_root;
-	int srcu_index;
-
-	key.objectid = root;
-	key.type = BTRFS_ROOT_ITEM_KEY;
-	key.offset = (u64)-1;
-
-	fs_info = fixup->root->fs_info;
-	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
-
-	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-	if (IS_ERR(local_root)) {
-		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-		return PTR_ERR(local_root);
-	}
-
-	key.type = BTRFS_INODE_ITEM_KEY;
-	key.objectid = inum;
-	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
-	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-
-	index = offset >> PAGE_SHIFT;
-
-	page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
-	if (!page) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	if (PageUptodate(page)) {
-		if (PageDirty(page)) {
-			/*
-			 * we need to write the data to the defect sector. the
-			 * data that was in that sector is not in memory,
-			 * because the page was modified. we must not write the
-			 * modified page to that sector.
-			 *
-			 * TODO: what could be done here: wait for the delalloc
-			 *       runner to write out that page (might involve
-			 *       COW) and see whether the sector is still
-			 *       referenced afterwards.
-			 *
-			 * For the meantime, we'll treat this error
-			 * incorrectable, although there is a chance that a
-			 * later scrub will find the bad sector again and that
-			 * there's no dirty page in memory, then.
-			 */
-			ret = -EIO;
-			goto out;
-		}
-		ret = repair_io_failure(fs_info, inum, offset, PAGE_SIZE,
-					fixup->logical, page,
-					offset - page_offset(page),
-					fixup->mirror_num);
-		unlock_page(page);
-		corrected = !ret;
-	} else {
-		/*
-		 * we need to get good data first. the general readpage path
-		 * will call repair_io_failure for us, we just have to make
-		 * sure we read the bad mirror.
-		 */
-		ret = set_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
-					EXTENT_DAMAGED);
-		if (ret) {
-			/* set_extent_bits should give proper error */
-			WARN_ON(ret > 0);
-			if (ret > 0)
-				ret = -EFAULT;
-			goto out;
-		}
-
-		ret = extent_read_full_page(&BTRFS_I(inode)->io_tree, page,
-						btrfs_get_extent,
-						fixup->mirror_num);
-		wait_on_page_locked(page);
-
-		corrected = !test_range_bit(&BTRFS_I(inode)->io_tree, offset,
-						end, EXTENT_DAMAGED, 0, NULL);
-		if (!corrected)
-			clear_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
-						EXTENT_DAMAGED);
-	}
-
-out:
-	if (page)
-		put_page(page);
-
-	iput(inode);
-
-	if (ret < 0)
-		return ret;
-
-	if (ret == 0 && corrected) {
-		/*
-		 * we only need to call readpage for one of the inodes belonging
-		 * to this extent. so make iterate_extent_inodes stop
-		 */
-		return 1;
-	}
-
-	return -EIO;
-}
-
-static void scrub_fixup_nodatasum(struct btrfs_work *work)
-{
-	struct btrfs_fs_info *fs_info;
-	int ret;
-	struct scrub_fixup_nodatasum *fixup;
-	struct scrub_ctx *sctx;
-	struct btrfs_trans_handle *trans = NULL;
-	struct btrfs_path *path;
-	int uncorrectable = 0;
-
-	fixup = container_of(work, struct scrub_fixup_nodatasum, work);
-	sctx = fixup->sctx;
-	fs_info = fixup->root->fs_info;
-
-	path = btrfs_alloc_path();
-	if (!path) {
-		spin_lock(&sctx->stat_lock);
-		++sctx->stat.malloc_errors;
-		spin_unlock(&sctx->stat_lock);
-		uncorrectable = 1;
-		goto out;
-	}
-
-	trans = btrfs_join_transaction(fixup->root);
-	if (IS_ERR(trans)) {
-		uncorrectable = 1;
-		goto out;
-	}
-
-	/*
-	 * the idea is to trigger a regular read through the standard path. we
-	 * read a page from the (failed) logical address by specifying the
-	 * corresponding copynum of the failed sector. thus, that readpage is
-	 * expected to fail.
-	 * that is the point where on-the-fly error correction will kick in
-	 * (once it's finished) and rewrite the failed sector if a good copy
-	 * can be found.
-	 */
-	ret = iterate_inodes_from_logical(fixup->logical, fs_info, path,
-					  scrub_fixup_readpage, fixup, false);
-	if (ret < 0) {
-		uncorrectable = 1;
-		goto out;
-	}
-	WARN_ON(ret != 1);
-
-	spin_lock(&sctx->stat_lock);
-	++sctx->stat.corrected_errors;
-	spin_unlock(&sctx->stat_lock);
-
-out:
-	if (trans && !IS_ERR(trans))
-		btrfs_end_transaction(trans);
-	if (uncorrectable) {
-		spin_lock(&sctx->stat_lock);
-		++sctx->stat.uncorrectable_errors;
-		spin_unlock(&sctx->stat_lock);
-		btrfs_dev_replace_stats_inc(
-			&fs_info->dev_replace.num_uncorrectable_read_errors);
-		btrfs_err_rl_in_rcu(fs_info,
-		    "unable to fixup (nodatasum) error at logical %llu on dev %s",
-			fixup->logical, rcu_str_deref(fixup->dev->name));
-	}
-
-	btrfs_free_path(path);
-	kfree(fixup);
-
-	scrub_pending_trans_workers_dec(sctx);
-}
-
 static inline void scrub_get_recover(struct scrub_recover *recover)
 {
 	refcount_inc(&recover->refs);
@@ -1264,42 +987,6 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	}
 
 	/*
-	 * NOTE: Even for nodatasum case, it's still possible that it's a
-	 * compressed data extent, thus scrub_fixup_nodatasum(), which write
-	 * inode page cache onto disk, could cause serious data corruption.
-	 *
-	 * So here we could only read from disk, and hope our recovery could
-	 * reach disk before the newer write.
-	 */
-	if (0 && !is_metadata && !have_csum) {
-		struct scrub_fixup_nodatasum *fixup_nodatasum;
-
-		WARN_ON(sctx->is_dev_replace);
-
-		/*
-		 * !is_metadata and !have_csum, this means that the data
-		 * might not be COWed, that it might be modified
-		 * concurrently. The general strategy to work on the
-		 * commit root does not help in the case when COW is not
-		 * used.
-		 */
-		fixup_nodatasum = kzalloc(sizeof(*fixup_nodatasum), GFP_NOFS);
-		if (!fixup_nodatasum)
-			goto did_not_correct_error;
-		fixup_nodatasum->sctx = sctx;
-		fixup_nodatasum->dev = dev;
-		fixup_nodatasum->logical = logical;
-		fixup_nodatasum->root = fs_info->extent_root;
-		fixup_nodatasum->mirror_num = failed_mirror_index + 1;
-		scrub_pending_trans_workers_inc(sctx);
-		btrfs_init_work(&fixup_nodatasum->work, btrfs_scrub_helper,
-				scrub_fixup_nodatasum, NULL, NULL);
-		btrfs_queue_work(fs_info->scrub_workers,
-				 &fixup_nodatasum->work);
-		goto out;
-	}
-
-	/*
 	 * now build and submit the bios for the other mirrors, check
 	 * checksums.
 	 * First try to pick the mirror which is completely without I/O
@@ -1866,7 +1553,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 		bio = btrfs_io_bio_alloc(1);
 		bio_set_dev(bio, page_bad->dev->bdev);
 		bio->bi_iter.bi_sector = page_bad->physical >> 9;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 
 		ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
 		if (PAGE_SIZE != ret) {
@@ -1961,7 +1648,7 @@ again:
 		bio->bi_end_io = scrub_wr_bio_end_io;
 		bio_set_dev(bio, sbio->dev->bdev);
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 		sbio->status = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical_for_dev_replace ||
@@ -2361,7 +2048,7 @@ again:
 		bio->bi_end_io = scrub_bio_end_io;
 		bio_set_dev(bio, sbio->dev->bdev);
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 		sbio->status = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical ||
@@ -2800,17 +2487,10 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map,
 			have_csum = scrub_find_csum(sctx, logical, csum);
 			if (have_csum == 0)
 				++sctx->stat.no_csum;
-			if (0 && sctx->is_dev_replace && !have_csum) {
-				ret = copy_nocow_pages(sctx, logical, l,
-						       mirror_num,
-						      physical_for_dev_replace);
-				goto behind_scrub_pages;
-			}
 		}
 		ret = scrub_pages(sctx, logical, l, physical, dev, flags, gen,
 				  mirror_num, have_csum ? csum : NULL, 0,
 				  physical_for_dev_replace);
-behind_scrub_pages:
 		if (ret)
 			return ret;
 		len -= l;
@@ -3863,7 +3543,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 * -> btrfs_scrub_pause()
 		 */
 		scrub_pause_on(fs_info);
-		ret = btrfs_inc_block_group_ro(fs_info, cache);
+		ret = btrfs_inc_block_group_ro(cache);
 		if (!ret && is_dev_replace) {
 			/*
 			 * If we are doing a device replace wait for any tasks
@@ -3982,14 +3662,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
 		    btrfs_block_group_used(&cache->item) == 0) {
 			spin_unlock(&cache->lock);
-			spin_lock(&fs_info->unused_bgs_lock);
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &fs_info->unused_bgs);
-			}
-			spin_unlock(&fs_info->unused_bgs_lock);
+			btrfs_mark_bg_unused(cache);
 		} else {
 			spin_unlock(&cache->lock);
 		}
@@ -4072,10 +3745,6 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 		if (!fs_info->scrub_wr_completion_workers)
 			goto fail_scrub_wr_completion_workers;
 
-		fs_info->scrub_nocow_workers =
-			btrfs_alloc_workqueue(fs_info, "scrubnc", flags, 1, 0);
-		if (!fs_info->scrub_nocow_workers)
-			goto fail_scrub_nocow_workers;
 		fs_info->scrub_parity_workers =
 			btrfs_alloc_workqueue(fs_info, "scrubparity", flags,
 					      max_active, 2);
@@ -4086,8 +3755,6 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 	return 0;
 
 fail_scrub_parity_workers:
-	btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
-fail_scrub_nocow_workers:
 	btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
 fail_scrub_wr_completion_workers:
 	btrfs_destroy_workqueue(fs_info->scrub_workers);
@@ -4100,7 +3767,6 @@ static noinline_for_stack void scrub_workers_put(struct btrfs_fs_info *fs_info)
 	if (--fs_info->scrub_workers_refcnt == 0) {
 		btrfs_destroy_workqueue(fs_info->scrub_workers);
 		btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
-		btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
 		btrfs_destroy_workqueue(fs_info->scrub_parity_workers);
 	}
 	WARN_ON(fs_info->scrub_workers_refcnt < 0);
@@ -4113,7 +3779,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	struct scrub_ctx *sctx;
 	int ret;
 	struct btrfs_device *dev;
-	struct rcu_string *name;
 
 	if (btrfs_fs_closing(fs_info))
 		return -EINVAL;
@@ -4167,11 +3832,8 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	if (!is_dev_replace && !readonly &&
 	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		rcu_read_lock();
-		name = rcu_dereference(dev->name);
-		btrfs_err(fs_info, "scrub: device %s is not writable",
-			  name->str);
-		rcu_read_unlock();
+		btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable",
+				rcu_str_deref(dev->name));
 		return -EROFS;
 	}
 
@@ -4359,330 +4021,3 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
 	*extent_dev = bbio->stripes[0].dev;
 	btrfs_put_bbio(bbio);
 }
-
-static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
-			    int mirror_num, u64 physical_for_dev_replace)
-{
-	struct scrub_copy_nocow_ctx *nocow_ctx;
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-
-	nocow_ctx = kzalloc(sizeof(*nocow_ctx), GFP_NOFS);
-	if (!nocow_ctx) {
-		spin_lock(&sctx->stat_lock);
-		sctx->stat.malloc_errors++;
-		spin_unlock(&sctx->stat_lock);
-		return -ENOMEM;
-	}
-
-	scrub_pending_trans_workers_inc(sctx);
-
-	nocow_ctx->sctx = sctx;
-	nocow_ctx->logical = logical;
-	nocow_ctx->len = len;
-	nocow_ctx->mirror_num = mirror_num;
-	nocow_ctx->physical_for_dev_replace = physical_for_dev_replace;
-	btrfs_init_work(&nocow_ctx->work, btrfs_scrubnc_helper,
-			copy_nocow_pages_worker, NULL, NULL);
-	INIT_LIST_HEAD(&nocow_ctx->inodes);
-	btrfs_queue_work(fs_info->scrub_nocow_workers,
-			 &nocow_ctx->work);
-
-	return 0;
-}
-
-static int record_inode_for_nocow(u64 inum, u64 offset, u64 root, void *ctx)
-{
-	struct scrub_copy_nocow_ctx *nocow_ctx = ctx;
-	struct scrub_nocow_inode *nocow_inode;
-
-	nocow_inode = kzalloc(sizeof(*nocow_inode), GFP_NOFS);
-	if (!nocow_inode)
-		return -ENOMEM;
-	nocow_inode->inum = inum;
-	nocow_inode->offset = offset;
-	nocow_inode->root = root;
-	list_add_tail(&nocow_inode->list, &nocow_ctx->inodes);
-	return 0;
-}
-
-#define COPY_COMPLETE 1
-
-static void copy_nocow_pages_worker(struct btrfs_work *work)
-{
-	struct scrub_copy_nocow_ctx *nocow_ctx =
-		container_of(work, struct scrub_copy_nocow_ctx, work);
-	struct scrub_ctx *sctx = nocow_ctx->sctx;
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-	struct btrfs_root *root = fs_info->extent_root;
-	u64 logical = nocow_ctx->logical;
-	u64 len = nocow_ctx->len;
-	int mirror_num = nocow_ctx->mirror_num;
-	u64 physical_for_dev_replace = nocow_ctx->physical_for_dev_replace;
-	int ret;
-	struct btrfs_trans_handle *trans = NULL;
-	struct btrfs_path *path;
-	int not_written = 0;
-
-	path = btrfs_alloc_path();
-	if (!path) {
-		spin_lock(&sctx->stat_lock);
-		sctx->stat.malloc_errors++;
-		spin_unlock(&sctx->stat_lock);
-		not_written = 1;
-		goto out;
-	}
-
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans)) {
-		not_written = 1;
-		goto out;
-	}
-
-	ret = iterate_inodes_from_logical(logical, fs_info, path,
-			record_inode_for_nocow, nocow_ctx, false);
-	if (ret != 0 && ret != -ENOENT) {
-		btrfs_warn(fs_info,
-			   "iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d",
-			   logical, physical_for_dev_replace, len, mirror_num,
-			   ret);
-		not_written = 1;
-		goto out;
-	}
-
-	btrfs_end_transaction(trans);
-	trans = NULL;
-	while (!list_empty(&nocow_ctx->inodes)) {
-		struct scrub_nocow_inode *entry;
-		entry = list_first_entry(&nocow_ctx->inodes,
-					 struct scrub_nocow_inode,
-					 list);
-		list_del_init(&entry->list);
-		ret = copy_nocow_pages_for_inode(entry->inum, entry->offset,
-						 entry->root, nocow_ctx);
-		kfree(entry);
-		if (ret == COPY_COMPLETE) {
-			ret = 0;
-			break;
-		} else if (ret) {
-			break;
-		}
-	}
-out:
-	while (!list_empty(&nocow_ctx->inodes)) {
-		struct scrub_nocow_inode *entry;
-		entry = list_first_entry(&nocow_ctx->inodes,
-					 struct scrub_nocow_inode,
-					 list);
-		list_del_init(&entry->list);
-		kfree(entry);
-	}
-	if (trans && !IS_ERR(trans))
-		btrfs_end_transaction(trans);
-	if (not_written)
-		btrfs_dev_replace_stats_inc(&fs_info->dev_replace.
-					    num_uncorrectable_read_errors);
-
-	btrfs_free_path(path);
-	kfree(nocow_ctx);
-
-	scrub_pending_trans_workers_dec(sctx);
-}
-
-static int check_extent_to_block(struct btrfs_inode *inode, u64 start, u64 len,
-				 u64 logical)
-{
-	struct extent_state *cached_state = NULL;
-	struct btrfs_ordered_extent *ordered;
-	struct extent_io_tree *io_tree;
-	struct extent_map *em;
-	u64 lockstart = start, lockend = start + len - 1;
-	int ret = 0;
-
-	io_tree = &inode->io_tree;
-
-	lock_extent_bits(io_tree, lockstart, lockend, &cached_state);
-	ordered = btrfs_lookup_ordered_range(inode, lockstart, len);
-	if (ordered) {
-		btrfs_put_ordered_extent(ordered);
-		ret = 1;
-		goto out_unlock;
-	}
-
-	em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
-	if (IS_ERR(em)) {
-		ret = PTR_ERR(em);
-		goto out_unlock;
-	}
-
-	/*
-	 * This extent does not actually cover the logical extent anymore,
-	 * move on to the next inode.
-	 */
-	if (em->block_start > logical ||
-	    em->block_start + em->block_len < logical + len ||
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
-		free_extent_map(em);
-		ret = 1;
-		goto out_unlock;
-	}
-	free_extent_map(em);
-
-out_unlock:
-	unlock_extent_cached(io_tree, lockstart, lockend, &cached_state);
-	return ret;
-}
-
-static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
-				      struct scrub_copy_nocow_ctx *nocow_ctx)
-{
-	struct btrfs_fs_info *fs_info = nocow_ctx->sctx->fs_info;
-	struct btrfs_key key;
-	struct inode *inode;
-	struct page *page;
-	struct btrfs_root *local_root;
-	struct extent_io_tree *io_tree;
-	u64 physical_for_dev_replace;
-	u64 nocow_ctx_logical;
-	u64 len = nocow_ctx->len;
-	unsigned long index;
-	int srcu_index;
-	int ret = 0;
-	int err = 0;
-
-	key.objectid = root;
-	key.type = BTRFS_ROOT_ITEM_KEY;
-	key.offset = (u64)-1;
-
-	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
-
-	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-	if (IS_ERR(local_root)) {
-		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-		return PTR_ERR(local_root);
-	}
-
-	key.type = BTRFS_INODE_ITEM_KEY;
-	key.objectid = inum;
-	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
-	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-
-	/* Avoid truncate/dio/punch hole.. */
-	inode_lock(inode);
-	inode_dio_wait(inode);
-
-	physical_for_dev_replace = nocow_ctx->physical_for_dev_replace;
-	io_tree = &BTRFS_I(inode)->io_tree;
-	nocow_ctx_logical = nocow_ctx->logical;
-
-	ret = check_extent_to_block(BTRFS_I(inode), offset, len,
-			nocow_ctx_logical);
-	if (ret) {
-		ret = ret > 0 ? 0 : ret;
-		goto out;
-	}
-
-	while (len >= PAGE_SIZE) {
-		index = offset >> PAGE_SHIFT;
-again:
-		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
-		if (!page) {
-			btrfs_err(fs_info, "find_or_create_page() failed");
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		if (PageUptodate(page)) {
-			if (PageDirty(page))
-				goto next_page;
-		} else {
-			ClearPageError(page);
-			err = extent_read_full_page(io_tree, page,
-							   btrfs_get_extent,
-							   nocow_ctx->mirror_num);
-			if (err) {
-				ret = err;
-				goto next_page;
-			}
-
-			lock_page(page);
-			/*
-			 * If the page has been remove from the page cache,
-			 * the data on it is meaningless, because it may be
-			 * old one, the new data may be written into the new
-			 * page in the page cache.
-			 */
-			if (page->mapping != inode->i_mapping) {
-				unlock_page(page);
-				put_page(page);
-				goto again;
-			}
-			if (!PageUptodate(page)) {
-				ret = -EIO;
-				goto next_page;
-			}
-		}
-
-		ret = check_extent_to_block(BTRFS_I(inode), offset, len,
-					    nocow_ctx_logical);
-		if (ret) {
-			ret = ret > 0 ? 0 : ret;
-			goto next_page;
-		}
-
-		err = write_page_nocow(nocow_ctx->sctx,
-				       physical_for_dev_replace, page);
-		if (err)
-			ret = err;
-next_page:
-		unlock_page(page);
-		put_page(page);
-
-		if (ret)
-			break;
-
-		offset += PAGE_SIZE;
-		physical_for_dev_replace += PAGE_SIZE;
-		nocow_ctx_logical += PAGE_SIZE;
-		len -= PAGE_SIZE;
-	}
-	ret = COPY_COMPLETE;
-out:
-	inode_unlock(inode);
-	iput(inode);
-	return ret;
-}
-
-static int write_page_nocow(struct scrub_ctx *sctx,
-			    u64 physical_for_dev_replace, struct page *page)
-{
-	struct bio *bio;
-	struct btrfs_device *dev;
-
-	dev = sctx->wr_tgtdev;
-	if (!dev)
-		return -EIO;
-	if (!dev->bdev) {
-		btrfs_warn_rl(dev->fs_info,
-			"scrub write_page_nocow(bdev == NULL) is unexpected");
-		return -EIO;
-	}
-	bio = btrfs_io_bio_alloc(1);
-	bio->bi_iter.bi_size = 0;
-	bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
-	bio_set_dev(bio, dev->bdev);
-	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
-	/* bio_add_page won't fail on a freshly allocated bio */
-	bio_add_page(bio, page, PAGE_SIZE, 0);
-
-	if (btrfsic_submit_bio_wait(bio)) {
-		bio_put(bio);
-		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
-		return -EIO;
-	}
-
-	bio_put(bio);
-	return 0;
-}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index c47f62b19226..ba8950bfd9c7 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -100,6 +100,7 @@ struct send_ctx {
 	u64 cur_inode_rdev;
 	u64 cur_inode_last_extent;
 	u64 cur_inode_next_write_offset;
+	bool ignore_cur_inode;
 
 	u64 send_progress;
 
@@ -1500,7 +1501,7 @@ static int read_symlink(struct btrfs_root *root,
 	BUG_ON(compression);
 
 	off = btrfs_file_extent_inline_start(ei);
-	len = btrfs_file_extent_inline_len(path->nodes[0], path->slots[0], ei);
+	len = btrfs_file_extent_ram_bytes(path->nodes[0], ei);
 
 	ret = fs_path_add_from_extent_buffer(dest, path->nodes[0], off, len);
 
@@ -5006,6 +5007,15 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 	u64 len;
 	int ret = 0;
 
+	/*
+	 * A hole that starts at EOF or beyond it. Since we do not yet support
+	 * fallocate (for extent preallocation and hole punching), sending a
+	 * write of zeroes starting at EOF or beyond would later require issuing
+	 * a truncate operation which would undo the write and achieve nothing.
+	 */
+	if (offset >= sctx->cur_inode_size)
+		return 0;
+
 	if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
 		return send_update_extent(sctx, offset, end - offset);
 
@@ -5160,7 +5170,7 @@ static int clone_range(struct send_ctx *sctx,
 		ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 		type = btrfs_file_extent_type(leaf, ei);
 		if (type == BTRFS_FILE_EXTENT_INLINE) {
-			ext_len = btrfs_file_extent_inline_len(leaf, slot, ei);
+			ext_len = btrfs_file_extent_ram_bytes(leaf, ei);
 			ext_len = PAGE_ALIGN(ext_len);
 		} else {
 			ext_len = btrfs_file_extent_num_bytes(leaf, ei);
@@ -5236,8 +5246,7 @@ static int send_write_or_clone(struct send_ctx *sctx,
 			struct btrfs_file_extent_item);
 	type = btrfs_file_extent_type(path->nodes[0], ei);
 	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		len = btrfs_file_extent_inline_len(path->nodes[0],
-						   path->slots[0], ei);
+		len = btrfs_file_extent_ram_bytes(path->nodes[0], ei);
 		/*
 		 * it is possible the inline item won't cover the whole page,
 		 * but there may be items after this page.  Make
@@ -5375,7 +5384,7 @@ static int is_extent_unchanged(struct send_ctx *sctx,
 		}
 
 		if (right_type == BTRFS_FILE_EXTENT_INLINE) {
-			right_len = btrfs_file_extent_inline_len(eb, slot, ei);
+			right_len = btrfs_file_extent_ram_bytes(eb, ei);
 			right_len = PAGE_ALIGN(right_len);
 		} else {
 			right_len = btrfs_file_extent_num_bytes(eb, ei);
@@ -5496,8 +5505,7 @@ static int get_last_extent(struct send_ctx *sctx, u64 offset)
 			    struct btrfs_file_extent_item);
 	type = btrfs_file_extent_type(path->nodes[0], fi);
 	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		u64 size = btrfs_file_extent_inline_len(path->nodes[0],
-							path->slots[0], fi);
+		u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
 		extent_end = ALIGN(key.offset + size,
 				   sctx->send_root->fs_info->sectorsize);
 	} else {
@@ -5560,7 +5568,7 @@ static int range_is_hole_in_parent(struct send_ctx *sctx,
 		fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 		if (btrfs_file_extent_type(leaf, fi) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			u64 size = btrfs_file_extent_inline_len(leaf, slot, fi);
+			u64 size = btrfs_file_extent_ram_bytes(leaf, fi);
 
 			extent_end = ALIGN(key.offset + size,
 					   root->fs_info->sectorsize);
@@ -5606,8 +5614,7 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 			    struct btrfs_file_extent_item);
 	type = btrfs_file_extent_type(path->nodes[0], fi);
 	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		u64 size = btrfs_file_extent_inline_len(path->nodes[0],
-							path->slots[0], fi);
+		u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
 		extent_end = ALIGN(key->offset + size,
 				   sctx->send_root->fs_info->sectorsize);
 	} else {
@@ -5799,6 +5806,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 	int pending_move = 0;
 	int refs_processed = 0;
 
+	if (sctx->ignore_cur_inode)
+		return 0;
+
 	ret = process_recorded_refs_if_needed(sctx, at_end, &pending_move,
 					      &refs_processed);
 	if (ret < 0)
@@ -5917,6 +5927,93 @@ out:
 	return ret;
 }
 
+struct parent_paths_ctx {
+	struct list_head *refs;
+	struct send_ctx *sctx;
+};
+
+static int record_parent_ref(int num, u64 dir, int index, struct fs_path *name,
+			     void *ctx)
+{
+	struct parent_paths_ctx *ppctx = ctx;
+
+	return record_ref(ppctx->sctx->parent_root, dir, name, ppctx->sctx,
+			  ppctx->refs);
+}
+
+/*
+ * Issue unlink operations for all paths of the current inode found in the
+ * parent snapshot.
+ */
+static int btrfs_unlink_all_paths(struct send_ctx *sctx)
+{
+	LIST_HEAD(deleted_refs);
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct parent_paths_ctx ctx;
+	int ret;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = sctx->cur_ino;
+	key.type = BTRFS_INODE_REF_KEY;
+	key.offset = 0;
+	ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	ctx.refs = &deleted_refs;
+	ctx.sctx = sctx;
+
+	while (true) {
+		struct extent_buffer *eb = path->nodes[0];
+		int slot = path->slots[0];
+
+		if (slot >= btrfs_header_nritems(eb)) {
+			ret = btrfs_next_leaf(sctx->parent_root, path);
+			if (ret < 0)
+				goto out;
+			else if (ret > 0)
+				break;
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(eb, &key, slot);
+		if (key.objectid != sctx->cur_ino)
+			break;
+		if (key.type != BTRFS_INODE_REF_KEY &&
+		    key.type != BTRFS_INODE_EXTREF_KEY)
+			break;
+
+		ret = iterate_inode_ref(sctx->parent_root, path, &key, 1,
+					record_parent_ref, &ctx);
+		if (ret < 0)
+			goto out;
+
+		path->slots[0]++;
+	}
+
+	while (!list_empty(&deleted_refs)) {
+		struct recorded_ref *ref;
+
+		ref = list_first_entry(&deleted_refs, struct recorded_ref, list);
+		ret = send_unlink(sctx, ref->full_path);
+		if (ret < 0)
+			goto out;
+		fs_path_free(ref->full_path);
+		list_del(&ref->list);
+		kfree(ref);
+	}
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	if (ret)
+		__free_recorded_refs(&deleted_refs);
+	return ret;
+}
+
 static int changed_inode(struct send_ctx *sctx,
 			 enum btrfs_compare_tree_result result)
 {
@@ -5931,6 +6028,7 @@ static int changed_inode(struct send_ctx *sctx,
 	sctx->cur_inode_new_gen = 0;
 	sctx->cur_inode_last_extent = (u64)-1;
 	sctx->cur_inode_next_write_offset = 0;
+	sctx->ignore_cur_inode = false;
 
 	/*
 	 * Set send_progress to current inode. This will tell all get_cur_xxx
@@ -5971,6 +6069,33 @@ static int changed_inode(struct send_ctx *sctx,
 			sctx->cur_inode_new_gen = 1;
 	}
 
+	/*
+	 * Normally we do not find inodes with a link count of zero (orphans)
+	 * because the most common case is to create a snapshot and use it
+	 * for a send operation. However other less common use cases involve
+	 * using a subvolume and send it after turning it to RO mode just
+	 * after deleting all hard links of a file while holding an open
+	 * file descriptor against it or turning a RO snapshot into RW mode,
+	 * keep an open file descriptor against a file, delete it and then
+	 * turn the snapshot back to RO mode before using it for a send
+	 * operation. So if we find such cases, ignore the inode and all its
+	 * items completely if it's a new inode, or if it's a changed inode
+	 * make sure all its previous paths (from the parent snapshot) are all
+	 * unlinked and all other the inode items are ignored.
+	 */
+	if (result == BTRFS_COMPARE_TREE_NEW ||
+	    result == BTRFS_COMPARE_TREE_CHANGED) {
+		u32 nlinks;
+
+		nlinks = btrfs_inode_nlink(sctx->left_path->nodes[0], left_ii);
+		if (nlinks == 0) {
+			sctx->ignore_cur_inode = true;
+			if (result == BTRFS_COMPARE_TREE_CHANGED)
+				ret = btrfs_unlink_all_paths(sctx);
+			goto out;
+		}
+	}
+
 	if (result == BTRFS_COMPARE_TREE_NEW) {
 		sctx->cur_inode_gen = left_gen;
 		sctx->cur_inode_new = 1;
@@ -6309,15 +6434,17 @@ static int changed_cb(struct btrfs_path *left_path,
 	    key->objectid == BTRFS_FREE_SPACE_OBJECTID)
 		goto out;
 
-	if (key->type == BTRFS_INODE_ITEM_KEY)
+	if (key->type == BTRFS_INODE_ITEM_KEY) {
 		ret = changed_inode(sctx, result);
-	else if (key->type == BTRFS_INODE_REF_KEY ||
-		 key->type == BTRFS_INODE_EXTREF_KEY)
-		ret = changed_ref(sctx, result);
-	else if (key->type == BTRFS_XATTR_ITEM_KEY)
-		ret = changed_xattr(sctx, result);
-	else if (key->type == BTRFS_EXTENT_DATA_KEY)
-		ret = changed_extent(sctx, result);
+	} else if (!sctx->ignore_cur_inode) {
+		if (key->type == BTRFS_INODE_REF_KEY ||
+		    key->type == BTRFS_INODE_EXTREF_KEY)
+			ret = changed_ref(sctx, result);
+		else if (key->type == BTRFS_XATTR_ITEM_KEY)
+			ret = changed_xattr(sctx, result);
+		else if (key->type == BTRFS_EXTENT_DATA_KEY)
+			ret = changed_extent(sctx, result);
+	}
 
 out:
 	return ret;
@@ -6328,7 +6455,6 @@ static int full_send_tree(struct send_ctx *sctx)
 	int ret;
 	struct btrfs_root *send_root = sctx->send_root;
 	struct btrfs_key key;
-	struct btrfs_key found_key;
 	struct btrfs_path *path;
 	struct extent_buffer *eb;
 	int slot;
@@ -6350,17 +6476,13 @@ static int full_send_tree(struct send_ctx *sctx)
 	while (1) {
 		eb = path->nodes[0];
 		slot = path->slots[0];
-		btrfs_item_key_to_cpu(eb, &found_key, slot);
+		btrfs_item_key_to_cpu(eb, &key, slot);
 
-		ret = changed_cb(path, NULL, &found_key,
+		ret = changed_cb(path, NULL, &key,
 				 BTRFS_COMPARE_TREE_NEW, sctx);
 		if (ret < 0)
 			goto out;
 
-		key.objectid = found_key.objectid;
-		key.type = found_key.type;
-		key.offset = found_key.offset + 1;
-
 		ret = btrfs_next_item(send_root, path);
 		if (ret < 0)
 			goto out;
diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c
index b7b4acb12833..4c13b737f568 100644
--- a/fs/btrfs/struct-funcs.c
+++ b/fs/btrfs/struct-funcs.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2007 Oracle.  All rights reserved.
  */
 
-#include <linux/highmem.h>
 #include <asm/unaligned.h>
 
 #include "ctree.h"
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 81107ad49f3a..6601c9aa5e35 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -5,7 +5,6 @@
 
 #include <linux/blkdev.h>
 #include <linux/module.h>
-#include <linux/buffer_head.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
@@ -15,8 +14,6 @@
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mount.h>
-#include <linux/mpage.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/statfs.h>
 #include <linux/compat.h>
@@ -468,9 +465,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_subvolrootid:
 		case Opt_device:
 			/*
-			 * These are parsed by btrfs_parse_subvol_options
-			 * and btrfs_parse_early_options
-			 * and can be happily ignored here.
+			 * These are parsed by btrfs_parse_subvol_options or
+			 * btrfs_parse_device_options and can be ignored here.
 			 */
 			break;
 		case Opt_nodatasum:
@@ -760,6 +756,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_recovery:
 			btrfs_warn(info,
 				   "'recovery' is deprecated, use 'usebackuproot' instead");
+			/* fall through */
 		case Opt_usebackuproot:
 			btrfs_info(info,
 				   "trying to use backup root at mount time");
@@ -885,13 +882,16 @@ out:
  * All other options will be parsed on much later in the mount process and
  * only when we need to allocate a new super block.
  */
-static int btrfs_parse_early_options(const char *options, fmode_t flags,
-		void *holder, struct btrfs_fs_devices **fs_devices)
+static int btrfs_parse_device_options(const char *options, fmode_t flags,
+				      void *holder)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *device_name, *opts, *orig, *p;
+	struct btrfs_device *device = NULL;
 	int error = 0;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	if (!options)
 		return 0;
 
@@ -917,11 +917,13 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 				error = -ENOMEM;
 				goto out;
 			}
-			error = btrfs_scan_one_device(device_name,
-					flags, holder, fs_devices);
+			device = btrfs_scan_one_device(device_name, flags,
+					holder);
 			kfree(device_name);
-			if (error)
+			if (IS_ERR(device)) {
+				error = PTR_ERR(device);
 				goto out;
+			}
 		}
 	}
 
@@ -935,8 +937,8 @@ out:
  *
  * The value is later passed to mount_subvol()
  */
-static int btrfs_parse_subvol_options(const char *options, fmode_t flags,
-		char **subvol_name, u64 *subvol_objectid)
+static int btrfs_parse_subvol_options(const char *options, char **subvol_name,
+		u64 *subvol_objectid)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *opts, *orig, *p;
@@ -948,7 +950,7 @@ static int btrfs_parse_subvol_options(const char *options, fmode_t flags,
 
 	/*
 	 * strsep changes the string, duplicate it because
-	 * btrfs_parse_early_options gets called later
+	 * btrfs_parse_device_options gets called later
 	 */
 	opts = kstrdup(options, GFP_KERNEL);
 	if (!opts)
@@ -1517,6 +1519,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 {
 	struct block_device *bdev = NULL;
 	struct super_block *s;
+	struct btrfs_device *device = NULL;
 	struct btrfs_fs_devices *fs_devices = NULL;
 	struct btrfs_fs_info *fs_info = NULL;
 	struct security_mnt_opts new_sec_opts;
@@ -1526,12 +1529,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
 
-	error = btrfs_parse_early_options(data, mode, fs_type,
-					  &fs_devices);
-	if (error) {
-		return ERR_PTR(error);
-	}
-
 	security_init_mnt_opts(&new_sec_opts);
 	if (data) {
 		error = parse_security_options(data, &new_sec_opts);
@@ -1539,10 +1536,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 			return ERR_PTR(error);
 	}
 
-	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
-	if (error)
-		goto error_sec_opts;
-
 	/*
 	 * Setup a dummy root and fs_info for test/set super.  This is because
 	 * we don't actually fill this stuff out until open_ctree, but we need
@@ -1555,8 +1548,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 		goto error_sec_opts;
 	}
 
-	fs_info->fs_devices = fs_devices;
-
 	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
 	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
 	security_init_mnt_opts(&fs_info->security_opts);
@@ -1565,7 +1556,25 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 		goto error_fs_info;
 	}
 
+	mutex_lock(&uuid_mutex);
+	error = btrfs_parse_device_options(data, mode, fs_type);
+	if (error) {
+		mutex_unlock(&uuid_mutex);
+		goto error_fs_info;
+	}
+
+	device = btrfs_scan_one_device(device_name, mode, fs_type);
+	if (IS_ERR(device)) {
+		mutex_unlock(&uuid_mutex);
+		error = PTR_ERR(device);
+		goto error_fs_info;
+	}
+
+	fs_devices = device->fs_devices;
+	fs_info->fs_devices = fs_devices;
+
 	error = btrfs_open_devices(fs_devices, mode, fs_type);
+	mutex_unlock(&uuid_mutex);
 	if (error)
 		goto error_fs_info;
 
@@ -1650,8 +1659,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
 
-	error = btrfs_parse_subvol_options(data, mode,
-					  &subvol_name, &subvol_objectid);
+	error = btrfs_parse_subvol_options(data, &subvol_name,
+					&subvol_objectid);
 	if (error) {
 		kfree(subvol_name);
 		return ERR_PTR(error);
@@ -2098,14 +2107,9 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 				btrfs_account_ro_block_groups_free_space(found);
 
 			for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
-				if (!list_empty(&found->block_groups[i])) {
-					switch (i) {
-					case BTRFS_RAID_DUP:
-					case BTRFS_RAID_RAID1:
-					case BTRFS_RAID_RAID10:
-						factor = 2;
-					}
-				}
+				if (!list_empty(&found->block_groups[i]))
+					factor = btrfs_bg_type_to_factor(
+						btrfs_raid_array[i].bg_flag);
 			}
 		}
 
@@ -2222,7 +2226,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg)
 {
 	struct btrfs_ioctl_vol_args *vol;
-	struct btrfs_fs_devices *fs_devices;
+	struct btrfs_device *device = NULL;
 	int ret = -ENOTTY;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -2234,15 +2238,24 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
-		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
-					    &btrfs_root_fs_type, &fs_devices);
+		mutex_lock(&uuid_mutex);
+		device = btrfs_scan_one_device(vol->name, FMODE_READ,
+					       &btrfs_root_fs_type);
+		ret = PTR_ERR_OR_ZERO(device);
+		mutex_unlock(&uuid_mutex);
 		break;
 	case BTRFS_IOC_DEVICES_READY:
-		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
-					    &btrfs_root_fs_type, &fs_devices);
-		if (ret)
+		mutex_lock(&uuid_mutex);
+		device = btrfs_scan_one_device(vol->name, FMODE_READ,
+					       &btrfs_root_fs_type);
+		if (IS_ERR(device)) {
+			mutex_unlock(&uuid_mutex);
+			ret = PTR_ERR(device);
 			break;
-		ret = !(fs_devices->num_devices == fs_devices->total_devices);
+		}
+		ret = !(device->fs_devices->num_devices ==
+			device->fs_devices->total_devices);
+		mutex_unlock(&uuid_mutex);
 		break;
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
 		ret = btrfs_ioctl_get_supported_features((void __user*)arg);
@@ -2290,7 +2303,6 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 	struct btrfs_fs_devices *cur_devices;
 	struct btrfs_device *dev, *first_dev = NULL;
 	struct list_head *head;
-	struct rcu_string *name;
 
 	/*
 	 * Lightweight locking of the devices. We should not need
@@ -2314,12 +2326,10 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 		cur_devices = cur_devices->seed;
 	}
 
-	if (first_dev) {
-		name = rcu_dereference(first_dev->name);
-		seq_escape(m, name->str, " \t\n\\");
-	} else {
+	if (first_dev)
+		seq_escape(m, rcu_str_deref(first_dev->name), " \t\n\\");
+	else
 		WARN_ON(1);
-	}
 	rcu_read_unlock();
 	return 0;
 }
@@ -2331,7 +2341,6 @@ static const struct super_operations btrfs_super_ops = {
 	.sync_fs	= btrfs_sync_fs,
 	.show_options	= btrfs_show_options,
 	.show_devname	= btrfs_show_devname,
-	.write_inode	= btrfs_write_inode,
 	.alloc_inode	= btrfs_alloc_inode,
 	.destroy_inode	= btrfs_destroy_inode,
 	.statfs		= btrfs_statfs,
@@ -2369,7 +2378,7 @@ static __cold void btrfs_interface_exit(void)
 
 static void __init btrfs_print_mod_info(void)
 {
-	pr_info("Btrfs loaded, crc32c=%s"
+	static const char options[] = ""
 #ifdef CONFIG_BTRFS_DEBUG
 			", debug=on"
 #endif
@@ -2382,8 +2391,8 @@ static void __init btrfs_print_mod_info(void)
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 			", ref-verify=on"
 #endif
-			"\n",
-			crc32c_impl());
+			;
+	pr_info("Btrfs loaded, crc32c=%s%s\n", crc32c_impl(), options);
 }
 
 static int __init init_btrfs_fs(void)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 4a4e960c7c66..3717c864ba23 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -7,10 +7,8 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
-#include <linux/buffer_head.h>
 #include <linux/kobject.h>
 #include <linux/bug.h>
-#include <linux/genhd.h>
 #include <linux/debugfs.h>
 
 #include "ctree.h"
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index ace94db09d29..412b910b04cc 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -216,7 +216,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 	btrfs_init_dummy_trans(&trans, fs_info);
 
 	test_msg("qgroup basic add");
-	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FS_TREE_OBJECTID);
+	ret = btrfs_create_qgroup(&trans, BTRFS_FS_TREE_OBJECTID);
 	if (ret) {
 		test_err("couldn't create a qgroup %d", ret);
 		return ret;
@@ -249,8 +249,8 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
@@ -285,8 +285,8 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return -EINVAL;
@@ -322,7 +322,7 @@ static int test_multiple_refs(struct btrfs_root *root,
 	 * We have BTRFS_FS_TREE_OBJECTID created already from the
 	 * previous test.
 	 */
-	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FIRST_FREE_OBJECTID);
+	ret = btrfs_create_qgroup(&trans, BTRFS_FIRST_FREE_OBJECTID);
 	if (ret) {
 		test_err("couldn't create a qgroup %d", ret);
 		return ret;
@@ -350,8 +350,8 @@ static int test_multiple_refs(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
@@ -385,8 +385,8 @@ static int test_multiple_refs(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
@@ -426,8 +426,8 @@ static int test_multiple_refs(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index ff5f6c719976..3b84f5015029 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -241,7 +241,7 @@ loop:
 	refcount_set(&cur_trans->use_count, 2);
 	atomic_set(&cur_trans->pending_ordered, 0);
 	cur_trans->flags = 0;
-	cur_trans->start_time = get_seconds();
+	cur_trans->start_time = ktime_get_seconds();
 
 	memset(&cur_trans->delayed_refs, 0, sizeof(cur_trans->delayed_refs));
 
@@ -680,7 +680,7 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root)
 
 	trans = start_transaction(root, 0, TRANS_ATTACH,
 				  BTRFS_RESERVE_NO_FLUSH, true);
-	if (IS_ERR(trans) && PTR_ERR(trans) == -ENOENT)
+	if (trans == ERR_PTR(-ENOENT))
 		btrfs_wait_for_commit(root->fs_info, 0);
 
 	return trans;
@@ -1152,7 +1152,7 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans)
 	ret = btrfs_run_dev_replace(trans, fs_info);
 	if (ret)
 		return ret;
-	ret = btrfs_run_qgroups(trans, fs_info);
+	ret = btrfs_run_qgroups(trans);
 	if (ret)
 		return ret;
 
@@ -1355,8 +1355,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 		goto out;
 
 	/* Now qgroup are all updated, we can inherit it to new qgroups */
-	ret = btrfs_qgroup_inherit(trans, fs_info,
-				   src->root_key.objectid, dst_objectid,
+	ret = btrfs_qgroup_inherit(trans, src->root_key.objectid, dst_objectid,
 				   inherit);
 	if (ret < 0)
 		goto out;
@@ -1574,7 +1573,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	/*
 	 * insert root back/forward references
 	 */
-	ret = btrfs_add_root_ref(trans, fs_info, objectid,
+	ret = btrfs_add_root_ref(trans, objectid,
 				 parent_root->root_key.objectid,
 				 btrfs_ino(BTRFS_I(parent_inode)), index,
 				 dentry->d_name.name, dentry->d_name.len);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 94439482a0ec..4cbb1b55387d 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -48,7 +48,7 @@ struct btrfs_transaction {
 	int aborted;
 	struct list_head list;
 	struct extent_io_tree dirty_pages;
-	unsigned long start_time;
+	time64_t start_time;
 	wait_queue_head_t writer_wait;
 	wait_queue_head_t commit_wait;
 	wait_queue_head_t pending_wait;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 8d40e7dd8c30..db835635372f 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -19,6 +19,7 @@
 #include "tree-checker.h"
 #include "disk-io.h"
 #include "compression.h"
+#include "volumes.h"
 
 /*
  * Error message should follow the following format:
@@ -353,6 +354,102 @@ static int check_dir_item(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+__printf(4, 5)
+__cold
+static void block_group_err(const struct btrfs_fs_info *fs_info,
+			    const struct extent_buffer *eb, int slot,
+			    const char *fmt, ...)
+{
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(fs_info,
+	"corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node",
+		btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
+		key.objectid, key.offset, &vaf);
+	va_end(args);
+}
+
+static int check_block_group_item(struct btrfs_fs_info *fs_info,
+				  struct extent_buffer *leaf,
+				  struct btrfs_key *key, int slot)
+{
+	struct btrfs_block_group_item bgi;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+	u64 flags;
+	u64 type;
+
+	/*
+	 * Here we don't really care about alignment since extent allocator can
+	 * handle it.  We care more about the size, as if one block group is
+	 * larger than maximum size, it's must be some obvious corruption.
+	 */
+	if (key->offset > BTRFS_MAX_DATA_CHUNK_SIZE || key->offset == 0) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group size, have %llu expect (0, %llu]",
+				key->offset, BTRFS_MAX_DATA_CHUNK_SIZE);
+		return -EUCLEAN;
+	}
+
+	if (item_size != sizeof(bgi)) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid item size, have %u expect %zu",
+				item_size, sizeof(bgi));
+		return -EUCLEAN;
+	}
+
+	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+			   sizeof(bgi));
+	if (btrfs_block_group_chunk_objectid(&bgi) !=
+	    BTRFS_FIRST_CHUNK_TREE_OBJECTID) {
+		block_group_err(fs_info, leaf, slot,
+		"invalid block group chunk objectid, have %llu expect %llu",
+				btrfs_block_group_chunk_objectid(&bgi),
+				BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+		return -EUCLEAN;
+	}
+
+	if (btrfs_block_group_used(&bgi) > key->offset) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group used, have %llu expect [0, %llu)",
+				btrfs_block_group_used(&bgi), key->offset);
+		return -EUCLEAN;
+	}
+
+	flags = btrfs_block_group_flags(&bgi);
+	if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) {
+		block_group_err(fs_info, leaf, slot,
+"invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
+			flags & BTRFS_BLOCK_GROUP_PROFILE_MASK,
+			hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK));
+		return -EUCLEAN;
+	}
+
+	type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
+	if (type != BTRFS_BLOCK_GROUP_DATA &&
+	    type != BTRFS_BLOCK_GROUP_METADATA &&
+	    type != BTRFS_BLOCK_GROUP_SYSTEM &&
+	    type != (BTRFS_BLOCK_GROUP_METADATA |
+			   BTRFS_BLOCK_GROUP_DATA)) {
+		block_group_err(fs_info, leaf, slot,
+"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx",
+			type, hweight64(type),
+			BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA,
+			BTRFS_BLOCK_GROUP_SYSTEM,
+			BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA);
+		return -EUCLEAN;
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */
@@ -374,6 +471,9 @@ static int check_leaf_item(struct btrfs_fs_info *fs_info,
 	case BTRFS_XATTR_ITEM_KEY:
 		ret = check_dir_item(fs_info, leaf, key, slot);
 		break;
+	case BTRFS_BLOCK_GROUP_ITEM_KEY:
+		ret = check_block_group_item(fs_info, leaf, key, slot);
+		break;
 	}
 	return ret;
 }
@@ -396,9 +496,22 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf,
 	 * skip this check for relocation trees.
 	 */
 	if (nritems == 0 && !btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_RELOC)) {
+		u64 owner = btrfs_header_owner(leaf);
 		struct btrfs_root *check_root;
 
-		key.objectid = btrfs_header_owner(leaf);
+		/* These trees must never be empty */
+		if (owner == BTRFS_ROOT_TREE_OBJECTID ||
+		    owner == BTRFS_CHUNK_TREE_OBJECTID ||
+		    owner == BTRFS_EXTENT_TREE_OBJECTID ||
+		    owner == BTRFS_DEV_TREE_OBJECTID ||
+		    owner == BTRFS_FS_TREE_OBJECTID ||
+		    owner == BTRFS_DATA_RELOC_TREE_OBJECTID) {
+			generic_err(fs_info, leaf, 0,
+			"invalid root, root %llu must never be empty",
+				    owner);
+			return -EUCLEAN;
+		}
+		key.objectid = owner;
 		key.type = BTRFS_ROOT_ITEM_KEY;
 		key.offset = (u64)-1;
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f8220ec02036..1650dc44a5e3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -545,12 +545,8 @@ static noinline struct inode *read_one_inode(struct btrfs_root *root,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 	inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
-	if (IS_ERR(inode)) {
+	if (IS_ERR(inode))
 		inode = NULL;
-	} else if (is_bad_inode(inode)) {
-		iput(inode);
-		inode = NULL;
-	}
 	return inode;
 }
 
@@ -597,7 +593,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
 			nbytes = 0;
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
-		size = btrfs_file_extent_inline_len(eb, slot, item);
+		size = btrfs_file_extent_ram_bytes(eb, item);
 		nbytes = btrfs_file_extent_ram_bytes(eb, item);
 		extent_end = ALIGN(start + size,
 				   fs_info->sectorsize);
@@ -685,7 +681,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		 * as the owner of the file extent changed from log tree
 		 * (doesn't affect qgroup) to fs/file tree(affects qgroup)
 		 */
-		ret = btrfs_qgroup_trace_extent(trans, fs_info,
+		ret = btrfs_qgroup_trace_extent(trans,
 				btrfs_file_extent_disk_bytenr(eb, item),
 				btrfs_file_extent_disk_num_bytes(eb, item),
 				GFP_NOFS);
@@ -715,7 +711,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 				 * allocation tree
 				 */
 				ret = btrfs_alloc_logged_file_extent(trans,
-						fs_info,
 						root->root_key.objectid,
 						key->objectid, offset, &ins);
 				if (ret)
@@ -1291,6 +1286,46 @@ again:
 	return ret;
 }
 
+static int btrfs_inode_ref_exists(struct inode *inode, struct inode *dir,
+				  const u8 ref_type, const char *name,
+				  const int namelen)
+{
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	const u64 parent_id = btrfs_ino(BTRFS_I(dir));
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = btrfs_ino(BTRFS_I(inode));
+	key.type = ref_type;
+	if (key.type == BTRFS_INODE_REF_KEY)
+		key.offset = parent_id;
+	else
+		key.offset = btrfs_extref_hash(parent_id, name, namelen);
+
+	ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
+	if (key.type == BTRFS_INODE_EXTREF_KEY)
+		ret = btrfs_find_name_in_ext_backref(path->nodes[0],
+						     path->slots[0], parent_id,
+						     name, namelen, NULL);
+	else
+		ret = btrfs_find_name_in_backref(path->nodes[0], path->slots[0],
+						 name, namelen, NULL);
+
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 /*
  * replay one inode back reference item found in the log tree.
  * eb, slot and key refer to the buffer and key found in the log tree.
@@ -1400,6 +1435,32 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				}
 			}
 
+			/*
+			 * If a reference item already exists for this inode
+			 * with the same parent and name, but different index,
+			 * drop it and the corresponding directory index entries
+			 * from the parent before adding the new reference item
+			 * and dir index entries, otherwise we would fail with
+			 * -EEXIST returned from btrfs_add_link() below.
+			 */
+			ret = btrfs_inode_ref_exists(inode, dir, key->type,
+						     name, namelen);
+			if (ret > 0) {
+				ret = btrfs_unlink_inode(trans, root,
+							 BTRFS_I(dir),
+							 BTRFS_I(inode),
+							 name, namelen);
+				/*
+				 * If we dropped the link count to 0, bump it so
+				 * that later the iput() on the inode will not
+				 * free it. We will fixup the link count later.
+				 */
+				if (!ret && inode->i_nlink == 0)
+					inc_nlink(inode);
+			}
+			if (ret < 0)
+				goto out;
+
 			/* insert our name */
 			ret = btrfs_add_link(trans, BTRFS_I(dir),
 					BTRFS_I(inode),
@@ -2120,7 +2181,7 @@ again:
 						     dir_key->offset,
 						     name, name_len, 0);
 		}
-		if (!log_di || (IS_ERR(log_di) && PTR_ERR(log_di) == -ENOENT)) {
+		if (!log_di || log_di == ERR_PTR(-ENOENT)) {
 			btrfs_dir_item_key_to_cpu(eb, di, &location);
 			btrfs_release_path(path);
 			btrfs_release_path(log_path);
@@ -2933,7 +2994,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	/* bail out if we need to do a full commit */
 	if (btrfs_need_log_full_commit(fs_info, trans)) {
 		ret = -EAGAIN;
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&root->log_mutex);
 		goto out;
 	}
@@ -2951,7 +3011,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (ret) {
 		blk_finish_plug(&plug);
 		btrfs_abort_transaction(trans, ret);
-		btrfs_free_logged_extents(log, log_transid);
 		btrfs_set_log_full_commit(fs_info, trans);
 		mutex_unlock(&root->log_mutex);
 		goto out;
@@ -3002,7 +3061,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 		btrfs_wait_tree_log_extents(log, mark);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = -EAGAIN;
 		goto out;
@@ -3020,7 +3078,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (atomic_read(&log_root_tree->log_commit[index2])) {
 		blk_finish_plug(&plug);
 		ret = btrfs_wait_tree_log_extents(log, mark);
-		btrfs_wait_logged_extents(trans, log, log_transid);
 		wait_log_commit(log_root_tree,
 				root_log_ctx.log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
@@ -3045,7 +3102,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (btrfs_need_log_full_commit(fs_info, trans)) {
 		blk_finish_plug(&plug);
 		btrfs_wait_tree_log_extents(log, mark);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = -EAGAIN;
 		goto out_wake_log_root;
@@ -3058,7 +3114,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (ret) {
 		btrfs_set_log_full_commit(fs_info, trans);
 		btrfs_abort_transaction(trans, ret);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out_wake_log_root;
 	}
@@ -3068,11 +3123,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 						  EXTENT_NEW | EXTENT_DIRTY);
 	if (ret) {
 		btrfs_set_log_full_commit(fs_info, trans);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out_wake_log_root;
 	}
-	btrfs_wait_logged_extents(trans, log, log_transid);
 
 	btrfs_set_super_log_root(fs_info->super_for_commit,
 				 log_root_tree->node->start);
@@ -3159,14 +3212,6 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 				  EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
 	}
 
-	/*
-	 * We may have short-circuited the log tree with the full commit logic
-	 * and left ordered extents on our list, so clear these out to keep us
-	 * from leaking inodes and memory.
-	 */
-	btrfs_free_logged_extents(log, 0);
-	btrfs_free_logged_extents(log, 1);
-
 	free_extent_buffer(log->node);
 	kfree(log);
 }
@@ -3756,7 +3801,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       int start_slot, int nr, int inode_only,
 			       u64 logged_isize)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	unsigned long src_offset;
 	unsigned long dst_offset;
 	struct btrfs_root *log = inode->root->log_root;
@@ -3937,9 +3982,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 					struct btrfs_file_extent_item);
 		if (btrfs_file_extent_type(src, extent) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_inline_len(src,
-							   src_path->slots[0],
-							   extent);
+			len = btrfs_file_extent_ram_bytes(src, extent);
 			*last_extent = ALIGN(key.offset + len,
 					     fs_info->sectorsize);
 		} else {
@@ -4004,7 +4047,7 @@ fill_holes:
 		extent = btrfs_item_ptr(src, i, struct btrfs_file_extent_item);
 		if (btrfs_file_extent_type(src, extent) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_inline_len(src, i, extent);
+			len = btrfs_file_extent_ram_bytes(src, extent);
 			extent_end = ALIGN(key.offset + len,
 					   fs_info->sectorsize);
 		} else {
@@ -4078,131 +4121,32 @@ static int extent_cmp(void *priv, struct list_head *a, struct list_head *b)
 	return 0;
 }
 
-static int wait_ordered_extents(struct btrfs_trans_handle *trans,
-				struct inode *inode,
-				struct btrfs_root *root,
-				const struct extent_map *em,
-				const struct list_head *logged_list,
-				bool *ordered_io_error)
+static int log_extent_csums(struct btrfs_trans_handle *trans,
+			    struct btrfs_inode *inode,
+			    struct btrfs_root *log_root,
+			    const struct extent_map *em)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_ordered_extent *ordered;
-	struct btrfs_root *log = root->log_root;
-	u64 mod_start = em->mod_start;
-	u64 mod_len = em->mod_len;
-	const bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 	u64 csum_offset;
 	u64 csum_len;
 	LIST_HEAD(ordered_sums);
 	int ret = 0;
 
-	*ordered_io_error = false;
-
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	if (inode->flags & BTRFS_INODE_NODATASUM ||
+	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
 	    em->block_start == EXTENT_MAP_HOLE)
 		return 0;
 
-	/*
-	 * Wait far any ordered extent that covers our extent map. If it
-	 * finishes without an error, first check and see if our csums are on
-	 * our outstanding ordered extents.
-	 */
-	list_for_each_entry(ordered, logged_list, log_list) {
-		struct btrfs_ordered_sum *sum;
-
-		if (!mod_len)
-			break;
-
-		if (ordered->file_offset + ordered->len <= mod_start ||
-		    mod_start + mod_len <= ordered->file_offset)
-			continue;
-
-		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
-			const u64 start = ordered->file_offset;
-			const u64 end = ordered->file_offset + ordered->len - 1;
-
-			WARN_ON(ordered->inode != inode);
-			filemap_fdatawrite_range(inode->i_mapping, start, end);
-		}
-
-		wait_event(ordered->wait,
-			   (test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) ||
-			    test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)));
-
-		if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) {
-			/*
-			 * Clear the AS_EIO/AS_ENOSPC flags from the inode's
-			 * i_mapping flags, so that the next fsync won't get
-			 * an outdated io error too.
-			 */
-			filemap_check_errors(inode->i_mapping);
-			*ordered_io_error = true;
-			break;
-		}
-		/*
-		 * We are going to copy all the csums on this ordered extent, so
-		 * go ahead and adjust mod_start and mod_len in case this
-		 * ordered extent has already been logged.
-		 */
-		if (ordered->file_offset > mod_start) {
-			if (ordered->file_offset + ordered->len >=
-			    mod_start + mod_len)
-				mod_len = ordered->file_offset - mod_start;
-			/*
-			 * If we have this case
-			 *
-			 * |--------- logged extent ---------|
-			 *       |----- ordered extent ----|
-			 *
-			 * Just don't mess with mod_start and mod_len, we'll
-			 * just end up logging more csums than we need and it
-			 * will be ok.
-			 */
-		} else {
-			if (ordered->file_offset + ordered->len <
-			    mod_start + mod_len) {
-				mod_len = (mod_start + mod_len) -
-					(ordered->file_offset + ordered->len);
-				mod_start = ordered->file_offset +
-					ordered->len;
-			} else {
-				mod_len = 0;
-			}
-		}
-
-		if (skip_csum)
-			continue;
-
-		/*
-		 * To keep us from looping for the above case of an ordered
-		 * extent that falls inside of the logged extent.
-		 */
-		if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM,
-				     &ordered->flags))
-			continue;
-
-		list_for_each_entry(sum, &ordered->list, list) {
-			ret = btrfs_csum_file_blocks(trans, log, sum);
-			if (ret)
-				break;
-		}
-	}
-
-	if (*ordered_io_error || !mod_len || ret || skip_csum)
-		return ret;
-
+	/* If we're compressed we have to save the entire range of csums. */
 	if (em->compress_type) {
 		csum_offset = 0;
 		csum_len = max(em->block_len, em->orig_block_len);
 	} else {
-		csum_offset = mod_start - em->start;
-		csum_len = mod_len;
+		csum_offset = em->mod_start - em->start;
+		csum_len = em->mod_len;
 	}
 
 	/* block start is already adjusted for the file extent offset. */
-	ret = btrfs_lookup_csums_range(fs_info->csum_root,
+	ret = btrfs_lookup_csums_range(trans->fs_info->csum_root,
 				       em->block_start + csum_offset,
 				       em->block_start + csum_offset +
 				       csum_len - 1, &ordered_sums, 0);
@@ -4214,7 +4158,7 @@ static int wait_ordered_extents(struct btrfs_trans_handle *trans,
 						   struct btrfs_ordered_sum,
 						   list);
 		if (!ret)
-			ret = btrfs_csum_file_blocks(trans, log, sums);
+			ret = btrfs_csum_file_blocks(trans, log_root, sums);
 		list_del(&sums->list);
 		kfree(sums);
 	}
@@ -4226,7 +4170,6 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 			  struct btrfs_inode *inode, struct btrfs_root *root,
 			  const struct extent_map *em,
 			  struct btrfs_path *path,
-			  const struct list_head *logged_list,
 			  struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *log = root->log_root;
@@ -4238,18 +4181,11 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	u64 block_len;
 	int ret;
 	int extent_inserted = 0;
-	bool ordered_io_err = false;
 
-	ret = wait_ordered_extents(trans, &inode->vfs_inode, root, em,
-			logged_list, &ordered_io_err);
+	ret = log_extent_csums(trans, inode, log, em);
 	if (ret)
 		return ret;
 
-	if (ordered_io_err) {
-		ctx->io_err = -EIO;
-		return ctx->io_err;
-	}
-
 	btrfs_init_map_token(&token);
 
 	ret = __btrfs_drop_extents(trans, log, &inode->vfs_inode, path, em->start,
@@ -4424,7 +4360,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
 				     struct btrfs_inode *inode,
 				     struct btrfs_path *path,
-				     struct list_head *logged_list,
 				     struct btrfs_log_ctx *ctx,
 				     const u64 start,
 				     const u64 end)
@@ -4480,20 +4415,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	}
 
 	list_sort(NULL, &extents, extent_cmp);
-	btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
-	/*
-	 * Some ordered extents started by fsync might have completed
-	 * before we could collect them into the list logged_list, which
-	 * means they're gone, not in our logged_list nor in the inode's
-	 * ordered tree. We want the application/user space to know an
-	 * error happened while attempting to persist file data so that
-	 * it can take proper action. If such error happened, we leave
-	 * without writing to the log tree and the fsync must report the
-	 * file data write error and not commit the current transaction.
-	 */
-	ret = filemap_check_errors(inode->vfs_inode.i_mapping);
-	if (ret)
-		ctx->io_err = ret;
 process:
 	while (!list_empty(&extents)) {
 		em = list_entry(extents.next, struct extent_map, list);
@@ -4512,8 +4433,7 @@ process:
 
 		write_unlock(&tree->lock);
 
-		ret = log_one_extent(trans, inode, root, em, path, logged_list,
-				     ctx);
+		ret = log_one_extent(trans, inode, root, em, path, ctx);
 		write_lock(&tree->lock);
 		clear_em_logging(tree, em);
 		free_extent_map(em);
@@ -4712,9 +4632,7 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 
 		if (btrfs_file_extent_type(leaf, extent) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_inline_len(leaf,
-							   path->slots[0],
-							   extent);
+			len = btrfs_file_extent_ram_bytes(leaf, extent);
 			ASSERT(len == i_size ||
 			       (len == fs_info->sectorsize &&
 				btrfs_file_extent_compression(leaf, extent) !=
@@ -4898,7 +4816,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_key min_key;
 	struct btrfs_key max_key;
 	struct btrfs_root *log = root->log_root;
-	LIST_HEAD(logged_list);
 	u64 last_extent = 0;
 	int err = 0;
 	int ret;
@@ -5094,8 +5011,7 @@ again:
 				 * we don't need to do more work nor fallback to
 				 * a transaction commit.
 				 */
-				if (IS_ERR(other_inode) &&
-				    PTR_ERR(other_inode) == -ENOENT) {
+				if (other_inode == ERR_PTR(-ENOENT)) {
 					goto next_key;
 				} else if (IS_ERR(other_inode)) {
 					err = PTR_ERR(other_inode);
@@ -5235,7 +5151,7 @@ log_extents:
 	}
 	if (fast_search) {
 		ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
-						&logged_list, ctx, start, end);
+						ctx, start, end);
 		if (ret) {
 			err = ret;
 			goto out_unlock;
@@ -5286,10 +5202,6 @@ log_extents:
 	inode->last_log_commit = inode->last_sub_trans;
 	spin_unlock(&inode->lock);
 out_unlock:
-	if (unlikely(err))
-		btrfs_put_logged_extents(&logged_list);
-	else
-		btrfs_submit_logged_extents(&logged_list, log);
 	mutex_unlock(&inode->log_mutex);
 
 	btrfs_free_path(path);
@@ -5585,7 +5497,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 				 struct btrfs_inode *inode,
 				 struct btrfs_log_ctx *ctx)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_key key;
@@ -6120,7 +6032,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
 			struct dentry *parent)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 
 	/*
 	 * this will force the logging code to walk the dentry chain
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1da162928d1a..da86706123ff 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -8,15 +8,12 @@
 #include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/iocontext.h>
-#include <linux/capability.h>
 #include <linux/ratelimit.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/semaphore.h>
 #include <linux/uuid.h>
 #include <linux/list_sort.h>
-#include <asm/div64.h>
 #include "ctree.h"
 #include "extent_map.h"
 #include "disk-io.h"
@@ -634,44 +631,48 @@ static void pending_bios_fn(struct btrfs_work *work)
  *		devices.
  */
 static void btrfs_free_stale_devices(const char *path,
-				     struct btrfs_device *skip_dev)
+				     struct btrfs_device *skip_device)
 {
-	struct btrfs_fs_devices *fs_devs, *tmp_fs_devs;
-	struct btrfs_device *dev, *tmp_dev;
+	struct btrfs_fs_devices *fs_devices, *tmp_fs_devices;
+	struct btrfs_device *device, *tmp_device;
 
-	list_for_each_entry_safe(fs_devs, tmp_fs_devs, &fs_uuids, fs_list) {
-
-		if (fs_devs->opened)
+	list_for_each_entry_safe(fs_devices, tmp_fs_devices, &fs_uuids, fs_list) {
+		mutex_lock(&fs_devices->device_list_mutex);
+		if (fs_devices->opened) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			continue;
+		}
 
-		list_for_each_entry_safe(dev, tmp_dev,
-					 &fs_devs->devices, dev_list) {
+		list_for_each_entry_safe(device, tmp_device,
+					 &fs_devices->devices, dev_list) {
 			int not_found = 0;
 
-			if (skip_dev && skip_dev == dev)
+			if (skip_device && skip_device == device)
 				continue;
-			if (path && !dev->name)
+			if (path && !device->name)
 				continue;
 
 			rcu_read_lock();
 			if (path)
-				not_found = strcmp(rcu_str_deref(dev->name),
+				not_found = strcmp(rcu_str_deref(device->name),
 						   path);
 			rcu_read_unlock();
 			if (not_found)
 				continue;
 
 			/* delete the stale device */
-			if (fs_devs->num_devices == 1) {
-				btrfs_sysfs_remove_fsid(fs_devs);
-				list_del(&fs_devs->fs_list);
-				free_fs_devices(fs_devs);
+			fs_devices->num_devices--;
+			list_del(&device->dev_list);
+			btrfs_free_device(device);
+
+			if (fs_devices->num_devices == 0)
 				break;
-			} else {
-				fs_devs->num_devices--;
-				list_del(&dev->dev_list);
-				btrfs_free_device(dev);
-			}
+		}
+		mutex_unlock(&fs_devices->device_list_mutex);
+		if (fs_devices->num_devices == 0) {
+			btrfs_sysfs_remove_fsid(fs_devices);
+			list_del(&fs_devices->fs_list);
+			free_fs_devices(fs_devices);
 		}
 	}
 }
@@ -750,7 +751,8 @@ error_brelse:
  * error pointer when failed
  */
 static noinline struct btrfs_device *device_list_add(const char *path,
-			   struct btrfs_super_block *disk_super)
+			   struct btrfs_super_block *disk_super,
+			   bool *new_device_added)
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *fs_devices;
@@ -764,21 +766,26 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		if (IS_ERR(fs_devices))
 			return ERR_CAST(fs_devices);
 
+		mutex_lock(&fs_devices->device_list_mutex);
 		list_add(&fs_devices->fs_list, &fs_uuids);
 
 		device = NULL;
 	} else {
+		mutex_lock(&fs_devices->device_list_mutex);
 		device = find_device(fs_devices, devid,
 				disk_super->dev_item.uuid);
 	}
 
 	if (!device) {
-		if (fs_devices->opened)
+		if (fs_devices->opened) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EBUSY);
+		}
 
 		device = btrfs_alloc_device(NULL, &devid,
 					    disk_super->dev_item.uuid);
 		if (IS_ERR(device)) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			/* we can safely leave the fs_devices entry around */
 			return device;
 		}
@@ -786,17 +793,16 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		name = rcu_string_strdup(path, GFP_NOFS);
 		if (!name) {
 			btrfs_free_device(device);
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-ENOMEM);
 		}
 		rcu_assign_pointer(device->name, name);
 
-		mutex_lock(&fs_devices->device_list_mutex);
 		list_add_rcu(&device->dev_list, &fs_devices->devices);
 		fs_devices->num_devices++;
-		mutex_unlock(&fs_devices->device_list_mutex);
 
 		device->fs_devices = fs_devices;
-		btrfs_free_stale_devices(path, device);
+		*new_device_added = true;
 
 		if (disk_super->label[0])
 			pr_info("BTRFS: device label %s devid %llu transid %llu %s\n",
@@ -840,12 +846,15 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 			 * with larger generation number or the last-in if
 			 * generation are equal.
 			 */
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EEXIST);
 		}
 
 		name = rcu_string_strdup(path, GFP_NOFS);
-		if (!name)
+		if (!name) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-ENOMEM);
+		}
 		rcu_string_free(device->name);
 		rcu_assign_pointer(device->name, name);
 		if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state)) {
@@ -865,6 +874,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 	fs_devices->total_devices = btrfs_super_num_devices(disk_super);
 
+	mutex_unlock(&fs_devices->device_list_mutex);
 	return device;
 }
 
@@ -1004,7 +1014,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 	blkdev_put(device->bdev, device->mode);
 }
 
-static void btrfs_prepare_close_one_device(struct btrfs_device *device)
+static void btrfs_close_one_device(struct btrfs_device *device)
 {
 	struct btrfs_fs_devices *fs_devices = device->fs_devices;
 	struct btrfs_device *new_device;
@@ -1022,6 +1032,8 @@ static void btrfs_prepare_close_one_device(struct btrfs_device *device)
 	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
 		fs_devices->missing_devices--;
 
+	btrfs_close_bdev(device);
+
 	new_device = btrfs_alloc_device(NULL, &device->devid,
 					device->uuid);
 	BUG_ON(IS_ERR(new_device)); /* -ENOMEM */
@@ -1035,39 +1047,23 @@ static void btrfs_prepare_close_one_device(struct btrfs_device *device)
 
 	list_replace_rcu(&device->dev_list, &new_device->dev_list);
 	new_device->fs_devices = device->fs_devices;
+
+	call_rcu(&device->rcu, free_device_rcu);
 }
 
 static int close_fs_devices(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *device, *tmp;
-	struct list_head pending_put;
-
-	INIT_LIST_HEAD(&pending_put);
 
 	if (--fs_devices->opened > 0)
 		return 0;
 
 	mutex_lock(&fs_devices->device_list_mutex);
 	list_for_each_entry_safe(device, tmp, &fs_devices->devices, dev_list) {
-		btrfs_prepare_close_one_device(device);
-		list_add(&device->dev_list, &pending_put);
+		btrfs_close_one_device(device);
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	/*
-	 * btrfs_show_devname() is using the device_list_mutex,
-	 * sometimes call to blkdev_put() leads vfs calling
-	 * into this func. So do put outside of device_list_mutex,
-	 * as of now.
-	 */
-	while (!list_empty(&pending_put)) {
-		device = list_first_entry(&pending_put,
-				struct btrfs_device, dev_list);
-		list_del(&device->dev_list);
-		btrfs_close_bdev(device);
-		call_rcu(&device->rcu, free_device_rcu);
-	}
-
 	WARN_ON(fs_devices->open_devices);
 	WARN_ON(fs_devices->rw_devices);
 	fs_devices->opened = 0;
@@ -1146,7 +1142,8 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 {
 	int ret;
 
-	mutex_lock(&uuid_mutex);
+	lockdep_assert_held(&uuid_mutex);
+
 	mutex_lock(&fs_devices->device_list_mutex);
 	if (fs_devices->opened) {
 		fs_devices->opened++;
@@ -1156,7 +1153,6 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		ret = open_fs_devices(fs_devices, flags, holder);
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
-	mutex_unlock(&uuid_mutex);
 
 	return ret;
 }
@@ -1217,16 +1213,18 @@ static int btrfs_read_disk_super(struct block_device *bdev, u64 bytenr,
  * and we are not allowed to call set_blocksize during the scan. The superblock
  * is read via pagecache
  */
-int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
-			  struct btrfs_fs_devices **fs_devices_ret)
+struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
+					   void *holder)
 {
 	struct btrfs_super_block *disk_super;
-	struct btrfs_device *device;
+	bool new_device_added = false;
+	struct btrfs_device *device = NULL;
 	struct block_device *bdev;
 	struct page *page;
-	int ret = 0;
 	u64 bytenr;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	/*
 	 * we would like to check all the supers, but that would make
 	 * a btrfs mount succeed after a mkfs from a different FS.
@@ -1238,112 +1236,25 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 
 	bdev = blkdev_get_by_path(path, flags, holder);
 	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
+		return ERR_CAST(bdev);
 
 	if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super)) {
-		ret = -EINVAL;
+		device = ERR_PTR(-EINVAL);
 		goto error_bdev_put;
 	}
 
-	mutex_lock(&uuid_mutex);
-	device = device_list_add(path, disk_super);
-	if (IS_ERR(device))
-		ret = PTR_ERR(device);
-	else
-		*fs_devices_ret = device->fs_devices;
-	mutex_unlock(&uuid_mutex);
+	device = device_list_add(path, disk_super, &new_device_added);
+	if (!IS_ERR(device)) {
+		if (new_device_added)
+			btrfs_free_stale_devices(path, device);
+	}
 
 	btrfs_release_disk_super(page);
 
 error_bdev_put:
 	blkdev_put(bdev, flags);
 
-	return ret;
-}
-
-/* helper to account the used device space in the range */
-int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
-				   u64 end, u64 *length)
-{
-	struct btrfs_key key;
-	struct btrfs_root *root = device->fs_info->dev_root;
-	struct btrfs_dev_extent *dev_extent;
-	struct btrfs_path *path;
-	u64 extent_end;
-	int ret;
-	int slot;
-	struct extent_buffer *l;
-
-	*length = 0;
-
-	if (start >= device->total_bytes ||
-		test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
-		return 0;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-	path->reada = READA_FORWARD;
-
-	key.objectid = device->devid;
-	key.offset = start;
-	key.type = BTRFS_DEV_EXTENT_KEY;
-
-	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
-		goto out;
-	if (ret > 0) {
-		ret = btrfs_previous_item(root, path, key.objectid, key.type);
-		if (ret < 0)
-			goto out;
-	}
-
-	while (1) {
-		l = path->nodes[0];
-		slot = path->slots[0];
-		if (slot >= btrfs_header_nritems(l)) {
-			ret = btrfs_next_leaf(root, path);
-			if (ret == 0)
-				continue;
-			if (ret < 0)
-				goto out;
-
-			break;
-		}
-		btrfs_item_key_to_cpu(l, &key, slot);
-
-		if (key.objectid < device->devid)
-			goto next;
-
-		if (key.objectid > device->devid)
-			break;
-
-		if (key.type != BTRFS_DEV_EXTENT_KEY)
-			goto next;
-
-		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
-		extent_end = key.offset + btrfs_dev_extent_length(l,
-								  dev_extent);
-		if (key.offset <= start && extent_end > end) {
-			*length = end - start + 1;
-			break;
-		} else if (key.offset <= start && extent_end > start)
-			*length += extent_end - start;
-		else if (key.offset > start && extent_end <= end)
-			*length += extent_end - key.offset;
-		else if (key.offset > start && key.offset <= end) {
-			*length += end - key.offset + 1;
-			break;
-		} else if (key.offset > end)
-			break;
-
-next:
-		path->slots[0]++;
-	}
-	ret = 0;
-out:
-	btrfs_free_path(path);
-	return ret;
+	return device;
 }
 
 static int contains_pending_extent(struct btrfs_transaction *transaction,
@@ -1755,10 +1666,8 @@ error:
  * the btrfs_device struct should be fully filled in
  */
 static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
 			    struct btrfs_device *device)
 {
-	struct btrfs_root *root = fs_info->chunk_root;
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_dev_item *dev_item;
@@ -1774,8 +1683,8 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_DEV_ITEM_KEY;
 	key.offset = device->devid;
 
-	ret = btrfs_insert_empty_item(trans, root, path, &key,
-				      sizeof(*dev_item));
+	ret = btrfs_insert_empty_item(trans, trans->fs_info->chunk_root, path,
+				      &key, sizeof(*dev_item));
 	if (ret)
 		goto out;
 
@@ -1800,7 +1709,7 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 	ptr = btrfs_device_uuid(dev_item);
 	write_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
 	ptr = btrfs_device_fsid(dev_item);
-	write_extent_buffer(leaf, fs_info->fsid, ptr, BTRFS_FSID_SIZE);
+	write_extent_buffer(leaf, trans->fs_info->fsid, ptr, BTRFS_FSID_SIZE);
 	btrfs_mark_buffer_dirty(leaf);
 
 	ret = 0;
@@ -1924,9 +1833,10 @@ static struct btrfs_device * btrfs_find_next_active_device(
  * where this function called, there should be always be another device (or
  * this_dev) which is active.
  */
-void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
-		struct btrfs_device *device, struct btrfs_device *this_dev)
+void btrfs_assign_next_active_device(struct btrfs_device *device,
+				     struct btrfs_device *this_dev)
 {
+	struct btrfs_fs_info *fs_info = device->fs_info;
 	struct btrfs_device *next_device;
 
 	if (this_dev)
@@ -2029,11 +1939,14 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 
 	cur_devices->num_devices--;
 	cur_devices->total_devices--;
+	/* Update total_devices of the parent fs_devices if it's seed */
+	if (cur_devices != fs_devices)
+		fs_devices->total_devices--;
 
 	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
 		cur_devices->missing_devices--;
 
-	btrfs_assign_next_active_device(fs_info, device, NULL);
+	btrfs_assign_next_active_device(device, NULL);
 
 	if (device->bdev) {
 		cur_devices->open_devices--;
@@ -2084,12 +1997,11 @@ error_undo:
 	goto out;
 }
 
-void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
-					struct btrfs_device *srcdev)
+void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev)
 {
 	struct btrfs_fs_devices *fs_devices;
 
-	lockdep_assert_held(&fs_info->fs_devices->device_list_mutex);
+	lockdep_assert_held(&srcdev->fs_info->fs_devices->device_list_mutex);
 
 	/*
 	 * in case of fs with no seed, srcdev->fs_devices will point
@@ -2151,10 +2063,9 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 	}
 }
 
-void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				      struct btrfs_device *tgtdev)
+void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
 {
-	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_fs_devices *fs_devices = tgtdev->fs_info->fs_devices;
 
 	WARN_ON(!tgtdev);
 	mutex_lock(&fs_devices->device_list_mutex);
@@ -2166,7 +2077,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 
 	fs_devices->num_devices--;
 
-	btrfs_assign_next_active_device(fs_info, tgtdev, NULL);
+	btrfs_assign_next_active_device(tgtdev, NULL);
 
 	list_del_rcu(&tgtdev->dev_list);
 
@@ -2297,7 +2208,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&seed_devices->alloc_list);
 	mutex_init(&seed_devices->device_list_mutex);
 
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 	list_splice_init_rcu(&fs_devices->devices, &seed_devices->devices,
 			      synchronize_rcu);
 	list_for_each_entry(device, &seed_devices->devices, dev_list)
@@ -2317,7 +2228,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	generate_random_uuid(fs_devices->fsid);
 	memcpy(fs_info->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
 	memcpy(disk_super->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	super_flags = btrfs_super_flags(disk_super) &
 		      ~BTRFS_SUPER_FLAG_SEEDING;
@@ -2407,15 +2318,16 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
 	struct block_device *bdev;
-	struct list_head *devices;
 	struct super_block *sb = fs_info->sb;
 	struct rcu_string *name;
-	u64 tmp;
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	u64 orig_super_total_bytes;
+	u64 orig_super_num_devices;
 	int seeding_dev = 0;
 	int ret = 0;
 	bool unlocked = false;
 
-	if (sb_rdonly(sb) && !fs_info->fs_devices->seeding)
+	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
 	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
@@ -2423,7 +2335,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
-	if (fs_info->fs_devices->seeding) {
+	if (fs_devices->seeding) {
 		seeding_dev = 1;
 		down_write(&sb->s_umount);
 		mutex_lock(&uuid_mutex);
@@ -2431,18 +2343,16 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 	filemap_write_and_wait(bdev->bd_inode->i_mapping);
 
-	devices = &fs_info->fs_devices->devices;
-
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
-	list_for_each_entry(device, devices, dev_list) {
+	mutex_lock(&fs_devices->device_list_mutex);
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
 		if (device->bdev == bdev) {
 			ret = -EEXIST;
 			mutex_unlock(
-				&fs_info->fs_devices->device_list_mutex);
+				&fs_devices->device_list_mutex);
 			goto error;
 		}
 	}
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	device = btrfs_alloc_device(fs_info, NULL, NULL);
 	if (IS_ERR(device)) {
@@ -2491,33 +2401,34 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		}
 	}
 
-	device->fs_devices = fs_info->fs_devices;
+	device->fs_devices = fs_devices;
 
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 	mutex_lock(&fs_info->chunk_mutex);
-	list_add_rcu(&device->dev_list, &fs_info->fs_devices->devices);
-	list_add(&device->dev_alloc_list,
-		 &fs_info->fs_devices->alloc_list);
-	fs_info->fs_devices->num_devices++;
-	fs_info->fs_devices->open_devices++;
-	fs_info->fs_devices->rw_devices++;
-	fs_info->fs_devices->total_devices++;
-	fs_info->fs_devices->total_rw_bytes += device->total_bytes;
+	list_add_rcu(&device->dev_list, &fs_devices->devices);
+	list_add(&device->dev_alloc_list, &fs_devices->alloc_list);
+	fs_devices->num_devices++;
+	fs_devices->open_devices++;
+	fs_devices->rw_devices++;
+	fs_devices->total_devices++;
+	fs_devices->total_rw_bytes += device->total_bytes;
 
 	atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
 
 	if (!blk_queue_nonrot(q))
-		fs_info->fs_devices->rotating = 1;
+		fs_devices->rotating = 1;
 
-	tmp = btrfs_super_total_bytes(fs_info->super_copy);
+	orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
 	btrfs_set_super_total_bytes(fs_info->super_copy,
-		round_down(tmp + device->total_bytes, fs_info->sectorsize));
+		round_down(orig_super_total_bytes + device->total_bytes,
+			   fs_info->sectorsize));
 
-	tmp = btrfs_super_num_devices(fs_info->super_copy);
-	btrfs_set_super_num_devices(fs_info->super_copy, tmp + 1);
+	orig_super_num_devices = btrfs_super_num_devices(fs_info->super_copy);
+	btrfs_set_super_num_devices(fs_info->super_copy,
+				    orig_super_num_devices + 1);
 
 	/* add sysfs device entry */
-	btrfs_sysfs_add_device_link(fs_info->fs_devices, device);
+	btrfs_sysfs_add_device_link(fs_devices, device);
 
 	/*
 	 * we've got more storage, clear any full flags on the space
@@ -2526,7 +2437,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	btrfs_clear_space_info_full(fs_info);
 
 	mutex_unlock(&fs_info->chunk_mutex);
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	if (seeding_dev) {
 		mutex_lock(&fs_info->chunk_mutex);
@@ -2538,7 +2449,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		}
 	}
 
-	ret = btrfs_add_dev_item(trans, fs_info, device);
+	ret = btrfs_add_dev_item(trans, device);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto error_sysfs;
@@ -2558,7 +2469,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		 */
 		snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU",
 						fs_info->fsid);
-		if (kobject_rename(&fs_info->fs_devices->fsid_kobj, fsid_buf))
+		if (kobject_rename(&fs_devices->fsid_kobj, fsid_buf))
 			btrfs_warn(fs_info,
 				   "sysfs: failed to create fsid for sprout");
 	}
@@ -2593,7 +2504,23 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	return ret;
 
 error_sysfs:
-	btrfs_sysfs_rm_device_link(fs_info->fs_devices, device);
+	btrfs_sysfs_rm_device_link(fs_devices, device);
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_info->chunk_mutex);
+	list_del_rcu(&device->dev_list);
+	list_del(&device->dev_alloc_list);
+	fs_info->fs_devices->num_devices--;
+	fs_info->fs_devices->open_devices--;
+	fs_info->fs_devices->rw_devices--;
+	fs_info->fs_devices->total_devices--;
+	fs_info->fs_devices->total_rw_bytes -= device->total_bytes;
+	atomic64_sub(device->total_bytes, &fs_info->free_chunk_space);
+	btrfs_set_super_total_bytes(fs_info->super_copy,
+				    orig_super_total_bytes);
+	btrfs_set_super_num_devices(fs_info->super_copy,
+				    orig_super_num_devices);
+	mutex_unlock(&fs_info->chunk_mutex);
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 error_trans:
 	if (seeding_dev)
 		sb->s_flags |= SB_RDONLY;
@@ -2697,9 +2624,9 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 	return btrfs_update_device(trans, device);
 }
 
-static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info, u64 chunk_offset)
+static int btrfs_free_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->chunk_root;
 	int ret;
 	struct btrfs_path *path;
@@ -2808,9 +2735,9 @@ static struct extent_map *get_chunk_map(struct btrfs_fs_info *fs_info,
 	return em;
 }
 
-int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 chunk_offset)
+int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct extent_map *em;
 	struct map_lookup *map;
 	u64 dev_extent_len = 0;
@@ -2829,7 +2756,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	}
 	map = em->map_lookup;
 	mutex_lock(&fs_info->chunk_mutex);
-	check_system_chunk(trans, fs_info, map->type);
+	check_system_chunk(trans, map->type);
 	mutex_unlock(&fs_info->chunk_mutex);
 
 	/*
@@ -2869,7 +2796,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	ret = btrfs_free_chunk(trans, fs_info, chunk_offset);
+	ret = btrfs_free_chunk(trans, chunk_offset);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -2885,7 +2812,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	ret = btrfs_remove_block_group(trans, fs_info, chunk_offset, em);
+	ret = btrfs_remove_block_group(trans, chunk_offset, em);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
@@ -2950,7 +2877,7 @@ static int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 	 * step two, delete the device extents and the
 	 * chunk tree entries
 	 */
-	ret = btrfs_remove_chunk(trans, fs_info, chunk_offset);
+	ret = btrfs_remove_chunk(trans, chunk_offset);
 	btrfs_end_transaction(trans);
 	return ret;
 }
@@ -3059,7 +2986,7 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 
-			ret = btrfs_force_chunk_alloc(trans, fs_info,
+			ret = btrfs_force_chunk_alloc(trans,
 						      BTRFS_BLOCK_GROUP_DATA);
 			btrfs_end_transaction(trans);
 			if (ret < 0)
@@ -4692,7 +4619,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
 		max_stripe_size = SZ_1G;
-		max_chunk_size = 10 * max_stripe_size;
+		max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS(info);
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
@@ -4900,7 +4827,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	refcount_inc(&em->refs);
 	write_unlock(&em_tree->lock);
 
-	ret = btrfs_make_block_group(trans, info, 0, type, start, num_bytes);
+	ret = btrfs_make_block_group(trans, 0, type, start, num_bytes);
 	if (ret)
 		goto error_del_extent;
 
@@ -4934,9 +4861,9 @@ error:
 }
 
 int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
-				u64 chunk_offset, u64 chunk_size)
+			     u64 chunk_offset, u64 chunk_size)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct btrfs_root *chunk_root = fs_info->chunk_root;
 	struct btrfs_key key;
@@ -5038,13 +4965,12 @@ out:
  * require modifying the chunk tree. This division is important for the
  * bootstrap process of adding storage to a seed btrfs.
  */
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info, u64 type)
+int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type)
 {
 	u64 chunk_offset;
 
-	lockdep_assert_held(&fs_info->chunk_mutex);
-	chunk_offset = find_next_chunk(fs_info);
+	lockdep_assert_held(&trans->fs_info->chunk_mutex);
+	chunk_offset = find_next_chunk(trans->fs_info);
 	return __btrfs_alloc_chunk(trans, chunk_offset, type);
 }
 
@@ -5175,7 +5101,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		/*
 		 * There could be two corrupted data stripes, we need
 		 * to loop retry in order to rebuild the correct data.
-		 * 
+		 *
 		 * Fail a stripe at a time on every retry except the
 		 * stripe under reconstruction.
 		 */
@@ -6187,21 +6113,11 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
 	btrfs_io_bio(bio)->stripe_index = dev_nr;
 	bio->bi_end_io = btrfs_end_bio;
 	bio->bi_iter.bi_sector = physical >> 9;
-#ifdef DEBUG
-	{
-		struct rcu_string *name;
-
-		rcu_read_lock();
-		name = rcu_dereference(dev->name);
-		btrfs_debug(fs_info,
-			"btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
-			bio_op(bio), bio->bi_opf,
-			(u64)bio->bi_iter.bi_sector,
-			(u_long)dev->bdev->bd_dev, name->str, dev->devid,
-			bio->bi_iter.bi_size);
-		rcu_read_unlock();
-	}
-#endif
+	btrfs_debug_in_rcu(fs_info,
+	"btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
+		bio_op(bio), bio->bi_opf, (u64)bio->bi_iter.bi_sector,
+		(u_long)dev->bdev->bd_dev, rcu_str_deref(dev->name), dev->devid,
+		bio->bi_iter.bi_size);
 	bio_set_dev(bio, dev->bdev);
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
@@ -6403,6 +6319,8 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info,
 	u16 num_stripes;
 	u16 sub_stripes;
 	u64 type;
+	u64 features;
+	bool mixed = false;
 
 	length = btrfs_chunk_length(leaf, chunk);
 	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
@@ -6441,6 +6359,32 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info,
 			  btrfs_chunk_type(leaf, chunk));
 		return -EIO;
 	}
+
+	if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) {
+		btrfs_err(fs_info, "missing chunk type flag: 0x%llx", type);
+		return -EIO;
+	}
+
+	if ((type & BTRFS_BLOCK_GROUP_SYSTEM) &&
+	    (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) {
+		btrfs_err(fs_info,
+			"system chunk with data or metadata type: 0x%llx", type);
+		return -EIO;
+	}
+
+	features = btrfs_super_incompat_flags(fs_info->super_copy);
+	if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+		mixed = true;
+
+	if (!mixed) {
+		if ((type & BTRFS_BLOCK_GROUP_METADATA) &&
+		    (type & BTRFS_BLOCK_GROUP_DATA)) {
+			btrfs_err(fs_info,
+			"mixed chunk type in non-mixed mode: 0x%llx", type);
+			return -EIO;
+		}
+	}
+
 	if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||
@@ -6527,6 +6471,7 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	map->stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
 	map->type = btrfs_chunk_type(leaf, chunk);
 	map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
+	map->verified_stripes = 0;
 	for (i = 0; i < num_stripes; i++) {
 		map->stripes[i].physical =
 			btrfs_stripe_offset_nr(leaf, chunk, i);
@@ -6563,10 +6508,14 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	write_lock(&map_tree->map_tree.lock);
 	ret = add_extent_mapping(&map_tree->map_tree, em, 0);
 	write_unlock(&map_tree->map_tree.lock);
-	BUG_ON(ret); /* Tree corruption */
+	if (ret < 0) {
+		btrfs_err(fs_info,
+			  "failed to add chunk map, start=%llu len=%llu: %d",
+			  em->start, em->len, ret);
+	}
 	free_extent_map(em);
 
-	return 0;
+	return ret;
 }
 
 static void fill_device_from_item(struct extent_buffer *leaf,
@@ -7108,9 +7057,9 @@ out:
 }
 
 static int update_dev_stat_item(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				struct btrfs_device *device)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *dev_root = fs_info->dev_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
@@ -7203,7 +7152,7 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
 		 */
 		smp_rmb();
 
-		ret = update_dev_stat_item(trans, fs_info, device);
+		ret = update_dev_stat_item(trans, device);
 		if (!ret)
 			atomic_sub(stats_cnt, &device->dev_stats_ccnt);
 	}
@@ -7382,3 +7331,197 @@ void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info)
 		fs_devices = fs_devices->seed;
 	}
 }
+
+/*
+ * Multiplicity factor for simple profiles: DUP, RAID1-like and RAID10.
+ */
+int btrfs_bg_type_to_factor(u64 flags)
+{
+	if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
+		     BTRFS_BLOCK_GROUP_RAID10))
+		return 2;
+	return 1;
+}
+
+
+static u64 calc_stripe_length(u64 type, u64 chunk_len, int num_stripes)
+{
+	int index = btrfs_bg_flags_to_raid_index(type);
+	int ncopies = btrfs_raid_array[index].ncopies;
+	int data_stripes;
+
+	switch (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+	case BTRFS_BLOCK_GROUP_RAID5:
+		data_stripes = num_stripes - 1;
+		break;
+	case BTRFS_BLOCK_GROUP_RAID6:
+		data_stripes = num_stripes - 2;
+		break;
+	default:
+		data_stripes = num_stripes / ncopies;
+		break;
+	}
+	return div_u64(chunk_len, data_stripes);
+}
+
+static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
+				 u64 chunk_offset, u64 devid,
+				 u64 physical_offset, u64 physical_len)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+	struct extent_map *em;
+	struct map_lookup *map;
+	u64 stripe_len;
+	bool found = false;
+	int ret = 0;
+	int i;
+
+	read_lock(&em_tree->lock);
+	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
+	read_unlock(&em_tree->lock);
+
+	if (!em) {
+		btrfs_err(fs_info,
+"dev extent physical offset %llu on devid %llu doesn't have corresponding chunk",
+			  physical_offset, devid);
+		ret = -EUCLEAN;
+		goto out;
+	}
+
+	map = em->map_lookup;
+	stripe_len = calc_stripe_length(map->type, em->len, map->num_stripes);
+	if (physical_len != stripe_len) {
+		btrfs_err(fs_info,
+"dev extent physical offset %llu on devid %llu length doesn't match chunk %llu, have %llu expect %llu",
+			  physical_offset, devid, em->start, physical_len,
+			  stripe_len);
+		ret = -EUCLEAN;
+		goto out;
+	}
+
+	for (i = 0; i < map->num_stripes; i++) {
+		if (map->stripes[i].dev->devid == devid &&
+		    map->stripes[i].physical == physical_offset) {
+			found = true;
+			if (map->verified_stripes >= map->num_stripes) {
+				btrfs_err(fs_info,
+				"too many dev extents for chunk %llu found",
+					  em->start);
+				ret = -EUCLEAN;
+				goto out;
+			}
+			map->verified_stripes++;
+			break;
+		}
+	}
+	if (!found) {
+		btrfs_err(fs_info,
+	"dev extent physical offset %llu devid %llu has no corresponding chunk",
+			physical_offset, devid);
+		ret = -EUCLEAN;
+	}
+out:
+	free_extent_map(em);
+	return ret;
+}
+
+static int verify_chunk_dev_extent_mapping(struct btrfs_fs_info *fs_info)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+	struct extent_map *em;
+	struct rb_node *node;
+	int ret = 0;
+
+	read_lock(&em_tree->lock);
+	for (node = rb_first(&em_tree->map); node; node = rb_next(node)) {
+		em = rb_entry(node, struct extent_map, rb_node);
+		if (em->map_lookup->num_stripes !=
+		    em->map_lookup->verified_stripes) {
+			btrfs_err(fs_info,
+			"chunk %llu has missing dev extent, have %d expect %d",
+				  em->start, em->map_lookup->verified_stripes,
+				  em->map_lookup->num_stripes);
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+out:
+	read_unlock(&em_tree->lock);
+	return ret;
+}
+
+/*
+ * Ensure that all dev extents are mapped to correct chunk, otherwise
+ * later chunk allocation/free would cause unexpected behavior.
+ *
+ * NOTE: This will iterate through the whole device tree, which should be of
+ * the same size level as the chunk tree.  This slightly increases mount time.
+ */
+int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_path *path;
+	struct btrfs_root *root = fs_info->dev_root;
+	struct btrfs_key key;
+	int ret = 0;
+
+	key.objectid = 1;
+	key.type = BTRFS_DEV_EXTENT_KEY;
+	key.offset = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	path->reada = READA_FORWARD;
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
+		ret = btrfs_next_item(root, path);
+		if (ret < 0)
+			goto out;
+		/* No dev extents at all? Not good */
+		if (ret > 0) {
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+	while (1) {
+		struct extent_buffer *leaf = path->nodes[0];
+		struct btrfs_dev_extent *dext;
+		int slot = path->slots[0];
+		u64 chunk_offset;
+		u64 physical_offset;
+		u64 physical_len;
+		u64 devid;
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.type != BTRFS_DEV_EXTENT_KEY)
+			break;
+		devid = key.objectid;
+		physical_offset = key.offset;
+
+		dext = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
+		chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dext);
+		physical_len = btrfs_dev_extent_length(leaf, dext);
+
+		ret = verify_one_dev_extent(fs_info, chunk_offset, devid,
+					    physical_offset, physical_len);
+		if (ret < 0)
+			goto out;
+		ret = btrfs_next_item(root, path);
+		if (ret < 0)
+			goto out;
+		if (ret > 0) {
+			ret = 0;
+			break;
+		}
+	}
+
+	/* Ensure all chunks have corresponding dev extents */
+	ret = verify_chunk_dev_extent_mapping(fs_info);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 5139ec8daf4c..23e9285d88de 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -11,6 +11,8 @@
 #include <linux/btrfs.h>
 #include "async-thread.h"
 
+#define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
+
 extern struct mutex uuid_mutex;
 
 #define BTRFS_STRIPE_LEN	SZ_64K
@@ -343,6 +345,7 @@ struct map_lookup {
 	u64 stripe_len;
 	int num_stripes;
 	int sub_stripes;
+	int verified_stripes; /* For mount time dev extent verification */
 	struct btrfs_bio_stripe stripes[];
 };
 
@@ -382,8 +385,6 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio)
 	}
 }
 
-int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
-				   u64 end, u64 *length);
 void btrfs_get_bbio(struct btrfs_bio *bbio);
 void btrfs_put_bbio(struct btrfs_bio *bbio);
 int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
@@ -396,20 +397,19 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 		     u64 physical, u64 **logical, int *naddrs, int *stripe_len);
 int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info, u64 type);
+int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);
 void btrfs_mapping_init(struct btrfs_mapping_tree *tree);
 void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree);
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			   int mirror_num, int async_submit);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       fmode_t flags, void *holder);
-int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
-			  struct btrfs_fs_devices **fs_devices_ret);
+struct btrfs_device *btrfs_scan_one_device(const char *path,
+					   fmode_t flags, void *holder);
 int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
 void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step);
-void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
-		struct btrfs_device *device, struct btrfs_device *this_dev);
+void btrfs_assign_next_active_device(struct btrfs_device *device,
+				     struct btrfs_device *this_dev);
 int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
 					 const char *device_path,
 					 struct btrfs_device **device);
@@ -453,22 +453,18 @@ void btrfs_init_devices_late(struct btrfs_fs_info *fs_info);
 int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info);
 int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info);
-void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
-					struct btrfs_device *srcdev);
+void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev);
 void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 				      struct btrfs_device *srcdev);
-void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				      struct btrfs_device *tgtdev);
+void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev);
 void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path);
 int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
 			   u64 logical, u64 len);
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    u64 logical);
 int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
-				u64 chunk_offset, u64 chunk_size);
-int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 chunk_offset);
+			     u64 chunk_offset, u64 chunk_size);
+int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
 
 static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
 				      int index)
@@ -560,4 +556,7 @@ void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info);
 bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 					struct btrfs_device *failing_dev);
 
+int btrfs_bg_type_to_factor(u64 flags);
+int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info);
+
 #endif
diff --git a/fs/buffer.c b/fs/buffer.c
index cabc045f483d..c8c2b7d8b8d6 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1900,15 +1900,16 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
 		break;
 	case IOMAP_UNWRITTEN:
 		/*
-		 * For unwritten regions, we always need to ensure that
-		 * sub-block writes cause the regions in the block we are not
-		 * writing to are zeroed. Set the buffer as new to ensure this.
+		 * For unwritten regions, we always need to ensure that regions
+		 * in the block we are not writing to are zeroed. Mark the
+		 * buffer as new to ensure this.
 		 */
 		set_buffer_new(bh);
 		set_buffer_unwritten(bh);
 		/* FALLTHRU */
 	case IOMAP_MAPPED:
-		if (offset >= i_size_read(inode))
+		if ((iomap->flags & IOMAP_F_NEW) ||
+		    offset >= i_size_read(inode))
 			set_buffer_new(bh);
 		bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
 				inode->i_blkbits;
@@ -2076,6 +2077,40 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 }
 EXPORT_SYMBOL(block_write_begin);
 
+int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
+		struct page *page)
+{
+	loff_t old_size = inode->i_size;
+	bool i_size_changed = false;
+
+	/*
+	 * No need to use i_size_read() here, the i_size cannot change under us
+	 * because we hold i_rwsem.
+	 *
+	 * But it's important to update i_size while still holding page lock:
+	 * page writeout could otherwise come in and zero beyond i_size.
+	 */
+	if (pos + copied > inode->i_size) {
+		i_size_write(inode, pos + copied);
+		i_size_changed = true;
+	}
+
+	unlock_page(page);
+	put_page(page);
+
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (i_size_changed)
+		mark_inode_dirty(inode);
+	return copied;
+}
+
 int block_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
@@ -2116,39 +2151,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
 {
-	struct inode *inode = mapping->host;
-	loff_t old_size = inode->i_size;
-	int i_size_changed = 0;
-
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
-
-	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold i_mutex.
-	 *
-	 * But it's important to update i_size while still holding page lock:
-	 * page writeout could otherwise come in and zero beyond i_size.
-	 */
-	if (pos+copied > inode->i_size) {
-		i_size_write(inode, pos+copied);
-		i_size_changed = 1;
-	}
-
-	unlock_page(page);
-	put_page(page);
-
-	if (old_size < pos)
-		pagecache_isize_extended(inode, old_size, pos);
-	/*
-	 * Don't mark the inode dirty under page lock. First, it unnecessarily
-	 * makes the holding time of page lock longer. Second, it forces lock
-	 * ordering of page lock and transaction start for journaling
-	 * filesystems.
-	 */
-	if (i_size_changed)
-		mark_inode_dirty(inode);
-
-	return copied;
+	return __generic_write_end(mapping->host, pos, copied, page);
 }
 EXPORT_SYMBOL(generic_write_end);
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ad0bed99b1d5..e2679e8a2535 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -429,8 +429,7 @@ out:
  * file or symlink, return 1 so the VFS can retry.
  */
 int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
-		     struct file *file, unsigned flags, umode_t mode,
-		     int *opened)
+		     struct file *file, unsigned flags, umode_t mode)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -507,9 +506,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		dout("atomic_open finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
 			ceph_init_inode_acls(d_inode(dentry), &acls);
-			*opened |= FILE_CREATED;
+			file->f_mode |= FMODE_CREATED;
 		}
-		err = finish_open(file, dentry, ceph_open, opened);
+		err = finish_open(file, dentry, ceph_open);
 	}
 out_req:
 	if (!req->r_err && req->r_target_inode)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index a7077a0c989f..971328b99ede 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1025,8 +1025,7 @@ extern const struct file_operations ceph_file_fops;
 extern int ceph_renew_caps(struct inode *inode);
 extern int ceph_open(struct inode *inode, struct file *file);
 extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
-			    struct file *file, unsigned flags, umode_t mode,
-			    int *opened);
+			    struct file *file, unsigned flags, umode_t mode);
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 5f132d59dfc2..35c83fe7dba0 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -16,24 +16,28 @@ config CIFS
 	select CRYPTO_DES
 	help
 	  This is the client VFS module for the SMB3 family of NAS protocols,
-	  as well as for earlier dialects such as SMB2.1, SMB2 and the
+	  (including support for the most recent, most secure dialect SMB3.1.1)
+	  as well as for earlier dialects such as SMB2.1, SMB2 and the older
 	  Common Internet File System (CIFS) protocol.  CIFS was the successor
 	  to the original dialect, the Server Message Block (SMB) protocol, the
 	  native file sharing mechanism for most early PC operating systems.
 
-	  The SMB3 protocol is supported by most modern operating systems and
-	  NAS appliances (e.g. Samba, Windows 8, Windows 2012, MacOS).
+	  The SMB3 protocol is supported by most modern operating systems
+	  and NAS appliances (e.g. Samba, Windows 10, Windows Server 2016,
+	  MacOS) and even in the cloud (e.g. Microsoft Azure).
 	  The older CIFS protocol was included in Windows NT4, 2000 and XP (and
 	  later) as well by Samba (which provides excellent CIFS and SMB3
-	  server support for Linux and many other operating systems). Limited
-	  support for OS/2 and Windows ME and similar very old servers is
-	  provided as well.
+	  server support for Linux and many other operating systems). Use of
+	  dialects older than SMB2.1 is often discouraged on public networks.
+	  This module also provides limited support for OS/2 and Windows ME
+	  and similar very old servers.
 
-	  The cifs module provides an advanced network file system client
+	  This module provides an advanced network file system client
 	  for mounting to SMB3 (and CIFS) compliant servers.  It includes
 	  support for DFS (hierarchical name space), secure per-user
-	  session establishment via Kerberos or NTLM or NTLMv2,
-	  safe distributed caching (oplock), optional packet
+	  session establishment via Kerberos or NTLM or NTLMv2, RDMA
+	  (smbdirect), advanced security features, per-share encryption,
+	  directory leases, safe distributed caching (oplock), optional packet
 	  signing, Unicode and other internationalization improvements.
 
 	  In general, the default dialects, SMB3 and later, enable better
@@ -43,18 +47,11 @@ config CIFS
 	  than SMB3 mounts. SMB2/SMB3 mount options are also
 	  slightly simpler (compared to CIFS) due to protocol improvements.
 
-	  If you need to mount to Samba, Macs or Windows from this machine, say Y.
-
-config CIFS_STATS
-        bool "CIFS statistics"
-        depends on CIFS
-        help
-          Enabling this option will cause statistics for each server share
-	  mounted by the cifs client to be displayed in /proc/fs/cifs/Stats
+	  If you need to mount to Samba, Azure, Macs or Windows from this machine, say Y.
 
 config CIFS_STATS2
 	bool "Extended statistics"
-	depends on CIFS_STATS
+	depends on CIFS
 	help
 	  Enabling this option will allow more detailed statistics on SMB
 	  request timing to be displayed in /proc/fs/cifs/DebugData and also
@@ -66,9 +63,24 @@ config CIFS_STATS2
 	  Unless you are a developer or are doing network performance analysis
 	  or tuning, say N.
 
+config CIFS_ALLOW_INSECURE_LEGACY
+	bool "Support legacy servers which use less secure dialects"
+	depends on CIFS
+	default y
+	help
+	  Modern dialects, SMB2.1 and later (including SMB3 and 3.1.1), have
+	  additional security features, including protection against
+	  man-in-the-middle attacks and stronger crypto hashes, so the use
+	  of legacy dialects (SMB1/CIFS and SMB2.0) is discouraged.
+
+	  Disabling this option prevents users from using vers=1.0 or vers=2.0
+	  on mounts with cifs.ko
+
+	  If unsure, say Y.
+
 config CIFS_WEAK_PW_HASH
 	bool "Support legacy servers which use weaker LANMAN security"
-	depends on CIFS
+	depends on CIFS && CIFS_ALLOW_INSECURE_LEGACY
 	help
 	  Modern CIFS servers including Samba and most Windows versions
 	  (since 1997) support stronger NTLM (and even NTLMv2 and Kerberos)
@@ -186,15 +198,6 @@ config CIFS_NFSD_EXPORT
 	  help
 	   Allows NFS server to export a CIFS mounted share (nfsd over cifs)
 
-config CIFS_SMB311
-	bool "SMB3.1.1 network file system support"
-	depends on CIFS
-	select CRYPTO_SHA512
-
-	help
-	  This enables support for the newest, and most secure dialect, SMB3.11.
-	  If unsure, say Y
-
 config CIFS_SMB_DIRECT
 	bool "SMB Direct support (Experimental)"
 	depends on CIFS=m && INFINIBAND && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND=y && INFINIBAND_ADDR_TRANS=y
diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c
index e1553d1e0e50..b7420e605b28 100644
--- a/fs/cifs/cache.c
+++ b/fs/cifs/cache.c
@@ -128,8 +128,10 @@ fscache_checkaux cifs_fscache_inode_check_aux(void *cookie_netfs_data,
 
 	memset(&auxdata, 0, sizeof(auxdata));
 	auxdata.eof = cifsi->server_eof;
-	auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
-	auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
+	auxdata.last_write_time_sec = cifsi->vfs_inode.i_mtime.tv_sec;
+	auxdata.last_change_time_sec = cifsi->vfs_inode.i_ctime.tv_sec;
+	auxdata.last_write_time_nsec = cifsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata.last_change_time_nsec = cifsi->vfs_inode.i_ctime.tv_nsec;
 
 	if (memcmp(data, &auxdata, datalen) != 0)
 		return FSCACHE_CHECKAUX_OBSOLETE;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index bfe999505815..f1fbea947fef 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -160,25 +160,41 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "CIFS Version %s\n", CIFS_VERSION);
 	seq_printf(m, "Features:");
 #ifdef CONFIG_CIFS_DFS_UPCALL
-	seq_printf(m, " dfs");
+	seq_printf(m, " DFS");
 #endif
 #ifdef CONFIG_CIFS_FSCACHE
-	seq_printf(m, " fscache");
+	seq_printf(m, ",FSCACHE");
+#endif
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	seq_printf(m, ",SMB_DIRECT");
+#endif
+#ifdef CONFIG_CIFS_STATS2
+	seq_printf(m, ",STATS2");
+#else
+	seq_printf(m, ",STATS");
+#endif
+#ifdef CONFIG_CIFS_DEBUG2
+	seq_printf(m, ",DEBUG2");
+#elif defined(CONFIG_CIFS_DEBUG)
+	seq_printf(m, ",DEBUG");
+#endif
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
+	seq_printf(m, ",ALLOW_INSECURE_LEGACY");
 #endif
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
-	seq_printf(m, " lanman");
+	seq_printf(m, ",WEAK_PW_HASH");
 #endif
 #ifdef CONFIG_CIFS_POSIX
-	seq_printf(m, " posix");
+	seq_printf(m, ",CIFS_POSIX");
 #endif
 #ifdef CONFIG_CIFS_UPCALL
-	seq_printf(m, " spnego");
+	seq_printf(m, ",UPCALL(SPNEGO)");
 #endif
 #ifdef CONFIG_CIFS_XATTR
-	seq_printf(m, " xattr");
+	seq_printf(m, ",XATTR");
 #endif
 #ifdef CONFIG_CIFS_ACL
-	seq_printf(m, " acl");
+	seq_printf(m, ",ACL");
 #endif
 	seq_putc(m, '\n');
 	seq_printf(m, "Active VFS Requests: %d\n", GlobalTotalActiveXid);
@@ -259,10 +275,9 @@ skip_rdma:
 			server->credits,  server->dialect);
 		if (server->sign)
 			seq_printf(m, " signed");
-#ifdef CONFIG_CIFS_SMB311
 		if (server->posix_ext_supported)
 			seq_printf(m, " posix");
-#endif /* 3.1.1 */
+
 		i++;
 		list_for_each(tmp2, &server->smb_ses_list) {
 			ses = list_entry(tmp2, struct cifs_ses,
@@ -350,7 +365,6 @@ skip_rdma:
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_STATS
 static ssize_t cifs_stats_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
@@ -364,13 +378,23 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 	rc = kstrtobool_from_user(buffer, count, &bv);
 	if (rc == 0) {
 #ifdef CONFIG_CIFS_STATS2
+		int i;
+
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
 #endif /* CONFIG_CIFS_STATS2 */
+		spin_lock(&GlobalMid_Lock);
+		GlobalMaxActiveXid = 0;
+		GlobalCurrentXid = 0;
+		spin_unlock(&GlobalMid_Lock);
 		spin_lock(&cifs_tcp_ses_lock);
 		list_for_each(tmp1, &cifs_tcp_ses_list) {
 			server = list_entry(tmp1, struct TCP_Server_Info,
 					    tcp_ses_list);
+#ifdef CONFIG_CIFS_STATS2
+			for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++)
+				atomic_set(&server->smb2slowcmd[i], 0);
+#endif /* CONFIG_CIFS_STATS2 */
 			list_for_each(tmp2, &server->smb_ses_list) {
 				ses = list_entry(tmp2, struct cifs_ses,
 						 smb_ses_list);
@@ -379,6 +403,10 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 							  struct cifs_tcon,
 							  tcon_list);
 					atomic_set(&tcon->num_smbs_sent, 0);
+					spin_lock(&tcon->stat_lock);
+					tcon->bytes_read = 0;
+					tcon->bytes_written = 0;
+					spin_unlock(&tcon->stat_lock);
 					if (server->ops->clear_stats)
 						server->ops->clear_stats(tcon);
 				}
@@ -395,13 +423,15 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 static int cifs_stats_proc_show(struct seq_file *m, void *v)
 {
 	int i;
+#ifdef CONFIG_CIFS_STATS2
+	int j;
+#endif /* STATS2 */
 	struct list_head *tmp1, *tmp2, *tmp3;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 
-	seq_printf(m,
-			"Resources in use\nCIFS Session: %d\n",
+	seq_printf(m, "Resources in use\nCIFS Session: %d\n",
 			sesInfoAllocCount.counter);
 	seq_printf(m, "Share (unique mount targets): %d\n",
 			tconInfoAllocCount.counter);
@@ -430,6 +460,13 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
 	list_for_each(tmp1, &cifs_tcp_ses_list) {
 		server = list_entry(tmp1, struct TCP_Server_Info,
 				    tcp_ses_list);
+#ifdef CONFIG_CIFS_STATS2
+		for (j = 0; j < NUMBER_OF_SMB2_COMMANDS; j++)
+			if (atomic_read(&server->smb2slowcmd[j]))
+				seq_printf(m, "%d slow responses from %s for command %d\n",
+					atomic_read(&server->smb2slowcmd[j]),
+					server->hostname, j);
+#endif /* STATS2 */
 		list_for_each(tmp2, &server->smb_ses_list) {
 			ses = list_entry(tmp2, struct cifs_ses,
 					 smb_ses_list);
@@ -466,7 +503,6 @@ static const struct file_operations cifs_stats_proc_fops = {
 	.release	= single_release,
 	.write		= cifs_stats_proc_write,
 };
-#endif /* STATS */
 
 #ifdef CONFIG_CIFS_SMB_DIRECT
 #define PROC_FILE_DEFINE(name) \
@@ -524,9 +560,7 @@ cifs_proc_init(void)
 	proc_create_single("DebugData", 0, proc_fs_cifs,
 			cifs_debug_data_proc_show);
 
-#ifdef CONFIG_CIFS_STATS
 	proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops);
-#endif /* STATS */
 	proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops);
 	proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops);
 	proc_create("LinuxExtensionsEnabled", 0644, proc_fs_cifs,
@@ -564,9 +598,7 @@ cifs_proc_clean(void)
 	remove_proc_entry("DebugData", proc_fs_cifs);
 	remove_proc_entry("cifsFYI", proc_fs_cifs);
 	remove_proc_entry("traceSMB", proc_fs_cifs);
-#ifdef CONFIG_CIFS_STATS
 	remove_proc_entry("Stats", proc_fs_cifs);
-#endif
 	remove_proc_entry("SecurityFlags", proc_fs_cifs);
 	remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs);
 	remove_proc_entry("LookupCacheEnabled", proc_fs_cifs);
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index ee2a8ec70056..85b31cfa2f3c 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -83,7 +83,13 @@ int __cifs_calc_signature(struct smb_rqst *rqst,
 
 		kaddr = (char *) kmap(rqst->rq_pages[i]) + offset;
 
-		crypto_shash_update(shash, kaddr, len);
+		rc = crypto_shash_update(shash, kaddr, len);
+		if (rc) {
+			cifs_dbg(VFS, "%s: Could not update with payload\n",
+				 __func__);
+			kunmap(rqst->rq_pages[i]);
+			return rc;
+		}
 
 		kunmap(rqst->rq_pages[i]);
 	}
@@ -452,7 +458,7 @@ find_timestamp(struct cifs_ses *ses)
 	unsigned char *blobptr;
 	unsigned char *blobend;
 	struct ntlmssp2_name *attrptr;
-	struct timespec ts;
+	struct timespec64 ts;
 
 	if (!ses->auth_key.len || !ses->auth_key.response)
 		return 0;
@@ -477,7 +483,7 @@ find_timestamp(struct cifs_ses *ses)
 		blobptr += attrsize; /* advance attr value */
 	}
 
-	ktime_get_real_ts(&ts);
+	ktime_get_real_ts64(&ts);
 	return cpu_to_le64(cifs_UnixTimeToNT(ts));
 }
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index d5aa7ae917bf..7065426b3280 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -139,6 +139,9 @@ cifs_read_super(struct super_block *sb)
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL)
 		sb->s_flags |= SB_POSIXACL;
 
+	if (tcon->snapshot_time)
+		sb->s_flags |= SB_RDONLY;
+
 	if (tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files)
 		sb->s_maxbytes = MAX_LFS_FILESIZE;
 	else
@@ -209,14 +212,16 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	xid = get_xid();
 
-	/*
-	 * PATH_MAX may be too long - it would presumably be total path,
-	 * but note that some servers (includinng Samba 3) have a shorter
-	 * maximum path.
-	 *
-	 * Instead could get the real value via SMB_QUERY_FS_ATTRIBUTE_INFO.
-	 */
-	buf->f_namelen = PATH_MAX;
+	if (le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength) > 0)
+		buf->f_namelen =
+		       le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength);
+	else
+		buf->f_namelen = PATH_MAX;
+
+	buf->f_fsid.val[0] = tcon->vol_serial_number;
+	/* are using part of create time for more randomness, see man statfs */
+	buf->f_fsid.val[1] =  (int)le64_to_cpu(tcon->vol_create_time);
+
 	buf->f_files = 0;	/* undefined */
 	buf->f_ffree = 0;	/* unlimited */
 
@@ -427,7 +432,7 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	else if (tcon->ses->user_name)
 		seq_show_option(s, "username", tcon->ses->user_name);
 
-	if (tcon->ses->domainName)
+	if (tcon->ses->domainName && tcon->ses->domainName[0] != 0)
 		seq_show_option(s, "domain", tcon->ses->domainName);
 
 	if (srcaddr->sa_family != AF_UNSPEC) {
@@ -481,20 +486,12 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",persistenthandles");
 	else if (tcon->use_resilient)
 		seq_puts(s, ",resilienthandles");
-
-#ifdef CONFIG_CIFS_SMB311
 	if (tcon->posix_extensions)
 		seq_puts(s, ",posix");
 	else if (tcon->unix_ext)
 		seq_puts(s, ",unix");
 	else
 		seq_puts(s, ",nounix");
-#else
-	if (tcon->unix_ext)
-		seq_puts(s, ",unix");
-	else
-		seq_puts(s, ",nounix");
-#endif /* SMB311 */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
 		seq_puts(s, ",posixpaths");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
@@ -546,6 +543,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	seq_printf(s, ",wsize=%u", cifs_sb->wsize);
 	seq_printf(s, ",echo_interval=%lu",
 			tcon->ses->server->echo_interval / HZ);
+	if (tcon->snapshot_time)
+		seq_printf(s, ",snapshot=%llu", tcon->snapshot_time);
 	/* convert actimeo and display it in seconds */
 	seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
 
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 5f0231803431..f3a78efc3109 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -65,8 +65,7 @@ extern struct inode *cifs_root_iget(struct super_block *);
 extern int cifs_create(struct inode *, struct dentry *, umode_t,
 		       bool excl);
 extern int cifs_atomic_open(struct inode *, struct dentry *,
-			    struct file *, unsigned, umode_t,
-			    int *);
+			    struct file *, unsigned, umode_t);
 extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
 				  unsigned int);
 extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index c923c7854027..0c9ab62c3df4 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -76,6 +76,9 @@
 #define SMB_ECHO_INTERVAL_MAX 600
 #define SMB_ECHO_INTERVAL_DEFAULT 60
 
+/* maximum number of PDUs in one compound */
+#define MAX_COMPOUND 5
+
 /*
  * Default number of credits to keep available for SMB3.
  * This value is chosen somewhat arbitrarily. The Windows client
@@ -191,9 +194,7 @@ enum smb_version {
 	Smb_21,
 	Smb_30,
 	Smb_302,
-#ifdef CONFIG_CIFS_SMB311
 	Smb_311,
-#endif /* SMB311 */
 	Smb_3any,
 	Smb_default,
 	Smb_version_err
@@ -456,13 +457,11 @@ struct smb_version_operations {
 	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 (*init_transform_rq)(struct TCP_Server_Info *, int num_rqst,
+				 struct smb_rqst *, struct smb_rqst *);
 	int (*is_transform_hdr)(void *buf);
 	int (*receive_transform)(struct TCP_Server_Info *,
-				 struct mid_q_entry **);
+				 struct mid_q_entry **, char **, int *);
 	enum securityEnum (*select_sectype)(struct TCP_Server_Info *,
 			    enum securityEnum);
 	int (*next_header)(char *);
@@ -684,15 +683,14 @@ struct TCP_Server_Info {
 #ifdef CONFIG_CIFS_STATS2
 	atomic_t in_send; /* requests trying to send */
 	atomic_t num_waiters;   /* blocked waiting to get in sendrecv */
-#endif
+	atomic_t smb2slowcmd[NUMBER_OF_SMB2_COMMANDS]; /* count resps > 1 sec */
+#endif /* STATS2 */
 	unsigned int	max_read;
 	unsigned int	max_write;
-#ifdef CONFIG_CIFS_SMB311
 	__le16	cipher_type;
 	 /* save initital negprot hash */
 	__u8	preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
 	bool	posix_ext_supported;
-#endif /* 3.1.1 */
 	struct delayed_work reconnect; /* reconnect workqueue job */
 	struct mutex reconnect_mutex; /* prevent simultaneous reconnects */
 	unsigned long echo_interval;
@@ -886,9 +884,7 @@ struct cifs_ses {
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
-#ifdef CONFIG_CIFS_SMB311
 	__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
-#endif /* 3.1.1 */
 
 	/*
 	 * Network interfaces available on the server this session is
@@ -913,6 +909,7 @@ cap_unix(struct cifs_ses *ses)
 
 struct cached_fid {
 	bool is_valid:1;	/* Do we have a useable root fid */
+	struct kref refcount;
 	struct cifs_fid *fid;
 	struct mutex fid_mutex;
 	struct cifs_tcon *tcon;
@@ -936,7 +933,6 @@ struct cifs_tcon {
 	__u32 tid;		/* The 4 byte tree id */
 	__u16 Flags;		/* optional support bits */
 	enum statusEnum tidStatus;
-#ifdef CONFIG_CIFS_STATS
 	atomic_t num_smbs_sent;
 	union {
 		struct {
@@ -967,24 +963,9 @@ struct cifs_tcon {
 			atomic_t smb2_com_failed[NUMBER_OF_SMB2_COMMANDS];
 		} smb2_stats;
 	} stats;
-#ifdef CONFIG_CIFS_STATS2
-	unsigned long long time_writes;
-	unsigned long long time_reads;
-	unsigned long long time_opens;
-	unsigned long long time_deletes;
-	unsigned long long time_closes;
-	unsigned long long time_mkdirs;
-	unsigned long long time_rmdirs;
-	unsigned long long time_renames;
-	unsigned long long time_t2renames;
-	unsigned long long time_ffirst;
-	unsigned long long time_fnext;
-	unsigned long long time_fclose;
-#endif /* CONFIG_CIFS_STATS2 */
 	__u64    bytes_read;
 	__u64    bytes_written;
 	spinlock_t stat_lock;  /* protects the two fields above */
-#endif /* CONFIG_CIFS_STATS */
 	FILE_SYSTEM_DEVICE_INFO fsDevInfo;
 	FILE_SYSTEM_ATTRIBUTE_INFO fsAttrInfo; /* ok if fs name truncated */
 	FILE_SYSTEM_UNIX_INFO fsUnixInfo;
@@ -997,9 +978,7 @@ struct cifs_tcon {
 	bool seal:1;      /* transport encryption for this mounted share */
 	bool unix_ext:1;  /* if false disable Linux extensions to CIFS protocol
 				for this mount even if server would support */
-#ifdef CONFIG_CIFS_SMB311
 	bool posix_extensions; /* if true SMB3.11 posix extensions enabled */
-#endif /* CIFS_311 */
 	bool local_lease:1; /* check leases (only) on local system not remote */
 	bool broken_posix_open; /* e.g. Samba server versions < 3.3.2, 3.2.9 */
 	bool broken_sparse_sup; /* if server or share does not support sparse */
@@ -1046,6 +1025,7 @@ struct tcon_link {
 };
 
 extern struct tcon_link *cifs_sb_tlink(struct cifs_sb_info *cifs_sb);
+extern void smb3_free_compound_rqst(int num_rqst, struct smb_rqst *rqst);
 
 static inline struct cifs_tcon *
 tlink_tcon(struct tcon_link *tlink)
@@ -1352,7 +1332,6 @@ convert_delimiter(char *path, char delim)
 		*pos = delim;
 }
 
-#ifdef CONFIG_CIFS_STATS
 #define cifs_stats_inc atomic_inc
 
 static inline void cifs_stats_bytes_written(struct cifs_tcon *tcon,
@@ -1372,13 +1351,6 @@ static inline void cifs_stats_bytes_read(struct cifs_tcon *tcon,
 	tcon->bytes_read += bytes;
 	spin_unlock(&tcon->stat_lock);
 }
-#else
-
-#define  cifs_stats_inc(field) do {} while (0)
-#define  cifs_stats_bytes_written(tcon, bytes) do {} while (0)
-#define  cifs_stats_bytes_read(tcon, bytes) do {} while (0)
-
-#endif
 
 
 /*
@@ -1544,9 +1516,9 @@ struct cifs_fattr {
 	dev_t		cf_rdev;
 	unsigned int	cf_nlink;
 	unsigned int	cf_dtype;
-	struct timespec	cf_atime;
-	struct timespec	cf_mtime;
-	struct timespec	cf_ctime;
+	struct timespec64 cf_atime;
+	struct timespec64 cf_mtime;
+	struct timespec64 cf_ctime;
 };
 
 static inline void free_dfs_info_param(struct dfs_info3_param *param)
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 1890f534c88b..20adda4de83b 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -94,6 +94,10 @@ extern int cifs_call_async(struct TCP_Server_Info *server,
 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 compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
+			      const int flags, const int num_rqst,
+			      struct smb_rqst *rqst, int *resp_buf_type,
+			      struct kvec *resp_iov);
 extern int SendReceive(const unsigned int /* xid */ , struct cifs_ses *,
 			struct smb_hdr * /* input */ ,
 			struct smb_hdr * /* out */ ,
@@ -143,9 +147,9 @@ extern enum securityEnum select_sectype(struct TCP_Server_Info *server,
 				enum securityEnum requested);
 extern int CIFS_SessSetup(const unsigned int xid, struct cifs_ses *ses,
 			  const struct nls_table *nls_cp);
-extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
-extern u64 cifs_UnixTimeToNT(struct timespec);
-extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
+extern struct timespec64 cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
+extern u64 cifs_UnixTimeToNT(struct timespec64);
+extern struct timespec64 cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
 				      int offset);
 extern void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock);
 extern int cifs_get_writer(struct cifsInodeInfo *cinode);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 93408eab92e7..dc2f4cf08fe9 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -508,13 +508,13 @@ decode_lanman_negprot_rsp(struct TCP_Server_Info *server, NEGOTIATE_RSP *pSMBr)
 		 * this requirement.
 		 */
 		int val, seconds, remain, result;
-		struct timespec ts;
-		unsigned long utc = ktime_get_real_seconds();
+		struct timespec64 ts;
+		time64_t utc = ktime_get_real_seconds();
 		ts = cnvrtDosUnixTm(rsp->SrvTime.Date,
 				    rsp->SrvTime.Time, 0);
-		cifs_dbg(FYI, "SrvTime %d sec since 1970 (utc: %d) diff: %d\n",
-			 (int)ts.tv_sec, (int)utc,
-			 (int)(utc - ts.tv_sec));
+		cifs_dbg(FYI, "SrvTime %lld sec since 1970 (utc: %lld) diff: %lld\n",
+			 ts.tv_sec, utc,
+			 utc - ts.tv_sec);
 		val = (int)(utc - ts.tv_sec);
 		seconds = abs(val);
 		result = (seconds / MIN_TZ_ADJ) * MIN_TZ_ADJ;
@@ -4082,7 +4082,7 @@ QInfRetry:
 	if (rc) {
 		cifs_dbg(FYI, "Send error in QueryInfo = %d\n", rc);
 	} else if (data) {
-		struct timespec ts;
+		struct timespec64 ts;
 		__u32 time = le32_to_cpu(pSMBr->last_write_time);
 
 		/* decode response */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 5df2c0698cda..c832a8a1970a 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -303,10 +303,8 @@ static const match_table_t cifs_smb_version_tokens = {
 	{ Smb_21, SMB21_VERSION_STRING },
 	{ Smb_30, SMB30_VERSION_STRING },
 	{ Smb_302, SMB302_VERSION_STRING },
-#ifdef CONFIG_CIFS_SMB311
 	{ Smb_311, SMB311_VERSION_STRING },
 	{ Smb_311, ALT_SMB311_VERSION_STRING },
-#endif /* SMB311 */
 	{ Smb_3any, SMB3ANY_VERSION_STRING },
 	{ Smb_default, SMBDEFAULT_VERSION_STRING },
 	{ Smb_version_err, NULL }
@@ -350,6 +348,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	server->max_read = 0;
 
 	cifs_dbg(FYI, "Reconnecting tcp session\n");
+	trace_smb3_reconnect(server->CurrentMid, server->hostname);
 
 	/* before reconnecting the tcp session, mark the smb session (uid)
 		and the tid bad so they are not used until reconnected */
@@ -851,13 +850,14 @@ cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 static int
 cifs_demultiplex_thread(void *p)
 {
-	int length;
+	int i, num_mids, length;
 	struct TCP_Server_Info *server = p;
 	unsigned int pdu_length;
 	unsigned int next_offset;
 	char *buf = NULL;
 	struct task_struct *task_to_wake = NULL;
-	struct mid_q_entry *mid_entry;
+	struct mid_q_entry *mids[MAX_COMPOUND];
+	char *bufs[MAX_COMPOUND];
 
 	current->flags |= PF_MEMALLOC;
 	cifs_dbg(FYI, "Demultiplex PID: %d\n", task_pid_nr(current));
@@ -924,58 +924,75 @@ next_pdu:
 				server->pdu_size = next_offset;
 		}
 
-		mid_entry = NULL;
+		memset(mids, 0, sizeof(mids));
+		memset(bufs, 0, sizeof(bufs));
+		num_mids = 0;
+
 		if (server->ops->is_transform_hdr &&
 		    server->ops->receive_transform &&
 		    server->ops->is_transform_hdr(buf)) {
 			length = server->ops->receive_transform(server,
-								&mid_entry);
+								mids,
+								bufs,
+								&num_mids);
 		} else {
-			mid_entry = server->ops->find_mid(server, buf);
+			mids[0] = server->ops->find_mid(server, buf);
+			bufs[0] = buf;
+			if (mids[0])
+				num_mids = 1;
 
-			if (!mid_entry || !mid_entry->receive)
-				length = standard_receive3(server, mid_entry);
+			if (!mids[0] || !mids[0]->receive)
+				length = standard_receive3(server, mids[0]);
 			else
-				length = mid_entry->receive(server, mid_entry);
+				length = mids[0]->receive(server, mids[0]);
 		}
 
 		if (length < 0) {
-			if (mid_entry)
-				cifs_mid_q_entry_release(mid_entry);
+			for (i = 0; i < num_mids; i++)
+				if (mids[i])
+					cifs_mid_q_entry_release(mids[i]);
 			continue;
 		}
 
 		if (server->large_buf)
 			buf = server->bigbuf;
 
+
 		server->lstrp = jiffies;
-		if (mid_entry != NULL) {
-			mid_entry->resp_buf_size = server->pdu_size;
-			if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
-			     mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
-					server->ops->handle_cancelled_mid)
-				server->ops->handle_cancelled_mid(
-							mid_entry->resp_buf,
-							server);
 
-			if (!mid_entry->multiRsp || mid_entry->multiEnd)
-				mid_entry->callback(mid_entry);
+		for (i = 0; i < num_mids; i++) {
+			if (mids[i] != NULL) {
+				mids[i]->resp_buf_size = server->pdu_size;
+				if ((mids[i]->mid_flags & MID_WAIT_CANCELLED) &&
+				    mids[i]->mid_state == MID_RESPONSE_RECEIVED &&
+				    server->ops->handle_cancelled_mid)
+					server->ops->handle_cancelled_mid(
+							mids[i]->resp_buf,
+							server);
 
-			cifs_mid_q_entry_release(mid_entry);
-		} else if (server->ops->is_oplock_break &&
-			   server->ops->is_oplock_break(buf, server)) {
-			cifs_dbg(FYI, "Received oplock break\n");
-		} else {
-			cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
-				 atomic_read(&midCount));
-			cifs_dump_mem("Received Data is: ", buf,
-				      HEADER_SIZE(server));
+				if (!mids[i]->multiRsp || mids[i]->multiEnd)
+					mids[i]->callback(mids[i]);
+
+				cifs_mid_q_entry_release(mids[i]);
+			} else if (server->ops->is_oplock_break &&
+				   server->ops->is_oplock_break(bufs[i],
+								server)) {
+				cifs_dbg(FYI, "Received oplock break\n");
+			} else {
+				cifs_dbg(VFS, "No task to wake, unknown frame "
+					 "received! NumMids %d\n",
+					 atomic_read(&midCount));
+				cifs_dump_mem("Received Data is: ", bufs[i],
+					      HEADER_SIZE(server));
 #ifdef CONFIG_CIFS_DEBUG2
-			if (server->ops->dump_detail)
-				server->ops->dump_detail(buf, server);
-			cifs_dump_mids(server);
+				if (server->ops->dump_detail)
+					server->ops->dump_detail(bufs[i],
+								 server);
+				cifs_dump_mids(server);
 #endif /* CIFS_DEBUG2 */
+			}
 		}
+
 		if (pdu_length > server->pdu_size) {
 			if (!allocate_buffers(server))
 				continue;
@@ -1174,6 +1191,7 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3)
 	substring_t args[MAX_OPT_ARGS];
 
 	switch (match_token(value, cifs_smb_version_tokens, args)) {
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	case Smb_1:
 		if (disable_legacy_dialects) {
 			cifs_dbg(VFS, "mount with legacy dialect disabled\n");
@@ -1198,6 +1216,14 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3)
 		vol->ops = &smb20_operations;
 		vol->vals = &smb20_values;
 		break;
+#else
+	case Smb_1:
+		cifs_dbg(VFS, "vers=1.0 (cifs) mount not permitted when legacy dialects disabled\n");
+		return 1;
+	case Smb_20:
+		cifs_dbg(VFS, "vers=2.0 mount not permitted when legacy dialects disabled\n");
+		return 1;
+#endif /* CIFS_ALLOW_INSECURE_LEGACY */
 	case Smb_21:
 		vol->ops = &smb21_operations;
 		vol->vals = &smb21_values;
@@ -1210,12 +1236,10 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3)
 		vol->ops = &smb30_operations; /* currently identical with 3.0 */
 		vol->vals = &smb302_values;
 		break;
-#ifdef CONFIG_CIFS_SMB311
 	case Smb_311:
 		vol->ops = &smb311_operations;
 		vol->vals = &smb311_values;
 		break;
-#endif /* SMB311 */
 	case Smb_3any:
 		vol->ops = &smb30_operations; /* currently identical with 3.0 */
 		vol->vals = &smb3any_values;
@@ -3030,15 +3054,17 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		}
 	}
 
-#ifdef CONFIG_CIFS_SMB311
-	if ((volume_info->linux_ext) && (ses->server->posix_ext_supported)) {
-		if (ses->server->vals->protocol_id == SMB311_PROT_ID) {
+	if (volume_info->linux_ext) {
+		if (ses->server->posix_ext_supported) {
 			tcon->posix_extensions = true;
 			printk_once(KERN_WARNING
 				"SMB3.11 POSIX Extensions are experimental\n");
+		} else {
+			cifs_dbg(VFS, "Server does not support mounting with posix SMB3.11 extensions.\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
 		}
 	}
-#endif /* 311 */
 
 	/*
 	 * BB Do we need to wrap session_mutex around this TCon call and Unix
@@ -3992,11 +4018,9 @@ try_mount_again:
 		goto remote_path_check;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
 	if (tcon->posix_extensions)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-#endif /* SMB3.11 */
 
 	/* tell server which Unix caps we support */
 	if (cap_unix(tcon->ses)) {
@@ -4459,11 +4483,10 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 		goto out;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
 	if (tcon->posix_extensions)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-#endif /* SMB3.11 */
+
 	if (cap_unix(ses))
 		reset_cifs_unix_caps(0, tcon, NULL, vol_info);
 
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index ddae52bd1993..3713d22b95a7 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -465,8 +465,7 @@ out_err:
 
 int
 cifs_atomic_open(struct inode *inode, struct dentry *direntry,
-		 struct file *file, unsigned oflags, umode_t mode,
-		 int *opened)
+		 struct file *file, unsigned oflags, umode_t mode)
 {
 	int rc;
 	unsigned int xid;
@@ -539,9 +538,9 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	}
 
 	if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
-		*opened |= FILE_CREATED;
+		file->f_mode |= FMODE_CREATED;
 
-	rc = finish_open(file, direntry, generic_file_open, opened);
+	rc = finish_open(file, direntry, generic_file_open);
 	if (rc) {
 		if (server->ops->close)
 			server->ops->close(xid, tcon, &fid);
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index 85145a763021..ea6ace9c2417 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -129,8 +129,10 @@ static void cifs_fscache_acquire_inode_cookie(struct cifsInodeInfo *cifsi,
 
 	memset(&auxdata, 0, sizeof(auxdata));
 	auxdata.eof = cifsi->server_eof;
-	auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
-	auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
+	auxdata.last_write_time_sec = cifsi->vfs_inode.i_mtime.tv_sec;
+	auxdata.last_change_time_sec = cifsi->vfs_inode.i_ctime.tv_sec;
+	auxdata.last_write_time_nsec = cifsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata.last_change_time_nsec = cifsi->vfs_inode.i_ctime.tv_nsec;
 
 	cifsi->fscache =
 		fscache_acquire_cookie(tcon->fscache,
@@ -166,8 +168,10 @@ void cifs_fscache_release_inode_cookie(struct inode *inode)
 	if (cifsi->fscache) {
 		memset(&auxdata, 0, sizeof(auxdata));
 		auxdata.eof = cifsi->server_eof;
-		auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
-		auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
+		auxdata.last_write_time_sec = cifsi->vfs_inode.i_mtime.tv_sec;
+		auxdata.last_change_time_sec = cifsi->vfs_inode.i_ctime.tv_sec;
+		auxdata.last_write_time_nsec = cifsi->vfs_inode.i_mtime.tv_nsec;
+		auxdata.last_change_time_nsec = cifsi->vfs_inode.i_ctime.tv_nsec;
 
 		cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cifsi->fscache);
 		fscache_relinquish_cookie(cifsi->fscache, &auxdata, false);
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index c7e3ac251e16..8c0862e41306 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -31,9 +31,11 @@
  * Auxiliary data attached to CIFS inode within the cache
  */
 struct cifs_fscache_inode_auxdata {
-	struct timespec	last_write_time;
-	struct timespec	last_change_time;
-	u64		eof;
+	u64 last_write_time_sec;
+	u64 last_change_time_sec;
+	u32 last_write_time_nsec;
+	u32 last_change_time_nsec;
+	u64 eof;
 };
 
 /*
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a2cfb33e85c1..d32eaa4b2437 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -95,7 +95,6 @@ static void
 cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 {
 	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
-	struct timespec ts;
 
 	cifs_dbg(FYI, "%s: revalidating inode %llu\n",
 		 __func__, cifs_i->uniqueid);
@@ -114,8 +113,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 	}
 
 	 /* revalidate if mtime or size have changed */
-	ts = timespec64_to_timespec(inode->i_mtime);
-	if (timespec_equal(&ts, &fattr->cf_mtime) &&
+	if (timespec64_equal(&inode->i_mtime, &fattr->cf_mtime) &&
 	    cifs_i->server_eof == fattr->cf_eof) {
 		cifs_dbg(FYI, "%s: inode %llu is unchanged\n",
 			 __func__, cifs_i->uniqueid);
@@ -164,9 +162,9 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 	cifs_revalidate_cache(inode, fattr);
 
 	spin_lock(&inode->i_lock);
-	inode->i_atime = timespec_to_timespec64(fattr->cf_atime);
-	inode->i_mtime = timespec_to_timespec64(fattr->cf_mtime);
-	inode->i_ctime = timespec_to_timespec64(fattr->cf_ctime);
+	inode->i_atime = fattr->cf_atime;
+	inode->i_mtime = fattr->cf_mtime;
+	inode->i_ctime = fattr->cf_ctime;
 	inode->i_rdev = fattr->cf_rdev;
 	cifs_nlink_fattr_to_inode(inode, fattr);
 	inode->i_uid = fattr->cf_uid;
@@ -327,8 +325,8 @@ cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb)
 	fattr->cf_mode = S_IFDIR | S_IXUGO | S_IRWXU;
 	fattr->cf_uid = cifs_sb->mnt_uid;
 	fattr->cf_gid = cifs_sb->mnt_gid;
-	ktime_get_real_ts(&fattr->cf_mtime);
-	fattr->cf_mtime = timespec_trunc(fattr->cf_mtime, sb->s_time_gran);
+	ktime_get_real_ts64(&fattr->cf_mtime);
+	fattr->cf_mtime = timespec64_trunc(fattr->cf_mtime, sb->s_time_gran);
 	fattr->cf_atime = fattr->cf_ctime = fattr->cf_mtime;
 	fattr->cf_nlink = 2;
 	fattr->cf_flags |= CIFS_FATTR_DFS_REFERRAL;
@@ -604,8 +602,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 	if (info->LastAccessTime)
 		fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
 	else {
-		ktime_get_real_ts(&fattr->cf_atime);
-		fattr->cf_atime = timespec_trunc(fattr->cf_atime, sb->s_time_gran);
+		ktime_get_real_ts64(&fattr->cf_atime);
+		fattr->cf_atime = timespec64_trunc(fattr->cf_atime, sb->s_time_gran);
 	}
 
 	fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime);
@@ -1122,17 +1120,19 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
 	if (!server->ops->set_file_info)
 		return -ENOSYS;
 
+	info_buf.Pad = 0;
+
 	if (attrs->ia_valid & ATTR_ATIME) {
 		set_time = true;
 		info_buf.LastAccessTime =
-			cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime)));
+			cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
 	} else
 		info_buf.LastAccessTime = 0;
 
 	if (attrs->ia_valid & ATTR_MTIME) {
 		set_time = true;
 		info_buf.LastWriteTime =
-		    cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime)));
+		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
 	} else
 		info_buf.LastWriteTime = 0;
 
@@ -1145,7 +1145,7 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
 	if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
 		cifs_dbg(FYI, "CIFS - CTIME changed\n");
 		info_buf.ChangeTime =
-		    cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime)));
+		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
 	} else
 		info_buf.ChangeTime = 0;
 
@@ -1577,14 +1577,12 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode)
 
 	server = tcon->ses->server;
 
-#ifdef CONFIG_CIFS_SMB311
 	if ((server->ops->posix_mkdir) && (tcon->posix_extensions)) {
 		rc = server->ops->posix_mkdir(xid, inode, mode, tcon, full_path,
 					      cifs_sb);
 		d_drop(direntry); /* for time being always refresh inode info */
 		goto mkdir_out;
 	}
-#endif /* SMB311 */
 
 	if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
 				le64_to_cpu(tcon->fsUnixInfo.Capability))) {
@@ -2071,8 +2069,8 @@ int cifs_getattr(const struct path *path, struct kstat *stat,
 	/* old CIFS Unix Extensions doesn't return create time */
 	if (CIFS_I(inode)->createtime) {
 		stat->result_mask |= STATX_BTIME;
-		stat->btime = timespec_to_timespec64(
-		      cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime)));
+		stat->btime =
+		      cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime));
 	}
 
 	stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED);
@@ -2278,17 +2276,17 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 		args->gid = INVALID_GID; /* no change */
 
 	if (attrs->ia_valid & ATTR_ATIME)
-		args->atime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime));
+		args->atime = cifs_UnixTimeToNT(attrs->ia_atime);
 	else
 		args->atime = NO_CHANGE_64;
 
 	if (attrs->ia_valid & ATTR_MTIME)
-		args->mtime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime));
+		args->mtime = cifs_UnixTimeToNT(attrs->ia_mtime);
 	else
 		args->mtime = NO_CHANGE_64;
 
 	if (attrs->ia_valid & ATTR_CTIME)
-		args->ctime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime));
+		args->ctime = cifs_UnixTimeToNT(attrs->ia_ctime);
 	else
 		args->ctime = NO_CHANGE_64;
 
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index de41f96aba49..2148b0f60e5e 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -396,7 +396,7 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_io_parms io_parms;
 	int buf_type = CIFS_NO_BUFFER;
 	__le16 *utf16_path;
-	__u8 oplock = SMB2_OPLOCK_LEVEL_II;
+	__u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct smb2_file_all_info *pfile_info = NULL;
 
 	oparms.tcon = tcon;
@@ -459,7 +459,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_io_parms io_parms;
 	int create_options = CREATE_NOT_DIR;
 	__le16 *utf16_path;
-	__u8 oplock = SMB2_OPLOCK_LEVEL_EXCLUSIVE;
+	__u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct kvec iov[2];
 
 	if (backup_cred(cifs_sb))
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 53e8362cbc4a..dacb2c05674c 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -122,9 +122,7 @@ tconInfoAlloc(void)
 		mutex_init(&ret_buf->crfid.fid_mutex);
 		ret_buf->crfid.fid = kzalloc(sizeof(struct cifs_fid),
 					     GFP_KERNEL);
-#ifdef CONFIG_CIFS_STATS
 		spin_lock_init(&ret_buf->stat_lock);
-#endif
 	}
 	return ret_buf;
 }
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index d7ad0dfe4e68..fdd908e4a26b 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -918,10 +918,10 @@ smbCalcSize(void *buf, struct TCP_Server_Info *server)
  * Convert the NT UTC (based 1601-01-01, in hundred nanosecond units)
  * into Unix UTC (based 1970-01-01, in seconds).
  */
-struct timespec
+struct timespec64
 cifs_NTtimeToUnix(__le64 ntutc)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 	/* BB what about the timezone? BB */
 
 	/* Subtract the NTFS time offset, then convert to 1s intervals. */
@@ -935,12 +935,12 @@ cifs_NTtimeToUnix(__le64 ntutc)
 	 */
 	if (t < 0) {
 		abs_t = -t;
-		ts.tv_nsec = (long)(do_div(abs_t, 10000000) * 100);
+		ts.tv_nsec = (time64_t)(do_div(abs_t, 10000000) * 100);
 		ts.tv_nsec = -ts.tv_nsec;
 		ts.tv_sec = -abs_t;
 	} else {
 		abs_t = t;
-		ts.tv_nsec = (long)do_div(abs_t, 10000000) * 100;
+		ts.tv_nsec = (time64_t)do_div(abs_t, 10000000) * 100;
 		ts.tv_sec = abs_t;
 	}
 
@@ -949,7 +949,7 @@ cifs_NTtimeToUnix(__le64 ntutc)
 
 /* Convert the Unix UTC into NT UTC. */
 u64
-cifs_UnixTimeToNT(struct timespec t)
+cifs_UnixTimeToNT(struct timespec64 t)
 {
 	/* Convert to 100ns intervals and then add the NTFS time offset. */
 	return (u64) t.tv_sec * 10000000 + t.tv_nsec/100 + NTFS_TIME_OFFSET;
@@ -959,10 +959,11 @@ static const int total_days_of_prev_months[] = {
 	0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334
 };
 
-struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
+struct timespec64 cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
 {
-	struct timespec ts;
-	int sec, min, days, month, year;
+	struct timespec64 ts;
+	time64_t sec;
+	int min, days, month, year;
 	u16 date = le16_to_cpu(le_date);
 	u16 time = le16_to_cpu(le_time);
 	SMB_TIME *st = (SMB_TIME *)&time;
@@ -973,7 +974,7 @@ struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
 	sec = 2 * st->TwoSeconds;
 	min = st->Minutes;
 	if ((sec > 59) || (min > 59))
-		cifs_dbg(VFS, "illegal time min %d sec %d\n", min, sec);
+		cifs_dbg(VFS, "illegal time min %d sec %lld\n", min, sec);
 	sec += (min * 60);
 	sec += 60 * 60 * st->Hours;
 	if (st->Hours > 24)
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 646dcd149de1..378151e09e91 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -624,7 +624,6 @@ cifs_query_file_info(const unsigned int xid, struct cifs_tcon *tcon,
 static void
 cifs_clear_stats(struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	atomic_set(&tcon->stats.cifs_stats.num_writes, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_reads, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_flushes, 0);
@@ -646,13 +645,11 @@ cifs_clear_stats(struct cifs_tcon *tcon)
 	atomic_set(&tcon->stats.cifs_stats.num_locks, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_acl_get, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_acl_set, 0);
-#endif
 }
 
 static void
 cifs_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	seq_printf(m, " Oplocks breaks: %d",
 		   atomic_read(&tcon->stats.cifs_stats.num_oplock_brks));
 	seq_printf(m, "\nReads:  %d Bytes: %llu",
@@ -684,7 +681,6 @@ cifs_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 		   atomic_read(&tcon->stats.cifs_stats.num_ffirst),
 		   atomic_read(&tcon->stats.cifs_stats.num_fnext),
 		   atomic_read(&tcon->stats.cifs_stats.num_fclose));
-#endif
 }
 
 static void
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index d01ad706d7fc..1eef1791d0c4 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -120,7 +120,9 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon,
 		break;
 	}
 
-	if (use_cached_root_handle == false)
+	if (use_cached_root_handle)
+		close_shroot(&tcon->crfid);
+	else
 		rc = SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	if (tmprc)
 		rc = tmprc;
@@ -281,7 +283,7 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	int rc;
 
 	if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) &&
-	    (buf->LastWriteTime == 0) && (buf->ChangeTime) &&
+	    (buf->LastWriteTime == 0) && (buf->ChangeTime == 0) &&
 	    (buf->Attributes == 0))
 		return 0; /* would be a no op, no sense sending this */
 
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 3ff7cec2da81..303d4592ebe7 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -93,7 +93,6 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 	/* SMB2_OPLOCK_BREAK */ cpu_to_le16(24)
 };
 
-#ifdef CONFIG_CIFS_SMB311
 static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
 			      __u32 non_ctxlen)
 {
@@ -127,7 +126,6 @@ static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
 	/* length of negcontexts including pad from end of sec blob to them */
 	return (len - nc_offset) + size_of_pad_before_neg_ctxts;
 }
-#endif /* CIFS_SMB311 */
 
 int
 smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
@@ -222,10 +220,9 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
 
 	clc_len = smb2_calc_size(buf, srvr);
 
-#ifdef CONFIG_CIFS_SMB311
 	if (shdr->Command == SMB2_NEGOTIATE)
 		clc_len += get_neg_ctxt_len(shdr, len, clc_len);
-#endif /* SMB311 */
+
 	if (len != clc_len) {
 		cifs_dbg(FYI, "Calculated size %u length %u mismatch mid %llu\n",
 			 clc_len, len, mid);
@@ -451,15 +448,13 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 	/* Windows doesn't allow paths beginning with \ */
 	if (from[0] == '\\')
 		start_of_path = from + 1;
-#ifdef CONFIG_CIFS_SMB311
+
 	/* SMB311 POSIX extensions paths do not include leading slash */
 	else if (cifs_sb_master_tlink(cifs_sb) &&
 		 cifs_sb_master_tcon(cifs_sb)->posix_extensions &&
 		 (from[0] == '/')) {
 		start_of_path = from + 1;
-	}
-#endif /* 311 */
-	else
+	} else
 		start_of_path = from;
 
 	to = cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
@@ -759,7 +754,6 @@ smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 /**
  * smb311_update_preauth_hash - update @ses hash with the packet data in @iov
  *
@@ -821,4 +815,3 @@ smb311_update_preauth_hash(struct cifs_ses *ses, struct kvec *iov, int nvec)
 
 	return 0;
 }
-#endif
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index ea92a38b2f08..541258447c4c 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -444,7 +444,11 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 			FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
 			NULL /* no data input */, 0 /* no data input */,
 			(char **)&out_buf, &ret_data_len);
-	if (rc != 0) {
+	if (rc == -EOPNOTSUPP) {
+		cifs_dbg(FYI,
+			 "server does not support query network interfaces\n");
+		goto out;
+	} else if (rc != 0) {
 		cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc);
 		goto out;
 	}
@@ -466,21 +470,36 @@ out:
 	return rc;
 }
 
-void
-smb2_cached_lease_break(struct work_struct *work)
+static void
+smb2_close_cached_fid(struct kref *ref)
 {
-	struct cached_fid *cfid = container_of(work,
-				struct cached_fid, lease_break);
-	mutex_lock(&cfid->fid_mutex);
+	struct cached_fid *cfid = container_of(ref, struct cached_fid,
+					       refcount);
+
 	if (cfid->is_valid) {
 		cifs_dbg(FYI, "clear cached root file handle\n");
 		SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid,
 			   cfid->fid->volatile_fid);
 		cfid->is_valid = false;
 	}
+}
+
+void close_shroot(struct cached_fid *cfid)
+{
+	mutex_lock(&cfid->fid_mutex);
+	kref_put(&cfid->refcount, smb2_close_cached_fid);
 	mutex_unlock(&cfid->fid_mutex);
 }
 
+void
+smb2_cached_lease_break(struct work_struct *work)
+{
+	struct cached_fid *cfid = container_of(work,
+				struct cached_fid, lease_break);
+
+	close_shroot(cfid);
+}
+
 /*
  * Open the directory at the root of a share
  */
@@ -495,6 +514,7 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
 	if (tcon->crfid.is_valid) {
 		cifs_dbg(FYI, "found a cached root file handle\n");
 		memcpy(pfid, tcon->crfid.fid, sizeof(struct cifs_fid));
+		kref_get(&tcon->crfid.refcount);
 		mutex_unlock(&tcon->crfid.fid_mutex);
 		return 0;
 	}
@@ -511,6 +531,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
 		memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid));
 		tcon->crfid.tcon = tcon;
 		tcon->crfid.is_valid = true;
+		kref_init(&tcon->crfid.refcount);
+		kref_get(&tcon->crfid.refcount);
 	}
 	mutex_unlock(&tcon->crfid.fid_mutex);
 	return rc;
@@ -549,9 +571,14 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
 	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
 			FS_DEVICE_INFORMATION);
 	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
+			FS_VOLUME_INFORMATION);
+	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
 			FS_SECTOR_SIZE_INFORMATION); /* SMB3 specific */
 	if (no_cached_open)
 		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+	else
+		close_shroot(&tcon->crfid);
+
 	return;
 }
 
@@ -873,13 +900,11 @@ smb2_can_echo(struct TCP_Server_Info *server)
 static void
 smb2_clear_stats(struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	int i;
 	for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++) {
 		atomic_set(&tcon->stats.smb2_stats.smb2_com_sent[i], 0);
 		atomic_set(&tcon->stats.smb2_stats.smb2_com_failed[i], 0);
 	}
-#endif
 }
 
 static void
@@ -918,67 +943,58 @@ smb2_dump_share_caps(struct seq_file *m, struct cifs_tcon *tcon)
 static void
 smb2_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	atomic_t *sent = tcon->stats.smb2_stats.smb2_com_sent;
 	atomic_t *failed = tcon->stats.smb2_stats.smb2_com_failed;
-	seq_printf(m, "\nNegotiates: %d sent %d failed",
-		   atomic_read(&sent[SMB2_NEGOTIATE_HE]),
-		   atomic_read(&failed[SMB2_NEGOTIATE_HE]));
-	seq_printf(m, "\nSessionSetups: %d sent %d failed",
-		   atomic_read(&sent[SMB2_SESSION_SETUP_HE]),
-		   atomic_read(&failed[SMB2_SESSION_SETUP_HE]));
-	seq_printf(m, "\nLogoffs: %d sent %d failed",
-		   atomic_read(&sent[SMB2_LOGOFF_HE]),
-		   atomic_read(&failed[SMB2_LOGOFF_HE]));
-	seq_printf(m, "\nTreeConnects: %d sent %d failed",
+
+	/*
+	 *  Can't display SMB2_NEGOTIATE, SESSION_SETUP, LOGOFF, CANCEL and ECHO
+	 *  totals (requests sent) since those SMBs are per-session not per tcon
+	 */
+	seq_printf(m, "\nBytes read: %llu  Bytes written: %llu",
+		   (long long)(tcon->bytes_read),
+		   (long long)(tcon->bytes_written));
+	seq_printf(m, "\nTreeConnects: %d total %d failed",
 		   atomic_read(&sent[SMB2_TREE_CONNECT_HE]),
 		   atomic_read(&failed[SMB2_TREE_CONNECT_HE]));
-	seq_printf(m, "\nTreeDisconnects: %d sent %d failed",
+	seq_printf(m, "\nTreeDisconnects: %d total %d failed",
 		   atomic_read(&sent[SMB2_TREE_DISCONNECT_HE]),
 		   atomic_read(&failed[SMB2_TREE_DISCONNECT_HE]));
-	seq_printf(m, "\nCreates: %d sent %d failed",
+	seq_printf(m, "\nCreates: %d total %d failed",
 		   atomic_read(&sent[SMB2_CREATE_HE]),
 		   atomic_read(&failed[SMB2_CREATE_HE]));
-	seq_printf(m, "\nCloses: %d sent %d failed",
+	seq_printf(m, "\nCloses: %d total %d failed",
 		   atomic_read(&sent[SMB2_CLOSE_HE]),
 		   atomic_read(&failed[SMB2_CLOSE_HE]));
-	seq_printf(m, "\nFlushes: %d sent %d failed",
+	seq_printf(m, "\nFlushes: %d total %d failed",
 		   atomic_read(&sent[SMB2_FLUSH_HE]),
 		   atomic_read(&failed[SMB2_FLUSH_HE]));
-	seq_printf(m, "\nReads: %d sent %d failed",
+	seq_printf(m, "\nReads: %d total %d failed",
 		   atomic_read(&sent[SMB2_READ_HE]),
 		   atomic_read(&failed[SMB2_READ_HE]));
-	seq_printf(m, "\nWrites: %d sent %d failed",
+	seq_printf(m, "\nWrites: %d total %d failed",
 		   atomic_read(&sent[SMB2_WRITE_HE]),
 		   atomic_read(&failed[SMB2_WRITE_HE]));
-	seq_printf(m, "\nLocks: %d sent %d failed",
+	seq_printf(m, "\nLocks: %d total %d failed",
 		   atomic_read(&sent[SMB2_LOCK_HE]),
 		   atomic_read(&failed[SMB2_LOCK_HE]));
-	seq_printf(m, "\nIOCTLs: %d sent %d failed",
+	seq_printf(m, "\nIOCTLs: %d total %d failed",
 		   atomic_read(&sent[SMB2_IOCTL_HE]),
 		   atomic_read(&failed[SMB2_IOCTL_HE]));
-	seq_printf(m, "\nCancels: %d sent %d failed",
-		   atomic_read(&sent[SMB2_CANCEL_HE]),
-		   atomic_read(&failed[SMB2_CANCEL_HE]));
-	seq_printf(m, "\nEchos: %d sent %d failed",
-		   atomic_read(&sent[SMB2_ECHO_HE]),
-		   atomic_read(&failed[SMB2_ECHO_HE]));
-	seq_printf(m, "\nQueryDirectories: %d sent %d failed",
+	seq_printf(m, "\nQueryDirectories: %d total %d failed",
 		   atomic_read(&sent[SMB2_QUERY_DIRECTORY_HE]),
 		   atomic_read(&failed[SMB2_QUERY_DIRECTORY_HE]));
-	seq_printf(m, "\nChangeNotifies: %d sent %d failed",
+	seq_printf(m, "\nChangeNotifies: %d total %d failed",
 		   atomic_read(&sent[SMB2_CHANGE_NOTIFY_HE]),
 		   atomic_read(&failed[SMB2_CHANGE_NOTIFY_HE]));
-	seq_printf(m, "\nQueryInfos: %d sent %d failed",
+	seq_printf(m, "\nQueryInfos: %d total %d failed",
 		   atomic_read(&sent[SMB2_QUERY_INFO_HE]),
 		   atomic_read(&failed[SMB2_QUERY_INFO_HE]));
-	seq_printf(m, "\nSetInfos: %d sent %d failed",
+	seq_printf(m, "\nSetInfos: %d total %d failed",
 		   atomic_read(&sent[SMB2_SET_INFO_HE]),
 		   atomic_read(&failed[SMB2_SET_INFO_HE]));
 	seq_printf(m, "\nOplockBreaks: %d sent %d failed",
 		   atomic_read(&sent[SMB2_OPLOCK_BREAK_HE]),
 		   atomic_read(&failed[SMB2_OPLOCK_BREAK_HE]));
-#endif
 }
 
 static void
@@ -1353,6 +1369,13 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 
 }
 
+/* GMT Token is @GMT-YYYY.MM.DD-HH.MM.SS Unicode which is 48 bytes + null */
+#define GMT_TOKEN_SIZE 50
+
+/*
+ * Input buffer contains (empty) struct smb_snapshot array with size filled in
+ * For output see struct SRV_SNAPSHOT_ARRAY in MS-SMB2 section 2.2.32.2
+ */
 static int
 smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 		   struct cifsFileInfo *cfile, void __user *ioc_buf)
@@ -1382,14 +1405,27 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 			kfree(retbuf);
 			return rc;
 		}
-		if (snapshot_in.snapshot_array_size < sizeof(struct smb_snapshot_array)) {
-			rc = -ERANGE;
-			kfree(retbuf);
-			return rc;
-		}
 
-		if (ret_data_len > snapshot_in.snapshot_array_size)
-			ret_data_len = snapshot_in.snapshot_array_size;
+		/*
+		 * Check for min size, ie not large enough to fit even one GMT
+		 * token (snapshot).  On the first ioctl some users may pass in
+		 * smaller size (or zero) to simply get the size of the array
+		 * so the user space caller can allocate sufficient memory
+		 * and retry the ioctl again with larger array size sufficient
+		 * to hold all of the snapshot GMT tokens on the second try.
+		 */
+		if (snapshot_in.snapshot_array_size < GMT_TOKEN_SIZE)
+			ret_data_len = sizeof(struct smb_snapshot_array);
+
+		/*
+		 * We return struct SRV_SNAPSHOT_ARRAY, followed by
+		 * the snapshot array (of 50 byte GMT tokens) each
+		 * representing an available previous version of the data
+		 */
+		if (ret_data_len > (snapshot_in.snapshot_array_size +
+					sizeof(struct smb_snapshot_array)))
+			ret_data_len = snapshot_in.snapshot_array_size +
+					sizeof(struct smb_snapshot_array);
 
 		if (copy_to_user(ioc_buf, retbuf, ret_data_len))
 			rc = -EFAULT;
@@ -1487,7 +1523,11 @@ smb2_is_session_expired(char *buf)
 	    shdr->Status != STATUS_USER_SESSION_DELETED)
 		return false;
 
+	trace_smb3_ses_expired(shdr->TreeId, shdr->SessionId,
+			       le16_to_cpu(shdr->Command),
+			       le64_to_cpu(shdr->MessageId));
 	cifs_dbg(FYI, "Session expired or deleted\n");
+
 	return true;
 }
 
@@ -1504,16 +1544,140 @@ smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid,
 				 CIFS_CACHE_READ(cinode) ? 1 : 0);
 }
 
+static void
+smb2_set_related(struct smb_rqst *rqst)
+{
+	struct smb2_sync_hdr *shdr;
+
+	shdr = (struct smb2_sync_hdr *)(rqst->rq_iov[0].iov_base);
+	shdr->Flags |= SMB2_FLAGS_RELATED_OPERATIONS;
+}
+
+char smb2_padding[7] = {0, 0, 0, 0, 0, 0, 0};
+
+static void
+smb2_set_next_command(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+{
+	struct smb2_sync_hdr *shdr;
+	unsigned long len = smb_rqst_len(server, rqst);
+
+	/* SMB headers in a compound are 8 byte aligned. */
+	if (len & 7) {
+		rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding;
+		rqst->rq_iov[rqst->rq_nvec].iov_len = 8 - (len & 7);
+		rqst->rq_nvec++;
+		len = smb_rqst_len(server, rqst);
+	}
+
+	shdr = (struct smb2_sync_hdr *)(rqst->rq_iov[0].iov_base);
+	shdr->NextCommand = cpu_to_le32(len);
+}
+
 static int
 smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	     struct kstatfs *buf)
 {
+	struct smb2_query_info_rsp *rsp;
+	struct smb2_fs_full_size_info *info = NULL;
+	struct smb_rqst rqst[3];
+	int resp_buftype[3];
+	struct kvec rsp_iov[3];
+	struct kvec open_iov[5]; /* 4 + potential padding. */
+	struct kvec qi_iov[1];
+	struct kvec close_iov[1];
+	struct cifs_ses *ses = tcon->ses;
+	struct TCP_Server_Info *server = ses->server;
+	__le16 srch_path = 0; /* Null - open root of share */
+	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+	struct cifs_open_parms oparms;
+	struct cifs_fid fid;
+	int flags = 0;
+	int rc;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	memset(rqst, 0, sizeof(rqst));
+	memset(resp_buftype, 0, sizeof(resp_buftype));
+	memset(rsp_iov, 0, sizeof(rsp_iov));
+
+	memset(&open_iov, 0, sizeof(open_iov));
+	rqst[0].rq_iov = open_iov;
+	rqst[0].rq_nvec = 4;
+
+	oparms.tcon = tcon;
+	oparms.desired_access = FILE_READ_ATTRIBUTES;
+	oparms.disposition = FILE_OPEN;
+	oparms.create_options = 0;
+	oparms.fid = &fid;
+	oparms.reconnect = false;
+
+	rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, &srch_path);
+	if (rc)
+		goto qfs_exit;
+	smb2_set_next_command(server, &rqst[0]);
+
+	memset(&qi_iov, 0, sizeof(qi_iov));
+	rqst[1].rq_iov = qi_iov;
+	rqst[1].rq_nvec = 1;
+
+	rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, COMPOUND_FID,
+				  FS_FULL_SIZE_INFORMATION,
+				  SMB2_O_INFO_FILESYSTEM, 0,
+				  sizeof(struct smb2_fs_full_size_info));
+	if (rc)
+		goto qfs_exit;
+	smb2_set_next_command(server, &rqst[1]);
+	smb2_set_related(&rqst[1]);
+
+	memset(&close_iov, 0, sizeof(close_iov));
+	rqst[2].rq_iov = close_iov;
+	rqst[2].rq_nvec = 1;
+
+	rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID);
+	if (rc)
+		goto qfs_exit;
+	smb2_set_related(&rqst[2]);
+
+	rc = compound_send_recv(xid, ses, flags, 3, rqst,
+				resp_buftype, rsp_iov);
+	if (rc)
+		goto qfs_exit;
+
+	rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base;
+	buf->f_type = SMB2_MAGIC_NUMBER;
+	info = (struct smb2_fs_full_size_info *)(
+		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength),
+			       &rsp_iov[1],
+			       sizeof(struct smb2_fs_full_size_info));
+	if (!rc)
+		smb2_copy_fs_info_to_kstatfs(info, buf);
+
+qfs_exit:
+	SMB2_open_free(&rqst[0]);
+	SMB2_query_info_free(&rqst[1]);
+	SMB2_close_free(&rqst[2]);
+	free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
+	free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
+	free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base);
+	return rc;
+}
+
+static int
+smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
+	     struct kstatfs *buf)
+{
 	int rc;
 	__le16 srch_path = 0; /* Null - open root of share */
 	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct cifs_open_parms oparms;
 	struct cifs_fid fid;
 
+	if (!tcon->posix_extensions)
+		return smb2_queryfs(xid, tcon, buf);
+
 	oparms.tcon = tcon;
 	oparms.desired_access = FILE_READ_ATTRIBUTES;
 	oparms.disposition = FILE_OPEN;
@@ -1524,9 +1688,10 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, NULL);
 	if (rc)
 		return rc;
+
+	rc = SMB311_posix_qfs_info(xid, tcon, fid.persistent_fid,
+				   fid.volatile_fid, buf);
 	buf->f_type = SMB2_MAGIC_NUMBER;
-	rc = SMB2_QFS_info(xid, tcon, fid.persistent_fid, fid.volatile_fid,
-			   buf);
 	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	return rc;
 }
@@ -1700,7 +1865,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 		       &resp_buftype);
 	if (!rc || !err_iov.iov_base) {
 		rc = -ENOENT;
-		goto querty_exit;
+		goto free_path;
 	}
 
 	err_buf = err_iov.iov_base;
@@ -1741,6 +1906,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 
  querty_exit:
 	free_rsp_buf(resp_buftype, err_buf);
+ free_path:
 	kfree(utf16_path);
 	return rc;
 }
@@ -2326,35 +2492,51 @@ static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf,
 	sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
 }
 
-/* Assumes:
- * rqst->rq_iov[0]  is transform header
- * rqst->rq_iov[1+] data to be encrypted/decrypted
+/* Assumes the first rqst has a transform header as the first iov.
+ * I.e.
+ * rqst[0].rq_iov[0]  is transform header
+ * rqst[0].rq_iov[1+] data to be encrypted/decrypted
+ * rqst[1+].rq_iov[0+] data to be encrypted/decrypted
  */
 static struct scatterlist *
-init_sg(struct smb_rqst *rqst, u8 *sign)
+init_sg(int num_rqst, 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) - 20;
+	unsigned int sg_len;
 	struct scatterlist *sg;
 	unsigned int i;
 	unsigned int j;
+	unsigned int idx = 0;
+	int skip;
+
+	sg_len = 1;
+	for (i = 0; i < num_rqst; i++)
+		sg_len += rqst[i].rq_nvec + rqst[i].rq_npages;
 
 	sg = kmalloc_array(sg_len, sizeof(struct scatterlist), GFP_KERNEL);
 	if (!sg)
 		return NULL;
 
 	sg_init_table(sg, sg_len);
-	smb2_sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 20, assoc_data_len);
-	for (i = 1; i < rqst->rq_nvec; i++)
-		smb2_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, offset;
+	for (i = 0; i < num_rqst; i++) {
+		for (j = 0; j < rqst[i].rq_nvec; j++) {
+			/*
+			 * The first rqst has a transform header where the
+			 * first 20 bytes are not part of the encrypted blob
+			 */
+			skip = (i == 0) && (j == 0) ? 20 : 0;
+			smb2_sg_set_buf(&sg[idx++],
+					rqst[i].rq_iov[j].iov_base + skip,
+					rqst[i].rq_iov[j].iov_len - skip);
+		}
 
-		rqst_page_get_length(rqst, j, &len, &offset);
-		sg_set_page(&sg[i], rqst->rq_pages[j], len, offset);
+		for (j = 0; j < rqst[i].rq_npages; j++) {
+			unsigned int len, offset;
+
+			rqst_page_get_length(&rqst[i], j, &len, &offset);
+			sg_set_page(&sg[idx++], rqst[i].rq_pages[j], len, offset);
+		}
 	}
-	smb2_sg_set_buf(&sg[sg_len - 1], sign, SMB2_SIGNATURE_SIZE);
+	smb2_sg_set_buf(&sg[idx], sign, SMB2_SIGNATURE_SIZE);
 	return sg;
 }
 
@@ -2386,10 +2568,11 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
  * untouched.
  */
 static int
-crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
+crypt_message(struct TCP_Server_Info *server, int num_rqst,
+	      struct smb_rqst *rqst, int enc)
 {
 	struct smb2_transform_hdr *tr_hdr =
-			(struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
+		(struct smb2_transform_hdr *)rqst[0].rq_iov[0].iov_base;
 	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
 	int rc = 0;
 	struct scatterlist *sg;
@@ -2440,7 +2623,7 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
 		crypt_len += SMB2_SIGNATURE_SIZE;
 	}
 
-	sg = init_sg(rqst, sign);
+	sg = init_sg(num_rqst, rqst, sign);
 	if (!sg) {
 		cifs_dbg(VFS, "%s: Failed to init sg", __func__);
 		rc = -ENOMEM;
@@ -2477,103 +2660,98 @@ free_req:
 	return rc;
 }
 
+void
+smb3_free_compound_rqst(int num_rqst, struct smb_rqst *rqst)
+{
+	int i, j;
+
+	for (i = 0; i < num_rqst; i++) {
+		if (rqst[i].rq_pages) {
+			for (j = rqst[i].rq_npages - 1; j >= 0; j--)
+				put_page(rqst[i].rq_pages[j]);
+			kfree(rqst[i].rq_pages);
+		}
+	}
+}
+
+/*
+ * This function will initialize new_rq and encrypt the content.
+ * The first entry, new_rq[0], only contains a single iov which contains
+ * a smb2_transform_hdr and is pre-allocated by the caller.
+ * This function then populates new_rq[1+] with the content from olq_rq[0+].
+ *
+ * The end result is an array of smb_rqst structures where the first structure
+ * only contains a single iov for the transform header which we then can pass
+ * to crypt_message().
+ *
+ * new_rq[0].rq_iov[0] :  smb2_transform_hdr pre-allocated by the caller
+ * new_rq[1+].rq_iov[*] == old_rq[0+].rq_iov[*] : SMB2/3 requests
+ */
 static int
-smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
-		       struct smb_rqst *old_rq)
+smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst,
+		       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;
-	unsigned int orig_len;
-	int i;
+	struct smb2_transform_hdr *tr_hdr = new_rq[0].rq_iov[0].iov_base;
+	unsigned int npages;
+	unsigned int orig_len = 0;
+	int i, j;
 	int rc = -ENOMEM;
 
-	pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
-	if (!pages)
-		return rc;
-
-	new_rq->rq_pages = pages;
-	new_rq->rq_offset = old_rq->rq_offset;
-	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 + 1, sizeof(struct kvec),
-			    GFP_KERNEL);
-	if (!iov)
-		goto err_free_pages;
+	for (i = 1; i < num_rqst; i++) {
+		npages = old_rq[i - 1].rq_npages;
+		pages = kmalloc_array(npages, sizeof(struct page *),
+				      GFP_KERNEL);
+		if (!pages)
+			goto err_free;
+
+		new_rq[i].rq_pages = pages;
+		new_rq[i].rq_npages = npages;
+		new_rq[i].rq_offset = old_rq[i - 1].rq_offset;
+		new_rq[i].rq_pagesz = old_rq[i - 1].rq_pagesz;
+		new_rq[i].rq_tailsz = old_rq[i - 1].rq_tailsz;
+		new_rq[i].rq_iov = old_rq[i - 1].rq_iov;
+		new_rq[i].rq_nvec = old_rq[i - 1].rq_nvec;
+
+		orig_len += smb_rqst_len(server, &old_rq[i - 1]);
+
+		for (j = 0; j < npages; j++) {
+			pages[j] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
+			if (!pages[j])
+				goto err_free;
+		}
 
-	/* copy all iovs from the old */
-	memcpy(&iov[1], &old_rq->rq_iov[0],
-				sizeof(struct kvec) * old_rq->rq_nvec);
+		/* copy pages form the old */
+		for (j = 0; j < npages; j++) {
+			char *dst, *src;
+			unsigned int offset, len;
 
-	new_rq->rq_iov = iov;
-	new_rq->rq_nvec = old_rq->rq_nvec + 1;
+			rqst_page_get_length(&new_rq[i], j, &len, &offset);
 
-	tr_hdr = kmalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL);
-	if (!tr_hdr)
-		goto err_free_iov;
+			dst = (char *) kmap(new_rq[i].rq_pages[j]) + offset;
+			src = (char *) kmap(old_rq[i - 1].rq_pages[j]) + offset;
 
-	orig_len = smb_rqst_len(server, old_rq);
+			memcpy(dst, src, len);
+			kunmap(new_rq[i].rq_pages[j]);
+			kunmap(old_rq[i - 1].rq_pages[j]);
+		}
+	}
 
-	/* fill the 2nd iov with a transform header */
+	/* fill the 1st iov with a transform header */
 	fill_transform_hdr(tr_hdr, orig_len, 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, *src;
-		unsigned int offset, len;
-
-		rqst_page_get_length(new_rq, i, &len, &offset);
-
-		dst = (char *) kmap(new_rq->rq_pages[i]) + offset;
-		src = (char *) kmap(old_rq->rq_pages[i]) + offset;
 
-		memcpy(dst, src, len);
-		kunmap(new_rq->rq_pages[i]);
-		kunmap(old_rq->rq_pages[i]);
-	}
-
-	rc = crypt_message(server, new_rq, 1);
+	rc = crypt_message(server, num_rqst, new_rq, 1);
 	cifs_dbg(FYI, "encrypt message returned %d", rc);
 	if (rc)
-		goto err_free_tr_hdr;
+		goto err_free;
 
 	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);
+err_free:
+	smb3_free_compound_rqst(num_rqst - 1, &new_rq[1]);
 	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)
 {
@@ -2603,7 +2781,7 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
 	rqst.rq_pagesz = PAGE_SIZE;
 	rqst.rq_tailsz = (page_data_size % PAGE_SIZE) ? : PAGE_SIZE;
 
-	rc = crypt_message(server, &rqst, 0);
+	rc = crypt_message(server, 1, &rqst, 0);
 	cifs_dbg(FYI, "decrypt message returned %d\n", rc);
 
 	if (rc)
@@ -2878,13 +3056,20 @@ discard_data:
 
 static int
 receive_encrypted_standard(struct TCP_Server_Info *server,
-			   struct mid_q_entry **mid)
+			   struct mid_q_entry **mids, char **bufs,
+			   int *num_mids)
 {
-	int length;
+	int ret, length;
 	char *buf = server->smallbuf;
+	char *tmpbuf;
+	struct smb2_sync_hdr *shdr;
 	unsigned int pdu_length = server->pdu_size;
 	unsigned int buf_size;
 	struct mid_q_entry *mid_entry;
+	int next_is_large;
+	char *next_buffer = NULL;
+
+	*num_mids = 0;
 
 	/* switch to large buffer if too big for a small one */
 	if (pdu_length > MAX_CIFS_SMALL_BUFFER_SIZE) {
@@ -2905,24 +3090,61 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 	if (length)
 		return length;
 
+	next_is_large = server->large_buf;
+ one_more:
+	shdr = (struct smb2_sync_hdr *)buf;
+	if (shdr->NextCommand) {
+		if (next_is_large) {
+			tmpbuf = server->bigbuf;
+			next_buffer = (char *)cifs_buf_get();
+		} else {
+			tmpbuf = server->smallbuf;
+			next_buffer = (char *)cifs_small_buf_get();
+		}
+		memcpy(next_buffer,
+		       tmpbuf + le32_to_cpu(shdr->NextCommand),
+		       pdu_length - le32_to_cpu(shdr->NextCommand));
+	}
+
 	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_entry->resp_buf_size = server->pdu_size;
 	}
 
-	*mid = mid_entry;
+	if (*num_mids >= MAX_COMPOUND) {
+		cifs_dbg(VFS, "too many PDUs in compound\n");
+		return -1;
+	}
+	bufs[*num_mids] = buf;
+	mids[(*num_mids)++] = mid_entry;
 
 	if (mid_entry && mid_entry->handle)
-		return mid_entry->handle(server, mid_entry);
+		ret = mid_entry->handle(server, mid_entry);
+	else
+		ret = cifs_handle_standard(server, mid_entry);
 
-	return cifs_handle_standard(server, mid_entry);
+	if (ret == 0 && shdr->NextCommand) {
+		pdu_length -= le32_to_cpu(shdr->NextCommand);
+		server->large_buf = next_is_large;
+		if (next_is_large)
+			server->bigbuf = next_buffer;
+		else
+			server->smallbuf = next_buffer;
+
+		buf += le32_to_cpu(shdr->NextCommand);
+		goto one_more;
+	}
+
+	return ret;
 }
 
 static int
-smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
+smb3_receive_transform(struct TCP_Server_Info *server,
+		       struct mid_q_entry **mids, char **bufs, int *num_mids)
 {
 	char *buf = server->smallbuf;
 	unsigned int pdu_length = server->pdu_size;
@@ -2945,10 +3167,11 @@ smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
 		return -ECONNABORTED;
 	}
 
+	/* TODO: add support for compounds containing READ. */
 	if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server))
-		return receive_encrypted_read(server, mid);
+		return receive_encrypted_read(server, &mids[0]);
 
-	return receive_encrypted_standard(server, mid);
+	return receive_encrypted_standard(server, mids, bufs, num_mids);
 }
 
 int
@@ -3250,7 +3473,6 @@ struct smb_version_operations smb30_operations = {
 	.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,
 	.get_dfs_refer = smb2_get_dfs_refer,
@@ -3267,7 +3489,6 @@ struct smb_version_operations smb30_operations = {
 	.next_header = smb2_next_header,
 };
 
-#ifdef CONFIG_CIFS_SMB311
 struct smb_version_operations smb311_operations = {
 	.compare_fids = smb2_compare_fids,
 	.setup_request = smb2_setup_request,
@@ -3335,7 +3556,7 @@ struct smb_version_operations smb311_operations = {
 	.is_status_pending = smb2_is_status_pending,
 	.is_session_expired = smb2_is_session_expired,
 	.oplock_response = smb2_oplock_response,
-	.queryfs = smb2_queryfs,
+	.queryfs = smb311_queryfs,
 	.mand_lock = smb2_mand_lock,
 	.mand_unlock_range = smb2_unlock_range,
 	.push_mand_locks = smb2_push_mandatory_locks,
@@ -3357,7 +3578,6 @@ struct smb_version_operations smb311_operations = {
 	.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,
 	.get_dfs_refer = smb2_get_dfs_refer,
@@ -3366,9 +3586,13 @@ struct smb_version_operations smb311_operations = {
 	.query_all_EAs = smb2_query_eas,
 	.set_EA = smb2_set_ea,
 #endif /* CIFS_XATTR */
+#ifdef CONFIG_CIFS_ACL
+	.get_acl = get_smb2_acl,
+	.get_acl_by_fid = get_smb2_acl_by_fid,
+	.set_acl = set_smb2_acl,
+#endif /* CIFS_ACL */
 	.next_header = smb2_next_header,
 };
-#endif /* CIFS_SMB311 */
 
 struct smb_version_values smb20_values = {
 	.version_string = SMB20_VERSION_STRING,
@@ -3496,7 +3720,6 @@ struct smb_version_values smb302_values = {
 	.create_lease_size = sizeof(struct create_lease_v2),
 };
 
-#ifdef CONFIG_CIFS_SMB311
 struct smb_version_values smb311_values = {
 	.version_string = SMB311_VERSION_STRING,
 	.protocol_id = SMB311_PROT_ID,
@@ -3517,4 +3740,3 @@ struct smb_version_values smb311_values = {
 	.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
 	.create_lease_size = sizeof(struct create_lease_v2),
 };
-#endif /* SMB311 */
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 3c92678cb45b..2f1938011395 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -80,7 +80,7 @@ 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 smb3_encryption_required(const struct cifs_tcon *tcon)
+int smb3_encryption_required(const struct cifs_tcon *tcon)
 {
 	if (!tcon)
 		return 0;
@@ -360,17 +360,15 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		       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;
 }
 
-#ifdef CONFIG_CIFS_SMB311
+
 /* offset is sizeof smb2_negotiate_req but rounded up to 8 bytes */
 #define OFFSET_OF_NEG_CONTEXT 0x68  /* sizeof(struct smb2_negotiate_req) */
 
@@ -585,13 +583,6 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode)
 	return 0;
 }
 
-#else
-static void assemble_neg_contexts(struct smb2_negotiate_req *req,
-				  unsigned int *total_len)
-{
-	return;
-}
-#endif /* SMB311 */
 
 /*
  *
@@ -636,10 +627,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		return rc;
 
 	req->sync_hdr.SessionId = 0;
-#ifdef CONFIG_CIFS_SMB311
+
 	memset(server->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
 	memset(ses->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
-#endif
 
 	if (strcmp(ses->server->vals->version_string,
 		   SMB3ANY_VERSION_STRING) == 0) {
@@ -741,10 +731,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		cifs_dbg(FYI, "negotiated smb3.0 dialect\n");
 	else if (rsp->DialectRevision == cpu_to_le16(SMB302_PROT_ID))
 		cifs_dbg(FYI, "negotiated smb3.02 dialect\n");
-#ifdef CONFIG_CIFS_SMB311
 	else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID))
 		cifs_dbg(FYI, "negotiated smb3.1.1 dialect\n");
-#endif /* SMB311 */
 	else {
 		cifs_dbg(VFS, "Illegal dialect returned by server 0x%x\n",
 			 le16_to_cpu(rsp->DialectRevision));
@@ -753,9 +741,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	}
 	server->dialect = le16_to_cpu(rsp->DialectRevision);
 
-	/* BB: add check that dialect was valid given dialect(s) we asked for */
-
-#ifdef CONFIG_CIFS_SMB311
 	/*
 	 * Keep a copy of the hash after negprot. This hash will be
 	 * the starting hash value for all sessions made from this
@@ -763,7 +748,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	 */
 	memcpy(server->preauth_sha_hash, ses->preauth_sha_hash,
 	       SMB2_PREAUTH_HASH_SIZE);
-#endif
+
 	/* SMB2 only has an extended negflavor */
 	server->negflavor = CIFS_NEGFLAVOR_EXTENDED;
 	/* set it to the maximum buffer size value we can send with 1 credit */
@@ -804,7 +789,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 			rc = -EIO;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
 		if (rsp->NegotiateContextCount)
 			rc = smb311_decode_neg_context(rsp, server,
@@ -812,7 +796,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		else
 			cifs_dbg(VFS, "Missing expected negotiate contexts\n");
 	}
-#endif /* CONFIG_CIFS_SMB311 */
 neg_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -1373,13 +1356,11 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	sess_data->nls_cp = (struct nls_table *) nls_cp;
 	sess_data->previous_session = ses->Suid;
 
-#ifdef CONFIG_CIFS_SMB311
 	/*
 	 * Initialize the session hash with the server one.
 	 */
 	memcpy(ses->preauth_sha_hash, ses->server->preauth_sha_hash,
 	       SMB2_PREAUTH_HASH_SIZE);
-#endif
 
 	while (sess_data->func)
 		sess_data->func(sess_data);
@@ -1875,6 +1856,51 @@ add_durable_context(struct kvec *iov, unsigned int *num_iovec,
 	return 0;
 }
 
+/* See MS-SMB2 2.2.13.2.7 */
+static struct crt_twarp_ctxt *
+create_twarp_buf(__u64 timewarp)
+{
+	struct crt_twarp_ctxt *buf;
+
+	buf = kzalloc(sizeof(struct crt_twarp_ctxt), GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	buf->ccontext.DataOffset = cpu_to_le16(offsetof
+					(struct crt_twarp_ctxt, Timestamp));
+	buf->ccontext.DataLength = cpu_to_le32(8);
+	buf->ccontext.NameOffset = cpu_to_le16(offsetof
+				(struct crt_twarp_ctxt, Name));
+	buf->ccontext.NameLength = cpu_to_le16(4);
+	/* SMB2_CREATE_TIMEWARP_TOKEN is "TWrp" */
+	buf->Name[0] = 'T';
+	buf->Name[1] = 'W';
+	buf->Name[2] = 'r';
+	buf->Name[3] = 'p';
+	buf->Timestamp = cpu_to_le64(timewarp);
+	return buf;
+}
+
+/* See MS-SMB2 2.2.13.2.7 */
+static int
+add_twarp_context(struct kvec *iov, unsigned int *num_iovec, __u64 timewarp)
+{
+	struct smb2_create_req *req = iov[0].iov_base;
+	unsigned int num = *num_iovec;
+
+	iov[num].iov_base = create_twarp_buf(timewarp);
+	if (iov[num].iov_base == NULL)
+		return -ENOMEM;
+	iov[num].iov_len = sizeof(struct crt_twarp_ctxt);
+	if (!req->CreateContextsOffset)
+		req->CreateContextsOffset = cpu_to_le32(
+				sizeof(struct smb2_create_req) +
+				iov[num - 1].iov_len);
+	le32_add_cpu(&req->CreateContextsLength, sizeof(struct crt_twarp_ctxt));
+	*num_iovec = num + 1;
+	return 0;
+}
+
 static int
 alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len,
 			    const char *treename, const __le16 *path)
@@ -1920,7 +1946,6 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len,
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 			       umode_t mode, struct cifs_tcon *tcon,
 			       const char *full_path,
@@ -1928,7 +1953,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 {
 	struct smb_rqst rqst;
 	struct smb2_create_req *req;
-	struct smb2_create_rsp *rsp;
+	struct smb2_create_rsp *rsp = NULL;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[3]; /* make sure at least one for each open context */
@@ -1943,27 +1968,31 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	char *pc_buf = NULL;
 	int flags = 0;
 	unsigned int total_len;
-	__le16 *path = cifs_convert_path_to_utf16(full_path, cifs_sb);
-
-	if (!path)
-		return -ENOMEM;
+	__le16 *utf16_path = NULL;
 
 	cifs_dbg(FYI, "mkdir\n");
 
+	/* resource #1: path allocation */
+	utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
+	if (!utf16_path)
+		return -ENOMEM;
+
 	if (ses && (ses->server))
 		server = ses->server;
-	else
-		return -EIO;
+	else {
+		rc = -EIO;
+		goto err_free_path;
+	}
 
+	/* resource #2: request */
 	rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len);
-
 	if (rc)
-		return rc;
+		goto err_free_path;
+
 
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
-
 	req->ImpersonationLevel = IL_IMPERSONATION;
 	req->DesiredAccess = cpu_to_le32(FILE_WRITE_ATTRIBUTES);
 	/* File attributes ignored on open (used in create though) */
@@ -1992,50 +2021,44 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 		req->sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
 		rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
 						 &name_len,
-						 tcon->treeName, path);
-		if (rc) {
-			cifs_small_buf_release(req);
-			return rc;
-		}
+						 tcon->treeName, utf16_path);
+		if (rc)
+			goto err_free_req;
+
 		req->NameLength = cpu_to_le16(name_len * 2);
 		uni_path_len = copy_size;
-		path = copy_path;
+		/* free before overwriting resource */
+		kfree(utf16_path);
+		utf16_path = copy_path;
 	} else {
-		uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
+		uni_path_len = (2 * UniStrnlen((wchar_t *)utf16_path, PATH_MAX)) + 2;
 		/* MUST set path len (NameLength) to 0 opening root of share */
 		req->NameLength = cpu_to_le16(uni_path_len - 2);
 		if (uni_path_len % 8 != 0) {
 			copy_size = roundup(uni_path_len, 8);
 			copy_path = kzalloc(copy_size, GFP_KERNEL);
 			if (!copy_path) {
-				cifs_small_buf_release(req);
-				return -ENOMEM;
+				rc = -ENOMEM;
+				goto err_free_req;
 			}
-			memcpy((char *)copy_path, (const char *)path,
+			memcpy((char *)copy_path, (const char *)utf16_path,
 			       uni_path_len);
 			uni_path_len = copy_size;
-			path = copy_path;
+			/* free before overwriting resource */
+			kfree(utf16_path);
+			utf16_path = copy_path;
 		}
 	}
 
 	iov[1].iov_len = uni_path_len;
-	iov[1].iov_base = path;
+	iov[1].iov_base = utf16_path;
 	req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_NONE;
 
 	if (tcon->posix_extensions) {
-		if (n_iov > 2) {
-			struct create_context *ccontext =
-			    (struct create_context *)iov[n_iov-1].iov_base;
-			ccontext->Next =
-				cpu_to_le32(iov[n_iov-1].iov_len);
-		}
-
+		/* resource #3: posix buf */
 		rc = add_posix_context(iov, &n_iov, mode);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
-			return rc;
-		}
+		if (rc)
+			goto err_free_req;
 		pc_buf = iov[n_iov-1].iov_base;
 	}
 
@@ -2044,73 +2067,57 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = n_iov;
 
-	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
-			    &rsp_iov);
-
-	cifs_small_buf_release(req);
-	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
-
-	if (rc != 0) {
+	/* resource #4: response buffer */
+	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
+	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
 		trace_smb3_posix_mkdir_err(xid, tcon->tid, ses->Suid,
-				    CREATE_NOT_FILE, FILE_WRITE_ATTRIBUTES, rc);
-		goto smb311_mkdir_exit;
-	} else
-		trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid,
-				     ses->Suid, CREATE_NOT_FILE,
-				     FILE_WRITE_ATTRIBUTES);
+					   CREATE_NOT_FILE,
+					   FILE_WRITE_ATTRIBUTES, rc);
+		goto err_free_rsp_buf;
+	}
+
+	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
+	trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid,
+				    ses->Suid, CREATE_NOT_FILE,
+				    FILE_WRITE_ATTRIBUTES);
 
 	SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId);
 
 	/* Eventually save off posix specific response info and timestaps */
 
-smb311_mkdir_exit:
-	kfree(copy_path);
-	kfree(pc_buf);
+err_free_rsp_buf:
 	free_rsp_buf(resp_buftype, rsp);
+	kfree(pc_buf);
+err_free_req:
+	cifs_small_buf_release(req);
+err_free_path:
+	kfree(utf16_path);
 	return rc;
-
 }
-#endif /* SMB311 */
 
 int
-SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
-	  __u8 *oplock, struct smb2_file_all_info *buf,
-	  struct kvec *err_iov, int *buftype)
+SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock,
+	       struct cifs_open_parms *oparms, __le16 *path)
 {
-	struct smb_rqst rqst;
+	struct TCP_Server_Info *server = tcon->ses->server;
 	struct smb2_create_req *req;
-	struct smb2_create_rsp *rsp;
-	struct TCP_Server_Info *server;
-	struct cifs_tcon *tcon = oparms->tcon;
-	struct cifs_ses *ses = tcon->ses;
-	struct kvec iov[5]; /* make sure at least one for each open context */
-	struct kvec rsp_iov = {NULL, 0};
-	int resp_buftype;
-	int uni_path_len;
-	__le16 *copy_path = NULL;
-	int copy_size;
-	int rc = 0;
 	unsigned int n_iov = 2;
 	__u32 file_attributes = 0;
-	char *dhc_buf = NULL, *lc_buf = NULL, *pc_buf = NULL;
-	int flags = 0;
+	int copy_size;
+	int uni_path_len;
 	unsigned int total_len;
-
-	cifs_dbg(FYI, "create/open\n");
-
-	if (ses && (ses->server))
-		server = ses->server;
-	else
-		return -EIO;
+	struct kvec *iov = rqst->rq_iov;
+	__le16 *copy_path;
+	int rc;
 
 	rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len);
-
 	if (rc)
 		return rc;
 
-	if (smb3_encryption_required(tcon))
-		flags |= CIFS_TRANSFORM_REQ;
+	iov[0].iov_base = (char *)req;
+	/* -1 since last byte is buf[0] which is sent below (path) */
+	iov[0].iov_len = total_len - 1;
 
 	if (oparms->create_options & CREATE_OPTION_READONLY)
 		file_attributes |= ATTR_READONLY;
@@ -2124,11 +2131,6 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	req->ShareAccess = FILE_SHARE_ALL_LE;
 	req->CreateDisposition = cpu_to_le32(oparms->disposition);
 	req->CreateOptions = cpu_to_le32(oparms->create_options & CREATE_OPTIONS_MASK);
-
-	iov[0].iov_base = (char *)req;
-	/* -1 since last byte is buf[0] which is sent below (path) */
-	iov[0].iov_len = total_len - 1;
-
 	req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req));
 
 	/* [MS-SMB2] 2.2.13 NameOffset:
@@ -2146,10 +2148,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
 						 &name_len,
 						 tcon->treeName, path);
-		if (rc) {
-			cifs_small_buf_release(req);
+		if (rc)
 			return rc;
-		}
 		req->NameLength = cpu_to_le16(name_len * 2);
 		uni_path_len = copy_size;
 		path = copy_path;
@@ -2157,18 +2157,16 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
 		/* MUST set path len (NameLength) to 0 opening root of share */
 		req->NameLength = cpu_to_le16(uni_path_len - 2);
-		if (uni_path_len % 8 != 0) {
-			copy_size = roundup(uni_path_len, 8);
-			copy_path = kzalloc(copy_size, GFP_KERNEL);
-			if (!copy_path) {
-				cifs_small_buf_release(req);
-				return -ENOMEM;
-			}
-			memcpy((char *)copy_path, (const char *)path,
-			       uni_path_len);
-			uni_path_len = copy_size;
-			path = copy_path;
-		}
+		copy_size = uni_path_len;
+		if (copy_size % 8 != 0)
+			copy_size = roundup(copy_size, 8);
+		copy_path = kzalloc(copy_size, GFP_KERNEL);
+		if (!copy_path)
+			return -ENOMEM;
+		memcpy((char *)copy_path, (const char *)path,
+		       uni_path_len);
+		uni_path_len = copy_size;
+		path = copy_path;
 	}
 
 	iov[1].iov_len = uni_path_len;
@@ -2183,12 +2181,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	else {
 		rc = add_lease_context(server, iov, &n_iov,
 				       oparms->fid->lease_key, oplock);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
+		if (rc)
 			return rc;
-		}
-		lc_buf = iov[n_iov-1].iov_base;
 	}
 
 	if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
@@ -2202,16 +2196,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 
 		rc = add_durable_context(iov, &n_iov, oparms,
 					tcon->use_persistent);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
-			kfree(lc_buf);
+		if (rc)
 			return rc;
-		}
-		dhc_buf = iov[n_iov-1].iov_base;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	if (tcon->posix_extensions) {
 		if (n_iov > 2) {
 			struct create_context *ccontext =
@@ -2221,24 +2209,79 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		}
 
 		rc = add_posix_context(iov, &n_iov, oparms->mode);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
-			kfree(lc_buf);
-			kfree(dhc_buf);
+		if (rc)
 			return rc;
+	}
+
+	if (tcon->snapshot_time) {
+		cifs_dbg(FYI, "adding snapshot context\n");
+		if (n_iov > 2) {
+			struct create_context *ccontext =
+			    (struct create_context *)iov[n_iov-1].iov_base;
+			ccontext->Next =
+				cpu_to_le32(iov[n_iov-1].iov_len);
 		}
-		pc_buf = iov[n_iov-1].iov_base;
+
+		rc = add_twarp_context(iov, &n_iov, tcon->snapshot_time);
+		if (rc)
+			return rc;
 	}
-#endif /* SMB311 */
+
+
+	rqst->rq_nvec = n_iov;
+	return 0;
+}
+
+/* rq_iov[0] is the request and is released by cifs_small_buf_release().
+ * All other vectors are freed by kfree().
+ */
+void
+SMB2_open_free(struct smb_rqst *rqst)
+{
+	int i;
+
+	cifs_small_buf_release(rqst->rq_iov[0].iov_base);
+	for (i = 1; i < rqst->rq_nvec; i++)
+		if (rqst->rq_iov[i].iov_base != smb2_padding)
+			kfree(rqst->rq_iov[i].iov_base);
+}
+
+int
+SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
+	  __u8 *oplock, struct smb2_file_all_info *buf,
+	  struct kvec *err_iov, int *buftype)
+{
+	struct smb_rqst rqst;
+	struct smb2_create_rsp *rsp = NULL;
+	struct TCP_Server_Info *server;
+	struct cifs_tcon *tcon = oparms->tcon;
+	struct cifs_ses *ses = tcon->ses;
+	struct kvec iov[5]; /* make sure at least one for each open context */
+	struct kvec rsp_iov = {NULL, 0};
+	int resp_buftype;
+	int rc = 0;
+	int flags = 0;
+
+	cifs_dbg(FYI, "create/open\n");
+	if (ses && (ses->server))
+		server = ses->server;
+	else
+		return -EIO;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
 
 	memset(&rqst, 0, sizeof(struct smb_rqst));
+	memset(&iov, 0, sizeof(iov));
 	rqst.rq_iov = iov;
-	rqst.rq_nvec = n_iov;
+	rqst.rq_nvec = 5;
+
+	rc = SMB2_open_init(tcon, &rqst, oplock, oparms, path);
+	if (rc)
+		goto creat_exit;
 
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
 			    &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
@@ -2275,10 +2318,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	else
 		*oplock = rsp->OplockLevel;
 creat_exit:
-	kfree(copy_path);
-	kfree(lc_buf);
-	kfree(dhc_buf);
-	kfree(pc_buf);
+	SMB2_open_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
@@ -2469,43 +2509,62 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 }
 
 int
+SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+		u64 persistent_fid, u64 volatile_fid)
+{
+	struct smb2_close_req *req;
+	struct kvec *iov = rqst->rq_iov;
+	unsigned int total_len;
+	int rc;
+
+	rc = smb2_plain_req_init(SMB2_CLOSE, tcon, (void **) &req, &total_len);
+	if (rc)
+		return rc;
+
+	req->PersistentFileId = persistent_fid;
+	req->VolatileFileId = volatile_fid;
+	iov[0].iov_base = (char *)req;
+	iov[0].iov_len = total_len;
+
+	return 0;
+}
+
+void
+SMB2_close_free(struct smb_rqst *rqst)
+{
+	cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+}
+
+int
 SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
 		 u64 persistent_fid, u64 volatile_fid, int flags)
 {
 	struct smb_rqst rqst;
-	struct smb2_close_req *req;
-	struct smb2_close_rsp *rsp;
+	struct smb2_close_rsp *rsp = NULL;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[1];
 	struct kvec rsp_iov;
 	int resp_buftype;
 	int rc = 0;
-	unsigned int total_len;
 
 	cifs_dbg(FYI, "Close\n");
 
 	if (!ses || !(ses->server))
 		return -EIO;
 
-	rc = smb2_plain_req_init(SMB2_CLOSE, tcon, (void **) &req, &total_len);
-	if (rc)
-		return rc;
-
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
-	req->PersistentFileId = persistent_fid;
-	req->VolatileFileId = volatile_fid;
-
-	iov[0].iov_base = (char *)req;
-	iov[0].iov_len = total_len;
-
 	memset(&rqst, 0, sizeof(struct smb_rqst));
+	memset(&iov, 0, sizeof(iov));
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
+	rc = SMB2_close_init(tcon, &rqst, persistent_fid, volatile_fid);
+	if (rc)
+		goto close_exit;
+
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_close_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
@@ -2518,6 +2577,7 @@ SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
 	/* BB FIXME - decode close response, update inode for caching */
 
 close_exit:
+	SMB2_close_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
@@ -2529,9 +2589,9 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	return SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0);
 }
 
-static int
-validate_iov(unsigned int offset, unsigned int buffer_length,
-	     struct kvec *iov, unsigned int min_buf_size)
+int
+smb2_validate_iov(unsigned int offset, unsigned int buffer_length,
+		  struct kvec *iov, unsigned int min_buf_size)
 {
 	unsigned int smb_len = iov->iov_len;
 	char *end_of_smb = smb_len + (char *)iov->iov_base;
@@ -2575,7 +2635,7 @@ validate_and_copy_iov(unsigned int offset, unsigned int buffer_length,
 	if (!data)
 		return -EINVAL;
 
-	rc = validate_iov(offset, buffer_length, iov, minbufsize);
+	rc = smb2_validate_iov(offset, buffer_length, iov, minbufsize);
 	if (rc)
 		return rc;
 
@@ -2584,36 +2644,22 @@ validate_and_copy_iov(unsigned int offset, unsigned int buffer_length,
 	return 0;
 }
 
-static int
-query_info(const unsigned int xid, struct cifs_tcon *tcon,
-	   u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type,
-	   u32 additional_info, size_t output_len, size_t min_len, void **data,
-		u32 *dlen)
+int
+SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+		     u64 persistent_fid, u64 volatile_fid,
+		     u8 info_class, u8 info_type, u32 additional_info,
+		     size_t output_len)
 {
-	struct smb_rqst rqst;
 	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 cifs_ses *ses = tcon->ses;
-	int flags = 0;
+	struct kvec *iov = rqst->rq_iov;
 	unsigned int total_len;
-
-	cifs_dbg(FYI, "Query Info\n");
-
-	if (!ses || !(ses->server))
-		return -EIO;
+	int rc;
 
 	rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, (void **) &req,
 			     &total_len);
 	if (rc)
 		return rc;
 
-	if (smb3_encryption_required(tcon))
-		flags |= CIFS_TRANSFORM_REQ;
-
 	req->InfoType = info_type;
 	req->FileInfoClass = info_class;
 	req->PersistentFileId = persistent_fid;
@@ -2630,13 +2676,50 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	iov[0].iov_base = (char *)req;
 	/* 1 for Buffer */
 	iov[0].iov_len = total_len - 1;
+	return 0;
+}
+
+void
+SMB2_query_info_free(struct smb_rqst *rqst)
+{
+	cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+}
+
+static int
+query_info(const unsigned int xid, struct cifs_tcon *tcon,
+	   u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type,
+	   u32 additional_info, size_t output_len, size_t min_len, void **data,
+		u32 *dlen)
+{
+	struct smb_rqst rqst;
+	struct smb2_query_info_rsp *rsp = NULL;
+	struct kvec iov[1];
+	struct kvec rsp_iov;
+	int rc = 0;
+	int resp_buftype;
+	struct cifs_ses *ses = tcon->ses;
+	int flags = 0;
+
+	cifs_dbg(FYI, "Query Info\n");
+
+	if (!ses || !(ses->server))
+		return -EIO;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
 
 	memset(&rqst, 0, sizeof(struct smb_rqst));
+	memset(&iov, 0, sizeof(iov));
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
+	rc = SMB2_query_info_init(tcon, &rqst, persistent_fid, volatile_fid,
+				  info_class, info_type, additional_info,
+				  output_len);
+	if (rc)
+		goto qinf_exit;
+
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
@@ -2665,6 +2748,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 				   &rsp_iov, min_len, *data);
 
 qinf_exit:
+	SMB2_query_info_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
@@ -3623,9 +3707,9 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 		goto qdir_exit;
 	}
 
-	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
-			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
-			  info_buf_size);
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			       info_buf_size);
 	if (rc)
 		goto qdir_exit;
 
@@ -3927,9 +4011,9 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 	return rc;
 }
 
-static void
-copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
-			struct kstatfs *kst)
+void
+smb2_copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
+			     struct kstatfs *kst)
 {
 	kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) *
 			  le32_to_cpu(pfs_inf->SectorsPerAllocationUnit);
@@ -3939,6 +4023,25 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
 	return;
 }
 
+static void
+copy_posix_fs_info_to_kstatfs(FILE_SYSTEM_POSIX_INFO *response_data,
+			struct kstatfs *kst)
+{
+	kst->f_bsize = le32_to_cpu(response_data->BlockSize);
+	kst->f_blocks = le64_to_cpu(response_data->TotalBlocks);
+	kst->f_bfree =  le64_to_cpu(response_data->BlocksAvail);
+	if (response_data->UserBlocksAvail == cpu_to_le64(-1))
+		kst->f_bavail = kst->f_bfree;
+	else
+		kst->f_bavail = le64_to_cpu(response_data->UserBlocksAvail);
+	if (response_data->TotalFileNodes != cpu_to_le64(-1))
+		kst->f_files = le64_to_cpu(response_data->TotalFileNodes);
+	if (response_data->FreeFileNodes != cpu_to_le64(-1))
+		kst->f_ffree = le64_to_cpu(response_data->FreeFileNodes);
+
+	return;
+}
+
 static int
 build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
 		   int outbuf_len, u64 persistent_fid, u64 volatile_fid)
@@ -3976,6 +4079,54 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
 }
 
 int
+SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
+	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
+{
+	struct smb_rqst rqst;
+	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;
+	FILE_SYSTEM_POSIX_INFO *info = NULL;
+	int flags = 0;
+
+	rc = build_qfs_info_req(&iov, tcon, FS_POSIX_INFORMATION,
+				sizeof(FILE_SYSTEM_POSIX_INFO),
+				persistent_fid, volatile_fid);
+	if (rc)
+		return rc;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	memset(&rqst, 0, sizeof(struct smb_rqst));
+	rqst.rq_iov = &iov;
+	rqst.rq_nvec = 1;
+
+	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(iov.iov_base);
+	if (rc) {
+		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
+		goto posix_qfsinf_exit;
+	}
+	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
+
+	info = (FILE_SYSTEM_POSIX_INFO *)(
+		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			       sizeof(FILE_SYSTEM_POSIX_INFO));
+	if (!rc)
+		copy_posix_fs_info_to_kstatfs(info, fsdata);
+
+posix_qfsinf_exit:
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+	return rc;
+}
+
+int
 SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
 {
@@ -4012,11 +4163,11 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	info = (struct smb2_fs_full_size_info *)(
 		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
-	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
-			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
-			  sizeof(struct smb2_fs_full_size_info));
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			       sizeof(struct smb2_fs_full_size_info));
 	if (!rc)
-		copy_fs_info_to_kstatfs(info, fsdata);
+		smb2_copy_fs_info_to_kstatfs(info, fsdata);
 
 qfsinf_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
@@ -4046,6 +4197,9 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	} else if (level == FS_SECTOR_SIZE_INFORMATION) {
 		max_len = sizeof(struct smb3_fs_ss_info);
 		min_len = sizeof(struct smb3_fs_ss_info);
+	} else if (level == FS_VOLUME_INFORMATION) {
+		max_len = sizeof(struct smb3_fs_vol_info) + MAX_VOL_LABEL_LEN;
+		min_len = sizeof(struct smb3_fs_vol_info);
 	} else {
 		cifs_dbg(FYI, "Invalid qfsinfo level %d\n", level);
 		return -EINVAL;
@@ -4073,7 +4227,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rsp_len = le32_to_cpu(rsp->OutputBufferLength);
 	offset = le16_to_cpu(rsp->OutputBufferOffset);
-	rc = validate_iov(offset, rsp_len, &rsp_iov, min_len);
+	rc = smb2_validate_iov(offset, rsp_len, &rsp_iov, min_len);
 	if (rc)
 		goto qfsattr_exit;
 
@@ -4090,6 +4244,11 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 		tcon->ss_flags = le32_to_cpu(ss_info->Flags);
 		tcon->perf_sector_size =
 			le32_to_cpu(ss_info->PhysicalBytesPerSectorForPerf);
+	} else if (level == FS_VOLUME_INFORMATION) {
+		struct smb3_fs_vol_info *vol_info = (struct smb3_fs_vol_info *)
+			(offset + (char *)rsp);
+		tcon->vol_serial_number = vol_info->VolumeSerialNumber;
+		tcon->vol_create_time = vol_info->VolumeCreationTime;
 	}
 
 qfsattr_exit:
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index a671adcc44a6..a2eeae9e0432 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -153,6 +153,8 @@ struct smb2_transform_hdr {
  *
  */
 
+#define COMPOUND_FID 0xFFFFFFFFFFFFFFFFULL
+
 #define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
 
 struct smb2_err_rsp {
@@ -765,6 +767,14 @@ struct create_durable_handle_reconnect_v2 {
 	struct durable_reconnect_context_v2 dcontext;
 } __packed;
 
+/* See MS-SMB2 2.2.13.2.5 */
+struct crt_twarp_ctxt {
+	struct create_context ccontext;
+	__u8	Name[8];
+	__le64	Timestamp;
+
+} __packed;
+
 #define COPY_CHUNK_RES_KEY_SIZE	24
 struct resume_key_req {
 	char ResumeKey[COPY_CHUNK_RES_KEY_SIZE];
@@ -1223,6 +1233,7 @@ struct smb2_lease_ack {
 #define FS_DRIVER_PATH_INFORMATION	9 /* Local only */
 #define FS_VOLUME_FLAGS_INFORMATION	10 /* Local only */
 #define FS_SECTOR_SIZE_INFORMATION	11 /* SMB3 or later. Query */
+#define FS_POSIX_INFORMATION		100 /* SMB3.1.1 POSIX. Query */
 
 struct smb2_fs_full_size_info {
 	__le64 TotalAllocationUnits;
@@ -1248,6 +1259,17 @@ struct smb3_fs_ss_info {
 	__le32 ByteOffsetForPartitionAlignment;
 } __packed;
 
+/* volume info struct - see MS-FSCC 2.5.9 */
+#define MAX_VOL_LABEL_LEN	32
+struct smb3_fs_vol_info {
+	__le64	VolumeCreationTime;
+	__u32	VolumeSerialNumber;
+	__le32	VolumeLabelLength; /* includes trailing null */
+	__u8	SupportsObjects; /* True if eg like NTFS, supports objects */
+	__u8	Reserved;
+	__u8	VolumeLabel[0]; /* variable len */
+} __packed;
+
 /* partial list of QUERY INFO levels */
 #define FILE_DIRECTORY_INFORMATION	1
 #define FILE_FULL_DIRECTORY_INFORMATION 2
@@ -1361,4 +1383,6 @@ struct smb2_file_eof_info { /* encoding of request for level 10 */
 	__le64 EndOfFile; /* new end of file value */
 } __packed; /* level 20 Set */
 
+extern char smb2_padding[7];
+
 #endif				/* _SMB2PDU_H */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 6e6a4f2ec890..b4076577eeb7 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -68,6 +68,7 @@ extern int smb3_handle_read_data(struct TCP_Server_Info *server,
 
 extern int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
 			struct cifs_fid *pfid);
+extern void close_shroot(struct cached_fid *cfid);
 extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst,
 				   struct smb2_file_all_info *src);
 extern int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
@@ -132,6 +133,10 @@ extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms,
 		     __le16 *path, __u8 *oplock,
 		     struct smb2_file_all_info *buf,
 		     struct kvec *err_iov, int *resp_buftype);
+extern int SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+			  __u8 *oplock, struct cifs_open_parms *oparms,
+			  __le16 *path);
+extern void SMB2_open_free(struct smb_rqst *rqst);
 extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
 		     u64 persistent_fid, u64 volatile_fid, u32 opcode,
 		     bool is_fsctl, char *in_data, u32 indatalen,
@@ -140,6 +145,9 @@ extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
 extern int SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
 			    u64 persistent_fid, u64 volatile_fid, int flags);
+extern int SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+		      u64 persistent_file_id, u64 volatile_file_id);
+extern void SMB2_close_free(struct smb_rqst *rqst);
 extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
 extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
@@ -149,6 +157,11 @@ extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 			   u64 persistent_file_id, u64 volatile_file_id,
 			   struct smb2_file_all_info *data);
+extern int SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+				u64 persistent_fid, u64 volatile_fid,
+				u8 info_class, u8 info_type,
+				u32 additional_info, size_t output_len);
+extern void SMB2_query_info_free(struct smb_rqst *rqst);
 extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
 			   u64 persistent_file_id, u64 volatile_file_id,
 			   void **data, unsigned int *plen);
@@ -197,6 +210,9 @@ void smb2_cancelled_close_fid(struct work_struct *work);
 extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id,
 			 struct kstatfs *FSData);
+extern int SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
+			 u64 persistent_file_id, u64 volatile_file_id,
+			 struct kstatfs *FSData);
 extern int SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id, int lvl);
 extern int SMB2_lock(const unsigned int xid, struct cifs_tcon *tcon,
@@ -213,9 +229,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
 extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
 					enum securityEnum);
-#ifdef CONFIG_CIFS_SMB311
+extern int smb3_encryption_required(const struct cifs_tcon *tcon);
+extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length,
+			     struct kvec *iov, unsigned int min_buf_size);
+extern void smb2_copy_fs_info_to_kstatfs(
+	 struct smb2_fs_full_size_info *pfs_inf,
+	 struct kstatfs *kst);
 extern int smb311_crypto_shash_allocate(struct TCP_Server_Info *server);
 extern int smb311_update_preauth_hash(struct cifs_ses *ses,
 				      struct kvec *iov, int nvec);
-#endif
 #endif			/* _SMB2PROTO_H */
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 719d55e63d88..7b351c65ee46 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -70,7 +70,6 @@ err:
 	return rc;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int
 smb311_crypto_shash_allocate(struct TCP_Server_Info *server)
 {
@@ -98,7 +97,6 @@ err:
 	cifs_free_hash(&p->hmacsha256, &p->sdeschmacsha256);
 	return rc;
 }
-#endif
 
 static struct cifs_ses *
 smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
@@ -173,7 +171,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	struct kvec *iov = rqst->rq_iov;
 	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
 	struct cifs_ses *ses;
-	struct shash_desc *shash = &server->secmech.sdeschmacsha256->shash;
+	struct shash_desc *shash;
 	struct smb_rqst drqst;
 
 	ses = smb2_find_smb_ses(server, shdr->SessionId);
@@ -187,7 +185,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 
 	rc = smb2_crypto_shash_allocate(server);
 	if (rc) {
-		cifs_dbg(VFS, "%s: shah256 alloc failed\n", __func__);
+		cifs_dbg(VFS, "%s: sha256 alloc failed\n", __func__);
 		return rc;
 	}
 
@@ -198,6 +196,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 		return rc;
 	}
 
+	shash = &server->secmech.sdeschmacsha256->shash;
 	rc = crypto_shash_init(shash);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not init sha256", __func__);
@@ -395,7 +394,6 @@ generate_smb30signingkey(struct cifs_ses *ses)
 	return generate_smb3signingkey(ses, &triplet);
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int
 generate_smb311signingkey(struct cifs_ses *ses)
 
@@ -423,7 +421,6 @@ generate_smb311signingkey(struct cifs_ses *ses)
 
 	return generate_smb3signingkey(ses, &triplet);
 }
-#endif /* 311 */
 
 int
 smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index 67e413f6ee4d..d4aed5217a56 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -281,6 +281,44 @@ DEFINE_EVENT(smb3_cmd_done_class, smb3_##name,    \
 	TP_ARGS(tid, sesid, cmd, mid))
 
 DEFINE_SMB3_CMD_DONE_EVENT(cmd_done);
+DEFINE_SMB3_CMD_DONE_EVENT(ses_expired);
+
+DECLARE_EVENT_CLASS(smb3_mid_class,
+	TP_PROTO(__u16	cmd,
+		__u64	mid,
+		__u32	pid,
+		unsigned long when_sent,
+		unsigned long when_received),
+	TP_ARGS(cmd, mid, pid, when_sent, when_received),
+	TP_STRUCT__entry(
+		__field(__u16, cmd)
+		__field(__u64, mid)
+		__field(__u32, pid)
+		__field(unsigned long, when_sent)
+		__field(unsigned long, when_received)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+		__entry->mid = mid;
+		__entry->pid = pid;
+		__entry->when_sent = when_sent;
+		__entry->when_received = when_received;
+	),
+	TP_printk("\tcmd=%u mid=%llu pid=%u, when_sent=%lu when_rcv=%lu",
+		__entry->cmd, __entry->mid, __entry->pid, __entry->when_sent,
+		__entry->when_received)
+)
+
+#define DEFINE_SMB3_MID_EVENT(name)          \
+DEFINE_EVENT(smb3_mid_class, smb3_##name,    \
+	TP_PROTO(__u16	cmd,			\
+		__u64	mid,			\
+		__u32	pid,			\
+		unsigned long when_sent,	\
+		unsigned long when_received),	\
+	TP_ARGS(cmd, mid, pid, when_sent, when_received))
+
+DEFINE_SMB3_MID_EVENT(slow_rsp);
 
 DECLARE_EVENT_CLASS(smb3_exit_err_class,
 	TP_PROTO(unsigned int xid,
@@ -422,6 +460,32 @@ DEFINE_EVENT(smb3_open_done_class, smb3_##name,  \
 DEFINE_SMB3_OPEN_DONE_EVENT(open_done);
 DEFINE_SMB3_OPEN_DONE_EVENT(posix_mkdir_done);
 
+DECLARE_EVENT_CLASS(smb3_reconnect_class,
+	TP_PROTO(__u64	currmid,
+		char *hostname),
+	TP_ARGS(currmid, hostname),
+	TP_STRUCT__entry(
+		__field(__u64, currmid)
+		__field(char *, hostname)
+	),
+	TP_fast_assign(
+		__entry->currmid = currmid;
+		__entry->hostname = hostname;
+	),
+	TP_printk("server=%s current_mid=0x%llx",
+		__entry->hostname,
+		__entry->currmid)
+)
+
+#define DEFINE_SMB3_RECONNECT_EVENT(name)        \
+DEFINE_EVENT(smb3_reconnect_class, smb3_##name,  \
+	TP_PROTO(__u64	currmid,		\
+		char *hostname),		\
+	TP_ARGS(currmid, hostname))
+
+DEFINE_SMB3_RECONNECT_EVENT(reconnect);
+DEFINE_SMB3_RECONNECT_EVENT(partial_send_reconnect);
+
 #endif /* _CIFS_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index a341ec839c83..78f96fa3d7d9 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -115,8 +115,17 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 	now = jiffies;
 	/* commands taking longer than one second are indications that
 	   something is wrong, unless it is quite a slow link or server */
-	if (time_after(now, midEntry->when_alloc + HZ)) {
-		if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) {
+	if (time_after(now, midEntry->when_alloc + HZ) &&
+	    (midEntry->command != command)) {
+		/* smb2slowcmd[NUMBER_OF_SMB2_COMMANDS] counts by command */
+		if ((le16_to_cpu(midEntry->command) < NUMBER_OF_SMB2_COMMANDS) &&
+		    (le16_to_cpu(midEntry->command) >= 0))
+			cifs_stats_inc(&midEntry->server->smb2slowcmd[le16_to_cpu(midEntry->command)]);
+
+		trace_smb3_slow_rsp(le16_to_cpu(midEntry->command),
+			       midEntry->mid, midEntry->pid,
+			       midEntry->when_sent, midEntry->when_received);
+		if (cifsFYI & CIFS_TIMER) {
 			pr_debug(" CIFS slow rsp: cmd %d mid %llu",
 			       midEntry->command, midEntry->mid);
 			pr_info(" A: 0x%lx S: 0x%lx R: 0x%lx\n",
@@ -361,6 +370,8 @@ uncork:
 		 * socket so the server throws away the partial SMB
 		 */
 		server->tcpStatus = CifsNeedReconnect;
+		trace_smb3_partial_send_reconnect(server->CurrentMid,
+						  server->hostname);
 	}
 smbd_done:
 	if (rc < 0 && rc != -EINTR)
@@ -373,26 +384,42 @@ smbd_done:
 }
 
 static int
-smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags)
+smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
+	      struct smb_rqst *rqst, int flags)
 {
-	struct smb_rqst cur_rqst;
+	struct kvec iov;
+	struct smb2_transform_hdr tr_hdr;
+	struct smb_rqst cur_rqst[MAX_COMPOUND];
 	int rc;
 
 	if (!(flags & CIFS_TRANSFORM_REQ))
-		return __smb_send_rqst(server, 1, rqst);
+		return __smb_send_rqst(server, num_rqst, rqst);
 
-	if (!server->ops->init_transform_rq ||
-	    !server->ops->free_transform_rq) {
-		cifs_dbg(VFS, "Encryption requested but transform callbacks are missed\n");
+	if (num_rqst > MAX_COMPOUND - 1)
+		return -ENOMEM;
+
+	memset(&cur_rqst[0], 0, sizeof(cur_rqst));
+	memset(&iov, 0, sizeof(iov));
+	memset(&tr_hdr, 0, sizeof(tr_hdr));
+
+	iov.iov_base = &tr_hdr;
+	iov.iov_len = sizeof(tr_hdr);
+	cur_rqst[0].rq_iov = &iov;
+	cur_rqst[0].rq_nvec = 1;
+
+	if (!server->ops->init_transform_rq) {
+		cifs_dbg(VFS, "Encryption requested but transform callback "
+			 "is missing\n");
 		return -EIO;
 	}
 
-	rc = server->ops->init_transform_rq(server, &cur_rqst, rqst);
+	rc = server->ops->init_transform_rq(server, num_rqst + 1,
+					    &cur_rqst[0], rqst);
 	if (rc)
 		return rc;
 
-	rc = __smb_send_rqst(server, 1, &cur_rqst);
-	server->ops->free_transform_rq(&cur_rqst);
+	rc = __smb_send_rqst(server, num_rqst + 1, &cur_rqst[0]);
+	smb3_free_compound_rqst(num_rqst, &cur_rqst[1]);
 	return rc;
 }
 
@@ -606,7 +633,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 	 */
 	cifs_save_when_sent(mid);
 	cifs_in_send_inc(server);
-	rc = smb_send_rqst(server, rqst, flags);
+	rc = smb_send_rqst(server, 1, rqst, flags);
 	cifs_in_send_dec(server);
 
 	if (rc < 0) {
@@ -746,20 +773,21 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
 }
 
 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)
+compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
+		   const int flags, const int num_rqst, struct smb_rqst *rqst,
+		   int *resp_buf_type, struct kvec *resp_iov)
 {
-	int rc = 0;
+	int i, j, rc = 0;
 	int timeout, optype;
-	struct mid_q_entry *midQ;
+	struct mid_q_entry *midQ[MAX_COMPOUND];
 	unsigned int credits = 1;
 	char *buf;
 
 	timeout = flags & CIFS_TIMEOUT_MASK;
 	optype = flags & CIFS_OP_MASK;
 
-	*resp_buf_type = CIFS_NO_BUFFER;  /* no response buf yet */
+	for (i = 0; i < num_rqst; i++)
+		resp_buf_type[i] = CIFS_NO_BUFFER;  /* no response buf yet */
 
 	if ((ses == NULL) || (ses->server == NULL)) {
 		cifs_dbg(VFS, "Null session\n");
@@ -786,98 +814,117 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 
 	mutex_lock(&ses->server->srv_mutex);
 
-	midQ = ses->server->ops->setup_request(ses, rqst);
-	if (IS_ERR(midQ)) {
-		mutex_unlock(&ses->server->srv_mutex);
-		/* Update # of requests on wire to server */
-		add_credits(ses->server, 1, optype);
-		return PTR_ERR(midQ);
+	for (i = 0; i < num_rqst; i++) {
+		midQ[i] = ses->server->ops->setup_request(ses, &rqst[i]);
+		if (IS_ERR(midQ[i])) {
+			for (j = 0; j < i; j++)
+				cifs_delete_mid(midQ[j]);
+			mutex_unlock(&ses->server->srv_mutex);
+			/* Update # of requests on wire to server */
+			add_credits(ses->server, 1, optype);
+			return PTR_ERR(midQ[i]);
+		}
+
+		midQ[i]->mid_state = MID_REQUEST_SUBMITTED;
 	}
 
-	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
-	rc = smb_send_rqst(ses->server, rqst, flags);
+	rc = smb_send_rqst(ses->server, num_rqst, rqst, flags);
 	cifs_in_send_dec(ses->server);
-	cifs_save_when_sent(midQ);
+
+	for (i = 0; i < num_rqst; i++)
+		cifs_save_when_sent(midQ[i]);
 
 	if (rc < 0)
 		ses->server->sequence_number -= 2;
+
 	mutex_unlock(&ses->server->srv_mutex);
 
-	if (rc < 0)
-		goto out;
+	for (i = 0; i < num_rqst; i++) {
+		if (rc < 0)
+			goto out;
 
-#ifdef CONFIG_CIFS_SMB311
-	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
-		smb311_update_preauth_hash(ses, rqst->rq_iov,
-					   rqst->rq_nvec);
-#endif
+		if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
+			smb311_update_preauth_hash(ses, rqst[i].rq_iov,
+						   rqst[i].rq_nvec);
 
-	if (timeout == CIFS_ASYNC_OP)
-		goto out;
+		if (timeout == CIFS_ASYNC_OP)
+			goto out;
 
-	rc = wait_for_response(ses->server, midQ);
-	if (rc != 0) {
-		cifs_dbg(FYI, "Cancelling wait for mid %llu\n",	midQ->mid);
-		send_cancel(ses->server, rqst, midQ);
-		spin_lock(&GlobalMid_Lock);
-		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
-			midQ->mid_flags |= MID_WAIT_CANCELLED;
-			midQ->callback = DeleteMidQEntry;
+		rc = wait_for_response(ses->server, midQ[i]);
+		if (rc != 0) {
+			cifs_dbg(FYI, "Cancelling wait for mid %llu\n",
+				 midQ[i]->mid);
+			send_cancel(ses->server, &rqst[i], midQ[i]);
+			spin_lock(&GlobalMid_Lock);
+			if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) {
+				midQ[i]->mid_flags |= MID_WAIT_CANCELLED;
+				midQ[i]->callback = DeleteMidQEntry;
+				spin_unlock(&GlobalMid_Lock);
+				add_credits(ses->server, 1, optype);
+				return rc;
+			}
 			spin_unlock(&GlobalMid_Lock);
+		}
+
+		rc = cifs_sync_mid_result(midQ[i], ses->server);
+		if (rc != 0) {
 			add_credits(ses->server, 1, optype);
 			return rc;
 		}
-		spin_unlock(&GlobalMid_Lock);
-	}
-
-	rc = cifs_sync_mid_result(midQ, ses->server);
-	if (rc != 0) {
-		add_credits(ses->server, 1, optype);
-		return rc;
-	}
-
-	if (!midQ->resp_buf || midQ->mid_state != MID_RESPONSE_RECEIVED) {
-		rc = -EIO;
-		cifs_dbg(FYI, "Bad MID state?\n");
-		goto out;
-	}
 
-	buf = (char *)midQ->resp_buf;
-	resp_iov->iov_base = buf;
-	resp_iov->iov_len = midQ->resp_buf_size +
-		ses->server->vals->header_preamble_size;
-	if (midQ->large_buf)
-		*resp_buf_type = CIFS_LARGE_BUFFER;
-	else
-		*resp_buf_type = CIFS_SMALL_BUFFER;
+		if (!midQ[i]->resp_buf ||
+		    midQ[i]->mid_state != MID_RESPONSE_RECEIVED) {
+			rc = -EIO;
+			cifs_dbg(FYI, "Bad MID state?\n");
+			goto out;
+		}
 
-#ifdef CONFIG_CIFS_SMB311
-	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
-		struct kvec iov = {
-			.iov_base = resp_iov->iov_base,
-			.iov_len = resp_iov->iov_len
-		};
-		smb311_update_preauth_hash(ses, &iov, 1);
-	}
-#endif
+		buf = (char *)midQ[i]->resp_buf;
+		resp_iov[i].iov_base = buf;
+		resp_iov[i].iov_len = midQ[i]->resp_buf_size +
+			ses->server->vals->header_preamble_size;
+
+		if (midQ[i]->large_buf)
+			resp_buf_type[i] = CIFS_LARGE_BUFFER;
+		else
+			resp_buf_type[i] = CIFS_SMALL_BUFFER;
+
+		if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
+			struct kvec iov = {
+				.iov_base = resp_iov[i].iov_base,
+				.iov_len = resp_iov[i].iov_len
+			};
+			smb311_update_preauth_hash(ses, &iov, 1);
+		}
 
-	credits = ses->server->ops->get_credits(midQ);
+		credits = ses->server->ops->get_credits(midQ[i]);
 
-	rc = ses->server->ops->check_receive(midQ, ses->server,
-					     flags & CIFS_LOG_ERROR);
+		rc = ses->server->ops->check_receive(midQ[i], ses->server,
+						     flags & CIFS_LOG_ERROR);
 
-	/* mark it so buf will not be freed by cifs_delete_mid */
-	if ((flags & CIFS_NO_RESP) == 0)
-		midQ->resp_buf = NULL;
+		/* mark it so buf will not be freed by cifs_delete_mid */
+		if ((flags & CIFS_NO_RESP) == 0)
+			midQ[i]->resp_buf = NULL;
+	}
 out:
-	cifs_delete_mid(midQ);
+	for (i = 0; i < num_rqst; i++)
+		cifs_delete_mid(midQ[i]);
 	add_credits(ses->server, credits, optype);
 
 	return rc;
 }
 
 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)
+{
+	return compound_send_recv(xid, ses, flags, 1, rqst, resp_buf_type,
+				  resp_iov);
+}
+
+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)
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 316af84674f1..50ddb795aaeb 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -35,6 +35,14 @@
 #define CIFS_XATTR_CIFS_ACL "system.cifs_acl"
 #define CIFS_XATTR_ATTRIB "cifs.dosattrib"  /* full name: user.cifs.dosattrib */
 #define CIFS_XATTR_CREATETIME "cifs.creationtime"  /* user.cifs.creationtime */
+/*
+ * Although these three are just aliases for the above, need to move away from
+ * confusing users and using the 20+ year old term 'cifs' when it is no longer
+ * secure, replaced by SMB2 (then even more highly secure SMB3) many years ago
+ */
+#define SMB3_XATTR_CIFS_ACL "system.smb3_acl"
+#define SMB3_XATTR_ATTRIB "smb3.dosattrib"  /* full name: user.smb3.dosattrib */
+#define SMB3_XATTR_CREATETIME "smb3.creationtime"  /* user.smb3.creationtime */
 /* BB need to add server (Samba e.g) support for security and trusted prefix */
 
 enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT };
@@ -220,10 +228,12 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
 	switch (handler->flags) {
 	case XATTR_USER:
 		cifs_dbg(FYI, "%s:querying user xattr %s\n", __func__, name);
-		if (strcmp(name, CIFS_XATTR_ATTRIB) == 0) {
+		if ((strcmp(name, CIFS_XATTR_ATTRIB) == 0) ||
+		    (strcmp(name, SMB3_XATTR_ATTRIB) == 0)) {
 			rc = cifs_attrib_get(dentry, inode, value, size);
 			break;
-		} else if (strcmp(name, CIFS_XATTR_CREATETIME) == 0) {
+		} else if ((strcmp(name, CIFS_XATTR_CREATETIME) == 0) ||
+		    (strcmp(name, SMB3_XATTR_CREATETIME) == 0)) {
 			rc = cifs_creation_time_get(dentry, inode, value, size);
 			break;
 		}
@@ -363,6 +373,19 @@ static const struct xattr_handler cifs_cifs_acl_xattr_handler = {
 	.set = cifs_xattr_set,
 };
 
+/*
+ * Although this is just an alias for the above, need to move away from
+ * confusing users and using the 20 year old term 'cifs' when it is no
+ * longer secure and was replaced by SMB2/SMB3 a long time ago, and
+ * SMB3 and later are highly secure.
+ */
+static const struct xattr_handler smb3_acl_xattr_handler = {
+	.name = SMB3_XATTR_CIFS_ACL,
+	.flags = XATTR_CIFS_ACL,
+	.get = cifs_xattr_get,
+	.set = cifs_xattr_set,
+};
+
 static const struct xattr_handler cifs_posix_acl_access_xattr_handler = {
 	.name = XATTR_NAME_POSIX_ACL_ACCESS,
 	.flags = XATTR_ACL_ACCESS,
@@ -381,6 +404,7 @@ const struct xattr_handler *cifs_xattr_handlers[] = {
 	&cifs_user_xattr_handler,
 	&cifs_os2_xattr_handler,
 	&cifs_cifs_acl_xattr_handler,
+	&smb3_acl_xattr_handler, /* alias for above since avoiding "cifs" */
 	&cifs_posix_acl_access_xattr_handler,
 	&cifs_posix_acl_default_xattr_handler,
 	NULL
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 577cff24707b..39843fa7e11b 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1777,6 +1777,16 @@ void configfs_unregister_group(struct config_group *group)
 	struct dentry *dentry = group->cg_item.ci_dentry;
 	struct dentry *parent = group->cg_item.ci_parent->ci_dentry;
 
+	mutex_lock(&subsys->su_mutex);
+	if (!group->cg_item.ci_parent->ci_group) {
+		/*
+		 * The parent has already been unlinked and detached
+		 * due to a rmdir.
+		 */
+		goto unlink_group;
+	}
+	mutex_unlock(&subsys->su_mutex);
+
 	inode_lock_nested(d_inode(parent), I_MUTEX_PARENT);
 	spin_lock(&configfs_dirent_lock);
 	configfs_detach_prep(dentry, NULL);
@@ -1791,6 +1801,7 @@ void configfs_unregister_group(struct config_group *group)
 	dput(dentry);
 
 	mutex_lock(&subsys->su_mutex);
+unlink_group:
 	unlink_group(group);
 	mutex_unlock(&subsys->su_mutex);
 }
diff --git a/fs/configfs/item.c b/fs/configfs/item.c
index 88f266efc09b..99d491cd01f9 100644
--- a/fs/configfs/item.c
+++ b/fs/configfs/item.c
@@ -64,7 +64,6 @@ static void config_item_init(struct config_item *item)
  */
 int config_item_set_name(struct config_item *item, const char *fmt, ...)
 {
-	int error = 0;
 	int limit = CONFIGFS_ITEM_NAME_LEN;
 	int need;
 	va_list args;
@@ -79,25 +78,11 @@ int config_item_set_name(struct config_item *item, const char *fmt, ...)
 	if (need < limit)
 		name = item->ci_namebuf;
 	else {
-		/*
-		 * Need more space? Allocate it and try again
-		 */
-		limit = need + 1;
-		name = kmalloc(limit, GFP_KERNEL);
-		if (!name) {
-			error = -ENOMEM;
-			goto Done;
-		}
 		va_start(args, fmt);
-		need = vsnprintf(name, limit, fmt, args);
+		name = kvasprintf(GFP_KERNEL, fmt, args);
 		va_end(args);
-
-		/* Still? Give up. */
-		if (need >= limit) {
-			kfree(name);
-			error = -EFAULT;
-			goto Done;
-		}
+		if (!name)
+			return -EFAULT;
 	}
 
 	/* Free the old name, if necessary. */
@@ -106,8 +91,7 @@ int config_item_set_name(struct config_item *item, const char *fmt, ...)
 
 	/* Now, set the new name */
 	item->ci_name = name;
- Done:
-	return error;
+	return 0;
 }
 EXPORT_SYMBOL(config_item_set_name);
 
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 78ffc2699993..a5c54af861f7 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -64,7 +64,7 @@ static void fill_item_path(struct config_item * item, char * buffer, int length)
 
 		/* back up enough to print this bus id with '/' */
 		length -= cur;
-		strncpy(buffer + length,config_item_name(p),cur);
+		memcpy(buffer + length, config_item_name(p), cur);
 		*(buffer + --length) = '/';
 	}
 }
diff --git a/fs/dax.c b/fs/dax.c
index 641192808bb6..897b51e41d8f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -566,7 +566,8 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 			if (index >= end)
 				break;
 
-			if (!radix_tree_exceptional_entry(pvec_ent))
+			if (WARN_ON_ONCE(
+			     !radix_tree_exceptional_entry(pvec_ent)))
 				continue;
 
 			xa_lock_irq(&mapping->i_pages);
@@ -578,6 +579,13 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 			if (page)
 				break;
 		}
+
+		/*
+		 * We don't expect normal struct page entries to exist in our
+		 * tree, but we keep these pagevec calls so that this code is
+		 * consistent with the common pattern for handling pagevecs
+		 * throughout the kernel.
+		 */
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		index++;
diff --git a/fs/dcache.c b/fs/dcache.c
index 0e8e5de3c48a..8d2ec4898c2b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -358,14 +358,11 @@ static void dentry_unlink_inode(struct dentry * dentry)
 	__releases(dentry->d_inode->i_lock)
 {
 	struct inode *inode = dentry->d_inode;
-	bool hashed = !d_unhashed(dentry);
 
-	if (hashed)
-		raw_write_seqcount_begin(&dentry->d_seq);
+	raw_write_seqcount_begin(&dentry->d_seq);
 	__d_clear_type_and_inode(dentry);
 	hlist_del_init(&dentry->d_u.d_alias);
-	if (hashed)
-		raw_write_seqcount_end(&dentry->d_seq);
+	raw_write_seqcount_end(&dentry->d_seq);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
 	if (!inode->i_nlink)
@@ -732,16 +729,16 @@ static inline bool fast_dput(struct dentry *dentry)
 		if (dentry->d_lockref.count > 1) {
 			dentry->d_lockref.count--;
 			spin_unlock(&dentry->d_lock);
-			return 1;
+			return true;
 		}
-		return 0;
+		return false;
 	}
 
 	/*
 	 * If we weren't the last ref, we're done.
 	 */
 	if (ret)
-		return 1;
+		return true;
 
 	/*
 	 * Careful, careful. The reference count went down
@@ -770,7 +767,7 @@ static inline bool fast_dput(struct dentry *dentry)
 
 	/* Nothing to do? Dropping the reference was all we needed? */
 	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
-		return 1;
+		return true;
 
 	/*
 	 * Not the fast normal case? Get the lock. We've already decremented
@@ -787,7 +784,7 @@ static inline bool fast_dput(struct dentry *dentry)
 	 */
 	if (dentry->d_lockref.count) {
 		spin_unlock(&dentry->d_lock);
-		return 1;
+		return true;
 	}
 
 	/*
@@ -796,7 +793,7 @@ static inline bool fast_dput(struct dentry *dentry)
 	 * set it to 1.
 	 */
 	dentry->d_lockref.count = 1;
-	return 0;
+	return false;
 }
 
 
@@ -1892,50 +1889,25 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode)
 	spin_lock(&inode->i_lock);
 	__d_instantiate(entry, inode);
 	WARN_ON(!(inode->i_state & I_NEW));
-	inode->i_state &= ~I_NEW;
+	inode->i_state &= ~I_NEW & ~I_CREATING;
 	smp_mb();
 	wake_up_bit(&inode->i_state, __I_NEW);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(d_instantiate_new);
 
-/**
- * d_instantiate_no_diralias - instantiate a non-aliased dentry
- * @entry: dentry to complete
- * @inode: inode to attach to this dentry
- *
- * Fill in inode information in the entry.  If a directory alias is found, then
- * return an error (and drop inode).  Together with d_materialise_unique() this
- * guarantees that a directory inode may never have more than one alias.
- */
-int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
-{
-	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
-
-	security_d_instantiate(entry, inode);
-	spin_lock(&inode->i_lock);
-	if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
-		spin_unlock(&inode->i_lock);
-		iput(inode);
-		return -EBUSY;
-	}
-	__d_instantiate(entry, inode);
-	spin_unlock(&inode->i_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL(d_instantiate_no_diralias);
-
 struct dentry *d_make_root(struct inode *root_inode)
 {
 	struct dentry *res = NULL;
 
 	if (root_inode) {
 		res = d_alloc_anon(root_inode->i_sb);
-		if (res)
+		if (res) {
+			res->d_flags |= DCACHE_RCUACCESS;
 			d_instantiate(res, root_inode);
-		else
+		} else {
 			iput(root_inode);
+		}
 	}
 	return res;
 }
@@ -2676,33 +2648,6 @@ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode)
 }
 EXPORT_SYMBOL(d_exact_alias);
 
-/**
- * dentry_update_name_case - update case insensitive dentry with a new name
- * @dentry: dentry to be updated
- * @name: new name
- *
- * Update a case insensitive dentry with new case of name.
- *
- * dentry must have been returned by d_lookup with name @name. Old and new
- * name lengths must match (ie. no d_compare which allows mismatched name
- * lengths).
- *
- * Parent inode i_mutex must be held over d_lookup and into this call (to
- * keep renames and concurrent inserts, and readdir(2) away).
- */
-void dentry_update_name_case(struct dentry *dentry, const struct qstr *name)
-{
-	BUG_ON(!inode_is_locked(dentry->d_parent->d_inode));
-	BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */
-
-	spin_lock(&dentry->d_lock);
-	write_seqcount_begin(&dentry->d_seq);
-	memcpy((unsigned char *)dentry->d_name.name, name->name, name->len);
-	write_seqcount_end(&dentry->d_seq);
-	spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(dentry_update_name_case);
-
 static void swap_names(struct dentry *dentry, struct dentry *target)
 {
 	if (unlikely(dname_external(target))) {
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 71fccccf317e..8c6ab6c95727 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -86,7 +86,9 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 	/* length of the variable name itself: remove GUID and separator */
 	namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
 
-	uuid_le_to_bin(dentry->d_name.name + namelen + 1, &var->var.VendorGuid);
+	err = guid_parse(dentry->d_name.name + namelen + 1, &var->var.VendorGuid);
+	if (err)
+		goto out;
 
 	if (efivar_variable_is_removable(var->var.VendorGuid,
 					 dentry->d_name.name, namelen))
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 1b8b44637e70..5331a15a61f1 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -873,8 +873,8 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp)
 			struct bio *bio;
 
 			if (per_dev != master_dev) {
-				bio = bio_clone_kmalloc(master_dev->bio,
-							GFP_KERNEL);
+				bio = bio_clone_fast(master_dev->bio,
+						     GFP_KERNEL, NULL);
 				if (unlikely(!bio)) {
 					ORE_DBGMSG(
 					      "Failed to allocate BIO size=%u\n",
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 6484199b35d1..5c3d7b7e4975 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -611,8 +611,7 @@ fail_drop:
 	dquot_drop(inode);
 	inode->i_flags |= S_NOQUOTA;
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return ERR_PTR(err);
 
 fail:
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 152453a91877..0c26dcc5d850 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -45,8 +45,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 		return 0;
 	}
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return err;
 }
 
@@ -192,8 +191,7 @@ out:
 
 out_fail:
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput (inode);
+	discard_new_inode(inode);
 	goto out;
 }
 
@@ -261,8 +259,7 @@ out:
 out_fail:
 	inode_dec_link_count(inode);
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 out_dir:
 	inode_dec_link_count(dir);
 	goto out;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index aa52d87985aa..e5d6ee61ff48 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -426,9 +426,9 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	}
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, "Cannot get buffer for block bitmap - "
-			   "block_group = %u, block_bitmap = %llu",
-			   block_group, bitmap_blk);
+		ext4_warning(sb, "Cannot get buffer for block bitmap - "
+			     "block_group = %u, block_bitmap = %llu",
+			     block_group, bitmap_blk);
 		return ERR_PTR(-ENOMEM);
 	}
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 7c7123f265c2..1fc013f3d944 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -789,17 +789,16 @@ struct move_extent {
  * affected filesystem before 2242.
  */
 
-static inline __le32 ext4_encode_extra_time(struct timespec *time)
+static inline __le32 ext4_encode_extra_time(struct timespec64 *time)
 {
-	u32 extra = sizeof(time->tv_sec) > 4 ?
-		((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0;
+	u32 extra =((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK;
 	return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
 }
 
-static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
+static inline void ext4_decode_extra_time(struct timespec64 *time,
+					  __le32 extra)
 {
-	if (unlikely(sizeof(time->tv_sec) > 4 &&
-			(extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
+	if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK))) {
 
 #if 1
 		/* Handle legacy encoding of pre-1970 dates with epoch
@@ -821,9 +820,8 @@ static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
 do {										\
 	(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);		\
 	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     {\
-		struct timespec ts = timespec64_to_timespec((inode)->xtime);	\
 		(raw_inode)->xtime ## _extra =					\
-				ext4_encode_extra_time(&ts);			\
+				ext4_encode_extra_time(&(inode)->xtime);	\
 		}								\
 } while (0)
 
@@ -840,10 +838,8 @@ do {									       \
 do {										\
 	(inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime);	\
 	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {	\
-		struct timespec ts = timespec64_to_timespec((inode)->xtime);	\
-		ext4_decode_extra_time(&ts,					\
+		ext4_decode_extra_time(&(inode)->xtime,				\
 				       raw_inode->xtime ## _extra);		\
-		(inode)->xtime = timespec_to_timespec64(ts);			\
 		}								\
 	else									\
 		(inode)->xtime.tv_nsec = 0;					\
@@ -993,9 +989,9 @@ struct ext4_inode_info {
 
 	/*
 	 * File creation time. Its function is same as that of
-	 * struct timespec i_{a,c,m}time in the generic inode.
+	 * struct timespec64 i_{a,c,m}time in the generic inode.
 	 */
-	struct timespec i_crtime;
+	struct timespec64 i_crtime;
 
 	/* mballoc */
 	struct list_head i_prealloc_list;
@@ -1299,7 +1295,14 @@ struct ext4_super_block {
 	__le32	s_lpf_ino;		/* Location of the lost+found inode */
 	__le32	s_prj_quota_inum;	/* inode for tracking project quota */
 	__le32	s_checksum_seed;	/* crc32c(uuid) if csum_seed set */
-	__le32	s_reserved[98];		/* Padding to the end of the block */
+	__u8	s_wtime_hi;
+	__u8	s_mtime_hi;
+	__u8	s_mkfs_time_hi;
+	__u8	s_lastcheck_hi;
+	__u8	s_first_error_time_hi;
+	__u8	s_last_error_time_hi;
+	__u8	s_pad[2];
+	__le32	s_reserved[96];		/* Padding to the end of the block */
 	__le32	s_checksum;		/* crc32c(superblock) */
 };
 
@@ -2456,6 +2459,7 @@ extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
 extern int ext4_truncate(struct inode *);
+extern int ext4_break_layouts(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
 extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
 extern void ext4_set_inode_flags(struct inode *);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 8ce6fd5b10dd..72a361d5ef74 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4826,6 +4826,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * released from page cache.
 		 */
 		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		ret = ext4_break_layouts(inode);
+		if (ret) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			goto out_mutex;
+		}
+
 		ret = ext4_update_disksize_before_punch(inode, offset, len);
 		if (ret) {
 			up_write(&EXT4_I(inode)->i_mmap_sem);
@@ -5499,6 +5506,11 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_mmap;
+
 	/*
 	 * Need to round down offset to be aligned with page size boundary
 	 * for page size > block size.
@@ -5647,6 +5659,11 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_mmap;
+
 	/*
 	 * Need to round down to align start offset to page size boundary
 	 * for page size > block size.
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f336cbc6e932..2addcb8730e1 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -138,9 +138,9 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	}
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, "Cannot read inode bitmap - "
-			    "block_group = %u, inode_bitmap = %llu",
-			    block_group, bitmap_blk);
+		ext4_warning(sb, "Cannot read inode bitmap - "
+			     "block_group = %u, inode_bitmap = %llu",
+			     block_group, bitmap_blk);
 		return ERR_PTR(-ENOMEM);
 	}
 	if (bitmap_uptodate(bh))
@@ -1086,7 +1086,7 @@ got:
 	/* This is the optimal IO size (for stat), not the fs block size */
 	inode->i_blocks = 0;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
-	ei->i_crtime = timespec64_to_timespec(inode->i_mtime);
+	ei->i_crtime = inode->i_mtime;
 
 	memset(ei->i_data, 0, sizeof(ei->i_data));
 	ei->i_dir_start_lookup = 0;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4efe77286ecd..8f6ad7667974 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -317,7 +317,7 @@ stop_handle:
 	 * (Well, we could do this if we need to, but heck - it works)
 	 */
 	ext4_orphan_del(handle, inode);
-	EXT4_I(inode)->i_dtime	= get_seconds();
+	EXT4_I(inode)->i_dtime	= (__u32)ktime_get_real_seconds();
 
 	/*
 	 * One subtle ordering requirement: if anything has gone wrong
@@ -4191,6 +4191,39 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 	return 0;
 }
 
+static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock)
+{
+	*did_unlock = true;
+	up_write(&ei->i_mmap_sem);
+	schedule();
+	down_write(&ei->i_mmap_sem);
+}
+
+int ext4_break_layouts(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct page *page;
+	bool retry;
+	int error;
+
+	if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+		return -EINVAL;
+
+	do {
+		retry = false;
+		page = dax_layout_busy_page(inode->i_mapping);
+		if (!page)
+			return 0;
+
+		error = ___wait_var_event(&page->_refcount,
+				atomic_read(&page->_refcount) == 1,
+				TASK_INTERRUPTIBLE, 0, 0,
+				ext4_wait_dax_page(ei, &retry));
+	} while (error == 0 && retry);
+
+	return error;
+}
+
 /*
  * ext4_punch_hole: punches a hole in a file by releasing the blocks
  * associated with the given offset and length
@@ -4264,6 +4297,11 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_dio;
+
 	first_block_offset = round_up(offset, sb->s_blocksize);
 	last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
@@ -4944,17 +4982,14 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		ret = -EFSCORRUPTED;
 		goto bad_inode;
 	} else if (!ext4_has_inline_data(inode)) {
-		if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
-			if ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-			    (S_ISLNK(inode->i_mode) &&
-			     !ext4_inode_is_fast_symlink(inode))))
-				/* Validate extent which is part of inode */
+		/* validate the block references in the inode */
+		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		   (S_ISLNK(inode->i_mode) &&
+		    !ext4_inode_is_fast_symlink(inode))) {
+			if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 				ret = ext4_ext_check_inode(inode);
-		} else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-			   (S_ISLNK(inode->i_mode) &&
-			    !ext4_inode_is_fast_symlink(inode))) {
-			/* Validate block references which are part of inode */
-			ret = ext4_ind_check_inode(inode);
+			else
+				ret = ext4_ind_check_inode(inode);
 		}
 	}
 	if (ret)
@@ -5553,6 +5588,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				ext4_wait_for_tail_page_commit(inode);
 		}
 		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		rc = ext4_break_layouts(inode);
+		if (rc) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			error = rc;
+			goto err_out;
+		}
+
 		/*
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f7ab34088162..e29fce2fbf25 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -14,6 +14,7 @@
 #include <linux/log2.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/nospec.h>
 #include <linux/backing-dev.h>
 #include <trace/events/ext4.h>
 
@@ -2140,7 +2141,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 		 * This should tell if fe_len is exactly power of 2
 		 */
 		if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0)
-			ac->ac_2order = i - 1;
+			ac->ac_2order = array_index_nospec(i - 1,
+							   sb->s_blocksize_bits + 2);
 	}
 
 	/* if stream allocation is enabled, use global goal */
@@ -3799,7 +3801,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 	ext4_group_t group;
 	ext4_grpblk_t bit;
 	unsigned long long grp_blk_start;
-	int err = 0;
 	int free = 0;
 
 	BUG_ON(pa->pa_deleted == 0);
@@ -3840,7 +3841,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 	}
 	atomic_add(free, &sbi->s_mb_discarded);
 
-	return err;
+	return 0;
 }
 
 static noinline_for_stack int
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 638ad4743477..39b07c2d3384 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -147,7 +147,7 @@ static int kmmpd(void *data)
 
 	mmp_block = le64_to_cpu(es->s_mmp_block);
 	mmp = (struct mmp_struct *)(bh->b_data);
-	mmp->mmp_time = cpu_to_le64(get_seconds());
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 	/*
 	 * Start with the higher mmp_check_interval and reduce it if
 	 * the MMP block is being updated on time.
@@ -165,7 +165,7 @@ static int kmmpd(void *data)
 			seq = 1;
 
 		mmp->mmp_seq = cpu_to_le32(seq);
-		mmp->mmp_time = cpu_to_le64(get_seconds());
+		mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 		last_update_time = jiffies;
 
 		retval = write_mmp_block(sb, bh);
@@ -241,7 +241,7 @@ static int kmmpd(void *data)
 	 * Unmount seems to be clean.
 	 */
 	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
-	mmp->mmp_time = cpu_to_le64(get_seconds());
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 
 	retval = write_mmp_block(sb, bh);
 
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 8e17efdcbf11..a409ff70d67b 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -134,9 +134,7 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2,
 		mapping[0] = inode1->i_mapping;
 		mapping[1] = inode2->i_mapping;
 	} else {
-		pgoff_t tmp = index1;
-		index1 = index2;
-		index2 = tmp;
+		swap(index1, index2);
 		mapping[0] = inode2->i_mapping;
 		mapping[1] = inode1->i_mapping;
 	}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2a4c25c4681d..116ff68c5bd4 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1398,6 +1398,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 			goto cleanup_and_exit;
 		dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
 			       "falling back\n"));
+		ret = NULL;
 	}
 	nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
 	if (!nblocks) {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b7f7922061be..5863fd22e90b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -312,6 +312,24 @@ void ext4_itable_unused_set(struct super_block *sb,
 		bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
 }
 
+static void __ext4_update_tstamp(__le32 *lo, __u8 *hi)
+{
+	time64_t now = ktime_get_real_seconds();
+
+	now = clamp_val(now, 0, (1ull << 40) - 1);
+
+	*lo = cpu_to_le32(lower_32_bits(now));
+	*hi = upper_32_bits(now);
+}
+
+static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi)
+{
+	return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo);
+}
+#define ext4_update_tstamp(es, tstamp) \
+	__ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
+#define ext4_get_tstamp(es, tstamp) \
+	__ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
 
 static void __save_error_info(struct super_block *sb, const char *func,
 			    unsigned int line)
@@ -322,11 +340,12 @@ static void __save_error_info(struct super_block *sb, const char *func,
 	if (bdev_read_only(sb->s_bdev))
 		return;
 	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-	es->s_last_error_time = cpu_to_le32(get_seconds());
+	ext4_update_tstamp(es, s_last_error_time);
 	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
 	es->s_last_error_line = cpu_to_le32(line);
 	if (!es->s_first_error_time) {
 		es->s_first_error_time = es->s_last_error_time;
+		es->s_first_error_time_hi = es->s_last_error_time_hi;
 		strncpy(es->s_first_error_func, func,
 			sizeof(es->s_first_error_func));
 		es->s_first_error_line = cpu_to_le32(line);
@@ -776,26 +795,26 @@ void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
 	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+	int ret;
 
-	if ((flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) &&
-	    !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) {
-		percpu_counter_sub(&sbi->s_freeclusters_counter,
-					grp->bb_free);
-		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
-			&grp->bb_state);
+	if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) {
+		ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
+					    &grp->bb_state);
+		if (!ret)
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 	}
 
-	if ((flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) &&
-	    !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
-		if (gdp) {
+	if (flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) {
+		ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
+					    &grp->bb_state);
+		if (!ret && gdp) {
 			int count;
 
 			count = ext4_free_inodes_count(sb, gdp);
 			percpu_counter_sub(&sbi->s_freeinodes_counter,
 					   count);
 		}
-		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
-			&grp->bb_state);
 	}
 }
 
@@ -2174,8 +2193,8 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 			 "warning: maximal mount count reached, "
 			 "running e2fsck is recommended");
 	else if (le32_to_cpu(es->s_checkinterval) &&
-		(le32_to_cpu(es->s_lastcheck) +
-			le32_to_cpu(es->s_checkinterval) <= get_seconds()))
+		 (ext4_get_tstamp(es, s_lastcheck) +
+		  le32_to_cpu(es->s_checkinterval) <= ktime_get_real_seconds()))
 		ext4_msg(sb, KERN_WARNING,
 			 "warning: checktime reached, "
 			 "running e2fsck is recommended");
@@ -2184,7 +2203,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
 		es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
 	le16_add_cpu(&es->s_mnt_count, 1);
-	es->s_mtime = cpu_to_le32(get_seconds());
+	ext4_update_tstamp(es, s_mtime);
 	ext4_update_dynamic_rev(sb);
 	if (sbi->s_journal)
 		ext4_set_feature_journal_needs_recovery(sb);
@@ -2875,8 +2894,9 @@ static void print_daily_error_info(struct timer_list *t)
 		ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
 			 le32_to_cpu(es->s_error_count));
 	if (es->s_first_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
-		       sb->s_id, le32_to_cpu(es->s_first_error_time),
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %llu: %.*s:%d",
+		       sb->s_id,
+		       ext4_get_tstamp(es, s_first_error_time),
 		       (int) sizeof(es->s_first_error_func),
 		       es->s_first_error_func,
 		       le32_to_cpu(es->s_first_error_line));
@@ -2889,8 +2909,9 @@ static void print_daily_error_info(struct timer_list *t)
 		printk(KERN_CONT "\n");
 	}
 	if (es->s_last_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
-		       sb->s_id, le32_to_cpu(es->s_last_error_time),
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %llu: %.*s:%d",
+		       sb->s_id,
+		       ext4_get_tstamp(es, s_last_error_time),
 		       (int) sizeof(es->s_last_error_func),
 		       es->s_last_error_func,
 		       le32_to_cpu(es->s_last_error_line));
@@ -3508,7 +3529,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_sb_block = sb_block;
 	if (sb->s_bdev->bd_part)
 		sbi->s_sectors_written_start =
-			part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+			part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]);
 
 	/* Cleanup superblock name */
 	strreplace(sb->s_id, '/', '!');
@@ -4813,11 +4834,12 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	 * to complain and force a full file system check.
 	 */
 	if (!(sb->s_flags & SB_RDONLY))
-		es->s_wtime = cpu_to_le32(get_seconds());
+		ext4_update_tstamp(es, s_wtime);
 	if (sb->s_bdev->bd_part)
 		es->s_kbytes_written =
 			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
-			    ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			    ((part_stat_read(sb->s_bdev->bd_part,
+					     sectors[STAT_WRITE]) -
 			      EXT4_SB(sb)->s_sectors_written_start) >> 1));
 	else
 		es->s_kbytes_written =
@@ -5080,6 +5102,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 #endif
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 
+	if (data && !orig_data)
+		return -ENOMEM;
+
 	/* Store the original options */
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;
@@ -5665,13 +5690,13 @@ static int ext4_enable_quotas(struct super_block *sb)
 				DQUOT_USAGE_ENABLED |
 				(quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
 			if (err) {
-				for (type--; type >= 0; type--)
-					dquot_quota_off(sb, type);
-
 				ext4_warning(sb,
 					"Failed to enable quota tracking "
 					"(type=%d, err=%d). Please run "
 					"e2fsck to fix.", type, err);
+				for (type--; type >= 0; type--)
+					dquot_quota_off(sb, type);
+
 				return err;
 			}
 		}
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index f34da0bb8f17..9212a026a1f1 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -25,6 +25,8 @@ typedef enum {
 	attr_reserved_clusters,
 	attr_inode_readahead,
 	attr_trigger_test_error,
+	attr_first_error_time,
+	attr_last_error_time,
 	attr_feature,
 	attr_pointer_ui,
 	attr_pointer_atomic,
@@ -56,7 +58,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 	if (!sb->s_bdev->bd_part)
 		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%lu\n",
-			(part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			(part_stat_read(sb->s_bdev->bd_part,
+					sectors[STAT_WRITE]) -
 			 sbi->s_sectors_written_start) >> 1);
 }
 
@@ -68,7 +71,8 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			(unsigned long long)(sbi->s_kbytes_written +
-			((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			((part_stat_read(sb->s_bdev->bd_part,
+					 sectors[STAT_WRITE]) -
 			  EXT4_SB(sb)->s_sectors_written_start) >> 1)));
 }
 
@@ -182,8 +186,8 @@ EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
 EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
-EXT4_RO_ATTR_ES_UI(first_error_time, s_first_error_time);
-EXT4_RO_ATTR_ES_UI(last_error_time, s_last_error_time);
+EXT4_ATTR(first_error_time, 0444, first_error_time);
+EXT4_ATTR(last_error_time, 0444, last_error_time);
 
 static unsigned int old_bump_val = 128;
 EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
@@ -249,6 +253,15 @@ static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi)
 	return NULL;
 }
 
+static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi)
+{
+	return snprintf(buf, PAGE_SIZE, "%lld",
+			((time64_t)hi << 32) + le32_to_cpu(lo));
+}
+
+#define print_tstamp(buf, es, tstamp) \
+	__print_tstamp(buf, (es)->tstamp, (es)->tstamp ## _hi)
+
 static ssize_t ext4_attr_show(struct kobject *kobj,
 			      struct attribute *attr, char *buf)
 {
@@ -274,8 +287,12 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 	case attr_pointer_ui:
 		if (!ptr)
 			return 0;
-		return snprintf(buf, PAGE_SIZE, "%u\n",
-				*((unsigned int *) ptr));
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			return snprintf(buf, PAGE_SIZE, "%u\n",
+					le32_to_cpup(ptr));
+		else
+			return snprintf(buf, PAGE_SIZE, "%u\n",
+					*((unsigned int *) ptr));
 	case attr_pointer_atomic:
 		if (!ptr)
 			return 0;
@@ -283,6 +300,10 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 				atomic_read((atomic_t *) ptr));
 	case attr_feature:
 		return snprintf(buf, PAGE_SIZE, "supported\n");
+	case attr_first_error_time:
+		return print_tstamp(buf, sbi->s_es, s_first_error_time);
+	case attr_last_error_time:
+		return print_tstamp(buf, sbi->s_es, s_last_error_time);
 	}
 
 	return 0;
@@ -308,7 +329,10 @@ static ssize_t ext4_attr_store(struct kobject *kobj,
 		ret = kstrtoul(skip_spaces(buf), 0, &t);
 		if (ret)
 			return ret;
-		*((unsigned int *) ptr) = t;
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			*((__le32 *) ptr) = cpu_to_le32(t);
+		else
+			*((unsigned int *) ptr) = t;
 		return len;
 	case attr_inode_readahead:
 		return inode_readahead_blks_store(sbi, buf, len);
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index 0cb13badf473..bcbe3668c1d4 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -11,6 +11,10 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	/*
+	 * We don't need to call ext4_break_layouts() because the blocks we
+	 * are truncating were never visible to userspace.
+	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
 	truncate_inode_pages(inode->i_mapping, inode->i_size);
 	ext4_truncate(inode);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 723df14f4084..f36fc5d5b257 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -190,6 +190,8 @@ ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end,
 		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
 		if ((void *)next >= end)
 			return -EFSCORRUPTED;
+		if (strnlen(e->e_name, e->e_name_len) != e->e_name_len)
+			return -EFSCORRUPTED;
 		e = next;
 	}
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 4d8b1de83143..6799c3fc44e3 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1304,7 +1304,7 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
  * and the return value is in kbytes. s is of struct f2fs_sb_info.
  */
 #define BD_PART_WRITTEN(s)						 \
-(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[1]) -		 \
+(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
 		(s)->sectors_written_start) >> 1)
 
 static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 3995e926ba3a..17bcff789c08 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2882,7 +2882,8 @@ try_onemore:
 	/* For write statistics */
 	if (sb->s_bdev->bd_part)
 		sbi->sectors_written_start =
-			(u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+			(u64)part_stat_read(sb->s_bdev->bd_part,
+					    sectors[STAT_WRITE]);
 
 	/* Read accumulated write IO statistics if exists */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
diff --git a/fs/file_table.c b/fs/file_table.c
index 7ec0b3e5f05d..d6eccd04d703 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -51,6 +51,7 @@ static void file_free_rcu(struct rcu_head *head)
 
 static inline void file_free(struct file *f)
 {
+	security_file_free(f);
 	percpu_counter_dec(&nr_files);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
@@ -100,9 +101,8 @@ int proc_nr_files(struct ctl_table *table, int write,
  * done, you will imbalance int the mount's writer count
  * and a warning at __fput() time.
  */
-struct file *get_empty_filp(void)
+struct file *alloc_empty_file(int flags, const struct cred *cred)
 {
-	const struct cred *cred = current_cred();
 	static long old_max;
 	struct file *f;
 	int error;
@@ -123,11 +123,10 @@ struct file *get_empty_filp(void)
 	if (unlikely(!f))
 		return ERR_PTR(-ENOMEM);
 
-	percpu_counter_inc(&nr_files);
 	f->f_cred = get_cred(cred);
 	error = security_file_alloc(f);
 	if (unlikely(error)) {
-		file_free(f);
+		file_free_rcu(&f->f_u.fu_rcuhead);
 		return ERR_PTR(error);
 	}
 
@@ -136,7 +135,10 @@ struct file *get_empty_filp(void)
 	spin_lock_init(&f->f_lock);
 	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
+	f->f_flags = flags;
+	f->f_mode = OPEN_FMODE(flags);
 	/* f->f_version: 0 */
+	percpu_counter_inc(&nr_files);
 	return f;
 
 over:
@@ -152,15 +154,15 @@ over:
  * alloc_file - allocate and initialize a 'struct file'
  *
  * @path: the (dentry, vfsmount) pair for the new file
- * @mode: the mode with which the new file will be opened
+ * @flags: O_... flags with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
  */
-struct file *alloc_file(const struct path *path, fmode_t mode,
+static struct file *alloc_file(const struct path *path, int flags,
 		const struct file_operations *fop)
 {
 	struct file *file;
 
-	file = get_empty_filp();
+	file = alloc_empty_file(flags, current_cred());
 	if (IS_ERR(file))
 		return file;
 
@@ -168,19 +170,56 @@ struct file *alloc_file(const struct path *path, fmode_t mode,
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
 	file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
-	if ((mode & FMODE_READ) &&
+	if ((file->f_mode & FMODE_READ) &&
 	     likely(fop->read || fop->read_iter))
-		mode |= FMODE_CAN_READ;
-	if ((mode & FMODE_WRITE) &&
+		file->f_mode |= FMODE_CAN_READ;
+	if ((file->f_mode & FMODE_WRITE) &&
 	     likely(fop->write || fop->write_iter))
-		mode |= FMODE_CAN_WRITE;
-	file->f_mode = mode;
+		file->f_mode |= FMODE_CAN_WRITE;
+	file->f_mode |= FMODE_OPENED;
 	file->f_op = fop;
-	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
 	return file;
 }
-EXPORT_SYMBOL(alloc_file);
+
+struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
+				const char *name, int flags,
+				const struct file_operations *fops)
+{
+	static const struct dentry_operations anon_ops = {
+		.d_dname = simple_dname
+	};
+	struct qstr this = QSTR_INIT(name, strlen(name));
+	struct path path;
+	struct file *file;
+
+	path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
+	if (!path.dentry)
+		return ERR_PTR(-ENOMEM);
+	if (!mnt->mnt_sb->s_d_op)
+		d_set_d_op(path.dentry, &anon_ops);
+	path.mnt = mntget(mnt);
+	d_instantiate(path.dentry, inode);
+	file = alloc_file(&path, flags, fops);
+	if (IS_ERR(file)) {
+		ihold(inode);
+		path_put(&path);
+	}
+	return file;
+}
+EXPORT_SYMBOL(alloc_file_pseudo);
+
+struct file *alloc_file_clone(struct file *base, int flags,
+				const struct file_operations *fops)
+{
+	struct file *f = alloc_file(&base->f_path, flags, fops);
+	if (!IS_ERR(f)) {
+		path_get(&f->f_path);
+		f->f_mapping = base->f_mapping;
+	}
+	return f;
+}
 
 /* the real guts of fput() - releasing the last reference to file
  */
@@ -190,6 +229,9 @@ static void __fput(struct file *file)
 	struct vfsmount *mnt = file->f_path.mnt;
 	struct inode *inode = file->f_inode;
 
+	if (unlikely(!(file->f_mode & FMODE_OPENED)))
+		goto out;
+
 	might_sleep();
 
 	fsnotify_close(file);
@@ -207,7 +249,6 @@ static void __fput(struct file *file)
 	}
 	if (file->f_op->release)
 		file->f_op->release(inode, file);
-	security_file_free(file);
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
 		     !(file->f_mode & FMODE_PATH))) {
 		cdev_put(inode->i_cdev);
@@ -220,12 +261,10 @@ static void __fput(struct file *file)
 		put_write_access(inode);
 		__mnt_drop_write(mnt);
 	}
-	file->f_path.dentry = NULL;
-	file->f_path.mnt = NULL;
-	file->f_inode = NULL;
-	file_free(file);
 	dput(dentry);
 	mntput(mnt);
+out:
+	file_free(file);
 }
 
 static LLIST_HEAD(delayed_fput_list);
@@ -300,14 +339,6 @@ void __fput_sync(struct file *file)
 
 EXPORT_SYMBOL(fput);
 
-void put_filp(struct file *file)
-{
-	if (atomic_long_dec_and_test(&file->f_count)) {
-		security_file_free(file);
-		file_free(file);
-	}
-}
-
 void __init files_init(void)
 {
 	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 56231b31f806..d80aab0d5982 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -399,7 +399,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
  */
 static int fuse_create_open(struct inode *dir, struct dentry *entry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	int err;
 	struct inode *inode;
@@ -469,7 +469,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	d_instantiate(entry, inode);
 	fuse_change_entry_timeout(entry, &outentry);
 	fuse_invalidate_attr(dir);
-	err = finish_open(file, entry, generic_file_open, opened);
+	err = finish_open(file, entry, generic_file_open);
 	if (err) {
 		fuse_sync_release(ff, flags);
 	} else {
@@ -489,7 +489,7 @@ out_err:
 static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	int err;
 	struct fuse_conn *fc = get_fuse_conn(dir);
@@ -508,12 +508,12 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 		goto no_open;
 
 	/* Only creates */
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 
 	if (fc->no_create)
 		goto mknod;
 
-	err = fuse_create_open(dir, entry, file, flags, mode, opened);
+	err = fuse_create_open(dir, entry, file, flags, mode);
 	if (err == -ENOSYS) {
 		fc->no_create = 1;
 		goto mknod;
@@ -539,6 +539,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args,
 {
 	struct fuse_entry_out outarg;
 	struct inode *inode;
+	struct dentry *d;
 	int err;
 	struct fuse_forget_link *forget;
 
@@ -570,11 +571,17 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args,
 	}
 	kfree(forget);
 
-	err = d_instantiate_no_diralias(entry, inode);
-	if (err)
-		return err;
+	d_drop(entry);
+	d = d_splice_alias(inode, entry);
+	if (IS_ERR(d))
+		return PTR_ERR(d);
 
-	fuse_change_entry_timeout(entry, &outarg);
+	if (d) {
+		fuse_change_entry_timeout(d, &outarg);
+		dput(d);
+	} else {
+		fuse_change_entry_timeout(entry, &outarg);
+	}
 	fuse_invalidate_attr(dir);
 	return 0;
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index feda55f67050..648f0ca1ad57 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -580,7 +580,7 @@ static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 			     struct file *file,
 			     umode_t mode, dev_t dev, const char *symname,
-			     unsigned int size, int excl, int *opened)
+			     unsigned int size, int excl)
 {
 	const struct qstr *name = &dentry->d_name;
 	struct posix_acl *default_acl, *acl;
@@ -626,7 +626,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		error = 0;
 		if (file) {
 			if (S_ISREG(inode->i_mode))
-				error = finish_open(file, dentry, gfs2_open_common, opened);
+				error = finish_open(file, dentry, gfs2_open_common);
 			else
 				error = finish_no_open(file, NULL);
 		}
@@ -767,8 +767,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	mark_inode_dirty(inode);
 	d_instantiate(dentry, inode);
 	if (file) {
-		*opened |= FILE_CREATED;
-		error = finish_open(file, dentry, gfs2_open_common, opened);
+		file->f_mode |= FMODE_CREATED;
+		error = finish_open(file, dentry, gfs2_open_common);
 	}
 	gfs2_glock_dq_uninit(ghs);
 	gfs2_glock_dq_uninit(ghs + 1);
@@ -822,7 +822,7 @@ fail:
 static int gfs2_create(struct inode *dir, struct dentry *dentry,
 		       umode_t mode, bool excl)
 {
-	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /**
@@ -830,14 +830,13 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
  * @dir: The directory inode
  * @dentry: The dentry of the new inode
  * @file: File to be opened
- * @opened: atomic_open flags
  *
  *
  * Returns: errno
  */
 
 static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
-				    struct file *file, int *opened)
+				    struct file *file)
 {
 	struct inode *inode;
 	struct dentry *d;
@@ -866,7 +865,7 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
 		return d;
 	}
 	if (file && S_ISREG(inode->i_mode))
-		error = finish_open(file, dentry, gfs2_open_common, opened);
+		error = finish_open(file, dentry, gfs2_open_common);
 
 	gfs2_glock_dq_uninit(&gh);
 	if (error) {
@@ -879,7 +878,7 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
 static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
 				  unsigned flags)
 {
-	return __gfs2_lookup(dir, dentry, NULL, NULL);
+	return __gfs2_lookup(dir, dentry, NULL);
 }
 
 /**
@@ -1189,7 +1188,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 	if (size >= gfs2_max_stuffed_size(GFS2_I(dir)))
 		return -ENAMETOOLONG;
 
-	return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
 }
 
 /**
@@ -1204,7 +1203,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir));
-	return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0);
 }
 
 /**
@@ -1219,7 +1218,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 		      dev_t dev)
 {
-	return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0);
 }
 
 /**
@@ -1229,14 +1228,13 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
  * @file: The proposed new struct file
  * @flags: open flags
  * @mode: File mode
- * @opened: Flag to say whether the file has been opened or not
  *
  * Returns: error code or 0 for success
  */
 
 static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	struct dentry *d;
 	bool excl = !!(flags & O_EXCL);
@@ -1244,13 +1242,13 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (!d_in_lookup(dentry))
 		goto skip_lookup;
 
-	d = __gfs2_lookup(dir, dentry, file, opened);
+	d = __gfs2_lookup(dir, dentry, file);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
 	if (d != NULL)
 		dentry = d;
 	if (d_really_is_positive(dentry)) {
-		if (!(*opened & FILE_OPENED))
+		if (!(file->f_mode & FMODE_OPENED))
 			return finish_no_open(file, d);
 		dput(d);
 		return 0;
@@ -1262,7 +1260,7 @@ skip_lookup:
 	if (!(flags & O_CREAT))
 		return -ENOENT;
 
-	return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl, opened);
+	return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /*
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 2a16111d312f..a2dfa1b2a89c 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -541,7 +541,7 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
 	HFS_I(inode)->rsrc_inode = dir;
 	HFS_I(dir)->rsrc_inode = inode;
 	igrab(dir);
-	hlist_add_fake(&inode->i_hash);
+	inode_fake_hash(inode);
 	mark_inode_dirty(inode);
 	dont_mount(dentry);
 out:
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 2597b290c2a5..444c7b170359 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -610,33 +610,21 @@ static struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
 	int err;
 
 	inode = hostfs_iget(ino->i_sb);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
+	if (IS_ERR(inode))
 		goto out;
-	}
 
 	err = -ENOMEM;
 	name = dentry_name(dentry);
-	if (name == NULL)
-		goto out_put;
-
-	err = read_name(inode, name);
-
-	__putname(name);
-	if (err == -ENOENT) {
+	if (name) {
+		err = read_name(inode, name);
+		__putname(name);
+	}
+	if (err) {
 		iput(inode);
-		inode = NULL;
+		inode = (err == -ENOENT) ? NULL : ERR_PTR(err);
 	}
-	else if (err)
-		goto out_put;
-
-	d_add(dentry, inode);
-	return NULL;
-
- out_put:
-	iput(inode);
  out:
-	return ERR_PTR(err);
+	return d_splice_alias(inode, dentry);
 }
 
 static int hostfs_link(struct dentry *to, struct inode *ino,
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index c83ece7facc5..d85230c84ef2 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -244,6 +244,7 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in
 	result = iget_locked(dir->i_sb, ino);
 	if (!result) {
 		hpfs_error(dir->i_sb, "hpfs_lookup: can't get inode");
+		result = ERR_PTR(-ENOMEM);
 		goto bail1;
 	}
 	if (result->i_state & I_NEW) {
@@ -266,6 +267,8 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in
 
 	if (de->has_acl || de->has_xtd_perm) if (!sb_rdonly(dir->i_sb)) {
 		hpfs_error(result->i_sb, "ACLs or XPERM found. This is probably HPFS386. This driver doesn't support it now. Send me some info on these structures");
+		iput(result);
+		result = ERR_PTR(-EINVAL);
 		goto bail1;
 	}
 
@@ -301,29 +304,17 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in
 		}
 	}
 
+bail1:
 	hpfs_brelse4(&qbh);
 
 	/*
 	 * Made it.
 	 */
 
-	end:
-	end_add:
+end:
+end_add:
 	hpfs_unlock(dir->i_sb);
-	d_add(dentry, result);
-	return NULL;
-
-	/*
-	 * Didn't.
-	 */
-	bail1:
-	
-	hpfs_brelse4(&qbh);
-	
-	/*bail:*/
-
-	hpfs_unlock(dir->i_sb);
-	return ERR_PTR(-ENOENT);
+	return d_splice_alias(result, dentry);
 }
 
 const struct file_operations hpfs_dir_ops =
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 40d4c66c7751..346a146c7617 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1310,10 +1310,6 @@ static int get_hstate_idx(int page_size_log)
 	return h - hstates;
 }
 
-static const struct dentry_operations anon_ops = {
-	.d_dname = simple_dname
-};
-
 /*
  * Note that size should be aligned to proper hugepage size in caller side,
  * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
@@ -1322,19 +1318,18 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 				vm_flags_t acctflag, struct user_struct **user,
 				int creat_flags, int page_size_log)
 {
-	struct file *file = ERR_PTR(-ENOMEM);
 	struct inode *inode;
-	struct path path;
-	struct super_block *sb;
-	struct qstr quick_string;
+	struct vfsmount *mnt;
 	int hstate_idx;
+	struct file *file;
 
 	hstate_idx = get_hstate_idx(page_size_log);
 	if (hstate_idx < 0)
 		return ERR_PTR(-ENODEV);
 
 	*user = NULL;
-	if (!hugetlbfs_vfsmount[hstate_idx])
+	mnt = hugetlbfs_vfsmount[hstate_idx];
+	if (!mnt)
 		return ERR_PTR(-ENOENT);
 
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
@@ -1350,45 +1345,28 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 		}
 	}
 
-	sb = hugetlbfs_vfsmount[hstate_idx]->mnt_sb;
-	quick_string.name = name;
-	quick_string.len = strlen(quick_string.name);
-	quick_string.hash = 0;
-	path.dentry = d_alloc_pseudo(sb, &quick_string);
-	if (!path.dentry)
-		goto out_shm_unlock;
-
-	d_set_d_op(path.dentry, &anon_ops);
-	path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
 	file = ERR_PTR(-ENOSPC);
-	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
-		goto out_dentry;
+		goto out;
 	if (creat_flags == HUGETLB_SHMFS_INODE)
 		inode->i_flags |= S_PRIVATE;
 
-	file = ERR_PTR(-ENOMEM);
-	if (hugetlb_reserve_pages(inode, 0,
-			size >> huge_page_shift(hstate_inode(inode)), NULL,
-			acctflag))
-		goto out_inode;
-
-	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
 	clear_nlink(inode);
 
-	file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
-			&hugetlbfs_file_operations);
-	if (IS_ERR(file))
-		goto out_dentry; /* inode is already attached */
-
-	return file;
+	if (hugetlb_reserve_pages(inode, 0,
+			size >> huge_page_shift(hstate_inode(inode)), NULL,
+			acctflag))
+		file = ERR_PTR(-ENOMEM);
+	else
+		file = alloc_file_pseudo(inode, mnt, name, O_RDWR,
+					&hugetlbfs_file_operations);
+	if (!IS_ERR(file))
+		return file;
 
-out_inode:
 	iput(inode);
-out_dentry:
-	path_put(&path);
-out_shm_unlock:
+out:
 	if (*user) {
 		user_shm_unlock(size, *user);
 		*user = NULL;
diff --git a/fs/inode.c b/fs/inode.c
index 8c86c809ca17..a06de4454232 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -804,6 +804,10 @@ repeat:
 			__wait_on_freeing_inode(inode);
 			goto repeat;
 		}
+		if (unlikely(inode->i_state & I_CREATING)) {
+			spin_unlock(&inode->i_lock);
+			return ERR_PTR(-ESTALE);
+		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
 		return inode;
@@ -831,6 +835,10 @@ repeat:
 			__wait_on_freeing_inode(inode);
 			goto repeat;
 		}
+		if (unlikely(inode->i_state & I_CREATING)) {
+			spin_unlock(&inode->i_lock);
+			return ERR_PTR(-ESTALE);
+		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
 		return inode;
@@ -961,13 +969,26 @@ void unlock_new_inode(struct inode *inode)
 	lockdep_annotate_inode_mutex_key(inode);
 	spin_lock(&inode->i_lock);
 	WARN_ON(!(inode->i_state & I_NEW));
-	inode->i_state &= ~I_NEW;
+	inode->i_state &= ~I_NEW & ~I_CREATING;
 	smp_mb();
 	wake_up_bit(&inode->i_state, __I_NEW);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(unlock_new_inode);
 
+void discard_new_inode(struct inode *inode)
+{
+	lockdep_annotate_inode_mutex_key(inode);
+	spin_lock(&inode->i_lock);
+	WARN_ON(!(inode->i_state & I_NEW));
+	inode->i_state &= ~I_NEW;
+	smp_mb();
+	wake_up_bit(&inode->i_state, __I_NEW);
+	spin_unlock(&inode->i_lock);
+	iput(inode);
+}
+EXPORT_SYMBOL(discard_new_inode);
+
 /**
  * lock_two_nondirectories - take two i_mutexes on non-directory objects
  *
@@ -1029,6 +1050,7 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
 {
 	struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
 	struct inode *old;
+	bool creating = inode->i_state & I_CREATING;
 
 again:
 	spin_lock(&inode_hash_lock);
@@ -1039,6 +1061,8 @@ again:
 		 * Use the old inode instead of the preallocated one.
 		 */
 		spin_unlock(&inode_hash_lock);
+		if (IS_ERR(old))
+			return NULL;
 		wait_on_inode(old);
 		if (unlikely(inode_unhashed(old))) {
 			iput(old);
@@ -1060,6 +1084,8 @@ again:
 	inode->i_state |= I_NEW;
 	hlist_add_head(&inode->i_hash, head);
 	spin_unlock(&inode->i_lock);
+	if (!creating)
+		inode_sb_list_add(inode);
 unlock:
 	spin_unlock(&inode_hash_lock);
 
@@ -1094,12 +1120,13 @@ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval,
 	struct inode *inode = ilookup5(sb, hashval, test, data);
 
 	if (!inode) {
-		struct inode *new = new_inode(sb);
+		struct inode *new = alloc_inode(sb);
 
 		if (new) {
+			new->i_state = 0;
 			inode = inode_insert5(new, hashval, test, set, data);
 			if (unlikely(inode != new))
-				iput(new);
+				destroy_inode(new);
 		}
 	}
 	return inode;
@@ -1128,6 +1155,8 @@ again:
 	inode = find_inode_fast(sb, head, ino);
 	spin_unlock(&inode_hash_lock);
 	if (inode) {
+		if (IS_ERR(inode))
+			return NULL;
 		wait_on_inode(inode);
 		if (unlikely(inode_unhashed(inode))) {
 			iput(inode);
@@ -1165,6 +1194,8 @@ again:
 		 */
 		spin_unlock(&inode_hash_lock);
 		destroy_inode(inode);
+		if (IS_ERR(old))
+			return NULL;
 		inode = old;
 		wait_on_inode(inode);
 		if (unlikely(inode_unhashed(inode))) {
@@ -1282,7 +1313,7 @@ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval,
 	inode = find_inode(sb, head, test, data);
 	spin_unlock(&inode_hash_lock);
 
-	return inode;
+	return IS_ERR(inode) ? NULL : inode;
 }
 EXPORT_SYMBOL(ilookup5_nowait);
 
@@ -1338,6 +1369,8 @@ again:
 	spin_unlock(&inode_hash_lock);
 
 	if (inode) {
+		if (IS_ERR(inode))
+			return NULL;
 		wait_on_inode(inode);
 		if (unlikely(inode_unhashed(inode))) {
 			iput(inode);
@@ -1421,12 +1454,17 @@ int insert_inode_locked(struct inode *inode)
 		}
 		if (likely(!old)) {
 			spin_lock(&inode->i_lock);
-			inode->i_state |= I_NEW;
+			inode->i_state |= I_NEW | I_CREATING;
 			hlist_add_head(&inode->i_hash, head);
 			spin_unlock(&inode->i_lock);
 			spin_unlock(&inode_hash_lock);
 			return 0;
 		}
+		if (unlikely(old->i_state & I_CREATING)) {
+			spin_unlock(&old->i_lock);
+			spin_unlock(&inode_hash_lock);
+			return -EBUSY;
+		}
 		__iget(old);
 		spin_unlock(&old->i_lock);
 		spin_unlock(&inode_hash_lock);
@@ -1443,7 +1481,10 @@ EXPORT_SYMBOL(insert_inode_locked);
 int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 		int (*test)(struct inode *, void *), void *data)
 {
-	struct inode *old = inode_insert5(inode, hashval, test, NULL, data);
+	struct inode *old;
+
+	inode->i_state |= I_CREATING;
+	old = inode_insert5(inode, hashval, test, NULL, data);
 
 	if (old != inode) {
 		iput(old);
diff --git a/fs/internal.h b/fs/internal.h
index 5645b4ebf494..50a28fc71300 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -43,6 +43,8 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait)
 extern void guard_bio_eod(int rw, struct bio *bio);
 extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
 		get_block_t *get_block, struct iomap *iomap);
+int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
+		struct page *page);
 
 /*
  * char_dev.c
@@ -93,7 +95,7 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern struct file *get_empty_filp(void);
+extern struct file *alloc_empty_file(int, const struct cred *);
 
 /*
  * super.c
@@ -125,8 +127,7 @@ int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 
-extern int open_check_o_direct(struct file *f);
-extern int vfs_open(const struct path *, struct file *, const struct cred *);
+extern int vfs_open(const struct path *, struct file *);
 
 /*
  * inode.c
diff --git a/fs/iomap.c b/fs/iomap.c
index 0d0bd8845586..009071e73bc0 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Red Hat, Inc.
- * Copyright (c) 2016 Christoph Hellwig.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -17,7 +17,9 @@
 #include <linux/iomap.h>
 #include <linux/uaccess.h>
 #include <linux/gfp.h>
+#include <linux/migrate.h>
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
@@ -103,6 +105,467 @@ iomap_sector(struct iomap *iomap, loff_t pos)
 	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
 }
 
+static struct iomap_page *
+iomap_page_create(struct inode *inode, struct page *page)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (iop || i_blocksize(inode) == PAGE_SIZE)
+		return iop;
+
+	iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL);
+	atomic_set(&iop->read_count, 0);
+	atomic_set(&iop->write_count, 0);
+	bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+	set_page_private(page, (unsigned long)iop);
+	SetPagePrivate(page);
+	return iop;
+}
+
+static void
+iomap_page_release(struct page *page)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (!iop)
+		return;
+	WARN_ON_ONCE(atomic_read(&iop->read_count));
+	WARN_ON_ONCE(atomic_read(&iop->write_count));
+	ClearPagePrivate(page);
+	set_page_private(page, 0);
+	kfree(iop);
+}
+
+/*
+ * Calculate the range inside the page that we actually need to read.
+ */
+static void
+iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
+		loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp)
+{
+	unsigned block_bits = inode->i_blkbits;
+	unsigned block_size = (1 << block_bits);
+	unsigned poff = offset_in_page(*pos);
+	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
+	unsigned first = poff >> block_bits;
+	unsigned last = (poff + plen - 1) >> block_bits;
+	unsigned end = offset_in_page(i_size_read(inode)) >> block_bits;
+
+	/*
+	 * If the block size is smaller than the page size we need to check the
+	 * per-block uptodate status and adjust the offset and length if needed
+	 * to avoid reading in already uptodate ranges.
+	 */
+	if (iop) {
+		unsigned int i;
+
+		/* move forward for each leading block marked uptodate */
+		for (i = first; i <= last; i++) {
+			if (!test_bit(i, iop->uptodate))
+				break;
+			*pos += block_size;
+			poff += block_size;
+			plen -= block_size;
+			first++;
+		}
+
+		/* truncate len if we find any trailing uptodate block(s) */
+		for ( ; i <= last; i++) {
+			if (test_bit(i, iop->uptodate)) {
+				plen -= (last - i + 1) * block_size;
+				last = i - 1;
+				break;
+			}
+		}
+	}
+
+	/*
+	 * If the extent spans the block that contains the i_size we need to
+	 * handle both halves separately so that we properly zero data in the
+	 * page cache for blocks that are entirely outside of i_size.
+	 */
+	if (first <= end && last > end)
+		plen -= (last - end) * block_size;
+
+	*offp = poff;
+	*lenp = plen;
+}
+
+static void
+iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+	struct inode *inode = page->mapping->host;
+	unsigned first = off >> inode->i_blkbits;
+	unsigned last = (off + len - 1) >> inode->i_blkbits;
+	unsigned int i;
+	bool uptodate = true;
+
+	if (iop) {
+		for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) {
+			if (i >= first && i <= last)
+				set_bit(i, iop->uptodate);
+			else if (!test_bit(i, iop->uptodate))
+				uptodate = false;
+		}
+	}
+
+	if (uptodate && !PageError(page))
+		SetPageUptodate(page);
+}
+
+static void
+iomap_read_finish(struct iomap_page *iop, struct page *page)
+{
+	if (!iop || atomic_dec_and_test(&iop->read_count))
+		unlock_page(page);
+}
+
+static void
+iomap_read_page_end_io(struct bio_vec *bvec, int error)
+{
+	struct page *page = bvec->bv_page;
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (unlikely(error)) {
+		ClearPageUptodate(page);
+		SetPageError(page);
+	} else {
+		iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len);
+	}
+
+	iomap_read_finish(iop, page);
+}
+
+static void
+iomap_read_inline_data(struct inode *inode, struct page *page,
+		struct iomap *iomap)
+{
+	size_t size = i_size_read(inode);
+	void *addr;
+
+	if (PageUptodate(page))
+		return;
+
+	BUG_ON(page->index);
+	BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data));
+
+	addr = kmap_atomic(page);
+	memcpy(addr, iomap->inline_data, size);
+	memset(addr + size, 0, PAGE_SIZE - size);
+	kunmap_atomic(addr);
+	SetPageUptodate(page);
+}
+
+static void
+iomap_read_end_io(struct bio *bio)
+{
+	int error = blk_status_to_errno(bio->bi_status);
+	struct bio_vec *bvec;
+	int i;
+
+	bio_for_each_segment_all(bvec, bio, i)
+		iomap_read_page_end_io(bvec, error);
+	bio_put(bio);
+}
+
+struct iomap_readpage_ctx {
+	struct page		*cur_page;
+	bool			cur_page_in_bio;
+	bool			is_readahead;
+	struct bio		*bio;
+	struct list_head	*pages;
+};
+
+static loff_t
+iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
+		struct iomap *iomap)
+{
+	struct iomap_readpage_ctx *ctx = data;
+	struct page *page = ctx->cur_page;
+	struct iomap_page *iop = iomap_page_create(inode, page);
+	bool is_contig = false;
+	loff_t orig_pos = pos;
+	unsigned poff, plen;
+	sector_t sector;
+
+	if (iomap->type == IOMAP_INLINE) {
+		WARN_ON_ONCE(poff);
+		iomap_read_inline_data(inode, page, iomap);
+		return PAGE_SIZE;
+	}
+
+	/* zero post-eof blocks as the page may be mapped */
+	iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen);
+	if (plen == 0)
+		goto done;
+
+	if (iomap->type != IOMAP_MAPPED || pos >= i_size_read(inode)) {
+		zero_user(page, poff, plen);
+		iomap_set_range_uptodate(page, poff, plen);
+		goto done;
+	}
+
+	ctx->cur_page_in_bio = true;
+
+	/*
+	 * Try to merge into a previous segment if we can.
+	 */
+	sector = iomap_sector(iomap, pos);
+	if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
+		if (__bio_try_merge_page(ctx->bio, page, plen, poff))
+			goto done;
+		is_contig = true;
+	}
+
+	/*
+	 * If we start a new segment we need to increase the read count, and we
+	 * need to do so before submitting any previous full bio to make sure
+	 * that we don't prematurely unlock the page.
+	 */
+	if (iop)
+		atomic_inc(&iop->read_count);
+
+	if (!ctx->bio || !is_contig || bio_full(ctx->bio)) {
+		gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
+		int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+		if (ctx->bio)
+			submit_bio(ctx->bio);
+
+		if (ctx->is_readahead) /* same as readahead_gfp_mask */
+			gfp |= __GFP_NORETRY | __GFP_NOWARN;
+		ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs));
+		ctx->bio->bi_opf = REQ_OP_READ;
+		if (ctx->is_readahead)
+			ctx->bio->bi_opf |= REQ_RAHEAD;
+		ctx->bio->bi_iter.bi_sector = sector;
+		bio_set_dev(ctx->bio, iomap->bdev);
+		ctx->bio->bi_end_io = iomap_read_end_io;
+	}
+
+	__bio_add_page(ctx->bio, page, plen, poff);
+done:
+	/*
+	 * Move the caller beyond our range so that it keeps making progress.
+	 * For that we have to include any leading non-uptodate ranges, but
+	 * we can skip trailing ones as they will be handled in the next
+	 * iteration.
+	 */
+	return pos - orig_pos + plen;
+}
+
+int
+iomap_readpage(struct page *page, const struct iomap_ops *ops)
+{
+	struct iomap_readpage_ctx ctx = { .cur_page = page };
+	struct inode *inode = page->mapping->host;
+	unsigned poff;
+	loff_t ret;
+
+	for (poff = 0; poff < PAGE_SIZE; poff += ret) {
+		ret = iomap_apply(inode, page_offset(page) + poff,
+				PAGE_SIZE - poff, 0, ops, &ctx,
+				iomap_readpage_actor);
+		if (ret <= 0) {
+			WARN_ON_ONCE(ret == 0);
+			SetPageError(page);
+			break;
+		}
+	}
+
+	if (ctx.bio) {
+		submit_bio(ctx.bio);
+		WARN_ON_ONCE(!ctx.cur_page_in_bio);
+	} else {
+		WARN_ON_ONCE(ctx.cur_page_in_bio);
+		unlock_page(page);
+	}
+
+	/*
+	 * Just like mpage_readpages and block_read_full_page we always
+	 * return 0 and just mark the page as PageError on errors.  This
+	 * should be cleaned up all through the stack eventually.
+	 */
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_readpage);
+
+static struct page *
+iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos,
+		loff_t length, loff_t *done)
+{
+	while (!list_empty(pages)) {
+		struct page *page = lru_to_page(pages);
+
+		if (page_offset(page) >= (u64)pos + length)
+			break;
+
+		list_del(&page->lru);
+		if (!add_to_page_cache_lru(page, inode->i_mapping, page->index,
+				GFP_NOFS))
+			return page;
+
+		/*
+		 * If we already have a page in the page cache at index we are
+		 * done.  Upper layers don't care if it is uptodate after the
+		 * readpages call itself as every page gets checked again once
+		 * actually needed.
+		 */
+		*done += PAGE_SIZE;
+		put_page(page);
+	}
+
+	return NULL;
+}
+
+static loff_t
+iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
+		void *data, struct iomap *iomap)
+{
+	struct iomap_readpage_ctx *ctx = data;
+	loff_t done, ret;
+
+	for (done = 0; done < length; done += ret) {
+		if (ctx->cur_page && offset_in_page(pos + done) == 0) {
+			if (!ctx->cur_page_in_bio)
+				unlock_page(ctx->cur_page);
+			put_page(ctx->cur_page);
+			ctx->cur_page = NULL;
+		}
+		if (!ctx->cur_page) {
+			ctx->cur_page = iomap_next_page(inode, ctx->pages,
+					pos, length, &done);
+			if (!ctx->cur_page)
+				break;
+			ctx->cur_page_in_bio = false;
+		}
+		ret = iomap_readpage_actor(inode, pos + done, length - done,
+				ctx, iomap);
+	}
+
+	return done;
+}
+
+int
+iomap_readpages(struct address_space *mapping, struct list_head *pages,
+		unsigned nr_pages, const struct iomap_ops *ops)
+{
+	struct iomap_readpage_ctx ctx = {
+		.pages		= pages,
+		.is_readahead	= true,
+	};
+	loff_t pos = page_offset(list_entry(pages->prev, struct page, lru));
+	loff_t last = page_offset(list_entry(pages->next, struct page, lru));
+	loff_t length = last - pos + PAGE_SIZE, ret = 0;
+
+	while (length > 0) {
+		ret = iomap_apply(mapping->host, pos, length, 0, ops,
+				&ctx, iomap_readpages_actor);
+		if (ret <= 0) {
+			WARN_ON_ONCE(ret == 0);
+			goto done;
+		}
+		pos += ret;
+		length -= ret;
+	}
+	ret = 0;
+done:
+	if (ctx.bio)
+		submit_bio(ctx.bio);
+	if (ctx.cur_page) {
+		if (!ctx.cur_page_in_bio)
+			unlock_page(ctx.cur_page);
+		put_page(ctx.cur_page);
+	}
+
+	/*
+	 * Check that we didn't lose a page due to the arcance calling
+	 * conventions..
+	 */
+	WARN_ON_ONCE(!ret && !list_empty(ctx.pages));
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iomap_readpages);
+
+int
+iomap_is_partially_uptodate(struct page *page, unsigned long from,
+		unsigned long count)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+	struct inode *inode = page->mapping->host;
+	unsigned first = from >> inode->i_blkbits;
+	unsigned last = (from + count - 1) >> inode->i_blkbits;
+	unsigned i;
+
+	if (iop) {
+		for (i = first; i <= last; i++)
+			if (!test_bit(i, iop->uptodate))
+				return 0;
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
+
+int
+iomap_releasepage(struct page *page, gfp_t gfp_mask)
+{
+	/*
+	 * mm accommodates an old ext3 case where clean pages might not have had
+	 * the dirty bit cleared. Thus, it can send actual dirty pages to
+	 * ->releasepage() via shrink_active_list(), skip those here.
+	 */
+	if (PageDirty(page) || PageWriteback(page))
+		return 0;
+	iomap_page_release(page);
+	return 1;
+}
+EXPORT_SYMBOL_GPL(iomap_releasepage);
+
+void
+iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len)
+{
+	/*
+	 * If we are invalidating the entire page, clear the dirty state from it
+	 * and release it to avoid unnecessary buildup of the LRU.
+	 */
+	if (offset == 0 && len == PAGE_SIZE) {
+		WARN_ON_ONCE(PageWriteback(page));
+		cancel_dirty_page(page);
+		iomap_page_release(page);
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_invalidatepage);
+
+#ifdef CONFIG_MIGRATION
+int
+iomap_migrate_page(struct address_space *mapping, struct page *newpage,
+		struct page *page, enum migrate_mode mode)
+{
+	int ret;
+
+	ret = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
+	if (ret != MIGRATEPAGE_SUCCESS)
+		return ret;
+
+	if (page_has_private(page)) {
+		ClearPagePrivate(page);
+		set_page_private(newpage, page_private(page));
+		set_page_private(page, 0);
+		SetPagePrivate(newpage);
+	}
+
+	if (mode != MIGRATE_SYNC_NO_COPY)
+		migrate_page_copy(newpage, page);
+	else
+		migrate_page_states(newpage, page);
+	return MIGRATEPAGE_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(iomap_migrate_page);
+#endif /* CONFIG_MIGRATION */
+
 static void
 iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 {
@@ -117,6 +580,61 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 }
 
 static int
+iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page,
+		unsigned poff, unsigned plen, unsigned from, unsigned to,
+		struct iomap *iomap)
+{
+	struct bio_vec bvec;
+	struct bio bio;
+
+	if (iomap->type != IOMAP_MAPPED || block_start >= i_size_read(inode)) {
+		zero_user_segments(page, poff, from, to, poff + plen);
+		iomap_set_range_uptodate(page, poff, plen);
+		return 0;
+	}
+
+	bio_init(&bio, &bvec, 1);
+	bio.bi_opf = REQ_OP_READ;
+	bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
+	bio_set_dev(&bio, iomap->bdev);
+	__bio_add_page(&bio, page, plen, poff);
+	return submit_bio_wait(&bio);
+}
+
+static int
+__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
+		struct page *page, struct iomap *iomap)
+{
+	struct iomap_page *iop = iomap_page_create(inode, page);
+	loff_t block_size = i_blocksize(inode);
+	loff_t block_start = pos & ~(block_size - 1);
+	loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
+	unsigned from = offset_in_page(pos), to = from + len, poff, plen;
+	int status = 0;
+
+	if (PageUptodate(page))
+		return 0;
+
+	do {
+		iomap_adjust_read_range(inode, iop, &block_start,
+				block_end - block_start, &poff, &plen);
+		if (plen == 0)
+			break;
+
+		if ((from > poff && from < poff + plen) ||
+		    (to > poff && to < poff + plen)) {
+			status = iomap_read_page_sync(inode, block_start, page,
+					poff, plen, from, to, iomap);
+			if (status)
+				break;
+		}
+
+	} while ((block_start += plen) < block_end);
+
+	return status;
+}
+
+static int
 iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, struct iomap *iomap)
 {
@@ -133,7 +651,12 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	if (!page)
 		return -ENOMEM;
 
-	status = __block_write_begin_int(page, pos, len, NULL, iomap);
+	if (iomap->type == IOMAP_INLINE)
+		iomap_read_inline_data(inode, page, iomap);
+	else if (iomap->flags & IOMAP_F_BUFFER_HEAD)
+		status = __block_write_begin_int(page, pos, len, NULL, iomap);
+	else
+		status = __iomap_write_begin(inode, pos, len, page, iomap);
 	if (unlikely(status)) {
 		unlock_page(page);
 		put_page(page);
@@ -146,14 +669,93 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	return status;
 }
 
+int
+iomap_set_page_dirty(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	int newly_dirty;
+
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	/*
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
+	 */
+	lock_page_memcg(page);
+	newly_dirty = !TestSetPageDirty(page);
+	if (newly_dirty)
+		__set_page_dirty(page, mapping, 0);
+	unlock_page_memcg(page);
+
+	if (newly_dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	return newly_dirty;
+}
+EXPORT_SYMBOL_GPL(iomap_set_page_dirty);
+
+static int
+__iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
+		unsigned copied, struct page *page, struct iomap *iomap)
+{
+	flush_dcache_page(page);
+
+	/*
+	 * The blocks that were entirely written will now be uptodate, so we
+	 * don't have to worry about a readpage reading them and overwriting a
+	 * partial write.  However if we have encountered a short write and only
+	 * partially written into a block, it will not be marked uptodate, so a
+	 * readpage might come in and destroy our partial write.
+	 *
+	 * Do the simplest thing, and just treat any short write to a non
+	 * uptodate page as a zero-length write, and force the caller to redo
+	 * the whole thing.
+	 */
+	if (unlikely(copied < len && !PageUptodate(page))) {
+		copied = 0;
+	} else {
+		iomap_set_range_uptodate(page, offset_in_page(pos), len);
+		iomap_set_page_dirty(page);
+	}
+	return __generic_write_end(inode, pos, copied, page);
+}
+
+static int
+iomap_write_end_inline(struct inode *inode, struct page *page,
+		struct iomap *iomap, loff_t pos, unsigned copied)
+{
+	void *addr;
+
+	WARN_ON_ONCE(!PageUptodate(page));
+	BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data));
+
+	addr = kmap_atomic(page);
+	memcpy(iomap->inline_data + pos, addr + pos, copied);
+	kunmap_atomic(addr);
+
+	mark_inode_dirty(inode);
+	__generic_write_end(inode, pos, copied, page);
+	return copied;
+}
+
 static int
 iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
-		unsigned copied, struct page *page)
+		unsigned copied, struct page *page, struct iomap *iomap)
 {
 	int ret;
 
-	ret = generic_write_end(NULL, inode->i_mapping, pos, len,
-			copied, page, NULL);
+	if (iomap->type == IOMAP_INLINE) {
+		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
+	} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
+		ret = generic_write_end(NULL, inode->i_mapping, pos, len,
+				copied, page, NULL);
+	} else {
+		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
+	}
+
+	if (iomap->page_done)
+		iomap->page_done(inode, pos, copied, page, iomap);
+
 	if (ret < len)
 		iomap_write_failed(inode, pos, len);
 	return ret;
@@ -174,7 +776,7 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		unsigned long bytes;	/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 
-		offset = (pos & (PAGE_SIZE - 1));
+		offset = offset_in_page(pos);
 		bytes = min_t(unsigned long, PAGE_SIZE - offset,
 						iov_iter_count(i));
 again:
@@ -208,7 +810,8 @@ again:
 
 		flush_dcache_page(page);
 
-		status = iomap_write_end(inode, pos, bytes, copied, page);
+		status = iomap_write_end(inode, pos, bytes, copied, page,
+				iomap);
 		if (unlikely(status < 0))
 			break;
 		copied = status;
@@ -287,7 +890,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		unsigned long offset;	/* Offset into pagecache page */
 		unsigned long bytes;	/* Bytes to write to page */
 
-		offset = (pos & (PAGE_SIZE - 1));
+		offset = offset_in_page(pos);
 		bytes = min_t(loff_t, PAGE_SIZE - offset, length);
 
 		rpage = __iomap_read_page(inode, pos);
@@ -302,7 +905,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 
 		WARN_ON_ONCE(!PageUptodate(page));
 
-		status = iomap_write_end(inode, pos, bytes, bytes, page);
+		status = iomap_write_end(inode, pos, bytes, bytes, page, iomap);
 		if (unlikely(status <= 0)) {
 			if (WARN_ON_ONCE(status == 0))
 				return -EIO;
@@ -354,7 +957,7 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 	zero_user(page, offset, bytes);
 	mark_page_accessed(page);
 
-	return iomap_write_end(inode, pos, bytes, bytes, page);
+	return iomap_write_end(inode, pos, bytes, bytes, page, iomap);
 }
 
 static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
@@ -379,7 +982,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 	do {
 		unsigned offset, bytes;
 
-		offset = pos & (PAGE_SIZE - 1); /* Within page */
+		offset = offset_in_page(pos);
 		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
 
 		if (IS_DAX(inode))
@@ -440,11 +1043,16 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct page *page = data;
 	int ret;
 
-	ret = __block_write_begin_int(page, pos, length, NULL, iomap);
-	if (ret)
-		return ret;
+	if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
+		ret = __block_write_begin_int(page, pos, length, NULL, iomap);
+		if (ret)
+			return ret;
+		block_commit_write(page, 0, length);
+	} else {
+		WARN_ON_ONCE(!PageUptodate(page));
+		iomap_page_create(inode, page);
+	}
 
-	block_commit_write(page, 0, length);
 	return length;
 }
 
@@ -467,7 +1075,7 @@ int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 
 	/* page is wholly or partially inside EOF */
 	if (((page->index + 1) << PAGE_SHIFT) > size)
-		length = size & ~PAGE_MASK;
+		length = offset_in_page(size);
 	else
 		length = PAGE_SIZE;
 
@@ -630,7 +1238,7 @@ page_seek_hole_data(struct inode *inode, struct page *page, loff_t *lastoff,
 		goto out_unlock_not_found;
 
 	for (off = 0; off < PAGE_SIZE; off += bsize) {
-		if ((*lastoff & ~PAGE_MASK) >= off + bsize)
+		if (offset_in_page(*lastoff) >= off + bsize)
 			continue;
 		if (ops->is_partially_uptodate(page, off, bsize) == seek_data) {
 			unlock_page(page);
@@ -811,6 +1419,7 @@ struct iomap_dio {
 	atomic_t		ref;
 	unsigned		flags;
 	int			error;
+	bool			wait_for_completion;
 
 	union {
 		/* used during submission and for synchronous completion: */
@@ -914,9 +1523,8 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 		iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status));
 
 	if (atomic_dec_and_test(&dio->ref)) {
-		if (is_sync_kiocb(dio->iocb)) {
+		if (dio->wait_for_completion) {
 			struct task_struct *waiter = dio->submit.waiter;
-
 			WRITE_ONCE(dio->submit.waiter, NULL);
 			wake_up_process(waiter);
 		} else if (dio->flags & IOMAP_DIO_WRITE) {
@@ -963,10 +1571,9 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 }
 
 static loff_t
-iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
-		void *data, struct iomap *iomap)
+iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
+		struct iomap_dio *dio, struct iomap *iomap)
 {
-	struct iomap_dio *dio = data;
 	unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
 	unsigned int fs_block_size = i_blocksize(inode), pad;
 	unsigned int align = iov_iter_alignment(dio->submit.iter);
@@ -980,41 +1587,27 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	if ((pos | length | align) & ((1 << blkbits) - 1))
 		return -EINVAL;
 
-	switch (iomap->type) {
-	case IOMAP_HOLE:
-		if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE))
-			return -EIO;
-		/*FALLTHRU*/
-	case IOMAP_UNWRITTEN:
-		if (!(dio->flags & IOMAP_DIO_WRITE)) {
-			length = iov_iter_zero(length, dio->submit.iter);
-			dio->size += length;
-			return length;
-		}
+	if (iomap->type == IOMAP_UNWRITTEN) {
 		dio->flags |= IOMAP_DIO_UNWRITTEN;
 		need_zeroout = true;
-		break;
-	case IOMAP_MAPPED:
-		if (iomap->flags & IOMAP_F_SHARED)
-			dio->flags |= IOMAP_DIO_COW;
-		if (iomap->flags & IOMAP_F_NEW) {
-			need_zeroout = true;
-		} else {
-			/*
-			 * Use a FUA write if we need datasync semantics, this
-			 * is a pure data IO that doesn't require any metadata
-			 * updates and the underlying device supports FUA. This
-			 * allows us to avoid cache flushes on IO completion.
-			 */
-			if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
-			    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
-			    blk_queue_fua(bdev_get_queue(iomap->bdev)))
-				use_fua = true;
-		}
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return -EIO;
+	}
+
+	if (iomap->flags & IOMAP_F_SHARED)
+		dio->flags |= IOMAP_DIO_COW;
+
+	if (iomap->flags & IOMAP_F_NEW) {
+		need_zeroout = true;
+	} else {
+		/*
+		 * Use a FUA write if we need datasync semantics, this
+		 * is a pure data IO that doesn't require any metadata
+		 * updates and the underlying device supports FUA. This
+		 * allows us to avoid cache flushes on IO completion.
+		 */
+		if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
+		    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
+		    blk_queue_fua(bdev_get_queue(iomap->bdev)))
+			use_fua = true;
 	}
 
 	/*
@@ -1093,6 +1686,66 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	return copied;
 }
 
+static loff_t
+iomap_dio_hole_actor(loff_t length, struct iomap_dio *dio)
+{
+	length = iov_iter_zero(length, dio->submit.iter);
+	dio->size += length;
+	return length;
+}
+
+static loff_t
+iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length,
+		struct iomap_dio *dio, struct iomap *iomap)
+{
+	struct iov_iter *iter = dio->submit.iter;
+	size_t copied;
+
+	BUG_ON(pos + length > PAGE_SIZE - offset_in_page(iomap->inline_data));
+
+	if (dio->flags & IOMAP_DIO_WRITE) {
+		loff_t size = inode->i_size;
+
+		if (pos > size)
+			memset(iomap->inline_data + size, 0, pos - size);
+		copied = copy_from_iter(iomap->inline_data + pos, length, iter);
+		if (copied) {
+			if (pos + copied > size)
+				i_size_write(inode, pos + copied);
+			mark_inode_dirty(inode);
+		}
+	} else {
+		copied = copy_to_iter(iomap->inline_data + pos, length, iter);
+	}
+	dio->size += copied;
+	return copied;
+}
+
+static loff_t
+iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
+		void *data, struct iomap *iomap)
+{
+	struct iomap_dio *dio = data;
+
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE))
+			return -EIO;
+		return iomap_dio_hole_actor(length, dio);
+	case IOMAP_UNWRITTEN:
+		if (!(dio->flags & IOMAP_DIO_WRITE))
+			return iomap_dio_hole_actor(length, dio);
+		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
+	case IOMAP_MAPPED:
+		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
+	case IOMAP_INLINE:
+		return iomap_dio_inline_actor(inode, pos, length, dio, iomap);
+	default:
+		WARN_ON_ONCE(1);
+		return -EIO;
+	}
+}
+
 /*
  * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO
  * is being issued as AIO or not.  This allows us to optimise pure data writes
@@ -1131,13 +1784,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->end_io = end_io;
 	dio->error = 0;
 	dio->flags = 0;
+	dio->wait_for_completion = is_sync_kiocb(iocb);
 
 	dio->submit.iter = iter;
-	if (is_sync_kiocb(iocb)) {
-		dio->submit.waiter = current;
-		dio->submit.cookie = BLK_QC_T_NONE;
-		dio->submit.last_queue = NULL;
-	}
+	dio->submit.waiter = current;
+	dio->submit.cookie = BLK_QC_T_NONE;
+	dio->submit.last_queue = NULL;
 
 	if (iov_iter_rw(iter) == READ) {
 		if (pos >= dio->i_size)
@@ -1187,7 +1839,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		dio_warn_stale_pagecache(iocb->ki_filp);
 	ret = 0;
 
-	if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
+	if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
 	    !inode->i_sb->s_dio_done_wq) {
 		ret = sb_init_dio_done_wq(inode->i_sb);
 		if (ret < 0)
@@ -1202,8 +1854,10 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 				iomap_dio_actor);
 		if (ret <= 0) {
 			/* magic error code to fall back to buffered I/O */
-			if (ret == -ENOTBLK)
+			if (ret == -ENOTBLK) {
+				dio->wait_for_completion = true;
 				ret = 0;
+			}
 			break;
 		}
 		pos += ret;
@@ -1224,7 +1878,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
 
 	if (!atomic_dec_and_test(&dio->ref)) {
-		if (!is_sync_kiocb(iocb))
+		if (!dio->wait_for_completion)
 			return -EIOCBQUEUED;
 
 		for (;;) {
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8de0e7723316..150cc030b4d7 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -121,7 +121,7 @@ static int journal_submit_commit_record(journal_t *journal,
 	struct commit_header *tmp;
 	struct buffer_head *bh;
 	int ret;
-	struct timespec64 now = current_kernel_time64();
+	struct timespec64 now;
 
 	*cbh = NULL;
 
@@ -134,6 +134,7 @@ static int journal_submit_commit_record(journal_t *journal,
 		return 1;
 
 	tmp = (struct commit_header *)bh->b_data;
+	ktime_get_coarse_real_ts64(&now);
 	tmp->h_commit_sec = cpu_to_be64(now.tv_sec);
 	tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec);
 
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index b2944f9218f7..f20cff1194bb 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -201,7 +201,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
 	if (ret)
 		goto fail;
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(ri->ctime));
 
 	jffs2_free_raw_inode(ri);
 
@@ -227,14 +227,14 @@ static int jffs2_unlink(struct inode *dir_i, struct dentry *dentry)
 	struct jffs2_inode_info *dir_f = JFFS2_INODE_INFO(dir_i);
 	struct jffs2_inode_info *dead_f = JFFS2_INODE_INFO(d_inode(dentry));
 	int ret;
-	uint32_t now = get_seconds();
+	uint32_t now = JFFS2_NOW();
 
 	ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name,
 			      dentry->d_name.len, dead_f, now);
 	if (dead_f->inocache)
 		set_nlink(d_inode(dentry), dead_f->inocache->pino_nlink);
 	if (!ret)
-		dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
 	return ret;
 }
 /***********************************************************************/
@@ -260,7 +260,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de
 	type = (d_inode(old_dentry)->i_mode & S_IFMT) >> 12;
 	if (!type) type = DT_REG;
 
-	now = get_seconds();
+	now = JFFS2_NOW();
 	ret = jffs2_do_link(c, dir_f, f->inocache->ino, type, dentry->d_name.name, dentry->d_name.len, now);
 
 	if (!ret) {
@@ -268,7 +268,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de
 		set_nlink(d_inode(old_dentry), ++f->inocache->pino_nlink);
 		mutex_unlock(&f->sem);
 		d_instantiate(dentry, d_inode(old_dentry));
-		dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
 		ihold(d_inode(old_dentry));
 	}
 	return ret;
@@ -400,7 +400,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 	rd->pino = cpu_to_je32(dir_i->i_ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = cpu_to_je32(inode->i_ino);
-	rd->mctime = cpu_to_je32(get_seconds());
+	rd->mctime = cpu_to_je32(JFFS2_NOW());
 	rd->nsize = namelen;
 	rd->type = DT_LNK;
 	rd->node_crc = cpu_to_je32(crc32(0, rd, sizeof(*rd)-8));
@@ -418,7 +418,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 		goto fail;
 	}
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
 
 	jffs2_free_raw_dirent(rd);
 
@@ -543,7 +543,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	rd->pino = cpu_to_je32(dir_i->i_ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = cpu_to_je32(inode->i_ino);
-	rd->mctime = cpu_to_je32(get_seconds());
+	rd->mctime = cpu_to_je32(JFFS2_NOW());
 	rd->nsize = namelen;
 	rd->type = DT_DIR;
 	rd->node_crc = cpu_to_je32(crc32(0, rd, sizeof(*rd)-8));
@@ -561,7 +561,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
 		goto fail;
 	}
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
 	inc_nlink(dir_i);
 
 	jffs2_free_raw_dirent(rd);
@@ -588,7 +588,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(d_inode(dentry));
 	struct jffs2_full_dirent *fd;
 	int ret;
-	uint32_t now = get_seconds();
+	uint32_t now = JFFS2_NOW();
 
 	for (fd = f->dents ; fd; fd = fd->next) {
 		if (fd->ino)
@@ -598,7 +598,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
 	ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name,
 			      dentry->d_name.len, f, now);
 	if (!ret) {
-		dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
 		clear_nlink(d_inode(dentry));
 		drop_nlink(dir_i);
 	}
@@ -712,7 +712,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	rd->pino = cpu_to_je32(dir_i->i_ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = cpu_to_je32(inode->i_ino);
-	rd->mctime = cpu_to_je32(get_seconds());
+	rd->mctime = cpu_to_je32(JFFS2_NOW());
 	rd->nsize = namelen;
 
 	/* XXX: This is ugly. */
@@ -733,7 +733,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
 		goto fail;
 	}
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
 
 	jffs2_free_raw_dirent(rd);
 
@@ -797,7 +797,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 	type = (d_inode(old_dentry)->i_mode & S_IFMT) >> 12;
 	if (!type) type = DT_REG;
 
-	now = get_seconds();
+	now = JFFS2_NOW();
 	ret = jffs2_do_link(c, JFFS2_INODE_INFO(new_dir_i),
 			    d_inode(old_dentry)->i_ino, type,
 			    new_dentry->d_name.name, new_dentry->d_name.len, now);
@@ -853,14 +853,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 		 * caller won't do it on its own since we are returning an error.
 		 */
 		d_invalidate(new_dentry);
-		new_dir_i->i_mtime = new_dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
 		return ret;
 	}
 
 	if (d_is_dir(old_dentry))
 		drop_nlink(old_dir_i);
 
-	new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+	new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = ITIME(now);
 
 	return 0;
 }
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 481afd4c2e1a..7d8654a1472e 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -175,7 +175,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		ri.uid = cpu_to_je16(i_uid_read(inode));
 		ri.gid = cpu_to_je16(i_gid_read(inode));
 		ri.isize = cpu_to_je32(max((uint32_t)inode->i_size, pageofs));
-		ri.atime = ri.ctime = ri.mtime = cpu_to_je32(get_seconds());
+		ri.atime = ri.ctime = ri.mtime = cpu_to_je32(JFFS2_NOW());
 		ri.offset = cpu_to_je32(inode->i_size);
 		ri.dsize = cpu_to_je32(pageofs - inode->i_size);
 		ri.csize = cpu_to_je32(0);
@@ -283,7 +283,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	ri->uid = cpu_to_je16(i_uid_read(inode));
 	ri->gid = cpu_to_je16(i_gid_read(inode));
 	ri->isize = cpu_to_je32((uint32_t)inode->i_size);
-	ri->atime = ri->ctime = ri->mtime = cpu_to_je32(get_seconds());
+	ri->atime = ri->ctime = ri->mtime = cpu_to_je32(JFFS2_NOW());
 
 	/* In 2.4, it was already kmapped by generic_file_write(). Doesn't
 	   hurt to do it again. The alternative is ifdefs, which are ugly. */
@@ -308,7 +308,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 			inode->i_size = pos + writtenlen;
 			inode->i_blocks = (inode->i_size + 511) >> 9;
 
-			inode->i_ctime = inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
+			inode->i_ctime = inode->i_mtime = ITIME(je32_to_cpu(ri->ctime));
 		}
 	}
 
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 0ecfb8ea38cd..eab04eca95a3 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -146,9 +146,9 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr)
 		return PTR_ERR(new_metadata);
 	}
 	/* It worked. Update the inode */
-	inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->atime)));
-	inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
-	inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->mtime)));
+	inode->i_atime = ITIME(je32_to_cpu(ri->atime));
+	inode->i_ctime = ITIME(je32_to_cpu(ri->ctime));
+	inode->i_mtime = ITIME(je32_to_cpu(ri->mtime));
 	inode->i_mode = jemode_to_cpu(ri->mode);
 	i_uid_write(inode, je16_to_cpu(ri->uid));
 	i_gid_write(inode, je16_to_cpu(ri->gid));
@@ -280,9 +280,9 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino)
 	i_uid_write(inode, je16_to_cpu(latest_node.uid));
 	i_gid_write(inode, je16_to_cpu(latest_node.gid));
 	inode->i_size = je32_to_cpu(latest_node.isize);
-	inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.atime)));
-	inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.mtime)));
-	inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.ctime)));
+	inode->i_atime = ITIME(je32_to_cpu(latest_node.atime));
+	inode->i_mtime = ITIME(je32_to_cpu(latest_node.mtime));
+	inode->i_ctime = ITIME(je32_to_cpu(latest_node.ctime));
 
 	set_nlink(inode, f->inocache->pino_nlink);
 
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index c2fbec19c616..a2dbbb3f4c74 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -31,12 +31,13 @@ struct kvec;
 #define JFFS2_F_I_GID(f) (i_gid_read(OFNI_EDONI_2SFFJ(f)))
 #define JFFS2_F_I_RDEV(f) (OFNI_EDONI_2SFFJ(f)->i_rdev)
 
-#define ITIME(sec) ((struct timespec){sec, 0})
-#define I_SEC(tv) ((tv).tv_sec)
-#define JFFS2_F_I_CTIME(f) (OFNI_EDONI_2SFFJ(f)->i_ctime.tv_sec)
-#define JFFS2_F_I_MTIME(f) (OFNI_EDONI_2SFFJ(f)->i_mtime.tv_sec)
-#define JFFS2_F_I_ATIME(f) (OFNI_EDONI_2SFFJ(f)->i_atime.tv_sec)
-
+#define JFFS2_CLAMP_TIME(t) ((uint32_t)clamp_t(time64_t, (t), 0, U32_MAX))
+#define ITIME(sec) ((struct timespec64){sec, 0})
+#define JFFS2_NOW() JFFS2_CLAMP_TIME(ktime_get_real_seconds())
+#define I_SEC(tv) JFFS2_CLAMP_TIME((tv).tv_sec)
+#define JFFS2_F_I_CTIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_ctime)
+#define JFFS2_F_I_MTIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_mtime)
+#define JFFS2_F_I_ATIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_atime)
 #define sleep_on_spinunlock(wq, s)				\
 	do {							\
 		DECLARE_WAITQUEUE(__wait, current);		\
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index f36ef68905a7..93e8c590ff5c 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -491,13 +491,7 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary)
 	/* release the page */
 	release_metapage(mp);
 
-	/*
-	 * __mark_inode_dirty expects inodes to be hashed.  Since we don't
-	 * want special inodes in the fileset inode space, we make them
-	 * appear hashed, but do not put on any lists.  hlist_del()
-	 * will work fine and require no locking.
-	 */
-	hlist_add_fake(&ip->i_hash);
+	inode_fake_hash(ip);
 
 	return (ip);
 }
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index 5e9b7bb3aabf..4572b7cf183d 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -61,8 +61,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
 	inode = new_inode(sb);
 	if (!inode) {
 		jfs_warn("ialloc: new_inode returned NULL!");
-		rc = -ENOMEM;
-		goto fail;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	jfs_inode = JFS_IP(inode);
@@ -70,8 +69,6 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
 	rc = diAlloc(parent, S_ISDIR(mode), inode);
 	if (rc) {
 		jfs_warn("ialloc: diAlloc returned %d!", rc);
-		if (rc == -EIO)
-			make_bad_inode(inode);
 		goto fail_put;
 	}
 
@@ -141,9 +138,10 @@ fail_drop:
 	dquot_drop(inode);
 	inode->i_flags |= S_NOQUOTA;
 	clear_nlink(inode);
-	unlock_new_inode(inode);
+	discard_new_inode(inode);
+	return ERR_PTR(rc);
+
 fail_put:
 	iput(inode);
-fail:
 	return ERR_PTR(rc);
 }
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 56c3fcbfe80e..14528c0ffe63 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -175,8 +175,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
@@ -309,8 +308,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
@@ -1054,8 +1052,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
@@ -1441,8 +1438,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index f08571433aba..09da5cf14e27 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -581,7 +581,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 	inode->i_ino = 0;
 	inode->i_size = i_size_read(sb->s_bdev->bd_inode);
 	inode->i_mapping->a_ops = &jfs_metapage_aops;
-	hlist_add_fake(&inode->i_hash);
+	inode_fake_hash(inode);
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 
 	sbi->direct_inode = inode;
diff --git a/fs/locks.c b/fs/locks.c
index db7b6917d9c5..bc047a7edc47 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -202,10 +202,6 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);
  * we often hold the flc_lock as well. In certain cases, when reading the fields
  * protected by this lock, we can skip acquiring it iff we already hold the
  * flc_lock.
- *
- * In particular, adding an entry to the fl_block list requires that you hold
- * both the flc_lock and the blocked_lock_lock (acquired in that order).
- * Deleting an entry from the list however only requires the file_lock_lock.
  */
 static DEFINE_SPINLOCK(blocked_lock_lock);
 
@@ -990,6 +986,7 @@ out:
 	if (new_fl)
 		locks_free_lock(new_fl);
 	locks_dispose_list(&dispose);
+	trace_flock_lock_inode(inode, request, error);
 	return error;
 }
 
@@ -2072,6 +2069,13 @@ static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns)
 		return -1;
 	if (IS_REMOTELCK(fl))
 		return fl->fl_pid;
+	/*
+	 * If the flock owner process is dead and its pid has been already
+	 * freed, the translation below won't work, but we still want to show
+	 * flock owner pid number in init pidns.
+	 */
+	if (ns == &init_pid_ns)
+		return (pid_t)fl->fl_pid;
 
 	rcu_read_lock();
 	pid = find_pid_ns(fl->fl_pid, &init_pid_ns);
@@ -2626,12 +2630,10 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 
 	fl_pid = locks_translate_pid(fl, proc_pidns);
 	/*
-	 * If there isn't a fl_pid don't display who is waiting on
-	 * the lock if we are called from locks_show, or if we are
-	 * called from __show_fd_info - skip lock entirely
+	 * If lock owner is dead (and pid is freed) or not visible in current
+	 * pidns, zero is shown as a pid value. Check lock info from
+	 * init_pid_ns to get saved lock pid value.
 	 */
-	if (fl_pid == 0)
-		return;
 
 	if (fl->fl_file != NULL)
 		inode = locks_inode(fl->fl_file);
diff --git a/fs/mpage.c b/fs/mpage.c
index b7e7f570733a..b73638db9866 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -51,8 +51,8 @@ static void mpage_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-		page_endio(page, op_is_write(bio_op(bio)),
-				blk_status_to_errno(bio->bi_status));
+		page_endio(page, bio_op(bio),
+			   blk_status_to_errno(bio->bi_status));
 	}
 
 	bio_put(bio);
diff --git a/fs/namei.c b/fs/namei.c
index 734cef54fdf8..3cd396277cd3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2028,6 +2028,8 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 {
 	int err;
 
+	if (IS_ERR(name))
+		return PTR_ERR(name);
 	while (*name=='/')
 		name++;
 	if (!*name)
@@ -2125,12 +2127,15 @@ OK:
 	}
 }
 
+/* must be paired with terminate_walk() */
 static const char *path_init(struct nameidata *nd, unsigned flags)
 {
 	const char *s = nd->name->name;
 
 	if (!*s)
 		flags &= ~LOOKUP_RCU;
+	if (flags & LOOKUP_RCU)
+		rcu_read_lock();
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
@@ -2143,7 +2148,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
-			rcu_read_lock();
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			nd->root_seq = nd->seq;
 			nd->m_seq = read_seqbegin(&mount_lock);
@@ -2159,21 +2163,15 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 
 	nd->m_seq = read_seqbegin(&mount_lock);
 	if (*s == '/') {
-		if (flags & LOOKUP_RCU)
-			rcu_read_lock();
 		set_root(nd);
 		if (likely(!nd_jump_root(nd)))
 			return s;
-		nd->root.mnt = NULL;
-		rcu_read_unlock();
 		return ERR_PTR(-ECHILD);
 	} else if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
 			unsigned seq;
 
-			rcu_read_lock();
-
 			do {
 				seq = read_seqcount_begin(&fs->seq);
 				nd->path = fs->pwd;
@@ -2195,16 +2193,13 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 
 		dentry = f.file->f_path.dentry;
 
-		if (*s) {
-			if (!d_can_lookup(dentry)) {
-				fdput(f);
-				return ERR_PTR(-ENOTDIR);
-			}
+		if (*s && unlikely(!d_can_lookup(dentry))) {
+			fdput(f);
+			return ERR_PTR(-ENOTDIR);
 		}
 
 		nd->path = f.file->f_path;
 		if (flags & LOOKUP_RCU) {
-			rcu_read_lock();
 			nd->inode = nd->path.dentry->d_inode;
 			nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 		} else {
@@ -2272,24 +2267,15 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	const char *s = path_init(nd, flags);
 	int err;
 
-	if (IS_ERR(s))
-		return PTR_ERR(s);
-
-	if (unlikely(flags & LOOKUP_DOWN)) {
+	if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
 		err = handle_lookup_down(nd);
-		if (unlikely(err < 0)) {
-			terminate_walk(nd);
-			return err;
-		}
+		if (unlikely(err < 0))
+			s = ERR_PTR(err);
 	}
 
 	while (!(err = link_path_walk(s, nd))
 		&& ((err = lookup_last(nd)) > 0)) {
 		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			err = PTR_ERR(s);
-			break;
-		}
 	}
 	if (!err)
 		err = complete_walk(nd);
@@ -2336,10 +2322,7 @@ static int path_parentat(struct nameidata *nd, unsigned flags,
 				struct path *parent)
 {
 	const char *s = path_init(nd, flags);
-	int err;
-	if (IS_ERR(s))
-		return PTR_ERR(s);
-	err = link_path_walk(s, nd);
+	int err = link_path_walk(s, nd);
 	if (!err)
 		err = complete_walk(nd);
 	if (!err) {
@@ -2666,15 +2649,10 @@ path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
 {
 	const char *s = path_init(nd, flags);
 	int err;
-	if (IS_ERR(s))
-		return PTR_ERR(s);
+
 	while (!(err = link_path_walk(s, nd)) &&
 		(err = mountpoint_last(nd)) > 0) {
 		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			err = PTR_ERR(s);
-			break;
-		}
 	}
 	if (!err) {
 		*path = nd->path;
@@ -3027,17 +3005,16 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m
  * Returns 0 if successful.  The file will have been created and attached to
  * @file by the filesystem calling finish_open().
  *
- * Returns 1 if the file was looked up only or didn't need creating.  The
- * caller will need to perform the open themselves.  @path will have been
- * updated to point to the new dentry.  This may be negative.
+ * If the file was looked up only or didn't need creating, FMODE_OPENED won't
+ * be set.  The caller will need to perform the open themselves.  @path will
+ * have been updated to point to the new dentry.  This may be negative.
  *
  * Returns an error code otherwise.
  */
 static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 			struct path *path, struct file *file,
 			const struct open_flags *op,
-			int open_flag, umode_t mode,
-			int *opened)
+			int open_flag, umode_t mode)
 {
 	struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
 	struct inode *dir =  nd->path.dentry->d_inode;
@@ -3052,39 +3029,38 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 	file->f_path.dentry = DENTRY_NOT_SET;
 	file->f_path.mnt = nd->path.mnt;
 	error = dir->i_op->atomic_open(dir, dentry, file,
-				       open_to_namei_flags(open_flag),
-				       mode, opened);
+				       open_to_namei_flags(open_flag), mode);
 	d_lookup_done(dentry);
 	if (!error) {
-		/*
-		 * We didn't have the inode before the open, so check open
-		 * permission here.
-		 */
-		int acc_mode = op->acc_mode;
-		if (*opened & FILE_CREATED) {
-			WARN_ON(!(open_flag & O_CREAT));
-			fsnotify_create(dir, dentry);
-			acc_mode = 0;
-		}
-		error = may_open(&file->f_path, acc_mode, open_flag);
-		if (WARN_ON(error > 0))
-			error = -EINVAL;
-	} else if (error > 0) {
-		if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
+		if (file->f_mode & FMODE_OPENED) {
+			/*
+			 * We didn't have the inode before the open, so check open
+			 * permission here.
+			 */
+			int acc_mode = op->acc_mode;
+			if (file->f_mode & FMODE_CREATED) {
+				WARN_ON(!(open_flag & O_CREAT));
+				fsnotify_create(dir, dentry);
+				acc_mode = 0;
+			}
+			error = may_open(&file->f_path, acc_mode, open_flag);
+			if (WARN_ON(error > 0))
+				error = -EINVAL;
+		} else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
 			error = -EIO;
 		} else {
 			if (file->f_path.dentry) {
 				dput(dentry);
 				dentry = file->f_path.dentry;
 			}
-			if (*opened & FILE_CREATED)
+			if (file->f_mode & FMODE_CREATED)
 				fsnotify_create(dir, dentry);
 			if (unlikely(d_is_negative(dentry))) {
 				error = -ENOENT;
 			} else {
 				path->dentry = dentry;
 				path->mnt = nd->path.mnt;
-				return 1;
+				return 0;
 			}
 		}
 	}
@@ -3095,25 +3071,22 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 /*
  * Look up and maybe create and open the last component.
  *
- * Must be called with i_mutex held on parent.
- *
- * Returns 0 if the file was successfully atomically created (if necessary) and
- * opened.  In this case the file will be returned attached to @file.
- *
- * Returns 1 if the file was not completely opened at this time, though lookups
- * and creations will have been performed and the dentry returned in @path will
- * be positive upon return if O_CREAT was specified.  If O_CREAT wasn't
- * specified then a negative dentry may be returned.
+ * Must be called with parent locked (exclusive in O_CREAT case).
  *
- * An error code is returned otherwise.
+ * Returns 0 on success, that is, if
+ *  the file was successfully atomically created (if necessary) and opened, or
+ *  the file was not completely opened at this time, though lookups and
+ *  creations were performed.
+ * These case are distinguished by presence of FMODE_OPENED on file->f_mode.
+ * In the latter case dentry returned in @path might be negative if O_CREAT
+ * hadn't been specified.
  *
- * FILE_CREATE will be set in @*opened if the dentry was created and will be
- * cleared otherwise prior to returning.
+ * An error code is returned on failure.
  */
 static int lookup_open(struct nameidata *nd, struct path *path,
 			struct file *file,
 			const struct open_flags *op,
-			bool got_write, int *opened)
+			bool got_write)
 {
 	struct dentry *dir = nd->path.dentry;
 	struct inode *dir_inode = dir->d_inode;
@@ -3126,7 +3099,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 	if (unlikely(IS_DEADDIR(dir_inode)))
 		return -ENOENT;
 
-	*opened &= ~FILE_CREATED;
+	file->f_mode &= ~FMODE_CREATED;
 	dentry = d_lookup(dir, &nd->last);
 	for (;;) {
 		if (!dentry) {
@@ -3188,7 +3161,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 
 	if (dir_inode->i_op->atomic_open) {
 		error = atomic_open(nd, dentry, path, file, op, open_flag,
-				    mode, opened);
+				    mode);
 		if (unlikely(error == -ENOENT) && create_error)
 			error = create_error;
 		return error;
@@ -3211,7 +3184,7 @@ no_open:
 
 	/* Negative dentry, just create the file */
 	if (!dentry->d_inode && (open_flag & O_CREAT)) {
-		*opened |= FILE_CREATED;
+		file->f_mode |= FMODE_CREATED;
 		audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
 		if (!dir_inode->i_op->create) {
 			error = -EACCES;
@@ -3230,7 +3203,7 @@ no_open:
 out_no_open:
 	path->dentry = dentry;
 	path->mnt = nd->path.mnt;
-	return 1;
+	return 0;
 
 out_dput:
 	dput(dentry);
@@ -3241,8 +3214,7 @@ out_dput:
  * Handle the last step of open()
  */
 static int do_last(struct nameidata *nd,
-		   struct file *file, const struct open_flags *op,
-		   int *opened)
+		   struct file *file, const struct open_flags *op)
 {
 	struct dentry *dir = nd->path.dentry;
 	int open_flag = op->open_flag;
@@ -3308,17 +3280,17 @@ static int do_last(struct nameidata *nd,
 		inode_lock(dir->d_inode);
 	else
 		inode_lock_shared(dir->d_inode);
-	error = lookup_open(nd, &path, file, op, got_write, opened);
+	error = lookup_open(nd, &path, file, op, got_write);
 	if (open_flag & O_CREAT)
 		inode_unlock(dir->d_inode);
 	else
 		inode_unlock_shared(dir->d_inode);
 
-	if (error <= 0) {
-		if (error)
-			goto out;
+	if (error)
+		goto out;
 
-		if ((*opened & FILE_CREATED) ||
+	if (file->f_mode & FMODE_OPENED) {
+		if ((file->f_mode & FMODE_CREATED) ||
 		    !S_ISREG(file_inode(file)->i_mode))
 			will_truncate = false;
 
@@ -3326,7 +3298,7 @@ static int do_last(struct nameidata *nd,
 		goto opened;
 	}
 
-	if (*opened & FILE_CREATED) {
+	if (file->f_mode & FMODE_CREATED) {
 		/* Don't check for write permission, don't truncate */
 		open_flag &= ~O_TRUNC;
 		will_truncate = false;
@@ -3395,20 +3367,15 @@ finish_open_created:
 	error = may_open(&nd->path, acc_mode, open_flag);
 	if (error)
 		goto out;
-	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
-	error = vfs_open(&nd->path, file, current_cred());
+	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
+	error = vfs_open(&nd->path, file);
 	if (error)
 		goto out;
-	*opened |= FILE_OPENED;
 opened:
-	error = open_check_o_direct(file);
-	if (!error)
-		error = ima_file_check(file, op->acc_mode, *opened);
+	error = ima_file_check(file, op->acc_mode);
 	if (!error && will_truncate)
 		error = handle_truncate(file);
 out:
-	if (unlikely(error) && (*opened & FILE_OPENED))
-		fput(file);
 	if (unlikely(error > 0)) {
 		WARN_ON(1);
 		error = -EINVAL;
@@ -3458,7 +3425,7 @@ EXPORT_SYMBOL(vfs_tmpfile);
 
 static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		const struct open_flags *op,
-		struct file *file, int *opened)
+		struct file *file)
 {
 	struct dentry *child;
 	struct path path;
@@ -3480,12 +3447,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	if (error)
 		goto out2;
 	file->f_path.mnt = path.mnt;
-	error = finish_open(file, child, NULL, opened);
-	if (error)
-		goto out2;
-	error = open_check_o_direct(file);
-	if (error)
-		fput(file);
+	error = finish_open(file, child, NULL);
 out2:
 	mnt_drop_write(path.mnt);
 out:
@@ -3499,7 +3461,7 @@ static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
 	int error = path_lookupat(nd, flags, &path);
 	if (!error) {
 		audit_inode(nd->name, path.dentry, 0);
-		error = vfs_open(&path, file, current_cred());
+		error = vfs_open(&path, file);
 		path_put(&path);
 	}
 	return error;
@@ -3508,59 +3470,40 @@ static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
 static struct file *path_openat(struct nameidata *nd,
 			const struct open_flags *op, unsigned flags)
 {
-	const char *s;
 	struct file *file;
-	int opened = 0;
 	int error;
 
-	file = get_empty_filp();
+	file = alloc_empty_file(op->open_flag, current_cred());
 	if (IS_ERR(file))
 		return file;
 
-	file->f_flags = op->open_flag;
-
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
-		error = do_tmpfile(nd, flags, op, file, &opened);
-		goto out2;
-	}
-
-	if (unlikely(file->f_flags & O_PATH)) {
+		error = do_tmpfile(nd, flags, op, file);
+	} else if (unlikely(file->f_flags & O_PATH)) {
 		error = do_o_path(nd, flags, file);
-		if (!error)
-			opened |= FILE_OPENED;
-		goto out2;
-	}
-
-	s = path_init(nd, flags);
-	if (IS_ERR(s)) {
-		put_filp(file);
-		return ERR_CAST(s);
-	}
-	while (!(error = link_path_walk(s, nd)) &&
-		(error = do_last(nd, file, op, &opened)) > 0) {
-		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
-		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			error = PTR_ERR(s);
-			break;
+	} else {
+		const char *s = path_init(nd, flags);
+		while (!(error = link_path_walk(s, nd)) &&
+			(error = do_last(nd, file, op)) > 0) {
+			nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
+			s = trailing_symlink(nd);
 		}
+		terminate_walk(nd);
 	}
-	terminate_walk(nd);
-out2:
-	if (!(opened & FILE_OPENED)) {
-		BUG_ON(!error);
-		put_filp(file);
+	if (likely(!error)) {
+		if (likely(file->f_mode & FMODE_OPENED))
+			return file;
+		WARN_ON(1);
+		error = -EINVAL;
 	}
-	if (unlikely(error)) {
-		if (error == -EOPENSTALE) {
-			if (flags & LOOKUP_RCU)
-				error = -ECHILD;
-			else
-				error = -ESTALE;
-		}
-		file = ERR_PTR(error);
+	fput(file);
+	if (error == -EOPENSTALE) {
+		if (flags & LOOKUP_RCU)
+			error = -ECHILD;
+		else
+			error = -ESTALE;
 	}
-	return file;
+	return ERR_PTR(error);
 }
 
 struct file *do_filp_open(int dfd, struct filename *pathname,
@@ -4712,29 +4655,6 @@ out:
 	return len;
 }
 
-/*
- * A helper for ->readlink().  This should be used *ONLY* for symlinks that
- * have ->get_link() not calling nd_jump_link().  Using (or not using) it
- * for any given inode is up to filesystem.
- */
-static int generic_readlink(struct dentry *dentry, char __user *buffer,
-			    int buflen)
-{
-	DEFINE_DELAYED_CALL(done);
-	struct inode *inode = d_inode(dentry);
-	const char *link = inode->i_link;
-	int res;
-
-	if (!link) {
-		link = inode->i_op->get_link(dentry, inode, &done);
-		if (IS_ERR(link))
-			return PTR_ERR(link);
-	}
-	res = readlink_copy(buffer, buflen, link);
-	do_delayed_call(&done);
-	return res;
-}
-
 /**
  * vfs_readlink - copy symlink body into userspace buffer
  * @dentry: dentry on which to get symbolic link
@@ -4748,6 +4668,9 @@ static int generic_readlink(struct dentry *dentry, char __user *buffer,
 int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
 	struct inode *inode = d_inode(dentry);
+	DEFINE_DELAYED_CALL(done);
+	const char *link;
+	int res;
 
 	if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) {
 		if (unlikely(inode->i_op->readlink))
@@ -4761,7 +4684,15 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 		spin_unlock(&inode->i_lock);
 	}
 
-	return generic_readlink(dentry, buffer, buflen);
+	link = inode->i_link;
+	if (!link) {
+		link = inode->i_op->get_link(dentry, inode, &done);
+		if (IS_ERR(link))
+			return PTR_ERR(link);
+	}
+	res = readlink_copy(buffer, buflen, link);
+	do_delayed_call(&done);
+	return res;
 }
 EXPORT_SYMBOL(vfs_readlink);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 8ddd14806799..bd2f4c68506a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -659,12 +659,21 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
 		return 0;
 	mnt = real_mount(bastard);
 	mnt_add_count(mnt, 1);
+	smp_mb();			// see mntput_no_expire()
 	if (likely(!read_seqretry(&mount_lock, seq)))
 		return 0;
 	if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
 		mnt_add_count(mnt, -1);
 		return 1;
 	}
+	lock_mount_hash();
+	if (unlikely(bastard->mnt_flags & MNT_DOOMED)) {
+		mnt_add_count(mnt, -1);
+		unlock_mount_hash();
+		return 1;
+	}
+	unlock_mount_hash();
+	/* caller will mntput() */
 	return -1;
 }
 
@@ -1195,12 +1204,27 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
 static void mntput_no_expire(struct mount *mnt)
 {
 	rcu_read_lock();
-	mnt_add_count(mnt, -1);
-	if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */
+	if (likely(READ_ONCE(mnt->mnt_ns))) {
+		/*
+		 * Since we don't do lock_mount_hash() here,
+		 * ->mnt_ns can change under us.  However, if it's
+		 * non-NULL, then there's a reference that won't
+		 * be dropped until after an RCU delay done after
+		 * turning ->mnt_ns NULL.  So if we observe it
+		 * non-NULL under rcu_read_lock(), the reference
+		 * we are dropping is not the final one.
+		 */
+		mnt_add_count(mnt, -1);
 		rcu_read_unlock();
 		return;
 	}
 	lock_mount_hash();
+	/*
+	 * make sure that if __legitimize_mnt() has not seen us grab
+	 * mount_lock, we'll see their refcount increment here.
+	 */
+	smp_mb();
+	mnt_add_count(mnt, -1);
 	if (mnt_get_count(mnt)) {
 		rcu_read_unlock();
 		unlock_mount_hash();
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 7a9c14426855..d7f158c3efc8 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1434,12 +1434,11 @@ static int do_open(struct inode *inode, struct file *filp)
 
 static int nfs_finish_open(struct nfs_open_context *ctx,
 			   struct dentry *dentry,
-			   struct file *file, unsigned open_flags,
-			   int *opened)
+			   struct file *file, unsigned open_flags)
 {
 	int err;
 
-	err = finish_open(file, dentry, do_open, opened);
+	err = finish_open(file, dentry, do_open);
 	if (err)
 		goto out;
 	if (S_ISREG(file->f_path.dentry->d_inode->i_mode))
@@ -1452,7 +1451,7 @@ out:
 
 int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		    struct file *file, unsigned open_flags,
-		    umode_t mode, int *opened)
+		    umode_t mode)
 {
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
 	struct nfs_open_context *ctx;
@@ -1461,6 +1460,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	unsigned int lookup_flags = 0;
 	bool switched = false;
+	int created = 0;
 	int err;
 
 	/* Expect a negative dentry */
@@ -1521,7 +1521,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		goto out;
 
 	trace_nfs_atomic_open_enter(dir, ctx, open_flags);
-	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened);
+	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, &created);
+	if (created)
+		file->f_mode |= FMODE_CREATED;
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
@@ -1546,7 +1548,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
-	err = nfs_finish_open(ctx, ctx->dentry, file, open_flags, opened);
+	err = nfs_finish_open(ctx, ctx->dentry, file, open_flags);
 	trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
 	put_nfs_open_context(ctx);
 out:
@@ -1641,6 +1643,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
 	struct dentry *parent = dget_parent(dentry);
 	struct inode *dir = d_inode(parent);
 	struct inode *inode;
+	struct dentry *d;
 	int error = -EACCES;
 
 	d_drop(dentry);
@@ -1662,10 +1665,12 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
 			goto out_error;
 	}
 	inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label);
-	error = PTR_ERR(inode);
-	if (IS_ERR(inode))
+	d = d_splice_alias(inode, dentry);
+	if (IS_ERR(d)) {
+		error = PTR_ERR(d);
 		goto out_error;
-	d_add(dentry, inode);
+	}
+	dput(d);
 out:
 	dput(parent);
 	return 0;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 137e18abb7e7..51beb6e38c90 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -258,7 +258,7 @@ extern const struct dentry_operations nfs4_dentry_operations;
 
 /* dir.c */
 int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
-		    unsigned, umode_t, int *);
+		    unsigned, umode_t);
 
 /* super.c */
 extern struct file_system_type nfs4_fs_type;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f6c4ccd693f4..b790976d3913 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2951,7 +2951,7 @@ static int _nfs4_do_open(struct inode *dir,
 		}
 	}
 	if (opened && opendata->file_created)
-		*opened |= FILE_CREATED;
+		*opened = 1;
 
 	if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) {
 		*ctx_th = opendata->f_attr.mdsthreshold;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index b0555d7d8200..55a099e47ba2 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -763,7 +763,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 		goto out_nfserr;
 	}
 
-	host_err = ima_file_check(file, may_flags, 0);
+	host_err = ima_file_check(file, may_flags);
 	if (host_err) {
 		fput(file);
 		goto out_nfserr;
diff --git a/fs/open.c b/fs/open.c
index d0e955b558ad..d98e19239bb7 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -724,27 +724,13 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 	return ksys_fchown(fd, user, group);
 }
 
-int open_check_o_direct(struct file *f)
-{
-	/* NB: we're sure to have correct a_ops only after f_op->open */
-	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
-			return -EINVAL;
-	}
-	return 0;
-}
-
 static int do_dentry_open(struct file *f,
 			  struct inode *inode,
-			  int (*open)(struct inode *, struct file *),
-			  const struct cred *cred)
+			  int (*open)(struct inode *, struct file *))
 {
 	static const struct file_operations empty_fops = {};
 	int error;
 
-	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
-				FMODE_PREAD | FMODE_PWRITE;
-
 	path_get(&f->f_path);
 	f->f_inode = inode;
 	f->f_mapping = inode->i_mapping;
@@ -753,7 +739,7 @@ static int do_dentry_open(struct file *f,
 	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
 
 	if (unlikely(f->f_flags & O_PATH)) {
-		f->f_mode = FMODE_PATH;
+		f->f_mode = FMODE_PATH | FMODE_OPENED;
 		f->f_op = &empty_fops;
 		return 0;
 	}
@@ -780,7 +766,7 @@ static int do_dentry_open(struct file *f,
 		goto cleanup_all;
 	}
 
-	error = security_file_open(f, cred);
+	error = security_file_open(f);
 	if (error)
 		goto cleanup_all;
 
@@ -788,6 +774,8 @@ static int do_dentry_open(struct file *f,
 	if (error)
 		goto cleanup_all;
 
+	/* normally all 3 are set; ->open() can clear them if needed */
+	f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
 	if (!open)
 		open = f->f_op->open;
 	if (open) {
@@ -795,6 +783,7 @@ static int do_dentry_open(struct file *f,
 		if (error)
 			goto cleanup_all;
 	}
+	f->f_mode |= FMODE_OPENED;
 	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(inode);
 	if ((f->f_mode & FMODE_READ) &&
@@ -809,9 +798,16 @@ static int do_dentry_open(struct file *f,
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
 
+	/* NB: we're sure to have correct a_ops only after f_op->open */
+	if (f->f_flags & O_DIRECT) {
+		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
+			return -EINVAL;
+	}
 	return 0;
 
 cleanup_all:
+	if (WARN_ON_ONCE(error > 0))
+		error = -EINVAL;
 	fops_put(f->f_op);
 	if (f->f_mode & FMODE_WRITER) {
 		put_write_access(inode);
@@ -847,19 +843,12 @@ cleanup_file:
  * Returns zero on success or -errno if the open failed.
  */
 int finish_open(struct file *file, struct dentry *dentry,
-		int (*open)(struct inode *, struct file *),
-		int *opened)
+		int (*open)(struct inode *, struct file *))
 {
-	int error;
-	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
+	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
 
 	file->f_path.dentry = dentry;
-	error = do_dentry_open(file, d_backing_inode(dentry), open,
-			       current_cred());
-	if (!error)
-		*opened |= FILE_OPENED;
-
-	return error;
+	return do_dentry_open(file, d_backing_inode(dentry), open);
 }
 EXPORT_SYMBOL(finish_open);
 
@@ -874,13 +863,13 @@ EXPORT_SYMBOL(finish_open);
  * NB: unlike finish_open() this function does consume the dentry reference and
  * the caller need not dput() it.
  *
- * Returns "1" which must be the return value of ->atomic_open() after having
+ * Returns "0" which must be the return value of ->atomic_open() after having
  * called this function.
  */
 int finish_no_open(struct file *file, struct dentry *dentry)
 {
 	file->f_path.dentry = dentry;
-	return 1;
+	return 0;
 }
 EXPORT_SYMBOL(finish_no_open);
 
@@ -896,8 +885,7 @@ EXPORT_SYMBOL(file_path);
  * @file: newly allocated file with f_flag initialized
  * @cred: credentials to use
  */
-int vfs_open(const struct path *path, struct file *file,
-	     const struct cred *cred)
+int vfs_open(const struct path *path, struct file *file)
 {
 	struct dentry *dentry = d_real(path->dentry, NULL, file->f_flags, 0);
 
@@ -905,7 +893,7 @@ int vfs_open(const struct path *path, struct file *file,
 		return PTR_ERR(dentry);
 
 	file->f_path = *path;
-	return do_dentry_open(file, d_backing_inode(dentry), NULL, cred);
+	return do_dentry_open(file, d_backing_inode(dentry), NULL);
 }
 
 struct file *dentry_open(const struct path *path, int flags,
@@ -919,19 +907,11 @@ struct file *dentry_open(const struct path *path, int flags,
 	/* We must always pass in a valid mount pointer. */
 	BUG_ON(!path->mnt);
 
-	f = get_empty_filp();
+	f = alloc_empty_file(flags, cred);
 	if (!IS_ERR(f)) {
-		f->f_flags = flags;
-		error = vfs_open(path, f, cred);
-		if (!error) {
-			/* from now on we need fput() to dispose of f */
-			error = open_check_o_direct(f);
-			if (error) {
-				fput(f);
-				f = ERR_PTR(error);
-			}
-		} else { 
-			put_filp(f);
+		error = vfs_open(path, f);
+		if (error) {
+			fput(f);
 			f = ERR_PTR(error);
 		}
 	}
@@ -1063,26 +1043,6 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 }
 EXPORT_SYMBOL(file_open_root);
 
-struct file *filp_clone_open(struct file *oldfile)
-{
-	struct file *file;
-	int retval;
-
-	file = get_empty_filp();
-	if (IS_ERR(file))
-		return file;
-
-	file->f_flags = oldfile->f_flags;
-	retval = vfs_open(&oldfile->f_path, file, oldfile->f_cred);
-	if (retval) {
-		put_filp(file);
-		return ERR_PTR(retval);
-	}
-
-	return file;
-}
-EXPORT_SYMBOL(filp_clone_open);
-
 long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
diff --git a/fs/pipe.c b/fs/pipe.c
index 39d6f431da83..bdc5d3c0977d 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -741,54 +741,33 @@ fail_inode:
 
 int create_pipe_files(struct file **res, int flags)
 {
-	int err;
 	struct inode *inode = get_pipe_inode();
 	struct file *f;
-	struct path path;
 
 	if (!inode)
 		return -ENFILE;
 
-	err = -ENOMEM;
-	path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &empty_name);
-	if (!path.dentry)
-		goto err_inode;
-	path.mnt = mntget(pipe_mnt);
-
-	d_instantiate(path.dentry, inode);
-
-	f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops);
+	f = alloc_file_pseudo(inode, pipe_mnt, "",
+				O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
+				&pipefifo_fops);
 	if (IS_ERR(f)) {
-		err = PTR_ERR(f);
-		goto err_dentry;
+		free_pipe_info(inode->i_pipe);
+		iput(inode);
+		return PTR_ERR(f);
 	}
 
-	f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
 	f->private_data = inode->i_pipe;
 
-	res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);
+	res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK),
+				  &pipefifo_fops);
 	if (IS_ERR(res[0])) {
-		err = PTR_ERR(res[0]);
-		goto err_file;
+		put_pipe_info(inode, inode->i_pipe);
+		fput(f);
+		return PTR_ERR(res[0]);
 	}
-
-	path_get(&path);
 	res[0]->private_data = inode->i_pipe;
-	res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK);
 	res[1] = f;
 	return 0;
-
-err_file:
-	put_filp(f);
-err_dentry:
-	free_pipe_info(inode->i_pipe);
-	path_put(&path);
-	return err;
-
-err_inode:
-	free_pipe_info(inode->i_pipe);
-	iput(inode);
-	return err;
 }
 
 static int __do_pipe_flags(int *fd, struct file **files, int flags)
diff --git a/fs/timerfd.c b/fs/timerfd.c
index cdad49da3ff7..d69ad801eb80 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -66,7 +66,7 @@ static void timerfd_triggered(struct timerfd_ctx *ctx)
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
 	ctx->expired = 1;
 	ctx->ticks++;
-	wake_up_locked(&ctx->wqh);
+	wake_up_locked_poll(&ctx->wqh, EPOLLIN);
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 }
 
@@ -107,7 +107,7 @@ void timerfd_clock_was_set(void)
 		if (ctx->moffs != moffs) {
 			ctx->moffs = KTIME_MAX;
 			ctx->ticks++;
-			wake_up_locked(&ctx->wqh);
+			wake_up_locked_poll(&ctx->wqh, EPOLLIN);
 		}
 		spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 	}
@@ -345,7 +345,7 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
 		spin_lock_irq(&ctx->wqh.lock);
 		if (!timerfd_canceled(ctx)) {
 			ctx->ticks = ticks;
-			wake_up_locked(&ctx->wqh);
+			wake_up_locked_poll(&ctx->wqh, EPOLLIN);
 		} else
 			ret = -ECANCELED;
 		spin_unlock_irq(&ctx->wqh.lock);
@@ -533,8 +533,8 @@ static int do_timerfd_gettime(int ufd, struct itimerspec64 *t)
 }
 
 SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
-		const struct itimerspec __user *, utmr,
-		struct itimerspec __user *, otmr)
+		const struct __kernel_itimerspec __user *, utmr,
+		struct __kernel_itimerspec __user *, otmr)
 {
 	struct itimerspec64 new, old;
 	int ret;
@@ -550,7 +550,7 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 	return ret;
 }
 
-SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
+SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, otmr)
 {
 	struct itimerspec64 kotmr;
 	int ret = do_timerfd_gettime(ufd, &kotmr);
@@ -559,7 +559,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
 	return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
 COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 		const struct compat_itimerspec __user *, utmr,
 		struct compat_itimerspec __user *, otmr)
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 06f37ddd2997..58cc2414992b 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -602,8 +602,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
 	fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err);
 	if (unlikely(!fi)) {
 		inode_dec_link_count(inode);
-		unlock_new_inode(inode);
-		iput(inode);
+		discard_new_inode(inode);
 		return err;
 	}
 	cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize);
@@ -694,8 +693,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	fi = udf_add_entry(inode, NULL, &fibh, &cfi, &err);
 	if (!fi) {
 		inode_dec_link_count(inode);
-		unlock_new_inode(inode);
-		iput(inode);
+		discard_new_inode(inode);
 		goto out;
 	}
 	set_nlink(inode, 2);
@@ -713,8 +711,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (!fi) {
 		clear_nlink(inode);
 		mark_inode_dirty(inode);
-		unlock_new_inode(inode);
-		iput(inode);
+		discard_new_inode(inode);
 		goto out;
 	}
 	cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize);
@@ -1041,8 +1038,7 @@ out:
 out_no_entry:
 	up_write(&iinfo->i_data_sem);
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	goto out;
 }
 
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index e1ef0f0a1353..02c0a4be4212 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -343,8 +343,7 @@ cg_found:
 fail_remove_inode:
 	mutex_unlock(&sbi->s_lock);
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
 	return ERR_PTR(err);
 failed:
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index d5f43ba76c59..9ef40f100415 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -43,8 +43,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode)
 		return 0;
 	}
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return err;
 }
 
@@ -142,8 +141,7 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry,
 
 out_fail:
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return err;
 }
 
@@ -198,8 +196,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 out_fail:
 	inode_dec_link_count(inode);
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput (inode);
+	discard_new_inode(inode);
 out_dir:
 	inode_dec_link_count(dir);
 	return err;
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 2f3f75a7f180..7f96bdadc372 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -158,6 +158,7 @@ xfs-$(CONFIG_XFS_QUOTA)		+= scrub/quota.o
 ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
 xfs-y				+= $(addprefix scrub/, \
 				   agheader_repair.o \
+				   bitmap.o \
 				   repair.o \
 				   )
 endif
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index fecd187fcf2c..e701ebc36c06 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -248,7 +248,8 @@ __xfs_ag_resv_init(
 /* Create a per-AG block reservation. */
 int
 xfs_ag_resv_init(
-	struct xfs_perag		*pag)
+	struct xfs_perag		*pag,
+	struct xfs_trans		*tp)
 {
 	struct xfs_mount		*mp = pag->pag_mount;
 	xfs_agnumber_t			agno = pag->pag_agno;
@@ -260,11 +261,11 @@ xfs_ag_resv_init(
 	if (pag->pag_meta_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_refcountbt_calc_reserves(mp, agno, &ask, &used);
+		error = xfs_refcountbt_calc_reserves(mp, tp, agno, &ask, &used);
 		if (error)
 			goto out;
 
-		error = xfs_finobt_calc_reserves(mp, agno, &ask, &used);
+		error = xfs_finobt_calc_reserves(mp, tp, agno, &ask, &used);
 		if (error)
 			goto out;
 
@@ -282,7 +283,7 @@ xfs_ag_resv_init(
 
 			mp->m_inotbt_nores = true;
 
-			error = xfs_refcountbt_calc_reserves(mp, agno, &ask,
+			error = xfs_refcountbt_calc_reserves(mp, tp, agno, &ask,
 					&used);
 			if (error)
 				goto out;
@@ -298,7 +299,7 @@ xfs_ag_resv_init(
 	if (pag->pag_rmapbt_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_rmapbt_calc_reserves(mp, agno, &ask, &used);
+		error = xfs_rmapbt_calc_reserves(mp, tp, agno, &ask, &used);
 		if (error)
 			goto out;
 
@@ -309,7 +310,7 @@ xfs_ag_resv_init(
 
 #ifdef DEBUG
 	/* need to read in the AGF for the ASSERT below to work */
-	error = xfs_alloc_pagf_init(pag->pag_mount, NULL, pag->pag_agno, 0);
+	error = xfs_alloc_pagf_init(pag->pag_mount, tp, pag->pag_agno, 0);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_ag_resv.h b/fs/xfs/libxfs/xfs_ag_resv.h
index 4619b554ee90..c0352edc8e41 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.h
+++ b/fs/xfs/libxfs/xfs_ag_resv.h
@@ -7,7 +7,7 @@
 #define	__XFS_AG_RESV_H__
 
 int xfs_ag_resv_free(struct xfs_perag *pag);
-int xfs_ag_resv_init(struct xfs_perag *pag);
+int xfs_ag_resv_init(struct xfs_perag *pag, struct xfs_trans *tp);
 
 bool xfs_ag_resv_critical(struct xfs_perag *pag, enum xfs_ag_resv_type type);
 xfs_extlen_t xfs_ag_resv_needed(struct xfs_perag *pag,
@@ -28,7 +28,7 @@ xfs_ag_resv_rmapbt_alloc(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
 {
-	struct xfs_alloc_arg	args = {0};
+	struct xfs_alloc_arg	args = { NULL };
 	struct xfs_perag	*pag;
 
 	args.len = 1;
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 75dbdc14c45f..e1c0c0d2f1b0 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2198,12 +2198,12 @@ xfs_agfl_reset(
  */
 STATIC void
 xfs_defer_agfl_block(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_agnumber_t			agno,
 	xfs_fsblock_t			agbno,
 	struct xfs_owner_info		*oinfo)
 {
+	struct xfs_mount		*mp = tp->t_mountp;
 	struct xfs_extent_free_item	*new;		/* new element */
 
 	ASSERT(xfs_bmap_free_item_zone != NULL);
@@ -2216,7 +2216,7 @@ xfs_defer_agfl_block(
 
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
 }
 
 /*
@@ -2323,16 +2323,8 @@ xfs_alloc_fix_freelist(
 		if (error)
 			goto out_agbp_relse;
 
-		/* defer agfl frees if dfops is provided */
-		if (tp->t_agfl_dfops) {
-			xfs_defer_agfl_block(mp, tp->t_agfl_dfops, args->agno,
-					     bno, &targs.oinfo);
-		} else {
-			error = xfs_free_agfl_block(tp, args->agno, bno, agbp,
-						    &targs.oinfo);
-			if (error)
-				goto out_agbp_relse;
-		}
+		/* defer agfl frees */
+		xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo);
 	}
 
 	targs.tp = tp;
@@ -2755,9 +2747,6 @@ xfs_alloc_read_agf(
 		pag->pagf_levels[XFS_BTNUM_RMAPi] =
 			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
 		pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
-		spin_lock_init(&pag->pagb_lock);
-		pag->pagb_count = 0;
-		pag->pagb_tree = RB_ROOT;
 		pag->pagf_init = 1;
 		pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
 	}
@@ -2784,16 +2773,16 @@ xfs_alloc_read_agf(
  */
 int				/* error */
 xfs_alloc_vextent(
-	xfs_alloc_arg_t	*args)	/* allocation argument structure */
+	struct xfs_alloc_arg	*args)	/* allocation argument structure */
 {
-	xfs_agblock_t	agsize;	/* allocation group size */
-	int		error;
-	int		flags;	/* XFS_ALLOC_FLAG_... locking flags */
-	xfs_mount_t	*mp;	/* mount structure pointer */
-	xfs_agnumber_t	sagno;	/* starting allocation group number */
-	xfs_alloctype_t	type;	/* input allocation type */
-	int		bump_rotor = 0;
-	xfs_agnumber_t	rotorstep = xfs_rotorstep; /* inode32 agf stepper */
+	xfs_agblock_t		agsize;	/* allocation group size */
+	int			error;
+	int			flags;	/* XFS_ALLOC_FLAG_... locking flags */
+	struct xfs_mount	*mp;	/* mount structure pointer */
+	xfs_agnumber_t		sagno;	/* starting allocation group number */
+	xfs_alloctype_t		type;	/* input allocation type */
+	int			bump_rotor = 0;
+	xfs_agnumber_t		rotorstep = xfs_rotorstep; /* inode32 agf stepper */
 
 	mp = args->mp;
 	type = args->otype = args->type;
@@ -2914,7 +2903,7 @@ xfs_alloc_vextent(
 			* locking of AGF, which might cause deadlock.
 			*/
 			if (++(args->agno) == mp->m_sb.sb_agcount) {
-				if (args->firstblock != NULLFSBLOCK)
+				if (args->tp->t_firstblock != NULLFSBLOCK)
 					args->agno = sagno;
 				else
 					args->agno = 0;
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index e716c993ac4c..00cd5ec4cb6b 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -74,7 +74,6 @@ typedef struct xfs_alloc_arg {
 	int		datatype;	/* mask defining data type treatment */
 	char		wasdel;		/* set if allocation was prev delayed */
 	char		wasfromfl;	/* set if allocation is from freelist */
-	xfs_fsblock_t	firstblock;	/* io first block allocated */
 	struct xfs_owner_info	oinfo;	/* owner of blocks being allocated */
 	enum xfs_ag_resv_type	resv;	/* block reservation to use */
 } xfs_alloc_arg_t;
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 99590f61d624..1e671d4eb6fa 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -202,9 +202,7 @@ xfs_attr_set(
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_buf		*leaf_bp = NULL;
 	struct xfs_da_args	args;
-	struct xfs_defer_ops	dfops;
 	struct xfs_trans_res	tres;
-	xfs_fsblock_t		firstblock;
 	int			rsvd = (flags & ATTR_ROOT) != 0;
 	int			error, err2, local;
 
@@ -219,8 +217,6 @@ xfs_attr_set(
 
 	args.value = value;
 	args.valuelen = valuelen;
-	args.firstblock = &firstblock;
-	args.dfops = &dfops;
 	args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 	args.total = xfs_attr_calc_size(&args, &local);
 
@@ -315,21 +311,18 @@ xfs_attr_set(
 		 * It won't fit in the shortform, transform to a leaf block.
 		 * GROT: another possible req'mt for a double-split btree op.
 		 */
-		xfs_defer_init(args.dfops, args.firstblock);
 		error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 		/*
 		 * Prevent the leaf buffer from being unlocked so that a
 		 * concurrent AIL push cannot grab the half-baked leaf
 		 * buffer and run into problems with the write verifier.
 		 */
 		xfs_trans_bhold(args.trans, leaf_bp);
-		xfs_defer_bjoin(args.dfops, leaf_bp);
-		xfs_defer_ijoin(args.dfops, dp);
-		error = xfs_defer_finish(&args.trans, args.dfops);
+		error = xfs_defer_finish(&args.trans);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 
 		/*
 		 * Commit the leaf transformation.  We'll need another (linked)
@@ -369,8 +362,6 @@ xfs_attr_set(
 
 	return error;
 
-out_defer_cancel:
-	xfs_defer_cancel(&dfops);
 out:
 	if (leaf_bp)
 		xfs_trans_brelse(args.trans, leaf_bp);
@@ -392,8 +383,6 @@ xfs_attr_remove(
 {
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_da_args	args;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		firstblock;
 	int			error;
 
 	XFS_STATS_INC(mp, xs_attr_remove);
@@ -405,9 +394,6 @@ xfs_attr_remove(
 	if (error)
 		return error;
 
-	args.firstblock = &firstblock;
-	args.dfops = &dfops;
-
 	/*
 	 * we have no control over the attribute names that userspace passes us
 	 * to remove, so we have to allow the name lookup prior to attribute
@@ -536,11 +522,12 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
  * if bmap_one_block() says there is only one block (ie: no remote blks).
  */
 STATIC int
-xfs_attr_leaf_addname(xfs_da_args_t *args)
+xfs_attr_leaf_addname(
+	struct xfs_da_args	*args)
 {
-	xfs_inode_t *dp;
-	struct xfs_buf *bp;
-	int retval, error, forkoff;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			retval, error, forkoff;
 
 	trace_xfs_attr_leaf_addname(args);
 
@@ -598,14 +585,12 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 		 * Commit that transaction so that the node_addname() call
 		 * can manage its own transactions.
 		 */
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 
 		/*
 		 * Commit the current trans (including the inode) and start
@@ -687,15 +672,13 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 		 * If the result is small enough, shrink it all into the inode.
 		 */
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->dfops, args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				return error;
 		}
 
 		/*
@@ -711,7 +694,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	}
 	return error;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans);
 	return error;
 }
 
@@ -722,11 +705,12 @@ out_defer_cancel:
  * if bmap_one_block() says there is only one block (ie: no remote blks).
  */
 STATIC int
-xfs_attr_leaf_removename(xfs_da_args_t *args)
+xfs_attr_leaf_removename(
+	struct xfs_da_args	*args)
 {
-	xfs_inode_t *dp;
-	struct xfs_buf *bp;
-	int error, forkoff;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			error, forkoff;
 
 	trace_xfs_attr_leaf_removename(args);
 
@@ -751,19 +735,17 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 	 * If the result is small enough, shrink it all into the inode.
 	 */
 	if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 	}
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans);
 	return error;
 }
 
@@ -814,13 +796,14 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
  * add a whole extra layer of confusion on top of that.
  */
 STATIC int
-xfs_attr_node_addname(xfs_da_args_t *args)
+xfs_attr_node_addname(
+	struct xfs_da_args	*args)
 {
-	xfs_da_state_t *state;
-	xfs_da_state_blk_t *blk;
-	xfs_inode_t *dp;
-	xfs_mount_t *mp;
-	int retval, error;
+	struct xfs_da_state	*state;
+	struct xfs_da_state_blk	*blk;
+	struct xfs_inode	*dp;
+	struct xfs_mount	*mp;
+	int			retval, error;
 
 	trace_xfs_attr_node_addname(args);
 
@@ -879,14 +862,12 @@ restart:
 			 */
 			xfs_da_state_free(state);
 			state = NULL;
-			xfs_defer_init(args->dfops, args->firstblock);
 			error = xfs_attr3_leaf_to_node(args);
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 
 			/*
 			 * Commit the node conversion and start the next
@@ -905,14 +886,12 @@ restart:
 		 * in the index/blkno/rmtblkno/rmtblkcnt fields and
 		 * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
 		 */
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_da3_split(state);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 	} else {
 		/*
 		 * Addition succeeded, update Btree hashvals.
@@ -1003,14 +982,12 @@ restart:
 		 * Check to see if the tree needs to be collapsed.
 		 */
 		if (retval && (state->path.active > 1)) {
-			xfs_defer_init(args->dfops, args->firstblock);
 			error = xfs_da3_join(state);
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 		}
 
 		/*
@@ -1037,7 +1014,7 @@ out:
 		return error;
 	return retval;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans);
 	goto out;
 }
 
@@ -1049,13 +1026,14 @@ out_defer_cancel:
  * the root node (a special case of an intermediate node).
  */
 STATIC int
-xfs_attr_node_removename(xfs_da_args_t *args)
+xfs_attr_node_removename(
+	struct xfs_da_args	*args)
 {
-	xfs_da_state_t *state;
-	xfs_da_state_blk_t *blk;
-	xfs_inode_t *dp;
-	struct xfs_buf *bp;
-	int retval, error, forkoff;
+	struct xfs_da_state	*state;
+	struct xfs_da_state_blk	*blk;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			retval, error, forkoff;
 
 	trace_xfs_attr_node_removename(args);
 
@@ -1127,14 +1105,12 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	 * Check to see if the tree needs to be collapsed.
 	 */
 	if (retval && (state->path.active > 1)) {
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_da3_join(state);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 		/*
 		 * Commit the Btree join operation and start a new trans.
 		 */
@@ -1159,15 +1135,13 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 			goto out;
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->dfops, args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 		} else
 			xfs_trans_brelse(args->trans, bp);
 	}
@@ -1177,7 +1151,7 @@ out:
 	xfs_da_state_free(state);
 	return error;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans);
 	goto out;
 }
 
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 76e90046731c..6fc5425b1474 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -242,8 +242,9 @@ xfs_attr3_leaf_verify(
 	struct xfs_attr3_icleaf_hdr	ichdr;
 	struct xfs_mount		*mp = bp->b_target->bt_mount;
 	struct xfs_attr_leafblock	*leaf = bp->b_addr;
-	struct xfs_perag		*pag = bp->b_pag;
 	struct xfs_attr_leaf_entry	*entries;
+	uint16_t			end;
+	int				i;
 
 	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
 
@@ -268,7 +269,7 @@ xfs_attr3_leaf_verify(
 	 * because we may have transitioned an empty shortform attr to a leaf
 	 * if the attr didn't fit in shortform.
 	 */
-	if (pag && pag->pagf_init && ichdr.count == 0)
+	if (!xfs_log_in_recovery(mp) && ichdr.count == 0)
 		return __this_address;
 
 	/*
@@ -289,6 +290,26 @@ xfs_attr3_leaf_verify(
 	/* XXX: need to range check rest of attr header values */
 	/* XXX: hash order check? */
 
+	/*
+	 * Quickly check the freemap information.  Attribute data has to be
+	 * aligned to 4-byte boundaries, and likewise for the free space.
+	 */
+	for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
+		if (ichdr.freemap[i].base > mp->m_attr_geo->blksize)
+			return __this_address;
+		if (ichdr.freemap[i].base & 0x3)
+			return __this_address;
+		if (ichdr.freemap[i].size > mp->m_attr_geo->blksize)
+			return __this_address;
+		if (ichdr.freemap[i].size & 0x3)
+			return __this_address;
+		end = ichdr.freemap[i].base + ichdr.freemap[i].size;
+		if (end < ichdr.freemap[i].base)
+			return __this_address;
+		if (end > mp->m_attr_geo->blksize)
+			return __this_address;
+	}
+
 	return NULL;
 }
 
@@ -506,7 +527,7 @@ xfs_attr_shortform_create(xfs_da_args_t *args)
 {
 	xfs_attr_sf_hdr_t *hdr;
 	xfs_inode_t *dp;
-	xfs_ifork_t *ifp;
+	struct xfs_ifork *ifp;
 
 	trace_xfs_attr_sf_create(args);
 
@@ -541,7 +562,7 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
 	int i, offset, size;
 	xfs_mount_t *mp;
 	xfs_inode_t *dp;
-	xfs_ifork_t *ifp;
+	struct xfs_ifork *ifp;
 
 	trace_xfs_attr_sf_add(args);
 
@@ -682,7 +703,7 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
 	xfs_attr_shortform_t *sf;
 	xfs_attr_sf_entry_t *sfe;
 	int i;
-	xfs_ifork_t *ifp;
+	struct xfs_ifork *ifp;
 
 	trace_xfs_attr_sf_lookup(args);
 
@@ -747,18 +768,18 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args)
  */
 int
 xfs_attr_shortform_to_leaf(
-	struct xfs_da_args	*args,
-	struct xfs_buf		**leaf_bp)
+	struct xfs_da_args		*args,
+	struct xfs_buf			**leaf_bp)
 {
-	xfs_inode_t *dp;
-	xfs_attr_shortform_t *sf;
-	xfs_attr_sf_entry_t *sfe;
-	xfs_da_args_t nargs;
-	char *tmpbuffer;
-	int error, i, size;
-	xfs_dablk_t blkno;
-	struct xfs_buf *bp;
-	xfs_ifork_t *ifp;
+	struct xfs_inode		*dp;
+	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_entry	*sfe;
+	struct xfs_da_args		nargs;
+	char				*tmpbuffer;
+	int				error, i, size;
+	xfs_dablk_t			blkno;
+	struct xfs_buf			*bp;
+	struct xfs_ifork		*ifp;
 
 	trace_xfs_attr_sf_to_leaf(args);
 
@@ -802,8 +823,6 @@ xfs_attr_shortform_to_leaf(
 	memset((char *)&nargs, 0, sizeof(nargs));
 	nargs.dp = dp;
 	nargs.geo = args->geo;
-	nargs.firstblock = args->firstblock;
-	nargs.dfops = args->dfops;
 	nargs.total = args->total;
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
@@ -1006,8 +1025,6 @@ xfs_attr3_leaf_to_shortform(
 	memset((char *)&nargs, 0, sizeof(nargs));
 	nargs.geo = args->geo;
 	nargs.dp = dp;
-	nargs.firstblock = args->firstblock;
-	nargs.dfops = args->dfops;
 	nargs.total = args->total;
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
@@ -1570,17 +1587,10 @@ xfs_attr3_leaf_rebalance(
 	 */
 	swap = 0;
 	if (xfs_attr3_leaf_order(blk1->bp, &ichdr1, blk2->bp, &ichdr2)) {
-		struct xfs_da_state_blk	*tmp_blk;
-		struct xfs_attr3_icleaf_hdr tmp_ichdr;
-
-		tmp_blk = blk1;
-		blk1 = blk2;
-		blk2 = tmp_blk;
+		swap(blk1, blk2);
 
-		/* struct copies to swap them rather than reconverting */
-		tmp_ichdr = ichdr1;
-		ichdr1 = ichdr2;
-		ichdr2 = tmp_ichdr;
+		/* swap structures rather than reconverting them */
+		swap(ichdr1, ichdr2);
 
 		leaf1 = blk1->bp->b_addr;
 		leaf2 = blk2->bp->b_addr;
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index bf2e0371149b..af094063e402 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -480,17 +480,15 @@ xfs_attr_rmtval_set(
 		 * extent and then crash then the block may not contain the
 		 * correct metadata after log recovery occurs.
 		 */
-		xfs_defer_init(args->dfops, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
-				  args->total, &map, &nmap, args->dfops);
+				  blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
+				  &nmap);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 
 		ASSERT(nmap == 1);
 		ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
@@ -522,7 +520,6 @@ xfs_attr_rmtval_set(
 
 		ASSERT(blkcnt > 0);
 
-		xfs_defer_init(args->dfops, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
 				       blkcnt, &map, &nmap,
@@ -557,8 +554,7 @@ xfs_attr_rmtval_set(
 	ASSERT(valuelen == 0);
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
-	args->trans = NULL;
+	xfs_defer_cancel(args->trans);
 	return error;
 }
 
@@ -626,16 +622,13 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	done = 0;
 	while (!done) {
-		xfs_defer_init(args->dfops, args->firstblock);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
-				    XFS_BMAPI_ATTRFORK, 1, args->firstblock,
-				    args->dfops, &done);
+				    XFS_BMAPI_ATTRFORK, 1, &done);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, args->dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 
 		/*
 		 * Close out trans and start the next one in the chain.
@@ -646,7 +639,6 @@ xfs_attr_rmtval_remove(
 	}
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
-	args->trans = NULL;
+	xfs_defer_cancel(args->trans);
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7205268b30bc..2760314fdf7f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -326,7 +326,7 @@ xfs_bmap_check_leaf_extents(
 	xfs_buf_t		*bp;	/* buffer for "block" */
 	int			error;	/* error return value */
 	xfs_extnum_t		i=0, j;	/* index into the extents list */
-	xfs_ifork_t		*ifp;	/* fork structure */
+	struct xfs_ifork	*ifp;	/* fork structure */
 	int			level;	/* btree level, for checking */
 	xfs_mount_t		*mp;	/* file system mount structure */
 	__be64			*pp;	/* pointer to block address */
@@ -533,8 +533,7 @@ xfs_bmap_validate_ret(
  */
 void
 __xfs_bmap_add_free(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	struct xfs_owner_info		*oinfo,
@@ -542,8 +541,9 @@ __xfs_bmap_add_free(
 {
 	struct xfs_extent_free_item	*new;		/* new element */
 #ifdef DEBUG
-	xfs_agnumber_t		agno;
-	xfs_agblock_t		agbno;
+	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
 
 	ASSERT(bno != NULLFSBLOCK);
 	ASSERT(len > 0);
@@ -566,9 +566,10 @@ __xfs_bmap_add_free(
 	else
 		xfs_rmap_skip_owner_update(&new->xefi_oinfo);
 	new->xefi_skip_discard = skip_discard;
-	trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(mp, bno), 0,
-			XFS_FSB_TO_AGBNO(mp, bno), len);
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
+	trace_xfs_bmap_free_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
+			XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
 }
 
 /*
@@ -594,7 +595,7 @@ xfs_bmap_btree_to_extents(
 	xfs_fsblock_t		cbno;	/* child block number */
 	xfs_buf_t		*cbp;	/* child block's buffer */
 	int			error;	/* error return value */
-	xfs_ifork_t		*ifp;	/* inode fork data */
+	struct xfs_ifork	*ifp;	/* inode fork data */
 	xfs_mount_t		*mp;	/* mount point structure */
 	__be64			*pp;	/* ptr to block address */
 	struct xfs_btree_block	*rblock;/* root btree block */
@@ -624,7 +625,7 @@ xfs_bmap_btree_to_extents(
 	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
 		return error;
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, cbno, 1, &oinfo);
+	xfs_bmap_add_free(cur->bc_tp, cbno, 1, &oinfo);
 	ip->i_d.di_nblocks--;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
 	xfs_trans_binval(tp, cbp);
@@ -644,25 +645,23 @@ xfs_bmap_btree_to_extents(
  */
 STATIC int					/* error */
 xfs_bmap_extents_to_btree(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first-block-allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks freed in xaction */
-	xfs_btree_cur_t		**curp,		/* cursor returned to caller */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode pointer */
+	struct xfs_btree_cur	**curp,		/* cursor returned to caller */
 	int			wasdel,		/* converting a delayed alloc */
 	int			*logflagsp,	/* inode logging flags */
 	int			whichfork)	/* data or attr fork */
 {
 	struct xfs_btree_block	*ablock;	/* allocated (child) bt block */
-	xfs_buf_t		*abp;		/* buffer for ablock */
-	xfs_alloc_arg_t		args;		/* allocation arguments */
-	xfs_bmbt_rec_t		*arp;		/* child record pointer */
+	struct xfs_buf		*abp;		/* buffer for ablock */
+	struct xfs_alloc_arg	args;		/* allocation arguments */
+	struct xfs_bmbt_rec	*arp;		/* child record pointer */
 	struct xfs_btree_block	*block;		/* btree root block */
-	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
+	struct xfs_btree_cur	*cur;		/* bmap btree cursor */
 	int			error;		/* error return value */
-	xfs_ifork_t		*ifp;		/* inode fork pointer */
-	xfs_bmbt_key_t		*kp;		/* root block key pointer */
-	xfs_mount_t		*mp;		/* mount structure */
+	struct xfs_ifork	*ifp;		/* inode fork pointer */
+	struct xfs_bmbt_key	*kp;		/* root block key pointer */
+	struct xfs_mount	*mp;		/* mount structure */
 	xfs_bmbt_ptr_t		*pp;		/* root block address pointer */
 	struct xfs_iext_cursor	icur;
 	struct xfs_bmbt_irec	rec;
@@ -690,8 +689,6 @@ xfs_bmap_extents_to_btree(
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
 	cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-	cur->bc_private.b.firstblock = *firstblock;
-	cur->bc_private.b.dfops = dfops;
 	cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
 	/*
 	 * Convert to a btree with two levels, one record in root.
@@ -701,45 +698,43 @@ xfs_bmap_extents_to_btree(
 	args.tp = tp;
 	args.mp = mp;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);
-	args.firstblock = *firstblock;
-	if (*firstblock == NULLFSBLOCK) {
+	if (tp->t_firstblock == NULLFSBLOCK) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
-	} else if (dfops->dop_low) {
+	} else if (tp->t_flags & XFS_TRANS_LOWMODE) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
-		args.fsbno = *firstblock;
+		args.fsbno = tp->t_firstblock;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-		args.fsbno = *firstblock;
+		args.fsbno = tp->t_firstblock;
 	}
 	args.minlen = args.maxlen = args.prod = 1;
 	args.wasdel = wasdel;
 	*logflagsp = 0;
 	if ((error = xfs_alloc_vextent(&args))) {
-		xfs_iroot_realloc(ip, -1, whichfork);
 		ASSERT(ifp->if_broot == NULL);
-		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
-		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-		return error;
+		goto err1;
 	}
 
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
-		xfs_iroot_realloc(ip, -1, whichfork);
 		ASSERT(ifp->if_broot == NULL);
-		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
-		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-		return -ENOSPC;
+		error = -ENOSPC;
+		goto err1;
 	}
 	/*
 	 * Allocation can't fail, the space was reserved.
 	 */
-	ASSERT(*firstblock == NULLFSBLOCK ||
-	       args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
-	*firstblock = cur->bc_private.b.firstblock = args.fsbno;
+	ASSERT(tp->t_firstblock == NULLFSBLOCK ||
+	       args.agno >= XFS_FSB_TO_AGNO(mp, tp->t_firstblock));
+	tp->t_firstblock = args.fsbno;
 	cur->bc_private.b.allocated++;
 	ip->i_d.di_nblocks++;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
 	abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0);
+	if (!abp) {
+		error = -ENOSPC;
+		goto err2;
+	}
 	/*
 	 * Fill in the child block.
 	 */
@@ -779,6 +774,15 @@ xfs_bmap_extents_to_btree(
 	*curp = cur;
 	*logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork);
 	return 0;
+
+err2:
+	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
+err1:
+	xfs_iroot_realloc(ip, -1, whichfork);
+	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
+	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+
+	return error;
 }
 
 /*
@@ -812,7 +816,6 @@ STATIC int				/* error */
 xfs_bmap_local_to_extents(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_inode_t	*ip,		/* incore inode pointer */
-	xfs_fsblock_t	*firstblock,	/* first block allocated in xaction */
 	xfs_extlen_t	total,		/* total blocks needed by transaction */
 	int		*logflagsp,	/* inode logging flags */
 	int		whichfork,
@@ -823,7 +826,7 @@ xfs_bmap_local_to_extents(
 {
 	int		error = 0;
 	int		flags;		/* logging flags returned */
-	xfs_ifork_t	*ifp;		/* inode fork pointer */
+	struct xfs_ifork *ifp;		/* inode fork pointer */
 	xfs_alloc_arg_t	args;		/* allocation arguments */
 	xfs_buf_t	*bp;		/* buffer for extent block */
 	struct xfs_bmbt_irec rec;
@@ -850,16 +853,15 @@ xfs_bmap_local_to_extents(
 	args.tp = tp;
 	args.mp = ip->i_mount;
 	xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);
-	args.firstblock = *firstblock;
 	/*
 	 * Allocate a block.  We know we need only one, since the
 	 * file currently fits in an inode.
 	 */
-	if (*firstblock == NULLFSBLOCK) {
+	if (tp->t_firstblock == NULLFSBLOCK) {
 		args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
-		args.fsbno = *firstblock;
+		args.fsbno = tp->t_firstblock;
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
 	}
 	args.total = total;
@@ -871,7 +873,7 @@ xfs_bmap_local_to_extents(
 	/* Can't fail, the space was reserved. */
 	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(args.len == 1);
-	*firstblock = args.fsbno;
+	tp->t_firstblock = args.fsbno;
 	bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
 
 	/*
@@ -917,8 +919,6 @@ STATIC int					/* error */
 xfs_bmap_add_attrfork_btree(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* btree cursor */
@@ -931,8 +931,6 @@ xfs_bmap_add_attrfork_btree(
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
-		cur->bc_private.b.dfops = dfops;
-		cur->bc_private.b.firstblock = *firstblock;
 		error = xfs_bmbt_lookup_first(cur, &stat);
 		if (error)
 			goto error0;
@@ -944,7 +942,6 @@ xfs_bmap_add_attrfork_btree(
 			xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 			return -ENOSPC;
 		}
-		*firstblock = cur->bc_private.b.firstblock;
 		cur->bc_private.b.allocated = 0;
 		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 	}
@@ -959,10 +956,8 @@ error0:
  */
 STATIC int					/* error */
 xfs_bmap_add_attrfork_extents(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode pointer */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
@@ -971,12 +966,11 @@ xfs_bmap_add_attrfork_extents(
 	if (ip->i_d.di_nextents * sizeof(xfs_bmbt_rec_t) <= XFS_IFORK_DSIZE(ip))
 		return 0;
 	cur = NULL;
-	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops, &cur, 0,
-		flags, XFS_DATA_FORK);
+	error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, flags,
+					  XFS_DATA_FORK);
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	}
 	return error;
 }
@@ -994,13 +988,11 @@ xfs_bmap_add_attrfork_extents(
  */
 STATIC int					/* error */
 xfs_bmap_add_attrfork_local(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode pointer */
 	int			*flags)		/* inode logging flags */
 {
-	xfs_da_args_t		dargs;		/* args for dir/attr code */
+	struct xfs_da_args	dargs;		/* args for dir/attr code */
 
 	if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
 		return 0;
@@ -1009,8 +1001,6 @@ xfs_bmap_add_attrfork_local(
 		memset(&dargs, 0, sizeof(dargs));
 		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
-		dargs.firstblock = firstblock;
-		dargs.dfops = dfops;
 		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
@@ -1018,8 +1008,8 @@ xfs_bmap_add_attrfork_local(
 	}
 
 	if (S_ISLNK(VFS_I(ip)->i_mode))
-		return xfs_bmap_local_to_extents(tp, ip, firstblock, 1,
-						 flags, XFS_DATA_FORK,
+		return xfs_bmap_local_to_extents(tp, ip, 1, flags,
+						 XFS_DATA_FORK,
 						 xfs_symlink_local_to_remote);
 
 	/* should only be called for types that support local format data */
@@ -1037,8 +1027,6 @@ xfs_bmap_add_attrfork(
 	int			size,		/* space new attribute needs */
 	int			rsvd)		/* xact may use reserved blks */
 {
-	xfs_fsblock_t		firstblock;	/* 1st block/ag allocated */
-	struct xfs_defer_ops	dfops;		/* freed extent records */
 	xfs_mount_t		*mp;		/* mount structure */
 	xfs_trans_t		*tp;		/* transaction pointer */
 	int			blks;		/* space reservation */
@@ -1104,19 +1092,15 @@ xfs_bmap_add_attrfork(
 	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
 	ip->i_afp->if_flags = XFS_IFEXTENTS;
 	logflags = 0;
-	xfs_defer_init(&dfops, &firstblock);
 	switch (ip->i_d.di_format) {
 	case XFS_DINODE_FMT_LOCAL:
-		error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &dfops,
-			&logflags);
+		error = xfs_bmap_add_attrfork_local(tp, ip, &logflags);
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
-		error = xfs_bmap_add_attrfork_extents(tp, ip, &firstblock,
-			&dfops, &logflags);
+		error = xfs_bmap_add_attrfork_extents(tp, ip, &logflags);
 		break;
 	case XFS_DINODE_FMT_BTREE:
-		error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock, &dfops,
-			&logflags);
+		error = xfs_bmap_add_attrfork_btree(tp, ip, &logflags);
 		break;
 	default:
 		error = 0;
@@ -1125,7 +1109,7 @@ xfs_bmap_add_attrfork(
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	if (error)
-		goto bmap_cancel;
+		goto trans_cancel;
 	if (!xfs_sb_version_hasattr(&mp->m_sb) ||
 	   (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
 		bool log_sb = false;
@@ -1144,15 +1128,10 @@ xfs_bmap_add_attrfork(
 			xfs_log_sb(tp);
 	}
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto bmap_cancel;
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 
-bmap_cancel:
-	xfs_defer_cancel(&dfops);
 trans_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1501,7 +1480,7 @@ xfs_bmap_one_block(
 	xfs_inode_t	*ip,		/* incore inode */
 	int		whichfork)	/* data or attr fork */
 {
-	xfs_ifork_t	*ifp;		/* inode fork pointer */
+	struct xfs_ifork *ifp;		/* inode fork pointer */
 	int		rval;		/* return value */
 	xfs_bmbt_irec_t	s;		/* internal version of extent */
 	struct xfs_iext_cursor icur;
@@ -1539,7 +1518,7 @@ xfs_bmap_add_extent_delay_real(
 	struct xfs_bmbt_irec	*new = &bma->got;
 	int			error;	/* error return value */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_fileoff_t		new_endoff;	/* end offset of new entry */
 	xfs_bmbt_irec_t		r[3];	/* neighbor extent entries */
 					/* left is 0, right is 1, prev is 2 */
@@ -1809,7 +1788,6 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->dfops,
 					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -1887,8 +1865,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->dfops, &bma->cur, 1,
-				&tmp_rval, whichfork);
+				&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1968,8 +1945,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->dfops, &bma->cur,
-					1, &tmp_rval, whichfork);
+					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1994,8 +1970,7 @@ xfs_bmap_add_extent_delay_real(
 
 	/* add reverse mapping unless caller opted out */
 	if (!(bma->flags & XFS_BMAPI_NORMAP)) {
-		error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip,
-				whichfork, new);
+		error = xfs_rmap_map_extent(bma->tp, bma->ip, whichfork, new);
 		if (error)
 			goto done;
 	}
@@ -2006,8 +1981,8 @@ xfs_bmap_add_extent_delay_real(
 
 		ASSERT(bma->cur == NULL);
 		error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->dfops, &bma->cur,
-				da_old > 0, &tmp_logflags, whichfork);
+				&bma->cur, da_old > 0, &tmp_logflags,
+				whichfork);
 		bma->logflags |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2046,14 +2021,12 @@ xfs_bmap_add_extent_unwritten_real(
 	struct xfs_iext_cursor	*icur,
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
-	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
-	struct xfs_defer_ops	*dfops,	/* list of extents to be freed */
 	int			*logflagsp) /* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;	/* btree cursor */
 	int			error;	/* error return value */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_fileoff_t		new_endoff;	/* end offset of new entry */
 	xfs_bmbt_irec_t		r[3];	/* neighbor extent entries */
 					/* left is 0, right is 1, prev is 2 */
@@ -2479,7 +2452,7 @@ xfs_bmap_add_extent_unwritten_real(
 	}
 
 	/* update reverse mappings */
-	error = xfs_rmap_convert_extent(mp, dfops, ip, whichfork, new);
+	error = xfs_rmap_convert_extent(mp, tp, ip, whichfork, new);
 	if (error)
 		goto done;
 
@@ -2488,8 +2461,8 @@ xfs_bmap_add_extent_unwritten_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, &cur,
-				0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
+				&tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2520,7 +2493,7 @@ xfs_bmap_add_extent_hole_delay(
 	struct xfs_iext_cursor	*icur,
 	xfs_bmbt_irec_t		*new)	/* new data to add to file extents */
 {
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_bmbt_irec_t		left;	/* left neighbor extent entry */
 	xfs_filblks_t		newlen=0;	/* new indirect size */
 	xfs_filblks_t		oldlen=0;	/* old indirect size */
@@ -2660,8 +2633,6 @@ xfs_bmap_add_extent_hole_real(
 	struct xfs_iext_cursor	*icur,
 	struct xfs_btree_cur	**curp,
 	struct xfs_bmbt_irec	*new,
-	xfs_fsblock_t		*first,
-	struct xfs_defer_ops	*dfops,
 	int			*logflagsp,
 	int			flags)
 {
@@ -2842,7 +2813,7 @@ xfs_bmap_add_extent_hole_real(
 
 	/* add reverse mapping unless caller opted out */
 	if (!(flags & XFS_BMAPI_NORMAP)) {
-		error = xfs_rmap_map_extent(mp, dfops, ip, whichfork, new);
+		error = xfs_rmap_map_extent(tp, ip, whichfork, new);
 		if (error)
 			goto done;
 	}
@@ -2852,8 +2823,8 @@ xfs_bmap_add_extent_hole_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, curp,
-				0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, curp, 0,
+				&tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		cur = *curp;
 		if (error)
@@ -3071,10 +3042,11 @@ xfs_bmap_adjacent(
 		XFS_FSB_TO_AGBNO(mp, x) < mp->m_sb.sb_agblocks)
 
 	mp = ap->ip->i_mount;
-	nullfb = *ap->firstblock == NULLFSBLOCK;
+	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
 	rt = XFS_IS_REALTIME_INODE(ap->ip) &&
 		xfs_alloc_is_userdata(ap->datatype);
-	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
+	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
+							ap->tp->t_firstblock);
 	/*
 	 * If allocating at eof, and there's a previous real block,
 	 * try to use its last block as our starting point.
@@ -3432,8 +3404,9 @@ xfs_bmap_btalloc(
 	}
 
 
-	nullfb = *ap->firstblock == NULLFSBLOCK;
-	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
+	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
+	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
+							ap->tp->t_firstblock);
 	if (nullfb) {
 		if (xfs_alloc_is_userdata(ap->datatype) &&
 		    xfs_inode_is_filestream(ap->ip)) {
@@ -3444,7 +3417,7 @@ xfs_bmap_btalloc(
 			ap->blkno = XFS_INO_TO_FSB(mp, ap->ip->i_ino);
 		}
 	} else
-		ap->blkno = *ap->firstblock;
+		ap->blkno = ap->tp->t_firstblock;
 
 	xfs_bmap_adjacent(ap);
 
@@ -3455,7 +3428,7 @@ xfs_bmap_btalloc(
 	if (nullfb || XFS_FSB_TO_AGNO(mp, ap->blkno) == fb_agno)
 		;
 	else
-		ap->blkno = *ap->firstblock;
+		ap->blkno = ap->tp->t_firstblock;
 	/*
 	 * Normal allocation, done through xfs_alloc_vextent.
 	 */
@@ -3468,7 +3441,6 @@ xfs_bmap_btalloc(
 
 	/* Trim the allocation back to the maximum an AG can fit. */
 	args.maxlen = min(ap->length, mp->m_ag_max_usable);
-	args.firstblock = *ap->firstblock;
 	blen = 0;
 	if (nullfb) {
 		/*
@@ -3483,7 +3455,7 @@ xfs_bmap_btalloc(
 			error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
 		if (error)
 			return error;
-	} else if (ap->dfops->dop_low) {
+	} else if (ap->tp->t_flags & XFS_TRANS_LOWMODE) {
 		if (xfs_inode_is_filestream(ap->ip))
 			args.type = XFS_ALLOCTYPE_FIRST_AG;
 		else
@@ -3518,7 +3490,7 @@ xfs_bmap_btalloc(
 	 * is >= the stripe unit and the allocation offset is
 	 * at the end of file.
 	 */
-	if (!ap->dfops->dop_low && ap->aeof) {
+	if (!(ap->tp->t_flags & XFS_TRANS_LOWMODE) && ap->aeof) {
 		if (!ap->offset) {
 			args.alignment = stripe_align;
 			atype = args.type;
@@ -3610,20 +3582,20 @@ xfs_bmap_btalloc(
 		args.total = ap->minlen;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
-		ap->dfops->dop_low = true;
+		ap->tp->t_flags |= XFS_TRANS_LOWMODE;
 	}
 	if (args.fsbno != NULLFSBLOCK) {
 		/*
 		 * check the allocation happened at the same or higher AG than
 		 * the first block that was allocated.
 		 */
-		ASSERT(*ap->firstblock == NULLFSBLOCK ||
-		       XFS_FSB_TO_AGNO(mp, *ap->firstblock) <=
+		ASSERT(ap->tp->t_firstblock == NULLFSBLOCK ||
+		       XFS_FSB_TO_AGNO(mp, ap->tp->t_firstblock) <=
 		       XFS_FSB_TO_AGNO(mp, args.fsbno));
 
 		ap->blkno = args.fsbno;
-		if (*ap->firstblock == NULLFSBLOCK)
-			*ap->firstblock = args.fsbno;
+		if (ap->tp->t_firstblock == NULLFSBLOCK)
+			ap->tp->t_firstblock = args.fsbno;
 		ASSERT(nullfb || fb_agno <= args.agno);
 		ap->length = args.len;
 		/*
@@ -3788,8 +3760,7 @@ xfs_bmapi_update_map(
 		   mval[-1].br_startblock != HOLESTARTBLOCK &&
 		   mval->br_startblock == mval[-1].br_startblock +
 					  mval[-1].br_blockcount &&
-		   ((flags & XFS_BMAPI_IGSTATE) ||
-			mval[-1].br_state == mval->br_state)) {
+		   mval[-1].br_state == mval->br_state) {
 		ASSERT(mval->br_startoff ==
 		       mval[-1].br_startoff + mval[-1].br_blockcount);
 		mval[-1].br_blockcount += mval->br_blockcount;
@@ -3834,7 +3805,7 @@ xfs_bmapi_read(
 
 	ASSERT(*nmap >= 1);
 	ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK|XFS_BMAPI_ENTIRE|
-			   XFS_BMAPI_IGSTATE|XFS_BMAPI_COWFORK)));
+			   XFS_BMAPI_COWFORK)));
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL));
 
 	if (unlikely(XFS_TEST_ERROR(
@@ -4079,15 +4050,10 @@ xfs_bmapi_allocate(
 	if (error)
 		return error;
 
-	if (bma->cur)
-		bma->cur->bc_private.b.firstblock = *bma->firstblock;
 	if (bma->blkno == NULLFSBLOCK)
 		return 0;
-	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
+	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur)
 		bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork);
-		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.dfops = bma->dfops;
-	}
 	/*
 	 * Bump the number of extents we've allocated
 	 * in this call.
@@ -4122,8 +4088,7 @@ xfs_bmapi_allocate(
 	else
 		error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
 				whichfork, &bma->icur, &bma->cur, &bma->got,
-				bma->firstblock, bma->dfops, &bma->logflags,
-				bma->flags);
+				&bma->logflags, bma->flags);
 
 	bma->logflags |= tmp_logflags;
 	if (error)
@@ -4174,8 +4139,6 @@ xfs_bmapi_convert_unwritten(
 	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
 		bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp,
 					bma->ip, whichfork);
-		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.dfops = bma->dfops;
 	}
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
@@ -4192,8 +4155,7 @@ xfs_bmapi_convert_unwritten(
 	}
 
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork,
-			&bma->icur, &bma->cur, mval, bma->firstblock,
-			bma->dfops, &tmp_logflags);
+			&bma->icur, &bma->cur, mval, &tmp_logflags);
 	/*
 	 * Log the inode core unconditionally in the unwritten extent conversion
 	 * path because the conversion might not have done so (e.g., if the
@@ -4231,12 +4193,6 @@ xfs_bmapi_convert_unwritten(
  * extent state if necessary.  Details behaviour is controlled by the flags
  * parameter.  Only allocates blocks from a single allocation group, to avoid
  * locking problems.
- *
- * The returned value in "firstblock" from the first call in a transaction
- * must be remembered and presented to subsequent calls in "firstblock".
- * An upper bound for the number of blocks to be allocated is supplied to
- * the first call in "total"; if no allocation group has that many free
- * blocks then the call will fail (return NULLFSBLOCK in "firstblock").
  */
 int
 xfs_bmapi_write(
@@ -4245,12 +4201,9 @@ xfs_bmapi_write(
 	xfs_fileoff_t		bno,		/* starting file offs. mapped */
 	xfs_filblks_t		len,		/* length to map in file */
 	int			flags,		/* XFS_BMAPI_... */
-	xfs_fsblock_t		*firstblock,	/* first allocated block
-						   controls a.g. for allocs */
 	xfs_extlen_t		total,		/* total blocks needed */
 	struct xfs_bmbt_irec	*mval,		/* output: map values */
-	int			*nmap,		/* i/o: mval size/count */
-	struct xfs_defer_ops	*dfops)		/* i/o: list extents to free */
+	int			*nmap)		/* i/o: mval size/count */
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
@@ -4279,7 +4232,6 @@ xfs_bmapi_write(
 
 	ASSERT(*nmap >= 1);
 	ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
-	ASSERT(!(flags & XFS_BMAPI_IGSTATE));
 	ASSERT(tp != NULL ||
 	       (flags & (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)) ==
 			(XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK));
@@ -4315,7 +4267,7 @@ xfs_bmapi_write(
 
 	XFS_STATS_INC(mp, xs_blk_mapw);
 
-	if (*firstblock == NULLFSBLOCK) {
+	if (!tp || tp->t_firstblock == NULLFSBLOCK) {
 		if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE)
 			bma.minleft = be16_to_cpu(ifp->if_broot->bb_level) + 1;
 		else
@@ -4342,8 +4294,6 @@ xfs_bmapi_write(
 	bma.ip = ip;
 	bma.total = total;
 	bma.datatype = 0;
-	bma.dfops = dfops;
-	bma.firstblock = firstblock;
 
 	while (bno < end && n < *nmap) {
 		bool			need_alloc = false, wasdelay = false;
@@ -4419,7 +4369,7 @@ xfs_bmapi_write(
 			 * the refcount btree for orphan recovery.
 			 */
 			if (whichfork == XFS_COW_FORK) {
-				error = xfs_refcount_alloc_cow_extent(mp, dfops,
+				error = xfs_refcount_alloc_cow_extent(tp,
 						bma.blkno, bma.length);
 				if (error)
 					goto error0;
@@ -4493,15 +4443,7 @@ error0:
 		xfs_trans_log_inode(tp, ip, bma.logflags);
 
 	if (bma.cur) {
-		if (!error) {
-			ASSERT(*firstblock == NULLFSBLOCK ||
-			       XFS_FSB_TO_AGNO(mp, *firstblock) <=
-			       XFS_FSB_TO_AGNO(mp,
-				       bma.cur->bc_private.b.firstblock));
-			*firstblock = bma.cur->bc_private.b.firstblock;
-		}
-		xfs_btree_del_cursor(bma.cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(bma.cur, error);
 	}
 	if (!error)
 		xfs_bmap_validate_ret(orig_bno, orig_len, orig_flags, orig_mval,
@@ -4516,13 +4458,11 @@ xfs_bmapi_remap(
 	xfs_fileoff_t		bno,
 	xfs_filblks_t		len,
 	xfs_fsblock_t		startblock,
-	struct xfs_defer_ops	*dfops,
 	int			flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
 	struct xfs_btree_cur	*cur = NULL;
-	xfs_fsblock_t		firstblock = NULLFSBLOCK;
 	struct xfs_bmbt_irec	got;
 	struct xfs_iext_cursor	icur;
 	int			whichfork = xfs_bmapi_whichfork(flags);
@@ -4565,8 +4505,6 @@ xfs_bmapi_remap(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = firstblock;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -4579,7 +4517,7 @@ xfs_bmapi_remap(
 		got.br_state = XFS_EXT_NORM;
 
 	error = xfs_bmap_add_extent_hole_real(tp, ip, whichfork, &icur,
-			&cur, &got, &firstblock, dfops, &logflags, flags);
+			&cur, &got, &logflags, flags);
 	if (error)
 		goto error0;
 
@@ -4599,10 +4537,8 @@ error0:
 
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
-	if (cur) {
-		xfs_btree_del_cursor(cur,
-				error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
-	}
+	if (cur)
+		xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -4898,7 +4834,6 @@ xfs_bmap_del_extent_real(
 	xfs_inode_t		*ip,	/* incore inode pointer */
 	xfs_trans_t		*tp,	/* current transaction pointer */
 	struct xfs_iext_cursor	*icur,
-	struct xfs_defer_ops	*dfops,	/* list of extents to be freed */
 	xfs_btree_cur_t		*cur,	/* if null, not a btree */
 	xfs_bmbt_irec_t		*del,	/* data to remove from extents */
 	int			*logflagsp, /* inode logging flags */
@@ -4913,7 +4848,7 @@ xfs_bmap_del_extent_real(
 	struct xfs_bmbt_irec	got;	/* current extent entry */
 	xfs_fileoff_t		got_endoff;	/* first offset past got */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_mount_t		*mp;	/* mount structure */
 	xfs_filblks_t		nblks;	/* quota/sb block count */
 	xfs_bmbt_irec_t		new;	/* new record to be inserted */
@@ -5104,7 +5039,7 @@ xfs_bmap_del_extent_real(
 	}
 
 	/* remove reverse mapping */
-	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, del);
+	error = xfs_rmap_unmap_extent(tp, ip, whichfork, del);
 	if (error)
 		goto done;
 
@@ -5113,11 +5048,11 @@ xfs_bmap_del_extent_real(
 	 */
 	if (do_fx && !(bflags & XFS_BMAPI_REMAP)) {
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
-			error = xfs_refcount_decrease_extent(mp, dfops, del);
+			error = xfs_refcount_decrease_extent(tp, del);
 			if (error)
 				goto done;
 		} else {
-			__xfs_bmap_add_free(mp, dfops, del->br_startblock,
+			__xfs_bmap_add_free(tp, del->br_startblock,
 					del->br_blockcount, NULL,
 					(bflags & XFS_BMAPI_NODISCARD) ||
 					del->br_state == XFS_EXT_UNWRITTEN);
@@ -5148,26 +5083,23 @@ done:
  */
 int						/* error */
 __xfs_bunmapi(
-	xfs_trans_t		*tp,		/* transaction pointer */
+	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_inode	*ip,		/* incore inode */
 	xfs_fileoff_t		start,		/* first file offset deleted */
 	xfs_filblks_t		*rlen,		/* i/o: amount remaining */
 	int			flags,		/* misc flags */
-	xfs_extnum_t		nexts,		/* number of extents max */
-	xfs_fsblock_t		*firstblock,	/* first allocated block
-						   controls a.g. for allocs */
-	struct xfs_defer_ops	*dfops)		/* i/o: deferred updates */
+	xfs_extnum_t		nexts)		/* number of extents max */
 {
-	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
-	xfs_bmbt_irec_t		del;		/* extent being deleted */
+	struct xfs_btree_cur	*cur;		/* bmap btree cursor */
+	struct xfs_bmbt_irec	del;		/* extent being deleted */
 	int			error;		/* error return value */
 	xfs_extnum_t		extno;		/* extent number in list */
-	xfs_bmbt_irec_t		got;		/* current extent record */
-	xfs_ifork_t		*ifp;		/* inode fork pointer */
+	struct xfs_bmbt_irec	got;		/* current extent record */
+	struct xfs_ifork	*ifp;		/* inode fork pointer */
 	int			isrt;		/* freeing in rt area */
 	int			logflags;	/* transaction logging flags */
 	xfs_extlen_t		mod;		/* rt extent offset */
-	xfs_mount_t		*mp;		/* mount structure */
+	struct xfs_mount	*mp;		/* mount structure */
 	int			tmp_logflags;	/* partial logging flags */
 	int			wasdel;		/* was a delayed alloc extent */
 	int			whichfork;	/* data or attribute fork */
@@ -5230,8 +5162,6 @@ __xfs_bunmapi(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	} else
 		cur = NULL;
@@ -5347,7 +5277,7 @@ __xfs_bunmapi(
 			del.br_state = XFS_EXT_UNWRITTEN;
 			error = xfs_bmap_add_extent_unwritten_real(tp, ip,
 					whichfork, &icur, &cur, &del,
-					firstblock, dfops, &logflags);
+					&logflags);
 			if (error)
 				goto error0;
 			goto nodelete;
@@ -5404,8 +5334,7 @@ __xfs_bunmapi(
 				prev.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&prev, firstblock, dfops,
-						&logflags);
+						&prev, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5414,8 +5343,7 @@ __xfs_bunmapi(
 				del.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&del, firstblock, dfops,
-						&logflags);
+						&del, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5427,8 +5355,8 @@ delete:
 			error = xfs_bmap_del_extent_delay(ip, whichfork, &icur,
 					&got, &del);
 		} else {
-			error = xfs_bmap_del_extent_real(ip, tp, &icur, dfops,
-					cur, &del, &tmp_logflags, whichfork,
+			error = xfs_bmap_del_extent_real(ip, tp, &icur, cur,
+					&del, &tmp_logflags, whichfork,
 					flags);
 			logflags |= tmp_logflags;
 		}
@@ -5462,8 +5390,8 @@ nodelete:
 	 */
 	if (xfs_bmap_needs_btree(ip, whichfork)) {
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops,
-			&cur, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
+				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 		if (error)
 			goto error0;
@@ -5501,12 +5429,9 @@ error0:
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	if (cur) {
-		if (!error) {
-			*firstblock = cur->bc_private.b.firstblock;
+		if (!error)
 			cur->bc_private.b.allocated = 0;
-		}
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	}
 	return error;
 }
@@ -5520,14 +5445,11 @@ xfs_bunmapi(
 	xfs_filblks_t		len,
 	int			flags,
 	xfs_extnum_t		nexts,
-	xfs_fsblock_t		*firstblock,
-	struct xfs_defer_ops	*dfops,
 	int			*done)
 {
 	int			error;
 
-	error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts, firstblock,
-			dfops);
+	error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts);
 	*done = (len == 0);
 	return error;
 }
@@ -5570,6 +5492,7 @@ xfs_bmse_can_merge(
  */
 STATIC int
 xfs_bmse_merge(
+	struct xfs_trans		*tp,
 	struct xfs_inode		*ip,
 	int				whichfork,
 	xfs_fileoff_t			shift,		/* shift fsb */
@@ -5577,8 +5500,7 @@ xfs_bmse_merge(
 	struct xfs_bmbt_irec		*got,		/* extent to shift */
 	struct xfs_bmbt_irec		*left,		/* preceding extent */
 	struct xfs_btree_cur		*cur,
-	int				*logflags,	/* output */
-	struct xfs_defer_ops		*dfops)
+	int				*logflags)	/* output */
 {
 	struct xfs_bmbt_irec		new;
 	xfs_filblks_t			blockcount;
@@ -5634,23 +5556,23 @@ done:
 			&new);
 
 	/* update reverse mapping. rmap functions merge the rmaps for us */
-	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, got);
+	error = xfs_rmap_unmap_extent(tp, ip, whichfork, got);
 	if (error)
 		return error;
 	memcpy(&new, got, sizeof(new));
 	new.br_startoff = left->br_startoff + left->br_blockcount;
-	return xfs_rmap_map_extent(mp, dfops, ip, whichfork, &new);
+	return xfs_rmap_map_extent(tp, ip, whichfork, &new);
 }
 
 static int
 xfs_bmap_shift_update_extent(
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_iext_cursor	*icur,
 	struct xfs_bmbt_irec	*got,
 	struct xfs_btree_cur	*cur,
 	int			*logflags,
-	struct xfs_defer_ops	*dfops,
 	xfs_fileoff_t		startoff)
 {
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5678,10 +5600,10 @@ xfs_bmap_shift_update_extent(
 			got);
 
 	/* update reverse mapping */
-	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, &prev);
+	error = xfs_rmap_unmap_extent(tp, ip, whichfork, &prev);
 	if (error)
 		return error;
-	return xfs_rmap_map_extent(mp, dfops, ip, whichfork, got);
+	return xfs_rmap_map_extent(tp, ip, whichfork, got);
 }
 
 int
@@ -5690,9 +5612,7 @@ xfs_bmap_collapse_extents(
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		*next_fsb,
 	xfs_fileoff_t		offset_shift_fsb,
-	bool			*done,
-	xfs_fsblock_t		*firstblock,
-	struct xfs_defer_ops	*dfops)
+	bool			*done)
 {
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5725,8 +5645,6 @@ xfs_bmap_collapse_extents(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5745,9 +5663,9 @@ xfs_bmap_collapse_extents(
 		}
 
 		if (xfs_bmse_can_merge(&prev, &got, offset_shift_fsb)) {
-			error = xfs_bmse_merge(ip, whichfork, offset_shift_fsb,
-					&icur, &got, &prev, cur, &logflags,
-					dfops);
+			error = xfs_bmse_merge(tp, ip, whichfork,
+					offset_shift_fsb, &icur, &got, &prev,
+					cur, &logflags);
 			if (error)
 				goto del_cursor;
 			goto done;
@@ -5759,8 +5677,8 @@ xfs_bmap_collapse_extents(
 		}
 	}
 
-	error = xfs_bmap_shift_update_extent(ip, whichfork, &icur, &got, cur,
-			&logflags, dfops, new_startoff);
+	error = xfs_bmap_shift_update_extent(tp, ip, whichfork, &icur, &got,
+			cur, &logflags, new_startoff);
 	if (error)
 		goto del_cursor;
 
@@ -5773,8 +5691,7 @@ done:
 	*next_fsb = got.br_startoff;
 del_cursor:
 	if (cur)
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	return error;
@@ -5813,9 +5730,7 @@ xfs_bmap_insert_extents(
 	xfs_fileoff_t		*next_fsb,
 	xfs_fileoff_t		offset_shift_fsb,
 	bool			*done,
-	xfs_fileoff_t		stop_fsb,
-	xfs_fsblock_t		*firstblock,
-	struct xfs_defer_ops	*dfops)
+	xfs_fileoff_t		stop_fsb)
 {
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5848,8 +5763,6 @@ xfs_bmap_insert_extents(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5891,8 +5804,8 @@ xfs_bmap_insert_extents(
 			WARN_ON_ONCE(1);
 	}
 
-	error = xfs_bmap_shift_update_extent(ip, whichfork, &icur, &got, cur,
-			&logflags, dfops, new_startoff);
+	error = xfs_bmap_shift_update_extent(tp, ip, whichfork, &icur, &got,
+			cur, &logflags, new_startoff);
 	if (error)
 		goto del_cursor;
 
@@ -5905,8 +5818,7 @@ xfs_bmap_insert_extents(
 	*next_fsb = got.br_startoff;
 del_cursor:
 	if (cur)
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	return error;
@@ -5922,9 +5834,7 @@ STATIC int
 xfs_bmap_split_extent_at(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
-	xfs_fileoff_t		split_fsb,
-	xfs_fsblock_t		*firstfsb,
-	struct xfs_defer_ops	*dfops)
+	xfs_fileoff_t		split_fsb)
 {
 	int				whichfork = XFS_DATA_FORK;
 	struct xfs_btree_cur		*cur = NULL;
@@ -5973,8 +5883,6 @@ xfs_bmap_split_extent_at(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstfsb;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
@@ -6018,16 +5926,15 @@ xfs_bmap_split_extent_at(
 		int tmp_logflags; /* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, dfops,
-				&cur, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
+				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 	}
 
 del_cursor:
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
-		xfs_btree_del_cursor(cur,
-				error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	}
 
 	if (logflags)
@@ -6042,8 +5949,6 @@ xfs_bmap_split_extent(
 {
 	struct xfs_mount        *mp = ip->i_mount;
 	struct xfs_trans        *tp;
-	struct xfs_defer_ops    dfops;
-	xfs_fsblock_t           firstfsb;
 	int                     error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write,
@@ -6054,21 +5959,13 @@ xfs_bmap_split_extent(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-	xfs_defer_init(&dfops, &firstfsb);
-
-	error = xfs_bmap_split_extent_at(tp, ip, split_fsb,
-			&firstfsb, &dfops);
-	if (error)
-		goto out;
-
-	error = xfs_defer_finish(&tp, &dfops);
+	error = xfs_bmap_split_extent_at(tp, ip, split_fsb);
 	if (error)
 		goto out;
 
 	return xfs_trans_commit(tp);
 
 out:
-	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -6085,20 +5982,18 @@ xfs_bmap_is_update_needed(
 /* Record a bmap intent. */
 static int
 __xfs_bmap_add(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	enum xfs_bmap_intent_type	type,
 	struct xfs_inode		*ip,
 	int				whichfork,
 	struct xfs_bmbt_irec		*bmap)
 {
-	int				error;
 	struct xfs_bmap_intent		*bi;
 
-	trace_xfs_bmap_defer(mp,
-			XFS_FSB_TO_AGNO(mp, bmap->br_startblock),
+	trace_xfs_bmap_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
 			type,
-			XFS_FSB_TO_AGBNO(mp, bmap->br_startblock),
+			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
 			ip->i_ino, whichfork,
 			bmap->br_startoff,
 			bmap->br_blockcount,
@@ -6111,44 +6006,34 @@ __xfs_bmap_add(
 	bi->bi_whichfork = whichfork;
 	bi->bi_bmap = *bmap;
 
-	error = xfs_defer_ijoin(dfops, bi->bi_owner);
-	if (error) {
-		kmem_free(bi);
-		return error;
-	}
-
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
 	return 0;
 }
 
 /* Map an extent into a file. */
 int
 xfs_bmap_map_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*PREV)
 {
 	if (!xfs_bmap_is_update_needed(PREV))
 		return 0;
 
-	return __xfs_bmap_add(mp, dfops, XFS_BMAP_MAP, ip,
-			XFS_DATA_FORK, PREV);
+	return __xfs_bmap_add(tp, XFS_BMAP_MAP, ip, XFS_DATA_FORK, PREV);
 }
 
 /* Unmap an extent out of a file. */
 int
 xfs_bmap_unmap_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*PREV)
 {
 	if (!xfs_bmap_is_update_needed(PREV))
 		return 0;
 
-	return __xfs_bmap_add(mp, dfops, XFS_BMAP_UNMAP, ip,
-			XFS_DATA_FORK, PREV);
+	return __xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, XFS_DATA_FORK, PREV);
 }
 
 /*
@@ -6158,7 +6043,6 @@ xfs_bmap_unmap_extent(
 int
 xfs_bmap_finish_one(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dfops,
 	struct xfs_inode		*ip,
 	enum xfs_bmap_intent_type	type,
 	int				whichfork,
@@ -6167,17 +6051,9 @@ xfs_bmap_finish_one(
 	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
-	xfs_fsblock_t			firstfsb;
 	int				error = 0;
 
-	/*
-	 * firstfsb is tied to the transaction lifetime and is used to
-	 * ensure correct AG locking order and schedule work item
-	 * continuations.  XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us
-	 * to only making one bmap call per transaction, so it should
-	 * be safe to have it as a local variable here.
-	 */
-	firstfsb = NULLFSBLOCK;
+	ASSERT(tp->t_firstblock == NULLFSBLOCK);
 
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
@@ -6194,12 +6070,12 @@ xfs_bmap_finish_one(
 	switch (type) {
 	case XFS_BMAP_MAP:
 		error = xfs_bmapi_remap(tp, ip, startoff, *blockcount,
-				startblock, dfops, 0);
+				startblock, 0);
 		*blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
 		error = __xfs_bunmapi(tp, ip, startoff, blockcount,
-				XFS_BMAPI_REMAP, 1, &firstfsb, dfops);
+				XFS_BMAPI_REMAP, 1);
 		break;
 	default:
 		ASSERT(0);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 9b49ddf99c41..b6e9b639e731 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -19,8 +19,6 @@ extern kmem_zone_t	*xfs_bmap_free_item_zone;
  * Argument structure for xfs_bmap_alloc.
  */
 struct xfs_bmalloca {
-	xfs_fsblock_t		*firstblock; /* i/o first block allocated */
-	struct xfs_defer_ops	*dfops;	/* bmap freelist */
 	struct xfs_trans	*tp;	/* transaction pointer */
 	struct xfs_inode	*ip;	/* incore inode pointer */
 	struct xfs_bmbt_irec	prev;	/* extent before the new one */
@@ -68,8 +66,6 @@ struct xfs_extent_free_item
 #define XFS_BMAPI_METADATA	0x002	/* mapping metadata not user data */
 #define XFS_BMAPI_ATTRFORK	0x004	/* use attribute fork not data */
 #define XFS_BMAPI_PREALLOC	0x008	/* preallocation op: unwritten space */
-#define XFS_BMAPI_IGSTATE	0x010	/* Ignore state - */
-					/* combine contig. space */
 #define XFS_BMAPI_CONTIG	0x020	/* must allocate only one extent */
 /*
  * unwritten extent conversion - this needs write cache flushing and no additional
@@ -116,7 +112,6 @@ struct xfs_extent_free_item
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \
 	{ XFS_BMAPI_ATTRFORK,	"ATTRFORK" }, \
 	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \
-	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \
 	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \
 	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
 	{ XFS_BMAPI_ZERO,	"ZERO" }, \
@@ -189,9 +184,9 @@ void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
 void	xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
-void	__xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-			  xfs_fsblock_t bno, xfs_filblks_t len,
-			  struct xfs_owner_info *oinfo, bool skip_discard);
+void	__xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno,
+		xfs_filblks_t len, struct xfs_owner_info *oinfo,
+		bool skip_discard);
 void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
 int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
@@ -205,17 +200,13 @@ int	xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
 		int *nmap, int flags);
 int	xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
-		xfs_fsblock_t *firstblock, xfs_extlen_t total,
-		struct xfs_bmbt_irec *mval, int *nmap,
-		struct xfs_defer_ops *dfops);
+		xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap);
 int	__xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t *rlen, int flags,
-		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops);
+		xfs_extnum_t nexts);
 int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
-		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops, int *done);
+		xfs_extnum_t nexts, int *done);
 int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
 		struct xfs_bmbt_irec *del);
@@ -225,14 +216,12 @@ void	xfs_bmap_del_extent_cow(struct xfs_inode *ip,
 uint	xfs_default_attroffset(struct xfs_inode *ip);
 int	xfs_bmap_collapse_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
-		bool *done, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops);
+		bool *done);
 int	xfs_bmap_can_insert_extents(struct xfs_inode *ip, xfs_fileoff_t off,
 		xfs_fileoff_t shift);
 int	xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
-		bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops);
+		bool *done, xfs_fileoff_t stop_fsb);
 int	xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset);
 int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 		xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,
@@ -241,13 +230,12 @@ int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 
 static inline void
 xfs_bmap_add_free(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	struct xfs_owner_info		*oinfo)
 {
-	__xfs_bmap_add_free(mp, dfops, bno, len, oinfo, false);
+	__xfs_bmap_add_free(tp, bno, len, oinfo, false);
 }
 
 enum xfs_bmap_intent_type {
@@ -263,14 +251,14 @@ struct xfs_bmap_intent {
 	struct xfs_bmbt_irec			bi_bmap;
 };
 
-int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, enum xfs_bmap_intent_type type,
-		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
+int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_inode *ip,
+		enum xfs_bmap_intent_type type, int whichfork,
+		xfs_fileoff_t startoff, xfs_fsblock_t startblock,
 		xfs_filblks_t *blockcount, xfs_exntst_t state);
-int	xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
-int	xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
+int	xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap);
+int	xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap);
 
 static inline int xfs_bmap_fork_to_state(int whichfork)
 {
@@ -289,6 +277,6 @@ xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
 
 int	xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
-		struct xfs_defer_ops *dfops, int flags);
+		int flags);
 
 #endif	/* __XFS_BMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index e1a2d9ceb615..cdb74d2e2a43 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -175,8 +175,6 @@ xfs_bmbt_dup_cursor(
 	 * Copy the firstblock, dfops, and flags values,
 	 * since init cursor doesn't get them.
 	 */
-	new->bc_private.b.firstblock = cur->bc_private.b.firstblock;
-	new->bc_private.b.dfops = cur->bc_private.b.dfops;
 	new->bc_private.b.flags = cur->bc_private.b.flags;
 
 	return new;
@@ -187,12 +185,11 @@ xfs_bmbt_update_cursor(
 	struct xfs_btree_cur	*src,
 	struct xfs_btree_cur	*dst)
 {
-	ASSERT((dst->bc_private.b.firstblock != NULLFSBLOCK) ||
+	ASSERT((dst->bc_tp->t_firstblock != NULLFSBLOCK) ||
 	       (dst->bc_private.b.ip->i_d.di_flags & XFS_DIFLAG_REALTIME));
-	ASSERT(dst->bc_private.b.dfops == src->bc_private.b.dfops);
 
 	dst->bc_private.b.allocated += src->bc_private.b.allocated;
-	dst->bc_private.b.firstblock = src->bc_private.b.firstblock;
+	dst->bc_tp->t_firstblock = src->bc_tp->t_firstblock;
 
 	src->bc_private.b.allocated = 0;
 }
@@ -210,8 +207,7 @@ xfs_bmbt_alloc_block(
 	memset(&args, 0, sizeof(args));
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
-	args.fsbno = cur->bc_private.b.firstblock;
-	args.firstblock = args.fsbno;
+	args.fsbno = cur->bc_tp->t_firstblock;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_private.b.ip->i_ino,
 			cur->bc_private.b.whichfork);
 
@@ -230,7 +226,7 @@ xfs_bmbt_alloc_block(
 		 * block allocation here and corrupt the filesystem.
 		 */
 		args.minleft = args.tp->t_blk_res;
-	} else if (cur->bc_private.b.dfops->dop_low) {
+	} else if (cur->bc_tp->t_flags & XFS_TRANS_LOWMODE) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -257,7 +253,7 @@ xfs_bmbt_alloc_block(
 		error = xfs_alloc_vextent(&args);
 		if (error)
 			goto error0;
-		cur->bc_private.b.dfops->dop_low = true;
+		cur->bc_tp->t_flags |= XFS_TRANS_LOWMODE;
 	}
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		*stat = 0;
@@ -265,7 +261,7 @@ xfs_bmbt_alloc_block(
 	}
 
 	ASSERT(args.len == 1);
-	cur->bc_private.b.firstblock = args.fsbno;
+	cur->bc_tp->t_firstblock = args.fsbno;
 	cur->bc_private.b.allocated++;
 	cur->bc_private.b.ip->i_d.di_nblocks++;
 	xfs_trans_log_inode(args.tp, cur->bc_private.b.ip, XFS_ILOG_CORE);
@@ -293,7 +289,7 @@ xfs_bmbt_free_block(
 	struct xfs_owner_info	oinfo;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_private.b.whichfork);
-	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, fsbno, 1, &oinfo);
+	xfs_bmap_add_free(cur->bc_tp, fsbno, 1, &oinfo);
 	ip->i_d.di_nblocks--;
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -564,8 +560,6 @@ xfs_bmbt_init_cursor(
 
 	cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
 	cur->bc_private.b.ip = ip;
-	cur->bc_private.b.firstblock = NULLFSBLOCK;
-	cur->bc_private.b.dfops = NULL;
 	cur->bc_private.b.allocated = 0;
 	cur->bc_private.b.flags = 0;
 	cur->bc_private.b.whichfork = whichfork;
@@ -645,7 +639,7 @@ xfs_bmbt_change_owner(
 	cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER;
 
 	error = xfs_btree_change_owner(cur, new_owner, buffer_list);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 0a4fdf7f11a7..e3b3e9dce5da 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -7,7 +7,6 @@
 #define	__XFS_BTREE_H__
 
 struct xfs_buf;
-struct xfs_defer_ops;
 struct xfs_inode;
 struct xfs_mount;
 struct xfs_trans;
@@ -209,14 +208,11 @@ typedef struct xfs_btree_cur
 	union {
 		struct {			/* needed for BNO, CNT, INO */
 			struct xfs_buf	*agbp;	/* agf/agi buffer pointer */
-			struct xfs_defer_ops *dfops;	/* deferred updates */
 			xfs_agnumber_t	agno;	/* ag number */
 			union xfs_btree_cur_private	priv;
 		} a;
 		struct {			/* needed for BMAP */
 			struct xfs_inode *ip;	/* pointer to our inode */
-			struct xfs_defer_ops *dfops;	/* deferred updates */
-			xfs_fsblock_t	firstblock;	/* 1st blk allocated */
 			int		allocated;	/* count of alloced */
 			short		forksize;	/* fork's inode space */
 			char		whichfork;	/* data or attr fork */
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 8a301402bbc4..376bee94b5dd 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -1481,6 +1481,7 @@ xfs_da3_node_lookup_int(
 	int			error;
 	int			retval;
 	unsigned int		expected_level = 0;
+	uint16_t		magic;
 	struct xfs_inode	*dp = state->args->dp;
 
 	args = state->args;
@@ -1505,25 +1506,27 @@ xfs_da3_node_lookup_int(
 			return error;
 		}
 		curr = blk->bp->b_addr;
-		blk->magic = be16_to_cpu(curr->magic);
+		magic = be16_to_cpu(curr->magic);
 
-		if (blk->magic == XFS_ATTR_LEAF_MAGIC ||
-		    blk->magic == XFS_ATTR3_LEAF_MAGIC) {
+		if (magic == XFS_ATTR_LEAF_MAGIC ||
+		    magic == XFS_ATTR3_LEAF_MAGIC) {
 			blk->magic = XFS_ATTR_LEAF_MAGIC;
 			blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
 			break;
 		}
 
-		if (blk->magic == XFS_DIR2_LEAFN_MAGIC ||
-		    blk->magic == XFS_DIR3_LEAFN_MAGIC) {
+		if (magic == XFS_DIR2_LEAFN_MAGIC ||
+		    magic == XFS_DIR3_LEAFN_MAGIC) {
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
 							      blk->bp, NULL);
 			break;
 		}
 
-		blk->magic = XFS_DA_NODE_MAGIC;
+		if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC)
+			return -EFSCORRUPTED;
 
+		blk->magic = XFS_DA_NODE_MAGIC;
 
 		/*
 		 * Search an intermediate node for a match.
@@ -2059,11 +2062,9 @@ xfs_da_grow_inode_int(
 	 * Try mapping it in one filesystem block.
 	 */
 	nmap = 1;
-	ASSERT(args->firstblock != NULL);
 	error = xfs_bmapi_write(tp, dp, *bno, count,
 			xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG,
-			args->firstblock, args->total, &map, &nmap,
-			args->dfops);
+			args->total, &map, &nmap);
 	if (error)
 		return error;
 
@@ -2085,8 +2086,7 @@ xfs_da_grow_inode_int(
 			c = (int)(*bno + count - b);
 			error = xfs_bmapi_write(tp, dp, b, c,
 					xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA,
-					args->firstblock, args->total,
-					&mapp[mapi], &nmap, args->dfops);
+					args->total, &mapp[mapi], &nmap);
 			if (error)
 				goto out_free_map;
 			if (nmap < 1)
@@ -2375,13 +2375,13 @@ done:
  */
 int
 xfs_da_shrink_inode(
-	xfs_da_args_t	*args,
-	xfs_dablk_t	dead_blkno,
-	struct xfs_buf	*dead_buf)
+	struct xfs_da_args	*args,
+	xfs_dablk_t		dead_blkno,
+	struct xfs_buf		*dead_buf)
 {
-	xfs_inode_t *dp;
-	int done, error, w, count;
-	xfs_trans_t *tp;
+	struct xfs_inode	*dp;
+	int			done, error, w, count;
+	struct xfs_trans	*tp;
 
 	trace_xfs_da_shrink_inode(args);
 
@@ -2395,8 +2395,7 @@ xfs_da_shrink_inode(
 		 * the last block to the place we want to kill.
 		 */
 		error = xfs_bunmapi(tp, dp, dead_blkno, count,
-				    xfs_bmapi_aflag(w), 0, args->firstblock,
-				    args->dfops, &done);
+				    xfs_bmapi_aflag(w), 0, &done);
 		if (error == -ENOSPC) {
 			if (w != XFS_DATA_FORK)
 				break;
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 28260073ae71..84dd865b6c3d 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -7,7 +7,6 @@
 #ifndef __XFS_DA_BTREE_H__
 #define	__XFS_DA_BTREE_H__
 
-struct xfs_defer_ops;
 struct xfs_inode;
 struct xfs_trans;
 struct zone;
@@ -57,8 +56,6 @@ typedef struct xfs_da_args {
 	xfs_dahash_t	hashval;	/* hash value of name */
 	xfs_ino_t	inumber;	/* input/output inode number */
 	struct xfs_inode *dp;		/* directory inode to manipulate */
-	xfs_fsblock_t	*firstblock;	/* ptr to firstblock for bmap calls */
-	struct xfs_defer_ops *dfops;	/* ptr to freelist for bmap_finish */
 	struct xfs_trans *trans;	/* current trans (changes over time) */
 	xfs_extlen_t	total;		/* total blocks needed, for 1st bmap */
 	int		whichfork;	/* data or attribute fork */
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index c3e5bffda4f5..e792b167150a 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -14,6 +14,9 @@
 #include "xfs_mount.h"
 #include "xfs_defer.h"
 #include "xfs_trans.h"
+#include "xfs_buf_item.h"
+#include "xfs_inode.h"
+#include "xfs_inode_item.h"
 #include "xfs_trace.h"
 
 /*
@@ -177,146 +180,157 @@ static const struct xfs_defer_op_type *defer_op_types[XFS_DEFER_OPS_TYPE_MAX];
  * the pending list.
  */
 STATIC void
-xfs_defer_intake_work(
-	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop)
+xfs_defer_create_intents(
+	struct xfs_trans		*tp)
 {
 	struct list_head		*li;
 	struct xfs_defer_pending	*dfp;
 
-	list_for_each_entry(dfp, &dop->dop_intake, dfp_list) {
+	list_for_each_entry(dfp, &tp->t_dfops, dfp_list) {
 		dfp->dfp_intent = dfp->dfp_type->create_intent(tp,
 				dfp->dfp_count);
-		trace_xfs_defer_intake_work(tp->t_mountp, dfp);
+		trace_xfs_defer_create_intent(tp->t_mountp, dfp);
 		list_sort(tp->t_mountp, &dfp->dfp_work,
 				dfp->dfp_type->diff_items);
 		list_for_each(li, &dfp->dfp_work)
 			dfp->dfp_type->log_item(tp, dfp->dfp_intent, li);
 	}
-
-	list_splice_tail_init(&dop->dop_intake, &dop->dop_pending);
 }
 
 /* Abort all the intents that were committed. */
 STATIC void
 xfs_defer_trans_abort(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
-	int				error)
+	struct list_head		*dop_pending)
 {
 	struct xfs_defer_pending	*dfp;
 
-	trace_xfs_defer_trans_abort(tp->t_mountp, dop, _RET_IP_);
+	trace_xfs_defer_trans_abort(tp, _RET_IP_);
 
 	/* Abort intent items that don't have a done item. */
-	list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
+	list_for_each_entry(dfp, dop_pending, dfp_list) {
 		trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
 		if (dfp->dfp_intent && !dfp->dfp_done) {
 			dfp->dfp_type->abort_intent(dfp->dfp_intent);
 			dfp->dfp_intent = NULL;
 		}
 	}
-
-	/* Shut down FS. */
-	xfs_force_shutdown(tp->t_mountp, (error == -EFSCORRUPTED) ?
-			SHUTDOWN_CORRUPT_INCORE : SHUTDOWN_META_IO_ERROR);
 }
 
 /* Roll a transaction so we can do some deferred op processing. */
 STATIC int
 xfs_defer_trans_roll(
-	struct xfs_trans		**tp,
-	struct xfs_defer_ops		*dop)
+	struct xfs_trans		**tpp)
 {
+	struct xfs_trans		*tp = *tpp;
+	struct xfs_buf_log_item		*bli;
+	struct xfs_inode_log_item	*ili;
+	struct xfs_log_item		*lip;
+	struct xfs_buf			*bplist[XFS_DEFER_OPS_NR_BUFS];
+	struct xfs_inode		*iplist[XFS_DEFER_OPS_NR_INODES];
+	int				bpcount = 0, ipcount = 0;
 	int				i;
 	int				error;
 
-	/* Log all the joined inodes. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
-		xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE);
-
-	/* Hold the (previously bjoin'd) buffer locked across the roll. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++)
-		xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]);
+	list_for_each_entry(lip, &tp->t_items, li_trans) {
+		switch (lip->li_type) {
+		case XFS_LI_BUF:
+			bli = container_of(lip, struct xfs_buf_log_item,
+					   bli_item);
+			if (bli->bli_flags & XFS_BLI_HOLD) {
+				if (bpcount >= XFS_DEFER_OPS_NR_BUFS) {
+					ASSERT(0);
+					return -EFSCORRUPTED;
+				}
+				xfs_trans_dirty_buf(tp, bli->bli_buf);
+				bplist[bpcount++] = bli->bli_buf;
+			}
+			break;
+		case XFS_LI_INODE:
+			ili = container_of(lip, struct xfs_inode_log_item,
+					   ili_item);
+			if (ili->ili_lock_flags == 0) {
+				if (ipcount >= XFS_DEFER_OPS_NR_INODES) {
+					ASSERT(0);
+					return -EFSCORRUPTED;
+				}
+				xfs_trans_log_inode(tp, ili->ili_inode,
+						    XFS_ILOG_CORE);
+				iplist[ipcount++] = ili->ili_inode;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
-	trace_xfs_defer_trans_roll((*tp)->t_mountp, dop, _RET_IP_);
+	trace_xfs_defer_trans_roll(tp, _RET_IP_);
 
 	/* Roll the transaction. */
-	error = xfs_trans_roll(tp);
+	error = xfs_trans_roll(tpp);
+	tp = *tpp;
 	if (error) {
-		trace_xfs_defer_trans_roll_error((*tp)->t_mountp, dop, error);
-		xfs_defer_trans_abort(*tp, dop, error);
+		trace_xfs_defer_trans_roll_error(tp, error);
 		return error;
 	}
-	dop->dop_committed = true;
 
 	/* Rejoin the joined inodes. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
-		xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0);
+	for (i = 0; i < ipcount; i++)
+		xfs_trans_ijoin(tp, iplist[i], 0);
 
 	/* Rejoin the buffers and dirty them so the log moves forward. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) {
-		xfs_trans_bjoin(*tp, dop->dop_bufs[i]);
-		xfs_trans_bhold(*tp, dop->dop_bufs[i]);
+	for (i = 0; i < bpcount; i++) {
+		xfs_trans_bjoin(tp, bplist[i]);
+		xfs_trans_bhold(tp, bplist[i]);
 	}
 
 	return error;
 }
 
-/* Do we have any work items to finish? */
-bool
-xfs_defer_has_unfinished_work(
-	struct xfs_defer_ops		*dop)
-{
-	return !list_empty(&dop->dop_pending) || !list_empty(&dop->dop_intake);
-}
-
 /*
- * Add this inode to the deferred op.  Each joined inode is relogged
- * each time we roll the transaction.
+ * Reset an already used dfops after finish.
  */
-int
-xfs_defer_ijoin(
-	struct xfs_defer_ops		*dop,
-	struct xfs_inode		*ip)
+static void
+xfs_defer_reset(
+	struct xfs_trans	*tp)
 {
-	int				i;
-
-	for (i = 0; i < XFS_DEFER_OPS_NR_INODES; i++) {
-		if (dop->dop_inodes[i] == ip)
-			return 0;
-		else if (dop->dop_inodes[i] == NULL) {
-			dop->dop_inodes[i] = ip;
-			return 0;
-		}
-	}
+	ASSERT(list_empty(&tp->t_dfops));
 
-	ASSERT(0);
-	return -EFSCORRUPTED;
+	/*
+	 * Low mode state transfers across transaction rolls to mirror dfops
+	 * lifetime. Clear it now that dfops is reset.
+	 */
+	tp->t_flags &= ~XFS_TRANS_LOWMODE;
 }
 
 /*
- * Add this buffer to the deferred op.  Each joined buffer is relogged
- * each time we roll the transaction.
+ * Free up any items left in the list.
  */
-int
-xfs_defer_bjoin(
-	struct xfs_defer_ops		*dop,
-	struct xfs_buf			*bp)
+static void
+xfs_defer_cancel_list(
+	struct xfs_mount		*mp,
+	struct list_head		*dop_list)
 {
-	int				i;
+	struct xfs_defer_pending	*dfp;
+	struct xfs_defer_pending	*pli;
+	struct list_head		*pwi;
+	struct list_head		*n;
 
-	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS; i++) {
-		if (dop->dop_bufs[i] == bp)
-			return 0;
-		else if (dop->dop_bufs[i] == NULL) {
-			dop->dop_bufs[i] = bp;
-			return 0;
+	/*
+	 * Free the pending items.  Caller should already have arranged
+	 * for the intent items to be released.
+	 */
+	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) {
+		trace_xfs_defer_cancel_list(mp, dfp);
+		list_del(&dfp->dfp_list);
+		list_for_each_safe(pwi, n, &dfp->dfp_work) {
+			list_del(pwi);
+			dfp->dfp_count--;
+			dfp->dfp_type->cancel_item(pwi);
 		}
+		ASSERT(dfp->dfp_count == 0);
+		kmem_free(dfp);
 	}
-
-	ASSERT(0);
-	return -EFSCORRUPTED;
 }
 
 /*
@@ -328,9 +342,8 @@ xfs_defer_bjoin(
  * If an inode is provided, relog it to the new transaction.
  */
 int
-xfs_defer_finish(
-	struct xfs_trans		**tp,
-	struct xfs_defer_ops		*dop)
+xfs_defer_finish_noroll(
+	struct xfs_trans		**tp)
 {
 	struct xfs_defer_pending	*dfp;
 	struct list_head		*li;
@@ -338,35 +351,28 @@ xfs_defer_finish(
 	void				*state;
 	int				error = 0;
 	void				(*cleanup_fn)(struct xfs_trans *, void *, int);
-	struct xfs_defer_ops		*orig_dop;
+	LIST_HEAD(dop_pending);
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
-	trace_xfs_defer_finish((*tp)->t_mountp, dop, _RET_IP_);
-
-	/*
-	 * Attach dfops to the transaction during deferred ops processing. This
-	 * explicitly causes calls into the allocator to defer AGFL block frees.
-	 * Note that this code can go away once all dfops users attach to the
-	 * associated tp.
-	 */
-	ASSERT(!(*tp)->t_agfl_dfops || ((*tp)->t_agfl_dfops == dop));
-	orig_dop = (*tp)->t_agfl_dfops;
-	(*tp)->t_agfl_dfops = dop;
+	trace_xfs_defer_finish(*tp, _RET_IP_);
 
 	/* Until we run out of pending work to finish... */
-	while (xfs_defer_has_unfinished_work(dop)) {
-		/* Log intents for work items sitting in the intake. */
-		xfs_defer_intake_work(*tp, dop);
-
-		/* Roll the transaction. */
-		error = xfs_defer_trans_roll(tp, dop);
+	while (!list_empty(&dop_pending) || !list_empty(&(*tp)->t_dfops)) {
+		/* log intents and pull in intake items */
+		xfs_defer_create_intents(*tp);
+		list_splice_tail_init(&(*tp)->t_dfops, &dop_pending);
+
+		/*
+		 * Roll the transaction.
+		 */
+		error = xfs_defer_trans_roll(tp);
 		if (error)
 			goto out;
 
 		/* Log an intent-done item for the first pending item. */
-		dfp = list_first_entry(&dop->dop_pending,
-				struct xfs_defer_pending, dfp_list);
+		dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
+				       dfp_list);
 		trace_xfs_defer_pending_finish((*tp)->t_mountp, dfp);
 		dfp->dfp_done = dfp->dfp_type->create_done(*tp, dfp->dfp_intent,
 				dfp->dfp_count);
@@ -377,7 +383,7 @@ xfs_defer_finish(
 		list_for_each_safe(li, n, &dfp->dfp_work) {
 			list_del(li);
 			dfp->dfp_count--;
-			error = dfp->dfp_type->finish_item(*tp, dop, li,
+			error = dfp->dfp_type->finish_item(*tp, li,
 					dfp->dfp_done, &state);
 			if (error == -EAGAIN) {
 				/*
@@ -396,7 +402,6 @@ xfs_defer_finish(
 				 */
 				if (cleanup_fn)
 					cleanup_fn(*tp, state, error);
-				xfs_defer_trans_abort(*tp, dop, error);
 				goto out;
 			}
 		}
@@ -425,72 +430,72 @@ xfs_defer_finish(
 	}
 
 out:
-	(*tp)->t_agfl_dfops = orig_dop;
-	if (error)
-		trace_xfs_defer_finish_error((*tp)->t_mountp, dop, error);
-	else
-		trace_xfs_defer_finish_done((*tp)->t_mountp, dop, _RET_IP_);
-	return error;
+	if (error) {
+		xfs_defer_trans_abort(*tp, &dop_pending);
+		xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE);
+		trace_xfs_defer_finish_error(*tp, error);
+		xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending);
+		xfs_defer_cancel(*tp);
+		return error;
+	}
+
+	trace_xfs_defer_finish_done(*tp, _RET_IP_);
+	return 0;
 }
 
-/*
- * Free up any items left in the list.
- */
-void
-xfs_defer_cancel(
-	struct xfs_defer_ops		*dop)
+int
+xfs_defer_finish(
+	struct xfs_trans	**tp)
 {
-	struct xfs_defer_pending	*dfp;
-	struct xfs_defer_pending	*pli;
-	struct list_head		*pwi;
-	struct list_head		*n;
-
-	trace_xfs_defer_cancel(NULL, dop, _RET_IP_);
+	int			error;
 
 	/*
-	 * Free the pending items.  Caller should already have arranged
-	 * for the intent items to be released.
+	 * Finish and roll the transaction once more to avoid returning to the
+	 * caller with a dirty transaction.
 	 */
-	list_for_each_entry_safe(dfp, pli, &dop->dop_intake, dfp_list) {
-		trace_xfs_defer_intake_cancel(NULL, dfp);
-		list_del(&dfp->dfp_list);
-		list_for_each_safe(pwi, n, &dfp->dfp_work) {
-			list_del(pwi);
-			dfp->dfp_count--;
-			dfp->dfp_type->cancel_item(pwi);
-		}
-		ASSERT(dfp->dfp_count == 0);
-		kmem_free(dfp);
-	}
-	list_for_each_entry_safe(dfp, pli, &dop->dop_pending, dfp_list) {
-		trace_xfs_defer_pending_cancel(NULL, dfp);
-		list_del(&dfp->dfp_list);
-		list_for_each_safe(pwi, n, &dfp->dfp_work) {
-			list_del(pwi);
-			dfp->dfp_count--;
-			dfp->dfp_type->cancel_item(pwi);
+	error = xfs_defer_finish_noroll(tp);
+	if (error)
+		return error;
+	if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
+		error = xfs_defer_trans_roll(tp);
+		if (error) {
+			xfs_force_shutdown((*tp)->t_mountp,
+					   SHUTDOWN_CORRUPT_INCORE);
+			return error;
 		}
-		ASSERT(dfp->dfp_count == 0);
-		kmem_free(dfp);
 	}
+	xfs_defer_reset(*tp);
+	return 0;
+}
+
+void
+xfs_defer_cancel(
+	struct xfs_trans	*tp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+
+	trace_xfs_defer_cancel(tp, _RET_IP_);
+	xfs_defer_cancel_list(mp, &tp->t_dfops);
 }
 
 /* Add an item for later deferred processing. */
 void
 xfs_defer_add(
-	struct xfs_defer_ops		*dop,
+	struct xfs_trans		*tp,
 	enum xfs_defer_ops_type		type,
 	struct list_head		*li)
 {
 	struct xfs_defer_pending	*dfp = NULL;
 
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
 	/*
 	 * Add the item to a pending item at the end of the intake list.
 	 * If the last pending item has the same type, reuse it.  Else,
 	 * create a new pending item at the end of the intake list.
 	 */
-	if (!list_empty(&dop->dop_intake)) {
-		dfp = list_last_entry(&dop->dop_intake,
+	if (!list_empty(&tp->t_dfops)) {
+		dfp = list_last_entry(&tp->t_dfops,
 				struct xfs_defer_pending, dfp_list);
 		if (dfp->dfp_type->type != type ||
 		    (dfp->dfp_type->max_items &&
@@ -505,7 +510,7 @@ xfs_defer_add(
 		dfp->dfp_done = NULL;
 		dfp->dfp_count = 0;
 		INIT_LIST_HEAD(&dfp->dfp_work);
-		list_add_tail(&dfp->dfp_list, &dop->dop_intake);
+		list_add_tail(&dfp->dfp_list, &tp->t_dfops);
 	}
 
 	list_add_tail(li, &dfp->dfp_work);
@@ -520,15 +525,25 @@ xfs_defer_init_op_type(
 	defer_op_types[type->type] = type;
 }
 
-/* Initialize a deferred operation. */
+/*
+ * Move deferred ops from one transaction to another and reset the source to
+ * initial state. This is primarily used to carry state forward across
+ * transaction rolls with pending dfops.
+ */
 void
-xfs_defer_init(
-	struct xfs_defer_ops		*dop,
-	xfs_fsblock_t			*fbp)
+xfs_defer_move(
+	struct xfs_trans	*dtp,
+	struct xfs_trans	*stp)
 {
-	memset(dop, 0, sizeof(struct xfs_defer_ops));
-	*fbp = NULLFSBLOCK;
-	INIT_LIST_HEAD(&dop->dop_intake);
-	INIT_LIST_HEAD(&dop->dop_pending);
-	trace_xfs_defer_init(NULL, dop, _RET_IP_);
+	list_splice_init(&stp->t_dfops, &dtp->t_dfops);
+
+	/*
+	 * Low free space mode was historically controlled by a dfops field.
+	 * This meant that low mode state potentially carried across multiple
+	 * transaction rolls. Transfer low mode on a dfops move to preserve
+	 * that behavior.
+	 */
+	dtp->t_flags |= (stp->t_flags & XFS_TRANS_LOWMODE);
+
+	xfs_defer_reset(stp);
 }
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index a02b2b748b6d..2584a5b95b0d 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -24,17 +24,6 @@ struct xfs_defer_pending {
 
 /*
  * Header for deferred operation list.
- *
- * dop_low is used by the allocator to activate the lowspace algorithm -
- * when free space is running low the extent allocator may choose to
- * allocate an extent from an AG without leaving sufficient space for
- * a btree split when inserting the new extent.  In this case the allocator
- * will enable the lowspace algorithm which is supposed to allow further
- * allocations (such as btree splits and newroots) to allocate from
- * sequential AGs.  In order to avoid locking AGs out of order the lowspace
- * algorithm will start searching for free space from AG 0.  If the correct
- * transaction reservations have been made then this algorithm will eventually
- * find all the space it needs.
  */
 enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_BMAP,
@@ -45,28 +34,12 @@ enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_MAX,
 };
 
-#define XFS_DEFER_OPS_NR_INODES	2	/* join up to two inodes */
-#define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
-
-struct xfs_defer_ops {
-	bool			dop_committed;	/* did any trans commit? */
-	bool			dop_low;	/* alloc in low mode */
-	struct list_head	dop_intake;	/* unlogged pending work */
-	struct list_head	dop_pending;	/* logged pending work */
-
-	/* relog these with each roll */
-	struct xfs_inode	*dop_inodes[XFS_DEFER_OPS_NR_INODES];
-	struct xfs_buf		*dop_bufs[XFS_DEFER_OPS_NR_BUFS];
-};
-
-void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
+void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type,
 		struct list_head *h);
-int xfs_defer_finish(struct xfs_trans **tp, struct xfs_defer_ops *dop);
-void xfs_defer_cancel(struct xfs_defer_ops *dop);
-void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp);
-bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
-int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
-int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp);
+int xfs_defer_finish_noroll(struct xfs_trans **tp);
+int xfs_defer_finish(struct xfs_trans **tp);
+void xfs_defer_cancel(struct xfs_trans *);
+void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
 struct xfs_defer_op_type {
@@ -74,8 +47,8 @@ struct xfs_defer_op_type {
 	unsigned int		max_items;
 	void (*abort_intent)(void *);
 	void *(*create_done)(struct xfs_trans *, void *, unsigned int);
-	int (*finish_item)(struct xfs_trans *, struct xfs_defer_ops *,
-			struct list_head *, void *, void **);
+	int (*finish_item)(struct xfs_trans *, struct list_head *, void *,
+			void **);
 	void (*finish_cleanup)(struct xfs_trans *, void *, int);
 	void (*cancel_item)(struct list_head *);
 	int (*diff_items)(void *, struct list_head *, struct list_head *);
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 59169aff30fe..229152cd1a24 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -239,12 +239,10 @@ xfs_dir_init(
  */
 int
 xfs_dir_createname(
-	xfs_trans_t		*tp,
-	xfs_inode_t		*dp,
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_name		*name,
 	xfs_ino_t		inum,		/* new entry inode number */
-	xfs_fsblock_t		*first,		/* bmap's firstblock */
-	struct xfs_defer_ops	*dfops,		/* bmap's freeblock list */
 	xfs_extlen_t		total)		/* bmap's total block count */
 {
 	struct xfs_da_args	*args;
@@ -252,6 +250,7 @@ xfs_dir_createname(
 	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+
 	if (inum) {
 		rval = xfs_dir_ino_validate(tp->t_mountp, inum);
 		if (rval)
@@ -270,8 +269,6 @@ xfs_dir_createname(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = inum;
 	args->dp = dp;
-	args->firstblock = first;
-	args->dfops = dfops;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -416,17 +413,15 @@ out_free:
  */
 int
 xfs_dir_removename(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*dp,
-	struct xfs_name	*name,
-	xfs_ino_t	ino,
-	xfs_fsblock_t	*first,		/* bmap's firstblock */
-	struct xfs_defer_ops	*dfops,		/* bmap's freeblock list */
-	xfs_extlen_t	total)		/* bmap's total block count */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_name		*name,
+	xfs_ino_t		ino,
+	xfs_extlen_t		total)		/* bmap's total block count */
 {
-	struct xfs_da_args *args;
-	int		rval;
-	int		v;		/* type-checking value */
+	struct xfs_da_args	*args;
+	int			rval;
+	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	XFS_STATS_INC(dp->i_mount, xs_dir_remove);
@@ -442,8 +437,6 @@ xfs_dir_removename(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = ino;
 	args->dp = dp;
-	args->firstblock = first;
-	args->dfops = dfops;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -478,17 +471,15 @@ out_free:
  */
 int
 xfs_dir_replace(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*dp,
-	struct xfs_name	*name,		/* name of entry to replace */
-	xfs_ino_t	inum,		/* new inode number */
-	xfs_fsblock_t	*first,		/* bmap's firstblock */
-	struct xfs_defer_ops	*dfops,		/* bmap's freeblock list */
-	xfs_extlen_t	total)		/* bmap's total block count */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_name		*name,		/* name of entry to replace */
+	xfs_ino_t		inum,		/* new inode number */
+	xfs_extlen_t		total)		/* bmap's total block count */
 {
-	struct xfs_da_args *args;
-	int		rval;
-	int		v;		/* type-checking value */
+	struct xfs_da_args	*args;
+	int			rval;
+	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 
@@ -507,8 +498,6 @@ xfs_dir_replace(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = inum;
 	args->dp = dp;
-	args->firstblock = first;
-	args->dfops = dfops;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -547,7 +536,7 @@ xfs_dir_canenter(
 	xfs_inode_t	*dp,
 	struct xfs_name	*name)		/* name of entry to add */
 {
-	return xfs_dir_createname(tp, dp, name, 0, NULL, NULL, 0);
+	return xfs_dir_createname(tp, dp, name, 0, 0);
 }
 
 /*
@@ -645,17 +634,17 @@ xfs_dir2_isleaf(
  */
 int
 xfs_dir2_shrink_inode(
-	xfs_da_args_t	*args,
-	xfs_dir2_db_t	db,
-	struct xfs_buf	*bp)
+	struct xfs_da_args	*args,
+	xfs_dir2_db_t		db,
+	struct xfs_buf		*bp)
 {
-	xfs_fileoff_t	bno;		/* directory file offset */
-	xfs_dablk_t	da;		/* directory file offset */
-	int		done;		/* bunmap is finished */
-	xfs_inode_t	*dp;
-	int		error;
-	xfs_mount_t	*mp;
-	xfs_trans_t	*tp;
+	xfs_fileoff_t		bno;		/* directory file offset */
+	xfs_dablk_t		da;		/* directory file offset */
+	int			done;		/* bunmap is finished */
+	struct xfs_inode	*dp;
+	int			error;
+	struct xfs_mount	*mp;
+	struct xfs_trans	*tp;
 
 	trace_xfs_dir2_shrink_inode(args, db);
 
@@ -665,8 +654,7 @@ xfs_dir2_shrink_inode(
 	da = xfs_dir2_db_to_da(args->geo, db);
 
 	/* Unmap the fsblock(s). */
-	error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount, 0, 0,
-			    args->firstblock, args->dfops, &done);
+	error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount, 0, 0, &done);
 	if (error) {
 		/*
 		 * ENOSPC actually can happen if we're in a removename with no
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index ed385316c7dc..c3e3f6b813d8 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -9,7 +9,6 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 
-struct xfs_defer_ops;
 struct xfs_da_args;
 struct xfs_inode;
 struct xfs_mount;
@@ -118,19 +117,16 @@ extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_inode *pdp);
 extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t inum,
-				xfs_fsblock_t *first,
-				struct xfs_defer_ops *dfops, xfs_extlen_t tot);
+				xfs_extlen_t tot);
 extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t *inum,
 				struct xfs_name *ci_name);
 extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t ino,
-				xfs_fsblock_t *first,
-				struct xfs_defer_ops *dfops, xfs_extlen_t tot);
+				xfs_extlen_t tot);
 extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t inum,
-				xfs_fsblock_t *first,
-				struct xfs_defer_ops *dfops, xfs_extlen_t tot);
+				xfs_extlen_t tot);
 extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name);
 
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 2daf874969ab..f1bb3434f51c 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -1012,7 +1012,7 @@ xfs_dir2_leafn_rebalance(
 	int			oldstale;	/* old count of stale leaves */
 #endif
 	int			oldsum;		/* old total leaf count */
-	int			swap;		/* swapped leaf blocks */
+	int			swap_blocks;	/* swapped leaf blocks */
 	struct xfs_dir2_leaf_entry *ents1;
 	struct xfs_dir2_leaf_entry *ents2;
 	struct xfs_dir3_icleaf_hdr hdr1;
@@ -1023,13 +1023,10 @@ xfs_dir2_leafn_rebalance(
 	/*
 	 * If the block order is wrong, swap the arguments.
 	 */
-	if ((swap = xfs_dir2_leafn_order(dp, blk1->bp, blk2->bp))) {
-		xfs_da_state_blk_t	*tmp;	/* temp for block swap */
+	swap_blocks = xfs_dir2_leafn_order(dp, blk1->bp, blk2->bp);
+	if (swap_blocks)
+		swap(blk1, blk2);
 
-		tmp = blk1;
-		blk1 = blk2;
-		blk2 = tmp;
-	}
 	leaf1 = blk1->bp->b_addr;
 	leaf2 = blk2->bp->b_addr;
 	dp->d_ops->leaf_hdr_from_disk(&hdr1, leaf1);
@@ -1093,11 +1090,11 @@ xfs_dir2_leafn_rebalance(
 	 * Mark whether we're inserting into the old or new leaf.
 	 */
 	if (hdr1.count < hdr2.count)
-		state->inleaf = swap;
+		state->inleaf = swap_blocks;
 	else if (hdr1.count > hdr2.count)
-		state->inleaf = !swap;
+		state->inleaf = !swap_blocks;
 	else
-		state->inleaf = swap ^ (blk1->index <= hdr1.count);
+		state->inleaf = swap_blocks ^ (blk1->index <= hdr1.count);
 	/*
 	 * Adjust the expected index for insertion.
 	 */
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index b9974e7a8e6e..66077a105cbb 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -53,7 +53,8 @@
 #define XFS_ERRTAG_LOG_ITEM_PIN				30
 #define XFS_ERRTAG_BUF_LRU_REF				31
 #define XFS_ERRTAG_FORCE_SCRUB_REPAIR			32
-#define XFS_ERRTAG_MAX					33
+#define XFS_ERRTAG_FORCE_SUMMARY_RECALC			33
+#define XFS_ERRTAG_MAX					34
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -91,5 +92,6 @@
 #define XFS_RANDOM_LOG_ITEM_PIN				1
 #define XFS_RANDOM_BUF_LRU_REF				2
 #define XFS_RANDOM_FORCE_SCRUB_REPAIR			1
+#define XFS_RANDOM_FORCE_SUMMARY_RECALC			1
 
 #endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 0d968e8143aa..a8f6db735d5d 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1838,23 +1838,24 @@ out_error:
  */
 STATIC void
 xfs_difree_inode_chunk(
-	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
 	xfs_agnumber_t			agno,
-	struct xfs_inobt_rec_incore	*rec,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_inobt_rec_incore	*rec)
 {
-	xfs_agblock_t	sagbno = XFS_AGINO_TO_AGBNO(mp, rec->ir_startino);
-	int		startidx, endidx;
-	int		nextbit;
-	xfs_agblock_t	agbno;
-	int		contigblk;
-	struct xfs_owner_info	oinfo;
+	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_agblock_t			sagbno = XFS_AGINO_TO_AGBNO(mp,
+							rec->ir_startino);
+	int				startidx, endidx;
+	int				nextbit;
+	xfs_agblock_t			agbno;
+	int				contigblk;
+	struct xfs_owner_info		oinfo;
 	DECLARE_BITMAP(holemask, XFS_INOBT_HOLEMASK_BITS);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
 
 	if (!xfs_inobt_issparse(rec->ir_holemask)) {
 		/* not sparse, calculate extent info directly */
-		xfs_bmap_add_free(mp, dfops, XFS_AGB_TO_FSB(mp, agno, sagbno),
+		xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, sagbno),
 				  mp->m_ialloc_blks, &oinfo);
 		return;
 	}
@@ -1898,7 +1899,7 @@ xfs_difree_inode_chunk(
 
 		ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
-		xfs_bmap_add_free(mp, dfops, XFS_AGB_TO_FSB(mp, agno, agbno),
+		xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, agbno),
 				  contigblk, &oinfo);
 
 		/* reset range to current bit and carry on... */
@@ -1915,7 +1916,6 @@ xfs_difree_inobt(
 	struct xfs_trans		*tp,
 	struct xfs_buf			*agbp,
 	xfs_agino_t			agino,
-	struct xfs_defer_ops		*dfops,
 	struct xfs_icluster		*xic,
 	struct xfs_inobt_rec_incore	*orec)
 {
@@ -2003,7 +2003,7 @@ xfs_difree_inobt(
 			goto error0;
 		}
 
-		xfs_difree_inode_chunk(mp, agno, &rec, dfops);
+		xfs_difree_inode_chunk(tp, agno, &rec);
 	} else {
 		xic->deleted = false;
 
@@ -2148,7 +2148,6 @@ int
 xfs_difree(
 	struct xfs_trans	*tp,		/* transaction pointer */
 	xfs_ino_t		inode,		/* inode to be freed */
-	struct xfs_defer_ops	*dfops,		/* extents to free */
 	struct xfs_icluster	*xic)	/* cluster info if deleted */
 {
 	/* REFERENCED */
@@ -2200,7 +2199,7 @@ xfs_difree(
 	/*
 	 * Fix up the inode allocation btree.
 	 */
-	error = xfs_difree_inobt(mp, tp, agbp, agino, dfops, xic, &rec);
+	error = xfs_difree_inobt(mp, tp, agbp, agino, xic, &rec);
 	if (error)
 		goto error0;
 
@@ -2260,7 +2259,7 @@ xfs_imap_lookup(
 	}
 
 	xfs_trans_brelse(tp, agbp);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	if (error)
 		return error;
 
@@ -2539,7 +2538,7 @@ xfs_agi_verify(
 		return __this_address;
 
 	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
-		if (agi->agi_unlinked[i] == NULLAGINO)
+		if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO))
 			continue;
 		if (!xfs_verify_ino(mp, be32_to_cpu(agi->agi_unlinked[i])))
 			return __this_address;
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 90b09c5f163b..e936b7cc9389 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -82,7 +82,6 @@ int					/* error */
 xfs_difree(
 	struct xfs_trans *tp,		/* transaction pointer */
 	xfs_ino_t	inode,		/* inode to be freed */
-	struct xfs_defer_ops *dfops,	/* extents to free */
 	struct xfs_icluster *ifree);	/* cluster info if deleted */
 
 /*
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index a5237afec5ab..86c50208a143 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -552,6 +552,7 @@ xfs_inobt_max_size(
 static int
 xfs_inobt_count_blocks(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_btnum_t		btnum,
 	xfs_extlen_t		*tree_blocks)
@@ -560,14 +561,14 @@ xfs_inobt_count_blocks(
 	struct xfs_btree_cur	*cur;
 	int			error;
 
-	error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
+	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
 	if (error)
 		return error;
 
-	cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, btnum);
 	error = xfs_btree_count_blocks(cur, tree_blocks);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
-	xfs_buf_relse(agbp);
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(tp, agbp);
 
 	return error;
 }
@@ -578,6 +579,7 @@ xfs_inobt_count_blocks(
 int
 xfs_finobt_calc_reserves(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
@@ -588,7 +590,7 @@ xfs_finobt_calc_reserves(
 	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
 		return 0;
 
-	error = xfs_inobt_count_blocks(mp, agno, XFS_BTNUM_FINO, &tree_len);
+	error = xfs_inobt_count_blocks(mp, tp, agno, XFS_BTNUM_FINO, &tree_len);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index bf8f0c405e7d..ebdd0c6b8766 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -60,8 +60,8 @@ int xfs_inobt_rec_check_count(struct xfs_mount *,
 #define xfs_inobt_rec_check_count(mp, rec)	0
 #endif	/* DEBUG */
 
-int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno,
-		xfs_extlen_t *ask, xfs_extlen_t *used);
+int xfs_finobt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp,
+		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
 extern xfs_extlen_t xfs_iallocbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
 
diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index b80c63faace2..771dd072015d 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -14,6 +14,7 @@
 #include "xfs_inode_fork.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_bmap.h"
 #include "xfs_trace.h"
 
 /*
@@ -612,6 +613,19 @@ xfs_iext_realloc_root(
 	cur->leaf = new;
 }
 
+/*
+ * Increment the sequence counter if we are on a COW fork.  This allows
+ * the writeback code to skip looking for a COW extent if the COW fork
+ * hasn't changed.  We use WRITE_ONCE here to ensure the update to the
+ * sequence counter is seen before the modifications to the extent
+ * tree itself take effect.
+ */
+static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp, int state)
+{
+	if (state & BMAP_COWFORK)
+		WRITE_ONCE(ifp->if_seq, READ_ONCE(ifp->if_seq) + 1);
+}
+
 void
 xfs_iext_insert(
 	struct xfs_inode	*ip,
@@ -624,6 +638,8 @@ xfs_iext_insert(
 	struct xfs_iext_leaf	*new = NULL;
 	int			nr_entries, i;
 
+	xfs_iext_inc_seq(ifp, state);
+
 	if (ifp->if_height == 0)
 		xfs_iext_alloc_root(ifp, cur);
 	else if (ifp->if_height == 1)
@@ -864,6 +880,8 @@ xfs_iext_remove(
 	ASSERT(ifp->if_u1.if_root != NULL);
 	ASSERT(xfs_iext_valid(ifp, cur));
 
+	xfs_iext_inc_seq(ifp, state);
+
 	nr_entries = xfs_iext_leaf_nr_entries(ifp, leaf, cur->pos) - 1;
 	for (i = cur->pos; i < nr_entries; i++)
 		leaf->recs[i] = leaf->recs[i + 1];
@@ -970,6 +988,8 @@ xfs_iext_update_extent(
 {
 	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
 
+	xfs_iext_inc_seq(ifp, state);
+
 	if (cur->pos == 0) {
 		struct xfs_bmbt_irec	old;
 
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 183ec0cb8921..f9acf1d436f6 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -158,7 +158,6 @@ xfs_init_local_fork(
 	}
 
 	ifp->if_bytes = size;
-	ifp->if_real_bytes = real_size;
 	ifp->if_flags &= ~(XFS_IFEXTENTS | XFS_IFBROOT);
 	ifp->if_flags |= XFS_IFINLINE;
 }
@@ -226,7 +225,6 @@ xfs_iformat_extents(
 		return -EFSCORRUPTED;
 	}
 
-	ifp->if_real_bytes = 0;
 	ifp->if_bytes = 0;
 	ifp->if_u1.if_root = NULL;
 	ifp->if_height = 0;
@@ -271,7 +269,7 @@ xfs_iformat_btree(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_bmdr_block_t	*dfp;
-	xfs_ifork_t		*ifp;
+	struct xfs_ifork	*ifp;
 	/* REFERENCED */
 	int			nrecs;
 	int			size;
@@ -317,7 +315,6 @@ xfs_iformat_btree(
 	ifp->if_flags &= ~XFS_IFEXTENTS;
 	ifp->if_flags |= XFS_IFBROOT;
 
-	ifp->if_real_bytes = 0;
 	ifp->if_bytes = 0;
 	ifp->if_u1.if_root = NULL;
 	ifp->if_height = 0;
@@ -350,7 +347,7 @@ xfs_iroot_realloc(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	int			cur_max;
-	xfs_ifork_t		*ifp;
+	struct xfs_ifork	*ifp;
 	struct xfs_btree_block	*new_broot;
 	int			new_max;
 	size_t			new_size;
@@ -471,55 +468,34 @@ xfs_iroot_realloc(
  */
 void
 xfs_idata_realloc(
-	xfs_inode_t	*ip,
-	int		byte_diff,
-	int		whichfork)
+	struct xfs_inode	*ip,
+	int			byte_diff,
+	int			whichfork)
 {
-	xfs_ifork_t	*ifp;
-	int		new_size;
-	int		real_size;
-
-	if (byte_diff == 0) {
-		return;
-	}
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	int			new_size = (int)ifp->if_bytes + byte_diff;
 
-	ifp = XFS_IFORK_PTR(ip, whichfork);
-	new_size = (int)ifp->if_bytes + byte_diff;
 	ASSERT(new_size >= 0);
+	ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork));
+
+	if (byte_diff == 0)
+		return;
 
 	if (new_size == 0) {
 		kmem_free(ifp->if_u1.if_data);
 		ifp->if_u1.if_data = NULL;
-		real_size = 0;
-	} else {
-		/*
-		 * Stuck with malloc/realloc.
-		 * For inline data, the underlying buffer must be
-		 * a multiple of 4 bytes in size so that it can be
-		 * logged and stay on word boundaries.  We enforce
-		 * that here.
-		 */
-		real_size = roundup(new_size, 4);
-		if (ifp->if_u1.if_data == NULL) {
-			ASSERT(ifp->if_real_bytes == 0);
-			ifp->if_u1.if_data = kmem_alloc(real_size,
-							KM_SLEEP | KM_NOFS);
-		} else {
-			/*
-			 * Only do the realloc if the underlying size
-			 * is really changing.
-			 */
-			if (ifp->if_real_bytes != real_size) {
-				ifp->if_u1.if_data =
-					kmem_realloc(ifp->if_u1.if_data,
-							real_size,
-							KM_SLEEP | KM_NOFS);
-			}
-		}
+		ifp->if_bytes = 0;
+		return;
 	}
-	ifp->if_real_bytes = real_size;
+
+	/*
+	 * For inline data, the underlying buffer must be a multiple of 4 bytes
+	 * in size so that it can be logged and stay on word boundaries.
+	 * We enforce that here.
+	 */
+	ifp->if_u1.if_data = kmem_realloc(ifp->if_u1.if_data,
+			roundup(new_size, 4), KM_SLEEP | KM_NOFS);
 	ifp->if_bytes = new_size;
-	ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
 }
 
 void
@@ -527,7 +503,7 @@ xfs_idestroy_fork(
 	xfs_inode_t	*ip,
 	int		whichfork)
 {
-	xfs_ifork_t	*ifp;
+	struct xfs_ifork	*ifp;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	if (ifp->if_broot != NULL) {
@@ -543,17 +519,13 @@ xfs_idestroy_fork(
 	 */
 	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
 		if (ifp->if_u1.if_data != NULL) {
-			ASSERT(ifp->if_real_bytes != 0);
 			kmem_free(ifp->if_u1.if_data);
 			ifp->if_u1.if_data = NULL;
-			ifp->if_real_bytes = 0;
 		}
 	} else if ((ifp->if_flags & XFS_IFEXTENTS) && ifp->if_height) {
 		xfs_iext_destroy(ifp);
 	}
 
-	ASSERT(ifp->if_real_bytes == 0);
-
 	if (whichfork == XFS_ATTR_FORK) {
 		kmem_zone_free(xfs_ifork_zone, ip->i_afp);
 		ip->i_afp = NULL;
@@ -620,7 +592,7 @@ xfs_iflush_fork(
 	int			whichfork)
 {
 	char			*cp;
-	xfs_ifork_t		*ifp;
+	struct xfs_ifork	*ifp;
 	xfs_mount_t		*mp;
 	static const short	brootflag[2] =
 		{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 781b1603df5e..60361d2d74a1 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -12,9 +12,9 @@ struct xfs_dinode;
 /*
  * File incore extent information, present for each of data & attr forks.
  */
-typedef struct xfs_ifork {
+struct xfs_ifork {
 	int			if_bytes;	/* bytes in if_u1 */
-	int			if_real_bytes;	/* bytes allocated in if_u1 */
+	unsigned int		if_seq;		/* cow fork mod counter */
 	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	unsigned char		if_flags;	/* per-fork flags */
@@ -23,7 +23,7 @@ typedef struct xfs_ifork {
 		void		*if_root;	/* extent tree root */
 		char		*if_data;	/* inline file data */
 	} if_u1;
-} xfs_ifork_t;
+};
 
 /*
  * Per-fork incore inode flags.
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 79bb79853c9f..e5f97c69b320 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -77,6 +77,19 @@ static inline uint xlog_get_cycle(char *ptr)
 
 #define XLOG_UNMOUNT_TYPE	0x556e	/* Un for Unmount */
 
+/*
+ * Log item for unmount records.
+ *
+ * The unmount record used to have a string "Unmount filesystem--" in the
+ * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE).
+ * We just write the magic number now; see xfs_log_unmount_write.
+ */
+struct xfs_unmount_log_format {
+	uint16_t	magic;	/* XLOG_UNMOUNT_TYPE */
+	uint16_t	pad1;
+	uint32_t	pad2;	/* may as well make it 64 bits */
+};
+
 /* Region types for iovec's i_type */
 #define XLOG_REG_TYPE_BFORMAT		1
 #define XLOG_REG_TYPE_BCHUNK		2
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 9dda6fd0bb13..542aa1475b5f 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -34,11 +34,9 @@ enum xfs_refc_adjust_op {
 };
 
 STATIC int __xfs_refcount_cow_alloc(struct xfs_btree_cur *rcur,
-		xfs_agblock_t agbno, xfs_extlen_t aglen,
-		struct xfs_defer_ops *dfops);
+		xfs_agblock_t agbno, xfs_extlen_t aglen);
 STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur,
-		xfs_agblock_t agbno, xfs_extlen_t aglen,
-		struct xfs_defer_ops *dfops);
+		xfs_agblock_t agbno, xfs_extlen_t aglen);
 
 /*
  * Look up the first record less than or equal to [bno, len] in the btree
@@ -870,7 +868,6 @@ xfs_refcount_adjust_extents(
 	xfs_agblock_t		*agbno,
 	xfs_extlen_t		*aglen,
 	enum xfs_refc_adjust_op	adj,
-	struct xfs_defer_ops	*dfops,
 	struct xfs_owner_info	*oinfo)
 {
 	struct xfs_refcount_irec	ext, tmp;
@@ -925,8 +922,8 @@ xfs_refcount_adjust_extents(
 				fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
 						cur->bc_private.a.agno,
 						tmp.rc_startblock);
-				xfs_bmap_add_free(cur->bc_mp, dfops, fsbno,
-						tmp.rc_blockcount, oinfo);
+				xfs_bmap_add_free(cur->bc_tp, fsbno,
+						  tmp.rc_blockcount, oinfo);
 			}
 
 			(*agbno) += tmp.rc_blockcount;
@@ -968,8 +965,8 @@ xfs_refcount_adjust_extents(
 			fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
 					cur->bc_private.a.agno,
 					ext.rc_startblock);
-			xfs_bmap_add_free(cur->bc_mp, dfops, fsbno,
-					ext.rc_blockcount, oinfo);
+			xfs_bmap_add_free(cur->bc_tp, fsbno, ext.rc_blockcount,
+					  oinfo);
 		}
 
 skip:
@@ -998,7 +995,6 @@ xfs_refcount_adjust(
 	xfs_agblock_t		*new_agbno,
 	xfs_extlen_t		*new_aglen,
 	enum xfs_refc_adjust_op	adj,
-	struct xfs_defer_ops	*dfops,
 	struct xfs_owner_info	*oinfo)
 {
 	bool			shape_changed;
@@ -1043,7 +1039,7 @@ xfs_refcount_adjust(
 
 	/* Now that we've taken care of the ends, adjust the middle extents */
 	error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen,
-			adj, dfops, oinfo);
+			adj, oinfo);
 	if (error)
 		goto out_error;
 
@@ -1067,7 +1063,7 @@ xfs_refcount_finish_one_cleanup(
 	if (rcur == NULL)
 		return;
 	agbp = rcur->bc_private.a.agbp;
-	xfs_btree_del_cursor(rcur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(rcur, error);
 	if (error)
 		xfs_trans_brelse(tp, agbp);
 }
@@ -1082,7 +1078,6 @@ xfs_refcount_finish_one_cleanup(
 int
 xfs_refcount_finish_one(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dfops,
 	enum xfs_refcount_intent_type	type,
 	xfs_fsblock_t			startblock,
 	xfs_extlen_t			blockcount,
@@ -1132,7 +1127,7 @@ xfs_refcount_finish_one(
 		if (!agbp)
 			return -EFSCORRUPTED;
 
-		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, dfops);
+		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
 		if (!rcur) {
 			error = -ENOMEM;
 			goto out_cur;
@@ -1145,23 +1140,23 @@ xfs_refcount_finish_one(
 	switch (type) {
 	case XFS_REFCOUNT_INCREASE:
 		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
-			new_len, XFS_REFCOUNT_ADJUST_INCREASE, dfops, NULL);
+			new_len, XFS_REFCOUNT_ADJUST_INCREASE, NULL);
 		*new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno);
 		break;
 	case XFS_REFCOUNT_DECREASE:
 		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
-			new_len, XFS_REFCOUNT_ADJUST_DECREASE, dfops, NULL);
+			new_len, XFS_REFCOUNT_ADJUST_DECREASE, NULL);
 		*new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno);
 		break;
 	case XFS_REFCOUNT_ALLOC_COW:
 		*new_fsb = startblock + blockcount;
 		*new_len = 0;
-		error = __xfs_refcount_cow_alloc(rcur, bno, blockcount, dfops);
+		error = __xfs_refcount_cow_alloc(rcur, bno, blockcount);
 		break;
 	case XFS_REFCOUNT_FREE_COW:
 		*new_fsb = startblock + blockcount;
 		*new_len = 0;
-		error = __xfs_refcount_cow_free(rcur, bno, blockcount, dfops);
+		error = __xfs_refcount_cow_free(rcur, bno, blockcount);
 		break;
 	default:
 		ASSERT(0);
@@ -1183,16 +1178,16 @@ out_cur:
  */
 static int
 __xfs_refcount_add(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	enum xfs_refcount_intent_type	type,
 	xfs_fsblock_t			startblock,
 	xfs_extlen_t			blockcount)
 {
 	struct xfs_refcount_intent	*ri;
 
-	trace_xfs_refcount_defer(mp, XFS_FSB_TO_AGNO(mp, startblock),
-			type, XFS_FSB_TO_AGBNO(mp, startblock),
+	trace_xfs_refcount_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, startblock),
+			type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
 			blockcount);
 
 	ri = kmem_alloc(sizeof(struct xfs_refcount_intent),
@@ -1202,7 +1197,7 @@ __xfs_refcount_add(
 	ri->ri_startblock = startblock;
 	ri->ri_blockcount = blockcount;
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
 	return 0;
 }
 
@@ -1211,14 +1206,13 @@ __xfs_refcount_add(
  */
 int
 xfs_refcount_increase_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	struct xfs_bmbt_irec		*PREV)
 {
-	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+	if (!xfs_sb_version_hasreflink(&tp->t_mountp->m_sb))
 		return 0;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_INCREASE,
+	return __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE,
 			PREV->br_startblock, PREV->br_blockcount);
 }
 
@@ -1227,14 +1221,13 @@ xfs_refcount_increase_extent(
  */
 int
 xfs_refcount_decrease_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	struct xfs_bmbt_irec		*PREV)
 {
-	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+	if (!xfs_sb_version_hasreflink(&tp->t_mountp->m_sb))
 		return 0;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_DECREASE,
+	return __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE,
 			PREV->br_startblock, PREV->br_blockcount);
 }
 
@@ -1522,8 +1515,7 @@ STATIC int
 __xfs_refcount_cow_alloc(
 	struct xfs_btree_cur	*rcur,
 	xfs_agblock_t		agbno,
-	xfs_extlen_t		aglen,
-	struct xfs_defer_ops	*dfops)
+	xfs_extlen_t		aglen)
 {
 	trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_private.a.agno,
 			agbno, aglen);
@@ -1540,8 +1532,7 @@ STATIC int
 __xfs_refcount_cow_free(
 	struct xfs_btree_cur	*rcur,
 	xfs_agblock_t		agbno,
-	xfs_extlen_t		aglen,
-	struct xfs_defer_ops	*dfops)
+	xfs_extlen_t		aglen)
 {
 	trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_private.a.agno,
 			agbno, aglen);
@@ -1554,47 +1545,45 @@ __xfs_refcount_cow_free(
 /* Record a CoW staging extent in the refcount btree. */
 int
 xfs_refcount_alloc_cow_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			fsb,
 	xfs_extlen_t			len)
 {
+	struct xfs_mount		*mp = tp->t_mountp;
 	int				error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
-	error = __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW,
-			fsb, len);
+	error = __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len);
 	if (error)
 		return error;
 
 	/* Add rmap entry */
-	return xfs_rmap_alloc_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb),
+	return xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
 			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
 }
 
 /* Forget a CoW staging event in the refcount btree. */
 int
 xfs_refcount_free_cow_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			fsb,
 	xfs_extlen_t			len)
 {
+	struct xfs_mount		*mp = tp->t_mountp;
 	int				error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
 	/* Remove rmap entry */
-	error = xfs_rmap_free_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb),
+	error = xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
 			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
 	if (error)
 		return error;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_FREE_COW,
-			fsb, len);
+	return __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len);
 }
 
 struct xfs_refcount_recovery {
@@ -1635,7 +1624,6 @@ xfs_refcount_recover_cow_leftovers(
 	struct list_head		debris;
 	union xfs_btree_irec		low;
 	union xfs_btree_irec		high;
-	struct xfs_defer_ops		dfops;
 	xfs_fsblock_t			fsb;
 	xfs_agblock_t			agbno;
 	int				error;
@@ -1666,7 +1654,7 @@ xfs_refcount_recover_cow_leftovers(
 		error = -ENOMEM;
 		goto out_trans;
 	}
-	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
 
 	/* Find all the leftover CoW staging extents. */
 	memset(&low, 0, sizeof(low));
@@ -1675,11 +1663,11 @@ xfs_refcount_recover_cow_leftovers(
 	high.rc.rc_startblock = -1U;
 	error = xfs_btree_query_range(cur, &low, &high,
 			xfs_refcount_recover_extent, &debris);
-	if (error)
-		goto out_cursor;
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	xfs_trans_brelse(tp, agbp);
 	xfs_trans_cancel(tp);
+	if (error)
+		goto out_free;
 
 	/* Now iterate the list to free the leftovers */
 	list_for_each_entry_safe(rr, n, &debris, rr_list) {
@@ -1691,21 +1679,15 @@ xfs_refcount_recover_cow_leftovers(
 		trace_xfs_refcount_recover_extent(mp, agno, &rr->rr_rrec);
 
 		/* Free the orphan record */
-		xfs_defer_init(&dfops, &fsb);
 		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
 		fsb = XFS_AGB_TO_FSB(mp, agno, agbno);
-		error = xfs_refcount_free_cow_extent(mp, &dfops, fsb,
+		error = xfs_refcount_free_cow_extent(tp, fsb,
 				rr->rr_rrec.rc_blockcount);
 		if (error)
-			goto out_defer;
+			goto out_trans;
 
 		/* Free the block. */
-		xfs_bmap_add_free(mp, &dfops, fsb,
-				rr->rr_rrec.rc_blockcount, NULL);
-
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto out_defer;
+		xfs_bmap_add_free(tp, fsb, rr->rr_rrec.rc_blockcount, NULL);
 
 		error = xfs_trans_commit(tp);
 		if (error)
@@ -1716,8 +1698,6 @@ xfs_refcount_recover_cow_leftovers(
 	}
 
 	return error;
-out_defer:
-	xfs_defer_cancel(&dfops);
 out_trans:
 	xfs_trans_cancel(tp);
 out_free:
@@ -1727,11 +1707,6 @@ out_free:
 		kmem_free(rr);
 	}
 	return error;
-
-out_cursor:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-	xfs_trans_brelse(tp, agbp);
-	goto out_trans;
 }
 
 /* Is there a record covering a given extent? */
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 5fef74412727..1d9c518575e7 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -29,29 +29,26 @@ struct xfs_refcount_intent {
 	xfs_extlen_t				ri_blockcount;
 };
 
-extern int xfs_refcount_increase_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, struct xfs_bmbt_irec *irec);
-extern int xfs_refcount_decrease_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, struct xfs_bmbt_irec *irec);
+extern int xfs_refcount_increase_extent(struct xfs_trans *tp,
+		struct xfs_bmbt_irec *irec);
+extern int xfs_refcount_decrease_extent(struct xfs_trans *tp,
+		struct xfs_bmbt_irec *irec);
 
 extern void xfs_refcount_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
 extern int xfs_refcount_finish_one(struct xfs_trans *tp,
-		struct xfs_defer_ops *dfops, enum xfs_refcount_intent_type type,
-		xfs_fsblock_t startblock, xfs_extlen_t blockcount,
-		xfs_fsblock_t *new_fsb, xfs_extlen_t *new_len,
-		struct xfs_btree_cur **pcur);
+		enum xfs_refcount_intent_type type, xfs_fsblock_t startblock,
+		xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb,
+		xfs_extlen_t *new_len, struct xfs_btree_cur **pcur);
 
 extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur,
 		xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno,
 		xfs_extlen_t *flen, bool find_end_of_shared);
 
-extern int xfs_refcount_alloc_cow_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, xfs_fsblock_t fsb,
-		xfs_extlen_t len);
-extern int xfs_refcount_free_cow_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, xfs_fsblock_t fsb,
-		xfs_extlen_t len);
+extern int xfs_refcount_alloc_cow_extent(struct xfs_trans *tp,
+		xfs_fsblock_t fsb, xfs_extlen_t len);
+extern int xfs_refcount_free_cow_extent(struct xfs_trans *tp,
+		xfs_fsblock_t fsb, xfs_extlen_t len);
 extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
 		xfs_agnumber_t agno);
 
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index b71937982c5b..1aaa01c97517 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -27,8 +27,7 @@ xfs_refcountbt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_refcountbt_init_cursor(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agbp, cur->bc_private.a.agno,
-			cur->bc_private.a.dfops);
+			cur->bc_private.a.agbp, cur->bc_private.a.agno);
 }
 
 STATIC void
@@ -71,7 +70,6 @@ xfs_refcountbt_alloc_block(
 	args.type = XFS_ALLOCTYPE_NEAR_BNO;
 	args.fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno,
 			xfs_refc_block(args.mp));
-	args.firstblock = args.fsbno;
 	xfs_rmap_ag_owner(&args.oinfo, XFS_RMAP_OWN_REFC);
 	args.minlen = args.maxlen = args.prod = 1;
 	args.resv = XFS_AG_RESV_METADATA;
@@ -323,8 +321,7 @@ xfs_refcountbt_init_cursor(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
-	xfs_agnumber_t		agno,
-	struct xfs_defer_ops	*dfops)
+	xfs_agnumber_t		agno)
 {
 	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
 	struct xfs_btree_cur	*cur;
@@ -344,7 +341,6 @@ xfs_refcountbt_init_cursor(
 
 	cur->bc_private.a.agbp = agbp;
 	cur->bc_private.a.agno = agno;
-	cur->bc_private.a.dfops = dfops;
 	cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
 	cur->bc_private.a.priv.refc.nr_ops = 0;
@@ -408,6 +404,7 @@ xfs_refcountbt_max_size(
 int
 xfs_refcountbt_calc_reserves(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
@@ -422,14 +419,14 @@ xfs_refcountbt_calc_reserves(
 		return 0;
 
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
 	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_refcount_blocks);
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
 
 	*ask += xfs_refcountbt_max_size(mp, agblocks);
 	*used += tree_len;
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index d2852b6e1fa8..ba416f71c824 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -44,8 +44,8 @@ struct xfs_mount;
 		 ((index) - 1) * sizeof(xfs_refcount_ptr_t)))
 
 extern struct xfs_btree_cur *xfs_refcountbt_init_cursor(struct xfs_mount *mp,
-		struct xfs_trans *tp, struct xfs_buf *agbp, xfs_agnumber_t agno,
-		struct xfs_defer_ops *dfops);
+		struct xfs_trans *tp, struct xfs_buf *agbp,
+		xfs_agnumber_t agno);
 extern int xfs_refcountbt_maxrecs(int blocklen, bool leaf);
 extern void xfs_refcountbt_compute_maxlevels(struct xfs_mount *mp);
 
@@ -55,6 +55,7 @@ extern xfs_extlen_t xfs_refcountbt_max_size(struct xfs_mount *mp,
 		xfs_agblock_t agblocks);
 
 extern int xfs_refcountbt_calc_reserves(struct xfs_mount *mp,
-		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
+		struct xfs_trans *tp, xfs_agnumber_t agno, xfs_extlen_t *ask,
+		xfs_extlen_t *used);
 
 #endif	/* __XFS_REFCOUNT_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index d4460b0d2d81..245af452840e 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -670,14 +670,8 @@ xfs_rmap_free(
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);
 
 	error = xfs_rmap_unmap(cur, bno, len, false, oinfo);
-	if (error)
-		goto out_error;
 
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
-	return 0;
-
-out_error:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -753,19 +747,19 @@ xfs_rmap_map(
 			&have_lt);
 	if (error)
 		goto out_error;
-	XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
-
-	error = xfs_rmap_get_rec(cur, &ltrec, &have_lt);
-	if (error)
-		goto out_error;
-	XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
-	trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
-			cur->bc_private.a.agno, ltrec.rm_startblock,
-			ltrec.rm_blockcount, ltrec.rm_owner,
-			ltrec.rm_offset, ltrec.rm_flags);
+	if (have_lt) {
+		error = xfs_rmap_get_rec(cur, &ltrec, &have_lt);
+		if (error)
+			goto out_error;
+		XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
+		trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
+				cur->bc_private.a.agno, ltrec.rm_startblock,
+				ltrec.rm_blockcount, ltrec.rm_owner,
+				ltrec.rm_offset, ltrec.rm_flags);
 
-	if (!xfs_rmap_is_mergeable(&ltrec, owner, flags))
-		have_lt = 0;
+		if (!xfs_rmap_is_mergeable(&ltrec, owner, flags))
+			have_lt = 0;
+	}
 
 	XFS_WANT_CORRUPTED_GOTO(mp,
 		have_lt == 0 ||
@@ -912,14 +906,8 @@ xfs_rmap_alloc(
 
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);
 	error = xfs_rmap_map(cur, bno, len, false, oinfo);
-	if (error)
-		goto out_error;
-
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
-	return 0;
 
-out_error:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -2156,7 +2144,7 @@ xfs_rmap_finish_one_cleanup(
 	if (rcur == NULL)
 		return;
 	agbp = rcur->bc_private.a.agbp;
-	xfs_btree_del_cursor(rcur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(rcur, error);
 	if (error)
 		xfs_trans_brelse(tp, agbp);
 }
@@ -2289,18 +2277,18 @@ xfs_rmap_update_is_needed(
  */
 static int
 __xfs_rmap_add(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	enum xfs_rmap_intent_type	type,
 	uint64_t			owner,
 	int				whichfork,
 	struct xfs_bmbt_irec		*bmap)
 {
-	struct xfs_rmap_intent	*ri;
+	struct xfs_rmap_intent		*ri;
 
-	trace_xfs_rmap_defer(mp, XFS_FSB_TO_AGNO(mp, bmap->br_startblock),
+	trace_xfs_rmap_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
 			type,
-			XFS_FSB_TO_AGBNO(mp, bmap->br_startblock),
+			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
 			owner, whichfork,
 			bmap->br_startoff,
 			bmap->br_blockcount,
@@ -2313,23 +2301,22 @@ __xfs_rmap_add(
 	ri->ri_whichfork = whichfork;
 	ri->ri_bmap = *bmap;
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
 	return 0;
 }
 
 /* Map an extent into a file. */
 int
 xfs_rmap_map_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_rmap_update_is_needed(mp, whichfork))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return 0;
 
-	return __xfs_rmap_add(mp, dfops, xfs_is_reflink_inode(ip) ?
+	return __xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
 			XFS_RMAP_MAP_SHARED : XFS_RMAP_MAP, ip->i_ino,
 			whichfork, PREV);
 }
@@ -2337,25 +2324,29 @@ xfs_rmap_map_extent(
 /* Unmap an extent out of a file. */
 int
 xfs_rmap_unmap_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_rmap_update_is_needed(mp, whichfork))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return 0;
 
-	return __xfs_rmap_add(mp, dfops, xfs_is_reflink_inode(ip) ?
+	return __xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
 			XFS_RMAP_UNMAP_SHARED : XFS_RMAP_UNMAP, ip->i_ino,
 			whichfork, PREV);
 }
 
-/* Convert a data fork extent from unwritten to real or vice versa. */
+/*
+ * Convert a data fork extent from unwritten to real or vice versa.
+ *
+ * Note that tp can be NULL here as no transaction is used for COW fork
+ * unwritten conversion.
+ */
 int
 xfs_rmap_convert_extent(
 	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
@@ -2363,7 +2354,7 @@ xfs_rmap_convert_extent(
 	if (!xfs_rmap_update_is_needed(mp, whichfork))
 		return 0;
 
-	return __xfs_rmap_add(mp, dfops, xfs_is_reflink_inode(ip) ?
+	return __xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
 			XFS_RMAP_CONVERT_SHARED : XFS_RMAP_CONVERT, ip->i_ino,
 			whichfork, PREV);
 }
@@ -2371,8 +2362,7 @@ xfs_rmap_convert_extent(
 /* Schedule the creation of an rmap for non-file data. */
 int
 xfs_rmap_alloc_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
@@ -2380,23 +2370,21 @@ xfs_rmap_alloc_extent(
 {
 	struct xfs_bmbt_irec	bmap;
 
-	if (!xfs_rmap_update_is_needed(mp, XFS_DATA_FORK))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK))
 		return 0;
 
-	bmap.br_startblock = XFS_AGB_TO_FSB(mp, agno, bno);
+	bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno);
 	bmap.br_blockcount = len;
 	bmap.br_startoff = 0;
 	bmap.br_state = XFS_EXT_NORM;
 
-	return __xfs_rmap_add(mp, dfops, XFS_RMAP_ALLOC, owner,
-			XFS_DATA_FORK, &bmap);
+	return __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, XFS_DATA_FORK, &bmap);
 }
 
 /* Schedule the deletion of an rmap for non-file data. */
 int
 xfs_rmap_free_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
@@ -2404,16 +2392,15 @@ xfs_rmap_free_extent(
 {
 	struct xfs_bmbt_irec	bmap;
 
-	if (!xfs_rmap_update_is_needed(mp, XFS_DATA_FORK))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK))
 		return 0;
 
-	bmap.br_startblock = XFS_AGB_TO_FSB(mp, agno, bno);
+	bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno);
 	bmap.br_blockcount = len;
 	bmap.br_startoff = 0;
 	bmap.br_state = XFS_EXT_NORM;
 
-	return __xfs_rmap_add(mp, dfops, XFS_RMAP_FREE, owner,
-			XFS_DATA_FORK, &bmap);
+	return __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, XFS_DATA_FORK, &bmap);
 }
 
 /* Compare rmap records.  Returns -1 if a < b, 1 if a > b, and 0 if equal. */
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 9f19454768b2..157dc722ad35 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -185,21 +185,17 @@ struct xfs_rmap_intent {
 };
 
 /* functions for updating the rmapbt based on bmbt map/unmap operations */
-int xfs_rmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
+int xfs_rmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		int whichfork, struct xfs_bmbt_irec *imap);
+int xfs_rmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		int whichfork, struct xfs_bmbt_irec *imap);
+int xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_trans *tp,
 		struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *imap);
-int xfs_rmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, int whichfork,
-		struct xfs_bmbt_irec *imap);
-int xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, int whichfork,
-		struct xfs_bmbt_irec *imap);
-int xfs_rmap_alloc_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		uint64_t owner);
-int xfs_rmap_free_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		uint64_t owner);
+int xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
+		xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner);
+int xfs_rmap_free_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
+		xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner);
 
 void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 221a88ea60bb..f79cf040d745 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -554,6 +554,7 @@ xfs_rmapbt_max_size(
 int
 xfs_rmapbt_calc_reserves(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
@@ -567,14 +568,14 @@ xfs_rmapbt_calc_reserves(
 	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
 		return 0;
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
 	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_rmap_blocks);
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
 
 	/* Reserve 1% of the AG or enough for 1 block per record. */
 	*ask += max(agblocks / 100, xfs_rmapbt_max_size(mp, agblocks));
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index 50198b6c3bb2..820d668b063d 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -51,7 +51,7 @@ extern xfs_extlen_t xfs_rmapbt_calc_size(struct xfs_mount *mp,
 extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp,
 		xfs_agblock_t agblocks);
 
-extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp,
+extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp,
 		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
 
 #endif	/* __XFS_RMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 350119eeaecb..081f46e30556 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -96,80 +96,146 @@ xfs_perag_put(
 	trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
 }
 
-/*
- * Check the validity of the SB found.
- */
+/* Check all the superblock fields we care about when reading one in. */
 STATIC int
-xfs_mount_validate_sb(
-	xfs_mount_t	*mp,
-	xfs_sb_t	*sbp,
-	bool		check_inprogress,
-	bool		check_version)
+xfs_validate_sb_read(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp)
 {
-	uint32_t	agcount = 0;
-	uint32_t	rem;
-
-	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
-		xfs_warn(mp, "bad magic number");
-		return -EWRONGFS;
-	}
-
-
-	if (!xfs_sb_good_version(sbp)) {
-		xfs_warn(mp, "bad version");
-		return -EWRONGFS;
-	}
+	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
+		return 0;
 
 	/*
-	 * Version 5 superblock feature mask validation. Reject combinations the
-	 * kernel cannot support up front before checking anything else. For
-	 * write validation, we don't need to check feature masks.
+	 * Version 5 superblock feature mask validation. Reject combinations
+	 * the kernel cannot support up front before checking anything else.
 	 */
-	if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) {
-		if (xfs_sb_has_compat_feature(sbp,
-					XFS_SB_FEAT_COMPAT_UNKNOWN)) {
-			xfs_warn(mp,
+	if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) {
+		xfs_warn(mp,
 "Superblock has unknown compatible features (0x%x) enabled.",
-				(sbp->sb_features_compat &
-						XFS_SB_FEAT_COMPAT_UNKNOWN));
-			xfs_warn(mp,
+			(sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN));
+		xfs_warn(mp,
 "Using a more recent kernel is recommended.");
-		}
+	}
 
-		if (xfs_sb_has_ro_compat_feature(sbp,
-					XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
-			xfs_alert(mp,
+	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+		xfs_alert(mp,
 "Superblock has unknown read-only compatible features (0x%x) enabled.",
-				(sbp->sb_features_ro_compat &
-						XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
-			if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-				xfs_warn(mp,
+			(sbp->sb_features_ro_compat &
+					XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
+		if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+			xfs_warn(mp,
 "Attempted to mount read-only compatible filesystem read-write.");
-				xfs_warn(mp,
+			xfs_warn(mp,
 "Filesystem can only be safely mounted read only.");
 
-				return -EINVAL;
-			}
-		}
-		if (xfs_sb_has_incompat_feature(sbp,
-					XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
-			xfs_warn(mp,
-"Superblock has unknown incompatible features (0x%x) enabled.",
-				(sbp->sb_features_incompat &
-						XFS_SB_FEAT_INCOMPAT_UNKNOWN));
-			xfs_warn(mp,
-"Filesystem can not be safely mounted by this kernel.");
 			return -EINVAL;
 		}
-	} else if (xfs_sb_version_hascrc(sbp)) {
-		/*
-		 * We can't read verify the sb LSN because the read verifier is
-		 * called before the log is allocated and processed. We know the
-		 * log is set up before write verifier (!check_version) calls,
-		 * so just check it here.
-		 */
-		if (!xfs_log_check_lsn(mp, sbp->sb_lsn))
-			return -EFSCORRUPTED;
+	}
+	if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
+		xfs_warn(mp,
+"Superblock has unknown incompatible features (0x%x) enabled.",
+			(sbp->sb_features_incompat &
+					XFS_SB_FEAT_INCOMPAT_UNKNOWN));
+		xfs_warn(mp,
+"Filesystem cannot be safely mounted by this kernel.");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Check all the superblock fields we care about when writing one out. */
+STATIC int
+xfs_validate_sb_write(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct xfs_sb		*sbp)
+{
+	/*
+	 * Carry out additional sb summary counter sanity checks when we write
+	 * the superblock.  We skip this in the read validator because there
+	 * could be newer superblocks in the log and if the values are garbage
+	 * even after replay we'll recalculate them at the end of log mount.
+	 *
+	 * mkfs has traditionally written zeroed counters to inprogress and
+	 * secondary superblocks, so allow this usage to continue because
+	 * we never read counters from such superblocks.
+	 */
+	if (XFS_BUF_ADDR(bp) == XFS_SB_DADDR && !sbp->sb_inprogress &&
+	    (sbp->sb_fdblocks > sbp->sb_dblocks ||
+	     !xfs_verify_icount(mp, sbp->sb_icount) ||
+	     sbp->sb_ifree > sbp->sb_icount)) {
+		xfs_warn(mp, "SB summary counter sanity check failed");
+		return -EFSCORRUPTED;
+	}
+
+	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
+		return 0;
+
+	/*
+	 * Version 5 superblock feature mask validation. Reject combinations
+	 * the kernel cannot support since we checked for unsupported bits in
+	 * the read verifier, which means that memory is corrupt.
+	 */
+	if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) {
+		xfs_warn(mp,
+"Corruption detected in superblock compatible features (0x%x)!",
+			(sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+
+	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+		xfs_alert(mp,
+"Corruption detected in superblock read-only compatible features (0x%x)!",
+			(sbp->sb_features_ro_compat &
+					XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+	if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
+		xfs_warn(mp,
+"Corruption detected in superblock incompatible features (0x%x)!",
+			(sbp->sb_features_incompat &
+					XFS_SB_FEAT_INCOMPAT_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+	if (xfs_sb_has_incompat_log_feature(sbp,
+			XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN)) {
+		xfs_warn(mp,
+"Corruption detected in superblock incompatible log features (0x%x)!",
+			(sbp->sb_features_log_incompat &
+					XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * We can't read verify the sb LSN because the read verifier is called
+	 * before the log is allocated and processed. We know the log is set up
+	 * before write verifier calls, so check it here.
+	 */
+	if (!xfs_log_check_lsn(mp, sbp->sb_lsn))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Check the validity of the SB. */
+STATIC int
+xfs_validate_sb_common(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct xfs_sb		*sbp)
+{
+	uint32_t		agcount = 0;
+	uint32_t		rem;
+
+	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
+		xfs_warn(mp, "bad magic number");
+		return -EWRONGFS;
+	}
+
+	if (!xfs_sb_good_version(sbp)) {
+		xfs_warn(mp, "bad version");
+		return -EWRONGFS;
 	}
 
 	if (xfs_sb_version_has_pquotino(sbp)) {
@@ -321,7 +387,12 @@ xfs_mount_validate_sb(
 		return -EFBIG;
 	}
 
-	if (check_inprogress && sbp->sb_inprogress) {
+	/*
+	 * Don't touch the filesystem if a user tool thinks it owns the primary
+	 * superblock.  mkfs doesn't clear the flag from secondary supers, so
+	 * we don't check them at all.
+	 */
+	if (XFS_BUF_ADDR(bp) == XFS_SB_DADDR && sbp->sb_inprogress) {
 		xfs_warn(mp, "Offline file system operation in progress!");
 		return -EFSCORRUPTED;
 	}
@@ -596,29 +667,6 @@ xfs_sb_to_disk(
 	}
 }
 
-static int
-xfs_sb_verify(
-	struct xfs_buf	*bp,
-	bool		check_version)
-{
-	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_sb	sb;
-
-	/*
-	 * Use call variant which doesn't convert quota flags from disk 
-	 * format, because xfs_mount_validate_sb checks the on-disk flags.
-	 */
-	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
-
-	/*
-	 * Only check the in progress field for the primary superblock as
-	 * mkfs.xfs doesn't clear it from secondary superblocks.
-	 */
-	return xfs_mount_validate_sb(mp, &sb,
-				     bp->b_maps[0].bm_bn == XFS_SB_DADDR,
-				     check_version);
-}
-
 /*
  * If the superblock has the CRC feature bit set or the CRC field is non-null,
  * check that the CRC is valid.  We check the CRC field is non-null because a
@@ -633,11 +681,12 @@ xfs_sb_verify(
  */
 static void
 xfs_sb_read_verify(
-	struct xfs_buf	*bp)
+	struct xfs_buf		*bp)
 {
-	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_dsb	*dsb = XFS_BUF_TO_SBP(bp);
-	int		error;
+	struct xfs_sb		sb;
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	struct xfs_dsb		*dsb = XFS_BUF_TO_SBP(bp);
+	int			error;
 
 	/*
 	 * open code the version check to avoid needing to convert the entire
@@ -657,7 +706,16 @@ xfs_sb_read_verify(
 			}
 		}
 	}
-	error = xfs_sb_verify(bp, true);
+
+	/*
+	 * Check all the superblock fields.  Don't byteswap the xquota flags
+	 * because _verify_common checks the on-disk values.
+	 */
+	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
+	error = xfs_validate_sb_common(mp, bp, &sb);
+	if (error)
+		goto out_error;
+	error = xfs_validate_sb_read(mp, &sb);
 
 out_error:
 	if (error == -EFSCORRUPTED || error == -EFSBADCRC)
@@ -691,15 +749,22 @@ static void
 xfs_sb_write_verify(
 	struct xfs_buf		*bp)
 {
+	struct xfs_sb		sb;
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_buf_log_item	*bip = bp->b_log_item;
 	int			error;
 
-	error = xfs_sb_verify(bp, false);
-	if (error) {
-		xfs_verifier_error(bp, error, __this_address);
-		return;
-	}
+	/*
+	 * Check all the superblock fields.  Don't byteswap the xquota flags
+	 * because _verify_common checks the on-disk values.
+	 */
+	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
+	error = xfs_validate_sb_common(mp, bp, &sb);
+	if (error)
+		goto out_error;
+	error = xfs_validate_sb_write(mp, bp, &sb);
+	if (error)
+		goto out_error;
 
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
 		return;
@@ -708,6 +773,10 @@ xfs_sb_write_verify(
 		XFS_BUF_TO_SBP(bp)->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
 	xfs_buf_update_cksum(bp, XFS_SB_CRC_OFF);
+	return;
+
+out_error:
+	xfs_verifier_error(bp, error, __this_address);
 }
 
 const struct xfs_buf_ops xfs_sb_buf_ops = {
@@ -804,6 +873,7 @@ xfs_initialize_perag_data(
 	uint64_t	bfree = 0;
 	uint64_t	bfreelst = 0;
 	uint64_t	btree = 0;
+	uint64_t	fdblocks;
 	int		error;
 
 	for (index = 0; index < agcount; index++) {
@@ -827,17 +897,31 @@ xfs_initialize_perag_data(
 		btree += pag->pagf_btreeblks;
 		xfs_perag_put(pag);
 	}
+	fdblocks = bfree + bfreelst + btree;
+
+	/*
+	 * If the new summary counts are obviously incorrect, fail the
+	 * mount operation because that implies the AGFs are also corrupt.
+	 * Clear BAD_SUMMARY so that we don't unmount with a dirty log, which
+	 * will prevent xfs_repair from fixing anything.
+	 */
+	if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
+		xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+		error = -EFSCORRUPTED;
+		goto out;
+	}
 
 	/* Overwrite incore superblock counters with just-read data */
 	spin_lock(&mp->m_sb_lock);
 	sbp->sb_ifree = ifree;
 	sbp->sb_icount = ialloc;
-	sbp->sb_fdblocks = bfree + bfreelst + btree;
+	sbp->sb_fdblocks = fdblocks;
 	spin_unlock(&mp->m_sb_lock);
 
 	xfs_reinit_percpu_counters(mp);
-
-	return 0;
+out:
+	mp->m_flags &= ~XFS_MOUNT_BAD_SUMMARY;
+	return error;
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 22089f1c880a..1c5debe748f0 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -64,6 +64,18 @@ void	xfs_log_get_max_trans_res(struct xfs_mount *mp,
 #define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
 #define XFS_TRANS_NO_WRITECOUNT 0x40	/* do not elevate SB writecount */
 #define XFS_TRANS_NOFS		0x80	/* pass KM_NOFS to kmem_alloc */
+/*
+ * LOWMODE is used by the allocator to activate the lowspace algorithm - when
+ * free space is running low the extent allocator may choose to allocate an
+ * extent from an AG without leaving sufficient space for a btree split when
+ * inserting the new extent. In this case the allocator will enable the
+ * lowspace algorithm which is supposed to allow further allocations (such as
+ * btree splits and newroots) to allocate from sequential AGs. In order to
+ * avoid locking AGs out of order the lowspace algorithm will start searching
+ * for free space from AG 0. If the correct transaction reservations have been
+ * made then this algorithm will eventually find all the space it needs.
+ */
+#define XFS_TRANS_LOWMODE	0x100	/* allocate in low space mode */
 
 /*
  * Field values for xfs_trans_mod_sb.
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index 2e2a243cef2e..33a5ca346baf 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -171,3 +171,37 @@ xfs_verify_rtbno(
 {
 	return rtbno < mp->m_sb.sb_rblocks;
 }
+
+/* Calculate the range of valid icount values. */
+static void
+xfs_icount_range(
+	struct xfs_mount	*mp,
+	unsigned long long	*min,
+	unsigned long long	*max)
+{
+	unsigned long long	nr_inos = 0;
+	xfs_agnumber_t		agno;
+
+	/* root, rtbitmap, rtsum all live in the first chunk */
+	*min = XFS_INODES_PER_CHUNK;
+
+	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
+		xfs_agino_t	first, last;
+
+		xfs_agino_range(mp, agno, &first, &last);
+		nr_inos += last - first + 1;
+	}
+	*max = nr_inos;
+}
+
+/* Sanity-checking of inode counts. */
+bool
+xfs_verify_icount(
+	struct xfs_mount	*mp,
+	unsigned long long	icount)
+{
+	unsigned long long	min, max;
+
+	xfs_icount_range(mp, &min, &max);
+	return icount >= min && icount <= max;
+}
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 4055d62f690c..b9e6c89284c3 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -165,5 +165,6 @@ bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
+bool xfs_verify_icount(struct xfs_mount *mp, unsigned long long icount);
 
 #endif	/* __XFS_TYPES_H__ */
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 9bb0745f1ad2..3068a9382feb 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -28,30 +28,30 @@
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_superblock_xref(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_superblock_xref(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agnumber_t			agno = sc->sm->sm_agno;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agnumber_t		agno = sc->sm->sm_agno;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_SB_BLOCK(mp);
 
-	error = xfs_scrub_ag_init(sc, agno, &sc->sa);
-	if (!xfs_scrub_xref_process_error(sc, agno, agbno, &error))
+	error = xchk_ag_init(sc, agno, &sc->sa);
+	if (!xchk_xref_process_error(sc, agno, agbno, &error))
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
@@ -65,17 +65,17 @@ xfs_scrub_superblock_xref(
  * sb 0 is ok and we can use its information to check everything else.
  */
 int
-xfs_scrub_superblock(
-	struct xfs_scrub_context	*sc)
+xchk_superblock(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_buf			*bp;
-	struct xfs_dsb			*sb;
-	xfs_agnumber_t			agno;
-	uint32_t			v2_ok;
-	__be32				features_mask;
-	int				error;
-	__be16				vernum_mask;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+	struct xfs_dsb		*sb;
+	xfs_agnumber_t		agno;
+	uint32_t		v2_ok;
+	__be32			features_mask;
+	int			error;
+	__be16			vernum_mask;
 
 	agno = sc->sm->sm_agno;
 	if (agno == 0)
@@ -98,7 +98,7 @@ xfs_scrub_superblock(
 	default:
 		break;
 	}
-	if (!xfs_scrub_process_error(sc, agno, XFS_SB_BLOCK(mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_SB_BLOCK(mp), &error))
 		return error;
 
 	sb = XFS_BUF_TO_SBP(bp);
@@ -110,46 +110,46 @@ xfs_scrub_superblock(
 	 * checked.
 	 */
 	if (sb->sb_blocksize != cpu_to_be32(mp->m_sb.sb_blocksize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_dblocks != cpu_to_be64(mp->m_sb.sb_dblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rblocks != cpu_to_be64(mp->m_sb.sb_rblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rextents != cpu_to_be64(mp->m_sb.sb_rextents))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (!uuid_equal(&sb->sb_uuid, &mp->m_sb.sb_uuid))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_logstart != cpu_to_be64(mp->m_sb.sb_logstart))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rootino != cpu_to_be64(mp->m_sb.sb_rootino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_rsumino != cpu_to_be64(mp->m_sb.sb_rsumino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_rextsize != cpu_to_be32(mp->m_sb.sb_rextsize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_agblocks != cpu_to_be32(mp->m_sb.sb_agblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_agcount != cpu_to_be32(mp->m_sb.sb_agcount))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rbmblocks != cpu_to_be32(mp->m_sb.sb_rbmblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logblocks != cpu_to_be32(mp->m_sb.sb_logblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Check sb_versionnum bits that are set at mkfs time. */
 	vernum_mask = cpu_to_be16(~XFS_SB_VERSION_OKBITS |
@@ -163,7 +163,7 @@ xfs_scrub_superblock(
 				  XFS_SB_VERSION_DIRV2BIT);
 	if ((sb->sb_versionnum & vernum_mask) !=
 	    (cpu_to_be16(mp->m_sb.sb_versionnum) & vernum_mask))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Check sb_versionnum bits that can be set after mkfs time. */
 	vernum_mask = cpu_to_be16(XFS_SB_VERSION_ATTRBIT |
@@ -171,40 +171,40 @@ xfs_scrub_superblock(
 				  XFS_SB_VERSION_QUOTABIT);
 	if ((sb->sb_versionnum & vernum_mask) !=
 	    (cpu_to_be16(mp->m_sb.sb_versionnum) & vernum_mask))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_sectsize != cpu_to_be16(mp->m_sb.sb_sectsize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inodesize != cpu_to_be16(mp->m_sb.sb_inodesize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inopblock != cpu_to_be16(mp->m_sb.sb_inopblock))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (memcmp(sb->sb_fname, mp->m_sb.sb_fname, sizeof(sb->sb_fname)))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_blocklog != mp->m_sb.sb_blocklog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_sectlog != mp->m_sb.sb_sectlog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inodelog != mp->m_sb.sb_inodelog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inopblog != mp->m_sb.sb_inopblog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_agblklog != mp->m_sb.sb_agblklog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rextslog != mp->m_sb.sb_rextslog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_imax_pct != mp->m_sb.sb_imax_pct)
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	/*
 	 * Skip the summary counters since we track them in memory anyway.
@@ -212,10 +212,10 @@ xfs_scrub_superblock(
 	 */
 
 	if (sb->sb_uquotino != cpu_to_be64(mp->m_sb.sb_uquotino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_gquotino != cpu_to_be64(mp->m_sb.sb_gquotino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	/*
 	 * Skip the quota flags since repair will force quotacheck.
@@ -223,46 +223,46 @@ xfs_scrub_superblock(
 	 */
 
 	if (sb->sb_flags != mp->m_sb.sb_flags)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_shared_vn != mp->m_sb.sb_shared_vn)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inoalignmt != cpu_to_be32(mp->m_sb.sb_inoalignmt))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_unit != cpu_to_be32(mp->m_sb.sb_unit))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_width != cpu_to_be32(mp->m_sb.sb_width))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_dirblklog != mp->m_sb.sb_dirblklog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logsectlog != mp->m_sb.sb_logsectlog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logsectsize != cpu_to_be16(mp->m_sb.sb_logsectsize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logsunit != cpu_to_be32(mp->m_sb.sb_logsunit))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Do we see any invalid bits in sb_features2? */
 	if (!xfs_sb_version_hasmorebits(&mp->m_sb)) {
 		if (sb->sb_features2 != 0)
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 	} else {
 		v2_ok = XFS_SB_VERSION2_OKBITS;
 		if (XFS_SB_VERSION_NUM(&mp->m_sb) >= XFS_SB_VERSION_5)
 			v2_ok |= XFS_SB_VERSION2_CRCBIT;
 
 		if (!!(sb->sb_features2 & cpu_to_be32(~v2_ok)))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		if (sb->sb_features2 != sb->sb_bad_features2)
-			xfs_scrub_block_set_preen(sc, bp);
+			xchk_block_set_preen(sc, bp);
 	}
 
 	/* Check sb_features2 flags that are set at mkfs time. */
@@ -272,26 +272,26 @@ xfs_scrub_superblock(
 				    XFS_SB_VERSION2_FTYPE);
 	if ((sb->sb_features2 & features_mask) !=
 	    (cpu_to_be32(mp->m_sb.sb_features2) & features_mask))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Check sb_features2 flags that can be set after mkfs time. */
 	features_mask = cpu_to_be32(XFS_SB_VERSION2_ATTR2BIT);
 	if ((sb->sb_features2 & features_mask) !=
 	    (cpu_to_be32(mp->m_sb.sb_features2) & features_mask))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (!xfs_sb_version_hascrc(&mp->m_sb)) {
 		/* all v5 fields must be zero */
 		if (memchr_inv(&sb->sb_features_compat, 0,
 				sizeof(struct xfs_dsb) -
 				offsetof(struct xfs_dsb, sb_features_compat)))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 	} else {
 		/* Check compat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_COMPAT_UNKNOWN);
 		if ((sb->sb_features_compat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_compat) & features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Check ro compat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_RO_COMPAT_UNKNOWN |
@@ -301,7 +301,7 @@ xfs_scrub_superblock(
 		if ((sb->sb_features_ro_compat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_ro_compat) &
 		     features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Check incompat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_INCOMPAT_UNKNOWN |
@@ -311,22 +311,22 @@ xfs_scrub_superblock(
 		if ((sb->sb_features_incompat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_incompat) &
 		     features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Check log incompat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN);
 		if ((sb->sb_features_log_incompat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_log_incompat) &
 		     features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Don't care about sb_crc */
 
 		if (sb->sb_spino_align != cpu_to_be32(mp->m_sb.sb_spino_align))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		if (sb->sb_pquotino != cpu_to_be64(mp->m_sb.sb_pquotino))
-			xfs_scrub_block_set_preen(sc, bp);
+			xchk_block_set_preen(sc, bp);
 
 		/* Don't care about sb_lsn */
 	}
@@ -334,15 +334,15 @@ xfs_scrub_superblock(
 	if (xfs_sb_version_hasmetauuid(&mp->m_sb)) {
 		/* The metadata UUID must be the same for all supers */
 		if (!uuid_equal(&sb->sb_meta_uuid, &mp->m_sb.sb_meta_uuid))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 	}
 
 	/* Everything else must be zero. */
 	if (memchr_inv(sb + 1, 0,
 			BBTOB(bp->b_length) - sizeof(struct xfs_dsb)))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
-	xfs_scrub_superblock_xref(sc, bp);
+	xchk_superblock_xref(sc, bp);
 
 	return error;
 }
@@ -351,7 +351,7 @@ xfs_scrub_superblock(
 
 /* Tally freespace record lengths. */
 STATIC int
-xfs_scrub_agf_record_bno_lengths(
+xchk_agf_record_bno_lengths(
 	struct xfs_btree_cur		*cur,
 	struct xfs_alloc_rec_incore	*rec,
 	void				*priv)
@@ -364,75 +364,75 @@ xfs_scrub_agf_record_bno_lengths(
 
 /* Check agf_freeblks */
 static inline void
-xfs_scrub_agf_xref_freeblks(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref_freeblks(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	xfs_extlen_t			blocks = 0;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	xfs_extlen_t		blocks = 0;
+	int			error;
 
 	if (!sc->sa.bno_cur)
 		return;
 
 	error = xfs_alloc_query_all(sc->sa.bno_cur,
-			xfs_scrub_agf_record_bno_lengths, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.bno_cur))
+			xchk_agf_record_bno_lengths, &blocks);
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
 	if (blocks != be32_to_cpu(agf->agf_freeblks))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Cross reference the AGF with the cntbt (freespace by length btree) */
 static inline void
-xfs_scrub_agf_xref_cntbt(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref_cntbt(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	xfs_agblock_t			agbno;
-	xfs_extlen_t			blocks;
-	int				have;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	xfs_agblock_t		agbno;
+	xfs_extlen_t		blocks;
+	int			have;
+	int			error;
 
 	if (!sc->sa.cnt_cur)
 		return;
 
 	/* Any freespace at all? */
 	error = xfs_alloc_lookup_le(sc->sa.cnt_cur, 0, -1U, &have);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.cnt_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.cnt_cur))
 		return;
 	if (!have) {
 		if (agf->agf_freeblks != be32_to_cpu(0))
-			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 		return;
 	}
 
 	/* Check agf_longest */
 	error = xfs_alloc_get_rec(sc->sa.cnt_cur, &agbno, &blocks, &have);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.cnt_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.cnt_cur))
 		return;
 	if (!have || blocks != be32_to_cpu(agf->agf_longest))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Check the btree block counts in the AGF against the btrees. */
 STATIC void
-xfs_scrub_agf_xref_btreeblks(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref_btreeblks(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			blocks;
-	xfs_agblock_t			btreeblks;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		blocks;
+	xfs_agblock_t		btreeblks;
+	int			error;
 
 	/* Check agf_rmap_blocks; set up for agf_btreeblks check */
 	if (sc->sa.rmap_cur) {
 		error = xfs_btree_count_blocks(sc->sa.rmap_cur, &blocks);
-		if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+		if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 			return;
 		btreeblks = blocks - 1;
 		if (blocks != be32_to_cpu(agf->agf_rmap_blocks))
-			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 	} else {
 		btreeblks = 0;
 	}
@@ -447,136 +447,136 @@ xfs_scrub_agf_xref_btreeblks(
 
 	/* Check agf_btreeblks */
 	error = xfs_btree_count_blocks(sc->sa.bno_cur, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.bno_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
 	btreeblks += blocks - 1;
 
 	error = xfs_btree_count_blocks(sc->sa.cnt_cur, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.cnt_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.cnt_cur))
 		return;
 	btreeblks += blocks - 1;
 
 	if (btreeblks != be32_to_cpu(agf->agf_btreeblks))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Check agf_refcount_blocks against tree size */
 static inline void
-xfs_scrub_agf_xref_refcblks(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref_refcblks(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	xfs_agblock_t			blocks;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	xfs_agblock_t		blocks;
+	int			error;
 
 	if (!sc->sa.refc_cur)
 		return;
 
 	error = xfs_btree_count_blocks(sc->sa.refc_cur, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (blocks != be32_to_cpu(agf->agf_refcount_blocks))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agf_xref(
-	struct xfs_scrub_context	*sc)
+xchk_agf_xref(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_AGF_BLOCK(mp);
 
-	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	error = xchk_ag_btcur_init(sc, &sc->sa);
 	if (error)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_agf_xref_freeblks(sc);
-	xfs_scrub_agf_xref_cntbt(sc);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_agf_xref_freeblks(sc);
+	xchk_agf_xref_cntbt(sc);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_agf_xref_btreeblks(sc);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
-	xfs_scrub_agf_xref_refcblks(sc);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_agf_xref_btreeblks(sc);
+	xchk_xref_is_not_shared(sc, agbno, 1);
+	xchk_agf_xref_refcblks(sc);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
 
 /* Scrub the AGF. */
 int
-xfs_scrub_agf(
-	struct xfs_scrub_context	*sc)
+xchk_agf(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_agf			*agf;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_agblock_t			eoag;
-	xfs_agblock_t			agfl_first;
-	xfs_agblock_t			agfl_last;
-	xfs_agblock_t			agfl_count;
-	xfs_agblock_t			fl_count;
-	int				level;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agf		*agf;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_agblock_t		eoag;
+	xfs_agblock_t		agfl_first;
+	xfs_agblock_t		agfl_last;
+	xfs_agblock_t		agfl_count;
+	xfs_agblock_t		fl_count;
+	int			level;
+	int			error = 0;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sc->sa.agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
 			&sc->sa.agf_bp, &sc->sa.agfl_bp);
-	if (!xfs_scrub_process_error(sc, agno, XFS_AGF_BLOCK(sc->mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_AGF_BLOCK(sc->mp), &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, sc->sa.agf_bp);
+	xchk_buffer_recheck(sc, sc->sa.agf_bp);
 
 	agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 
 	/* Check the AG length */
 	eoag = be32_to_cpu(agf->agf_length);
 	if (eoag != xfs_ag_block_count(mp, agno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	/* Check the AGF btree roots and levels */
 	agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_BNO]);
 	if (!xfs_verify_agbno(mp, agno, agbno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_CNT]);
 	if (!xfs_verify_agbno(mp, agno, agbno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]);
 	if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]);
 	if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
 		agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_RMAP]);
 		if (!xfs_verify_agbno(mp, agno, agbno))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 		level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]);
 		if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 	}
 
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
 		agbno = be32_to_cpu(agf->agf_refcount_root);
 		if (!xfs_verify_agbno(mp, agno, agbno))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 		level = be32_to_cpu(agf->agf_refcount_level);
 		if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 	}
 
 	/* Check the AGFL counters */
@@ -588,57 +588,57 @@ xfs_scrub_agf(
 	else
 		fl_count = xfs_agfl_size(mp) - agfl_first + agfl_last + 1;
 	if (agfl_count != 0 && fl_count != agfl_count)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
-	xfs_scrub_agf_xref(sc);
+	xchk_agf_xref(sc);
 out:
 	return error;
 }
 
 /* AGFL */
 
-struct xfs_scrub_agfl_info {
-	struct xfs_owner_info		oinfo;
-	unsigned int			sz_entries;
-	unsigned int			nr_entries;
-	xfs_agblock_t			*entries;
-	struct xfs_scrub_context	*sc;
+struct xchk_agfl_info {
+	struct xfs_owner_info	oinfo;
+	unsigned int		sz_entries;
+	unsigned int		nr_entries;
+	xfs_agblock_t		*entries;
+	struct xfs_scrub	*sc;
 };
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agfl_block_xref(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	struct xfs_owner_info		*oinfo)
+xchk_agfl_block_xref(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	struct xfs_owner_info	*oinfo)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 }
 
 /* Scrub an AGFL block. */
 STATIC int
-xfs_scrub_agfl_block(
-	struct xfs_mount		*mp,
-	xfs_agblock_t			agbno,
-	void				*priv)
+xchk_agfl_block(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agbno,
+	void			*priv)
 {
-	struct xfs_scrub_agfl_info	*sai = priv;
-	struct xfs_scrub_context	*sc = sai->sc;
-	xfs_agnumber_t			agno = sc->sa.agno;
+	struct xchk_agfl_info	*sai = priv;
+	struct xfs_scrub	*sc = sai->sc;
+	xfs_agnumber_t		agno = sc->sa.agno;
 
 	if (xfs_verify_agbno(mp, agno, agbno) &&
 	    sai->nr_entries < sai->sz_entries)
 		sai->entries[sai->nr_entries++] = agbno;
 	else
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agfl_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agfl_bp);
 
-	xfs_scrub_agfl_block_xref(sc, agbno, priv);
+	xchk_agfl_block_xref(sc, agbno, priv);
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return XFS_BTREE_QUERY_RANGE_ABORT;
@@ -647,7 +647,7 @@ xfs_scrub_agfl_block(
 }
 
 static int
-xfs_scrub_agblock_cmp(
+xchk_agblock_cmp(
 	const void		*pa,
 	const void		*pb)
 {
@@ -659,28 +659,28 @@ xfs_scrub_agblock_cmp(
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agfl_xref(
-	struct xfs_scrub_context	*sc)
+xchk_agfl_xref(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_AGFL_BLOCK(mp);
 
-	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	error = xchk_ag_btcur_init(sc, &sc->sa);
 	if (error)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 
 	/*
 	 * Scrub teardown will take care of sc->sa for us.  Leave sc->sa
@@ -690,26 +690,26 @@ xfs_scrub_agfl_xref(
 
 /* Scrub the AGFL. */
 int
-xfs_scrub_agfl(
-	struct xfs_scrub_context	*sc)
+xchk_agfl(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_scrub_agfl_info	sai;
-	struct xfs_agf			*agf;
-	xfs_agnumber_t			agno;
-	unsigned int			agflcount;
-	unsigned int			i;
-	int				error;
+	struct xchk_agfl_info	sai;
+	struct xfs_agf		*agf;
+	xfs_agnumber_t		agno;
+	unsigned int		agflcount;
+	unsigned int		i;
+	int			error;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sc->sa.agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
 			&sc->sa.agf_bp, &sc->sa.agfl_bp);
-	if (!xfs_scrub_process_error(sc, agno, XFS_AGFL_BLOCK(sc->mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_AGFL_BLOCK(sc->mp), &error))
 		goto out;
 	if (!sc->sa.agf_bp)
 		return -EFSCORRUPTED;
-	xfs_scrub_buffer_recheck(sc, sc->sa.agfl_bp);
+	xchk_buffer_recheck(sc, sc->sa.agfl_bp);
 
-	xfs_scrub_agfl_xref(sc);
+	xchk_agfl_xref(sc);
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
@@ -718,7 +718,7 @@ xfs_scrub_agfl(
 	agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 	agflcount = be32_to_cpu(agf->agf_flcount);
 	if (agflcount > xfs_agfl_size(sc->mp)) {
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 		goto out;
 	}
 	memset(&sai, 0, sizeof(sai));
@@ -734,7 +734,7 @@ xfs_scrub_agfl(
 	/* Check the blocks in the AGFL. */
 	xfs_rmap_ag_owner(&sai.oinfo, XFS_RMAP_OWN_AG);
 	error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(sc->sa.agf_bp),
-			sc->sa.agfl_bp, xfs_scrub_agfl_block, &sai);
+			sc->sa.agfl_bp, xchk_agfl_block, &sai);
 	if (error == XFS_BTREE_QUERY_RANGE_ABORT) {
 		error = 0;
 		goto out_free;
@@ -743,16 +743,16 @@ xfs_scrub_agfl(
 		goto out_free;
 
 	if (agflcount != sai.nr_entries) {
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 		goto out_free;
 	}
 
 	/* Sort entries, check for duplicates. */
 	sort(sai.entries, sai.nr_entries, sizeof(sai.entries[0]),
-			xfs_scrub_agblock_cmp, NULL);
+			xchk_agblock_cmp, NULL);
 	for (i = 1; i < sai.nr_entries; i++) {
 		if (sai.entries[i] == sai.entries[i - 1]) {
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 			break;
 		}
 	}
@@ -767,103 +767,103 @@ out:
 
 /* Check agi_count/agi_freecount */
 static inline void
-xfs_scrub_agi_xref_icounts(
-	struct xfs_scrub_context	*sc)
+xchk_agi_xref_icounts(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_agi			*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
-	xfs_agino_t			icount;
-	xfs_agino_t			freecount;
-	int				error;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
+	xfs_agino_t		icount;
+	xfs_agino_t		freecount;
+	int			error;
 
 	if (!sc->sa.ino_cur)
 		return;
 
 	error = xfs_ialloc_count_inodes(sc->sa.ino_cur, &icount, &freecount);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.ino_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.ino_cur))
 		return;
 	if (be32_to_cpu(agi->agi_count) != icount ||
 	    be32_to_cpu(agi->agi_freecount) != freecount)
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agi_bp);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agi_xref(
-	struct xfs_scrub_context	*sc)
+xchk_agi_xref(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_AGI_BLOCK(mp);
 
-	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	error = xchk_ag_btcur_init(sc, &sc->sa);
 	if (error)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
-	xfs_scrub_agi_xref_icounts(sc);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_agi_xref_icounts(sc);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
 
 /* Scrub the AGI. */
 int
-xfs_scrub_agi(
-	struct xfs_scrub_context	*sc)
+xchk_agi(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_agi			*agi;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_agblock_t			eoag;
-	xfs_agino_t			agino;
-	xfs_agino_t			first_agino;
-	xfs_agino_t			last_agino;
-	xfs_agino_t			icount;
-	int				i;
-	int				level;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agi		*agi;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_agblock_t		eoag;
+	xfs_agino_t		agino;
+	xfs_agino_t		first_agino;
+	xfs_agino_t		last_agino;
+	xfs_agino_t		icount;
+	int			i;
+	int			level;
+	int			error = 0;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sc->sa.agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
 			&sc->sa.agf_bp, &sc->sa.agfl_bp);
-	if (!xfs_scrub_process_error(sc, agno, XFS_AGI_BLOCK(sc->mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_AGI_BLOCK(sc->mp), &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, sc->sa.agi_bp);
+	xchk_buffer_recheck(sc, sc->sa.agi_bp);
 
 	agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
 
 	/* Check the AG length */
 	eoag = be32_to_cpu(agi->agi_length);
 	if (eoag != xfs_ag_block_count(mp, agno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check btree roots and levels */
 	agbno = be32_to_cpu(agi->agi_root);
 	if (!xfs_verify_agbno(mp, agno, agbno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	level = be32_to_cpu(agi->agi_level);
 	if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
 		agbno = be32_to_cpu(agi->agi_free_root);
 		if (!xfs_verify_agbno(mp, agno, agbno))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 		level = be32_to_cpu(agi->agi_free_level);
 		if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 	}
 
 	/* Check inode counters */
@@ -871,16 +871,16 @@ xfs_scrub_agi(
 	icount = be32_to_cpu(agi->agi_count);
 	if (icount > last_agino - first_agino + 1 ||
 	    icount < be32_to_cpu(agi->agi_freecount))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check inode pointers */
 	agino = be32_to_cpu(agi->agi_newino);
 	if (agino != NULLAGINO && !xfs_verify_agino(mp, agno, agino))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	agino = be32_to_cpu(agi->agi_dirino);
 	if (agino != NULLAGINO && !xfs_verify_agino(mp, agno, agino))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check unlinked inode buckets */
 	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
@@ -888,13 +888,13 @@ xfs_scrub_agi(
 		if (agino == NULLAGINO)
 			continue;
 		if (!xfs_verify_agino(mp, agno, agino))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 	}
 
 	if (agi->agi_pad32 != cpu_to_be32(0))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
-	xfs_scrub_agi_xref(sc);
+	xchk_agi_xref(sc);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 117eedac53df..f7568a4b5fe5 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -17,24 +17,31 @@
 #include "xfs_sb.h"
 #include "xfs_inode.h"
 #include "xfs_alloc.h"
+#include "xfs_alloc_btree.h"
 #include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
 #include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_refcount_btree.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
 
 /* Superblock */
 
 /* Repair the superblock. */
 int
-xfs_repair_superblock(
-	struct xfs_scrub_context	*sc)
+xrep_superblock(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_buf			*bp;
-	xfs_agnumber_t			agno;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+	xfs_agnumber_t		agno;
+	int			error;
 
 	/* Don't try to repair AG 0's sb; let xfs_repair deal with it. */
 	agno = sc->sm->sm_agno;
@@ -54,3 +61,873 @@ xfs_repair_superblock(
 	xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
 	return error;
 }
+
+/* AGF */
+
+struct xrep_agf_allocbt {
+	struct xfs_scrub	*sc;
+	xfs_agblock_t		freeblks;
+	xfs_agblock_t		longest;
+};
+
+/* Record free space shape information. */
+STATIC int
+xrep_agf_walk_allocbt(
+	struct xfs_btree_cur		*cur,
+	struct xfs_alloc_rec_incore	*rec,
+	void				*priv)
+{
+	struct xrep_agf_allocbt		*raa = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(raa->sc, &error))
+		return error;
+
+	raa->freeblks += rec->ar_blockcount;
+	if (rec->ar_blockcount > raa->longest)
+		raa->longest = rec->ar_blockcount;
+	return error;
+}
+
+/* Does this AGFL block look sane? */
+STATIC int
+xrep_agf_check_agfl_block(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agbno,
+	void			*priv)
+{
+	struct xfs_scrub	*sc = priv;
+
+	if (!xfs_verify_agbno(mp, sc->sa.agno, agbno))
+		return -EFSCORRUPTED;
+	return 0;
+}
+
+/*
+ * Offset within the xrep_find_ag_btree array for each btree type.  Avoid the
+ * XFS_BTNUM_ names here to avoid creating a sparse array.
+ */
+enum {
+	XREP_AGF_BNOBT = 0,
+	XREP_AGF_CNTBT,
+	XREP_AGF_RMAPBT,
+	XREP_AGF_REFCOUNTBT,
+	XREP_AGF_END,
+	XREP_AGF_MAX
+};
+
+/* Check a btree root candidate. */
+static inline bool
+xrep_check_btree_root(
+	struct xfs_scrub		*sc,
+	struct xrep_find_ag_btree	*fab)
+{
+	struct xfs_mount		*mp = sc->mp;
+	xfs_agnumber_t			agno = sc->sm->sm_agno;
+
+	return xfs_verify_agbno(mp, agno, fab->root) &&
+	       fab->height <= XFS_BTREE_MAXLEVELS;
+}
+
+/*
+ * Given the btree roots described by *fab, find the roots, check them for
+ * sanity, and pass the root data back out via *fab.
+ *
+ * This is /also/ a chicken and egg problem because we have to use the rmapbt
+ * (rooted in the AGF) to find the btrees rooted in the AGF.  We also have no
+ * idea if the btrees make any sense.  If we hit obvious corruptions in those
+ * btrees we'll bail out.
+ */
+STATIC int
+xrep_agf_find_btrees(
+	struct xfs_scrub		*sc,
+	struct xfs_buf			*agf_bp,
+	struct xrep_find_ag_btree	*fab,
+	struct xfs_buf			*agfl_bp)
+{
+	struct xfs_agf			*old_agf = XFS_BUF_TO_AGF(agf_bp);
+	int				error;
+
+	/* Go find the root data. */
+	error = xrep_find_ag_btree_roots(sc, agf_bp, fab, agfl_bp);
+	if (error)
+		return error;
+
+	/* We must find the bnobt, cntbt, and rmapbt roots. */
+	if (!xrep_check_btree_root(sc, &fab[XREP_AGF_BNOBT]) ||
+	    !xrep_check_btree_root(sc, &fab[XREP_AGF_CNTBT]) ||
+	    !xrep_check_btree_root(sc, &fab[XREP_AGF_RMAPBT]))
+		return -EFSCORRUPTED;
+
+	/*
+	 * We relied on the rmapbt to reconstruct the AGF.  If we get a
+	 * different root then something's seriously wrong.
+	 */
+	if (fab[XREP_AGF_RMAPBT].root !=
+	    be32_to_cpu(old_agf->agf_roots[XFS_BTNUM_RMAPi]))
+		return -EFSCORRUPTED;
+
+	/* We must find the refcountbt root if that feature is enabled. */
+	if (xfs_sb_version_hasreflink(&sc->mp->m_sb) &&
+	    !xrep_check_btree_root(sc, &fab[XREP_AGF_REFCOUNTBT]))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/*
+ * Reinitialize the AGF header, making an in-core copy of the old contents so
+ * that we know which in-core state needs to be reinitialized.
+ */
+STATIC void
+xrep_agf_init_header(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp,
+	struct xfs_agf		*old_agf)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+
+	memcpy(old_agf, agf, sizeof(*old_agf));
+	memset(agf, 0, BBTOB(agf_bp->b_length));
+	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
+	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
+	agf->agf_seqno = cpu_to_be32(sc->sa.agno);
+	agf->agf_length = cpu_to_be32(xfs_ag_block_count(mp, sc->sa.agno));
+	agf->agf_flfirst = old_agf->agf_flfirst;
+	agf->agf_fllast = old_agf->agf_fllast;
+	agf->agf_flcount = old_agf->agf_flcount;
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
+
+	/* Mark the incore AGF data stale until we're done fixing things. */
+	ASSERT(sc->sa.pag->pagf_init);
+	sc->sa.pag->pagf_init = 0;
+}
+
+/* Set btree root information in an AGF. */
+STATIC void
+xrep_agf_set_roots(
+	struct xfs_scrub		*sc,
+	struct xfs_agf			*agf,
+	struct xrep_find_ag_btree	*fab)
+{
+	agf->agf_roots[XFS_BTNUM_BNOi] =
+			cpu_to_be32(fab[XREP_AGF_BNOBT].root);
+	agf->agf_levels[XFS_BTNUM_BNOi] =
+			cpu_to_be32(fab[XREP_AGF_BNOBT].height);
+
+	agf->agf_roots[XFS_BTNUM_CNTi] =
+			cpu_to_be32(fab[XREP_AGF_CNTBT].root);
+	agf->agf_levels[XFS_BTNUM_CNTi] =
+			cpu_to_be32(fab[XREP_AGF_CNTBT].height);
+
+	agf->agf_roots[XFS_BTNUM_RMAPi] =
+			cpu_to_be32(fab[XREP_AGF_RMAPBT].root);
+	agf->agf_levels[XFS_BTNUM_RMAPi] =
+			cpu_to_be32(fab[XREP_AGF_RMAPBT].height);
+
+	if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
+		agf->agf_refcount_root =
+				cpu_to_be32(fab[XREP_AGF_REFCOUNTBT].root);
+		agf->agf_refcount_level =
+				cpu_to_be32(fab[XREP_AGF_REFCOUNTBT].height);
+	}
+}
+
+/* Update all AGF fields which derive from btree contents. */
+STATIC int
+xrep_agf_calc_from_btrees(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp)
+{
+	struct xrep_agf_allocbt	raa = { .sc = sc };
+	struct xfs_btree_cur	*cur = NULL;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		btreeblks;
+	xfs_agblock_t		blocks;
+	int			error;
+
+	/* Update the AGF counters from the bnobt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_BNO);
+	error = xfs_alloc_query_all(cur, xrep_agf_walk_allocbt, &raa);
+	if (error)
+		goto err;
+	error = xfs_btree_count_blocks(cur, &blocks);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+	btreeblks = blocks - 1;
+	agf->agf_freeblks = cpu_to_be32(raa.freeblks);
+	agf->agf_longest = cpu_to_be32(raa.longest);
+
+	/* Update the AGF counters from the cntbt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_CNT);
+	error = xfs_btree_count_blocks(cur, &blocks);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+	btreeblks += blocks - 1;
+
+	/* Update the AGF counters from the rmapbt. */
+	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
+	error = xfs_btree_count_blocks(cur, &blocks);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+	agf->agf_rmap_blocks = cpu_to_be32(blocks);
+	btreeblks += blocks - 1;
+
+	agf->agf_btreeblks = cpu_to_be32(btreeblks);
+
+	/* Update the AGF counters from the refcountbt. */
+	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+		cur = xfs_refcountbt_init_cursor(mp, sc->tp, agf_bp,
+				sc->sa.agno);
+		error = xfs_btree_count_blocks(cur, &blocks);
+		if (error)
+			goto err;
+		xfs_btree_del_cursor(cur, error);
+		agf->agf_refcount_blocks = cpu_to_be32(blocks);
+	}
+
+	return 0;
+err:
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/* Commit the new AGF and reinitialize the incore state. */
+STATIC int
+xrep_agf_commit_new(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp)
+{
+	struct xfs_perag	*pag;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+
+	/* Trigger fdblocks recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/* Write this to disk. */
+	xfs_trans_buf_set_type(sc->tp, agf_bp, XFS_BLFT_AGF_BUF);
+	xfs_trans_log_buf(sc->tp, agf_bp, 0, BBTOB(agf_bp->b_length) - 1);
+
+	/* Now reinitialize the in-core counters we changed. */
+	pag = sc->sa.pag;
+	pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
+	pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
+	pag->pagf_longest = be32_to_cpu(agf->agf_longest);
+	pag->pagf_levels[XFS_BTNUM_BNOi] =
+			be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]);
+	pag->pagf_levels[XFS_BTNUM_CNTi] =
+			be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]);
+	pag->pagf_levels[XFS_BTNUM_RMAPi] =
+			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
+	pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
+	pag->pagf_init = 1;
+
+	return 0;
+}
+
+/* Repair the AGF. v5 filesystems only. */
+int
+xrep_agf(
+	struct xfs_scrub		*sc)
+{
+	struct xrep_find_ag_btree	fab[XREP_AGF_MAX] = {
+		[XREP_AGF_BNOBT] = {
+			.rmap_owner = XFS_RMAP_OWN_AG,
+			.buf_ops = &xfs_allocbt_buf_ops,
+			.magic = XFS_ABTB_CRC_MAGIC,
+		},
+		[XREP_AGF_CNTBT] = {
+			.rmap_owner = XFS_RMAP_OWN_AG,
+			.buf_ops = &xfs_allocbt_buf_ops,
+			.magic = XFS_ABTC_CRC_MAGIC,
+		},
+		[XREP_AGF_RMAPBT] = {
+			.rmap_owner = XFS_RMAP_OWN_AG,
+			.buf_ops = &xfs_rmapbt_buf_ops,
+			.magic = XFS_RMAP_CRC_MAGIC,
+		},
+		[XREP_AGF_REFCOUNTBT] = {
+			.rmap_owner = XFS_RMAP_OWN_REFC,
+			.buf_ops = &xfs_refcountbt_buf_ops,
+			.magic = XFS_REFC_CRC_MAGIC,
+		},
+		[XREP_AGF_END] = {
+			.buf_ops = NULL,
+		},
+	};
+	struct xfs_agf			old_agf;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_buf			*agf_bp;
+	struct xfs_buf			*agfl_bp;
+	struct xfs_agf			*agf;
+	int				error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	xchk_perag_get(sc->mp, &sc->sa);
+	/*
+	 * Make sure we have the AGF buffer, as scrub might have decided it
+	 * was corrupt after xfs_alloc_read_agf failed with -EFSCORRUPTED.
+	 */
+	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGF_DADDR(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &agf_bp, NULL);
+	if (error)
+		return error;
+	agf_bp->b_ops = &xfs_agf_buf_ops;
+	agf = XFS_BUF_TO_AGF(agf_bp);
+
+	/*
+	 * Load the AGFL so that we can screen out OWN_AG blocks that are on
+	 * the AGFL now; these blocks might have once been part of the
+	 * bno/cnt/rmap btrees but are not now.  This is a chicken and egg
+	 * problem: the AGF is corrupt, so we have to trust the AGFL contents
+	 * because we can't do any serious cross-referencing with any of the
+	 * btrees rooted in the AGF.  If the AGFL contents are obviously bad
+	 * then we'll bail out.
+	 */
+	error = xfs_alloc_read_agfl(mp, sc->tp, sc->sa.agno, &agfl_bp);
+	if (error)
+		return error;
+
+	/*
+	 * Spot-check the AGFL blocks; if they're obviously corrupt then
+	 * there's nothing we can do but bail out.
+	 */
+	error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(agf_bp), agfl_bp,
+			xrep_agf_check_agfl_block, sc);
+	if (error)
+		return error;
+
+	/*
+	 * Find the AGF btree roots.  This is also a chicken-and-egg situation;
+	 * see the function for more details.
+	 */
+	error = xrep_agf_find_btrees(sc, agf_bp, fab, agfl_bp);
+	if (error)
+		return error;
+
+	/* Start rewriting the header and implant the btrees we found. */
+	xrep_agf_init_header(sc, agf_bp, &old_agf);
+	xrep_agf_set_roots(sc, agf, fab);
+	error = xrep_agf_calc_from_btrees(sc, agf_bp);
+	if (error)
+		goto out_revert;
+
+	/* Commit the changes and reinitialize incore state. */
+	return xrep_agf_commit_new(sc, agf_bp);
+
+out_revert:
+	/* Mark the incore AGF state stale and revert the AGF. */
+	sc->sa.pag->pagf_init = 0;
+	memcpy(agf, &old_agf, sizeof(old_agf));
+	return error;
+}
+
+/* AGFL */
+
+struct xrep_agfl {
+	/* Bitmap of other OWN_AG metadata blocks. */
+	struct xfs_bitmap	agmetablocks;
+
+	/* Bitmap of free space. */
+	struct xfs_bitmap	*freesp;
+
+	struct xfs_scrub	*sc;
+};
+
+/* Record all OWN_AG (free space btree) information from the rmap data. */
+STATIC int
+xrep_agfl_walk_rmap(
+	struct xfs_btree_cur	*cur,
+	struct xfs_rmap_irec	*rec,
+	void			*priv)
+{
+	struct xrep_agfl	*ra = priv;
+	xfs_fsblock_t		fsb;
+	int			error = 0;
+
+	if (xchk_should_terminate(ra->sc, &error))
+		return error;
+
+	/* Record all the OWN_AG blocks. */
+	if (rec->rm_owner == XFS_RMAP_OWN_AG) {
+		fsb = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno,
+				rec->rm_startblock);
+		error = xfs_bitmap_set(ra->freesp, fsb, rec->rm_blockcount);
+		if (error)
+			return error;
+	}
+
+	return xfs_bitmap_set_btcur_path(&ra->agmetablocks, cur);
+}
+
+/*
+ * Map out all the non-AGFL OWN_AG space in this AG so that we can deduce
+ * which blocks belong to the AGFL.
+ *
+ * Compute the set of old AGFL blocks by subtracting from the list of OWN_AG
+ * blocks the list of blocks owned by all other OWN_AG metadata (bnobt, cntbt,
+ * rmapbt).  These are the old AGFL blocks, so return that list and the number
+ * of blocks we're actually going to put back on the AGFL.
+ */
+STATIC int
+xrep_agfl_collect_blocks(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp,
+	struct xfs_bitmap	*agfl_extents,
+	xfs_agblock_t		*flcount)
+{
+	struct xrep_agfl	ra;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_btree_cur	*cur;
+	struct xfs_bitmap_range	*br;
+	struct xfs_bitmap_range	*n;
+	int			error;
+
+	ra.sc = sc;
+	ra.freesp = agfl_extents;
+	xfs_bitmap_init(&ra.agmetablocks);
+
+	/* Find all space used by the free space btrees & rmapbt. */
+	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
+	error = xfs_rmap_query_all(cur, xrep_agfl_walk_rmap, &ra);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+
+	/* Find all blocks currently being used by the bnobt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_BNO);
+	error = xfs_bitmap_set_btblocks(&ra.agmetablocks, cur);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+
+	/* Find all blocks currently being used by the cntbt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_CNT);
+	error = xfs_bitmap_set_btblocks(&ra.agmetablocks, cur);
+	if (error)
+		goto err;
+
+	xfs_btree_del_cursor(cur, error);
+
+	/*
+	 * Drop the freesp meta blocks that are in use by btrees.
+	 * The remaining blocks /should/ be AGFL blocks.
+	 */
+	error = xfs_bitmap_disunion(agfl_extents, &ra.agmetablocks);
+	xfs_bitmap_destroy(&ra.agmetablocks);
+	if (error)
+		return error;
+
+	/*
+	 * Calculate the new AGFL size.  If we found more blocks than fit in
+	 * the AGFL we'll free them later.
+	 */
+	*flcount = 0;
+	for_each_xfs_bitmap_extent(br, n, agfl_extents) {
+		*flcount += br->len;
+		if (*flcount > xfs_agfl_size(mp))
+			break;
+	}
+	if (*flcount > xfs_agfl_size(mp))
+		*flcount = xfs_agfl_size(mp);
+	return 0;
+
+err:
+	xfs_bitmap_destroy(&ra.agmetablocks);
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/* Update the AGF and reset the in-core state. */
+STATIC void
+xrep_agfl_update_agf(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp,
+	xfs_agblock_t		flcount)
+{
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+
+	ASSERT(flcount <= xfs_agfl_size(sc->mp));
+
+	/* Trigger fdblocks recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/* Update the AGF counters. */
+	if (sc->sa.pag->pagf_init)
+		sc->sa.pag->pagf_flcount = flcount;
+	agf->agf_flfirst = cpu_to_be32(0);
+	agf->agf_flcount = cpu_to_be32(flcount);
+	agf->agf_fllast = cpu_to_be32(flcount - 1);
+
+	xfs_alloc_log_agf(sc->tp, agf_bp,
+			XFS_AGF_FLFIRST | XFS_AGF_FLLAST | XFS_AGF_FLCOUNT);
+}
+
+/* Write out a totally new AGFL. */
+STATIC void
+xrep_agfl_init_header(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agfl_bp,
+	struct xfs_bitmap	*agfl_extents,
+	xfs_agblock_t		flcount)
+{
+	struct xfs_mount	*mp = sc->mp;
+	__be32			*agfl_bno;
+	struct xfs_bitmap_range	*br;
+	struct xfs_bitmap_range	*n;
+	struct xfs_agfl		*agfl;
+	xfs_agblock_t		agbno;
+	unsigned int		fl_off;
+
+	ASSERT(flcount <= xfs_agfl_size(mp));
+
+	/*
+	 * Start rewriting the header by setting the bno[] array to
+	 * NULLAGBLOCK, then setting AGFL header fields.
+	 */
+	agfl = XFS_BUF_TO_AGFL(agfl_bp);
+	memset(agfl, 0xFF, BBTOB(agfl_bp->b_length));
+	agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
+	agfl->agfl_seqno = cpu_to_be32(sc->sa.agno);
+	uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
+
+	/*
+	 * Fill the AGFL with the remaining blocks.  If agfl_extents has more
+	 * blocks than fit in the AGFL, they will be freed in a subsequent
+	 * step.
+	 */
+	fl_off = 0;
+	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, agfl_bp);
+	for_each_xfs_bitmap_extent(br, n, agfl_extents) {
+		agbno = XFS_FSB_TO_AGBNO(mp, br->start);
+
+		trace_xrep_agfl_insert(mp, sc->sa.agno, agbno, br->len);
+
+		while (br->len > 0 && fl_off < flcount) {
+			agfl_bno[fl_off] = cpu_to_be32(agbno);
+			fl_off++;
+			agbno++;
+
+			/*
+			 * We've now used br->start by putting it in the AGFL,
+			 * so bump br so that we don't reap the block later.
+			 */
+			br->start++;
+			br->len--;
+		}
+
+		if (br->len)
+			break;
+		list_del(&br->list);
+		kmem_free(br);
+	}
+
+	/* Write new AGFL to disk. */
+	xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF);
+	xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1);
+}
+
+/* Repair the AGFL. */
+int
+xrep_agfl(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_owner_info	oinfo;
+	struct xfs_bitmap	agfl_extents;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*agf_bp;
+	struct xfs_buf		*agfl_bp;
+	xfs_agblock_t		flcount;
+	int			error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	xchk_perag_get(sc->mp, &sc->sa);
+	xfs_bitmap_init(&agfl_extents);
+
+	/*
+	 * Read the AGF so that we can query the rmapbt.  We hope that there's
+	 * nothing wrong with the AGF, but all the AG header repair functions
+	 * have this chicken-and-egg problem.
+	 */
+	error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp);
+	if (error)
+		return error;
+	if (!agf_bp)
+		return -ENOMEM;
+
+	/*
+	 * Make sure we have the AGFL buffer, as scrub might have decided it
+	 * was corrupt after xfs_alloc_read_agfl failed with -EFSCORRUPTED.
+	 */
+	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGFL_DADDR(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL);
+	if (error)
+		return error;
+	agfl_bp->b_ops = &xfs_agfl_buf_ops;
+
+	/* Gather all the extents we're going to put on the new AGFL. */
+	error = xrep_agfl_collect_blocks(sc, agf_bp, &agfl_extents, &flcount);
+	if (error)
+		goto err;
+
+	/*
+	 * Update AGF and AGFL.  We reset the global free block counter when
+	 * we adjust the AGF flcount (which can fail) so avoid updating any
+	 * buffers until we know that part works.
+	 */
+	xrep_agfl_update_agf(sc, agf_bp, flcount);
+	xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount);
+
+	/*
+	 * Ok, the AGFL should be ready to go now.  Roll the transaction to
+	 * make the new AGFL permanent before we start using it to return
+	 * freespace overflow to the freespace btrees.
+	 */
+	sc->sa.agf_bp = agf_bp;
+	sc->sa.agfl_bp = agfl_bp;
+	error = xrep_roll_ag_trans(sc);
+	if (error)
+		goto err;
+
+	/* Dump any AGFL overflow. */
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
+	return xrep_reap_extents(sc, &agfl_extents, &oinfo, XFS_AG_RESV_AGFL);
+err:
+	xfs_bitmap_destroy(&agfl_extents);
+	return error;
+}
+
+/* AGI */
+
+/*
+ * Offset within the xrep_find_ag_btree array for each btree type.  Avoid the
+ * XFS_BTNUM_ names here to avoid creating a sparse array.
+ */
+enum {
+	XREP_AGI_INOBT = 0,
+	XREP_AGI_FINOBT,
+	XREP_AGI_END,
+	XREP_AGI_MAX
+};
+
+/*
+ * Given the inode btree roots described by *fab, find the roots, check them
+ * for sanity, and pass the root data back out via *fab.
+ */
+STATIC int
+xrep_agi_find_btrees(
+	struct xfs_scrub		*sc,
+	struct xrep_find_ag_btree	*fab)
+{
+	struct xfs_buf			*agf_bp;
+	struct xfs_mount		*mp = sc->mp;
+	int				error;
+
+	/* Read the AGF. */
+	error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp);
+	if (error)
+		return error;
+	if (!agf_bp)
+		return -ENOMEM;
+
+	/* Find the btree roots. */
+	error = xrep_find_ag_btree_roots(sc, agf_bp, fab, NULL);
+	if (error)
+		return error;
+
+	/* We must find the inobt root. */
+	if (!xrep_check_btree_root(sc, &fab[XREP_AGI_INOBT]))
+		return -EFSCORRUPTED;
+
+	/* We must find the finobt root if that feature is enabled. */
+	if (xfs_sb_version_hasfinobt(&mp->m_sb) &&
+	    !xrep_check_btree_root(sc, &fab[XREP_AGI_FINOBT]))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/*
+ * Reinitialize the AGI header, making an in-core copy of the old contents so
+ * that we know which in-core state needs to be reinitialized.
+ */
+STATIC void
+xrep_agi_init_header(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agi_bp,
+	struct xfs_agi		*old_agi)
+{
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
+	struct xfs_mount	*mp = sc->mp;
+
+	memcpy(old_agi, agi, sizeof(*old_agi));
+	memset(agi, 0, BBTOB(agi_bp->b_length));
+	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
+	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
+	agi->agi_seqno = cpu_to_be32(sc->sa.agno);
+	agi->agi_length = cpu_to_be32(xfs_ag_block_count(mp, sc->sa.agno));
+	agi->agi_newino = cpu_to_be32(NULLAGINO);
+	agi->agi_dirino = cpu_to_be32(NULLAGINO);
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
+
+	/* We don't know how to fix the unlinked list yet. */
+	memcpy(&agi->agi_unlinked, &old_agi->agi_unlinked,
+			sizeof(agi->agi_unlinked));
+
+	/* Mark the incore AGF data stale until we're done fixing things. */
+	ASSERT(sc->sa.pag->pagi_init);
+	sc->sa.pag->pagi_init = 0;
+}
+
+/* Set btree root information in an AGI. */
+STATIC void
+xrep_agi_set_roots(
+	struct xfs_scrub		*sc,
+	struct xfs_agi			*agi,
+	struct xrep_find_ag_btree	*fab)
+{
+	agi->agi_root = cpu_to_be32(fab[XREP_AGI_INOBT].root);
+	agi->agi_level = cpu_to_be32(fab[XREP_AGI_INOBT].height);
+
+	if (xfs_sb_version_hasfinobt(&sc->mp->m_sb)) {
+		agi->agi_free_root = cpu_to_be32(fab[XREP_AGI_FINOBT].root);
+		agi->agi_free_level = cpu_to_be32(fab[XREP_AGI_FINOBT].height);
+	}
+}
+
+/* Update the AGI counters. */
+STATIC int
+xrep_agi_calc_from_btrees(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agi_bp)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agino_t		count;
+	xfs_agino_t		freecount;
+	int			error;
+
+	cur = xfs_inobt_init_cursor(mp, sc->tp, agi_bp, sc->sa.agno,
+			XFS_BTNUM_INO);
+	error = xfs_ialloc_count_inodes(cur, &count, &freecount);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+
+	agi->agi_count = cpu_to_be32(count);
+	agi->agi_freecount = cpu_to_be32(freecount);
+	return 0;
+err:
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/* Trigger reinitialization of the in-core data. */
+STATIC int
+xrep_agi_commit_new(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agi_bp)
+{
+	struct xfs_perag	*pag;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
+
+	/* Trigger inode count recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/* Write this to disk. */
+	xfs_trans_buf_set_type(sc->tp, agi_bp, XFS_BLFT_AGI_BUF);
+	xfs_trans_log_buf(sc->tp, agi_bp, 0, BBTOB(agi_bp->b_length) - 1);
+
+	/* Now reinitialize the in-core counters if necessary. */
+	pag = sc->sa.pag;
+	pag->pagi_count = be32_to_cpu(agi->agi_count);
+	pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
+	pag->pagi_init = 1;
+
+	return 0;
+}
+
+/* Repair the AGI. */
+int
+xrep_agi(
+	struct xfs_scrub		*sc)
+{
+	struct xrep_find_ag_btree	fab[XREP_AGI_MAX] = {
+		[XREP_AGI_INOBT] = {
+			.rmap_owner = XFS_RMAP_OWN_INOBT,
+			.buf_ops = &xfs_inobt_buf_ops,
+			.magic = XFS_IBT_CRC_MAGIC,
+		},
+		[XREP_AGI_FINOBT] = {
+			.rmap_owner = XFS_RMAP_OWN_INOBT,
+			.buf_ops = &xfs_inobt_buf_ops,
+			.magic = XFS_FIBT_CRC_MAGIC,
+		},
+		[XREP_AGI_END] = {
+			.buf_ops = NULL
+		},
+	};
+	struct xfs_agi			old_agi;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_buf			*agi_bp;
+	struct xfs_agi			*agi;
+	int				error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	xchk_perag_get(sc->mp, &sc->sa);
+	/*
+	 * Make sure we have the AGI buffer, as scrub might have decided it
+	 * was corrupt after xfs_ialloc_read_agi failed with -EFSCORRUPTED.
+	 */
+	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGI_DADDR(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &agi_bp, NULL);
+	if (error)
+		return error;
+	agi_bp->b_ops = &xfs_agi_buf_ops;
+	agi = XFS_BUF_TO_AGI(agi_bp);
+
+	/* Find the AGI btree roots. */
+	error = xrep_agi_find_btrees(sc, fab);
+	if (error)
+		return error;
+
+	/* Start rewriting the header and implant the btrees we found. */
+	xrep_agi_init_header(sc, agi_bp, &old_agi);
+	xrep_agi_set_roots(sc, agi, fab);
+	error = xrep_agi_calc_from_btrees(sc, agi_bp);
+	if (error)
+		goto out_revert;
+
+	/* Reinitialize in-core state. */
+	return xrep_agi_commit_new(sc, agi_bp);
+
+out_revert:
+	/* Mark the incore AGI state stale and revert the AGI. */
+	sc->sa.pag->pagi_init = 0;
+	memcpy(agi, &old_agi, sizeof(old_agi));
+	return error;
+}
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 50e4f7fa06f0..036b5c7021eb 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -28,11 +28,11 @@
  * Set us up to scrub free space btrees.
  */
 int
-xfs_scrub_setup_ag_allocbt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_ag_allocbt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, ip, false);
 }
 
 /* Free space btree scrubber. */
@@ -41,71 +41,71 @@ xfs_scrub_setup_ag_allocbt(
  * bnobt/cntbt record, respectively.
  */
 STATIC void
-xfs_scrub_allocbt_xref_other(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_allocbt_xref_other(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	struct xfs_btree_cur		**pcur;
-	xfs_agblock_t			fbno;
-	xfs_extlen_t			flen;
-	int				has_otherrec;
-	int				error;
+	struct xfs_btree_cur	**pcur;
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	int			has_otherrec;
+	int			error;
 
 	if (sc->sm->sm_type == XFS_SCRUB_TYPE_BNOBT)
 		pcur = &sc->sa.cnt_cur;
 	else
 		pcur = &sc->sa.bno_cur;
-	if (!*pcur || xfs_scrub_skip_xref(sc->sm))
+	if (!*pcur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_alloc_lookup_le(*pcur, agbno, len, &has_otherrec);
-	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
+	if (!xchk_should_check_xref(sc, &error, pcur))
 		return;
 	if (!has_otherrec) {
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 		return;
 	}
 
 	error = xfs_alloc_get_rec(*pcur, &fbno, &flen, &has_otherrec);
-	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
+	if (!xchk_should_check_xref(sc, &error, pcur))
 		return;
 	if (!has_otherrec) {
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 		return;
 	}
 
 	if (fbno != agbno || flen != len)
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_allocbt_xref(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_allocbt_xref(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_allocbt_xref_other(sc, agbno, len);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
-	xfs_scrub_xref_has_no_owner(sc, agbno, len);
-	xfs_scrub_xref_is_not_shared(sc, agbno, len);
+	xchk_allocbt_xref_other(sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(sc, agbno, len);
+	xchk_xref_has_no_owner(sc, agbno, len);
+	xchk_xref_is_not_shared(sc, agbno, len);
 }
 
 /* Scrub a bnobt/cntbt record. */
 STATIC int
-xfs_scrub_allocbt_rec(
-	struct xfs_scrub_btree		*bs,
-	union xfs_btree_rec		*rec)
+xchk_allocbt_rec(
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
-	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
-	xfs_agblock_t			bno;
-	xfs_extlen_t			len;
-	int				error = 0;
+	struct xfs_mount	*mp = bs->cur->bc_mp;
+	xfs_agnumber_t		agno = bs->cur->bc_private.a.agno;
+	xfs_agblock_t		bno;
+	xfs_extlen_t		len;
+	int			error = 0;
 
 	bno = be32_to_cpu(rec->alloc.ar_startblock);
 	len = be32_to_cpu(rec->alloc.ar_blockcount);
@@ -113,57 +113,57 @@ xfs_scrub_allocbt_rec(
 	if (bno + len <= bno ||
 	    !xfs_verify_agbno(mp, agno, bno) ||
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xfs_scrub_allocbt_xref(bs->sc, bno, len);
+	xchk_allocbt_xref(bs->sc, bno, len);
 
 	return error;
 }
 
 /* Scrub the freespace btrees for some AG. */
 STATIC int
-xfs_scrub_allocbt(
-	struct xfs_scrub_context	*sc,
-	xfs_btnum_t			which)
+xchk_allocbt(
+	struct xfs_scrub	*sc,
+	xfs_btnum_t		which)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_btree_cur		*cur;
+	struct xfs_owner_info	oinfo;
+	struct xfs_btree_cur	*cur;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
 	cur = which == XFS_BTNUM_BNO ? sc->sa.bno_cur : sc->sa.cnt_cur;
-	return xfs_scrub_btree(sc, cur, xfs_scrub_allocbt_rec, &oinfo, NULL);
+	return xchk_btree(sc, cur, xchk_allocbt_rec, &oinfo, NULL);
 }
 
 int
-xfs_scrub_bnobt(
-	struct xfs_scrub_context	*sc)
+xchk_bnobt(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_allocbt(sc, XFS_BTNUM_BNO);
+	return xchk_allocbt(sc, XFS_BTNUM_BNO);
 }
 
 int
-xfs_scrub_cntbt(
-	struct xfs_scrub_context	*sc)
+xchk_cntbt(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_allocbt(sc, XFS_BTNUM_CNT);
+	return xchk_allocbt(sc, XFS_BTNUM_CNT);
 }
 
 /* xref check that the extent is not free */
 void
-xfs_scrub_xref_is_used_space(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_xref_is_used_space(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	bool				is_freesp;
-	int				error;
+	bool			is_freesp;
+	int			error;
 
-	if (!sc->sa.bno_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.bno_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_alloc_has_record(sc->sa.bno_cur, agbno, len, &is_freesp);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.bno_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
 	if (is_freesp)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.bno_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.bno_cur, 0);
 }
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index de51cf8a8516..81d5e90547a1 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -32,11 +32,11 @@
 
 /* Set us up to scrub an inode's extended attributes. */
 int
-xfs_scrub_setup_xattr(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_xattr(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	size_t				sz;
+	size_t			sz;
 
 	/*
 	 * Allocate the buffer without the inode lock held.  We need enough
@@ -50,14 +50,14 @@ xfs_scrub_setup_xattr(
 	if (!sc->buf)
 		return -ENOMEM;
 
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Extended Attributes */
 
-struct xfs_scrub_xattr {
+struct xchk_xattr {
 	struct xfs_attr_list_context	context;
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub		*sc;
 };
 
 /*
@@ -69,22 +69,22 @@ struct xfs_scrub_xattr {
  * or if we get more or less data than we expected.
  */
 static void
-xfs_scrub_xattr_listent(
+xchk_xattr_listent(
 	struct xfs_attr_list_context	*context,
 	int				flags,
 	unsigned char			*name,
 	int				namelen,
 	int				valuelen)
 {
-	struct xfs_scrub_xattr		*sx;
+	struct xchk_xattr		*sx;
 	struct xfs_da_args		args = { NULL };
 	int				error = 0;
 
-	sx = container_of(context, struct xfs_scrub_xattr, context);
+	sx = container_of(context, struct xchk_xattr, context);
 
 	if (flags & XFS_ATTR_INCOMPLETE) {
 		/* Incomplete attr key, just mark the inode for preening. */
-		xfs_scrub_ino_set_preen(sx->sc, context->dp->i_ino);
+		xchk_ino_set_preen(sx->sc, context->dp->i_ino);
 		return;
 	}
 
@@ -106,11 +106,11 @@ xfs_scrub_xattr_listent(
 	error = xfs_attr_get_ilocked(context->dp, &args);
 	if (error == -EEXIST)
 		error = 0;
-	if (!xfs_scrub_fblock_process_error(sx->sc, XFS_ATTR_FORK, args.blkno,
+	if (!xchk_fblock_process_error(sx->sc, XFS_ATTR_FORK, args.blkno,
 			&error))
 		goto fail_xref;
 	if (args.valuelen != valuelen)
-		xfs_scrub_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
+		xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
 					     args.blkno);
 fail_xref:
 	if (sx->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -126,14 +126,14 @@ fail_xref:
  * the smallest address
  */
 STATIC bool
-xfs_scrub_xattr_set_map(
-	struct xfs_scrub_context	*sc,
-	unsigned long			*map,
-	unsigned int			start,
-	unsigned int			len)
+xchk_xattr_set_map(
+	struct xfs_scrub	*sc,
+	unsigned long		*map,
+	unsigned int		start,
+	unsigned int		len)
 {
-	unsigned int			mapsize = sc->mp->m_attr_geo->blksize;
-	bool				ret = true;
+	unsigned int		mapsize = sc->mp->m_attr_geo->blksize;
+	bool			ret = true;
 
 	if (start >= mapsize)
 		return false;
@@ -154,8 +154,8 @@ xfs_scrub_xattr_set_map(
  * attr freemap has problems or points to used space.
  */
 STATIC bool
-xfs_scrub_xattr_check_freemap(
-	struct xfs_scrub_context	*sc,
+xchk_xattr_check_freemap(
+	struct xfs_scrub		*sc,
 	unsigned long			*map,
 	struct xfs_attr3_icleaf_hdr	*leafhdr)
 {
@@ -168,7 +168,7 @@ xfs_scrub_xattr_check_freemap(
 	freemap = (unsigned long *)sc->buf + BITS_TO_LONGS(mapsize);
 	bitmap_zero(freemap, mapsize);
 	for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
-		if (!xfs_scrub_xattr_set_map(sc, freemap,
+		if (!xchk_xattr_set_map(sc, freemap,
 				leafhdr->freemap[i].base,
 				leafhdr->freemap[i].size))
 			return false;
@@ -184,8 +184,8 @@ xfs_scrub_xattr_check_freemap(
  * Returns the number of bytes used for the name/value data.
  */
 STATIC void
-xfs_scrub_xattr_entry(
-	struct xfs_scrub_da_btree	*ds,
+xchk_xattr_entry(
+	struct xchk_da_btree		*ds,
 	int				level,
 	char				*buf_end,
 	struct xfs_attr_leafblock	*leaf,
@@ -204,17 +204,17 @@ xfs_scrub_xattr_entry(
 	unsigned int			namesize;
 
 	if (ent->pad2 != 0)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	/* Hash values in order? */
 	if (be32_to_cpu(ent->hashval) < *last_hashval)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	*last_hashval = be32_to_cpu(ent->hashval);
 
 	nameidx = be16_to_cpu(ent->nameidx);
 	if (nameidx < leafhdr->firstused ||
 	    nameidx >= mp->m_attr_geo->blksize) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		return;
 	}
 
@@ -225,27 +225,27 @@ xfs_scrub_xattr_entry(
 				be16_to_cpu(lentry->valuelen));
 		name_end = (char *)lentry + namesize;
 		if (lentry->namelen == 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	} else {
 		rentry = xfs_attr3_leaf_name_remote(leaf, idx);
 		namesize = xfs_attr_leaf_entsize_remote(rentry->namelen);
 		name_end = (char *)rentry + namesize;
 		if (rentry->namelen == 0 || rentry->valueblk == 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	}
 	if (name_end > buf_end)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
-	if (!xfs_scrub_xattr_set_map(ds->sc, usedmap, nameidx, namesize))
-		xfs_scrub_da_set_corrupt(ds, level);
+	if (!xchk_xattr_set_map(ds->sc, usedmap, nameidx, namesize))
+		xchk_da_set_corrupt(ds, level);
 	if (!(ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		*usedbytes += namesize;
 }
 
 /* Scrub an attribute leaf. */
 STATIC int
-xfs_scrub_xattr_block(
-	struct xfs_scrub_da_btree	*ds,
+xchk_xattr_block(
+	struct xchk_da_btree		*ds,
 	int				level)
 {
 	struct xfs_attr3_icleaf_hdr	leafhdr;
@@ -275,10 +275,10 @@ xfs_scrub_xattr_block(
 
 		if (leaf->hdr.pad1 != 0 || leaf->hdr.pad2 != 0 ||
 		    leaf->hdr.info.hdr.pad != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	} else {
 		if (leaf->hdr.pad1 != 0 || leaf->hdr.info.pad != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	}
 
 	/* Check the leaf header */
@@ -286,44 +286,44 @@ xfs_scrub_xattr_block(
 	hdrsize = xfs_attr3_leaf_hdr_size(leaf);
 
 	if (leafhdr.usedbytes > mp->m_attr_geo->blksize)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	if (leafhdr.firstused > mp->m_attr_geo->blksize)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	if (leafhdr.firstused < hdrsize)
-		xfs_scrub_da_set_corrupt(ds, level);
-	if (!xfs_scrub_xattr_set_map(ds->sc, usedmap, 0, hdrsize))
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
+	if (!xchk_xattr_set_map(ds->sc, usedmap, 0, hdrsize))
+		xchk_da_set_corrupt(ds, level);
 
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
 	entries = xfs_attr3_leaf_entryp(leaf);
 	if ((char *)&entries[leafhdr.count] > (char *)leaf + leafhdr.firstused)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	buf_end = (char *)bp->b_addr + mp->m_attr_geo->blksize;
 	for (i = 0, ent = entries; i < leafhdr.count; ent++, i++) {
 		/* Mark the leaf entry itself. */
 		off = (char *)ent - (char *)leaf;
-		if (!xfs_scrub_xattr_set_map(ds->sc, usedmap, off,
+		if (!xchk_xattr_set_map(ds->sc, usedmap, off,
 				sizeof(xfs_attr_leaf_entry_t))) {
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 			goto out;
 		}
 
 		/* Check the entry and nameval. */
-		xfs_scrub_xattr_entry(ds, level, buf_end, leaf, &leafhdr,
+		xchk_xattr_entry(ds, level, buf_end, leaf, &leafhdr,
 				usedmap, ent, i, &usedbytes, &last_hashval);
 
 		if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			goto out;
 	}
 
-	if (!xfs_scrub_xattr_check_freemap(ds->sc, usedmap, &leafhdr))
-		xfs_scrub_da_set_corrupt(ds, level);
+	if (!xchk_xattr_check_freemap(ds->sc, usedmap, &leafhdr))
+		xchk_da_set_corrupt(ds, level);
 
 	if (leafhdr.usedbytes != usedbytes)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 out:
 	return 0;
@@ -331,8 +331,8 @@ out:
 
 /* Scrub a attribute btree record. */
 STATIC int
-xfs_scrub_xattr_rec(
-	struct xfs_scrub_da_btree	*ds,
+xchk_xattr_rec(
+	struct xchk_da_btree		*ds,
 	int				level,
 	void				*rec)
 {
@@ -352,14 +352,14 @@ xfs_scrub_xattr_rec(
 	blk = &ds->state->path.blk[level];
 
 	/* Check the whole block, if necessary. */
-	error = xfs_scrub_xattr_block(ds, level);
+	error = xchk_xattr_block(ds, level);
 	if (error)
 		goto out;
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
 	/* Check the hash of the entry. */
-	error = xfs_scrub_da_btree_hash(ds, level, &ent->hashval);
+	error = xchk_da_btree_hash(ds, level, &ent->hashval);
 	if (error)
 		goto out;
 
@@ -368,7 +368,7 @@ xfs_scrub_xattr_rec(
 	hdrsize = xfs_attr3_leaf_hdr_size(bp->b_addr);
 	nameidx = be16_to_cpu(ent->nameidx);
 	if (nameidx < hdrsize || nameidx >= mp->m_attr_geo->blksize) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out;
 	}
 
@@ -377,12 +377,12 @@ xfs_scrub_xattr_rec(
 	badflags = ~(XFS_ATTR_LOCAL | XFS_ATTR_ROOT | XFS_ATTR_SECURE |
 			XFS_ATTR_INCOMPLETE);
 	if ((ent->flags & badflags) != 0)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	if (ent->flags & XFS_ATTR_LOCAL) {
 		lentry = (struct xfs_attr_leaf_name_local *)
 				(((char *)bp->b_addr) + nameidx);
 		if (lentry->namelen <= 0) {
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 			goto out;
 		}
 		calc_hash = xfs_da_hashname(lentry->nameval, lentry->namelen);
@@ -390,13 +390,13 @@ xfs_scrub_xattr_rec(
 		rentry = (struct xfs_attr_leaf_name_remote *)
 				(((char *)bp->b_addr) + nameidx);
 		if (rentry->namelen <= 0) {
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 			goto out;
 		}
 		calc_hash = xfs_da_hashname(rentry->name, rentry->namelen);
 	}
 	if (calc_hash != hash)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 out:
 	return error;
@@ -404,10 +404,10 @@ out:
 
 /* Scrub the extended attribute metadata. */
 int
-xfs_scrub_xattr(
-	struct xfs_scrub_context	*sc)
+xchk_xattr(
+	struct xfs_scrub		*sc)
 {
-	struct xfs_scrub_xattr		sx;
+	struct xchk_xattr		sx;
 	struct attrlist_cursor_kern	cursor = { 0 };
 	xfs_dablk_t			last_checked = -1U;
 	int				error = 0;
@@ -417,7 +417,7 @@ xfs_scrub_xattr(
 
 	memset(&sx, 0, sizeof(sx));
 	/* Check attribute tree structure */
-	error = xfs_scrub_da_btree(sc, XFS_ATTR_FORK, xfs_scrub_xattr_rec,
+	error = xchk_da_btree(sc, XFS_ATTR_FORK, xchk_xattr_rec,
 			&last_checked);
 	if (error)
 		goto out;
@@ -429,7 +429,7 @@ xfs_scrub_xattr(
 	sx.context.dp = sc->ip;
 	sx.context.cursor = &cursor;
 	sx.context.resynch = 1;
-	sx.context.put_listent = xfs_scrub_xattr_listent;
+	sx.context.put_listent = xchk_xattr_listent;
 	sx.context.tp = sc->tp;
 	sx.context.flags = ATTR_INCOMPLETE;
 	sx.sc = sc;
@@ -438,7 +438,7 @@ xfs_scrub_xattr(
 	 * Look up every xattr in this file by name.
 	 *
 	 * Use the backend implementation of xfs_attr_list to call
-	 * xfs_scrub_xattr_listent on every attribute key in this inode.
+	 * xchk_xattr_listent on every attribute key in this inode.
 	 * In other words, we use the same iterator/callback mechanism
 	 * that listattr uses to scrub extended attributes, though in our
 	 * _listent function, we check the value of the attribute.
@@ -451,7 +451,7 @@ xfs_scrub_xattr(
 	 * locking order.
 	 */
 	error = xfs_attr_list_int_ilocked(&sx.context);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error))
 		goto out;
 out:
 	return error;
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
new file mode 100644
index 000000000000..fdadc9e1dc49
--- /dev/null
+++ b/fs/xfs/scrub/bitmap.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_btree.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+
+/*
+ * Set a range of this bitmap.  Caller must ensure the range is not set.
+ *
+ * This is the logical equivalent of bitmap |= mask(start, len).
+ */
+int
+xfs_bitmap_set(
+	struct xfs_bitmap	*bitmap,
+	uint64_t		start,
+	uint64_t		len)
+{
+	struct xfs_bitmap_range	*bmr;
+
+	bmr = kmem_alloc(sizeof(struct xfs_bitmap_range), KM_MAYFAIL);
+	if (!bmr)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&bmr->list);
+	bmr->start = start;
+	bmr->len = len;
+	list_add_tail(&bmr->list, &bitmap->list);
+
+	return 0;
+}
+
+/* Free everything related to this bitmap. */
+void
+xfs_bitmap_destroy(
+	struct xfs_bitmap	*bitmap)
+{
+	struct xfs_bitmap_range	*bmr;
+	struct xfs_bitmap_range	*n;
+
+	for_each_xfs_bitmap_extent(bmr, n, bitmap) {
+		list_del(&bmr->list);
+		kmem_free(bmr);
+	}
+}
+
+/* Set up a per-AG block bitmap. */
+void
+xfs_bitmap_init(
+	struct xfs_bitmap	*bitmap)
+{
+	INIT_LIST_HEAD(&bitmap->list);
+}
+
+/* Compare two btree extents. */
+static int
+xfs_bitmap_range_cmp(
+	void			*priv,
+	struct list_head	*a,
+	struct list_head	*b)
+{
+	struct xfs_bitmap_range	*ap;
+	struct xfs_bitmap_range	*bp;
+
+	ap = container_of(a, struct xfs_bitmap_range, list);
+	bp = container_of(b, struct xfs_bitmap_range, list);
+
+	if (ap->start > bp->start)
+		return 1;
+	if (ap->start < bp->start)
+		return -1;
+	return 0;
+}
+
+/*
+ * Remove all the blocks mentioned in @sub from the extents in @bitmap.
+ *
+ * The intent is that callers will iterate the rmapbt for all of its records
+ * for a given owner to generate @bitmap; and iterate all the blocks of the
+ * metadata structures that are not being rebuilt and have the same rmapbt
+ * owner to generate @sub.  This routine subtracts all the extents
+ * mentioned in sub from all the extents linked in @bitmap, which leaves
+ * @bitmap as the list of blocks that are not accounted for, which we assume
+ * are the dead blocks of the old metadata structure.  The blocks mentioned in
+ * @bitmap can be reaped.
+ *
+ * This is the logical equivalent of bitmap &= ~sub.
+ */
+#define LEFT_ALIGNED	(1 << 0)
+#define RIGHT_ALIGNED	(1 << 1)
+int
+xfs_bitmap_disunion(
+	struct xfs_bitmap	*bitmap,
+	struct xfs_bitmap	*sub)
+{
+	struct list_head	*lp;
+	struct xfs_bitmap_range	*br;
+	struct xfs_bitmap_range	*new_br;
+	struct xfs_bitmap_range	*sub_br;
+	uint64_t		sub_start;
+	uint64_t		sub_len;
+	int			state;
+	int			error = 0;
+
+	if (list_empty(&bitmap->list) || list_empty(&sub->list))
+		return 0;
+	ASSERT(!list_empty(&sub->list));
+
+	list_sort(NULL, &bitmap->list, xfs_bitmap_range_cmp);
+	list_sort(NULL, &sub->list, xfs_bitmap_range_cmp);
+
+	/*
+	 * Now that we've sorted both lists, we iterate bitmap once, rolling
+	 * forward through sub and/or bitmap as necessary until we find an
+	 * overlap or reach the end of either list.  We do not reset lp to the
+	 * head of bitmap nor do we reset sub_br to the head of sub.  The
+	 * list traversal is similar to merge sort, but we're deleting
+	 * instead.  In this manner we avoid O(n^2) operations.
+	 */
+	sub_br = list_first_entry(&sub->list, struct xfs_bitmap_range,
+			list);
+	lp = bitmap->list.next;
+	while (lp != &bitmap->list) {
+		br = list_entry(lp, struct xfs_bitmap_range, list);
+
+		/*
+		 * Advance sub_br and/or br until we find a pair that
+		 * intersect or we run out of extents.
+		 */
+		while (sub_br->start + sub_br->len <= br->start) {
+			if (list_is_last(&sub_br->list, &sub->list))
+				goto out;
+			sub_br = list_next_entry(sub_br, list);
+		}
+		if (sub_br->start >= br->start + br->len) {
+			lp = lp->next;
+			continue;
+		}
+
+		/* trim sub_br to fit the extent we have */
+		sub_start = sub_br->start;
+		sub_len = sub_br->len;
+		if (sub_br->start < br->start) {
+			sub_len -= br->start - sub_br->start;
+			sub_start = br->start;
+		}
+		if (sub_len > br->len)
+			sub_len = br->len;
+
+		state = 0;
+		if (sub_start == br->start)
+			state |= LEFT_ALIGNED;
+		if (sub_start + sub_len == br->start + br->len)
+			state |= RIGHT_ALIGNED;
+		switch (state) {
+		case LEFT_ALIGNED:
+			/* Coincides with only the left. */
+			br->start += sub_len;
+			br->len -= sub_len;
+			break;
+		case RIGHT_ALIGNED:
+			/* Coincides with only the right. */
+			br->len -= sub_len;
+			lp = lp->next;
+			break;
+		case LEFT_ALIGNED | RIGHT_ALIGNED:
+			/* Total overlap, just delete ex. */
+			lp = lp->next;
+			list_del(&br->list);
+			kmem_free(br);
+			break;
+		case 0:
+			/*
+			 * Deleting from the middle: add the new right extent
+			 * and then shrink the left extent.
+			 */
+			new_br = kmem_alloc(sizeof(struct xfs_bitmap_range),
+					KM_MAYFAIL);
+			if (!new_br) {
+				error = -ENOMEM;
+				goto out;
+			}
+			INIT_LIST_HEAD(&new_br->list);
+			new_br->start = sub_start + sub_len;
+			new_br->len = br->start + br->len - new_br->start;
+			list_add(&new_br->list, &br->list);
+			br->len = sub_start - br->start;
+			lp = lp->next;
+			break;
+		default:
+			ASSERT(0);
+			break;
+		}
+	}
+
+out:
+	return error;
+}
+#undef LEFT_ALIGNED
+#undef RIGHT_ALIGNED
+
+/*
+ * Record all btree blocks seen while iterating all records of a btree.
+ *
+ * We know that the btree query_all function starts at the left edge and walks
+ * towards the right edge of the tree.  Therefore, we know that we can walk up
+ * the btree cursor towards the root; if the pointer for a given level points
+ * to the first record/key in that block, we haven't seen this block before;
+ * and therefore we need to remember that we saw this block in the btree.
+ *
+ * So if our btree is:
+ *
+ *    4
+ *  / | \
+ * 1  2  3
+ *
+ * Pretend for this example that each leaf block has 100 btree records.  For
+ * the first btree record, we'll observe that bc_ptrs[0] == 1, so we record
+ * that we saw block 1.  Then we observe that bc_ptrs[1] == 1, so we record
+ * block 4.  The list is [1, 4].
+ *
+ * For the second btree record, we see that bc_ptrs[0] == 2, so we exit the
+ * loop.  The list remains [1, 4].
+ *
+ * For the 101st btree record, we've moved onto leaf block 2.  Now
+ * bc_ptrs[0] == 1 again, so we record that we saw block 2.  We see that
+ * bc_ptrs[1] == 2, so we exit the loop.  The list is now [1, 4, 2].
+ *
+ * For the 102nd record, bc_ptrs[0] == 2, so we continue.
+ *
+ * For the 201st record, we've moved on to leaf block 3.  bc_ptrs[0] == 1, so
+ * we add 3 to the list.  Now it is [1, 4, 2, 3].
+ *
+ * For the 300th record we just exit, with the list being [1, 4, 2, 3].
+ */
+
+/*
+ * Record all the buffers pointed to by the btree cursor.  Callers already
+ * engaged in a btree walk should call this function to capture the list of
+ * blocks going from the leaf towards the root.
+ */
+int
+xfs_bitmap_set_btcur_path(
+	struct xfs_bitmap	*bitmap,
+	struct xfs_btree_cur	*cur)
+{
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsb;
+	int			i;
+	int			error;
+
+	for (i = 0; i < cur->bc_nlevels && cur->bc_ptrs[i] == 1; i++) {
+		xfs_btree_get_block(cur, i, &bp);
+		if (!bp)
+			continue;
+		fsb = XFS_DADDR_TO_FSB(cur->bc_mp, bp->b_bn);
+		error = xfs_bitmap_set(bitmap, fsb, 1);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Collect a btree's block in the bitmap. */
+STATIC int
+xfs_bitmap_collect_btblock(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	void			*priv)
+{
+	struct xfs_bitmap	*bitmap = priv;
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsbno;
+
+	xfs_btree_get_block(cur, level, &bp);
+	if (!bp)
+		return 0;
+
+	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, bp->b_bn);
+	return xfs_bitmap_set(bitmap, fsbno, 1);
+}
+
+/* Walk the btree and mark the bitmap wherever a btree block is found. */
+int
+xfs_bitmap_set_btblocks(
+	struct xfs_bitmap	*bitmap,
+	struct xfs_btree_cur	*cur)
+{
+	return xfs_btree_visit_blocks(cur, xfs_bitmap_collect_btblock, bitmap);
+}
diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h
new file mode 100644
index 000000000000..ae8ecbce6fa6
--- /dev/null
+++ b/fs/xfs/scrub/bitmap.h
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#ifndef __XFS_SCRUB_BITMAP_H__
+#define __XFS_SCRUB_BITMAP_H__
+
+struct xfs_bitmap_range {
+	struct list_head	list;
+	uint64_t		start;
+	uint64_t		len;
+};
+
+struct xfs_bitmap {
+	struct list_head	list;
+};
+
+void xfs_bitmap_init(struct xfs_bitmap *bitmap);
+void xfs_bitmap_destroy(struct xfs_bitmap *bitmap);
+
+#define for_each_xfs_bitmap_extent(bex, n, bitmap) \
+	list_for_each_entry_safe((bex), (n), &(bitmap)->list, list)
+
+#define for_each_xfs_bitmap_block(b, bex, n, bitmap) \
+	list_for_each_entry_safe((bex), (n), &(bitmap)->list, list) \
+		for ((b) = bex->start; (b) < bex->start + bex->len; (b)++)
+
+int xfs_bitmap_set(struct xfs_bitmap *bitmap, uint64_t start, uint64_t len);
+int xfs_bitmap_disunion(struct xfs_bitmap *bitmap, struct xfs_bitmap *sub);
+int xfs_bitmap_set_btcur_path(struct xfs_bitmap *bitmap,
+		struct xfs_btree_cur *cur);
+int xfs_bitmap_set_btblocks(struct xfs_bitmap *bitmap,
+		struct xfs_btree_cur *cur);
+
+#endif	/* __XFS_SCRUB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 3d08589f5c60..e1d11f3223e3 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -33,13 +33,13 @@
 
 /* Set us up with an inode's bmap. */
 int
-xfs_scrub_setup_inode_bmap(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_inode_bmap(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	int				error;
+	int			error;
 
-	error = xfs_scrub_get_inode(sc, ip);
+	error = xchk_get_inode(sc, ip);
 	if (error)
 		goto out;
 
@@ -60,7 +60,7 @@ xfs_scrub_setup_inode_bmap(
 	}
 
 	/* Got the inode, lock it and we're ready to go. */
-	error = xfs_scrub_trans_alloc(sc, 0);
+	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -78,27 +78,27 @@ out:
  * is in btree format.
  */
 
-struct xfs_scrub_bmap_info {
-	struct xfs_scrub_context	*sc;
-	xfs_fileoff_t			lastoff;
-	bool				is_rt;
-	bool				is_shared;
-	int				whichfork;
+struct xchk_bmap_info {
+	struct xfs_scrub	*sc;
+	xfs_fileoff_t		lastoff;
+	bool			is_rt;
+	bool			is_shared;
+	int			whichfork;
 };
 
 /* Look for a corresponding rmap for this irec. */
 static inline bool
-xfs_scrub_bmap_get_rmap(
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_bmbt_irec		*irec,
-	xfs_agblock_t			agbno,
-	uint64_t			owner,
-	struct xfs_rmap_irec		*rmap)
+xchk_bmap_get_rmap(
+	struct xchk_bmap_info	*info,
+	struct xfs_bmbt_irec	*irec,
+	xfs_agblock_t		agbno,
+	uint64_t		owner,
+	struct xfs_rmap_irec	*rmap)
 {
-	xfs_fileoff_t			offset;
-	unsigned int			rflags = 0;
-	int				has_rmap;
-	int				error;
+	xfs_fileoff_t		offset;
+	unsigned int		rflags = 0;
+	int			has_rmap;
+	int			error;
 
 	if (info->whichfork == XFS_ATTR_FORK)
 		rflags |= XFS_RMAP_ATTR_FORK;
@@ -120,7 +120,7 @@ xfs_scrub_bmap_get_rmap(
 	if (info->is_shared) {
 		error = xfs_rmap_lookup_le_range(info->sc->sa.rmap_cur, agbno,
 				owner, offset, rflags, rmap, &has_rmap);
-		if (!xfs_scrub_should_check_xref(info->sc, &error,
+		if (!xchk_should_check_xref(info->sc, &error,
 				&info->sc->sa.rmap_cur))
 			return false;
 		goto out;
@@ -131,36 +131,36 @@ xfs_scrub_bmap_get_rmap(
 	 */
 	error = xfs_rmap_lookup_le(info->sc->sa.rmap_cur, agbno, 0, owner,
 			offset, rflags, &has_rmap);
-	if (!xfs_scrub_should_check_xref(info->sc, &error,
+	if (!xchk_should_check_xref(info->sc, &error,
 			&info->sc->sa.rmap_cur))
 		return false;
 	if (!has_rmap)
 		goto out;
 
 	error = xfs_rmap_get_rec(info->sc->sa.rmap_cur, rmap, &has_rmap);
-	if (!xfs_scrub_should_check_xref(info->sc, &error,
+	if (!xchk_should_check_xref(info->sc, &error,
 			&info->sc->sa.rmap_cur))
 		return false;
 
 out:
 	if (!has_rmap)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 			irec->br_startoff);
 	return has_rmap;
 }
 
 /* Make sure that we have rmapbt records for this extent. */
 STATIC void
-xfs_scrub_bmap_xref_rmap(
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_bmbt_irec		*irec,
-	xfs_agblock_t			agbno)
+xchk_bmap_xref_rmap(
+	struct xchk_bmap_info	*info,
+	struct xfs_bmbt_irec	*irec,
+	xfs_agblock_t		agbno)
 {
-	struct xfs_rmap_irec		rmap;
-	unsigned long long		rmap_end;
-	uint64_t			owner;
+	struct xfs_rmap_irec	rmap;
+	unsigned long long	rmap_end;
+	uint64_t		owner;
 
-	if (!info->sc->sa.rmap_cur || xfs_scrub_skip_xref(info->sc->sm))
+	if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm))
 		return;
 
 	if (info->whichfork == XFS_COW_FORK)
@@ -169,14 +169,14 @@ xfs_scrub_bmap_xref_rmap(
 		owner = info->sc->ip->i_ino;
 
 	/* Find the rmap record for this irec. */
-	if (!xfs_scrub_bmap_get_rmap(info, irec, agbno, owner, &rmap))
+	if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap))
 		return;
 
 	/* Check the rmap. */
 	rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount;
 	if (rmap.rm_startblock > agbno ||
 	    agbno + irec->br_blockcount > rmap_end)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/*
@@ -189,12 +189,12 @@ xfs_scrub_bmap_xref_rmap(
 				rmap.rm_blockcount;
 		if (rmap.rm_offset > irec->br_startoff ||
 		    irec->br_startoff + irec->br_blockcount > rmap_end)
-			xfs_scrub_fblock_xref_set_corrupt(info->sc,
+			xchk_fblock_xref_set_corrupt(info->sc,
 					info->whichfork, irec->br_startoff);
 	}
 
 	if (rmap.rm_owner != owner)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/*
@@ -207,46 +207,46 @@ xfs_scrub_bmap_xref_rmap(
 	if (owner != XFS_RMAP_OWN_COW &&
 	    irec->br_state == XFS_EXT_UNWRITTEN &&
 	    !(rmap.rm_flags & XFS_RMAP_UNWRITTEN))
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	if (info->whichfork == XFS_ATTR_FORK &&
 	    !(rmap.rm_flags & XFS_RMAP_ATTR_FORK))
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 }
 
 /* Cross-reference a single rtdev extent record. */
 STATIC void
-xfs_scrub_bmap_rt_extent_xref(
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_inode		*ip,
-	struct xfs_btree_cur		*cur,
-	struct xfs_bmbt_irec		*irec)
+xchk_bmap_rt_extent_xref(
+	struct xchk_bmap_info	*info,
+	struct xfs_inode	*ip,
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*irec)
 {
 	if (info->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_rt_space(info->sc, irec->br_startblock,
+	xchk_xref_is_used_rt_space(info->sc, irec->br_startblock,
 			irec->br_blockcount);
 }
 
 /* Cross-reference a single datadev extent record. */
 STATIC void
-xfs_scrub_bmap_extent_xref(
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_inode		*ip,
-	struct xfs_btree_cur		*cur,
-	struct xfs_bmbt_irec		*irec)
+xchk_bmap_extent_xref(
+	struct xchk_bmap_info	*info,
+	struct xfs_inode	*ip,
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_mount		*mp = info->sc->mp;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_extlen_t			len;
-	int				error;
+	struct xfs_mount	*mp = info->sc->mp;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_extlen_t		len;
+	int			error;
 
 	if (info->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -255,44 +255,44 @@ xfs_scrub_bmap_extent_xref(
 	agbno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock);
 	len = irec->br_blockcount;
 
-	error = xfs_scrub_ag_init(info->sc, agno, &info->sc->sa);
-	if (!xfs_scrub_fblock_process_error(info->sc, info->whichfork,
+	error = xchk_ag_init(info->sc, agno, &info->sc->sa);
+	if (!xchk_fblock_process_error(info->sc, info->whichfork,
 			irec->br_startoff, &error))
 		return;
 
-	xfs_scrub_xref_is_used_space(info->sc, agbno, len);
-	xfs_scrub_xref_is_not_inode_chunk(info->sc, agbno, len);
-	xfs_scrub_bmap_xref_rmap(info, irec, agbno);
+	xchk_xref_is_used_space(info->sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(info->sc, agbno, len);
+	xchk_bmap_xref_rmap(info, irec, agbno);
 	switch (info->whichfork) {
 	case XFS_DATA_FORK:
 		if (xfs_is_reflink_inode(info->sc->ip))
 			break;
 		/* fall through */
 	case XFS_ATTR_FORK:
-		xfs_scrub_xref_is_not_shared(info->sc, agbno,
+		xchk_xref_is_not_shared(info->sc, agbno,
 				irec->br_blockcount);
 		break;
 	case XFS_COW_FORK:
-		xfs_scrub_xref_is_cow_staging(info->sc, agbno,
+		xchk_xref_is_cow_staging(info->sc, agbno,
 				irec->br_blockcount);
 		break;
 	}
 
-	xfs_scrub_ag_free(info->sc, &info->sc->sa);
+	xchk_ag_free(info->sc, &info->sc->sa);
 }
 
 /* Scrub a single extent record. */
 STATIC int
-xfs_scrub_bmap_extent(
-	struct xfs_inode		*ip,
-	struct xfs_btree_cur		*cur,
-	struct xfs_scrub_bmap_info	*info,
-	struct xfs_bmbt_irec		*irec)
+xchk_bmap_extent(
+	struct xfs_inode	*ip,
+	struct xfs_btree_cur	*cur,
+	struct xchk_bmap_info	*info,
+	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_mount		*mp = info->sc->mp;
-	struct xfs_buf			*bp = NULL;
-	xfs_filblks_t			end;
-	int				error = 0;
+	struct xfs_mount	*mp = info->sc->mp;
+	struct xfs_buf		*bp = NULL;
+	xfs_filblks_t		end;
+	int			error = 0;
 
 	if (cur)
 		xfs_btree_get_block(cur, 0, &bp);
@@ -302,12 +302,12 @@ xfs_scrub_bmap_extent(
 	 * from the incore list, for which there is no ordering check.
 	 */
 	if (irec->br_startoff < info->lastoff)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/* There should never be a "hole" extent in either extent list. */
 	if (irec->br_startblock == HOLESTARTBLOCK)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/*
@@ -315,40 +315,40 @@ xfs_scrub_bmap_extent(
 	 * in-core extent scan, and we should never see these in the bmbt.
 	 */
 	if (isnullstartblock(irec->br_startblock))
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/* Make sure the extent points to a valid place. */
 	if (irec->br_blockcount > MAXEXTLEN)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	if (irec->br_startblock + irec->br_blockcount <= irec->br_startblock)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	end = irec->br_startblock + irec->br_blockcount - 1;
 	if (info->is_rt &&
 	    (!xfs_verify_rtbno(mp, irec->br_startblock) ||
 	     !xfs_verify_rtbno(mp, end)))
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	if (!info->is_rt &&
 	    (!xfs_verify_fsbno(mp, irec->br_startblock) ||
 	     !xfs_verify_fsbno(mp, end) ||
 	     XFS_FSB_TO_AGNO(mp, irec->br_startblock) !=
 				XFS_FSB_TO_AGNO(mp, end)))
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/* We don't allow unwritten extents on attr forks. */
 	if (irec->br_state == XFS_EXT_UNWRITTEN &&
 	    info->whichfork == XFS_ATTR_FORK)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	if (info->is_rt)
-		xfs_scrub_bmap_rt_extent_xref(info, ip, cur, irec);
+		xchk_bmap_rt_extent_xref(info, ip, cur, irec);
 	else
-		xfs_scrub_bmap_extent_xref(info, ip, cur, irec);
+		xchk_bmap_extent_xref(info, ip, cur, irec);
 
 	info->lastoff = irec->br_startoff + irec->br_blockcount;
 	return error;
@@ -356,17 +356,17 @@ xfs_scrub_bmap_extent(
 
 /* Scrub a bmbt record. */
 STATIC int
-xfs_scrub_bmapbt_rec(
-	struct xfs_scrub_btree		*bs,
-	union xfs_btree_rec		*rec)
+xchk_bmapbt_rec(
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xfs_scrub_bmap_info	*info = bs->private;
-	struct xfs_inode		*ip = bs->cur->bc_private.b.ip;
-	struct xfs_buf			*bp = NULL;
-	struct xfs_btree_block		*block;
-	uint64_t			owner;
-	int				i;
+	struct xfs_bmbt_irec	irec;
+	struct xchk_bmap_info	*info = bs->private;
+	struct xfs_inode	*ip = bs->cur->bc_private.b.ip;
+	struct xfs_buf		*bp = NULL;
+	struct xfs_btree_block	*block;
+	uint64_t		owner;
+	int			i;
 
 	/*
 	 * Check the owners of the btree blocks up to the level below
@@ -378,54 +378,53 @@ xfs_scrub_bmapbt_rec(
 			block = xfs_btree_get_block(bs->cur, i, &bp);
 			owner = be64_to_cpu(block->bb_u.l.bb_owner);
 			if (owner != ip->i_ino)
-				xfs_scrub_fblock_set_corrupt(bs->sc,
+				xchk_fblock_set_corrupt(bs->sc,
 						info->whichfork, 0);
 		}
 	}
 
 	/* Set up the in-core record and scrub it. */
 	xfs_bmbt_disk_get_all(&rec->bmbt, &irec);
-	return xfs_scrub_bmap_extent(ip, bs->cur, info, &irec);
+	return xchk_bmap_extent(ip, bs->cur, info, &irec);
 }
 
 /* Scan the btree records. */
 STATIC int
-xfs_scrub_bmap_btree(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	struct xfs_scrub_bmap_info	*info)
+xchk_bmap_btree(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	struct xchk_bmap_info	*info)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip = sc->ip;
-	struct xfs_btree_cur		*cur;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_btree_cur	*cur;
+	int			error;
 
 	cur = xfs_bmbt_init_cursor(mp, sc->tp, ip, whichfork);
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	error = xfs_scrub_btree(sc, cur, xfs_scrub_bmapbt_rec, &oinfo, info);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR :
-					  XFS_BTREE_NOERROR);
+	error = xchk_btree(sc, cur, xchk_bmapbt_rec, &oinfo, info);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
-struct xfs_scrub_bmap_check_rmap_info {
-	struct xfs_scrub_context	*sc;
-	int				whichfork;
-	struct xfs_iext_cursor		icur;
+struct xchk_bmap_check_rmap_info {
+	struct xfs_scrub	*sc;
+	int			whichfork;
+	struct xfs_iext_cursor	icur;
 };
 
 /* Can we find bmaps that fit this rmap? */
 STATIC int
-xfs_scrub_bmap_check_rmap(
+xchk_bmap_check_rmap(
 	struct xfs_btree_cur		*cur,
 	struct xfs_rmap_irec		*rec,
 	void				*priv)
 {
 	struct xfs_bmbt_irec		irec;
-	struct xfs_scrub_bmap_check_rmap_info	*sbcri = priv;
+	struct xchk_bmap_check_rmap_info	*sbcri = priv;
 	struct xfs_ifork		*ifp;
-	struct xfs_scrub_context	*sc = sbcri->sc;
+	struct xfs_scrub		*sc = sbcri->sc;
 	bool				have_map;
 
 	/* Is this even the right fork? */
@@ -440,14 +439,14 @@ xfs_scrub_bmap_check_rmap(
 	/* Now look up the bmbt record. */
 	ifp = XFS_IFORK_PTR(sc->ip, sbcri->whichfork);
 	if (!ifp) {
-		xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+		xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 				rec->rm_offset);
 		goto out;
 	}
 	have_map = xfs_iext_lookup_extent(sc->ip, ifp, rec->rm_offset,
 			&sbcri->icur, &irec);
 	if (!have_map)
-		xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+		xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 				rec->rm_offset);
 	/*
 	 * bmap extent record lengths are constrained to 2^21 blocks in length
@@ -458,14 +457,14 @@ xfs_scrub_bmap_check_rmap(
 	 */
 	while (have_map) {
 		if (irec.br_startoff != rec->rm_offset)
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 		if (irec.br_startblock != XFS_AGB_TO_FSB(sc->mp,
 				cur->bc_private.a.agno, rec->rm_startblock))
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 		if (irec.br_blockcount > rec->rm_blockcount)
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			break;
@@ -476,7 +475,7 @@ xfs_scrub_bmap_check_rmap(
 			break;
 		have_map = xfs_iext_next_extent(ifp, &sbcri->icur, &irec);
 		if (!have_map)
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 	}
 
@@ -488,12 +487,12 @@ out:
 
 /* Make sure each rmap has a corresponding bmbt entry. */
 STATIC int
-xfs_scrub_bmap_check_ag_rmaps(
-	struct xfs_scrub_context	*sc,
+xchk_bmap_check_ag_rmaps(
+	struct xfs_scrub		*sc,
 	int				whichfork,
 	xfs_agnumber_t			agno)
 {
-	struct xfs_scrub_bmap_check_rmap_info	sbcri;
+	struct xchk_bmap_check_rmap_info	sbcri;
 	struct xfs_btree_cur		*cur;
 	struct xfs_buf			*agf;
 	int				error;
@@ -510,11 +509,11 @@ xfs_scrub_bmap_check_ag_rmaps(
 
 	sbcri.sc = sc;
 	sbcri.whichfork = whichfork;
-	error = xfs_rmap_query_all(cur, xfs_scrub_bmap_check_rmap, &sbcri);
+	error = xfs_rmap_query_all(cur, xchk_bmap_check_rmap, &sbcri);
 	if (error == XFS_BTREE_QUERY_RANGE_ABORT)
 		error = 0;
 
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 out_agf:
 	xfs_trans_brelse(sc->tp, agf);
 	return error;
@@ -522,13 +521,13 @@ out_agf:
 
 /* Make sure each rmap has a corresponding bmbt entry. */
 STATIC int
-xfs_scrub_bmap_check_rmaps(
-	struct xfs_scrub_context	*sc,
-	int				whichfork)
+xchk_bmap_check_rmaps(
+	struct xfs_scrub	*sc,
+	int			whichfork)
 {
-	loff_t				size;
-	xfs_agnumber_t			agno;
-	int				error;
+	loff_t			size;
+	xfs_agnumber_t		agno;
+	int			error;
 
 	if (!xfs_sb_version_hasrmapbt(&sc->mp->m_sb) ||
 	    whichfork == XFS_COW_FORK ||
@@ -562,7 +561,7 @@ xfs_scrub_bmap_check_rmaps(
 		return 0;
 
 	for (agno = 0; agno < sc->mp->m_sb.sb_agcount; agno++) {
-		error = xfs_scrub_bmap_check_ag_rmaps(sc, whichfork, agno);
+		error = xchk_bmap_check_ag_rmaps(sc, whichfork, agno);
 		if (error)
 			return error;
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -579,18 +578,18 @@ xfs_scrub_bmap_check_rmaps(
  * Then we unconditionally scan the incore extent cache.
  */
 STATIC int
-xfs_scrub_bmap(
-	struct xfs_scrub_context	*sc,
-	int				whichfork)
+xchk_bmap(
+	struct xfs_scrub	*sc,
+	int			whichfork)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xfs_scrub_bmap_info	info = { NULL };
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip = sc->ip;
-	struct xfs_ifork		*ifp;
-	xfs_fileoff_t			endoff;
-	struct xfs_iext_cursor		icur;
-	int				error = 0;
+	struct xfs_bmbt_irec	irec;
+	struct xchk_bmap_info	info = { NULL };
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_ifork	*ifp;
+	xfs_fileoff_t		endoff;
+	struct xfs_iext_cursor	icur;
+	int			error = 0;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 
@@ -606,7 +605,7 @@ xfs_scrub_bmap(
 			goto out;
 		/* No CoW forks on non-reflink inodes/filesystems. */
 		if (!xfs_is_reflink_inode(ip)) {
-			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 			goto out;
 		}
 		break;
@@ -615,7 +614,7 @@ xfs_scrub_bmap(
 			goto out_check_rmap;
 		if (!xfs_sb_version_hasattr(&mp->m_sb) &&
 		    !xfs_sb_version_hasattr2(&mp->m_sb))
-			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		break;
 	default:
 		ASSERT(whichfork == XFS_DATA_FORK);
@@ -631,22 +630,22 @@ xfs_scrub_bmap(
 		goto out;
 	case XFS_DINODE_FMT_EXTENTS:
 		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-			xfs_scrub_fblock_set_corrupt(sc, whichfork, 0);
+			xchk_fblock_set_corrupt(sc, whichfork, 0);
 			goto out;
 		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (whichfork == XFS_COW_FORK) {
-			xfs_scrub_fblock_set_corrupt(sc, whichfork, 0);
+			xchk_fblock_set_corrupt(sc, whichfork, 0);
 			goto out;
 		}
 
-		error = xfs_scrub_bmap_btree(sc, whichfork, &info);
+		error = xchk_bmap_btree(sc, whichfork, &info);
 		if (error)
 			goto out;
 		break;
 	default:
-		xfs_scrub_fblock_set_corrupt(sc, whichfork, 0);
+		xchk_fblock_set_corrupt(sc, whichfork, 0);
 		goto out;
 	}
 
@@ -656,37 +655,37 @@ xfs_scrub_bmap(
 	/* Now try to scrub the in-memory extent list. */
         if (!(ifp->if_flags & XFS_IFEXTENTS)) {
 		error = xfs_iread_extents(sc->tp, ip, whichfork);
-		if (!xfs_scrub_fblock_process_error(sc, whichfork, 0, &error))
+		if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
 			goto out;
 	}
 
 	/* Find the offset of the last extent in the mapping. */
 	error = xfs_bmap_last_offset(ip, &endoff, whichfork);
-	if (!xfs_scrub_fblock_process_error(sc, whichfork, 0, &error))
+	if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
 		goto out;
 
 	/* Scrub extent records. */
 	info.lastoff = 0;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	for_each_xfs_iext(ifp, &icur, &irec) {
-		if (xfs_scrub_should_terminate(sc, &error) ||
+		if (xchk_should_terminate(sc, &error) ||
 		    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 			break;
 		if (isnullstartblock(irec.br_startblock))
 			continue;
 		if (irec.br_startoff >= endoff) {
-			xfs_scrub_fblock_set_corrupt(sc, whichfork,
+			xchk_fblock_set_corrupt(sc, whichfork,
 					irec.br_startoff);
 			goto out;
 		}
-		error = xfs_scrub_bmap_extent(ip, NULL, &info, &irec);
+		error = xchk_bmap_extent(ip, NULL, &info, &irec);
 		if (error)
 			goto out;
 	}
 
 out_check_rmap:
-	error = xfs_scrub_bmap_check_rmaps(sc, whichfork);
-	if (!xfs_scrub_fblock_xref_process_error(sc, whichfork, 0, &error))
+	error = xchk_bmap_check_rmaps(sc, whichfork);
+	if (!xchk_fblock_xref_process_error(sc, whichfork, 0, &error))
 		goto out;
 out:
 	return error;
@@ -694,27 +693,27 @@ out:
 
 /* Scrub an inode's data fork. */
 int
-xfs_scrub_bmap_data(
-	struct xfs_scrub_context	*sc)
+xchk_bmap_data(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_bmap(sc, XFS_DATA_FORK);
+	return xchk_bmap(sc, XFS_DATA_FORK);
 }
 
 /* Scrub an inode's attr fork. */
 int
-xfs_scrub_bmap_attr(
-	struct xfs_scrub_context	*sc)
+xchk_bmap_attr(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_bmap(sc, XFS_ATTR_FORK);
+	return xchk_bmap(sc, XFS_ATTR_FORK);
 }
 
 /* Scrub an inode's CoW fork. */
 int
-xfs_scrub_bmap_cow(
-	struct xfs_scrub_context	*sc)
+xchk_bmap_cow(
+	struct xfs_scrub	*sc)
 {
 	if (!xfs_is_reflink_inode(sc->ip))
 		return -ENOENT;
 
-	return xfs_scrub_bmap(sc, XFS_COW_FORK);
+	return xchk_bmap(sc, XFS_COW_FORK);
 }
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 5b472045f036..4ae959f7ad2c 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -29,13 +29,13 @@
  * operational errors in common.c.
  */
 static bool
-__xfs_scrub_btree_process_error(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	int				*error,
-	__u32				errflag,
-	void				*ret_ip)
+__xchk_btree_process_error(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*error,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	if (*error == 0)
 		return true;
@@ -43,7 +43,7 @@ __xfs_scrub_btree_process_error(
 	switch (*error) {
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -53,10 +53,10 @@ __xfs_scrub_btree_process_error(
 		/* fall through */
 	default:
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
-			trace_xfs_scrub_ifork_btree_op_error(sc, cur, level,
+			trace_xchk_ifork_btree_op_error(sc, cur, level,
 					*error, ret_ip);
 		else
-			trace_xfs_scrub_btree_op_error(sc, cur, level,
+			trace_xchk_btree_op_error(sc, cur, level,
 					*error, ret_ip);
 		break;
 	}
@@ -64,63 +64,63 @@ __xfs_scrub_btree_process_error(
 }
 
 bool
-xfs_scrub_btree_process_error(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	int				*error)
+xchk_btree_process_error(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*error)
 {
-	return __xfs_scrub_btree_process_error(sc, cur, level, error,
+	return __xchk_btree_process_error(sc, cur, level, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
 bool
-xfs_scrub_btree_xref_process_error(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	int				*error)
+xchk_btree_xref_process_error(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*error)
 {
-	return __xfs_scrub_btree_process_error(sc, cur, level, error,
+	return __xchk_btree_process_error(sc, cur, level, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
 }
 
 /* Record btree block corruption. */
 static void
-__xfs_scrub_btree_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	__u32				errflag,
-	void				*ret_ip)
+__xchk_btree_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	sc->sm->sm_flags |= errflag;
 
 	if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
-		trace_xfs_scrub_ifork_btree_error(sc, cur, level,
+		trace_xchk_ifork_btree_error(sc, cur, level,
 				ret_ip);
 	else
-		trace_xfs_scrub_btree_error(sc, cur, level,
+		trace_xchk_btree_error(sc, cur, level,
 				ret_ip);
 }
 
 void
-xfs_scrub_btree_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level)
+xchk_btree_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
-	__xfs_scrub_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_CORRUPT,
+	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_CORRUPT,
 			__return_address);
 }
 
 void
-xfs_scrub_btree_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level)
+xchk_btree_xref_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
-	__xfs_scrub_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_XCORRUPT,
+	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_XCORRUPT,
 			__return_address);
 }
 
@@ -129,8 +129,8 @@ xfs_scrub_btree_xref_set_corrupt(
  * keys.
  */
 STATIC void
-xfs_scrub_btree_rec(
-	struct xfs_scrub_btree	*bs)
+xchk_btree_rec(
+	struct xchk_btree	*bs)
 {
 	struct xfs_btree_cur	*cur = bs->cur;
 	union xfs_btree_rec	*rec;
@@ -144,11 +144,11 @@ xfs_scrub_btree_rec(
 	block = xfs_btree_get_block(cur, 0, &bp);
 	rec = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
 
-	trace_xfs_scrub_btree_rec(bs->sc, cur, 0);
+	trace_xchk_btree_rec(bs->sc, cur, 0);
 
 	/* If this isn't the first record, are they in order? */
 	if (!bs->firstrec && !cur->bc_ops->recs_inorder(cur, &bs->lastrec, rec))
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 0);
+		xchk_btree_set_corrupt(bs->sc, cur, 0);
 	bs->firstrec = false;
 	memcpy(&bs->lastrec, rec, cur->bc_ops->rec_len);
 
@@ -160,7 +160,7 @@ xfs_scrub_btree_rec(
 	keyblock = xfs_btree_get_block(cur, 1, &bp);
 	keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, &key, keyp) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 
 	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 		return;
@@ -169,7 +169,7 @@ xfs_scrub_btree_rec(
 	cur->bc_ops->init_high_key_from_rec(&hkey, rec);
 	keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, keyp, &hkey) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 }
 
 /*
@@ -177,8 +177,8 @@ xfs_scrub_btree_rec(
  * keys.
  */
 STATIC void
-xfs_scrub_btree_key(
-	struct xfs_scrub_btree	*bs,
+xchk_btree_key(
+	struct xchk_btree	*bs,
 	int			level)
 {
 	struct xfs_btree_cur	*cur = bs->cur;
@@ -191,12 +191,12 @@ xfs_scrub_btree_key(
 	block = xfs_btree_get_block(cur, level, &bp);
 	key = xfs_btree_key_addr(cur, cur->bc_ptrs[level], block);
 
-	trace_xfs_scrub_btree_key(bs->sc, cur, level);
+	trace_xchk_btree_key(bs->sc, cur, level);
 
 	/* If this isn't the first key, are they in order? */
 	if (!bs->firstkey[level] &&
 	    !cur->bc_ops->keys_inorder(cur, &bs->lastkey[level], key))
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 	bs->firstkey[level] = false;
 	memcpy(&bs->lastkey[level], key, cur->bc_ops->key_len);
 
@@ -207,7 +207,7 @@ xfs_scrub_btree_key(
 	keyblock = xfs_btree_get_block(cur, level + 1, &bp);
 	keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, key, keyp) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 
 	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 		return;
@@ -216,7 +216,7 @@ xfs_scrub_btree_key(
 	key = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level], block);
 	keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, keyp, key) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 }
 
 /*
@@ -224,12 +224,12 @@ xfs_scrub_btree_key(
  * Callers do not need to set the corrupt flag.
  */
 static bool
-xfs_scrub_btree_ptr_ok(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	union xfs_btree_ptr		*ptr)
+xchk_btree_ptr_ok(
+	struct xchk_btree	*bs,
+	int			level,
+	union xfs_btree_ptr	*ptr)
 {
-	bool				res;
+	bool			res;
 
 	/* A btree rooted in an inode has no block pointer to the root. */
 	if ((bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
@@ -242,29 +242,29 @@ xfs_scrub_btree_ptr_ok(
 	else
 		res = xfs_btree_check_sptr(bs->cur, be32_to_cpu(ptr->s), level);
 	if (!res)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 
 	return res;
 }
 
 /* Check that a btree block's sibling matches what we expect it. */
 STATIC int
-xfs_scrub_btree_block_check_sibling(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	int				direction,
-	union xfs_btree_ptr		*sibling)
+xchk_btree_block_check_sibling(
+	struct xchk_btree	*bs,
+	int			level,
+	int			direction,
+	union xfs_btree_ptr	*sibling)
 {
-	struct xfs_btree_cur		*cur = bs->cur;
-	struct xfs_btree_block		*pblock;
-	struct xfs_buf			*pbp;
-	struct xfs_btree_cur		*ncur = NULL;
-	union xfs_btree_ptr		*pp;
-	int				success;
-	int				error;
+	struct xfs_btree_cur	*cur = bs->cur;
+	struct xfs_btree_block	*pblock;
+	struct xfs_buf		*pbp;
+	struct xfs_btree_cur	*ncur = NULL;
+	union xfs_btree_ptr	*pp;
+	int			success;
+	int			error;
 
 	error = xfs_btree_dup_cursor(cur, &ncur);
-	if (!xfs_scrub_btree_process_error(bs->sc, cur, level + 1, &error) ||
+	if (!xchk_btree_process_error(bs->sc, cur, level + 1, &error) ||
 	    !ncur)
 		return error;
 
@@ -278,7 +278,7 @@ xfs_scrub_btree_block_check_sibling(
 		else
 			error = xfs_btree_decrement(ncur, level + 1, &success);
 		if (error == 0 && success)
-			xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+			xchk_btree_set_corrupt(bs->sc, cur, level);
 		error = 0;
 		goto out;
 	}
@@ -288,23 +288,23 @@ xfs_scrub_btree_block_check_sibling(
 		error = xfs_btree_increment(ncur, level + 1, &success);
 	else
 		error = xfs_btree_decrement(ncur, level + 1, &success);
-	if (!xfs_scrub_btree_process_error(bs->sc, cur, level + 1, &error))
+	if (!xchk_btree_process_error(bs->sc, cur, level + 1, &error))
 		goto out;
 	if (!success) {
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level + 1);
+		xchk_btree_set_corrupt(bs->sc, cur, level + 1);
 		goto out;
 	}
 
 	/* Compare upper level pointer to sibling pointer. */
 	pblock = xfs_btree_get_block(ncur, level + 1, &pbp);
 	pp = xfs_btree_ptr_addr(ncur, ncur->bc_ptrs[level + 1], pblock);
-	if (!xfs_scrub_btree_ptr_ok(bs, level + 1, pp))
+	if (!xchk_btree_ptr_ok(bs, level + 1, pp))
 		goto out;
 	if (pbp)
-		xfs_scrub_buffer_recheck(bs->sc, pbp);
+		xchk_buffer_recheck(bs->sc, pbp);
 
 	if (xfs_btree_diff_two_ptrs(cur, pp, sibling))
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 out:
 	xfs_btree_del_cursor(ncur, XFS_BTREE_ERROR);
 	return error;
@@ -312,15 +312,15 @@ out:
 
 /* Check the siblings of a btree block. */
 STATIC int
-xfs_scrub_btree_block_check_siblings(
-	struct xfs_scrub_btree		*bs,
-	struct xfs_btree_block		*block)
+xchk_btree_block_check_siblings(
+	struct xchk_btree	*bs,
+	struct xfs_btree_block	*block)
 {
-	struct xfs_btree_cur		*cur = bs->cur;
-	union xfs_btree_ptr		leftsib;
-	union xfs_btree_ptr		rightsib;
-	int				level;
-	int				error = 0;
+	struct xfs_btree_cur	*cur = bs->cur;
+	union xfs_btree_ptr	leftsib;
+	union xfs_btree_ptr	rightsib;
+	int			level;
+	int			error = 0;
 
 	xfs_btree_get_sibling(cur, block, &leftsib, XFS_BB_LEFTSIB);
 	xfs_btree_get_sibling(cur, block, &rightsib, XFS_BB_RIGHTSIB);
@@ -330,7 +330,7 @@ xfs_scrub_btree_block_check_siblings(
 	if (level == cur->bc_nlevels - 1) {
 		if (!xfs_btree_ptr_is_null(cur, &leftsib) ||
 		    !xfs_btree_ptr_is_null(cur, &rightsib))
-			xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+			xchk_btree_set_corrupt(bs->sc, cur, level);
 		goto out;
 	}
 
@@ -339,10 +339,10 @@ xfs_scrub_btree_block_check_siblings(
 	 * parent level pointers?
 	 * (These function absorbs error codes for us.)
 	 */
-	error = xfs_scrub_btree_block_check_sibling(bs, level, -1, &leftsib);
+	error = xchk_btree_block_check_sibling(bs, level, -1, &leftsib);
 	if (error)
 		return error;
-	error = xfs_scrub_btree_block_check_sibling(bs, level, 1, &rightsib);
+	error = xchk_btree_block_check_sibling(bs, level, 1, &rightsib);
 	if (error)
 		return error;
 out:
@@ -360,16 +360,16 @@ struct check_owner {
  * an rmap record for it.
  */
 STATIC int
-xfs_scrub_btree_check_block_owner(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	xfs_daddr_t			daddr)
+xchk_btree_check_block_owner(
+	struct xchk_btree	*bs,
+	int			level,
+	xfs_daddr_t		daddr)
 {
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_btnum_t			btnum;
-	bool				init_sa;
-	int				error = 0;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_btnum_t		btnum;
+	bool			init_sa;
+	int			error = 0;
 
 	if (!bs->cur)
 		return 0;
@@ -380,13 +380,13 @@ xfs_scrub_btree_check_block_owner(
 
 	init_sa = bs->cur->bc_flags & XFS_BTREE_LONG_PTRS;
 	if (init_sa) {
-		error = xfs_scrub_ag_init(bs->sc, agno, &bs->sc->sa);
-		if (!xfs_scrub_btree_xref_process_error(bs->sc, bs->cur,
+		error = xchk_ag_init(bs->sc, agno, &bs->sc->sa);
+		if (!xchk_btree_xref_process_error(bs->sc, bs->cur,
 				level, &error))
 			return error;
 	}
 
-	xfs_scrub_xref_is_used_space(bs->sc, agbno, 1);
+	xchk_xref_is_used_space(bs->sc, agbno, 1);
 	/*
 	 * The bnobt scrubber aliases bs->cur to bs->sc->sa.bno_cur, so we
 	 * have to nullify it (to shut down further block owner checks) if
@@ -395,25 +395,25 @@ xfs_scrub_btree_check_block_owner(
 	if (!bs->sc->sa.bno_cur && btnum == XFS_BTNUM_BNO)
 		bs->cur = NULL;
 
-	xfs_scrub_xref_is_owned_by(bs->sc, agbno, 1, bs->oinfo);
+	xchk_xref_is_owned_by(bs->sc, agbno, 1, bs->oinfo);
 	if (!bs->sc->sa.rmap_cur && btnum == XFS_BTNUM_RMAP)
 		bs->cur = NULL;
 
 	if (init_sa)
-		xfs_scrub_ag_free(bs->sc, &bs->sc->sa);
+		xchk_ag_free(bs->sc, &bs->sc->sa);
 
 	return error;
 }
 
 /* Check the owner of a btree block. */
 STATIC int
-xfs_scrub_btree_check_owner(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	struct xfs_buf			*bp)
+xchk_btree_check_owner(
+	struct xchk_btree	*bs,
+	int			level,
+	struct xfs_buf		*bp)
 {
-	struct xfs_btree_cur		*cur = bs->cur;
-	struct check_owner		*co;
+	struct xfs_btree_cur	*cur = bs->cur;
+	struct check_owner	*co;
 
 	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && bp == NULL)
 		return 0;
@@ -437,7 +437,7 @@ xfs_scrub_btree_check_owner(
 		return 0;
 	}
 
-	return xfs_scrub_btree_check_block_owner(bs, level, XFS_BUF_ADDR(bp));
+	return xchk_btree_check_block_owner(bs, level, XFS_BUF_ADDR(bp));
 }
 
 /*
@@ -445,8 +445,8 @@ xfs_scrub_btree_check_owner(
  * special blocks that don't require that.
  */
 STATIC void
-xfs_scrub_btree_check_minrecs(
-	struct xfs_scrub_btree	*bs,
+xchk_btree_check_minrecs(
+	struct xchk_btree	*bs,
 	int			level,
 	struct xfs_btree_block	*block)
 {
@@ -475,7 +475,7 @@ xfs_scrub_btree_check_minrecs(
 	if (level >= ok_level)
 		return;
 
-	xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+	xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 }
 
 /*
@@ -483,21 +483,21 @@ xfs_scrub_btree_check_minrecs(
  * and buffer pointers (if applicable) if they're ok to use.
  */
 STATIC int
-xfs_scrub_btree_get_block(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	union xfs_btree_ptr		*pp,
-	struct xfs_btree_block		**pblock,
-	struct xfs_buf			**pbp)
+xchk_btree_get_block(
+	struct xchk_btree	*bs,
+	int			level,
+	union xfs_btree_ptr	*pp,
+	struct xfs_btree_block	**pblock,
+	struct xfs_buf		**pbp)
 {
-	void				*failed_at;
-	int				error;
+	xfs_failaddr_t		failed_at;
+	int			error;
 
 	*pblock = NULL;
 	*pbp = NULL;
 
 	error = xfs_btree_lookup_get_block(bs->cur, level, pp, pblock);
-	if (!xfs_scrub_btree_process_error(bs->sc, bs->cur, level, &error) ||
+	if (!xchk_btree_process_error(bs->sc, bs->cur, level, &error) ||
 	    !*pblock)
 		return error;
 
@@ -509,19 +509,19 @@ xfs_scrub_btree_get_block(
 		failed_at = __xfs_btree_check_sblock(bs->cur, *pblock,
 				 level, *pbp);
 	if (failed_at) {
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 		return 0;
 	}
 	if (*pbp)
-		xfs_scrub_buffer_recheck(bs->sc, *pbp);
+		xchk_buffer_recheck(bs->sc, *pbp);
 
-	xfs_scrub_btree_check_minrecs(bs, level, *pblock);
+	xchk_btree_check_minrecs(bs, level, *pblock);
 
 	/*
 	 * Check the block's owner; this function absorbs error codes
 	 * for us.
 	 */
-	error = xfs_scrub_btree_check_owner(bs, level, *pbp);
+	error = xchk_btree_check_owner(bs, level, *pbp);
 	if (error)
 		return error;
 
@@ -529,7 +529,7 @@ xfs_scrub_btree_get_block(
 	 * Check the block's siblings; this function absorbs error codes
 	 * for us.
 	 */
-	return xfs_scrub_btree_block_check_siblings(bs, *pblock);
+	return xchk_btree_block_check_siblings(bs, *pblock);
 }
 
 /*
@@ -537,18 +537,18 @@ xfs_scrub_btree_get_block(
  * in the parent block.
  */
 STATIC void
-xfs_scrub_btree_block_keys(
-	struct xfs_scrub_btree		*bs,
-	int				level,
-	struct xfs_btree_block		*block)
+xchk_btree_block_keys(
+	struct xchk_btree	*bs,
+	int			level,
+	struct xfs_btree_block	*block)
 {
-	union xfs_btree_key		block_keys;
-	struct xfs_btree_cur		*cur = bs->cur;
-	union xfs_btree_key		*high_bk;
-	union xfs_btree_key		*parent_keys;
-	union xfs_btree_key		*high_pk;
-	struct xfs_btree_block		*parent_block;
-	struct xfs_buf			*bp;
+	union xfs_btree_key	block_keys;
+	struct xfs_btree_cur	*cur = bs->cur;
+	union xfs_btree_key	*high_bk;
+	union xfs_btree_key	*parent_keys;
+	union xfs_btree_key	*high_pk;
+	struct xfs_btree_block	*parent_block;
+	struct xfs_buf		*bp;
 
 	if (level >= cur->bc_nlevels - 1)
 		return;
@@ -562,7 +562,7 @@ xfs_scrub_btree_block_keys(
 			parent_block);
 
 	if (cur->bc_ops->diff_two_keys(cur, &block_keys, parent_keys) != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 
 	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 		return;
@@ -573,7 +573,7 @@ xfs_scrub_btree_block_keys(
 			parent_block);
 
 	if (cur->bc_ops->diff_two_keys(cur, high_bk, high_pk) != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 }
 
 /*
@@ -582,24 +582,24 @@ xfs_scrub_btree_block_keys(
  * so that the caller can verify individual records.
  */
 int
-xfs_scrub_btree(
-	struct xfs_scrub_context	*sc,
-	struct xfs_btree_cur		*cur,
-	xfs_scrub_btree_rec_fn		scrub_fn,
-	struct xfs_owner_info		*oinfo,
-	void				*private)
+xchk_btree(
+	struct xfs_scrub	*sc,
+	struct xfs_btree_cur	*cur,
+	xchk_btree_rec_fn	scrub_fn,
+	struct xfs_owner_info	*oinfo,
+	void			*private)
 {
-	struct xfs_scrub_btree		bs = { NULL };
-	union xfs_btree_ptr		ptr;
-	union xfs_btree_ptr		*pp;
-	union xfs_btree_rec		*recp;
-	struct xfs_btree_block		*block;
-	int				level;
-	struct xfs_buf			*bp;
-	struct check_owner		*co;
-	struct check_owner		*n;
-	int				i;
-	int				error = 0;
+	struct xchk_btree	bs = { NULL };
+	union xfs_btree_ptr	ptr;
+	union xfs_btree_ptr	*pp;
+	union xfs_btree_rec	*recp;
+	struct xfs_btree_block	*block;
+	int			level;
+	struct xfs_buf		*bp;
+	struct check_owner	*co;
+	struct check_owner	*n;
+	int			i;
+	int			error = 0;
 
 	/* Initialize scrub state */
 	bs.cur = cur;
@@ -614,7 +614,7 @@ xfs_scrub_btree(
 
 	/* Don't try to check a tree with a height we can't handle. */
 	if (cur->bc_nlevels > XFS_BTREE_MAXLEVELS) {
-		xfs_scrub_btree_set_corrupt(sc, cur, 0);
+		xchk_btree_set_corrupt(sc, cur, 0);
 		goto out;
 	}
 
@@ -624,9 +624,9 @@ xfs_scrub_btree(
 	 */
 	level = cur->bc_nlevels - 1;
 	cur->bc_ops->init_ptr_from_cur(cur, &ptr);
-	if (!xfs_scrub_btree_ptr_ok(&bs, cur->bc_nlevels, &ptr))
+	if (!xchk_btree_ptr_ok(&bs, cur->bc_nlevels, &ptr))
 		goto out;
-	error = xfs_scrub_btree_get_block(&bs, level, &ptr, &block, &bp);
+	error = xchk_btree_get_block(&bs, level, &ptr, &block, &bp);
 	if (error || !block)
 		goto out;
 
@@ -639,7 +639,7 @@ xfs_scrub_btree(
 			/* End of leaf, pop back towards the root. */
 			if (cur->bc_ptrs[level] >
 			    be16_to_cpu(block->bb_numrecs)) {
-				xfs_scrub_btree_block_keys(&bs, level, block);
+				xchk_btree_block_keys(&bs, level, block);
 				if (level < cur->bc_nlevels - 1)
 					cur->bc_ptrs[level + 1]++;
 				level++;
@@ -647,14 +647,14 @@ xfs_scrub_btree(
 			}
 
 			/* Records in order for scrub? */
-			xfs_scrub_btree_rec(&bs);
+			xchk_btree_rec(&bs);
 
 			/* Call out to the record checker. */
 			recp = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
 			error = bs.scrub_rec(&bs, recp);
 			if (error)
 				break;
-			if (xfs_scrub_should_terminate(sc, &error) ||
+			if (xchk_should_terminate(sc, &error) ||
 			    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 				break;
 
@@ -664,7 +664,7 @@ xfs_scrub_btree(
 
 		/* End of node, pop back towards the root. */
 		if (cur->bc_ptrs[level] > be16_to_cpu(block->bb_numrecs)) {
-			xfs_scrub_btree_block_keys(&bs, level, block);
+			xchk_btree_block_keys(&bs, level, block);
 			if (level < cur->bc_nlevels - 1)
 				cur->bc_ptrs[level + 1]++;
 			level++;
@@ -672,16 +672,16 @@ xfs_scrub_btree(
 		}
 
 		/* Keys in order for scrub? */
-		xfs_scrub_btree_key(&bs, level);
+		xchk_btree_key(&bs, level);
 
 		/* Drill another level deeper. */
 		pp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[level], block);
-		if (!xfs_scrub_btree_ptr_ok(&bs, level, pp)) {
+		if (!xchk_btree_ptr_ok(&bs, level, pp)) {
 			cur->bc_ptrs[level]++;
 			continue;
 		}
 		level--;
-		error = xfs_scrub_btree_get_block(&bs, level, pp, &block, &bp);
+		error = xchk_btree_get_block(&bs, level, pp, &block, &bp);
 		if (error || !block)
 			goto out;
 
@@ -692,7 +692,7 @@ out:
 	/* Process deferred owner checks on btree blocks. */
 	list_for_each_entry_safe(co, n, &bs.to_check, list) {
 		if (!error && bs.cur)
-			error = xfs_scrub_btree_check_block_owner(&bs,
+			error = xchk_btree_check_block_owner(&bs,
 					co->level, co->daddr);
 		list_del(&co->list);
 		kmem_free(co);
diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h
index 956627500f2c..aada763cd006 100644
--- a/fs/xfs/scrub/btree.h
+++ b/fs/xfs/scrub/btree.h
@@ -9,44 +9,43 @@
 /* btree scrub */
 
 /* Check for btree operation errors. */
-bool xfs_scrub_btree_process_error(struct xfs_scrub_context *sc,
+bool xchk_btree_process_error(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level, int *error);
 
 /* Check for btree xref operation errors. */
-bool xfs_scrub_btree_xref_process_error(struct xfs_scrub_context *sc,
-				struct xfs_btree_cur *cur, int level,
-				int *error);
+bool xchk_btree_xref_process_error(struct xfs_scrub *sc,
+		struct xfs_btree_cur *cur, int level, int *error);
 
 /* Check for btree corruption. */
-void xfs_scrub_btree_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_btree_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level);
 
 /* Check for btree xref discrepancies. */
-void xfs_scrub_btree_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_btree_xref_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level);
 
-struct xfs_scrub_btree;
-typedef int (*xfs_scrub_btree_rec_fn)(
-	struct xfs_scrub_btree	*bs,
+struct xchk_btree;
+typedef int (*xchk_btree_rec_fn)(
+	struct xchk_btree	*bs,
 	union xfs_btree_rec	*rec);
 
-struct xfs_scrub_btree {
+struct xchk_btree {
 	/* caller-provided scrub state */
-	struct xfs_scrub_context	*sc;
-	struct xfs_btree_cur		*cur;
-	xfs_scrub_btree_rec_fn		scrub_rec;
-	struct xfs_owner_info		*oinfo;
-	void				*private;
+	struct xfs_scrub	*sc;
+	struct xfs_btree_cur	*cur;
+	xchk_btree_rec_fn	scrub_rec;
+	struct xfs_owner_info	*oinfo;
+	void			*private;
 
 	/* internal scrub state */
-	union xfs_btree_rec		lastrec;
-	bool				firstrec;
-	union xfs_btree_key		lastkey[XFS_BTREE_MAXLEVELS];
-	bool				firstkey[XFS_BTREE_MAXLEVELS];
-	struct list_head		to_check;
+	union xfs_btree_rec	lastrec;
+	bool			firstrec;
+	union xfs_btree_key	lastkey[XFS_BTREE_MAXLEVELS];
+	bool			firstkey[XFS_BTREE_MAXLEVELS];
+	struct list_head	to_check;
 };
-int xfs_scrub_btree(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
-		    xfs_scrub_btree_rec_fn scrub_fn,
-		    struct xfs_owner_info *oinfo, void *private);
+int xchk_btree(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
+		xchk_btree_rec_fn scrub_fn, struct xfs_owner_info *oinfo,
+		void *private);
 
 #endif /* __XFS_SCRUB_BTREE_H__ */
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 70e70c69f83f..346b02abccf7 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -68,20 +68,20 @@
 
 /* Check for operational errors. */
 static bool
-__xfs_scrub_process_error(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	xfs_agblock_t			bno,
-	int				*error,
-	__u32				errflag,
-	void				*ret_ip)
+__xchk_process_error(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	int			*error,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	switch (*error) {
 	case 0:
 		return true;
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -90,7 +90,7 @@ __xfs_scrub_process_error(
 		*error = 0;
 		/* fall through */
 	default:
-		trace_xfs_scrub_op_error(sc, agno, bno, *error,
+		trace_xchk_op_error(sc, agno, bno, *error,
 				ret_ip);
 		break;
 	}
@@ -98,43 +98,43 @@ __xfs_scrub_process_error(
 }
 
 bool
-xfs_scrub_process_error(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	xfs_agblock_t			bno,
-	int				*error)
+xchk_process_error(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	int			*error)
 {
-	return __xfs_scrub_process_error(sc, agno, bno, error,
+	return __xchk_process_error(sc, agno, bno, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
 bool
-xfs_scrub_xref_process_error(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	xfs_agblock_t			bno,
-	int				*error)
+xchk_xref_process_error(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	int			*error)
 {
-	return __xfs_scrub_process_error(sc, agno, bno, error,
+	return __xchk_process_error(sc, agno, bno, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
 }
 
 /* Check for operational errors for a file offset. */
 static bool
-__xfs_scrub_fblock_process_error(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset,
-	int				*error,
-	__u32				errflag,
-	void				*ret_ip)
+__xchk_fblock_process_error(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset,
+	int			*error,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	switch (*error) {
 	case 0:
 		return true;
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -143,7 +143,7 @@ __xfs_scrub_fblock_process_error(
 		*error = 0;
 		/* fall through */
 	default:
-		trace_xfs_scrub_file_op_error(sc, whichfork, offset, *error,
+		trace_xchk_file_op_error(sc, whichfork, offset, *error,
 				ret_ip);
 		break;
 	}
@@ -151,24 +151,24 @@ __xfs_scrub_fblock_process_error(
 }
 
 bool
-xfs_scrub_fblock_process_error(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset,
-	int				*error)
+xchk_fblock_process_error(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset,
+	int			*error)
 {
-	return __xfs_scrub_fblock_process_error(sc, whichfork, offset, error,
+	return __xchk_fblock_process_error(sc, whichfork, offset, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
 bool
-xfs_scrub_fblock_xref_process_error(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset,
-	int				*error)
+xchk_fblock_xref_process_error(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset,
+	int			*error)
 {
-	return __xfs_scrub_fblock_process_error(sc, whichfork, offset, error,
+	return __xchk_fblock_process_error(sc, whichfork, offset, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
 }
 
@@ -186,12 +186,12 @@ xfs_scrub_fblock_xref_process_error(
 
 /* Record a block which could be optimized. */
 void
-xfs_scrub_block_set_preen(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_block_set_preen(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
-	trace_xfs_scrub_block_preen(sc, bp->b_bn, __return_address);
+	trace_xchk_block_preen(sc, bp->b_bn, __return_address);
 }
 
 /*
@@ -200,32 +200,32 @@ xfs_scrub_block_set_preen(
  * the block location of the inode record itself.
  */
 void
-xfs_scrub_ino_set_preen(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_ino_set_preen(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
-	trace_xfs_scrub_ino_preen(sc, ino, __return_address);
+	trace_xchk_ino_preen(sc, ino, __return_address);
 }
 
 /* Record a corrupt block. */
 void
-xfs_scrub_block_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_block_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_block_error(sc, bp->b_bn, __return_address);
+	trace_xchk_block_error(sc, bp->b_bn, __return_address);
 }
 
 /* Record a corruption while cross-referencing. */
 void
-xfs_scrub_block_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_block_xref_set_corrupt(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
-	trace_xfs_scrub_block_error(sc, bp->b_bn, __return_address);
+	trace_xchk_block_error(sc, bp->b_bn, __return_address);
 }
 
 /*
@@ -234,44 +234,44 @@ xfs_scrub_block_xref_set_corrupt(
  * inode record itself.
  */
 void
-xfs_scrub_ino_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_ino_set_corrupt(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_ino_error(sc, ino, __return_address);
+	trace_xchk_ino_error(sc, ino, __return_address);
 }
 
 /* Record a corruption while cross-referencing with an inode. */
 void
-xfs_scrub_ino_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_ino_xref_set_corrupt(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
-	trace_xfs_scrub_ino_error(sc, ino, __return_address);
+	trace_xchk_ino_error(sc, ino, __return_address);
 }
 
 /* Record corruption in a block indexed by a file fork. */
 void
-xfs_scrub_fblock_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset)
+xchk_fblock_set_corrupt(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_fblock_error(sc, whichfork, offset, __return_address);
+	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
 }
 
 /* Record a corruption while cross-referencing a fork block. */
 void
-xfs_scrub_fblock_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset)
+xchk_fblock_xref_set_corrupt(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
-	trace_xfs_scrub_fblock_error(sc, whichfork, offset, __return_address);
+	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
 }
 
 /*
@@ -279,32 +279,32 @@ xfs_scrub_fblock_xref_set_corrupt(
  * incorrect.
  */
 void
-xfs_scrub_ino_set_warning(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_ino_set_warning(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
-	trace_xfs_scrub_ino_warning(sc, ino, __return_address);
+	trace_xchk_ino_warning(sc, ino, __return_address);
 }
 
 /* Warn about a block indexed by a file fork that needs review. */
 void
-xfs_scrub_fblock_set_warning(
-	struct xfs_scrub_context	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset)
+xchk_fblock_set_warning(
+	struct xfs_scrub	*sc,
+	int			whichfork,
+	xfs_fileoff_t		offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
-	trace_xfs_scrub_fblock_warning(sc, whichfork, offset, __return_address);
+	trace_xchk_fblock_warning(sc, whichfork, offset, __return_address);
 }
 
 /* Signal an incomplete scrub. */
 void
-xfs_scrub_set_incomplete(
-	struct xfs_scrub_context	*sc)
+xchk_set_incomplete(
+	struct xfs_scrub	*sc)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_INCOMPLETE;
-	trace_xfs_scrub_incomplete(sc, __return_address);
+	trace_xchk_incomplete(sc, __return_address);
 }
 
 /*
@@ -312,20 +312,20 @@ xfs_scrub_set_incomplete(
  * at least according to the reverse mapping data.
  */
 
-struct xfs_scrub_rmap_ownedby_info {
+struct xchk_rmap_ownedby_info {
 	struct xfs_owner_info	*oinfo;
 	xfs_filblks_t		*blocks;
 };
 
 STATIC int
-xfs_scrub_count_rmap_ownedby_irec(
-	struct xfs_btree_cur			*cur,
-	struct xfs_rmap_irec			*rec,
-	void					*priv)
+xchk_count_rmap_ownedby_irec(
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*priv)
 {
-	struct xfs_scrub_rmap_ownedby_info	*sroi = priv;
-	bool					irec_attr;
-	bool					oinfo_attr;
+	struct xchk_rmap_ownedby_info	*sroi = priv;
+	bool				irec_attr;
+	bool				oinfo_attr;
 
 	irec_attr = rec->rm_flags & XFS_RMAP_ATTR_FORK;
 	oinfo_attr = sroi->oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK;
@@ -344,19 +344,19 @@ xfs_scrub_count_rmap_ownedby_irec(
  * The caller should pass us an rmapbt cursor.
  */
 int
-xfs_scrub_count_rmap_ownedby_ag(
-	struct xfs_scrub_context		*sc,
-	struct xfs_btree_cur			*cur,
-	struct xfs_owner_info			*oinfo,
-	xfs_filblks_t				*blocks)
+xchk_count_rmap_ownedby_ag(
+	struct xfs_scrub		*sc,
+	struct xfs_btree_cur		*cur,
+	struct xfs_owner_info		*oinfo,
+	xfs_filblks_t			*blocks)
 {
-	struct xfs_scrub_rmap_ownedby_info	sroi;
+	struct xchk_rmap_ownedby_info	sroi;
 
 	sroi.oinfo = oinfo;
 	*blocks = 0;
 	sroi.blocks = blocks;
 
-	return xfs_rmap_query_all(cur, xfs_scrub_count_rmap_ownedby_irec,
+	return xfs_rmap_query_all(cur, xchk_count_rmap_ownedby_irec,
 			&sroi);
 }
 
@@ -371,8 +371,8 @@ xfs_scrub_count_rmap_ownedby_ag(
 /* Decide if we want to return an AG header read failure. */
 static inline bool
 want_ag_read_header_failure(
-	struct xfs_scrub_context	*sc,
-	unsigned int			type)
+	struct xfs_scrub	*sc,
+	unsigned int		type)
 {
 	/* Return all AG header read failures when scanning btrees. */
 	if (sc->sm->sm_type != XFS_SCRUB_TYPE_AGF &&
@@ -392,20 +392,20 @@ want_ag_read_header_failure(
 /*
  * Grab all the headers for an AG.
  *
- * The headers should be released by xfs_scrub_ag_free, but as a fail
+ * The headers should be released by xchk_ag_free, but as a fail
  * safe we attach all the buffers we grab to the scrub transaction so
  * they'll all be freed when we cancel it.
  */
 int
-xfs_scrub_ag_read_headers(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	struct xfs_buf			**agi,
-	struct xfs_buf			**agf,
-	struct xfs_buf			**agfl)
-{
-	struct xfs_mount		*mp = sc->mp;
-	int				error;
+xchk_ag_read_headers(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	struct xfs_buf		**agi,
+	struct xfs_buf		**agf,
+	struct xfs_buf		**agfl)
+{
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
 
 	error = xfs_ialloc_read_agi(mp, sc->tp, agno, agi);
 	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
@@ -425,8 +425,8 @@ out:
 
 /* Release all the AG btree cursors. */
 void
-xfs_scrub_ag_btcur_free(
-	struct xfs_scrub_ag		*sa)
+xchk_ag_btcur_free(
+	struct xchk_ag		*sa)
 {
 	if (sa->refc_cur)
 		xfs_btree_del_cursor(sa->refc_cur, XFS_BTREE_ERROR);
@@ -451,12 +451,12 @@ xfs_scrub_ag_btcur_free(
 
 /* Initialize all the btree cursors for an AG. */
 int
-xfs_scrub_ag_btcur_init(
-	struct xfs_scrub_context	*sc,
-	struct xfs_scrub_ag		*sa)
+xchk_ag_btcur_init(
+	struct xfs_scrub	*sc,
+	struct xchk_ag		*sa)
 {
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agnumber_t			agno = sa->agno;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agnumber_t		agno = sa->agno;
 
 	if (sa->agf_bp) {
 		/* Set up a bnobt cursor for cross-referencing. */
@@ -499,7 +499,7 @@ xfs_scrub_ag_btcur_init(
 	/* Set up a refcountbt cursor for cross-referencing. */
 	if (sa->agf_bp && xfs_sb_version_hasreflink(&mp->m_sb)) {
 		sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp,
-				sa->agf_bp, agno, NULL);
+				sa->agf_bp, agno);
 		if (!sa->refc_cur)
 			goto err;
 	}
@@ -511,11 +511,11 @@ err:
 
 /* Release the AG header context and btree cursors. */
 void
-xfs_scrub_ag_free(
-	struct xfs_scrub_context	*sc,
-	struct xfs_scrub_ag		*sa)
+xchk_ag_free(
+	struct xfs_scrub	*sc,
+	struct xchk_ag		*sa)
 {
-	xfs_scrub_ag_btcur_free(sa);
+	xchk_ag_btcur_free(sa);
 	if (sa->agfl_bp) {
 		xfs_trans_brelse(sc->tp, sa->agfl_bp);
 		sa->agfl_bp = NULL;
@@ -543,30 +543,30 @@ xfs_scrub_ag_free(
  * transaction ourselves.
  */
 int
-xfs_scrub_ag_init(
-	struct xfs_scrub_context	*sc,
-	xfs_agnumber_t			agno,
-	struct xfs_scrub_ag		*sa)
+xchk_ag_init(
+	struct xfs_scrub	*sc,
+	xfs_agnumber_t		agno,
+	struct xchk_ag		*sa)
 {
-	int				error;
+	int			error;
 
 	sa->agno = agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sa->agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sa->agi_bp,
 			&sa->agf_bp, &sa->agfl_bp);
 	if (error)
 		return error;
 
-	return xfs_scrub_ag_btcur_init(sc, sa);
+	return xchk_ag_btcur_init(sc, sa);
 }
 
 /*
  * Grab the per-ag structure if we haven't already gotten it.  Teardown of the
- * xfs_scrub_ag will release it for us.
+ * xchk_ag will release it for us.
  */
 void
-xfs_scrub_perag_get(
+xchk_perag_get(
 	struct xfs_mount	*mp,
-	struct xfs_scrub_ag	*sa)
+	struct xchk_ag		*sa)
 {
 	if (!sa->pag)
 		sa->pag = xfs_perag_get(mp, sa->agno);
@@ -585,9 +585,9 @@ xfs_scrub_perag_get(
  * the metadata object.
  */
 int
-xfs_scrub_trans_alloc(
-	struct xfs_scrub_context	*sc,
-	uint				resblks)
+xchk_trans_alloc(
+	struct xfs_scrub	*sc,
+	uint			resblks)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
 		return xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
@@ -598,25 +598,25 @@ xfs_scrub_trans_alloc(
 
 /* Set us up with a transaction and an empty context. */
 int
-xfs_scrub_setup_fs(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_fs(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	uint				resblks;
+	uint			resblks;
 
-	resblks = xfs_repair_calc_ag_resblks(sc);
-	return xfs_scrub_trans_alloc(sc, resblks);
+	resblks = xrep_calc_ag_resblks(sc);
+	return xchk_trans_alloc(sc, resblks);
 }
 
 /* Set us up with AG headers and btree cursors. */
 int
-xfs_scrub_setup_ag_btree(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip,
-	bool				force_log)
+xchk_setup_ag_btree(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	bool			force_log)
 {
-	struct xfs_mount		*mp = sc->mp;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
 
 	/*
 	 * If the caller asks us to checkpont the log, do so.  This
@@ -625,21 +625,21 @@ xfs_scrub_setup_ag_btree(
 	 * document why they need to do so.
 	 */
 	if (force_log) {
-		error = xfs_scrub_checkpoint_log(mp);
+		error = xchk_checkpoint_log(mp);
 		if (error)
 			return error;
 	}
 
-	error = xfs_scrub_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc, ip);
 	if (error)
 		return error;
 
-	return xfs_scrub_ag_init(sc, sc->sm->sm_agno, &sc->sa);
+	return xchk_ag_init(sc, sc->sm->sm_agno, &sc->sa);
 }
 
 /* Push everything out of the log onto disk. */
 int
-xfs_scrub_checkpoint_log(
+xchk_checkpoint_log(
 	struct xfs_mount	*mp)
 {
 	int			error;
@@ -657,14 +657,14 @@ xfs_scrub_checkpoint_log(
  * The inode is not locked.
  */
 int
-xfs_scrub_get_inode(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip_in)
+xchk_get_inode(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip_in)
 {
-	struct xfs_imap			imap;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip = NULL;
-	int				error;
+	struct xfs_imap		imap;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = NULL;
+	int			error;
 
 	/* We want to scan the inode we already had opened. */
 	if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino) {
@@ -704,14 +704,14 @@ xfs_scrub_get_inode(
 		error = -EFSCORRUPTED;
 		/* fall through */
 	default:
-		trace_xfs_scrub_op_error(sc,
+		trace_xchk_op_error(sc,
 				XFS_INO_TO_AGNO(mp, sc->sm->sm_ino),
 				XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino),
 				error, __return_address);
 		return error;
 	}
 	if (VFS_I(ip)->i_generation != sc->sm->sm_gen) {
-		iput(VFS_I(ip));
+		xfs_irele(ip);
 		return -ENOENT;
 	}
 
@@ -721,21 +721,21 @@ xfs_scrub_get_inode(
 
 /* Set us up to scrub a file's contents. */
 int
-xfs_scrub_setup_inode_contents(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip,
-	unsigned int			resblks)
+xchk_setup_inode_contents(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip,
+	unsigned int		resblks)
 {
-	int				error;
+	int			error;
 
-	error = xfs_scrub_get_inode(sc, ip);
+	error = xchk_get_inode(sc, ip);
 	if (error)
 		return error;
 
 	/* Got the inode, lock it and we're ready to go. */
 	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	error = xfs_scrub_trans_alloc(sc, resblks);
+	error = xchk_trans_alloc(sc, resblks);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -752,13 +752,13 @@ out:
  * the cursor and skip the check.
  */
 bool
-xfs_scrub_should_check_xref(
-	struct xfs_scrub_context	*sc,
-	int				*error,
-	struct xfs_btree_cur		**curpp)
+xchk_should_check_xref(
+	struct xfs_scrub	*sc,
+	int			*error,
+	struct xfs_btree_cur	**curpp)
 {
 	/* No point in xref if we already know we're corrupt. */
-	if (xfs_scrub_skip_xref(sc->sm))
+	if (xchk_skip_xref(sc->sm))
 		return false;
 
 	if (*error == 0)
@@ -775,7 +775,7 @@ xfs_scrub_should_check_xref(
 	}
 
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XFAIL;
-	trace_xfs_scrub_xref_error(sc, *error, __return_address);
+	trace_xchk_xref_error(sc, *error, __return_address);
 
 	/*
 	 * Errors encountered during cross-referencing with another
@@ -787,25 +787,25 @@ xfs_scrub_should_check_xref(
 
 /* Run the structure verifiers on in-memory buffers to detect bad memory. */
 void
-xfs_scrub_buffer_recheck(
-	struct xfs_scrub_context	*sc,
-	struct xfs_buf			*bp)
+xchk_buffer_recheck(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*bp)
 {
-	xfs_failaddr_t			fa;
+	xfs_failaddr_t		fa;
 
 	if (bp->b_ops == NULL) {
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 		return;
 	}
 	if (bp->b_ops->verify_struct == NULL) {
-		xfs_scrub_set_incomplete(sc);
+		xchk_set_incomplete(sc);
 		return;
 	}
 	fa = bp->b_ops->verify_struct(bp);
 	if (!fa)
 		return;
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_block_error(sc, bp->b_bn, fa);
+	trace_xchk_block_error(sc, bp->b_bn, fa);
 }
 
 /*
@@ -813,38 +813,38 @@ xfs_scrub_buffer_recheck(
  * pointed to by sc->ip and the ILOCK must be held.
  */
 int
-xfs_scrub_metadata_inode_forks(
-	struct xfs_scrub_context	*sc)
+xchk_metadata_inode_forks(
+	struct xfs_scrub	*sc)
 {
-	__u32				smtype;
-	bool				shared;
-	int				error;
+	__u32			smtype;
+	bool			shared;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return 0;
 
 	/* Metadata inodes don't live on the rt device. */
 	if (sc->ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
 
 	/* They should never participate in reflink. */
 	if (xfs_is_reflink_inode(sc->ip)) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
 
 	/* They also should never have extended attributes. */
 	if (xfs_inode_hasattr(sc->ip)) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
 
 	/* Invoke the data fork scrubber. */
 	smtype = sc->sm->sm_type;
 	sc->sm->sm_type = XFS_SCRUB_TYPE_BMBTD;
-	error = xfs_scrub_bmap_data(sc);
+	error = xchk_bmap_data(sc);
 	sc->sm->sm_type = smtype;
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
@@ -853,11 +853,11 @@ xfs_scrub_metadata_inode_forks(
 	if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
 		error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
 				&shared);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0,
 				&error))
 			return error;
 		if (shared)
-			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 	}
 
 	return error;
@@ -871,7 +871,7 @@ xfs_scrub_metadata_inode_forks(
  * we can't.
  */
 int
-xfs_scrub_ilock_inverted(
+xchk_ilock_inverted(
 	struct xfs_inode	*ip,
 	uint			lock_mode)
 {
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 2172bd5361e2..2d4324d12f9a 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -12,8 +12,8 @@
  * Note that we're careful not to make any judgements about *error.
  */
 static inline bool
-xfs_scrub_should_terminate(
-	struct xfs_scrub_context	*sc,
+xchk_should_terminate(
+	struct xfs_scrub	*sc,
 	int				*error)
 {
 	if (fatal_signal_pending(current)) {
@@ -24,121 +24,118 @@ xfs_scrub_should_terminate(
 	return false;
 }
 
-int xfs_scrub_trans_alloc(struct xfs_scrub_context *sc, uint resblks);
-bool xfs_scrub_process_error(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+int xchk_trans_alloc(struct xfs_scrub *sc, uint resblks);
+bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		xfs_agblock_t bno, int *error);
-bool xfs_scrub_fblock_process_error(struct xfs_scrub_context *sc, int whichfork,
+bool xchk_fblock_process_error(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset, int *error);
 
-bool xfs_scrub_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_xref_process_error(struct xfs_scrub *sc,
 		xfs_agnumber_t agno, xfs_agblock_t bno, int *error);
-bool xfs_scrub_fblock_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_fblock_xref_process_error(struct xfs_scrub *sc,
 		int whichfork, xfs_fileoff_t offset, int *error);
 
-void xfs_scrub_block_set_preen(struct xfs_scrub_context *sc,
+void xchk_block_set_preen(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
-void xfs_scrub_ino_set_preen(struct xfs_scrub_context *sc, xfs_ino_t ino);
+void xchk_ino_set_preen(struct xfs_scrub *sc, xfs_ino_t ino);
 
-void xfs_scrub_block_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_block_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
-void xfs_scrub_ino_set_corrupt(struct xfs_scrub_context *sc, xfs_ino_t ino);
-void xfs_scrub_fblock_set_corrupt(struct xfs_scrub_context *sc, int whichfork,
+void xchk_ino_set_corrupt(struct xfs_scrub *sc, xfs_ino_t ino);
+void xchk_fblock_set_corrupt(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset);
 
-void xfs_scrub_block_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_block_xref_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
-void xfs_scrub_ino_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_ino_xref_set_corrupt(struct xfs_scrub *sc,
 		xfs_ino_t ino);
-void xfs_scrub_fblock_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_fblock_xref_set_corrupt(struct xfs_scrub *sc,
 		int whichfork, xfs_fileoff_t offset);
 
-void xfs_scrub_ino_set_warning(struct xfs_scrub_context *sc, xfs_ino_t ino);
-void xfs_scrub_fblock_set_warning(struct xfs_scrub_context *sc, int whichfork,
+void xchk_ino_set_warning(struct xfs_scrub *sc, xfs_ino_t ino);
+void xchk_fblock_set_warning(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset);
 
-void xfs_scrub_set_incomplete(struct xfs_scrub_context *sc);
-int xfs_scrub_checkpoint_log(struct xfs_mount *mp);
+void xchk_set_incomplete(struct xfs_scrub *sc);
+int xchk_checkpoint_log(struct xfs_mount *mp);
 
 /* Are we set up for a cross-referencing check? */
-bool xfs_scrub_should_check_xref(struct xfs_scrub_context *sc, int *error,
+bool xchk_should_check_xref(struct xfs_scrub *sc, int *error,
 			   struct xfs_btree_cur **curpp);
 
 /* Setup functions */
-int xfs_scrub_setup_fs(struct xfs_scrub_context *sc, struct xfs_inode *ip);
-int xfs_scrub_setup_ag_allocbt(struct xfs_scrub_context *sc,
+int xchk_setup_fs(struct xfs_scrub *sc, struct xfs_inode *ip);
+int xchk_setup_ag_allocbt(struct xfs_scrub *sc,
 			       struct xfs_inode *ip);
-int xfs_scrub_setup_ag_iallocbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_iallocbt(struct xfs_scrub *sc,
 				struct xfs_inode *ip);
-int xfs_scrub_setup_ag_rmapbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_rmapbt(struct xfs_scrub *sc,
 			      struct xfs_inode *ip);
-int xfs_scrub_setup_ag_refcountbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_refcountbt(struct xfs_scrub *sc,
 				  struct xfs_inode *ip);
-int xfs_scrub_setup_inode(struct xfs_scrub_context *sc,
+int xchk_setup_inode(struct xfs_scrub *sc,
 			  struct xfs_inode *ip);
-int xfs_scrub_setup_inode_bmap(struct xfs_scrub_context *sc,
+int xchk_setup_inode_bmap(struct xfs_scrub *sc,
 			       struct xfs_inode *ip);
-int xfs_scrub_setup_inode_bmap_data(struct xfs_scrub_context *sc,
+int xchk_setup_inode_bmap_data(struct xfs_scrub *sc,
 				    struct xfs_inode *ip);
-int xfs_scrub_setup_directory(struct xfs_scrub_context *sc,
+int xchk_setup_directory(struct xfs_scrub *sc,
 			      struct xfs_inode *ip);
-int xfs_scrub_setup_xattr(struct xfs_scrub_context *sc,
+int xchk_setup_xattr(struct xfs_scrub *sc,
 			  struct xfs_inode *ip);
-int xfs_scrub_setup_symlink(struct xfs_scrub_context *sc,
+int xchk_setup_symlink(struct xfs_scrub *sc,
 			    struct xfs_inode *ip);
-int xfs_scrub_setup_parent(struct xfs_scrub_context *sc,
+int xchk_setup_parent(struct xfs_scrub *sc,
 			   struct xfs_inode *ip);
 #ifdef CONFIG_XFS_RT
-int xfs_scrub_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip);
 #else
 static inline int
-xfs_scrub_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip)
+xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip)
 {
 	return -ENOENT;
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
-int xfs_scrub_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip);
 #else
 static inline int
-xfs_scrub_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip)
+xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip)
 {
 	return -ENOENT;
 }
 #endif
 
-void xfs_scrub_ag_free(struct xfs_scrub_context *sc, struct xfs_scrub_ag *sa);
-int xfs_scrub_ag_init(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
-		      struct xfs_scrub_ag *sa);
-void xfs_scrub_perag_get(struct xfs_mount *mp, struct xfs_scrub_ag *sa);
-int xfs_scrub_ag_read_headers(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
-			      struct xfs_buf **agi, struct xfs_buf **agf,
-			      struct xfs_buf **agfl);
-void xfs_scrub_ag_btcur_free(struct xfs_scrub_ag *sa);
-int xfs_scrub_ag_btcur_init(struct xfs_scrub_context *sc,
-			    struct xfs_scrub_ag *sa);
-int xfs_scrub_count_rmap_ownedby_ag(struct xfs_scrub_context *sc,
-				    struct xfs_btree_cur *cur,
-				    struct xfs_owner_info *oinfo,
-				    xfs_filblks_t *blocks);
+void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
+int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,
+		struct xchk_ag *sa);
+void xchk_perag_get(struct xfs_mount *mp, struct xchk_ag *sa);
+int xchk_ag_read_headers(struct xfs_scrub *sc, xfs_agnumber_t agno,
+		struct xfs_buf **agi, struct xfs_buf **agf,
+		struct xfs_buf **agfl);
+void xchk_ag_btcur_free(struct xchk_ag *sa);
+int xchk_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
+int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
+		struct xfs_owner_info *oinfo, xfs_filblks_t *blocks);
 
-int xfs_scrub_setup_ag_btree(struct xfs_scrub_context *sc,
-			     struct xfs_inode *ip, bool force_log);
-int xfs_scrub_get_inode(struct xfs_scrub_context *sc, struct xfs_inode *ip_in);
-int xfs_scrub_setup_inode_contents(struct xfs_scrub_context *sc,
-				   struct xfs_inode *ip, unsigned int resblks);
-void xfs_scrub_buffer_recheck(struct xfs_scrub_context *sc, struct xfs_buf *bp);
+int xchk_setup_ag_btree(struct xfs_scrub *sc, struct xfs_inode *ip,
+		bool force_log);
+int xchk_get_inode(struct xfs_scrub *sc, struct xfs_inode *ip_in);
+int xchk_setup_inode_contents(struct xfs_scrub *sc, struct xfs_inode *ip,
+		unsigned int resblks);
+void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
 
 /*
  * Don't bother cross-referencing if we already found corruption or cross
  * referencing discrepancies.
  */
-static inline bool xfs_scrub_skip_xref(struct xfs_scrub_metadata *sm)
+static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
 {
 	return sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
 			       XFS_SCRUB_OFLAG_XCORRUPT);
 }
 
-int xfs_scrub_metadata_inode_forks(struct xfs_scrub_context *sc);
-int xfs_scrub_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
+int xchk_metadata_inode_forks(struct xfs_scrub *sc);
+int xchk_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
 
 #endif	/* __XFS_SCRUB_COMMON_H__ */
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index d700c4d4d4ef..f1260b4bfdee 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -35,12 +35,12 @@
  * operational errors in common.c.
  */
 bool
-xfs_scrub_da_process_error(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	int				*error)
+xchk_da_process_error(
+	struct xchk_da_btree	*ds,
+	int			level,
+	int			*error)
 {
-	struct xfs_scrub_context	*sc = ds->sc;
+	struct xfs_scrub	*sc = ds->sc;
 
 	if (*error == 0)
 		return true;
@@ -48,7 +48,7 @@ xfs_scrub_da_process_error(
 	switch (*error) {
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -57,7 +57,7 @@ xfs_scrub_da_process_error(
 		*error = 0;
 		/* fall through */
 	default:
-		trace_xfs_scrub_file_op_error(sc, ds->dargs.whichfork,
+		trace_xchk_file_op_error(sc, ds->dargs.whichfork,
 				xfs_dir2_da_to_db(ds->dargs.geo,
 					ds->state->path.blk[level].blkno),
 				*error, __return_address);
@@ -71,15 +71,15 @@ xfs_scrub_da_process_error(
  * operational errors in common.c.
  */
 void
-xfs_scrub_da_set_corrupt(
-	struct xfs_scrub_da_btree	*ds,
-	int				level)
+xchk_da_set_corrupt(
+	struct xchk_da_btree	*ds,
+	int			level)
 {
-	struct xfs_scrub_context	*sc = ds->sc;
+	struct xfs_scrub	*sc = ds->sc;
 
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 
-	trace_xfs_scrub_fblock_error(sc, ds->dargs.whichfork,
+	trace_xchk_fblock_error(sc, ds->dargs.whichfork,
 			xfs_dir2_da_to_db(ds->dargs.geo,
 				ds->state->path.blk[level].blkno),
 			__return_address);
@@ -87,14 +87,14 @@ xfs_scrub_da_set_corrupt(
 
 /* Find an entry at a certain level in a da btree. */
 STATIC void *
-xfs_scrub_da_btree_entry(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	int				rec)
+xchk_da_btree_entry(
+	struct xchk_da_btree	*ds,
+	int			level,
+	int			rec)
 {
-	char				*ents;
-	struct xfs_da_state_blk		*blk;
-	void				*baddr;
+	char			*ents;
+	struct xfs_da_state_blk	*blk;
+	void			*baddr;
 
 	/* Dispatch the entry finding function. */
 	blk = &ds->state->path.blk[level];
@@ -123,8 +123,8 @@ xfs_scrub_da_btree_entry(
 
 /* Scrub a da btree hash (key). */
 int
-xfs_scrub_da_btree_hash(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_hash(
+	struct xchk_da_btree		*ds,
 	int				level,
 	__be32				*hashp)
 {
@@ -136,7 +136,7 @@ xfs_scrub_da_btree_hash(
 	/* Is this hash in order? */
 	hash = be32_to_cpu(*hashp);
 	if (hash < ds->hashes[level])
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	ds->hashes[level] = hash;
 
 	if (level == 0)
@@ -144,10 +144,10 @@ xfs_scrub_da_btree_hash(
 
 	/* Is this hash no larger than the parent hash? */
 	blks = ds->state->path.blk;
-	entry = xfs_scrub_da_btree_entry(ds, level - 1, blks[level - 1].index);
+	entry = xchk_da_btree_entry(ds, level - 1, blks[level - 1].index);
 	parent_hash = be32_to_cpu(entry->hashval);
 	if (parent_hash < hash)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	return 0;
 }
@@ -157,13 +157,13 @@ xfs_scrub_da_btree_hash(
  * pointer.
  */
 STATIC bool
-xfs_scrub_da_btree_ptr_ok(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	xfs_dablk_t			blkno)
+xchk_da_btree_ptr_ok(
+	struct xchk_da_btree	*ds,
+	int			level,
+	xfs_dablk_t		blkno)
 {
 	if (blkno < ds->lowest || (ds->highest != 0 && blkno >= ds->highest)) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		return false;
 	}
 
@@ -176,7 +176,7 @@ xfs_scrub_da_btree_ptr_ok(
  * leaf1, we must multiplex the verifiers.
  */
 static void
-xfs_scrub_da_btree_read_verify(
+xchk_da_btree_read_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -198,7 +198,7 @@ xfs_scrub_da_btree_read_verify(
 	}
 }
 static void
-xfs_scrub_da_btree_write_verify(
+xchk_da_btree_write_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -220,7 +220,7 @@ xfs_scrub_da_btree_write_verify(
 	}
 }
 static void *
-xfs_scrub_da_btree_verify(
+xchk_da_btree_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -236,23 +236,23 @@ xfs_scrub_da_btree_verify(
 	}
 }
 
-static const struct xfs_buf_ops xfs_scrub_da_btree_buf_ops = {
-	.name = "xfs_scrub_da_btree",
-	.verify_read = xfs_scrub_da_btree_read_verify,
-	.verify_write = xfs_scrub_da_btree_write_verify,
-	.verify_struct = xfs_scrub_da_btree_verify,
+static const struct xfs_buf_ops xchk_da_btree_buf_ops = {
+	.name = "xchk_da_btree",
+	.verify_read = xchk_da_btree_read_verify,
+	.verify_write = xchk_da_btree_write_verify,
+	.verify_struct = xchk_da_btree_verify,
 };
 
 /* Check a block's sibling. */
 STATIC int
-xfs_scrub_da_btree_block_check_sibling(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	int				direction,
-	xfs_dablk_t			sibling)
+xchk_da_btree_block_check_sibling(
+	struct xchk_da_btree	*ds,
+	int			level,
+	int			direction,
+	xfs_dablk_t		sibling)
 {
-	int				retval;
-	int				error;
+	int			retval;
+	int			error;
 
 	memcpy(&ds->state->altpath, &ds->state->path,
 			sizeof(ds->state->altpath));
@@ -265,7 +265,7 @@ xfs_scrub_da_btree_block_check_sibling(
 		error = xfs_da3_path_shift(ds->state, &ds->state->altpath,
 				direction, false, &retval);
 		if (error == 0 && retval == 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		error = 0;
 		goto out;
 	}
@@ -273,19 +273,19 @@ xfs_scrub_da_btree_block_check_sibling(
 	/* Move the alternate cursor one block in the direction given. */
 	error = xfs_da3_path_shift(ds->state, &ds->state->altpath,
 			direction, false, &retval);
-	if (!xfs_scrub_da_process_error(ds, level, &error))
+	if (!xchk_da_process_error(ds, level, &error))
 		return error;
 	if (retval) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		return error;
 	}
 	if (ds->state->altpath.blk[level].bp)
-		xfs_scrub_buffer_recheck(ds->sc,
+		xchk_buffer_recheck(ds->sc,
 				ds->state->altpath.blk[level].bp);
 
 	/* Compare upper level pointer to sibling pointer. */
 	if (ds->state->altpath.blk[level].blkno != sibling)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	xfs_trans_brelse(ds->dargs.trans, ds->state->altpath.blk[level].bp);
 out:
 	return error;
@@ -293,14 +293,14 @@ out:
 
 /* Check a block's sibling pointers. */
 STATIC int
-xfs_scrub_da_btree_block_check_siblings(
-	struct xfs_scrub_da_btree	*ds,
-	int				level,
-	struct xfs_da_blkinfo		*hdr)
+xchk_da_btree_block_check_siblings(
+	struct xchk_da_btree	*ds,
+	int			level,
+	struct xfs_da_blkinfo	*hdr)
 {
-	xfs_dablk_t			forw;
-	xfs_dablk_t			back;
-	int				error = 0;
+	xfs_dablk_t		forw;
+	xfs_dablk_t		back;
+	int			error = 0;
 
 	forw = be32_to_cpu(hdr->forw);
 	back = be32_to_cpu(hdr->back);
@@ -308,7 +308,7 @@ xfs_scrub_da_btree_block_check_siblings(
 	/* Top level blocks should not have sibling pointers. */
 	if (level == 0) {
 		if (forw != 0 || back != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		return 0;
 	}
 
@@ -316,10 +316,10 @@ xfs_scrub_da_btree_block_check_siblings(
 	 * Check back (left) and forw (right) pointers.  These functions
 	 * absorb error codes for us.
 	 */
-	error = xfs_scrub_da_btree_block_check_sibling(ds, level, 0, back);
+	error = xchk_da_btree_block_check_sibling(ds, level, 0, back);
 	if (error)
 		goto out;
-	error = xfs_scrub_da_btree_block_check_sibling(ds, level, 1, forw);
+	error = xchk_da_btree_block_check_sibling(ds, level, 1, forw);
 
 out:
 	memset(&ds->state->altpath, 0, sizeof(ds->state->altpath));
@@ -328,8 +328,8 @@ out:
 
 /* Load a dir/attribute block from a btree. */
 STATIC int
-xfs_scrub_da_btree_block(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_block(
+	struct xchk_da_btree		*ds,
 	int				level,
 	xfs_dablk_t			blkno)
 {
@@ -355,17 +355,17 @@ xfs_scrub_da_btree_block(
 
 	/* Check the pointer. */
 	blk->blkno = blkno;
-	if (!xfs_scrub_da_btree_ptr_ok(ds, level, blkno))
+	if (!xchk_da_btree_ptr_ok(ds, level, blkno))
 		goto out_nobuf;
 
 	/* Read the buffer. */
 	error = xfs_da_read_buf(dargs->trans, dargs->dp, blk->blkno, -2,
 			&blk->bp, dargs->whichfork,
-			&xfs_scrub_da_btree_buf_ops);
-	if (!xfs_scrub_da_process_error(ds, level, &error))
+			&xchk_da_btree_buf_ops);
+	if (!xchk_da_process_error(ds, level, &error))
 		goto out_nobuf;
 	if (blk->bp)
-		xfs_scrub_buffer_recheck(ds->sc, blk->bp);
+		xchk_buffer_recheck(ds->sc, blk->bp);
 
 	/*
 	 * We didn't find a dir btree root block, which means that
@@ -378,7 +378,7 @@ xfs_scrub_da_btree_block(
 
 	/* It's /not/ ok for attr trees not to have a da btree. */
 	if (blk->bp == NULL) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out_nobuf;
 	}
 
@@ -388,17 +388,17 @@ xfs_scrub_da_btree_block(
 
 	/* We only started zeroing the header on v5 filesystems. */
 	if (xfs_sb_version_hascrc(&ds->sc->mp->m_sb) && hdr3->hdr.pad)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	/* Check the owner. */
 	if (xfs_sb_version_hascrc(&ip->i_mount->m_sb)) {
 		owner = be64_to_cpu(hdr3->owner);
 		if (owner != ip->i_ino)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	}
 
 	/* Check the siblings. */
-	error = xfs_scrub_da_btree_block_check_siblings(ds, level, &hdr3->hdr);
+	error = xchk_da_btree_block_check_siblings(ds, level, &hdr3->hdr);
 	if (error)
 		goto out;
 
@@ -411,7 +411,7 @@ xfs_scrub_da_btree_block(
 		blk->magic = XFS_ATTR_LEAF_MAGIC;
 		blk->hashval = xfs_attr_leaf_lasthash(blk->bp, pmaxrecs);
 		if (ds->tree_level != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		break;
 	case XFS_DIR2_LEAFN_MAGIC:
 	case XFS_DIR3_LEAFN_MAGIC:
@@ -420,7 +420,7 @@ xfs_scrub_da_btree_block(
 		blk->magic = XFS_DIR2_LEAFN_MAGIC;
 		blk->hashval = xfs_dir2_leaf_lasthash(ip, blk->bp, pmaxrecs);
 		if (ds->tree_level != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		break;
 	case XFS_DIR2_LEAF1_MAGIC:
 	case XFS_DIR3_LEAF1_MAGIC:
@@ -429,7 +429,7 @@ xfs_scrub_da_btree_block(
 		blk->magic = XFS_DIR2_LEAF1_MAGIC;
 		blk->hashval = xfs_dir2_leaf_lasthash(ip, blk->bp, pmaxrecs);
 		if (ds->tree_level != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		break;
 	case XFS_DA_NODE_MAGIC:
 	case XFS_DA3_NODE_MAGIC:
@@ -443,13 +443,13 @@ xfs_scrub_da_btree_block(
 		blk->hashval = be32_to_cpu(btree[*pmaxrecs - 1].hashval);
 		if (level == 0) {
 			if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) {
-				xfs_scrub_da_set_corrupt(ds, level);
+				xchk_da_set_corrupt(ds, level);
 				goto out_freebp;
 			}
 			ds->tree_level = nodehdr.level;
 		} else {
 			if (ds->tree_level != nodehdr.level) {
-				xfs_scrub_da_set_corrupt(ds, level);
+				xchk_da_set_corrupt(ds, level);
 				goto out_freebp;
 			}
 		}
@@ -457,7 +457,7 @@ xfs_scrub_da_btree_block(
 		/* XXX: Check hdr3.pad32 once we know how to fix it. */
 		break;
 	default:
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out_freebp;
 	}
 
@@ -473,13 +473,13 @@ out_nobuf:
 
 /* Visit all nodes and leaves of a da btree. */
 int
-xfs_scrub_da_btree(
-	struct xfs_scrub_context	*sc,
+xchk_da_btree(
+	struct xfs_scrub		*sc,
 	int				whichfork,
-	xfs_scrub_da_btree_rec_fn	scrub_fn,
+	xchk_da_btree_rec_fn		scrub_fn,
 	void				*private)
 {
-	struct xfs_scrub_da_btree	ds = {};
+	struct xchk_da_btree		ds = {};
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_da_state_blk		*blks;
 	struct xfs_da_node_entry	*key;
@@ -517,7 +517,7 @@ xfs_scrub_da_btree(
 
 	/* Find the root of the da tree, if present. */
 	blks = ds.state->path.blk;
-	error = xfs_scrub_da_btree_block(&ds, level, blkno);
+	error = xchk_da_btree_block(&ds, level, blkno);
 	if (error)
 		goto out_state;
 	/*
@@ -542,12 +542,12 @@ xfs_scrub_da_btree(
 			}
 
 			/* Dispatch record scrubbing. */
-			rec = xfs_scrub_da_btree_entry(&ds, level,
+			rec = xchk_da_btree_entry(&ds, level,
 					blks[level].index);
 			error = scrub_fn(&ds, level, rec);
 			if (error)
 				break;
-			if (xfs_scrub_should_terminate(sc, &error) ||
+			if (xchk_should_terminate(sc, &error) ||
 			    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 				break;
 
@@ -566,8 +566,8 @@ xfs_scrub_da_btree(
 		}
 
 		/* Hashes in order for scrub? */
-		key = xfs_scrub_da_btree_entry(&ds, level, blks[level].index);
-		error = xfs_scrub_da_btree_hash(&ds, level, &key->hashval);
+		key = xchk_da_btree_entry(&ds, level, blks[level].index);
+		error = xchk_da_btree_hash(&ds, level, &key->hashval);
 		if (error)
 			goto out;
 
@@ -575,7 +575,7 @@ xfs_scrub_da_btree(
 		blkno = be32_to_cpu(key->before);
 		level++;
 		ds.tree_level--;
-		error = xfs_scrub_da_btree_block(&ds, level, blkno);
+		error = xchk_da_btree_block(&ds, level, blkno);
 		if (error)
 			goto out;
 		if (blks[level].bp == NULL)
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index 365f9f0019e6..cb3f0003245b 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -8,13 +8,13 @@
 
 /* dir/attr btree */
 
-struct xfs_scrub_da_btree {
-	struct xfs_da_args		dargs;
-	xfs_dahash_t			hashes[XFS_DA_NODE_MAXDEPTH];
-	int				maxrecs[XFS_DA_NODE_MAXDEPTH];
-	struct xfs_da_state		*state;
-	struct xfs_scrub_context	*sc;
-	void				*private;
+struct xchk_da_btree {
+	struct xfs_da_args	dargs;
+	xfs_dahash_t		hashes[XFS_DA_NODE_MAXDEPTH];
+	int			maxrecs[XFS_DA_NODE_MAXDEPTH];
+	struct xfs_da_state	*state;
+	struct xfs_scrub	*sc;
+	void			*private;
 
 	/*
 	 * Lowest and highest directory block address in which we expect
@@ -22,24 +22,23 @@ struct xfs_scrub_da_btree {
 	 * (presumably) means between LEAF_OFFSET and FREE_OFFSET; for
 	 * attributes there is no limit.
 	 */
-	xfs_dablk_t			lowest;
-	xfs_dablk_t			highest;
+	xfs_dablk_t		lowest;
+	xfs_dablk_t		highest;
 
-	int				tree_level;
+	int			tree_level;
 };
 
-typedef int (*xfs_scrub_da_btree_rec_fn)(struct xfs_scrub_da_btree *ds,
+typedef int (*xchk_da_btree_rec_fn)(struct xchk_da_btree *ds,
 		int level, void *rec);
 
 /* Check for da btree operation errors. */
-bool xfs_scrub_da_process_error(struct xfs_scrub_da_btree *ds, int level, int *error);
+bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error);
 
 /* Check for da btree corruption. */
-void xfs_scrub_da_set_corrupt(struct xfs_scrub_da_btree *ds, int level);
+void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
 
-int xfs_scrub_da_btree_hash(struct xfs_scrub_da_btree *ds, int level,
-			    __be32 *hashp);
-int xfs_scrub_da_btree(struct xfs_scrub_context *sc, int whichfork,
-		       xfs_scrub_da_btree_rec_fn scrub_fn, void *private);
+int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp);
+int xchk_da_btree(struct xfs_scrub *sc, int whichfork,
+		xchk_da_btree_rec_fn scrub_fn, void *private);
 
 #endif /* __XFS_SCRUB_DABTREE_H__ */
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 86324775fc9b..cd3e4d768a18 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -31,40 +31,40 @@
 
 /* Set us up to scrub directories. */
 int
-xfs_scrub_setup_directory(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_directory(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Directories */
 
 /* Scrub a directory entry. */
 
-struct xfs_scrub_dir_ctx {
+struct xchk_dir_ctx {
 	/* VFS fill-directory iterator */
-	struct dir_context		dir_iter;
+	struct dir_context	dir_iter;
 
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 };
 
 /* Check that an inode's mode matches a given DT_ type. */
 STATIC int
-xfs_scrub_dir_check_ftype(
-	struct xfs_scrub_dir_ctx	*sdc,
-	xfs_fileoff_t			offset,
-	xfs_ino_t			inum,
-	int				dtype)
+xchk_dir_check_ftype(
+	struct xchk_dir_ctx	*sdc,
+	xfs_fileoff_t		offset,
+	xfs_ino_t		inum,
+	int			dtype)
 {
-	struct xfs_mount		*mp = sdc->sc->mp;
-	struct xfs_inode		*ip;
-	int				ino_dtype;
-	int				error = 0;
+	struct xfs_mount	*mp = sdc->sc->mp;
+	struct xfs_inode	*ip;
+	int			ino_dtype;
+	int			error = 0;
 
 	if (!xfs_sb_version_hasftype(&mp->m_sb)) {
 		if (dtype != DT_UNKNOWN && dtype != DT_DIR)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 		goto out;
 	}
@@ -78,7 +78,7 @@ xfs_scrub_dir_check_ftype(
 	 * inodes can trigger immediate inactive cleanup of the inode.
 	 */
 	error = xfs_iget(mp, sdc->sc->tp, inum, 0, 0, &ip);
-	if (!xfs_scrub_fblock_xref_process_error(sdc->sc, XFS_DATA_FORK, offset,
+	if (!xchk_fblock_xref_process_error(sdc->sc, XFS_DATA_FORK, offset,
 			&error))
 		goto out;
 
@@ -86,8 +86,8 @@ xfs_scrub_dir_check_ftype(
 	ino_dtype = xfs_dir3_get_dtype(mp,
 			xfs_mode_to_ftype(VFS_I(ip)->i_mode));
 	if (ino_dtype != dtype)
-		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
-	iput(VFS_I(ip));
+		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
+	xfs_irele(ip);
 out:
 	return error;
 }
@@ -101,23 +101,23 @@ out:
  * we can look up this filename.  Finally, we check the ftype.
  */
 STATIC int
-xfs_scrub_dir_actor(
-	struct dir_context		*dir_iter,
-	const char			*name,
-	int				namelen,
-	loff_t				pos,
-	u64				ino,
-	unsigned			type)
+xchk_dir_actor(
+	struct dir_context	*dir_iter,
+	const char		*name,
+	int			namelen,
+	loff_t			pos,
+	u64			ino,
+	unsigned		type)
 {
-	struct xfs_mount		*mp;
-	struct xfs_inode		*ip;
-	struct xfs_scrub_dir_ctx	*sdc;
-	struct xfs_name			xname;
-	xfs_ino_t			lookup_ino;
-	xfs_dablk_t			offset;
-	int				error = 0;
-
-	sdc = container_of(dir_iter, struct xfs_scrub_dir_ctx, dir_iter);
+	struct xfs_mount	*mp;
+	struct xfs_inode	*ip;
+	struct xchk_dir_ctx	*sdc;
+	struct xfs_name		xname;
+	xfs_ino_t		lookup_ino;
+	xfs_dablk_t		offset;
+	int			error = 0;
+
+	sdc = container_of(dir_iter, struct xchk_dir_ctx, dir_iter);
 	ip = sdc->sc->ip;
 	mp = ip->i_mount;
 	offset = xfs_dir2_db_to_da(mp->m_dir_geo,
@@ -125,17 +125,17 @@ xfs_scrub_dir_actor(
 
 	/* Does this inode number make sense? */
 	if (!xfs_verify_dir_ino(mp, ino)) {
-		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
 		goto out;
 	}
 
 	if (!strncmp(".", name, namelen)) {
 		/* If this is "." then check that the inum matches the dir. */
 		if (xfs_sb_version_hasftype(&mp->m_sb) && type != DT_DIR)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 		if (ino != ip->i_ino)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 	} else if (!strncmp("..", name, namelen)) {
 		/*
@@ -143,10 +143,10 @@ xfs_scrub_dir_actor(
 		 * matches this dir.
 		 */
 		if (xfs_sb_version_hasftype(&mp->m_sb) && type != DT_DIR)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 		if (ip->i_ino == mp->m_sb.sb_rootino && ino != ip->i_ino)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 	}
 
@@ -156,23 +156,23 @@ xfs_scrub_dir_actor(
 	xname.type = XFS_DIR3_FT_UNKNOWN;
 
 	error = xfs_dir_lookup(sdc->sc->tp, ip, &xname, &lookup_ino, NULL);
-	if (!xfs_scrub_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset,
+	if (!xchk_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset,
 			&error))
 		goto out;
 	if (lookup_ino != ino) {
-		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
 		goto out;
 	}
 
 	/* Verify the file type.  This function absorbs error codes. */
-	error = xfs_scrub_dir_check_ftype(sdc, offset, lookup_ino, type);
+	error = xchk_dir_check_ftype(sdc, offset, lookup_ino, type);
 	if (error)
 		goto out;
 out:
 	/*
 	 * A negative error code returned here is supposed to cause the
 	 * dir_emit caller (xfs_readdir) to abort the directory iteration
-	 * and return zero to xfs_scrub_directory.
+	 * and return zero to xchk_directory.
 	 */
 	if (error == 0 && sdc->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return -EFSCORRUPTED;
@@ -181,8 +181,8 @@ out:
 
 /* Scrub a directory btree record. */
 STATIC int
-xfs_scrub_dir_rec(
-	struct xfs_scrub_da_btree	*ds,
+xchk_dir_rec(
+	struct xchk_da_btree		*ds,
 	int				level,
 	void				*rec)
 {
@@ -203,7 +203,7 @@ xfs_scrub_dir_rec(
 	int				error;
 
 	/* Check the hash of the entry. */
-	error = xfs_scrub_da_btree_hash(ds, level, &ent->hashval);
+	error = xchk_da_btree_hash(ds, level, &ent->hashval);
 	if (error)
 		goto out;
 
@@ -218,18 +218,18 @@ xfs_scrub_dir_rec(
 	rec_bno = xfs_dir2_db_to_da(mp->m_dir_geo, db);
 
 	if (rec_bno >= mp->m_dir_geo->leafblk) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out;
 	}
 	error = xfs_dir3_data_read(ds->dargs.trans, dp, rec_bno, -2, &bp);
-	if (!xfs_scrub_fblock_process_error(ds->sc, XFS_DATA_FORK, rec_bno,
+	if (!xchk_fblock_process_error(ds->sc, XFS_DATA_FORK, rec_bno,
 			&error))
 		goto out;
 	if (!bp) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out;
 	}
-	xfs_scrub_buffer_recheck(ds->sc, bp);
+	xchk_buffer_recheck(ds->sc, bp);
 
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out_relse;
@@ -240,7 +240,7 @@ xfs_scrub_dir_rec(
 	p = (char *)mp->m_dir_inode_ops->data_entry_p(bp->b_addr);
 	endp = xfs_dir3_data_endp(mp->m_dir_geo, bp->b_addr);
 	if (!endp) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out_relse;
 	}
 	while (p < endp) {
@@ -258,7 +258,7 @@ xfs_scrub_dir_rec(
 		p += mp->m_dir_inode_ops->data_entsize(dep->namelen);
 	}
 	if (p >= endp) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out_relse;
 	}
 
@@ -267,14 +267,14 @@ xfs_scrub_dir_rec(
 	hash = be32_to_cpu(ent->hashval);
 	tag = be16_to_cpup(dp->d_ops->data_entry_tag_p(dent));
 	if (!xfs_verify_dir_ino(mp, ino) || tag != off)
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 	if (dent->namelen == 0) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out_relse;
 	}
 	calc_hash = xfs_da_hashname(dent->name, dent->namelen);
 	if (calc_hash != hash)
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 
 out_relse:
 	xfs_trans_brelse(ds->dargs.trans, bp);
@@ -288,8 +288,8 @@ out:
  * shortest, and that there aren't any bogus entries.
  */
 STATIC void
-xfs_scrub_directory_check_free_entry(
-	struct xfs_scrub_context	*sc,
+xchk_directory_check_free_entry(
+	struct xfs_scrub		*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_dir2_data_free	*bf,
 	struct xfs_dir2_data_unused	*dup)
@@ -308,13 +308,13 @@ xfs_scrub_directory_check_free_entry(
 			return;
 
 	/* Unused entry should be in the bestfrees but wasn't found. */
-	xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+	xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 }
 
 /* Check free space info in a directory data block. */
 STATIC int
-xfs_scrub_directory_data_bestfree(
-	struct xfs_scrub_context	*sc,
+xchk_directory_data_bestfree(
+	struct xfs_scrub		*sc,
 	xfs_dablk_t			lblk,
 	bool				is_block)
 {
@@ -339,15 +339,15 @@ xfs_scrub_directory_data_bestfree(
 	if (is_block) {
 		/* dir block format */
 		if (lblk != XFS_B_TO_FSBT(mp, XFS_DIR2_DATA_OFFSET))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		error = xfs_dir3_block_read(sc->tp, sc->ip, &bp);
 	} else {
 		/* dir data format */
 		error = xfs_dir3_data_read(sc->tp, sc->ip, lblk, -1, &bp);
 	}
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, bp);
+	xchk_buffer_recheck(sc, bp);
 
 	/* XXX: Check xfs_dir3_data_hdr.pad is zero once we start setting it. */
 
@@ -362,7 +362,7 @@ xfs_scrub_directory_data_bestfree(
 		if (offset == 0)
 			continue;
 		if (offset >= mp->m_dir_geo->blksize) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 		dup = (struct xfs_dir2_data_unused *)(bp->b_addr + offset);
@@ -372,13 +372,13 @@ xfs_scrub_directory_data_bestfree(
 		if (dup->freetag != cpu_to_be16(XFS_DIR2_DATA_FREE_TAG) ||
 		    be16_to_cpu(dup->length) != be16_to_cpu(dfp->length) ||
 		    tag != ((char *)dup - (char *)bp->b_addr)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 
 		/* bestfree records should be ordered largest to smallest */
 		if (smallest_bestfree < be16_to_cpu(dfp->length)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 
@@ -400,7 +400,7 @@ xfs_scrub_directory_data_bestfree(
 			dep = (struct xfs_dir2_data_entry *)ptr;
 			newlen = d_ops->data_entsize(dep->namelen);
 			if (newlen <= 0) {
-				xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+				xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 						lblk);
 				goto out_buf;
 			}
@@ -411,7 +411,7 @@ xfs_scrub_directory_data_bestfree(
 		/* Spot check this free entry */
 		tag = be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup));
 		if (tag != ((char *)dup - (char *)bp->b_addr)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 
@@ -419,14 +419,14 @@ xfs_scrub_directory_data_bestfree(
 		 * Either this entry is a bestfree or it's smaller than
 		 * any of the bestfrees.
 		 */
-		xfs_scrub_directory_check_free_entry(sc, lblk, bf, dup);
+		xchk_directory_check_free_entry(sc, lblk, bf, dup);
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			goto out_buf;
 
 		/* Move on. */
 		newlen = be16_to_cpu(dup->length);
 		if (newlen <= 0) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 		ptr += newlen;
@@ -436,11 +436,11 @@ xfs_scrub_directory_data_bestfree(
 
 	/* We're required to fill all the space. */
 	if (ptr != endptr)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 
 	/* Did we see at least as many free slots as there are bestfrees? */
 	if (nr_frees < nr_bestfrees)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 out_buf:
 	xfs_trans_brelse(sc->tp, bp);
 out:
@@ -454,8 +454,8 @@ out:
  * array is in order.
  */
 STATIC void
-xfs_scrub_directory_check_freesp(
-	struct xfs_scrub_context	*sc,
+xchk_directory_check_freesp(
+	struct xfs_scrub		*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_buf			*dbp,
 	unsigned int			len)
@@ -465,16 +465,16 @@ xfs_scrub_directory_check_freesp(
 	dfp = sc->ip->d_ops->data_bestfree_p(dbp->b_addr);
 
 	if (len != be16_to_cpu(dfp->length))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 
 	if (len > 0 && be16_to_cpu(dfp->offset) == 0)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 }
 
 /* Check free space info in a directory leaf1 block. */
 STATIC int
-xfs_scrub_directory_leaf1_bestfree(
-	struct xfs_scrub_context	*sc,
+xchk_directory_leaf1_bestfree(
+	struct xfs_scrub		*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
 {
@@ -497,9 +497,9 @@ xfs_scrub_directory_leaf1_bestfree(
 
 	/* Read the free space block. */
 	error = xfs_dir3_leaf_read(sc->tp, sc->ip, lblk, -1, &bp);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, bp);
+	xchk_buffer_recheck(sc, bp);
 
 	leaf = bp->b_addr;
 	d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
@@ -512,7 +512,7 @@ xfs_scrub_directory_leaf1_bestfree(
 		struct xfs_dir3_leaf_hdr	*hdr3 = bp->b_addr;
 
 		if (hdr3->pad != cpu_to_be32(0))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 	}
 
 	/*
@@ -520,19 +520,19 @@ xfs_scrub_directory_leaf1_bestfree(
 	 * blocks that can fit under i_size.
 	 */
 	if (bestcount != xfs_dir2_byte_to_db(geo, sc->ip->i_d.di_size)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
 
 	/* Is the leaf count even remotely sane? */
 	if (leafhdr.count > d_ops->leaf_max_ents(geo)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
 
 	/* Leaves and bests don't overlap in leaf format. */
 	if ((char *)&ents[leafhdr.count] > (char *)bestp) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
 
@@ -540,13 +540,13 @@ xfs_scrub_directory_leaf1_bestfree(
 	for (i = 0; i < leafhdr.count; i++) {
 		hash = be32_to_cpu(ents[i].hashval);
 		if (i > 0 && lasthash > hash)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		lasthash = hash;
 		if (ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
 			stale++;
 	}
 	if (leafhdr.stale != stale)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
@@ -557,10 +557,10 @@ xfs_scrub_directory_leaf1_bestfree(
 			continue;
 		error = xfs_dir3_data_read(sc->tp, sc->ip,
 				i * args->geo->fsbcount, -1, &dbp);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
 				&error))
 			break;
-		xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
+		xchk_directory_check_freesp(sc, lblk, dbp, best);
 		xfs_trans_brelse(sc->tp, dbp);
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			goto out;
@@ -571,8 +571,8 @@ out:
 
 /* Check free space info in a directory freespace block. */
 STATIC int
-xfs_scrub_directory_free_bestfree(
-	struct xfs_scrub_context	*sc,
+xchk_directory_free_bestfree(
+	struct xfs_scrub		*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
 {
@@ -587,15 +587,15 @@ xfs_scrub_directory_free_bestfree(
 
 	/* Read the free space block */
 	error = xfs_dir2_free_read(sc->tp, sc->ip, lblk, &bp);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, bp);
+	xchk_buffer_recheck(sc, bp);
 
 	if (xfs_sb_version_hascrc(&sc->mp->m_sb)) {
 		struct xfs_dir3_free_hdr	*hdr3 = bp->b_addr;
 
 		if (hdr3->pad != cpu_to_be32(0))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 	}
 
 	/* Check all the entries. */
@@ -610,36 +610,36 @@ xfs_scrub_directory_free_bestfree(
 		error = xfs_dir3_data_read(sc->tp, sc->ip,
 				(freehdr.firstdb + i) * args->geo->fsbcount,
 				-1, &dbp);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
 				&error))
 			break;
-		xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
+		xchk_directory_check_freesp(sc, lblk, dbp, best);
 		xfs_trans_brelse(sc->tp, dbp);
 	}
 
 	if (freehdr.nused + stale != freehdr.nvalid)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 out:
 	return error;
 }
 
 /* Check free space information in directories. */
 STATIC int
-xfs_scrub_directory_blocks(
-	struct xfs_scrub_context	*sc)
+xchk_directory_blocks(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_bmbt_irec		got;
-	struct xfs_da_args		args;
-	struct xfs_ifork		*ifp;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_fileoff_t			leaf_lblk;
-	xfs_fileoff_t			free_lblk;
-	xfs_fileoff_t			lblk;
-	struct xfs_iext_cursor		icur;
-	xfs_dablk_t			dabno;
-	bool				found;
-	int				is_block = 0;
-	int				error;
+	struct xfs_bmbt_irec	got;
+	struct xfs_da_args	args;
+	struct xfs_ifork	*ifp;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_fileoff_t		leaf_lblk;
+	xfs_fileoff_t		free_lblk;
+	xfs_fileoff_t		lblk;
+	struct xfs_iext_cursor	icur;
+	xfs_dablk_t		dabno;
+	bool			found;
+	int			is_block = 0;
+	int			error;
 
 	/* Ignore local format directories. */
 	if (sc->ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
@@ -656,7 +656,7 @@ xfs_scrub_directory_blocks(
 	args.geo = mp->m_dir_geo;
 	args.trans = sc->tp;
 	error = xfs_dir2_isblock(&args, &is_block);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
 
 	/* Iterate all the data extents in the directory... */
@@ -666,7 +666,7 @@ xfs_scrub_directory_blocks(
 		if (is_block &&
 		    (got.br_startoff > 0 ||
 		     got.br_blockcount != args.geo->fsbcount)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					got.br_startoff);
 			break;
 		}
@@ -690,7 +690,7 @@ xfs_scrub_directory_blocks(
 				args.geo->fsbcount);
 		     lblk < got.br_startoff + got.br_blockcount;
 		     lblk += args.geo->fsbcount) {
-			error = xfs_scrub_directory_data_bestfree(sc, lblk,
+			error = xchk_directory_data_bestfree(sc, lblk,
 					is_block);
 			if (error)
 				goto out;
@@ -709,10 +709,10 @@ xfs_scrub_directory_blocks(
 	    got.br_blockcount == args.geo->fsbcount &&
 	    !xfs_iext_next_extent(ifp, &icur, &got)) {
 		if (is_block) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out;
 		}
-		error = xfs_scrub_directory_leaf1_bestfree(sc, &args,
+		error = xchk_directory_leaf1_bestfree(sc, &args,
 				leaf_lblk);
 		if (error)
 			goto out;
@@ -731,11 +731,11 @@ xfs_scrub_directory_blocks(
 		 */
 		lblk = got.br_startoff;
 		if (lblk & ~0xFFFFFFFFULL) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out;
 		}
 		if (is_block) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out;
 		}
 
@@ -754,7 +754,7 @@ xfs_scrub_directory_blocks(
 				args.geo->fsbcount);
 		     lblk < got.br_startoff + got.br_blockcount;
 		     lblk += args.geo->fsbcount) {
-			error = xfs_scrub_directory_free_bestfree(sc, &args,
+			error = xchk_directory_free_bestfree(sc, &args,
 					lblk);
 			if (error)
 				goto out;
@@ -769,29 +769,29 @@ out:
 
 /* Scrub a whole directory. */
 int
-xfs_scrub_directory(
-	struct xfs_scrub_context	*sc)
+xchk_directory(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_scrub_dir_ctx	sdc = {
-		.dir_iter.actor = xfs_scrub_dir_actor,
+	struct xchk_dir_ctx	sdc = {
+		.dir_iter.actor = xchk_dir_actor,
 		.dir_iter.pos = 0,
 		.sc = sc,
 	};
-	size_t				bufsize;
-	loff_t				oldpos;
-	int				error = 0;
+	size_t			bufsize;
+	loff_t			oldpos;
+	int			error = 0;
 
 	if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
 		return -ENOENT;
 
 	/* Plausible size? */
 	if (sc->ip->i_d.di_size < xfs_dir2_sf_hdr_size(0)) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		goto out;
 	}
 
 	/* Check directory tree structure */
-	error = xfs_scrub_da_btree(sc, XFS_DATA_FORK, xfs_scrub_dir_rec, NULL);
+	error = xchk_da_btree(sc, XFS_DATA_FORK, xchk_dir_rec, NULL);
 	if (error)
 		return error;
 
@@ -799,7 +799,7 @@ xfs_scrub_directory(
 		return error;
 
 	/* Check the freespace. */
-	error = xfs_scrub_directory_blocks(sc);
+	error = xchk_directory_blocks(sc);
 	if (error)
 		return error;
 
@@ -816,7 +816,7 @@ xfs_scrub_directory(
 	/*
 	 * Look up every name in this directory by hash.
 	 *
-	 * Use the xfs_readdir function to call xfs_scrub_dir_actor on
+	 * Use the xfs_readdir function to call xchk_dir_actor on
 	 * every directory entry in this directory.  In _actor, we check
 	 * the name, inode number, and ftype (if applicable) of the
 	 * entry.  xfs_readdir uses the VFS filldir functions to provide
@@ -834,7 +834,7 @@ xfs_scrub_directory(
 	xfs_iunlock(sc->ip, XFS_ILOCK_EXCL);
 	while (true) {
 		error = xfs_readdir(sc->tp, sc->ip, &sdc.dir_iter, bufsize);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0,
 				&error))
 			goto out;
 		if (oldpos == sdc.dir_iter.pos)
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 13d43d108574..224dba937492 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -35,11 +35,11 @@
  * try again after forcing logged inode cores out to disk.
  */
 int
-xfs_scrub_setup_ag_iallocbt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_ag_iallocbt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, sc->try_harder);
+	return xchk_setup_ag_btree(sc, ip, sc->try_harder);
 }
 
 /* Inode btree scrubber. */
@@ -50,8 +50,8 @@ xfs_scrub_setup_ag_iallocbt(
  * we have a record or not depending on freecount.
  */
 static inline void
-xfs_scrub_iallocbt_chunk_xref_other(
-	struct xfs_scrub_context	*sc,
+xchk_iallocbt_chunk_xref_other(
+	struct xfs_scrub		*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino)
 {
@@ -66,17 +66,17 @@ xfs_scrub_iallocbt_chunk_xref_other(
 	if (!(*pcur))
 		return;
 	error = xfs_ialloc_has_inode_record(*pcur, agino, agino, &has_irec);
-	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
+	if (!xchk_should_check_xref(sc, &error, pcur))
 		return;
 	if (((irec->ir_freecount > 0 && !has_irec) ||
 	     (irec->ir_freecount == 0 && has_irec)))
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_iallocbt_chunk_xref(
-	struct xfs_scrub_context	*sc,
+xchk_iallocbt_chunk_xref(
+	struct xfs_scrub		*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino,
 	xfs_agblock_t			agbno,
@@ -87,17 +87,17 @@ xfs_scrub_iallocbt_chunk_xref(
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, len);
-	xfs_scrub_iallocbt_chunk_xref_other(sc, irec, agino);
+	xchk_xref_is_used_space(sc, agbno, len);
+	xchk_iallocbt_chunk_xref_other(sc, irec, agino);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
-	xfs_scrub_xref_is_owned_by(sc, agbno, len, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, len);
+	xchk_xref_is_owned_by(sc, agbno, len, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, len);
 }
 
 /* Is this chunk worth checking? */
 STATIC bool
-xfs_scrub_iallocbt_chunk(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_chunk(
+	struct xchk_btree		*bs,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino,
 	xfs_extlen_t			len)
@@ -110,16 +110,16 @@ xfs_scrub_iallocbt_chunk(
 	if (bno + len <= bno ||
 	    !xfs_verify_agbno(mp, agno, bno) ||
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xfs_scrub_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);
+	xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);
 
 	return true;
 }
 
 /* Count the number of free inodes. */
 static unsigned int
-xfs_scrub_iallocbt_freecount(
+xchk_iallocbt_freecount(
 	xfs_inofree_t			freemask)
 {
 	BUILD_BUG_ON(sizeof(freemask) != sizeof(__u64));
@@ -128,8 +128,8 @@ xfs_scrub_iallocbt_freecount(
 
 /* Check a particular inode with ir_free. */
 STATIC int
-xfs_scrub_iallocbt_check_cluster_freemask(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_check_cluster_freemask(
+	struct xchk_btree		*bs,
 	xfs_ino_t			fsino,
 	xfs_agino_t			chunkino,
 	xfs_agino_t			clusterino,
@@ -143,14 +143,14 @@ xfs_scrub_iallocbt_check_cluster_freemask(
 	bool				inuse;
 	int				error = 0;
 
-	if (xfs_scrub_should_terminate(bs->sc, &error))
+	if (xchk_should_terminate(bs->sc, &error))
 		return error;
 
 	dip = xfs_buf_offset(bp, clusterino * mp->m_sb.sb_inodesize);
 	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
 	    (dip->di_version >= 3 &&
 	     be64_to_cpu(dip->di_ino) != fsino + clusterino)) {
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		goto out;
 	}
 
@@ -175,15 +175,15 @@ xfs_scrub_iallocbt_check_cluster_freemask(
 		freemask_ok = inode_is_free ^ inuse;
 	}
 	if (!freemask_ok)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 out:
 	return 0;
 }
 
 /* Make sure the free mask is consistent with what the inodes think. */
 STATIC int
-xfs_scrub_iallocbt_check_freemask(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_check_freemask(
+	struct xchk_btree		*bs,
 	struct xfs_inobt_rec_incore	*irec)
 {
 	struct xfs_owner_info		oinfo;
@@ -223,18 +223,18 @@ xfs_scrub_iallocbt_check_freemask(
 		/* The whole cluster must be a hole or not a hole. */
 		ir_holemask = (irec->ir_holemask & holemask);
 		if (ir_holemask != holemask && ir_holemask != 0) {
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 			continue;
 		}
 
 		/* If any part of this is a hole, skip it. */
 		if (ir_holemask) {
-			xfs_scrub_xref_is_not_owned_by(bs->sc, agbno,
+			xchk_xref_is_not_owned_by(bs->sc, agbno,
 					blks_per_cluster, &oinfo);
 			continue;
 		}
 
-		xfs_scrub_xref_is_owned_by(bs->sc, agbno, blks_per_cluster,
+		xchk_xref_is_owned_by(bs->sc, agbno, blks_per_cluster,
 				&oinfo);
 
 		/* Grab the inode cluster buffer. */
@@ -245,13 +245,13 @@ xfs_scrub_iallocbt_check_freemask(
 
 		error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap,
 				&dip, &bp, 0, 0);
-		if (!xfs_scrub_btree_xref_process_error(bs->sc, bs->cur, 0,
+		if (!xchk_btree_xref_process_error(bs->sc, bs->cur, 0,
 				&error))
 			continue;
 
 		/* Which inodes are free? */
 		for (clusterino = 0; clusterino < nr_inodes; clusterino++) {
-			error = xfs_scrub_iallocbt_check_cluster_freemask(bs,
+			error = xchk_iallocbt_check_cluster_freemask(bs,
 					fsino, chunkino, clusterino, irec, bp);
 			if (error) {
 				xfs_trans_brelse(bs->cur->bc_tp, bp);
@@ -267,8 +267,8 @@ xfs_scrub_iallocbt_check_freemask(
 
 /* Scrub an inobt/finobt record. */
 STATIC int
-xfs_scrub_iallocbt_rec(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_rec(
+	struct xchk_btree		*bs,
 	union xfs_btree_rec		*rec)
 {
 	struct xfs_mount		*mp = bs->cur->bc_mp;
@@ -289,18 +289,18 @@ xfs_scrub_iallocbt_rec(
 
 	if (irec.ir_count > XFS_INODES_PER_CHUNK ||
 	    irec.ir_freecount > XFS_INODES_PER_CHUNK)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	real_freecount = irec.ir_freecount +
 			(XFS_INODES_PER_CHUNK - irec.ir_count);
-	if (real_freecount != xfs_scrub_iallocbt_freecount(irec.ir_free))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+	if (real_freecount != xchk_iallocbt_freecount(irec.ir_free))
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	agino = irec.ir_startino;
 	/* Record has to be properly aligned within the AG. */
 	if (!xfs_verify_agino(mp, agno, agino) ||
 	    !xfs_verify_agino(mp, agno, agino + XFS_INODES_PER_CHUNK - 1)) {
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		goto out;
 	}
 
@@ -308,7 +308,7 @@ xfs_scrub_iallocbt_rec(
 	agbno = XFS_AGINO_TO_AGBNO(mp, irec.ir_startino);
 	if ((agbno & (xfs_ialloc_cluster_alignment(mp) - 1)) ||
 	    (agbno & (xfs_icluster_size_fsb(mp) - 1)))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	*inode_blocks += XFS_B_TO_FSB(mp,
 			irec.ir_count * mp->m_sb.sb_inodesize);
@@ -318,9 +318,9 @@ xfs_scrub_iallocbt_rec(
 		len = XFS_B_TO_FSB(mp,
 				XFS_INODES_PER_CHUNK * mp->m_sb.sb_inodesize);
 		if (irec.ir_count != XFS_INODES_PER_CHUNK)
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-		if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
+		if (!xchk_iallocbt_chunk(bs, &irec, agino, len))
 			goto out;
 		goto check_freemask;
 	}
@@ -333,12 +333,12 @@ xfs_scrub_iallocbt_rec(
 	holes = ~xfs_inobt_irec_to_allocmask(&irec);
 	if ((holes & irec.ir_free) != holes ||
 	    irec.ir_freecount > irec.ir_count)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; i++) {
 		if (holemask & 1)
 			holecount += XFS_INODES_PER_HOLEMASK_BIT;
-		else if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
+		else if (!xchk_iallocbt_chunk(bs, &irec, agino, len))
 			break;
 		holemask >>= 1;
 		agino += XFS_INODES_PER_HOLEMASK_BIT;
@@ -346,10 +346,10 @@ xfs_scrub_iallocbt_rec(
 
 	if (holecount > XFS_INODES_PER_CHUNK ||
 	    holecount + irec.ir_count != XFS_INODES_PER_CHUNK)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 check_freemask:
-	error = xfs_scrub_iallocbt_check_freemask(bs, &irec);
+	error = xchk_iallocbt_check_freemask(bs, &irec);
 	if (error)
 		goto out;
 
@@ -362,39 +362,39 @@ out:
  * Don't bother if we're missing btree cursors, as we're already corrupt.
  */
 STATIC void
-xfs_scrub_iallocbt_xref_rmap_btreeblks(
-	struct xfs_scrub_context	*sc,
-	int				which)
+xchk_iallocbt_xref_rmap_btreeblks(
+	struct xfs_scrub	*sc,
+	int			which)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_filblks_t			blocks;
-	xfs_extlen_t			inobt_blocks = 0;
-	xfs_extlen_t			finobt_blocks = 0;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_filblks_t		blocks;
+	xfs_extlen_t		inobt_blocks = 0;
+	xfs_extlen_t		finobt_blocks = 0;
+	int			error;
 
 	if (!sc->sa.ino_cur || !sc->sa.rmap_cur ||
 	    (xfs_sb_version_hasfinobt(&sc->mp->m_sb) && !sc->sa.fino_cur) ||
-	    xfs_scrub_skip_xref(sc->sm))
+	    xchk_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many inobt blocks as the rmap says. */
 	error = xfs_btree_count_blocks(sc->sa.ino_cur, &inobt_blocks);
-	if (!xfs_scrub_process_error(sc, 0, 0, &error))
+	if (!xchk_process_error(sc, 0, 0, &error))
 		return;
 
 	if (sc->sa.fino_cur) {
 		error = xfs_btree_count_blocks(sc->sa.fino_cur, &finobt_blocks);
-		if (!xfs_scrub_process_error(sc, 0, 0, &error))
+		if (!xchk_process_error(sc, 0, 0, &error))
 			return;
 	}
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != inobt_blocks + finobt_blocks)
-		xfs_scrub_btree_set_corrupt(sc, sc->sa.ino_cur, 0);
+		xchk_btree_set_corrupt(sc, sc->sa.ino_cur, 0);
 }
 
 /*
@@ -402,47 +402,47 @@ xfs_scrub_iallocbt_xref_rmap_btreeblks(
  * the rmap says are owned by inodes.
  */
 STATIC void
-xfs_scrub_iallocbt_xref_rmap_inodes(
-	struct xfs_scrub_context	*sc,
-	int				which,
-	xfs_filblks_t			inode_blocks)
+xchk_iallocbt_xref_rmap_inodes(
+	struct xfs_scrub	*sc,
+	int			which,
+	xfs_filblks_t		inode_blocks)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_filblks_t			blocks;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_filblks_t		blocks;
+	int			error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many inode blocks as the rmap knows about. */
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != inode_blocks)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* Scrub the inode btrees for some AG. */
 STATIC int
-xfs_scrub_iallocbt(
-	struct xfs_scrub_context	*sc,
-	xfs_btnum_t			which)
+xchk_iallocbt(
+	struct xfs_scrub	*sc,
+	xfs_btnum_t		which)
 {
-	struct xfs_btree_cur		*cur;
-	struct xfs_owner_info		oinfo;
-	xfs_filblks_t			inode_blocks = 0;
-	int				error;
+	struct xfs_btree_cur	*cur;
+	struct xfs_owner_info	oinfo;
+	xfs_filblks_t		inode_blocks = 0;
+	int			error;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
 	cur = which == XFS_BTNUM_INO ? sc->sa.ino_cur : sc->sa.fino_cur;
-	error = xfs_scrub_btree(sc, cur, xfs_scrub_iallocbt_rec, &oinfo,
+	error = xchk_btree(sc, cur, xchk_iallocbt_rec, &oinfo,
 			&inode_blocks);
 	if (error)
 		return error;
 
-	xfs_scrub_iallocbt_xref_rmap_btreeblks(sc, which);
+	xchk_iallocbt_xref_rmap_btreeblks(sc, which);
 
 	/*
 	 * If we're scrubbing the inode btree, inode_blocks is the number of
@@ -452,64 +452,64 @@ xfs_scrub_iallocbt(
 	 * to inode chunks with free inodes.
 	 */
 	if (which == XFS_BTNUM_INO)
-		xfs_scrub_iallocbt_xref_rmap_inodes(sc, which, inode_blocks);
+		xchk_iallocbt_xref_rmap_inodes(sc, which, inode_blocks);
 
 	return error;
 }
 
 int
-xfs_scrub_inobt(
-	struct xfs_scrub_context	*sc)
+xchk_inobt(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_iallocbt(sc, XFS_BTNUM_INO);
+	return xchk_iallocbt(sc, XFS_BTNUM_INO);
 }
 
 int
-xfs_scrub_finobt(
-	struct xfs_scrub_context	*sc)
+xchk_finobt(
+	struct xfs_scrub	*sc)
 {
-	return xfs_scrub_iallocbt(sc, XFS_BTNUM_FINO);
+	return xchk_iallocbt(sc, XFS_BTNUM_FINO);
 }
 
 /* See if an inode btree has (or doesn't have) an inode chunk record. */
 static inline void
-xfs_scrub_xref_inode_check(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len,
-	struct xfs_btree_cur		**icur,
-	bool				should_have_inodes)
+xchk_xref_inode_check(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len,
+	struct xfs_btree_cur	**icur,
+	bool			should_have_inodes)
 {
-	bool				has_inodes;
-	int				error;
+	bool			has_inodes;
+	int			error;
 
-	if (!(*icur) || xfs_scrub_skip_xref(sc->sm))
+	if (!(*icur) || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_ialloc_has_inodes_at_extent(*icur, agbno, len, &has_inodes);
-	if (!xfs_scrub_should_check_xref(sc, &error, icur))
+	if (!xchk_should_check_xref(sc, &error, icur))
 		return;
 	if (has_inodes != should_have_inodes)
-		xfs_scrub_btree_xref_set_corrupt(sc, *icur, 0);
+		xchk_btree_xref_set_corrupt(sc, *icur, 0);
 }
 
 /* xref check that the extent is not covered by inodes */
 void
-xfs_scrub_xref_is_not_inode_chunk(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_xref_is_not_inode_chunk(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, false);
-	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, false);
+	xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, false);
+	xchk_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, false);
 }
 
 /* xref check that the extent is covered by inodes */
 void
-xfs_scrub_xref_is_inode_chunk(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_xref_is_inode_chunk(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, true);
+	xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, true);
 }
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 7a6208505980..5b3b177c0fc9 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -37,23 +37,23 @@
  * the goal.
  */
 int
-xfs_scrub_setup_inode(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_inode(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	int				error;
+	int			error;
 
 	/*
 	 * Try to get the inode.  If the verifiers fail, we try again
 	 * in raw mode.
 	 */
-	error = xfs_scrub_get_inode(sc, ip);
+	error = xchk_get_inode(sc, ip);
 	switch (error) {
 	case 0:
 		break;
 	case -EFSCORRUPTED:
 	case -EFSBADCRC:
-		return xfs_scrub_trans_alloc(sc, 0);
+		return xchk_trans_alloc(sc, 0);
 	default:
 		return error;
 	}
@@ -61,7 +61,7 @@ xfs_scrub_setup_inode(
 	/* Got the inode, lock it and we're ready to go. */
 	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	error = xfs_scrub_trans_alloc(sc, 0);
+	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -76,19 +76,19 @@ out:
 
 /* Validate di_extsize hint. */
 STATIC void
-xfs_scrub_inode_extsize(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags)
+xchk_inode_extsize(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags)
 {
-	xfs_failaddr_t			fa;
+	xfs_failaddr_t		fa;
 
 	fa = xfs_inode_validate_extsize(sc->mp, be32_to_cpu(dip->di_extsize),
 			mode, flags);
 	if (fa)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 }
 
 /*
@@ -98,33 +98,33 @@ xfs_scrub_inode_extsize(
  * These functions must be kept in sync with each other.
  */
 STATIC void
-xfs_scrub_inode_cowextsize(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags,
-	uint64_t			flags2)
+xchk_inode_cowextsize(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags,
+	uint64_t		flags2)
 {
-	xfs_failaddr_t			fa;
+	xfs_failaddr_t		fa;
 
 	fa = xfs_inode_validate_cowextsize(sc->mp,
 			be32_to_cpu(dip->di_cowextsize), mode, flags,
 			flags2);
 	if (fa)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Make sure the di_flags make sense for the inode. */
 STATIC void
-xfs_scrub_inode_flags(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags)
+xchk_inode_flags(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags)
 {
-	struct xfs_mount		*mp = sc->mp;
+	struct xfs_mount	*mp = sc->mp;
 
 	if (flags & ~XFS_DIFLAG_ANY)
 		goto bad;
@@ -157,20 +157,20 @@ xfs_scrub_inode_flags(
 
 	return;
 bad:
-	xfs_scrub_ino_set_corrupt(sc, ino);
+	xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Make sure the di_flags2 make sense for the inode. */
 STATIC void
-xfs_scrub_inode_flags2(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags,
-	uint64_t			flags2)
+xchk_inode_flags2(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags,
+	uint64_t		flags2)
 {
-	struct xfs_mount		*mp = sc->mp;
+	struct xfs_mount	*mp = sc->mp;
 
 	if (flags2 & ~XFS_DIFLAG2_ANY)
 		goto bad;
@@ -200,23 +200,23 @@ xfs_scrub_inode_flags2(
 
 	return;
 bad:
-	xfs_scrub_ino_set_corrupt(sc, ino);
+	xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Scrub all the ondisk inode fields. */
 STATIC void
-xfs_scrub_dinode(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino)
+xchk_dinode(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino)
 {
-	struct xfs_mount		*mp = sc->mp;
-	size_t				fork_recs;
-	unsigned long long		isize;
-	uint64_t			flags2;
-	uint32_t			nextents;
-	uint16_t			flags;
-	uint16_t			mode;
+	struct xfs_mount	*mp = sc->mp;
+	size_t			fork_recs;
+	unsigned long long	isize;
+	uint64_t		flags2;
+	uint32_t		nextents;
+	uint16_t		flags;
+	uint16_t		mode;
 
 	flags = be16_to_cpu(dip->di_flags);
 	if (dip->di_version >= 3)
@@ -237,7 +237,7 @@ xfs_scrub_dinode(
 		/* mode is recognized */
 		break;
 	default:
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 		break;
 	}
 
@@ -248,22 +248,22 @@ xfs_scrub_dinode(
 		 * We autoconvert v1 inodes into v2 inodes on writeout,
 		 * so just mark this inode for preening.
 		 */
-		xfs_scrub_ino_set_preen(sc, ino);
+		xchk_ino_set_preen(sc, ino);
 		break;
 	case 2:
 	case 3:
 		if (dip->di_onlink != 0)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 
 		if (dip->di_mode == 0 && sc->ip)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 
 		if (dip->di_projid_hi != 0 &&
 		    !xfs_sb_version_hasprojid32bit(&mp->m_sb))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	default:
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 		return;
 	}
 
@@ -273,40 +273,40 @@ xfs_scrub_dinode(
 	 */
 	if (dip->di_uid == cpu_to_be32(-1U) ||
 	    dip->di_gid == cpu_to_be32(-1U))
-		xfs_scrub_ino_set_warning(sc, ino);
+		xchk_ino_set_warning(sc, ino);
 
 	/* di_format */
 	switch (dip->di_format) {
 	case XFS_DINODE_FMT_DEV:
 		if (!S_ISCHR(mode) && !S_ISBLK(mode) &&
 		    !S_ISFIFO(mode) && !S_ISSOCK(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_LOCAL:
 		if (!S_ISDIR(mode) && !S_ISLNK(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
 		if (!S_ISREG(mode) && !S_ISDIR(mode) && !S_ISLNK(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (!S_ISREG(mode) && !S_ISDIR(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_UUID:
 	default:
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 		break;
 	}
 
 	/* di_[amc]time.nsec */
 	if (be32_to_cpu(dip->di_atime.t_nsec) >= NSEC_PER_SEC)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (be32_to_cpu(dip->di_mtime.t_nsec) >= NSEC_PER_SEC)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (be32_to_cpu(dip->di_ctime.t_nsec) >= NSEC_PER_SEC)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/*
 	 * di_size.  xfs_dinode_verify checks for things that screw up
@@ -315,19 +315,19 @@ xfs_scrub_dinode(
 	 */
 	isize = be64_to_cpu(dip->di_size);
 	if (isize & (1ULL << 63))
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* Devices, fifos, and sockets must have zero size */
 	if (!S_ISDIR(mode) && !S_ISREG(mode) && !S_ISLNK(mode) && isize != 0)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* Directories can't be larger than the data section size (32G) */
 	if (S_ISDIR(mode) && (isize == 0 || isize >= XFS_DIR2_SPACE_SIZE))
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* Symlinks can't be larger than SYMLINK_MAXLEN */
 	if (S_ISLNK(mode) && (isize == 0 || isize >= XFS_SYMLINK_MAXLEN))
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/*
 	 * Warn if the running kernel can't handle the kinds of offsets
@@ -336,7 +336,7 @@ xfs_scrub_dinode(
 	 * overly large offsets, flag the inode for admin review.
 	 */
 	if (isize >= mp->m_super->s_maxbytes)
-		xfs_scrub_ino_set_warning(sc, ino);
+		xchk_ino_set_warning(sc, ino);
 
 	/* di_nblocks */
 	if (flags2 & XFS_DIFLAG2_REFLINK) {
@@ -351,15 +351,15 @@ xfs_scrub_dinode(
 		 */
 		if (be64_to_cpu(dip->di_nblocks) >=
 		    mp->m_sb.sb_dblocks + mp->m_sb.sb_rblocks)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 	} else {
 		if (be64_to_cpu(dip->di_nblocks) >= mp->m_sb.sb_dblocks)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 	}
 
-	xfs_scrub_inode_flags(sc, dip, ino, mode, flags);
+	xchk_inode_flags(sc, dip, ino, mode, flags);
 
-	xfs_scrub_inode_extsize(sc, dip, ino, mode, flags);
+	xchk_inode_extsize(sc, dip, ino, mode, flags);
 
 	/* di_nextents */
 	nextents = be32_to_cpu(dip->di_nextents);
@@ -367,31 +367,31 @@ xfs_scrub_dinode(
 	switch (dip->di_format) {
 	case XFS_DINODE_FMT_EXTENTS:
 		if (nextents > fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (nextents <= fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	default:
 		if (nextents != 0)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	}
 
 	/* di_forkoff */
 	if (XFS_DFORK_APTR(dip) >= (char *)dip + mp->m_sb.sb_inodesize)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (dip->di_anextents != 0 && dip->di_forkoff == 0)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (dip->di_forkoff == 0 && dip->di_aformat != XFS_DINODE_FMT_EXTENTS)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* di_aformat */
 	if (dip->di_aformat != XFS_DINODE_FMT_LOCAL &&
 	    dip->di_aformat != XFS_DINODE_FMT_EXTENTS &&
 	    dip->di_aformat != XFS_DINODE_FMT_BTREE)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* di_anextents */
 	nextents = be16_to_cpu(dip->di_anextents);
@@ -399,22 +399,22 @@ xfs_scrub_dinode(
 	switch (dip->di_aformat) {
 	case XFS_DINODE_FMT_EXTENTS:
 		if (nextents > fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (nextents <= fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	default:
 		if (nextents != 0)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 	}
 
 	if (dip->di_version >= 3) {
 		if (be32_to_cpu(dip->di_crtime.t_nsec) >= NSEC_PER_SEC)
-			xfs_scrub_ino_set_corrupt(sc, ino);
-		xfs_scrub_inode_flags2(sc, dip, ino, mode, flags, flags2);
-		xfs_scrub_inode_cowextsize(sc, dip, ino, mode, flags,
+			xchk_ino_set_corrupt(sc, ino);
+		xchk_inode_flags2(sc, dip, ino, mode, flags, flags2);
+		xchk_inode_cowextsize(sc, dip, ino, mode, flags,
 				flags2);
 	}
 }
@@ -425,8 +425,8 @@ xfs_scrub_dinode(
  * IGET_UNTRUSTED, which checks the inobt for us.
  */
 static void
-xfs_scrub_inode_xref_finobt(
-	struct xfs_scrub_context	*sc,
+xchk_inode_xref_finobt(
+	struct xfs_scrub		*sc,
 	xfs_ino_t			ino)
 {
 	struct xfs_inobt_rec_incore	rec;
@@ -434,7 +434,7 @@ xfs_scrub_inode_xref_finobt(
 	int				has_record;
 	int				error;
 
-	if (!sc->sa.fino_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.fino_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	agino = XFS_INO_TO_AGINO(sc->mp, ino);
@@ -445,12 +445,12 @@ xfs_scrub_inode_xref_finobt(
 	 */
 	error = xfs_inobt_lookup(sc->sa.fino_cur, agino, XFS_LOOKUP_LE,
 			&has_record);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
 	    !has_record)
 		return;
 
 	error = xfs_inobt_get_rec(sc->sa.fino_cur, &rec, &has_record);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
 	    !has_record)
 		return;
 
@@ -463,54 +463,54 @@ xfs_scrub_inode_xref_finobt(
 		return;
 
 	if (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino))
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.fino_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.fino_cur, 0);
 }
 
 /* Cross reference the inode fields with the forks. */
 STATIC void
-xfs_scrub_inode_xref_bmap(
-	struct xfs_scrub_context	*sc,
-	struct xfs_dinode		*dip)
+xchk_inode_xref_bmap(
+	struct xfs_scrub	*sc,
+	struct xfs_dinode	*dip)
 {
-	xfs_extnum_t			nextents;
-	xfs_filblks_t			count;
-	xfs_filblks_t			acount;
-	int				error;
+	xfs_extnum_t		nextents;
+	xfs_filblks_t		count;
+	xfs_filblks_t		acount;
+	int			error;
 
-	if (xfs_scrub_skip_xref(sc->sm))
+	if (xchk_skip_xref(sc->sm))
 		return;
 
 	/* Walk all the extents to check nextents/naextents/nblocks. */
 	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
 			&nextents, &count);
-	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
+	if (!xchk_should_check_xref(sc, &error, NULL))
 		return;
 	if (nextents < be32_to_cpu(dip->di_nextents))
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 
 	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
 			&nextents, &acount);
-	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
+	if (!xchk_should_check_xref(sc, &error, NULL))
 		return;
 	if (nextents != be16_to_cpu(dip->di_anextents))
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 
 	/* Check nblocks against the inode. */
 	if (count + acount != be64_to_cpu(dip->di_nblocks))
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_inode_xref(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino,
-	struct xfs_dinode		*dip)
+xchk_inode_xref(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino,
+	struct xfs_dinode	*dip)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -518,18 +518,18 @@ xfs_scrub_inode_xref(
 	agno = XFS_INO_TO_AGNO(sc->mp, ino);
 	agbno = XFS_INO_TO_AGBNO(sc->mp, ino);
 
-	error = xfs_scrub_ag_init(sc, agno, &sc->sa);
-	if (!xfs_scrub_xref_process_error(sc, agno, agbno, &error))
+	error = xchk_ag_init(sc, agno, &sc->sa);
+	if (!xchk_xref_process_error(sc, agno, agbno, &error))
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_inode_xref_finobt(sc, ino);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_inode_xref_finobt(sc, ino);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
-	xfs_scrub_inode_xref_bmap(sc, dip);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
+	xchk_inode_xref_bmap(sc, dip);
 
-	xfs_scrub_ag_free(sc, &sc->sa);
+	xchk_ag_free(sc, &sc->sa);
 }
 
 /*
@@ -539,35 +539,35 @@ xfs_scrub_inode_xref(
  * reflink filesystem.
  */
 static void
-xfs_scrub_inode_check_reflink_iflag(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			ino)
+xchk_inode_check_reflink_iflag(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		ino)
 {
-	struct xfs_mount		*mp = sc->mp;
-	bool				has_shared;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	bool			has_shared;
+	int			error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return;
 
 	error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
 			&has_shared);
-	if (!xfs_scrub_xref_process_error(sc, XFS_INO_TO_AGNO(mp, ino),
+	if (!xchk_xref_process_error(sc, XFS_INO_TO_AGNO(mp, ino),
 			XFS_INO_TO_AGBNO(mp, ino), &error))
 		return;
 	if (xfs_is_reflink_inode(sc->ip) && !has_shared)
-		xfs_scrub_ino_set_preen(sc, ino);
+		xchk_ino_set_preen(sc, ino);
 	else if (!xfs_is_reflink_inode(sc->ip) && has_shared)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Scrub an inode. */
 int
-xfs_scrub_inode(
-	struct xfs_scrub_context	*sc)
+xchk_inode(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_dinode		di;
-	int				error = 0;
+	struct xfs_dinode	di;
+	int			error = 0;
 
 	/*
 	 * If sc->ip is NULL, that means that the setup function called
@@ -575,13 +575,13 @@ xfs_scrub_inode(
 	 * and a NULL inode, so flag the corruption error and return.
 	 */
 	if (!sc->ip) {
-		xfs_scrub_ino_set_corrupt(sc, sc->sm->sm_ino);
+		xchk_ino_set_corrupt(sc, sc->sm->sm_ino);
 		return 0;
 	}
 
 	/* Scrub the inode core. */
 	xfs_inode_to_disk(sc->ip, &di, 0);
-	xfs_scrub_dinode(sc, &di, sc->ip->i_ino);
+	xchk_dinode(sc, &di, sc->ip->i_ino);
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
@@ -591,9 +591,9 @@ xfs_scrub_inode(
 	 * we scrubbed the dinode.
 	 */
 	if (S_ISREG(VFS_I(sc->ip)->i_mode))
-		xfs_scrub_inode_check_reflink_iflag(sc, sc->ip->i_ino);
+		xchk_inode_check_reflink_iflag(sc, sc->ip->i_ino);
 
-	xfs_scrub_inode_xref(sc, sc->ip->i_ino, &di);
+	xchk_inode_xref(sc, sc->ip->i_ino, &di);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index e2bda58c32f0..1c9d7c7f64f5 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -27,36 +27,36 @@
 
 /* Set us up to scrub parents. */
 int
-xfs_scrub_setup_parent(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_parent(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Parent pointers */
 
 /* Look for an entry in a parent pointing to this inode. */
 
-struct xfs_scrub_parent_ctx {
-	struct dir_context		dc;
-	xfs_ino_t			ino;
-	xfs_nlink_t			nlink;
+struct xchk_parent_ctx {
+	struct dir_context	dc;
+	xfs_ino_t		ino;
+	xfs_nlink_t		nlink;
 };
 
 /* Look for a single entry in a directory pointing to an inode. */
 STATIC int
-xfs_scrub_parent_actor(
-	struct dir_context		*dc,
-	const char			*name,
-	int				namelen,
-	loff_t				pos,
-	u64				ino,
-	unsigned			type)
+xchk_parent_actor(
+	struct dir_context	*dc,
+	const char		*name,
+	int			namelen,
+	loff_t			pos,
+	u64			ino,
+	unsigned		type)
 {
-	struct xfs_scrub_parent_ctx	*spc;
+	struct xchk_parent_ctx	*spc;
 
-	spc = container_of(dc, struct xfs_scrub_parent_ctx, dc);
+	spc = container_of(dc, struct xchk_parent_ctx, dc);
 	if (spc->ino == ino)
 		spc->nlink++;
 	return 0;
@@ -64,21 +64,21 @@ xfs_scrub_parent_actor(
 
 /* Count the number of dentries in the parent dir that point to this inode. */
 STATIC int
-xfs_scrub_parent_count_parent_dentries(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*parent,
-	xfs_nlink_t			*nlink)
+xchk_parent_count_parent_dentries(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*parent,
+	xfs_nlink_t		*nlink)
 {
-	struct xfs_scrub_parent_ctx	spc = {
-		.dc.actor = xfs_scrub_parent_actor,
+	struct xchk_parent_ctx	spc = {
+		.dc.actor = xchk_parent_actor,
 		.dc.pos = 0,
 		.ino = sc->ip->i_ino,
 		.nlink = 0,
 	};
-	size_t				bufsize;
-	loff_t				oldpos;
-	uint				lock_mode;
-	int				error = 0;
+	size_t			bufsize;
+	loff_t			oldpos;
+	uint			lock_mode;
+	int			error = 0;
 
 	/*
 	 * If there are any blocks, read-ahead block 0 as we're almost
@@ -120,16 +120,16 @@ out:
  * entry pointing back to the inode being scrubbed.
  */
 STATIC int
-xfs_scrub_parent_validate(
-	struct xfs_scrub_context	*sc,
-	xfs_ino_t			dnum,
-	bool				*try_again)
+xchk_parent_validate(
+	struct xfs_scrub	*sc,
+	xfs_ino_t		dnum,
+	bool			*try_again)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*dp = NULL;
-	xfs_nlink_t			expected_nlink;
-	xfs_nlink_t			nlink;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*dp = NULL;
+	xfs_nlink_t		expected_nlink;
+	xfs_nlink_t		nlink;
+	int			error = 0;
 
 	*try_again = false;
 
@@ -138,7 +138,7 @@ xfs_scrub_parent_validate(
 
 	/* '..' must not point to ourselves. */
 	if (sc->ip->i_ino == dnum) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -165,13 +165,13 @@ xfs_scrub_parent_validate(
 	error = xfs_iget(mp, sc->tp, dnum, XFS_IGET_UNTRUSTED, 0, &dp);
 	if (error == -EINVAL) {
 		error = -EFSCORRUPTED;
-		xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error);
+		xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error);
 		goto out;
 	}
-	if (!xfs_scrub_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 	if (dp == sc->ip || !S_ISDIR(VFS_I(dp)->i_mode)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out_rele;
 	}
 
@@ -183,12 +183,12 @@ xfs_scrub_parent_validate(
 	 * the child inodes.
 	 */
 	if (xfs_ilock_nowait(dp, XFS_IOLOCK_SHARED)) {
-		error = xfs_scrub_parent_count_parent_dentries(sc, dp, &nlink);
-		if (!xfs_scrub_fblock_xref_process_error(sc, XFS_DATA_FORK, 0,
+		error = xchk_parent_count_parent_dentries(sc, dp, &nlink);
+		if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0,
 				&error))
 			goto out_unlock;
 		if (nlink != expected_nlink)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out_unlock;
 	}
 
@@ -200,18 +200,18 @@ xfs_scrub_parent_validate(
 	 */
 	xfs_iunlock(sc->ip, sc->ilock_flags);
 	sc->ilock_flags = 0;
-	error = xfs_scrub_ilock_inverted(dp, XFS_IOLOCK_SHARED);
+	error = xchk_ilock_inverted(dp, XFS_IOLOCK_SHARED);
 	if (error)
 		goto out_rele;
 
 	/* Go looking for our dentry. */
-	error = xfs_scrub_parent_count_parent_dentries(sc, dp, &nlink);
-	if (!xfs_scrub_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
+	error = xchk_parent_count_parent_dentries(sc, dp, &nlink);
+	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out_unlock;
 
 	/* Drop the parent lock, relock this inode. */
 	xfs_iunlock(dp, XFS_IOLOCK_SHARED);
-	error = xfs_scrub_ilock_inverted(sc->ip, XFS_IOLOCK_EXCL);
+	error = xchk_ilock_inverted(sc->ip, XFS_IOLOCK_EXCL);
 	if (error)
 		goto out_rele;
 	sc->ilock_flags = XFS_IOLOCK_EXCL;
@@ -225,43 +225,43 @@ xfs_scrub_parent_validate(
 
 	/* Look up '..' to see if the inode changed. */
 	error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &dnum, NULL);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out_rele;
 
 	/* Drat, parent changed.  Try again! */
 	if (dnum != dp->i_ino) {
-		iput(VFS_I(dp));
+		xfs_irele(dp);
 		*try_again = true;
 		return 0;
 	}
-	iput(VFS_I(dp));
+	xfs_irele(dp);
 
 	/*
 	 * '..' didn't change, so check that there was only one entry
 	 * for us in the parent.
 	 */
 	if (nlink != expected_nlink)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 	return error;
 
 out_unlock:
 	xfs_iunlock(dp, XFS_IOLOCK_SHARED);
 out_rele:
-	iput(VFS_I(dp));
+	xfs_irele(dp);
 out:
 	return error;
 }
 
 /* Scrub a parent pointer. */
 int
-xfs_scrub_parent(
-	struct xfs_scrub_context	*sc)
+xchk_parent(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	xfs_ino_t			dnum;
-	bool				try_again;
-	int				tries = 0;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_ino_t		dnum;
+	bool			try_again;
+	int			tries = 0;
+	int			error = 0;
 
 	/*
 	 * If we're a directory, check that the '..' link points up to
@@ -272,7 +272,7 @@ xfs_scrub_parent(
 
 	/* We're not a special inode, are we? */
 	if (!xfs_verify_dir_ino(mp, sc->ip->i_ino)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -288,10 +288,10 @@ xfs_scrub_parent(
 
 	/* Look up '..' */
 	error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &dnum, NULL);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 	if (!xfs_verify_dir_ino(mp, dnum)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -299,12 +299,12 @@ xfs_scrub_parent(
 	if (sc->ip == mp->m_rootip) {
 		if (sc->ip->i_ino != mp->m_sb.sb_rootino ||
 		    sc->ip->i_ino != dnum)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
 	do {
-		error = xfs_scrub_parent_validate(sc, dnum, &try_again);
+		error = xchk_parent_validate(sc, dnum, &try_again);
 		if (error)
 			goto out;
 	} while (try_again && ++tries < 20);
@@ -314,7 +314,7 @@ xfs_scrub_parent(
 	 * incomplete.  Userspace can decide if it wants to try again.
 	 */
 	if (try_again && tries == 20)
-		xfs_scrub_set_incomplete(sc);
+		xchk_set_incomplete(sc);
 out:
 	/*
 	 * If we failed to lock the parent inode even after a retry, just mark
@@ -322,7 +322,7 @@ out:
 	 */
 	if (sc->try_harder && error == -EDEADLOCK) {
 		error = 0;
-		xfs_scrub_set_incomplete(sc);
+		xchk_set_incomplete(sc);
 	}
 	return error;
 }
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 6ff906aa0a3b..782d582d3edd 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -30,8 +30,8 @@
 
 /* Convert a scrub type code to a DQ flag, or return 0 if error. */
 static inline uint
-xfs_scrub_quota_to_dqtype(
-	struct xfs_scrub_context	*sc)
+xchk_quota_to_dqtype(
+	struct xfs_scrub	*sc)
 {
 	switch (sc->sm->sm_type) {
 	case XFS_SCRUB_TYPE_UQUOTA:
@@ -47,24 +47,24 @@ xfs_scrub_quota_to_dqtype(
 
 /* Set us up to scrub a quota. */
 int
-xfs_scrub_setup_quota(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_quota(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	uint				dqtype;
-	int				error;
+	uint			dqtype;
+	int			error;
 
 	if (!XFS_IS_QUOTA_RUNNING(sc->mp) || !XFS_IS_QUOTA_ON(sc->mp))
 		return -ENOENT;
 
-	dqtype = xfs_scrub_quota_to_dqtype(sc);
+	dqtype = xchk_quota_to_dqtype(sc);
 	if (dqtype == 0)
 		return -EINVAL;
 	sc->has_quotaofflock = true;
 	mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock);
 	if (!xfs_this_quota_on(sc->mp, dqtype))
 		return -ENOENT;
-	error = xfs_scrub_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc, ip);
 	if (error)
 		return error;
 	sc->ip = xfs_quota_inode(sc->mp, dqtype);
@@ -75,35 +75,35 @@ xfs_scrub_setup_quota(
 
 /* Quotas. */
 
-struct xfs_scrub_quota_info {
-	struct xfs_scrub_context	*sc;
-	xfs_dqid_t			last_id;
+struct xchk_quota_info {
+	struct xfs_scrub	*sc;
+	xfs_dqid_t		last_id;
 };
 
 /* Scrub the fields in an individual quota item. */
 STATIC int
-xfs_scrub_quota_item(
-	struct xfs_dquot		*dq,
-	uint				dqtype,
-	void				*priv)
+xchk_quota_item(
+	struct xfs_dquot	*dq,
+	uint			dqtype,
+	void			*priv)
 {
-	struct xfs_scrub_quota_info	*sqi = priv;
-	struct xfs_scrub_context	*sc = sqi->sc;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_disk_dquot		*d = &dq->q_core;
-	struct xfs_quotainfo		*qi = mp->m_quotainfo;
-	xfs_fileoff_t			offset;
-	unsigned long long		bsoft;
-	unsigned long long		isoft;
-	unsigned long long		rsoft;
-	unsigned long long		bhard;
-	unsigned long long		ihard;
-	unsigned long long		rhard;
-	unsigned long long		bcount;
-	unsigned long long		icount;
-	unsigned long long		rcount;
-	xfs_ino_t			fs_icount;
-	xfs_dqid_t			id = be32_to_cpu(d->d_id);
+	struct xchk_quota_info	*sqi = priv;
+	struct xfs_scrub	*sc = sqi->sc;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_disk_dquot	*d = &dq->q_core;
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	xfs_fileoff_t		offset;
+	unsigned long long	bsoft;
+	unsigned long long	isoft;
+	unsigned long long	rsoft;
+	unsigned long long	bhard;
+	unsigned long long	ihard;
+	unsigned long long	rhard;
+	unsigned long long	bcount;
+	unsigned long long	icount;
+	unsigned long long	rcount;
+	xfs_ino_t		fs_icount;
+	xfs_dqid_t		id = be32_to_cpu(d->d_id);
 
 	/*
 	 * Except for the root dquot, the actual dquot we got must either have
@@ -111,16 +111,16 @@ xfs_scrub_quota_item(
 	 */
 	offset = id / qi->qi_dqperchunk;
 	if (id && id <= sqi->last_id)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	sqi->last_id = id;
 
 	/* Did we get the dquot type we wanted? */
 	if (dqtype != (d->d_flags & XFS_DQ_ALLTYPES))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	if (d->d_pad0 != cpu_to_be32(0) || d->d_pad != cpu_to_be16(0))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/* Check the limits. */
 	bhard = be64_to_cpu(d->d_blk_hardlimit);
@@ -140,19 +140,19 @@ xfs_scrub_quota_item(
 	 * the hard limit.
 	 */
 	if (bhard > mp->m_sb.sb_dblocks)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (bsoft > bhard)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	if (ihard > mp->m_maxicount)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (isoft > ihard)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	if (rhard > mp->m_sb.sb_rblocks)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (rsoft > rhard)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/* Check the resource counts. */
 	bcount = be64_to_cpu(d->d_bcount);
@@ -167,15 +167,15 @@ xfs_scrub_quota_item(
 	 */
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
 		if (mp->m_sb.sb_dblocks < bcount)
-			xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK,
+			xchk_fblock_set_warning(sc, XFS_DATA_FORK,
 					offset);
 	} else {
 		if (mp->m_sb.sb_dblocks < bcount)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					offset);
 	}
 	if (icount > fs_icount || rcount > mp->m_sb.sb_rblocks)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/*
 	 * We can violate the hard limits if the admin suddenly sets a
@@ -183,29 +183,29 @@ xfs_scrub_quota_item(
 	 * admin review.
 	 */
 	if (id != 0 && bhard != 0 && bcount > bhard)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (id != 0 && ihard != 0 && icount > ihard)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (id != 0 && rhard != 0 && rcount > rhard)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 
 	return 0;
 }
 
 /* Check the quota's data fork. */
 STATIC int
-xfs_scrub_quota_data_fork(
-	struct xfs_scrub_context	*sc)
+xchk_quota_data_fork(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_bmbt_irec		irec = { 0 };
-	struct xfs_iext_cursor		icur;
-	struct xfs_quotainfo		*qi = sc->mp->m_quotainfo;
-	struct xfs_ifork		*ifp;
-	xfs_fileoff_t			max_dqid_off;
-	int				error = 0;
+	struct xfs_bmbt_irec	irec = { 0 };
+	struct xfs_iext_cursor	icur;
+	struct xfs_quotainfo	*qi = sc->mp->m_quotainfo;
+	struct xfs_ifork	*ifp;
+	xfs_fileoff_t		max_dqid_off;
+	int			error = 0;
 
 	/* Invoke the fork scrubber. */
-	error = xfs_scrub_metadata_inode_forks(sc);
+	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 
@@ -213,7 +213,7 @@ xfs_scrub_quota_data_fork(
 	max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk;
 	ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK);
 	for_each_xfs_iext(ifp, &icur, &irec) {
-		if (xfs_scrub_should_terminate(sc, &error))
+		if (xchk_should_terminate(sc, &error))
 			break;
 		/*
 		 * delalloc extents or blocks mapped above the highest
@@ -222,7 +222,7 @@ xfs_scrub_quota_data_fork(
 		if (isnullstartblock(irec.br_startblock) ||
 		    irec.br_startoff > max_dqid_off ||
 		    irec.br_startoff + irec.br_blockcount - 1 > max_dqid_off) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					irec.br_startoff);
 			break;
 		}
@@ -233,19 +233,19 @@ xfs_scrub_quota_data_fork(
 
 /* Scrub all of a quota type's items. */
 int
-xfs_scrub_quota(
-	struct xfs_scrub_context	*sc)
+xchk_quota(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_scrub_quota_info	sqi;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_quotainfo		*qi = mp->m_quotainfo;
-	uint				dqtype;
-	int				error = 0;
+	struct xchk_quota_info	sqi;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	uint			dqtype;
+	int			error = 0;
 
-	dqtype = xfs_scrub_quota_to_dqtype(sc);
+	dqtype = xchk_quota_to_dqtype(sc);
 
 	/* Look for problem extents. */
-	error = xfs_scrub_quota_data_fork(sc);
+	error = xchk_quota_data_fork(sc);
 	if (error)
 		goto out;
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -260,10 +260,10 @@ xfs_scrub_quota(
 	sc->ilock_flags = 0;
 	sqi.sc = sc;
 	sqi.last_id = 0;
-	error = xfs_qm_dqiterate(mp, dqtype, xfs_scrub_quota_item, &sqi);
+	error = xfs_qm_dqiterate(mp, dqtype, xchk_quota_item, &sqi);
 	sc->ilock_flags = XFS_ILOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK,
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK,
 			sqi.last_id * qi->qi_dqperchunk, &error))
 		goto out;
 
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 607a9faa8ecc..e8c82b026083 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -28,11 +28,11 @@
  * Set us up to scrub reference count btrees.
  */
 int
-xfs_scrub_setup_ag_refcountbt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_ag_refcountbt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, ip, false);
 }
 
 /* Reference count btree scrubber. */
@@ -73,22 +73,22 @@ xfs_scrub_setup_ag_refcountbt(
  * If the refcount is correct, all the check conditions in the algorithm
  * should always hold true.  If not, the refcount is incorrect.
  */
-struct xfs_scrub_refcnt_frag {
-	struct list_head		list;
-	struct xfs_rmap_irec		rm;
+struct xchk_refcnt_frag {
+	struct list_head	list;
+	struct xfs_rmap_irec	rm;
 };
 
-struct xfs_scrub_refcnt_check {
-	struct xfs_scrub_context	*sc;
-	struct list_head		fragments;
+struct xchk_refcnt_check {
+	struct xfs_scrub	*sc;
+	struct list_head	fragments;
 
 	/* refcount extent we're examining */
-	xfs_agblock_t			bno;
-	xfs_extlen_t			len;
-	xfs_nlink_t			refcount;
+	xfs_agblock_t		bno;
+	xfs_extlen_t		len;
+	xfs_nlink_t		refcount;
 
 	/* number of owners seen */
-	xfs_nlink_t			seen;
+	xfs_nlink_t		seen;
 };
 
 /*
@@ -99,18 +99,18 @@ struct xfs_scrub_refcnt_check {
  * fragments as the refcountbt says we should have.
  */
 STATIC int
-xfs_scrub_refcountbt_rmap_check(
+xchk_refcountbt_rmap_check(
 	struct xfs_btree_cur		*cur,
 	struct xfs_rmap_irec		*rec,
 	void				*priv)
 {
-	struct xfs_scrub_refcnt_check	*refchk = priv;
-	struct xfs_scrub_refcnt_frag	*frag;
+	struct xchk_refcnt_check	*refchk = priv;
+	struct xchk_refcnt_frag		*frag;
 	xfs_agblock_t			rm_last;
 	xfs_agblock_t			rc_last;
 	int				error = 0;
 
-	if (xfs_scrub_should_terminate(refchk->sc, &error))
+	if (xchk_should_terminate(refchk->sc, &error))
 		return error;
 
 	rm_last = rec->rm_startblock + rec->rm_blockcount - 1;
@@ -118,7 +118,7 @@ xfs_scrub_refcountbt_rmap_check(
 
 	/* Confirm that a single-owner refc extent is a CoW stage. */
 	if (refchk->refcount == 1 && rec->rm_owner != XFS_RMAP_OWN_COW) {
-		xfs_scrub_btree_xref_set_corrupt(refchk->sc, cur, 0);
+		xchk_btree_xref_set_corrupt(refchk->sc, cur, 0);
 		return 0;
 	}
 
@@ -135,7 +135,7 @@ xfs_scrub_refcountbt_rmap_check(
 		 * is healthy each rmap_irec we see will be in agbno order
 		 * so we don't need insertion sort here.
 		 */
-		frag = kmem_alloc(sizeof(struct xfs_scrub_refcnt_frag),
+		frag = kmem_alloc(sizeof(struct xchk_refcnt_frag),
 				KM_MAYFAIL);
 		if (!frag)
 			return -ENOMEM;
@@ -154,12 +154,12 @@ xfs_scrub_refcountbt_rmap_check(
  * we have a refcountbt error.
  */
 STATIC void
-xfs_scrub_refcountbt_process_rmap_fragments(
-	struct xfs_scrub_refcnt_check	*refchk)
+xchk_refcountbt_process_rmap_fragments(
+	struct xchk_refcnt_check	*refchk)
 {
 	struct list_head		worklist;
-	struct xfs_scrub_refcnt_frag	*frag;
-	struct xfs_scrub_refcnt_frag	*n;
+	struct xchk_refcnt_frag		*frag;
+	struct xchk_refcnt_frag		*n;
 	xfs_agblock_t			bno;
 	xfs_agblock_t			rbno;
 	xfs_agblock_t			next_rbno;
@@ -277,13 +277,13 @@ done:
 
 /* Use the rmap entries covering this extent to verify the refcount. */
 STATIC void
-xfs_scrub_refcountbt_xref_rmap(
-	struct xfs_scrub_context	*sc,
+xchk_refcountbt_xref_rmap(
+	struct xfs_scrub		*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	xfs_nlink_t			refcount)
 {
-	struct xfs_scrub_refcnt_check	refchk = {
+	struct xchk_refcnt_check	refchk = {
 		.sc = sc,
 		.bno = bno,
 		.len = len,
@@ -292,11 +292,11 @@ xfs_scrub_refcountbt_xref_rmap(
 	};
 	struct xfs_rmap_irec		low;
 	struct xfs_rmap_irec		high;
-	struct xfs_scrub_refcnt_frag	*frag;
-	struct xfs_scrub_refcnt_frag	*n;
+	struct xchk_refcnt_frag		*frag;
+	struct xchk_refcnt_frag		*n;
 	int				error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Cross-reference with the rmapbt to confirm the refcount. */
@@ -307,13 +307,13 @@ xfs_scrub_refcountbt_xref_rmap(
 
 	INIT_LIST_HEAD(&refchk.fragments);
 	error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high,
-			&xfs_scrub_refcountbt_rmap_check, &refchk);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+			&xchk_refcountbt_rmap_check, &refchk);
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		goto out_free;
 
-	xfs_scrub_refcountbt_process_rmap_fragments(&refchk);
+	xchk_refcountbt_process_rmap_fragments(&refchk);
 	if (refcount != refchk.seen)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 
 out_free:
 	list_for_each_entry_safe(frag, n, &refchk.fragments, list) {
@@ -324,34 +324,34 @@ out_free:
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_refcountbt_xref(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len,
-	xfs_nlink_t			refcount)
+xchk_refcountbt_xref(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len,
+	xfs_nlink_t		refcount)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, len);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
-	xfs_scrub_refcountbt_xref_rmap(sc, agbno, len, refcount);
+	xchk_xref_is_used_space(sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(sc, agbno, len);
+	xchk_refcountbt_xref_rmap(sc, agbno, len, refcount);
 }
 
 /* Scrub a refcountbt record. */
 STATIC int
-xfs_scrub_refcountbt_rec(
-	struct xfs_scrub_btree		*bs,
-	union xfs_btree_rec		*rec)
+xchk_refcountbt_rec(
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
-	xfs_agblock_t			*cow_blocks = bs->private;
-	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
-	xfs_agblock_t			bno;
-	xfs_extlen_t			len;
-	xfs_nlink_t			refcount;
-	bool				has_cowflag;
-	int				error = 0;
+	struct xfs_mount	*mp = bs->cur->bc_mp;
+	xfs_agblock_t		*cow_blocks = bs->private;
+	xfs_agnumber_t		agno = bs->cur->bc_private.a.agno;
+	xfs_agblock_t		bno;
+	xfs_extlen_t		len;
+	xfs_nlink_t		refcount;
+	bool			has_cowflag;
+	int			error = 0;
 
 	bno = be32_to_cpu(rec->refc.rc_startblock);
 	len = be32_to_cpu(rec->refc.rc_blockcount);
@@ -360,7 +360,7 @@ xfs_scrub_refcountbt_rec(
 	/* Only CoW records can have refcount == 1. */
 	has_cowflag = (bno & XFS_REFC_COW_START);
 	if ((refcount == 1 && !has_cowflag) || (refcount != 1 && has_cowflag))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	if (has_cowflag)
 		(*cow_blocks) += len;
 
@@ -369,75 +369,75 @@ xfs_scrub_refcountbt_rec(
 	if (bno + len <= bno ||
 	    !xfs_verify_agbno(mp, agno, bno) ||
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (refcount == 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xfs_scrub_refcountbt_xref(bs->sc, bno, len, refcount);
+	xchk_refcountbt_xref(bs->sc, bno, len, refcount);
 
 	return error;
 }
 
 /* Make sure we have as many refc blocks as the rmap says. */
 STATIC void
-xfs_scrub_refcount_xref_rmap(
-	struct xfs_scrub_context	*sc,
-	struct xfs_owner_info		*oinfo,
-	xfs_filblks_t			cow_blocks)
+xchk_refcount_xref_rmap(
+	struct xfs_scrub	*sc,
+	struct xfs_owner_info	*oinfo,
+	xfs_filblks_t		cow_blocks)
 {
-	xfs_extlen_t			refcbt_blocks = 0;
-	xfs_filblks_t			blocks;
-	int				error;
+	xfs_extlen_t		refcbt_blocks = 0;
+	xfs_filblks_t		blocks;
+	int			error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many refcbt blocks as the rmap knows about. */
 	error = xfs_btree_count_blocks(sc->sa.refc_cur, &refcbt_blocks);
-	if (!xfs_scrub_btree_process_error(sc, sc->sa.refc_cur, 0, &error))
+	if (!xchk_btree_process_error(sc, sc->sa.refc_cur, 0, &error))
 		return;
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != refcbt_blocks)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 
 	/* Check that we saw as many cow blocks as the rmap knows about. */
 	xfs_rmap_ag_owner(oinfo, XFS_RMAP_OWN_COW);
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != cow_blocks)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* Scrub the refcount btree for some AG. */
 int
-xfs_scrub_refcountbt(
-	struct xfs_scrub_context	*sc)
+xchk_refcountbt(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_agblock_t			cow_blocks = 0;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_agblock_t		cow_blocks = 0;
+	int			error;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_REFC);
-	error = xfs_scrub_btree(sc, sc->sa.refc_cur, xfs_scrub_refcountbt_rec,
+	error = xchk_btree(sc, sc->sa.refc_cur, xchk_refcountbt_rec,
 			&oinfo, &cow_blocks);
 	if (error)
 		return error;
 
-	xfs_scrub_refcount_xref_rmap(sc, &oinfo, cow_blocks);
+	xchk_refcount_xref_rmap(sc, &oinfo, cow_blocks);
 
 	return 0;
 }
 
 /* xref check that a cow staging extent is marked in the refcountbt. */
 void
-xfs_scrub_xref_is_cow_staging(
-	struct xfs_scrub_context	*sc,
+xchk_xref_is_cow_staging(
+	struct xfs_scrub		*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
@@ -446,35 +446,35 @@ xfs_scrub_xref_is_cow_staging(
 	int				has_refcount;
 	int				error;
 
-	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Find the CoW staging extent. */
 	error = xfs_refcount_lookup_le(sc->sa.refc_cur,
 			agbno + XFS_REFC_COW_START, &has_refcount);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (!has_refcount) {
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 		return;
 	}
 
 	error = xfs_refcount_get_rec(sc->sa.refc_cur, &rc, &has_refcount);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (!has_refcount) {
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 		return;
 	}
 
 	/* CoW flag must be set, refcount must be 1. */
 	has_cowflag = (rc.rc_startblock & XFS_REFC_COW_START);
 	if (!has_cowflag || rc.rc_refcount != 1)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 
 	/* Must be at least as long as what was passed in */
 	if (rc.rc_blockcount < len)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
 
 /*
@@ -482,20 +482,20 @@ xfs_scrub_xref_is_cow_staging(
  * can have multiple owners.
  */
 void
-xfs_scrub_xref_is_not_shared(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+xchk_xref_is_not_shared(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	bool				shared;
-	int				error;
+	bool			shared;
+	int			error;
 
-	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (shared)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 326be4e8b71e..17cf48564390 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -34,6 +34,7 @@
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/repair.h"
+#include "scrub/bitmap.h"
 
 /*
  * Attempt to repair some metadata, if the metadata is corrupt and userspace
@@ -41,21 +42,21 @@
  * and will set *fixed to true if it thinks it repaired anything.
  */
 int
-xfs_repair_attempt(
-	struct xfs_inode		*ip,
-	struct xfs_scrub_context	*sc,
-	bool				*fixed)
+xrep_attempt(
+	struct xfs_inode	*ip,
+	struct xfs_scrub	*sc,
+	bool			*fixed)
 {
-	int				error = 0;
+	int			error = 0;
 
-	trace_xfs_repair_attempt(ip, sc->sm, error);
+	trace_xrep_attempt(ip, sc->sm, error);
 
-	xfs_scrub_ag_btcur_free(&sc->sa);
+	xchk_ag_btcur_free(&sc->sa);
 
 	/* Repair whatever's broken. */
 	ASSERT(sc->ops->repair);
 	error = sc->ops->repair(sc);
-	trace_xfs_repair_done(ip, sc->sm, error);
+	trace_xrep_done(ip, sc->sm, error);
 	switch (error) {
 	case 0:
 		/*
@@ -93,8 +94,8 @@ xfs_repair_attempt(
  * structure to track rate limiting information.
  */
 void
-xfs_repair_failure(
-	struct xfs_mount		*mp)
+xrep_failure(
+	struct xfs_mount	*mp)
 {
 	xfs_alert_ratelimited(mp,
 "Corruption not fixed during online repair.  Unmount and run xfs_repair.");
@@ -105,12 +106,12 @@ xfs_repair_failure(
  * given mountpoint.
  */
 int
-xfs_repair_probe(
-	struct xfs_scrub_context	*sc)
+xrep_probe(
+	struct xfs_scrub	*sc)
 {
-	int				error = 0;
+	int			error = 0;
 
-	if (xfs_scrub_should_terminate(sc, &error))
+	if (xchk_should_terminate(sc, &error))
 		return error;
 
 	return 0;
@@ -121,15 +122,18 @@ xfs_repair_probe(
  * the btree cursors.
  */
 int
-xfs_repair_roll_ag_trans(
-	struct xfs_scrub_context	*sc)
+xrep_roll_ag_trans(
+	struct xfs_scrub	*sc)
 {
-	int				error;
+	int			error;
 
 	/* Keep the AG header buffers locked so we can keep going. */
-	xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
-	xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
-	xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
+	if (sc->sa.agi_bp)
+		xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
+	if (sc->sa.agfl_bp)
+		xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
 
 	/* Roll the transaction. */
 	error = xfs_trans_roll(&sc->tp);
@@ -137,9 +141,12 @@ xfs_repair_roll_ag_trans(
 		goto out_release;
 
 	/* Join AG headers to the new transaction. */
-	xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
-	xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
-	xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
+	if (sc->sa.agi_bp)
+		xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
+	if (sc->sa.agfl_bp)
+		xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
 
 	return 0;
 
@@ -149,9 +156,12 @@ out_release:
 	 * buffers will be released during teardown on our way out
 	 * of the kernel.
 	 */
-	xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp);
-	xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp);
-	xfs_trans_bhold_release(sc->tp, sc->sa.agfl_bp);
+	if (sc->sa.agi_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp);
+	if (sc->sa.agfl_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agfl_bp);
 
 	return error;
 }
@@ -162,10 +172,10 @@ out_release:
  * in AG reservations) to construct a whole btree.
  */
 bool
-xfs_repair_ag_has_space(
-	struct xfs_perag		*pag,
-	xfs_extlen_t			nr_blocks,
-	enum xfs_ag_resv_type		type)
+xrep_ag_has_space(
+	struct xfs_perag	*pag,
+	xfs_extlen_t		nr_blocks,
+	enum xfs_ag_resv_type	type)
 {
 	return  !xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) &&
 		!xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA) &&
@@ -178,8 +188,8 @@ xfs_repair_ag_has_space(
  * any type of per-AG btree.
  */
 xfs_extlen_t
-xfs_repair_calc_ag_resblks(
-	struct xfs_scrub_context	*sc)
+xrep_calc_ag_resblks(
+	struct xfs_scrub		*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_scrub_metadata	*sm = sc->sm;
@@ -231,7 +241,7 @@ xfs_repair_calc_ag_resblks(
 	}
 	xfs_perag_put(pag);
 
-	trace_xfs_repair_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
+	trace_xrep_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
 			freelen, usedlen);
 
 	/*
@@ -270,7 +280,7 @@ xfs_repair_calc_ag_resblks(
 		rmapbt_sz = 0;
 	}
 
-	trace_xfs_repair_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
+	trace_xrep_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
 			inobt_sz, rmapbt_sz, refcbt_sz);
 
 	return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz));
@@ -278,15 +288,15 @@ xfs_repair_calc_ag_resblks(
 
 /* Allocate a block in an AG. */
 int
-xfs_repair_alloc_ag_block(
-	struct xfs_scrub_context	*sc,
-	struct xfs_owner_info		*oinfo,
-	xfs_fsblock_t			*fsbno,
-	enum xfs_ag_resv_type		resv)
+xrep_alloc_ag_block(
+	struct xfs_scrub	*sc,
+	struct xfs_owner_info	*oinfo,
+	xfs_fsblock_t		*fsbno,
+	enum xfs_ag_resv_type	resv)
 {
-	struct xfs_alloc_arg		args = {0};
-	xfs_agblock_t			bno;
-	int				error;
+	struct xfs_alloc_arg	args = {0};
+	xfs_agblock_t		bno;
+	int			error;
 
 	switch (resv) {
 	case XFS_AG_RESV_AGFL:
@@ -329,8 +339,8 @@ xfs_repair_alloc_ag_block(
 
 /* Initialize a new AG btree root block with zero entries. */
 int
-xfs_repair_init_btblock(
-	struct xfs_scrub_context	*sc,
+xrep_init_btblock(
+	struct xfs_scrub		*sc,
 	xfs_fsblock_t			fsb,
 	struct xfs_buf			**bpp,
 	xfs_btnum_t			btnum,
@@ -340,7 +350,7 @@ xfs_repair_init_btblock(
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_buf			*bp;
 
-	trace_xfs_repair_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb),
+	trace_xrep_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb),
 			XFS_FSB_TO_AGBNO(mp, fsb), btnum);
 
 	ASSERT(XFS_FSB_TO_AGNO(mp, fsb) == sc->sa.agno);
@@ -367,222 +377,29 @@ xfs_repair_init_btblock(
  *
  * However, that leaves the matter of removing all the metadata describing the
  * old broken structure.  For primary metadata we use the rmap data to collect
- * every extent with a matching rmap owner (exlist); we then iterate all other
+ * every extent with a matching rmap owner (bitmap); we then iterate all other
  * metadata structures with the same rmap owner to collect the extents that
- * cannot be removed (sublist).  We then subtract sublist from exlist to
+ * cannot be removed (sublist).  We then subtract sublist from bitmap to
  * derive the blocks that were used by the old btree.  These blocks can be
  * reaped.
  *
  * For rmapbt reconstructions we must use different tactics for extent
  * collection.  First we iterate all primary metadata (this excludes the old
  * rmapbt, obviously) to generate new rmap records.  The gaps in the rmap
- * records are collected as exlist.  The bnobt records are collected as
- * sublist.  As with the other btrees we subtract sublist from exlist, and the
+ * records are collected as bitmap.  The bnobt records are collected as
+ * sublist.  As with the other btrees we subtract sublist from bitmap, and the
  * result (since the rmapbt lives in the free space) are the blocks from the
  * old rmapbt.
- */
-
-/* Collect a dead btree extent for later disposal. */
-int
-xfs_repair_collect_btree_extent(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist,
-	xfs_fsblock_t			fsbno,
-	xfs_extlen_t			len)
-{
-	struct xfs_repair_extent	*rex;
-
-	trace_xfs_repair_collect_btree_extent(sc->mp,
-			XFS_FSB_TO_AGNO(sc->mp, fsbno),
-			XFS_FSB_TO_AGBNO(sc->mp, fsbno), len);
-
-	rex = kmem_alloc(sizeof(struct xfs_repair_extent), KM_MAYFAIL);
-	if (!rex)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&rex->list);
-	rex->fsbno = fsbno;
-	rex->len = len;
-	list_add_tail(&rex->list, &exlist->list);
-
-	return 0;
-}
-
-/*
- * An error happened during the rebuild so the transaction will be cancelled.
- * The fs will shut down, and the administrator has to unmount and run repair.
- * Therefore, free all the memory associated with the list so we can die.
- */
-void
-xfs_repair_cancel_btree_extents(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist)
-{
-	struct xfs_repair_extent	*rex;
-	struct xfs_repair_extent	*n;
-
-	for_each_xfs_repair_extent_safe(rex, n, exlist) {
-		list_del(&rex->list);
-		kmem_free(rex);
-	}
-}
-
-/* Compare two btree extents. */
-static int
-xfs_repair_btree_extent_cmp(
-	void				*priv,
-	struct list_head		*a,
-	struct list_head		*b)
-{
-	struct xfs_repair_extent	*ap;
-	struct xfs_repair_extent	*bp;
-
-	ap = container_of(a, struct xfs_repair_extent, list);
-	bp = container_of(b, struct xfs_repair_extent, list);
-
-	if (ap->fsbno > bp->fsbno)
-		return 1;
-	if (ap->fsbno < bp->fsbno)
-		return -1;
-	return 0;
-}
-
-/*
- * Remove all the blocks mentioned in @sublist from the extents in @exlist.
  *
- * The intent is that callers will iterate the rmapbt for all of its records
- * for a given owner to generate @exlist; and iterate all the blocks of the
- * metadata structures that are not being rebuilt and have the same rmapbt
- * owner to generate @sublist.  This routine subtracts all the extents
- * mentioned in sublist from all the extents linked in @exlist, which leaves
- * @exlist as the list of blocks that are not accounted for, which we assume
- * are the dead blocks of the old metadata structure.  The blocks mentioned in
- * @exlist can be reaped.
- */
-#define LEFT_ALIGNED	(1 << 0)
-#define RIGHT_ALIGNED	(1 << 1)
-int
-xfs_repair_subtract_extents(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist,
-	struct xfs_repair_extent_list	*sublist)
-{
-	struct list_head		*lp;
-	struct xfs_repair_extent	*ex;
-	struct xfs_repair_extent	*newex;
-	struct xfs_repair_extent	*subex;
-	xfs_fsblock_t			sub_fsb;
-	xfs_extlen_t			sub_len;
-	int				state;
-	int				error = 0;
-
-	if (list_empty(&exlist->list) || list_empty(&sublist->list))
-		return 0;
-	ASSERT(!list_empty(&sublist->list));
-
-	list_sort(NULL, &exlist->list, xfs_repair_btree_extent_cmp);
-	list_sort(NULL, &sublist->list, xfs_repair_btree_extent_cmp);
-
-	/*
-	 * Now that we've sorted both lists, we iterate exlist once, rolling
-	 * forward through sublist and/or exlist as necessary until we find an
-	 * overlap or reach the end of either list.  We do not reset lp to the
-	 * head of exlist nor do we reset subex to the head of sublist.  The
-	 * list traversal is similar to merge sort, but we're deleting
-	 * instead.  In this manner we avoid O(n^2) operations.
-	 */
-	subex = list_first_entry(&sublist->list, struct xfs_repair_extent,
-			list);
-	lp = exlist->list.next;
-	while (lp != &exlist->list) {
-		ex = list_entry(lp, struct xfs_repair_extent, list);
-
-		/*
-		 * Advance subex and/or ex until we find a pair that
-		 * intersect or we run out of extents.
-		 */
-		while (subex->fsbno + subex->len <= ex->fsbno) {
-			if (list_is_last(&subex->list, &sublist->list))
-				goto out;
-			subex = list_next_entry(subex, list);
-		}
-		if (subex->fsbno >= ex->fsbno + ex->len) {
-			lp = lp->next;
-			continue;
-		}
-
-		/* trim subex to fit the extent we have */
-		sub_fsb = subex->fsbno;
-		sub_len = subex->len;
-		if (subex->fsbno < ex->fsbno) {
-			sub_len -= ex->fsbno - subex->fsbno;
-			sub_fsb = ex->fsbno;
-		}
-		if (sub_len > ex->len)
-			sub_len = ex->len;
-
-		state = 0;
-		if (sub_fsb == ex->fsbno)
-			state |= LEFT_ALIGNED;
-		if (sub_fsb + sub_len == ex->fsbno + ex->len)
-			state |= RIGHT_ALIGNED;
-		switch (state) {
-		case LEFT_ALIGNED:
-			/* Coincides with only the left. */
-			ex->fsbno += sub_len;
-			ex->len -= sub_len;
-			break;
-		case RIGHT_ALIGNED:
-			/* Coincides with only the right. */
-			ex->len -= sub_len;
-			lp = lp->next;
-			break;
-		case LEFT_ALIGNED | RIGHT_ALIGNED:
-			/* Total overlap, just delete ex. */
-			lp = lp->next;
-			list_del(&ex->list);
-			kmem_free(ex);
-			break;
-		case 0:
-			/*
-			 * Deleting from the middle: add the new right extent
-			 * and then shrink the left extent.
-			 */
-			newex = kmem_alloc(sizeof(struct xfs_repair_extent),
-					KM_MAYFAIL);
-			if (!newex) {
-				error = -ENOMEM;
-				goto out;
-			}
-			INIT_LIST_HEAD(&newex->list);
-			newex->fsbno = sub_fsb + sub_len;
-			newex->len = ex->fsbno + ex->len - newex->fsbno;
-			list_add(&newex->list, &ex->list);
-			ex->len = sub_fsb - ex->fsbno;
-			lp = lp->next;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
-	}
-
-out:
-	return error;
-}
-#undef LEFT_ALIGNED
-#undef RIGHT_ALIGNED
-
-/*
  * Disposal of Blocks from Old per-AG Btrees
  *
  * Now that we've constructed a new btree to replace the damaged one, we want
  * to dispose of the blocks that (we think) the old btree was using.
- * Previously, we used the rmapbt to collect the extents (exlist) with the
+ * Previously, we used the rmapbt to collect the extents (bitmap) with the
  * rmap owner corresponding to the tree we rebuilt, collected extents for any
  * blocks with the same rmap owner that are owned by another data structure
- * (sublist), and subtracted sublist from exlist.  In theory the extents
- * remaining in exlist are the old btree's blocks.
+ * (sublist), and subtracted sublist from bitmap.  In theory the extents
+ * remaining in bitmap are the old btree's blocks.
  *
  * Unfortunately, it's possible that the btree was crosslinked with other
  * blocks on disk.  The rmap data can tell us if there are multiple owners, so
@@ -598,7 +415,7 @@ out:
  * If there are no rmap records at all, we also free the block.  If the btree
  * being rebuilt lives in the free space (bnobt/cntbt/rmapbt) then there isn't
  * supposed to be a rmap record and everything is ok.  For other btrees there
- * had to have been an rmap entry for the block to have ended up on @exlist,
+ * had to have been an rmap entry for the block to have ended up on @bitmap,
  * so if it's gone now there's something wrong and the fs will shut down.
  *
  * Note: If there are multiple rmap records with only the same rmap owner as
@@ -611,7 +428,7 @@ out:
  * The caller is responsible for locking the AG headers for the entire rebuild
  * operation so that nothing else can sneak in and change the AG state while
  * we're not looking.  We also assume that the caller already invalidated any
- * buffers associated with @exlist.
+ * buffers associated with @bitmap.
  */
 
 /*
@@ -619,15 +436,14 @@ out:
  * is not intended for use with file data repairs; we have bunmapi for that.
  */
 int
-xfs_repair_invalidate_blocks(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist)
+xrep_invalidate_blocks(
+	struct xfs_scrub	*sc,
+	struct xfs_bitmap	*bitmap)
 {
-	struct xfs_repair_extent	*rex;
-	struct xfs_repair_extent	*n;
-	struct xfs_buf			*bp;
-	xfs_fsblock_t			fsbno;
-	xfs_agblock_t			i;
+	struct xfs_bitmap_range	*bmr;
+	struct xfs_bitmap_range	*n;
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsbno;
 
 	/*
 	 * For each block in each extent, see if there's an incore buffer for
@@ -637,18 +453,16 @@ xfs_repair_invalidate_blocks(
 	 * because we never own those; and if we can't TRYLOCK the buffer we
 	 * assume it's owned by someone else.
 	 */
-	for_each_xfs_repair_extent_safe(rex, n, exlist) {
-		for (fsbno = rex->fsbno, i = rex->len; i > 0; fsbno++, i--) {
-			/* Skip AG headers and post-EOFS blocks */
-			if (!xfs_verify_fsbno(sc->mp, fsbno))
-				continue;
-			bp = xfs_buf_incore(sc->mp->m_ddev_targp,
-					XFS_FSB_TO_DADDR(sc->mp, fsbno),
-					XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
-			if (bp) {
-				xfs_trans_bjoin(sc->tp, bp);
-				xfs_trans_binval(sc->tp, bp);
-			}
+	for_each_xfs_bitmap_block(fsbno, bmr, n, bitmap) {
+		/* Skip AG headers and post-EOFS blocks */
+		if (!xfs_verify_fsbno(sc->mp, fsbno))
+			continue;
+		bp = xfs_buf_incore(sc->mp->m_ddev_targp,
+				XFS_FSB_TO_DADDR(sc->mp, fsbno),
+				XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
+		if (bp) {
+			xfs_trans_bjoin(sc->tp, bp);
+			xfs_trans_binval(sc->tp, bp);
 		}
 	}
 
@@ -657,11 +471,11 @@ xfs_repair_invalidate_blocks(
 
 /* Ensure the freelist is the correct size. */
 int
-xfs_repair_fix_freelist(
-	struct xfs_scrub_context	*sc,
-	bool				can_shrink)
+xrep_fix_freelist(
+	struct xfs_scrub	*sc,
+	bool			can_shrink)
 {
-	struct xfs_alloc_arg		args = {0};
+	struct xfs_alloc_arg	args = {0};
 
 	args.mp = sc->mp;
 	args.tp = sc->tp;
@@ -677,15 +491,15 @@ xfs_repair_fix_freelist(
  * Put a block back on the AGFL.
  */
 STATIC int
-xfs_repair_put_freelist(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			agbno)
+xrep_put_freelist(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		agbno)
 {
-	struct xfs_owner_info		oinfo;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	int			error;
 
 	/* Make sure there's space on the freelist. */
-	error = xfs_repair_fix_freelist(sc, true);
+	error = xrep_fix_freelist(sc, true);
 	if (error)
 		return error;
 
@@ -711,20 +525,20 @@ xfs_repair_put_freelist(
 	return 0;
 }
 
-/* Dispose of a single metadata block. */
+/* Dispose of a single block. */
 STATIC int
-xfs_repair_dispose_btree_block(
-	struct xfs_scrub_context	*sc,
-	xfs_fsblock_t			fsbno,
-	struct xfs_owner_info		*oinfo,
-	enum xfs_ag_resv_type		resv)
+xrep_reap_block(
+	struct xfs_scrub	*sc,
+	xfs_fsblock_t		fsbno,
+	struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type	resv)
 {
-	struct xfs_btree_cur		*cur;
-	struct xfs_buf			*agf_bp = NULL;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	bool				has_other_rmap;
-	int				error;
+	struct xfs_btree_cur	*cur;
+	struct xfs_buf		*agf_bp = NULL;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	bool			has_other_rmap;
+	int			error;
 
 	agno = XFS_FSB_TO_AGNO(sc->mp, fsbno);
 	agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno);
@@ -747,9 +561,9 @@ xfs_repair_dispose_btree_block(
 
 	/* Can we find any other rmappings? */
 	error = xfs_rmap_has_other_keys(cur, agbno, 1, oinfo, &has_other_rmap);
+	xfs_btree_del_cursor(cur, error);
 	if (error)
-		goto out_cur;
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+		goto out_free;
 
 	/*
 	 * If there are other rmappings, this block is cross linked and must
@@ -767,7 +581,7 @@ xfs_repair_dispose_btree_block(
 	if (has_other_rmap)
 		error = xfs_rmap_free(sc->tp, agf_bp, agno, agbno, 1, oinfo);
 	else if (resv == XFS_AG_RESV_AGFL)
-		error = xfs_repair_put_freelist(sc, agbno);
+		error = xrep_put_freelist(sc, agbno);
 	else
 		error = xfs_free_extent(sc->tp, fsbno, 1, oinfo, resv);
 	if (agf_bp != sc->sa.agf_bp)
@@ -777,50 +591,43 @@ xfs_repair_dispose_btree_block(
 
 	if (sc->ip)
 		return xfs_trans_roll_inode(&sc->tp, sc->ip);
-	return xfs_repair_roll_ag_trans(sc);
+	return xrep_roll_ag_trans(sc);
 
-out_cur:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+out_free:
 	if (agf_bp != sc->sa.agf_bp)
 		xfs_trans_brelse(sc->tp, agf_bp);
 	return error;
 }
 
-/* Dispose of btree blocks from an old per-AG btree. */
+/* Dispose of every block of every extent in the bitmap. */
 int
-xfs_repair_reap_btree_extents(
-	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist,
-	struct xfs_owner_info		*oinfo,
-	enum xfs_ag_resv_type		type)
+xrep_reap_extents(
+	struct xfs_scrub	*sc,
+	struct xfs_bitmap	*bitmap,
+	struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type	type)
 {
-	struct xfs_repair_extent	*rex;
-	struct xfs_repair_extent	*n;
-	int				error = 0;
+	struct xfs_bitmap_range	*bmr;
+	struct xfs_bitmap_range	*n;
+	xfs_fsblock_t		fsbno;
+	int			error = 0;
 
 	ASSERT(xfs_sb_version_hasrmapbt(&sc->mp->m_sb));
 
-	/* Dispose of every block from the old btree. */
-	for_each_xfs_repair_extent_safe(rex, n, exlist) {
+	for_each_xfs_bitmap_block(fsbno, bmr, n, bitmap) {
 		ASSERT(sc->ip != NULL ||
-		       XFS_FSB_TO_AGNO(sc->mp, rex->fsbno) == sc->sa.agno);
+		       XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.agno);
+		trace_xrep_dispose_btree_extent(sc->mp,
+				XFS_FSB_TO_AGNO(sc->mp, fsbno),
+				XFS_FSB_TO_AGBNO(sc->mp, fsbno), 1);
 
-		trace_xfs_repair_dispose_btree_extent(sc->mp,
-				XFS_FSB_TO_AGNO(sc->mp, rex->fsbno),
-				XFS_FSB_TO_AGBNO(sc->mp, rex->fsbno), rex->len);
-
-		for (; rex->len > 0; rex->len--, rex->fsbno++) {
-			error = xfs_repair_dispose_btree_block(sc, rex->fsbno,
-					oinfo, type);
-			if (error)
-				goto out;
-		}
-		list_del(&rex->list);
-		kmem_free(rex);
+		error = xrep_reap_block(sc, fsbno, oinfo, type);
+		if (error)
+			goto out;
 	}
 
 out:
-	xfs_repair_cancel_btree_extents(sc, exlist);
+	xfs_bitmap_destroy(bitmap);
 	return error;
 }
 
@@ -832,12 +639,12 @@ out:
  * btree roots.  This is not guaranteed to work if the AG is heavily damaged
  * or the rmap data are corrupt.
  *
- * Callers of xfs_repair_find_ag_btree_roots must lock the AGF and AGFL
+ * Callers of xrep_find_ag_btree_roots must lock the AGF and AGFL
  * buffers if the AGF is being rebuilt; or the AGF and AGI buffers if the
  * AGI is being rebuilt.  It must maintain these locks until it's safe for
  * other threads to change the btrees' shapes.  The caller provides
  * information about the btrees to look for by passing in an array of
- * xfs_repair_find_ag_btree with the (rmap owner, buf_ops, magic) fields set.
+ * xrep_find_ag_btree with the (rmap owner, buf_ops, magic) fields set.
  * The (root, height) fields will be set on return if anything is found.  The
  * last element of the array should have a NULL buf_ops to mark the end of the
  * array.
@@ -851,30 +658,30 @@ out:
  * should be the roots.
  */
 
-struct xfs_repair_findroot {
-	struct xfs_scrub_context	*sc;
+struct xrep_findroot {
+	struct xfs_scrub		*sc;
 	struct xfs_buf			*agfl_bp;
 	struct xfs_agf			*agf;
-	struct xfs_repair_find_ag_btree	*btree_info;
+	struct xrep_find_ag_btree	*btree_info;
 };
 
 /* See if our block is in the AGFL. */
 STATIC int
-xfs_repair_findroot_agfl_walk(
-	struct xfs_mount		*mp,
-	xfs_agblock_t			bno,
-	void				*priv)
+xrep_findroot_agfl_walk(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		bno,
+	void			*priv)
 {
-	xfs_agblock_t			*agbno = priv;
+	xfs_agblock_t		*agbno = priv;
 
 	return (*agbno == bno) ? XFS_BTREE_QUERY_RANGE_ABORT : 0;
 }
 
 /* Does this block match the btree information passed in? */
 STATIC int
-xfs_repair_findroot_block(
-	struct xfs_repair_findroot	*ri,
-	struct xfs_repair_find_ag_btree	*fab,
+xrep_findroot_block(
+	struct xrep_findroot		*ri,
+	struct xrep_find_ag_btree	*fab,
 	uint64_t			owner,
 	xfs_agblock_t			agbno,
 	bool				*found_it)
@@ -895,7 +702,7 @@ xfs_repair_findroot_block(
 	 */
 	if (owner == XFS_RMAP_OWN_AG) {
 		error = xfs_agfl_walk(mp, ri->agf, ri->agfl_bp,
-				xfs_repair_findroot_agfl_walk, &agbno);
+				xrep_findroot_agfl_walk, &agbno);
 		if (error == XFS_BTREE_QUERY_RANGE_ABORT)
 			return 0;
 		if (error)
@@ -933,7 +740,7 @@ xfs_repair_findroot_block(
 	fab->height = xfs_btree_get_level(btblock) + 1;
 	*found_it = true;
 
-	trace_xfs_repair_findroot_block(mp, ri->sc->sa.agno, agbno,
+	trace_xrep_findroot_block(mp, ri->sc->sa.agno, agbno,
 			be32_to_cpu(btblock->bb_magic), fab->height - 1);
 out:
 	xfs_trans_brelse(ri->sc->tp, bp);
@@ -945,13 +752,13 @@ out:
  * looking for?
  */
 STATIC int
-xfs_repair_findroot_rmap(
+xrep_findroot_rmap(
 	struct xfs_btree_cur		*cur,
 	struct xfs_rmap_irec		*rec,
 	void				*priv)
 {
-	struct xfs_repair_findroot	*ri = priv;
-	struct xfs_repair_find_ag_btree	*fab;
+	struct xrep_findroot		*ri = priv;
+	struct xrep_find_ag_btree	*fab;
 	xfs_agblock_t			b;
 	bool				found_it;
 	int				error = 0;
@@ -966,7 +773,7 @@ xfs_repair_findroot_rmap(
 		for (fab = ri->btree_info; fab->buf_ops; fab++) {
 			if (rec->rm_owner != fab->rmap_owner)
 				continue;
-			error = xfs_repair_findroot_block(ri, fab,
+			error = xrep_findroot_block(ri, fab,
 					rec->rm_owner, rec->rm_startblock + b,
 					&found_it);
 			if (error)
@@ -981,15 +788,15 @@ xfs_repair_findroot_rmap(
 
 /* Find the roots of the per-AG btrees described in btree_info. */
 int
-xfs_repair_find_ag_btree_roots(
-	struct xfs_scrub_context	*sc,
+xrep_find_ag_btree_roots(
+	struct xfs_scrub		*sc,
 	struct xfs_buf			*agf_bp,
-	struct xfs_repair_find_ag_btree	*btree_info,
+	struct xrep_find_ag_btree	*btree_info,
 	struct xfs_buf			*agfl_bp)
 {
 	struct xfs_mount		*mp = sc->mp;
-	struct xfs_repair_findroot	ri;
-	struct xfs_repair_find_ag_btree	*fab;
+	struct xrep_findroot		ri;
+	struct xrep_find_ag_btree	*fab;
 	struct xfs_btree_cur		*cur;
 	int				error;
 
@@ -1008,19 +815,19 @@ xfs_repair_find_ag_btree_roots(
 	}
 
 	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
-	error = xfs_rmap_query_all(cur, xfs_repair_findroot_rmap, &ri);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	error = xfs_rmap_query_all(cur, xrep_findroot_rmap, &ri);
+	xfs_btree_del_cursor(cur, error);
 
 	return error;
 }
 
 /* Force a quotacheck the next time we mount. */
 void
-xfs_repair_force_quotacheck(
-	struct xfs_scrub_context	*sc,
-	uint				dqtype)
+xrep_force_quotacheck(
+	struct xfs_scrub	*sc,
+	uint			dqtype)
 {
-	uint				flag;
+	uint			flag;
 
 	flag = xfs_quota_chkd_flag(dqtype);
 	if (!(flag & sc->mp->m_qflags))
@@ -1044,10 +851,10 @@ xfs_repair_force_quotacheck(
  * repair corruptions in the quota metadata.
  */
 int
-xfs_repair_ino_dqattach(
-	struct xfs_scrub_context	*sc)
+xrep_ino_dqattach(
+	struct xfs_scrub	*sc)
 {
-	int				error;
+	int			error;
 
 	error = xfs_qm_dqattach_locked(sc->ip, false);
 	switch (error) {
@@ -1058,11 +865,11 @@ xfs_repair_ino_dqattach(
 "inode %llu repair encountered quota error %d, quotacheck forced.",
 				(unsigned long long)sc->ip->i_ino, error);
 		if (XFS_IS_UQUOTA_ON(sc->mp) && !sc->ip->i_udquot)
-			xfs_repair_force_quotacheck(sc, XFS_DQ_USER);
+			xrep_force_quotacheck(sc, XFS_DQ_USER);
 		if (XFS_IS_GQUOTA_ON(sc->mp) && !sc->ip->i_gdquot)
-			xfs_repair_force_quotacheck(sc, XFS_DQ_GROUP);
+			xrep_force_quotacheck(sc, XFS_DQ_GROUP);
 		if (XFS_IS_PQUOTA_ON(sc->mp) && !sc->ip->i_pdquot)
-			xfs_repair_force_quotacheck(sc, XFS_DQ_PROJ);
+			xrep_force_quotacheck(sc, XFS_DQ_PROJ);
 		/* fall through */
 	case -ESRCH:
 		error = 0;
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index ef47826b6725..9de321eee4ab 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -6,7 +6,7 @@
 #ifndef __XFS_SCRUB_REPAIR_H__
 #define __XFS_SCRUB_REPAIR_H__
 
-static inline int xfs_repair_notsupported(struct xfs_scrub_context *sc)
+static inline int xrep_notsupported(struct xfs_scrub *sc)
 {
 	return -EOPNOTSUPP;
 }
@@ -15,55 +15,26 @@ static inline int xfs_repair_notsupported(struct xfs_scrub_context *sc)
 
 /* Repair helpers */
 
-int xfs_repair_attempt(struct xfs_inode *ip, struct xfs_scrub_context *sc,
-		bool *fixed);
-void xfs_repair_failure(struct xfs_mount *mp);
-int xfs_repair_roll_ag_trans(struct xfs_scrub_context *sc);
-bool xfs_repair_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
+int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub *sc, bool *fixed);
+void xrep_failure(struct xfs_mount *mp);
+int xrep_roll_ag_trans(struct xfs_scrub *sc);
+bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
 		enum xfs_ag_resv_type type);
-xfs_extlen_t xfs_repair_calc_ag_resblks(struct xfs_scrub_context *sc);
-int xfs_repair_alloc_ag_block(struct xfs_scrub_context *sc,
-		struct xfs_owner_info *oinfo, xfs_fsblock_t *fsbno,
-		enum xfs_ag_resv_type resv);
-int xfs_repair_init_btblock(struct xfs_scrub_context *sc, xfs_fsblock_t fsb,
+xfs_extlen_t xrep_calc_ag_resblks(struct xfs_scrub *sc);
+int xrep_alloc_ag_block(struct xfs_scrub *sc, struct xfs_owner_info *oinfo,
+		xfs_fsblock_t *fsbno, enum xfs_ag_resv_type resv);
+int xrep_init_btblock(struct xfs_scrub *sc, xfs_fsblock_t fsb,
 		struct xfs_buf **bpp, xfs_btnum_t btnum,
 		const struct xfs_buf_ops *ops);
 
-struct xfs_repair_extent {
-	struct list_head		list;
-	xfs_fsblock_t			fsbno;
-	xfs_extlen_t			len;
-};
-
-struct xfs_repair_extent_list {
-	struct list_head		list;
-};
-
-static inline void
-xfs_repair_init_extent_list(
-	struct xfs_repair_extent_list	*exlist)
-{
-	INIT_LIST_HEAD(&exlist->list);
-}
+struct xfs_bitmap;
 
-#define for_each_xfs_repair_extent_safe(rbe, n, exlist) \
-	list_for_each_entry_safe((rbe), (n), &(exlist)->list, list)
-int xfs_repair_collect_btree_extent(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *btlist, xfs_fsblock_t fsbno,
-		xfs_extlen_t len);
-void xfs_repair_cancel_btree_extents(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *btlist);
-int xfs_repair_subtract_extents(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *exlist,
-		struct xfs_repair_extent_list *sublist);
-int xfs_repair_fix_freelist(struct xfs_scrub_context *sc, bool can_shrink);
-int xfs_repair_invalidate_blocks(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *btlist);
-int xfs_repair_reap_btree_extents(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *exlist,
+int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink);
+int xrep_invalidate_blocks(struct xfs_scrub *sc, struct xfs_bitmap *btlist);
+int xrep_reap_extents(struct xfs_scrub *sc, struct xfs_bitmap *exlist,
 		struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
 
-struct xfs_repair_find_ag_btree {
+struct xrep_find_ag_btree {
 	/* in: rmap owner of the btree we're looking for */
 	uint64_t			rmap_owner;
 
@@ -78,40 +49,44 @@ struct xfs_repair_find_ag_btree {
 	unsigned int			height;
 };
 
-int xfs_repair_find_ag_btree_roots(struct xfs_scrub_context *sc,
-		struct xfs_buf *agf_bp,
-		struct xfs_repair_find_ag_btree *btree_info,
-		struct xfs_buf *agfl_bp);
-void xfs_repair_force_quotacheck(struct xfs_scrub_context *sc, uint dqtype);
-int xfs_repair_ino_dqattach(struct xfs_scrub_context *sc);
+int xrep_find_ag_btree_roots(struct xfs_scrub *sc, struct xfs_buf *agf_bp,
+		struct xrep_find_ag_btree *btree_info, struct xfs_buf *agfl_bp);
+void xrep_force_quotacheck(struct xfs_scrub *sc, uint dqtype);
+int xrep_ino_dqattach(struct xfs_scrub *sc);
 
 /* Metadata repairers */
 
-int xfs_repair_probe(struct xfs_scrub_context *sc);
-int xfs_repair_superblock(struct xfs_scrub_context *sc);
+int xrep_probe(struct xfs_scrub *sc);
+int xrep_superblock(struct xfs_scrub *sc);
+int xrep_agf(struct xfs_scrub *sc);
+int xrep_agfl(struct xfs_scrub *sc);
+int xrep_agi(struct xfs_scrub *sc);
 
 #else
 
-static inline int xfs_repair_attempt(
-	struct xfs_inode		*ip,
-	struct xfs_scrub_context	*sc,
-	bool				*fixed)
+static inline int xrep_attempt(
+	struct xfs_inode	*ip,
+	struct xfs_scrub	*sc,
+	bool			*fixed)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline void xfs_repair_failure(struct xfs_mount *mp) {}
+static inline void xrep_failure(struct xfs_mount *mp) {}
 
 static inline xfs_extlen_t
-xfs_repair_calc_ag_resblks(
-	struct xfs_scrub_context	*sc)
+xrep_calc_ag_resblks(
+	struct xfs_scrub	*sc)
 {
 	ASSERT(!(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR));
 	return 0;
 }
 
-#define xfs_repair_probe		xfs_repair_notsupported
-#define xfs_repair_superblock		xfs_repair_notsupported
+#define xrep_probe			xrep_notsupported
+#define xrep_superblock			xrep_notsupported
+#define xrep_agf			xrep_notsupported
+#define xrep_agfl			xrep_notsupported
+#define xrep_agi			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index c6d763236ba7..5e293c129813 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -29,30 +29,30 @@
  * Set us up to scrub reverse mapping btrees.
  */
 int
-xfs_scrub_setup_ag_rmapbt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_ag_rmapbt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, ip, false);
 }
 
 /* Reverse-mapping scrubber. */
 
 /* Cross-reference a rmap against the refcount btree. */
 STATIC void
-xfs_scrub_rmapbt_xref_refc(
-	struct xfs_scrub_context	*sc,
-	struct xfs_rmap_irec		*irec)
+xchk_rmapbt_xref_refc(
+	struct xfs_scrub	*sc,
+	struct xfs_rmap_irec	*irec)
 {
-	xfs_agblock_t			fbno;
-	xfs_extlen_t			flen;
-	bool				non_inode;
-	bool				is_bmbt;
-	bool				is_attr;
-	bool				is_unwritten;
-	int				error;
-
-	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	bool			non_inode;
+	bool			is_bmbt;
+	bool			is_attr;
+	bool			is_unwritten;
+	int			error;
+
+	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	non_inode = XFS_RMAP_NON_INODE_OWNER(irec->rm_owner);
@@ -63,58 +63,58 @@ xfs_scrub_rmapbt_xref_refc(
 	/* If this is shared, must be a data fork extent. */
 	error = xfs_refcount_find_shared(sc->sa.refc_cur, irec->rm_startblock,
 			irec->rm_blockcount, &fbno, &flen, false);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (flen != 0 && (non_inode || is_attr || is_bmbt || is_unwritten))
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_rmapbt_xref(
-	struct xfs_scrub_context	*sc,
-	struct xfs_rmap_irec		*irec)
+xchk_rmapbt_xref(
+	struct xfs_scrub	*sc,
+	struct xfs_rmap_irec	*irec)
 {
-	xfs_agblock_t			agbno = irec->rm_startblock;
-	xfs_extlen_t			len = irec->rm_blockcount;
+	xfs_agblock_t		agbno = irec->rm_startblock;
+	xfs_extlen_t		len = irec->rm_blockcount;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, len);
+	xchk_xref_is_used_space(sc, agbno, len);
 	if (irec->rm_owner == XFS_RMAP_OWN_INODES)
-		xfs_scrub_xref_is_inode_chunk(sc, agbno, len);
+		xchk_xref_is_inode_chunk(sc, agbno, len);
 	else
-		xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
+		xchk_xref_is_not_inode_chunk(sc, agbno, len);
 	if (irec->rm_owner == XFS_RMAP_OWN_COW)
-		xfs_scrub_xref_is_cow_staging(sc, irec->rm_startblock,
+		xchk_xref_is_cow_staging(sc, irec->rm_startblock,
 				irec->rm_blockcount);
 	else
-		xfs_scrub_rmapbt_xref_refc(sc, irec);
+		xchk_rmapbt_xref_refc(sc, irec);
 }
 
 /* Scrub an rmapbt record. */
 STATIC int
-xfs_scrub_rmapbt_rec(
-	struct xfs_scrub_btree		*bs,
-	union xfs_btree_rec		*rec)
+xchk_rmapbt_rec(
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
-	struct xfs_rmap_irec		irec;
-	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
-	bool				non_inode;
-	bool				is_unwritten;
-	bool				is_bmbt;
-	bool				is_attr;
-	int				error;
+	struct xfs_mount	*mp = bs->cur->bc_mp;
+	struct xfs_rmap_irec	irec;
+	xfs_agnumber_t		agno = bs->cur->bc_private.a.agno;
+	bool			non_inode;
+	bool			is_unwritten;
+	bool			is_bmbt;
+	bool			is_attr;
+	int			error;
 
 	error = xfs_rmap_btrec_to_irec(rec, &irec);
-	if (!xfs_scrub_btree_process_error(bs->sc, bs->cur, 0, &error))
+	if (!xchk_btree_process_error(bs->sc, bs->cur, 0, &error))
 		goto out;
 
 	/* Check extent. */
 	if (irec.rm_startblock + irec.rm_blockcount <= irec.rm_startblock)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (irec.rm_owner == XFS_RMAP_OWN_FS) {
 		/*
@@ -124,7 +124,7 @@ xfs_scrub_rmapbt_rec(
 		 */
 		if (irec.rm_startblock != 0 ||
 		    irec.rm_blockcount != XFS_AGFL_BLOCK(mp) + 1)
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	} else {
 		/*
 		 * Otherwise we must point somewhere past the static metadata
@@ -133,7 +133,7 @@ xfs_scrub_rmapbt_rec(
 		if (!xfs_verify_agbno(mp, agno, irec.rm_startblock) ||
 		    !xfs_verify_agbno(mp, agno, irec.rm_startblock +
 				irec.rm_blockcount - 1))
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	}
 
 	/* Check flags. */
@@ -143,105 +143,105 @@ xfs_scrub_rmapbt_rec(
 	is_unwritten = irec.rm_flags & XFS_RMAP_UNWRITTEN;
 
 	if (is_bmbt && irec.rm_offset != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (non_inode && irec.rm_offset != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (is_unwritten && (is_bmbt || non_inode || is_attr))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (non_inode && (is_bmbt || is_unwritten || is_attr))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (!non_inode) {
 		if (!xfs_verify_ino(mp, irec.rm_owner))
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	} else {
 		/* Non-inode owner within the magic values? */
 		if (irec.rm_owner <= XFS_RMAP_OWN_MIN ||
 		    irec.rm_owner > XFS_RMAP_OWN_FS)
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	}
 
-	xfs_scrub_rmapbt_xref(bs->sc, &irec);
+	xchk_rmapbt_xref(bs->sc, &irec);
 out:
 	return error;
 }
 
 /* Scrub the rmap btree for some AG. */
 int
-xfs_scrub_rmapbt(
-	struct xfs_scrub_context	*sc)
+xchk_rmapbt(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
+	struct xfs_owner_info	oinfo;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
-	return xfs_scrub_btree(sc, sc->sa.rmap_cur, xfs_scrub_rmapbt_rec,
+	return xchk_btree(sc, sc->sa.rmap_cur, xchk_rmapbt_rec,
 			&oinfo, NULL);
 }
 
 /* xref check that the extent is owned by a given owner */
 static inline void
-xfs_scrub_xref_check_owner(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	struct xfs_owner_info		*oinfo,
-	bool				should_have_rmap)
+xchk_xref_check_owner(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo,
+	bool			should_have_rmap)
 {
-	bool				has_rmap;
-	int				error;
+	bool			has_rmap;
+	int			error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_rmap_record_exists(sc->sa.rmap_cur, bno, len, oinfo,
 			&has_rmap);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (has_rmap != should_have_rmap)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* xref check that the extent is owned by a given owner */
 void
-xfs_scrub_xref_is_owned_by(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	struct xfs_owner_info		*oinfo)
+xchk_xref_is_owned_by(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo)
 {
-	xfs_scrub_xref_check_owner(sc, bno, len, oinfo, true);
+	xchk_xref_check_owner(sc, bno, len, oinfo, true);
 }
 
 /* xref check that the extent is not owned by a given owner */
 void
-xfs_scrub_xref_is_not_owned_by(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	struct xfs_owner_info		*oinfo)
+xchk_xref_is_not_owned_by(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo)
 {
-	xfs_scrub_xref_check_owner(sc, bno, len, oinfo, false);
+	xchk_xref_check_owner(sc, bno, len, oinfo, false);
 }
 
 /* xref check that the extent has no reverse mapping at all */
 void
-xfs_scrub_xref_has_no_owner(
-	struct xfs_scrub_context	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len)
+xchk_xref_has_no_owner(
+	struct xfs_scrub	*sc,
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len)
 {
-	bool				has_rmap;
-	int				error;
+	bool			has_rmap;
+	int			error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_rmap_has_record(sc->sa.rmap_cur, bno, len, &has_rmap);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (has_rmap)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 1f86e02a07ca..665d4bbb17cc 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -25,13 +25,13 @@
 
 /* Set us up with the realtime metadata locked. */
 int
-xfs_scrub_setup_rt(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_rt(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
-	int				error;
+	int			error;
 
-	error = xfs_scrub_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc, ip);
 	if (error)
 		return error;
 
@@ -46,14 +46,14 @@ xfs_scrub_setup_rt(
 
 /* Scrub a free extent record from the realtime bitmap. */
 STATIC int
-xfs_scrub_rtbitmap_rec(
-	struct xfs_trans		*tp,
-	struct xfs_rtalloc_rec		*rec,
-	void				*priv)
+xchk_rtbitmap_rec(
+	struct xfs_trans	*tp,
+	struct xfs_rtalloc_rec	*rec,
+	void			*priv)
 {
-	struct xfs_scrub_context	*sc = priv;
-	xfs_rtblock_t			startblock;
-	xfs_rtblock_t			blockcount;
+	struct xfs_scrub	*sc = priv;
+	xfs_rtblock_t		startblock;
+	xfs_rtblock_t		blockcount;
 
 	startblock = rec->ar_startext * tp->t_mountp->m_sb.sb_rextsize;
 	blockcount = rec->ar_extcount * tp->t_mountp->m_sb.sb_rextsize;
@@ -61,24 +61,24 @@ xfs_scrub_rtbitmap_rec(
 	if (startblock + blockcount <= startblock ||
 	    !xfs_verify_rtbno(sc->mp, startblock) ||
 	    !xfs_verify_rtbno(sc->mp, startblock + blockcount - 1))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 	return 0;
 }
 
 /* Scrub the realtime bitmap. */
 int
-xfs_scrub_rtbitmap(
-	struct xfs_scrub_context	*sc)
+xchk_rtbitmap(
+	struct xfs_scrub	*sc)
 {
-	int				error;
+	int			error;
 
 	/* Invoke the fork scrubber. */
-	error = xfs_scrub_metadata_inode_forks(sc);
+	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 
-	error = xfs_rtalloc_query_all(sc->tp, xfs_scrub_rtbitmap_rec, sc);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	error = xfs_rtalloc_query_all(sc->tp, xchk_rtbitmap_rec, sc);
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 
 out:
@@ -87,13 +87,13 @@ out:
 
 /* Scrub the realtime summary. */
 int
-xfs_scrub_rtsummary(
-	struct xfs_scrub_context	*sc)
+xchk_rtsummary(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_inode		*rsumip = sc->mp->m_rsumip;
-	struct xfs_inode		*old_ip = sc->ip;
-	uint				old_ilock_flags = sc->ilock_flags;
-	int				error = 0;
+	struct xfs_inode	*rsumip = sc->mp->m_rsumip;
+	struct xfs_inode	*old_ip = sc->ip;
+	uint			old_ilock_flags = sc->ilock_flags;
+	int			error = 0;
 
 	/*
 	 * We ILOCK'd the rt bitmap ip in the setup routine, now lock the
@@ -107,12 +107,12 @@ xfs_scrub_rtsummary(
 	xfs_ilock(sc->ip, sc->ilock_flags);
 
 	/* Invoke the fork scrubber. */
-	error = xfs_scrub_metadata_inode_forks(sc);
+	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		goto out;
 
 	/* XXX: implement this some day */
-	xfs_scrub_set_incomplete(sc);
+	xchk_set_incomplete(sc);
 out:
 	/* Switch back to the rtbitmap inode and lock flags. */
 	xfs_iunlock(sc->ip, sc->ilock_flags);
@@ -124,18 +124,18 @@ out:
 
 /* xref check that the extent is not free in the rtbitmap */
 void
-xfs_scrub_xref_is_used_rt_space(
-	struct xfs_scrub_context	*sc,
-	xfs_rtblock_t			fsbno,
-	xfs_extlen_t			len)
+xchk_xref_is_used_rt_space(
+	struct xfs_scrub	*sc,
+	xfs_rtblock_t		fsbno,
+	xfs_extlen_t		len)
 {
-	xfs_rtblock_t			startext;
-	xfs_rtblock_t			endext;
-	xfs_rtblock_t			extcount;
-	bool				is_free;
-	int				error;
+	xfs_rtblock_t		startext;
+	xfs_rtblock_t		endext;
+	xfs_rtblock_t		extcount;
+	bool			is_free;
+	int			error;
 
-	if (xfs_scrub_skip_xref(sc->sm))
+	if (xchk_skip_xref(sc->sm))
 		return;
 
 	startext = fsbno;
@@ -147,10 +147,10 @@ xfs_scrub_xref_is_used_rt_space(
 	xfs_ilock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 	error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, startext, extcount,
 			&is_free);
-	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
+	if (!xchk_should_check_xref(sc, &error, NULL))
 		goto out_unlock;
 	if (is_free)
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
 out_unlock:
 	xfs_iunlock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 }
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 58ae76b3a421..4bfae1e61d30 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -131,6 +131,12 @@
  * optimize the structure so that the rebuild knows what to do.  The
  * second check evaluates the completeness of the repair; that is what
  * is reported to userspace.
+ *
+ * A quick note on symbol prefixes:
+ * - "xfs_" are general XFS symbols.
+ * - "xchk_" are symbols related to metadata checking.
+ * - "xrep_" are symbols related to metadata repair.
+ * - "xfs_scrub_" are symbols that tie online fsck to the rest of XFS.
  */
 
 /*
@@ -144,12 +150,12 @@
  * supported by the running kernel.
  */
 static int
-xfs_scrub_probe(
-	struct xfs_scrub_context	*sc)
+xchk_probe(
+	struct xfs_scrub	*sc)
 {
-	int				error = 0;
+	int			error = 0;
 
-	if (xfs_scrub_should_terminate(sc, &error))
+	if (xchk_should_terminate(sc, &error))
 		return error;
 
 	return 0;
@@ -159,12 +165,12 @@ xfs_scrub_probe(
 
 /* Free all the resources and finish the transactions. */
 STATIC int
-xfs_scrub_teardown(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip_in,
-	int				error)
+xchk_teardown(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip_in,
+	int			error)
 {
-	xfs_scrub_ag_free(sc, &sc->sa);
+	xchk_ag_free(sc, &sc->sa);
 	if (sc->tp) {
 		if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
 			error = xfs_trans_commit(sc->tp);
@@ -177,7 +183,7 @@ xfs_scrub_teardown(
 			xfs_iunlock(sc->ip, sc->ilock_flags);
 		if (sc->ip != ip_in &&
 		    !xfs_internal_inum(sc->mp, sc->ip->i_ino))
-			iput(VFS_I(sc->ip));
+			xfs_irele(sc->ip);
 		sc->ip = NULL;
 	}
 	if (sc->has_quotaofflock)
@@ -191,165 +197,165 @@ xfs_scrub_teardown(
 
 /* Scrubbing dispatch. */
 
-static const struct xfs_scrub_meta_ops meta_scrub_ops[] = {
+static const struct xchk_meta_ops meta_scrub_ops[] = {
 	[XFS_SCRUB_TYPE_PROBE] = {	/* ioctl presence test */
 		.type	= ST_NONE,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_probe,
-		.repair = xfs_repair_probe,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_probe,
+		.repair = xrep_probe,
 	},
 	[XFS_SCRUB_TYPE_SB] = {		/* superblock */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_superblock,
-		.repair	= xfs_repair_superblock,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_superblock,
+		.repair	= xrep_superblock,
 	},
 	[XFS_SCRUB_TYPE_AGF] = {	/* agf */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_agf,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_agf,
+		.repair	= xrep_agf,
 	},
 	[XFS_SCRUB_TYPE_AGFL]= {	/* agfl */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_agfl,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_agfl,
+		.repair	= xrep_agfl,
 	},
 	[XFS_SCRUB_TYPE_AGI] = {	/* agi */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_agi,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_agi,
+		.repair	= xrep_agi,
 	},
 	[XFS_SCRUB_TYPE_BNOBT] = {	/* bnobt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_allocbt,
-		.scrub	= xfs_scrub_bnobt,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_ag_allocbt,
+		.scrub	= xchk_bnobt,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_CNTBT] = {	/* cntbt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_allocbt,
-		.scrub	= xfs_scrub_cntbt,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_ag_allocbt,
+		.scrub	= xchk_cntbt,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INOBT] = {	/* inobt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_iallocbt,
-		.scrub	= xfs_scrub_inobt,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_ag_iallocbt,
+		.scrub	= xchk_inobt,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_FINOBT] = {	/* finobt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_iallocbt,
-		.scrub	= xfs_scrub_finobt,
+		.setup	= xchk_setup_ag_iallocbt,
+		.scrub	= xchk_finobt,
 		.has	= xfs_sb_version_hasfinobt,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RMAPBT] = {	/* rmapbt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_rmapbt,
-		.scrub	= xfs_scrub_rmapbt,
+		.setup	= xchk_setup_ag_rmapbt,
+		.scrub	= xchk_rmapbt,
 		.has	= xfs_sb_version_hasrmapbt,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_REFCNTBT] = {	/* refcountbt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_refcountbt,
-		.scrub	= xfs_scrub_refcountbt,
+		.setup	= xchk_setup_ag_refcountbt,
+		.scrub	= xchk_refcountbt,
 		.has	= xfs_sb_version_hasreflink,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INODE] = {	/* inode record */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode,
-		.scrub	= xfs_scrub_inode,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_inode,
+		.scrub	= xchk_inode,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTD] = {	/* inode data fork */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode_bmap,
-		.scrub	= xfs_scrub_bmap_data,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_inode_bmap,
+		.scrub	= xchk_bmap_data,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTA] = {	/* inode attr fork */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode_bmap,
-		.scrub	= xfs_scrub_bmap_attr,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_inode_bmap,
+		.scrub	= xchk_bmap_attr,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTC] = {	/* inode CoW fork */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode_bmap,
-		.scrub	= xfs_scrub_bmap_cow,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_inode_bmap,
+		.scrub	= xchk_bmap_cow,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_DIR] = {	/* directory */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_directory,
-		.scrub	= xfs_scrub_directory,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_directory,
+		.scrub	= xchk_directory,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_XATTR] = {	/* extended attributes */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_xattr,
-		.scrub	= xfs_scrub_xattr,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_xattr,
+		.scrub	= xchk_xattr,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_SYMLINK] = {	/* symbolic link */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_symlink,
-		.scrub	= xfs_scrub_symlink,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_symlink,
+		.scrub	= xchk_symlink,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PARENT] = {	/* parent pointers */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_parent,
-		.scrub	= xfs_scrub_parent,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_parent,
+		.scrub	= xchk_parent,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_rt,
-		.scrub	= xfs_scrub_rtbitmap,
+		.setup	= xchk_setup_rt,
+		.scrub	= xchk_rtbitmap,
 		.has	= xfs_sb_version_hasrealtime,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_rt,
-		.scrub	= xfs_scrub_rtsummary,
+		.setup	= xchk_setup_rt,
+		.scrub	= xchk_rtsummary,
 		.has	= xfs_sb_version_hasrealtime,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_UQUOTA] = {	/* user quota */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_quota,
-		.scrub	= xfs_scrub_quota,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_quota,
+		.scrub	= xchk_quota,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_GQUOTA] = {	/* group quota */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_quota,
-		.scrub	= xfs_scrub_quota,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_quota,
+		.scrub	= xchk_quota,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PQUOTA] = {	/* project quota */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_quota,
-		.scrub	= xfs_scrub_quota,
-		.repair	= xfs_repair_notsupported,
+		.setup	= xchk_setup_quota,
+		.scrub	= xchk_quota,
+		.repair	= xrep_notsupported,
 	},
 };
 
 /* This isn't a stable feature, warn once per day. */
 static inline void
-xfs_scrub_experimental_warning(
+xchk_experimental_warning(
 	struct xfs_mount	*mp)
 {
 	static struct ratelimit_state scrub_warning = RATELIMIT_STATE_INIT(
-			"xfs_scrub_warning", 86400 * HZ, 1);
+			"xchk_warning", 86400 * HZ, 1);
 	ratelimit_set_flags(&scrub_warning, RATELIMIT_MSG_ON_RELEASE);
 
 	if (__ratelimit(&scrub_warning))
@@ -358,12 +364,12 @@ xfs_scrub_experimental_warning(
 }
 
 static int
-xfs_scrub_validate_inputs(
+xchk_validate_inputs(
 	struct xfs_mount		*mp,
 	struct xfs_scrub_metadata	*sm)
 {
 	int				error;
-	const struct xfs_scrub_meta_ops	*ops;
+	const struct xchk_meta_ops	*ops;
 
 	error = -EINVAL;
 	/* Check our inputs. */
@@ -441,7 +447,7 @@ out:
 }
 
 #ifdef CONFIG_XFS_ONLINE_REPAIR
-static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+static inline void xchk_postmortem(struct xfs_scrub *sc)
 {
 	/*
 	 * Userspace asked us to repair something, we repaired it, rescanned
@@ -451,10 +457,10 @@ static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
 	if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
 	    (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
 				 XFS_SCRUB_OFLAG_XCORRUPT)))
-		xfs_repair_failure(sc->mp);
+		xrep_failure(sc->mp);
 }
 #else
-static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+static inline void xchk_postmortem(struct xfs_scrub *sc)
 {
 	/*
 	 * Userspace asked us to scrub something, it's broken, and we have no
@@ -473,16 +479,16 @@ xfs_scrub_metadata(
 	struct xfs_inode		*ip,
 	struct xfs_scrub_metadata	*sm)
 {
-	struct xfs_scrub_context	sc;
+	struct xfs_scrub		sc;
 	struct xfs_mount		*mp = ip->i_mount;
 	bool				try_harder = false;
 	bool				already_fixed = false;
 	int				error = 0;
 
 	BUILD_BUG_ON(sizeof(meta_scrub_ops) !=
-		(sizeof(struct xfs_scrub_meta_ops) * XFS_SCRUB_TYPE_NR));
+		(sizeof(struct xchk_meta_ops) * XFS_SCRUB_TYPE_NR));
 
-	trace_xfs_scrub_start(ip, sm, error);
+	trace_xchk_start(ip, sm, error);
 
 	/* Forbidden if we are shut down or mounted norecovery. */
 	error = -ESHUTDOWN;
@@ -492,11 +498,11 @@ xfs_scrub_metadata(
 	if (mp->m_flags & XFS_MOUNT_NORECOVERY)
 		goto out;
 
-	error = xfs_scrub_validate_inputs(mp, sm);
+	error = xchk_validate_inputs(mp, sm);
 	if (error)
 		goto out;
 
-	xfs_scrub_experimental_warning(mp);
+	xchk_experimental_warning(mp);
 
 retry_op:
 	/* Set up for the operation. */
@@ -518,7 +524,7 @@ retry_op:
 		 * Tear down everything we hold, then set up again with
 		 * preparation for worst-case scenarios.
 		 */
-		error = xfs_scrub_teardown(&sc, ip, 0);
+		error = xchk_teardown(&sc, ip, 0);
 		if (error)
 			goto out;
 		try_harder = true;
@@ -549,13 +555,13 @@ retry_op:
 		 * If it's broken, userspace wants us to fix it, and we haven't
 		 * already tried to fix it, then attempt a repair.
 		 */
-		error = xfs_repair_attempt(ip, &sc, &already_fixed);
+		error = xrep_attempt(ip, &sc, &already_fixed);
 		if (error == -EAGAIN) {
 			if (sc.try_harder)
 				try_harder = true;
-			error = xfs_scrub_teardown(&sc, ip, 0);
+			error = xchk_teardown(&sc, ip, 0);
 			if (error) {
-				xfs_repair_failure(mp);
+				xrep_failure(mp);
 				goto out;
 			}
 			goto retry_op;
@@ -563,11 +569,11 @@ retry_op:
 	}
 
 out_nofix:
-	xfs_scrub_postmortem(&sc);
+	xchk_postmortem(&sc);
 out_teardown:
-	error = xfs_scrub_teardown(&sc, ip, error);
+	error = xchk_teardown(&sc, ip, error);
 out:
-	trace_xfs_scrub_done(ip, sm, error);
+	trace_xchk_done(ip, sm, error);
 	if (error == -EFSCORRUPTED || error == -EFSBADCRC) {
 		sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 		error = 0;
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index b295edd5fc0e..af323b229c4b 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -6,58 +6,58 @@
 #ifndef __XFS_SCRUB_SCRUB_H__
 #define __XFS_SCRUB_SCRUB_H__
 
-struct xfs_scrub_context;
+struct xfs_scrub;
 
 /* Type info and names for the scrub types. */
-enum xfs_scrub_type {
+enum xchk_type {
 	ST_NONE = 1,	/* disabled */
 	ST_PERAG,	/* per-AG metadata */
 	ST_FS,		/* per-FS metadata */
 	ST_INODE,	/* per-inode metadata */
 };
 
-struct xfs_scrub_meta_ops {
+struct xchk_meta_ops {
 	/* Acquire whatever resources are needed for the operation. */
-	int		(*setup)(struct xfs_scrub_context *,
+	int		(*setup)(struct xfs_scrub *,
 				 struct xfs_inode *);
 
 	/* Examine metadata for errors. */
-	int		(*scrub)(struct xfs_scrub_context *);
+	int		(*scrub)(struct xfs_scrub *);
 
 	/* Repair or optimize the metadata. */
-	int		(*repair)(struct xfs_scrub_context *);
+	int		(*repair)(struct xfs_scrub *);
 
 	/* Decide if we even have this piece of metadata. */
 	bool		(*has)(struct xfs_sb *);
 
 	/* type describing required/allowed inputs */
-	enum xfs_scrub_type	type;
+	enum xchk_type	type;
 };
 
 /* Buffer pointers and btree cursors for an entire AG. */
-struct xfs_scrub_ag {
-	xfs_agnumber_t			agno;
-	struct xfs_perag		*pag;
+struct xchk_ag {
+	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag;
 
 	/* AG btree roots */
-	struct xfs_buf			*agf_bp;
-	struct xfs_buf			*agfl_bp;
-	struct xfs_buf			*agi_bp;
+	struct xfs_buf		*agf_bp;
+	struct xfs_buf		*agfl_bp;
+	struct xfs_buf		*agi_bp;
 
 	/* AG btrees */
-	struct xfs_btree_cur		*bno_cur;
-	struct xfs_btree_cur		*cnt_cur;
-	struct xfs_btree_cur		*ino_cur;
-	struct xfs_btree_cur		*fino_cur;
-	struct xfs_btree_cur		*rmap_cur;
-	struct xfs_btree_cur		*refc_cur;
+	struct xfs_btree_cur	*bno_cur;
+	struct xfs_btree_cur	*cnt_cur;
+	struct xfs_btree_cur	*ino_cur;
+	struct xfs_btree_cur	*fino_cur;
+	struct xfs_btree_cur	*rmap_cur;
+	struct xfs_btree_cur	*refc_cur;
 };
 
-struct xfs_scrub_context {
+struct xfs_scrub {
 	/* General scrub state. */
 	struct xfs_mount		*mp;
 	struct xfs_scrub_metadata	*sm;
-	const struct xfs_scrub_meta_ops	*ops;
+	const struct xchk_meta_ops	*ops;
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip;
 	void				*buf;
@@ -66,78 +66,76 @@ struct xfs_scrub_context {
 	bool				has_quotaofflock;
 
 	/* State tracking for single-AG operations. */
-	struct xfs_scrub_ag		sa;
+	struct xchk_ag			sa;
 };
 
 /* Metadata scrubbers */
-int xfs_scrub_tester(struct xfs_scrub_context *sc);
-int xfs_scrub_superblock(struct xfs_scrub_context *sc);
-int xfs_scrub_agf(struct xfs_scrub_context *sc);
-int xfs_scrub_agfl(struct xfs_scrub_context *sc);
-int xfs_scrub_agi(struct xfs_scrub_context *sc);
-int xfs_scrub_bnobt(struct xfs_scrub_context *sc);
-int xfs_scrub_cntbt(struct xfs_scrub_context *sc);
-int xfs_scrub_inobt(struct xfs_scrub_context *sc);
-int xfs_scrub_finobt(struct xfs_scrub_context *sc);
-int xfs_scrub_rmapbt(struct xfs_scrub_context *sc);
-int xfs_scrub_refcountbt(struct xfs_scrub_context *sc);
-int xfs_scrub_inode(struct xfs_scrub_context *sc);
-int xfs_scrub_bmap_data(struct xfs_scrub_context *sc);
-int xfs_scrub_bmap_attr(struct xfs_scrub_context *sc);
-int xfs_scrub_bmap_cow(struct xfs_scrub_context *sc);
-int xfs_scrub_directory(struct xfs_scrub_context *sc);
-int xfs_scrub_xattr(struct xfs_scrub_context *sc);
-int xfs_scrub_symlink(struct xfs_scrub_context *sc);
-int xfs_scrub_parent(struct xfs_scrub_context *sc);
+int xchk_tester(struct xfs_scrub *sc);
+int xchk_superblock(struct xfs_scrub *sc);
+int xchk_agf(struct xfs_scrub *sc);
+int xchk_agfl(struct xfs_scrub *sc);
+int xchk_agi(struct xfs_scrub *sc);
+int xchk_bnobt(struct xfs_scrub *sc);
+int xchk_cntbt(struct xfs_scrub *sc);
+int xchk_inobt(struct xfs_scrub *sc);
+int xchk_finobt(struct xfs_scrub *sc);
+int xchk_rmapbt(struct xfs_scrub *sc);
+int xchk_refcountbt(struct xfs_scrub *sc);
+int xchk_inode(struct xfs_scrub *sc);
+int xchk_bmap_data(struct xfs_scrub *sc);
+int xchk_bmap_attr(struct xfs_scrub *sc);
+int xchk_bmap_cow(struct xfs_scrub *sc);
+int xchk_directory(struct xfs_scrub *sc);
+int xchk_xattr(struct xfs_scrub *sc);
+int xchk_symlink(struct xfs_scrub *sc);
+int xchk_parent(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
-int xfs_scrub_rtbitmap(struct xfs_scrub_context *sc);
-int xfs_scrub_rtsummary(struct xfs_scrub_context *sc);
+int xchk_rtbitmap(struct xfs_scrub *sc);
+int xchk_rtsummary(struct xfs_scrub *sc);
 #else
 static inline int
-xfs_scrub_rtbitmap(struct xfs_scrub_context *sc)
+xchk_rtbitmap(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 static inline int
-xfs_scrub_rtsummary(struct xfs_scrub_context *sc)
+xchk_rtsummary(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
-int xfs_scrub_quota(struct xfs_scrub_context *sc);
+int xchk_quota(struct xfs_scrub *sc);
 #else
 static inline int
-xfs_scrub_quota(struct xfs_scrub_context *sc)
+xchk_quota(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 #endif
 
 /* cross-referencing helpers */
-void xfs_scrub_xref_is_used_space(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_not_inode_chunk(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_inode_chunk(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_owned_by(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len,
-		struct xfs_owner_info *oinfo);
-void xfs_scrub_xref_is_not_owned_by(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len,
-		struct xfs_owner_info *oinfo);
-void xfs_scrub_xref_has_no_owner(struct xfs_scrub_context *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_cow_staging(struct xfs_scrub_context *sc,
-		xfs_agblock_t bno, xfs_extlen_t len);
-void xfs_scrub_xref_is_not_shared(struct xfs_scrub_context *sc,
-		xfs_agblock_t bno, xfs_extlen_t len);
+void xchk_xref_is_used_space(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_not_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo);
+void xchk_xref_is_not_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo);
+void xchk_xref_has_no_owner(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_cow_staging(struct xfs_scrub *sc, xfs_agblock_t bno,
+		xfs_extlen_t len);
+void xchk_xref_is_not_shared(struct xfs_scrub *sc, xfs_agblock_t bno,
+		xfs_extlen_t len);
 #ifdef CONFIG_XFS_RT
-void xfs_scrub_xref_is_used_rt_space(struct xfs_scrub_context *sc,
-		xfs_rtblock_t rtbno, xfs_extlen_t len);
+void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno,
+		xfs_extlen_t len);
 #else
-# define xfs_scrub_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
+# define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
 #endif
 
 #endif	/* __XFS_SCRUB_SCRUB_H__ */
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 570a89812116..f7ebaa946999 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -25,28 +25,28 @@
 
 /* Set us up to scrub a symbolic link. */
 int
-xfs_scrub_setup_symlink(
-	struct xfs_scrub_context	*sc,
-	struct xfs_inode		*ip)
+xchk_setup_symlink(
+	struct xfs_scrub	*sc,
+	struct xfs_inode	*ip)
 {
 	/* Allocate the buffer without the inode lock held. */
 	sc->buf = kmem_zalloc_large(XFS_SYMLINK_MAXLEN + 1, KM_SLEEP);
 	if (!sc->buf)
 		return -ENOMEM;
 
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Symbolic links. */
 
 int
-xfs_scrub_symlink(
-	struct xfs_scrub_context	*sc)
+xchk_symlink(
+	struct xfs_scrub	*sc)
 {
-	struct xfs_inode		*ip = sc->ip;
-	struct xfs_ifork		*ifp;
-	loff_t				len;
-	int				error = 0;
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_ifork	*ifp;
+	loff_t			len;
+	int			error = 0;
 
 	if (!S_ISLNK(VFS_I(ip)->i_mode))
 		return -ENOENT;
@@ -55,7 +55,7 @@ xfs_scrub_symlink(
 
 	/* Plausible size? */
 	if (len > XFS_SYMLINK_MAXLEN || len <= 0) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -63,16 +63,16 @@ xfs_scrub_symlink(
 	if (ifp->if_flags & XFS_IFINLINE) {
 		if (len > XFS_IFORK_DSIZE(ip) ||
 		    len > strnlen(ifp->if_u1.if_data, XFS_IFORK_DSIZE(ip)))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
 	/* Remote symlink; must read the contents. */
 	error = xfs_readlink_bmap_ilocked(sc->ip, sc->buf);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 	if (strnlen(sc->buf, XFS_SYMLINK_MAXLEN) < len)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 7c76d8b5cb05..96feaf8dcdec 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -22,9 +22,9 @@
 
 /* Figure out which block the btree cursor was pointing to. */
 static inline xfs_fsblock_t
-xfs_scrub_btree_cur_fsbno(
-	struct xfs_btree_cur		*cur,
-	int				level)
+xchk_btree_cur_fsbno(
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
 	if (level < cur->bc_nlevels && cur->bc_bufs[level])
 		return XFS_DADDR_TO_FSB(cur->bc_mp, cur->bc_bufs[level]->b_bn);
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index cec3e5ece5a1..4e20f0e48232 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -12,7 +12,7 @@
 #include <linux/tracepoint.h>
 #include "xfs_bit.h"
 
-DECLARE_EVENT_CLASS(xfs_scrub_class,
+DECLARE_EVENT_CLASS(xchk_class,
 	TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm,
 		 int error),
 	TP_ARGS(ip, sm, error),
@@ -47,19 +47,19 @@ DECLARE_EVENT_CLASS(xfs_scrub_class,
 		  __entry->error)
 )
 #define DEFINE_SCRUB_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_class, name, \
+DEFINE_EVENT(xchk_class, name, \
 	TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm, \
 		 int error), \
 	TP_ARGS(ip, sm, error))
 
-DEFINE_SCRUB_EVENT(xfs_scrub_start);
-DEFINE_SCRUB_EVENT(xfs_scrub_done);
-DEFINE_SCRUB_EVENT(xfs_scrub_deadlock_retry);
-DEFINE_SCRUB_EVENT(xfs_repair_attempt);
-DEFINE_SCRUB_EVENT(xfs_repair_done);
+DEFINE_SCRUB_EVENT(xchk_start);
+DEFINE_SCRUB_EVENT(xchk_done);
+DEFINE_SCRUB_EVENT(xchk_deadlock_retry);
+DEFINE_SCRUB_EVENT(xrep_attempt);
+DEFINE_SCRUB_EVENT(xrep_done);
 
-TRACE_EVENT(xfs_scrub_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+TRACE_EVENT(xchk_op_error,
+	TP_PROTO(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		 xfs_agblock_t bno, int error, void *ret_ip),
 	TP_ARGS(sc, agno, bno, error, ret_ip),
 	TP_STRUCT__entry(
@@ -87,8 +87,8 @@ TRACE_EVENT(xfs_scrub_op_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_file_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, int whichfork,
+TRACE_EVENT(xchk_file_op_error,
+	TP_PROTO(struct xfs_scrub *sc, int whichfork,
 		 xfs_fileoff_t offset, int error, void *ret_ip),
 	TP_ARGS(sc, whichfork, offset, error, ret_ip),
 	TP_STRUCT__entry(
@@ -119,8 +119,8 @@ TRACE_EVENT(xfs_scrub_file_op_error,
 		  __entry->ret_ip)
 );
 
-DECLARE_EVENT_CLASS(xfs_scrub_block_error_class,
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_daddr_t daddr, void *ret_ip),
+DECLARE_EVENT_CLASS(xchk_block_error_class,
+	TP_PROTO(struct xfs_scrub *sc, xfs_daddr_t daddr, void *ret_ip),
 	TP_ARGS(sc, daddr, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -153,16 +153,16 @@ DECLARE_EVENT_CLASS(xfs_scrub_block_error_class,
 )
 
 #define DEFINE_SCRUB_BLOCK_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_block_error_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_daddr_t daddr, \
+DEFINE_EVENT(xchk_block_error_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, xfs_daddr_t daddr, \
 		 void *ret_ip), \
 	TP_ARGS(sc, daddr, ret_ip))
 
-DEFINE_SCRUB_BLOCK_ERROR_EVENT(xfs_scrub_block_error);
-DEFINE_SCRUB_BLOCK_ERROR_EVENT(xfs_scrub_block_preen);
+DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_error);
+DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_preen);
 
-DECLARE_EVENT_CLASS(xfs_scrub_ino_error_class,
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_ino_t ino, void *ret_ip),
+DECLARE_EVENT_CLASS(xchk_ino_error_class,
+	TP_PROTO(struct xfs_scrub *sc, xfs_ino_t ino, void *ret_ip),
 	TP_ARGS(sc, ino, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -184,17 +184,17 @@ DECLARE_EVENT_CLASS(xfs_scrub_ino_error_class,
 )
 
 #define DEFINE_SCRUB_INO_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_ino_error_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_ino_t ino, \
+DEFINE_EVENT(xchk_ino_error_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, xfs_ino_t ino, \
 		 void *ret_ip), \
 	TP_ARGS(sc, ino, ret_ip))
 
-DEFINE_SCRUB_INO_ERROR_EVENT(xfs_scrub_ino_error);
-DEFINE_SCRUB_INO_ERROR_EVENT(xfs_scrub_ino_preen);
-DEFINE_SCRUB_INO_ERROR_EVENT(xfs_scrub_ino_warning);
+DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_error);
+DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_preen);
+DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_warning);
 
-DECLARE_EVENT_CLASS(xfs_scrub_fblock_error_class,
-	TP_PROTO(struct xfs_scrub_context *sc, int whichfork,
+DECLARE_EVENT_CLASS(xchk_fblock_error_class,
+	TP_PROTO(struct xfs_scrub *sc, int whichfork,
 		 xfs_fileoff_t offset, void *ret_ip),
 	TP_ARGS(sc, whichfork, offset, ret_ip),
 	TP_STRUCT__entry(
@@ -223,16 +223,16 @@ DECLARE_EVENT_CLASS(xfs_scrub_fblock_error_class,
 );
 
 #define DEFINE_SCRUB_FBLOCK_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_fblock_error_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, int whichfork, \
+DEFINE_EVENT(xchk_fblock_error_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, int whichfork, \
 		 xfs_fileoff_t offset, void *ret_ip), \
 	TP_ARGS(sc, whichfork, offset, ret_ip))
 
-DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xfs_scrub_fblock_error);
-DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xfs_scrub_fblock_warning);
+DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_error);
+DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_warning);
 
-TRACE_EVENT(xfs_scrub_incomplete,
-	TP_PROTO(struct xfs_scrub_context *sc, void *ret_ip),
+TRACE_EVENT(xchk_incomplete,
+	TP_PROTO(struct xfs_scrub *sc, void *ret_ip),
 	TP_ARGS(sc, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -250,8 +250,8 @@ TRACE_EVENT(xfs_scrub_incomplete,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_btree_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+TRACE_EVENT(xchk_btree_op_error,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, int error, void *ret_ip),
 	TP_ARGS(sc, cur, level, error, ret_ip),
 	TP_STRUCT__entry(
@@ -266,7 +266,7 @@ TRACE_EVENT(xfs_scrub_btree_op_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->type = sc->sm->sm_type;
@@ -290,8 +290,8 @@ TRACE_EVENT(xfs_scrub_btree_op_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+TRACE_EVENT(xchk_ifork_btree_op_error,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, int error, void *ret_ip),
 	TP_ARGS(sc, cur, level, error, ret_ip),
 	TP_STRUCT__entry(
@@ -308,7 +308,7 @@ TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->ino = sc->ip->i_ino;
 		__entry->whichfork = cur->bc_private.b.whichfork;
@@ -335,8 +335,8 @@ TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_btree_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+TRACE_EVENT(xchk_btree_error,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, void *ret_ip),
 	TP_ARGS(sc, cur, level, ret_ip),
 	TP_STRUCT__entry(
@@ -350,7 +350,7 @@ TRACE_EVENT(xfs_scrub_btree_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->type = sc->sm->sm_type;
 		__entry->btnum = cur->bc_btnum;
@@ -371,8 +371,8 @@ TRACE_EVENT(xfs_scrub_btree_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_ifork_btree_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+TRACE_EVENT(xchk_ifork_btree_error,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, void *ret_ip),
 	TP_ARGS(sc, cur, level, ret_ip),
 	TP_STRUCT__entry(
@@ -388,7 +388,7 @@ TRACE_EVENT(xfs_scrub_ifork_btree_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->ino = sc->ip->i_ino;
 		__entry->whichfork = cur->bc_private.b.whichfork;
@@ -413,8 +413,8 @@ TRACE_EVENT(xfs_scrub_ifork_btree_error,
 		  __entry->ret_ip)
 );
 
-DECLARE_EVENT_CLASS(xfs_scrub_sbtree_class,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+DECLARE_EVENT_CLASS(xchk_sbtree_class,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level),
 	TP_ARGS(sc, cur, level),
 	TP_STRUCT__entry(
@@ -428,7 +428,7 @@ DECLARE_EVENT_CLASS(xfs_scrub_sbtree_class,
 		__field(int, ptr)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->type = sc->sm->sm_type;
@@ -450,16 +450,16 @@ DECLARE_EVENT_CLASS(xfs_scrub_sbtree_class,
 		  __entry->ptr)
 )
 #define DEFINE_SCRUB_SBTREE_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_sbtree_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur, \
+DEFINE_EVENT(xchk_sbtree_class, name, \
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur, \
 		 int level), \
 	TP_ARGS(sc, cur, level))
 
-DEFINE_SCRUB_SBTREE_EVENT(xfs_scrub_btree_rec);
-DEFINE_SCRUB_SBTREE_EVENT(xfs_scrub_btree_key);
+DEFINE_SCRUB_SBTREE_EVENT(xchk_btree_rec);
+DEFINE_SCRUB_SBTREE_EVENT(xchk_btree_key);
 
-TRACE_EVENT(xfs_scrub_xref_error,
-	TP_PROTO(struct xfs_scrub_context *sc, int error, void *ret_ip),
+TRACE_EVENT(xchk_xref_error,
+	TP_PROTO(struct xfs_scrub *sc, int error, void *ret_ip),
 	TP_ARGS(sc, error, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -483,7 +483,7 @@ TRACE_EVENT(xfs_scrub_xref_error,
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 
-DECLARE_EVENT_CLASS(xfs_repair_extent_class,
+DECLARE_EVENT_CLASS(xrep_extent_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len),
 	TP_ARGS(mp, agno, agbno, len),
@@ -506,15 +506,14 @@ DECLARE_EVENT_CLASS(xfs_repair_extent_class,
 		  __entry->len)
 );
 #define DEFINE_REPAIR_EXTENT_EVENT(name) \
-DEFINE_EVENT(xfs_repair_extent_class, name, \
+DEFINE_EVENT(xrep_extent_class, name, \
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
 		 xfs_agblock_t agbno, xfs_extlen_t len), \
 	TP_ARGS(mp, agno, agbno, len))
-DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_dispose_btree_extent);
-DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_collect_btree_extent);
-DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_agfl_insert);
+DEFINE_REPAIR_EXTENT_EVENT(xrep_dispose_btree_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert);
 
-DECLARE_EVENT_CLASS(xfs_repair_rmap_class,
+DECLARE_EVENT_CLASS(xrep_rmap_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len,
 		 uint64_t owner, uint64_t offset, unsigned int flags),
@@ -547,17 +546,17 @@ DECLARE_EVENT_CLASS(xfs_repair_rmap_class,
 		  __entry->flags)
 );
 #define DEFINE_REPAIR_RMAP_EVENT(name) \
-DEFINE_EVENT(xfs_repair_rmap_class, name, \
+DEFINE_EVENT(xrep_rmap_class, name, \
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
 		 xfs_agblock_t agbno, xfs_extlen_t len, \
 		 uint64_t owner, uint64_t offset, unsigned int flags), \
 	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_alloc_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_ialloc_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_rmap_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_bmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_alloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_ialloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_rmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_extent_fn);
 
-TRACE_EVENT(xfs_repair_refcount_extent_fn,
+TRACE_EVENT(xrep_refcount_extent_fn,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 struct xfs_refcount_irec *irec),
 	TP_ARGS(mp, agno, irec),
@@ -583,7 +582,7 @@ TRACE_EVENT(xfs_repair_refcount_extent_fn,
 		  __entry->refcount)
 )
 
-TRACE_EVENT(xfs_repair_init_btblock,
+TRACE_EVENT(xrep_init_btblock,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
 		 xfs_btnum_t btnum),
 	TP_ARGS(mp, agno, agbno, btnum),
@@ -605,7 +604,7 @@ TRACE_EVENT(xfs_repair_init_btblock,
 		  __entry->agbno,
 		  __entry->btnum)
 )
-TRACE_EVENT(xfs_repair_findroot_block,
+TRACE_EVENT(xrep_findroot_block,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
 		 uint32_t magic, uint16_t level),
 	TP_ARGS(mp, agno, agbno, magic, level),
@@ -630,7 +629,7 @@ TRACE_EVENT(xfs_repair_findroot_block,
 		  __entry->magic,
 		  __entry->level)
 )
-TRACE_EVENT(xfs_repair_calc_ag_resblks,
+TRACE_EVENT(xrep_calc_ag_resblks,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agino_t icount, xfs_agblock_t aglen, xfs_agblock_t freelen,
 		 xfs_agblock_t usedlen),
@@ -659,7 +658,7 @@ TRACE_EVENT(xfs_repair_calc_ag_resblks,
 		  __entry->freelen,
 		  __entry->usedlen)
 )
-TRACE_EVENT(xfs_repair_calc_ag_resblks_btsize,
+TRACE_EVENT(xrep_calc_ag_resblks_btsize,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t bnobt_sz, xfs_agblock_t inobt_sz,
 		 xfs_agblock_t rmapbt_sz, xfs_agblock_t refcbt_sz),
@@ -688,7 +687,7 @@ TRACE_EVENT(xfs_repair_calc_ag_resblks_btsize,
 		  __entry->rmapbt_sz,
 		  __entry->refcbt_sz)
 )
-TRACE_EVENT(xfs_repair_reset_counters,
+TRACE_EVENT(xrep_reset_counters,
 	TP_PROTO(struct xfs_mount *mp),
 	TP_ARGS(mp),
 	TP_STRUCT__entry(
@@ -701,7 +700,7 @@ TRACE_EVENT(xfs_repair_reset_counters,
 		  MAJOR(__entry->dev), MINOR(__entry->dev))
 )
 
-TRACE_EVENT(xfs_repair_ialloc_insert,
+TRACE_EVENT(xrep_ialloc_insert,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agino_t startino, uint16_t holemask, uint8_t count,
 		 uint8_t freecount, uint64_t freemask),
diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h
index 583a9f539bf1..f6ffb4f248f7 100644
--- a/fs/xfs/xfs.h
+++ b/fs/xfs/xfs.h
@@ -8,7 +8,6 @@
 
 #ifdef CONFIG_XFS_DEBUG
 #define DEBUG 1
-#define XFS_BUF_LOCK_TRACKING 1
 #endif
 
 #ifdef CONFIG_XFS_ASSERT_FATAL
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 8eb3ba3d4d00..49f5f5896a43 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  * All Rights Reserved.
  */
 #include "xfs.h"
@@ -20,9 +21,6 @@
 #include "xfs_bmap_util.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
-#include <linux/gfp.h>
-#include <linux/mpage.h>
-#include <linux/pagevec.h>
 #include <linux/writeback.h>
 
 /*
@@ -30,31 +28,11 @@
  */
 struct xfs_writepage_ctx {
 	struct xfs_bmbt_irec    imap;
-	bool			imap_valid;
 	unsigned int		io_type;
+	unsigned int		cow_seq;
 	struct xfs_ioend	*ioend;
-	sector_t		last_block;
 };
 
-void
-xfs_count_page_state(
-	struct page		*page,
-	int			*delalloc,
-	int			*unwritten)
-{
-	struct buffer_head	*bh, *head;
-
-	*delalloc = *unwritten = 0;
-
-	bh = head = page_buffers(page);
-	do {
-		if (buffer_unwritten(bh))
-			(*unwritten) = 1;
-		else if (buffer_delay(bh))
-			(*delalloc) = 1;
-	} while ((bh = bh->b_this_page) != head);
-}
-
 struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
@@ -81,60 +59,23 @@ xfs_find_daxdev_for_inode(
 		return mp->m_ddev_targp->bt_daxdev;
 }
 
-/*
- * We're now finished for good with this page.  Update the page state via the
- * associated buffer_heads, paying attention to the start and end offsets that
- * we need to process on the page.
- *
- * Note that we open code the action in end_buffer_async_write here so that we
- * only have to iterate over the buffers attached to the page once.  This is not
- * only more efficient, but also ensures that we only calls end_page_writeback
- * at the end of the iteration, and thus avoids the pitfall of having the page
- * and buffers potentially freed after every call to end_buffer_async_write.
- */
 static void
 xfs_finish_page_writeback(
 	struct inode		*inode,
 	struct bio_vec		*bvec,
 	int			error)
 {
-	struct buffer_head	*head = page_buffers(bvec->bv_page), *bh = head;
-	bool			busy = false;
-	unsigned int		off = 0;
-	unsigned long		flags;
-
-	ASSERT(bvec->bv_offset < PAGE_SIZE);
-	ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0);
-	ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE);
-	ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0);
-
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
-	do {
-		if (off >= bvec->bv_offset &&
-		    off < bvec->bv_offset + bvec->bv_len) {
-			ASSERT(buffer_async_write(bh));
-			ASSERT(bh->b_end_io == NULL);
-
-			if (error) {
-				mark_buffer_write_io_error(bh);
-				clear_buffer_uptodate(bh);
-				SetPageError(bvec->bv_page);
-			} else {
-				set_buffer_uptodate(bh);
-			}
-			clear_buffer_async_write(bh);
-			unlock_buffer(bh);
-		} else if (buffer_async_write(bh)) {
-			ASSERT(buffer_locked(bh));
-			busy = true;
-		}
-		off += bh->b_size;
-	} while ((bh = bh->b_this_page) != head);
-	bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
-	local_irq_restore(flags);
+	struct iomap_page	*iop = to_iomap_page(bvec->bv_page);
+
+	if (error) {
+		SetPageError(bvec->bv_page);
+		mapping_set_error(inode->i_mapping, -EIO);
+	}
+
+	ASSERT(iop || i_blocksize(inode) == PAGE_SIZE);
+	ASSERT(!iop || atomic_read(&iop->write_count) > 0);
 
-	if (!busy)
+	if (!iop || atomic_dec_and_test(&iop->write_count))
 		end_page_writeback(bvec->bv_page);
 }
 
@@ -170,7 +111,6 @@ xfs_destroy_ioend(
 		/* walk each page on bio, ending page IO on them */
 		bio_for_each_segment_all(bvec, bio, i)
 			xfs_finish_page_writeback(inode, bvec, error);
-
 		bio_put(bio);
 	}
 
@@ -363,39 +303,66 @@ xfs_end_bio(
 
 STATIC int
 xfs_map_blocks(
+	struct xfs_writepage_ctx *wpc,
 	struct inode		*inode,
-	loff_t			offset,
-	struct xfs_bmbt_irec	*imap,
-	int			type)
+	loff_t			offset)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	ssize_t			count = i_blocksize(inode);
-	xfs_fileoff_t		offset_fsb, end_fsb;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset), end_fsb;
+	xfs_fileoff_t		cow_fsb = NULLFILEOFF;
+	struct xfs_bmbt_irec	imap;
+	int			whichfork = XFS_DATA_FORK;
+	struct xfs_iext_cursor	icur;
+	bool			imap_valid;
 	int			error = 0;
-	int			bmapi_flags = XFS_BMAPI_ENTIRE;
-	int			nimaps = 1;
 
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
+	/*
+	 * We have to make sure the cached mapping is within EOF to protect
+	 * against eofblocks trimming on file release leaving us with a stale
+	 * mapping. Otherwise, a page for a subsequent file extending buffered
+	 * write could get picked up by this writeback cycle and written to the
+	 * wrong blocks.
+	 *
+	 * Note that what we really want here is a generic mapping invalidation
+	 * mechanism to protect us from arbitrary extent modifying contexts, not
+	 * just eofblocks.
+	 */
+	xfs_trim_extent_eof(&wpc->imap, ip);
 
 	/*
-	 * Truncate can race with writeback since writeback doesn't take the
-	 * iolock and truncate decreases the file size before it starts
-	 * truncating the pages between new_size and old_size.  Therefore, we
-	 * can end up in the situation where writeback gets a CoW fork mapping
-	 * but the truncate makes the mapping invalid and we end up in here
-	 * trying to get a new mapping.  Bail out here so that we simply never
-	 * get a valid mapping and so we drop the write altogether.  The page
-	 * truncation will kill the contents anyway.
+	 * COW fork blocks can overlap data fork blocks even if the blocks
+	 * aren't shared.  COW I/O always takes precedent, so we must always
+	 * check for overlap on reflink inodes unless the mapping is already a
+	 * COW one, or the COW fork hasn't changed from the last time we looked
+	 * at it.
+	 *
+	 * It's safe to check the COW fork if_seq here without the ILOCK because
+	 * we've indirectly protected against concurrent updates: writeback has
+	 * the page locked, which prevents concurrent invalidations by reflink
+	 * and directio and prevents concurrent buffered writes to the same
+	 * page.  Changes to if_seq always happen under i_lock, which protects
+	 * against concurrent updates and provides a memory barrier on the way
+	 * out that ensures that we always see the current value.
 	 */
-	if (type == XFS_IO_COW && offset > i_size_read(inode))
+	imap_valid = offset_fsb >= wpc->imap.br_startoff &&
+		     offset_fsb < wpc->imap.br_startoff + wpc->imap.br_blockcount;
+	if (imap_valid &&
+	    (!xfs_inode_has_cow_data(ip) ||
+	     wpc->io_type == XFS_IO_COW ||
+	     wpc->cow_seq == READ_ONCE(ip->i_cowfp->if_seq)))
 		return 0;
 
-	ASSERT(type != XFS_IO_COW);
-	if (type == XFS_IO_UNWRITTEN)
-		bmapi_flags |= XFS_BMAPI_IGSTATE;
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
 
+	/*
+	 * If we don't have a valid map, now it's time to get a new one for this
+	 * offset.  This will convert delayed allocations (including COW ones)
+	 * into real extents.  If we return without a valid map, it means we
+	 * landed in a hole and we skip the block.
+	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
@@ -404,109 +371,96 @@ xfs_map_blocks(
 	if (offset > mp->m_super->s_maxbytes - count)
 		count = mp->m_super->s_maxbytes - offset;
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
-	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
-				imap, &nimaps, bmapi_flags);
+
 	/*
-	 * Truncate an overwrite extent if there's a pending CoW
-	 * reservation before the end of this extent.  This forces us
-	 * to come back to writepage to take care of the CoW.
+	 * Check if this is offset is covered by a COW extents, and if yes use
+	 * it directly instead of looking up anything in the data fork.
 	 */
-	if (nimaps && type == XFS_IO_OVERWRITE)
-		xfs_reflink_trim_irec_to_next_cow(ip, offset_fsb, imap);
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	if (error)
-		return error;
-
-	if (type == XFS_IO_DELALLOC &&
-	    (!nimaps || isnullstartblock(imap->br_startblock))) {
-		error = xfs_iomap_write_allocate(ip, XFS_DATA_FORK, offset,
-				imap);
-		if (!error)
-			trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
-		return error;
-	}
-
-#ifdef DEBUG
-	if (type == XFS_IO_UNWRITTEN) {
-		ASSERT(nimaps);
-		ASSERT(imap->br_startblock != HOLESTARTBLOCK);
-		ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
+	if (xfs_inode_has_cow_data(ip) &&
+	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
+		cow_fsb = imap.br_startoff;
+	if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
+		wpc->cow_seq = READ_ONCE(ip->i_cowfp->if_seq);
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		/*
+		 * Truncate can race with writeback since writeback doesn't
+		 * take the iolock and truncate decreases the file size before
+		 * it starts truncating the pages between new_size and old_size.
+		 * Therefore, we can end up in the situation where writeback
+		 * gets a CoW fork mapping but the truncate makes the mapping
+		 * invalid and we end up in here trying to get a new mapping.
+		 * bail out here so that we simply never get a valid mapping
+		 * and so we drop the write altogether.  The page truncation
+		 * will kill the contents anyway.
+		 */
+		if (offset > i_size_read(inode)) {
+			wpc->io_type = XFS_IO_HOLE;
+			return 0;
+		}
+		whichfork = XFS_COW_FORK;
+		wpc->io_type = XFS_IO_COW;
+		goto allocate_blocks;
 	}
-#endif
-	if (nimaps)
-		trace_xfs_map_blocks_found(ip, offset, count, type, imap);
-	return 0;
-}
-
-STATIC bool
-xfs_imap_valid(
-	struct inode		*inode,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
-{
-	offset >>= inode->i_blkbits;
 
 	/*
-	 * We have to make sure the cached mapping is within EOF to protect
-	 * against eofblocks trimming on file release leaving us with a stale
-	 * mapping. Otherwise, a page for a subsequent file extending buffered
-	 * write could get picked up by this writeback cycle and written to the
-	 * wrong blocks.
-	 *
-	 * Note that what we really want here is a generic mapping invalidation
-	 * mechanism to protect us from arbitrary extent modifying contexts, not
-	 * just eofblocks.
+	 * Map valid and no COW extent in the way?  We're done.
 	 */
-	xfs_trim_extent_eof(imap, XFS_I(inode));
-
-	return offset >= imap->br_startoff &&
-		offset < imap->br_startoff + imap->br_blockcount;
-}
-
-STATIC void
-xfs_start_buffer_writeback(
-	struct buffer_head	*bh)
-{
-	ASSERT(buffer_mapped(bh));
-	ASSERT(buffer_locked(bh));
-	ASSERT(!buffer_delay(bh));
-	ASSERT(!buffer_unwritten(bh));
-
-	bh->b_end_io = NULL;
-	set_buffer_async_write(bh);
-	set_buffer_uptodate(bh);
-	clear_buffer_dirty(bh);
-}
-
-STATIC void
-xfs_start_page_writeback(
-	struct page		*page,
-	int			clear_dirty)
-{
-	ASSERT(PageLocked(page));
-	ASSERT(!PageWriteback(page));
+	if (imap_valid) {
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		return 0;
+	}
 
 	/*
-	 * if the page was not fully cleaned, we need to ensure that the higher
-	 * layers come back to it correctly. That means we need to keep the page
-	 * dirty, and for WB_SYNC_ALL writeback we need to ensure the
-	 * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to
-	 * write this page in this writeback sweep will be made.
+	 * If we don't have a valid map, now it's time to get a new one for this
+	 * offset.  This will convert delayed allocations (including COW ones)
+	 * into real extents.
 	 */
-	if (clear_dirty) {
-		clear_page_dirty_for_io(page);
-		set_page_writeback(page);
-	} else
-		set_page_writeback_keepwrite(page);
+	if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap))
+		imap.br_startoff = end_fsb;	/* fake a hole past EOF */
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
-	unlock_page(page);
-}
+	if (imap.br_startoff > offset_fsb) {
+		/* landed in a hole or beyond EOF */
+		imap.br_blockcount = imap.br_startoff - offset_fsb;
+		imap.br_startoff = offset_fsb;
+		imap.br_startblock = HOLESTARTBLOCK;
+		wpc->io_type = XFS_IO_HOLE;
+	} else {
+		/*
+		 * Truncate to the next COW extent if there is one.  This is the
+		 * only opportunity to do this because we can skip COW fork
+		 * lookups for the subsequent blocks in the mapping; however,
+		 * the requirement to treat the COW range separately remains.
+		 */
+		if (cow_fsb != NULLFILEOFF &&
+		    cow_fsb < imap.br_startoff + imap.br_blockcount)
+			imap.br_blockcount = cow_fsb - imap.br_startoff;
+
+		if (isnullstartblock(imap.br_startblock)) {
+			/* got a delalloc extent */
+			wpc->io_type = XFS_IO_DELALLOC;
+			goto allocate_blocks;
+		}
 
-static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
-{
-	return bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+		if (imap.br_state == XFS_EXT_UNWRITTEN)
+			wpc->io_type = XFS_IO_UNWRITTEN;
+		else
+			wpc->io_type = XFS_IO_OVERWRITE;
+	}
+
+	wpc->imap = imap;
+	trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap);
+	return 0;
+allocate_blocks:
+	error = xfs_iomap_write_allocate(ip, whichfork, offset, &imap,
+			&wpc->cow_seq);
+	if (error)
+		return error;
+	ASSERT(whichfork == XFS_COW_FORK || cow_fsb == NULLFILEOFF ||
+	       imap.br_startoff + imap.br_blockcount <= cow_fsb);
+	wpc->imap = imap;
+	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap);
+	return 0;
 }
 
 /*
@@ -574,27 +528,20 @@ xfs_submit_ioend(
 	return 0;
 }
 
-static void
-xfs_init_bio_from_bh(
-	struct bio		*bio,
-	struct buffer_head	*bh)
-{
-	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
-	bio_set_dev(bio, bh->b_bdev);
-}
-
 static struct xfs_ioend *
 xfs_alloc_ioend(
 	struct inode		*inode,
 	unsigned int		type,
 	xfs_off_t		offset,
-	struct buffer_head	*bh)
+	struct block_device	*bdev,
+	sector_t		sector)
 {
 	struct xfs_ioend	*ioend;
 	struct bio		*bio;
 
 	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset);
-	xfs_init_bio_from_bh(bio, bh);
+	bio_set_dev(bio, bdev);
+	bio->bi_iter.bi_sector = sector;
 
 	ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
 	INIT_LIST_HEAD(&ioend->io_list);
@@ -619,13 +566,14 @@ static void
 xfs_chain_bio(
 	struct xfs_ioend	*ioend,
 	struct writeback_control *wbc,
-	struct buffer_head	*bh)
+	struct block_device	*bdev,
+	sector_t		sector)
 {
 	struct bio *new;
 
 	new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
-	xfs_init_bio_from_bh(new, bh);
-
+	bio_set_dev(new, bdev);
+	new->bi_iter.bi_sector = sector;
 	bio_chain(ioend->io_bio, new);
 	bio_get(ioend->io_bio);		/* for xfs_destroy_ioend */
 	ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
@@ -635,122 +583,47 @@ xfs_chain_bio(
 }
 
 /*
- * Test to see if we've been building up a completion structure for
- * earlier buffers -- if so, we try to append to this ioend if we
- * can, otherwise we finish off any current ioend and start another.
- * Return the ioend we finished off so that the caller can submit it
- * once it has finished processing the dirty page.
+ * Test to see if we have an existing ioend structure that we could append to
+ * first, otherwise finish off the current ioend and start another.
  */
 STATIC void
 xfs_add_to_ioend(
 	struct inode		*inode,
-	struct buffer_head	*bh,
 	xfs_off_t		offset,
+	struct page		*page,
+	struct iomap_page	*iop,
 	struct xfs_writepage_ctx *wpc,
 	struct writeback_control *wbc,
 	struct list_head	*iolist)
 {
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct block_device	*bdev = xfs_find_bdev_for_inode(inode);
+	unsigned		len = i_blocksize(inode);
+	unsigned		poff = offset & (PAGE_SIZE - 1);
+	sector_t		sector;
+
+	sector = xfs_fsb_to_db(ip, wpc->imap.br_startblock) +
+		((offset - XFS_FSB_TO_B(mp, wpc->imap.br_startoff)) >> 9);
+
 	if (!wpc->ioend || wpc->io_type != wpc->ioend->io_type ||
-	    bh->b_blocknr != wpc->last_block + 1 ||
+	    sector != bio_end_sector(wpc->ioend->io_bio) ||
 	    offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
 		if (wpc->ioend)
 			list_add(&wpc->ioend->io_list, iolist);
-		wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset, bh);
+		wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset,
+				bdev, sector);
 	}
 
-	/*
-	 * If the buffer doesn't fit into the bio we need to allocate a new
-	 * one.  This shouldn't happen more than once for a given buffer.
-	 */
-	while (xfs_bio_add_buffer(wpc->ioend->io_bio, bh) != bh->b_size)
-		xfs_chain_bio(wpc->ioend, wbc, bh);
-
-	wpc->ioend->io_size += bh->b_size;
-	wpc->last_block = bh->b_blocknr;
-	xfs_start_buffer_writeback(bh);
-}
-
-STATIC void
-xfs_map_buffer(
-	struct inode		*inode,
-	struct buffer_head	*bh,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
-{
-	sector_t		bn;
-	struct xfs_mount	*m = XFS_I(inode)->i_mount;
-	xfs_off_t		iomap_offset = XFS_FSB_TO_B(m, imap->br_startoff);
-	xfs_daddr_t		iomap_bn = xfs_fsb_to_db(XFS_I(inode), imap->br_startblock);
-
-	ASSERT(imap->br_startblock != HOLESTARTBLOCK);
-	ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
-
-	bn = (iomap_bn >> (inode->i_blkbits - BBSHIFT)) +
-	      ((offset - iomap_offset) >> inode->i_blkbits);
-
-	ASSERT(bn || XFS_IS_REALTIME_INODE(XFS_I(inode)));
-
-	bh->b_blocknr = bn;
-	set_buffer_mapped(bh);
-}
-
-STATIC void
-xfs_map_at_offset(
-	struct inode		*inode,
-	struct buffer_head	*bh,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
-{
-	ASSERT(imap->br_startblock != HOLESTARTBLOCK);
-	ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
-
-	xfs_map_buffer(inode, bh, imap, offset);
-	set_buffer_mapped(bh);
-	clear_buffer_delay(bh);
-	clear_buffer_unwritten(bh);
-}
-
-/*
- * Test if a given page contains at least one buffer of a given @type.
- * If @check_all_buffers is true, then we walk all the buffers in the page to
- * try to find one of the type passed in. If it is not set, then the caller only
- * needs to check the first buffer on the page for a match.
- */
-STATIC bool
-xfs_check_page_type(
-	struct page		*page,
-	unsigned int		type,
-	bool			check_all_buffers)
-{
-	struct buffer_head	*bh;
-	struct buffer_head	*head;
-
-	if (PageWriteback(page))
-		return false;
-	if (!page->mapping)
-		return false;
-	if (!page_has_buffers(page))
-		return false;
-
-	bh = head = page_buffers(page);
-	do {
-		if (buffer_unwritten(bh)) {
-			if (type == XFS_IO_UNWRITTEN)
-				return true;
-		} else if (buffer_delay(bh)) {
-			if (type == XFS_IO_DELALLOC)
-				return true;
-		} else if (buffer_dirty(bh) && buffer_mapped(bh)) {
-			if (type == XFS_IO_OVERWRITE)
-				return true;
-		}
-
-		/* If we are only checking the first buffer, we are done now. */
-		if (!check_all_buffers)
-			break;
-	} while ((bh = bh->b_this_page) != head);
+	if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff)) {
+		if (iop)
+			atomic_inc(&iop->write_count);
+		if (bio_full(wpc->ioend->io_bio))
+			xfs_chain_bio(wpc->ioend, wbc, bdev, sector);
+		__bio_add_page(wpc->ioend->io_bio, page, len, poff);
+	}
 
-	return false;
+	wpc->ioend->io_size += len;
 }
 
 STATIC void
@@ -759,34 +632,20 @@ xfs_vm_invalidatepage(
 	unsigned int		offset,
 	unsigned int		length)
 {
-	trace_xfs_invalidatepage(page->mapping->host, page, offset,
-				 length);
-
-	/*
-	 * If we are invalidating the entire page, clear the dirty state from it
-	 * so that we can check for attempts to release dirty cached pages in
-	 * xfs_vm_releasepage().
-	 */
-	if (offset == 0 && length >= PAGE_SIZE)
-		cancel_dirty_page(page);
-	block_invalidatepage(page, offset, length);
+	trace_xfs_invalidatepage(page->mapping->host, page, offset, length);
+	iomap_invalidatepage(page, offset, length);
 }
 
 /*
- * If the page has delalloc buffers on it, we need to punch them out before we
- * invalidate the page. If we don't, we leave a stale delalloc mapping on the
- * inode that can trip a BUG() in xfs_get_blocks() later on if a direct IO read
- * is done on that same region - the delalloc extent is returned when none is
- * supposed to be there.
- *
- * We prevent this by truncating away the delalloc regions on the page before
- * invalidating it. Because they are delalloc, we can do this without needing a
- * transaction. Indeed - if we get ENOSPC errors, we have to be able to do this
- * truncation without a transaction as there is no space left for block
- * reservation (typically why we see a ENOSPC in writeback).
+ * If the page has delalloc blocks on it, we need to punch them out before we
+ * invalidate the page.  If we don't, we leave a stale delalloc mapping on the
+ * inode that can trip up a later direct I/O read operation on the same region.
  *
- * This is not a performance critical path, so for now just do the punching a
- * buffer head at a time.
+ * We prevent this by truncating away the delalloc regions on the page.  Because
+ * they are delalloc, we can do this without needing a transaction. Indeed - if
+ * we get ENOSPC errors, we have to be able to do this truncation without a
+ * transaction as there is no space left for block reservation (typically why we
+ * see a ENOSPC in writeback).
  */
 STATIC void
 xfs_aops_discard_page(
@@ -794,104 +653,31 @@ xfs_aops_discard_page(
 {
 	struct inode		*inode = page->mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	struct buffer_head	*bh, *head;
+	struct xfs_mount	*mp = ip->i_mount;
 	loff_t			offset = page_offset(page);
+	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, offset);
+	int			error;
 
-	if (!xfs_check_page_type(page, XFS_IO_DELALLOC, true))
-		goto out_invalidate;
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+	if (XFS_FORCED_SHUTDOWN(mp))
 		goto out_invalidate;
 
-	xfs_alert(ip->i_mount,
+	xfs_alert(mp,
 		"page discard on page "PTR_FMT", inode 0x%llx, offset %llu.",
 			page, ip->i_ino, offset);
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	bh = head = page_buffers(page);
-	do {
-		int		error;
-		xfs_fileoff_t	start_fsb;
-
-		if (!buffer_delay(bh))
-			goto next_buffer;
-
-		start_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
-		error = xfs_bmap_punch_delalloc_range(ip, start_fsb, 1);
-		if (error) {
-			/* something screwed, just bail */
-			if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-				xfs_alert(ip->i_mount,
-			"page discard unable to remove delalloc mapping.");
-			}
-			break;
-		}
-next_buffer:
-		offset += i_blocksize(inode);
-
-	} while ((bh = bh->b_this_page) != head);
-
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
+			PAGE_SIZE / i_blocksize(inode));
+	if (error && !XFS_FORCED_SHUTDOWN(mp))
+		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
 	xfs_vm_invalidatepage(page, 0, PAGE_SIZE);
-	return;
-}
-
-static int
-xfs_map_cow(
-	struct xfs_writepage_ctx *wpc,
-	struct inode		*inode,
-	loff_t			offset,
-	unsigned int		*new_type)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_bmbt_irec	imap;
-	bool			is_cow = false;
-	int			error;
-
-	/*
-	 * If we already have a valid COW mapping keep using it.
-	 */
-	if (wpc->io_type == XFS_IO_COW) {
-		wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap, offset);
-		if (wpc->imap_valid) {
-			*new_type = XFS_IO_COW;
-			return 0;
-		}
-	}
-
-	/*
-	 * Else we need to check if there is a COW mapping at this offset.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap);
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	if (!is_cow)
-		return 0;
-
-	/*
-	 * And if the COW mapping has a delayed extent here we need to
-	 * allocate real space for it now.
-	 */
-	if (isnullstartblock(imap.br_startblock)) {
-		error = xfs_iomap_write_allocate(ip, XFS_COW_FORK, offset,
-				&imap);
-		if (error)
-			return error;
-	}
-
-	wpc->io_type = *new_type = XFS_IO_COW;
-	wpc->imap_valid = true;
-	wpc->imap = imap;
-	return 0;
 }
 
 /*
  * We implement an immediate ioend submission policy here to avoid needing to
  * chain multiple ioends and hence nest mempool allocations which can violate
  * forward progress guarantees we need to provide. The current ioend we are
- * adding buffers to is cached on the writepage context, and if the new buffer
+ * adding blocks to is cached on the writepage context, and if the new block
  * does not append to the cached ioend it will create a new ioend and cache that
  * instead.
  *
@@ -912,138 +698,99 @@ xfs_writepage_map(
 	uint64_t		end_offset)
 {
 	LIST_HEAD(submit_list);
+	struct iomap_page	*iop = to_iomap_page(page);
+	unsigned		len = i_blocksize(inode);
 	struct xfs_ioend	*ioend, *next;
-	struct buffer_head	*bh, *head;
-	ssize_t			len = i_blocksize(inode);
-	uint64_t		offset;
-	int			error = 0;
-	int			count = 0;
-	int			uptodate = 1;
-	unsigned int		new_type;
-
-	bh = head = page_buffers(page);
-	offset = page_offset(page);
-	do {
-		if (offset >= end_offset)
-			break;
-		if (!buffer_uptodate(bh))
-			uptodate = 0;
+	uint64_t		file_offset;	/* file offset of page */
+	int			error = 0, count = 0, i;
 
-		/*
-		 * set_page_dirty dirties all buffers in a page, independent
-		 * of their state.  The dirty state however is entirely
-		 * meaningless for holes (!mapped && uptodate), so skip
-		 * buffers covering holes here.
-		 */
-		if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
-			wpc->imap_valid = false;
-			continue;
-		}
+	ASSERT(iop || i_blocksize(inode) == PAGE_SIZE);
+	ASSERT(!iop || atomic_read(&iop->write_count) == 0);
 
-		if (buffer_unwritten(bh))
-			new_type = XFS_IO_UNWRITTEN;
-		else if (buffer_delay(bh))
-			new_type = XFS_IO_DELALLOC;
-		else if (buffer_uptodate(bh))
-			new_type = XFS_IO_OVERWRITE;
-		else {
-			if (PageUptodate(page))
-				ASSERT(buffer_mapped(bh));
-			/*
-			 * This buffer is not uptodate and will not be
-			 * written to disk.  Ensure that we will put any
-			 * subsequent writeable buffers into a new
-			 * ioend.
-			 */
-			wpc->imap_valid = false;
+	/*
+	 * Walk through the page to find areas to write back. If we run off the
+	 * end of the current map or find the current map invalid, grab a new
+	 * one.
+	 */
+	for (i = 0, file_offset = page_offset(page);
+	     i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset;
+	     i++, file_offset += len) {
+		if (iop && !test_bit(i, iop->uptodate))
 			continue;
-		}
 
-		if (xfs_is_reflink_inode(XFS_I(inode))) {
-			error = xfs_map_cow(wpc, inode, offset, &new_type);
-			if (error)
-				goto out;
-		}
-
-		if (wpc->io_type != new_type) {
-			wpc->io_type = new_type;
-			wpc->imap_valid = false;
-		}
-
-		if (wpc->imap_valid)
-			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
-							 offset);
-		if (!wpc->imap_valid) {
-			error = xfs_map_blocks(inode, offset, &wpc->imap,
-					     wpc->io_type);
-			if (error)
-				goto out;
-			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
-							 offset);
-		}
-		if (wpc->imap_valid) {
-			lock_buffer(bh);
-			if (wpc->io_type != XFS_IO_OVERWRITE)
-				xfs_map_at_offset(inode, bh, &wpc->imap, offset);
-			xfs_add_to_ioend(inode, bh, offset, wpc, wbc, &submit_list);
-			count++;
-		}
-
-	} while (offset += len, ((bh = bh->b_this_page) != head));
-
-	if (uptodate && bh == head)
-		SetPageUptodate(page);
+		error = xfs_map_blocks(wpc, inode, file_offset);
+		if (error)
+			break;
+		if (wpc->io_type == XFS_IO_HOLE)
+			continue;
+		xfs_add_to_ioend(inode, file_offset, page, iop, wpc, wbc,
+				 &submit_list);
+		count++;
+	}
 
 	ASSERT(wpc->ioend || list_empty(&submit_list));
+	ASSERT(PageLocked(page));
+	ASSERT(!PageWriteback(page));
 
-out:
 	/*
-	 * On error, we have to fail the ioend here because we have locked
-	 * buffers in the ioend. If we don't do this, we'll deadlock
-	 * invalidating the page as that tries to lock the buffers on the page.
-	 * Also, because we may have set pages under writeback, we have to make
-	 * sure we run IO completion to mark the error state of the IO
-	 * appropriately, so we can't cancel the ioend directly here. That means
-	 * we have to mark this page as under writeback if we included any
-	 * buffers from it in the ioend chain so that completion treats it
-	 * correctly.
+	 * On error, we have to fail the ioend here because we may have set
+	 * pages under writeback, we have to make sure we run IO completion to
+	 * mark the error state of the IO appropriately, so we can't cancel the
+	 * ioend directly here.  That means we have to mark this page as under
+	 * writeback if we included any blocks from it in the ioend chain so
+	 * that completion treats it correctly.
 	 *
 	 * If we didn't include the page in the ioend, the on error we can
 	 * simply discard and unlock it as there are no other users of the page
-	 * or it's buffers right now. The caller will still need to trigger
-	 * submission of outstanding ioends on the writepage context so they are
-	 * treated correctly on error.
+	 * now.  The caller will still need to trigger submission of outstanding
+	 * ioends on the writepage context so they are treated correctly on
+	 * error.
 	 */
-	if (count) {
-		xfs_start_page_writeback(page, !error);
+	if (unlikely(error)) {
+		if (!count) {
+			xfs_aops_discard_page(page);
+			ClearPageUptodate(page);
+			unlock_page(page);
+			goto done;
+		}
 
 		/*
-		 * Preserve the original error if there was one, otherwise catch
-		 * submission errors here and propagate into subsequent ioend
-		 * submissions.
+		 * If the page was not fully cleaned, we need to ensure that the
+		 * higher layers come back to it correctly.  That means we need
+		 * to keep the page dirty, and for WB_SYNC_ALL writeback we need
+		 * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed
+		 * so another attempt to write this page in this writeback sweep
+		 * will be made.
 		 */
-		list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
-			int error2;
-
-			list_del_init(&ioend->io_list);
-			error2 = xfs_submit_ioend(wbc, ioend, error);
-			if (error2 && !error)
-				error = error2;
-		}
-	} else if (error) {
-		xfs_aops_discard_page(page);
-		ClearPageUptodate(page);
-		unlock_page(page);
+		set_page_writeback_keepwrite(page);
 	} else {
-		/*
-		 * We can end up here with no error and nothing to write if we
-		 * race with a partial page truncate on a sub-page block sized
-		 * filesystem. In that case we need to mark the page clean.
-		 */
-		xfs_start_page_writeback(page, 1);
-		end_page_writeback(page);
+		clear_page_dirty_for_io(page);
+		set_page_writeback(page);
 	}
 
+	unlock_page(page);
+
+	/*
+	 * Preserve the original error if there was one, otherwise catch
+	 * submission errors here and propagate into subsequent ioend
+	 * submissions.
+	 */
+	list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
+		int error2;
+
+		list_del_init(&ioend->io_list);
+		error2 = xfs_submit_ioend(wbc, ioend, error);
+		if (error2 && !error)
+			error = error2;
+	}
+
+	/*
+	 * We can end up here with no error and nothing to write only if we race
+	 * with a partial page truncate on a sub-page block sized filesystem.
+	 */
+	if (!count)
+		end_page_writeback(page);
+done:
 	mapping_set_error(page->mapping, error);
 	return error;
 }
@@ -1054,7 +801,6 @@ out:
  * For delalloc space on the page we need to allocate space and flush it.
  * For unwritten space on the page we need to start the conversion to
  * regular allocated space.
- * For any other dirty buffer heads on the page we should flush them.
  */
 STATIC int
 xfs_do_writepage(
@@ -1070,8 +816,6 @@ xfs_do_writepage(
 
 	trace_xfs_writepage(inode, page, 0, 0);
 
-	ASSERT(page_has_buffers(page));
-
 	/*
 	 * Refuse to write the page out if we are called from reclaim context.
 	 *
@@ -1210,166 +954,13 @@ xfs_dax_writepages(
 			xfs_find_bdev_for_inode(mapping->host), wbc);
 }
 
-/*
- * Called to move a page into cleanable state - and from there
- * to be released. The page should already be clean. We always
- * have buffer heads in this call.
- *
- * Returns 1 if the page is ok to release, 0 otherwise.
- */
 STATIC int
 xfs_vm_releasepage(
 	struct page		*page,
 	gfp_t			gfp_mask)
 {
-	int			delalloc, unwritten;
-
 	trace_xfs_releasepage(page->mapping->host, page, 0, 0);
-
-	/*
-	 * mm accommodates an old ext3 case where clean pages might not have had
-	 * the dirty bit cleared. Thus, it can send actual dirty pages to
-	 * ->releasepage() via shrink_active_list(). Conversely,
-	 * block_invalidatepage() can send pages that are still marked dirty but
-	 * otherwise have invalidated buffers.
-	 *
-	 * We want to release the latter to avoid unnecessary buildup of the
-	 * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages
-	 * that are entirely invalidated and need to be released.  Hence the
-	 * only time we should get dirty pages here is through
-	 * shrink_active_list() and so we can simply skip those now.
-	 *
-	 * warn if we've left any lingering delalloc/unwritten buffers on clean
-	 * or invalidated pages we are about to release.
-	 */
-	if (PageDirty(page))
-		return 0;
-
-	xfs_count_page_state(page, &delalloc, &unwritten);
-
-	if (WARN_ON_ONCE(delalloc))
-		return 0;
-	if (WARN_ON_ONCE(unwritten))
-		return 0;
-
-	return try_to_free_buffers(page);
-}
-
-/*
- * If this is O_DIRECT or the mpage code calling tell them how large the mapping
- * is, so that we can avoid repeated get_blocks calls.
- *
- * If the mapping spans EOF, then we have to break the mapping up as the mapping
- * for blocks beyond EOF must be marked new so that sub block regions can be
- * correctly zeroed. We can't do this for mappings within EOF unless the mapping
- * was just allocated or is unwritten, otherwise the callers would overwrite
- * existing data with zeros. Hence we have to split the mapping into a range up
- * to and including EOF, and a second mapping for beyond EOF.
- */
-static void
-xfs_map_trim_size(
-	struct inode		*inode,
-	sector_t		iblock,
-	struct buffer_head	*bh_result,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset,
-	ssize_t			size)
-{
-	xfs_off_t		mapping_size;
-
-	mapping_size = imap->br_startoff + imap->br_blockcount - iblock;
-	mapping_size <<= inode->i_blkbits;
-
-	ASSERT(mapping_size > 0);
-	if (mapping_size > size)
-		mapping_size = size;
-	if (offset < i_size_read(inode) &&
-	    (xfs_ufsize_t)offset + mapping_size >= i_size_read(inode)) {
-		/* limit mapping to block that spans EOF */
-		mapping_size = roundup_64(i_size_read(inode) - offset,
-					  i_blocksize(inode));
-	}
-	if (mapping_size > LONG_MAX)
-		mapping_size = LONG_MAX;
-
-	bh_result->b_size = mapping_size;
-}
-
-static int
-xfs_get_blocks(
-	struct inode		*inode,
-	sector_t		iblock,
-	struct buffer_head	*bh_result,
-	int			create)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		offset_fsb, end_fsb;
-	int			error = 0;
-	int			lockmode = 0;
-	struct xfs_bmbt_irec	imap;
-	int			nimaps = 1;
-	xfs_off_t		offset;
-	ssize_t			size;
-
-	BUG_ON(create);
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	offset = (xfs_off_t)iblock << inode->i_blkbits;
-	ASSERT(bh_result->b_size >= i_blocksize(inode));
-	size = bh_result->b_size;
-
-	if (offset >= i_size_read(inode))
-		return 0;
-
-	/*
-	 * Direct I/O is usually done on preallocated files, so try getting
-	 * a block mapping without an exclusive lock first.
-	 */
-	lockmode = xfs_ilock_data_map_shared(ip);
-
-	ASSERT(offset <= mp->m_super->s_maxbytes);
-	if (offset > mp->m_super->s_maxbytes - size)
-		size = mp->m_super->s_maxbytes - offset;
-	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size);
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
-
-	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
-			&nimaps, 0);
-	if (error)
-		goto out_unlock;
-	if (!nimaps) {
-		trace_xfs_get_blocks_notfound(ip, offset, size);
-		goto out_unlock;
-	}
-
-	trace_xfs_get_blocks_found(ip, offset, size,
-		imap.br_state == XFS_EXT_UNWRITTEN ?
-			XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, &imap);
-	xfs_iunlock(ip, lockmode);
-
-	/* trim mapping down to size requested */
-	xfs_map_trim_size(inode, iblock, bh_result, &imap, offset, size);
-
-	/*
-	 * For unwritten extents do not report a disk address in the buffered
-	 * read case (treat as if we're reading into a hole).
-	 */
-	if (xfs_bmap_is_real_extent(&imap))
-		xfs_map_buffer(inode, bh_result, &imap, offset);
-
-	/*
-	 * If this is a realtime file, data may be on a different device.
-	 * to that pointed to from the buffer_head b_bdev currently.
-	 */
-	bh_result->b_bdev = xfs_find_bdev_for_inode(inode);
-	return 0;
-
-out_unlock:
-	xfs_iunlock(ip, lockmode);
-	return error;
+	return iomap_releasepage(page, gfp_mask);
 }
 
 STATIC sector_t
@@ -1401,7 +992,7 @@ xfs_vm_readpage(
 	struct page		*page)
 {
 	trace_xfs_vm_readpage(page->mapping->host, 1);
-	return mpage_readpage(page, xfs_get_blocks);
+	return iomap_readpage(page, &xfs_iomap_ops);
 }
 
 STATIC int
@@ -1412,63 +1003,7 @@ xfs_vm_readpages(
 	unsigned		nr_pages)
 {
 	trace_xfs_vm_readpages(mapping->host, nr_pages);
-	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
-}
-
-/*
- * This is basically a copy of __set_page_dirty_buffers() with one
- * small tweak: buffers beyond EOF do not get marked dirty. If we mark them
- * dirty, we'll never be able to clean them because we don't write buffers
- * beyond EOF, and that means we can't invalidate pages that span EOF
- * that have been marked dirty. Further, the dirty state can leak into
- * the file interior if the file is extended, resulting in all sorts of
- * bad things happening as the state does not match the underlying data.
- *
- * XXX: this really indicates that bufferheads in XFS need to die. Warts like
- * this only exist because of bufferheads and how the generic code manages them.
- */
-STATIC int
-xfs_vm_set_page_dirty(
-	struct page		*page)
-{
-	struct address_space	*mapping = page->mapping;
-	struct inode		*inode = mapping->host;
-	loff_t			end_offset;
-	loff_t			offset;
-	int			newly_dirty;
-
-	if (unlikely(!mapping))
-		return !TestSetPageDirty(page);
-
-	end_offset = i_size_read(inode);
-	offset = page_offset(page);
-
-	spin_lock(&mapping->private_lock);
-	if (page_has_buffers(page)) {
-		struct buffer_head *head = page_buffers(page);
-		struct buffer_head *bh = head;
-
-		do {
-			if (offset < end_offset)
-				set_buffer_dirty(bh);
-			bh = bh->b_this_page;
-			offset += i_blocksize(inode);
-		} while (bh != head);
-	}
-	/*
-	 * Lock out page->mem_cgroup migration to keep PageDirty
-	 * synchronized with per-memcg dirty page counters.
-	 */
-	lock_page_memcg(page);
-	newly_dirty = !TestSetPageDirty(page);
-	spin_unlock(&mapping->private_lock);
-
-	if (newly_dirty)
-		__set_page_dirty(page, mapping, 1);
-	unlock_page_memcg(page);
-	if (newly_dirty)
-		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-	return newly_dirty;
+	return iomap_readpages(mapping, pages, nr_pages, &xfs_iomap_ops);
 }
 
 static int
@@ -1486,13 +1021,13 @@ const struct address_space_operations xfs_address_space_operations = {
 	.readpages		= xfs_vm_readpages,
 	.writepage		= xfs_vm_writepage,
 	.writepages		= xfs_vm_writepages,
-	.set_page_dirty		= xfs_vm_set_page_dirty,
+	.set_page_dirty		= iomap_set_page_dirty,
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
 	.bmap			= xfs_vm_bmap,
 	.direct_IO		= noop_direct_IO,
-	.migratepage		= buffer_migrate_page,
-	.is_partially_uptodate  = block_is_partially_uptodate,
+	.migratepage		= iomap_migrate_page,
+	.is_partially_uptodate  = iomap_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
 	.swap_activate		= xfs_iomap_swapfile_activate,
 };
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 25bc6d4a1231..9af867951a10 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -17,6 +17,7 @@ enum {
 	XFS_IO_UNWRITTEN,	/* covers allocated but uninitialized data */
 	XFS_IO_OVERWRITE,	/* covers already allocated extent */
 	XFS_IO_COW,		/* covers copy-on-write extent */
+	XFS_IO_HOLE,		/* covers region without any block allocation */
 };
 
 #define XFS_IO_TYPES \
@@ -24,7 +25,8 @@ enum {
 	{ XFS_IO_DELALLOC,		"delalloc" }, \
 	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
 	{ XFS_IO_OVERWRITE,		"overwrite" }, \
-	{ XFS_IO_COW,			"CoW" }
+	{ XFS_IO_COW,			"CoW" }, \
+	{ XFS_IO_HOLE,			"hole" }
 
 /*
  * Structure for buffered I/O completions.
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 7ce10055f275..228821b2ebe0 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -26,6 +26,7 @@
 #include "xfs_quota.h"
 #include "xfs_trace.h"
 #include "xfs_dir2.h"
+#include "xfs_defer.h"
 
 /*
  * Look at all the extents for this logical region,
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index f9ca80154c9c..a58034049995 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -87,7 +87,7 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
 	 */
 	if (context->bufsize == 0 ||
 	    (XFS_ISRESET_CURSOR(cursor) &&
-             (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) {
+	     (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) {
 		for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
 			context->put_listent(context,
 					     sfe->flags,
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 956ebd583e27..ce45f066995e 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -375,9 +375,8 @@ xfs_bud_init(
  */
 int
 xfs_bui_recover(
-	struct xfs_mount		*mp,
-	struct xfs_bui_log_item		*buip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_trans		*parent_tp,
+	struct xfs_bui_log_item		*buip)
 {
 	int				error = 0;
 	unsigned int			bui_type;
@@ -393,6 +392,7 @@ xfs_bui_recover(
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip = NULL;
 	struct xfs_bmbt_irec		irec;
+	struct xfs_mount		*mp = parent_tp->t_mountp;
 
 	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
 
@@ -441,6 +441,12 @@ xfs_bui_recover(
 			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
 	if (error)
 		return error;
+	/*
+	 * Recovery stashes all deferred ops during intent processing and
+	 * finishes them on completion. Transfer current dfops state to this
+	 * transaction and transfer the result back before we return.
+	 */
+	xfs_defer_move(tp, parent_tp);
 	budp = xfs_trans_get_bud(tp, buip);
 
 	/* Grab the inode. */
@@ -469,9 +475,8 @@ xfs_bui_recover(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	count = bmap->me_len;
-	error = xfs_trans_log_finish_bmap_update(tp, budp, dfops, type,
-			ip, whichfork, bmap->me_startoff,
-			bmap->me_startblock, &count, state);
+	error = xfs_trans_log_finish_bmap_update(tp, budp, type, ip, whichfork,
+			bmap->me_startoff, bmap->me_startblock, &count, state);
 	if (error)
 		goto err_inode;
 
@@ -481,23 +486,25 @@ xfs_bui_recover(
 		irec.br_blockcount = count;
 		irec.br_startoff = bmap->me_startoff;
 		irec.br_state = state;
-		error = xfs_bmap_unmap_extent(tp->t_mountp, dfops, ip, &irec);
+		error = xfs_bmap_unmap_extent(tp, ip, &irec);
 		if (error)
 			goto err_inode;
 	}
 
 	set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
+	xfs_defer_move(parent_tp, tp);
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	IRELE(ip);
+	xfs_irele(ip);
 
 	return error;
 
 err_inode:
+	xfs_defer_move(parent_tp, tp);
 	xfs_trans_cancel(tp);
 	if (ip) {
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 	return error;
 }
diff --git a/fs/xfs/xfs_bmap_item.h b/fs/xfs/xfs_bmap_item.h
index fd1a1b13df51..89e043a88bb8 100644
--- a/fs/xfs/xfs_bmap_item.h
+++ b/fs/xfs/xfs_bmap_item.h
@@ -79,7 +79,6 @@ struct xfs_bud_log_item *xfs_bud_init(struct xfs_mount *,
 		struct xfs_bui_log_item *);
 void xfs_bui_item_free(struct xfs_bui_log_item *);
 void xfs_bui_release(struct xfs_bui_log_item *);
-int xfs_bui_recover(struct xfs_mount *mp, struct xfs_bui_log_item *buip,
-		struct xfs_defer_ops *dfops);
+int xfs_bui_recover(struct xfs_trans *parent_tp, struct xfs_bui_log_item *buip);
 
 #endif	/* __XFS_BMAP_ITEM_H__ */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 83b1e8c6c18f..addbd74ecd8e 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -702,16 +702,15 @@ xfs_bmap_punch_delalloc_range(
 	struct xfs_iext_cursor	icur;
 	int			error = 0;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
 		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
 		if (error)
-			return error;
+			goto out_unlock;
 	}
 
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
-		return 0;
+		goto out_unlock;
 
 	while (got.br_startoff + got.br_blockcount > start_fsb) {
 		del = got;
@@ -735,6 +734,8 @@ xfs_bmap_punch_delalloc_range(
 			break;
 	}
 
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
 
@@ -872,13 +873,11 @@ xfs_alloc_file_space(
 	xfs_filblks_t		allocatesize_fsb;
 	xfs_extlen_t		extsz, temp;
 	xfs_fileoff_t		startoffset_fsb;
-	xfs_fsblock_t		firstfsb;
 	int			nimaps;
 	int			quota_flag;
 	int			rt;
 	xfs_trans_t		*tp;
 	xfs_bmbt_irec_t		imaps[1], *imapp;
-	struct xfs_defer_ops	dfops;
 	uint			qblocks, resblks, resrtextents;
 	int			error;
 
@@ -971,20 +970,15 @@ xfs_alloc_file_space(
 
 		xfs_trans_ijoin(tp, ip, 0);
 
-		xfs_defer_init(&dfops, &firstfsb);
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-					allocatesize_fsb, alloc_type, &firstfsb,
-					resblks, imapp, &nimaps, &dfops);
+					allocatesize_fsb, alloc_type, resblks,
+					imapp, &nimaps);
 		if (error)
 			goto error0;
 
 		/*
 		 * Complete the transaction
 		 */
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto error0;
-
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
@@ -1003,8 +997,7 @@ xfs_alloc_file_space(
 
 	return error;
 
-error0:	/* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
-	xfs_defer_cancel(&dfops);
+error0:	/* unlock inode, unreserve quota blocks, cancel trans */
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
 
 error1:	/* Just cancel transaction */
@@ -1022,8 +1015,6 @@ xfs_unmap_extent(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		firstfsb;
 	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
 	int			error;
 
@@ -1041,24 +1032,15 @@ xfs_unmap_extent(
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(&dfops, &firstfsb);
-	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, &firstfsb,
-			&dfops, done);
-	if (error)
-		goto out_bmap_cancel;
-
-	xfs_defer_ijoin(&dfops, ip);
-	error = xfs_defer_finish(&tp, &dfops);
+	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
 	error = xfs_trans_commit(tp);
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	goto out_unlock;
@@ -1279,7 +1261,7 @@ xfs_prepare_shift(
 	 * we've flushed all the dirty data out to disk to avoid having
 	 * CoW extents at the wrong offsets.
 	 */
-	if (xfs_is_reflink_inode(ip)) {
+	if (xfs_inode_has_cow_data(ip)) {
 		error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
 				true);
 		if (error)
@@ -1310,8 +1292,6 @@ xfs_collapse_file_space(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		next_fsb = XFS_B_TO_FSB(mp, offset + len);
 	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
 	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
@@ -1344,22 +1324,16 @@ xfs_collapse_file_space(
 			goto out_trans_cancel;
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(&dfops, &first_block);
 		error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, &first_block, &dfops);
+				&done);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
 	}
 
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
@@ -1386,8 +1360,6 @@ xfs_insert_file_space(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		stop_fsb = XFS_B_TO_FSB(mp, offset);
 	xfs_fileoff_t		next_fsb = NULLFSBLOCK;
 	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
@@ -1423,22 +1395,17 @@ xfs_insert_file_space(
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-		xfs_defer_init(&dfops, &first_block);
 		error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, stop_fsb, &first_block, &dfops);
+				&done, stop_fsb);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
 	}
 
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -1566,14 +1533,13 @@ xfs_swap_extent_rmap(
 	struct xfs_inode		*ip,
 	struct xfs_inode		*tip)
 {
+	struct xfs_trans		*tp = *tpp;
 	struct xfs_bmbt_irec		irec;
 	struct xfs_bmbt_irec		uirec;
 	struct xfs_bmbt_irec		tirec;
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
 	xfs_filblks_t			count_fsb;
-	xfs_fsblock_t			firstfsb;
-	struct xfs_defer_ops		dfops;
 	int				error;
 	xfs_filblks_t			ilen;
 	xfs_filblks_t			rlen;
@@ -1609,7 +1575,7 @@ xfs_swap_extent_rmap(
 
 		/* Unmap the old blocks in the source file. */
 		while (tirec.br_blockcount) {
-			xfs_defer_init(&dfops, &firstfsb);
+			ASSERT(tp->t_firstblock == NULLFSBLOCK);
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
 
 			/* Read extent from the source file */
@@ -1631,33 +1597,29 @@ xfs_swap_extent_rmap(
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec);
 
 			/* Remove the mapping from the donor file. */
-			error = xfs_bmap_unmap_extent((*tpp)->t_mountp, &dfops,
-					tip, &uirec);
+			error = xfs_bmap_unmap_extent(tp, tip, &uirec);
 			if (error)
 				goto out_defer;
 
 			/* Remove the mapping from the source file. */
-			error = xfs_bmap_unmap_extent((*tpp)->t_mountp, &dfops,
-					ip, &irec);
+			error = xfs_bmap_unmap_extent(tp, ip, &irec);
 			if (error)
 				goto out_defer;
 
 			/* Map the donor file's blocks into the source file. */
-			error = xfs_bmap_map_extent((*tpp)->t_mountp, &dfops,
-					ip, &uirec);
+			error = xfs_bmap_map_extent(tp, ip, &uirec);
 			if (error)
 				goto out_defer;
 
 			/* Map the source file's blocks into the donor file. */
-			error = xfs_bmap_map_extent((*tpp)->t_mountp, &dfops,
-					tip, &irec);
+			error = xfs_bmap_map_extent(tp, tip, &irec);
 			if (error)
 				goto out_defer;
 
-			xfs_defer_ijoin(&dfops, ip);
-			error = xfs_defer_finish(tpp, &dfops);
+			error = xfs_defer_finish(tpp);
+			tp = *tpp;
 			if (error)
-				goto out_defer;
+				goto out;
 
 			tirec.br_startoff += rlen;
 			if (tirec.br_startblock != HOLESTARTBLOCK &&
@@ -1675,7 +1637,7 @@ xfs_swap_extent_rmap(
 	return 0;
 
 out_defer:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp);
 out:
 	trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
 	tip->i_d.di_flags2 = tip_flags2;
@@ -1691,7 +1653,6 @@ xfs_swap_extent_forks(
 	int			*src_log_flags,
 	int			*target_log_flags)
 {
-	struct xfs_ifork	tempifp, *ifp, *tifp;
 	xfs_filblks_t		aforkblks = 0;
 	xfs_filblks_t		taforkblks = 0;
 	xfs_extnum_t		junk;
@@ -1733,11 +1694,7 @@ xfs_swap_extent_forks(
 	/*
 	 * Swap the data forks of the inodes
 	 */
-	ifp = &ip->i_df;
-	tifp = &tip->i_df;
-	tempifp = *ifp;		/* struct copy */
-	*ifp = *tifp;		/* struct copy */
-	*tifp = tempifp;	/* struct copy */
+	swap(ip->i_df, tip->i_df);
 
 	/*
 	 * Fix the on-disk inode values
@@ -1746,13 +1703,8 @@ xfs_swap_extent_forks(
 	ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
 	tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
 
-	tmp = (uint64_t) ip->i_d.di_nextents;
-	ip->i_d.di_nextents = tip->i_d.di_nextents;
-	tip->i_d.di_nextents = tmp;
-
-	tmp = (uint64_t) ip->i_d.di_format;
-	ip->i_d.di_format = tip->i_d.di_format;
-	tip->i_d.di_format = tmp;
+	swap(ip->i_d.di_nextents, tip->i_d.di_nextents);
+	swap(ip->i_d.di_format, tip->i_d.di_format);
 
 	/*
 	 * The extents in the source inode could still contain speculative
@@ -1846,7 +1798,6 @@ xfs_swap_extents(
 	int			src_log_flags, target_log_flags;
 	int			error = 0;
 	int			lock_flags;
-	struct xfs_ifork	*cowfp;
 	uint64_t		f;
 	int			resblks = 0;
 
@@ -1987,18 +1938,11 @@ xfs_swap_extents(
 
 	/* Swap the cow forks. */
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
-		xfs_extnum_t	extnum;
-
 		ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
 		ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);
 
-		extnum = ip->i_cnextents;
-		ip->i_cnextents = tip->i_cnextents;
-		tip->i_cnextents = extnum;
-
-		cowfp = ip->i_cowfp;
-		ip->i_cowfp = tip->i_cowfp;
-		tip->i_cowfp = cowfp;
+		swap(ip->i_cnextents, tip->i_cnextents);
+		swap(ip->i_cowfp, tip->i_cowfp);
 
 		if (ip->i_cowfp && ip->i_cowfp->if_bytes)
 			xfs_inode_set_cowblocks_tag(ip);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index e9c058e3761c..e839907e8492 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -34,16 +34,6 @@
 
 static kmem_zone_t *xfs_buf_zone;
 
-#ifdef XFS_BUF_LOCK_TRACKING
-# define XB_SET_OWNER(bp)	((bp)->b_last_holder = current->pid)
-# define XB_CLEAR_OWNER(bp)	((bp)->b_last_holder = -1)
-# define XB_GET_OWNER(bp)	((bp)->b_last_holder)
-#else
-# define XB_SET_OWNER(bp)	do { } while (0)
-# define XB_CLEAR_OWNER(bp)	do { } while (0)
-# define XB_GET_OWNER(bp)	do { } while (0)
-#endif
-
 #define xb_to_gfp(flags) \
 	((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN)
 
@@ -226,7 +216,6 @@ _xfs_buf_alloc(
 	INIT_LIST_HEAD(&bp->b_li_list);
 	sema_init(&bp->b_sema, 0); /* held, no waiters */
 	spin_lock_init(&bp->b_lock);
-	XB_SET_OWNER(bp);
 	bp->b_target = target;
 	bp->b_flags = flags;
 
@@ -757,11 +746,7 @@ _xfs_buf_read(
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
 
-	if (flags & XBF_ASYNC) {
-		xfs_buf_submit(bp);
-		return 0;
-	}
-	return xfs_buf_submit_wait(bp);
+	return xfs_buf_submit(bp);
 }
 
 xfs_buf_t *
@@ -846,7 +831,7 @@ xfs_buf_read_uncached(
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = ops;
 
-	xfs_buf_submit_wait(bp);
+	xfs_buf_submit(bp);
 	if (bp->b_error) {
 		int	error = bp->b_error;
 		xfs_buf_relse(bp);
@@ -1095,12 +1080,10 @@ xfs_buf_trylock(
 	int			locked;
 
 	locked = down_trylock(&bp->b_sema) == 0;
-	if (locked) {
-		XB_SET_OWNER(bp);
+	if (locked)
 		trace_xfs_buf_trylock(bp, _RET_IP_);
-	} else {
+	else
 		trace_xfs_buf_trylock_fail(bp, _RET_IP_);
-	}
 	return locked;
 }
 
@@ -1122,7 +1105,6 @@ xfs_buf_lock(
 	if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
 		xfs_log_force(bp->b_target->bt_mount, 0);
 	down(&bp->b_sema);
-	XB_SET_OWNER(bp);
 
 	trace_xfs_buf_lock_done(bp, _RET_IP_);
 }
@@ -1133,9 +1115,7 @@ xfs_buf_unlock(
 {
 	ASSERT(xfs_buf_islocked(bp));
 
-	XB_CLEAR_OWNER(bp);
 	up(&bp->b_sema);
-
 	trace_xfs_buf_unlock(bp, _RET_IP_);
 }
 
@@ -1249,7 +1229,7 @@ xfs_bwrite(
 	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q |
 			 XBF_WRITE_FAIL | XBF_DONE);
 
-	error = xfs_buf_submit_wait(bp);
+	error = xfs_buf_submit(bp);
 	if (error) {
 		xfs_force_shutdown(bp->b_target->bt_mount,
 				   SHUTDOWN_META_IO_ERROR);
@@ -1453,29 +1433,55 @@ _xfs_buf_ioapply(
 }
 
 /*
- * Asynchronous IO submission path. This transfers the buffer lock ownership and
- * the current reference to the IO. It is not safe to reference the buffer after
- * a call to this function unless the caller holds an additional reference
- * itself.
+ * Wait for I/O completion of a sync buffer and return the I/O error code.
  */
-void
-xfs_buf_submit(
+static int
+xfs_buf_iowait(
 	struct xfs_buf	*bp)
 {
+	ASSERT(!(bp->b_flags & XBF_ASYNC));
+
+	trace_xfs_buf_iowait(bp, _RET_IP_);
+	wait_for_completion(&bp->b_iowait);
+	trace_xfs_buf_iowait_done(bp, _RET_IP_);
+
+	return bp->b_error;
+}
+
+/*
+ * Buffer I/O submission path, read or write. Asynchronous submission transfers
+ * the buffer lock ownership and the current reference to the IO. It is not
+ * safe to reference the buffer after a call to this function unless the caller
+ * holds an additional reference itself.
+ */
+int
+__xfs_buf_submit(
+	struct xfs_buf	*bp,
+	bool		wait)
+{
+	int		error = 0;
+
 	trace_xfs_buf_submit(bp, _RET_IP_);
 
 	ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
-	ASSERT(bp->b_flags & XBF_ASYNC);
 
 	/* on shutdown we stale and complete the buffer immediately */
 	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
 		xfs_buf_ioerror(bp, -EIO);
 		bp->b_flags &= ~XBF_DONE;
 		xfs_buf_stale(bp);
-		xfs_buf_ioend(bp);
-		return;
+		if (bp->b_flags & XBF_ASYNC)
+			xfs_buf_ioend(bp);
+		return -EIO;
 	}
 
+	/*
+	 * Grab a reference so the buffer does not go away underneath us. For
+	 * async buffers, I/O completion drops the callers reference, which
+	 * could occur before submission returns.
+	 */
+	xfs_buf_hold(bp);
+
 	if (bp->b_flags & XBF_WRITE)
 		xfs_buf_wait_unpin(bp);
 
@@ -1483,22 +1489,13 @@ xfs_buf_submit(
 	bp->b_io_error = 0;
 
 	/*
-	 * The caller's reference is released during I/O completion.
-	 * This occurs some time after the last b_io_remaining reference is
-	 * released, so after we drop our Io reference we have to have some
-	 * other reference to ensure the buffer doesn't go away from underneath
-	 * us. Take a direct reference to ensure we have safe access to the
-	 * buffer until we are finished with it.
-	 */
-	xfs_buf_hold(bp);
-
-	/*
 	 * Set the count to 1 initially, this will stop an I/O completion
 	 * callout which happens before we have started all the I/O from calling
 	 * xfs_buf_ioend too early.
 	 */
 	atomic_set(&bp->b_io_remaining, 1);
-	xfs_buf_ioacct_inc(bp);
+	if (bp->b_flags & XBF_ASYNC)
+		xfs_buf_ioacct_inc(bp);
 	_xfs_buf_ioapply(bp);
 
 	/*
@@ -1507,74 +1504,19 @@ xfs_buf_submit(
 	 * that we don't return to the caller with completion still pending.
 	 */
 	if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
-		if (bp->b_error)
+		if (bp->b_error || !(bp->b_flags & XBF_ASYNC))
 			xfs_buf_ioend(bp);
 		else
 			xfs_buf_ioend_async(bp);
 	}
 
-	xfs_buf_rele(bp);
-	/* Note: it is not safe to reference bp now we've dropped our ref */
-}
-
-/*
- * Synchronous buffer IO submission path, read or write.
- */
-int
-xfs_buf_submit_wait(
-	struct xfs_buf	*bp)
-{
-	int		error;
-
-	trace_xfs_buf_submit_wait(bp, _RET_IP_);
-
-	ASSERT(!(bp->b_flags & (_XBF_DELWRI_Q | XBF_ASYNC)));
-
-	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
-		xfs_buf_ioerror(bp, -EIO);
-		xfs_buf_stale(bp);
-		bp->b_flags &= ~XBF_DONE;
-		return -EIO;
-	}
-
-	if (bp->b_flags & XBF_WRITE)
-		xfs_buf_wait_unpin(bp);
-
-	/* clear the internal error state to avoid spurious errors */
-	bp->b_io_error = 0;
+	if (wait)
+		error = xfs_buf_iowait(bp);
 
 	/*
-	 * For synchronous IO, the IO does not inherit the submitters reference
-	 * count, nor the buffer lock. Hence we cannot release the reference we
-	 * are about to take until we've waited for all IO completion to occur,
-	 * including any xfs_buf_ioend_async() work that may be pending.
-	 */
-	xfs_buf_hold(bp);
-
-	/*
-	 * Set the count to 1 initially, this will stop an I/O completion
-	 * callout which happens before we have started all the I/O from calling
-	 * xfs_buf_ioend too early.
-	 */
-	atomic_set(&bp->b_io_remaining, 1);
-	_xfs_buf_ioapply(bp);
-
-	/*
-	 * make sure we run completion synchronously if it raced with us and is
-	 * already complete.
-	 */
-	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
-		xfs_buf_ioend(bp);
-
-	/* wait for completion before gathering the error from the buffer */
-	trace_xfs_buf_iowait(bp, _RET_IP_);
-	wait_for_completion(&bp->b_iowait);
-	trace_xfs_buf_iowait_done(bp, _RET_IP_);
-	error = bp->b_error;
-
-	/*
-	 * all done now, we can release the hold that keeps the buffer
-	 * referenced for the entire IO.
+	 * Release the hold that keeps the buffer referenced for the entire
+	 * I/O. Note that if the buffer is async, it is not safe to reference
+	 * after this release.
 	 */
 	xfs_buf_rele(bp);
 	return error;
@@ -1972,16 +1914,11 @@ xfs_buf_cmp(
 }
 
 /*
- * submit buffers for write.
- *
- * When we have a large buffer list, we do not want to hold all the buffers
- * locked while we block on the request queue waiting for IO dispatch. To avoid
- * this problem, we lock and submit buffers in groups of 50, thereby minimising
- * the lock hold times for lists which may contain thousands of objects.
- *
- * To do this, we sort the buffer list before we walk the list to lock and
- * submit buffers, and we plug and unplug around each group of buffers we
- * submit.
+ * Submit buffers for write. If wait_list is specified, the buffers are
+ * submitted using sync I/O and placed on the wait list such that the caller can
+ * iowait each buffer. Otherwise async I/O is used and the buffers are released
+ * at I/O completion time. In either case, buffers remain locked until I/O
+ * completes and the buffer is released from the queue.
  */
 static int
 xfs_buf_delwri_submit_buffers(
@@ -2023,21 +1960,21 @@ xfs_buf_delwri_submit_buffers(
 		trace_xfs_buf_delwri_split(bp, _RET_IP_);
 
 		/*
-		 * We do all IO submission async. This means if we need
-		 * to wait for IO completion we need to take an extra
-		 * reference so the buffer is still valid on the other
-		 * side. We need to move the buffer onto the io_list
-		 * at this point so the caller can still access it.
+		 * If we have a wait list, each buffer (and associated delwri
+		 * queue reference) transfers to it and is submitted
+		 * synchronously. Otherwise, drop the buffer from the delwri
+		 * queue and submit async.
 		 */
 		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_WRITE_FAIL);
-		bp->b_flags |= XBF_WRITE | XBF_ASYNC;
+		bp->b_flags |= XBF_WRITE;
 		if (wait_list) {
-			xfs_buf_hold(bp);
+			bp->b_flags &= ~XBF_ASYNC;
 			list_move_tail(&bp->b_list, wait_list);
-		} else
+		} else {
+			bp->b_flags |= XBF_ASYNC;
 			list_del_init(&bp->b_list);
-
-		xfs_buf_submit(bp);
+		}
+		__xfs_buf_submit(bp, false);
 	}
 	blk_finish_plug(&plug);
 
@@ -2084,9 +2021,11 @@ xfs_buf_delwri_submit(
 
 		list_del_init(&bp->b_list);
 
-		/* locking the buffer will wait for async IO completion. */
-		xfs_buf_lock(bp);
-		error2 = bp->b_error;
+		/*
+		 * Wait on the locked buffer, check for errors and unlock and
+		 * release the delwri queue reference.
+		 */
+		error2 = xfs_buf_iowait(bp);
 		xfs_buf_relse(bp);
 		if (!error)
 			error = error2;
@@ -2132,23 +2071,18 @@ xfs_buf_delwri_pushbuf(
 
 	/*
 	 * Delwri submission clears the DELWRI_Q buffer flag and returns with
-	 * the buffer on the wait list with an associated reference. Rather than
+	 * the buffer on the wait list with the original reference. Rather than
 	 * bounce the buffer from a local wait list back to the original list
 	 * after I/O completion, reuse the original list as the wait list.
 	 */
 	xfs_buf_delwri_submit_buffers(&submit_list, buffer_list);
 
 	/*
-	 * The buffer is now under I/O and wait listed as during typical delwri
-	 * submission. Lock the buffer to wait for I/O completion. Rather than
-	 * remove the buffer from the wait list and release the reference, we
-	 * want to return with the buffer queued to the original list. The
-	 * buffer already sits on the original list with a wait list reference,
-	 * however. If we let the queue inherit that wait list reference, all we
-	 * need to do is reset the DELWRI_Q flag.
+	 * The buffer is now locked, under I/O and wait listed on the original
+	 * delwri queue. Wait for I/O completion, restore the DELWRI_Q flag and
+	 * return with the buffer unlocked and on the original queue.
 	 */
-	xfs_buf_lock(bp);
-	error = bp->b_error;
+	error = xfs_buf_iowait(bp);
 	bp->b_flags |= _XBF_DELWRI_Q;
 	xfs_buf_unlock(bp);
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index d24dbd4dac39..4e3171acd0f8 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -12,7 +12,6 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/dax.h>
-#include <linux/buffer_head.h>
 #include <linux/uio.h>
 #include <linux/list_lru.h>
 
@@ -199,10 +198,6 @@ typedef struct xfs_buf {
 	int			b_last_error;
 
 	const struct xfs_buf_ops	*b_ops;
-
-#ifdef XFS_BUF_LOCK_TRACKING
-	int			b_last_holder;
-#endif
 } xfs_buf_t;
 
 /* Finding and Reading Buffers */
@@ -298,8 +293,14 @@ extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error,
 		xfs_failaddr_t failaddr);
 #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address)
 extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
-extern void xfs_buf_submit(struct xfs_buf *bp);
-extern int xfs_buf_submit_wait(struct xfs_buf *bp);
+
+extern int __xfs_buf_submit(struct xfs_buf *bp, bool);
+static inline int xfs_buf_submit(struct xfs_buf *bp)
+{
+	bool wait = bp->b_flags & XBF_ASYNC ? false : true;
+	return __xfs_buf_submit(bp, wait);
+}
+
 extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 				xfs_buf_rw_t);
 #define xfs_buf_zero(bp, off, len) \
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 678a5fcd7576..93f07edafd81 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -128,7 +128,7 @@ next_extent:
 	}
 
 out_del_cursor:
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	xfs_buf_relse(agbp);
 out_put_perag:
 	xfs_perag_put(pag);
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 0973a0423bed..87e6dd5326d5 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -286,17 +286,15 @@ xfs_dquot_disk_alloc(
 	struct xfs_buf		**bpp)
 {
 	struct xfs_bmbt_irec	map;
-	struct xfs_defer_ops	dfops;
-	struct xfs_mount	*mp = (*tpp)->t_mountp;
+	struct xfs_trans	*tp = *tpp;
+	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_buf		*bp;
 	struct xfs_inode	*quotip = xfs_quota_inode(mp, dqp->dq_flags);
-	xfs_fsblock_t		firstblock;
 	int			nmaps = 1;
 	int			error;
 
 	trace_xfs_dqalloc(dqp);
 
-	xfs_defer_init(&dfops, &firstblock);
 	xfs_ilock(quotip, XFS_ILOCK_EXCL);
 	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
 		/*
@@ -308,13 +306,12 @@ xfs_dquot_disk_alloc(
 	}
 
 	/* Create the block mapping. */
-	xfs_trans_ijoin(*tpp, quotip, XFS_ILOCK_EXCL);
-	error = xfs_bmapi_write(*tpp, quotip, dqp->q_fileoffset,
+	xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
+	error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset,
 			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
-			&firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
-			&map, &nmaps, &dfops);
+			XFS_QM_DQALLOC_SPACE_RES(mp), &map, &nmaps);
 	if (error)
-		goto error0;
+		return error;
 	ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
 	ASSERT(nmaps == 1);
 	ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
@@ -326,19 +323,17 @@ xfs_dquot_disk_alloc(
 	dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
 
 	/* now we can just get the buffer (there's nothing to read yet) */
-	bp = xfs_trans_get_buf(*tpp, mp->m_ddev_targp, dqp->q_blkno,
+	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, dqp->q_blkno,
 			mp->m_quotainfo->qi_dqchunklen, 0);
-	if (!bp) {
-		error = -ENOMEM;
-		goto error1;
-	}
+	if (!bp)
+		return -ENOMEM;
 	bp->b_ops = &xfs_dquot_buf_ops;
 
 	/*
 	 * Make a chunk of dquots out of this buffer and log
 	 * the entire thing.
 	 */
-	xfs_qm_init_dquot_blk(*tpp, mp, be32_to_cpu(dqp->q_core.d_id),
+	xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
 			      dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
 	xfs_buf_set_ref(bp, XFS_DQUOT_REF);
 
@@ -352,10 +347,8 @@ xfs_dquot_disk_alloc(
 	 * the buffer locked across the _defer_finish call.  We can now do
 	 * this correctly with xfs_defer_bjoin.
 	 *
-	 * Above, we allocated a disk block for the dquot information and
-	 * used get_buf to initialize the dquot.  If the _defer_bjoin fails,
-	 * the buffer is still locked to *tpp, so we must _bhold_release and
-	 * then _trans_brelse the buffer.  If the _defer_finish fails, the old
+	 * Above, we allocated a disk block for the dquot information and used
+	 * get_buf to initialize the dquot. If the _defer_finish fails, the old
 	 * transaction is gone but the new buffer is not joined or held to any
 	 * transaction, so we must _buf_relse it.
 	 *
@@ -364,25 +357,15 @@ xfs_dquot_disk_alloc(
 	 * is responsible for unlocking any buffer passed back, either
 	 * manually or by committing the transaction.
 	 */
-	xfs_trans_bhold(*tpp, bp);
-	error = xfs_defer_bjoin(&dfops, bp);
-	if (error) {
-		xfs_trans_bhold_release(*tpp, bp);
-		xfs_trans_brelse(*tpp, bp);
-		goto error1;
-	}
-	error = xfs_defer_finish(tpp, &dfops);
+	xfs_trans_bhold(tp, bp);
+	error = xfs_defer_finish(tpp);
+	tp = *tpp;
 	if (error) {
 		xfs_buf_relse(bp);
-		goto error1;
+		return error;
 	}
 	*bpp = bp;
 	return 0;
-
-error1:
-	xfs_defer_cancel(&dfops);
-error0:
-	return error;
 }
 
 /*
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 0470114a8d80..9866f542e77b 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -50,6 +50,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_LOG_ITEM_PIN,
 	XFS_RANDOM_BUF_LRU_REF,
 	XFS_RANDOM_FORCE_SCRUB_REPAIR,
+	XFS_RANDOM_FORCE_SUMMARY_RECALC,
 };
 
 struct xfs_errortag_attr {
@@ -157,6 +158,7 @@ XFS_ERRORTAG_ATTR_RW(log_bad_crc,	XFS_ERRTAG_LOG_BAD_CRC);
 XFS_ERRORTAG_ATTR_RW(log_item_pin,	XFS_ERRTAG_LOG_ITEM_PIN);
 XFS_ERRORTAG_ATTR_RW(buf_lru_ref,	XFS_ERRTAG_BUF_LRU_REF);
 XFS_ERRORTAG_ATTR_RW(force_repair,	XFS_ERRTAG_FORCE_SCRUB_REPAIR);
+XFS_ERRORTAG_ATTR_RW(bad_summary,	XFS_ERRTAG_FORCE_SUMMARY_RECALC);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -192,6 +194,7 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(log_item_pin),
 	XFS_ERRORTAG_ATTR_LIST(buf_lru_ref),
 	XFS_ERRORTAG_ATTR_LIST(force_repair),
+	XFS_ERRORTAG_ATTR_LIST(bad_summary),
 	NULL,
 };
 
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 3cf4682e2510..f2284ceb129f 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -150,7 +150,7 @@ xfs_nfs_get_inode(
 	}
 
 	if (VFS_I(ip)->i_generation != generation) {
-		IRELE(ip);
+		xfs_irele(ip);
 		return ERR_PTR(-ESTALE);
 	}
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a3e7767a5715..181e9084519b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -721,12 +721,10 @@ xfs_file_write_iter(
 
 static void
 xfs_wait_dax_page(
-	struct inode		*inode,
-	bool			*did_unlock)
+	struct inode		*inode)
 {
 	struct xfs_inode        *ip = XFS_I(inode);
 
-	*did_unlock = true;
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	schedule();
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
@@ -735,8 +733,7 @@ xfs_wait_dax_page(
 static int
 xfs_break_dax_layouts(
 	struct inode		*inode,
-	uint			iolock,
-	bool			*did_unlock)
+	bool			*retry)
 {
 	struct page		*page;
 
@@ -746,9 +743,10 @@ xfs_break_dax_layouts(
 	if (!page)
 		return 0;
 
+	*retry = true;
 	return ___wait_var_event(&page->_refcount,
 			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
-			0, 0, xfs_wait_dax_page(inode, did_unlock));
+			0, 0, xfs_wait_dax_page(inode));
 }
 
 int
@@ -766,7 +764,7 @@ xfs_break_layouts(
 		retry = false;
 		switch (reason) {
 		case BREAK_UNMAP:
-			error = xfs_break_dax_layouts(inode, *iolock, &retry);
+			error = xfs_break_dax_layouts(inode, &retry);
 			if (error || retry)
 				break;
 			/* fall through */
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 2d2c5ab9143c..182501373af2 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -19,6 +19,8 @@
 #include "xfs_filestream.h"
 #include "xfs_trace.h"
 #include "xfs_ag_resv.h"
+#include "xfs_trans.h"
+#include "xfs_shared.h"
 
 struct xfs_fstrm_item {
 	struct xfs_mru_cache_elem	mru;
@@ -339,7 +341,7 @@ xfs_filestream_lookup_ag(
 	if (xfs_filestream_pick_ag(pip, startag, &ag, 0, 0))
 		ag = NULLAGNUMBER;
 out:
-	IRELE(pip);
+	xfs_irele(pip);
 	return ag;
 }
 
@@ -377,7 +379,7 @@ xfs_filestream_new_ag(
 
 	if (xfs_alloc_is_userdata(ap->datatype))
 		flags |= XFS_PICK_USERDATA;
-	if (ap->dfops->dop_low)
+	if (ap->tp->t_flags & XFS_TRANS_LOWMODE)
 		flags |= XFS_PICK_LOWSPACE;
 
 	err = xfs_filestream_pick_ag(pip, startag, agp, flags, minlen);
@@ -388,7 +390,7 @@ xfs_filestream_new_ag(
 	if (mru)
 		xfs_fstrm_free_func(mp, mru);
 
-	IRELE(pip);
+	xfs_irele(pip);
 exit:
 	if (*agp == NULLAGNUMBER)
 		*agp = 0;
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index c7157bc48bd1..3d76a9e35870 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -214,12 +214,12 @@ xfs_getfsmap_is_shared(
 	/* Are there any shared blocks here? */
 	flen = 0;
 	cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp,
-			info->agno, NULL);
+			info->agno);
 
 	error = xfs_refcount_find_shared(cur, rec->rm_startblock,
 			rec->rm_blockcount, &fbno, &flen, false);
 
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 3f2bd6032cf8..7c00b8bedfe3 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -536,7 +536,7 @@ xfs_fs_reserve_ag_blocks(
 
 	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
 		pag = xfs_perag_get(mp, agno);
-		err2 = xfs_ag_resv_init(pag);
+		err2 = xfs_ag_resv_init(pag, NULL);
 		xfs_perag_put(pag);
 		if (err2 && !error)
 			error = err2;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 47f417d20a30..245483cc282b 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -66,7 +66,7 @@ xfs_inode_alloc(
 	ip->i_cowfp = NULL;
 	ip->i_cnextents = 0;
 	ip->i_cformat = XFS_DINODE_FMT_EXTENTS;
-	memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
+	memset(&ip->i_df, 0, sizeof(ip->i_df));
 	ip->i_flags = 0;
 	ip->i_delayed_blks = 0;
 	memset(&ip->i_d, 0, sizeof(ip->i_d));
@@ -716,7 +716,7 @@ xfs_icache_inode_is_allocated(
 		return error;
 
 	*inuse = !!(VFS_I(ip)->i_mode);
-	IRELE(ip);
+	xfs_irele(ip);
 	return 0;
 }
 
@@ -856,7 +856,7 @@ restart:
 			    xfs_iflags_test(batch[i], XFS_INEW))
 				xfs_inew_wait(batch[i]);
 			error = execute(batch[i], flags, args);
-			IRELE(batch[i]);
+			xfs_irele(batch[i]);
 			if (error == -EAGAIN) {
 				skipped++;
 				continue;
@@ -1697,14 +1697,13 @@ xfs_inode_clear_eofblocks_tag(
  */
 static bool
 xfs_prep_free_cowblocks(
-	struct xfs_inode	*ip,
-	struct xfs_ifork	*ifp)
+	struct xfs_inode	*ip)
 {
 	/*
 	 * Just clear the tag if we have an empty cow fork or none at all. It's
 	 * possible the inode was fully unshared since it was originally tagged.
 	 */
-	if (!xfs_is_reflink_inode(ip) || !ifp->if_bytes) {
+	if (!xfs_inode_has_cow_data(ip)) {
 		trace_xfs_inode_free_cowblocks_invalid(ip);
 		xfs_inode_clear_cowblocks_tag(ip);
 		return false;
@@ -1742,11 +1741,10 @@ xfs_inode_free_cowblocks(
 	void			*args)
 {
 	struct xfs_eofblocks	*eofb = args;
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	int			match;
 	int			ret = 0;
 
-	if (!xfs_prep_free_cowblocks(ip, ifp))
+	if (!xfs_prep_free_cowblocks(ip))
 		return 0;
 
 	if (eofb) {
@@ -1771,7 +1769,7 @@ xfs_inode_free_cowblocks(
 	 * Check again, nobody else should be able to dirty blocks or change
 	 * the reflink iflag now that we have the first two locks held.
 	 */
-	if (xfs_prep_free_cowblocks(ip, ifp))
+	if (xfs_prep_free_cowblocks(ip))
 		ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 5df4de666cc1..d957a46dc1cb 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -927,7 +927,7 @@ xfs_ialloc(
 	case S_IFLNK:
 		ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
 		ip->i_df.if_flags = XFS_IFEXTENTS;
-		ip->i_df.if_bytes = ip->i_df.if_real_bytes = 0;
+		ip->i_df.if_bytes = 0;
 		ip->i_df.if_u1.if_root = NULL;
 		break;
 	default:
@@ -1142,8 +1142,6 @@ xfs_create(
 	struct xfs_inode	*ip = NULL;
 	struct xfs_trans	*tp = NULL;
 	int			error;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	bool                    unlock_dp_on_error = false;
 	prid_t			prid;
 	struct xfs_dquot	*udqp = NULL;
@@ -1195,9 +1193,6 @@ xfs_create(
 	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
 	unlock_dp_on_error = true;
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-
 	/*
 	 * Reserve disk quota and the inode.
 	 */
@@ -1226,7 +1221,7 @@ xfs_create(
 	unlock_dp_on_error = false;
 
 	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
-					&first_block, &dfops, resblks ?
+				   resblks ?
 					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
 	if (error) {
 		ASSERT(error != -ENOSPC);
@@ -1238,11 +1233,11 @@ xfs_create(
 	if (is_dir) {
 		error = xfs_dir_init(tp, ip, dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		error = xfs_bumplink(tp, dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -1260,10 +1255,6 @@ xfs_create(
 	 */
 	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_release_inode;
@@ -1275,8 +1266,6 @@ xfs_create(
 	*ipp = ip;
 	return 0;
 
- out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
  out_trans_cancel:
 	xfs_trans_cancel(tp);
  out_release_inode:
@@ -1287,7 +1276,7 @@ xfs_create(
 	 */
 	if (ip) {
 		xfs_finish_inode_setup(ip);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 
 	xfs_qm_dqrele(udqp);
@@ -1382,7 +1371,7 @@ xfs_create_tmpfile(
 	 */
 	if (ip) {
 		xfs_finish_inode_setup(ip);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 
 	xfs_qm_dqrele(udqp);
@@ -1401,8 +1390,6 @@ xfs_link(
 	xfs_mount_t		*mp = tdp->i_mount;
 	xfs_trans_t		*tp;
 	int			error;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t           first_block;
 	int			resblks;
 
 	trace_xfs_link(tdp, target_name);
@@ -1451,9 +1438,6 @@ xfs_link(
 			goto error_return;
 	}
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-
 	/*
 	 * Handle initial link state of O_TMPFILE inode
 	 */
@@ -1464,7 +1448,7 @@ xfs_link(
 	}
 
 	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
-					&first_block, &dfops, resblks);
+				   resblks);
 	if (error)
 		goto error_return;
 	xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -1482,12 +1466,6 @@ xfs_link(
 	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error) {
-		xfs_defer_cancel(&dfops);
-		goto error_return;
-	}
-
 	return xfs_trans_commit(tp);
 
  error_return:
@@ -1545,8 +1523,6 @@ xfs_itruncate_extents_flags(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		first_unmap_block;
 	xfs_fileoff_t		last_block;
 	xfs_filblks_t		unmap_len;
@@ -1583,10 +1559,9 @@ xfs_itruncate_extents_flags(
 	ASSERT(first_unmap_block < last_block);
 	unmap_len = last_block - first_unmap_block + 1;
 	while (!done) {
-		xfs_defer_init(&dfops, &first_block);
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
-				    XFS_ITRUNC_MAX_EXTENTS, &first_block,
-				    &dfops, &done);
+				    XFS_ITRUNC_MAX_EXTENTS, &done);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1594,10 +1569,9 @@ xfs_itruncate_extents_flags(
 		 * Duplicate the transaction that has the permanent
 		 * reservation and commit the old transaction.
 		 */
-		xfs_defer_ijoin(&dfops, ip);
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out;
 
 		error = xfs_trans_roll_inode(&tp, ip);
 		if (error)
@@ -1631,7 +1605,7 @@ out_bmap_cancel:
 	 * the transaction can be properly aborted.  We just need to make sure
 	 * we're not holding any resources that we were not when we came in.
 	 */
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp);
 	goto out;
 }
 
@@ -1733,7 +1707,6 @@ xfs_inactive_truncate(
 		ASSERT(XFS_FORCED_SHUTDOWN(mp));
 		return error;
 	}
-
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
@@ -1774,8 +1747,6 @@ STATIC int
 xfs_inactive_ifree(
 	struct xfs_inode *ip)
 {
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
@@ -1812,9 +1783,7 @@ xfs_inactive_ifree(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-	error = xfs_ifree(tp, ip, &dfops);
+	error = xfs_ifree(tp, ip);
 	if (error) {
 		/*
 		 * If we fail to free the inode, shut down.  The cancel
@@ -1840,12 +1809,6 @@ xfs_inactive_ifree(
 	 * Just ignore errors at this point.  There is nothing we can do except
 	 * to try to keep going. Make sure it's not a silent error.
 	 */
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error) {
-		xfs_notice(mp, "%s: xfs_defer_finish returned error %d",
-			__func__, error);
-		xfs_defer_cancel(&dfops);
-	}
 	error = xfs_trans_commit(tp);
 	if (error)
 		xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
@@ -1868,7 +1831,6 @@ xfs_inactive(
 	xfs_inode_t	*ip)
 {
 	struct xfs_mount	*mp;
-	struct xfs_ifork	*cow_ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	int			error;
 	int			truncate = 0;
 
@@ -1877,7 +1839,6 @@ xfs_inactive(
 	 * to clean up here.
 	 */
 	if (VFS_I(ip)->i_mode == 0) {
-		ASSERT(ip->i_df.if_real_bytes == 0);
 		ASSERT(ip->i_df.if_broot_bytes == 0);
 		return;
 	}
@@ -1890,7 +1851,7 @@ xfs_inactive(
 		return;
 
 	/* Try to clean out the cow blocks if there are any. */
-	if (xfs_is_reflink_inode(ip) && cow_ifp->if_bytes > 0)
+	if (xfs_inode_has_cow_data(ip))
 		xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
 
 	if (VFS_I(ip)->i_nlink != 0) {
@@ -2445,9 +2406,8 @@ xfs_ifree_local_data(
  */
 int
 xfs_ifree(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
 {
 	int			error;
 	struct xfs_icluster	xic = { 0 };
@@ -2466,7 +2426,7 @@ xfs_ifree(
 	if (error)
 		return error;
 
-	error = xfs_difree(tp, ip->i_ino, dfops, &xic);
+	error = xfs_difree(tp, ip->i_ino, &xic);
 	if (error)
 		return error;
 
@@ -2577,8 +2537,6 @@ xfs_remove(
 	xfs_trans_t             *tp = NULL;
 	int			is_dir = S_ISDIR(VFS_I(ip)->i_mode);
 	int                     error = 0;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t           first_block;
 	uint			resblks;
 
 	trace_xfs_remove(dp, name);
@@ -2658,13 +2616,10 @@ xfs_remove(
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-	error = xfs_dir_removename(tp, dp, name, ip->i_ino,
-					&first_block, &dfops, resblks);
+	error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks);
 	if (error) {
 		ASSERT(error != -ENOENT);
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 	}
 
 	/*
@@ -2675,10 +2630,6 @@ xfs_remove(
 	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto std_return;
@@ -2688,8 +2639,6 @@ xfs_remove(
 
 	return 0;
 
- out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
  out_trans_cancel:
 	xfs_trans_cancel(tp);
  std_return:
@@ -2749,11 +2698,8 @@ xfs_sort_for_rename(
 
 static int
 xfs_finish_rename(
-	struct xfs_trans	*tp,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_trans	*tp)
 {
-	int			error;
-
 	/*
 	 * If this is a synchronous mount, make sure that the rename transaction
 	 * goes to disk before returning to the user.
@@ -2761,13 +2707,6 @@ xfs_finish_rename(
 	if (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_defer_finish(&tp, dfops);
-	if (error) {
-		xfs_defer_cancel(dfops);
-		xfs_trans_cancel(tp);
-		return error;
-	}
-
 	return xfs_trans_commit(tp);
 }
 
@@ -2785,8 +2724,6 @@ xfs_cross_rename(
 	struct xfs_inode	*dp2,
 	struct xfs_name		*name2,
 	struct xfs_inode	*ip2,
-	struct xfs_defer_ops	*dfops,
-	xfs_fsblock_t		*first_block,
 	int			spaceres)
 {
 	int		error = 0;
@@ -2795,16 +2732,12 @@ xfs_cross_rename(
 	int		dp2_flags = 0;
 
 	/* Swap inode number for dirent in first parent */
-	error = xfs_dir_replace(tp, dp1, name1,
-				ip2->i_ino,
-				first_block, dfops, spaceres);
+	error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, spaceres);
 	if (error)
 		goto out_trans_abort;
 
 	/* Swap inode number for dirent in second parent */
-	error = xfs_dir_replace(tp, dp2, name2,
-				ip1->i_ino,
-				first_block, dfops, spaceres);
+	error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, spaceres);
 	if (error)
 		goto out_trans_abort;
 
@@ -2818,8 +2751,7 @@ xfs_cross_rename(
 
 		if (S_ISDIR(VFS_I(ip2)->i_mode)) {
 			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
-						dp1->i_ino, first_block,
-						dfops, spaceres);
+						dp1->i_ino, spaceres);
 			if (error)
 				goto out_trans_abort;
 
@@ -2845,8 +2777,7 @@ xfs_cross_rename(
 
 		if (S_ISDIR(VFS_I(ip1)->i_mode)) {
 			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
-						dp2->i_ino, first_block,
-						dfops, spaceres);
+						dp2->i_ino, spaceres);
 			if (error)
 				goto out_trans_abort;
 
@@ -2885,10 +2816,9 @@ xfs_cross_rename(
 	}
 	xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
-	return xfs_finish_rename(tp, dfops);
+	return xfs_finish_rename(tp);
 
 out_trans_abort:
-	xfs_defer_cancel(dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -2943,8 +2873,6 @@ xfs_rename(
 {
 	struct xfs_mount	*mp = src_dp->i_mount;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	struct xfs_inode	*wip = NULL;		/* whiteout inode */
 	struct xfs_inode	*inodes[__XFS_SORT_INODES];
 	int			num_inodes = __XFS_SORT_INODES;
@@ -3026,14 +2954,11 @@ xfs_rename(
 		goto out_trans_cancel;
 	}
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-
 	/* RENAME_EXCHANGE is unique from here on. */
 	if (flags & RENAME_EXCHANGE)
 		return xfs_cross_rename(tp, src_dp, src_name, src_ip,
 					target_dp, target_name, target_ip,
-					&dfops, &first_block, spaceres);
+					spaceres);
 
 	/*
 	 * Set up the target.
@@ -3054,10 +2979,9 @@ xfs_rename(
 		 * to account for the ".." reference from the new entry.
 		 */
 		error = xfs_dir_createname(tp, target_dp, target_name,
-						src_ip->i_ino, &first_block,
-						&dfops, spaceres);
+					   src_ip->i_ino, spaceres);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		xfs_trans_ichgtime(tp, target_dp,
 					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -3065,7 +2989,7 @@ xfs_rename(
 		if (new_parent && src_is_directory) {
 			error = xfs_bumplink(tp, target_dp);
 			if (error)
-				goto out_bmap_cancel;
+				goto out_trans_cancel;
 		}
 	} else { /* target_ip != NULL */
 		/*
@@ -3094,10 +3018,9 @@ xfs_rename(
 		 * name at the destination directory, remove it first.
 		 */
 		error = xfs_dir_replace(tp, target_dp, target_name,
-					src_ip->i_ino,
-					&first_block, &dfops, spaceres);
+					src_ip->i_ino, spaceres);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		xfs_trans_ichgtime(tp, target_dp,
 					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -3108,7 +3031,7 @@ xfs_rename(
 		 */
 		error = xfs_droplink(tp, target_ip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		if (src_is_directory) {
 			/*
@@ -3116,7 +3039,7 @@ xfs_rename(
 			 */
 			error = xfs_droplink(tp, target_ip);
 			if (error)
-				goto out_bmap_cancel;
+				goto out_trans_cancel;
 		}
 	} /* target_ip != NULL */
 
@@ -3129,11 +3052,10 @@ xfs_rename(
 		 * directory.
 		 */
 		error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
-					target_dp->i_ino,
-					&first_block, &dfops, spaceres);
+					target_dp->i_ino, spaceres);
 		ASSERT(error != -EEXIST);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -3159,7 +3081,7 @@ xfs_rename(
 		 */
 		error = xfs_droplink(tp, src_dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -3169,12 +3091,12 @@ xfs_rename(
 	 */
 	if (wip) {
 		error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino,
-					&first_block, &dfops, spaceres);
+					spaceres);
 	} else
 		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
-					   &first_block, &dfops, spaceres);
+					   spaceres);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
 	/*
 	 * For whiteouts, we need to bump the link count on the whiteout inode.
@@ -3188,10 +3110,10 @@ xfs_rename(
 		ASSERT(VFS_I(wip)->i_nlink == 0);
 		error = xfs_bumplink(tp, wip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 		error = xfs_iunlink_remove(tp, wip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 		xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
 
 		/*
@@ -3207,18 +3129,16 @@ xfs_rename(
 	if (new_parent)
 		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
 
-	error = xfs_finish_rename(tp, &dfops);
+	error = xfs_finish_rename(tp);
 	if (wip)
-		IRELE(wip);
+		xfs_irele(wip);
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 out_release_wip:
 	if (wip)
-		IRELE(wip);
+		xfs_irele(wip);
 	return error;
 }
 
@@ -3674,3 +3594,12 @@ xfs_iflush_int(
 corrupt_out:
 	return -EFSCORRUPTED;
 }
+
+/* Release an inode. */
+void
+xfs_irele(
+	struct xfs_inode	*ip)
+{
+	trace_xfs_irele(ip, _RET_IP_);
+	iput(VFS_I(ip));
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 2ed63a49e890..be2014520155 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -15,7 +15,6 @@
 struct xfs_dinode;
 struct xfs_inode;
 struct xfs_buf;
-struct xfs_defer_ops;
 struct xfs_bmbt_irec;
 struct xfs_inode_log_item;
 struct xfs_mount;
@@ -34,9 +33,9 @@ typedef struct xfs_inode {
 	struct xfs_imap		i_imap;		/* location for xfs_imap() */
 
 	/* Extent information. */
-	xfs_ifork_t		*i_afp;		/* attribute fork pointer */
-	xfs_ifork_t		*i_cowfp;	/* copy on write extents */
-	xfs_ifork_t		i_df;		/* data fork */
+	struct xfs_ifork	*i_afp;		/* attribute fork pointer */
+	struct xfs_ifork	*i_cowfp;	/* copy on write extents */
+	struct xfs_ifork	i_df;		/* data fork */
 
 	/* operations vectors */
 	const struct xfs_dir_ops *d_ops;		/* directory ops vector */
@@ -199,6 +198,15 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
 }
 
 /*
+ * Check if an inode has any data in the COW fork.  This might be often false
+ * even for inodes with the reflink flag when there is no pending COW operation.
+ */
+static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
+{
+	return ip->i_cowfp && ip->i_cowfp->if_bytes;
+}
+
+/*
  * In-core inode flags.
  */
 #define XFS_IRECLAIM		(1 << 0) /* started reclaiming this inode */
@@ -415,8 +423,7 @@ uint		xfs_ilock_data_map_shared(struct xfs_inode *);
 uint		xfs_ilock_attr_map_shared(struct xfs_inode *);
 
 uint		xfs_ip2xflags(struct xfs_inode *);
-int		xfs_ifree(struct xfs_trans *, xfs_inode_t *,
-			   struct xfs_defer_ops *);
+int		xfs_ifree(struct xfs_trans *, struct xfs_inode *);
 int		xfs_itruncate_extents_flags(struct xfs_trans **,
 				struct xfs_inode *, int, xfs_fsize_t, int);
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
@@ -484,18 +491,7 @@ static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
 	xfs_finish_inode_setup(ip);
 }
 
-#define IHOLD(ip) \
-do { \
-	ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \
-	ihold(VFS_I(ip)); \
-	trace_xfs_ihold(ip, _THIS_IP_); \
-} while (0)
-
-#define IRELE(ip) \
-do { \
-	trace_xfs_irele(ip, _THIS_IP_); \
-	iput(VFS_I(ip)); \
-} while (0)
+void xfs_irele(struct xfs_inode *ip);
 
 extern struct kmem_zone	*xfs_inode_zone;
 
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 2389c34c172d..fa1c4fe2ffbf 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -194,8 +194,6 @@ xfs_inode_item_format_data_fork(
 			 * to be there by xfs_idata_realloc().
 			 */
 			data_bytes = roundup(ip->i_df.if_bytes, 4);
-			ASSERT(ip->i_df.if_real_bytes == 0 ||
-			       ip->i_df.if_real_bytes >= data_bytes);
 			ASSERT(ip->i_df.if_u1.if_data != NULL);
 			ASSERT(ip->i_d.di_size > 0);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
@@ -280,8 +278,6 @@ xfs_inode_item_format_attr_fork(
 			 * to be there by xfs_idata_realloc().
 			 */
 			data_bytes = roundup(ip->i_afp->if_bytes, 4);
-			ASSERT(ip->i_afp->if_real_bytes == 0 ||
-			       ip->i_afp->if_real_bytes >= data_bytes);
 			ASSERT(ip->i_afp->if_u1.if_data != NULL);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
 					ip->i_afp->if_u1.if_data,
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 55876dd02f0c..6320aca39f39 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2000-2006 Silicon Graphics, Inc.
- * Copyright (c) 2016 Christoph Hellwig.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  * All Rights Reserved.
  */
 #include <linux/iomap.h>
@@ -152,13 +152,11 @@ xfs_iomap_write_direct(
 	xfs_fileoff_t	offset_fsb;
 	xfs_fileoff_t	last_fsb;
 	xfs_filblks_t	count_fsb, resaligned;
-	xfs_fsblock_t	firstfsb;
 	xfs_extlen_t	extsz;
 	int		nimaps;
 	int		quota_flag;
 	int		rt;
 	xfs_trans_t	*tp;
-	struct xfs_defer_ops dfops;
 	uint		qblocks, resblks, resrtextents;
 	int		error;
 	int		lockmode;
@@ -254,21 +252,15 @@ xfs_iomap_write_direct(
 	 * From this point onwards we overwrite the imap pointer that the
 	 * caller gave to us.
 	 */
-	xfs_defer_init(&dfops, &firstfsb);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				bmapi_flags, &firstfsb, resblks, imap,
-				&nimaps, &dfops);
+				bmapi_flags, resblks, imap, &nimaps);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_res_cancel;
 
 	/*
 	 * Complete the transaction
 	 */
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_unlock;
@@ -288,8 +280,7 @@ out_unlock:
 	xfs_iunlock(ip, lockmode);
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+out_res_cancel:
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
@@ -626,7 +617,7 @@ retry:
 	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
 	 * them out if the write happens to fail.
 	 */
-	iomap->flags = IOMAP_F_NEW;
+	iomap->flags |= IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
 	if (isnullstartblock(got.br_startblock))
@@ -660,13 +651,13 @@ xfs_iomap_write_allocate(
 	xfs_inode_t	*ip,
 	int		whichfork,
 	xfs_off_t	offset,
-	xfs_bmbt_irec_t *imap)
+	xfs_bmbt_irec_t *imap,
+	unsigned int	*cow_seq)
 {
 	xfs_mount_t	*mp = ip->i_mount;
+	struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
 	xfs_fileoff_t	offset_fsb, last_block;
 	xfs_fileoff_t	end_fsb, map_start_fsb;
-	xfs_fsblock_t	first_block;
-	struct xfs_defer_ops	dfops;
 	xfs_filblks_t	count_fsb;
 	xfs_trans_t	*tp;
 	int		nimaps;
@@ -716,8 +707,6 @@ xfs_iomap_write_allocate(
 			xfs_ilock(ip, XFS_ILOCK_EXCL);
 			xfs_trans_ijoin(tp, ip, 0);
 
-			xfs_defer_init(&dfops, &first_block);
-
 			/*
 			 * it is possible that the extents have changed since
 			 * we did the read call as we dropped the ilock for a
@@ -770,13 +759,8 @@ xfs_iomap_write_allocate(
 			 * pointer that the caller gave to us.
 			 */
 			error = xfs_bmapi_write(tp, ip, map_start_fsb,
-						count_fsb, flags, &first_block,
-						nres, imap, &nimaps,
-						&dfops);
-			if (error)
-				goto trans_cancel;
-
-			error = xfs_defer_finish(&tp, &dfops);
+						count_fsb, flags, nres, imap,
+						&nimaps);
 			if (error)
 				goto trans_cancel;
 
@@ -784,6 +768,8 @@ xfs_iomap_write_allocate(
 			if (error)
 				goto error0;
 
+			if (whichfork == XFS_COW_FORK)
+				*cow_seq = READ_ONCE(ifp->if_seq);
 			xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		}
 
@@ -810,7 +796,6 @@ xfs_iomap_write_allocate(
 	}
 
 trans_cancel:
-	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 error0:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -828,11 +813,9 @@ xfs_iomap_write_unwritten(
 	xfs_fileoff_t	offset_fsb;
 	xfs_filblks_t	count_fsb;
 	xfs_filblks_t	numblks_fsb;
-	xfs_fsblock_t	firstfsb;
 	int		nimaps;
 	xfs_trans_t	*tp;
 	xfs_bmbt_irec_t imap;
-	struct xfs_defer_ops dfops;
 	struct inode	*inode = VFS_I(ip);
 	xfs_fsize_t	i_size;
 	uint		resblks;
@@ -877,11 +860,10 @@ xfs_iomap_write_unwritten(
 		/*
 		 * Modify the unwritten extent state of the buffer.
 		 */
-		xfs_defer_init(&dfops, &firstfsb);
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-					XFS_BMAPI_CONVERT, &firstfsb, resblks,
-					&imap, &nimaps, &dfops);
+					XFS_BMAPI_CONVERT, resblks, &imap,
+					&nimaps);
 		if (error)
 			goto error_on_bmapi_transaction;
 
@@ -901,10 +883,6 @@ xfs_iomap_write_unwritten(
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		}
 
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto error_on_bmapi_transaction;
-
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
@@ -928,7 +906,6 @@ xfs_iomap_write_unwritten(
 	return 0;
 
 error_on_bmapi_transaction:
-	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -1132,7 +1109,7 @@ xfs_file_iomap_begin(
 	if (error)
 		return error;
 
-	iomap->flags = IOMAP_F_NEW;
+	iomap->flags |= IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
 
 out_finish:
@@ -1202,11 +1179,8 @@ xfs_file_iomap_end_delalloc(
 		truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
 					 XFS_FSB_TO_B(mp, end_fsb) - 1);
 
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
 					       end_fsb - start_fsb);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
 		if (error && !XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_alert(mp, "%s: unable to clean up ino %lld",
 				__func__, ip->i_ino);
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 83474c9cede9..c6170548831b 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -14,7 +14,7 @@ struct xfs_bmbt_irec;
 int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
 			struct xfs_bmbt_irec *, int);
 int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t,
-			struct xfs_bmbt_irec *);
+			struct xfs_bmbt_irec *, unsigned int *);
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 
 void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 0fa29f39d658..c3e74f9128e8 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -26,6 +26,7 @@
 #include "xfs_dir2.h"
 #include "xfs_trans_space.h"
 #include "xfs_iomap.h"
+#include "xfs_defer.h"
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
@@ -208,7 +209,7 @@ xfs_generic_create(
 	xfs_finish_inode_setup(ip);
 	if (!tmpfile)
 		xfs_cleanup_inode(dir, inode, dentry);
-	iput(inode);
+	xfs_irele(ip);
 	goto out_free_acl;
 }
 
@@ -390,7 +391,7 @@ xfs_vn_symlink(
  out_cleanup_inode:
 	xfs_finish_inode_setup(cip);
 	xfs_cleanup_inode(dir, inode, dentry);
-	iput(inode);
+	xfs_irele(cip);
  out:
 	return error;
 }
@@ -1253,7 +1254,7 @@ xfs_setup_inode(
 
 	inode_sb_list_add(inode);
 	/* make the inode look hashed for the writeback code */
-	hlist_add_fake(&inode->i_hash);
+	inode_fake_hash(inode);
 
 	inode->i_uid    = xfs_uid_to_kuid(ip->i_d.di_uid);
 	inode->i_gid    = xfs_gid_to_kgid(ip->i_d.di_gid);
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 24f4f1c555b5..e9508ba01ed1 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -114,7 +114,7 @@ xfs_bulkstat_one_int(
 		break;
 	}
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	IRELE(ip);
+	xfs_irele(ip);
 
 	error = formatter(buffer, ubsize, ubused, buf);
 	if (!error)
@@ -458,8 +458,7 @@ xfs_bulkstat(
 		 * pending error, then we are done.
 		 */
 del_cursor:
-		xfs_btree_del_cursor(cur, error ?
-					  XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 		xfs_buf_relse(agbp);
 		if (error)
 			break;
@@ -632,8 +631,7 @@ next_ag:
 
 	kmem_free(buffer);
 	if (cur)
-		xfs_btree_del_cursor(cur, (error ? XFS_BTREE_ERROR :
-					   XFS_BTREE_NOERROR));
+		xfs_btree_del_cursor(cur, error);
 	if (agbp)
 		xfs_buf_relse(agbp);
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 5e56f3b93d4b..c3b610b687d1 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -410,7 +410,7 @@ out_error:
 }
 
 /*
- * Reserve log space and return a ticket corresponding the reservation.
+ * Reserve log space and return a ticket corresponding to the reservation.
  *
  * Each reservation is going to reserve extra space for a log record header.
  * When writes happen to the on-disk log, we don't subtract the length of the
@@ -826,6 +826,88 @@ xfs_log_mount_cancel(
  * deallocation must not be done until source-end.
  */
 
+/* Actually write the unmount record to disk. */
+static void
+xfs_log_write_unmount_record(
+	struct xfs_mount	*mp)
+{
+	/* the data section must be 32 bit size aligned */
+	struct xfs_unmount_log_format magic = {
+		.magic = XLOG_UNMOUNT_TYPE,
+	};
+	struct xfs_log_iovec reg = {
+		.i_addr = &magic,
+		.i_len = sizeof(magic),
+		.i_type = XLOG_REG_TYPE_UNMOUNT,
+	};
+	struct xfs_log_vec vec = {
+		.lv_niovecs = 1,
+		.lv_iovecp = &reg,
+	};
+	struct xlog		*log = mp->m_log;
+	struct xlog_in_core	*iclog;
+	struct xlog_ticket	*tic = NULL;
+	xfs_lsn_t		lsn;
+	uint			flags = XLOG_UNMOUNT_TRANS;
+	int			error;
+
+	error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
+	if (error)
+		goto out_err;
+
+	/*
+	 * If we think the summary counters are bad, clear the unmount header
+	 * flag in the unmount record so that the summary counters will be
+	 * recalculated during log recovery at next mount.  Refer to
+	 * xlog_check_unmount_rec for more details.
+	 */
+	if (XFS_TEST_ERROR((mp->m_flags & XFS_MOUNT_BAD_SUMMARY), mp,
+			XFS_ERRTAG_FORCE_SUMMARY_RECALC)) {
+		xfs_alert(mp, "%s: will fix summary counters at next mount",
+				__func__);
+		flags &= ~XLOG_UNMOUNT_TRANS;
+	}
+
+	/* remove inited flag, and account for space used */
+	tic->t_flags = 0;
+	tic->t_curr_res -= sizeof(magic);
+	error = xlog_write(log, &vec, tic, &lsn, NULL, flags);
+	/*
+	 * At this point, we're umounting anyway, so there's no point in
+	 * transitioning log state to IOERROR. Just continue...
+	 */
+out_err:
+	if (error)
+		xfs_alert(mp, "%s: unmount record failed", __func__);
+
+	spin_lock(&log->l_icloglock);
+	iclog = log->l_iclog;
+	atomic_inc(&iclog->ic_refcnt);
+	xlog_state_want_sync(log, iclog);
+	spin_unlock(&log->l_icloglock);
+	error = xlog_state_release_iclog(log, iclog);
+
+	spin_lock(&log->l_icloglock);
+	switch (iclog->ic_state) {
+	default:
+		if (!XLOG_FORCED_SHUTDOWN(log)) {
+			xlog_wait(&iclog->ic_force_wait, &log->l_icloglock);
+			break;
+		}
+		/* fall through */
+	case XLOG_STATE_ACTIVE:
+	case XLOG_STATE_DIRTY:
+		spin_unlock(&log->l_icloglock);
+		break;
+	}
+
+	if (tic) {
+		trace_xfs_log_umount_write(log, tic);
+		xlog_ungrant_log_space(log, tic);
+		xfs_log_ticket_put(tic);
+	}
+}
+
 /*
  * Unmount record used to have a string "Unmount filesystem--" in the
  * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE).
@@ -842,8 +924,6 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 #ifdef DEBUG
 	xlog_in_core_t	 *first_iclog;
 #endif
-	xlog_ticket_t	*tic = NULL;
-	xfs_lsn_t	 lsn;
 	int		 error;
 
 	/*
@@ -870,66 +950,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 	} while (iclog != first_iclog);
 #endif
 	if (! (XLOG_FORCED_SHUTDOWN(log))) {
-		error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
-		if (!error) {
-			/* the data section must be 32 bit size aligned */
-			struct {
-			    uint16_t magic;
-			    uint16_t pad1;
-			    uint32_t pad2; /* may as well make it 64 bits */
-			} magic = {
-				.magic = XLOG_UNMOUNT_TYPE,
-			};
-			struct xfs_log_iovec reg = {
-				.i_addr = &magic,
-				.i_len = sizeof(magic),
-				.i_type = XLOG_REG_TYPE_UNMOUNT,
-			};
-			struct xfs_log_vec vec = {
-				.lv_niovecs = 1,
-				.lv_iovecp = &reg,
-			};
-
-			/* remove inited flag, and account for space used */
-			tic->t_flags = 0;
-			tic->t_curr_res -= sizeof(magic);
-			error = xlog_write(log, &vec, tic, &lsn,
-					   NULL, XLOG_UNMOUNT_TRANS);
-			/*
-			 * At this point, we're umounting anyway,
-			 * so there's no point in transitioning log state
-			 * to IOERROR. Just continue...
-			 */
-		}
-
-		if (error)
-			xfs_alert(mp, "%s: unmount record failed", __func__);
-
-
-		spin_lock(&log->l_icloglock);
-		iclog = log->l_iclog;
-		atomic_inc(&iclog->ic_refcnt);
-		xlog_state_want_sync(log, iclog);
-		spin_unlock(&log->l_icloglock);
-		error = xlog_state_release_iclog(log, iclog);
-
-		spin_lock(&log->l_icloglock);
-		if (!(iclog->ic_state == XLOG_STATE_ACTIVE ||
-		      iclog->ic_state == XLOG_STATE_DIRTY)) {
-			if (!XLOG_FORCED_SHUTDOWN(log)) {
-				xlog_wait(&iclog->ic_force_wait,
-							&log->l_icloglock);
-			} else {
-				spin_unlock(&log->l_icloglock);
-			}
-		} else {
-			spin_unlock(&log->l_icloglock);
-		}
-		if (tic) {
-			trace_xfs_log_umount_write(log, tic);
-			xlog_ungrant_log_space(log, tic);
-			xfs_log_ticket_put(tic);
-		}
+		xfs_log_write_unmount_record(mp);
 	} else {
 		/*
 		 * We're already in forced_shutdown mode, couldn't
@@ -4083,3 +4104,12 @@ xfs_log_check_lsn(
 
 	return valid;
 }
+
+bool
+xfs_log_in_recovery(
+	struct xfs_mount	*mp)
+{
+	struct xlog		*log = mp->m_log;
+
+	return log->l_flags & XLOG_ACTIVE_RECOVERY;
+}
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 3c1f6a8b4b70..73a64bf32f6f 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -153,5 +153,6 @@ bool	xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
 void	xfs_log_work_queue(struct xfs_mount *mp);
 void	xfs_log_quiesce(struct xfs_mount *mp);
 bool	xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
+bool	xfs_log_in_recovery(struct xfs_mount *);
 
 #endif	/* __XFS_LOG_H__ */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b181b5f57a19..a21dc61ec09e 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -196,7 +196,7 @@ xlog_bread_noalign(
 	bp->b_io_length = nbblks;
 	bp->b_error = 0;
 
-	error = xfs_buf_submit_wait(bp);
+	error = xfs_buf_submit(bp);
 	if (error && !XFS_FORCED_SHUTDOWN(log->l_mp))
 		xfs_buf_ioerror_alert(bp, __func__);
 	return error;
@@ -4733,10 +4733,9 @@ xlog_recover_cancel_rui(
 /* Recover the CUI if necessary. */
 STATIC int
 xlog_recover_process_cui(
-	struct xfs_mount		*mp,
+	struct xfs_trans		*parent_tp,
 	struct xfs_ail			*ailp,
-	struct xfs_log_item		*lip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_log_item		*lip)
 {
 	struct xfs_cui_log_item		*cuip;
 	int				error;
@@ -4749,7 +4748,7 @@ xlog_recover_process_cui(
 		return 0;
 
 	spin_unlock(&ailp->ail_lock);
-	error = xfs_cui_recover(mp, cuip, dfops);
+	error = xfs_cui_recover(parent_tp, cuip);
 	spin_lock(&ailp->ail_lock);
 
 	return error;
@@ -4774,10 +4773,9 @@ xlog_recover_cancel_cui(
 /* Recover the BUI if necessary. */
 STATIC int
 xlog_recover_process_bui(
-	struct xfs_mount		*mp,
+	struct xfs_trans		*parent_tp,
 	struct xfs_ail			*ailp,
-	struct xfs_log_item		*lip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_log_item		*lip)
 {
 	struct xfs_bui_log_item		*buip;
 	int				error;
@@ -4790,7 +4788,7 @@ xlog_recover_process_bui(
 		return 0;
 
 	spin_unlock(&ailp->ail_lock);
-	error = xfs_bui_recover(mp, buip, dfops);
+	error = xfs_bui_recover(parent_tp, buip);
 	spin_lock(&ailp->ail_lock);
 
 	return error;
@@ -4829,9 +4827,9 @@ static inline bool xlog_item_is_intent(struct xfs_log_item *lip)
 /* Take all the collected deferred ops and finish them in order. */
 static int
 xlog_finish_defer_ops(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_trans	*parent_tp)
 {
+	struct xfs_mount	*mp = parent_tp->t_mountp;
 	struct xfs_trans	*tp;
 	int64_t			freeblks;
 	uint			resblks;
@@ -4854,16 +4852,10 @@ xlog_finish_defer_ops(
 			0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
-
-	error = xfs_defer_finish(&tp, dfops);
-	if (error)
-		goto out_cancel;
+	/* transfer all collected dfops to this transaction */
+	xfs_defer_move(tp, parent_tp);
 
 	return xfs_trans_commit(tp);
-
-out_cancel:
-	xfs_trans_cancel(tp);
-	return error;
 }
 
 /*
@@ -4886,23 +4878,34 @@ STATIC int
 xlog_recover_process_intents(
 	struct xlog		*log)
 {
-	struct xfs_defer_ops	dfops;
+	struct xfs_trans	*parent_tp;
 	struct xfs_ail_cursor	cur;
 	struct xfs_log_item	*lip;
 	struct xfs_ail		*ailp;
-	xfs_fsblock_t		firstfsb;
-	int			error = 0;
+	int			error;
 #if defined(DEBUG) || defined(XFS_WARN)
 	xfs_lsn_t		last_lsn;
 #endif
 
+	/*
+	 * The intent recovery handlers commit transactions to complete recovery
+	 * for individual intents, but any new deferred operations that are
+	 * queued during that process are held off until the very end. The
+	 * purpose of this transaction is to serve as a container for deferred
+	 * operations. Each intent recovery handler must transfer dfops here
+	 * before its local transaction commits, and we'll finish the entire
+	 * list below.
+	 */
+	error = xfs_trans_alloc_empty(log->l_mp, &parent_tp);
+	if (error)
+		return error;
+
 	ailp = log->l_ailp;
 	spin_lock(&ailp->ail_lock);
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
 #if defined(DEBUG) || defined(XFS_WARN)
 	last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
 #endif
-	xfs_defer_init(&dfops, &firstfsb);
 	while (lip != NULL) {
 		/*
 		 * We're done when we see something other than an intent.
@@ -4937,12 +4940,10 @@ xlog_recover_process_intents(
 			error = xlog_recover_process_rui(log->l_mp, ailp, lip);
 			break;
 		case XFS_LI_CUI:
-			error = xlog_recover_process_cui(log->l_mp, ailp, lip,
-					&dfops);
+			error = xlog_recover_process_cui(parent_tp, ailp, lip);
 			break;
 		case XFS_LI_BUI:
-			error = xlog_recover_process_bui(log->l_mp, ailp, lip,
-					&dfops);
+			error = xlog_recover_process_bui(parent_tp, ailp, lip);
 			break;
 		}
 		if (error)
@@ -4952,10 +4953,9 @@ xlog_recover_process_intents(
 out:
 	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->ail_lock);
-	if (error)
-		xfs_defer_cancel(&dfops);
-	else
-		error = xlog_finish_defer_ops(log->l_mp, &dfops);
+	if (!error)
+		error = xlog_finish_defer_ops(parent_tp);
+	xfs_trans_cancel(parent_tp);
 
 	return error;
 }
@@ -5094,11 +5094,11 @@ xlog_recover_process_one_iunlink(
 	 */
 	ip->i_d.di_dmevmask = 0;
 
-	IRELE(ip);
+	xfs_irele(ip);
 	return agino;
 
  fail_iput:
-	IRELE(ip);
+	xfs_irele(ip);
  fail:
 	/*
 	 * We can't read in the inode this bucket points to, or this inode
@@ -5707,7 +5707,7 @@ xlog_do_recover(
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = &xfs_sb_buf_ops;
 
-	error = xfs_buf_submit_wait(bp);
+	error = xfs_buf_submit(bp);
 	if (error) {
 		if (!XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_buf_ioerror_alert(bp, __func__);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index a3378252baa1..99db27d6ac8a 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -207,6 +207,9 @@ xfs_initialize_perag(
 		if (xfs_buf_hash_init(pag))
 			goto out_free_pag;
 		init_waitqueue_head(&pag->pagb_wait);
+		spin_lock_init(&pag->pagb_lock);
+		pag->pagb_count = 0;
+		pag->pagb_tree = RB_ROOT;
 
 		if (radix_tree_preload(GFP_NOFS))
 			goto out_hash_destroy;
@@ -606,6 +609,56 @@ xfs_default_resblks(xfs_mount_t *mp)
 	return resblks;
 }
 
+/* Ensure the summary counts are correct. */
+STATIC int
+xfs_check_summary_counts(
+	struct xfs_mount	*mp)
+{
+	/*
+	 * The AG0 superblock verifier rejects in-progress filesystems,
+	 * so we should never see the flag set this far into mounting.
+	 */
+	if (mp->m_sb.sb_inprogress) {
+		xfs_err(mp, "sb_inprogress set after log recovery??");
+		WARN_ON(1);
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * Now the log is mounted, we know if it was an unclean shutdown or
+	 * not. If it was, with the first phase of recovery has completed, we
+	 * have consistent AG blocks on disk. We have not recovered EFIs yet,
+	 * but they are recovered transactionally in the second recovery phase
+	 * later.
+	 *
+	 * If the log was clean when we mounted, we can check the summary
+	 * counters.  If any of them are obviously incorrect, we can recompute
+	 * them from the AGF headers in the next step.
+	 */
+	if (XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
+	    (mp->m_sb.sb_fdblocks > mp->m_sb.sb_dblocks ||
+	     mp->m_sb.sb_ifree > mp->m_sb.sb_icount))
+		mp->m_flags |= XFS_MOUNT_BAD_SUMMARY;
+
+	/*
+	 * We can safely re-initialise incore superblock counters from the
+	 * per-ag data. These may not be correct if the filesystem was not
+	 * cleanly unmounted, so we waited for recovery to finish before doing
+	 * this.
+	 *
+	 * If the filesystem was cleanly unmounted or the previous check did
+	 * not flag anything weird, then we can trust the values in the
+	 * superblock to be correct and we don't need to do anything here.
+	 * Otherwise, recalculate the summary counters.
+	 */
+	if ((!xfs_sb_version_haslazysbcount(&mp->m_sb) ||
+	     XFS_LAST_UNMOUNT_WAS_CLEAN(mp)) &&
+	    !(mp->m_flags & XFS_MOUNT_BAD_SUMMARY))
+		return 0;
+
+	return xfs_initialize_perag_data(mp, mp->m_sb.sb_agcount);
+}
+
 /*
  * This function does the following on an initial mount of a file system:
  *	- reads the superblock from disk and init the mount struct
@@ -831,32 +884,10 @@ xfs_mountfs(
 		goto out_fail_wait;
 	}
 
-	/*
-	 * Now the log is mounted, we know if it was an unclean shutdown or
-	 * not. If it was, with the first phase of recovery has completed, we
-	 * have consistent AG blocks on disk. We have not recovered EFIs yet,
-	 * but they are recovered transactionally in the second recovery phase
-	 * later.
-	 *
-	 * Hence we can safely re-initialise incore superblock counters from
-	 * the per-ag data. These may not be correct if the filesystem was not
-	 * cleanly unmounted, so we need to wait for recovery to finish before
-	 * doing this.
-	 *
-	 * If the filesystem was cleanly unmounted, then we can trust the
-	 * values in the superblock to be correct and we don't need to do
-	 * anything here.
-	 *
-	 * If we are currently making the filesystem, the initialisation will
-	 * fail as the perag data is in an undefined state.
-	 */
-	if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
-	    !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
-	     !mp->m_sb.sb_inprogress) {
-		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
-		if (error)
-			goto out_log_dealloc;
-	}
+	/* Make sure the summary counts are ok. */
+	error = xfs_check_summary_counts(mp);
+	if (error)
+		goto out_log_dealloc;
 
 	/*
 	 * Get and sanity-check the root inode.
@@ -1011,7 +1042,7 @@ xfs_mountfs(
  out_rtunmount:
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
-	IRELE(rip);
+	xfs_irele(rip);
 	/* Clean out dquots that might be in memory after quotacheck. */
 	xfs_qm_unmount(mp);
 	/*
@@ -1067,7 +1098,7 @@ xfs_unmountfs(
 	xfs_fs_unreserve_ag_blocks(mp);
 	xfs_qm_unmount_quotas(mp);
 	xfs_rtunmount_inodes(mp);
-	IRELE(mp->m_rootip);
+	xfs_irele(mp->m_rootip);
 
 	/*
 	 * We can potentially deadlock here if we have an inode cluster
@@ -1395,3 +1426,16 @@ xfs_dev_is_read_only(
 	}
 	return 0;
 }
+
+/* Force the summary counters to be recalculated at next mount. */
+void
+xfs_force_summary_recalc(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
+		return;
+
+	spin_lock(&mp->m_sb_lock);
+	mp->m_flags |= XFS_MOUNT_BAD_SUMMARY;
+	spin_unlock(&mp->m_sb_lock);
+}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 245349d1e23f..7964513c3128 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -202,6 +202,7 @@ typedef struct xfs_mount {
 						   must be synchronous except
 						   for space allocations */
 #define XFS_MOUNT_UNMOUNTING	(1ULL << 1)	/* filesystem is unmounting */
+#define XFS_MOUNT_BAD_SUMMARY	(1ULL << 2)	/* summary counters are bad */
 #define XFS_MOUNT_WAS_CLEAN	(1ULL << 3)
 #define XFS_MOUNT_FS_SHUTDOWN	(1ULL << 4)	/* atomic stop of all filesystem
 						   operations, typically for
@@ -216,7 +217,6 @@ typedef struct xfs_mount {
 #define XFS_MOUNT_SMALL_INUMS	(1ULL << 14)	/* user wants 32bit inodes */
 #define XFS_MOUNT_32BITINODES	(1ULL << 15)	/* inode32 allocator active */
 #define XFS_MOUNT_NOUUID	(1ULL << 16)	/* ignore uuid during mount */
-#define XFS_MOUNT_BARRIER	(1ULL << 17)
 #define XFS_MOUNT_IKEEP		(1ULL << 18)	/* keep empty inode clusters*/
 #define XFS_MOUNT_SWALLOC	(1ULL << 19)	/* turn on stripe width
 						 * allocation */
@@ -434,5 +434,6 @@ int	xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
 
 struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp,
 		int error_class, int error);
+void xfs_force_summary_recalc(struct xfs_mount *mp);
 
 #endif	/* __XFS_MOUNT_H__ */
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 9ceb85cce33a..52ed7904df10 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -231,15 +231,15 @@ xfs_qm_unmount_quotas(
 	 */
 	if (mp->m_quotainfo) {
 		if (mp->m_quotainfo->qi_uquotaip) {
-			IRELE(mp->m_quotainfo->qi_uquotaip);
+			xfs_irele(mp->m_quotainfo->qi_uquotaip);
 			mp->m_quotainfo->qi_uquotaip = NULL;
 		}
 		if (mp->m_quotainfo->qi_gquotaip) {
-			IRELE(mp->m_quotainfo->qi_gquotaip);
+			xfs_irele(mp->m_quotainfo->qi_gquotaip);
 			mp->m_quotainfo->qi_gquotaip = NULL;
 		}
 		if (mp->m_quotainfo->qi_pquotaip) {
-			IRELE(mp->m_quotainfo->qi_pquotaip);
+			xfs_irele(mp->m_quotainfo->qi_pquotaip);
 			mp->m_quotainfo->qi_pquotaip = NULL;
 		}
 	}
@@ -1200,12 +1200,12 @@ xfs_qm_dqusage_adjust(
 			goto error0;
 	}
 
-	IRELE(ip);
+	xfs_irele(ip);
 	*res = BULKSTAT_RV_DIDONE;
 	return 0;
 
 error0:
-	IRELE(ip);
+	xfs_irele(ip);
 	*res = BULKSTAT_RV_GIVEUP;
 	return error;
 }
@@ -1575,11 +1575,11 @@ xfs_qm_init_quotainos(
 
 error_rele:
 	if (uip)
-		IRELE(uip);
+		xfs_irele(uip);
 	if (gip)
-		IRELE(gip);
+		xfs_irele(gip);
 	if (pip)
-		IRELE(pip);
+		xfs_irele(pip);
 	return error;
 }
 
@@ -1588,15 +1588,15 @@ xfs_qm_destroy_quotainos(
 	xfs_quotainfo_t	*qi)
 {
 	if (qi->qi_uquotaip) {
-		IRELE(qi->qi_uquotaip);
+		xfs_irele(qi->qi_uquotaip);
 		qi->qi_uquotaip = NULL; /* paranoia */
 	}
 	if (qi->qi_gquotaip) {
-		IRELE(qi->qi_gquotaip);
+		xfs_irele(qi->qi_gquotaip);
 		qi->qi_gquotaip = NULL;
 	}
 	if (qi->qi_pquotaip) {
-		IRELE(qi->qi_pquotaip);
+		xfs_irele(qi->qi_pquotaip);
 		qi->qi_pquotaip = NULL;
 	}
 }
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index abc8a21e3a82..b3190890f096 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -22,6 +22,7 @@
 #include "xfs_qm.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
+#include "xfs_defer.h"
 
 STATIC int	xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint);
 STATIC int	xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *,
@@ -189,15 +190,15 @@ xfs_qm_scall_quotaoff(
 	 * Release our quotainode references if we don't need them anymore.
 	 */
 	if ((dqtype & XFS_QMOPT_UQUOTA) && q->qi_uquotaip) {
-		IRELE(q->qi_uquotaip);
+		xfs_irele(q->qi_uquotaip);
 		q->qi_uquotaip = NULL;
 	}
 	if ((dqtype & XFS_QMOPT_GQUOTA) && q->qi_gquotaip) {
-		IRELE(q->qi_gquotaip);
+		xfs_irele(q->qi_gquotaip);
 		q->qi_gquotaip = NULL;
 	}
 	if ((dqtype & XFS_QMOPT_PQUOTA) && q->qi_pquotaip) {
-		IRELE(q->qi_pquotaip);
+		xfs_irele(q->qi_pquotaip);
 		q->qi_pquotaip = NULL;
 	}
 
@@ -250,7 +251,7 @@ xfs_qm_scall_trunc_qfile(
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 out_put:
-	IRELE(ip);
+	xfs_irele(ip);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 205fbb2a77e4..a7c0c657dfaf 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -45,7 +45,7 @@ xfs_qm_fill_state(
 	tstate->ino_warnlimit = q->qi_iwarnlimit;
 	tstate->rt_spc_warnlimit = q->qi_rtbwarnlimit;
 	if (tempqip)
-		IRELE(ip);
+		xfs_irele(ip);
 }
 
 /*
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 472a73e9d331..fce38b56b962 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -380,9 +380,8 @@ xfs_cud_init(
  */
 int
 xfs_cui_recover(
-	struct xfs_mount		*mp,
-	struct xfs_cui_log_item		*cuip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_trans		*parent_tp,
+	struct xfs_cui_log_item		*cuip)
 {
 	int				i;
 	int				error = 0;
@@ -398,6 +397,7 @@ xfs_cui_recover(
 	xfs_extlen_t			new_len;
 	struct xfs_bmbt_irec		irec;
 	bool				requeue_only = false;
+	struct xfs_mount		*mp = parent_tp->t_mountp;
 
 	ASSERT(!test_bit(XFS_CUI_RECOVERED, &cuip->cui_flags));
 
@@ -452,6 +452,12 @@ xfs_cui_recover(
 			mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
+	/*
+	 * Recovery stashes all deferred ops during intent processing and
+	 * finishes them on completion. Transfer current dfops state to this
+	 * transaction and transfer the result back before we return.
+	 */
+	xfs_defer_move(tp, parent_tp);
 	cudp = xfs_trans_get_cud(tp, cuip);
 
 	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
@@ -473,7 +479,7 @@ xfs_cui_recover(
 			new_len = refc->pe_len;
 		} else
 			error = xfs_trans_log_finish_refcount_update(tp, cudp,
-				dfops, type, refc->pe_startblock, refc->pe_len,
+				type, refc->pe_startblock, refc->pe_len,
 				&new_fsb, &new_len, &rcur);
 		if (error)
 			goto abort_error;
@@ -484,22 +490,18 @@ xfs_cui_recover(
 			irec.br_blockcount = new_len;
 			switch (type) {
 			case XFS_REFCOUNT_INCREASE:
-				error = xfs_refcount_increase_extent(
-						tp->t_mountp, dfops, &irec);
+				error = xfs_refcount_increase_extent(tp, &irec);
 				break;
 			case XFS_REFCOUNT_DECREASE:
-				error = xfs_refcount_decrease_extent(
-						tp->t_mountp, dfops, &irec);
+				error = xfs_refcount_decrease_extent(tp, &irec);
 				break;
 			case XFS_REFCOUNT_ALLOC_COW:
-				error = xfs_refcount_alloc_cow_extent(
-						tp->t_mountp, dfops,
+				error = xfs_refcount_alloc_cow_extent(tp,
 						irec.br_startblock,
 						irec.br_blockcount);
 				break;
 			case XFS_REFCOUNT_FREE_COW:
-				error = xfs_refcount_free_cow_extent(
-						tp->t_mountp, dfops,
+				error = xfs_refcount_free_cow_extent(tp,
 						irec.br_startblock,
 						irec.br_blockcount);
 				break;
@@ -514,11 +516,13 @@ xfs_cui_recover(
 
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
+	xfs_defer_move(parent_tp, tp);
 	error = xfs_trans_commit(tp);
 	return error;
 
 abort_error:
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
+	xfs_defer_move(parent_tp, tp);
 	xfs_trans_cancel(tp);
 	return error;
 }
diff --git a/fs/xfs/xfs_refcount_item.h b/fs/xfs/xfs_refcount_item.h
index dd830b69cd1e..3896dcc2368f 100644
--- a/fs/xfs/xfs_refcount_item.h
+++ b/fs/xfs/xfs_refcount_item.h
@@ -82,7 +82,6 @@ struct xfs_cud_log_item *xfs_cud_init(struct xfs_mount *,
 		struct xfs_cui_log_item *);
 void xfs_cui_item_free(struct xfs_cui_log_item *);
 void xfs_cui_release(struct xfs_cui_log_item *);
-int xfs_cui_recover(struct xfs_mount *mp, struct xfs_cui_log_item *cuip,
-		struct xfs_defer_ops *dfops);
+int xfs_cui_recover(struct xfs_trans *parent_tp, struct xfs_cui_log_item *cuip);
 
 #endif	/* __XFS_REFCOUNT_ITEM_H__ */
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 592fb2071a03..38f405415b88 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -157,12 +157,12 @@ xfs_reflink_find_shared(
 	if (!agbp)
 		return -ENOMEM;
 
-	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
 
 	error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
 			find_end_of_shared);
 
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 
 	xfs_trans_brelse(tp, agbp);
 	return error;
@@ -312,10 +312,8 @@ xfs_reflink_convert_cow_extent(
 	struct xfs_inode		*ip,
 	struct xfs_bmbt_irec		*imap,
 	xfs_fileoff_t			offset_fsb,
-	xfs_filblks_t			count_fsb,
-	struct xfs_defer_ops		*dfops)
+	xfs_filblks_t			count_fsb)
 {
-	xfs_fsblock_t			first_block = NULLFSBLOCK;
 	int				nimaps = 1;
 
 	if (imap->br_state == XFS_EXT_NORM)
@@ -326,8 +324,8 @@ xfs_reflink_convert_cow_extent(
 	if (imap->br_blockcount == 0)
 		return 0;
 	return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, &first_block,
-			0, imap, &nimaps, dfops);
+			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, 0, imap,
+			&nimaps);
 }
 
 /* Convert all of the unwritten CoW extents in a file's range to real ones. */
@@ -342,8 +340,6 @@ xfs_reflink_convert_cow(
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
 	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
 	struct xfs_bmbt_irec	imap;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block = NULLFSBLOCK;
 	int			nimaps = 1, error = 0;
 
 	ASSERT(count != 0);
@@ -351,8 +347,7 @@ xfs_reflink_convert_cow(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_write(NULL, ip, offset_fsb, count_fsb,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT |
-			XFS_BMAPI_CONVERT_ONLY, &first_block, 0, &imap, &nimaps,
-			&dfops);
+			XFS_BMAPI_CONVERT_ONLY, 0, &imap, &nimaps);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
@@ -369,9 +364,7 @@ xfs_reflink_allocate_cow(
 	xfs_fileoff_t		offset_fsb = imap->br_startoff;
 	xfs_filblks_t		count_fsb = imap->br_blockcount;
 	struct xfs_bmbt_irec	got;
-	struct xfs_defer_ops	dfops;
 	struct xfs_trans	*tp = NULL;
-	xfs_fsblock_t		first_block;
 	int			nimaps, error = 0;
 	bool			trimmed;
 	xfs_filblks_t		resaligned;
@@ -430,23 +423,18 @@ retry:
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(&dfops, &first_block);
 	nimaps = 1;
 
 	/* Allocate the entire reservation as unwritten blocks. */
 	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, &first_block,
-			resblks, imap, &nimaps, &dfops);
+			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC,
+			resblks, imap, &nimaps);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
 	xfs_inode_set_cowblocks_tag(ip);
 
 	/* Finish up. */
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		return error;
@@ -458,10 +446,8 @@ retry:
 	if (nimaps == 0)
 		return -ENOSPC;
 convert:
-	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb,
-			&dfops);
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb);
+out_trans_cancel:
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
 			XFS_QMOPT_RES_REGBLKS);
 out:
@@ -471,69 +457,6 @@ out:
 }
 
 /*
- * Find the CoW reservation for a given byte offset of a file.
- */
-bool
-xfs_reflink_find_cow_mapping(
-	struct xfs_inode		*ip,
-	xfs_off_t			offset,
-	struct xfs_bmbt_irec		*imap)
-{
-	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	xfs_fileoff_t			offset_fsb;
-	struct xfs_bmbt_irec		got;
-	struct xfs_iext_cursor		icur;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
-
-	if (!xfs_is_reflink_inode(ip))
-		return false;
-	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
-	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got))
-		return false;
-	if (got.br_startoff > offset_fsb)
-		return false;
-
-	trace_xfs_reflink_find_cow_mapping(ip, offset, 1, XFS_IO_OVERWRITE,
-			&got);
-	*imap = got;
-	return true;
-}
-
-/*
- * Trim an extent to end at the next CoW reservation past offset_fsb.
- */
-void
-xfs_reflink_trim_irec_to_next_cow(
-	struct xfs_inode		*ip,
-	xfs_fileoff_t			offset_fsb,
-	struct xfs_bmbt_irec		*imap)
-{
-	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	struct xfs_bmbt_irec		got;
-	struct xfs_iext_cursor		icur;
-
-	if (!xfs_is_reflink_inode(ip))
-		return;
-
-	/* Find the extent in the CoW fork. */
-	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got))
-		return;
-
-	/* This is the extent before; try sliding up one. */
-	if (got.br_startoff < offset_fsb) {
-		if (!xfs_iext_next_extent(ifp, &icur, &got))
-			return;
-	}
-
-	if (got.br_startoff >= imap->br_startoff + imap->br_blockcount)
-		return;
-
-	imap->br_blockcount = got.br_startoff - imap->br_startoff;
-	trace_xfs_reflink_trim_irec(ip, imap);
-}
-
-/*
  * Cancel CoW reservations for some block range of an inode.
  *
  * If cancel_real is true this function cancels all COW fork extents for the
@@ -553,11 +476,9 @@ xfs_reflink_cancel_cow_blocks(
 	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	struct xfs_bmbt_irec		got, del;
 	struct xfs_iext_cursor		icur;
-	xfs_fsblock_t			firstfsb;
-	struct xfs_defer_ops		dfops;
 	int				error = 0;
 
-	if (!xfs_is_reflink_inode(ip))
+	if (!xfs_inode_has_cow_data(ip))
 		return 0;
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
 		return 0;
@@ -581,26 +502,21 @@ xfs_reflink_cancel_cow_blocks(
 			if (error)
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
-			xfs_defer_init(&dfops, &firstfsb);
+			ASSERT((*tpp)->t_firstblock == NULLFSBLOCK);
 
 			/* Free the CoW orphan record. */
-			error = xfs_refcount_free_cow_extent(ip->i_mount,
-					&dfops, del.br_startblock,
-					del.br_blockcount);
+			error = xfs_refcount_free_cow_extent(*tpp,
+					del.br_startblock, del.br_blockcount);
 			if (error)
 				break;
 
-			xfs_bmap_add_free(ip->i_mount, &dfops,
-					del.br_startblock, del.br_blockcount,
-					NULL);
+			xfs_bmap_add_free(*tpp, del.br_startblock,
+					  del.br_blockcount, NULL);
 
 			/* Roll the transaction */
-			xfs_defer_ijoin(&dfops, ip);
-			error = xfs_defer_finish(tpp, &dfops);
-			if (error) {
-				xfs_defer_cancel(&dfops);
+			error = xfs_defer_finish(tpp);
+			if (error)
 				break;
-			}
 
 			/* Remove the mapping from the CoW fork. */
 			xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
@@ -623,7 +539,6 @@ next_extent:
 	/* clear tag if cow fork is emptied */
 	if (!ifp->if_bytes)
 		xfs_inode_clear_cowblocks_tag(ip);
-
 	return error;
 }
 
@@ -696,8 +611,6 @@ xfs_reflink_end_cow(
 	struct xfs_trans		*tp;
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
-	xfs_fsblock_t			firstfsb;
-	struct xfs_defer_ops		dfops;
 	int				error;
 	unsigned int			resblks;
 	xfs_filblks_t			rlen;
@@ -764,12 +677,11 @@ xfs_reflink_end_cow(
 			goto prev_extent;
 
 		/* Unmap the old blocks in the data fork. */
-		xfs_defer_init(&dfops, &firstfsb);
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
 		rlen = del.br_blockcount;
-		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
-				&firstfsb, &dfops);
+		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Trim the extent to whatever got unmapped. */
 		if (rlen) {
@@ -779,15 +691,15 @@ xfs_reflink_end_cow(
 		trace_xfs_reflink_cow_remap(ip, &del);
 
 		/* Free the CoW orphan record. */
-		error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
-				del.br_startblock, del.br_blockcount);
+		error = xfs_refcount_free_cow_extent(tp, del.br_startblock,
+				del.br_blockcount);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Map the new blocks into the data fork. */
-		error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
+		error = xfs_bmap_map_extent(tp, ip, &del);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Charge this new data fork mapping to the on-disk quota. */
 		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT,
@@ -796,10 +708,9 @@ xfs_reflink_end_cow(
 		/* Remove the mapping from the CoW fork. */
 		xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
 
-		xfs_defer_ijoin(&dfops, ip);
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 		if (!xfs_iext_get_extent(ifp, &icur, &got))
 			break;
 		continue;
@@ -814,8 +725,6 @@ prev_extent:
 		goto out;
 	return 0;
 
-out_defer:
-	xfs_defer_cancel(&dfops);
 out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1070,9 +979,7 @@ xfs_reflink_remap_extent(
 	struct xfs_mount	*mp = ip->i_mount;
 	bool			real_extent = xfs_bmap_is_real_extent(irec);
 	struct xfs_trans	*tp;
-	xfs_fsblock_t		firstfsb;
 	unsigned int		resblks;
-	struct xfs_defer_ops	dfops;
 	struct xfs_bmbt_irec	uirec;
 	xfs_filblks_t		rlen;
 	xfs_filblks_t		unmap_len;
@@ -1113,11 +1020,10 @@ xfs_reflink_remap_extent(
 	/* Unmap the old blocks in the data fork. */
 	rlen = unmap_len;
 	while (rlen) {
-		xfs_defer_init(&dfops, &firstfsb);
-		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1,
-				&firstfsb, &dfops);
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
+		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/*
 		 * Trim the extent to whatever got unmapped.
@@ -1136,14 +1042,14 @@ xfs_reflink_remap_extent(
 				uirec.br_blockcount, uirec.br_startblock);
 
 		/* Update the refcount tree */
-		error = xfs_refcount_increase_extent(mp, &dfops, &uirec);
+		error = xfs_refcount_increase_extent(tp, &uirec);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Map the new blocks into the data fork. */
-		error = xfs_bmap_map_extent(mp, &dfops, ip, &uirec);
+		error = xfs_bmap_map_extent(tp, ip, &uirec);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Update quota accounting. */
 		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT,
@@ -1162,10 +1068,9 @@ xfs_reflink_remap_extent(
 
 next_extent:
 		/* Process all the deferred stuff. */
-		xfs_defer_ijoin(&dfops, ip);
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 	}
 
 	error = xfs_trans_commit(tp);
@@ -1174,8 +1079,6 @@ next_extent:
 		goto out;
 	return 0;
 
-out_defer:
-	xfs_defer_cancel(&dfops);
 out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 1532827ba911..c585ad9552b2 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -18,10 +18,6 @@ extern int xfs_reflink_allocate_cow(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *imap, bool *shared, uint *lockmode);
 extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
-extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
-		struct xfs_bmbt_irec *imap);
-extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
-		xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap);
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
 		struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 329d4d26c13e..926ed314ffba 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -761,8 +761,6 @@ xfs_growfs_rt_alloc(
 	struct xfs_buf		*bp;	/* temporary buffer for zeroing */
 	xfs_daddr_t		d;		/* disk block address */
 	int			error;		/* error return value */
-	xfs_fsblock_t		firstblock;/* first block allocated in xaction */
-	struct xfs_defer_ops	dfops;		/* list of freed blocks */
 	xfs_fsblock_t		fsbno;		/* filesystem block for bno */
 	struct xfs_bmbt_irec	map;		/* block map output */
 	int			nmap;		/* number of block maps */
@@ -787,24 +785,20 @@ xfs_growfs_rt_alloc(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(&dfops, &firstblock);
 		/*
 		 * Allocate blocks to the bitmap file.
 		 */
 		nmap = 1;
 		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
-					XFS_BMAPI_METADATA, &firstblock,
-					resblks, &map, &nmap, &dfops);
+					XFS_BMAPI_METADATA, resblks, &map,
+					&nmap);
 		if (!error && nmap < 1)
 			error = -ENOSPC;
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 		/*
 		 * Free any blocks freed up in the transaction, then commit.
 		 */
-		error = xfs_defer_finish(&tp, &dfops);
-		if (error)
-			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
 		if (error)
 			return error;
@@ -854,8 +848,6 @@ xfs_growfs_rt_alloc(
 
 	return 0;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
@@ -1215,7 +1207,7 @@ xfs_rtmount_inodes(
 	ASSERT(sbp->sb_rsumino != NULLFSINO);
 	error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip);
 	if (error) {
-		IRELE(mp->m_rbmip);
+		xfs_irele(mp->m_rbmip);
 		return error;
 	}
 	ASSERT(mp->m_rsumip != NULL);
@@ -1227,9 +1219,9 @@ xfs_rtunmount_inodes(
 	struct xfs_mount	*mp)
 {
 	if (mp->m_rbmip)
-		IRELE(mp->m_rbmip);
+		xfs_irele(mp->m_rbmip);
 	if (mp->m_rsumip)
-		IRELE(mp->m_rsumip);
+		xfs_irele(mp->m_rsumip);
 }
 
 /*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 9d791f158dfe..207ee302b1bb 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -65,11 +65,10 @@ enum {
 	Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_biosize,
 	Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid,
 	Opt_mtpt, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
-	Opt_allocsize, Opt_norecovery, Opt_barrier, Opt_nobarrier,
-	Opt_inode64, Opt_inode32, Opt_ikeep, Opt_noikeep,
-	Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2, Opt_filestreams,
-	Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota,
-	Opt_uquota, Opt_gquota, Opt_pquota,
+	Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, Opt_ikeep,
+	Opt_noikeep, Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2,
+	Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota,
+	Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota,
 	Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
 	Opt_discard, Opt_nodiscard, Opt_dax, Opt_err,
 };
@@ -118,14 +117,7 @@ static const match_table_t tokens = {
 	{Opt_qnoenforce, "qnoenforce"},	/* same as uqnoenforce */
 	{Opt_discard,	"discard"},	/* Discard unused blocks */
 	{Opt_nodiscard,	"nodiscard"},	/* Do not discard unused blocks */
-
 	{Opt_dax,	"dax"},		/* Enable direct access to bdev pages */
-
-	/* Deprecated mount options scheduled for removal */
-	{Opt_barrier,	"barrier"},	/* use writer barriers for log write and
-					 * unwritten extent conversion */
-	{Opt_nobarrier,	"nobarrier"},	/* .. disable */
-
 	{Opt_err,	NULL},
 };
 
@@ -209,7 +201,6 @@ xfs_parseargs(
 	 * Set some default flags that could be cleared by the mount option
 	 * parsing.
 	 */
-	mp->m_flags |= XFS_MOUNT_BARRIER;
 	mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
 
 	/*
@@ -362,14 +353,6 @@ xfs_parseargs(
 			mp->m_flags |= XFS_MOUNT_DAX;
 			break;
 #endif
-		case Opt_barrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags |= XFS_MOUNT_BARRIER;
-			break;
-		case Opt_nobarrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags &= ~XFS_MOUNT_BARRIER;
-			break;
 		default:
 			xfs_warn(mp, "unknown mount option [%s].", p);
 			return -EINVAL;
@@ -487,7 +470,6 @@ xfs_showargs(
 	static struct proc_xfs_info xfs_info_unset[] = {
 		/* the few simple ones we can get from the mount struct */
 		{ XFS_MOUNT_COMPAT_IOSIZE,	",largeio" },
-		{ XFS_MOUNT_BARRIER,		",nobarrier" },
 		{ XFS_MOUNT_SMALL_INUMS,	",inode64" },
 		{ 0, NULL }
 	};
@@ -1278,14 +1260,6 @@ xfs_fs_remount(
 
 		token = match_token(p, tokens, args);
 		switch (token) {
-		case Opt_barrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags |= XFS_MOUNT_BARRIER;
-			break;
-		case Opt_nobarrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags &= ~XFS_MOUNT_BARRIER;
-			break;
 		case Opt_inode64:
 			mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
 			mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
@@ -1860,7 +1834,7 @@ MODULE_ALIAS_FS("xfs");
 STATIC int __init
 xfs_init_zones(void)
 {
-	if (bioset_init(&xfs_ioend_bioset, 4 * MAX_BUF_PER_PAGE,
+	if (bioset_init(&xfs_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
 			offsetof(struct xfs_ioend, io_inline_bio),
 			BIOSET_NEED_BVECS))
 		goto out;
@@ -1886,7 +1860,7 @@ xfs_init_zones(void)
 	if (!xfs_da_state_zone)
 		goto out_destroy_btree_cur_zone;
 
-	xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
+	xfs_ifork_zone = kmem_zone_init(sizeof(struct xfs_ifork), "xfs_ifork");
 	if (!xfs_ifork_zone)
 		goto out_destroy_da_state_zone;
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 3783afcb68d2..a3e98c64b6e3 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -163,8 +163,6 @@ xfs_symlink(
 	struct xfs_inode	*ip = NULL;
 	int			error = 0;
 	int			pathlen;
-	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	bool                    unlock_dp_on_error = false;
 	xfs_fileoff_t		first_fsb;
 	xfs_filblks_t		fs_blocks;
@@ -243,13 +241,6 @@ xfs_symlink(
 		goto out_trans_cancel;
 
 	/*
-	 * Initialize the bmap freelist prior to calling either
-	 * bmapi or the directory create code.
-	 */
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
-
-	/*
 	 * Allocate an inode for the symlink.
 	 */
 	error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0,
@@ -290,10 +281,9 @@ xfs_symlink(
 		nmaps = XFS_SYMLINK_MAPS;
 
 		error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
-				  XFS_BMAPI_METADATA, &first_block, resblks,
-				  mval, &nmaps, &dfops);
+				  XFS_BMAPI_METADATA, resblks, mval, &nmaps);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		if (resblks)
 			resblks -= fs_blocks;
@@ -311,7 +301,7 @@ xfs_symlink(
 					       BTOBB(byte_cnt), 0);
 			if (!bp) {
 				error = -ENOMEM;
-				goto out_bmap_cancel;
+				goto out_trans_cancel;
 			}
 			bp->b_ops = &xfs_symlink_buf_ops;
 
@@ -338,10 +328,9 @@ xfs_symlink(
 	/*
 	 * Create the directory entry for the symlink.
 	 */
-	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino,
-					&first_block, &dfops, resblks);
+	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino, resblks);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
@@ -354,10 +343,6 @@ xfs_symlink(
 		xfs_trans_set_sync(tp);
 	}
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_release_inode;
@@ -369,8 +354,6 @@ xfs_symlink(
 	*ipp = ip;
 	return 0;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 out_release_inode:
@@ -381,7 +364,7 @@ out_release_inode:
 	 */
 	if (ip) {
 		xfs_finish_inode_setup(ip);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 
 	xfs_qm_dqrele(udqp);
@@ -403,8 +386,6 @@ xfs_inactive_symlink_rmt(
 	xfs_buf_t	*bp;
 	int		done;
 	int		error;
-	xfs_fsblock_t	first_block;
-	struct xfs_defer_ops	dfops;
 	int		i;
 	xfs_mount_t	*mp;
 	xfs_bmbt_irec_t	mval[XFS_SYMLINK_MAPS];
@@ -443,7 +424,6 @@ xfs_inactive_symlink_rmt(
 	 * Find the block(s) so we can inval and unmap them.
 	 */
 	done = 0;
-	xfs_defer_init(&dfops, &first_block);
 	nmaps = ARRAY_SIZE(mval);
 	error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
 				mval, &nmaps, 0);
@@ -458,28 +438,21 @@ xfs_inactive_symlink_rmt(
 			XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0);
 		if (!bp) {
 			error = -ENOMEM;
-			goto error_bmap_cancel;
+			goto error_trans_cancel;
 		}
 		xfs_trans_binval(tp, bp);
 	}
 	/*
 	 * Unmap the dead block(s) to the dfops.
 	 */
-	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps,
-			    &first_block, &dfops, &done);
+	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &done);
 	if (error)
-		goto error_bmap_cancel;
+		goto error_trans_cancel;
 	ASSERT(done);
-	/*
-	 * Commit the first transaction.  This logs the EFI and the inode.
-	 */
-	xfs_defer_ijoin(&dfops, ip);
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto error_bmap_cancel;
 
 	/*
-	 * Commit the transaction containing extent freeing and EFDs.
+	 * Commit the transaction. This first logs the EFI and the inode, then
+	 * rolls and commits the transaction that frees the extents.
 	 */
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	error = xfs_trans_commit(tp);
@@ -498,8 +471,6 @@ xfs_inactive_symlink_rmt(
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return 0;
 
-error_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 error_trans_cancel:
 	xfs_trans_cancel(tp);
 error_unlock:
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 972d45d28097..ad315e83bc02 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -310,7 +310,6 @@ DEFINE_BUF_EVENT(xfs_buf_hold);
 DEFINE_BUF_EVENT(xfs_buf_rele);
 DEFINE_BUF_EVENT(xfs_buf_iodone);
 DEFINE_BUF_EVENT(xfs_buf_submit);
-DEFINE_BUF_EVENT(xfs_buf_submit_wait);
 DEFINE_BUF_EVENT(xfs_buf_lock);
 DEFINE_BUF_EVENT(xfs_buf_lock_done);
 DEFINE_BUF_EVENT(xfs_buf_trylock_fail);
@@ -1153,33 +1152,23 @@ DECLARE_EVENT_CLASS(xfs_page_class,
 		__field(loff_t, size)
 		__field(unsigned long, offset)
 		__field(unsigned int, length)
-		__field(int, delalloc)
-		__field(int, unwritten)
 	),
 	TP_fast_assign(
-		int delalloc = -1, unwritten = -1;
-
-		if (page_has_buffers(page))
-			xfs_count_page_state(page, &delalloc, &unwritten);
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = XFS_I(inode)->i_ino;
 		__entry->pgoff = page_offset(page);
 		__entry->size = i_size_read(inode);
 		__entry->offset = off;
 		__entry->length = len;
-		__entry->delalloc = delalloc;
-		__entry->unwritten = unwritten;
 	),
 	TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx "
-		  "length %x delalloc %d unwritten %d",
+		  "length %x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->pgoff,
 		  __entry->size,
 		  __entry->offset,
-		  __entry->length,
-		  __entry->delalloc,
-		  __entry->unwritten)
+		  __entry->length)
 )
 
 #define DEFINE_PAGE_EVENT(name)		\
@@ -1263,9 +1252,6 @@ DEFINE_EVENT(xfs_imap_class, name,	\
 	TP_ARGS(ip, offset, count, type, irec))
 DEFINE_IOMAP_EVENT(xfs_map_blocks_found);
 DEFINE_IOMAP_EVENT(xfs_map_blocks_alloc);
-DEFINE_IOMAP_EVENT(xfs_get_blocks_found);
-DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc);
-DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct);
 DEFINE_IOMAP_EVENT(xfs_iomap_alloc);
 DEFINE_IOMAP_EVENT(xfs_iomap_found);
 
@@ -1304,7 +1290,6 @@ DEFINE_EVENT(xfs_simple_io_class, name,	\
 	TP_ARGS(ip, offset, count))
 DEFINE_SIMPLE_IO_EVENT(xfs_delalloc_enospc);
 DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert);
-DEFINE_SIMPLE_IO_EVENT(xfs_get_blocks_notfound);
 DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize);
 DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
@@ -1604,7 +1589,7 @@ DECLARE_EVENT_CLASS(xfs_alloc_class,
 		__entry->wasfromfl = args->wasfromfl;
 		__entry->resv = args->resv;
 		__entry->datatype = args->datatype;
-		__entry->firstblock = args->firstblock;
+		__entry->firstblock = args->tp->t_firstblock;
 	),
 	TP_printk("dev %d:%d agno %u agbno %u minlen %u maxlen %u mod %u "
 		  "prod %u minleft %u total %u alignment %u minalignslop %u "
@@ -2228,67 +2213,54 @@ DEFINE_BTREE_CUR_EVENT(xfs_btree_overlapped_query_range);
 
 /* deferred ops */
 struct xfs_defer_pending;
-struct xfs_defer_ops;
 
 DECLARE_EVENT_CLASS(xfs_defer_class,
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop,
-		 unsigned long caller_ip),
-	TP_ARGS(mp, dop, caller_ip),
+	TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip),
+	TP_ARGS(tp, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(void *, dop)
+		__field(struct xfs_trans *, tp)
 		__field(char, committed)
-		__field(char, low)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
-		__entry->dev = mp ? mp->m_super->s_dev : 0;
-		__entry->dop = dop;
-		__entry->committed = dop->dop_committed;
-		__entry->low = dop->dop_low;
+		__entry->dev = tp->t_mountp->m_super->s_dev;
+		__entry->tp = tp;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d ops %p committed %d low %d, caller %pS",
+	TP_printk("dev %d:%d tp %p caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->dop,
-		  __entry->committed,
-		  __entry->low,
+		  __entry->tp,
 		  (char *)__entry->caller_ip)
 )
 #define DEFINE_DEFER_EVENT(name) \
 DEFINE_EVENT(xfs_defer_class, name, \
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, \
-		 unsigned long caller_ip), \
-	TP_ARGS(mp, dop, caller_ip))
+	TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip), \
+	TP_ARGS(tp, caller_ip))
 
 DECLARE_EVENT_CLASS(xfs_defer_error_class,
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, int error),
-	TP_ARGS(mp, dop, error),
+	TP_PROTO(struct xfs_trans *tp, int error),
+	TP_ARGS(tp, error),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(void *, dop)
+		__field(struct xfs_trans *, tp)
 		__field(char, committed)
-		__field(char, low)
 		__field(int, error)
 	),
 	TP_fast_assign(
-		__entry->dev = mp ? mp->m_super->s_dev : 0;
-		__entry->dop = dop;
-		__entry->committed = dop->dop_committed;
-		__entry->low = dop->dop_low;
+		__entry->dev = tp->t_mountp->m_super->s_dev;
+		__entry->tp = tp;
 		__entry->error = error;
 	),
-	TP_printk("dev %d:%d ops %p committed %d low %d err %d",
+	TP_printk("dev %d:%d tp %p err %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->dop,
-		  __entry->committed,
-		  __entry->low,
+		  __entry->tp,
 		  __entry->error)
 )
 #define DEFINE_DEFER_ERROR_EVENT(name) \
 DEFINE_EVENT(xfs_defer_error_class, name, \
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, int error), \
-	TP_ARGS(mp, dop, error))
+	TP_PROTO(struct xfs_trans *tp, int error), \
+	TP_ARGS(tp, error))
 
 DECLARE_EVENT_CLASS(xfs_defer_pending_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp),
@@ -2407,7 +2379,6 @@ DEFINE_EVENT(xfs_map_extent_deferred_class, name, \
 		 xfs_exntst_t state), \
 	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state))
 
-DEFINE_DEFER_EVENT(xfs_defer_init);
 DEFINE_DEFER_EVENT(xfs_defer_cancel);
 DEFINE_DEFER_EVENT(xfs_defer_trans_roll);
 DEFINE_DEFER_EVENT(xfs_defer_trans_abort);
@@ -2417,9 +2388,8 @@ DEFINE_DEFER_EVENT(xfs_defer_finish_done);
 DEFINE_DEFER_ERROR_EVENT(xfs_defer_trans_roll_error);
 DEFINE_DEFER_ERROR_EVENT(xfs_defer_finish_error);
 
-DEFINE_DEFER_PENDING_EVENT(xfs_defer_intake_work);
-DEFINE_DEFER_PENDING_EVENT(xfs_defer_intake_cancel);
-DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_cancel);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_create_intent);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_cancel_list);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_finish);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort);
 
@@ -3215,8 +3185,6 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow);
 DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
 
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write);
-DEFINE_IOMAP_EVENT(xfs_reflink_find_cow_mapping);
-DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
 
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 524f543c5b82..bedc5a5133a5 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -100,6 +100,8 @@ xfs_trans_dup(
 	ntp->t_mountp = tp->t_mountp;
 	INIT_LIST_HEAD(&ntp->t_items);
 	INIT_LIST_HEAD(&ntp->t_busy);
+	INIT_LIST_HEAD(&ntp->t_dfops);
+	ntp->t_firstblock = NULLFSBLOCK;
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(tp->t_ticket != NULL);
@@ -118,7 +120,9 @@ xfs_trans_dup(
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
 	tp->t_rtx_res = tp->t_rtx_res_used;
 	ntp->t_pflags = tp->t_pflags;
-	ntp->t_agfl_dfops = tp->t_agfl_dfops;
+
+	/* move deferred ops over to the new tp */
+	xfs_defer_move(ntp, tp);
 
 	xfs_trans_dup_dqinfo(tp, ntp);
 
@@ -273,6 +277,8 @@ xfs_trans_alloc(
 	tp->t_mountp = mp;
 	INIT_LIST_HEAD(&tp->t_items);
 	INIT_LIST_HEAD(&tp->t_busy);
+	INIT_LIST_HEAD(&tp->t_dfops);
+	tp->t_firstblock = NULLFSBLOCK;
 
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
 	if (error) {
@@ -914,12 +920,21 @@ __xfs_trans_commit(
 	int			error = 0;
 	int			sync = tp->t_flags & XFS_TRANS_SYNC;
 
-	ASSERT(!tp->t_agfl_dfops ||
-	       !xfs_defer_has_unfinished_work(tp->t_agfl_dfops) || regrant);
-
 	trace_xfs_trans_commit(tp, _RET_IP_);
 
 	/*
+	 * Finish deferred items on final commit. Only permanent transactions
+	 * should ever have deferred ops.
+	 */
+	WARN_ON_ONCE(!list_empty(&tp->t_dfops) &&
+		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
+	if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) {
+		error = xfs_defer_finish_noroll(&tp);
+		if (error)
+			goto out_unreserve;
+	}
+
+	/*
 	 * If there is nothing to be logged by the transaction,
 	 * then unlock all of the items associated with the
 	 * transaction and free the transaction structure.
@@ -1008,6 +1023,9 @@ xfs_trans_cancel(
 
 	trace_xfs_trans_cancel(tp, _RET_IP_);
 
+	if (tp->t_flags & XFS_TRANS_PERM_LOG_RES)
+		xfs_defer_cancel(tp);
+
 	/*
 	 * See if the caller is relying on us to shut down the
 	 * filesystem.  This happens in paths where we detect
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 6526314f0b8f..c3d278e96ad1 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -24,7 +24,6 @@ struct xfs_rui_log_item;
 struct xfs_btree_cur;
 struct xfs_cui_log_item;
 struct xfs_cud_log_item;
-struct xfs_defer_ops;
 struct xfs_bui_log_item;
 struct xfs_bud_log_item;
 
@@ -90,6 +89,11 @@ void	xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
 #define XFS_ITEM_LOCKED		2
 #define XFS_ITEM_FLUSHING	3
 
+/*
+ * Deferred operation item relogging limits.
+ */
+#define XFS_DEFER_OPS_NR_INODES	2	/* join up to two inodes */
+#define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
 
 /*
  * This is the structure maintained for every active transaction.
@@ -102,11 +106,11 @@ typedef struct xfs_trans {
 	unsigned int		t_blk_res_used;	/* # of resvd blocks used */
 	unsigned int		t_rtx_res;	/* # of rt extents resvd */
 	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
+	unsigned int		t_flags;	/* misc flags */
+	xfs_fsblock_t		t_firstblock;	/* first block allocated */
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
-	struct xfs_defer_ops	*t_agfl_dfops;	/* optional agfl fixup dfops */
-	unsigned int		t_flags;	/* misc flags */
 	int64_t			t_icount_delta;	/* superblock icount change */
 	int64_t			t_ifree_delta;	/* superblock ifree change */
 	int64_t			t_fdblocks_delta; /* superblock fdblocks chg */
@@ -128,6 +132,7 @@ typedef struct xfs_trans {
 	int64_t			t_rextslog_delta;/* superblocks rextslog chg */
 	struct list_head	t_items;	/* log item descriptors */
 	struct list_head	t_busy;		/* list of busy extents */
+	struct list_head	t_dfops;	/* deferred operations */
 	unsigned long		t_pflags;	/* saved process flags state */
 } xfs_trans_t;
 
@@ -258,7 +263,7 @@ void xfs_refcount_update_init_defer_op(void);
 struct xfs_cud_log_item *xfs_trans_get_cud(struct xfs_trans *tp,
 		struct xfs_cui_log_item *cuip);
 int xfs_trans_log_finish_refcount_update(struct xfs_trans *tp,
-		struct xfs_cud_log_item *cudp, struct xfs_defer_ops *dfops,
+		struct xfs_cud_log_item *cudp,
 		enum xfs_refcount_intent_type type, xfs_fsblock_t startblock,
 		xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb,
 		xfs_extlen_t *new_len, struct xfs_btree_cur **pcur);
@@ -270,9 +275,9 @@ void xfs_bmap_update_init_defer_op(void);
 struct xfs_bud_log_item *xfs_trans_get_bud(struct xfs_trans *tp,
 		struct xfs_bui_log_item *buip);
 int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp,
-		struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops,
-		enum xfs_bmap_intent_type type, struct xfs_inode *ip,
-		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t *blockcount, xfs_exntst_t state);
+		struct xfs_bud_log_item *rudp, enum xfs_bmap_intent_type type,
+		struct xfs_inode *ip, int whichfork, xfs_fileoff_t startoff,
+		xfs_fsblock_t startblock, xfs_filblks_t *blockcount,
+		xfs_exntst_t state);
 
 #endif	/* __XFS_TRANS_H__ */
diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c
index a15a5cd867f9..741c558b2179 100644
--- a/fs/xfs/xfs_trans_bmap.c
+++ b/fs/xfs/xfs_trans_bmap.c
@@ -43,7 +43,6 @@ int
 xfs_trans_log_finish_bmap_update(
 	struct xfs_trans		*tp,
 	struct xfs_bud_log_item		*budp,
-	struct xfs_defer_ops		*dop,
 	enum xfs_bmap_intent_type	type,
 	struct xfs_inode		*ip,
 	int				whichfork,
@@ -54,7 +53,7 @@ xfs_trans_log_finish_bmap_update(
 {
 	int				error;
 
-	error = xfs_bmap_finish_one(tp, dop, ip, type, whichfork, startoff,
+	error = xfs_bmap_finish_one(tp, ip, type, whichfork, startoff,
 			startblock, blockcount, state);
 
 	/*
@@ -176,7 +175,6 @@ xfs_bmap_update_create_done(
 STATIC int
 xfs_bmap_update_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
@@ -187,7 +185,7 @@ xfs_bmap_update_finish_item(
 
 	bmap = container_of(item, struct xfs_bmap_intent, bi_list);
 	count = bmap->bi_bmap.br_blockcount;
-	error = xfs_trans_log_finish_bmap_update(tp, done_item, dop,
+	error = xfs_trans_log_finish_bmap_update(tp, done_item,
 			bmap->bi_type,
 			bmap->bi_owner, bmap->bi_whichfork,
 			bmap->bi_bmap.br_startoff,
diff --git a/fs/xfs/xfs_trans_extfree.c b/fs/xfs/xfs_trans_extfree.c
index bd66c76f55e6..855c0b651fd4 100644
--- a/fs/xfs/xfs_trans_extfree.c
+++ b/fs/xfs/xfs_trans_extfree.c
@@ -171,7 +171,6 @@ xfs_extent_free_create_done(
 STATIC int
 xfs_extent_free_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
@@ -226,7 +225,6 @@ static const struct xfs_defer_op_type xfs_extent_free_defer_type = {
 STATIC int
 xfs_agfl_free_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
diff --git a/fs/xfs/xfs_trans_refcount.c b/fs/xfs/xfs_trans_refcount.c
index 46dd4fca8aa7..523c55663954 100644
--- a/fs/xfs/xfs_trans_refcount.c
+++ b/fs/xfs/xfs_trans_refcount.c
@@ -42,7 +42,6 @@ int
 xfs_trans_log_finish_refcount_update(
 	struct xfs_trans		*tp,
 	struct xfs_cud_log_item		*cudp,
-	struct xfs_defer_ops		*dop,
 	enum xfs_refcount_intent_type	type,
 	xfs_fsblock_t			startblock,
 	xfs_extlen_t			blockcount,
@@ -52,7 +51,7 @@ xfs_trans_log_finish_refcount_update(
 {
 	int				error;
 
-	error = xfs_refcount_finish_one(tp, dop, type, startblock,
+	error = xfs_refcount_finish_one(tp, type, startblock,
 			blockcount, new_fsb, new_len, pcur);
 
 	/*
@@ -169,7 +168,6 @@ xfs_refcount_update_create_done(
 STATIC int
 xfs_refcount_update_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
@@ -180,7 +178,7 @@ xfs_refcount_update_finish_item(
 	int				error;
 
 	refc = container_of(item, struct xfs_refcount_intent, ri_list);
-	error = xfs_trans_log_finish_refcount_update(tp, done_item, dop,
+	error = xfs_trans_log_finish_refcount_update(tp, done_item,
 			refc->ri_type,
 			refc->ri_startblock,
 			refc->ri_blockcount,
diff --git a/fs/xfs/xfs_trans_rmap.c b/fs/xfs/xfs_trans_rmap.c
index 726d8e2c0558..05b00e40251f 100644
--- a/fs/xfs/xfs_trans_rmap.c
+++ b/fs/xfs/xfs_trans_rmap.c
@@ -193,7 +193,6 @@ xfs_rmap_update_create_done(
 STATIC int
 xfs_rmap_update_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index ec07f23678ea..0d4b1d3dbc1e 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -84,42 +84,59 @@ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 ne
 }
 #endif
 
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+#ifdef arch_atomic_fetch_add_unless
+#define atomic_fetch_add_unless atomic_fetch_add_unless
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	kasan_check_write(v, sizeof(*v));
-	return __arch_atomic_add_unless(v, a, u);
+	return arch_atomic_fetch_add_unless(v, a, u);
 }
+#endif
 
-
-static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
+#ifdef arch_atomic64_fetch_add_unless
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
+static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	kasan_check_write(v, sizeof(*v));
-	return arch_atomic64_add_unless(v, a, u);
+	return arch_atomic64_fetch_add_unless(v, a, u);
 }
+#endif
 
+#ifdef arch_atomic_inc
+#define atomic_inc atomic_inc
 static __always_inline void atomic_inc(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic_inc(v);
 }
+#endif
 
+#ifdef arch_atomic64_inc
+#define atomic64_inc atomic64_inc
 static __always_inline void atomic64_inc(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_inc(v);
 }
+#endif
 
+#ifdef arch_atomic_dec
+#define atomic_dec atomic_dec
 static __always_inline void atomic_dec(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic_dec(v);
 }
+#endif
 
+#ifdef atch_atomic64_dec
+#define atomic64_dec
 static __always_inline void atomic64_dec(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_dec(v);
 }
+#endif
 
 static __always_inline void atomic_add(int i, atomic_t *v)
 {
@@ -181,65 +198,95 @@ static __always_inline void atomic64_xor(s64 i, atomic64_t *v)
 	arch_atomic64_xor(i, v);
 }
 
+#ifdef arch_atomic_inc_return
+#define atomic_inc_return atomic_inc_return
 static __always_inline int atomic_inc_return(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_return(v);
 }
+#endif
 
+#ifdef arch_atomic64_in_return
+#define atomic64_inc_return atomic64_inc_return
 static __always_inline s64 atomic64_inc_return(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_return(v);
 }
+#endif
 
+#ifdef arch_atomic_dec_return
+#define atomic_dec_return atomic_dec_return
 static __always_inline int atomic_dec_return(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_return(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_return
+#define atomic64_dec_return atomic64_dec_return
 static __always_inline s64 atomic64_dec_return(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_return(v);
 }
+#endif
 
-static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v)
+#ifdef arch_atomic64_inc_not_zero
+#define atomic64_inc_not_zero atomic64_inc_not_zero
+static __always_inline bool atomic64_inc_not_zero(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_not_zero(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_if_positive
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_if_positive(v);
 }
+#endif
 
+#ifdef arch_atomic_dec_and_test
+#define atomic_dec_and_test atomic_dec_and_test
 static __always_inline bool atomic_dec_and_test(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_and_test
+#define atomic64_dec_and_test atomic64_dec_and_test
 static __always_inline bool atomic64_dec_and_test(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic_inc_and_test
+#define atomic_inc_and_test atomic_inc_and_test
 static __always_inline bool atomic_inc_and_test(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic64_inc_and_test
+#define atomic64_inc_and_test atomic64_inc_and_test
 static __always_inline bool atomic64_inc_and_test(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_and_test(v);
 }
+#endif
 
 static __always_inline int atomic_add_return(int i, atomic_t *v)
 {
@@ -325,152 +372,96 @@ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v)
 	return arch_atomic64_fetch_xor(i, v);
 }
 
+#ifdef arch_atomic_sub_and_test
+#define atomic_sub_and_test atomic_sub_and_test
 static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_sub_and_test(i, v);
 }
+#endif
 
+#ifdef arch_atomic64_sub_and_test
+#define atomic64_sub_and_test atomic64_sub_and_test
 static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_sub_and_test(i, v);
 }
+#endif
 
+#ifdef arch_atomic_add_negative
+#define atomic_add_negative atomic_add_negative
 static __always_inline bool atomic_add_negative(int i, atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_add_negative(i, v);
 }
+#endif
 
+#ifdef arch_atomic64_add_negative
+#define atomic64_add_negative atomic64_add_negative
 static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_add_negative(i, v);
 }
+#endif
 
-static __always_inline unsigned long
-cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
+#define xchg(ptr, new)							\
+({									\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_xchg(__ai_ptr, (new));					\
+})
 
 #define cmpxchg(ptr, old, new)						\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg_size((ptr), (unsigned long)(old),	\
-		(unsigned long)(new), sizeof(*(ptr))));			\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg(__ai_ptr, (old), (new));				\
 })
 
-static __always_inline unsigned long
-sync_cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new,
-		  int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_sync_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_sync_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_sync_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_sync_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
-
 #define sync_cmpxchg(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))sync_cmpxchg_size((ptr),			\
-		(unsigned long)(old), (unsigned long)(new),		\
-		sizeof(*(ptr))));					\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_sync_cmpxchg(__ai_ptr, (old), (new));			\
 })
 
-static __always_inline unsigned long
-cmpxchg_local_size(volatile void *ptr, unsigned long old, unsigned long new,
-		   int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_cmpxchg_local((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_cmpxchg_local((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_cmpxchg_local((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_cmpxchg_local((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
-
 #define cmpxchg_local(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg_local_size((ptr),			\
-		(unsigned long)(old), (unsigned long)(new),		\
-		sizeof(*(ptr))));					\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg_local(__ai_ptr, (old), (new));			\
 })
 
-static __always_inline u64
-cmpxchg64_size(volatile u64 *ptr, u64 old, u64 new)
-{
-	kasan_check_write(ptr, sizeof(*ptr));
-	return arch_cmpxchg64(ptr, old, new);
-}
-
 #define cmpxchg64(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg64_size((ptr), (u64)(old),		\
-		(u64)(new)));						\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg64(__ai_ptr, (old), (new));				\
 })
 
-static __always_inline u64
-cmpxchg64_local_size(volatile u64 *ptr, u64 old, u64 new)
-{
-	kasan_check_write(ptr, sizeof(*ptr));
-	return arch_cmpxchg64_local(ptr, old, new);
-}
-
 #define cmpxchg64_local(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg64_local_size((ptr), (u64)(old),	\
-		(u64)(new)));						\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg64_local(__ai_ptr, (old), (new));			\
 })
 
-/*
- * Originally we had the following code here:
- *     __typeof__(p1) ____p1 = (p1);
- *     kasan_check_write(____p1, 2 * sizeof(*____p1));
- *     arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2));
- * But it leads to compilation failures (see gcc issue 72873).
- * So for now it's left non-instrumented.
- * There are few callers of cmpxchg_double(), so it's not critical.
- */
 #define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\
 ({									\
-	arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2));	\
+	typeof(p1) __ai_p1 = (p1);					\
+	kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1));		\
+	arch_cmpxchg_double(__ai_p1, (p2), (o1), (o2), (n1), (n2));	\
 })
 
-#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)			\
-({									\
-	arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2));	\
+#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)				\
+({										\
+	typeof(p1) __ai_p1 = (p1);						\
+	kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1));			\
+	arch_cmpxchg_double_local(__ai_p1, (p2), (o1), (o2), (n1), (n2));	\
 })
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index abe6dd9ca2a8..13324aa828eb 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -186,11 +186,6 @@ ATOMIC_OP(xor, ^)
 
 #include <linux/irqflags.h>
 
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
-	return atomic_add_return(i, v) < 0;
-}
-
 static inline void atomic_add(int i, atomic_t *v)
 {
 	atomic_add_return(i, v);
@@ -201,35 +196,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	atomic_sub_return(i, v);
 }
 
-static inline void atomic_inc(atomic_t *v)
-{
-	atomic_add_return(1, v);
-}
-
-static inline void atomic_dec(atomic_t *v)
-{
-	atomic_sub_return(1, v);
-}
-
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
-#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
-#ifndef __atomic_add_unless
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
-		c = old;
-	return c;
-}
-#endif
-
 #endif /* __ASM_GENERIC_ATOMIC_H */
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index 8d28eb010d0d..97b28b7f1f29 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -11,6 +11,7 @@
  */
 #ifndef _ASM_GENERIC_ATOMIC64_H
 #define _ASM_GENERIC_ATOMIC64_H
+#include <linux/types.h>
 
 typedef struct {
 	long long counter;
@@ -50,18 +51,10 @@ ATOMIC64_OPS(xor)
 #undef ATOMIC64_OP
 
 extern long long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
 extern long long atomic64_xchg(atomic64_t *v, long long new);
-extern int	 atomic64_add_unless(atomic64_t *v, long long a, long long u);
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v) 	atomic64_add_unless((v), 1LL, 0LL)
+extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif  /*  _ASM_GENERIC_ATOMIC64_H  */
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 04deffaf5f7d..dd90c9792909 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -2,189 +2,67 @@
 #ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_
 #define _ASM_GENERIC_BITOPS_ATOMIC_H_
 
-#include <asm/types.h>
-#include <linux/irqflags.h>
-
-#ifdef CONFIG_SMP
-#include <asm/spinlock.h>
-#include <asm/cache.h>		/* we use L1_CACHE_BYTES */
-
-/* Use an array of spinlocks for our atomic_ts.
- * Hash function to index into a different SPINLOCK.
- * Since "a" is usually an address, use one spinlock per cacheline.
- */
-#  define ATOMIC_HASH_SIZE 4
-#  define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
-
-extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
-
-/* Can't use raw_spin_lock_irq because of #include problems, so
- * this is the substitute */
-#define _atomic_spin_lock_irqsave(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);	\
-	local_irq_save(f);			\
-	arch_spin_lock(s);			\
-} while(0)
-
-#define _atomic_spin_unlock_irqrestore(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);		\
-	arch_spin_unlock(s);				\
-	local_irq_restore(f);				\
-} while(0)
-
-
-#else
-#  define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
-#  define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
-#endif
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
 
 /*
- * NMI events can occur at any time, including when interrupts have been
- * disabled by *_irqsave().  So you can get NMI events occurring while a
- * *_bit function is holding a spin lock.  If the NMI handler also wants
- * to do bit manipulation (and they do) then you can get a deadlock
- * between the original caller of *_bit() and the NMI handler.
- *
- * by Keith Owens
+ * Implementation of atomic bitops using atomic-fetch ops.
+ * See Documentation/atomic_bitops.txt for details.
  */
 
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note: there are no guarantees that this function will not be reordered
- * on non x86 architectures, so if you are writing portable code,
- * make sure not to rely on its reordering guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(int nr, volatile unsigned long *addr)
+static inline void set_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p  |= mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p &= ~mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered. It may be
- * reordered on other architectures than x86.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static inline void change_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p ^= mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It may be reordered on other architectures than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
 
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old | mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	if (READ_ONCE(*p) & mask)
+		return 1;
 
-	return (old & mask) != 0;
+	old = atomic_long_fetch_or(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It can be reorderdered on other architectures other than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
 
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old & ~mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	if (!(READ_ONCE(*p) & mask))
+		return 0;
 
-	return (old & mask) != 0;
+	old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old ^ mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
 
-	return (old & mask) != 0;
+	p += BIT_WORD(nr);
+	old = atomic_long_fetch_xor(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
 #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */
diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
index 67ab280ad134..3ae021368f48 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_GENERIC_BITOPS_LOCK_H_
 #define _ASM_GENERIC_BITOPS_LOCK_H_
 
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
 /**
  * test_and_set_bit_lock - Set a bit and return its old value, for lock
  * @nr: Bit to set
@@ -11,7 +15,20 @@
  * the returned value is 0.
  * It can be used to implement bit locks.
  */
-#define test_and_set_bit_lock(nr, addr)	test_and_set_bit(nr, addr)
+static inline int test_and_set_bit_lock(unsigned int nr,
+					volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	if (READ_ONCE(*p) & mask)
+		return 1;
+
+	old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
+	return !!(old & mask);
+}
+
 
 /**
  * clear_bit_unlock - Clear a bit in memory, for unlock
@@ -20,11 +37,11 @@
  *
  * This operation is atomic and provides release barrier semantics.
  */
-#define clear_bit_unlock(nr, addr)	\
-do {					\
-	smp_mb__before_atomic();	\
-	clear_bit(nr, addr);		\
-} while (0)
+static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
+{
+	p += BIT_WORD(nr);
+	atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
+}
 
 /**
  * __clear_bit_unlock - Clear a bit in memory, for unlock
@@ -37,11 +54,38 @@ do {					\
  *
  * See for example x86's implementation.
  */
-#define __clear_bit_unlock(nr, addr)	\
-do {					\
-	smp_mb__before_atomic();	\
-	clear_bit(nr, addr);		\
-} while (0)
+static inline void __clear_bit_unlock(unsigned int nr,
+				      volatile unsigned long *p)
+{
+	unsigned long old;
 
-#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
+	p += BIT_WORD(nr);
+	old = READ_ONCE(*p);
+	old &= ~BIT_MASK(nr);
+	atomic_long_set_release((atomic_long_t *)p, old);
+}
+
+/**
+ * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
+ *                                     byte is negative, for unlock.
+ * @nr: the bit to clear
+ * @addr: the address to start counting from
+ *
+ * This is a bit of a one-trick-pony for the filemap code, which clears
+ * PG_locked and tests PG_waiters,
+ */
+#ifndef clear_bit_unlock_is_negative_byte
+static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr,
+						     volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
+	return !!(old & BIT(7));
+}
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+#endif
 
+#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f59639afaa39..a75cb371cd19 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1019,8 +1019,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
 int pud_clear_huge(pud_t *pud);
 int pmd_clear_huge(pmd_t *pmd);
-int pud_free_pmd_page(pud_t *pud);
-int pmd_free_pte_page(pmd_t *pmd);
+int pud_free_pmd_page(pud_t *pud, unsigned long addr);
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
 static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
@@ -1046,11 +1046,11 @@ static inline int pmd_clear_huge(pmd_t *pmd)
 {
 	return 0;
 }
-static inline int pud_free_pmd_page(pud_t *pud)
+static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
 	return 0;
 }
-static inline int pmd_free_pte_page(pmd_t *pmd)
+static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	return 0;
 }
@@ -1083,6 +1083,18 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 static inline void init_espfix_bsp(void) { }
 #endif
 
+#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
+static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	return true;
+}
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return false;
+}
+#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */
+
 #endif /* !__ASSEMBLY__ */
 
 #ifndef io_remap_pfn_range
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 3063125197ad..e811ef7b8350 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -303,4 +303,14 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 
 #define tlb_migrate_finish(mm) do {} while (0)
 
+/*
+ * Used to flush the TLB when page tables are removed, when lazy
+ * TLB mode may cause a CPU to retain intermediate translations
+ * pointing to about-to-be-freed page table memory.
+ */
+#ifndef HAVE_TLB_FLUSH_REMOVE_TABLES
+#define tlb_flush_remove_tables(mm) do {} while (0)
+#define tlb_flush_remove_tables_local(mm) do {} while (0)
+#endif
+
 #endif /* _ASM_GENERIC__TLB_H */
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 01ce3997cb42..1e8e88bdaf09 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -2,6 +2,8 @@
 /* Atomic operations usable in machine independent code */
 #ifndef _LINUX_ATOMIC_H
 #define _LINUX_ATOMIC_H
+#include <linux/types.h>
+
 #include <asm/atomic.h>
 #include <asm/barrier.h>
 
@@ -36,40 +38,46 @@
  * barriers on top of the relaxed variant. In the case where the relaxed
  * variant is already fully ordered, no additional barriers are needed.
  *
- * Besides, if an arch has a special barrier for acquire/release, it could
- * implement its own __atomic_op_* and use the same framework for building
- * variants
- *
- * If an architecture overrides __atomic_op_acquire() it will probably want
- * to define smp_mb__after_spinlock().
+ * If an architecture overrides __atomic_acquire_fence() it will probably
+ * want to define smp_mb__after_spinlock().
  */
-#ifndef __atomic_op_acquire
+#ifndef __atomic_acquire_fence
+#define __atomic_acquire_fence		smp_mb__after_atomic
+#endif
+
+#ifndef __atomic_release_fence
+#define __atomic_release_fence		smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_pre_full_fence
+#define __atomic_pre_full_fence		smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_post_full_fence
+#define __atomic_post_full_fence	smp_mb__after_atomic
+#endif
+
 #define __atomic_op_acquire(op, args...)				\
 ({									\
 	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	smp_mb__after_atomic();						\
+	__atomic_acquire_fence();					\
 	__ret;								\
 })
-#endif
 
-#ifndef __atomic_op_release
 #define __atomic_op_release(op, args...)				\
 ({									\
-	smp_mb__before_atomic();					\
+	__atomic_release_fence();					\
 	op##_relaxed(args);						\
 })
-#endif
 
-#ifndef __atomic_op_fence
 #define __atomic_op_fence(op, args...)					\
 ({									\
 	typeof(op##_relaxed(args)) __ret;				\
-	smp_mb__before_atomic();					\
+	__atomic_pre_full_fence();					\
 	__ret = op##_relaxed(args);					\
-	smp_mb__after_atomic();						\
+	__atomic_post_full_fence();					\
 	__ret;								\
 })
-#endif
 
 /* atomic_add_return_relaxed */
 #ifndef atomic_add_return_relaxed
@@ -95,11 +103,23 @@
 #endif
 #endif /* atomic_add_return_relaxed */
 
+#ifndef atomic_inc
+#define atomic_inc(v)			atomic_add(1, (v))
+#endif
+
 /* atomic_inc_return_relaxed */
 #ifndef atomic_inc_return_relaxed
+
+#ifndef atomic_inc_return
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+#define atomic_inc_return_relaxed(v)	atomic_add_return_relaxed(1, (v))
+#define atomic_inc_return_acquire(v)	atomic_add_return_acquire(1, (v))
+#define atomic_inc_return_release(v)	atomic_add_return_release(1, (v))
+#else /* atomic_inc_return */
 #define  atomic_inc_return_relaxed	atomic_inc_return
 #define  atomic_inc_return_acquire	atomic_inc_return
 #define  atomic_inc_return_release	atomic_inc_return
+#endif /* atomic_inc_return */
 
 #else /* atomic_inc_return_relaxed */
 
@@ -143,11 +163,23 @@
 #endif
 #endif /* atomic_sub_return_relaxed */
 
+#ifndef atomic_dec
+#define atomic_dec(v)			atomic_sub(1, (v))
+#endif
+
 /* atomic_dec_return_relaxed */
 #ifndef atomic_dec_return_relaxed
+
+#ifndef atomic_dec_return
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+#define atomic_dec_return_relaxed(v)	atomic_sub_return_relaxed(1, (v))
+#define atomic_dec_return_acquire(v)	atomic_sub_return_acquire(1, (v))
+#define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
+#else /* atomic_dec_return */
 #define  atomic_dec_return_relaxed	atomic_dec_return
 #define  atomic_dec_return_acquire	atomic_dec_return
 #define  atomic_dec_return_release	atomic_dec_return
+#endif /* atomic_dec_return */
 
 #else /* atomic_dec_return_relaxed */
 
@@ -328,12 +360,22 @@
 #endif
 #endif /* atomic_fetch_and_relaxed */
 
-#ifdef atomic_andnot
-/* atomic_fetch_andnot_relaxed */
+#ifndef atomic_andnot
+#define atomic_andnot(i, v)		atomic_and(~(int)(i), (v))
+#endif
+
 #ifndef atomic_fetch_andnot_relaxed
-#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot
-#define atomic_fetch_andnot_acquire	atomic_fetch_andnot
-#define atomic_fetch_andnot_release	atomic_fetch_andnot
+
+#ifndef atomic_fetch_andnot
+#define atomic_fetch_andnot(i, v)		atomic_fetch_and(~(int)(i), (v))
+#define atomic_fetch_andnot_relaxed(i, v)	atomic_fetch_and_relaxed(~(int)(i), (v))
+#define atomic_fetch_andnot_acquire(i, v)	atomic_fetch_and_acquire(~(int)(i), (v))
+#define atomic_fetch_andnot_release(i, v)	atomic_fetch_and_release(~(int)(i), (v))
+#else /* atomic_fetch_andnot */
+#define atomic_fetch_andnot_relaxed		atomic_fetch_andnot
+#define atomic_fetch_andnot_acquire		atomic_fetch_andnot
+#define atomic_fetch_andnot_release		atomic_fetch_andnot
+#endif /* atomic_fetch_andnot */
 
 #else /* atomic_fetch_andnot_relaxed */
 
@@ -352,7 +394,6 @@
 	__atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__)
 #endif
 #endif /* atomic_fetch_andnot_relaxed */
-#endif /* atomic_andnot */
 
 /* atomic_fetch_xor_relaxed */
 #ifndef atomic_fetch_xor_relaxed
@@ -520,112 +561,140 @@
 #endif /* xchg_relaxed */
 
 /**
+ * atomic_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic_fetch_add_unless
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
+{
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c == u))
+			break;
+	} while (!atomic_try_cmpxchg(v, &c, c + a));
+
+	return c;
+}
+#endif
+
+/**
  * atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
  */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
+static inline bool atomic_add_unless(atomic_t *v, int a, int u)
 {
-	return __atomic_add_unless(v, a, u) != u;
+	return atomic_fetch_add_unless(v, a, u) != u;
 }
 
 /**
  * atomic_inc_not_zero - increment unless the number is zero
  * @v: pointer of type atomic_t
  *
- * Atomically increments @v by 1, so long as @v is non-zero.
- * Returns non-zero if @v was non-zero, and zero otherwise.
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
  */
 #ifndef atomic_inc_not_zero
 #define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
 #endif
 
-#ifndef atomic_andnot
-static inline void atomic_andnot(int i, atomic_t *v)
-{
-	atomic_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot(int i, atomic_t *v)
-{
-	return atomic_fetch_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v)
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_inc_and_test
+static inline bool atomic_inc_and_test(atomic_t *v)
 {
-	return atomic_fetch_and_relaxed(~i, v);
+	return atomic_inc_return(v) == 0;
 }
+#endif
 
-static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v)
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic_dec_and_test
+static inline bool atomic_dec_and_test(atomic_t *v)
 {
-	return atomic_fetch_and_acquire(~i, v);
+	return atomic_dec_return(v) == 0;
 }
+#endif
 
-static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_sub_and_test
+static inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
-	return atomic_fetch_and_release(~i, v);
+	return atomic_sub_return(i, v) == 0;
 }
 #endif
 
 /**
- * atomic_inc_not_zero_hint - increment if not null
+ * atomic_add_negative - add and test if negative
+ * @i: integer value to add
  * @v: pointer of type atomic_t
- * @hint: probable value of the atomic before the increment
- *
- * This version of atomic_inc_not_zero() gives a hint of probable
- * value of the atomic. This helps processor to not read the memory
- * before doing the atomic read/modify/write cycle, lowering
- * number of bus transactions on some arches.
  *
- * Returns: 0 if increment was not done, 1 otherwise.
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
  */
-#ifndef atomic_inc_not_zero_hint
-static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
+#ifndef atomic_add_negative
+static inline bool atomic_add_negative(int i, atomic_t *v)
 {
-	int val, c = hint;
-
-	/* sanity test, should be removed by compiler if hint is a constant */
-	if (!hint)
-		return atomic_inc_not_zero(v);
-
-	do {
-		val = atomic_cmpxchg(v, c, c + 1);
-		if (val == c)
-			return 1;
-		c = val;
-	} while (c);
-
-	return 0;
+	return atomic_add_return(i, v) < 0;
 }
 #endif
 
 #ifndef atomic_inc_unless_negative
-static inline int atomic_inc_unless_negative(atomic_t *p)
+static inline bool atomic_inc_unless_negative(atomic_t *v)
 {
-	int v, v1;
-	for (v = 0; v >= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v + 1);
-		if (likely(v1 == v))
-			return 1;
-	}
-	return 0;
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c < 0))
+			return false;
+	} while (!atomic_try_cmpxchg(v, &c, c + 1));
+
+	return true;
 }
 #endif
 
 #ifndef atomic_dec_unless_positive
-static inline int atomic_dec_unless_positive(atomic_t *p)
+static inline bool atomic_dec_unless_positive(atomic_t *v)
 {
-	int v, v1;
-	for (v = 0; v <= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v - 1);
-		if (likely(v1 == v))
-			return 1;
-	}
-	return 0;
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c > 0))
+			return false;
+	} while (!atomic_try_cmpxchg(v, &c, c - 1));
+
+	return true;
 }
 #endif
 
@@ -639,17 +708,14 @@ static inline int atomic_dec_unless_positive(atomic_t *p)
 #ifndef atomic_dec_if_positive
 static inline int atomic_dec_if_positive(atomic_t *v)
 {
-	int c, old, dec;
-	c = atomic_read(v);
-	for (;;) {
+	int dec, c = atomic_read(v);
+
+	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-		old = atomic_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
+	} while (!atomic_try_cmpxchg(v, &c, dec));
+
 	return dec;
 }
 #endif
@@ -693,11 +759,23 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_add_return_relaxed */
 
+#ifndef atomic64_inc
+#define atomic64_inc(v)			atomic64_add(1, (v))
+#endif
+
 /* atomic64_inc_return_relaxed */
 #ifndef atomic64_inc_return_relaxed
+
+#ifndef atomic64_inc_return
+#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
+#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1, (v))
+#define atomic64_inc_return_acquire(v)	atomic64_add_return_acquire(1, (v))
+#define atomic64_inc_return_release(v)	atomic64_add_return_release(1, (v))
+#else /* atomic64_inc_return */
 #define  atomic64_inc_return_relaxed	atomic64_inc_return
 #define  atomic64_inc_return_acquire	atomic64_inc_return
 #define  atomic64_inc_return_release	atomic64_inc_return
+#endif /* atomic64_inc_return */
 
 #else /* atomic64_inc_return_relaxed */
 
@@ -742,11 +820,23 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_sub_return_relaxed */
 
+#ifndef atomic64_dec
+#define atomic64_dec(v)			atomic64_sub(1, (v))
+#endif
+
 /* atomic64_dec_return_relaxed */
 #ifndef atomic64_dec_return_relaxed
+
+#ifndef atomic64_dec_return
+#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
+#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1, (v))
+#define atomic64_dec_return_acquire(v)	atomic64_sub_return_acquire(1, (v))
+#define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
+#else /* atomic64_dec_return */
 #define  atomic64_dec_return_relaxed	atomic64_dec_return
 #define  atomic64_dec_return_acquire	atomic64_dec_return
 #define  atomic64_dec_return_release	atomic64_dec_return
+#endif /* atomic64_dec_return */
 
 #else /* atomic64_dec_return_relaxed */
 
@@ -927,12 +1017,22 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_fetch_and_relaxed */
 
-#ifdef atomic64_andnot
-/* atomic64_fetch_andnot_relaxed */
+#ifndef atomic64_andnot
+#define atomic64_andnot(i, v)		atomic64_and(~(long long)(i), (v))
+#endif
+
 #ifndef atomic64_fetch_andnot_relaxed
-#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot
-#define atomic64_fetch_andnot_acquire	atomic64_fetch_andnot
-#define atomic64_fetch_andnot_release	atomic64_fetch_andnot
+
+#ifndef atomic64_fetch_andnot
+#define atomic64_fetch_andnot(i, v)		atomic64_fetch_and(~(long long)(i), (v))
+#define atomic64_fetch_andnot_relaxed(i, v)	atomic64_fetch_and_relaxed(~(long long)(i), (v))
+#define atomic64_fetch_andnot_acquire(i, v)	atomic64_fetch_and_acquire(~(long long)(i), (v))
+#define atomic64_fetch_andnot_release(i, v)	atomic64_fetch_and_release(~(long long)(i), (v))
+#else /* atomic64_fetch_andnot */
+#define atomic64_fetch_andnot_relaxed		atomic64_fetch_andnot
+#define atomic64_fetch_andnot_acquire		atomic64_fetch_andnot
+#define atomic64_fetch_andnot_release		atomic64_fetch_andnot
+#endif /* atomic64_fetch_andnot */
 
 #else /* atomic64_fetch_andnot_relaxed */
 
@@ -951,7 +1051,6 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 	__atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__)
 #endif
 #endif /* atomic64_fetch_andnot_relaxed */
-#endif /* atomic64_andnot */
 
 /* atomic64_fetch_xor_relaxed */
 #ifndef atomic64_fetch_xor_relaxed
@@ -1049,30 +1148,164 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #define atomic64_try_cmpxchg_release	atomic64_try_cmpxchg
 #endif /* atomic64_try_cmpxchg */
 
-#ifndef atomic64_andnot
-static inline void atomic64_andnot(long long i, atomic64_t *v)
+/**
+ * atomic64_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic64_fetch_add_unless
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	atomic64_and(~i, v);
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c == u))
+			break;
+	} while (!atomic64_try_cmpxchg(v, &c, c + a));
+
+	return c;
 }
+#endif
 
-static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v)
+/**
+ * atomic64_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
+ */
+static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
-	return atomic64_fetch_and(~i, v);
+	return atomic64_fetch_add_unless(v, a, u) != u;
 }
 
-static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v)
+/**
+ * atomic64_inc_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
+ */
+#ifndef atomic64_inc_not_zero
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
+#endif
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_inc_and_test
+static inline bool atomic64_inc_and_test(atomic64_t *v)
 {
-	return atomic64_fetch_and_relaxed(~i, v);
+	return atomic64_inc_return(v) == 0;
 }
+#endif
 
-static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v)
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic64_dec_and_test
+static inline bool atomic64_dec_and_test(atomic64_t *v)
 {
-	return atomic64_fetch_and_acquire(~i, v);
+	return atomic64_dec_return(v) == 0;
 }
+#endif
 
-static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v)
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_sub_and_test
+static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
+{
+	return atomic64_sub_return(i, v) == 0;
+}
+#endif
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+#ifndef atomic64_add_negative
+static inline bool atomic64_add_negative(long long i, atomic64_t *v)
 {
-	return atomic64_fetch_and_release(~i, v);
+	return atomic64_add_return(i, v) < 0;
+}
+#endif
+
+#ifndef atomic64_inc_unless_negative
+static inline bool atomic64_inc_unless_negative(atomic64_t *v)
+{
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c < 0))
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &c, c + 1));
+
+	return true;
+}
+#endif
+
+#ifndef atomic64_dec_unless_positive
+static inline bool atomic64_dec_unless_positive(atomic64_t *v)
+{
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c > 0))
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &c, c - 1));
+
+	return true;
+}
+#endif
+
+/*
+ * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic64_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic64 variable, v, was not decremented.
+ */
+#ifndef atomic64_dec_if_positive
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long dec, c = atomic64_read(v);
+
+	do {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+	} while (!atomic64_try_cmpxchg(v, &c, dec));
+
+	return dec;
 }
 #endif
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index f08f5fe7bd08..51371740d2a8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -429,7 +429,6 @@ extern void bio_put(struct bio *);
 
 extern void __bio_clone_fast(struct bio *, struct bio *);
 extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
-extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
 extern struct bio_set fs_bio_set;
 
@@ -443,12 +442,6 @@ static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 	return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
 }
 
-static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
-{
-	return bio_clone_bioset(bio, gfp_mask, NULL);
-
-}
-
 extern blk_qc_t submit_bio(struct bio *);
 
 extern void bio_endio(struct bio *);
@@ -496,9 +489,9 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
-void generic_start_io_acct(struct request_queue *q, int rw,
+void generic_start_io_acct(struct request_queue *q, int op,
 				unsigned long sectors, struct hd_struct *part);
-void generic_end_io_acct(struct request_queue *q, int rw,
+void generic_end_io_acct(struct request_queue *q, int op,
 				struct hd_struct *part,
 				unsigned long start_time);
 
@@ -553,8 +546,16 @@ do {						\
 #define bio_dev(bio) \
 	disk_devt((bio)->bi_disk)
 
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+int bio_associate_blkcg_from_page(struct bio *bio, struct page *page);
+#else
+static inline int bio_associate_blkcg_from_page(struct bio *bio,
+						struct page *page) {  return 0; }
+#endif
+
 #ifdef CONFIG_BLK_CGROUP
 int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
+int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg);
 void bio_disassociate_task(struct bio *bio);
 void bio_clone_blkcg_association(struct bio *dst, struct bio *src);
 #else	/* CONFIG_BLK_CGROUP */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 4cac4e1a72ff..af419012d77d 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -2,29 +2,9 @@
 #ifndef _LINUX_BITOPS_H
 #define _LINUX_BITOPS_H
 #include <asm/types.h>
+#include <linux/bits.h>
 
-#ifdef	__KERNEL__
-#define BIT(nr)			(1UL << (nr))
-#define BIT_ULL(nr)		(1ULL << (nr))
-#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
-#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
-#define BITS_PER_BYTE		8
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#endif
-
-/*
- * Create a contiguous bitmask starting at bit position @l and ending at
- * position @h. For example
- * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
- */
-#define GENMASK(h, l) \
-	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
-
-#define GENMASK_ULL(h, l) \
-	(((~0ULL) - (1ULL << (l)) + 1) & \
-	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
 
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/include/linux/bits.h b/include/linux/bits.h
new file mode 100644
index 000000000000..2b7b532c1d51
--- /dev/null
+++ b/include/linux/bits.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+#include <asm/bitsperlong.h>
+
+#define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE		8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+	(((~0ULL) - (1ULL << (l)) + 1) & \
+	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif	/* __LINUX_BITS_H */
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 6c666fd7de3c..34aec30e06c7 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -35,6 +35,7 @@ enum blkg_rwstat_type {
 	BLKG_RWSTAT_WRITE,
 	BLKG_RWSTAT_SYNC,
 	BLKG_RWSTAT_ASYNC,
+	BLKG_RWSTAT_DISCARD,
 
 	BLKG_RWSTAT_NR,
 	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
@@ -136,6 +137,12 @@ struct blkcg_gq {
 	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
 
 	struct rcu_head			rcu_head;
+
+	atomic_t			use_delay;
+	atomic64_t			delay_nsec;
+	atomic64_t			delay_start;
+	u64				last_delay;
+	int				last_use;
 };
 
 typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
@@ -148,6 +155,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
+typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf,
+				      size_t size);
 
 struct blkcg_policy {
 	int				plid;
@@ -167,6 +176,7 @@ struct blkcg_policy {
 	blkcg_pol_offline_pd_fn		*pd_offline_fn;
 	blkcg_pol_free_pd_fn		*pd_free_fn;
 	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
+	blkcg_pol_stat_pd_fn		*pd_stat_fn;
 };
 
 extern struct blkcg blkcg_root;
@@ -238,6 +248,42 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 	return css_to_blkcg(task_css(current, io_cgrp_id));
 }
 
+static inline bool blk_cgroup_congested(void)
+{
+	struct cgroup_subsys_state *css;
+	bool ret = false;
+
+	rcu_read_lock();
+	css = kthread_blkcg();
+	if (!css)
+		css = task_css(current, io_cgrp_id);
+	while (css) {
+		if (atomic_read(&css->cgroup->congestion_count)) {
+			ret = true;
+			break;
+		}
+		css = css->parent;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg
+ * @return: true if this bio needs to be submitted with the root blkg context.
+ *
+ * In order to avoid priority inversions we sometimes need to issue a bio as if
+ * it were attached to the root blkg, and then backcharge to the actual owning
+ * blkg.  The idea is we do bio_blkcg() to look up the actual context for the
+ * bio and attach the appropriate blkg to the bio.  Then we call this helper and
+ * if it is true run with the root blkg for that queue and then do any
+ * backcharging to the originating cgroup once the io is complete.
+ */
+static inline bool bio_issue_as_root_blkg(struct bio *bio)
+{
+	return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0;
+}
+
 /**
  * blkcg_parent - get the parent of a blkcg
  * @blkcg: blkcg of interest
@@ -296,6 +342,17 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 }
 
 /**
+ * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair
+ * @q: request_queue of interest
+ *
+ * Lookup blkg for @q at the root level. See also blkg_lookup().
+ */
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{
+	return q->root_blkg;
+}
+
+/**
  * blkg_to_pdata - get policy private data
  * @blkg: blkg of interest
  * @pol: policy of interest
@@ -355,6 +412,21 @@ static inline void blkg_get(struct blkcg_gq *blkg)
 	atomic_inc(&blkg->refcnt);
 }
 
+/**
+ * blkg_try_get - try and get a blkg reference
+ * @blkg: blkg to get
+ *
+ * This is for use when doing an RCU lookup of the blkg.  We may be in the midst
+ * of freeing this blkg, so we can only use it if the refcnt is not zero.
+ */
+static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg)
+{
+	if (atomic_inc_not_zero(&blkg->refcnt))
+		return blkg;
+	return NULL;
+}
+
+
 void __blkg_release_rcu(struct rcu_head *rcu);
 
 /**
@@ -589,7 +661,9 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
 {
 	struct percpu_counter *cnt;
 
-	if (op_is_write(op))
+	if (op_is_discard(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
+	else if (op_is_write(op))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
@@ -706,8 +780,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 
 	if (!throtl) {
 		blkg = blkg ?: q->root_blkg;
-		blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
-				bio->bi_iter.bi_size);
+		/*
+		 * If the bio is flagged with BIO_QUEUE_ENTERED it means this
+		 * is a split bio and we would have already accounted for the
+		 * size of the bio.
+		 */
+		if (!bio_flagged(bio, BIO_QUEUE_ENTERED))
+			blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
+					bio->bi_iter.bi_size);
 		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
 	}
 
@@ -715,6 +795,59 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 	return !throtl;
 }
 
+static inline void blkcg_use_delay(struct blkcg_gq *blkg)
+{
+	if (atomic_add_return(1, &blkg->use_delay) == 1)
+		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+}
+
+static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+
+	if (old == 0)
+		return 0;
+
+	/*
+	 * We do this song and dance because we can race with somebody else
+	 * adding or removing delay.  If we just did an atomic_dec we'd end up
+	 * negative and we'd already be in trouble.  We need to subtract 1 and
+	 * then check to see if we were the last delay so we can drop the
+	 * congestion count on the cgroup.
+	 */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1);
+		if (cur == old)
+			break;
+		old = cur;
+	}
+
+	if (old == 0)
+		return 0;
+	if (old == 1)
+		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+	return 1;
+}
+
+static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+	if (!old)
+		return;
+	/* We only want 1 person clearing the congestion count for this blkg. */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, 0);
+		if (cur == old) {
+			atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+			break;
+		}
+		old = cur;
+	}
+}
+
+void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
+void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
+void blkcg_maybe_throttle_current(void);
 #else	/* CONFIG_BLK_CGROUP */
 
 struct blkcg {
@@ -734,9 +867,16 @@ struct blkcg_policy {
 
 #define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
 
+static inline void blkcg_maybe_throttle_current(void) { }
+static inline bool blk_cgroup_congested(void) { return false; }
+
 #ifdef CONFIG_BLOCK
 
+static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
+
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{ return NULL; }
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }
 static inline void blkcg_exit_queue(struct request_queue *q) { }
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ca3f2c2edd85..1da59c16f637 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -35,10 +35,12 @@ struct blk_mq_hw_ctx {
 	struct sbitmap		ctx_map;
 
 	struct blk_mq_ctx	*dispatch_from;
+	unsigned int		dispatch_busy;
 
-	struct blk_mq_ctx	**ctxs;
 	unsigned int		nr_ctx;
+	struct blk_mq_ctx	**ctxs;
 
+	spinlock_t		dispatch_wait_lock;
 	wait_queue_entry_t	dispatch_wait;
 	atomic_t		wait_index;
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 3c4f390aea4b..f6dfb30737d8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -179,11 +179,9 @@ struct bio {
 	 */
 	struct io_context	*bi_ioc;
 	struct cgroup_subsys_state *bi_css;
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	void			*bi_cg_private;
+	struct blkcg_gq		*bi_blkg;
 	struct bio_issue	bi_issue;
 #endif
-#endif
 	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 		struct bio_integrity_payload *bi_integrity; /* data integrity */
@@ -329,7 +327,7 @@ enum req_flag_bits {
 
 	/* for driver use */
 	__REQ_DRV,
-
+	__REQ_SWAP,		/* swapping request. */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -351,6 +349,7 @@ enum req_flag_bits {
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
 
 #define REQ_DRV			(1ULL << __REQ_DRV)
+#define REQ_SWAP		(1ULL << __REQ_SWAP)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
@@ -358,6 +357,14 @@ enum req_flag_bits {
 #define REQ_NOMERGE_FLAGS \
 	(REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA)
 
+enum stat_group {
+	STAT_READ,
+	STAT_WRITE,
+	STAT_DISCARD,
+
+	NR_STAT_GROUPS
+};
+
 #define bio_op(bio) \
 	((bio)->bi_opf & REQ_OP_MASK)
 #define req_op(req) \
@@ -395,6 +402,18 @@ static inline bool op_is_sync(unsigned int op)
 		(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
 }
 
+static inline bool op_is_discard(unsigned int op)
+{
+	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
+}
+
+static inline int op_stat_group(unsigned int op)
+{
+	if (op_is_discard(op))
+		return STAT_DISCARD;
+	return op_is_write(op);
+}
+
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE		-1U
 #define BLK_QC_T_SHIFT		16
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 79226ca8f80f..d6869e0e2b64 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -27,8 +27,6 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
-#include <linux/seqlock.h>
-#include <linux/u64_stats_sync.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -42,7 +40,7 @@ struct bsg_job;
 struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
-struct rq_wb;
+struct rq_qos;
 struct blk_queue_stats;
 struct blk_stat_callback;
 
@@ -442,10 +440,8 @@ struct request_queue {
 	int			nr_rqs[2];	/* # allocated [a]sync rqs */
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
-	atomic_t		shared_hctx_restart;
-
 	struct blk_queue_stats	*stats;
-	struct rq_wb		*rq_wb;
+	struct rq_qos		*rq_qos;
 
 	/*
 	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg
@@ -592,6 +588,7 @@ struct request_queue {
 
 	struct queue_limits	limits;
 
+#ifdef CONFIG_BLK_DEV_ZONED
 	/*
 	 * Zoned block device information for request dispatch control.
 	 * nr_zones is the total number of zones of the device. This is always
@@ -612,6 +609,7 @@ struct request_queue {
 	unsigned int		nr_zones;
 	unsigned long		*seq_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
 	 * sg stuff
@@ -800,11 +798,7 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
-static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
-{
-	return q->nr_zones;
-}
-
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 					     sector_t sector)
 {
@@ -820,6 +814,7 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return false;
 	return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap);
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
 {
@@ -1070,6 +1065,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_rq_zone_no(struct request *rq)
 {
 	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
@@ -1079,6 +1075,7 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
 {
 	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 /*
  * Some commands like WRITE SAME have a payload or data transfer size which
@@ -1437,8 +1434,6 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
-
 static inline unsigned long queue_segment_boundary(struct request_queue *q)
 {
 	return q->limits.seg_boundary_mask;
@@ -1639,15 +1634,6 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
 	return 0;
 }
 
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return blk_queue_nr_zones(q);
-	return 0;
-}
-
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
@@ -1877,6 +1863,28 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 				bip_next->bip_vec[0].bv_offset);
 }
 
+/**
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
+ * @bi:		blk_integrity profile for device
+ * @sectors:	Size of the bio in 512-byte sectors
+ *
+ * Description: The block layer calculates everything in 512 byte
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device.  Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
+ */
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return sectors >> (bi->interval_exp - 9);
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct bio;
@@ -1950,12 +1958,24 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 	return false;
 }
 
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return 0;
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return 0;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
-	int (*rw_page)(struct block_device *, sector_t, struct page *, bool);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index e75dfd1f1dec..528271c60018 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -13,6 +13,7 @@
 
 #include <linux/fs.h>		/* not really needed, later.. */
 #include <linux/list.h>
+#include <scsi/scsi_common.h>
 #include <uapi/linux/cdrom.h>
 
 struct packet_command
@@ -21,7 +22,7 @@ struct packet_command
 	unsigned char 		*buffer;
 	unsigned int 		buflen;
 	int			stat;
-	struct request_sense	*sense;
+	struct scsi_sense_hdr	*sshdr;
 	unsigned char		data_direction;
 	int			quiet;
 	int			timeout;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index c0e68f903011..ff20b677fb9f 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -438,6 +438,9 @@ struct cgroup {
 	/* used to store eBPF programs */
 	struct cgroup_bpf bpf;
 
+	/* If there is block congestion on this cgroup. */
+	atomic_t congestion_count;
+
 	/* ids of the ancestors at each level including self */
 	int ancestor_ids[];
 };
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 7dff1963c185..308918928767 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -194,6 +194,9 @@ extern void clocksource_suspend(void);
 extern void clocksource_resume(void);
 extern struct clocksource * __init clocksource_default_clock(void);
 extern void clocksource_mark_unstable(struct clocksource *cs);
+extern void
+clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles);
+extern u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 now);
 
 extern u64
 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles);
diff --git a/include/linux/compat.h b/include/linux/compat.h
index c68acc47da57..df45ee8413d6 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -115,11 +115,6 @@ typedef	compat_ulong_t		compat_aio_context_t;
 struct compat_sel_arg_struct;
 struct rusage;
 
-struct compat_itimerspec {
-	struct compat_timespec it_interval;
-	struct compat_timespec it_value;
-};
-
 struct compat_utimbuf {
 	compat_time_t		actime;
 	compat_time_t		modtime;
@@ -300,10 +295,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *);
 extern int compat_put_timespec(const struct timespec *, void __user *);
 extern int compat_get_timeval(struct timeval *, const void __user *);
 extern int compat_put_timeval(const struct timeval *, void __user *);
-extern int get_compat_itimerspec64(struct itimerspec64 *its,
-			const struct compat_itimerspec __user *uits);
-extern int put_compat_itimerspec64(const struct itimerspec64 *its,
-			struct compat_itimerspec __user *uits);
 
 struct compat_iovec {
 	compat_uptr_t	iov_base;
diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h
index 31f2774f1994..e70bfd1d2c3f 100644
--- a/include/linux/compat_time.h
+++ b/include/linux/compat_time.h
@@ -17,7 +17,16 @@ struct compat_timeval {
 	s32		tv_usec;
 };
 
+struct compat_itimerspec {
+	struct compat_timespec it_interval;
+	struct compat_timespec it_value;
+};
+
 extern int compat_get_timespec64(struct timespec64 *, const void __user *);
 extern int compat_put_timespec64(const struct timespec64 *, void __user *);
+extern int get_compat_itimerspec64(struct itimerspec64 *its,
+			const struct compat_itimerspec __user *uits);
+extern int put_compat_itimerspec64(const struct itimerspec64 *its,
+			struct compat_itimerspec __user *uits);
 
 #endif /* _LINUX_COMPAT_TIME_H */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index a97a63eef59f..45789a892c41 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -30,7 +30,7 @@ struct cpu {
 };
 
 extern void boot_cpu_init(void);
-extern void boot_cpu_state_init(void);
+extern void boot_cpu_hotplug_init(void);
 extern void cpu_init(void);
 extern void trap_init(void);
 
@@ -55,6 +55,8 @@ extern ssize_t cpu_show_spectre_v2(struct device *dev,
 				   struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_spec_store_bypass(struct device *dev,
 					  struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_l1tf(struct device *dev,
+			     struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
@@ -166,4 +168,23 @@ void cpuhp_report_idle_dead(void);
 static inline void cpuhp_report_idle_dead(void) { }
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
+enum cpuhp_smt_control {
+	CPU_SMT_ENABLED,
+	CPU_SMT_DISABLED,
+	CPU_SMT_FORCE_DISABLED,
+	CPU_SMT_NOT_SUPPORTED,
+};
+
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
+extern enum cpuhp_smt_control cpu_smt_control;
+extern void cpu_smt_disable(bool force);
+extern void cpu_smt_check_topology_early(void);
+extern void cpu_smt_check_topology(void);
+#else
+# define cpu_smt_control		(CPU_SMT_ENABLED)
+static inline void cpu_smt_disable(bool force) { }
+static inline void cpu_smt_check_topology_early(void) { }
+static inline void cpu_smt_check_topology(void) { }
+#endif
+
 #endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 8796ba387152..4cf06a64bc02 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -164,6 +164,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
+	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 66c6e17e61e5..d32957b423d5 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -227,7 +227,6 @@ extern void d_instantiate(struct dentry *, struct inode *);
 extern void d_instantiate_new(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
-extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
 extern void d_delete(struct dentry *);
@@ -271,8 +270,6 @@ extern void d_rehash(struct dentry *);
  
 extern void d_add(struct dentry *, struct inode *);
 
-extern void dentry_update_name_case(struct dentry *, const struct qstr *);
-
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
 extern void d_exchange(struct dentry *, struct dentry *);
diff --git a/include/linux/device.h b/include/linux/device.h
index 055a69dbcd18..6d3b000be57e 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -886,6 +886,8 @@ struct dev_links_info {
  * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all
  * 		hardware supports 64-bit addresses for consistent allocations
  * 		such descriptors.
+ * @bus_dma_mask: Mask of an upstream bridge or bus which imposes a smaller DMA
+ *		limit than the device itself supports.
  * @dma_pfn_offset: offset of DMA memory range relatively of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
@@ -912,8 +914,6 @@ struct dev_links_info {
  * @offline:	Set after successful invocation of bus type's .offline().
  * @of_node_reused: Set if the device-tree node is shared with an ancestor
  *              device.
- * @dma_32bit_limit: bridge limited to 32bit DMA even if the device itself
- *		indicates support for a higher limit in the dma_mask field.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -967,6 +967,7 @@ struct device {
 					     not all hardware supports
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
+	u64		bus_dma_mask;	/* upstream dma_mask constraint */
 	unsigned long	dma_pfn_offset;
 
 	struct device_dma_parameters *dma_parms;
@@ -1002,7 +1003,6 @@ struct device {
 	bool			offline_disabled:1;
 	bool			offline:1;
 	bool			of_node_reused:1;
-	bool			dma_32bit_limit:1;
 };
 
 static inline struct device *kobj_to_dev(struct kobject *kobj)
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index f9cc309507d9..1db6a6b46d0d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -538,10 +538,17 @@ static inline void dma_free_attrs(struct device *dev, size_t size,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!ops);
-	WARN_ON(irqs_disabled());
 
 	if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr))
 		return;
+	/*
+	 * On non-coherent platforms which implement DMA-coherent buffers via
+	 * non-cacheable remaps, ops->free() may call vunmap(). Thus getting
+	 * this far in IRQ context is a) at risk of a BUG_ON() or trying to
+	 * sleep on some machines, and b) an indication that the driver is
+	 * probably misusing the coherent API anyway.
+	 */
+	WARN_ON(irqs_disabled());
 
 	if (!ops->free || !cpu_addr)
 		return;
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 10b2654d549b..a0aa00cc909d 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -44,4 +44,12 @@ static inline void arch_sync_dma_for_cpu(struct device *dev,
 }
 #endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
 
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+void arch_sync_dma_for_cpu_all(struct device *dev);
+#else
+static inline void arch_sync_dma_for_cpu_all(struct device *dev)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
+
 #endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 56add823f190..401e4b254e30 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -894,6 +894,16 @@ typedef struct _efi_file_handle {
 	void *flush;
 } efi_file_handle_t;
 
+typedef struct {
+	u64 revision;
+	u32 open_volume;
+} efi_file_io_interface_32_t;
+
+typedef struct {
+	u64 revision;
+	u64 open_volume;
+} efi_file_io_interface_64_t;
+
 typedef struct _efi_file_io_interface {
 	u64 revision;
 	int (*open_volume)(struct _efi_file_io_interface *,
@@ -988,14 +998,12 @@ extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg);
 extern void efi_gettimeofday (struct timespec64 *ts);
 extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if possible */
 #ifdef CONFIG_X86
-extern void efi_late_init(void);
 extern void efi_free_boot_services(void);
 extern efi_status_t efi_query_variable_store(u32 attributes,
 					     unsigned long size,
 					     bool nonblocking);
 extern void efi_find_mirror(void);
 #else
-static inline void efi_late_init(void) {}
 static inline void efi_free_boot_services(void) {}
 
 static inline efi_status_t efi_query_variable_store(u32 attributes,
@@ -1651,4 +1659,7 @@ struct linux_efi_tpm_eventlog {
 
 extern int efi_tpm_eventlog_init(void);
 
+/* Workqueue to queue EFI Runtime Services */
+extern struct workqueue_struct *efi_rts_wq;
+
 #endif /* _LINUX_EFI_H */
diff --git a/include/linux/file.h b/include/linux/file.h
index 279720db984a..6b2fb032416c 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -17,9 +17,12 @@ extern void fput(struct file *);
 struct file_operations;
 struct vfsmount;
 struct dentry;
+struct inode;
 struct path;
-extern struct file *alloc_file(const struct path *, fmode_t mode,
-	const struct file_operations *fop);
+extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
+	const char *, int flags, const struct file_operations *);
+extern struct file *alloc_file_clone(struct file *, int flags,
+	const struct file_operations *);
 
 static inline void fput_light(struct file *file, int fput_needed)
 {
@@ -78,7 +81,6 @@ extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);
 extern int replace_fd(unsigned fd, struct file *file, unsigned flags);
 extern void set_close_on_exec(unsigned int fd, int flag);
 extern bool get_close_on_exec(unsigned int fd);
-extern void put_filp(struct file *);
 extern int get_unused_fd_flags(unsigned flags);
 extern void put_unused_fd(unsigned int fd);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 805bf22898cf..1ec33fd0423f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -148,6 +148,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* Has write method(s) */
 #define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
 
+#define FMODE_OPENED		((__force fmode_t)0x80000)
+#define FMODE_CREATED		((__force fmode_t)0x100000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
@@ -275,6 +278,7 @@ struct writeback_control;
 
 /*
  * Write life time hint values.
+ * Stored in struct inode as u8.
  */
 enum rw_hint {
 	WRITE_LIFE_NOT_SET	= 0,
@@ -609,8 +613,8 @@ struct inode {
 	struct timespec64	i_ctime;
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
-	unsigned int		i_blkbits;
-	enum rw_hint		i_write_hint;
+	u8			i_blkbits;
+	u8			i_write_hint;
 	blkcnt_t		i_blocks;
 
 #ifdef __NEED_I_SIZE_ORDERED
@@ -685,6 +689,17 @@ static inline int inode_unhashed(struct inode *inode)
 }
 
 /*
+ * __mark_inode_dirty expects inodes to be hashed.  Since we don't
+ * want special inodes in the fileset inode space, we make them
+ * appear hashed, but do not put on any lists.  hlist_del()
+ * will work fine and require no locking.
+ */
+static inline void inode_fake_hash(struct inode *inode)
+{
+	hlist_add_fake(&inode->i_hash);
+}
+
+/*
  * inode->i_mutex nesting subclasses for the lock validator:
  *
  * 0: the object of the current VFS operation
@@ -1776,7 +1791,7 @@ struct inode_operations {
 	int (*update_time)(struct inode *, struct timespec64 *, int);
 	int (*atomic_open)(struct inode *, struct dentry *,
 			   struct file *, unsigned open_flag,
-			   umode_t create_mode, int *opened);
+			   umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
 } ____cacheline_aligned;
@@ -2014,6 +2029,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
  * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
  *			and work dirs among overlayfs mounts.
  *
+ * I_CREATING		New object's inode in the middle of setting up.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -2034,7 +2051,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 #define __I_DIRTY_TIME_EXPIRED	12
 #define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
 #define I_WB_SWITCH		(1 << 13)
-#define I_OVL_INUSE			(1 << 14)
+#define I_OVL_INUSE		(1 << 14)
+#define I_CREATING		(1 << 15)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
@@ -2420,7 +2438,10 @@ extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int, umode_t);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
-extern struct file *filp_clone_open(struct file *);
+static inline struct file *file_clone_open(struct file *file)
+{
+	return dentry_open(&file->f_path, file->f_flags, file->f_cred);
+}
 extern int filp_close(struct file *, fl_owner_t id);
 
 extern struct filename *getname_flags(const char __user *, int, int *);
@@ -2428,13 +2449,8 @@ extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 extern void putname(struct filename *name);
 
-enum {
-	FILE_CREATED = 1,
-	FILE_OPENED = 2
-};
 extern int finish_open(struct file *file, struct dentry *dentry,
-			int (*open)(struct inode *, struct file *),
-			int *opened);
+			int (*open)(struct inode *, struct file *));
 extern int finish_no_open(struct file *file, struct dentry *dentry);
 
 /* fs/ioctl.c */
@@ -2622,8 +2638,6 @@ static inline int filemap_fdatawait(struct address_space *mapping)
 
 extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
 				  loff_t lend);
-extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
-						loff_t lend);
 extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
@@ -2918,6 +2932,7 @@ extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
 static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
 #endif
 extern void unlock_new_inode(struct inode *);
+extern void discard_new_inode(struct inode *);
 extern unsigned int get_next_ino(void);
 extern void evict_inodes(struct super_block *sb);
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 6cb8a5789668..57864422a2c8 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/percpu-refcount.h>
 #include <linux/uuid.h>
+#include <linux/blk_types.h>
 
 #ifdef CONFIG_BLOCK
 
@@ -82,10 +83,10 @@ struct partition {
 } __attribute__((packed));
 
 struct disk_stats {
-	unsigned long sectors[2];	/* READs and WRITEs */
-	unsigned long ios[2];
-	unsigned long merges[2];
-	unsigned long ticks[2];
+	unsigned long sectors[NR_STAT_GROUPS];
+	unsigned long ios[NR_STAT_GROUPS];
+	unsigned long merges[NR_STAT_GROUPS];
+	unsigned long ticks[NR_STAT_GROUPS];
 	unsigned long io_ticks;
 	unsigned long time_in_queue;
 };
@@ -353,6 +354,11 @@ static inline void free_part_stats(struct hd_struct *part)
 
 #endif /* CONFIG_SMP */
 
+#define part_stat_read_accum(part, field)				\
+	(part_stat_read(part, field[STAT_READ]) +			\
+	 part_stat_read(part, field[STAT_WRITE]) +			\
+	 part_stat_read(part, field[STAT_DISCARD]))
+
 #define part_stat_add(cpu, part, field, addnd)	do {			\
 	__part_stat_add((cpu), (part), field, addnd);			\
 	if ((part)->partno)						\
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 0e4647e0eb60..d9ba3fc363b7 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -16,7 +16,7 @@ struct linux_binprm;
 
 #ifdef CONFIG_IMA
 extern int ima_bprm_check(struct linux_binprm *bprm);
-extern int ima_file_check(struct file *file, int mask, int opened);
+extern int ima_file_check(struct file *file, int mask);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
 extern int ima_read_file(struct file *file, enum kernel_read_file_id id);
@@ -34,7 +34,7 @@ static inline int ima_bprm_check(struct linux_binprm *bprm)
 	return 0;
 }
 
-static inline int ima_file_check(struct file *file, int mask, int opened)
+static inline int ima_file_check(struct file *file, int mask)
 {
 	return 0;
 }
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index a044a824da85..3555d54bf79a 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -2,6 +2,9 @@
 #ifndef LINUX_IOMAP_H
 #define LINUX_IOMAP_H 1
 
+#include <linux/atomic.h>
+#include <linux/bitmap.h>
+#include <linux/mm.h>
 #include <linux/types.h>
 
 struct address_space;
@@ -9,6 +12,7 @@ struct fiemap_extent_info;
 struct inode;
 struct iov_iter;
 struct kiocb;
+struct page;
 struct vm_area_struct;
 struct vm_fault;
 
@@ -29,6 +33,7 @@ struct vm_fault;
  */
 #define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
 #define IOMAP_F_DIRTY		0x02	/* uncommitted metadata */
+#define IOMAP_F_BUFFER_HEAD	0x04	/* file system requires buffer heads */
 
 /*
  * Flags that only need to be reported for IOMAP_REPORT requests:
@@ -55,6 +60,16 @@ struct iomap {
 	u16			flags;	/* flags for mapping */
 	struct block_device	*bdev;	/* block device for I/O */
 	struct dax_device	*dax_dev; /* dax_dev for dax operations */
+	void			*inline_data;
+	void			*private; /* filesystem private */
+
+	/*
+	 * Called when finished processing a page in the mapping returned in
+	 * this iomap.  At least for now this is only supported in the buffered
+	 * write path.
+	 */
+	void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
+			struct page *page, struct iomap *iomap);
 };
 
 /*
@@ -86,8 +101,40 @@ struct iomap_ops {
 			ssize_t written, unsigned flags, struct iomap *iomap);
 };
 
+/*
+ * Structure allocate for each page when block size < PAGE_SIZE to track
+ * sub-page uptodate status and I/O completions.
+ */
+struct iomap_page {
+	atomic_t		read_count;
+	atomic_t		write_count;
+	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
+};
+
+static inline struct iomap_page *to_iomap_page(struct page *page)
+{
+	if (page_has_private(page))
+		return (struct iomap_page *)page_private(page);
+	return NULL;
+}
+
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
+int iomap_readpage(struct page *page, const struct iomap_ops *ops);
+int iomap_readpages(struct address_space *mapping, struct list_head *pages,
+		unsigned nr_pages, const struct iomap_ops *ops);
+int iomap_set_page_dirty(struct page *page);
+int iomap_is_partially_uptodate(struct page *page, unsigned long from,
+		unsigned long count);
+int iomap_releasepage(struct page *page, gfp_t gfp_mask);
+void iomap_invalidatepage(struct page *page, unsigned int offset,
+		unsigned int len);
+#ifdef CONFIG_MIGRATION
+int iomap_migrate_page(struct address_space *mapping, struct page *newpage,
+		struct page *page, enum migrate_mode mode);
+#else
+#define iomap_migrate_page NULL
+#endif
 int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index cbb872c1b607..9d2ea3e907d0 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -73,6 +73,7 @@
 #define GICD_TYPER_MBIS			(1U << 16)
 
 #define GICD_TYPER_ID_BITS(typer)	((((typer) >> 19) & 0x1f) + 1)
+#define GICD_TYPER_NUM_LPIS(typer)	((((typer) >> 11) & 0x1f) + 1)
 #define GICD_TYPER_IRQS(typer)		((((typer) & 0x1f) + 1) * 32)
 
 #define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
@@ -576,8 +577,8 @@ struct rdists {
 		phys_addr_t	phys_base;
 	} __percpu		*rdist;
 	struct page		*prop_page;
-	int			id_bits;
 	u64			flags;
+	u32			gicd_typer;
 	bool			has_vlpis;
 	bool			has_direct_lpi;
 };
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 9440a2fc8893..e909413e4e38 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -63,7 +63,6 @@ struct pt_regs;
 struct kretprobe;
 struct kretprobe_instance;
 typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *);
-typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *);
 typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *,
 				       unsigned long flags);
 typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *,
@@ -101,12 +100,6 @@ struct kprobe {
 	 */
 	kprobe_fault_handler_t fault_handler;
 
-	/*
-	 * ... called if breakpoint trap occurs in probe handler.
-	 * Return 1 if it handled break, otherwise kernel will see it.
-	 */
-	kprobe_break_handler_t break_handler;
-
 	/* Saved opcode (which has been replaced with breakpoint) */
 	kprobe_opcode_t opcode;
 
@@ -155,24 +148,6 @@ static inline int kprobe_ftrace(struct kprobe *p)
 }
 
 /*
- * Special probe type that uses setjmp-longjmp type tricks to resume
- * execution at a specified entry with a matching prototype corresponding
- * to the probed function - a trick to enable arguments to become
- * accessible seamlessly by probe handling logic.
- * Note:
- * Because of the way compilers allocate stack space for local variables
- * etc upfront, regardless of sub-scopes within a function, this mirroring
- * principle currently works only for probes placed on function entry points.
- */
-struct jprobe {
-	struct kprobe kp;
-	void *entry;	/* probe handling code to jump to */
-};
-
-/* For backward compatibility with old code using JPROBE_ENTRY() */
-#define JPROBE_ENTRY(handler)	(handler)
-
-/*
  * Function-return probe -
  * Note:
  * User needs to provide a handler function, and initialize maxactive.
@@ -389,9 +364,6 @@ int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
 int register_kprobes(struct kprobe **kps, int num);
 void unregister_kprobes(struct kprobe **kps, int num);
-int setjmp_pre_handler(struct kprobe *, struct pt_regs *);
-int longjmp_break_handler(struct kprobe *, struct pt_regs *);
-void jprobe_return(void);
 unsigned long arch_deref_entry_point(void *);
 
 int register_kretprobe(struct kretprobe *rp);
@@ -439,9 +411,6 @@ static inline void unregister_kprobe(struct kprobe *p)
 static inline void unregister_kprobes(struct kprobe **kps, int num)
 {
 }
-static inline void jprobe_return(void)
-{
-}
 static inline int register_kretprobe(struct kretprobe *rp)
 {
 	return -ENOSYS;
@@ -468,20 +437,6 @@ static inline int enable_kprobe(struct kprobe *kp)
 	return -ENOSYS;
 }
 #endif /* CONFIG_KPROBES */
-static inline int register_jprobe(struct jprobe *p)
-{
-	return -ENOSYS;
-}
-static inline int register_jprobes(struct jprobe **jps, int num)
-{
-	return -ENOSYS;
-}
-static inline void unregister_jprobe(struct jprobe *p)
-{
-}
-static inline void unregister_jprobes(struct jprobe **jps, int num)
-{
-}
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
 	return disable_kprobe(&rp->kp);
@@ -490,14 +445,6 @@ static inline int enable_kretprobe(struct kretprobe *rp)
 {
 	return enable_kprobe(&rp->kp);
 }
-static inline int disable_jprobe(struct jprobe *jp)
-{
-	return -ENOSYS;
-}
-static inline int enable_jprobe(struct jprobe *jp)
-{
-	return -ENOSYS;
-}
 
 #ifndef CONFIG_KPROBES
 static inline bool is_kprobe_insn_slot(unsigned long addr)
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 5b9fddbaac41..b2bb44f87f5a 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -93,8 +93,11 @@ static inline ktime_t timeval_to_ktime(struct timeval tv)
 /* Map the ktime_t to timeval conversion to ns_to_timeval function */
 #define ktime_to_timeval(kt)		ns_to_timeval((kt))
 
-/* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */
-#define ktime_to_ns(kt)			(kt)
+/* Convert ktime_t to nanoseconds */
+static inline s64 ktime_to_ns(const ktime_t kt)
+{
+	return kt;
+}
 
 /**
  * ktime_compare - Compares two ktime_t variables for less, greater or equal
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 8f1131c8dd54..a8ee106b865d 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1569,7 +1569,7 @@ union security_list_options {
 	int (*file_send_sigiotask)(struct task_struct *tsk,
 					struct fown_struct *fown, int sig);
 	int (*file_receive)(struct file *file);
-	int (*file_open)(struct file *file, const struct cred *cred);
+	int (*file_open)(struct file *file);
 
 	int (*task_alloc)(struct task_struct *task, unsigned long clone_flags);
 	void (*task_free)(struct task_struct *task);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6c6fb116e925..680d3395fc83 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -317,6 +317,9 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
 			  bool compound);
+int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
+			  bool compound);
 void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
 			      bool lrucare, bool compound);
 void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
@@ -789,6 +792,16 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 	return 0;
 }
 
+static inline int mem_cgroup_try_charge_delay(struct page *page,
+					      struct mm_struct *mm,
+					      gfp_t gfp_mask,
+					      struct mem_cgroup **memcgp,
+					      bool compound)
+{
+	*memcgp = NULL;
+	return 0;
+}
+
 static inline void mem_cgroup_commit_charge(struct page *page,
 					    struct mem_cgroup *memcg,
 					    bool lrucare, bool compound)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 99ce070e7dcb..efdc24dd9e97 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -335,176 +335,183 @@ struct core_state {
 
 struct kioctx_table;
 struct mm_struct {
-	struct vm_area_struct *mmap;		/* list of VMAs */
-	struct rb_root mm_rb;
-	u32 vmacache_seqnum;                   /* per-thread vmacache */
+	struct {
+		struct vm_area_struct *mmap;		/* list of VMAs */
+		struct rb_root mm_rb;
+		u32 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
-	unsigned long (*get_unmapped_area) (struct file *filp,
+		unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
 				unsigned long pgoff, unsigned long flags);
 #endif
-	unsigned long mmap_base;		/* base of mmap area */
-	unsigned long mmap_legacy_base;         /* base of mmap area in bottom-up allocations */
+		unsigned long mmap_base;	/* base of mmap area */
+		unsigned long mmap_legacy_base;	/* base of mmap area in bottom-up allocations */
 #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
-	/* Base adresses for compatible mmap() */
-	unsigned long mmap_compat_base;
-	unsigned long mmap_compat_legacy_base;
+		/* Base adresses for compatible mmap() */
+		unsigned long mmap_compat_base;
+		unsigned long mmap_compat_legacy_base;
 #endif
-	unsigned long task_size;		/* size of task vm space */
-	unsigned long highest_vm_end;		/* highest vma end address */
-	pgd_t * pgd;
-
-	/**
-	 * @mm_users: The number of users including userspace.
-	 *
-	 * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops
-	 * to 0 (i.e. when the task exits and there are no other temporary
-	 * reference holders), we also release a reference on @mm_count
-	 * (which may then free the &struct mm_struct if @mm_count also
-	 * drops to 0).
-	 */
-	atomic_t mm_users;
-
-	/**
-	 * @mm_count: The number of references to &struct mm_struct
-	 * (@mm_users count as 1).
-	 *
-	 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
-	 * &struct mm_struct is freed.
-	 */
-	atomic_t mm_count;
+		unsigned long task_size;	/* size of task vm space */
+		unsigned long highest_vm_end;	/* highest vma end address */
+		pgd_t * pgd;
+
+		/**
+		 * @mm_users: The number of users including userspace.
+		 *
+		 * Use mmget()/mmget_not_zero()/mmput() to modify. When this
+		 * drops to 0 (i.e. when the task exits and there are no other
+		 * temporary reference holders), we also release a reference on
+		 * @mm_count (which may then free the &struct mm_struct if
+		 * @mm_count also drops to 0).
+		 */
+		atomic_t mm_users;
+
+		/**
+		 * @mm_count: The number of references to &struct mm_struct
+		 * (@mm_users count as 1).
+		 *
+		 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
+		 * &struct mm_struct is freed.
+		 */
+		atomic_t mm_count;
 
 #ifdef CONFIG_MMU
-	atomic_long_t pgtables_bytes;		/* PTE page table pages */
+		atomic_long_t pgtables_bytes;	/* PTE page table pages */
 #endif
-	int map_count;				/* number of VMAs */
+		int map_count;			/* number of VMAs */
 
-	spinlock_t page_table_lock;		/* Protects page tables and some counters */
-	struct rw_semaphore mmap_sem;
+		spinlock_t page_table_lock; /* Protects page tables and some
+					     * counters
+					     */
+		struct rw_semaphore mmap_sem;
 
-	struct list_head mmlist;		/* List of maybe swapped mm's.	These are globally strung
-						 * together off init_mm.mmlist, and are protected
-						 * by mmlist_lock
-						 */
+		struct list_head mmlist; /* List of maybe swapped mm's.	These
+					  * are globally strung together off
+					  * init_mm.mmlist, and are protected
+					  * by mmlist_lock
+					  */
 
 
-	unsigned long hiwater_rss;	/* High-watermark of RSS usage */
-	unsigned long hiwater_vm;	/* High-water virtual memory usage */
+		unsigned long hiwater_rss; /* High-watermark of RSS usage */
+		unsigned long hiwater_vm;  /* High-water virtual memory usage */
 
-	unsigned long total_vm;		/* Total pages mapped */
-	unsigned long locked_vm;	/* Pages that have PG_mlocked set */
-	unsigned long pinned_vm;	/* Refcount permanently increased */
-	unsigned long data_vm;		/* VM_WRITE & ~VM_SHARED & ~VM_STACK */
-	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE & ~VM_STACK */
-	unsigned long stack_vm;		/* VM_STACK */
-	unsigned long def_flags;
+		unsigned long total_vm;	   /* Total pages mapped */
+		unsigned long locked_vm;   /* Pages that have PG_mlocked set */
+		unsigned long pinned_vm;   /* Refcount permanently increased */
+		unsigned long data_vm;	   /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
+		unsigned long exec_vm;	   /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
+		unsigned long stack_vm;	   /* VM_STACK */
+		unsigned long def_flags;
 
-	spinlock_t arg_lock; /* protect the below fields */
-	unsigned long start_code, end_code, start_data, end_data;
-	unsigned long start_brk, brk, start_stack;
-	unsigned long arg_start, arg_end, env_start, env_end;
+		spinlock_t arg_lock; /* protect the below fields */
+		unsigned long start_code, end_code, start_data, end_data;
+		unsigned long start_brk, brk, start_stack;
+		unsigned long arg_start, arg_end, env_start, env_end;
 
-	unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
+		unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
 
-	/*
-	 * Special counters, in some configurations protected by the
-	 * page_table_lock, in other configurations by being atomic.
-	 */
-	struct mm_rss_stat rss_stat;
-
-	struct linux_binfmt *binfmt;
+		/*
+		 * Special counters, in some configurations protected by the
+		 * page_table_lock, in other configurations by being atomic.
+		 */
+		struct mm_rss_stat rss_stat;
 
-	cpumask_var_t cpu_vm_mask_var;
+		struct linux_binfmt *binfmt;
 
-	/* Architecture-specific MM context */
-	mm_context_t context;
+		/* Architecture-specific MM context */
+		mm_context_t context;
 
-	unsigned long flags; /* Must use atomic bitops to access the bits */
+		unsigned long flags; /* Must use atomic bitops to access */
 
-	struct core_state *core_state; /* coredumping support */
+		struct core_state *core_state; /* coredumping support */
 #ifdef CONFIG_MEMBARRIER
-	atomic_t membarrier_state;
+		atomic_t membarrier_state;
 #endif
 #ifdef CONFIG_AIO
-	spinlock_t			ioctx_lock;
-	struct kioctx_table __rcu	*ioctx_table;
+		spinlock_t			ioctx_lock;
+		struct kioctx_table __rcu	*ioctx_table;
 #endif
 #ifdef CONFIG_MEMCG
-	/*
-	 * "owner" points to a task that is regarded as the canonical
-	 * user/owner of this mm. All of the following must be true in
-	 * order for it to be changed:
-	 *
-	 * current == mm->owner
-	 * current->mm != mm
-	 * new_owner->mm == mm
-	 * new_owner->alloc_lock is held
-	 */
-	struct task_struct __rcu *owner;
+		/*
+		 * "owner" points to a task that is regarded as the canonical
+		 * user/owner of this mm. All of the following must be true in
+		 * order for it to be changed:
+		 *
+		 * current == mm->owner
+		 * current->mm != mm
+		 * new_owner->mm == mm
+		 * new_owner->alloc_lock is held
+		 */
+		struct task_struct __rcu *owner;
 #endif
-	struct user_namespace *user_ns;
+		struct user_namespace *user_ns;
 
-	/* store ref to file /proc/<pid>/exe symlink points to */
-	struct file __rcu *exe_file;
+		/* store ref to file /proc/<pid>/exe symlink points to */
+		struct file __rcu *exe_file;
 #ifdef CONFIG_MMU_NOTIFIER
-	struct mmu_notifier_mm *mmu_notifier_mm;
+		struct mmu_notifier_mm *mmu_notifier_mm;
 #endif
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
-	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
-#endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	struct cpumask cpumask_allocation;
+		pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
 #ifdef CONFIG_NUMA_BALANCING
-	/*
-	 * numa_next_scan is the next time that the PTEs will be marked
-	 * pte_numa. NUMA hinting faults will gather statistics and migrate
-	 * pages to new nodes if necessary.
-	 */
-	unsigned long numa_next_scan;
+		/*
+		 * numa_next_scan is the next time that the PTEs will be marked
+		 * pte_numa. NUMA hinting faults will gather statistics and
+		 * migrate pages to new nodes if necessary.
+		 */
+		unsigned long numa_next_scan;
 
-	/* Restart point for scanning and setting pte_numa */
-	unsigned long numa_scan_offset;
+		/* Restart point for scanning and setting pte_numa */
+		unsigned long numa_scan_offset;
 
-	/* numa_scan_seq prevents two threads setting pte_numa */
-	int numa_scan_seq;
+		/* numa_scan_seq prevents two threads setting pte_numa */
+		int numa_scan_seq;
 #endif
-	/*
-	 * An operation with batched TLB flushing is going on. Anything that
-	 * can move process memory needs to flush the TLB when moving a
-	 * PROT_NONE or PROT_NUMA mapped page.
-	 */
-	atomic_t tlb_flush_pending;
+		/*
+		 * An operation with batched TLB flushing is going on. Anything
+		 * that can move process memory needs to flush the TLB when
+		 * moving a PROT_NONE or PROT_NUMA mapped page.
+		 */
+		atomic_t tlb_flush_pending;
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
-	/* See flush_tlb_batched_pending() */
-	bool tlb_flush_batched;
+		/* See flush_tlb_batched_pending() */
+		bool tlb_flush_batched;
 #endif
-	struct uprobes_state uprobes_state;
+		struct uprobes_state uprobes_state;
 #ifdef CONFIG_HUGETLB_PAGE
-	atomic_long_t hugetlb_usage;
+		atomic_long_t hugetlb_usage;
 #endif
-	struct work_struct async_put_work;
+		struct work_struct async_put_work;
 
 #if IS_ENABLED(CONFIG_HMM)
-	/* HMM needs to track a few things per mm */
-	struct hmm *hmm;
+		/* HMM needs to track a few things per mm */
+		struct hmm *hmm;
 #endif
-} __randomize_layout;
+	} __randomize_layout;
+
+	/*
+	 * The mm_cpumask needs to be at the end of mm_struct, because it
+	 * is dynamically sized based on nr_cpu_ids.
+	 */
+	unsigned long cpu_bitmap[];
+};
 
 extern struct mm_struct init_mm;
 
+/* Pointer magic because the dynamic array size confuses some compilers. */
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	mm->cpu_vm_mask_var = &mm->cpumask_allocation;
-#endif
-	cpumask_clear(mm->cpu_vm_mask_var);
+	unsigned long cpu_bitmap = (unsigned long)mm;
+
+	cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap);
+	cpumask_clear((struct cpumask *)cpu_bitmap);
 }
 
 /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
 static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 {
-	return mm->cpu_vm_mask_var;
+	return (struct cpumask *)&mm->cpu_bitmap;
 }
 
 struct mmu_gather;
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index a86c4fa93115..cd0be91bdefa 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -67,9 +67,11 @@ struct mtd_erase_region_info {
  * @datbuf:	data buffer - if NULL only oob data are read/written
  * @oobbuf:	oob data buffer
  *
- * Note, it is allowed to read more than one OOB area at one go, but not write.
- * The interface assumes that the OOB write requests program only one page's
- * OOB area.
+ * Note, some MTD drivers do not allow you to write more than one OOB area at
+ * one go. If you try to do that on such an MTD device, -EINVAL will be
+ * returned. If you want to make your implementation portable on all kind of MTD
+ * devices you should split the write request into several sub-requests when the
+ * request crosses a page boundary.
  */
 struct mtd_oob_ops {
 	unsigned int	mode;
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 3e8ec3b8a39c..efb2345359bb 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -21,11 +21,10 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/flashchip.h>
 #include <linux/mtd/bbm.h>
+#include <linux/of.h>
 #include <linux/types.h>
 
-struct mtd_info;
 struct nand_flash_dev;
-struct device_node;
 
 /* Scan and identify a NAND device */
 int nand_scan_with_ids(struct mtd_info *mtd, int max_chips,
@@ -36,17 +35,6 @@ static inline int nand_scan(struct mtd_info *mtd, int max_chips)
 	return nand_scan_with_ids(mtd, max_chips, NULL);
 }
 
-/*
- * Separate phases of nand_scan(), allowing board driver to intervene
- * and override command or ECC setup according to flash type.
- */
-int nand_scan_ident(struct mtd_info *mtd, int max_chips,
-			   struct nand_flash_dev *table);
-int nand_scan_tail(struct mtd_info *mtd);
-
-/* Unregister the MTD device and free resources held by the NAND device */
-void nand_release(struct mtd_info *mtd);
-
 /* Internal helper for board drivers which need to override command function */
 void nand_wait_ready(struct mtd_info *mtd);
 
@@ -121,6 +109,7 @@ enum nand_ecc_algo {
 	NAND_ECC_UNKNOWN,
 	NAND_ECC_HAMMING,
 	NAND_ECC_BCH,
+	NAND_ECC_RS,
 };
 
 /*
@@ -218,6 +207,12 @@ enum nand_ecc_algo {
  */
 #define NAND_WAIT_TCCS		0x00200000
 
+/*
+ * Whether the NAND chip is a boot medium. Drivers might use this information
+ * to select ECC algorithms supported by the boot ROM or similar restrictions.
+ */
+#define NAND_IS_BOOT_MEDIUM	0x00400000
+
 /* Options set by nand scan */
 /* Nand scan has allocated controller struct */
 #define NAND_CONTROLLER_ALLOC	0x80000000
@@ -230,6 +225,17 @@ enum nand_ecc_algo {
 /* Keep gcc happy */
 struct nand_chip;
 
+/* ONFI version bits */
+#define ONFI_VERSION_1_0		BIT(1)
+#define ONFI_VERSION_2_0		BIT(2)
+#define ONFI_VERSION_2_1		BIT(3)
+#define ONFI_VERSION_2_2		BIT(4)
+#define ONFI_VERSION_2_3		BIT(5)
+#define ONFI_VERSION_3_0		BIT(6)
+#define ONFI_VERSION_3_1		BIT(7)
+#define ONFI_VERSION_3_2		BIT(8)
+#define ONFI_VERSION_4_0		BIT(9)
+
 /* ONFI features */
 #define ONFI_FEATURE_16_BIT_BUS		(1 << 0)
 #define ONFI_FEATURE_EXT_PARAM_PAGE	(1 << 7)
@@ -470,13 +476,13 @@ struct onfi_params {
  */
 struct nand_parameters {
 	/* Generic parameters */
-	char model[100];
+	const char *model;
 	bool supports_set_get_features;
 	DECLARE_BITMAP(set_feature_list, ONFI_FEATURE_NUMBER);
 	DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER);
 
 	/* ONFI parameters */
-	struct onfi_params onfi;
+	struct onfi_params *onfi;
 };
 
 /* The maximum expected count of bytes in the NAND ID sequence */
@@ -493,20 +499,42 @@ struct nand_id {
 };
 
 /**
- * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices
+ * struct nand_controller_ops - Controller operations
+ *
+ * @attach_chip: this method is called after the NAND detection phase after
+ *		 flash ID and MTD fields such as erase size, page size and OOB
+ *		 size have been set up. ECC requirements are available if
+ *		 provided by the NAND chip or device tree. Typically used to
+ *		 choose the appropriate ECC configuration and allocate
+ *		 associated resources.
+ *		 This hook is optional.
+ * @detach_chip: free all resources allocated/claimed in
+ *		 nand_controller_ops->attach_chip().
+ *		 This hook is optional.
+ */
+struct nand_controller_ops {
+	int (*attach_chip)(struct nand_chip *chip);
+	void (*detach_chip)(struct nand_chip *chip);
+};
+
+/**
+ * struct nand_controller - Structure used to describe a NAND controller
+ *
  * @lock:               protection lock
  * @active:		the mtd device which holds the controller currently
  * @wq:			wait queue to sleep on if a NAND operation is in
  *			progress used instead of the per chip wait queue
  *			when a hw controller is available.
+ * @ops:		NAND controller operations.
  */
-struct nand_hw_control {
+struct nand_controller {
 	spinlock_t lock;
 	struct nand_chip *active;
 	wait_queue_head_t wq;
+	const struct nand_controller_ops *ops;
 };
 
-static inline void nand_hw_control_init(struct nand_hw_control *nfc)
+static inline void nand_controller_init(struct nand_controller *nfc)
 {
 	nfc->active = NULL;
 	spin_lock_init(&nfc->lock);
@@ -778,11 +806,15 @@ nand_get_sdr_timings(const struct nand_data_interface *conf)
  *	  implementation) if any.
  * @cleanup: the ->init() function may have allocated resources, ->cleanup()
  *	     is here to let vendor specific code release those resources.
+ * @fixup_onfi_param_page: apply vendor specific fixups to the ONFI parameter
+ *			   page. This is called after the checksum is verified.
  */
 struct nand_manufacturer_ops {
 	void (*detect)(struct nand_chip *chip);
 	int (*init)(struct nand_chip *chip);
 	void (*cleanup)(struct nand_chip *chip);
+	void (*fixup_onfi_param_page)(struct nand_chip *chip,
+				      struct nand_onfi_params *p);
 };
 
 /**
@@ -986,14 +1018,14 @@ struct nand_subop {
 	unsigned int last_instr_end_off;
 };
 
-int nand_subop_get_addr_start_off(const struct nand_subop *subop,
-				  unsigned int op_id);
-int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
-				unsigned int op_id);
-int nand_subop_get_data_start_off(const struct nand_subop *subop,
-				  unsigned int op_id);
-int nand_subop_get_data_len(const struct nand_subop *subop,
-			    unsigned int op_id);
+unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop,
+					   unsigned int op_id);
+unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
+					 unsigned int op_id);
+unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop,
+					   unsigned int op_id);
+unsigned int nand_subop_get_data_len(const struct nand_subop *subop,
+				     unsigned int op_id);
 
 /**
  * struct nand_op_parser_addr_constraints - Constraints for address instructions
@@ -1176,9 +1208,9 @@ int nand_op_parser_exec_op(struct nand_chip *chip,
  *			setting the read-retry mode. Mostly needed for MLC NAND.
  * @ecc:		[BOARDSPECIFIC] ECC control structure
  * @buf_align:		minimum buffer alignment required by a platform
- * @hwcontrol:		platform-specific hardware control structure
+ * @dummy_controller:	dummy controller implementation for drivers that can
+ *			only control a single chip
  * @erase:		[REPLACEABLE] erase function
- * @scan_bbt:		[REPLACEABLE] function to scan bad block table
  * @chip_delay:		[BOARDSPECIFIC] chip dependent delay for transferring
  *			data from array to read regs (tR).
  * @state:		[INTERN] the current state of the NAND device
@@ -1271,7 +1303,6 @@ struct nand_chip {
 		       const struct nand_operation *op,
 		       bool check_only);
 	int (*erase)(struct mtd_info *mtd, int page);
-	int (*scan_bbt)(struct mtd_info *mtd);
 	int (*set_features)(struct mtd_info *mtd, struct nand_chip *chip,
 			    int feature_addr, uint8_t *subfeature_para);
 	int (*get_features)(struct mtd_info *mtd, struct nand_chip *chip,
@@ -1314,11 +1345,11 @@ struct nand_chip {
 	flstate_t state;
 
 	uint8_t *oob_poi;
-	struct nand_hw_control *controller;
+	struct nand_controller *controller;
 
 	struct nand_ecc_ctrl ecc;
 	unsigned long buf_align;
-	struct nand_hw_control hwcontrol;
+	struct nand_controller dummy_controller;
 
 	uint8_t *bbt;
 	struct nand_bbt_descr *bbt_td;
@@ -1517,14 +1548,12 @@ extern const struct nand_manufacturer_ops micron_nand_manuf_ops;
 extern const struct nand_manufacturer_ops amd_nand_manuf_ops;
 extern const struct nand_manufacturer_ops macronix_nand_manuf_ops;
 
-int nand_default_bbt(struct mtd_info *mtd);
+int nand_create_bbt(struct nand_chip *chip);
 int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs);
 int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs);
 int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt);
 int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 		    int allowbbt);
-int nand_do_read(struct mtd_info *mtd, loff_t from, size_t len,
-		 size_t *retlen, uint8_t *buf);
 
 /**
  * struct platform_nand_chip - chip level device structure
@@ -1555,14 +1584,12 @@ struct platform_device;
  * struct platform_nand_ctrl - controller level device structure
  * @probe:		platform specific function to probe/setup hardware
  * @remove:		platform specific function to remove/teardown hardware
- * @hwcontrol:		platform specific hardware control structure
  * @dev_ready:		platform specific function to read ready/busy pin
  * @select_chip:	platform specific chip select function
  * @cmd_ctrl:		platform specific function for controlling
  *			ALE/CLE/nCE. Also used to write command and address
  * @write_buf:		platform specific function for write buffer
  * @read_buf:		platform specific function for read buffer
- * @read_byte:		platform specific function to read one byte from chip
  * @priv:		private data to transport driver specific settings
  *
  * All fields are optional and depend on the hardware driver requirements
@@ -1570,13 +1597,11 @@ struct platform_device;
 struct platform_nand_ctrl {
 	int (*probe)(struct platform_device *pdev);
 	void (*remove)(struct platform_device *pdev);
-	void (*hwcontrol)(struct mtd_info *mtd, int cmd);
 	int (*dev_ready)(struct mtd_info *mtd);
 	void (*select_chip)(struct mtd_info *mtd, int chip);
 	void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl);
 	void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len);
 	void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len);
-	unsigned char (*read_byte)(struct mtd_info *mtd);
 	void *priv;
 };
 
@@ -1593,10 +1618,10 @@ struct platform_nand_data {
 /* return the supported asynchronous timing mode. */
 static inline int onfi_get_async_timing_mode(struct nand_chip *chip)
 {
-	if (!chip->parameters.onfi.version)
+	if (!chip->parameters.onfi)
 		return ONFI_TIMING_MODE_UNKNOWN;
 
-	return chip->parameters.onfi.async_timing_mode;
+	return chip->parameters.onfi->async_timing_mode;
 }
 
 int onfi_fill_data_interface(struct nand_chip *chip,
@@ -1641,14 +1666,8 @@ int nand_check_erased_ecc_chunk(void *data, int datalen,
 				void *extraoob, int extraooblen,
 				int threshold);
 
-int nand_check_ecc_caps(struct nand_chip *chip,
-			const struct nand_ecc_caps *caps, int oobavail);
-
-int nand_match_ecc_req(struct nand_chip *chip,
-		       const struct nand_ecc_caps *caps,  int oobavail);
-
-int nand_maximize_ecc(struct nand_chip *chip,
-		      const struct nand_ecc_caps *caps, int oobavail);
+int nand_ecc_choose_conf(struct nand_chip *chip,
+			 const struct nand_ecc_caps *caps, int oobavail);
 
 /* Default write_oob implementation */
 int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page);
@@ -1674,10 +1693,14 @@ int nand_get_set_features_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
 /* Default read_page_raw implementation */
 int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 		       uint8_t *buf, int oob_required, int page);
+int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+			       u8 *buf, int oob_required, int page);
 
 /* Default write_page_raw implementation */
 int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 			const uint8_t *buf, int oob_required, int page);
+int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+				const u8 *buf, int oob_required, int page);
 
 /* Reset and initialize a NAND device */
 int nand_reset(struct nand_chip *chip, int chipnr);
@@ -1711,8 +1734,13 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len,
 int nand_write_data_op(struct nand_chip *chip, const void *buf,
 		       unsigned int len, bool force_8bit);
 
-/* Free resources held by the NAND device */
+/*
+ * Free resources held by the NAND device, must be called on error after a
+ * sucessful nand_scan().
+ */
 void nand_cleanup(struct nand_chip *chip);
+/* Unregister the MTD device and calls nand_cleanup() */
+void nand_release(struct mtd_info *mtd);
 
 /* Default extended ID decoding function */
 void nand_decode_ext_id(struct nand_chip *chip);
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index e60da0d34cc1..c922e97f205a 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -235,6 +235,7 @@ enum spi_nor_option_flags {
 	SNOR_F_S3AN_ADDR_DEFAULT = BIT(3),
 	SNOR_F_READY_XSR_RDY	= BIT(4),
 	SNOR_F_USE_CLSR		= BIT(5),
+	SNOR_F_BROKEN_RESET	= BIT(6),
 };
 
 /**
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
new file mode 100644
index 000000000000..088ff96c3eb6
--- /dev/null
+++ b/include/linux/mtd/spinand.h
@@ -0,0 +1,421 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2017 Micron Technology, Inc.
+ *
+ *  Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ */
+#ifndef __LINUX_MTD_SPINAND_H
+#define __LINUX_MTD_SPINAND_H
+
+#include <linux/mutex.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+/**
+ * Standard SPI NAND flash operations
+ */
+
+#define SPINAND_RESET_OP						\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xff, 1),				\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_WR_EN_DIS_OP(enable)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD((enable) ? 0x06 : 0x04, 1),		\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_READID_OP(ndummy, buf, len)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x9f, 1),				\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+
+#define SPINAND_SET_FEATURE_OP(reg, valptr)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x1f, 1),				\
+		   SPI_MEM_OP_ADDR(1, reg, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(1, valptr, 1))
+
+#define SPINAND_GET_FEATURE_OP(reg, valptr)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0f, 1),				\
+		   SPI_MEM_OP_ADDR(1, reg, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_IN(1, valptr, 1))
+
+#define SPINAND_BLK_ERASE_OP(addr)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xd8, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_PAGE_READ_OP(addr)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x13, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_PAGE_READ_FROM_CACHE_OP(fast, addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 2),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 4),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+
+#define SPINAND_PROG_EXEC_OP(addr)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_PROG_LOAD(reset, addr, buf, len)			\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x02 : 0x84, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(len, buf, 1))
+
+#define SPINAND_PROG_LOAD_X4(reset, addr, buf, len)			\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x32 : 0x34, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(len, buf, 4))
+
+/**
+ * Standard SPI NAND flash commands
+ */
+#define SPINAND_CMD_PROG_LOAD_X4		0x32
+#define SPINAND_CMD_PROG_LOAD_RDM_DATA_X4	0x34
+
+/* feature register */
+#define REG_BLOCK_LOCK		0xa0
+#define BL_ALL_UNLOCKED		0x00
+
+/* configuration register */
+#define REG_CFG			0xb0
+#define CFG_OTP_ENABLE		BIT(6)
+#define CFG_ECC_ENABLE		BIT(4)
+#define CFG_QUAD_ENABLE		BIT(0)
+
+/* status register */
+#define REG_STATUS		0xc0
+#define STATUS_BUSY		BIT(0)
+#define STATUS_ERASE_FAILED	BIT(2)
+#define STATUS_PROG_FAILED	BIT(3)
+#define STATUS_ECC_MASK		GENMASK(5, 4)
+#define STATUS_ECC_NO_BITFLIPS	(0 << 4)
+#define STATUS_ECC_HAS_BITFLIPS	(1 << 4)
+#define STATUS_ECC_UNCOR_ERROR	(2 << 4)
+
+struct spinand_op;
+struct spinand_device;
+
+#define SPINAND_MAX_ID_LEN	4
+
+/**
+ * struct spinand_id - SPI NAND id structure
+ * @data: buffer containing the id bytes. Currently 4 bytes large, but can
+ *	  be extended if required
+ * @len: ID length
+ *
+ * struct_spinand_id->data contains all bytes returned after a READ_ID command,
+ * including dummy bytes if the chip does not emit ID bytes right after the
+ * READ_ID command. The responsibility to extract real ID bytes is left to
+ * struct_manufacurer_ops->detect().
+ */
+struct spinand_id {
+	u8 data[SPINAND_MAX_ID_LEN];
+	int len;
+};
+
+/**
+ * struct manufacurer_ops - SPI NAND manufacturer specific operations
+ * @detect: detect a SPI NAND device. Every time a SPI NAND device is probed
+ *	    the core calls the struct_manufacurer_ops->detect() hook of each
+ *	    registered manufacturer until one of them return 1. Note that
+ *	    the first thing to check in this hook is that the manufacturer ID
+ *	    in struct_spinand_device->id matches the manufacturer whose
+ *	    ->detect() hook has been called. Should return 1 if there's a
+ *	    match, 0 if the manufacturer ID does not match and a negative
+ *	    error code otherwise. When true is returned, the core assumes
+ *	    that properties of the NAND chip (spinand->base.memorg and
+ *	    spinand->base.eccreq) have been filled
+ * @init: initialize a SPI NAND device
+ * @cleanup: cleanup a SPI NAND device
+ *
+ * Each SPI NAND manufacturer driver should implement this interface so that
+ * NAND chips coming from this vendor can be detected and initialized properly.
+ */
+struct spinand_manufacturer_ops {
+	int (*detect)(struct spinand_device *spinand);
+	int (*init)(struct spinand_device *spinand);
+	void (*cleanup)(struct spinand_device *spinand);
+};
+
+/**
+ * struct spinand_manufacturer - SPI NAND manufacturer instance
+ * @id: manufacturer ID
+ * @name: manufacturer name
+ * @ops: manufacturer operations
+ */
+struct spinand_manufacturer {
+	u8 id;
+	char *name;
+	const struct spinand_manufacturer_ops *ops;
+};
+
+/* SPI NAND manufacturers */
+extern const struct spinand_manufacturer macronix_spinand_manufacturer;
+extern const struct spinand_manufacturer micron_spinand_manufacturer;
+extern const struct spinand_manufacturer winbond_spinand_manufacturer;
+
+/**
+ * struct spinand_op_variants - SPI NAND operation variants
+ * @ops: the list of variants for a given operation
+ * @nops: the number of variants
+ *
+ * Some operations like read-from-cache/write-to-cache have several variants
+ * depending on the number of IO lines you use to transfer data or address
+ * cycles. This structure is a way to describe the different variants supported
+ * by a chip and let the core pick the best one based on the SPI mem controller
+ * capabilities.
+ */
+struct spinand_op_variants {
+	const struct spi_mem_op *ops;
+	unsigned int nops;
+};
+
+#define SPINAND_OP_VARIANTS(name, ...)					\
+	const struct spinand_op_variants name = {			\
+		.ops = (struct spi_mem_op[]) { __VA_ARGS__ },		\
+		.nops = sizeof((struct spi_mem_op[]){ __VA_ARGS__ }) /	\
+			sizeof(struct spi_mem_op),			\
+	}
+
+/**
+ * spinand_ecc_info - description of the on-die ECC implemented by a SPI NAND
+ *		      chip
+ * @get_status: get the ECC status. Should return a positive number encoding
+ *		the number of corrected bitflips if correction was possible or
+ *		-EBADMSG if there are uncorrectable errors. I can also return
+ *		other negative error codes if the error is not caused by
+ *		uncorrectable bitflips
+ * @ooblayout: the OOB layout used by the on-die ECC implementation
+ */
+struct spinand_ecc_info {
+	int (*get_status)(struct spinand_device *spinand, u8 status);
+	const struct mtd_ooblayout_ops *ooblayout;
+};
+
+#define SPINAND_HAS_QE_BIT		BIT(0)
+
+/**
+ * struct spinand_info - Structure used to describe SPI NAND chips
+ * @model: model name
+ * @devid: device ID
+ * @flags: OR-ing of the SPINAND_XXX flags
+ * @memorg: memory organization
+ * @eccreq: ECC requirements
+ * @eccinfo: on-die ECC info
+ * @op_variants: operations variants
+ * @op_variants.read_cache: variants of the read-cache operation
+ * @op_variants.write_cache: variants of the write-cache operation
+ * @op_variants.update_cache: variants of the update-cache operation
+ * @select_target: function used to select a target/die. Required only for
+ *		   multi-die chips
+ *
+ * Each SPI NAND manufacturer driver should have a spinand_info table
+ * describing all the chips supported by the driver.
+ */
+struct spinand_info {
+	const char *model;
+	u8 devid;
+	u32 flags;
+	struct nand_memory_organization memorg;
+	struct nand_ecc_req eccreq;
+	struct spinand_ecc_info eccinfo;
+	struct {
+		const struct spinand_op_variants *read_cache;
+		const struct spinand_op_variants *write_cache;
+		const struct spinand_op_variants *update_cache;
+	} op_variants;
+	int (*select_target)(struct spinand_device *spinand,
+			     unsigned int target);
+};
+
+#define SPINAND_INFO_OP_VARIANTS(__read, __write, __update)		\
+	{								\
+		.read_cache = __read,					\
+		.write_cache = __write,					\
+		.update_cache = __update,				\
+	}
+
+#define SPINAND_ECCINFO(__ooblayout, __get_status)			\
+	.eccinfo = {							\
+		.ooblayout = __ooblayout,				\
+		.get_status = __get_status,				\
+	}
+
+#define SPINAND_SELECT_TARGET(__func)					\
+	.select_target = __func,
+
+#define SPINAND_INFO(__model, __id, __memorg, __eccreq, __op_variants,	\
+		     __flags, ...)					\
+	{								\
+		.model = __model,					\
+		.devid = __id,						\
+		.memorg = __memorg,					\
+		.eccreq = __eccreq,					\
+		.op_variants = __op_variants,				\
+		.flags = __flags,					\
+		__VA_ARGS__						\
+	}
+
+/**
+ * struct spinand_device - SPI NAND device instance
+ * @base: NAND device instance
+ * @spimem: pointer to the SPI mem object
+ * @lock: lock used to serialize accesses to the NAND
+ * @id: NAND ID as returned by READ_ID
+ * @flags: NAND flags
+ * @op_templates: various SPI mem op templates
+ * @op_templates.read_cache: read cache op template
+ * @op_templates.write_cache: write cache op template
+ * @op_templates.update_cache: update cache op template
+ * @select_target: select a specific target/die. Usually called before sending
+ *		   a command addressing a page or an eraseblock embedded in
+ *		   this die. Only required if your chip exposes several dies
+ * @cur_target: currently selected target/die
+ * @eccinfo: on-die ECC information
+ * @cfg_cache: config register cache. One entry per die
+ * @databuf: bounce buffer for data
+ * @oobbuf: bounce buffer for OOB data
+ * @scratchbuf: buffer used for everything but page accesses. This is needed
+ *		because the spi-mem interface explicitly requests that buffers
+ *		passed in spi_mem_op be DMA-able, so we can't based the bufs on
+ *		the stack
+ * @manufacturer: SPI NAND manufacturer information
+ * @priv: manufacturer private data
+ */
+struct spinand_device {
+	struct nand_device base;
+	struct spi_mem *spimem;
+	struct mutex lock;
+	struct spinand_id id;
+	u32 flags;
+
+	struct {
+		const struct spi_mem_op *read_cache;
+		const struct spi_mem_op *write_cache;
+		const struct spi_mem_op *update_cache;
+	} op_templates;
+
+	int (*select_target)(struct spinand_device *spinand,
+			     unsigned int target);
+	unsigned int cur_target;
+
+	struct spinand_ecc_info eccinfo;
+
+	u8 *cfg_cache;
+	u8 *databuf;
+	u8 *oobbuf;
+	u8 *scratchbuf;
+	const struct spinand_manufacturer *manufacturer;
+	void *priv;
+};
+
+/**
+ * mtd_to_spinand() - Get the SPI NAND device attached to an MTD instance
+ * @mtd: MTD instance
+ *
+ * Return: the SPI NAND device attached to @mtd.
+ */
+static inline struct spinand_device *mtd_to_spinand(struct mtd_info *mtd)
+{
+	return container_of(mtd_to_nanddev(mtd), struct spinand_device, base);
+}
+
+/**
+ * spinand_to_mtd() - Get the MTD device embedded in a SPI NAND device
+ * @spinand: SPI NAND device
+ *
+ * Return: the MTD device embedded in @spinand.
+ */
+static inline struct mtd_info *spinand_to_mtd(struct spinand_device *spinand)
+{
+	return nanddev_to_mtd(&spinand->base);
+}
+
+/**
+ * nand_to_spinand() - Get the SPI NAND device embedding an NAND object
+ * @nand: NAND object
+ *
+ * Return: the SPI NAND device embedding @nand.
+ */
+static inline struct spinand_device *nand_to_spinand(struct nand_device *nand)
+{
+	return container_of(nand, struct spinand_device, base);
+}
+
+/**
+ * spinand_to_nand() - Get the NAND device embedded in a SPI NAND object
+ * @spinand: SPI NAND device
+ *
+ * Return: the NAND device embedded in @spinand.
+ */
+static inline struct nand_device *
+spinand_to_nand(struct spinand_device *spinand)
+{
+	return &spinand->base;
+}
+
+/**
+ * spinand_set_of_node - Attach a DT node to a SPI NAND device
+ * @spinand: SPI NAND device
+ * @np: DT node
+ *
+ * Attach a DT node to a SPI NAND device.
+ */
+static inline void spinand_set_of_node(struct spinand_device *spinand,
+				       struct device_node *np)
+{
+	nanddev_set_of_node(&spinand->base, np);
+}
+
+int spinand_match_and_init(struct spinand_device *dev,
+			   const struct spinand_info *table,
+			   unsigned int table_size, u8 devid);
+
+int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val);
+int spinand_select_target(struct spinand_device *spinand, unsigned int target);
+
+#endif /* __LINUX_MTD_SPINAND_H */
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index b8d868d23e79..08f9247e9827 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -45,12 +45,18 @@ extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern unsigned int  softlockup_panic;
-#else
+
+extern int lockup_detector_online_cpu(unsigned int cpu);
+extern int lockup_detector_offline_cpu(unsigned int cpu);
+#else /* CONFIG_SOFTLOCKUP_DETECTOR */
 static inline void touch_softlockup_watchdog_sched(void) { }
 static inline void touch_softlockup_watchdog(void) { }
 static inline void touch_softlockup_watchdog_sync(void) { }
 static inline void touch_all_softlockup_watchdogs(void) { }
-#endif
+
+#define lockup_detector_online_cpu	NULL
+#define lockup_detector_offline_cpu	NULL
+#endif /* CONFIG_SOFTLOCKUP_DETECTOR */
 
 #ifdef CONFIG_DETECT_HUNG_TASK
 void reset_hung_task_detector(void);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 2950ce957656..68e91ef5494c 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -242,7 +242,12 @@ struct nvme_id_ctrl {
 	__le32			sanicap;
 	__le32			hmminds;
 	__le16			hmmaxd;
-	__u8			rsvd338[174];
+	__u8			rsvd338[4];
+	__u8			anatt;
+	__u8			anacap;
+	__le32			anagrpmax;
+	__le32			nanagrpid;
+	__u8			rsvd352[160];
 	__u8			sqes;
 	__u8			cqes;
 	__le16			maxcmd;
@@ -254,11 +259,12 @@ struct nvme_id_ctrl {
 	__le16			awun;
 	__le16			awupf;
 	__u8			nvscc;
-	__u8			rsvd531;
+	__u8			nwpc;
 	__le16			acwu;
 	__u8			rsvd534[2];
 	__le32			sgls;
-	__u8			rsvd540[228];
+	__le32			mnan;
+	__u8			rsvd544[224];
 	char			subnqn[256];
 	__u8			rsvd1024[768];
 	__le32			ioccsz;
@@ -312,7 +318,11 @@ struct nvme_id_ns {
 	__le16			nabspf;
 	__le16			noiob;
 	__u8			nvmcap[16];
-	__u8			rsvd64[40];
+	__u8			rsvd64[28];
+	__le32			anagrpid;
+	__u8			rsvd96[3];
+	__u8			nsattr;
+	__u8			rsvd100[4];
 	__u8			nguid[16];
 	__u8			eui64[8];
 	struct nvme_lbaf	lbaf[16];
@@ -425,6 +435,32 @@ struct nvme_effects_log {
 	__u8   resv[2048];
 };
 
+enum nvme_ana_state {
+	NVME_ANA_OPTIMIZED		= 0x01,
+	NVME_ANA_NONOPTIMIZED		= 0x02,
+	NVME_ANA_INACCESSIBLE		= 0x03,
+	NVME_ANA_PERSISTENT_LOSS	= 0x04,
+	NVME_ANA_CHANGE			= 0x0f,
+};
+
+struct nvme_ana_group_desc {
+	__le32	grpid;
+	__le32	nnsids;
+	__le64	chgcnt;
+	__u8	state;
+	__u8	rsvd17[15];
+	__le32	nsids[];
+};
+
+/* flag for the log specific field of the ANA log */
+#define NVME_ANA_LOG_RGO	(1 << 0)
+
+struct nvme_ana_rsp_hdr {
+	__le64	chgcnt;
+	__le16	ngrps;
+	__le16	rsvd10[3];
+};
+
 enum {
 	NVME_SMART_CRIT_SPARE		= 1 << 0,
 	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
@@ -444,11 +480,13 @@ enum {
 enum {
 	NVME_AER_NOTICE_NS_CHANGED	= 0x00,
 	NVME_AER_NOTICE_FW_ACT_STARTING = 0x01,
+	NVME_AER_NOTICE_ANA		= 0x03,
 };
 
 enum {
 	NVME_AEN_CFG_NS_ATTR		= 1 << 8,
 	NVME_AEN_CFG_FW_ACT		= 1 << 9,
+	NVME_AEN_CFG_ANA_CHANGE		= 1 << 11,
 };
 
 struct nvme_lba_range_type {
@@ -749,15 +787,22 @@ enum {
 	NVME_FEAT_HOST_MEM_BUF	= 0x0d,
 	NVME_FEAT_TIMESTAMP	= 0x0e,
 	NVME_FEAT_KATO		= 0x0f,
+	NVME_FEAT_HCTM		= 0x10,
+	NVME_FEAT_NOPSC		= 0x11,
+	NVME_FEAT_RRL		= 0x12,
+	NVME_FEAT_PLM_CONFIG	= 0x13,
+	NVME_FEAT_PLM_WINDOW	= 0x14,
 	NVME_FEAT_SW_PROGRESS	= 0x80,
 	NVME_FEAT_HOST_ID	= 0x81,
 	NVME_FEAT_RESV_MASK	= 0x82,
 	NVME_FEAT_RESV_PERSIST	= 0x83,
+	NVME_FEAT_WRITE_PROTECT	= 0x84,
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
 	NVME_LOG_CHANGED_NS	= 0x04,
 	NVME_LOG_CMD_EFFECTS	= 0x05,
+	NVME_LOG_ANA		= 0x0c,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
@@ -765,6 +810,14 @@ enum {
 	NVME_FWACT_ACTV		= (2 << 3),
 };
 
+/* NVMe Namespace Write Protect State */
+enum {
+	NVME_NS_NO_WRITE_PROTECT = 0,
+	NVME_NS_WRITE_PROTECT,
+	NVME_NS_WRITE_PROTECT_POWER_CYCLE,
+	NVME_NS_WRITE_PROTECT_PERMANENT,
+};
+
 #define NVME_MAX_CHANGED_NAMESPACES	1024
 
 struct nvme_identify {
@@ -880,7 +933,7 @@ struct nvme_get_log_page_command {
 	__u64			rsvd2[2];
 	union nvme_data_ptr	dptr;
 	__u8			lid;
-	__u8			rsvd10;
+	__u8			lsp; /* upper 4 bits reserved */
 	__le16			numdl;
 	__le16			numdu;
 	__u16			rsvd11;
@@ -1111,6 +1164,8 @@ enum {
 	NVME_SC_SGL_INVALID_OFFSET	= 0x16,
 	NVME_SC_SGL_INVALID_SUBTYPE	= 0x17,
 
+	NVME_SC_NS_WRITE_PROTECTED	= 0x20,
+
 	NVME_SC_LBA_RANGE		= 0x80,
 	NVME_SC_CAP_EXCEEDED		= 0x81,
 	NVME_SC_NS_NOT_READY		= 0x82,
@@ -1180,6 +1235,13 @@ enum {
 	NVME_SC_ACCESS_DENIED		= 0x286,
 	NVME_SC_UNWRITTEN_BLOCK		= 0x287,
 
+	/*
+	 * Path-related Errors:
+	 */
+	NVME_SC_ANA_PERSISTENT_LOSS	= 0x301,
+	NVME_SC_ANA_INACCESSIBLE	= 0x302,
+	NVME_SC_ANA_TRANSITION		= 0x303,
+
 	NVME_SC_DNR			= 0x4000,
 };
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 87f6db437e4a..53c500f0ca79 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -490,7 +490,7 @@ struct perf_addr_filters_head {
 };
 
 /**
- * enum perf_event_state - the states of a event
+ * enum perf_event_state - the states of an event:
  */
 enum perf_event_state {
 	PERF_EVENT_STATE_DEAD		= -4,
diff --git a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h b/include/linux/platform_data/jz4740/jz4740_nand.h
index f381d465e768..bc571f6d5ced 100644
--- a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
+++ b/include/linux/platform_data/jz4740/jz4740_nand.h
@@ -13,8 +13,8 @@
  *
  */
 
-#ifndef __ASM_MACH_JZ4740_JZ4740_NAND_H__
-#define __ASM_MACH_JZ4740_JZ4740_NAND_H__
+#ifndef __JZ4740_NAND_H__
+#define __JZ4740_NAND_H__
 
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
diff --git a/include/linux/platform_data/mtd-orion_nand.h b/include/linux/platform_data/mtd-orion_nand.h
index a7ce77c7c1a8..34828eb85982 100644
--- a/include/linux/platform_data/mtd-orion_nand.h
+++ b/include/linux/platform_data/mtd-orion_nand.h
@@ -12,7 +12,6 @@
  */
 struct orion_nand_data {
 	struct mtd_partition *parts;
-	int (*dev_ready)(struct mtd_info *mtd);
 	u32 nr_parts;
 	u8 ale;		/* address line number connected to ALE */
 	u8 cle;		/* address line number connected to CLE */
diff --git a/arch/mips/include/asm/txx9/ndfmc.h b/include/linux/platform_data/txx9/ndfmc.h
index fa67f3df78fc..fc172627d54e 100644
--- a/arch/mips/include/asm/txx9/ndfmc.h
+++ b/include/linux/platform_data/txx9/ndfmc.h
@@ -5,8 +5,8 @@
  *
  * (C) Copyright TOSHIBA CORPORATION 2007
  */
-#ifndef __ASM_TXX9_NDFMC_H
-#define __ASM_TXX9_NDFMC_H
+#ifndef __TXX9_NDFMC_H
+#define __TXX9_NDFMC_H
 
 #define NDFMC_PLAT_FLAG_USE_BSPRT	0x01
 #define NDFMC_PLAT_FLAG_NO_RSTR		0x02
@@ -27,4 +27,4 @@ struct txx9ndfmc_platform_data {
 void txx9_ndfmc_init(unsigned long baseaddr,
 		     const struct txx9ndfmc_platform_data *plat_data);
 
-#endif /* __ASM_TXX9_NDFMC_H */
+#endif /* __TXX9_NDFMC_H */
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index c85704fcdbd2..ee7e987ea1b4 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -95,8 +95,8 @@ struct k_itimer {
 	clockid_t		it_clock;
 	timer_t			it_id;
 	int			it_active;
-	int			it_overrun;
-	int			it_overrun_last;
+	s64			it_overrun;
+	s64			it_overrun_last;
 	int			it_requeue_pending;
 	int			it_sigev_notify;
 	ktime_t			it_interval;
diff --git a/include/linux/pti.h b/include/linux/pti.h
index 0174883a935a..1a941efcaa62 100644
--- a/include/linux/pti.h
+++ b/include/linux/pti.h
@@ -6,6 +6,7 @@
 #include <asm/pti.h>
 #else
 static inline void pti_init(void) { }
+static inline void pti_finalize(void) { }
 #endif
 
 #endif
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 36df6ccbc874..4786c2235b98 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -396,7 +396,16 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * @member:	the name of the list_head within the struct.
  *
  * Continue to iterate over list of given type, continuing after
- * the current position.
+ * the current position which must have been in the list when the RCU read
+ * lock was taken.
+ * This would typically require either that you obtained the node from a
+ * previous walk of the list in the same RCU read-side critical section, or
+ * that you held some sort of non-RCU reference (such as a reference count)
+ * to keep the node alive *and* in the list.
+ *
+ * This iterator is similar to list_for_each_entry_from_rcu() except
+ * this starts after the given position and that one starts at the given
+ * position.
  */
 #define list_for_each_entry_continue_rcu(pos, head, member) 		\
 	for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \
@@ -411,6 +420,14 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  *
  * Iterate over the tail of a list starting from a given position,
  * which must have been in the list when the RCU read lock was taken.
+ * This would typically require either that you obtained the node from a
+ * previous walk of the list in the same RCU read-side critical section, or
+ * that you held some sort of non-RCU reference (such as a reference count)
+ * to keep the node alive *and* in the list.
+ *
+ * This iterator is similar to list_for_each_entry_continue_rcu() except
+ * this starts from the given position and that one starts from the position
+ * after the given position.
  */
 #define list_for_each_entry_from_rcu(pos, head, member)			\
 	for (; &(pos)->member != (head);					\
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 65163aa0bb04..75e5b393cf44 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -64,7 +64,6 @@ void rcu_barrier_tasks(void);
 
 void __rcu_read_lock(void);
 void __rcu_read_unlock(void);
-void rcu_read_unlock_special(struct task_struct *t);
 void synchronize_rcu(void);
 
 /*
@@ -159,11 +158,11 @@ static inline void rcu_init_nohz(void) { }
 	} while (0)
 
 /*
- * Note a voluntary context switch for RCU-tasks benefit.  This is a
- * macro rather than an inline function to avoid #include hell.
+ * Note a quasi-voluntary context switch for RCU-tasks's benefit.
+ * This is a macro rather than an inline function to avoid #include hell.
  */
 #ifdef CONFIG_TASKS_RCU
-#define rcu_note_voluntary_context_switch_lite(t) \
+#define rcu_tasks_qs(t) \
 	do { \
 		if (READ_ONCE((t)->rcu_tasks_holdout)) \
 			WRITE_ONCE((t)->rcu_tasks_holdout, false); \
@@ -171,14 +170,14 @@ static inline void rcu_init_nohz(void) { }
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
 		rcu_all_qs(); \
-		rcu_note_voluntary_context_switch_lite(t); \
+		rcu_tasks_qs(t); \
 	} while (0)
 void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
 void synchronize_rcu_tasks(void);
 void exit_tasks_rcu_start(void);
 void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU */
-#define rcu_note_voluntary_context_switch_lite(t)	do { } while (0)
+#define rcu_tasks_qs(t)	do { } while (0)
 #define rcu_note_voluntary_context_switch(t)		rcu_all_qs()
 #define call_rcu_tasks call_rcu_sched
 #define synchronize_rcu_tasks synchronize_sched
@@ -195,8 +194,8 @@ static inline void exit_tasks_rcu_finish(void) { }
  */
 #define cond_resched_tasks_rcu_qs() \
 do { \
-	if (!cond_resched()) \
-		rcu_note_voluntary_context_switch_lite(current); \
+	rcu_tasks_qs(current); \
+	cond_resched(); \
 } while (0)
 
 /*
@@ -567,8 +566,8 @@ static inline void rcu_preempt_sleep_check(void) { }
  * This is simply an identity function, but it documents where a pointer
  * is handed off from RCU to some other synchronization mechanism, for
  * example, reference counting or locking.  In C11, it would map to
- * kill_dependency().  It could be used as follows:
- * ``
+ * kill_dependency().  It could be used as follows::
+ *
  *	rcu_read_lock();
  *	p = rcu_dereference(gp);
  *	long_lived = is_long_lived(p);
@@ -579,7 +578,6 @@ static inline void rcu_preempt_sleep_check(void) { }
  *			p = rcu_pointer_handoff(p);
  *	}
  *	rcu_read_unlock();
- *``
  */
 #define rcu_pointer_handoff(p) (p)
 
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 7b3c82e8a625..8d9a0ea8f0b5 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -93,7 +93,7 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 #define rcu_note_context_switch(preempt) \
 	do { \
 		rcu_sched_qs(); \
-		rcu_note_voluntary_context_switch_lite(current); \
+		rcu_tasks_qs(current); \
 	} while (0)
 
 static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index a685da2c4522..e28cce21bad6 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -3,9 +3,10 @@
 #define _LINUX_REFCOUNT_H
 
 #include <linux/atomic.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/spinlock_types.h>
+
+struct mutex;
 
 /**
  * struct refcount_t - variant of atomic_t specialized for reference counts
@@ -42,17 +43,30 @@ static inline unsigned int refcount_read(const refcount_t *r)
 	return atomic_read(&r->refs);
 }
 
+extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r);
+extern void refcount_add_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r);
+extern void refcount_inc_checked(refcount_t *r);
+
+extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_dec_and_test_checked(refcount_t *r);
+extern void refcount_dec_checked(refcount_t *r);
+
 #ifdef CONFIG_REFCOUNT_FULL
-extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r);
-extern void refcount_add(unsigned int i, refcount_t *r);
 
-extern __must_check bool refcount_inc_not_zero(refcount_t *r);
-extern void refcount_inc(refcount_t *r);
+#define refcount_add_not_zero	refcount_add_not_zero_checked
+#define refcount_add		refcount_add_checked
+
+#define refcount_inc_not_zero	refcount_inc_not_zero_checked
+#define refcount_inc		refcount_inc_checked
+
+#define refcount_sub_and_test	refcount_sub_and_test_checked
 
-extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r);
+#define refcount_dec_and_test	refcount_dec_and_test_checked
+#define refcount_dec		refcount_dec_checked
 
-extern __must_check bool refcount_dec_and_test(refcount_t *r);
-extern void refcount_dec(refcount_t *r);
 #else
 # ifdef CONFIG_ARCH_HAS_REFCOUNT
 #  include <asm/refcount.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 43731fe51c97..95a5018c338e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -167,8 +167,8 @@ struct task_group;
  *   need_sleep = false;
  *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
- * Where wake_up_state() (and all other wakeup primitives) imply enough
- * barriers to order the store of the variable against wakeup.
+ * where wake_up_state() executes a full memory barrier before accessing the
+ * task state.
  *
  * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
@@ -734,6 +734,10 @@ struct task_struct {
 	/* disallow userland-initiated cgroup migration */
 	unsigned			no_cgroup_migration:1;
 #endif
+#ifdef CONFIG_BLK_CGROUP
+	/* to be used once the psi infrastructure lands upstream. */
+	unsigned			use_memdelay:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
@@ -1017,7 +1021,6 @@ struct task_struct {
 	u64				last_sum_exec_runtime;
 	struct callback_head		numa_work;
 
-	struct list_head		numa_entry;
 	struct numa_group		*numa_group;
 
 	/*
@@ -1151,6 +1154,10 @@ struct task_struct {
 	unsigned int			memcg_nr_pages_over_high;
 #endif
 
+#ifdef CONFIG_BLK_CGROUP
+	struct request_queue		*throttle_queue;
+#endif
+
 #ifdef CONFIG_UPROBES
 	struct uprobe_task		*utask;
 #endif
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 1c1a1512ec55..913488d828cb 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -40,7 +40,6 @@ extern unsigned int sysctl_numa_balancing_scan_size;
 #ifdef CONFIG_SCHED_DEBUG
 extern __read_mostly unsigned int sysctl_sched_migration_cost;
 extern __read_mostly unsigned int sysctl_sched_nr_migrate;
-extern __read_mostly unsigned int sysctl_sched_time_avg;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
index 411b52e424e1..abe28d5cb3f4 100644
--- a/include/linux/sched_clock.h
+++ b/include/linux/sched_clock.h
@@ -9,17 +9,16 @@
 #define LINUX_SCHED_CLOCK
 
 #ifdef CONFIG_GENERIC_SCHED_CLOCK
-extern void sched_clock_postinit(void);
+extern void generic_sched_clock_init(void);
 
 extern void sched_clock_register(u64 (*read)(void), int bits,
 				 unsigned long rate);
 #else
-static inline void sched_clock_postinit(void) { }
+static inline void generic_sched_clock_init(void) { }
 
 static inline void sched_clock_register(u64 (*read)(void), int bits,
 					unsigned long rate)
 {
-	;
 }
 #endif
 
diff --git a/include/linux/security.h b/include/linux/security.h
index 63030c85ee19..88d30fc975e7 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -309,7 +309,7 @@ void security_file_set_fowner(struct file *file);
 int security_file_send_sigiotask(struct task_struct *tsk,
 				 struct fown_struct *fown, int sig);
 int security_file_receive(struct file *file);
-int security_file_open(struct file *file, const struct cred *cred);
+int security_file_open(struct file *file);
 int security_task_alloc(struct task_struct *task, unsigned long clone_flags);
 void security_task_free(struct task_struct *task);
 int security_cred_alloc_blank(struct cred *cred, gfp_t gfp);
@@ -858,8 +858,7 @@ static inline int security_file_receive(struct file *file)
 	return 0;
 }
 
-static inline int security_file_open(struct file *file,
-				     const struct cred *cred)
+static inline int security_file_open(struct file *file)
 {
 	return 0;
 }
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index c174844cf663..d0884b525001 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -25,8 +25,6 @@ struct smpboot_thread_data;
  *			parked (cpu offline)
  * @unpark:		Optional unpark function, called when the thread is
  *			unparked (cpu online)
- * @cpumask:		Internal state.  To update which threads are unparked,
- *			call smpboot_update_cpumask_percpu_thread().
  * @selfparking:	Thread is not parked by the park function.
  * @thread_comm:	The base name of the thread
  */
@@ -40,23 +38,12 @@ struct smp_hotplug_thread {
 	void				(*cleanup)(unsigned int cpu, bool online);
 	void				(*park)(unsigned int cpu);
 	void				(*unpark)(unsigned int cpu);
-	cpumask_var_t			cpumask;
 	bool				selfparking;
 	const char			*thread_comm;
 };
 
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
-					   const struct cpumask *cpumask);
-
-static inline int
-smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
-{
-	return smpboot_register_percpu_thread_cpumask(plug_thread,
-						      cpu_possible_mask);
-}
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
 
 void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					  const struct cpumask *);
 
 #endif
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index bb4bd15ae1f6..4fa34a227a0f 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -3,7 +3,9 @@
  * Copyright (C) 2018 Exceet Electronics GmbH
  * Copyright (C) 2018 Bootlin
  *
- * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ * Author:
+ *	Peter Pan <peterpandong@micron.com>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
  */
 
 #ifndef __LINUX_SPI_MEM_H
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index fd57888d4942..3190997df9ca 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -114,29 +114,48 @@ do {								\
 #endif /*arch_spin_is_contended*/
 
 /*
- * This barrier must provide two things:
+ * smp_mb__after_spinlock() provides the equivalent of a full memory barrier
+ * between program-order earlier lock acquisitions and program-order later
+ * memory accesses.
  *
- *   - it must guarantee a STORE before the spin_lock() is ordered against a
- *     LOAD after it, see the comments at its two usage sites.
+ * This guarantees that the following two properties hold:
  *
- *   - it must ensure the critical section is RCsc.
+ *   1) Given the snippet:
  *
- * The latter is important for cases where we observe values written by other
- * CPUs in spin-loops, without barriers, while being subject to scheduling.
+ *	  { X = 0;  Y = 0; }
  *
- * CPU0			CPU1			CPU2
+ *	  CPU0				CPU1
  *
- *			for (;;) {
- *			  if (READ_ONCE(X))
- *			    break;
- *			}
- * X=1
- *			<sched-out>
- *						<sched-in>
- *						r = X;
+ *	  WRITE_ONCE(X, 1);		WRITE_ONCE(Y, 1);
+ *	  spin_lock(S);			smp_mb();
+ *	  smp_mb__after_spinlock();	r1 = READ_ONCE(X);
+ *	  r0 = READ_ONCE(Y);
+ *	  spin_unlock(S);
  *
- * without transitivity it could be that CPU1 observes X!=0 breaks the loop,
- * we get migrated and CPU2 sees X==0.
+ *      it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0)
+ *      and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments
+ *      preceding the call to smp_mb__after_spinlock() in __schedule() and in
+ *      try_to_wake_up().
+ *
+ *   2) Given the snippet:
+ *
+ *  { X = 0;  Y = 0; }
+ *
+ *  CPU0		CPU1				CPU2
+ *
+ *  spin_lock(S);	spin_lock(S);			r1 = READ_ONCE(Y);
+ *  WRITE_ONCE(X, 1);	smp_mb__after_spinlock();	smp_rmb();
+ *  spin_unlock(S);	r0 = READ_ONCE(X);		r2 = READ_ONCE(X);
+ *			WRITE_ONCE(Y, 1);
+ *			spin_unlock(S);
+ *
+ *      it is forbidden that CPU0's critical section executes before CPU1's
+ *      critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1)
+ *      and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments
+ *      preceding the calls to smp_rmb() in try_to_wake_up() for similar
+ *      snippets but "projected" onto two CPUs.
+ *
+ * Property (2) upgrades the lock to an RCsc lock.
  *
  * Since most load-store architectures implement ACQUIRE with an smp_mb() after
  * the LL/SC loop, they need no further barriers. Similarly all our TSO
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 91494d7e8e41..3e72a291c401 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -195,6 +195,16 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
 	return retval;
 }
 
+/* Used by tracing, cannot be traced and cannot invoke lockdep. */
+static inline notrace int
+srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp)
+{
+	int retval;
+
+	retval = __srcu_read_lock(sp);
+	return retval;
+}
+
 /**
  * srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
  * @sp: srcu_struct in which to unregister the old reader.
@@ -209,6 +219,13 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
 	__srcu_read_unlock(sp, idx);
 }
 
+/* Used by tracing, cannot be traced and cannot call lockdep. */
+static inline notrace void
+srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp)
+{
+	__srcu_read_unlock(sp, idx);
+}
+
 /**
  * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock
  *
diff --git a/include/linux/swait.h b/include/linux/swait.h
index bf8cb0dee23c..73e06e9986d4 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -16,7 +16,7 @@
  * wait-queues, but the semantics are actually completely different, and
  * every single user we have ever had has been buggy (or pointless).
  *
- * A "swake_up()" only wakes up _one_ waiter, which is not at all what
+ * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what
  * "wake_up()" does, and has led to problems. In other cases, it has
  * been fine, because there's only ever one waiter (kvm), but in that
  * case gthe whole "simple" wait-queue is just pointless to begin with,
@@ -38,8 +38,8 @@
  *    all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
  *    sleeper state.
  *
- *  - the exclusive mode; because this requires preserving the list order
- *    and this is hard.
+ *  - the !exclusive mode; because that leads to O(n) wakeups, everything is
+ *    exclusive.
  *
  *  - custom wake callback functions; because you cannot give any guarantees
  *    about random code. This also allows swait to be used in RT, such that
@@ -115,7 +115,7 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name
  *      CPU0 - waker                    CPU1 - waiter
  *
  *                                      for (;;) {
- *      @cond = true;                     prepare_to_swait(&wq_head, &wait, state);
+ *      @cond = true;                     prepare_to_swait_exclusive(&wq_head, &wait, state);
  *      smp_mb();                         // smp_mb() from set_current_state()
  *      if (swait_active(wq_head))        if (@cond)
  *        wake_up(wq_head);                      break;
@@ -157,20 +157,20 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq)
 	return swait_active(wq);
 }
 
-extern void swake_up(struct swait_queue_head *q);
+extern void swake_up_one(struct swait_queue_head *q);
 extern void swake_up_all(struct swait_queue_head *q);
 extern void swake_up_locked(struct swait_queue_head *q);
 
-extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
-extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
+extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state);
 extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
 
 extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 
-/* as per ___wait_event() but for swait, therefore "exclusive == 0" */
+/* as per ___wait_event() but for swait, therefore "exclusive == 1" */
 #define ___swait_event(wq, condition, state, ret, cmd)			\
 ({									\
+	__label__ __out;						\
 	struct swait_queue __wait;					\
 	long __ret = ret;						\
 									\
@@ -183,20 +183,20 @@ extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 									\
 		if (___wait_is_interruptible(state) && __int) {		\
 			__ret = __int;					\
-			break;						\
+			goto __out;					\
 		}							\
 									\
 		cmd;							\
 	}								\
 	finish_swait(&wq, &__wait);					\
-	__ret;								\
+__out:	__ret;								\
 })
 
 #define __swait_event(wq, condition)					\
 	(void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,	\
 			    schedule())
 
-#define swait_event(wq, condition)					\
+#define swait_event_exclusive(wq, condition)				\
 do {									\
 	if (condition)							\
 		break;							\
@@ -208,7 +208,7 @@ do {									\
 		      TASK_UNINTERRUPTIBLE, timeout,			\
 		      __ret = schedule_timeout(__ret))
 
-#define swait_event_timeout(wq, condition, timeout)			\
+#define swait_event_timeout_exclusive(wq, condition, timeout)		\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
@@ -220,7 +220,7 @@ do {									\
 	___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0,		\
 		      schedule())
 
-#define swait_event_interruptible(wq, condition)			\
+#define swait_event_interruptible_exclusive(wq, condition)		\
 ({									\
 	int __ret = 0;							\
 	if (!(condition))						\
@@ -233,7 +233,7 @@ do {									\
 		      TASK_INTERRUPTIBLE, timeout,			\
 		      __ret = schedule_timeout(__ret))
 
-#define swait_event_interruptible_timeout(wq, condition, timeout)	\
+#define swait_event_interruptible_timeout_exclusive(wq, condition, timeout)\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
@@ -246,7 +246,7 @@ do {									\
 	(void)___swait_event(wq, condition, TASK_IDLE, 0, schedule())
 
 /**
- * swait_event_idle - wait without system load contribution
+ * swait_event_idle_exclusive - wait without system load contribution
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
@@ -257,7 +257,7 @@ do {									\
  * condition and doesn't want to contribute to system load. Signals are
  * ignored.
  */
-#define swait_event_idle(wq, condition)					\
+#define swait_event_idle_exclusive(wq, condition)			\
 do {									\
 	if (condition)							\
 		break;							\
@@ -270,7 +270,7 @@ do {									\
 		       __ret = schedule_timeout(__ret))
 
 /**
- * swait_event_idle_timeout - wait up to timeout without load contribution
+ * swait_event_idle_timeout_exclusive - wait up to timeout without load contribution
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout at which we'll give up in jiffies
@@ -288,7 +288,7 @@ do {									\
  * or the remaining jiffies (at least 1) if the @condition evaluated
  * to %true before the @timeout elapsed.
  */
-#define swait_event_idle_timeout(wq, condition, timeout)		\
+#define swait_event_idle_timeout_exclusive(wq, condition, timeout)	\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c063443d8638..1a8bd05a335e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -629,7 +629,6 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 
 	return memcg->swappiness;
 }
-
 #else
 static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 {
@@ -637,6 +636,16 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 }
 #endif
 
+#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
+					 gfp_t gfp_mask);
+#else
+static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg,
+						int node, gfp_t gfp_mask)
+{
+}
+#endif
+
 #ifdef CONFIG_MEMCG_SWAP
 extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
 extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h
index 06bd7b096167..e06febf62978 100644
--- a/include/linux/swapfile.h
+++ b/include/linux/swapfile.h
@@ -10,5 +10,7 @@ extern spinlock_t swap_lock;
 extern struct plist_head swap_active_head;
 extern struct swap_info_struct *swap_info[];
 extern int try_to_unuse(unsigned int, bool, unsigned long);
+extern unsigned long generic_max_swapfile_size(void);
+extern unsigned long max_swapfile_size(void);
 
 #endif /* _LINUX_SWAPFILE_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5c1a0933768e..ebb2f24027e8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -506,9 +506,9 @@ asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
 /* fs/timerfd.c */
 asmlinkage long sys_timerfd_create(int clockid, int flags);
 asmlinkage long sys_timerfd_settime(int ufd, int flags,
-				    const struct itimerspec __user *utmr,
-				    struct itimerspec __user *otmr);
-asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr);
+				    const struct __kernel_itimerspec __user *utmr,
+				    struct __kernel_itimerspec __user *otmr);
+asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user *otmr);
 
 /* fs/utimes.c */
 asmlinkage long sys_utimensat(int dfd, const char __user *filename,
@@ -573,10 +573,10 @@ asmlinkage long sys_timer_create(clockid_t which_clock,
 				 struct sigevent __user *timer_event_spec,
 				 timer_t __user * created_timer_id);
 asmlinkage long sys_timer_gettime(timer_t timer_id,
-				struct itimerspec __user *setting);
+				struct __kernel_itimerspec __user *setting);
 asmlinkage long sys_timer_getoverrun(timer_t timer_id);
 asmlinkage long sys_timer_settime(timer_t timer_id, int flags,
-				const struct itimerspec __user *new_setting,
+				const struct __kernel_itimerspec __user *new_setting,
 				struct itimerspec __user *old_setting);
 asmlinkage long sys_timer_delete(timer_t timer_id);
 asmlinkage long sys_clock_settime(clockid_t which_clock,
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index c6aa8a3c42ed..b9626aa7e90c 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -37,9 +37,33 @@ struct t10_pi_tuple {
 #define T10_PI_APP_ESCAPE cpu_to_be16(0xffff)
 #define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff)
 
+static inline u32 t10_pi_ref_tag(struct request *rq)
+{
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+	return blk_rq_pos(rq) >>
+		(rq->q->integrity.interval_exp - 9) & 0xffffffff;
+#else
+	return -1U;
+#endif
+}
+
 extern const struct blk_integrity_profile t10_pi_type1_crc;
 extern const struct blk_integrity_profile t10_pi_type1_ip;
 extern const struct blk_integrity_profile t10_pi_type3_crc;
 extern const struct blk_integrity_profile t10_pi_type3_ip;
 
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+extern void t10_pi_prepare(struct request *rq, u8 protection_type);
+extern void t10_pi_complete(struct request *rq, u8 protection_type,
+			    unsigned int intervals);
+#else
+static inline void t10_pi_complete(struct request *rq, u8 protection_type,
+				   unsigned int intervals)
+{
+}
+static inline void t10_pi_prepare(struct request *rq, u8 protection_type)
+{
+}
+#endif
+
 #endif
diff --git a/include/linux/time.h b/include/linux/time.h
index aed74463592d..27d83fd2ae61 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -14,9 +14,9 @@ int get_timespec64(struct timespec64 *ts,
 int put_timespec64(const struct timespec64 *ts,
 		struct __kernel_timespec __user *uts);
 int get_itimerspec64(struct itimerspec64 *it,
-			const struct itimerspec __user *uit);
+			const struct __kernel_itimerspec __user *uit);
 int put_itimerspec64(const struct itimerspec64 *it,
-			struct itimerspec __user *uit);
+			struct __kernel_itimerspec __user *uit);
 
 extern time64_t mktime64(const unsigned int year, const unsigned int mon,
 			const unsigned int day, const unsigned int hour,
diff --git a/include/linux/time64.h b/include/linux/time64.h
index 0a7b2f79cec7..05634afba0db 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -12,6 +12,7 @@ typedef __u64 timeu64_t;
  */
 #ifndef CONFIG_64BIT_TIME
 #define __kernel_timespec timespec
+#define __kernel_itimerspec itimerspec
 #endif
 
 #include <uapi/linux/time.h>
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 86bc2026efce..e79861418fd7 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -177,7 +177,7 @@ static inline time64_t ktime_get_clocktai_seconds(void)
 extern bool timekeeping_rtc_skipsuspend(void);
 extern bool timekeeping_rtc_skipresume(void);
 
-extern void timekeeping_inject_sleeptime64(struct timespec64 *delta);
+extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta);
 
 /*
  * struct system_time_snapshot - simultaneous raw/real time capture with
@@ -243,7 +243,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot);
 extern int persistent_clock_is_local;
 
 extern void read_persistent_clock64(struct timespec64 *ts);
-extern void read_boot_clock64(struct timespec64 *ts);
+void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock,
+					   struct timespec64 *boot_offset);
 extern int update_persistent_clock64(struct timespec64 now);
 
 /*
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 66272862070b..61dfd93b6ee4 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -64,6 +64,8 @@ struct torture_random_state {
 	long trs_count;
 };
 #define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 }
+#define DEFINE_TORTURE_RANDOM_PERCPU(name) \
+	DEFINE_PER_CPU(struct torture_random_state, name)
 unsigned long torture_random(struct torture_random_state *trsp);
 
 /* Task shuffler, which causes CPUs to occasionally go idle. */
@@ -79,7 +81,7 @@ void stutter_wait(const char *title);
 int torture_stutter_init(int s);
 
 /* Initialization and cleanup. */
-bool torture_init_begin(char *ttype, bool v);
+bool torture_init_begin(char *ttype, int v);
 void torture_init_end(void);
 bool torture_cleanup_begin(void);
 void torture_cleanup_end(void);
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 4a8841963c2e..05589a3e37f4 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -51,6 +51,7 @@
 #include <linux/security.h>
 #include <linux/task_work.h>
 #include <linux/memcontrol.h>
+#include <linux/blk-cgroup.h>
 struct linux_binprm;
 
 /*
@@ -192,6 +193,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 		task_work_run();
 
 	mem_cgroup_handle_over_high();
+	blkcg_maybe_throttle_current();
 }
 
 #endif	/* <linux/tracehook.h> */
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 9324ac2d9ff2..43913ae79f64 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -64,7 +64,8 @@ struct vsock_sock {
 	struct list_head pending_links;
 	struct list_head accept_queue;
 	bool rejected;
-	struct delayed_work dwork;
+	struct delayed_work connect_work;
+	struct delayed_work pending_work;
 	struct delayed_work close_work;
 	bool close_work_scheduled;
 	u32 peer_shutdown;
@@ -77,7 +78,6 @@ struct vsock_sock {
 
 s64 vsock_stream_has_data(struct vsock_sock *vsk);
 s64 vsock_stream_has_space(struct vsock_sock *vsk);
-void vsock_pending_work(struct work_struct *work);
 struct sock *__vsock_create(struct net *net,
 			    struct socket *sock,
 			    struct sock *parent,
diff --git a/include/net/llc.h b/include/net/llc.h
index dc35f25eb679..890a87318014 100644
--- a/include/net/llc.h
+++ b/include/net/llc.h
@@ -116,6 +116,11 @@ static inline void llc_sap_hold(struct llc_sap *sap)
 	refcount_inc(&sap->refcnt);
 }
 
+static inline bool llc_sap_hold_safe(struct llc_sap *sap)
+{
+	return refcount_inc_not_zero(&sap->refcnt);
+}
+
 void llc_sap_close(struct llc_sap *sap);
 
 static inline void llc_sap_put(struct llc_sap *sap)
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index aaf1e971c6a3..c891ada3c5c2 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -4,6 +4,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/blkdev.h>
+#include <linux/t10-pi.h>
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/timer.h>
@@ -14,8 +15,6 @@
 struct Scsi_Host;
 struct scsi_driver;
 
-#include <scsi/scsi_device.h>
-
 /*
  * MAX_COMMAND_SIZE is:
  * The longest fixed-length SCSI CDB as per the SCSI standard.
@@ -120,11 +119,11 @@ struct scsi_cmnd {
 	struct request *request;	/* The command we are
 				   	   working on */
 
-#define SCSI_SENSE_BUFFERSIZE 	96
 	unsigned char *sense_buffer;
 				/* obtained by REQUEST SENSE when
 				 * CHECK CONDITION is received on original
-				 * command (auto-sense) */
+				 * command (auto-sense). Length must be
+				 * SCSI_SENSE_BUFFERSIZE bytes. */
 
 	/* Low-level done function - can be used by low-level driver to point
 	 *        to completion function.  Not used by mid/upper level code. */
@@ -313,12 +312,6 @@ static inline unsigned int scsi_prot_interval(struct scsi_cmnd *scmd)
 	return scmd->device->sector_size;
 }
 
-static inline u32 scsi_prot_ref_tag(struct scsi_cmnd *scmd)
-{
-	return blk_rq_pos(scmd->request) >>
-		(ilog2(scsi_prot_interval(scmd)) - 9) & 0xffffffff;
-}
-
 static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd)
 {
 	return cmd->prot_sdb ? cmd->prot_sdb->table.nents : 0;
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 4c36af6edd79..202f4d6a4342 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -17,6 +17,8 @@ struct scsi_sense_hdr;
 
 typedef __u64 __bitwise blist_flags_t;
 
+#define SCSI_SENSE_BUFFERSIZE	96
+
 struct scsi_mode_data {
 	__u32	length;
 	__u16	block_descriptor_length;
@@ -426,11 +428,21 @@ extern const char *scsi_device_state_name(enum scsi_device_state);
 extern int scsi_is_sdev_device(const struct device *);
 extern int scsi_is_target_device(const struct device *);
 extern void scsi_sanitize_inquiry_string(unsigned char *s, int len);
-extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+extern int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 			int data_direction, void *buffer, unsigned bufflen,
 			unsigned char *sense, struct scsi_sense_hdr *sshdr,
 			int timeout, int retries, u64 flags,
 			req_flags_t rq_flags, int *resid);
+/* Make sure any sense buffer is the correct size. */
+#define scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense,	\
+		     sshdr, timeout, retries, flags, rq_flags, resid)	\
+({									\
+	BUILD_BUG_ON((sense) != NULL &&					\
+		     sizeof(sense) != SCSI_SENSE_BUFFERSIZE);		\
+	__scsi_execute(sdev, cmd, data_direction, buffer, bufflen,	\
+		       sense, sshdr, timeout, retries, flags, rq_flags,	\
+		       resid);						\
+})
 static inline int scsi_execute_req(struct scsi_device *sdev,
 	const unsigned char *cmd, int data_direction, void *buffer,
 	unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout,
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 39b94ec965be..b401c4e36394 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -374,7 +374,7 @@ DECLARE_EVENT_CLASS(
 		__entry->extent_type	= btrfs_file_extent_type(l, fi);
 		__entry->compression	= btrfs_file_extent_compression(l, fi);
 		__entry->extent_start	= start;
-		__entry->extent_end	= (start + btrfs_file_extent_inline_len(l, slot, fi));
+		__entry->extent_end	= (start + btrfs_file_extent_ram_bytes(l, fi));
 	),
 
 	TP_printk_btrfs(
@@ -433,7 +433,6 @@ DEFINE_EVENT(
 		{ (1 << BTRFS_ORDERED_DIRECT),	 	"DIRECT" 	}, \
 		{ (1 << BTRFS_ORDERED_IOERR), 		"IOERR" 	}, \
 		{ (1 << BTRFS_ORDERED_UPDATED_ISIZE), 	"UPDATED_ISIZE"	}, \
-		{ (1 << BTRFS_ORDERED_LOGGED_CSUM), 	"LOGGED_CSUM"	}, \
 		{ (1 << BTRFS_ORDERED_TRUNCATED), 	"TRUNCATED"	})
 
 
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index d1faf3597b9d..68b17c116907 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -112,8 +112,11 @@ DEFINE_EVENT(filelock_lock, locks_remove_posix,
 		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
 		TP_ARGS(inode, fl, ret));
 
-DECLARE_EVENT_CLASS(filelock_lease,
+DEFINE_EVENT(filelock_lock, flock_lock_inode,
+		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
+		TP_ARGS(inode, fl, ret));
 
+DECLARE_EVENT_CLASS(filelock_lease,
 	TP_PROTO(struct inode *inode, struct file_lock *fl),
 
 	TP_ARGS(inode, fl),
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 5936aac357ab..a8d07feff6a0 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -52,6 +52,7 @@ TRACE_EVENT(rcu_utilization,
  *	"cpuqs": CPU passes through a quiescent state.
  *	"cpuonl": CPU comes online.
  *	"cpuofl": CPU goes offline.
+ *	"cpuofl-bgp": CPU goes offline while blocking a grace period.
  *	"reqwait": GP kthread sleeps waiting for grace-period request.
  *	"reqwaitsig": GP kthread awakened by signal from reqwait state.
  *	"fqswait": GP kthread waiting until time to force quiescent states.
@@ -63,24 +64,24 @@ TRACE_EVENT(rcu_utilization,
  */
 TRACE_EVENT(rcu_grace_period,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, const char *gpevent),
 
-	TP_ARGS(rcuname, gpnum, gpevent),
+	TP_ARGS(rcuname, gp_seq, gpevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(const char *, gpevent)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->gpevent = gpevent;
 	),
 
 	TP_printk("%s %lu %s",
-		  __entry->rcuname, __entry->gpnum, __entry->gpevent)
+		  __entry->rcuname, __entry->gp_seq, __entry->gpevent)
 );
 
 /*
@@ -90,8 +91,8 @@ TRACE_EVENT(rcu_grace_period,
  *
  * "Startleaf": Request a grace period based on leaf-node data.
  * "Prestarted": Someone beat us to the request
- * "Startedleaf": Leaf-node start proved sufficient.
- * "Startedleafroot": Leaf-node start proved sufficient after checking root.
+ * "Startedleaf": Leaf node marked for future GP.
+ * "Startedleafroot": All nodes from leaf to root marked for future GP.
  * "Startedroot": Requested a nocb grace period based on root-node data.
  * "NoGPkthread": The RCU grace-period kthread has not yet started.
  * "StartWait": Start waiting for the requested grace period.
@@ -102,17 +103,16 @@ TRACE_EVENT(rcu_grace_period,
  */
 TRACE_EVENT(rcu_future_grace_period,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed,
-		 unsigned long c, u8 level, int grplo, int grphi,
+	TP_PROTO(const char *rcuname, unsigned long gp_seq,
+		 unsigned long gp_seq_req, u8 level, int grplo, int grphi,
 		 const char *gpevent),
 
-	TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent),
+	TP_ARGS(rcuname, gp_seq, gp_seq_req, level, grplo, grphi, gpevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
-		__field(unsigned long, completed)
-		__field(unsigned long, c)
+		__field(unsigned long, gp_seq)
+		__field(unsigned long, gp_seq_req)
 		__field(u8, level)
 		__field(int, grplo)
 		__field(int, grphi)
@@ -121,19 +121,17 @@ TRACE_EVENT(rcu_future_grace_period,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
-		__entry->completed = completed;
-		__entry->c = c;
+		__entry->gp_seq = gp_seq;
+		__entry->gp_seq_req = gp_seq_req;
 		__entry->level = level;
 		__entry->grplo = grplo;
 		__entry->grphi = grphi;
 		__entry->gpevent = gpevent;
 	),
 
-	TP_printk("%s %lu %lu %lu %u %d %d %s",
-		  __entry->rcuname, __entry->gpnum, __entry->completed,
-		  __entry->c, __entry->level, __entry->grplo, __entry->grphi,
-		  __entry->gpevent)
+	TP_printk("%s %lu %lu %u %d %d %s",
+		  __entry->rcuname, __entry->gp_seq, __entry->gp_seq_req, __entry->level,
+		  __entry->grplo, __entry->grphi, __entry->gpevent)
 );
 
 /*
@@ -145,14 +143,14 @@ TRACE_EVENT(rcu_future_grace_period,
  */
 TRACE_EVENT(rcu_grace_period_init,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level,
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, u8 level,
 		 int grplo, int grphi, unsigned long qsmask),
 
-	TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask),
+	TP_ARGS(rcuname, gp_seq, level, grplo, grphi, qsmask),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(u8, level)
 		__field(int, grplo)
 		__field(int, grphi)
@@ -161,7 +159,7 @@ TRACE_EVENT(rcu_grace_period_init,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->level = level;
 		__entry->grplo = grplo;
 		__entry->grphi = grphi;
@@ -169,7 +167,7 @@ TRACE_EVENT(rcu_grace_period_init,
 	),
 
 	TP_printk("%s %lu %u %d %d %lx",
-		  __entry->rcuname, __entry->gpnum, __entry->level,
+		  __entry->rcuname, __entry->gp_seq, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->qsmask)
 );
 
@@ -301,24 +299,24 @@ TRACE_EVENT(rcu_nocb_wake,
  */
 TRACE_EVENT(rcu_preempt_task,
 
-	TP_PROTO(const char *rcuname, int pid, unsigned long gpnum),
+	TP_PROTO(const char *rcuname, int pid, unsigned long gp_seq),
 
-	TP_ARGS(rcuname, pid, gpnum),
+	TP_ARGS(rcuname, pid, gp_seq),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(int, pid)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->pid = pid;
 	),
 
 	TP_printk("%s %lu %d",
-		  __entry->rcuname, __entry->gpnum, __entry->pid)
+		  __entry->rcuname, __entry->gp_seq, __entry->pid)
 );
 
 /*
@@ -328,23 +326,23 @@ TRACE_EVENT(rcu_preempt_task,
  */
 TRACE_EVENT(rcu_unlock_preempted_task,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, int pid),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, int pid),
 
-	TP_ARGS(rcuname, gpnum, pid),
+	TP_ARGS(rcuname, gp_seq, pid),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(int, pid)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->pid = pid;
 	),
 
-	TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid)
+	TP_printk("%s %lu %d", __entry->rcuname, __entry->gp_seq, __entry->pid)
 );
 
 /*
@@ -357,15 +355,15 @@ TRACE_EVENT(rcu_unlock_preempted_task,
  */
 TRACE_EVENT(rcu_quiescent_state_report,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum,
+	TP_PROTO(const char *rcuname, unsigned long gp_seq,
 		 unsigned long mask, unsigned long qsmask,
 		 u8 level, int grplo, int grphi, int gp_tasks),
 
-	TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks),
+	TP_ARGS(rcuname, gp_seq, mask, qsmask, level, grplo, grphi, gp_tasks),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(unsigned long, mask)
 		__field(unsigned long, qsmask)
 		__field(u8, level)
@@ -376,7 +374,7 @@ TRACE_EVENT(rcu_quiescent_state_report,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->mask = mask;
 		__entry->qsmask = qsmask;
 		__entry->level = level;
@@ -386,41 +384,41 @@ TRACE_EVENT(rcu_quiescent_state_report,
 	),
 
 	TP_printk("%s %lu %lx>%lx %u %d %d %u",
-		  __entry->rcuname, __entry->gpnum,
+		  __entry->rcuname, __entry->gp_seq,
 		  __entry->mask, __entry->qsmask, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->gp_tasks)
 );
 
 /*
  * 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, "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.
+ * 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, "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,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, int cpu, const char *qsevent),
 
-	TP_ARGS(rcuname, gpnum, cpu, qsevent),
+	TP_ARGS(rcuname, gp_seq, cpu, qsevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(int, cpu)
 		__field(const char *, qsevent)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->cpu = cpu;
 		__entry->qsevent = qsevent;
 	),
 
 	TP_printk("%s %lu %d %s",
-		  __entry->rcuname, __entry->gpnum,
+		  __entry->rcuname, __entry->gp_seq,
 		  __entry->cpu, __entry->qsevent)
 );
 
@@ -753,23 +751,23 @@ TRACE_EVENT(rcu_barrier,
 
 #else /* #ifdef CONFIG_RCU_TRACE */
 
-#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
-#define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \
+#define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0)
+#define trace_rcu_future_grace_period(rcuname, gp_seq, gp_seq_req, \
 				      level, grplo, grphi, event) \
 				      do { } while (0)
-#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
+#define trace_rcu_grace_period_init(rcuname, gp_seq, level, grplo, grphi, \
 				    qsmask) do { } while (0)
 #define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \
 	do { } while (0)
 #define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \
 	do { } while (0)
 #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0)
-#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
-#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
-#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
+#define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0)
+#define trace_rcu_unlock_preempted_task(rcuname, gp_seq, pid) do { } while (0)
+#define trace_rcu_quiescent_state_report(rcuname, gp_seq, mask, qsmask, level, \
 					 grplo, grphi, gp_tasks) do { } \
 	while (0)
-#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
+#define trace_rcu_fqs(rcuname, gp_seq, cpu, qsevent) do { } while (0)
 #define trace_rcu_dyntick(polarity, oldnesting, newnesting, dyntick) do { } while (0)
 #define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0)
 #define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index d4593a6062ef..ce43d340f010 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -38,10 +38,8 @@ enum {
 	IOCB_CMD_PWRITE = 1,
 	IOCB_CMD_FSYNC = 2,
 	IOCB_CMD_FDSYNC = 3,
-	/* These two are experimental.
-	 * IOCB_CMD_PREADX = 4,
-	 * IOCB_CMD_POLL = 5,
-	 */
+	/* 4 was the experimental IOCB_CMD_PREADX */
+	IOCB_CMD_POLL = 5,
 	IOCB_CMD_NOOP = 6,
 	IOCB_CMD_PREADV = 7,
 	IOCB_CMD_PWRITEV = 8,
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
index 821f71a2e48f..8d19e02d752a 100644
--- a/include/uapi/linux/bcache.h
+++ b/include/uapi/linux/bcache.h
@@ -195,7 +195,7 @@ struct cache_sb {
 	};
 	};
 
-	__u32			last_mount;	/* time_t */
+	__u32			last_mount;	/* time overflow in y2106 */
 
 	__u16			first_bucket;
 	union {
@@ -318,7 +318,7 @@ struct uuid_entry {
 		struct {
 			__u8	uuid[16];
 			__u8	label[32];
-			__u32	first_reg;
+			__u32	first_reg; /* time overflow in y2106 */
 			__u32	last_reg;
 			__u32	invalidated;
 
diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index e3c70fe6bf0f..ff5a5db8906a 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -117,7 +117,7 @@ struct blk_zone_report {
 	__u32		nr_zones;
 	__u8		reserved[4];
 	struct blk_zone zones[0];
-} __packed;
+};
 
 /**
  * struct blk_zone_range - BLKRESETZONE ioctl request
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 4e12c423b9fe..c5358e0ae7c5 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -422,6 +422,8 @@ typedef struct elf64_shdr {
 #define NT_ARM_SVE	0x405		/* ARM Scalable Vector Extension registers */
 #define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
 #define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
+#define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
+#define NT_MIPS_FP_MODE	0x801		/* MIPS floating-point mode */
 
 /* Note header in a PT_NOTE section */
 typedef struct elf32_note {
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index b6270a3b38e9..b955b986b341 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -949,6 +949,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
 #define KVM_CAP_HYPERV_TLBFLUSH 155
+#define KVM_CAP_S390_HPAGE_1M 156
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h
index fcf936656493..6b56a2208be7 100644
--- a/include/uapi/linux/time.h
+++ b/include/uapi/linux/time.h
@@ -49,6 +49,13 @@ struct __kernel_timespec {
 };
 #endif
 
+#ifndef __kernel_itimerspec
+struct __kernel_itimerspec {
+	struct __kernel_timespec it_interval;    /* timer period */
+	struct __kernel_timespec it_value;       /* timer expiration */
+};
+#endif
+
 /*
  * legacy timeval structure, only embedded in structures that
  * traditionally used 'timeval' to pass time intervals (not absolute
diff --git a/init/Kconfig b/init/Kconfig
index 041f3a022122..8b1ab81ecda8 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -125,10 +125,13 @@ config HAVE_KERNEL_LZO
 config HAVE_KERNEL_LZ4
 	bool
 
+config HAVE_KERNEL_UNCOMPRESSED
+	bool
+
 choice
 	prompt "Kernel compression mode"
 	default KERNEL_GZIP
-	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4
+	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_UNCOMPRESSED
 	help
 	  The linux kernel is a kind of self-extracting executable.
 	  Several compression algorithms are available, which differ
@@ -207,6 +210,16 @@ config KERNEL_LZ4
 	  is about 8% bigger than LZO. But the decompression speed is
 	  faster than LZO.
 
+config KERNEL_UNCOMPRESSED
+	bool "None"
+	depends on HAVE_KERNEL_UNCOMPRESSED
+	help
+	  Produce uncompressed kernel image. This option is usually not what
+	  you want. It is useful for debugging the kernel in slow simulation
+	  environments, where decompressing and moving the kernel is awfully
+	  slow. This option allows early boot code to skip the decompressor
+	  and jump right at uncompressed kernel image.
+
 endchoice
 
 config DEFAULT_HOSTNAME
diff --git a/init/main.c b/init/main.c
index 3b4ada11ed52..38c68b593d0d 100644
--- a/init/main.c
+++ b/init/main.c
@@ -79,7 +79,7 @@
 #include <linux/pti.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
-#include <linux/sched_clock.h>
+#include <linux/sched/clock.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/context_tracking.h>
@@ -561,8 +561,8 @@ asmlinkage __visible void __init start_kernel(void)
 	setup_command_line(command_line);
 	setup_nr_cpu_ids();
 	setup_per_cpu_areas();
-	boot_cpu_state_init();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
+	boot_cpu_hotplug_init();
 
 	build_all_zonelists(NULL);
 	page_alloc_init();
@@ -642,7 +642,6 @@ asmlinkage __visible void __init start_kernel(void)
 	softirq_init();
 	timekeeping_init();
 	time_init();
-	sched_clock_postinit();
 	printk_safe_init();
 	perf_event_init();
 	profile_init();
@@ -697,6 +696,7 @@ asmlinkage __visible void __init start_kernel(void)
 	acpi_early_init();
 	if (late_time_init)
 		late_time_init();
+	sched_clock_init();
 	calibrate_delay();
 	pid_idr_init();
 	anon_vma_init();
@@ -1065,6 +1065,13 @@ static int __ref kernel_init(void *unused)
 	jump_label_invalidate_initmem();
 	free_initmem();
 	mark_readonly();
+
+	/*
+	 * Kernel mappings are now finalized - update the userspace page-table
+	 * to finalize PTI.
+	 */
+	pti_finalize();
+
 	system_state = SYSTEM_RUNNING;
 	numa_default_policy();
 
diff --git a/ipc/shm.c b/ipc/shm.c
index fefa00d310fb..d8a38b3be5dd 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1366,15 +1366,14 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	struct shmid_kernel *shp;
 	unsigned long addr = (unsigned long)shmaddr;
 	unsigned long size;
-	struct file *file;
+	struct file *file, *base;
 	int    err;
 	unsigned long flags = MAP_SHARED;
 	unsigned long prot;
 	int acc_mode;
 	struct ipc_namespace *ns;
 	struct shm_file_data *sfd;
-	struct path path;
-	fmode_t f_mode;
+	int f_flags;
 	unsigned long populate = 0;
 
 	err = -EINVAL;
@@ -1407,11 +1406,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	if (shmflg & SHM_RDONLY) {
 		prot = PROT_READ;
 		acc_mode = S_IRUGO;
-		f_mode = FMODE_READ;
+		f_flags = O_RDONLY;
 	} else {
 		prot = PROT_READ | PROT_WRITE;
 		acc_mode = S_IRUGO | S_IWUGO;
-		f_mode = FMODE_READ | FMODE_WRITE;
+		f_flags = O_RDWR;
 	}
 	if (shmflg & SHM_EXEC) {
 		prot |= PROT_EXEC;
@@ -1447,46 +1446,44 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 		goto out_unlock;
 	}
 
-	path = shp->shm_file->f_path;
-	path_get(&path);
+	/*
+	 * We need to take a reference to the real shm file to prevent the
+	 * pointer from becoming stale in cases where the lifetime of the outer
+	 * file extends beyond that of the shm segment.  It's not usually
+	 * possible, but it can happen during remap_file_pages() emulation as
+	 * that unmaps the memory, then does ->mmap() via file reference only.
+	 * We'll deny the ->mmap() if the shm segment was since removed, but to
+	 * detect shm ID reuse we need to compare the file pointers.
+	 */
+	base = get_file(shp->shm_file);
 	shp->shm_nattch++;
-	size = i_size_read(d_inode(path.dentry));
+	size = i_size_read(file_inode(base));
 	ipc_unlock_object(&shp->shm_perm);
 	rcu_read_unlock();
 
 	err = -ENOMEM;
 	sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
 	if (!sfd) {
-		path_put(&path);
+		fput(base);
 		goto out_nattch;
 	}
 
-	file = alloc_file(&path, f_mode,
-			  is_file_hugepages(shp->shm_file) ?
+	file = alloc_file_clone(base, f_flags,
+			  is_file_hugepages(base) ?
 				&shm_file_operations_huge :
 				&shm_file_operations);
 	err = PTR_ERR(file);
 	if (IS_ERR(file)) {
 		kfree(sfd);
-		path_put(&path);
+		fput(base);
 		goto out_nattch;
 	}
 
-	file->private_data = sfd;
-	file->f_mapping = shp->shm_file->f_mapping;
 	sfd->id = shp->shm_perm.id;
 	sfd->ns = get_ipc_ns(ns);
-	/*
-	 * We need to take a reference to the real shm file to prevent the
-	 * pointer from becoming stale in cases where the lifetime of the outer
-	 * file extends beyond that of the shm segment.  It's not usually
-	 * possible, but it can happen during remap_file_pages() emulation as
-	 * that unmaps the memory, then does ->mmap() via file reference only.
-	 * We'll deny the ->mmap() if the shm segment was since removed, but to
-	 * detect shm ID reuse we need to compare the file pointers.
-	 */
-	sfd->file = get_file(shp->shm_file);
+	sfd->file = base;
 	sfd->vm_ops = NULL;
+	file->private_data = sfd;
 
 	err = security_mmap_file(file, prot, flags);
 	if (err)
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index e0918d180f08..46f5f29605d4 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -69,7 +69,7 @@ struct bpf_cpu_map {
 };
 
 static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
-			     struct xdp_bulk_queue *bq);
+			     struct xdp_bulk_queue *bq, bool in_napi_ctx);
 
 static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
 {
@@ -375,7 +375,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu)
 		struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
 
 		/* No concurrent bq_enqueue can run at this point */
-		bq_flush_to_queue(rcpu, bq);
+		bq_flush_to_queue(rcpu, bq, false);
 	}
 	free_percpu(rcpu->bulkq);
 	/* Cannot kthread_stop() here, last put free rcpu resources */
@@ -558,7 +558,7 @@ const struct bpf_map_ops cpu_map_ops = {
 };
 
 static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
-			     struct xdp_bulk_queue *bq)
+			     struct xdp_bulk_queue *bq, bool in_napi_ctx)
 {
 	unsigned int processed = 0, drops = 0;
 	const int to_cpu = rcpu->cpu;
@@ -578,7 +578,10 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
 		err = __ptr_ring_produce(q, xdpf);
 		if (err) {
 			drops++;
-			xdp_return_frame_rx_napi(xdpf);
+			if (likely(in_napi_ctx))
+				xdp_return_frame_rx_napi(xdpf);
+			else
+				xdp_return_frame(xdpf);
 		}
 		processed++;
 	}
@@ -598,7 +601,7 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
 
 	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
-		bq_flush_to_queue(rcpu, bq);
+		bq_flush_to_queue(rcpu, bq, true);
 
 	/* Notice, xdp_buff/page MUST be queued here, long enough for
 	 * driver to code invoking us to finished, due to driver
@@ -661,7 +664,7 @@ void __cpu_map_flush(struct bpf_map *map)
 
 		/* Flush all frames in bulkq to real queue */
 		bq = this_cpu_ptr(rcpu->bulkq);
-		bq_flush_to_queue(rcpu, bq);
+		bq_flush_to_queue(rcpu, bq, true);
 
 		/* If already running, costs spin_lock_irqsave + smb_mb */
 		wake_up_process(rcpu->kthread);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index d361fc1e3bf3..750d45edae79 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -217,7 +217,8 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit)
 }
 
 static int bq_xmit_all(struct bpf_dtab_netdev *obj,
-		       struct xdp_bulk_queue *bq, u32 flags)
+		       struct xdp_bulk_queue *bq, u32 flags,
+		       bool in_napi_ctx)
 {
 	struct net_device *dev = obj->dev;
 	int sent = 0, drops = 0, err = 0;
@@ -254,7 +255,10 @@ error:
 		struct xdp_frame *xdpf = bq->q[i];
 
 		/* RX path under NAPI protection, can return frames faster */
-		xdp_return_frame_rx_napi(xdpf);
+		if (likely(in_napi_ctx))
+			xdp_return_frame_rx_napi(xdpf);
+		else
+			xdp_return_frame(xdpf);
 		drops++;
 	}
 	goto out;
@@ -286,7 +290,7 @@ void __dev_map_flush(struct bpf_map *map)
 		__clear_bit(bit, bitmap);
 
 		bq = this_cpu_ptr(dev->bulkq);
-		bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+		bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
 	}
 }
 
@@ -316,7 +320,7 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
 	struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
 
 	if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
-		bq_xmit_all(obj, bq, 0);
+		bq_xmit_all(obj, bq, 0, true);
 
 	/* Ingress dev_rx will be the same for all xdp_frame's in
 	 * bulk_queue, because bq stored per-CPU and must be flushed
@@ -385,7 +389,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
 			__clear_bit(dev->bit, bitmap);
 
 			bq = per_cpu_ptr(dev->bulkq, cpu);
-			bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+			bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
 		}
 	}
 }
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 98fb7938beea..c4d75c52b4fc 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -1048,12 +1048,12 @@ static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
 	while (msg_data_left(msg)) {
-		struct sk_msg_buff *m;
+		struct sk_msg_buff *m = NULL;
 		bool enospc = false;
 		int copy;
 
 		if (sk->sk_err) {
-			err = sk->sk_err;
+			err = -sk->sk_err;
 			goto out_err;
 		}
 
@@ -1116,8 +1116,11 @@ wait_for_sndbuf:
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
 		err = sk_stream_wait_memory(sk, &timeo);
-		if (err)
+		if (err) {
+			if (m && m != psock->cork)
+				free_start_sg(sk, m);
 			goto out_err;
+		}
 	}
 out_err:
 	if (err < 0)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a31a1ba0f8ea..b41c6cf2eb88 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -575,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
 {
 	int refold;
 
-	refold = __atomic_add_unless(&map->refcnt, 1, 0);
+	refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
 
 	if (refold >= BPF_MAX_REFCNT) {
 		__bpf_map_put(map, false);
@@ -1144,7 +1144,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 {
 	int refold;
 
-	refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+	refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
 
 	if (refold >= BPF_MAX_REFCNT) {
 		__bpf_prog_put(prog, false);
diff --git a/kernel/compat.c b/kernel/compat.c
index 702aa846ddac..8e40efc2928a 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -324,35 +324,6 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t,  pid, unsigned int, len,
 	return ret;
 }
 
-/* Todo: Delete these extern declarations when get/put_compat_itimerspec64()
- * are moved to kernel/time/time.c .
- */
-extern int __compat_get_timespec64(struct timespec64 *ts64,
-				   const struct compat_timespec __user *cts);
-extern int __compat_put_timespec64(const struct timespec64 *ts64,
-				   struct compat_timespec __user *cts);
-
-int get_compat_itimerspec64(struct itimerspec64 *its,
-			const struct compat_itimerspec __user *uits)
-{
-
-	if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
-	    __compat_get_timespec64(&its->it_value, &uits->it_value))
-		return -EFAULT;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
-
-int put_compat_itimerspec64(const struct itimerspec64 *its,
-			struct compat_itimerspec __user *uits)
-{
-	if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
-	    __compat_put_timespec64(&its->it_value, &uits->it_value))
-		return -EFAULT;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
-
 /*
  * We currently only need the following fields from the sigevent
  * structure: sigev_value, sigev_signo, sig_notify and (sometimes
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0db8938fbb23..099fb20cd7be 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -60,6 +60,7 @@ struct cpuhp_cpu_state {
 	bool			rollback;
 	bool			single;
 	bool			bringup;
+	bool			booted_once;
 	struct hlist_node	*node;
 	struct hlist_node	*last;
 	enum cpuhp_state	cb_state;
@@ -342,6 +343,85 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
+#ifdef CONFIG_HOTPLUG_SMT
+enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+EXPORT_SYMBOL_GPL(cpu_smt_control);
+
+static bool cpu_smt_available __read_mostly;
+
+void __init cpu_smt_disable(bool force)
+{
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
+		cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		return;
+
+	if (force) {
+		pr_info("SMT: Force disabled\n");
+		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
+	} else {
+		cpu_smt_control = CPU_SMT_DISABLED;
+	}
+}
+
+/*
+ * The decision whether SMT is supported can only be done after the full
+ * CPU identification. Called from architecture code before non boot CPUs
+ * are brought up.
+ */
+void __init cpu_smt_check_topology_early(void)
+{
+	if (!topology_smt_supported())
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
+/*
+ * If SMT was disabled by BIOS, detect it here, after the CPUs have been
+ * brought online. This ensures the smt/l1tf sysfs entries are consistent
+ * with reality. cpu_smt_available is set to true during the bringup of non
+ * boot CPUs when a SMT sibling is detected. Note, this may overwrite
+ * cpu_smt_control's previous setting.
+ */
+void __init cpu_smt_check_topology(void)
+{
+	if (!cpu_smt_available)
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
+static int __init smt_cmdline_disable(char *str)
+{
+	cpu_smt_disable(str && !strcmp(str, "force"));
+	return 0;
+}
+early_param("nosmt", smt_cmdline_disable);
+
+static inline bool cpu_smt_allowed(unsigned int cpu)
+{
+	if (topology_is_primary_thread(cpu))
+		return true;
+
+	/*
+	 * If the CPU is not a 'primary' thread and the booted_once bit is
+	 * set then the processor has SMT support. Store this information
+	 * for the late check of SMT support in cpu_smt_check_topology().
+	 */
+	if (per_cpu(cpuhp_state, cpu).booted_once)
+		cpu_smt_available = true;
+
+	if (cpu_smt_control == CPU_SMT_ENABLED)
+		return true;
+
+	/*
+	 * On x86 it's required to boot all logical CPUs at least once so
+	 * that the init code can get a chance to set CR4.MCE on each
+	 * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
+	 * core will shutdown the machine.
+	 */
+	return !per_cpu(cpuhp_state, cpu).booted_once;
+}
+#else
+static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
+#endif
+
 static inline enum cpuhp_state
 cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
 {
@@ -422,6 +502,16 @@ static int bringup_wait_for_ap(unsigned int cpu)
 	stop_machine_unpark(cpu);
 	kthread_unpark(st->thread);
 
+	/*
+	 * SMT soft disabling on X86 requires to bring the CPU out of the
+	 * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit.  The
+	 * CPU marked itself as booted_once in cpu_notify_starting() so the
+	 * cpu_smt_allowed() check will now return false if this is not the
+	 * primary sibling.
+	 */
+	if (!cpu_smt_allowed(cpu))
+		return -ECANCELED;
+
 	if (st->target <= CPUHP_AP_ONLINE_IDLE)
 		return 0;
 
@@ -754,7 +844,6 @@ static int takedown_cpu(unsigned int cpu)
 
 	/* Park the smpboot threads */
 	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
-	smpboot_park_threads(cpu);
 
 	/*
 	 * Prevent irq alloc/free while the dying cpu reorganizes the
@@ -907,20 +996,19 @@ out:
 	return ret;
 }
 
+static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
+{
+	if (cpu_hotplug_disabled)
+		return -EBUSY;
+	return _cpu_down(cpu, 0, target);
+}
+
 static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
 {
 	int err;
 
 	cpu_maps_update_begin();
-
-	if (cpu_hotplug_disabled) {
-		err = -EBUSY;
-		goto out;
-	}
-
-	err = _cpu_down(cpu, 0, target);
-
-out:
+	err = cpu_down_maps_locked(cpu, target);
 	cpu_maps_update_done();
 	return err;
 }
@@ -949,6 +1037,7 @@ void notify_cpu_starting(unsigned int cpu)
 	int ret;
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
+	st->booted_once = true;
 	while (st->state < target) {
 		st->state++;
 		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
@@ -1058,6 +1147,10 @@ static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
 		err = -EBUSY;
 		goto out;
 	}
+	if (!cpu_smt_allowed(cpu)) {
+		err = -EPERM;
+		goto out;
+	}
 
 	err = _cpu_up(cpu, 0, target);
 out:
@@ -1274,7 +1367,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	 * otherwise a RCU stall occurs.
 	 */
 	[CPUHP_TIMERS_PREPARE] = {
-		.name			= "timers:dead",
+		.name			= "timers:prepare",
 		.startup.single		= timers_prepare_cpu,
 		.teardown.single	= timers_dead_cpu,
 	},
@@ -1332,7 +1425,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_AP_SMPBOOT_THREADS] = {
 		.name			= "smpboot/threads:online",
 		.startup.single		= smpboot_unpark_threads,
-		.teardown.single	= NULL,
+		.teardown.single	= smpboot_park_threads,
 	},
 	[CPUHP_AP_IRQ_AFFINITY_ONLINE] = {
 		.name			= "irq/affinity:online",
@@ -1344,6 +1437,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= perf_event_init_cpu,
 		.teardown.single	= perf_event_exit_cpu,
 	},
+	[CPUHP_AP_WATCHDOG_ONLINE] = {
+		.name			= "lockup_detector:online",
+		.startup.single		= lockup_detector_online_cpu,
+		.teardown.single	= lockup_detector_offline_cpu,
+	},
 	[CPUHP_AP_WORKQUEUE_ONLINE] = {
 		.name			= "workqueue:online",
 		.startup.single		= workqueue_online_cpu,
@@ -1906,10 +2004,172 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
 	NULL
 };
 
+#ifdef CONFIG_HOTPLUG_SMT
+
+static const char *smt_states[] = {
+	[CPU_SMT_ENABLED]		= "on",
+	[CPU_SMT_DISABLED]		= "off",
+	[CPU_SMT_FORCE_DISABLED]	= "forceoff",
+	[CPU_SMT_NOT_SUPPORTED]		= "notsupported",
+};
+
+static ssize_t
+show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
+}
+
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = true;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = false;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	for_each_online_cpu(cpu) {
+		if (topology_is_primary_thread(cpu))
+			continue;
+		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+		if (ret)
+			break;
+		/*
+		 * As this needs to hold the cpu maps lock it's impossible
+		 * to call device_offline() because that ends up calling
+		 * cpu_down() which takes cpu maps lock. cpu maps lock
+		 * needs to be held as this might race against in kernel
+		 * abusers of the hotplug machinery (thermal management).
+		 *
+		 * So nothing would update device:offline state. That would
+		 * leave the sysfs entry stale and prevent onlining after
+		 * smt control has been changed to 'off' again. This is
+		 * called under the sysfs hotplug lock, so it is properly
+		 * serialized against the regular offline usage.
+		 */
+		cpuhp_offline_cpu_device(cpu);
+	}
+	if (!ret)
+		cpu_smt_control = ctrlval;
+	cpu_maps_update_done();
+	return ret;
+}
+
+static int cpuhp_smt_enable(void)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	cpu_smt_control = CPU_SMT_ENABLED;
+	for_each_present_cpu(cpu) {
+		/* Skip online CPUs and CPUs on offline nodes */
+		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+			continue;
+		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+		if (ret)
+			break;
+		/* See comment in cpuhp_smt_disable() */
+		cpuhp_online_cpu_device(cpu);
+	}
+	cpu_maps_update_done();
+	return ret;
+}
+
+static ssize_t
+store_smt_control(struct device *dev, struct device_attribute *attr,
+		  const char *buf, size_t count)
+{
+	int ctrlval, ret;
+
+	if (sysfs_streq(buf, "on"))
+		ctrlval = CPU_SMT_ENABLED;
+	else if (sysfs_streq(buf, "off"))
+		ctrlval = CPU_SMT_DISABLED;
+	else if (sysfs_streq(buf, "forceoff"))
+		ctrlval = CPU_SMT_FORCE_DISABLED;
+	else
+		return -EINVAL;
+
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
+		return -EPERM;
+
+	if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		return -ENODEV;
+
+	ret = lock_device_hotplug_sysfs();
+	if (ret)
+		return ret;
+
+	if (ctrlval != cpu_smt_control) {
+		switch (ctrlval) {
+		case CPU_SMT_ENABLED:
+			ret = cpuhp_smt_enable();
+			break;
+		case CPU_SMT_DISABLED:
+		case CPU_SMT_FORCE_DISABLED:
+			ret = cpuhp_smt_disable(ctrlval);
+			break;
+		}
+	}
+
+	unlock_device_hotplug();
+	return ret ? ret : count;
+}
+static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
+
+static ssize_t
+show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	bool active = topology_max_smt_threads() > 1;
+
+	return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
+}
+static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
+
+static struct attribute *cpuhp_smt_attrs[] = {
+	&dev_attr_control.attr,
+	&dev_attr_active.attr,
+	NULL
+};
+
+static const struct attribute_group cpuhp_smt_attr_group = {
+	.attrs = cpuhp_smt_attrs,
+	.name = "smt",
+	NULL
+};
+
+static int __init cpu_smt_state_init(void)
+{
+	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
+				  &cpuhp_smt_attr_group);
+}
+
+#else
+static inline int cpu_smt_state_init(void) { return 0; }
+#endif
+
 static int __init cpuhp_sysfs_init(void)
 {
 	int cpu, ret;
 
+	ret = cpu_smt_state_init();
+	if (ret)
+		return ret;
+
 	ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
 				 &cpuhp_cpu_root_attr_group);
 	if (ret)
@@ -2010,7 +2270,8 @@ void __init boot_cpu_init(void)
 /*
  * Must be called _AFTER_ setting up the per_cpu areas
  */
-void __init boot_cpu_state_init(void)
+void __init boot_cpu_hotplug_init(void)
 {
-	per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
+	this_cpu_write(cpuhp_state.booted_once, true);
+	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 }
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8be8106270c2..c2860c5a9e96 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -180,10 +180,10 @@ int dma_direct_supported(struct device *dev, u64 mask)
 		return 0;
 #endif
 	/*
-	 * Various PCI/PCIe bridges have broken support for > 32bit DMA even
-	 * if the device itself might support it.
+	 * Upstream PCI/PCIe bridges or SoC interconnects may not carry
+	 * as many DMA address bits as the device itself supports.
 	 */
-	if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32))
+	if (dev->bus_dma_mask && mask > dev->bus_dma_mask)
 		return 0;
 	return 1;
 }
diff --git a/kernel/dma/noncoherent.c b/kernel/dma/noncoherent.c
index 79e9a757387f..031fe235d958 100644
--- a/kernel/dma/noncoherent.c
+++ b/kernel/dma/noncoherent.c
@@ -49,11 +49,13 @@ static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
 	return nents;
 }
 
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
 	arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
+	arch_sync_dma_for_cpu_all(dev);
 }
 
 static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
@@ -64,6 +66,7 @@ static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
 
 	for_each_sg(sgl, sg, nents, i)
 		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+	arch_sync_dma_for_cpu_all(dev);
 }
 
 static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
@@ -89,7 +92,8 @@ const struct dma_map_ops dma_noncoherent_ops = {
 	.sync_sg_for_device	= dma_noncoherent_sync_sg_for_device,
 	.map_page		= dma_noncoherent_map_page,
 	.map_sg			= dma_noncoherent_map_sg,
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 	.sync_single_for_cpu	= dma_noncoherent_sync_single_for_cpu,
 	.sync_sg_for_cpu	= dma_noncoherent_sync_sg_for_cpu,
 	.unmap_page		= dma_noncoherent_unmap_page,
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 904541055792..4f8a6dbf0b60 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -17,6 +17,8 @@
  * 08/12/11 beckyb	Add highmem support
  */
 
+#define pr_fmt(fmt) "software IO TLB: " fmt
+
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
 #include <linux/mm.h>
@@ -162,20 +164,16 @@ static bool no_iotlb_memory;
 void swiotlb_print_info(void)
 {
 	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-	unsigned char *vstart, *vend;
 
 	if (no_iotlb_memory) {
-		pr_warn("software IO TLB: No low mem\n");
+		pr_warn("No low mem\n");
 		return;
 	}
 
-	vstart = phys_to_virt(io_tlb_start);
-	vend = phys_to_virt(io_tlb_end);
-
-	printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+	pr_info("mapped [mem %#010llx-%#010llx] (%luMB)\n",
 	       (unsigned long long)io_tlb_start,
 	       (unsigned long long)io_tlb_end,
-	       bytes >> 20, vstart, vend - 1);
+	       bytes >> 20);
 }
 
 /*
@@ -275,7 +273,7 @@ swiotlb_init(int verbose)
 	if (io_tlb_start)
 		memblock_free_early(io_tlb_start,
 				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
-	pr_warn("Cannot allocate SWIOTLB buffer");
+	pr_warn("Cannot allocate buffer");
 	no_iotlb_memory = true;
 }
 
@@ -317,8 +315,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
 		return -ENOMEM;
 	}
 	if (order != get_order(bytes)) {
-		printk(KERN_WARNING "Warning: only able to allocate %ld MB "
-		       "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+		pr_warn("only able to allocate %ld MB\n",
+			(PAGE_SIZE << order) >> 20);
 		io_tlb_nslabs = SLABS_PER_PAGE << order;
 	}
 	rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index eec2d5fb676b..f6ea33a9f904 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1656,7 +1656,7 @@ perf_event_groups_next(struct perf_event *event)
 				typeof(*event), group_node))
 
 /*
- * Add a event from the lists for its context.
+ * Add an event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
  */
 static void
@@ -1844,7 +1844,7 @@ static void perf_group_attach(struct perf_event *event)
 }
 
 /*
- * Remove a event from the lists for its context.
+ * Remove an event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
  */
 static void
@@ -2148,7 +2148,7 @@ static void __perf_event_disable(struct perf_event *event,
 }
 
 /*
- * Disable a event.
+ * Disable an event.
  *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
@@ -2677,7 +2677,7 @@ static void __perf_event_enable(struct perf_event *event,
 }
 
 /*
- * Enable a event.
+ * Enable an event.
  *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
@@ -2755,7 +2755,7 @@ static int __perf_event_stop(void *info)
 	 * events will refuse to restart because of rb::aux_mmap_count==0,
 	 * see comments in perf_aux_output_begin().
 	 *
-	 * Since this is happening on a event-local CPU, no trace is lost
+	 * Since this is happening on an event-local CPU, no trace is lost
 	 * while restarting.
 	 */
 	if (sd->restart)
@@ -4827,7 +4827,7 @@ __perf_read(struct perf_event *event, char __user *buf, size_t count)
 	int ret;
 
 	/*
-	 * Return end-of-file for a read on a event that is in
+	 * Return end-of-file for a read on an event that is in
 	 * error state (i.e. because it was pinned but it couldn't be
 	 * scheduled on to the CPU at some point).
 	 */
@@ -5273,11 +5273,11 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(perf_event_update_userpage);
 
-static int perf_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t perf_mmap_fault(struct vm_fault *vmf)
 {
 	struct perf_event *event = vmf->vma->vm_file->private_data;
 	struct ring_buffer *rb;
-	int ret = VM_FAULT_SIGBUS;
+	vm_fault_t ret = VM_FAULT_SIGBUS;
 
 	if (vmf->flags & FAULT_FLAG_MKWRITE) {
 		if (vmf->pgoff == 0)
@@ -9904,7 +9904,7 @@ enabled:
 }
 
 /*
- * Allocate and initialize a event structure
+ * Allocate and initialize an event structure
  */
 static struct perf_event *
 perf_event_alloc(struct perf_event_attr *attr, int cpu,
@@ -11235,7 +11235,7 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
 }
 
 /*
- * Inherit a event from parent task to child task.
+ * Inherit an event from parent task to child task.
  *
  * Returns:
  *  - valid pointer on success
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 6e28d2866be5..b3814fce5ecb 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -345,13 +345,13 @@ void release_bp_slot(struct perf_event *bp)
 	mutex_unlock(&nr_bp_mutex);
 }
 
-static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 {
 	int err;
 
 	__release_bp_slot(bp, old_type);
 
-	err = __reserve_bp_slot(bp, bp->attr.bp_type);
+	err = __reserve_bp_slot(bp, new_type);
 	if (err) {
 		/*
 		 * Reserve the old_type slot back in case
@@ -367,12 +367,12 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
 	return err;
 }
 
-static int modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 {
 	int ret;
 
 	mutex_lock(&nr_bp_mutex);
-	ret = __modify_bp_slot(bp, old_type);
+	ret = __modify_bp_slot(bp, old_type, new_type);
 	mutex_unlock(&nr_bp_mutex);
 	return ret;
 }
@@ -400,16 +400,18 @@ int dbg_release_bp_slot(struct perf_event *bp)
 	return 0;
 }
 
-static int validate_hw_breakpoint(struct perf_event *bp)
+static int hw_breakpoint_parse(struct perf_event *bp,
+			       const struct perf_event_attr *attr,
+			       struct arch_hw_breakpoint *hw)
 {
-	int ret;
+	int err;
 
-	ret = arch_validate_hwbkpt_settings(bp);
-	if (ret)
-		return ret;
+	err = hw_breakpoint_arch_parse(bp, attr, hw);
+	if (err)
+		return err;
 
-	if (arch_check_bp_in_kernelspace(bp)) {
-		if (bp->attr.exclude_kernel)
+	if (arch_check_bp_in_kernelspace(hw)) {
+		if (attr->exclude_kernel)
 			return -EINVAL;
 		/*
 		 * Don't let unprivileged users set a breakpoint in the trap
@@ -424,19 +426,22 @@ static int validate_hw_breakpoint(struct perf_event *bp)
 
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
-	int ret;
-
-	ret = reserve_bp_slot(bp);
-	if (ret)
-		return ret;
+	struct arch_hw_breakpoint hw;
+	int err;
 
-	ret = validate_hw_breakpoint(bp);
+	err = reserve_bp_slot(bp);
+	if (err)
+		return err;
 
-	/* if arch_validate_hwbkpt_settings() fails then release bp slot */
-	if (ret)
+	err = hw_breakpoint_parse(bp, &bp->attr, &hw);
+	if (err) {
 		release_bp_slot(bp);
+		return err;
+	}
 
-	return ret;
+	bp->hw.info = hw;
+
+	return 0;
 }
 
 /**
@@ -456,35 +461,44 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
+static void hw_breakpoint_copy_attr(struct perf_event_attr *to,
+				    struct perf_event_attr *from)
+{
+	to->bp_addr = from->bp_addr;
+	to->bp_type = from->bp_type;
+	to->bp_len  = from->bp_len;
+	to->disabled = from->disabled;
+}
+
 int
 modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
 			        bool check)
 {
-	u64 old_addr = bp->attr.bp_addr;
-	u64 old_len  = bp->attr.bp_len;
-	int old_type = bp->attr.bp_type;
-	bool modify  = attr->bp_type != old_type;
-	int err = 0;
+	struct arch_hw_breakpoint hw;
+	int err;
 
-	bp->attr.bp_addr = attr->bp_addr;
-	bp->attr.bp_type = attr->bp_type;
-	bp->attr.bp_len  = attr->bp_len;
+	err = hw_breakpoint_parse(bp, attr, &hw);
+	if (err)
+		return err;
 
-	if (check && memcmp(&bp->attr, attr, sizeof(*attr)))
-		return -EINVAL;
+	if (check) {
+		struct perf_event_attr old_attr;
 
-	err = validate_hw_breakpoint(bp);
-	if (!err && modify)
-		err = modify_bp_slot(bp, old_type);
+		old_attr = bp->attr;
+		hw_breakpoint_copy_attr(&old_attr, attr);
+		if (memcmp(&old_attr, attr, sizeof(*attr)))
+			return -EINVAL;
+	}
 
-	if (err) {
-		bp->attr.bp_addr = old_addr;
-		bp->attr.bp_type = old_type;
-		bp->attr.bp_len  = old_len;
-		return err;
+	if (bp->attr.bp_type != attr->bp_type) {
+		err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type);
+		if (err)
+			return err;
 	}
 
-	bp->attr.disabled = attr->disabled;
+	hw_breakpoint_copy_attr(&bp->attr, attr);
+	bp->hw.info = hw;
+
 	return 0;
 }
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ccc579a7d32e..aed1ba569954 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -918,7 +918,7 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 EXPORT_SYMBOL_GPL(uprobe_register);
 
 /*
- * uprobe_apply - unregister a already registered probe.
+ * uprobe_apply - unregister an already registered probe.
  * @inode: the file in which the probe has to be removed.
  * @offset: offset from the start of the file.
  * @uc: consumer which wants to add more or remove some breakpoints
@@ -947,7 +947,7 @@ int uprobe_apply(struct inode *inode, loff_t offset,
 }
 
 /*
- * uprobe_unregister - unregister a already registered probe.
+ * uprobe_unregister - unregister an already registered probe.
  * @inode: the file in which the probe has to be removed.
  * @offset: offset from the start of the file.
  * @uc: identify which probe if multiple probes are colocated.
@@ -1403,7 +1403,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri)
 
 /*
  * Called with no locks held.
- * Called in context of a exiting or a exec-ing thread.
+ * Called in context of an exiting or an exec-ing thread.
  */
 void uprobe_free_utask(struct task_struct *t)
 {
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 5349c91c2298..bc80a4e268c0 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -184,9 +184,6 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
 	if (should_fail(&fei_fault_attr, 1)) {
 		regs_set_return_value(regs, attr->retval);
 		override_function_with_return(regs);
-		/* Kprobe specific fixup */
-		reset_current_kprobe();
-		preempt_enable_no_resched();
 		return 1;
 	}
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 1b27babc4c78..33112315b5c0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -866,6 +866,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->fail_nth = 0;
 #endif
 
+#ifdef CONFIG_BLK_CGROUP
+	tsk->throttle_queue = NULL;
+	tsk->use_memdelay = 0;
+#endif
+
 	return tsk;
 
 free_stack:
@@ -2276,6 +2281,8 @@ static void sighand_ctor(void *data)
 
 void __init proc_caches_init(void)
 {
+	unsigned int mm_size;
+
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -2292,15 +2299,16 @@ void __init proc_caches_init(void)
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			NULL);
+
 	/*
-	 * FIXME! The "sizeof(struct mm_struct)" currently includes the
-	 * whole struct cpumask for the OFFSTACK case. We could change
-	 * this to *only* allocate as much of it as required by the
-	 * maximum number of CPU's we can ever have.  The cpumask_allocation
-	 * is at the end of the structure, exactly for that reason.
+	 * The mm_cpumask is located at the end of mm_struct, and is
+	 * dynamically sized based on the maximum CPU number this system
+	 * can have, taking hotplug into account (nr_cpu_ids).
 	 */
+	mm_size = sizeof(struct mm_struct) + cpumask_size();
+
 	mm_cachep = kmem_cache_create_usercopy("mm_struct",
-			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
+			mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			offsetof(struct mm_struct, saved_auxv),
 			sizeof_field(struct mm_struct, saved_auxv),
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index c6766f326072..5f3e2baefca9 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -134,7 +134,6 @@ config GENERIC_IRQ_DEBUGFS
 endmenu
 
 config GENERIC_IRQ_MULTI_HANDLER
-	depends on !MULTI_IRQ_HANDLER
 	bool
 	help
 	  Allow to specify the low level IRQ handler at run time.
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index afc7f902d74a..578d0e5f1b5b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -443,6 +443,7 @@ static void free_desc(unsigned int irq)
 	 * We free the descriptor, masks and stat fields via RCU. That
 	 * allows demultiplex interrupts to do rcu based management of
 	 * the child interrupts.
+	 * This also allows us to use rcu in kstat_irqs_usr().
 	 */
 	call_rcu(&desc->rcu, delayed_free_desc);
 }
@@ -928,17 +929,17 @@ unsigned int kstat_irqs(unsigned int irq)
  * kstat_irqs_usr - Get the statistics for an interrupt
  * @irq:	The interrupt number
  *
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. Contrary to kstat_irqs() this can be called from any
- * preemptible context. It's protected against concurrent removal of
- * an interrupt descriptor when sparse irqs are enabled.
+ * Returns the sum of interrupt counts on all cpus since boot for @irq.
+ * Contrary to kstat_irqs() this can be called from any context.
+ * It uses rcu since a concurrent removal of an interrupt descriptor is
+ * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
 	unsigned int sum;
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	sum = kstat_irqs(irq);
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return sum;
 }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9a8b7ba9aa88..fb86146037a7 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -790,9 +790,19 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
 
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
-	set_current_state(TASK_INTERRUPTIBLE);
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
 
-	while (!kthread_should_stop()) {
+		if (kthread_should_stop()) {
+			/* may need to run one last time */
+			if (test_and_clear_bit(IRQTF_RUNTHREAD,
+					       &action->thread_flags)) {
+				__set_current_state(TASK_RUNNING);
+				return 0;
+			}
+			__set_current_state(TASK_RUNNING);
+			return -1;
+		}
 
 		if (test_and_clear_bit(IRQTF_RUNTHREAD,
 				       &action->thread_flags)) {
@@ -800,10 +810,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 			return 0;
 		}
 		schedule();
-		set_current_state(TASK_INTERRUPTIBLE);
 	}
-	__set_current_state(TASK_RUNNING);
-	return -1;
 }
 
 /*
@@ -1024,11 +1031,8 @@ static int irq_thread(void *data)
 	/*
 	 * This is the regular exit path. __free_irq() is stopping the
 	 * thread via kthread_stop() after calling
-	 * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
-	 * oneshot mask bit can be set. We cannot verify that as we
-	 * cannot touch the oneshot mask at this point anymore as
-	 * __setup_irq() might have given out currents thread_mask
-	 * again.
+	 * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
+	 * oneshot mask bit can be set.
 	 */
 	task_work_cancel(current, irq_thread_dtor);
 	return 0;
@@ -1251,8 +1255,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	/*
 	 * Protects against a concurrent __free_irq() call which might wait
-	 * for synchronize_irq() to complete without holding the optional
-	 * chip bus lock and desc->lock.
+	 * for synchronize_hardirq() to complete without holding the optional
+	 * chip bus lock and desc->lock. Also protects against handing out
+	 * a recycled oneshot thread_mask bit while it's still in use by
+	 * its previous owner.
 	 */
 	mutex_lock(&desc->request_mutex);
 
@@ -1571,9 +1577,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 
 	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
 
-	if (!desc)
-		return NULL;
-
 	mutex_lock(&desc->request_mutex);
 	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
@@ -1620,11 +1623,11 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	/*
 	 * Drop bus_lock here so the changes which were done in the chip
 	 * callbacks above are synced out to the irq chips which hang
-	 * behind a slow bus (I2C, SPI) before calling synchronize_irq().
+	 * behind a slow bus (I2C, SPI) before calling synchronize_hardirq().
 	 *
 	 * Aside of that the bus_lock can also be taken from the threaded
 	 * handler in irq_finalize_oneshot() which results in a deadlock
-	 * because synchronize_irq() would wait forever for the thread to
+	 * because kthread_stop() would wait forever for the thread to
 	 * complete, which is blocked on the bus lock.
 	 *
 	 * The still held desc->request_mutex() protects against a
@@ -1636,7 +1639,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	unregister_handler_proc(irq, action);
 
 	/* Make sure it's not being used on another CPU: */
-	synchronize_irq(irq);
+	synchronize_hardirq(irq);
 
 #ifdef CONFIG_DEBUG_SHIRQ
 	/*
@@ -1645,7 +1648,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	 * is so by doing an extra call to the handler ....
 	 *
 	 * ( We do this after actually deregistering it, to make sure that a
-	 *   'real' IRQ doesn't run in * parallel with our fake. )
+	 *   'real' IRQ doesn't run in parallel with our fake. )
 	 */
 	if (action->flags & IRQF_SHARED) {
 		local_irq_save(flags);
@@ -1654,6 +1657,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	}
 #endif
 
+	/*
+	 * The action has already been removed above, but the thread writes
+	 * its oneshot mask bit when it completes. Though request_mutex is
+	 * held across this which prevents __setup_irq() from handing out
+	 * the same bit to a newly requested action.
+	 */
 	if (action->thread) {
 		kthread_stop(action->thread);
 		put_task_struct(action->thread);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 37eda10f5c36..da9addb8d655 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -475,22 +475,24 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	desc = irq_to_desc(i);
 	if (!desc)
 		goto outsparse;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for_each_online_cpu(j)
-		any_count |= kstat_irqs_cpu(i, j);
-	action = desc->action;
-	if ((!action || irq_desc_is_chained(desc)) && !any_count)
-		goto out;
+	if (desc->kstat_irqs)
+		for_each_online_cpu(j)
+			any_count |= *per_cpu_ptr(desc->kstat_irqs, j);
+
+	if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
+		goto outsparse;
 
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+		seq_printf(p, "%10u ", desc->kstat_irqs ?
+					*per_cpu_ptr(desc->kstat_irqs, j) : 0);
 
+	raw_spin_lock_irqsave(&desc->lock, flags);
 	if (desc->irq_data.chip) {
 		if (desc->irq_data.chip->irq_print_chip)
 			desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
@@ -511,6 +513,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (desc->name)
 		seq_printf(p, "-%-8s", desc->name);
 
+	action = desc->action;
 	if (action) {
 		seq_printf(p, "  %s", action->name);
 		while ((action = action->next) != NULL)
@@ -518,10 +521,9 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	seq_putc(p, '\n');
-out:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 outsparse:
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return 0;
 }
 #endif
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ea619021d901..ab257be4d924 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -627,8 +627,8 @@ static void optimize_kprobe(struct kprobe *p)
 	    (kprobe_disabled(p) || kprobes_all_disarmed))
 		return;
 
-	/* Both of break_handler and post_handler are not supported. */
-	if (p->break_handler || p->post_handler)
+	/* kprobes with post_handler can not be optimized */
+	if (p->post_handler)
 		return;
 
 	op = container_of(p, struct optimized_kprobe, kp);
@@ -710,9 +710,7 @@ static void reuse_unused_kprobe(struct kprobe *ap)
 	 * there is still a relative jump) and disabled.
 	 */
 	op = container_of(ap, struct optimized_kprobe, kp);
-	if (unlikely(list_empty(&op->list)))
-		printk(KERN_WARNING "Warning: found a stray unused "
-			"aggrprobe@%p\n", ap->addr);
+	WARN_ON_ONCE(list_empty(&op->list));
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
@@ -985,7 +983,8 @@ static int arm_kprobe_ftrace(struct kprobe *p)
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 				   (unsigned long)p->addr, 0, 0);
 	if (ret) {
-		pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+		pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n",
+			 p->addr, ret);
 		return ret;
 	}
 
@@ -1025,7 +1024,8 @@ static int disarm_kprobe_ftrace(struct kprobe *p)
 
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 			   (unsigned long)p->addr, 1, 0);
-	WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+	WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n",
+		  p->addr, ret);
 	return ret;
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
@@ -1116,20 +1116,6 @@ static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
 }
 NOKPROBE_SYMBOL(aggr_fault_handler);
 
-static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe *cur = __this_cpu_read(kprobe_instance);
-	int ret = 0;
-
-	if (cur && cur->break_handler) {
-		if (cur->break_handler(cur, regs))
-			ret = 1;
-	}
-	reset_kprobe_instance();
-	return ret;
-}
-NOKPROBE_SYMBOL(aggr_break_handler);
-
 /* Walks the list and increments nmissed count for multiprobe case */
 void kprobes_inc_nmissed_count(struct kprobe *p)
 {
@@ -1270,24 +1256,15 @@ static void cleanup_rp_inst(struct kretprobe *rp)
 }
 NOKPROBE_SYMBOL(cleanup_rp_inst);
 
-/*
-* Add the new probe to ap->list. Fail if this is the
-* second jprobe at the address - two jprobes can't coexist
-*/
+/* Add the new probe to ap->list */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
 	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
 
-	if (p->break_handler || p->post_handler)
+	if (p->post_handler)
 		unoptimize_kprobe(ap, true);	/* Fall back to normal kprobe */
 
-	if (p->break_handler) {
-		if (ap->break_handler)
-			return -EEXIST;
-		list_add_tail_rcu(&p->list, &ap->list);
-		ap->break_handler = aggr_break_handler;
-	} else
-		list_add_rcu(&p->list, &ap->list);
+	list_add_rcu(&p->list, &ap->list);
 	if (p->post_handler && !ap->post_handler)
 		ap->post_handler = aggr_post_handler;
 
@@ -1310,8 +1287,6 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 	/* We don't care the kprobe which has gone. */
 	if (p->post_handler && !kprobe_gone(p))
 		ap->post_handler = aggr_post_handler;
-	if (p->break_handler && !kprobe_gone(p))
-		ap->break_handler = aggr_break_handler;
 
 	INIT_LIST_HEAD(&ap->list);
 	INIT_HLIST_NODE(&ap->hlist);
@@ -1706,8 +1681,6 @@ static int __unregister_kprobe_top(struct kprobe *p)
 		goto disarmed;
 	else {
 		/* If disabling probe has special handlers, update aggrprobe */
-		if (p->break_handler && !kprobe_gone(p))
-			ap->break_handler = NULL;
 		if (p->post_handler && !kprobe_gone(p)) {
 			list_for_each_entry_rcu(list_p, &ap->list, list) {
 				if ((list_p != p) && (list_p->post_handler))
@@ -1812,77 +1785,6 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 	return (unsigned long)entry;
 }
 
-#if 0
-int register_jprobes(struct jprobe **jps, int num)
-{
-	int ret = 0, i;
-
-	if (num <= 0)
-		return -EINVAL;
-
-	for (i = 0; i < num; i++) {
-		ret = register_jprobe(jps[i]);
-
-		if (ret < 0) {
-			if (i > 0)
-				unregister_jprobes(jps, i);
-			break;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(register_jprobes);
-
-int register_jprobe(struct jprobe *jp)
-{
-	unsigned long addr, offset;
-	struct kprobe *kp = &jp->kp;
-
-	/*
-	 * Verify probepoint as well as the jprobe handler are
-	 * valid function entry points.
-	 */
-	addr = arch_deref_entry_point(jp->entry);
-
-	if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 &&
-	    kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) {
-		kp->pre_handler = setjmp_pre_handler;
-		kp->break_handler = longjmp_break_handler;
-		return register_kprobe(kp);
-	}
-
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(register_jprobe);
-
-void unregister_jprobe(struct jprobe *jp)
-{
-	unregister_jprobes(&jp, 1);
-}
-EXPORT_SYMBOL_GPL(unregister_jprobe);
-
-void unregister_jprobes(struct jprobe **jps, int num)
-{
-	int i;
-
-	if (num <= 0)
-		return;
-	mutex_lock(&kprobe_mutex);
-	for (i = 0; i < num; i++)
-		if (__unregister_kprobe_top(&jps[i]->kp) < 0)
-			jps[i]->kp.addr = NULL;
-	mutex_unlock(&kprobe_mutex);
-
-	synchronize_sched();
-	for (i = 0; i < num; i++) {
-		if (jps[i]->kp.addr)
-			__unregister_kprobe_bottom(&jps[i]->kp);
-	}
-}
-EXPORT_SYMBOL_GPL(unregister_jprobes);
-#endif
-
 #ifdef CONFIG_KRETPROBES
 /*
  * This kprobe pre_handler is registered with every kretprobe. When probe
@@ -1982,7 +1884,6 @@ int register_kretprobe(struct kretprobe *rp)
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
 	rp->kp.fault_handler = NULL;
-	rp->kp.break_handler = NULL;
 
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {
@@ -2105,7 +2006,6 @@ static void kill_kprobe(struct kprobe *p)
 		list_for_each_entry_rcu(kp, &p->list, list)
 			kp->flags |= KPROBE_FLAG_GONE;
 		p->post_handler = NULL;
-		p->break_handler = NULL;
 		kill_optimized_kprobe(p);
 	}
 	/*
@@ -2169,11 +2069,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(enable_kprobe);
 
+/* Caller must NOT call this in usual path. This is only for critical case */
 void dump_kprobe(struct kprobe *kp)
 {
-	printk(KERN_WARNING "Dumping kprobe:\n");
-	printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
-	       kp->symbol_name, kp->addr, kp->offset);
+	pr_err("Dumping kprobe:\n");
+	pr_err("Name: %s\nOffset: %x\nAddress: %pS\n",
+	       kp->symbol_name, kp->offset, kp->addr);
 }
 NOKPROBE_SYMBOL(dump_kprobe);
 
@@ -2196,11 +2097,8 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
 		entry = arch_deref_entry_point((void *)*iter);
 
 		if (!kernel_text_address(entry) ||
-		    !kallsyms_lookup_size_offset(entry, &size, &offset)) {
-			pr_err("Failed to find blacklist at %p\n",
-				(void *)entry);
+		    !kallsyms_lookup_size_offset(entry, &size, &offset))
 			continue;
-		}
 
 		ent = kmalloc(sizeof(*ent), GFP_KERNEL);
 		if (!ent)
@@ -2326,21 +2224,23 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
 		const char *sym, int offset, char *modname, struct kprobe *pp)
 {
 	char *kprobe_type;
+	void *addr = p->addr;
 
 	if (p->pre_handler == pre_handler_kretprobe)
 		kprobe_type = "r";
-	else if (p->pre_handler == setjmp_pre_handler)
-		kprobe_type = "j";
 	else
 		kprobe_type = "k";
 
+	if (!kallsyms_show_value())
+		addr = NULL;
+
 	if (sym)
-		seq_printf(pi, "%p  %s  %s+0x%x  %s ",
-			p->addr, kprobe_type, sym, offset,
+		seq_printf(pi, "%px  %s  %s+0x%x  %s ",
+			addr, kprobe_type, sym, offset,
 			(modname ? modname : " "));
-	else
-		seq_printf(pi, "%p  %s  %p ",
-			p->addr, kprobe_type, p->addr);
+	else	/* try to use %pS */
+		seq_printf(pi, "%px  %s  %pS ",
+			addr, kprobe_type, p->addr);
 
 	if (!pp)
 		pp = p;
@@ -2428,8 +2328,16 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	struct kprobe_blacklist_entry *ent =
 		list_entry(v, struct kprobe_blacklist_entry, list);
 
-	seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
-		   (void *)ent->end_addr, (void *)ent->start_addr);
+	/*
+	 * If /proc/kallsyms is not showing kernel address, we won't
+	 * show them here either.
+	 */
+	if (!kallsyms_show_value())
+		seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
+			   (void *)ent->start_addr);
+	else
+		seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
+			   (void *)ent->end_addr, (void *)ent->start_addr);
 	return 0;
 }
 
@@ -2611,7 +2519,7 @@ static int __init debugfs_kprobe_init(void)
 	if (!dir)
 		return -ENOMEM;
 
-	file = debugfs_create_file("list", 0444, dir, NULL,
+	file = debugfs_create_file("list", 0400, dir, NULL,
 				&debugfs_kprobes_operations);
 	if (!file)
 		goto error;
@@ -2621,7 +2529,7 @@ static int __init debugfs_kprobe_init(void)
 	if (!file)
 		goto error;
 
-	file = debugfs_create_file("blacklist", 0444, dir, NULL,
+	file = debugfs_create_file("blacklist", 0400, dir, NULL,
 				&debugfs_kprobe_blacklist_ops);
 	if (!file)
 		goto error;
@@ -2637,6 +2545,3 @@ late_initcall(debugfs_kprobe_init);
 #endif /* CONFIG_DEBUG_FS */
 
 module_init(init_kprobes);
-
-/* defined in arch/.../kernel/kprobes.c */
-EXPORT_SYMBOL_GPL(jprobe_return);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 486dedbd9af5..087d18d771b5 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -190,7 +190,7 @@ static void __kthread_parkme(struct kthread *self)
 		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
 			break;
 
-		complete_all(&self->parked);
+		complete(&self->parked);
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -471,7 +471,6 @@ void kthread_unpark(struct task_struct *k)
 	if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
 		__kthread_bind(k, kthread->cpu, TASK_PARKED);
 
-	reinit_completion(&kthread->parked);
 	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	/*
 	 * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
@@ -499,6 +498,9 @@ int kthread_park(struct task_struct *k)
 	if (WARN_ON(k->flags & PF_EXITING))
 		return -ENOSYS;
 
+	if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
+		return -EBUSY;
+
 	set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	if (k != current) {
 		wake_up_process(k);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 8402b3349dca..57bef4fbfb31 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -21,6 +21,9 @@
  *          Davidlohr Bueso <dave@stgolabs.net>
  *	Based on kernel/rcu/torture.c.
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
@@ -57,7 +60,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
 torture_param(int, stat_interval, 60,
 	     "Number of seconds between stats printk()s");
 torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
 	     "Enable verbose debugging printk()s");
 
 static char *torture_type = "spin_lock";
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 87331565e505..70178f6ffdc4 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -92,7 +92,7 @@ static void s2idle_enter(void)
 	/* Push all the CPUs into the idle loop. */
 	wake_up_all_idle_cpus();
 	/* Make the current CPU wait so it can enter the idle loop too. */
-	swait_event(s2idle_wait_head,
+	swait_event_exclusive(s2idle_wait_head,
 		    s2idle_state == S2IDLE_STATE_WAKE);
 
 	cpuidle_pause();
@@ -160,7 +160,7 @@ void s2idle_wake(void)
 	raw_spin_lock_irqsave(&s2idle_lock, flags);
 	if (s2idle_state > S2IDLE_STATE_NONE) {
 		s2idle_state = S2IDLE_STATE_WAKE;
-		swake_up(&s2idle_wait_head);
+		swake_up_one(&s2idle_wait_head);
 	}
 	raw_spin_unlock_irqrestore(&s2idle_lock, flags);
 }
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 40cea6735c2d..4d04683c31b2 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -91,7 +91,17 @@ static inline void rcu_seq_end(unsigned long *sp)
 	WRITE_ONCE(*sp, rcu_seq_endval(sp));
 }
 
-/* Take a snapshot of the update side's sequence number. */
+/*
+ * rcu_seq_snap - Take a snapshot of the update side's sequence number.
+ *
+ * This function returns the earliest value of the grace-period sequence number
+ * that will indicate that a full grace period has elapsed since the current
+ * time.  Once the grace-period sequence number has reached this value, it will
+ * be safe to invoke all callbacks that have been registered prior to the
+ * current time. This value is the current grace-period number plus two to the
+ * power of the number of low-order bits reserved for state, then rounded up to
+ * the next value in which the state bits are all zero.
+ */
 static inline unsigned long rcu_seq_snap(unsigned long *sp)
 {
 	unsigned long s;
@@ -108,6 +118,15 @@ static inline unsigned long rcu_seq_current(unsigned long *sp)
 }
 
 /*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not the
+ * corresponding update-side operation has started.
+ */
+static inline bool rcu_seq_started(unsigned long *sp, unsigned long s)
+{
+	return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp));
+}
+
+/*
  * Given a snapshot from rcu_seq_snap(), determine whether or not a
  * full update-side operation has occurred.
  */
@@ -117,6 +136,45 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
 }
 
 /*
+ * Has a grace period completed since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new)
+{
+	return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK);
+}
+
+/*
+ * Has a grace period started since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new)
+{
+	return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK,
+			    new);
+}
+
+/*
+ * Roughly how many full grace periods have elapsed between the collection
+ * of the two specified grace periods?
+ */
+static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old)
+{
+	unsigned long rnd_diff;
+
+	if (old == new)
+		return 0;
+	/*
+	 * Compute the number of grace periods (still shifted up), plus
+	 * one if either of new and old is not an exact grace period.
+	 */
+	rnd_diff = (new & ~RCU_SEQ_STATE_MASK) -
+		   ((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) +
+		   ((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK));
+	if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff))
+		return 1; /* Definitely no grace period has elapsed. */
+	return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2;
+}
+
+/*
  * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
  * by call_rcu() and rcu callback execution, and are therefore not part of the
  * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
@@ -276,6 +334,9 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 /* Is this rcu_node a leaf? */
 #define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
 
+/* Is this rcu_node the last leaf? */
+#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1])
+
 /*
  * Do a full breadth-first scan of the rcu_node structures for the
  * specified rcu_state structure.
@@ -405,8 +466,7 @@ enum rcutorture_type {
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
-			    unsigned long *gpnum, unsigned long *completed);
-void rcutorture_record_test_transition(void);
+			    unsigned long *gp_seq);
 void rcutorture_record_progress(unsigned long vernum);
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
@@ -415,15 +475,11 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long c);
 #else
 static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
-					  int *flags,
-					  unsigned long *gpnum,
-					  unsigned long *completed)
+					  int *flags, unsigned long *gp_seq)
 {
 	*flags = 0;
-	*gpnum = 0;
-	*completed = 0;
+	*gp_seq = 0;
 }
-static inline void rcutorture_record_test_transition(void) { }
 static inline void rcutorture_record_progress(unsigned long vernum) { }
 #ifdef CONFIG_RCU_TRACE
 void do_trace_rcu_torture_read(const char *rcutorturename,
@@ -441,31 +497,26 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 
 static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
 					   struct srcu_struct *sp, int *flags,
-					   unsigned long *gpnum,
-					   unsigned long *completed)
+					   unsigned long *gp_seq)
 {
 	if (test_type != SRCU_FLAVOR)
 		return;
 	*flags = 0;
-	*completed = sp->srcu_idx;
-	*gpnum = *completed;
+	*gp_seq = sp->srcu_idx;
 }
 
 #elif defined(CONFIG_TREE_SRCU)
 
 void srcutorture_get_gp_data(enum rcutorture_type test_type,
 			     struct srcu_struct *sp, int *flags,
-			     unsigned long *gpnum, unsigned long *completed);
+			     unsigned long *gp_seq);
 
 #endif
 
 #ifdef CONFIG_TINY_RCU
-static inline unsigned long rcu_batches_started(void) { return 0; }
-static inline unsigned long rcu_batches_started_bh(void) { return 0; }
-static inline unsigned long rcu_batches_started_sched(void) { return 0; }
-static inline unsigned long rcu_batches_completed(void) { return 0; }
-static inline unsigned long rcu_batches_completed_bh(void) { return 0; }
-static inline unsigned long rcu_batches_completed_sched(void) { return 0; }
+static inline unsigned long rcu_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; }
 static inline unsigned long
@@ -474,19 +525,16 @@ static inline void rcu_force_quiescent_state(void) { }
 static inline void rcu_bh_force_quiescent_state(void) { }
 static inline void rcu_sched_force_quiescent_state(void) { }
 static inline void show_rcu_gp_kthreads(void) { }
+static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
 #else /* #ifdef CONFIG_TINY_RCU */
-extern unsigned long rcutorture_testseq;
-extern unsigned long rcutorture_vernum;
-unsigned long rcu_batches_started(void);
-unsigned long rcu_batches_started_bh(void);
-unsigned long rcu_batches_started_sched(void);
-unsigned long rcu_batches_completed(void);
-unsigned long rcu_batches_completed_bh(void);
-unsigned long rcu_batches_completed_sched(void);
+unsigned long rcu_get_gp_seq(void);
+unsigned long rcu_bh_get_gp_seq(void);
+unsigned long rcu_sched_get_gp_seq(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long rcu_exp_batches_completed_sched(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void show_rcu_gp_kthreads(void);
+int rcu_get_gp_kthreads_prio(void);
 void rcu_force_quiescent_state(void);
 void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index e232846516b3..34244523550e 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -19,6 +19,9 @@
  *
  * Authors: Paul E. McKenney <paulmck@us.ibm.com>
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -88,7 +91,7 @@ torture_param(int, nreaders, -1, "Number of RCU reader threads");
 torture_param(int, nwriters, -1, "Number of RCU updater threads");
 torture_param(bool, shutdown, !IS_ENABLED(MODULE),
 	      "Shutdown at end of performance tests.");
-torture_param(bool, verbose, true, "Enable verbose debugging printk()s");
+torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
 
 static char *perf_type = "rcu";
@@ -135,8 +138,8 @@ struct rcu_perf_ops {
 	void (*cleanup)(void);
 	int (*readlock)(void);
 	void (*readunlock)(int idx);
-	unsigned long (*started)(void);
-	unsigned long (*completed)(void);
+	unsigned long (*get_gp_seq)(void);
+	unsigned long (*gp_diff)(unsigned long new, unsigned long old);
 	unsigned long (*exp_completed)(void);
 	void (*async)(struct rcu_head *head, rcu_callback_t func);
 	void (*gp_barrier)(void);
@@ -176,8 +179,8 @@ static struct rcu_perf_ops rcu_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= rcu_perf_read_lock,
 	.readunlock	= rcu_perf_read_unlock,
-	.started	= rcu_batches_started,
-	.completed	= rcu_batches_completed,
+	.get_gp_seq	= rcu_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed,
 	.async		= call_rcu,
 	.gp_barrier	= rcu_barrier,
@@ -206,8 +209,8 @@ static struct rcu_perf_ops rcu_bh_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= rcu_bh_perf_read_lock,
 	.readunlock	= rcu_bh_perf_read_unlock,
-	.started	= rcu_batches_started_bh,
-	.completed	= rcu_batches_completed_bh,
+	.get_gp_seq	= rcu_bh_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed_sched,
 	.async		= call_rcu_bh,
 	.gp_barrier	= rcu_barrier_bh,
@@ -263,8 +266,8 @@ static struct rcu_perf_ops srcu_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= srcu_perf_read_lock,
 	.readunlock	= srcu_perf_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_perf_completed,
+	.get_gp_seq	= srcu_perf_completed,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= srcu_perf_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
@@ -292,8 +295,8 @@ static struct rcu_perf_ops srcud_ops = {
 	.cleanup	= srcu_sync_perf_cleanup,
 	.readlock	= srcu_perf_read_lock,
 	.readunlock	= srcu_perf_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_perf_completed,
+	.get_gp_seq	= srcu_perf_completed,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= srcu_perf_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
@@ -322,8 +325,8 @@ static struct rcu_perf_ops sched_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= sched_perf_read_lock,
 	.readunlock	= sched_perf_read_unlock,
-	.started	= rcu_batches_started_sched,
-	.completed	= rcu_batches_completed_sched,
+	.get_gp_seq	= rcu_sched_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed_sched,
 	.async		= call_rcu_sched,
 	.gp_barrier	= rcu_barrier_sched,
@@ -350,8 +353,8 @@ static struct rcu_perf_ops tasks_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= tasks_perf_read_lock,
 	.readunlock	= tasks_perf_read_unlock,
-	.started	= rcu_no_completed,
-	.completed	= rcu_no_completed,
+	.get_gp_seq	= rcu_no_completed,
+	.gp_diff	= rcu_seq_diff,
 	.async		= call_rcu_tasks,
 	.gp_barrier	= rcu_barrier_tasks,
 	.sync		= synchronize_rcu_tasks,
@@ -359,9 +362,11 @@ static struct rcu_perf_ops tasks_ops = {
 	.name		= "tasks"
 };
 
-static bool __maybe_unused torturing_tasks(void)
+static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
 {
-	return cur_ops == &tasks_ops;
+	if (!cur_ops->gp_diff)
+		return new - old;
+	return cur_ops->gp_diff(new, old);
 }
 
 /*
@@ -444,8 +449,7 @@ rcu_perf_writer(void *arg)
 			b_rcu_perf_writer_started =
 				cur_ops->exp_completed() / 2;
 		} else {
-			b_rcu_perf_writer_started =
-				cur_ops->completed();
+			b_rcu_perf_writer_started = cur_ops->get_gp_seq();
 		}
 	}
 
@@ -502,7 +506,7 @@ retry:
 						cur_ops->exp_completed() / 2;
 				} else {
 					b_rcu_perf_writer_finished =
-						cur_ops->completed();
+						cur_ops->get_gp_seq();
 				}
 				if (shutdown) {
 					smp_mb(); /* Assign before wake. */
@@ -527,7 +531,7 @@ retry:
 	return 0;
 }
 
-static inline void
+static void
 rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
 {
 	pr_alert("%s" PERF_FLAG
@@ -582,8 +586,8 @@ rcu_perf_cleanup(void)
 			 t_rcu_perf_writer_finished -
 			 t_rcu_perf_writer_started,
 			 ngps,
-			 b_rcu_perf_writer_finished -
-			 b_rcu_perf_writer_started);
+			 rcuperf_seq_diff(b_rcu_perf_writer_finished,
+					  b_rcu_perf_writer_started));
 		for (i = 0; i < nrealwriters; i++) {
 			if (!writer_durations)
 				break;
@@ -671,12 +675,11 @@ rcu_perf_init(void)
 			break;
 	}
 	if (i == ARRAY_SIZE(perf_ops)) {
-		pr_alert("rcu-perf: invalid perf type: \"%s\"\n",
-			 perf_type);
+		pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type);
 		pr_alert("rcu-perf types:");
 		for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
-			pr_alert(" %s", perf_ops[i]->name);
-		pr_alert("\n");
+			pr_cont(" %s", perf_ops[i]->name);
+		pr_cont("\n");
 		firsterr = -EINVAL;
 		goto unwind;
 	}
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 42fcb7f05fac..c596c6f1e457 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -22,6 +22,9 @@
  *
  * See also:  Documentation/RCU/torture.txt
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -52,6 +55,7 @@
 #include <linux/torture.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/sysctl.h>
 
 #include "rcu.h"
 
@@ -59,6 +63,19 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
 
+/* Bits for ->extendables field, extendables param, and related definitions. */
+#define RCUTORTURE_RDR_SHIFT	 8	/* Put SRCU index in upper bits. */
+#define RCUTORTURE_RDR_MASK	 ((1 << RCUTORTURE_RDR_SHIFT) - 1)
+#define RCUTORTURE_RDR_BH	 0x1	/* Extend readers by disabling bh. */
+#define RCUTORTURE_RDR_IRQ	 0x2	/*  ... disabling interrupts. */
+#define RCUTORTURE_RDR_PREEMPT	 0x4	/*  ... disabling preemption. */
+#define RCUTORTURE_RDR_RCU	 0x8	/*  ... entering another RCU reader. */
+#define RCUTORTURE_RDR_NBITS	 4	/* Number of bits defined above. */
+#define RCUTORTURE_MAX_EXTEND	 (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \
+				  RCUTORTURE_RDR_PREEMPT)
+#define RCUTORTURE_RDR_MAX_LOOPS 0x7	/* Maximum reader extensions. */
+					/* Must be power of two minus one. */
+
 torture_param(int, cbflood_inter_holdoff, HZ,
 	      "Holdoff between floods (jiffies)");
 torture_param(int, cbflood_intra_holdoff, 1,
@@ -66,6 +83,8 @@ torture_param(int, cbflood_intra_holdoff, 1,
 torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
 torture_param(int, cbflood_n_per_burst, 20000,
 	      "# callbacks per burst in flood");
+torture_param(int, extendables, RCUTORTURE_MAX_EXTEND,
+	      "Extend readers by disabling bh (1), irqs (2), or preempt (4)");
 torture_param(int, fqs_duration, 0,
 	      "Duration of fqs bursts (us), 0 to disable");
 torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
@@ -84,7 +103,7 @@ torture_param(int, object_debug, 0,
 	     "Enable debug-object double call_rcu() testing");
 torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
 torture_param(int, onoff_interval, 0,
-	     "Time between CPU hotplugs (s), 0=disable");
+	     "Time between CPU hotplugs (jiffies), 0=disable");
 torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
 torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
@@ -101,7 +120,7 @@ torture_param(int, test_boost_interval, 7,
 	     "Interval between boost tests, seconds.");
 torture_param(bool, test_no_idle_hz, true,
 	     "Test support for tickless idle CPUs");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
 	     "Enable verbose debugging printk()s");
 
 static char *torture_type = "rcu";
@@ -148,9 +167,9 @@ static long n_rcu_torture_boost_ktrerror;
 static long n_rcu_torture_boost_rterror;
 static long n_rcu_torture_boost_failure;
 static long n_rcu_torture_boosts;
-static long n_rcu_torture_timers;
+static atomic_long_t n_rcu_torture_timers;
 static long n_barrier_attempts;
-static long n_barrier_successes;
+static long n_barrier_successes; /* did rcu_barrier test succeed? */
 static atomic_long_t n_cbfloods;
 static struct list_head rcu_torture_removed;
 
@@ -261,8 +280,8 @@ struct rcu_torture_ops {
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
-	unsigned long (*started)(void);
-	unsigned long (*completed)(void);
+	unsigned long (*get_gp_seq)(void);
+	unsigned long (*gp_diff)(unsigned long new, unsigned long old);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*exp_sync)(void);
@@ -274,6 +293,8 @@ struct rcu_torture_ops {
 	void (*stats)(void);
 	int irq_capable;
 	int can_boost;
+	int extendables;
+	int ext_irq_conflict;
 	const char *name;
 };
 
@@ -302,10 +323,10 @@ static void rcu_read_delay(struct torture_random_state *rrsp)
 	 * force_quiescent_state. */
 
 	if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
-		started = cur_ops->completed();
+		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
 		mdelay(longdelay_ms);
-		completed = cur_ops->completed();
+		completed = cur_ops->get_gp_seq();
 		do_trace_rcu_torture_read(cur_ops->name, NULL, ts,
 					  started, completed);
 	}
@@ -397,8 +418,8 @@ static struct rcu_torture_ops rcu_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
-	.started	= rcu_batches_started,
-	.completed	= rcu_batches_completed,
+	.get_gp_seq	= rcu_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
@@ -439,8 +460,8 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
-	.started	= rcu_batches_started_bh,
-	.completed	= rcu_batches_completed_bh,
+	.get_gp_seq	= rcu_bh_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
 	.exp_sync	= synchronize_rcu_bh_expedited,
@@ -449,6 +470,8 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.fqs		= rcu_bh_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
+	.extendables	= (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ),
+	.ext_irq_conflict = RCUTORTURE_RDR_RCU,
 	.name		= "rcu_bh"
 };
 
@@ -483,8 +506,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_torture_read_unlock,
-	.started	= rcu_no_completed,
-	.completed	= rcu_no_completed,
+	.get_gp_seq	= rcu_no_completed,
 	.deferred_free	= rcu_busted_torture_deferred_free,
 	.sync		= synchronize_rcu_busted,
 	.exp_sync	= synchronize_rcu_busted,
@@ -572,8 +594,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_torture_completed,
+	.get_gp_seq	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
 	.exp_sync	= srcu_torture_synchronize_expedited,
@@ -610,8 +631,7 @@ static struct rcu_torture_ops srcud_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_torture_completed,
+	.get_gp_seq	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
 	.exp_sync	= srcu_torture_synchronize_expedited,
@@ -622,6 +642,26 @@ static struct rcu_torture_ops srcud_ops = {
 	.name		= "srcud"
 };
 
+/* As above, but broken due to inappropriate reader extension. */
+static struct rcu_torture_ops busted_srcud_ops = {
+	.ttype		= SRCU_FLAVOR,
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= rcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.get_gp_seq	= srcu_torture_completed,
+	.deferred_free	= srcu_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.exp_sync	= srcu_torture_synchronize_expedited,
+	.call		= srcu_torture_call,
+	.cb_barrier	= srcu_torture_barrier,
+	.stats		= srcu_torture_stats,
+	.irq_capable	= 1,
+	.extendables	= RCUTORTURE_MAX_EXTEND,
+	.name		= "busted_srcud"
+};
+
 /*
  * Definitions for sched torture testing.
  */
@@ -648,8 +688,8 @@ static struct rcu_torture_ops sched_ops = {
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
-	.started	= rcu_batches_started_sched,
-	.completed	= rcu_batches_completed_sched,
+	.get_gp_seq	= rcu_sched_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
 	.exp_sync	= synchronize_sched_expedited,
@@ -660,6 +700,7 @@ static struct rcu_torture_ops sched_ops = {
 	.fqs		= rcu_sched_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
+	.extendables	= RCUTORTURE_MAX_EXTEND,
 	.name		= "sched"
 };
 
@@ -687,8 +728,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.readlock	= tasks_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= tasks_torture_read_unlock,
-	.started	= rcu_no_completed,
-	.completed	= rcu_no_completed,
+	.get_gp_seq	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
 	.exp_sync	= synchronize_rcu_tasks,
@@ -700,6 +740,13 @@ static struct rcu_torture_ops tasks_ops = {
 	.name		= "tasks"
 };
 
+static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
+{
+	if (!cur_ops->gp_diff)
+		return new - old;
+	return cur_ops->gp_diff(new, old);
+}
+
 static bool __maybe_unused torturing_tasks(void)
 {
 	return cur_ops == &tasks_ops;
@@ -726,6 +773,44 @@ static void rcu_torture_boost_cb(struct rcu_head *head)
 	smp_store_release(&rbip->inflight, 0);
 }
 
+static int old_rt_runtime = -1;
+
+static void rcu_torture_disable_rt_throttle(void)
+{
+	/*
+	 * Disable RT throttling so that rcutorture's boost threads don't get
+	 * throttled. Only possible if rcutorture is built-in otherwise the
+	 * user should manually do this by setting the sched_rt_period_us and
+	 * sched_rt_runtime sysctls.
+	 */
+	if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime != -1)
+		return;
+
+	old_rt_runtime = sysctl_sched_rt_runtime;
+	sysctl_sched_rt_runtime = -1;
+}
+
+static void rcu_torture_enable_rt_throttle(void)
+{
+	if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime == -1)
+		return;
+
+	sysctl_sched_rt_runtime = old_rt_runtime;
+	old_rt_runtime = -1;
+}
+
+static bool rcu_torture_boost_failed(unsigned long start, unsigned long end)
+{
+	if (end - start > test_boost_duration * HZ - HZ / 2) {
+		VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
+		n_rcu_torture_boost_failure++;
+
+		return true; /* failed */
+	}
+
+	return false; /* passed */
+}
+
 static int rcu_torture_boost(void *arg)
 {
 	unsigned long call_rcu_time;
@@ -746,6 +831,21 @@ static int rcu_torture_boost(void *arg)
 	init_rcu_head_on_stack(&rbi.rcu);
 	/* Each pass through the following loop does one boost-test cycle. */
 	do {
+		/* Track if the test failed already in this test interval? */
+		bool failed = false;
+
+		/* Increment n_rcu_torture_boosts once per boost-test */
+		while (!kthread_should_stop()) {
+			if (mutex_trylock(&boost_mutex)) {
+				n_rcu_torture_boosts++;
+				mutex_unlock(&boost_mutex);
+				break;
+			}
+			schedule_timeout_uninterruptible(1);
+		}
+		if (kthread_should_stop())
+			goto checkwait;
+
 		/* Wait for the next test interval. */
 		oldstarttime = boost_starttime;
 		while (ULONG_CMP_LT(jiffies, oldstarttime)) {
@@ -764,11 +864,10 @@ static int rcu_torture_boost(void *arg)
 				/* RCU core before ->inflight = 1. */
 				smp_store_release(&rbi.inflight, 1);
 				call_rcu(&rbi.rcu, rcu_torture_boost_cb);
-				if (jiffies - call_rcu_time >
-					 test_boost_duration * HZ - HZ / 2) {
-					VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
-					n_rcu_torture_boost_failure++;
-				}
+				/* Check if the boost test failed */
+				failed = failed ||
+					 rcu_torture_boost_failed(call_rcu_time,
+								 jiffies);
 				call_rcu_time = jiffies;
 			}
 			stutter_wait("rcu_torture_boost");
@@ -777,6 +876,14 @@ static int rcu_torture_boost(void *arg)
 		}
 
 		/*
+		 * If boost never happened, then inflight will always be 1, in
+		 * this case the boost check would never happen in the above
+		 * loop so do another one here.
+		 */
+		if (!failed && smp_load_acquire(&rbi.inflight))
+			rcu_torture_boost_failed(call_rcu_time, jiffies);
+
+		/*
 		 * Set the start time of the next test interval.
 		 * Yes, this is vulnerable to long delays, but such
 		 * delays simply cause a false negative for the next
@@ -788,7 +895,6 @@ static int rcu_torture_boost(void *arg)
 			if (mutex_trylock(&boost_mutex)) {
 				boost_starttime = jiffies +
 						  test_boost_interval * HZ;
-				n_rcu_torture_boosts++;
 				mutex_unlock(&boost_mutex);
 				break;
 			}
@@ -1010,7 +1116,7 @@ rcu_torture_writer(void *arg)
 				break;
 			}
 		}
-		rcutorture_record_progress(++rcu_torture_current_version);
+		rcu_torture_current_version++;
 		/* Cycle through nesting levels of rcu_expedite_gp() calls. */
 		if (can_expedite &&
 		    !(torture_random(&rand) & 0xff & (!!expediting - 1))) {
@@ -1084,27 +1190,133 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp)
 }
 
 /*
- * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
- * incrementing the corresponding element of the pipeline array.  The
- * counter in the element should never be greater than 1, otherwise, the
- * RCU implementation is broken.
+ * Do one extension of an RCU read-side critical section using the
+ * current reader state in readstate (set to zero for initial entry
+ * to extended critical section), set the new state as specified by
+ * newstate (set to zero for final exit from extended critical section),
+ * and random-number-generator state in trsp.  If this is neither the
+ * beginning or end of the critical section and if there was actually a
+ * change, do a ->read_delay().
  */
-static void rcu_torture_timer(struct timer_list *unused)
+static void rcutorture_one_extend(int *readstate, int newstate,
+				  struct torture_random_state *trsp)
+{
+	int idxnew = -1;
+	int idxold = *readstate;
+	int statesnew = ~*readstate & newstate;
+	int statesold = *readstate & ~newstate;
+
+	WARN_ON_ONCE(idxold < 0);
+	WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1);
+
+	/* First, put new protection in place to avoid critical-section gap. */
+	if (statesnew & RCUTORTURE_RDR_BH)
+		local_bh_disable();
+	if (statesnew & RCUTORTURE_RDR_IRQ)
+		local_irq_disable();
+	if (statesnew & RCUTORTURE_RDR_PREEMPT)
+		preempt_disable();
+	if (statesnew & RCUTORTURE_RDR_RCU)
+		idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
+
+	/* Next, remove old protection, irq first due to bh conflict. */
+	if (statesold & RCUTORTURE_RDR_IRQ)
+		local_irq_enable();
+	if (statesold & RCUTORTURE_RDR_BH)
+		local_bh_enable();
+	if (statesold & RCUTORTURE_RDR_PREEMPT)
+		preempt_enable();
+	if (statesold & RCUTORTURE_RDR_RCU)
+		cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+
+	/* Delay if neither beginning nor end and there was a change. */
+	if ((statesnew || statesold) && *readstate && newstate)
+		cur_ops->read_delay(trsp);
+
+	/* Update the reader state. */
+	if (idxnew == -1)
+		idxnew = idxold & ~RCUTORTURE_RDR_MASK;
+	WARN_ON_ONCE(idxnew < 0);
+	WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1);
+	*readstate = idxnew | newstate;
+	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0);
+	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1);
+}
+
+/* Return the biggest extendables mask given current RCU and boot parameters. */
+static int rcutorture_extend_mask_max(void)
+{
+	int mask;
+
+	WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND);
+	mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables;
+	mask = mask | RCUTORTURE_RDR_RCU;
+	return mask;
+}
+
+/* Return a random protection state mask, but with at least one bit set. */
+static int
+rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
+{
+	int mask = rcutorture_extend_mask_max();
+	unsigned long randmask1 = torture_random(trsp) >> 8;
+	unsigned long randmask2 = randmask1 >> 1;
+
+	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
+	/* Half the time lots of bits, half the time only one bit. */
+	if (randmask1 & 0x1)
+		mask = mask & randmask2;
+	else
+		mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
+	if ((mask & RCUTORTURE_RDR_IRQ) &&
+	    !(mask & RCUTORTURE_RDR_BH) &&
+	    (oldmask & RCUTORTURE_RDR_BH))
+		mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */
+	if ((mask & RCUTORTURE_RDR_IRQ) &&
+	    !(mask & cur_ops->ext_irq_conflict) &&
+	    (oldmask & cur_ops->ext_irq_conflict))
+		mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */
+	return mask ?: RCUTORTURE_RDR_RCU;
+}
+
+/*
+ * Do a randomly selected number of extensions of an existing RCU read-side
+ * critical section.
+ */
+static void rcutorture_loop_extend(int *readstate,
+				   struct torture_random_state *trsp)
+{
+	int i;
+	int mask = rcutorture_extend_mask_max();
+
+	WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */
+	if (!((mask - 1) & mask))
+		return;  /* Current RCU flavor not extendable. */
+	i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS;
+	while (i--) {
+		mask = rcutorture_extend_mask(*readstate, trsp);
+		rcutorture_one_extend(readstate, mask, trsp);
+	}
+}
+
+/*
+ * Do one read-side critical section, returning false if there was
+ * no data to read.  Can be invoked both from process context and
+ * from a timer handler.
+ */
+static bool rcu_torture_one_read(struct torture_random_state *trsp)
 {
-	int idx;
 	unsigned long started;
 	unsigned long completed;
-	static DEFINE_TORTURE_RANDOM(rand);
-	static DEFINE_SPINLOCK(rand_lock);
+	int newstate;
 	struct rcu_torture *p;
 	int pipe_count;
+	int readstate = 0;
 	unsigned long long ts;
 
-	idx = cur_ops->readlock();
-	if (cur_ops->started)
-		started = cur_ops->started();
-	else
-		started = cur_ops->completed();
+	newstate = rcutorture_extend_mask(readstate, trsp);
+	rcutorture_one_extend(&readstate, newstate, trsp);
+	started = cur_ops->get_gp_seq();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
@@ -1112,39 +1324,50 @@ static void rcu_torture_timer(struct timer_list *unused)
 				  srcu_read_lock_held(srcu_ctlp) ||
 				  torturing_tasks());
 	if (p == NULL) {
-		/* Leave because rcu_torture_writer is not yet underway */
-		cur_ops->readunlock(idx);
-		return;
+		/* Wait for rcu_torture_writer to get underway */
+		rcutorture_one_extend(&readstate, 0, trsp);
+		return false;
 	}
 	if (p->rtort_mbtest == 0)
 		atomic_inc(&n_rcu_torture_mberror);
-	spin_lock(&rand_lock);
-	cur_ops->read_delay(&rand);
-	n_rcu_torture_timers++;
-	spin_unlock(&rand_lock);
+	rcutorture_loop_extend(&readstate, trsp);
 	preempt_disable();
 	pipe_count = p->rtort_pipe_count;
 	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	completed = cur_ops->completed();
+	completed = cur_ops->get_gp_seq();
 	if (pipe_count > 1) {
-		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
-					  started, completed);
+		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
+					  ts, started, completed);
 		rcu_ftrace_dump(DUMP_ALL);
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = completed - started;
-	if (cur_ops->started)
-		completed++;
+	completed = rcutorture_seq_diff(completed, started);
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
 	}
 	__this_cpu_inc(rcu_torture_batch[completed]);
 	preempt_enable();
-	cur_ops->readunlock(idx);
+	rcutorture_one_extend(&readstate, 0, trsp);
+	WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK);
+	return true;
+}
+
+static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand);
+
+/*
+ * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
+ * incrementing the corresponding element of the pipeline array.  The
+ * counter in the element should never be greater than 1, otherwise, the
+ * RCU implementation is broken.
+ */
+static void rcu_torture_timer(struct timer_list *unused)
+{
+	atomic_long_inc(&n_rcu_torture_timers);
+	(void)rcu_torture_one_read(this_cpu_ptr(&rcu_torture_timer_rand));
 
 	/* Test call_rcu() invocation from interrupt handler. */
 	if (cur_ops->call) {
@@ -1164,14 +1387,8 @@ static void rcu_torture_timer(struct timer_list *unused)
 static int
 rcu_torture_reader(void *arg)
 {
-	unsigned long started;
-	unsigned long completed;
-	int idx;
 	DEFINE_TORTURE_RANDOM(rand);
-	struct rcu_torture *p;
-	int pipe_count;
 	struct timer_list t;
-	unsigned long long ts;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_reader task started");
 	set_user_nice(current, MAX_NICE);
@@ -1183,49 +1400,8 @@ rcu_torture_reader(void *arg)
 			if (!timer_pending(&t))
 				mod_timer(&t, jiffies + 1);
 		}
-		idx = cur_ops->readlock();
-		if (cur_ops->started)
-			started = cur_ops->started();
-		else
-			started = cur_ops->completed();
-		ts = rcu_trace_clock_local();
-		p = rcu_dereference_check(rcu_torture_current,
-					  rcu_read_lock_bh_held() ||
-					  rcu_read_lock_sched_held() ||
-					  srcu_read_lock_held(srcu_ctlp) ||
-					  torturing_tasks());
-		if (p == NULL) {
-			/* Wait for rcu_torture_writer to get underway */
-			cur_ops->readunlock(idx);
+		if (!rcu_torture_one_read(&rand))
 			schedule_timeout_interruptible(HZ);
-			continue;
-		}
-		if (p->rtort_mbtest == 0)
-			atomic_inc(&n_rcu_torture_mberror);
-		cur_ops->read_delay(&rand);
-		preempt_disable();
-		pipe_count = p->rtort_pipe_count;
-		if (pipe_count > RCU_TORTURE_PIPE_LEN) {
-			/* Should not happen, but... */
-			pipe_count = RCU_TORTURE_PIPE_LEN;
-		}
-		completed = cur_ops->completed();
-		if (pipe_count > 1) {
-			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-						  ts, started, completed);
-			rcu_ftrace_dump(DUMP_ALL);
-		}
-		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = completed - started;
-		if (cur_ops->started)
-			completed++;
-		if (completed > RCU_TORTURE_PIPE_LEN) {
-			/* Should not happen, but... */
-			completed = RCU_TORTURE_PIPE_LEN;
-		}
-		__this_cpu_inc(rcu_torture_batch[completed]);
-		preempt_enable();
-		cur_ops->readunlock(idx);
 		stutter_wait("rcu_torture_reader");
 	} while (!torture_must_stop());
 	if (irqreader && cur_ops->irq_capable) {
@@ -1282,7 +1458,7 @@ rcu_torture_stats_print(void)
 	pr_cont("rtbf: %ld rtb: %ld nt: %ld ",
 		n_rcu_torture_boost_failure,
 		n_rcu_torture_boosts,
-		n_rcu_torture_timers);
+		atomic_long_read(&n_rcu_torture_timers));
 	torture_onoff_stats();
 	pr_cont("barrier: %ld/%ld:%ld ",
 		n_barrier_successes,
@@ -1324,18 +1500,16 @@ rcu_torture_stats_print(void)
 	if (rtcv_snap == rcu_torture_current_version &&
 	    rcu_torture_current != NULL) {
 		int __maybe_unused flags = 0;
-		unsigned long __maybe_unused gpnum = 0;
-		unsigned long __maybe_unused completed = 0;
+		unsigned long __maybe_unused gp_seq = 0;
 
 		rcutorture_get_gp_data(cur_ops->ttype,
-				       &flags, &gpnum, &completed);
+				       &flags, &gp_seq);
 		srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
-					&flags, &gpnum, &completed);
+					&flags, &gp_seq);
 		wtp = READ_ONCE(writer_task);
-		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n",
+		pr_alert("??? Writer stall state %s(%d) g%lu f%#x ->state %#lx cpu %d\n",
 			 rcu_torture_writer_state_getname(),
-			 rcu_torture_writer_state,
-			 gpnum, completed, flags,
+			 rcu_torture_writer_state, gp_seq, flags,
 			 wtp == NULL ? ~0UL : wtp->state,
 			 wtp == NULL ? -1 : (int)task_cpu(wtp));
 		if (!splatted && wtp) {
@@ -1365,7 +1539,7 @@ rcu_torture_stats(void *arg)
 	return 0;
 }
 
-static inline void
+static void
 rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 {
 	pr_alert("%s" TORTURE_FLAG
@@ -1397,6 +1571,7 @@ static int rcutorture_booster_cleanup(unsigned int cpu)
 	mutex_lock(&boost_mutex);
 	t = boost_tasks[cpu];
 	boost_tasks[cpu] = NULL;
+	rcu_torture_enable_rt_throttle();
 	mutex_unlock(&boost_mutex);
 
 	/* This must be outside of the mutex, otherwise deadlock! */
@@ -1413,6 +1588,7 @@ static int rcutorture_booster_init(unsigned int cpu)
 
 	/* Don't allow time recalculation while creating a new task. */
 	mutex_lock(&boost_mutex);
+	rcu_torture_disable_rt_throttle();
 	VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task");
 	boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL,
 						  cpu_to_node(cpu),
@@ -1446,7 +1622,7 @@ static int rcu_torture_stall(void *args)
 		VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
 	}
 	if (!kthread_should_stop()) {
-		stop_at = get_seconds() + stall_cpu;
+		stop_at = ktime_get_seconds() + stall_cpu;
 		/* RCU CPU stall is expected behavior in following code. */
 		rcu_read_lock();
 		if (stall_cpu_irqsoff)
@@ -1455,7 +1631,8 @@ static int rcu_torture_stall(void *args)
 			preempt_disable();
 		pr_alert("rcu_torture_stall start on CPU %d.\n",
 			 smp_processor_id());
-		while (ULONG_CMP_LT(get_seconds(), stop_at))
+		while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
+				    stop_at))
 			continue;  /* Induce RCU CPU stall warning. */
 		if (stall_cpu_irqsoff)
 			local_irq_enable();
@@ -1546,8 +1723,9 @@ static int rcu_torture_barrier(void *arg)
 			       atomic_read(&barrier_cbs_invoked),
 			       n_barrier_cbs);
 			WARN_ON_ONCE(1);
+		} else {
+			n_barrier_successes++;
 		}
-		n_barrier_successes++;
 		schedule_timeout_interruptible(HZ / 10);
 	} while (!torture_must_stop());
 	torture_kthread_stopping("rcu_torture_barrier");
@@ -1610,17 +1788,39 @@ static void rcu_torture_barrier_cleanup(void)
 	}
 }
 
+static bool rcu_torture_can_boost(void)
+{
+	static int boost_warn_once;
+	int prio;
+
+	if (!(test_boost == 1 && cur_ops->can_boost) && test_boost != 2)
+		return false;
+
+	prio = rcu_get_gp_kthreads_prio();
+	if (!prio)
+		return false;
+
+	if (prio < 2) {
+		if (boost_warn_once  == 1)
+			return false;
+
+		pr_alert("%s: WARN: RCU kthread priority too low to test boosting.  Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 on the kernel command line.\n", KBUILD_MODNAME);
+		boost_warn_once = 1;
+		return false;
+	}
+
+	return true;
+}
+
 static enum cpuhp_state rcutor_hp;
 
 static void
 rcu_torture_cleanup(void)
 {
 	int flags = 0;
-	unsigned long gpnum = 0;
-	unsigned long completed = 0;
+	unsigned long gp_seq = 0;
 	int i;
 
-	rcutorture_record_test_transition();
 	if (torture_cleanup_begin()) {
 		if (cur_ops->cb_barrier != NULL)
 			cur_ops->cb_barrier();
@@ -1648,17 +1848,15 @@ rcu_torture_cleanup(void)
 		fakewriter_tasks = NULL;
 	}
 
-	rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed);
-	srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
-				&flags, &gpnum, &completed);
-	pr_alert("%s:  End-test grace-period state: g%lu c%lu f%#x\n",
-		 cur_ops->name, gpnum, completed, flags);
+	rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq);
+	srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq);
+	pr_alert("%s:  End-test grace-period state: g%lu f%#x\n",
+		 cur_ops->name, gp_seq, flags);
 	torture_stop_kthread(rcu_torture_stats, stats_task);
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
 	for (i = 0; i < ncbflooders; i++)
 		torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
-	if ((test_boost == 1 && cur_ops->can_boost) ||
-	    test_boost == 2)
+	if (rcu_torture_can_boost())
 		cpuhp_remove_state(rcutor_hp);
 
 	/*
@@ -1746,7 +1944,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
-		&sched_ops, &tasks_ops,
+		&busted_srcud_ops, &sched_ops, &tasks_ops,
 	};
 
 	if (!torture_init_begin(torture_type, verbose))
@@ -1763,8 +1961,8 @@ rcu_torture_init(void)
 			 torture_type);
 		pr_alert("rcu-torture types:");
 		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
-			pr_alert(" %s", torture_ops[i]->name);
-		pr_alert("\n");
+			pr_cont(" %s", torture_ops[i]->name);
+		pr_cont("\n");
 		firsterr = -EINVAL;
 		goto unwind;
 	}
@@ -1882,8 +2080,7 @@ rcu_torture_init(void)
 		test_boost_interval = 1;
 	if (test_boost_duration < 2)
 		test_boost_duration = 2;
-	if ((test_boost == 1 && cur_ops->can_boost) ||
-	    test_boost == 2) {
+	if (rcu_torture_can_boost()) {
 
 		boost_starttime = jiffies + test_boost_interval * HZ;
 
@@ -1897,7 +2094,7 @@ rcu_torture_init(void)
 	firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
 	if (firsterr)
 		goto unwind;
-	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ);
+	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval);
 	if (firsterr)
 		goto unwind;
 	firsterr = rcu_torture_stall_init();
@@ -1926,7 +2123,6 @@ rcu_torture_init(void)
 				goto unwind;
 		}
 	}
-	rcutorture_record_test_transition();
 	torture_init_end();
 	return 0;
 
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 622792abe41a..04fc2ed71af8 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -110,7 +110,7 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 
 	WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
 	if (!newval && READ_ONCE(sp->srcu_gp_waiting))
-		swake_up(&sp->srcu_wq);
+		swake_up_one(&sp->srcu_wq);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -140,7 +140,7 @@ void srcu_drive_gp(struct work_struct *wp)
 	idx = sp->srcu_idx;
 	WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
 	WRITE_ONCE(sp->srcu_gp_waiting, true);  /* srcu_read_unlock() wakes! */
-	swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
+	swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
 	WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
 
 	/* Invoke the callbacks we removed above. */
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index b4123d7a2cec..6c9866a854b1 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -26,6 +26,8 @@
  *
  */
 
+#define pr_fmt(fmt) "rcu: " fmt
+
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/percpu.h>
@@ -390,7 +392,8 @@ void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
 		}
 	if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
 	    WARN_ON(srcu_readers_active(sp))) {
-		pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+		pr_info("%s: Active srcu_struct %p state: %d\n",
+			__func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
 		return; /* Caller forgot to stop doing call_srcu()? */
 	}
 	free_percpu(sp->sda);
@@ -641,6 +644,9 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
  * period s.  Losers must either ensure that their desired grace-period
  * number is recorded on at least their leaf srcu_node structure, or they
  * must take steps to invoke their own callbacks.
+ *
+ * Note that this function also does the work of srcu_funnel_exp_start(),
+ * in some cases by directly invoking it.
  */
 static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 				 unsigned long s, bool do_norm)
@@ -823,17 +829,17 @@ static void srcu_leak_callback(struct rcu_head *rhp)
  * more than one CPU, this means that when "func()" is invoked, each CPU
  * is guaranteed to have executed a full memory barrier since the end of
  * its last corresponding SRCU read-side critical section whose beginning
- * preceded the call to call_rcu().  It also means that each CPU executing
+ * preceded the call to call_srcu().  It also means that each CPU executing
  * an SRCU read-side critical section that continues beyond the start of
- * "func()" must have executed a memory barrier after the call_rcu()
+ * "func()" must have executed a memory barrier after the call_srcu()
  * but before the beginning of that SRCU read-side critical section.
  * Note that these guarantees include CPUs that are offline, idle, or
  * executing in user mode, as well as CPUs that are executing in the kernel.
  *
- * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * Furthermore, if CPU A invoked call_srcu() and CPU B invoked the
  * resulting SRCU callback function "func()", then both CPU A and CPU
  * B are guaranteed to execute a full memory barrier during the time
- * interval between the call to call_rcu() and the invocation of "func()".
+ * interval between the call to call_srcu() and the invocation of "func()".
  * This guarantee applies even if CPU A and CPU B are the same CPU (but
  * again only if the system has more than one CPU).
  *
@@ -1246,13 +1252,12 @@ static void process_srcu(struct work_struct *work)
 
 void srcutorture_get_gp_data(enum rcutorture_type test_type,
 			     struct srcu_struct *sp, int *flags,
-			     unsigned long *gpnum, unsigned long *completed)
+			     unsigned long *gp_seq)
 {
 	if (test_type != SRCU_FLAVOR)
 		return;
 	*flags = 0;
-	*completed = rcu_seq_ctr(sp->srcu_gp_seq);
-	*gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed);
+	*gp_seq = rcu_seq_current(&sp->srcu_gp_seq);
 }
 EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
 
@@ -1263,16 +1268,17 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
 	unsigned long s0 = 0, s1 = 0;
 
 	idx = sp->srcu_idx & 0x1;
-	pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", tt, tf, idx);
+	pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):",
+		 tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx);
 	for_each_possible_cpu(cpu) {
 		unsigned long l0, l1;
 		unsigned long u0, u1;
 		long c0, c1;
-		struct srcu_data *counts;
+		struct srcu_data *sdp;
 
-		counts = per_cpu_ptr(sp->sda, cpu);
-		u0 = counts->srcu_unlock_count[!idx];
-		u1 = counts->srcu_unlock_count[idx];
+		sdp = per_cpu_ptr(sp->sda, cpu);
+		u0 = sdp->srcu_unlock_count[!idx];
+		u1 = sdp->srcu_unlock_count[idx];
 
 		/*
 		 * Make sure that a lock is always counted if the corresponding
@@ -1280,12 +1286,13 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
 		 */
 		smp_rmb();
 
-		l0 = counts->srcu_lock_count[!idx];
-		l1 = counts->srcu_lock_count[idx];
+		l0 = sdp->srcu_lock_count[!idx];
+		l1 = sdp->srcu_lock_count[idx];
 
 		c0 = l0 - u0;
 		c1 = l1 - u1;
-		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
+		pr_cont(" %d(%ld,%ld %1p)",
+			cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist));
 		s0 += c0;
 		s1 += c1;
 	}
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index a64eee0db39e..befc9321a89c 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -122,10 +122,8 @@ void rcu_check_callbacks(int user)
 {
 	if (user)
 		rcu_sched_qs();
-	else if (!in_softirq())
+	if (user || !in_softirq())
 		rcu_bh_qs();
-	if (user)
-		rcu_note_voluntary_context_switch(current);
 }
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index aa7cade1b9f3..0b760c1369f7 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -27,6 +27,9 @@
  * For detailed explanation of Read-Copy Update mechanism see -
  *	Documentation/RCU
  */
+
+#define pr_fmt(fmt) "rcu: " fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -95,13 +98,13 @@ struct rcu_state sname##_state = { \
 	.rda = &sname##_data, \
 	.call = cr, \
 	.gp_state = RCU_GP_IDLE, \
-	.gpnum = 0UL - 300UL, \
-	.completed = 0UL - 300UL, \
+	.gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.name = RCU_STATE_NAME(sname), \
 	.abbr = sabbr, \
 	.exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \
 	.exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \
+	.ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \
 }
 
 RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
@@ -155,6 +158,9 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
  */
 static int rcu_scheduler_fully_active __read_mostly;
 
+static void
+rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
+		  struct rcu_node *rnp, unsigned long gps, unsigned long flags);
 static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
 static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
@@ -177,6 +183,13 @@ module_param(gp_init_delay, int, 0444);
 static int gp_cleanup_delay;
 module_param(gp_cleanup_delay, int, 0444);
 
+/* Retreive RCU kthreads priority for rcutorture */
+int rcu_get_gp_kthreads_prio(void)
+{
+	return kthread_prio;
+}
+EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio);
+
 /*
  * Number of grace periods between delays, normalized by the duration of
  * the delay.  The longer the delay, the more the grace periods between
@@ -189,18 +202,6 @@ module_param(gp_cleanup_delay, int, 0444);
 #define PER_RCU_NODE_PERIOD 3	/* Number of grace periods between delays. */
 
 /*
- * Track the rcutorture test sequence number and the update version
- * number within a given test.  The rcutorture_testseq is incremented
- * on every rcutorture module load and unload, so has an odd value
- * when a test is running.  The rcutorture_vernum is set to zero
- * when rcutorture starts and is incremented on each rcutorture update.
- * These variables enable correlating rcutorture output with the
- * RCU tracing information.
- */
-unsigned long rcutorture_testseq;
-unsigned long rcutorture_vernum;
-
-/*
  * Compute the mask of online CPUs for the specified rcu_node structure.
  * This will not be stable unless the rcu_node structure's ->lock is
  * held, but the bit corresponding to the current CPU will be stable
@@ -218,7 +219,7 @@ unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
  */
 static int rcu_gp_in_progress(struct rcu_state *rsp)
 {
-	return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
+	return rcu_seq_state(rcu_seq_current(&rsp->gp_seq));
 }
 
 /*
@@ -233,7 +234,7 @@ void rcu_sched_qs(void)
 	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s))
 		return;
 	trace_rcu_grace_period(TPS("rcu_sched"),
-			       __this_cpu_read(rcu_sched_data.gpnum),
+			       __this_cpu_read(rcu_sched_data.gp_seq),
 			       TPS("cpuqs"));
 	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
 	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
@@ -248,7 +249,7 @@ void rcu_bh_qs(void)
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!");
 	if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_bh"),
-				       __this_cpu_read(rcu_bh_data.gpnum),
+				       __this_cpu_read(rcu_bh_data.gp_seq),
 				       TPS("cpuqs"));
 		__this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
 	}
@@ -380,20 +381,6 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap)
 }
 
 /*
- * 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 * RCU_DYNTICK_CTRL_CTR,
-					&rdtp->dynticks);
-
-	/* It is illegal to call this from idle state. */
-	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
-}
-
-/*
  * Set the special (bottom) bit of the specified CPU so that it
  * will take special action (such as flushing its TLB) on the
  * next exit from an extended quiescent state.  Returns true if
@@ -424,12 +411,17 @@ bool rcu_eqs_special_set(int cpu)
  *
  * We inform the RCU core by emulating a zero-duration dyntick-idle period.
  *
- * The caller must have disabled interrupts.
+ * The caller must have disabled interrupts and must not be idle.
  */
 static void rcu_momentary_dyntick_idle(void)
 {
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int special;
+
 	raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false);
-	rcu_dynticks_momentary_idle();
+	special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+	/* It is illegal to call this from idle state. */
+	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
 }
 
 /*
@@ -451,7 +443,7 @@ void rcu_note_context_switch(bool preempt)
 		rcu_momentary_dyntick_idle();
 	this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
 	if (!preempt)
-		rcu_note_voluntary_context_switch_lite(current);
+		rcu_tasks_qs(current);
 out:
 	trace_rcu_utilization(TPS("End context switch"));
 	barrier(); /* Avoid RCU read-side critical sections leaking up. */
@@ -513,8 +505,38 @@ static ulong jiffies_till_first_fqs = ULONG_MAX;
 static ulong jiffies_till_next_fqs = ULONG_MAX;
 static bool rcu_kick_kthreads;
 
-module_param(jiffies_till_first_fqs, ulong, 0644);
-module_param(jiffies_till_next_fqs, ulong, 0644);
+static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+	ulong j;
+	int ret = kstrtoul(val, 0, &j);
+
+	if (!ret)
+		WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j);
+	return ret;
+}
+
+static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+	ulong j;
+	int ret = kstrtoul(val, 0, &j);
+
+	if (!ret)
+		WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1));
+	return ret;
+}
+
+static struct kernel_param_ops first_fqs_jiffies_ops = {
+	.set = param_set_first_fqs_jiffies,
+	.get = param_get_ulong,
+};
+
+static struct kernel_param_ops next_fqs_jiffies_ops = {
+	.set = param_set_next_fqs_jiffies,
+	.get = param_get_ulong,
+};
+
+module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644);
+module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644);
 module_param(rcu_kick_kthreads, bool, 0644);
 
 /*
@@ -529,58 +551,31 @@ static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(void);
 
 /*
- * Return the number of RCU batches started thus far for debug & stats.
+ * Return the number of RCU GPs completed thus far for debug & stats.
  */
-unsigned long rcu_batches_started(void)
+unsigned long rcu_get_gp_seq(void)
 {
-	return rcu_state_p->gpnum;
+	return READ_ONCE(rcu_state_p->gp_seq);
 }
-EXPORT_SYMBOL_GPL(rcu_batches_started);
+EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
 
 /*
- * Return the number of RCU-sched batches started thus far for debug & stats.
+ * Return the number of RCU-sched GPs completed thus far for debug & stats.
  */
-unsigned long rcu_batches_started_sched(void)
+unsigned long rcu_sched_get_gp_seq(void)
 {
-	return rcu_sched_state.gpnum;
+	return READ_ONCE(rcu_sched_state.gp_seq);
 }
-EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
+EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq);
 
 /*
- * Return the number of RCU BH batches started thus far for debug & stats.
+ * Return the number of RCU-bh GPs completed thus far for debug & stats.
  */
-unsigned long rcu_batches_started_bh(void)
+unsigned long rcu_bh_get_gp_seq(void)
 {
-	return rcu_bh_state.gpnum;
+	return READ_ONCE(rcu_bh_state.gp_seq);
 }
-EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
-
-/*
- * Return the number of RCU batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed(void)
-{
-	return rcu_state_p->completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-/*
- * Return the number of RCU-sched batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_sched(void)
-{
-	return rcu_sched_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
-
-/*
- * Return the number of RCU BH batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_bh(void)
-{
-	return rcu_bh_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
+EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq);
 
 /*
  * Return the number of RCU expedited batches completed thus far for
@@ -636,35 +631,42 @@ EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
  */
 void show_rcu_gp_kthreads(void)
 {
+	int cpu;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp) {
 		pr_info("%s: wait state: %d ->state: %#lx\n",
 			rsp->name, rsp->gp_state, rsp->gp_kthread->state);
+		rcu_for_each_node_breadth_first(rsp, rnp) {
+			if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed))
+				continue;
+			pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n",
+				rnp->grplo, rnp->grphi, rnp->gp_seq,
+				rnp->gp_seq_needed);
+			if (!rcu_is_leaf_node(rnp))
+				continue;
+			for_each_leaf_node_possible_cpu(rnp, cpu) {
+				rdp = per_cpu_ptr(rsp->rda, cpu);
+				if (rdp->gpwrap ||
+				    ULONG_CMP_GE(rsp->gp_seq,
+						 rdp->gp_seq_needed))
+					continue;
+				pr_info("\tcpu %d ->gp_seq_needed %lu\n",
+					cpu, rdp->gp_seq_needed);
+			}
+		}
 		/* sched_show_task(rsp->gp_kthread); */
 	}
 }
 EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
 
 /*
- * Record the number of times rcutorture tests have been initiated and
- * terminated.  This information allows the debugfs tracing stats to be
- * correlated to the rcutorture messages, even when the rcutorture module
- * is being repeatedly loaded and unloaded.  In other words, we cannot
- * store this state in rcutorture itself.
- */
-void rcutorture_record_test_transition(void)
-{
-	rcutorture_testseq++;
-	rcutorture_vernum = 0;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
-
-/*
  * Send along grace-period-related data for rcutorture diagnostics.
  */
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
-			    unsigned long *gpnum, unsigned long *completed)
+			    unsigned long *gp_seq)
 {
 	struct rcu_state *rsp = NULL;
 
@@ -684,23 +686,11 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 	if (rsp == NULL)
 		return;
 	*flags = READ_ONCE(rsp->gp_flags);
-	*gpnum = READ_ONCE(rsp->gpnum);
-	*completed = READ_ONCE(rsp->completed);
+	*gp_seq = rcu_seq_current(&rsp->gp_seq);
 }
 EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
 
 /*
- * Record the number of writer passes through the current rcutorture test.
- * This is also used to correlate debugfs tracing stats with the rcutorture
- * messages.
- */
-void rcutorture_record_progress(unsigned long vernum)
-{
-	rcutorture_vernum++;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_progress);
-
-/*
  * Return the root node of the specified rcu_state structure.
  */
 static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
@@ -1059,41 +1049,41 @@ void rcu_request_urgent_qs_task(struct task_struct *t)
 #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
 
 /*
- * Is the current CPU online?  Disable preemption to avoid false positives
- * that could otherwise happen due to the current CPU number being sampled,
- * this task being preempted, its old CPU being taken offline, resuming
- * on some other CPU, then determining that its old CPU is now offline.
- * It is OK to use RCU on an offline processor during initial boot, hence
- * the check for rcu_scheduler_fully_active.  Note also that it is OK
- * for a CPU coming online to use RCU for one jiffy prior to marking itself
- * online in the cpu_online_mask.  Similarly, it is OK for a CPU going
- * offline to continue to use RCU for one jiffy after marking itself
- * offline in the cpu_online_mask.  This leniency is necessary given the
- * non-atomic nature of the online and offline processing, for example,
- * the fact that a CPU enters the scheduler after completing the teardown
- * of the CPU.
+ * Is the current CPU online as far as RCU is concerned?
  *
- * This is also why RCU internally marks CPUs online during in the
- * preparation phase and offline after the CPU has been taken down.
+ * Disable preemption to avoid false positives that could otherwise
+ * happen due to the current CPU number being sampled, this task being
+ * preempted, its old CPU being taken offline, resuming on some other CPU,
+ * then determining that its old CPU is now offline.  Because there are
+ * multiple flavors of RCU, and because this function can be called in the
+ * midst of updating the flavors while a given CPU coming online or going
+ * offline, it is necessary to check all flavors.  If any of the flavors
+ * believe that given CPU is online, it is considered to be online.
  *
- * Disable checking if in an NMI handler because we cannot safely report
- * errors from NMI handlers anyway.
+ * Disable checking if in an NMI handler because we cannot safely
+ * report errors from NMI handlers anyway.  In addition, it is OK to use
+ * RCU on an offline processor during initial boot, hence the check for
+ * rcu_scheduler_fully_active.
  */
 bool rcu_lockdep_current_cpu_online(void)
 {
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
-	bool ret;
+	struct rcu_state *rsp;
 
-	if (in_nmi())
+	if (in_nmi() || !rcu_scheduler_fully_active)
 		return true;
 	preempt_disable();
-	rdp = this_cpu_ptr(&rcu_sched_data);
-	rnp = rdp->mynode;
-	ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) ||
-	      !rcu_scheduler_fully_active;
+	for_each_rcu_flavor(rsp) {
+		rdp = this_cpu_ptr(rsp->rda);
+		rnp = rdp->mynode;
+		if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) {
+			preempt_enable();
+			return true;
+		}
+	}
 	preempt_enable();
-	return ret;
+	return false;
 }
 EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
 
@@ -1115,17 +1105,18 @@ static int rcu_is_cpu_rrupt_from_idle(void)
 /*
  * We are reporting a quiescent state on behalf of some other CPU, so
  * it is our responsibility to check for and handle potential overflow
- * of the rcu_node ->gpnum counter with respect to the rcu_data counters.
+ * of the rcu_node ->gp_seq counter with respect to the rcu_data counters.
  * After all, the CPU might be in deep idle state, and thus executing no
  * code whatsoever.
  */
 static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	raw_lockdep_assert_held_rcu_node(rnp);
-	if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum))
+	if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4,
+			 rnp->gp_seq))
 		WRITE_ONCE(rdp->gpwrap, true);
-	if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum))
-		rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4;
+	if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq))
+		rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4;
 }
 
 /*
@@ -1137,7 +1128,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
 	rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
 	if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
 		rcu_gpnum_ovf(rdp->mynode, rdp);
 		return 1;
 	}
@@ -1159,7 +1150,7 @@ static void rcu_iw_handler(struct irq_work *iwp)
 	rnp = rdp->mynode;
 	raw_spin_lock_rcu_node(rnp);
 	if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
-		rdp->rcu_iw_gpnum = rnp->gpnum;
+		rdp->rcu_iw_gp_seq = rnp->gp_seq;
 		rdp->rcu_iw_pending = false;
 	}
 	raw_spin_unlock_rcu_node(rnp);
@@ -1187,7 +1178,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * of the current RCU grace period.
 	 */
 	if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
 		rdp->dynticks_fqs++;
 		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
@@ -1203,8 +1194,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
 	if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
 	    READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.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"));
+	    rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) {
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc"));
 		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
 	} else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) {
@@ -1212,12 +1203,25 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		smp_store_release(ruqp, true);
 	}
 
-	/* 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++;
-		rcu_gpnum_ovf(rnp, rdp);
-		return 1;
+	/* If waiting too long on an offline CPU, complain. */
+	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
+	    time_after(jiffies, rdp->rsp->gp_start + HZ)) {
+		bool onl;
+		struct rcu_node *rnp1;
+
+		WARN_ON(1);  /* Offline CPUs are supposed to report QS! */
+		pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+			__func__, rnp->grplo, rnp->grphi, rnp->level,
+			(long)rnp->gp_seq, (long)rnp->completedqs);
+		for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+			pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n",
+				__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask);
+		onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+		pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n",
+			__func__, rdp->cpu, ".o"[onl],
+			(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+			(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+		return 1; /* Break things loose after complaining. */
 	}
 
 	/*
@@ -1256,11 +1260,11 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) {
 		resched_cpu(rdp->cpu);
 		if (IS_ENABLED(CONFIG_IRQ_WORK) &&
-		    !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum &&
+		    !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
 		    (rnp->ffmask & rdp->grpmask)) {
 			init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
 			rdp->rcu_iw_pending = true;
-			rdp->rcu_iw_gpnum = rnp->gpnum;
+			rdp->rcu_iw_gp_seq = rnp->gp_seq;
 			irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
 		}
 	}
@@ -1274,9 +1278,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 	unsigned long j1;
 
 	rsp->gp_start = j;
-	smp_wmb(); /* Record start time before stall time. */
 	j1 = rcu_jiffies_till_stall_check();
-	WRITE_ONCE(rsp->jiffies_stall, j + j1);
+	/* Record ->gp_start before ->jiffies_stall. */
+	smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */
 	rsp->jiffies_resched = j + j1 / 2;
 	rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
 }
@@ -1302,9 +1306,9 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 	j = jiffies;
 	gpa = READ_ONCE(rsp->gp_activity);
 	if (j - gpa > 2 * HZ) {
-		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
+		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
 		       rsp->name, j - gpa,
-		       rsp->gpnum, rsp->completed,
+		       (long)rcu_seq_current(&rsp->gp_seq),
 		       rsp->gp_flags,
 		       gp_state_getname(rsp->gp_state), rsp->gp_state,
 		       rsp->gp_kthread ? rsp->gp_kthread->state : ~0,
@@ -1359,16 +1363,15 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp)
 	}
 }
 
-static inline void panic_on_rcu_stall(void)
+static void panic_on_rcu_stall(void)
 {
 	if (sysctl_panic_on_rcu_stall)
 		panic("RCU Stall\n");
 }
 
-static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
+static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq)
 {
 	int cpu;
-	long delta;
 	unsigned long flags;
 	unsigned long gpa;
 	unsigned long j;
@@ -1381,25 +1384,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	if (rcu_cpu_stall_suppress)
 		return;
 
-	/* Only let one CPU complain about others per time interval. */
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	delta = jiffies - READ_ONCE(rsp->jiffies_stall);
-	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	WRITE_ONCE(rsp->jiffies_stall,
-		   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
 	/*
 	 * OK, time to rat on our buddy...
 	 * See Documentation/RCU/stallwarn.txt for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
-	pr_err("INFO: %s detected stalls on CPUs/tasks:",
-	       rsp->name);
+	pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name);
 	print_cpu_stall_info_begin();
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -1418,17 +1408,16 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
 							    cpu)->cblist);
-	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
+	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start),
-	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
+	       (long)rcu_seq_current(&rsp->gp_seq), 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) {
+		if (rcu_seq_current(&rsp->gp_seq) != gp_seq) {
 			pr_err("INFO: Stall ended before state dump start\n");
 		} else {
 			j = jiffies;
@@ -1441,6 +1430,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 			sched_show_task(current);
 		}
 	}
+	/* Rewrite if needed in case of slow consoles. */
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+		WRITE_ONCE(rsp->jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 
 	rcu_check_gp_kthread_starvation(rsp);
 
@@ -1476,15 +1469,16 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
 							    cpu)->cblist);
-	pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
+	pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
 		jiffies - rsp->gp_start,
-		(long)rsp->gpnum, (long)rsp->completed, totqlen);
+		(long)rcu_seq_current(&rsp->gp_seq), totqlen);
 
 	rcu_check_gp_kthread_starvation(rsp);
 
 	rcu_dump_cpu_stacks(rsp);
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	/* Rewrite if needed in case of slow consoles. */
 	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
 		WRITE_ONCE(rsp->jiffies_stall,
 			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
@@ -1504,10 +1498,11 @@ static void print_cpu_stall(struct rcu_state *rsp)
 
 static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	unsigned long completed;
-	unsigned long gpnum;
+	unsigned long gs1;
+	unsigned long gs2;
 	unsigned long gps;
 	unsigned long j;
+	unsigned long jn;
 	unsigned long js;
 	struct rcu_node *rnp;
 
@@ -1520,43 +1515,46 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	/*
 	 * Lots of memory barriers to reject false positives.
 	 *
-	 * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall,
-	 * then rsp->gp_start, and finally rsp->completed.  These values
-	 * are updated in the opposite order with memory barriers (or
-	 * equivalent) during grace-period initialization and cleanup.
-	 * Now, a false positive can occur if we get an new value of
-	 * rsp->gp_start and a old value of rsp->jiffies_stall.  But given
-	 * the memory barriers, the only way that this can happen is if one
-	 * grace period ends and another starts between these two fetches.
-	 * Detect this by comparing rsp->completed with the previous fetch
-	 * from rsp->gpnum.
+	 * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall,
+	 * then rsp->gp_start, and finally another copy of rsp->gp_seq.
+	 * These values are updated in the opposite order with memory
+	 * barriers (or equivalent) during grace-period initialization
+	 * and cleanup.  Now, a false positive can occur if we get an new
+	 * value of rsp->gp_start and a old value of rsp->jiffies_stall.
+	 * But given the memory barriers, the only way that this can happen
+	 * is if one grace period ends and another starts between these
+	 * two fetches.  This is detected by comparing the second fetch
+	 * of rsp->gp_seq with the previous fetch from rsp->gp_seq.
 	 *
 	 * Given this check, comparisons of jiffies, rsp->jiffies_stall,
 	 * and rsp->gp_start suffice to forestall false positives.
 	 */
-	gpnum = READ_ONCE(rsp->gpnum);
-	smp_rmb(); /* Pick up ->gpnum first... */
+	gs1 = READ_ONCE(rsp->gp_seq);
+	smp_rmb(); /* Pick up ->gp_seq first... */
 	js = READ_ONCE(rsp->jiffies_stall);
 	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
 	gps = READ_ONCE(rsp->gp_start);
-	smp_rmb(); /* ...and finally ->gp_start before ->completed. */
-	completed = READ_ONCE(rsp->completed);
-	if (ULONG_CMP_GE(completed, gpnum) ||
+	smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
+	gs2 = READ_ONCE(rsp->gp_seq);
+	if (gs1 != gs2 ||
 	    ULONG_CMP_LT(j, js) ||
 	    ULONG_CMP_GE(gps, js))
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
+	jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
 	if (rcu_gp_in_progress(rsp) &&
-	    (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
+	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+	    cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
 
 	} else if (rcu_gp_in_progress(rsp) &&
-		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
+		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+		   cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
 
 		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(rsp, gpnum);
+		print_other_cpu_stall(rsp, gs2);
 	}
 }
 
@@ -1577,123 +1575,99 @@ void rcu_cpu_stall_reset(void)
 		WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
 }
 
-/*
- * Determine the value that ->completed will have at the end of the
- * next subsequent grace period.  This is used to tag callbacks so that
- * a CPU can invoke callbacks in a timely fashion even if that CPU has
- * been dyntick-idle for an extended period with callbacks under the
- * influence of RCU_FAST_NO_HZ.
- *
- * The caller must hold rnp->lock with interrupts disabled.
- */
-static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
-				       struct rcu_node *rnp)
-{
-	raw_lockdep_assert_held_rcu_node(rnp);
-
-	/*
-	 * If RCU is idle, we just wait for the next grace period.
-	 * But we can only be sure that RCU is idle if we are looking
-	 * at the root rcu_node structure -- otherwise, a new grace
-	 * period might have started, but just not yet gotten around
-	 * to initializing the current non-root rcu_node structure.
-	 */
-	if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed)
-		return rnp->completed + 1;
-
-	/*
-	 * If the current rcu_node structure believes that RCU is
-	 * idle, and if the rcu_state structure does not yet reflect
-	 * the start of a new grace period, then the next grace period
-	 * will suffice.  The memory barrier is needed to accurately
-	 * sample the rsp->gpnum, and pairs with the second lock
-	 * acquisition in rcu_gp_init(), which is augmented with
-	 * smp_mb__after_unlock_lock() for this purpose.
-	 */
-	if (rnp->gpnum == rnp->completed) {
-		smp_mb(); /* See above block comment. */
-		if (READ_ONCE(rsp->gpnum) == rnp->completed)
-			return rnp->completed + 1;
-	}
-
-	/*
-	 * Otherwise, wait for a possible partial grace period and
-	 * then the subsequent full grace period.
-	 */
-	return rnp->completed + 2;
-}
-
 /* Trace-event wrapper function for trace_rcu_future_grace_period.  */
 static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
-			      unsigned long c, const char *s)
+			      unsigned long gp_seq_req, const char *s)
 {
-	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
-				      rnp->completed, c, rnp->level,
-				      rnp->grplo, rnp->grphi, s);
+	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req,
+				      rnp->level, rnp->grplo, rnp->grphi, s);
 }
 
 /*
+ * rcu_start_this_gp - Request the start of a particular grace period
+ * @rnp_start: The leaf node of the CPU from which to start.
+ * @rdp: The rcu_data corresponding to the CPU from which to start.
+ * @gp_seq_req: The gp_seq of the grace period to start.
+ *
  * Start the specified grace period, as needed to handle newly arrived
  * callbacks.  The required future grace periods are recorded in each
- * rcu_node structure's ->need_future_gp[] field.  Returns true if there
+ * rcu_node structure's ->gp_seq_needed field.  Returns true if there
  * is reason to awaken the grace-period kthread.
  *
  * The caller must hold the specified rcu_node structure's ->lock, which
  * is why the caller is responsible for waking the grace-period kthread.
+ *
+ * Returns true if the GP thread needs to be awakened else false.
  */
-static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
-			      unsigned long c)
+static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
+			      unsigned long gp_seq_req)
 {
 	bool ret = false;
 	struct rcu_state *rsp = rdp->rsp;
-	struct rcu_node *rnp_root;
+	struct rcu_node *rnp;
 
 	/*
 	 * Use funnel locking to either acquire the root rcu_node
 	 * structure's lock or bail out if the need for this grace period
-	 * has already been recorded -- or has already started.  If there
-	 * is already a grace period in progress in a non-leaf node, no
-	 * recording is needed because the end of the grace period will
-	 * scan the leaf rcu_node structures.  Note that rnp->lock must
-	 * not be released.
+	 * has already been recorded -- or if that grace period has in
+	 * fact already started.  If there is already a grace period in
+	 * progress in a non-leaf node, no recording is needed because the
+	 * end of the grace period will scan the leaf rcu_node structures.
+	 * Note that rnp_start->lock must not be released.
 	 */
-	raw_lockdep_assert_held_rcu_node(rnp);
-	trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
-	for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
-		if (rnp_root != rnp)
-			raw_spin_lock_rcu_node(rnp_root);
-		WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum +
-					  need_future_gp_mask(), c));
-		if (need_future_gp_element(rnp_root, c) ||
-		    ULONG_CMP_GE(rnp_root->gpnum, c) ||
-		    (rnp != rnp_root &&
-		     rnp_root->gpnum != rnp_root->completed)) {
-			trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
+	raw_lockdep_assert_held_rcu_node(rnp_start);
+	trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf"));
+	for (rnp = rnp_start; 1; rnp = rnp->parent) {
+		if (rnp != rnp_start)
+			raw_spin_lock_rcu_node(rnp);
+		if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) ||
+		    rcu_seq_started(&rnp->gp_seq, gp_seq_req) ||
+		    (rnp != rnp_start &&
+		     rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) {
+			trace_rcu_this_gp(rnp, rdp, gp_seq_req,
+					  TPS("Prestarted"));
 			goto unlock_out;
 		}
-		need_future_gp_element(rnp_root, c) = true;
-		if (rnp_root != rnp && rnp_root->parent != NULL)
-			raw_spin_unlock_rcu_node(rnp_root);
-		if (!rnp_root->parent)
+		rnp->gp_seq_needed = gp_seq_req;
+		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
+			/*
+			 * We just marked the leaf or internal node, and a
+			 * grace period is in progress, which means that
+			 * rcu_gp_cleanup() will see the marking.  Bail to
+			 * reduce contention.
+			 */
+			trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
+					  TPS("Startedleaf"));
+			goto unlock_out;
+		}
+		if (rnp != rnp_start && rnp->parent != NULL)
+			raw_spin_unlock_rcu_node(rnp);
+		if (!rnp->parent)
 			break;  /* At root, and perhaps also leaf. */
 	}
 
 	/* If GP already in progress, just leave, otherwise start one. */
-	if (rnp_root->gpnum != rnp_root->completed) {
-		trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot"));
+	if (rcu_gp_in_progress(rsp)) {
+		trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot"));
 		goto unlock_out;
 	}
-	trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot"));
+	trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
 	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
+	rsp->gp_req_activity = jiffies;
 	if (!rsp->gp_kthread) {
-		trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
+		trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
 		goto unlock_out;
 	}
-	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq"));
+	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq"));
 	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
-	if (rnp != rnp_root)
-		raw_spin_unlock_rcu_node(rnp_root);
+	/* Push furthest requested GP to leaf node and rcu_data structure. */
+	if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
+		rnp_start->gp_seq_needed = rnp->gp_seq_needed;
+		rdp->gp_seq_needed = rnp->gp_seq_needed;
+	}
+	if (rnp != rnp_start)
+		raw_spin_unlock_rcu_node(rnp);
 	return ret;
 }
 
@@ -1703,13 +1677,13 @@ unlock_out:
  */
 static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 {
-	unsigned long c = rnp->completed;
 	bool needmore;
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
-	need_future_gp_element(rnp, c) = false;
-	needmore = need_any_future_gp(rnp);
-	trace_rcu_this_gp(rnp, rdp, c,
+	needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed);
+	if (!needmore)
+		rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */
+	trace_rcu_this_gp(rnp, rdp, rnp->gp_seq,
 			  needmore ? TPS("CleanupMore") : TPS("Cleanup"));
 	return needmore;
 }
@@ -1727,25 +1701,25 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 	    !READ_ONCE(rsp->gp_flags) ||
 	    !rsp->gp_kthread)
 		return;
-	swake_up(&rsp->gp_wq);
+	swake_up_one(&rsp->gp_wq);
 }
 
 /*
- * If there is room, assign a ->completed number to any callbacks on
- * this CPU that have not already been assigned.  Also accelerate any
- * callbacks that were previously assigned a ->completed number that has
- * since proven to be too conservative, which can happen if callbacks get
- * assigned a ->completed number while RCU is idle, but with reference to
- * a non-root rcu_node structure.  This function is idempotent, so it does
- * not hurt to call it repeatedly.  Returns an flag saying that we should
- * awaken the RCU grace-period kthread.
+ * If there is room, assign a ->gp_seq number to any callbacks on this
+ * CPU that have not already been assigned.  Also accelerate any callbacks
+ * that were previously assigned a ->gp_seq number that has since proven
+ * to be too conservative, which can happen if callbacks get assigned a
+ * ->gp_seq number while RCU is idle, but with reference to a non-root
+ * rcu_node structure.  This function is idempotent, so it does not hurt
+ * to call it repeatedly.  Returns an flag saying that we should awaken
+ * the RCU grace-period kthread.
  *
  * The caller must hold rnp->lock with interrupts disabled.
  */
 static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 			       struct rcu_data *rdp)
 {
-	unsigned long c;
+	unsigned long gp_seq_req;
 	bool ret = false;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
@@ -1764,22 +1738,50 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 	 * accelerating callback invocation to an earlier grace-period
 	 * number.
 	 */
-	c = rcu_cbs_completed(rsp, rnp);
-	if (rcu_segcblist_accelerate(&rdp->cblist, c))
-		ret = rcu_start_this_gp(rnp, rdp, c);
+	gp_seq_req = rcu_seq_snap(&rsp->gp_seq);
+	if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req))
+		ret = rcu_start_this_gp(rnp, rdp, gp_seq_req);
 
 	/* Trace depending on how much we were able to accelerate. */
 	if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB"));
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB"));
 	else
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB"));
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB"));
 	return ret;
 }
 
 /*
+ * Similar to rcu_accelerate_cbs(), but does not require that the leaf
+ * rcu_node structure's ->lock be held.  It consults the cached value
+ * of ->gp_seq_needed in the rcu_data structure, and if that indicates
+ * that a new grace-period request be made, invokes rcu_accelerate_cbs()
+ * while holding the leaf rcu_node structure's ->lock.
+ */
+static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp,
+					struct rcu_node *rnp,
+					struct rcu_data *rdp)
+{
+	unsigned long c;
+	bool needwake;
+
+	lockdep_assert_irqs_disabled();
+	c = rcu_seq_snap(&rsp->gp_seq);
+	if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+		/* Old request still live, so mark recent callbacks. */
+		(void)rcu_segcblist_accelerate(&rdp->cblist, c);
+		return;
+	}
+	raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+	needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+	raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
+	if (needwake)
+		rcu_gp_kthread_wake(rsp);
+}
+
+/*
  * Move any callbacks whose grace period has completed to the
  * RCU_DONE_TAIL sublist, then compact the remaining sublists and
- * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
+ * assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL
  * sublist.  This function is idempotent, so it does not hurt to
  * invoke it repeatedly.  As long as it is not invoked -too- often...
  * Returns true if the RCU grace-period kthread needs to be awakened.
@@ -1796,10 +1798,10 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 		return false;
 
 	/*
-	 * Find all callbacks whose ->completed numbers indicate that they
+	 * Find all callbacks whose ->gp_seq numbers indicate that they
 	 * are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
 	 */
-	rcu_segcblist_advance(&rdp->cblist, rnp->completed);
+	rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq);
 
 	/* Classify any remaining callbacks. */
 	return rcu_accelerate_cbs(rsp, rnp, rdp);
@@ -1819,39 +1821,38 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 
 	raw_lockdep_assert_held_rcu_node(rnp);
 
-	/* Handle the ends of any preceding grace periods first. */
-	if (rdp->completed == rnp->completed &&
-	    !unlikely(READ_ONCE(rdp->gpwrap))) {
-
-		/* No grace period end, so just accelerate recent callbacks. */
-		ret = rcu_accelerate_cbs(rsp, rnp, rdp);
+	if (rdp->gp_seq == rnp->gp_seq)
+		return false; /* Nothing to do. */
 
+	/* Handle the ends of any preceding grace periods first. */
+	if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
+	    unlikely(READ_ONCE(rdp->gpwrap))) {
+		ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend"));
 	} else {
-
-		/* Advance callbacks. */
-		ret = rcu_advance_cbs(rsp, rnp, rdp);
-
-		/* Remember that we saw this grace-period completion. */
-		rdp->completed = rnp->completed;
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
+		ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */
 	}
 
-	if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
+	/* Now handle the beginnings of any new-to-this-CPU grace periods. */
+	if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) ||
+	    unlikely(READ_ONCE(rdp->gpwrap))) {
 		/*
 		 * If the current grace period is waiting for this CPU,
 		 * set up to detect a quiescent state, otherwise don't
 		 * go looking for one.
 		 */
-		rdp->gpnum = rnp->gpnum;
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
+		trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart"));
 		need_gp = !!(rnp->qsmask & rdp->grpmask);
 		rdp->cpu_no_qs.b.norm = need_gp;
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
 		rdp->core_needs_qs = need_gp;
 		zero_cpu_stall_ticks(rdp);
-		WRITE_ONCE(rdp->gpwrap, false);
-		rcu_gpnum_ovf(rnp, rdp);
 	}
+	rdp->gp_seq = rnp->gp_seq;  /* Remember new grace-period state. */
+	if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap)
+		rdp->gp_seq_needed = rnp->gp_seq_needed;
+	WRITE_ONCE(rdp->gpwrap, false);
+	rcu_gpnum_ovf(rnp, rdp);
 	return ret;
 }
 
@@ -1863,8 +1864,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	local_irq_save(flags);
 	rnp = rdp->mynode;
-	if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
-	     rdp->completed == READ_ONCE(rnp->completed) &&
+	if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) &&
 	     !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
 	    !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
@@ -1879,7 +1879,8 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 static void rcu_gp_slow(struct rcu_state *rsp, int delay)
 {
 	if (delay > 0 &&
-	    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
+	    !(rcu_seq_ctr(rsp->gp_seq) %
+	      (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
 		schedule_timeout_uninterruptible(delay);
 }
 
@@ -1888,7 +1889,9 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay)
  */
 static bool rcu_gp_init(struct rcu_state *rsp)
 {
+	unsigned long flags;
 	unsigned long oldmask;
+	unsigned long mask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
@@ -1912,9 +1915,9 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 
 	/* Advance to a new grace period and initialize state. */
 	record_gp_stall_check_time(rsp);
-	/* Record GP times before starting GP, hence smp_store_release(). */
-	smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
-	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
+	/* Record GP times before starting GP, hence rcu_seq_start(). */
+	rcu_seq_start(&rsp->gp_seq);
+	trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start"));
 	raw_spin_unlock_irq_rcu_node(rnp);
 
 	/*
@@ -1923,13 +1926,15 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 * for subsequent online CPUs, and that quiescent-state forcing
 	 * will handle subsequent offline CPUs.
 	 */
+	rsp->gp_state = RCU_GP_ONOFF;
 	rcu_for_each_leaf_node(rsp, rnp) {
-		rcu_gp_slow(rsp, gp_preinit_delay);
+		spin_lock(&rsp->ofl_lock);
 		raw_spin_lock_irq_rcu_node(rnp);
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
 		    !rnp->wait_blkd_tasks) {
 			/* Nothing to do on this leaf rcu_node structure. */
 			raw_spin_unlock_irq_rcu_node(rnp);
+			spin_unlock(&rsp->ofl_lock);
 			continue;
 		}
 
@@ -1939,12 +1944,14 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 
 		/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
 		if (!oldmask != !rnp->qsmaskinit) {
-			if (!oldmask) /* First online CPU for this rcu_node. */
-				rcu_init_new_rnp(rnp);
-			else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */
-				rnp->wait_blkd_tasks = true;
-			else /* Last offline CPU and can propagate. */
+			if (!oldmask) { /* First online CPU for rcu_node. */
+				if (!rnp->wait_blkd_tasks) /* Ever offline? */
+					rcu_init_new_rnp(rnp);
+			} else if (rcu_preempt_has_tasks(rnp)) {
+				rnp->wait_blkd_tasks = true; /* blocked tasks */
+			} else { /* Last offline CPU and can propagate. */
 				rcu_cleanup_dead_rnp(rnp);
+			}
 		}
 
 		/*
@@ -1953,18 +1960,19 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		 * still offline, propagate up the rcu_node tree and
 		 * clear ->wait_blkd_tasks.  Otherwise, if one of this
 		 * rcu_node structure's CPUs has since come back online,
-		 * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp()
-		 * checks for this, so just call it unconditionally).
+		 * simply clear ->wait_blkd_tasks.
 		 */
 		if (rnp->wait_blkd_tasks &&
-		    (!rcu_preempt_has_tasks(rnp) ||
-		     rnp->qsmaskinit)) {
+		    (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) {
 			rnp->wait_blkd_tasks = false;
-			rcu_cleanup_dead_rnp(rnp);
+			if (!rnp->qsmaskinit)
+				rcu_cleanup_dead_rnp(rnp);
 		}
 
 		raw_spin_unlock_irq_rcu_node(rnp);
+		spin_unlock(&rsp->ofl_lock);
 	}
+	rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */
 
 	/*
 	 * Set the quiescent-state-needed bits in all the rcu_node
@@ -1978,22 +1986,27 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 * The grace period cannot complete until the initialization
 	 * process finishes, because this kthread handles both.
 	 */
+	rsp->gp_state = RCU_GP_INIT;
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_init_delay);
-		raw_spin_lock_irq_rcu_node(rnp);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		rdp = this_cpu_ptr(rsp->rda);
-		rcu_preempt_check_blocked_tasks(rnp);
+		rcu_preempt_check_blocked_tasks(rsp, rnp);
 		rnp->qsmask = rnp->qsmaskinit;
-		WRITE_ONCE(rnp->gpnum, rsp->gpnum);
-		if (WARN_ON_ONCE(rnp->completed != rsp->completed))
-			WRITE_ONCE(rnp->completed, rsp->completed);
+		WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
 		if (rnp == rdp->mynode)
 			(void)__note_gp_changes(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
-		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
+		trace_rcu_grace_period_init(rsp->name, rnp->gp_seq,
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
-		raw_spin_unlock_irq_rcu_node(rnp);
+		/* Quiescent states for tasks on any now-offline CPUs. */
+		mask = rnp->qsmask & ~rnp->qsmaskinitnext;
+		rnp->rcu_gp_init_mask = mask;
+		if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+		else
+			raw_spin_unlock_irq_rcu_node(rnp);
 		cond_resched_tasks_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 	}
@@ -2002,7 +2015,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 }
 
 /*
- * Helper function for swait_event_idle() wakeup at force-quiescent-state
+ * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state
  * time.
  */
 static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
@@ -2053,6 +2066,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 {
 	unsigned long gp_duration;
 	bool needgp = false;
+	unsigned long new_gp_seq;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	struct swait_queue_head *sq;
@@ -2074,19 +2088,22 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	raw_spin_unlock_irq_rcu_node(rnp);
 
 	/*
-	 * Propagate new ->completed value to rcu_node structures so
-	 * that other CPUs don't have to wait until the start of the next
-	 * grace period to process their callbacks.  This also avoids
-	 * some nasty RCU grace-period initialization races by forcing
-	 * the end of the current grace period to be completely recorded in
-	 * all of the rcu_node structures before the beginning of the next
-	 * grace period is recorded in any of the rcu_node structures.
+	 * Propagate new ->gp_seq value to rcu_node structures so that
+	 * other CPUs don't have to wait until the start of the next grace
+	 * period to process their callbacks.  This also avoids some nasty
+	 * RCU grace-period initialization races by forcing the end of
+	 * the current grace period to be completely recorded in all of
+	 * the rcu_node structures before the beginning of the next grace
+	 * period is recorded in any of the rcu_node structures.
 	 */
+	new_gp_seq = rsp->gp_seq;
+	rcu_seq_end(&new_gp_seq);
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq_rcu_node(rnp);
-		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+		if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+			dump_blkd_tasks(rsp, rnp, 10);
 		WARN_ON_ONCE(rnp->qsmask);
-		WRITE_ONCE(rnp->completed, rsp->gpnum);
+		WRITE_ONCE(rnp->gp_seq, new_gp_seq);
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
 			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
@@ -2100,26 +2117,28 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
-	raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
+	raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */
 
 	/* Declare grace period done. */
-	WRITE_ONCE(rsp->completed, rsp->gpnum);
-	trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
+	rcu_seq_end(&rsp->gp_seq);
+	trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end"));
 	rsp->gp_state = RCU_GP_IDLE;
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(rsp->rda);
-	if (need_any_future_gp(rnp)) {
-		trace_rcu_this_gp(rnp, rdp, rsp->completed - 1,
+	if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
+		trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed,
 				  TPS("CleanupMore"));
 		needgp = true;
 	}
 	/* Advance CBs to reduce false positives below. */
 	if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
 		WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
-		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
+		rsp->gp_req_activity = jiffies;
+		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq),
 				       TPS("newreq"));
+	} else {
+		WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
 	}
-	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
 	raw_spin_unlock_irq_rcu_node(rnp);
 }
 
@@ -2141,10 +2160,10 @@ static int __noreturn rcu_gp_kthread(void *arg)
 		/* Handle grace-period start. */
 		for (;;) {
 			trace_rcu_grace_period(rsp->name,
-					       READ_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gp_seq),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
-			swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
+			swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
 						     RCU_GP_FLAG_INIT);
 			rsp->gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
@@ -2154,17 +2173,13 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			WRITE_ONCE(rsp->gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
 			trace_rcu_grace_period(rsp->name,
-					       READ_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gp_seq),
 					       TPS("reqwaitsig"));
 		}
 
 		/* Handle quiescent-state forcing. */
 		first_gp_fqs = true;
 		j = jiffies_till_first_fqs;
-		if (j > HZ) {
-			j = HZ;
-			jiffies_till_first_fqs = HZ;
-		}
 		ret = 0;
 		for (;;) {
 			if (!ret) {
@@ -2173,10 +2188,10 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					   jiffies + 3 * j);
 			}
 			trace_rcu_grace_period(rsp->name,
-					       READ_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gp_seq),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
-			ret = swait_event_idle_timeout(rsp->gp_wq,
+			ret = swait_event_idle_timeout_exclusive(rsp->gp_wq,
 					rcu_gp_fqs_check_wake(rsp, &gf), j);
 			rsp->gp_state = RCU_GP_DOING_FQS;
 			/* Locking provides needed memory barriers. */
@@ -2188,31 +2203,24 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
 			    (gf & RCU_GP_FLAG_FQS)) {
 				trace_rcu_grace_period(rsp->name,
-						       READ_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gp_seq),
 						       TPS("fqsstart"));
 				rcu_gp_fqs(rsp, first_gp_fqs);
 				first_gp_fqs = false;
 				trace_rcu_grace_period(rsp->name,
-						       READ_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gp_seq),
 						       TPS("fqsend"));
 				cond_resched_tasks_rcu_qs();
 				WRITE_ONCE(rsp->gp_activity, jiffies);
 				ret = 0; /* Force full wait till next FQS. */
 				j = jiffies_till_next_fqs;
-				if (j > HZ) {
-					j = HZ;
-					jiffies_till_next_fqs = HZ;
-				} else if (j < 1) {
-					j = 1;
-					jiffies_till_next_fqs = 1;
-				}
 			} else {
 				/* Deal with stray signal. */
 				cond_resched_tasks_rcu_qs();
 				WRITE_ONCE(rsp->gp_activity, jiffies);
 				WARN_ON(signal_pending(current));
 				trace_rcu_grace_period(rsp->name,
-						       READ_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gp_seq),
 						       TPS("fqswaitsig"));
 				ret = 1; /* Keep old FQS timing. */
 				j = jiffies;
@@ -2256,8 +2264,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
  * must be represented by the same rcu_node structure (which need not be a
  * leaf rcu_node structure, though it often will be).  The gps parameter
  * is the grace-period snapshot, which means that the quiescent states
- * are valid only if rnp->gpnum is equal to gps.  That structure's lock
+ * are valid only if rnp->gp_seq is equal to gps.  That structure's lock
  * must be held upon entry, and it is released before return.
+ *
+ * As a special case, if mask is zero, the bit-already-cleared check is
+ * disabled.  This allows propagating quiescent state due to resumed tasks
+ * during grace-period initialization.
  */
 static void
 rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
@@ -2271,7 +2283,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 
 	/* Walk up the rcu_node hierarchy. */
 	for (;;) {
-		if (!(rnp->qsmask & mask) || rnp->gpnum != gps) {
+		if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) {
 
 			/*
 			 * Our bit has already been cleared, or the
@@ -2284,7 +2296,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
 			     rcu_preempt_blocked_readers_cgp(rnp));
 		rnp->qsmask &= ~mask;
-		trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
+		trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq,
 						 mask, rnp->qsmask, rnp->level,
 						 rnp->grplo, rnp->grphi,
 						 !!rnp->gp_tasks);
@@ -2294,6 +2306,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			return;
 		}
+		rnp->completedqs = rnp->gp_seq;
 		mask = rnp->grpmask;
 		if (rnp->parent == NULL) {
 
@@ -2323,8 +2336,9 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
  * irqs disabled, and this lock is released upon return, but irqs remain
  * disabled.
  */
-static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
-				      struct rcu_node *rnp, unsigned long flags)
+static void __maybe_unused
+rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
+			  struct rcu_node *rnp, unsigned long flags)
 	__releases(rnp->lock)
 {
 	unsigned long gps;
@@ -2332,12 +2346,15 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 	struct rcu_node *rnp_p;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
-	if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p ||
-	    rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
+	if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) ||
+	    WARN_ON_ONCE(rsp != rcu_state_p) ||
+	    WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
+	    rnp->qsmask != 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;  /* Still need more quiescent states! */
 	}
 
+	rnp->completedqs = rnp->gp_seq;
 	rnp_p = rnp->parent;
 	if (rnp_p == NULL) {
 		/*
@@ -2348,8 +2365,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 		return;
 	}
 
-	/* Report up the rest of the hierarchy, tracking current ->gpnum. */
-	gps = rnp->gpnum;
+	/* Report up the rest of the hierarchy, tracking current ->gp_seq. */
+	gps = rnp->gp_seq;
 	mask = rnp->grpmask;
 	raw_spin_unlock_rcu_node(rnp);	/* irqs remain disabled. */
 	raw_spin_lock_rcu_node(rnp_p);	/* irqs already disabled. */
@@ -2370,8 +2387,8 @@ 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->gpnum != rnp->gpnum ||
-	    rnp->completed == rnp->gpnum || rdp->gpwrap) {
+	if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
+	    rdp->gpwrap) {
 
 		/*
 		 * The grace period in which this quiescent state was
@@ -2396,7 +2413,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 */
 		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 
-		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
 		/* ^^^ Released rnp->lock */
 		if (needwake)
 			rcu_gp_kthread_wake(rsp);
@@ -2441,17 +2458,16 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
 {
-	RCU_TRACE(unsigned long mask;)
+	RCU_TRACE(bool blkd;)
 	RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);)
 	RCU_TRACE(struct rcu_node *rnp = rdp->mynode;)
 
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
 		return;
 
-	RCU_TRACE(mask = rdp->grpmask;)
-	trace_rcu_grace_period(rsp->name,
-			       rnp->gpnum + 1 - !!(rnp->qsmask & mask),
-			       TPS("cpuofl"));
+	RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);)
+	trace_rcu_grace_period(rsp->name, rnp->gp_seq,
+			       blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
 }
 
 /*
@@ -2463,7 +2479,7 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
  * This function therefore goes up the tree of rcu_node structures,
  * clearing the corresponding bits in the ->qsmaskinit fields.  Note that
  * the leaf rcu_node structure's ->qsmaskinit field has already been
- * updated
+ * updated.
  *
  * This function does check that the specified rcu_node structure has
  * all CPUs offline and no blocked tasks, so it is OK to invoke it
@@ -2476,9 +2492,10 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 	long mask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	raw_lockdep_assert_held_rcu_node(rnp);
+	raw_lockdep_assert_held_rcu_node(rnp_leaf);
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
-	    rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+	    WARN_ON_ONCE(rnp_leaf->qsmaskinit) ||
+	    WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf)))
 		return;
 	for (;;) {
 		mask = rnp->grpmask;
@@ -2487,7 +2504,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 			break;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		rnp->qsmaskinit &= ~mask;
-		rnp->qsmask &= ~mask;
+		/* Between grace periods, so better already be zero! */
+		WARN_ON_ONCE(rnp->qsmask);
 		if (rnp->qsmaskinit) {
 			raw_spin_unlock_rcu_node(rnp);
 			/* irqs remain disabled. */
@@ -2630,6 +2648,7 @@ void rcu_check_callbacks(int user)
 
 		rcu_sched_qs();
 		rcu_bh_qs();
+		rcu_note_voluntary_context_switch(current);
 
 	} else if (!in_softirq()) {
 
@@ -2645,8 +2664,7 @@ void rcu_check_callbacks(int user)
 	rcu_preempt_check_callbacks();
 	if (rcu_pending())
 		invoke_rcu_core();
-	if (user)
-		rcu_note_voluntary_context_switch(current);
+
 	trace_rcu_utilization(TPS("End scheduler-tick"));
 }
 
@@ -2681,17 +2699,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
 				/* rcu_initiate_boost() releases rnp->lock */
 				continue;
 			}
-			if (rnp->parent &&
-			    (rnp->parent->qsmask & rnp->grpmask)) {
-				/*
-				 * Race between grace-period
-				 * initialization and task exiting RCU
-				 * read-side critical section: Report.
-				 */
-				rcu_report_unblock_qs_rnp(rsp, rnp, flags);
-				/* rcu_report_unblock_qs_rnp() rlses ->lock */
-				continue;
-			}
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+			continue;
 		}
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
@@ -2701,8 +2710,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
 			}
 		}
 		if (mask != 0) {
-			/* Idle/offline CPUs, report (releases rnp->lock. */
-			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+			/* Idle/offline CPUs, report (releases rnp->lock). */
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
 		} else {
 			/* Nothing to do here, so just drop the lock. */
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2747,6 +2756,65 @@ static void force_quiescent_state(struct rcu_state *rsp)
 }
 
 /*
+ * This function checks for grace-period requests that fail to motivate
+ * RCU to come out of its idle mode.
+ */
+static void
+rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
+			 struct rcu_data *rdp)
+{
+	const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
+	unsigned long flags;
+	unsigned long j;
+	struct rcu_node *rnp_root = rcu_get_root(rsp);
+	static atomic_t warned = ATOMIC_INIT(0);
+
+	if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+		return;
+	j = jiffies; /* Expensive access, and in common case don't get here. */
+	if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
+	    atomic_read(&warned))
+		return;
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	j = jiffies;
+	if (rcu_gp_in_progress(rsp) ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
+	    atomic_read(&warned)) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	/* Hold onto the leaf lock to make others see warned==1. */
+
+	if (rnp_root != rnp)
+		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+	j = jiffies;
+	if (rcu_gp_in_progress(rsp) ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    time_before(j, rsp->gp_req_activity + gpssdelay) ||
+	    time_before(j, rsp->gp_activity + gpssdelay) ||
+	    atomic_xchg(&warned, 1)) {
+		raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
+		 __func__, (long)READ_ONCE(rsp->gp_seq),
+		 (long)READ_ONCE(rnp_root->gp_seq_needed),
+		 j - rsp->gp_req_activity, j - rsp->gp_activity,
+		 rsp->gp_flags, rsp->gp_state, rsp->name,
+		 rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL);
+	WARN_ON(1);
+	if (rnp_root != rnp)
+		raw_spin_unlock_rcu_node(rnp_root);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+}
+
+/*
  * This does the RCU core processing work for the specified rcu_state
  * and rcu_data structures.  This may be called only from the CPU to
  * whom the rdp belongs.
@@ -2755,9 +2823,8 @@ static void
 __rcu_process_callbacks(struct rcu_state *rsp)
 {
 	unsigned long flags;
-	bool needwake;
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
-	struct rcu_node *rnp;
+	struct rcu_node *rnp = rdp->mynode;
 
 	WARN_ON_ONCE(!rdp->beenonline);
 
@@ -2768,18 +2835,13 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	if (!rcu_gp_in_progress(rsp) &&
 	    rcu_segcblist_is_enabled(&rdp->cblist)) {
 		local_irq_save(flags);
-		if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
-			local_irq_restore(flags);
-		} else {
-			rnp = rdp->mynode;
-			raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
-			needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
-			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-			if (needwake)
-				rcu_gp_kthread_wake(rsp);
-		}
+		if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
+			rcu_accelerate_cbs_unlocked(rsp, rnp, rdp);
+		local_irq_restore(flags);
 	}
 
+	rcu_check_gp_start_stall(rsp, rnp, rdp);
+
 	/* If there are callbacks ready, invoke them. */
 	if (rcu_segcblist_ready_cbs(&rdp->cblist))
 		invoke_rcu_callbacks(rsp, rdp);
@@ -2833,8 +2895,6 @@ static void invoke_rcu_core(void)
 static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 			    struct rcu_head *head, unsigned long flags)
 {
-	bool needwake;
-
 	/*
 	 * If called from an extended quiescent state, invoke the RCU
 	 * core in order to force a re-evaluation of RCU's idleness.
@@ -2861,13 +2921,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 
 		/* Start a new grace period if one not already started. */
 		if (!rcu_gp_in_progress(rsp)) {
-			struct rcu_node *rnp = rdp->mynode;
-
-			raw_spin_lock_rcu_node(rnp);
-			needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
-			raw_spin_unlock_rcu_node(rnp);
-			if (needwake)
-				rcu_gp_kthread_wake(rsp);
+			rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp);
 		} else {
 			/* Give the grace period a kick. */
 			rdp->blimit = LONG_MAX;
@@ -3037,7 +3091,7 @@ EXPORT_SYMBOL_GPL(kfree_call_rcu);
  * when there was in fact only one the whole time, as this just adds
  * some overhead: RCU still operates correctly.
  */
-static inline int rcu_blocking_is_gp(void)
+static int rcu_blocking_is_gp(void)
 {
 	int ret;
 
@@ -3136,16 +3190,10 @@ unsigned long get_state_synchronize_rcu(void)
 {
 	/*
 	 * Any prior manipulation of RCU-protected data must happen
-	 * before the load from ->gpnum.
+	 * before the load from ->gp_seq.
 	 */
 	smp_mb();  /* ^^^ */
-
-	/*
-	 * Make sure this load happens before the purportedly
-	 * time-consuming work between get_state_synchronize_rcu()
-	 * and cond_synchronize_rcu().
-	 */
-	return smp_load_acquire(&rcu_state_p->gpnum);
+	return rcu_seq_snap(&rcu_state_p->gp_seq);
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
 
@@ -3165,15 +3213,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
  */
 void cond_synchronize_rcu(unsigned long oldstate)
 {
-	unsigned long newstate;
-
-	/*
-	 * Ensure that this load happens before any RCU-destructive
-	 * actions the caller might carry out after we return.
-	 */
-	newstate = smp_load_acquire(&rcu_state_p->completed);
-	if (ULONG_CMP_GE(oldstate, newstate))
+	if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate))
 		synchronize_rcu();
+	else
+		smp_mb(); /* Ensure GP ends before subsequent accesses. */
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
 
@@ -3188,16 +3231,10 @@ unsigned long get_state_synchronize_sched(void)
 {
 	/*
 	 * Any prior manipulation of RCU-protected data must happen
-	 * before the load from ->gpnum.
+	 * before the load from ->gp_seq.
 	 */
 	smp_mb();  /* ^^^ */
-
-	/*
-	 * Make sure this load happens before the purportedly
-	 * time-consuming work between get_state_synchronize_sched()
-	 * and cond_synchronize_sched().
-	 */
-	return smp_load_acquire(&rcu_sched_state.gpnum);
+	return rcu_seq_snap(&rcu_sched_state.gp_seq);
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
 
@@ -3217,15 +3254,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
  */
 void cond_synchronize_sched(unsigned long oldstate)
 {
-	unsigned long newstate;
-
-	/*
-	 * Ensure that this load happens before any RCU-destructive
-	 * actions the caller might carry out after we return.
-	 */
-	newstate = smp_load_acquire(&rcu_sched_state.completed);
-	if (ULONG_CMP_GE(oldstate, newstate))
+	if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate))
 		synchronize_sched();
+	else
+		smp_mb(); /* Ensure GP ends before subsequent accesses. */
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_sched);
 
@@ -3261,12 +3293,8 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	    !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
 		return 1;
 
-	/* Has another RCU grace period completed?  */
-	if (READ_ONCE(rnp->completed) != rdp->completed) /* outside lock */
-		return 1;
-
-	/* Has a new RCU grace period started? */
-	if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
+	/* Have RCU grace period completed or started?  */
+	if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq ||
 	    unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */
 		return 1;
 
@@ -3298,7 +3326,7 @@ static int rcu_pending(void)
  * non-NULL, store an indication of whether all callbacks are lazy.
  * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
+static bool rcu_cpu_has_callbacks(bool *all_lazy)
 {
 	bool al = true;
 	bool hc = false;
@@ -3484,17 +3512,22 @@ EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 {
 	long mask;
+	long oldmask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	raw_lockdep_assert_held_rcu_node(rnp);
+	raw_lockdep_assert_held_rcu_node(rnp_leaf);
+	WARN_ON_ONCE(rnp->wait_blkd_tasks);
 	for (;;) {
 		mask = rnp->grpmask;
 		rnp = rnp->parent;
 		if (rnp == NULL)
 			return;
 		raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
+		oldmask = rnp->qsmaskinit;
 		rnp->qsmaskinit |= mask;
 		raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */
+		if (oldmask)
+			return;
 	}
 }
 
@@ -3511,6 +3544,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1);
 	WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
+	rdp->rcu_ofl_gp_seq = rsp->gp_seq;
+	rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
+	rdp->rcu_onl_gp_seq = rsp->gp_seq;
+	rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	rcu_boot_init_nocb_percpu_data(rdp);
@@ -3518,9 +3555,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 
 /*
  * Initialize a CPU's per-CPU RCU data.  Note that only one online or
- * offline event can be happening at a given time.  Note also that we
- * can accept some slop in the rsp->completed access due to the fact
- * that this CPU cannot possibly have any RCU callbacks in flight yet.
+ * offline event can be happening at a given time.  Note also that we can
+ * accept some slop in the rsp->gp_seq access due to the fact that this
+ * CPU cannot possibly have any RCU callbacks in flight yet.
  */
 static void
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
@@ -3549,14 +3586,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rnp = rdp->mynode;
 	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	rdp->beenonline = true;	 /* We have now been online. */
-	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
-	rdp->completed = rnp->completed;
+	rdp->gp_seq = rnp->gp_seq;
+	rdp->gp_seq_needed = rnp->gp_seq;
 	rdp->cpu_no_qs.b.norm = true;
 	rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
 	rdp->core_needs_qs = false;
 	rdp->rcu_iw_pending = false;
-	rdp->rcu_iw_gpnum = rnp->gpnum - 1;
-	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
+	rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
+	trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
@@ -3705,7 +3742,15 @@ void rcu_cpu_starting(unsigned int cpu)
 		nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
 		/* Allow lockless access for expedited grace periods. */
 		smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
+		rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq);
+		rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags);
+		if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+			/* Report QS -after- changing ->qsmaskinitnext! */
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+		} else {
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		}
 	}
 	smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
 }
@@ -3713,7 +3758,7 @@ void rcu_cpu_starting(unsigned int cpu)
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
- * function.  We now remove it from the rcu_node tree's ->qsmaskinit
+ * function.  We now remove it from the rcu_node tree's ->qsmaskinitnext
  * bit masks.
  */
 static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
@@ -3725,9 +3770,18 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
+	spin_lock(&rsp->ofl_lock);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+	rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq);
+	rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags);
+	if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
+		/* Report quiescent state -before- changing ->qsmaskinitnext! */
+		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	}
 	rnp->qsmaskinitnext &= ~mask;
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	spin_unlock(&rsp->ofl_lock);
 }
 
 /*
@@ -3839,12 +3893,16 @@ static int __init rcu_spawn_gp_kthread(void)
 	struct task_struct *t;
 
 	/* Force priority into range. */
-	if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
+	if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2
+	    && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST))
+		kthread_prio = 2;
+	else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
 		kthread_prio = 1;
 	else if (kthread_prio < 0)
 		kthread_prio = 0;
 	else if (kthread_prio > 99)
 		kthread_prio = 99;
+
 	if (kthread_prio != kthread_prio_in)
 		pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n",
 			 kthread_prio, kthread_prio_in);
@@ -3928,8 +3986,9 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 			raw_spin_lock_init(&rnp->fqslock);
 			lockdep_set_class_and_name(&rnp->fqslock,
 						   &rcu_fqs_class[i], fqs[i]);
-			rnp->gpnum = rsp->gpnum;
-			rnp->completed = rsp->completed;
+			rnp->gp_seq = rsp->gp_seq;
+			rnp->gp_seq_needed = rsp->gp_seq;
+			rnp->completedqs = rsp->gp_seq;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
 			rnp->grplo = j * cpustride;
@@ -3997,7 +4056,7 @@ static void __init rcu_init_geometry(void)
 	if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
 		return;
-	pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
+	pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
 		rcu_fanout_leaf, nr_cpu_ids);
 
 	/*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 78e051dffc5b..4e74df768c57 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -81,18 +81,16 @@ struct rcu_node {
 	raw_spinlock_t __private lock;	/* Root rcu_node's lock protects */
 					/*  some rcu_state fields as well as */
 					/*  following. */
-	unsigned long gpnum;	/* Current grace period for this node. */
-				/*  This will either be equal to or one */
-				/*  behind the root rcu_node's gpnum. */
-	unsigned long completed; /* Last GP completed for this node. */
-				/*  This will either be equal to or one */
-				/*  behind the root rcu_node's gpnum. */
+	unsigned long gp_seq;	/* Track rsp->rcu_gp_seq. */
+	unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
+	unsigned long completedqs; /* All QSes done for this node. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
 				/*  order for current grace period to proceed.*/
 				/*  In leaf rcu_node, each bit corresponds to */
 				/*  an rcu_data structure, otherwise, each */
 				/*  bit corresponds to a child rcu_node */
 				/*  structure. */
+	unsigned long rcu_gp_init_mask;	/* Mask of offline CPUs at GP init. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask. */
 				/*  Initialized from ->qsmaskinitnext at the */
@@ -158,7 +156,6 @@ struct rcu_node {
 	struct swait_queue_head nocb_gp_wq[2];
 				/* Place for rcu_nocb_kthread() to wait GP. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-	u8 need_future_gp[4];	/* Counts of upcoming GP requests. */
 	raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
 
 	spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
@@ -168,22 +165,6 @@ struct rcu_node {
 	bool exp_need_flush;	/* Need to flush workitem? */
 } ____cacheline_internodealigned_in_smp;
 
-/* Accessors for ->need_future_gp[] array. */
-#define need_future_gp_mask() \
-	(ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1)
-#define need_future_gp_element(rnp, c) \
-	((rnp)->need_future_gp[(c) & need_future_gp_mask()])
-#define need_any_future_gp(rnp)						\
-({									\
-	int __i;							\
-	bool __nonzero = false;						\
-									\
-	for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++)	\
-		__nonzero = __nonzero ||				\
-			    READ_ONCE((rnp)->need_future_gp[__i]);	\
-	__nonzero;							\
-})
-
 /*
  * Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
  * are indexed relative to this interval rather than the global CPU ID space.
@@ -206,16 +187,14 @@ union rcu_noqs {
 /* Per-CPU data for read-copy update. */
 struct rcu_data {
 	/* 1) quiescent-state and grace-period handling : */
-	unsigned long	completed;	/* Track rsp->completed gp number */
-					/*  in order to detect GP end. */
-	unsigned long	gpnum;		/* Highest gp number that this CPU */
-					/*  is aware of having started. */
+	unsigned long	gp_seq;		/* Track rsp->rcu_gp_seq counter. */
+	unsigned long	gp_seq_needed;	/* Track rsp->rcu_gp_seq_needed ctr. */
 	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
 					/*  for rcu_all_qs() invocations. */
 	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
 	bool		core_needs_qs;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
-	bool		gpwrap;		/* Possible gpnum/completed wrap. */
+	bool		gpwrap;		/* Possible ->gp_seq wrap. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 	unsigned long	ticks_this_gp;	/* The number of scheduling-clock */
@@ -239,7 +218,6 @@ struct rcu_data {
 
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
 	unsigned long dynticks_fqs;	/* Kicked due to dynticks idle. */
-	unsigned long offline_fqs;	/* Kicked due to being offline. */
 	unsigned long cond_resched_completed;
 					/* Grace period that needs help */
 					/*  from cond_resched(). */
@@ -278,12 +256,16 @@ struct rcu_data {
 					/* Leader CPU takes GP-end wakeups. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
-	/* 7) RCU CPU stall data. */
+	/* 7) Diagnostic data, including RCU CPU stall warnings. */
 	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
 	/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
 	struct irq_work rcu_iw;		/* Check for non-irq activity. */
 	bool rcu_iw_pending;		/* Is ->rcu_iw pending? */
-	unsigned long rcu_iw_gpnum;	/* ->gpnum associated with ->rcu_iw. */
+	unsigned long rcu_iw_gp_seq;	/* ->gp_seq associated with ->rcu_iw. */
+	unsigned long rcu_ofl_gp_seq;	/* ->gp_seq at last offline. */
+	short rcu_ofl_gp_flags;		/* ->gp_flags at last offline. */
+	unsigned long rcu_onl_gp_seq;	/* ->gp_seq at last online. */
+	short rcu_onl_gp_flags;		/* ->gp_flags at last online. */
 
 	int cpu;
 	struct rcu_state *rsp;
@@ -340,8 +322,7 @@ struct rcu_state {
 
 	u8	boost ____cacheline_internodealigned_in_smp;
 						/* Subject to priority boost. */
-	unsigned long gpnum;			/* Current gp number. */
-	unsigned long completed;		/* # of last completed gp. */
+	unsigned long gp_seq;			/* Grace-period sequence #. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
 	struct swait_queue_head gp_wq;		/* Where GP task waits. */
 	short gp_flags;				/* Commands for GP task. */
@@ -373,6 +354,8 @@ struct rcu_state {
 						/*  but in jiffies. */
 	unsigned long gp_activity;		/* Time of last GP kthread */
 						/*  activity in jiffies. */
+	unsigned long gp_req_activity;		/* Time of last GP request */
+						/*  in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 	unsigned long jiffies_resched;		/* Time at which to resched */
@@ -384,6 +367,10 @@ struct rcu_state {
 	const char *name;			/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 	struct list_head flavors;		/* List of RCU flavors. */
+
+	spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
+						/* Synchronize offline with */
+						/*  GP pre-initialization. */
 };
 
 /* Values for rcu_state structure's gp_flags field. */
@@ -394,16 +381,20 @@ struct rcu_state {
 #define RCU_GP_IDLE	 0	/* Initial state and no GP in progress. */
 #define RCU_GP_WAIT_GPS  1	/* Wait for grace-period start. */
 #define RCU_GP_DONE_GPS  2	/* Wait done for grace-period start. */
-#define RCU_GP_WAIT_FQS  3	/* Wait for force-quiescent-state time. */
-#define RCU_GP_DOING_FQS 4	/* Wait done for force-quiescent-state time. */
-#define RCU_GP_CLEANUP   5	/* Grace-period cleanup started. */
-#define RCU_GP_CLEANED   6	/* Grace-period cleanup complete. */
+#define RCU_GP_ONOFF     3	/* Grace-period initialization hotplug. */
+#define RCU_GP_INIT      4	/* Grace-period initialization. */
+#define RCU_GP_WAIT_FQS  5	/* Wait for force-quiescent-state time. */
+#define RCU_GP_DOING_FQS 6	/* Wait done for force-quiescent-state time. */
+#define RCU_GP_CLEANUP   7	/* Grace-period cleanup started. */
+#define RCU_GP_CLEANED   8	/* Grace-period cleanup complete. */
 
 #ifndef RCU_TREE_NONCORE
 static const char * const gp_state_names[] = {
 	"RCU_GP_IDLE",
 	"RCU_GP_WAIT_GPS",
 	"RCU_GP_DONE_GPS",
+	"RCU_GP_ONOFF",
+	"RCU_GP_INIT",
 	"RCU_GP_WAIT_FQS",
 	"RCU_GP_DOING_FQS",
 	"RCU_GP_CLEANUP",
@@ -449,10 +440,13 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static int rcu_print_task_stall(struct rcu_node *rnp);
 static int rcu_print_task_exp_stall(struct rcu_node *rnp);
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
+static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp,
+					    struct rcu_node *rnp);
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void __init __rcu_init_preempt(void);
+static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp,
+			    int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static void invoke_rcu_callbacks_kthread(void);
@@ -489,7 +483,6 @@ static void __init rcu_spawn_nocb_kthreads(void);
 #ifdef CONFIG_RCU_NOCB_CPU
 static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
 static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d40708e8c5d6..0b2c2ad69629 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			if (wake) {
 				smp_mb(); /* EGP done before wake_up(). */
-				swake_up(&rsp->expedited_wq);
+				swake_up_one(&rsp->expedited_wq);
 			}
 			break;
 		}
@@ -472,6 +472,7 @@ retry_ipi:
 static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 				     smp_call_func_t func)
 {
+	int cpu;
 	struct rcu_node *rnp;
 
 	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
@@ -486,13 +487,20 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		rnp->rew.rew_func = func;
 		rnp->rew.rew_rsp = rsp;
 		if (!READ_ONCE(rcu_par_gp_wq) ||
-		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
-			/* No workqueues yet. */
+		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
+		    rcu_is_last_leaf_node(rsp, rnp)) {
+			/* No workqueues yet or last leaf, do direct call. */
 			sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
 			continue;
 		}
 		INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
-		queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work);
+		preempt_disable();
+		cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
+		/* If all offline, queue the work on an unbound CPU. */
+		if (unlikely(cpu > rnp->grphi))
+			cpu = WORK_CPU_UNBOUND;
+		queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
+		preempt_enable();
 		rnp->exp_need_flush = true;
 	}
 
@@ -518,7 +526,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	jiffies_start = jiffies;
 
 	for (;;) {
-		ret = swait_event_timeout(
+		ret = swait_event_timeout_exclusive(
 				rsp->expedited_wq,
 				sync_rcu_preempt_exp_done_unlocked(rnp_root),
 				jiffies_stall);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7fd12039e512..a97c20ea9bce 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -74,8 +74,8 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tRCU event tracing is enabled.\n");
 	if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
 	    (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
-		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
-		       RCU_FANOUT);
+		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d.\n",
+			RCU_FANOUT);
 	if (rcu_fanout_exact)
 		pr_info("\tHierarchical RCU autobalancing is disabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
@@ -88,11 +88,13 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
 			RCU_FANOUT_LEAF);
 	if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
-		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
+		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n",
+			rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%u.\n", NR_CPUS, nr_cpu_ids);
 #ifdef CONFIG_RCU_BOOST
-	pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY);
+	pr_info("\tRCU priority boosting: priority %d delay %d ms.\n",
+		kthread_prio, CONFIG_RCU_BOOST_DELAY);
 #endif
 	if (blimit != DEFAULT_RCU_BLIMIT)
 		pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit);
@@ -127,6 +129,7 @@ static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
 
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			       bool wake);
+static void rcu_read_unlock_special(struct task_struct *t);
 
 /*
  * Tell them what RCU they are running.
@@ -183,6 +186,9 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	raw_lockdep_assert_held_rcu_node(rnp);
 	WARN_ON_ONCE(rdp->mynode != rnp);
 	WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
+	/* RCU better not be waiting on newly onlined CPUs! */
+	WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask &
+		     rdp->grpmask);
 
 	/*
 	 * Decide where to queue the newly blocked task.  In theory,
@@ -260,8 +266,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * ->exp_tasks pointers, respectively, to reference the newly
 	 * blocked tasks.
 	 */
-	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD))
+	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) {
 		rnp->gp_tasks = &t->rcu_node_entry;
+		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
+	}
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
 		rnp->exp_tasks = &t->rcu_node_entry;
 	WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
@@ -286,20 +294,24 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 }
 
 /*
- * Record a preemptible-RCU quiescent state for the specified CPU.  Note
- * that this just means that the task currently running on the CPU is
- * not in a quiescent state.  There might be any number of tasks blocked
- * while in an RCU read-side critical section.
+ * Record a preemptible-RCU quiescent state for the specified CPU.
+ * Note that this does not necessarily mean that the task currently running
+ * on the CPU is in a quiescent state:  Instead, it means that the current
+ * grace period need not wait on any RCU read-side critical section that
+ * starts later on this CPU.  It also means that if the current task is
+ * in an RCU read-side critical section, it has already added itself to
+ * some leaf rcu_node structure's ->blkd_tasks list.  In addition to the
+ * current task, there might be any number of other tasks blocked while
+ * in an RCU read-side critical section.
  *
- * As with the other rcu_*_qs() functions, callers to this function
- * must disable preemption.
+ * Callers to this function must disable preemption.
  */
 static void rcu_preempt_qs(void)
 {
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n");
 	if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_preempt"),
-				       __this_cpu_read(rcu_data_p->gpnum),
+				       __this_cpu_read(rcu_data_p->gp_seq),
 				       TPS("cpuqs"));
 		__this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false);
 		barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
@@ -348,8 +360,8 @@ static void rcu_preempt_note_context_switch(bool preempt)
 		trace_rcu_preempt_task(rdp->rsp->name,
 				       t->pid,
 				       (rnp->qsmask & rdp->grpmask)
-				       ? rnp->gpnum
-				       : rnp->gpnum + 1);
+				       ? rnp->gp_seq
+				       : rcu_seq_snap(&rnp->gp_seq));
 		rcu_preempt_ctxt_queue(rnp, rdp);
 	} else if (t->rcu_read_lock_nesting < 0 &&
 		   t->rcu_read_unlock_special.s) {
@@ -456,7 +468,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
  */
-void rcu_read_unlock_special(struct task_struct *t)
+static void rcu_read_unlock_special(struct task_struct *t)
 {
 	bool empty_exp;
 	bool empty_norm;
@@ -535,13 +547,15 @@ void rcu_read_unlock_special(struct task_struct *t)
 		WARN_ON_ONCE(rnp != t->rcu_blocked_node);
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
+		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq &&
+			     (!empty_norm || rnp->qsmask));
 		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
 		np = rcu_next_node_entry(t, rnp);
 		list_del_init(&t->rcu_node_entry);
 		t->rcu_blocked_node = NULL;
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt"),
-						rnp->gpnum, t->pid);
+						rnp->gp_seq, t->pid);
 		if (&t->rcu_node_entry == rnp->gp_tasks)
 			rnp->gp_tasks = np;
 		if (&t->rcu_node_entry == rnp->exp_tasks)
@@ -562,7 +576,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		empty_exp_now = sync_rcu_preempt_exp_done(rnp);
 		if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
 			trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
-							 rnp->gpnum,
+							 rnp->gp_seq,
 							 0, rnp->qsmask,
 							 rnp->level,
 							 rnp->grplo,
@@ -686,24 +700,27 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * Check that the list of blocked tasks for the newly completed grace
  * period is in fact empty.  It is a serious bug to complete a grace
  * period that still has RCU readers blocked!  This function must be
- * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
+ * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock
  * must be held by the caller.
  *
  * Also, if there are blocked tasks on the list, they automatically
  * block the newly created grace period, so set up ->gp_tasks accordingly.
  */
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	struct task_struct *t;
 
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
-	WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
-	if (rcu_preempt_has_tasks(rnp)) {
+	if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+		dump_blkd_tasks(rsp, rnp, 10);
+	if (rcu_preempt_has_tasks(rnp) &&
+	    (rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
 		rnp->gp_tasks = rnp->blkd_tasks.next;
 		t = container_of(rnp->gp_tasks, struct task_struct,
 				 rcu_node_entry);
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"),
-						rnp->gpnum, t->pid);
+						rnp->gp_seq, t->pid);
 	}
 	WARN_ON_ONCE(rnp->qsmask);
 }
@@ -717,6 +734,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
  */
 static void rcu_preempt_check_callbacks(void)
 {
+	struct rcu_state *rsp = &rcu_preempt_state;
 	struct task_struct *t = current;
 
 	if (t->rcu_read_lock_nesting == 0) {
@@ -725,7 +743,9 @@ static void rcu_preempt_check_callbacks(void)
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
 	    __this_cpu_read(rcu_data_p->core_needs_qs) &&
-	    __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm))
+	    __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm) &&
+	    !t->rcu_read_unlock_special.b.need_qs &&
+	    time_after(jiffies, rsp->gp_start + HZ))
 		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
@@ -841,6 +861,47 @@ void exit_rcu(void)
 	__rcu_read_unlock();
 }
 
+/*
+ * Dump the blocked-tasks state, but limit the list dump to the
+ * specified number of elements.
+ */
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
+{
+	int cpu;
+	int i;
+	struct list_head *lhp;
+	bool onl;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp1;
+
+	raw_lockdep_assert_held_rcu_node(rnp);
+	pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+		__func__, rnp->grplo, rnp->grphi, rnp->level,
+		(long)rnp->gp_seq, (long)rnp->completedqs);
+	for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+		pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
+			__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
+	pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
+		__func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks);
+	pr_info("%s: ->blkd_tasks", __func__);
+	i = 0;
+	list_for_each(lhp, &rnp->blkd_tasks) {
+		pr_cont(" %p", lhp);
+		if (++i >= 10)
+			break;
+	}
+	pr_cont("\n");
+	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+		pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n",
+			cpu, ".o"[onl],
+			(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+			(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+	}
+}
+
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
 static struct rcu_state *const rcu_state_p = &rcu_sched_state;
@@ -911,7 +972,8 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * so there is no need to check for blocked tasks.  So check only for
  * bogus qsmask values.
  */
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	WARN_ON_ONCE(rnp->qsmask);
 }
@@ -949,6 +1011,15 @@ void exit_rcu(void)
 {
 }
 
+/*
+ * Dump the guaranteed-empty blocked-tasks state.  Trust but verify.
+ */
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
+{
+	WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks));
+}
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST
@@ -1433,7 +1504,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
 		 * completed since we last checked and there are
 		 * callbacks not yet ready to invoke.
 		 */
-		if ((rdp->completed != rnp->completed ||
+		if ((rcu_seq_completed_gp(rdp->gp_seq,
+					  rcu_seq_current(&rnp->gp_seq)) ||
 		     unlikely(READ_ONCE(rdp->gpwrap))) &&
 		    rcu_segcblist_pend_cbs(&rdp->cblist))
 			note_gp_changes(rsp, rdp);
@@ -1720,16 +1792,16 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 	 */
 	touch_nmi_watchdog();
 
-	if (rsp->gpnum == rdp->gpnum) {
+	ticks_value = rcu_seq_ctr(rsp->gp_seq - rdp->gp_seq);
+	if (ticks_value) {
+		ticks_title = "GPs behind";
+	} else {
 		ticks_title = "ticks this GP";
 		ticks_value = rdp->ticks_this_gp;
-	} else {
-		ticks_title = "GPs behind";
-		ticks_value = rsp->gpnum - rdp->gpnum;
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
-	delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum;
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%ld softirq=%u/%u fqs=%ld %s\n",
+	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -1817,7 +1889,7 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
 
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
 {
-	return &rnp->nocb_gp_wq[rnp->completed & 0x1];
+	return &rnp->nocb_gp_wq[rcu_seq_ctr(rnp->gp_seq) & 0x1];
 }
 
 static void rcu_init_one_nocb(struct rcu_node *rnp)
@@ -1854,8 +1926,8 @@ static void __wake_nocb_leader(struct rcu_data *rdp, bool force,
 		WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
 		del_timer(&rdp->nocb_timer);
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
-		smp_mb(); /* ->nocb_leader_sleep before swake_up(). */
-		swake_up(&rdp_leader->nocb_wq);
+		smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */
+		swake_up_one(&rdp_leader->nocb_wq);
 	} else {
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 	}
@@ -2069,12 +2141,17 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	bool needwake;
 	struct rcu_node *rnp = rdp->mynode;
 
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	c = rcu_cbs_completed(rdp->rsp, rnp);
-	needwake = rcu_start_this_gp(rnp, rdp, c);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	if (needwake)
-		rcu_gp_kthread_wake(rdp->rsp);
+	local_irq_save(flags);
+	c = rcu_seq_snap(&rdp->rsp->gp_seq);
+	if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+		local_irq_restore(flags);
+	} else {
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+		needwake = rcu_start_this_gp(rnp, rdp, c);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		if (needwake)
+			rcu_gp_kthread_wake(rdp->rsp);
+	}
 
 	/*
 	 * Wait for the grace period.  Do so interruptibly to avoid messing
@@ -2082,9 +2159,9 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	 */
 	trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
 	for (;;) {
-		swait_event_interruptible(
-			rnp->nocb_gp_wq[c & 0x1],
-			(d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
+		swait_event_interruptible_exclusive(
+			rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1],
+			(d = rcu_seq_done(&rnp->gp_seq, c)));
 		if (likely(d))
 			break;
 		WARN_ON(signal_pending(current));
@@ -2111,7 +2188,7 @@ wait_again:
 	/* Wait for callbacks to appear. */
 	if (!rcu_nocb_poll) {
 		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep"));
-		swait_event_interruptible(my_rdp->nocb_wq,
+		swait_event_interruptible_exclusive(my_rdp->nocb_wq,
 				!READ_ONCE(my_rdp->nocb_leader_sleep));
 		raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags);
 		my_rdp->nocb_leader_sleep = true;
@@ -2176,7 +2253,7 @@ wait_again:
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 		if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
 			/* List was empty, so wake up the follower.  */
-			swake_up(&rdp->nocb_wq);
+			swake_up_one(&rdp->nocb_wq);
 		}
 	}
 
@@ -2193,7 +2270,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
 {
 	for (;;) {
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep"));
-		swait_event_interruptible(rdp->nocb_wq,
+		swait_event_interruptible_exclusive(rdp->nocb_wq,
 					 READ_ONCE(rdp->nocb_follower_head));
 		if (smp_load_acquire(&rdp->nocb_follower_head)) {
 			/* ^^^ Ensure CB invocation follows _head test. */
@@ -2569,23 +2646,6 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
 /*
- * An adaptive-ticks CPU can potentially execute in kernel mode for an
- * arbitrarily long period of time with the scheduling-clock tick turned
- * off.  RCU will be paying attention to this CPU because it is in the
- * kernel, but the CPU cannot be guaranteed to be executing the RCU state
- * machine because the scheduling-clock tick has been disabled.  Therefore,
- * if an adaptive-ticks CPU is failing to respond to the current grace
- * period and has not be idle from an RCU perspective, kick it.
- */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
-{
-#ifdef CONFIG_NO_HZ_FULL
-	if (tick_nohz_full_cpu(cpu))
-		smp_send_reschedule(cpu);
-#endif /* #ifdef CONFIG_NO_HZ_FULL */
-}
-
-/*
  * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
  * grace-period kthread will do force_quiescent_state() processing?
  * The idea is to avoid waking up RCU core processing on such a
@@ -2610,8 +2670,6 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
  */
 static void rcu_bind_gp_kthread(void)
 {
-	int __maybe_unused cpu;
-
 	if (!tick_nohz_full_enabled())
 		return;
 	housekeeping_affine(current, HK_FLAG_RCU);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4c230a60ece4..39cb23d22109 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -507,14 +507,15 @@ early_initcall(check_cpu_stall_init);
 #ifdef CONFIG_TASKS_RCU
 
 /*
- * Simple variant of RCU whose quiescent states are voluntary context switch,
- * user-space execution, and idle.  As such, grace periods can take one good
- * long time.  There are no read-side primitives similar to rcu_read_lock()
- * and rcu_read_unlock() because this implementation is intended to get
- * the system into a safe state for some of the manipulations involved in
- * tracing and the like.  Finally, this implementation does not support
- * high call_rcu_tasks() rates from multiple CPUs.  If this is required,
- * per-CPU callback lists will be needed.
+ * Simple variant of RCU whose quiescent states are voluntary context
+ * switch, cond_resched_rcu_qs(), user-space execution, and idle.
+ * As such, grace periods can take one good long time.  There are no
+ * read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
+ * because this implementation is intended to get the system into a safe
+ * state for some of the manipulations involved in tracing and the like.
+ * Finally, this implementation does not support high call_rcu_tasks()
+ * rates from multiple CPUs.  If this is required, per-CPU callback lists
+ * will be needed.
  */
 
 /* Global list of callbacks and associated lock. */
@@ -542,11 +543,11 @@ static struct task_struct *rcu_tasks_kthread_ptr;
  * period elapses, in other words after all currently executing RCU
  * read-side critical sections have completed. call_rcu_tasks() assumes
  * that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), entry into idle, or transition to usermode
- * execution.  As such, there are no read-side primitives analogous to
- * rcu_read_lock() and rcu_read_unlock() because this primitive is intended
- * to determine that all tasks have passed through a safe state, not so
- * much for data-strcuture synchronization.
+ * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * or transition to usermode execution.  As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-strcuture synchronization.
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
@@ -667,6 +668,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	struct rcu_head *list;
 	struct rcu_head *next;
 	LIST_HEAD(rcu_tasks_holdouts);
+	int fract;
 
 	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
 	housekeeping_affine(current, HK_FLAG_RCU);
@@ -748,13 +750,25 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		 * holdouts.  When the list is empty, we are done.
 		 */
 		lastreport = jiffies;
-		while (!list_empty(&rcu_tasks_holdouts)) {
+
+		/* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
+		fract = 10;
+
+		for (;;) {
 			bool firstreport;
 			bool needreport;
 			int rtst;
 			struct task_struct *t1;
 
-			schedule_timeout_interruptible(HZ);
+			if (list_empty(&rcu_tasks_holdouts))
+				break;
+
+			/* Slowly back off waiting for holdouts */
+			schedule_timeout_interruptible(HZ/fract);
+
+			if (fract > 1)
+				fract--;
+
 			rtst = READ_ONCE(rcu_task_stall_timeout);
 			needreport = rtst > 0 &&
 				     time_after(jiffies, lastreport + rtst);
@@ -800,6 +814,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 			list = next;
 			cond_resched();
 		}
+		/* Paranoid sleep to keep this from entering a tight loop */
 		schedule_timeout_uninterruptible(HZ/10);
 	}
 }
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index d9a02b318108..7fe183404c38 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -20,7 +20,7 @@ obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle.o fair.o rt.o deadline.o
 obj-y += wait.o wait_bit.o swait.o completion.o
 
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 10c83e73837a..e3e3b979f9bd 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -53,6 +53,7 @@
  *
  */
 #include "sched.h"
+#include <linux/sched_clock.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -66,12 +67,7 @@ unsigned long long __weak sched_clock(void)
 }
 EXPORT_SYMBOL_GPL(sched_clock);
 
-__read_mostly int sched_clock_running;
-
-void sched_clock_init(void)
-{
-	sched_clock_running = 1;
-}
+static DEFINE_STATIC_KEY_FALSE(sched_clock_running);
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 /*
@@ -195,17 +191,40 @@ void clear_sched_clock_stable(void)
 
 	smp_mb(); /* matches sched_clock_init_late() */
 
-	if (sched_clock_running == 2)
+	if (static_key_count(&sched_clock_running.key) == 2)
 		__clear_sched_clock_stable();
 }
 
+static void __sched_clock_gtod_offset(void)
+{
+	struct sched_clock_data *scd = this_scd();
+
+	__scd_stamp(scd);
+	__gtod_offset = (scd->tick_raw + __sched_clock_offset) - scd->tick_gtod;
+}
+
+void __init sched_clock_init(void)
+{
+	/*
+	 * Set __gtod_offset such that once we mark sched_clock_running,
+	 * sched_clock_tick() continues where sched_clock() left off.
+	 *
+	 * Even if TSC is buggered, we're still UP at this point so it
+	 * can't really be out of sync.
+	 */
+	local_irq_disable();
+	__sched_clock_gtod_offset();
+	local_irq_enable();
+
+	static_branch_inc(&sched_clock_running);
+}
 /*
  * We run this as late_initcall() such that it runs after all built-in drivers,
  * notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
  */
 static int __init sched_clock_init_late(void)
 {
-	sched_clock_running = 2;
+	static_branch_inc(&sched_clock_running);
 	/*
 	 * Ensure that it is impossible to not do a static_key update.
 	 *
@@ -350,8 +369,8 @@ u64 sched_clock_cpu(int cpu)
 	if (sched_clock_stable())
 		return sched_clock() + __sched_clock_offset;
 
-	if (unlikely(!sched_clock_running))
-		return 0ull;
+	if (!static_branch_unlikely(&sched_clock_running))
+		return sched_clock();
 
 	preempt_disable_notrace();
 	scd = cpu_sdc(cpu);
@@ -373,7 +392,7 @@ void sched_clock_tick(void)
 	if (sched_clock_stable())
 		return;
 
-	if (unlikely(!sched_clock_running))
+	if (!static_branch_unlikely(&sched_clock_running))
 		return;
 
 	lockdep_assert_irqs_disabled();
@@ -385,8 +404,6 @@ void sched_clock_tick(void)
 
 void sched_clock_tick_stable(void)
 {
-	u64 gtod, clock;
-
 	if (!sched_clock_stable())
 		return;
 
@@ -398,9 +415,7 @@ void sched_clock_tick_stable(void)
 	 * TSC to be unstable, any computation will be computing crap.
 	 */
 	local_irq_disable();
-	gtod = ktime_get_ns();
-	clock = sched_clock();
-	__gtod_offset = (clock + __sched_clock_offset) - gtod;
+	__sched_clock_gtod_offset();
 	local_irq_enable();
 }
 
@@ -434,9 +449,17 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
+void __init sched_clock_init(void)
+{
+	static_branch_inc(&sched_clock_running);
+	local_irq_disable();
+	generic_sched_clock_init();
+	local_irq_enable();
+}
+
 u64 sched_clock_cpu(int cpu)
 {
-	if (unlikely(!sched_clock_running))
+	if (!static_branch_unlikely(&sched_clock_running))
 		return 0;
 
 	return sched_clock();
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index e426b0cb9ac6..a1ad5b7d5521 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -22,8 +22,8 @@
  *
  * See also complete_all(), wait_for_completion() and related routines.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void complete(struct completion *x)
 {
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete);
  *
  * This will wake up all threads waiting on this particular completion event.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  *
  * Since complete_all() sets the completion of @x permanently to done
  * to allow multiple waiters to finish, a call to reinit_completion()
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe365c9a08e9..454adf9f8180 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -17,6 +17,8 @@
 #include "../workqueue_internal.h"
 #include "../smpboot.h"
 
+#include "pelt.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
@@ -45,14 +47,6 @@ const_debug unsigned int sysctl_sched_features =
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
 /*
- * period over which we average the RT time consumption, measured
- * in ms.
- *
- * default: 1s
- */
-const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
-
-/*
  * period over which we measure -rt task CPU usage in us.
  * default: 1s
  */
@@ -183,9 +177,9 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->clock_task += delta;
 
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef HAVE_SCHED_AVG_IRQ
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
-		sched_rt_avg_update(rq, irq_delta + steal);
+		update_irq_load_avg(rq, irq_delta + steal);
 #endif
 }
 
@@ -412,8 +406,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * its already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
-	 * This cmpxchg() implies a full barrier, which pairs with the write
-	 * barrier implied by the wakeup in wake_up_q().
+	 * This cmpxchg() executes a full barrier, which pairs with the full
+	 * barrier executed by the wakeup in wake_up_q().
 	 */
 	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
 		return;
@@ -441,8 +435,8 @@ void wake_up_q(struct wake_q_head *head)
 		task->wake_q.next = NULL;
 
 		/*
-		 * wake_up_process() implies a wmb() to pair with the queueing
-		 * in wake_q_add() so as not to miss wakeups.
+		 * wake_up_process() executes a full barrier, which pairs with
+		 * the queueing in wake_q_add() so as not to miss wakeups.
 		 */
 		wake_up_process(task);
 		put_task_struct(task);
@@ -649,23 +643,6 @@ bool sched_can_stop_tick(struct rq *rq)
 	return true;
 }
 #endif /* CONFIG_NO_HZ_FULL */
-
-void sched_avg_update(struct rq *rq)
-{
-	s64 period = sched_avg_period();
-
-	while ((s64)(rq_clock(rq) - rq->age_stamp) > period) {
-		/*
-		 * Inline assembly required to prevent the compiler
-		 * optimising this loop into a divmod call.
-		 * See __iter_div_u64_rem() for another example of this.
-		 */
-		asm("" : "+rm" (rq->age_stamp));
-		rq->age_stamp += period;
-		rq->rt_avg /= 2;
-	}
-}
-
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
@@ -1199,6 +1176,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
 	if (task_on_rq_queued(p)) {
@@ -1280,16 +1258,17 @@ unlock:
 /*
  * Cross migrate two tasks
  */
-int migrate_swap(struct task_struct *cur, struct task_struct *p)
+int migrate_swap(struct task_struct *cur, struct task_struct *p,
+		int target_cpu, int curr_cpu)
 {
 	struct migration_swap_arg arg;
 	int ret = -EINVAL;
 
 	arg = (struct migration_swap_arg){
 		.src_task = cur,
-		.src_cpu = task_cpu(cur),
+		.src_cpu = curr_cpu,
 		.dst_task = p,
-		.dst_cpu = task_cpu(p),
+		.dst_cpu = target_cpu,
 	};
 
 	if (arg.src_cpu == arg.dst_cpu)
@@ -1314,6 +1293,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
 out:
 	return ret;
 }
+#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * wait_task_inactive - wait for a thread to unschedule.
@@ -1879,8 +1859,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *     rq(c1)->lock (if not at the same time, then in that order).
  *  C) LOCK of the rq(c1)->lock scheduling in task
  *
- * Transitivity guarantees that B happens after A and C after B.
- * Note: we only require RCpc transitivity.
+ * Release/acquire chaining guarantees that B happens after A and C after B.
  * Note: the CPU doing B need not be c0 or c1
  *
  * Example:
@@ -1942,16 +1921,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *   UNLOCK rq(0)->lock
  *
  *
- * However; for wakeups there is a second guarantee we must provide, namely we
- * must observe the state that lead to our wakeup. That is, not only must our
- * task observe its own prior state, it must also observe the stores prior to
- * its wakeup.
- *
- * This means that any means of doing remote wakeups must order the CPU doing
- * the wakeup against the CPU the task is going to end up running on. This,
- * however, is already required for the regular Program-Order guarantee above,
- * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
- *
+ * However, for wakeups there is a second guarantee we must provide, namely we
+ * must ensure that CONDITION=1 done by the caller can not be reordered with
+ * accesses to the task state; see try_to_wake_up() and set_current_state().
  */
 
 /**
@@ -1967,6 +1939,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * Atomic against schedule() which would dequeue a task, also see
  * set_current_state().
  *
+ * This function executes a full memory barrier before accessing the task
+ * state; see set_current_state().
+ *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
  */
@@ -1998,21 +1973,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
 	 * in smp_cond_load_acquire() below.
 	 *
-	 * sched_ttwu_pending()                 try_to_wake_up()
-	 *   [S] p->on_rq = 1;                  [L] P->state
-	 *       UNLOCK rq->lock  -----.
-	 *                              \
-	 *				 +---   RMB
-	 * schedule()                   /
-	 *       LOCK rq->lock    -----'
-	 *       UNLOCK rq->lock
+	 * sched_ttwu_pending()			try_to_wake_up()
+	 *   STORE p->on_rq = 1			  LOAD p->state
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   UNLOCK rq->lock
 	 *
 	 * [task p]
-	 *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+	 *   STORE p->state = UNINTERRUPTIBLE	  LOAD p->on_rq
 	 *
-	 * Pairs with the UNLOCK+LOCK on rq->lock from the
-	 * last wakeup of our task and the schedule that got our task
-	 * current.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
@@ -2026,15 +2000,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * One must be running (->on_cpu == 1) in order to remove oneself
 	 * from the runqueue.
 	 *
-	 *  [S] ->on_cpu = 1;	[L] ->on_rq
-	 *      UNLOCK rq->lock
-	 *			RMB
-	 *      LOCK   rq->lock
-	 *  [S] ->on_rq = 0;    [L] ->on_cpu
+	 * __schedule() (switch to task 'p')	try_to_wake_up()
+	 *   STORE p->on_cpu = 1		  LOAD p->on_rq
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (put 'p' to sleep)
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   STORE p->on_rq = 0			  LOAD p->on_cpu
 	 *
-	 * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
-	 * from the consecutive calls to schedule(); the first switching to our
-	 * task, the second putting it to sleep.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 
@@ -2140,8 +2116,7 @@ out:
  *
  * Return: 1 if the process was woken up, 0 if it was already running.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * This function executes a full memory barrier before accessing the task state.
  */
 int wake_up_process(struct task_struct *p)
 {
@@ -2317,7 +2292,6 @@ static inline void init_schedstats(void) {}
 int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
-	int cpu = get_cpu();
 
 	__sched_fork(clone_flags, p);
 	/*
@@ -2353,14 +2327,12 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->sched_reset_on_fork = 0;
 	}
 
-	if (dl_prio(p->prio)) {
-		put_cpu();
+	if (dl_prio(p->prio))
 		return -EAGAIN;
-	} else if (rt_prio(p->prio)) {
+	else if (rt_prio(p->prio))
 		p->sched_class = &rt_sched_class;
-	} else {
+	else
 		p->sched_class = &fair_sched_class;
-	}
 
 	init_entity_runnable_average(&p->se);
 
@@ -2376,7 +2348,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
 	 */
-	__set_task_cpu(p, cpu);
+	__set_task_cpu(p, smp_processor_id());
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
@@ -2393,8 +2365,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 	RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
-
-	put_cpu();
 	return 0;
 }
 
@@ -5714,13 +5684,6 @@ void set_rq_offline(struct rq *rq)
 	}
 }
 
-static void set_cpu_rq_start_time(unsigned int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-
-	rq->age_stamp = sched_clock_cpu(cpu);
-}
-
 /*
  * used to mark begin/end of suspend/resume:
  */
@@ -5774,6 +5737,18 @@ int sched_cpu_activate(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
+#ifdef CONFIG_SCHED_SMT
+	/*
+	 * The sched_smt_present static key needs to be evaluated on every
+	 * hotplug event because at boot time SMT might be disabled when
+	 * the number of booted CPUs is limited.
+	 *
+	 * If then later a sibling gets hotplugged, then the key would stay
+	 * off and SMT scheduling would never be functional.
+	 */
+	if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
+		static_branch_enable_cpuslocked(&sched_smt_present);
+#endif
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {
@@ -5838,7 +5813,6 @@ static void sched_rq_cpu_starting(unsigned int cpu)
 
 int sched_cpu_starting(unsigned int cpu)
 {
-	set_cpu_rq_start_time(cpu);
 	sched_rq_cpu_starting(cpu);
 	sched_tick_start(cpu);
 	return 0;
@@ -5871,22 +5845,6 @@ int sched_cpu_dying(unsigned int cpu)
 }
 #endif
 
-#ifdef CONFIG_SCHED_SMT
-DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-
-static void sched_init_smt(void)
-{
-	/*
-	 * We've enumerated all CPUs and will assume that if any CPU
-	 * has SMT siblings, CPU0 will too.
-	 */
-	if (cpumask_weight(cpu_smt_mask(0)) > 1)
-		static_branch_enable(&sched_smt_present);
-}
-#else
-static inline void sched_init_smt(void) { }
-#endif
-
 void __init sched_init_smp(void)
 {
 	sched_init_numa();
@@ -5908,8 +5866,6 @@ void __init sched_init_smp(void)
 	init_sched_rt_class();
 	init_sched_dl_class();
 
-	sched_init_smt();
-
 	sched_smp_initialized = true;
 }
 
@@ -5954,7 +5910,6 @@ void __init sched_init(void)
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
-	sched_clock_init();
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6106,7 +6061,6 @@ void __init sched_init(void)
 
 #ifdef CONFIG_SMP
 	idle_thread_set_boot_cpu();
-	set_cpu_rq_start_time(smp_processor_id());
 #endif
 	init_sched_fair_class();
 
@@ -6785,6 +6739,16 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
 	seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
 	seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
 
+	if (schedstat_enabled() && tg != &root_task_group) {
+		u64 ws = 0;
+		int i;
+
+		for_each_possible_cpu(i)
+			ws += schedstat_val(tg->se[i]->statistics.wait_sum);
+
+		seq_printf(sf, "wait_sum %llu\n", ws);
+	}
+
 	return 0;
 }
 #endif /* CONFIG_CFS_BANDWIDTH */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index c907fde01eaa..3fffad3bc8a8 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -53,9 +53,7 @@ struct sugov_cpu {
 	unsigned int		iowait_boost_max;
 	u64			last_update;
 
-	/* The fields below are only needed when sharing a policy: */
-	unsigned long		util_cfs;
-	unsigned long		util_dl;
+	unsigned long		bw_dl;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -179,33 +177,90 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
-static void sugov_get_util(struct sugov_cpu *sg_cpu)
+/*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ *   cpu_util_{cfs,rt,dl,irq}()
+ *   cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the irq utilization.
+ *
+ * The DL bandwidth number otoh is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long util, irq, max;
 
-	sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
-	sg_cpu->util_cfs = cpu_util_cfs(rq);
-	sg_cpu->util_dl  = cpu_util_dl(rq);
-}
-
-static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
-{
-	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+	sg_cpu->bw_dl = cpu_bw_dl(rq);
 
 	if (rt_rq_is_runnable(&rq->rt))
-		return sg_cpu->max;
+		return max;
+
+	/*
+	 * Early check to see if IRQ/steal time saturates the CPU, can be
+	 * because of inaccuracies in how we track these -- see
+	 * update_irq_load_avg().
+	 */
+	irq = cpu_util_irq(rq);
+	if (unlikely(irq >= max))
+		return max;
+
+	/*
+	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
+	 * CFS tasks and we use the same metric to track the effective
+	 * utilization (PELT windows are synchronized) we can directly add them
+	 * to obtain the CPU's actual utilization.
+	 */
+	util = cpu_util_cfs(rq);
+	util += cpu_util_rt(rq);
+
+	/*
+	 * We do not make cpu_util_dl() a permanent part of this sum because we
+	 * want to use cpu_bw_dl() later on, but we need to check if the
+	 * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
+	 * f_max when there is no idle time.
+	 *
+	 * NOTE: numerical errors or stop class might cause us to not quite hit
+	 * saturation when we should -- something for later.
+	 */
+	if ((util + cpu_util_dl(rq)) >= max)
+		return max;
+
+	/*
+	 * There is still idle time; further improve the number by using the
+	 * irq metric. Because IRQ/steal time is hidden from the task clock we
+	 * need to scale the task numbers:
+	 *
+	 *              1 - irq
+	 *   U' = irq + ------- * U
+	 *                max
+	 */
+	util = scale_irq_capacity(util, irq, max);
+	util += irq;
 
 	/*
-	 * Utilization required by DEADLINE must always be granted while, for
-	 * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
-	 * gracefully reduce the frequency when no tasks show up for longer
+	 * Bandwidth required by DEADLINE must always be granted while, for
+	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
+	 * to gracefully reduce the frequency when no tasks show up for longer
 	 * periods of time.
 	 *
-	 * Ideally we would like to set util_dl as min/guaranteed freq and
-	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
-	 * ready for such an interface. So, we only do the latter for now.
+	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
+	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
+	 * an interface. So, we only do the latter for now.
 	 */
-	return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
+	return min(max, util + sg_cpu->bw_dl);
 }
 
 /**
@@ -360,7 +415,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
  */
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
 {
-	if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl)
+	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
 		sg_policy->need_freq_update = true;
 }
 
@@ -383,9 +438,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 
 	busy = sugov_cpu_is_busy(sg_cpu);
 
-	sugov_get_util(sg_cpu);
+	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
-	util = sugov_aggregate_util(sg_cpu);
 	sugov_iowait_apply(sg_cpu, time, &util, &max);
 	next_f = get_next_freq(sg_policy, util, max);
 	/*
@@ -424,9 +478,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
 		unsigned long j_util, j_max;
 
-		sugov_get_util(j_sg_cpu);
+		j_util = sugov_get_util(j_sg_cpu);
 		j_max = j_sg_cpu->max;
-		j_util = sugov_aggregate_util(j_sg_cpu);
 		sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
 
 		if (j_util * max > j_max * util) {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b5fbdde6afa9..997ea7b839fa 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,7 @@
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
 #include "sched.h"
+#include "pelt.h"
 
 struct dl_bandwidth def_dl_bandwidth;
 
@@ -1179,8 +1180,6 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (dl_entity_is_special(dl_se))
 		return;
 
@@ -1761,6 +1760,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	deadline_queue_push_tasks(rq);
 
+	if (rq->curr->sched_class != &dl_sched_class)
+		update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
 	return p;
 }
 
@@ -1768,6 +1770,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
 	update_curr_dl(rq);
 
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
 	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
 }
@@ -1784,6 +1787,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
 {
 	update_curr_dl(rq);
 
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
 	/*
 	 * Even when we have runtime, update_curr_dl() might have resulted in us
 	 * not being the leftmost task anymore. In that case NEED_RESCHED will
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e593b4118578..60caf1fb94e0 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -111,20 +111,19 @@ static int sched_feat_set(char *cmp)
 		cmp += 3;
 	}
 
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (strcmp(cmp, sched_feat_names[i]) == 0) {
-			if (neg) {
-				sysctl_sched_features &= ~(1UL << i);
-				sched_feat_disable(i);
-			} else {
-				sysctl_sched_features |= (1UL << i);
-				sched_feat_enable(i);
-			}
-			break;
-		}
+	i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp);
+	if (i < 0)
+		return i;
+
+	if (neg) {
+		sysctl_sched_features &= ~(1UL << i);
+		sched_feat_disable(i);
+	} else {
+		sysctl_sched_features |= (1UL << i);
+		sched_feat_enable(i);
 	}
 
-	return i;
+	return 0;
 }
 
 static ssize_t
@@ -133,7 +132,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 {
 	char buf[64];
 	char *cmp;
-	int i;
+	int ret;
 	struct inode *inode;
 
 	if (cnt > 63)
@@ -148,10 +147,10 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 	/* Ensure the static_key remains in a consistent state */
 	inode = file_inode(filp);
 	inode_lock(inode);
-	i = sched_feat_set(cmp);
+	ret = sched_feat_set(cmp);
 	inode_unlock(inode);
-	if (i == __SCHED_FEAT_NR)
-		return -EINVAL;
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
@@ -623,8 +622,6 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 #undef PU
 }
 
-extern __read_mostly int sched_clock_running;
-
 static void print_cpu(struct seq_file *m, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -843,8 +840,8 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
 		unsigned long tpf, unsigned long gsf, unsigned long gpf)
 {
 	SEQ_printf(m, "numa_faults node=%d ", node);
-	SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
-	SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+	SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf);
+	SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf);
 }
 #endif
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2f0a0be4d344..b39fb596f6c1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -255,9 +255,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 	return cfs_rq->rq;
 }
 
-/* An entity is a task if it doesn't "own" a runqueue */
-#define entity_is_task(se)	(!se->my_q)
-
 static inline struct task_struct *task_of(struct sched_entity *se)
 {
 	SCHED_WARN_ON(!entity_is_task(se));
@@ -419,7 +416,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 	return container_of(cfs_rq, struct rq, cfs);
 }
 
-#define entity_is_task(se)	1
 
 #define for_each_sched_entity(se) \
 		for (; se; se = NULL)
@@ -692,7 +688,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 #ifdef CONFIG_SMP
-
+#include "pelt.h"
 #include "sched-pelt.h"
 
 static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
@@ -735,11 +731,12 @@ static void attach_entity_cfs_rq(struct sched_entity *se);
  * To solve this problem, we also cap the util_avg of successive tasks to
  * only 1/2 of the left utilization budget:
  *
- *   util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
+ *   util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n
  *
- * where n denotes the nth task.
+ * where n denotes the nth task and cpu_scale the CPU capacity.
  *
- * For example, a simplest series from the beginning would be like:
+ * For example, for a CPU with 1024 of capacity, a simplest series from
+ * the beginning would be like:
  *
  *  task  util_avg: 512, 256, 128,  64,  32,   16,    8, ...
  * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
@@ -751,7 +748,8 @@ void post_init_entity_util_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	struct sched_avg *sa = &se->avg;
-	long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+	long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq)));
+	long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
 
 	if (cap > 0) {
 		if (cfs_rq->avg.util_avg != 0) {
@@ -1314,7 +1312,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 		 * of each group. Skip other nodes.
 		 */
 		if (sched_numa_topology_type == NUMA_BACKPLANE &&
-					dist > maxdist)
+					dist >= maxdist)
 			continue;
 
 		/* Add up the faults from nearby nodes. */
@@ -1452,15 +1450,12 @@ static unsigned long capacity_of(int cpu);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
-	unsigned long nr_running;
 	unsigned long load;
 
 	/* Total compute capacity of CPUs on a node */
 	unsigned long compute_capacity;
 
-	/* Approximate capacity in terms of runnable tasks on a node */
-	unsigned long task_capacity;
-	int has_free_capacity;
+	unsigned int nr_running;
 };
 
 /*
@@ -1487,8 +1482,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	 * the @ns structure is NULL'ed and task_numa_compare() will
 	 * not find this node attractive.
 	 *
-	 * We'll either bail at !has_free_capacity, or we'll detect a huge
-	 * imbalance and bail there.
+	 * We'll detect a huge imbalance and bail there.
 	 */
 	if (!cpus)
 		return;
@@ -1497,9 +1491,8 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
 	capacity = cpus / smt; /* cores */
 
-	ns->task_capacity = min_t(unsigned, capacity,
+	capacity = min_t(unsigned, capacity,
 		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
-	ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
 }
 
 struct task_numa_env {
@@ -1548,28 +1541,12 @@ static bool load_too_imbalanced(long src_load, long dst_load,
 	src_capacity = env->src_stats.compute_capacity;
 	dst_capacity = env->dst_stats.compute_capacity;
 
-	/* We care about the slope of the imbalance, not the direction. */
-	if (dst_load < src_load)
-		swap(dst_load, src_load);
+	imb = abs(dst_load * src_capacity - src_load * dst_capacity);
 
-	/* Is the difference below the threshold? */
-	imb = dst_load * src_capacity * 100 -
-	      src_load * dst_capacity * env->imbalance_pct;
-	if (imb <= 0)
-		return false;
-
-	/*
-	 * The imbalance is above the allowed threshold.
-	 * Compare it with the old imbalance.
-	 */
 	orig_src_load = env->src_stats.load;
 	orig_dst_load = env->dst_stats.load;
 
-	if (orig_dst_load < orig_src_load)
-		swap(orig_dst_load, orig_src_load);
-
-	old_imb = orig_dst_load * src_capacity * 100 -
-		  orig_src_load * dst_capacity * env->imbalance_pct;
+	old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity);
 
 	/* Would this change make things worse? */
 	return (imb > old_imb);
@@ -1582,9 +1559,8 @@ static bool load_too_imbalanced(long src_load, long dst_load,
  * be exchanged with the source task
  */
 static void task_numa_compare(struct task_numa_env *env,
-			      long taskimp, long groupimp)
+			      long taskimp, long groupimp, bool maymove)
 {
-	struct rq *src_rq = cpu_rq(env->src_cpu);
 	struct rq *dst_rq = cpu_rq(env->dst_cpu);
 	struct task_struct *cur;
 	long src_load, dst_load;
@@ -1605,97 +1581,73 @@ static void task_numa_compare(struct task_numa_env *env,
 	if (cur == env->p)
 		goto unlock;
 
+	if (!cur) {
+		if (maymove || imp > env->best_imp)
+			goto assign;
+		else
+			goto unlock;
+	}
+
 	/*
 	 * "imp" is the fault differential for the source task between the
 	 * source and destination node. Calculate the total differential for
 	 * the source task and potential destination task. The more negative
-	 * the value is, the more rmeote accesses that would be expected to
+	 * the value is, the more remote accesses that would be expected to
 	 * be incurred if the tasks were swapped.
 	 */
-	if (cur) {
-		/* Skip this swap candidate if cannot move to the source CPU: */
-		if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
-			goto unlock;
+	/* Skip this swap candidate if cannot move to the source cpu */
+	if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+		goto unlock;
 
+	/*
+	 * If dst and source tasks are in the same NUMA group, or not
+	 * in any group then look only at task weights.
+	 */
+	if (cur->numa_group == env->p->numa_group) {
+		imp = taskimp + task_weight(cur, env->src_nid, dist) -
+		      task_weight(cur, env->dst_nid, dist);
 		/*
-		 * If dst and source tasks are in the same NUMA group, or not
-		 * in any group then look only at task weights.
+		 * Add some hysteresis to prevent swapping the
+		 * tasks within a group over tiny differences.
 		 */
-		if (cur->numa_group == env->p->numa_group) {
-			imp = taskimp + task_weight(cur, env->src_nid, dist) -
-			      task_weight(cur, env->dst_nid, dist);
-			/*
-			 * Add some hysteresis to prevent swapping the
-			 * tasks within a group over tiny differences.
-			 */
-			if (cur->numa_group)
-				imp -= imp/16;
-		} else {
-			/*
-			 * Compare the group weights. If a task is all by
-			 * itself (not part of a group), use the task weight
-			 * instead.
-			 */
-			if (cur->numa_group)
-				imp += group_weight(cur, env->src_nid, dist) -
-				       group_weight(cur, env->dst_nid, dist);
-			else
-				imp += task_weight(cur, env->src_nid, dist) -
-				       task_weight(cur, env->dst_nid, dist);
-		}
+		if (cur->numa_group)
+			imp -= imp / 16;
+	} else {
+		/*
+		 * Compare the group weights. If a task is all by itself
+		 * (not part of a group), use the task weight instead.
+		 */
+		if (cur->numa_group && env->p->numa_group)
+			imp += group_weight(cur, env->src_nid, dist) -
+			       group_weight(cur, env->dst_nid, dist);
+		else
+			imp += task_weight(cur, env->src_nid, dist) -
+			       task_weight(cur, env->dst_nid, dist);
 	}
 
-	if (imp <= env->best_imp && moveimp <= env->best_imp)
+	if (imp <= env->best_imp)
 		goto unlock;
 
-	if (!cur) {
-		/* Is there capacity at our destination? */
-		if (env->src_stats.nr_running <= env->src_stats.task_capacity &&
-		    !env->dst_stats.has_free_capacity)
-			goto unlock;
-
-		goto balance;
-	}
-
-	/* Balance doesn't matter much if we're running a task per CPU: */
-	if (imp > env->best_imp && src_rq->nr_running == 1 &&
-			dst_rq->nr_running == 1)
+	if (maymove && moveimp > imp && moveimp > env->best_imp) {
+		imp = moveimp - 1;
+		cur = NULL;
 		goto assign;
+	}
 
 	/*
 	 * In the overloaded case, try and keep the load balanced.
 	 */
-balance:
-	load = task_h_load(env->p);
+	load = task_h_load(env->p) - task_h_load(cur);
+	if (!load)
+		goto assign;
+
 	dst_load = env->dst_stats.load + load;
 	src_load = env->src_stats.load - load;
 
-	if (moveimp > imp && moveimp > env->best_imp) {
-		/*
-		 * If the improvement from just moving env->p direction is
-		 * better than swapping tasks around, check if a move is
-		 * possible. Store a slightly smaller score than moveimp,
-		 * so an actually idle CPU will win.
-		 */
-		if (!load_too_imbalanced(src_load, dst_load, env)) {
-			imp = moveimp - 1;
-			cur = NULL;
-			goto assign;
-		}
-	}
-
-	if (imp <= env->best_imp)
-		goto unlock;
-
-	if (cur) {
-		load = task_h_load(cur);
-		dst_load -= load;
-		src_load += load;
-	}
-
 	if (load_too_imbalanced(src_load, dst_load, env))
 		goto unlock;
 
+assign:
 	/*
 	 * One idle CPU per node is evaluated for a task numa move.
 	 * Call select_idle_sibling to maybe find a better one.
@@ -1711,7 +1663,6 @@ balance:
 		local_irq_enable();
 	}
 
-assign:
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
@@ -1720,43 +1671,30 @@ unlock:
 static void task_numa_find_cpu(struct task_numa_env *env,
 				long taskimp, long groupimp)
 {
+	long src_load, dst_load, load;
+	bool maymove = false;
 	int cpu;
 
+	load = task_h_load(env->p);
+	dst_load = env->dst_stats.load + load;
+	src_load = env->src_stats.load - load;
+
+	/*
+	 * If the improvement from just moving env->p direction is better
+	 * than swapping tasks around, check if a move is possible.
+	 */
+	maymove = !load_too_imbalanced(src_load, dst_load, env);
+
 	for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
 		/* Skip this CPU if the source task cannot migrate */
 		if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
 			continue;
 
 		env->dst_cpu = cpu;
-		task_numa_compare(env, taskimp, groupimp);
+		task_numa_compare(env, taskimp, groupimp, maymove);
 	}
 }
 
-/* Only move tasks to a NUMA node less busy than the current node. */
-static bool numa_has_capacity(struct task_numa_env *env)
-{
-	struct numa_stats *src = &env->src_stats;
-	struct numa_stats *dst = &env->dst_stats;
-
-	if (src->has_free_capacity && !dst->has_free_capacity)
-		return false;
-
-	/*
-	 * Only consider a task move if the source has a higher load
-	 * than the destination, corrected for CPU capacity on each node.
-	 *
-	 *      src->load                dst->load
-	 * --------------------- vs ---------------------
-	 * src->compute_capacity    dst->compute_capacity
-	 */
-	if (src->load * dst->compute_capacity * env->imbalance_pct >
-
-	    dst->load * src->compute_capacity * 100)
-		return true;
-
-	return false;
-}
-
 static int task_numa_migrate(struct task_struct *p)
 {
 	struct task_numa_env env = {
@@ -1797,7 +1735,7 @@ static int task_numa_migrate(struct task_struct *p)
 	 * elsewhere, so there is no point in (re)trying.
 	 */
 	if (unlikely(!sd)) {
-		p->numa_preferred_nid = task_node(p);
+		sched_setnuma(p, task_node(p));
 		return -EINVAL;
 	}
 
@@ -1811,8 +1749,7 @@ static int task_numa_migrate(struct task_struct *p)
 	update_numa_stats(&env.dst_stats, env.dst_nid);
 
 	/* Try to find a spot on the preferred nid. */
-	if (numa_has_capacity(&env))
-		task_numa_find_cpu(&env, taskimp, groupimp);
+	task_numa_find_cpu(&env, taskimp, groupimp);
 
 	/*
 	 * Look at other nodes in these cases:
@@ -1842,8 +1779,7 @@ static int task_numa_migrate(struct task_struct *p)
 			env.dist = dist;
 			env.dst_nid = nid;
 			update_numa_stats(&env.dst_stats, env.dst_nid);
-			if (numa_has_capacity(&env))
-				task_numa_find_cpu(&env, taskimp, groupimp);
+			task_numa_find_cpu(&env, taskimp, groupimp);
 		}
 	}
 
@@ -1856,15 +1792,13 @@ static int task_numa_migrate(struct task_struct *p)
 	 * trying for a better one later. Do not set the preferred node here.
 	 */
 	if (p->numa_group) {
-		struct numa_group *ng = p->numa_group;
-
 		if (env.best_cpu == -1)
 			nid = env.src_nid;
 		else
-			nid = env.dst_nid;
+			nid = cpu_to_node(env.best_cpu);
 
-		if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
-			sched_setnuma(p, env.dst_nid);
+		if (nid != p->numa_preferred_nid)
+			sched_setnuma(p, nid);
 	}
 
 	/* No better CPU than the current one was found. */
@@ -1884,7 +1818,8 @@ static int task_numa_migrate(struct task_struct *p)
 		return ret;
 	}
 
-	ret = migrate_swap(p, env.best_task);
+	ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+
 	if (ret != 0)
 		trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
 	put_task_struct(env.best_task);
@@ -2144,8 +2079,8 @@ static int preferred_group_nid(struct task_struct *p, int nid)
 
 static void task_numa_placement(struct task_struct *p)
 {
-	int seq, nid, max_nid = -1, max_group_nid = -1;
-	unsigned long max_faults = 0, max_group_faults = 0;
+	int seq, nid, max_nid = -1;
+	unsigned long max_faults = 0;
 	unsigned long fault_types[2] = { 0, 0 };
 	unsigned long total_faults;
 	u64 runtime, period;
@@ -2224,33 +2159,30 @@ static void task_numa_placement(struct task_struct *p)
 			}
 		}
 
-		if (faults > max_faults) {
-			max_faults = faults;
+		if (!p->numa_group) {
+			if (faults > max_faults) {
+				max_faults = faults;
+				max_nid = nid;
+			}
+		} else if (group_faults > max_faults) {
+			max_faults = group_faults;
 			max_nid = nid;
 		}
-
-		if (group_faults > max_group_faults) {
-			max_group_faults = group_faults;
-			max_group_nid = nid;
-		}
 	}
 
-	update_task_scan_period(p, fault_types[0], fault_types[1]);
-
 	if (p->numa_group) {
 		numa_group_count_active_nodes(p->numa_group);
 		spin_unlock_irq(group_lock);
-		max_nid = preferred_group_nid(p, max_group_nid);
+		max_nid = preferred_group_nid(p, max_nid);
 	}
 
 	if (max_faults) {
 		/* Set the new preferred node */
 		if (max_nid != p->numa_preferred_nid)
 			sched_setnuma(p, max_nid);
-
-		if (task_node(p) != p->numa_preferred_nid)
-			numa_migrate_preferred(p);
 	}
+
+	update_task_scan_period(p, fault_types[0], fault_types[1]);
 }
 
 static inline int get_numa_group(struct numa_group *grp)
@@ -2450,14 +2382,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 				numa_is_active_node(mem_node, ng))
 		local = 1;
 
-	task_numa_placement(p);
-
 	/*
 	 * Retry task to preferred node migration periodically, in case it
 	 * case it previously failed, or the scheduler moved us.
 	 */
-	if (time_after(jiffies, p->numa_migrate_retry))
+	if (time_after(jiffies, p->numa_migrate_retry)) {
+		task_numa_placement(p);
 		numa_migrate_preferred(p);
+	}
 
 	if (migrated)
 		p->numa_pages_migrated += pages;
@@ -2749,19 +2681,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 } while (0)
 
 #ifdef CONFIG_SMP
-/*
- * XXX we want to get rid of these helpers and use the full load resolution.
- */
-static inline long se_weight(struct sched_entity *se)
-{
-	return scale_load_down(se->load.weight);
-}
-
-static inline long se_runnable(struct sched_entity *se)
-{
-	return scale_load_down(se->runnable_weight);
-}
-
 static inline void
 enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -3062,314 +2981,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 }
 
 #ifdef CONFIG_SMP
-/*
- * Approximate:
- *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
- */
-static u64 decay_load(u64 val, u64 n)
-{
-	unsigned int local_n;
-
-	if (unlikely(n > LOAD_AVG_PERIOD * 63))
-		return 0;
-
-	/* after bounds checking we can collapse to 32-bit */
-	local_n = n;
-
-	/*
-	 * As y^PERIOD = 1/2, we can combine
-	 *    y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
-	 * With a look-up table which covers y^n (n<PERIOD)
-	 *
-	 * To achieve constant time decay_load.
-	 */
-	if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
-		val >>= local_n / LOAD_AVG_PERIOD;
-		local_n %= LOAD_AVG_PERIOD;
-	}
-
-	val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
-	return val;
-}
-
-static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
-{
-	u32 c1, c2, c3 = d3; /* y^0 == 1 */
-
-	/*
-	 * c1 = d1 y^p
-	 */
-	c1 = decay_load((u64)d1, periods);
-
-	/*
-	 *            p-1
-	 * c2 = 1024 \Sum y^n
-	 *            n=1
-	 *
-	 *              inf        inf
-	 *    = 1024 ( \Sum y^n - \Sum y^n - y^0 )
-	 *              n=0        n=p
-	 */
-	c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
-
-	return c1 + c2 + c3;
-}
-
-/*
- * Accumulate the three separate parts of the sum; d1 the remainder
- * of the last (incomplete) period, d2 the span of full periods and d3
- * the remainder of the (incomplete) current period.
- *
- *           d1          d2           d3
- *           ^           ^            ^
- *           |           |            |
- *         |<->|<----------------->|<--->|
- * ... |---x---|------| ... |------|-----x (now)
- *
- *                           p-1
- * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
- *                           n=1
- *
- *    = u y^p +					(Step 1)
- *
- *                     p-1
- *      d1 y^p + 1024 \Sum y^n + d3 y^0		(Step 2)
- *                     n=1
- */
-static __always_inline u32
-accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
-	       unsigned long load, unsigned long runnable, int running)
-{
-	unsigned long scale_freq, scale_cpu;
-	u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
-	u64 periods;
-
-	scale_freq = arch_scale_freq_capacity(cpu);
-	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
-
-	delta += sa->period_contrib;
-	periods = delta / 1024; /* A period is 1024us (~1ms) */
-
-	/*
-	 * Step 1: decay old *_sum if we crossed period boundaries.
-	 */
-	if (periods) {
-		sa->load_sum = decay_load(sa->load_sum, periods);
-		sa->runnable_load_sum =
-			decay_load(sa->runnable_load_sum, periods);
-		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
-
-		/*
-		 * Step 2
-		 */
-		delta %= 1024;
-		contrib = __accumulate_pelt_segments(periods,
-				1024 - sa->period_contrib, delta);
-	}
-	sa->period_contrib = delta;
-
-	contrib = cap_scale(contrib, scale_freq);
-	if (load)
-		sa->load_sum += load * contrib;
-	if (runnable)
-		sa->runnable_load_sum += runnable * contrib;
-	if (running)
-		sa->util_sum += contrib * scale_cpu;
-
-	return periods;
-}
-
-/*
- * We can represent the historical contribution to runnable average as the
- * coefficients of a geometric series.  To do this we sub-divide our runnable
- * history into segments of approximately 1ms (1024us); label the segment that
- * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
- *
- * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
- *      p0            p1           p2
- *     (now)       (~1ms ago)  (~2ms ago)
- *
- * Let u_i denote the fraction of p_i that the entity was runnable.
- *
- * We then designate the fractions u_i as our co-efficients, yielding the
- * following representation of historical load:
- *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
- *
- * We choose y based on the with of a reasonably scheduling period, fixing:
- *   y^32 = 0.5
- *
- * This means that the contribution to load ~32ms ago (u_32) will be weighted
- * approximately half as much as the contribution to load within the last ms
- * (u_0).
- *
- * When a period "rolls over" and we have new u_0`, multiplying the previous
- * sum again by y is sufficient to update:
- *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
- *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
- */
-static __always_inline int
-___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
-		  unsigned long load, unsigned long runnable, int running)
-{
-	u64 delta;
-
-	delta = now - sa->last_update_time;
-	/*
-	 * This should only happen when time goes backwards, which it
-	 * unfortunately does during sched clock init when we swap over to TSC.
-	 */
-	if ((s64)delta < 0) {
-		sa->last_update_time = now;
-		return 0;
-	}
-
-	/*
-	 * Use 1024ns as the unit of measurement since it's a reasonable
-	 * approximation of 1us and fast to compute.
-	 */
-	delta >>= 10;
-	if (!delta)
-		return 0;
-
-	sa->last_update_time += delta << 10;
-
-	/*
-	 * running is a subset of runnable (weight) so running can't be set if
-	 * runnable is clear. But there are some corner cases where the current
-	 * se has been already dequeued but cfs_rq->curr still points to it.
-	 * This means that weight will be 0 but not running for a sched_entity
-	 * but also for a cfs_rq if the latter becomes idle. As an example,
-	 * this happens during idle_balance() which calls
-	 * update_blocked_averages()
-	 */
-	if (!load)
-		runnable = running = 0;
-
-	/*
-	 * Now we know we crossed measurement unit boundaries. The *_avg
-	 * accrues by two steps:
-	 *
-	 * Step 1: accumulate *_sum since last_update_time. If we haven't
-	 * crossed period boundaries, finish.
-	 */
-	if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
-		return 0;
-
-	return 1;
-}
-
-static __always_inline void
-___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
-{
-	u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
-
-	/*
-	 * Step 2: update *_avg.
-	 */
-	sa->load_avg = div_u64(load * sa->load_sum, divider);
-	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
-	sa->util_avg = sa->util_sum / divider;
-}
-
-/*
- * When a task is dequeued, its estimated utilization should not be update if
- * its util_avg has not been updated at least once.
- * This flag is used to synchronize util_avg updates with util_est updates.
- * We map this information into the LSB bit of the utilization saved at
- * dequeue time (i.e. util_est.dequeued).
- */
-#define UTIL_AVG_UNCHANGED 0x1
-
-static inline void cfs_se_util_change(struct sched_avg *avg)
-{
-	unsigned int enqueued;
-
-	if (!sched_feat(UTIL_EST))
-		return;
-
-	/* Avoid store if the flag has been already set */
-	enqueued = avg->util_est.enqueued;
-	if (!(enqueued & UTIL_AVG_UNCHANGED))
-		return;
-
-	/* Reset flag to report util_avg has been updated */
-	enqueued &= ~UTIL_AVG_UNCHANGED;
-	WRITE_ONCE(avg->util_est.enqueued, enqueued);
-}
-
-/*
- * sched_entity:
- *
- *   task:
- *     se_runnable() == se_weight()
- *
- *   group: [ see update_cfs_group() ]
- *     se_weight()   = tg->weight * grq->load_avg / tg->load_avg
- *     se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
- *
- *   load_sum := runnable_sum
- *   load_avg = se_weight(se) * runnable_avg
- *
- *   runnable_load_sum := runnable_sum
- *   runnable_load_avg = se_runnable(se) * runnable_avg
- *
- * XXX collapse load_sum and runnable_load_sum
- *
- * cfq_rs:
- *
- *   load_sum = \Sum se_weight(se) * se->avg.load_sum
- *   load_avg = \Sum se->avg.load_avg
- *
- *   runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
- *   runnable_load_avg = \Sum se->avg.runable_load_avg
- */
-
-static int
-__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
-{
-	if (entity_is_task(se))
-		se->runnable_weight = se->load.weight;
-
-	if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
-		return 1;
-	}
-
-	return 0;
-}
-
-static int
-__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	if (entity_is_task(se))
-		se->runnable_weight = se->load.weight;
-
-	if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
-				cfs_rq->curr == se)) {
-
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
-		cfs_se_util_change(&se->avg);
-		return 1;
-	}
-
-	return 0;
-}
-
-static int
-__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
-{
-	if (___update_load_sum(now, cpu, &cfs_rq->avg,
-				scale_load_down(cfs_rq->load.weight),
-				scale_load_down(cfs_rq->runnable_weight),
-				cfs_rq->curr != NULL)) {
-
-		___update_load_avg(&cfs_rq->avg, 1, 1);
-		return 1;
-	}
-
-	return 0;
-}
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /**
  * update_tg_load_avg - update the tg's load avg
@@ -4037,12 +3648,6 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 
 #else /* CONFIG_SMP */
 
-static inline int
-update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
-{
-	return 0;
-}
-
 #define UPDATE_TG	0x0
 #define SKIP_AGE_LOAD	0x0
 #define DO_ATTACH	0x0
@@ -4726,7 +4331,6 @@ static inline int throttled_lb_pair(struct task_group *tg,
 	       throttled_hierarchy(dest_cfs_rq);
 }
 
-/* updated child weight may affect parent so we have to do this bottom up */
 static int tg_unthrottle_up(struct task_group *tg, void *data)
 {
 	struct rq *rq = data;
@@ -5653,8 +5257,6 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
 
 		this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
 	}
-
-	sched_avg_update(this_rq);
 }
 
 /* Used instead of source_load when we know the type == 0 */
@@ -6237,6 +5839,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 }
 
 #ifdef CONFIG_SCHED_SMT
+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 
 static inline void set_idle_cores(int cpu, int val)
 {
@@ -7294,8 +6897,8 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 {
 	struct numa_group *numa_group = rcu_dereference(p->numa_group);
-	unsigned long src_faults, dst_faults;
-	int src_nid, dst_nid;
+	unsigned long src_weight, dst_weight;
+	int src_nid, dst_nid, dist;
 
 	if (!static_branch_likely(&sched_numa_balancing))
 		return -1;
@@ -7322,18 +6925,19 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 		return 0;
 
 	/* Leaving a core idle is often worse than degrading locality. */
-	if (env->idle != CPU_NOT_IDLE)
+	if (env->idle == CPU_IDLE)
 		return -1;
 
+	dist = node_distance(src_nid, dst_nid);
 	if (numa_group) {
-		src_faults = group_faults(p, src_nid);
-		dst_faults = group_faults(p, dst_nid);
+		src_weight = group_weight(p, src_nid, dist);
+		dst_weight = group_weight(p, dst_nid, dist);
 	} else {
-		src_faults = task_faults(p, src_nid);
-		dst_faults = task_faults(p, dst_nid);
+		src_weight = task_weight(p, src_nid, dist);
+		dst_weight = task_weight(p, dst_nid, dist);
 	}
 
-	return dst_faults < src_faults;
+	return dst_weight < src_weight;
 }
 
 #else
@@ -7620,6 +7224,22 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
 	return false;
 }
 
+static inline bool others_have_blocked(struct rq *rq)
+{
+	if (READ_ONCE(rq->avg_rt.util_avg))
+		return true;
+
+	if (READ_ONCE(rq->avg_dl.util_avg))
+		return true;
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	if (READ_ONCE(rq->avg_irq.util_avg))
+		return true;
+#endif
+
+	return false;
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
@@ -7679,6 +7299,12 @@ static void update_blocked_averages(int cpu)
 		if (cfs_rq_has_blocked(cfs_rq))
 			done = false;
 	}
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_irq_load_avg(rq, 0);
+	/* Don't need periodic decay once load/util_avg are null */
+	if (others_have_blocked(rq))
+		done = false;
 
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
@@ -7744,9 +7370,12 @@ static inline void update_blocked_averages(int cpu)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_irq_load_avg(rq, 0);
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
-	if (!cfs_rq_has_blocked(cfs_rq))
+	if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq))
 		rq->has_blocked_load = 0;
 #endif
 	rq_unlock_irqrestore(rq, &rf);
@@ -7856,39 +7485,32 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	u64 total, used, age_stamp, avg;
-	s64 delta;
+	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+	unsigned long used, free;
+	unsigned long irq;
 
-	/*
-	 * Since we're reading these variables without serialization make sure
-	 * we read them once before doing sanity checks on them.
-	 */
-	age_stamp = READ_ONCE(rq->age_stamp);
-	avg = READ_ONCE(rq->rt_avg);
-	delta = __rq_clock_broken(rq) - age_stamp;
+	irq = cpu_util_irq(rq);
 
-	if (unlikely(delta < 0))
-		delta = 0;
+	if (unlikely(irq >= max))
+		return 1;
 
-	total = sched_avg_period() + delta;
+	used = READ_ONCE(rq->avg_rt.util_avg);
+	used += READ_ONCE(rq->avg_dl.util_avg);
 
-	used = div_u64(avg, total);
+	if (unlikely(used >= max))
+		return 1;
 
-	if (likely(used < SCHED_CAPACITY_SCALE))
-		return SCHED_CAPACITY_SCALE - used;
+	free = max - used;
 
-	return 1;
+	return scale_irq_capacity(free, irq, max);
 }
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
+	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
 
-	cpu_rq(cpu)->cpu_capacity_orig = capacity;
-
-	capacity *= scale_rt_capacity(cpu);
-	capacity >>= SCHED_CAPACITY_SHIFT;
+	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
 
 	if (!capacity)
 		capacity = 1;
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
new file mode 100644
index 000000000000..35475c0c5419
--- /dev/null
+++ b/kernel/sched/pelt.c
@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Per Entity Load Tracking
+ *
+ *  Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ *  Interactivity improvements by Mike Galbraith
+ *  (C) 2007 Mike Galbraith <efault@gmx.de>
+ *
+ *  Various enhancements by Dmitry Adamushko.
+ *  (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
+ *
+ *  Group scheduling enhancements by Srivatsa Vaddagiri
+ *  Copyright IBM Corporation, 2007
+ *  Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
+ *
+ *  Scaled math optimizations by Thomas Gleixner
+ *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
+ *
+ *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
+ *
+ *  Move PELT related code from fair.c into this pelt.c file
+ *  Author: Vincent Guittot <vincent.guittot@linaro.org>
+ */
+
+#include <linux/sched.h>
+#include "sched.h"
+#include "sched-pelt.h"
+#include "pelt.h"
+
+/*
+ * Approximate:
+ *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
+ */
+static u64 decay_load(u64 val, u64 n)
+{
+	unsigned int local_n;
+
+	if (unlikely(n > LOAD_AVG_PERIOD * 63))
+		return 0;
+
+	/* after bounds checking we can collapse to 32-bit */
+	local_n = n;
+
+	/*
+	 * As y^PERIOD = 1/2, we can combine
+	 *    y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
+	 * With a look-up table which covers y^n (n<PERIOD)
+	 *
+	 * To achieve constant time decay_load.
+	 */
+	if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
+		val >>= local_n / LOAD_AVG_PERIOD;
+		local_n %= LOAD_AVG_PERIOD;
+	}
+
+	val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
+	return val;
+}
+
+static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
+{
+	u32 c1, c2, c3 = d3; /* y^0 == 1 */
+
+	/*
+	 * c1 = d1 y^p
+	 */
+	c1 = decay_load((u64)d1, periods);
+
+	/*
+	 *            p-1
+	 * c2 = 1024 \Sum y^n
+	 *            n=1
+	 *
+	 *              inf        inf
+	 *    = 1024 ( \Sum y^n - \Sum y^n - y^0 )
+	 *              n=0        n=p
+	 */
+	c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
+
+	return c1 + c2 + c3;
+}
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
+/*
+ * Accumulate the three separate parts of the sum; d1 the remainder
+ * of the last (incomplete) period, d2 the span of full periods and d3
+ * the remainder of the (incomplete) current period.
+ *
+ *           d1          d2           d3
+ *           ^           ^            ^
+ *           |           |            |
+ *         |<->|<----------------->|<--->|
+ * ... |---x---|------| ... |------|-----x (now)
+ *
+ *                           p-1
+ * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
+ *                           n=1
+ *
+ *    = u y^p +					(Step 1)
+ *
+ *                     p-1
+ *      d1 y^p + 1024 \Sum y^n + d3 y^0		(Step 2)
+ *                     n=1
+ */
+static __always_inline u32
+accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
+	       unsigned long load, unsigned long runnable, int running)
+{
+	unsigned long scale_freq, scale_cpu;
+	u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
+	u64 periods;
+
+	scale_freq = arch_scale_freq_capacity(cpu);
+	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+
+	delta += sa->period_contrib;
+	periods = delta / 1024; /* A period is 1024us (~1ms) */
+
+	/*
+	 * Step 1: decay old *_sum if we crossed period boundaries.
+	 */
+	if (periods) {
+		sa->load_sum = decay_load(sa->load_sum, periods);
+		sa->runnable_load_sum =
+			decay_load(sa->runnable_load_sum, periods);
+		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
+
+		/*
+		 * Step 2
+		 */
+		delta %= 1024;
+		contrib = __accumulate_pelt_segments(periods,
+				1024 - sa->period_contrib, delta);
+	}
+	sa->period_contrib = delta;
+
+	contrib = cap_scale(contrib, scale_freq);
+	if (load)
+		sa->load_sum += load * contrib;
+	if (runnable)
+		sa->runnable_load_sum += runnable * contrib;
+	if (running)
+		sa->util_sum += contrib * scale_cpu;
+
+	return periods;
+}
+
+/*
+ * We can represent the historical contribution to runnable average as the
+ * coefficients of a geometric series.  To do this we sub-divide our runnable
+ * history into segments of approximately 1ms (1024us); label the segment that
+ * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
+ *
+ * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
+ *      p0            p1           p2
+ *     (now)       (~1ms ago)  (~2ms ago)
+ *
+ * Let u_i denote the fraction of p_i that the entity was runnable.
+ *
+ * We then designate the fractions u_i as our co-efficients, yielding the
+ * following representation of historical load:
+ *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
+ *
+ * We choose y based on the with of a reasonably scheduling period, fixing:
+ *   y^32 = 0.5
+ *
+ * This means that the contribution to load ~32ms ago (u_32) will be weighted
+ * approximately half as much as the contribution to load within the last ms
+ * (u_0).
+ *
+ * When a period "rolls over" and we have new u_0`, multiplying the previous
+ * sum again by y is sufficient to update:
+ *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
+ *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
+ */
+static __always_inline int
+___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
+		  unsigned long load, unsigned long runnable, int running)
+{
+	u64 delta;
+
+	delta = now - sa->last_update_time;
+	/*
+	 * This should only happen when time goes backwards, which it
+	 * unfortunately does during sched clock init when we swap over to TSC.
+	 */
+	if ((s64)delta < 0) {
+		sa->last_update_time = now;
+		return 0;
+	}
+
+	/*
+	 * Use 1024ns as the unit of measurement since it's a reasonable
+	 * approximation of 1us and fast to compute.
+	 */
+	delta >>= 10;
+	if (!delta)
+		return 0;
+
+	sa->last_update_time += delta << 10;
+
+	/*
+	 * running is a subset of runnable (weight) so running can't be set if
+	 * runnable is clear. But there are some corner cases where the current
+	 * se has been already dequeued but cfs_rq->curr still points to it.
+	 * This means that weight will be 0 but not running for a sched_entity
+	 * but also for a cfs_rq if the latter becomes idle. As an example,
+	 * this happens during idle_balance() which calls
+	 * update_blocked_averages()
+	 */
+	if (!load)
+		runnable = running = 0;
+
+	/*
+	 * Now we know we crossed measurement unit boundaries. The *_avg
+	 * accrues by two steps:
+	 *
+	 * Step 1: accumulate *_sum since last_update_time. If we haven't
+	 * crossed period boundaries, finish.
+	 */
+	if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
+		return 0;
+
+	return 1;
+}
+
+static __always_inline void
+___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
+{
+	u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+
+	/*
+	 * Step 2: update *_avg.
+	 */
+	sa->load_avg = div_u64(load * sa->load_sum, divider);
+	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
+	WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
+}
+
+/*
+ * sched_entity:
+ *
+ *   task:
+ *     se_runnable() == se_weight()
+ *
+ *   group: [ see update_cfs_group() ]
+ *     se_weight()   = tg->weight * grq->load_avg / tg->load_avg
+ *     se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
+ *
+ *   load_sum := runnable_sum
+ *   load_avg = se_weight(se) * runnable_avg
+ *
+ *   runnable_load_sum := runnable_sum
+ *   runnable_load_avg = se_runnable(se) * runnable_avg
+ *
+ * XXX collapse load_sum and runnable_load_sum
+ *
+ * cfq_rq:
+ *
+ *   load_sum = \Sum se_weight(se) * se->avg.load_sum
+ *   load_avg = \Sum se->avg.load_avg
+ *
+ *   runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
+ *   runnable_load_avg = \Sum se->avg.runable_load_avg
+ */
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
+{
+	if (entity_is_task(se))
+		se->runnable_weight = se->load.weight;
+
+	if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
+		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		return 1;
+	}
+
+	return 0;
+}
+
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	if (entity_is_task(se))
+		se->runnable_weight = se->load.weight;
+
+	if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
+				cfs_rq->curr == se)) {
+
+		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		cfs_se_util_change(&se->avg);
+		return 1;
+	}
+
+	return 0;
+}
+
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
+{
+	if (___update_load_sum(now, cpu, &cfs_rq->avg,
+				scale_load_down(cfs_rq->load.weight),
+				scale_load_down(cfs_rq->runnable_weight),
+				cfs_rq->curr != NULL)) {
+
+		___update_load_avg(&cfs_rq->avg, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * rt_rq:
+ *
+ *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ *   util_sum = cpu_scale * load_sum
+ *   runnable_load_sum = load_sum
+ *
+ *   load_avg and runnable_load_avg are not supported and meaningless.
+ *
+ */
+
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	if (___update_load_sum(now, rq->cpu, &rq->avg_rt,
+				running,
+				running,
+				running)) {
+
+		___update_load_avg(&rq->avg_rt, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * dl_rq:
+ *
+ *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ *   util_sum = cpu_scale * load_sum
+ *   runnable_load_sum = load_sum
+ *
+ */
+
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	if (___update_load_sum(now, rq->cpu, &rq->avg_dl,
+				running,
+				running,
+				running)) {
+
+		___update_load_avg(&rq->avg_dl, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+/*
+ * irq:
+ *
+ *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ *   util_sum = cpu_scale * load_sum
+ *   runnable_load_sum = load_sum
+ *
+ */
+
+int update_irq_load_avg(struct rq *rq, u64 running)
+{
+	int ret = 0;
+	/*
+	 * We know the time that has been used by interrupt since last update
+	 * but we don't when. Let be pessimistic and assume that interrupt has
+	 * happened just before the update. This is not so far from reality
+	 * because interrupt will most probably wake up task and trig an update
+	 * of rq clock during which the metric si updated.
+	 * We start to decay with normal context time and then we add the
+	 * interrupt context time.
+	 * We can safely remove running from rq->clock because
+	 * rq->clock += delta with delta >= running
+	 */
+	ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq,
+				0,
+				0,
+				0);
+	ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq,
+				1,
+				1,
+				1);
+
+	if (ret)
+		___update_load_avg(&rq->avg_irq, 1, 1);
+
+	return ret;
+}
+#endif
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
new file mode 100644
index 000000000000..d2894db28955
--- /dev/null
+++ b/kernel/sched/pelt.h
@@ -0,0 +1,72 @@
+#ifdef CONFIG_SMP
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se);
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se);
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+int update_irq_load_avg(struct rq *rq, u64 running);
+#else
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+	return 0;
+}
+#endif
+
+/*
+ * When a task is dequeued, its estimated utilization should not be update if
+ * its util_avg has not been updated at least once.
+ * This flag is used to synchronize util_avg updates with util_est updates.
+ * We map this information into the LSB bit of the utilization saved at
+ * dequeue time (i.e. util_est.dequeued).
+ */
+#define UTIL_AVG_UNCHANGED 0x1
+
+static inline void cfs_se_util_change(struct sched_avg *avg)
+{
+	unsigned int enqueued;
+
+	if (!sched_feat(UTIL_EST))
+		return;
+
+	/* Avoid store if the flag has been already set */
+	enqueued = avg->util_est.enqueued;
+	if (!(enqueued & UTIL_AVG_UNCHANGED))
+		return;
+
+	/* Reset flag to report util_avg has been updated */
+	enqueued &= ~UTIL_AVG_UNCHANGED;
+	WRITE_ONCE(avg->util_est.enqueued, enqueued);
+}
+
+#else
+
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+{
+	return 0;
+}
+
+static inline int
+update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	return 0;
+}
+
+static inline int
+update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	return 0;
+}
+
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+	return 0;
+}
+#endif
+
+
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index eaaec8364f96..2e2955a8cf8f 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -5,6 +5,8 @@
  */
 #include "sched.h"
 
+#include "pelt.h"
+
 int sched_rr_timeslice = RR_TIMESLICE;
 int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
 
@@ -973,8 +975,6 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -1578,6 +1578,14 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	rt_queue_push_tasks(rq);
 
+	/*
+	 * If prev task was rt, put_prev_task() has already updated the
+	 * utilization. We only care of the case where we start to schedule a
+	 * rt task
+	 */
+	if (rq->curr->sched_class != &rt_sched_class)
+		update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+
 	return p;
 }
 
@@ -1585,6 +1593,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 {
 	update_curr_rt(rq);
 
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
+
 	/*
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
@@ -2314,6 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	struct sched_rt_entity *rt_se = &p->rt;
 
 	update_curr_rt(rq);
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
 
 	watchdog(rq, p);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c7742dcc136c..4a2e8cae63c4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -594,6 +594,7 @@ struct rt_rq {
 	unsigned long		rt_nr_total;
 	int			overloaded;
 	struct plist_head	pushable_tasks;
+
 #endif /* CONFIG_SMP */
 	int			rt_queued;
 
@@ -673,7 +674,26 @@ struct dl_rq {
 	u64			bw_ratio;
 };
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* An entity is a task if it doesn't "own" a runqueue */
+#define entity_is_task(se)	(!se->my_q)
+#else
+#define entity_is_task(se)	1
+#endif
+
 #ifdef CONFIG_SMP
+/*
+ * XXX we want to get rid of these helpers and use the full load resolution.
+ */
+static inline long se_weight(struct sched_entity *se)
+{
+	return scale_load_down(se->load.weight);
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+	return scale_load_down(se->runnable_weight);
+}
 
 static inline bool sched_asym_prefer(int a, int b)
 {
@@ -833,8 +853,12 @@ struct rq {
 
 	struct list_head cfs_tasks;
 
-	u64			rt_avg;
-	u64			age_stamp;
+	struct sched_avg	avg_rt;
+	struct sched_avg	avg_dl;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#define HAVE_SCHED_AVG_IRQ
+	struct sched_avg	avg_irq;
+#endif
 	u64			idle_stamp;
 	u64			avg_idle;
 
@@ -1075,7 +1099,8 @@ enum numa_faults_stats {
 };
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
-extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern int migrate_swap(struct task_struct *p, struct task_struct *t,
+			int cpu, int scpu);
 extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
 #else
 static inline void
@@ -1690,15 +1715,9 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
 extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
-extern const_debug unsigned int sysctl_sched_time_avg;
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
-static inline u64 sched_avg_period(void)
-{
-	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
-}
-
 #ifdef CONFIG_SCHED_HRTICK
 
 /*
@@ -1735,8 +1754,6 @@ unsigned long arch_scale_freq_capacity(int cpu)
 #endif
 
 #ifdef CONFIG_SMP
-extern void sched_avg_update(struct rq *rq);
-
 #ifndef arch_scale_cpu_capacity
 static __always_inline
 unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
@@ -1747,12 +1764,6 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 	return SCHED_CAPACITY_SCALE;
 }
 #endif
-
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
-{
-	rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq));
-	sched_avg_update(rq);
-}
 #else
 #ifndef arch_scale_cpu_capacity
 static __always_inline
@@ -1761,8 +1772,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
 	return SCHED_CAPACITY_SCALE;
 }
 #endif
-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 *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
@@ -2177,11 +2186,16 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
-static inline unsigned long cpu_util_dl(struct rq *rq)
+static inline unsigned long cpu_bw_dl(struct rq *rq)
 {
 	return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
 }
 
+static inline unsigned long cpu_util_dl(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_dl.util_avg);
+}
+
 static inline unsigned long cpu_util_cfs(struct rq *rq)
 {
 	unsigned long util = READ_ONCE(rq->cfs.avg.util_avg);
@@ -2193,4 +2207,37 @@ static inline unsigned long cpu_util_cfs(struct rq *rq)
 
 	return util;
 }
+
+static inline unsigned long cpu_util_rt(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_rt.util_avg);
+}
+#endif
+
+#ifdef HAVE_SCHED_AVG_IRQ
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return rq->avg_irq.util_avg;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+	util *= (max - irq);
+	util /= max;
+
+	return util;
+
+}
+#else
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return 0;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+	return util;
+}
 #endif
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index b6fb2c3b3ff7..66b59ac77c22 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -32,7 +32,7 @@ void swake_up_locked(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_locked);
 
-void swake_up(struct swait_queue_head *q)
+void swake_up_one(struct swait_queue_head *q)
 {
 	unsigned long flags;
 
@@ -40,7 +40,7 @@ void swake_up(struct swait_queue_head *q)
 	swake_up_locked(q);
 	raw_spin_unlock_irqrestore(&q->lock, flags);
 }
-EXPORT_SYMBOL(swake_up);
+EXPORT_SYMBOL(swake_up_one);
 
 /*
  * Does not allow usage from IRQ disabled, since we must be able to
@@ -69,14 +69,14 @@ void swake_up_all(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_all);
 
-void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
 {
 	wait->task = current;
 	if (list_empty(&wait->task_list))
-		list_add(&wait->task_list, &q->task_list);
+		list_add_tail(&wait->task_list, &q->task_list);
 }
 
-void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
+void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state)
 {
 	unsigned long flags;
 
@@ -85,16 +85,28 @@ void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int
 	set_current_state(state);
 	raw_spin_unlock_irqrestore(&q->lock, flags);
 }
-EXPORT_SYMBOL(prepare_to_swait);
+EXPORT_SYMBOL(prepare_to_swait_exclusive);
 
 long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
 {
-	if (signal_pending_state(state, current))
-		return -ERESTARTSYS;
+	unsigned long flags;
+	long ret = 0;
 
-	prepare_to_swait(q, wait, state);
+	raw_spin_lock_irqsave(&q->lock, flags);
+	if (unlikely(signal_pending_state(state, current))) {
+		/*
+		 * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one()
+		 * must not see us.
+		 */
+		list_del_init(&wait->task_list);
+		ret = -ERESTARTSYS;
+	} else {
+		__prepare_to_swait(q, wait);
+		set_current_state(state);
+	}
+	raw_spin_unlock_irqrestore(&q->lock, flags);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(prepare_to_swait_event);
 
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 928be527477e..870f97b313e3 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -134,8 +134,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
  *
  * On UP it can prevent extra preemption.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -392,35 +392,36 @@ static inline bool is_kthread_should_stop(void)
  *     if (condition)
  *         break;
  *
- *     p->state = mode;				condition = true;
- *     smp_mb(); // A				smp_wmb(); // C
- *     if (!wq_entry->flags & WQ_FLAG_WOKEN)	wq_entry->flags |= WQ_FLAG_WOKEN;
- *         schedule()				try_to_wake_up();
- *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
- *     wq_entry->flags &= ~WQ_FLAG_WOKEN;		condition = true;
- *     smp_mb() // B				smp_wmb(); // C
- *						wq_entry->flags |= WQ_FLAG_WOKEN;
- * }
- * remove_wait_queue(&wq_head, &wait);
+ *     // in wait_woken()			// in woken_wake_function()
  *
+ *     p->state = mode;				wq_entry->flags |= WQ_FLAG_WOKEN;
+ *     smp_mb(); // A				try_to_wake_up():
+ *     if (!(wq_entry->flags & WQ_FLAG_WOKEN))	   <full barrier>
+ *         schedule()				   if (p->state & mode)
+ *     p->state = TASK_RUNNING;			      p->state = TASK_RUNNING;
+ *     wq_entry->flags &= ~WQ_FLAG_WOKEN;	~~~~~~~~~~~~~~~~~~
+ *     smp_mb(); // B				condition = true;
+ * }						smp_mb(); // C
+ * remove_wait_queue(&wq_head, &wait);		wq_entry->flags |= WQ_FLAG_WOKEN;
  */
 long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
 {
-	set_current_state(mode); /* A */
 	/*
-	 * The above implies an smp_mb(), which matches with the smp_wmb() from
-	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
-	 * also observe all state before the wakeup.
+	 * The below executes an smp_mb(), which matches with the full barrier
+	 * executed by the try_to_wake_up() in woken_wake_function() such that
+	 * either we see the store to wq_entry->flags in woken_wake_function()
+	 * or woken_wake_function() sees our store to current->state.
 	 */
+	set_current_state(mode); /* A */
 	if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
 		timeout = schedule_timeout(timeout);
 	__set_current_state(TASK_RUNNING);
 
 	/*
-	 * The below implies an smp_mb(), it too pairs with the smp_wmb() from
-	 * woken_wake_function() such that we must either observe the wait
-	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
-	 * an event.
+	 * The below executes an smp_mb(), which matches with the smp_mb() (C)
+	 * in woken_wake_function() such that either we see the wait condition
+	 * being true or the store to wq_entry->flags in woken_wake_function()
+	 * follows ours in the coherence order.
 	 */
 	smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
 
@@ -430,14 +431,8 @@ EXPORT_SYMBOL(wait_woken);
 
 int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
 {
-	/*
-	 * Although this function is called under waitqueue lock, LOCK
-	 * doesn't imply write barrier and the users expects write
-	 * barrier semantics on wakeup functions.  The following
-	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
-	 * and is paired with smp_store_mb() in wait_woken().
-	 */
-	smp_wmb(); /* C */
+	/* Pairs with the smp_store_mb() in wait_woken(). */
+	smp_mb(); /* C */
 	wq_entry->flags |= WQ_FLAG_WOKEN;
 
 	return default_wake_function(wq_entry, mode, sync, key);
diff --git a/kernel/smp.c b/kernel/smp.c
index 084c8b3a2681..d86eec5f51c1 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -584,6 +584,8 @@ void __init smp_init(void)
 		num_nodes, (num_nodes > 1 ? "s" : ""),
 		num_cpus,  (num_cpus  > 1 ? "s" : ""));
 
+	/* Final decision about SMT support */
+	cpu_smt_check_topology();
 	/* Any cleanup work */
 	smp_cpus_done(setup_max_cpus);
 }
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 5043e7433f4b..c230c2dd48e1 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -238,8 +238,7 @@ int smpboot_unpark_threads(unsigned int cpu)
 
 	mutex_lock(&smpboot_threads_lock);
 	list_for_each_entry(cur, &hotplug_threads, list)
-		if (cpumask_test_cpu(cpu, cur->cpumask))
-			smpboot_unpark_thread(cur, cpu);
+		smpboot_unpark_thread(cur, cpu);
 	mutex_unlock(&smpboot_threads_lock);
 	return 0;
 }
@@ -280,34 +279,26 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
 }
 
 /**
- * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related
+ * smpboot_register_percpu_thread - Register a per_cpu thread related
  * 					    to hotplug
  * @plug_thread:	Hotplug thread descriptor
- * @cpumask:		The cpumask where threads run
  *
  * Creates and starts the threads on all online cpus.
  */
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
-					   const struct cpumask *cpumask)
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
 {
 	unsigned int cpu;
 	int ret = 0;
 
-	if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL))
-		return -ENOMEM;
-	cpumask_copy(plug_thread->cpumask, cpumask);
-
 	get_online_cpus();
 	mutex_lock(&smpboot_threads_lock);
 	for_each_online_cpu(cpu) {
 		ret = __smpboot_create_thread(plug_thread, cpu);
 		if (ret) {
 			smpboot_destroy_threads(plug_thread);
-			free_cpumask_var(plug_thread->cpumask);
 			goto out;
 		}
-		if (cpumask_test_cpu(cpu, cpumask))
-			smpboot_unpark_thread(plug_thread, cpu);
+		smpboot_unpark_thread(plug_thread, cpu);
 	}
 	list_add(&plug_thread->list, &hotplug_threads);
 out:
@@ -315,7 +306,7 @@ out:
 	put_online_cpus();
 	return ret;
 }
-EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask);
+EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
 
 /**
  * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
@@ -331,44 +322,9 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	smpboot_destroy_threads(plug_thread);
 	mutex_unlock(&smpboot_threads_lock);
 	put_online_cpus();
-	free_cpumask_var(plug_thread->cpumask);
 }
 EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
 
-/**
- * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked
- * @plug_thread:	Hotplug thread descriptor
- * @new:		Revised mask to use
- *
- * The cpumask field in the smp_hotplug_thread must not be updated directly
- * by the client, but only by calling this function.
- * This function can only be called on a registered smp_hotplug_thread.
- */
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					  const struct cpumask *new)
-{
-	struct cpumask *old = plug_thread->cpumask;
-	static struct cpumask tmp;
-	unsigned int cpu;
-
-	lockdep_assert_cpus_held();
-	mutex_lock(&smpboot_threads_lock);
-
-	/* Park threads that were exclusively enabled on the old mask. */
-	cpumask_andnot(&tmp, old, new);
-	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
-		smpboot_park_thread(plug_thread, cpu);
-
-	/* Unpark threads that are exclusively enabled on the new mask. */
-	cpumask_andnot(&tmp, new, old);
-	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
-		smpboot_unpark_thread(plug_thread, cpu);
-
-	cpumask_copy(old, new);
-
-	mutex_unlock(&smpboot_threads_lock);
-}
-
 static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
 
 /*
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index e190d1ef3a23..067cb83f37ea 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -81,6 +81,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	unsigned long flags;
 	bool enabled;
 
+	preempt_disable();
 	raw_spin_lock_irqsave(&stopper->lock, flags);
 	enabled = stopper->enabled;
 	if (enabled)
@@ -90,6 +91,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 
 	wake_up_q(&wakeq);
+	preempt_enable();
 
 	return enabled;
 }
@@ -236,13 +238,24 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
 	DEFINE_WAKE_Q(wakeq);
 	int err;
+
 retry:
+	/*
+	 * The waking up of stopper threads has to happen in the same
+	 * scheduling context as the queueing.  Otherwise, there is a
+	 * possibility of one of the above stoppers being woken up by another
+	 * CPU, and preempting us. This will cause us to not wake up the other
+	 * stopper forever.
+	 */
+	preempt_disable();
 	raw_spin_lock_irq(&stopper1->lock);
 	raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
 
-	err = -ENOENT;
-	if (!stopper1->enabled || !stopper2->enabled)
+	if (!stopper1->enabled || !stopper2->enabled) {
+		err = -ENOENT;
 		goto unlock;
+	}
+
 	/*
 	 * Ensure that if we race with __stop_cpus() the stoppers won't get
 	 * queued up in reverse order leading to system deadlock.
@@ -253,36 +266,30 @@ retry:
 	 * It can be falsely true but it is safe to spin until it is cleared,
 	 * queue_stop_cpus_work() does everything under preempt_disable().
 	 */
-	err = -EDEADLK;
-	if (unlikely(stop_cpus_in_progress))
-			goto unlock;
+	if (unlikely(stop_cpus_in_progress)) {
+		err = -EDEADLK;
+		goto unlock;
+	}
 
 	err = 0;
 	__cpu_stop_queue_work(stopper1, work1, &wakeq);
 	__cpu_stop_queue_work(stopper2, work2, &wakeq);
-	/*
-	 * The waking up of stopper threads has to happen
-	 * in the same scheduling context as the queueing.
-	 * Otherwise, there is a possibility of one of the
-	 * above stoppers being woken up by another CPU,
-	 * and preempting us. This will cause us to n ot
-	 * wake up the other stopper forever.
-	 */
-	preempt_disable();
+
 unlock:
 	raw_spin_unlock(&stopper2->lock);
 	raw_spin_unlock_irq(&stopper1->lock);
 
 	if (unlikely(err == -EDEADLK)) {
+		preempt_enable();
+
 		while (stop_cpus_in_progress)
 			cpu_relax();
+
 		goto retry;
 	}
 
-	if (!err) {
-		wake_up_q(&wakeq);
-		preempt_enable();
-	}
+	wake_up_q(&wakeq);
+	preempt_enable();
 
 	return err;
 }
diff --git a/kernel/sys.c b/kernel/sys.c
index 38509dc1f77b..e27b51d3facd 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2512,11 +2512,11 @@ static int do_sysinfo(struct sysinfo *info)
 {
 	unsigned long mem_total, sav_total;
 	unsigned int mem_unit, bitcount;
-	struct timespec tp;
+	struct timespec64 tp;
 
 	memset(info, 0, sizeof(struct sysinfo));
 
-	get_monotonic_boottime(&tp);
+	ktime_get_boottime_ts64(&tp);
 	info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
 
 	get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2d9837c0aff4..f22f76b7a138 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -368,14 +368,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "sched_time_avg_ms",
-		.data		= &sysctl_sched_time_avg,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-	},
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname	= "sched_schedstats",
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index dd53e354f630..7bca480151b0 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -162,90 +162,6 @@ static int test_kprobes(void)
 
 }
 
-#if 0
-static u32 jph_val;
-
-static u32 j_kprobe_target(u32 value)
-{
-	if (preemptible()) {
-		handler_errors++;
-		pr_err("jprobe-handler is preemptible\n");
-	}
-	if (value != rand1) {
-		handler_errors++;
-		pr_err("incorrect value in jprobe handler\n");
-	}
-
-	jph_val = rand1;
-	jprobe_return();
-	return 0;
-}
-
-static struct jprobe jp = {
-	.entry		= j_kprobe_target,
-	.kp.symbol_name = "kprobe_target"
-};
-
-static int test_jprobe(void)
-{
-	int ret;
-
-	ret = register_jprobe(&jp);
-	if (ret < 0) {
-		pr_err("register_jprobe returned %d\n", ret);
-		return ret;
-	}
-
-	ret = target(rand1);
-	unregister_jprobe(&jp);
-	if (jph_val == 0) {
-		pr_err("jprobe handler not called\n");
-		handler_errors++;
-	}
-
-	return 0;
-}
-
-static struct jprobe jp2 = {
-	.entry          = j_kprobe_target,
-	.kp.symbol_name = "kprobe_target2"
-};
-
-static int test_jprobes(void)
-{
-	int ret;
-	struct jprobe *jps[2] = {&jp, &jp2};
-
-	/* addr and flags should be cleard for reusing kprobe. */
-	jp.kp.addr = NULL;
-	jp.kp.flags = 0;
-	ret = register_jprobes(jps, 2);
-	if (ret < 0) {
-		pr_err("register_jprobes returned %d\n", ret);
-		return ret;
-	}
-
-	jph_val = 0;
-	ret = target(rand1);
-	if (jph_val == 0) {
-		pr_err("jprobe handler not called\n");
-		handler_errors++;
-	}
-
-	jph_val = 0;
-	ret = target2(rand1);
-	if (jph_val == 0) {
-		pr_err("jprobe handler2 not called\n");
-		handler_errors++;
-	}
-	unregister_jprobes(jps, 2);
-
-	return 0;
-}
-#else
-#define test_jprobe() (0)
-#define test_jprobes() (0)
-#endif
 #ifdef CONFIG_KRETPROBES
 static u32 krph_val;
 
@@ -383,16 +299,6 @@ int init_test_probes(void)
 	if (ret < 0)
 		errors++;
 
-	num_tests++;
-	ret = test_jprobe();
-	if (ret < 0)
-		errors++;
-
-	num_tests++;
-	ret = test_jprobes();
-	if (ret < 0)
-		errors++;
-
 #ifdef CONFIG_KRETPROBES
 	num_tests++;
 	ret = test_kretprobe();
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 639321bf2e39..fa5de5e8de61 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -581,11 +581,11 @@ static void alarm_timer_rearm(struct k_itimer *timr)
  * @timr:	Pointer to the posixtimer data struct
  * @now:	Current time to forward the timer against
  */
-static int alarm_timer_forward(struct k_itimer *timr, ktime_t now)
+static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now)
 {
 	struct alarm *alarm = &timr->it.alarm.alarmtimer;
 
-	return (int) alarm_forward(alarm, timr->it_interval, now);
+	return alarm_forward(alarm, timr->it_interval, now);
 }
 
 /**
@@ -808,7 +808,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	/* Convert (if necessary) to absolute time */
 	if (flags != TIMER_ABSTIME) {
 		ktime_t now = alarm_bases[type].gettime();
-		exp = ktime_add(now, exp);
+
+		exp = ktime_add_safe(now, exp);
 	}
 
 	ret = alarmtimer_do_nsleep(&alarm, exp, type);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 16c027e9cc73..8c0e4092f661 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -463,6 +463,12 @@ void clockevents_register_device(struct clock_event_device *dev)
 		dev->cpumask = cpumask_of(smp_processor_id());
 	}
 
+	if (dev->cpumask == cpu_all_mask) {
+		WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n",
+		     dev->name);
+		dev->cpumask = cpu_possible_mask;
+	}
+
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
 	list_add(&dev->list, &clockevent_devices);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index f89a78e2792b..f74fb00d8064 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -94,6 +94,8 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);
 /*[Clocksource internal variables]---------
  * curr_clocksource:
  *	currently selected clocksource.
+ * suspend_clocksource:
+ *	used to calculate the suspend time.
  * clocksource_list:
  *	linked list with the registered clocksources
  * clocksource_mutex:
@@ -102,10 +104,12 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);
  *	Name of the user-specified clocksource.
  */
 static struct clocksource *curr_clocksource;
+static struct clocksource *suspend_clocksource;
 static LIST_HEAD(clocksource_list);
 static DEFINE_MUTEX(clocksource_mutex);
 static char override_name[CS_NAME_LEN];
 static int finished_booting;
+static u64 suspend_start;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static void clocksource_watchdog_work(struct work_struct *work);
@@ -447,6 +451,140 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) { }
 
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
+static bool clocksource_is_suspend(struct clocksource *cs)
+{
+	return cs == suspend_clocksource;
+}
+
+static void __clocksource_suspend_select(struct clocksource *cs)
+{
+	/*
+	 * Skip the clocksource which will be stopped in suspend state.
+	 */
+	if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP))
+		return;
+
+	/*
+	 * The nonstop clocksource can be selected as the suspend clocksource to
+	 * calculate the suspend time, so it should not supply suspend/resume
+	 * interfaces to suspend the nonstop clocksource when system suspends.
+	 */
+	if (cs->suspend || cs->resume) {
+		pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n",
+			cs->name);
+	}
+
+	/* Pick the best rating. */
+	if (!suspend_clocksource || cs->rating > suspend_clocksource->rating)
+		suspend_clocksource = cs;
+}
+
+/**
+ * clocksource_suspend_select - Select the best clocksource for suspend timing
+ * @fallback:	if select a fallback clocksource
+ */
+static void clocksource_suspend_select(bool fallback)
+{
+	struct clocksource *cs, *old_suspend;
+
+	old_suspend = suspend_clocksource;
+	if (fallback)
+		suspend_clocksource = NULL;
+
+	list_for_each_entry(cs, &clocksource_list, list) {
+		/* Skip current if we were requested for a fallback. */
+		if (fallback && cs == old_suspend)
+			continue;
+
+		__clocksource_suspend_select(cs);
+	}
+}
+
+/**
+ * clocksource_start_suspend_timing - Start measuring the suspend timing
+ * @cs:			current clocksource from timekeeping
+ * @start_cycles:	current cycles from timekeeping
+ *
+ * This function will save the start cycle values of suspend timer to calculate
+ * the suspend time when resuming system.
+ *
+ * This function is called late in the suspend process from timekeeping_suspend(),
+ * that means processes are freezed, non-boot cpus and interrupts are disabled
+ * now. It is therefore possible to start the suspend timer without taking the
+ * clocksource mutex.
+ */
+void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles)
+{
+	if (!suspend_clocksource)
+		return;
+
+	/*
+	 * If current clocksource is the suspend timer, we should use the
+	 * tkr_mono.cycle_last value as suspend_start to avoid same reading
+	 * from suspend timer.
+	 */
+	if (clocksource_is_suspend(cs)) {
+		suspend_start = start_cycles;
+		return;
+	}
+
+	if (suspend_clocksource->enable &&
+	    suspend_clocksource->enable(suspend_clocksource)) {
+		pr_warn_once("Failed to enable the non-suspend-able clocksource.\n");
+		return;
+	}
+
+	suspend_start = suspend_clocksource->read(suspend_clocksource);
+}
+
+/**
+ * clocksource_stop_suspend_timing - Stop measuring the suspend timing
+ * @cs:		current clocksource from timekeeping
+ * @cycle_now:	current cycles from timekeeping
+ *
+ * This function will calculate the suspend time from suspend timer.
+ *
+ * Returns nanoseconds since suspend started, 0 if no usable suspend clocksource.
+ *
+ * This function is called early in the resume process from timekeeping_resume(),
+ * that means there is only one cpu, no processes are running and the interrupts
+ * are disabled. It is therefore possible to stop the suspend timer without
+ * taking the clocksource mutex.
+ */
+u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now)
+{
+	u64 now, delta, nsec = 0;
+
+	if (!suspend_clocksource)
+		return 0;
+
+	/*
+	 * If current clocksource is the suspend timer, we should use the
+	 * tkr_mono.cycle_last value from timekeeping as current cycle to
+	 * avoid same reading from suspend timer.
+	 */
+	if (clocksource_is_suspend(cs))
+		now = cycle_now;
+	else
+		now = suspend_clocksource->read(suspend_clocksource);
+
+	if (now > suspend_start) {
+		delta = clocksource_delta(now, suspend_start,
+					  suspend_clocksource->mask);
+		nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult,
+				       suspend_clocksource->shift);
+	}
+
+	/*
+	 * Disable the suspend timer to save power if current clocksource is
+	 * not the suspend timer.
+	 */
+	if (!clocksource_is_suspend(cs) && suspend_clocksource->disable)
+		suspend_clocksource->disable(suspend_clocksource);
+
+	return nsec;
+}
+
 /**
  * clocksource_suspend - suspend the clocksource(s)
  */
@@ -792,6 +930,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 
 	clocksource_select();
 	clocksource_select_watchdog(false);
+	__clocksource_suspend_select(cs);
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -820,6 +959,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
 
 	clocksource_select();
 	clocksource_select_watchdog(false);
+	clocksource_suspend_select(false);
 	mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
@@ -845,6 +985,15 @@ static int clocksource_unbind(struct clocksource *cs)
 			return -EBUSY;
 	}
 
+	if (clocksource_is_suspend(cs)) {
+		/*
+		 * Select and try to install a replacement suspend clocksource.
+		 * If no replacement suspend clocksource, we will just let the
+		 * clocksource go and have no suspend clocksource.
+		 */
+		clocksource_suspend_select(true);
+	}
+
 	clocksource_watchdog_lock(&flags);
 	clocksource_dequeue_watchdog(cs);
 	list_del_init(&cs->list);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 3e93c54bd3a1..e1a549c9e399 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -718,8 +718,8 @@ static void hrtimer_switch_to_hres(void)
 	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
 	if (tick_init_highres()) {
-		printk(KERN_WARNING "Could not switch to high resolution "
-				    "mode on CPU %d\n", base->cpu);
+		pr_warn("Could not switch to high resolution mode on CPU %u\n",
+			base->cpu);
 		return;
 	}
 	base->hres_active = 1;
@@ -1573,8 +1573,7 @@ retry:
 	else
 		expires_next = ktime_add(now, delta);
 	tick_program_event(expires_next, 1);
-	printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
-		    ktime_to_ns(delta));
+	pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta));
 }
 
 /* called with interrupts disabled */
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index a09ded765f6c..c5e0cba3b39c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -502,7 +502,7 @@ static void sched_sync_hw_clock(struct timespec64 now,
 {
 	struct timespec64 next;
 
-	getnstimeofday64(&next);
+	ktime_get_real_ts64(&next);
 	if (!fail)
 		next.tv_sec = 659;
 	else {
@@ -537,7 +537,7 @@ static void sync_rtc_clock(void)
 	if (!IS_ENABLED(CONFIG_RTC_SYSTOHC))
 		return;
 
-	getnstimeofday64(&now);
+	ktime_get_real_ts64(&now);
 
 	adjust = now;
 	if (persistent_clock_is_local)
@@ -591,7 +591,7 @@ static bool sync_cmos_clock(void)
 	 * Architectures are strongly encouraged to use rtclib and not
 	 * implement this legacy API.
 	 */
-	getnstimeofday64(&now);
+	ktime_get_real_ts64(&now);
 	if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) {
 		if (persistent_clock_is_local)
 			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
@@ -642,7 +642,7 @@ void ntp_notify_cmos_timer(void)
 /*
  * Propagate a new txc->status value into the NTP state:
  */
-static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
+static inline void process_adj_status(const struct timex *txc)
 {
 	if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
 		time_state = TIME_OK;
@@ -665,12 +665,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
 }
 
 
-static inline void process_adjtimex_modes(struct timex *txc,
-						struct timespec64 *ts,
-						s32 *time_tai)
+static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai)
 {
 	if (txc->modes & ADJ_STATUS)
-		process_adj_status(txc, ts);
+		process_adj_status(txc);
 
 	if (txc->modes & ADJ_NANO)
 		time_status |= STA_NANO;
@@ -718,7 +716,7 @@ static inline void process_adjtimex_modes(struct timex *txc,
  * adjtimex mainly allows reading (and writing, if superuser) of
  * kernel time-keeping variables. used by xntpd.
  */
-int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
+int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai)
 {
 	int result;
 
@@ -735,7 +733,7 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
 
 		/* If there are input parameters, then process them: */
 		if (txc->modes)
-			process_adjtimex_modes(txc, ts, time_tai);
+			process_adjtimex_modes(txc, time_tai);
 
 		txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
 				  NTP_SCALE_SHIFT);
@@ -1022,12 +1020,11 @@ void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_t
 
 static int __init ntp_tick_adj_setup(char *str)
 {
-	int rc = kstrtol(str, 0, (long *)&ntp_tick_adj);
-
+	int rc = kstrtos64(str, 0, &ntp_tick_adj);
 	if (rc)
 		return rc;
-	ntp_tick_adj <<= NTP_SCALE_SHIFT;
 
+	ntp_tick_adj <<= NTP_SCALE_SHIFT;
 	return 1;
 }
 
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index 909bd1f1bfb1..c24b0e13f011 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -8,6 +8,6 @@ extern void ntp_clear(void);
 extern u64 ntp_tick_length(void);
 extern ktime_t ntp_get_next_leap(void);
 extern int second_overflow(time64_t secs);
-extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
-extern void __hardpps(const struct timespec64 *, const struct timespec64 *);
+extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai);
+extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
 #endif /* _LINUX_NTP_INTERNAL_H */
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 9cdf54b04ca8..294d7b65af33 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -85,7 +85,7 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now)
 			continue;
 
 		timer->it.cpu.expires += incr;
-		timer->it_overrun += 1 << i;
+		timer->it_overrun += 1LL << i;
 		delta -= incr;
 	}
 }
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 26aa9569e24a..2c6847d5d69b 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -81,7 +81,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
 		ktime_get_ts64(tp);
 		break;
 	case CLOCK_BOOTTIME:
-		get_monotonic_boottime64(tp);
+		ktime_get_boottime_ts64(tp);
 		break;
 	default:
 		return -EINVAL;
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index e08ce3f27447..f23cc46ecf3e 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -86,15 +86,6 @@ static const struct k_clock clock_realtime, clock_monotonic;
 #endif
 
 /*
- * parisc wants ENOTSUP instead of EOPNOTSUPP
- */
-#ifndef ENOTSUP
-# define ENANOSLEEP_NOTSUP EOPNOTSUPP
-#else
-# define ENANOSLEEP_NOTSUP ENOTSUP
-#endif
-
-/*
  * The timer ID is turned into a timer address by idr_find().
  * Verifying a valid ID consists of:
  *
@@ -228,21 +219,21 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp)
  */
 static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
 {
-	getrawmonotonic64(tp);
+	ktime_get_raw_ts64(tp);
 	return 0;
 }
 
 
 static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp)
 {
-	*tp = current_kernel_time64();
+	ktime_get_coarse_real_ts64(tp);
 	return 0;
 }
 
 static int posix_get_monotonic_coarse(clockid_t which_clock,
 						struct timespec64 *tp)
 {
-	*tp = get_monotonic_coarse64();
+	ktime_get_coarse_ts64(tp);
 	return 0;
 }
 
@@ -254,13 +245,13 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
 
 static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
 {
-	get_monotonic_boottime64(tp);
+	ktime_get_boottime_ts64(tp);
 	return 0;
 }
 
 static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
 {
-	timekeeping_clocktai64(tp);
+	ktime_get_clocktai_ts64(tp);
 	return 0;
 }
 
@@ -283,6 +274,17 @@ static __init int init_posix_timers(void)
 }
 __initcall(init_posix_timers);
 
+/*
+ * The siginfo si_overrun field and the return value of timer_getoverrun(2)
+ * are of type int. Clamp the overrun value to INT_MAX
+ */
+static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
+{
+	s64 sum = timr->it_overrun_last + (s64)baseval;
+
+	return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
+}
+
 static void common_hrtimer_rearm(struct k_itimer *timr)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
@@ -290,9 +292,8 @@ static void common_hrtimer_rearm(struct k_itimer *timr)
 	if (!timr->it_interval)
 		return;
 
-	timr->it_overrun += (unsigned int) hrtimer_forward(timer,
-						timer->base->get_time(),
-						timr->it_interval);
+	timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
+					    timr->it_interval);
 	hrtimer_restart(timer);
 }
 
@@ -321,10 +322,10 @@ void posixtimer_rearm(struct siginfo *info)
 
 		timr->it_active = 1;
 		timr->it_overrun_last = timr->it_overrun;
-		timr->it_overrun = -1;
+		timr->it_overrun = -1LL;
 		++timr->it_requeue_pending;
 
-		info->si_overrun += timr->it_overrun_last;
+		info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
 	}
 
 	unlock_timer(timr, flags);
@@ -418,9 +419,8 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 					now = ktime_add(now, kj);
 			}
 #endif
-			timr->it_overrun += (unsigned int)
-				hrtimer_forward(timer, now,
-						timr->it_interval);
+			timr->it_overrun += hrtimer_forward(timer, now,
+							    timr->it_interval);
 			ret = HRTIMER_RESTART;
 			++timr->it_requeue_pending;
 			timr->it_active = 1;
@@ -524,7 +524,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event,
 	new_timer->it_id = (timer_t) new_timer_id;
 	new_timer->it_clock = which_clock;
 	new_timer->kclock = kc;
-	new_timer->it_overrun = -1;
+	new_timer->it_overrun = -1LL;
 
 	if (event) {
 		rcu_read_lock();
@@ -645,11 +645,11 @@ static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now)
 	return __hrtimer_expires_remaining_adjusted(timer, now);
 }
 
-static int common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
+static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
 
-	return (int)hrtimer_forward(timer, now, timr->it_interval);
+	return hrtimer_forward(timer, now, timr->it_interval);
 }
 
 /*
@@ -743,7 +743,7 @@ static int do_timer_gettime(timer_t timer_id,  struct itimerspec64 *setting)
 
 /* Get the time remaining on a POSIX.1b interval timer. */
 SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
-		struct itimerspec __user *, setting)
+		struct __kernel_itimerspec __user *, setting)
 {
 	struct itimerspec64 cur_setting;
 
@@ -755,7 +755,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 	return ret;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
 COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 		       struct compat_itimerspec __user *, setting)
 {
@@ -768,6 +769,7 @@ COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 	}
 	return ret;
 }
+
 #endif
 
 /*
@@ -789,7 +791,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 	if (!timr)
 		return -EINVAL;
 
-	overrun = timr->it_overrun_last;
+	overrun = timer_overrun_to_int(timr, 0);
 	unlock_timer(timr, flags);
 
 	return overrun;
@@ -906,8 +908,8 @@ retry:
 
 /* Set a POSIX.1b interval timer */
 SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
-		const struct itimerspec __user *, new_setting,
-		struct itimerspec __user *, old_setting)
+		const struct __kernel_itimerspec __user *, new_setting,
+		struct __kernel_itimerspec __user *, old_setting)
 {
 	struct itimerspec64 new_spec, old_spec;
 	struct itimerspec64 *rtn = old_setting ? &old_spec : NULL;
@@ -927,7 +929,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 	return error;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
 COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 		       struct compat_itimerspec __user *, new,
 		       struct compat_itimerspec __user *, old)
@@ -1220,7 +1222,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	if (!kc)
 		return -EINVAL;
 	if (!kc->nsleep)
-		return -ENANOSLEEP_NOTSUP;
+		return -EOPNOTSUPP;
 
 	if (get_timespec64(&t, rqtp))
 		return -EFAULT;
@@ -1247,7 +1249,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
 	if (!kc)
 		return -EINVAL;
 	if (!kc->nsleep)
-		return -ENANOSLEEP_NOTSUP;
+		return -EOPNOTSUPP;
 
 	if (compat_get_timespec64(&t, rqtp))
 		return -EFAULT;
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index 151e28f5bf30..ddb21145211a 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -19,7 +19,7 @@ struct k_clock {
 	void	(*timer_get)(struct k_itimer *timr,
 			     struct itimerspec64 *cur_setting);
 	void	(*timer_rearm)(struct k_itimer *timr);
-	int	(*timer_forward)(struct k_itimer *timr, ktime_t now);
+	s64	(*timer_forward)(struct k_itimer *timr, ktime_t now);
 	ktime_t	(*timer_remaining)(struct k_itimer *timr, ktime_t now);
 	int	(*timer_try_to_cancel)(struct k_itimer *timr);
 	void	(*timer_arm)(struct k_itimer *timr, ktime_t expires,
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 2d8f05aad442..cbc72c2c1fca 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -237,7 +237,7 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 	pr_debug("Registered %pF as sched_clock source\n", read);
 }
 
-void __init sched_clock_postinit(void)
+void __init generic_sched_clock_init(void)
 {
 	/*
 	 * If no sched_clock() function has been provided at that point,
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index 58045eb976c3..a59641fb88b6 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -90,7 +90,7 @@ static struct clock_event_device ce_broadcast_hrtimer = {
 	.max_delta_ticks	= ULONG_MAX,
 	.mult			= 1,
 	.shift			= 0,
-	.cpumask		= cpu_all_mask,
+	.cpumask		= cpu_possible_mask,
 };
 
 static enum hrtimer_restart bc_handler(struct hrtimer *t)
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 2b41e8e2d31d..ccdb351277ee 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(sys_tz);
  */
 SYSCALL_DEFINE1(time, time_t __user *, tloc)
 {
-	time_t i = get_seconds();
+	time_t i = (time_t)ktime_get_real_seconds();
 
 	if (tloc) {
 		if (put_user(i,tloc))
@@ -107,11 +107,9 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr)
 /* compat_time_t is a 32 bit "long" and needs to get converted. */
 COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc)
 {
-	struct timeval tv;
 	compat_time_t i;
 
-	do_gettimeofday(&tv);
-	i = tv.tv_sec;
+	i = (compat_time_t)ktime_get_real_seconds();
 
 	if (tloc) {
 		if (put_user(i,tloc))
@@ -931,7 +929,7 @@ int compat_put_timespec64(const struct timespec64 *ts, void __user *uts)
 EXPORT_SYMBOL_GPL(compat_put_timespec64);
 
 int get_itimerspec64(struct itimerspec64 *it,
-			const struct itimerspec __user *uit)
+			const struct __kernel_itimerspec __user *uit)
 {
 	int ret;
 
@@ -946,7 +944,7 @@ int get_itimerspec64(struct itimerspec64 *it,
 EXPORT_SYMBOL_GPL(get_itimerspec64);
 
 int put_itimerspec64(const struct itimerspec64 *it,
-			struct itimerspec __user *uit)
+			struct __kernel_itimerspec __user *uit)
 {
 	int ret;
 
@@ -959,3 +957,24 @@ int put_itimerspec64(const struct itimerspec64 *it,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(put_itimerspec64);
+
+int get_compat_itimerspec64(struct itimerspec64 *its,
+			const struct compat_itimerspec __user *uits)
+{
+
+	if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
+	    __compat_get_timespec64(&its->it_value, &uits->it_value))
+		return -EFAULT;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
+
+int put_compat_itimerspec64(const struct itimerspec64 *its,
+			struct compat_itimerspec __user *uits)
+{
+	if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
+	    __compat_put_timespec64(&its->it_value, &uits->it_value))
+		return -EFAULT;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4786df904c22..f3b22f456fac 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -17,6 +17,7 @@
 #include <linux/nmi.h>
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/clock.h>
 #include <linux/syscore_ops.h>
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
@@ -34,6 +35,14 @@
 #define TK_MIRROR		(1 << 1)
 #define TK_CLOCK_WAS_SET	(1 << 2)
 
+enum timekeeping_adv_mode {
+	/* Update timekeeper when a tick has passed */
+	TK_ADV_TICK,
+
+	/* Update timekeeper on a direct frequency change */
+	TK_ADV_FREQ
+};
+
 /*
  * The most important data for readout fits into a single 64 byte
  * cache line.
@@ -97,7 +106,7 @@ static inline void tk_normalize_xtime(struct timekeeper *tk)
 	}
 }
 
-static inline struct timespec64 tk_xtime(struct timekeeper *tk)
+static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
 {
 	struct timespec64 ts;
 
@@ -154,7 +163,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
  * a read of the fast-timekeeper tkrs (which is protected by its own locking
  * and update logic).
  */
-static inline u64 tk_clock_read(struct tk_read_base *tkr)
+static inline u64 tk_clock_read(const struct tk_read_base *tkr)
 {
 	struct clocksource *clock = READ_ONCE(tkr->clock);
 
@@ -203,7 +212,7 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 	}
 }
 
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	u64 now, last, mask, max, delta;
@@ -247,7 +256,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
 static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 {
 }
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
 {
 	u64 cycle_now, delta;
 
@@ -344,7 +353,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
-static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
+static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta)
 {
 	u64 nsec;
 
@@ -355,7 +364,7 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
 	return nsec + arch_gettimeoffset();
 }
 
-static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr)
 {
 	u64 delta;
 
@@ -363,7 +372,7 @@ static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
 	return timekeeping_delta_to_ns(tkr, delta);
 }
 
-static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
+static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles)
 {
 	u64 delta;
 
@@ -386,7 +395,8 @@ static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
  * slightly wrong timestamp (a few nanoseconds). See
  * @ktime_get_mono_fast_ns.
  */
-static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf)
+static void update_fast_timekeeper(const struct tk_read_base *tkr,
+				   struct tk_fast *tkf)
 {
 	struct tk_read_base *base = tkf->base;
 
@@ -541,10 +551,10 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
  * number of cycles every time until timekeeping is resumed at which time the
  * proper readout base for the fast timekeeper will be restored automatically.
  */
-static void halt_fast_timekeeper(struct timekeeper *tk)
+static void halt_fast_timekeeper(const struct timekeeper *tk)
 {
 	static struct tk_read_base tkr_dummy;
-	struct tk_read_base *tkr = &tk->tkr_mono;
+	const struct tk_read_base *tkr = &tk->tkr_mono;
 
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
 	cycles_at_suspend = tk_clock_read(tkr);
@@ -1269,7 +1279,7 @@ EXPORT_SYMBOL(do_settimeofday64);
  *
  * Adds or subtracts an offset value from the current time.
  */
-static int timekeeping_inject_offset(struct timespec64 *ts)
+static int timekeeping_inject_offset(const struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
@@ -1496,22 +1506,39 @@ void __weak read_persistent_clock64(struct timespec64 *ts64)
 }
 
 /**
- * read_boot_clock64 -  Return time of the system start.
+ * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
+ *                                        from the boot.
  *
  * Weak dummy function for arches that do not yet support it.
- * Function to read the exact time the system has been started.
- * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
- *
- *  XXX - Do be sure to remove it once all arches implement it.
+ * wall_time	- current time as returned by persistent clock
+ * boot_offset	- offset that is defined as wall_time - boot_time
+ * The default function calculates offset based on the current value of
+ * local_clock(). This way architectures that support sched_clock() but don't
+ * support dedicated boot time clock will provide the best estimate of the
+ * boot time.
  */
-void __weak read_boot_clock64(struct timespec64 *ts)
+void __weak __init
+read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+				     struct timespec64 *boot_offset)
 {
-	ts->tv_sec = 0;
-	ts->tv_nsec = 0;
+	read_persistent_clock64(wall_time);
+	*boot_offset = ns_to_timespec64(local_clock());
 }
 
-/* Flag for if timekeeping_resume() has injected sleeptime */
-static bool sleeptime_injected;
+/*
+ * Flag reflecting whether timekeeping_resume() has injected sleeptime.
+ *
+ * The flag starts of false and is only set when a suspend reaches
+ * timekeeping_suspend(), timekeeping_resume() sets it to false when the
+ * timekeeper clocksource is not stopping across suspend and has been
+ * used to update sleep time. If the timekeeper clocksource has stopped
+ * then the flag stays true and is used by the RTC resume code to decide
+ * whether sleeptime must be injected and if so the flag gets false then.
+ *
+ * If a suspend fails before reaching timekeeping_resume() then the flag
+ * stays false and prevents erroneous sleeptime injection.
+ */
+static bool suspend_timing_needed;
 
 /* Flag for if there is a persistent clock on this platform */
 static bool persistent_clock_exists;
@@ -1521,28 +1548,29 @@ static bool persistent_clock_exists;
  */
 void __init timekeeping_init(void)
 {
+	struct timespec64 wall_time, boot_offset, wall_to_mono;
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct clocksource *clock;
 	unsigned long flags;
-	struct timespec64 now, boot, tmp;
-
-	read_persistent_clock64(&now);
-	if (!timespec64_valid_strict(&now)) {
-		pr_warn("WARNING: Persistent clock returned invalid value!\n"
-			"         Check your CMOS/BIOS settings.\n");
-		now.tv_sec = 0;
-		now.tv_nsec = 0;
-	} else if (now.tv_sec || now.tv_nsec)
-		persistent_clock_exists = true;
 
-	read_boot_clock64(&boot);
-	if (!timespec64_valid_strict(&boot)) {
-		pr_warn("WARNING: Boot clock returned invalid value!\n"
-			"         Check your CMOS/BIOS settings.\n");
-		boot.tv_sec = 0;
-		boot.tv_nsec = 0;
+	read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
+	if (timespec64_valid_strict(&wall_time) &&
+	    timespec64_to_ns(&wall_time) > 0) {
+		persistent_clock_exists = true;
+	} else if (timespec64_to_ns(&wall_time) != 0) {
+		pr_warn("Persistent clock returned invalid value");
+		wall_time = (struct timespec64){0};
 	}
 
+	if (timespec64_compare(&wall_time, &boot_offset) < 0)
+		boot_offset = (struct timespec64){0};
+
+	/*
+	 * We want set wall_to_mono, so the following is true:
+	 * wall time + wall_to_mono = boot time
+	 */
+	wall_to_mono = timespec64_sub(boot_offset, wall_time);
+
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	ntp_init();
@@ -1552,13 +1580,10 @@ void __init timekeeping_init(void)
 		clock->enable(clock);
 	tk_setup_internals(tk, clock);
 
-	tk_set_xtime(tk, &now);
+	tk_set_xtime(tk, &wall_time);
 	tk->raw_sec = 0;
-	if (boot.tv_sec == 0 && boot.tv_nsec == 0)
-		boot = tk_xtime(tk);
 
-	set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
-	tk_set_wall_to_mono(tk, tmp);
+	tk_set_wall_to_mono(tk, wall_to_mono);
 
 	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 
@@ -1577,7 +1602,7 @@ static struct timespec64 timekeeping_suspend_time;
  * adds the sleep offset to the timekeeping variables.
  */
 static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
-					   struct timespec64 *delta)
+					   const struct timespec64 *delta)
 {
 	if (!timespec64_valid_strict(delta)) {
 		printk_deferred(KERN_WARNING
@@ -1610,7 +1635,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
  */
 bool timekeeping_rtc_skipresume(void)
 {
-	return sleeptime_injected;
+	return !suspend_timing_needed;
 }
 
 /**
@@ -1638,7 +1663,7 @@ bool timekeeping_rtc_skipsuspend(void)
  * This function should only be called by rtc_resume(), and allows
  * a suspend offset to be injected into the timekeeping values.
  */
-void timekeeping_inject_sleeptime64(struct timespec64 *delta)
+void timekeeping_inject_sleeptime64(const struct timespec64 *delta)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
@@ -1646,6 +1671,8 @@ void timekeeping_inject_sleeptime64(struct timespec64 *delta)
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 
+	suspend_timing_needed = false;
+
 	timekeeping_forward_now(tk);
 
 	__timekeeping_inject_sleeptime(tk, delta);
@@ -1669,9 +1696,9 @@ void timekeeping_resume(void)
 	struct clocksource *clock = tk->tkr_mono.clock;
 	unsigned long flags;
 	struct timespec64 ts_new, ts_delta;
-	u64 cycle_now;
+	u64 cycle_now, nsec;
+	bool inject_sleeptime = false;
 
-	sleeptime_injected = false;
 	read_persistent_clock64(&ts_new);
 
 	clockevents_resume();
@@ -1693,22 +1720,19 @@ void timekeeping_resume(void)
 	 * usable source. The rtc part is handled separately in rtc core code.
 	 */
 	cycle_now = tk_clock_read(&tk->tkr_mono);
-	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
-		cycle_now > tk->tkr_mono.cycle_last) {
-		u64 nsec, cyc_delta;
-
-		cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last,
-					      tk->tkr_mono.mask);
-		nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift);
+	nsec = clocksource_stop_suspend_timing(clock, cycle_now);
+	if (nsec > 0) {
 		ts_delta = ns_to_timespec64(nsec);
-		sleeptime_injected = true;
+		inject_sleeptime = true;
 	} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
 		ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
-		sleeptime_injected = true;
+		inject_sleeptime = true;
 	}
 
-	if (sleeptime_injected)
+	if (inject_sleeptime) {
+		suspend_timing_needed = false;
 		__timekeeping_inject_sleeptime(tk, &ts_delta);
+	}
 
 	/* Re-base the last cycle value */
 	tk->tkr_mono.cycle_last = cycle_now;
@@ -1732,6 +1756,8 @@ int timekeeping_suspend(void)
 	unsigned long flags;
 	struct timespec64		delta, delta_delta;
 	static struct timespec64	old_delta;
+	struct clocksource *curr_clock;
+	u64 cycle_now;
 
 	read_persistent_clock64(&timekeeping_suspend_time);
 
@@ -1743,11 +1769,22 @@ int timekeeping_suspend(void)
 	if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
 		persistent_clock_exists = true;
 
+	suspend_timing_needed = true;
+
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	timekeeping_forward_now(tk);
 	timekeeping_suspended = 1;
 
+	/*
+	 * Since we've called forward_now, cycle_last stores the value
+	 * just read from the current clocksource. Save this to potentially
+	 * use in suspend timing.
+	 */
+	curr_clock = tk->tkr_mono.clock;
+	cycle_now = tk->tkr_mono.cycle_last;
+	clocksource_start_suspend_timing(curr_clock, cycle_now);
+
 	if (persistent_clock_exists) {
 		/*
 		 * To avoid drift caused by repeated suspend/resumes,
@@ -2021,11 +2058,11 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
 	return offset;
 }
 
-/**
- * update_wall_time - Uses the current clocksource to increment the wall time
- *
+/*
+ * timekeeping_advance - Updates the timekeeper to the current time and
+ * current NTP tick length
  */
-void update_wall_time(void)
+static void timekeeping_advance(enum timekeeping_adv_mode mode)
 {
 	struct timekeeper *real_tk = &tk_core.timekeeper;
 	struct timekeeper *tk = &shadow_timekeeper;
@@ -2042,14 +2079,17 @@ void update_wall_time(void)
 
 #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
 	offset = real_tk->cycle_interval;
+
+	if (mode != TK_ADV_TICK)
+		goto out;
 #else
 	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
 				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
-#endif
 
 	/* Check if there's really nothing to do */
-	if (offset < real_tk->cycle_interval)
+	if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
 		goto out;
+#endif
 
 	/* Do some additional sanity checking */
 	timekeeping_check_update(tk, offset);
@@ -2106,6 +2146,15 @@ out:
 }
 
 /**
+ * update_wall_time - Uses the current clocksource to increment the wall time
+ *
+ */
+void update_wall_time(void)
+{
+	timekeeping_advance(TK_ADV_TICK);
+}
+
+/**
  * getboottime64 - Return the real time of system boot.
  * @ts:		pointer to the timespec64 to be set
  *
@@ -2220,7 +2269,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
 /**
  * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex
  */
-static int timekeeping_validate_timex(struct timex *txc)
+static int timekeeping_validate_timex(const struct timex *txc)
 {
 	if (txc->modes & ADJ_ADJTIME) {
 		/* singleshot must not be used with any other mode bits */
@@ -2310,7 +2359,7 @@ int do_adjtimex(struct timex *txc)
 			return ret;
 	}
 
-	getnstimeofday64(&ts);
+	ktime_get_real_ts64(&ts);
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
@@ -2327,6 +2376,10 @@ int do_adjtimex(struct timex *txc)
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	/* Update the multiplier immediately if frequency was set directly */
+	if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK))
+		timekeeping_advance(TK_ADV_FREQ);
+
 	if (tai != orig_tai)
 		clock_was_set();
 
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 0754cadfa9e6..238e4be60229 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -70,7 +70,7 @@ static int __init tk_debug_sleep_time_init(void)
 }
 late_initcall(tk_debug_sleep_time_init);
 
-void tk_debug_account_sleep_time(struct timespec64 *t)
+void tk_debug_account_sleep_time(const struct timespec64 *t)
 {
 	/* Cap bin index so we don't overflow the array */
 	int bin = min(fls(t->tv_sec), NUM_BINS-1);
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index cf5c0828ee31..bcbb52db2256 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -8,7 +8,7 @@
 #include <linux/time.h>
 
 #ifdef CONFIG_DEBUG_FS
-extern void tk_debug_account_sleep_time(struct timespec64 *t);
+extern void tk_debug_account_sleep_time(const struct timespec64 *t);
 #else
 #define tk_debug_account_sleep_time(x)
 #endif
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index cc2d23e6ff61..fa49cd753dea 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -581,7 +581,7 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 	 * wheel:
 	 */
 	base->next_expiry = timer->expires;
-		wake_up_nohz_cpu(base->cpu);
+	wake_up_nohz_cpu(base->cpu);
 }
 
 static void
@@ -1657,6 +1657,22 @@ static inline void __run_timers(struct timer_base *base)
 
 	raw_spin_lock_irq(&base->lock);
 
+	/*
+	 * timer_base::must_forward_clk must be cleared before running
+	 * timers so that any timer functions that call mod_timer() will
+	 * not try to forward the base. Idle tracking / clock forwarding
+	 * logic is only used with BASE_STD timers.
+	 *
+	 * The must_forward_clk flag is cleared unconditionally also for
+	 * the deferrable base. The deferrable base is not affected by idle
+	 * tracking and never forwarded, so clearing the flag is a NOOP.
+	 *
+	 * The fact that the deferrable base is never forwarded can cause
+	 * large variations in granularity for deferrable timers, but they
+	 * can be deferred for long periods due to idle anyway.
+	 */
+	base->must_forward_clk = false;
+
 	while (time_after_eq(jiffies, base->clk)) {
 
 		levels = collect_expired_timers(base, heads);
@@ -1676,19 +1692,6 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
-	/*
-	 * must_forward_clk must be cleared before running timers so that any
-	 * timer functions that call mod_timer will not try to forward the
-	 * base. idle trcking / clock forwarding logic is only used with
-	 * BASE_STD timers.
-	 *
-	 * The deferrable base does not do idle tracking at all, so we do
-	 * not forward it. This can result in very large variations in
-	 * granularity for deferrable timers, but they can be deferred for
-	 * long periods due to idle.
-	 */
-	base->must_forward_clk = false;
-
 	__run_timers(base);
 	if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
diff --git a/kernel/torture.c b/kernel/torture.c
index 3de1efbecd6a..1ac24a826589 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -20,6 +20,9 @@
  * Author: Paul E. McKenney <paulmck@us.ibm.com>
  *	Based on kernel/rcu/torture.c.
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -53,7 +56,7 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
 
 static char *torture_type;
-static bool verbose;
+static int verbose;
 
 /* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
 #define FULLSTOP_DONTSTOP 0	/* Normal operation. */
@@ -98,7 +101,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 	if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
 		return false;
 
-	if (verbose)
+	if (verbose > 1)
 		pr_alert("%s" TORTURE_FLAG
 			 "torture_onoff task: offlining %d\n",
 			 torture_type, cpu);
@@ -111,7 +114,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 				 "torture_onoff task: offline %d failed: errno %d\n",
 				 torture_type, cpu, ret);
 	} else {
-		if (verbose)
+		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
 				 "torture_onoff task: offlined %d\n",
 				 torture_type, cpu);
@@ -147,7 +150,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 	if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
 		return false;
 
-	if (verbose)
+	if (verbose > 1)
 		pr_alert("%s" TORTURE_FLAG
 			 "torture_onoff task: onlining %d\n",
 			 torture_type, cpu);
@@ -160,7 +163,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 				 "torture_onoff task: online %d failed: errno %d\n",
 				 torture_type, cpu, ret);
 	} else {
-		if (verbose)
+		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
 				 "torture_onoff task: onlined %d\n",
 				 torture_type, cpu);
@@ -647,7 +650,7 @@ static void torture_stutter_cleanup(void)
  * The runnable parameter points to a flag that controls whether or not
  * the test is currently runnable.  If there is no such flag, pass in NULL.
  */
-bool torture_init_begin(char *ttype, bool v)
+bool torture_init_begin(char *ttype, int v)
 {
 	mutex_lock(&fullstop_mutex);
 	if (torture_type != NULL) {
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 987d9a9ae283..b951aa1fac61 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -494,6 +494,9 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
+	if (!blk_debugfs_root)
+		return -ENOENT;
+
 	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
 	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
 
@@ -518,9 +521,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = -ENOENT;
 
-	if (!blk_debugfs_root)
-		goto err;
-
 	dir = debugfs_lookup(buts->name, blk_debugfs_root);
 	if (!dir)
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 6b71860f3998..e9d99463e5df 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1228,16 +1228,11 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 
 		/*
 		 * We need to check and see if we modified the pc of the
-		 * pt_regs, and if so clear the kprobe and return 1 so that we
-		 * don't do the single stepping.
-		 * The ftrace kprobe handler leaves it up to us to re-enable
-		 * preemption here before returning if we've modified the ip.
+		 * pt_regs, and if so return 1 so that we don't do the
+		 * single stepping.
 		 */
-		if (orig_ip != instruction_pointer(regs)) {
-			reset_current_kprobe();
-			preempt_enable_no_resched();
+		if (orig_ip != instruction_pointer(regs))
 			return 1;
-		}
 		if (!ret)
 			return 0;
 	}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 576d18045811..5470dce212c0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -18,18 +18,14 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/sysctl.h>
-#include <linux/smpboot.h>
-#include <linux/sched/rt.h>
-#include <uapi/linux/sched/types.h>
 #include <linux/tick.h>
-#include <linux/workqueue.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/isolation.h>
+#include <linux/stop_machine.h>
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
-#include <linux/kthread.h>
 
 static DEFINE_MUTEX(watchdog_mutex);
 
@@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void)
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 
-static bool softlockup_threads_initialized __read_mostly;
+static bool softlockup_initialized __read_mostly;
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
-static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
 static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
 static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
@@ -335,6 +330,27 @@ static void watchdog_interrupt_count(void)
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
+static DEFINE_PER_CPU(struct completion, softlockup_completion);
+static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
+
+/*
+ * The watchdog thread function - touches the timestamp.
+ *
+ * It only runs once every sample_period seconds (4 seconds by
+ * default) to reset the softlockup timestamp. If this gets delayed
+ * for more than 2*watchdog_thresh seconds then the debug-printout
+ * triggers in watchdog_timer_fn().
+ */
+static int softlockup_fn(void *data)
+{
+	__this_cpu_write(soft_lockup_hrtimer_cnt,
+			 __this_cpu_read(hrtimer_interrupts));
+	__touch_watchdog();
+	complete(this_cpu_ptr(&softlockup_completion));
+
+	return 0;
+}
+
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -350,7 +366,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	watchdog_interrupt_count();
 
 	/* kick the softlockup detector */
-	wake_up_process(__this_cpu_read(softlockup_watchdog));
+	if (completion_done(this_cpu_ptr(&softlockup_completion))) {
+		reinit_completion(this_cpu_ptr(&softlockup_completion));
+		stop_one_cpu_nowait(smp_processor_id(),
+				softlockup_fn, NULL,
+				this_cpu_ptr(&softlockup_stop_work));
+	}
 
 	/* .. and repeat */
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
@@ -448,16 +469,15 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static void watchdog_set_prio(unsigned int policy, unsigned int prio)
-{
-	struct sched_param param = { .sched_priority = prio };
-
-	sched_setscheduler(current, policy, &param);
-}
-
 static void watchdog_enable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
+	struct completion *done = this_cpu_ptr(&softlockup_completion);
+
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
+	init_completion(done);
+	complete(done);
 
 	/*
 	 * Start the timer first to prevent the NMI watchdog triggering
@@ -473,15 +493,14 @@ static void watchdog_enable(unsigned int cpu)
 	/* Enable the perf event */
 	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
 		watchdog_nmi_enable(cpu);
-
-	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
 }
 
 static void watchdog_disable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
-	watchdog_set_prio(SCHED_NORMAL, 0);
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
 	/*
 	 * Disable the perf event first. That prevents that a large delay
 	 * between disabling the timer and disabling the perf event causes
@@ -489,79 +508,66 @@ static void watchdog_disable(unsigned int cpu)
 	 */
 	watchdog_nmi_disable(cpu);
 	hrtimer_cancel(hrtimer);
+	wait_for_completion(this_cpu_ptr(&softlockup_completion));
 }
 
-static void watchdog_cleanup(unsigned int cpu, bool online)
+static int softlockup_stop_fn(void *data)
 {
-	watchdog_disable(cpu);
+	watchdog_disable(smp_processor_id());
+	return 0;
 }
 
-static int watchdog_should_run(unsigned int cpu)
+static void softlockup_stop_all(void)
 {
-	return __this_cpu_read(hrtimer_interrupts) !=
-		__this_cpu_read(soft_lockup_hrtimer_cnt);
+	int cpu;
+
+	if (!softlockup_initialized)
+		return;
+
+	for_each_cpu(cpu, &watchdog_allowed_mask)
+		smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false);
+
+	cpumask_clear(&watchdog_allowed_mask);
 }
 
-/*
- * The watchdog thread function - touches the timestamp.
- *
- * It only runs once every sample_period seconds (4 seconds by
- * default) to reset the softlockup timestamp. If this gets delayed
- * for more than 2*watchdog_thresh seconds then the debug-printout
- * triggers in watchdog_timer_fn().
- */
-static void watchdog(unsigned int cpu)
+static int softlockup_start_fn(void *data)
 {
-	__this_cpu_write(soft_lockup_hrtimer_cnt,
-			 __this_cpu_read(hrtimer_interrupts));
-	__touch_watchdog();
+	watchdog_enable(smp_processor_id());
+	return 0;
 }
 
-static struct smp_hotplug_thread watchdog_threads = {
-	.store			= &softlockup_watchdog,
-	.thread_should_run	= watchdog_should_run,
-	.thread_fn		= watchdog,
-	.thread_comm		= "watchdog/%u",
-	.setup			= watchdog_enable,
-	.cleanup		= watchdog_cleanup,
-	.park			= watchdog_disable,
-	.unpark			= watchdog_enable,
-};
-
-static void softlockup_update_smpboot_threads(void)
+static void softlockup_start_all(void)
 {
-	lockdep_assert_held(&watchdog_mutex);
-
-	if (!softlockup_threads_initialized)
-		return;
+	int cpu;
 
-	smpboot_update_cpumask_percpu_thread(&watchdog_threads,
-					     &watchdog_allowed_mask);
+	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+	for_each_cpu(cpu, &watchdog_allowed_mask)
+		smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false);
 }
 
-/* Temporarily park all watchdog threads */
-static void softlockup_park_all_threads(void)
+int lockup_detector_online_cpu(unsigned int cpu)
 {
-	cpumask_clear(&watchdog_allowed_mask);
-	softlockup_update_smpboot_threads();
+	watchdog_enable(cpu);
+	return 0;
 }
 
-/* Unpark enabled threads */
-static void softlockup_unpark_threads(void)
+int lockup_detector_offline_cpu(unsigned int cpu)
 {
-	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
-	softlockup_update_smpboot_threads();
+	watchdog_disable(cpu);
+	return 0;
 }
 
 static void lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
 	watchdog_nmi_stop();
-	softlockup_park_all_threads();
+
+	softlockup_stop_all();
 	set_sample_period();
 	lockup_detector_update_enable();
 	if (watchdog_enabled && watchdog_thresh)
-		softlockup_unpark_threads();
+		softlockup_start_all();
+
 	watchdog_nmi_start();
 	cpus_read_unlock();
 	/*
@@ -580,8 +586,6 @@ static void lockup_detector_reconfigure(void)
  */
 static __init void lockup_detector_setup(void)
 {
-	int ret;
-
 	/*
 	 * If sysctl is off and watchdog got disabled on the command line,
 	 * nothing to do here.
@@ -592,24 +596,13 @@ static __init void lockup_detector_setup(void)
 	    !(watchdog_enabled && watchdog_thresh))
 		return;
 
-	ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
-						     &watchdog_allowed_mask);
-	if (ret) {
-		pr_err("Failed to initialize soft lockup detector threads\n");
-		return;
-	}
-
 	mutex_lock(&watchdog_mutex);
-	softlockup_threads_initialized = true;
 	lockup_detector_reconfigure();
+	softlockup_initialized = true;
 	mutex_unlock(&watchdog_mutex);
 }
 
 #else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static inline int watchdog_park_threads(void) { return 0; }
-static inline void watchdog_unpark_threads(void) { }
-static inline int watchdog_enable_all_cpus(void) { return 0; }
-static inline void watchdog_disable_all_cpus(void) { }
 static void lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index e449a23e9d59..1f7020d65d0a 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -175,8 +175,8 @@ static int hardlockup_detector_event_create(void)
 	evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
 					       watchdog_overflow_callback, NULL);
 	if (IS_ERR(evt)) {
-		pr_info("Perf event create on CPU %d failed with %ld\n", cpu,
-			PTR_ERR(evt));
+		pr_debug("Perf event create on CPU %d failed with %ld\n", cpu,
+			 PTR_ERR(evt));
 		return PTR_ERR(evt);
 	}
 	this_cpu_write(watchdog_ev, evt);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8838d1158d19..0b066b3c9284 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1718,7 +1718,7 @@ config KPROBES_SANITY_TEST
 	default n
 	help
 	  This option provides for testing basic kprobes functionality on
-	  boot. A sample kprobe, jprobe and kretprobe are inserted and
+	  boot. Samples of kprobe and kretprobe are inserted and
 	  verified for functionality.
 
 	  Say N if you are unsure.
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index 19d42ea75ec2..98fa559ebd80 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -1,9 +1,6 @@
 config ARCH_HAS_UBSAN_SANITIZE_ALL
 	bool
 
-config ARCH_WANTS_UBSAN_NO_NULL
-	def_bool n
-
 config UBSAN
 	bool "Undefined behaviour sanity checker"
 	help
@@ -39,14 +36,6 @@ config UBSAN_ALIGNMENT
 	  Enabling this option on architectures that support unaligned
 	  accesses may produce a lot of false positives.
 
-config UBSAN_NULL
-	bool "Enable checking of null pointers"
-	depends on UBSAN
-	default y if !ARCH_WANTS_UBSAN_NO_NULL
-	help
-	  This option enables detection of memory accesses via a
-	  null pointer.
-
 config TEST_UBSAN
 	tristate "Module for testing for undefined behavior detection"
 	depends on m && UBSAN
diff --git a/lib/Makefile b/lib/Makefile
index 90dc5520b784..d4a3773ce4a6 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -116,6 +116,7 @@ obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
 obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
 obj-$(CONFIG_BCH) += bch.o
+CFLAGS_bch.o := $(call cc-option,-Wframe-larger-than=4500)
 obj-$(CONFIG_LZO_COMPRESS) += lzo/
 obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
 obj-$(CONFIG_LZ4_COMPRESS) += lz4/
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 53c2d5edc826..1d91e31eceec 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -178,18 +178,18 @@ long long atomic64_xchg(atomic64_t *v, long long new)
 }
 EXPORT_SYMBOL(atomic64_xchg);
 
-int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	int ret = 0;
+	long long val;
 
 	raw_spin_lock_irqsave(lock, flags);
-	if (v->counter != u) {
+	val = v->counter;
+	if (val != u)
 		v->counter += a;
-		ret = 1;
-	}
 	raw_spin_unlock_irqrestore(lock, flags);
-	return ret;
+
+	return val;
 }
-EXPORT_SYMBOL(atomic64_add_unless);
+EXPORT_SYMBOL(atomic64_fetch_add_unless);
diff --git a/lib/bch.c b/lib/bch.c
index bc89dfe4d1b3..7b0f2006698b 100644
--- a/lib/bch.c
+++ b/lib/bch.c
@@ -78,15 +78,22 @@
 #define GF_M(_p)               (CONFIG_BCH_CONST_M)
 #define GF_T(_p)               (CONFIG_BCH_CONST_T)
 #define GF_N(_p)               ((1 << (CONFIG_BCH_CONST_M))-1)
+#define BCH_MAX_M              (CONFIG_BCH_CONST_M)
 #else
 #define GF_M(_p)               ((_p)->m)
 #define GF_T(_p)               ((_p)->t)
 #define GF_N(_p)               ((_p)->n)
+#define BCH_MAX_M              15
 #endif
 
+#define BCH_MAX_T              (((1 << BCH_MAX_M) - 1) / BCH_MAX_M)
+
 #define BCH_ECC_WORDS(_p)      DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 32)
 #define BCH_ECC_BYTES(_p)      DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 8)
 
+#define BCH_ECC_MAX_WORDS      DIV_ROUND_UP(BCH_MAX_M * BCH_MAX_T, 32)
+#define BCH_ECC_MAX_BYTES      DIV_ROUND_UP(BCH_MAX_M * BCH_MAX_T, 8)
+
 #ifndef dbg
 #define dbg(_fmt, args...)     do {} while (0)
 #endif
@@ -187,7 +194,8 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	const unsigned int l = BCH_ECC_WORDS(bch)-1;
 	unsigned int i, mlen;
 	unsigned long m;
-	uint32_t w, r[l+1];
+	uint32_t w, r[BCH_ECC_MAX_WORDS];
+	const size_t r_bytes = BCH_ECC_WORDS(bch) * sizeof(*r);
 	const uint32_t * const tab0 = bch->mod8_tab;
 	const uint32_t * const tab1 = tab0 + 256*(l+1);
 	const uint32_t * const tab2 = tab1 + 256*(l+1);
@@ -198,7 +206,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 		/* load ecc parity bytes into internal 32-bit buffer */
 		load_ecc8(bch, bch->ecc_buf, ecc);
 	} else {
-		memset(bch->ecc_buf, 0, sizeof(r));
+		memset(bch->ecc_buf, 0, r_bytes);
 	}
 
 	/* process first unaligned data bytes */
@@ -215,7 +223,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	mlen  = len/4;
 	data += 4*mlen;
 	len  -= 4*mlen;
-	memcpy(r, bch->ecc_buf, sizeof(r));
+	memcpy(r, bch->ecc_buf, r_bytes);
 
 	/*
 	 * split each 32-bit word into 4 polynomials of weight 8 as follows:
@@ -241,7 +249,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 
 		r[l] = p0[l]^p1[l]^p2[l]^p3[l];
 	}
-	memcpy(bch->ecc_buf, r, sizeof(r));
+	memcpy(bch->ecc_buf, r, r_bytes);
 
 	/* process last unaligned bytes */
 	if (len)
@@ -434,7 +442,7 @@ static int solve_linear_system(struct bch_control *bch, unsigned int *rows,
 {
 	const int m = GF_M(bch);
 	unsigned int tmp, mask;
-	int rem, c, r, p, k, param[m];
+	int rem, c, r, p, k, param[BCH_MAX_M];
 
 	k = 0;
 	mask = 1 << m;
@@ -1114,7 +1122,7 @@ static int build_deg2_base(struct bch_control *bch)
 {
 	const int m = GF_M(bch);
 	int i, j, r;
-	unsigned int sum, x, y, remaining, ak = 0, xi[m];
+	unsigned int sum, x, y, remaining, ak = 0, xi[BCH_MAX_M];
 
 	/* find k s.t. Tr(a^k) = 1 and 0 <= k < m */
 	for (i = 0; i < m; i++) {
@@ -1254,7 +1262,6 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 	struct bch_control *bch = NULL;
 
 	const int min_m = 5;
-	const int max_m = 15;
 
 	/* default primitive polynomials */
 	static const unsigned int prim_poly_tab[] = {
@@ -1270,7 +1277,7 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 		goto fail;
 	}
 #endif
-	if ((m < min_m) || (m > max_m))
+	if ((m < min_m) || (m > BCH_MAX_M))
 		/*
 		 * values of m greater than 15 are not currently supported;
 		 * supporting m > 15 would require changing table base type
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 994be4805cec..70935ed91125 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -360,9 +360,12 @@ static void debug_object_is_on_stack(void *addr, int onstack)
 
 	limit++;
 	if (is_on_stack)
-		pr_warn("object is on stack, but not annotated\n");
+		pr_warn("object %p is on stack %p, but NOT annotated.\n", addr,
+			 task_stack_page(current));
 	else
-		pr_warn("object is not on stack, but annotated\n");
+		pr_warn("object %p is NOT on stack %p, but annotated.\n", addr,
+			 task_stack_page(current));
+
 	WARN_ON(1);
 }
 
@@ -1185,8 +1188,7 @@ void __init debug_objects_mem_init(void)
 
 	if (!obj_cache || debug_objects_replace_static_objects()) {
 		debug_objects_enabled = 0;
-		if (obj_cache)
-			kmem_cache_destroy(obj_cache);
+		kmem_cache_destroy(obj_cache);
 		pr_warn("out of memory.\n");
 	} else
 		debug_objects_selftest();
diff --git a/lib/ioremap.c b/lib/ioremap.c
index 54e5bbaa3200..517f5853ffed 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -92,7 +92,7 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
 		if (ioremap_pmd_enabled() &&
 		    ((next - addr) == PMD_SIZE) &&
 		    IS_ALIGNED(phys_addr + addr, PMD_SIZE) &&
-		    pmd_free_pte_page(pmd)) {
+		    pmd_free_pte_page(pmd, addr)) {
 			if (pmd_set_huge(pmd, phys_addr + addr, prot))
 				continue;
 		}
@@ -119,7 +119,7 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 		if (ioremap_pud_enabled() &&
 		    ((next - addr) == PUD_SIZE) &&
 		    IS_ALIGNED(phys_addr + addr, PUD_SIZE) &&
-		    pud_free_pmd_page(pud)) {
+		    pud_free_pmd_page(pud, addr)) {
 			if (pud_set_huge(pud, phys_addr + addr, prot))
 				continue;
 		}
diff --git a/lib/raid6/s390vx.uc b/lib/raid6/s390vx.uc
index 140fa8bb5c23..914ebe98fc21 100644
--- a/lib/raid6/s390vx.uc
+++ b/lib/raid6/s390vx.uc
@@ -55,22 +55,24 @@ static inline void XOR(int x, int y, int z)
 	asm volatile ("VX %0,%1,%2" : : "i" (x), "i" (y), "i" (z));
 }
 
-static inline void LOAD_DATA(int x, int n, u8 *ptr)
+static inline void LOAD_DATA(int x, u8 *ptr)
 {
-	typedef struct { u8 _[16*n]; } addrtype;
+	typedef struct { u8 _[16 * $#]; } addrtype;
 	register addrtype *__ptr asm("1") = (addrtype *) ptr;
 
 	asm volatile ("VLM %2,%3,0,%r1"
-		      : : "m" (*__ptr), "a" (__ptr), "i" (x), "i" (x + n - 1));
+		      : : "m" (*__ptr), "a" (__ptr), "i" (x),
+			  "i" (x + $# - 1));
 }
 
-static inline void STORE_DATA(int x, int n, u8 *ptr)
+static inline void STORE_DATA(int x, u8 *ptr)
 {
-	typedef struct { u8 _[16*n]; } addrtype;
+	typedef struct { u8 _[16 * $#]; } addrtype;
 	register addrtype *__ptr asm("1") = (addrtype *) ptr;
 
 	asm volatile ("VSTM %2,%3,0,1"
-		      : "=m" (*__ptr) : "a" (__ptr), "i" (x), "i" (x + n - 1));
+		      : "=m" (*__ptr) : "a" (__ptr), "i" (x),
+			"i" (x + $# - 1));
 }
 
 static inline void COPY_VEC(int x, int y)
@@ -93,19 +95,19 @@ static void raid6_s390vx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
 	q = dptr[z0 + 2];	/* RS syndrome */
 
 	for (d = 0; d < bytes; d += $#*NSIZE) {
-		LOAD_DATA(0,$#,&dptr[z0][d]);
+		LOAD_DATA(0,&dptr[z0][d]);
 		COPY_VEC(8+$$,0+$$);
 		for (z = z0 - 1; z >= 0; z--) {
 			MASK(16+$$,8+$$);
 			AND(16+$$,16+$$,25);
 			SHLBYTE(8+$$,8+$$);
 			XOR(8+$$,8+$$,16+$$);
-			LOAD_DATA(16,$#,&dptr[z][d]);
+			LOAD_DATA(16,&dptr[z][d]);
 			XOR(0+$$,0+$$,16+$$);
 			XOR(8+$$,8+$$,16+$$);
 		}
-		STORE_DATA(0,$#,&p[d]);
-		STORE_DATA(8,$#,&q[d]);
+		STORE_DATA(0,&p[d]);
+		STORE_DATA(8,&q[d]);
 	}
 	kernel_fpu_end(&vxstate, KERNEL_VXR);
 }
@@ -127,14 +129,14 @@ static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop,
 
 	for (d = 0; d < bytes; d += $#*NSIZE) {
 		/* P/Q data pages */
-		LOAD_DATA(0,$#,&dptr[z0][d]);
+		LOAD_DATA(0,&dptr[z0][d]);
 		COPY_VEC(8+$$,0+$$);
 		for (z = z0 - 1; z >= start; z--) {
 			MASK(16+$$,8+$$);
 			AND(16+$$,16+$$,25);
 			SHLBYTE(8+$$,8+$$);
 			XOR(8+$$,8+$$,16+$$);
-			LOAD_DATA(16,$#,&dptr[z][d]);
+			LOAD_DATA(16,&dptr[z][d]);
 			XOR(0+$$,0+$$,16+$$);
 			XOR(8+$$,8+$$,16+$$);
 		}
@@ -145,12 +147,12 @@ static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop,
 			SHLBYTE(8+$$,8+$$);
 			XOR(8+$$,8+$$,16+$$);
 		}
-		LOAD_DATA(16,$#,&p[d]);
+		LOAD_DATA(16,&p[d]);
 		XOR(16+$$,16+$$,0+$$);
-		STORE_DATA(16,$#,&p[d]);
-		LOAD_DATA(16,$#,&q[d]);
+		STORE_DATA(16,&p[d]);
+		LOAD_DATA(16,&q[d]);
 		XOR(16+$$,16+$$,8+$$);
-		STORE_DATA(16,$#,&q[d]);
+		STORE_DATA(16,&q[d]);
 	}
 	kernel_fpu_end(&vxstate, KERNEL_VXR);
 }
diff --git a/lib/refcount.c b/lib/refcount.c
index d3b81cefce91..ebcf8cd49e05 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -35,13 +35,13 @@
  *
  */
 
+#include <linux/mutex.h>
 #include <linux/refcount.h>
+#include <linux/spinlock.h>
 #include <linux/bug.h>
 
-#ifdef CONFIG_REFCOUNT_FULL
-
 /**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * refcount_add_not_zero_checked - add a value to a refcount unless it is 0
  * @i: the value to add to the refcount
  * @r: the refcount
  *
@@ -58,7 +58,7 @@
  *
  * Return: false if the passed refcount is 0, true otherwise
  */
-bool refcount_add_not_zero(unsigned int i, refcount_t *r)
+bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -79,10 +79,10 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 
 	return true;
 }
-EXPORT_SYMBOL(refcount_add_not_zero);
+EXPORT_SYMBOL(refcount_add_not_zero_checked);
 
 /**
- * refcount_add - add a value to a refcount
+ * refcount_add_checked - add a value to a refcount
  * @i: the value to add to the refcount
  * @r: the refcount
  *
@@ -97,14 +97,14 @@ EXPORT_SYMBOL(refcount_add_not_zero);
  * cases, refcount_inc(), or one of its variants, should instead be used to
  * increment a reference count.
  */
-void refcount_add(unsigned int i, refcount_t *r)
+void refcount_add_checked(unsigned int i, refcount_t *r)
 {
-	WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n");
 }
-EXPORT_SYMBOL(refcount_add);
+EXPORT_SYMBOL(refcount_add_checked);
 
 /**
- * refcount_inc_not_zero - increment a refcount unless it is 0
+ * refcount_inc_not_zero_checked - increment a refcount unless it is 0
  * @r: the refcount to increment
  *
  * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN.
@@ -115,7 +115,7 @@ EXPORT_SYMBOL(refcount_add);
  *
  * Return: true if the increment was successful, false otherwise
  */
-bool refcount_inc_not_zero(refcount_t *r)
+bool refcount_inc_not_zero_checked(refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -134,10 +134,10 @@ bool refcount_inc_not_zero(refcount_t *r)
 
 	return true;
 }
-EXPORT_SYMBOL(refcount_inc_not_zero);
+EXPORT_SYMBOL(refcount_inc_not_zero_checked);
 
 /**
- * refcount_inc - increment a refcount
+ * refcount_inc_checked - increment a refcount
  * @r: the refcount to increment
  *
  * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN.
@@ -148,14 +148,14 @@ EXPORT_SYMBOL(refcount_inc_not_zero);
  * Will WARN if the refcount is 0, as this represents a possible use-after-free
  * condition.
  */
-void refcount_inc(refcount_t *r)
+void refcount_inc_checked(refcount_t *r)
 {
-	WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n");
 }
-EXPORT_SYMBOL(refcount_inc);
+EXPORT_SYMBOL(refcount_inc_checked);
 
 /**
- * refcount_sub_and_test - subtract from a refcount and test if it is 0
+ * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0
  * @i: amount to subtract from the refcount
  * @r: the refcount
  *
@@ -174,7 +174,7 @@ EXPORT_SYMBOL(refcount_inc);
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -192,10 +192,10 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 
 	return !new;
 }
-EXPORT_SYMBOL(refcount_sub_and_test);
+EXPORT_SYMBOL(refcount_sub_and_test_checked);
 
 /**
- * refcount_dec_and_test - decrement a refcount and test if it is 0
+ * refcount_dec_and_test_checked - decrement a refcount and test if it is 0
  * @r: the refcount
  *
  * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
@@ -207,14 +207,14 @@ EXPORT_SYMBOL(refcount_sub_and_test);
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-bool refcount_dec_and_test(refcount_t *r)
+bool refcount_dec_and_test_checked(refcount_t *r)
 {
-	return refcount_sub_and_test(1, r);
+	return refcount_sub_and_test_checked(1, r);
 }
-EXPORT_SYMBOL(refcount_dec_and_test);
+EXPORT_SYMBOL(refcount_dec_and_test_checked);
 
 /**
- * refcount_dec - decrement a refcount
+ * refcount_dec_checked - decrement a refcount
  * @r: the refcount
  *
  * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
@@ -223,12 +223,11 @@ EXPORT_SYMBOL(refcount_dec_and_test);
  * Provides release memory ordering, such that prior loads and stores are done
  * before.
  */
-void refcount_dec(refcount_t *r)
+void refcount_dec_checked(refcount_t *r)
 {
-	WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+	WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n");
 }
-EXPORT_SYMBOL(refcount_dec);
-#endif /* CONFIG_REFCOUNT_FULL */
+EXPORT_SYMBOL(refcount_dec_checked);
 
 /**
  * refcount_dec_if_one - decrement a refcount if it is 1
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 25346bd99364..a9e1e093df51 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -552,7 +552,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) {
+	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1142,7 +1142,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd,
 		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, vma,
 					       vmf->address, page_to_nid(page));
 		if (unlikely(!pages[i] ||
-			     mem_cgroup_try_charge(pages[i], vma->vm_mm,
+			     mem_cgroup_try_charge_delay(pages[i], vma->vm_mm,
 				     GFP_KERNEL, &memcg, false))) {
 			if (pages[i])
 				put_page(pages[i]);
@@ -1312,7 +1312,7 @@ alloc:
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
+	if (unlikely(mem_cgroup_try_charge_delay(new_page, vma->vm_mm,
 					huge_gfp, &memcg, true))) {
 		put_page(new_page);
 		split_huge_pmd(vma, vmf->pmd, vmf->address);
diff --git a/mm/init-mm.c b/mm/init-mm.c
index f0179c9c04c2..a787a319211e 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -15,6 +15,16 @@
 #define INIT_MM_CONTEXT(name)
 #endif
 
+/*
+ * For dynamically allocated mm_structs, there is a dynamically sized cpumask
+ * at the end of the structure, the size of which depends on the maximum CPU
+ * number the system can see. That way we allocate only as much memory for
+ * mm_cpumask() as needed for the hundreds, or thousands of processes that
+ * a system typically runs.
+ *
+ * Since there is only one init_mm in the entire system, keep it simple
+ * and size this cpu_bitmask to NR_CPUS.
+ */
 struct mm_struct init_mm = {
 	.mm_rb		= RB_ROOT,
 	.pgd		= swapper_pg_dir,
@@ -25,5 +35,6 @@ struct mm_struct init_mm = {
 	.arg_lock	=  __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
 	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
 	.user_ns	= &init_user_ns,
+	.cpu_bitmap	= { [BITS_TO_LONGS(NR_CPUS)] = 0},
 	INIT_MM_CONTEXT(init_mm)
 };
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b2173f7e5164..b836e7f00309 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5600,6 +5600,19 @@ out:
 	return ret;
 }
 
+int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
+			  bool compound)
+{
+	struct mem_cgroup *memcg;
+	int ret;
+
+	ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp, compound);
+	memcg = *memcgp;
+	mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask);
+	return ret;
+}
+
 /**
  * mem_cgroup_commit_charge - commit a page charge
  * @page: page to charge
diff --git a/mm/memfd.c b/mm/memfd.c
index 27069518e3c5..2bb5e257080e 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -326,7 +326,7 @@ SYSCALL_DEFINE2(memfd_create,
 		goto err_fd;
 	}
 	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
-	file->f_flags |= O_RDWR | O_LARGEFILE;
+	file->f_flags |= O_LARGEFILE;
 
 	if (flags & MFD_ALLOW_SEALING) {
 		file_seals = memfd_file_seals_ptr(file);
diff --git a/mm/memory.c b/mm/memory.c
index dab1511294ad..348279ff6e51 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -326,16 +326,20 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 
-/*
- * See the comment near struct mmu_table_batch.
- */
-
 static void tlb_remove_table_smp_sync(void *arg)
 {
-	/* Simply deliver the interrupt */
+	struct mm_struct __maybe_unused *mm = arg;
+	/*
+	 * On most architectures this does nothing. Simply delivering the
+	 * interrupt is enough to prevent races with software page table
+	 * walking like that done in get_user_pages_fast.
+	 *
+	 * See the comment near struct mmu_table_batch.
+	 */
+	tlb_flush_remove_tables_local(mm);
 }
 
-static void tlb_remove_table_one(void *table)
+static void tlb_remove_table_one(void *table, struct mmu_gather *tlb)
 {
 	/*
 	 * This isn't an RCU grace period and hence the page-tables cannot be
@@ -344,7 +348,7 @@ static void tlb_remove_table_one(void *table)
 	 * It is however sufficient for software page-table walkers that rely on
 	 * IRQ disabling. See the comment near struct mmu_table_batch.
 	 */
-	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+	smp_call_function(tlb_remove_table_smp_sync, tlb->mm, 1);
 	__tlb_remove_table(table);
 }
 
@@ -365,6 +369,8 @@ void tlb_table_flush(struct mmu_gather *tlb)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
+	tlb_flush_remove_tables(tlb->mm);
+
 	if (*batch) {
 		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
 		*batch = NULL;
@@ -387,7 +393,7 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 	if (*batch == NULL) {
 		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
 		if (*batch == NULL) {
-			tlb_remove_table_one(table);
+			tlb_remove_table_one(table, tlb);
 			return;
 		}
 		(*batch)->nr = 0;
@@ -1884,6 +1890,9 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
 
+	if (!pfn_modify_allowed(pfn, pgprot))
+		return -EACCES;
+
 	track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
 
 	ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
@@ -1919,6 +1928,9 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
+	if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
+		return -EACCES;
+
 	/*
 	 * If we don't have pte special, then we have to use the pfn_valid()
 	 * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
@@ -1980,6 +1992,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 {
 	pte_t *pte;
 	spinlock_t *ptl;
+	int err = 0;
 
 	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
@@ -1987,12 +2000,16 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	arch_enter_lazy_mmu_mode();
 	do {
 		BUG_ON(!pte_none(*pte));
+		if (!pfn_modify_allowed(pfn, prot)) {
+			err = -EACCES;
+			break;
+		}
 		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
-	return 0;
+	return err;
 }
 
 static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
@@ -2001,6 +2018,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 {
 	pmd_t *pmd;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pmd = pmd_alloc(mm, pud, addr);
@@ -2009,9 +2027,10 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 	VM_BUG_ON(pmd_trans_huge(*pmd));
 	do {
 		next = pmd_addr_end(addr, end);
-		if (remap_pte_range(mm, pmd, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pte_range(mm, pmd, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pmd++, addr = next, addr != end);
 	return 0;
 }
@@ -2022,6 +2041,7 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 {
 	pud_t *pud;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pud = pud_alloc(mm, p4d, addr);
@@ -2029,9 +2049,10 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 		return -ENOMEM;
 	do {
 		next = pud_addr_end(addr, end);
-		if (remap_pmd_range(mm, pud, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pmd_range(mm, pud, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pud++, addr = next, addr != end);
 	return 0;
 }
@@ -2042,6 +2063,7 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 {
 	p4d_t *p4d;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	p4d = p4d_alloc(mm, pgd, addr);
@@ -2049,9 +2071,10 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 		return -ENOMEM;
 	do {
 		next = p4d_addr_end(addr, end);
-		if (remap_pud_range(mm, p4d, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pud_range(mm, p4d, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (p4d++, addr = next, addr != end);
 	return 0;
 }
@@ -2501,7 +2524,7 @@ static int wp_page_copy(struct vm_fault *vmf)
 		cow_user_page(new_page, old_page, vmf->address, vma);
 	}
 
-	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false))
+	if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))
 		goto oom_free_new;
 
 	__SetPageUptodate(new_page);
@@ -3001,8 +3024,8 @@ int do_swap_page(struct vm_fault *vmf)
 		goto out_page;
 	}
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL,
-				&memcg, false)) {
+	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL,
+					&memcg, false)) {
 		ret = VM_FAULT_OOM;
 		goto out_page;
 	}
@@ -3163,7 +3186,8 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	if (!page)
 		goto oom;
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false))
+	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg,
+					false))
 		goto oom_free_page;
 
 	/*
@@ -3659,7 +3683,7 @@ static int do_cow_fault(struct vm_fault *vmf)
 	if (!vmf->cow_page)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_try_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL,
+	if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, GFP_KERNEL,
 				&vmf->memcg, false)) {
 		put_page(vmf->cow_page);
 		return VM_FAULT_OOM;
@@ -4395,6 +4419,9 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 		return -EINVAL;
 
 	maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
+	if (!maddr)
+		return -ENOMEM;
+
 	if (write)
 		memcpy_toio(maddr + offset, buf, len);
 	else
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 625608bc8962..6d331620b9e5 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -306,6 +306,42 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 	return pages;
 }
 
+static int prot_none_pte_entry(pte_t *pte, unsigned long addr,
+			       unsigned long next, struct mm_walk *walk)
+{
+	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask,
+				   unsigned long addr, unsigned long next,
+				   struct mm_walk *walk)
+{
+	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+static int prot_none_test(unsigned long addr, unsigned long next,
+			  struct mm_walk *walk)
+{
+	return 0;
+}
+
+static int prot_none_walk(struct vm_area_struct *vma, unsigned long start,
+			   unsigned long end, unsigned long newflags)
+{
+	pgprot_t new_pgprot = vm_get_page_prot(newflags);
+	struct mm_walk prot_none_walk = {
+		.pte_entry = prot_none_pte_entry,
+		.hugetlb_entry = prot_none_hugetlb_entry,
+		.test_walk = prot_none_test,
+		.mm = current->mm,
+		.private = &new_pgprot,
+	};
+
+	return walk_page_range(start, end, &prot_none_walk);
+}
+
 int
 mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	unsigned long start, unsigned long end, unsigned long newflags)
@@ -324,6 +360,19 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	}
 
 	/*
+	 * Do PROT_NONE PFN permission checks here when we can still
+	 * bail out without undoing a lot of state. This is a rather
+	 * uncommon case, so doesn't need to be very optimized.
+	 */
+	if (arch_has_pfn_modify_check() &&
+	    (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
+	    (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) {
+		error = prot_none_walk(vma, start, end, newflags);
+		if (error)
+			return error;
+	}
+
+	/*
 	 * If we make a private mapping writable we increase our commit;
 	 * but (without finer accounting) cannot reduce our commit if we
 	 * make it unwritable again. hugetlb mapping were accounted for
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a790ef4be74e..3222193c46c6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6939,9 +6939,21 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
 	start = (void *)PAGE_ALIGN((unsigned long)start);
 	end = (void *)((unsigned long)end & PAGE_MASK);
 	for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
+		struct page *page = virt_to_page(pos);
+		void *direct_map_addr;
+
+		/*
+		 * 'direct_map_addr' might be different from 'pos'
+		 * because some architectures' virt_to_page()
+		 * work with aliases.  Getting the direct map
+		 * address ensures that we get a _writeable_
+		 * alias for the memset().
+		 */
+		direct_map_addr = page_address(page);
 		if ((unsigned int)poison <= 0xFF)
-			memset(pos, poison, PAGE_SIZE);
-		free_reserved_page(virt_to_page(pos));
+			memset(direct_map_addr, poison, PAGE_SIZE);
+
+		free_reserved_page(page);
 	}
 
 	if (pages && s)
diff --git a/mm/page_io.c b/mm/page_io.c
index b41cf9644585..aafd19ec1db4 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -338,7 +338,8 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		ret = -ENOMEM;
 		goto out;
 	}
-	bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
+	bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc);
+	bio_associate_blkcg_from_page(bio, page);
 	count_swpout_vm_event(page);
 	set_page_writeback(page);
 	unlock_page(page);
diff --git a/mm/readahead.c b/mm/readahead.c
index e273f0de3376..a59ea70527b9 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -19,6 +19,7 @@
 #include <linux/syscalls.h>
 #include <linux/file.h>
 #include <linux/mm_inline.h>
+#include <linux/blk-cgroup.h>
 
 #include "internal.h"
 
@@ -385,6 +386,7 @@ ondemand_readahead(struct address_space *mapping,
 {
 	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	unsigned long max_pages = ra->ra_pages;
+	unsigned long add_pages;
 	pgoff_t prev_offset;
 
 	/*
@@ -474,10 +476,17 @@ readit:
 	 * Will this read hit the readahead marker made by itself?
 	 * If so, trigger the readahead marker hit now, and merge
 	 * the resulted next readahead window into the current one.
+	 * Take care of maximum IO pages as above.
 	 */
 	if (offset == ra->start && ra->size == ra->async_size) {
-		ra->async_size = get_next_ra_size(ra, max_pages);
-		ra->size += ra->async_size;
+		add_pages = get_next_ra_size(ra, max_pages);
+		if (ra->size + add_pages <= max_pages) {
+			ra->async_size = add_pages;
+			ra->size += add_pages;
+		} else {
+			ra->size = max_pages;
+			ra->async_size = max_pages >> 1;
+		}
 	}
 
 	return ra_submit(ra, mapping, filp);
@@ -505,6 +514,9 @@ void page_cache_sync_readahead(struct address_space *mapping,
 	if (!ra->ra_pages)
 		return;
 
+	if (blk_cgroup_congested())
+		return;
+
 	/* be dumb */
 	if (filp && (filp->f_mode & FMODE_RANDOM)) {
 		force_page_cache_readahead(mapping, filp, offset, req_size);
@@ -555,6 +567,9 @@ page_cache_async_readahead(struct address_space *mapping,
 	if (inode_read_congested(mapping->host))
 		return;
 
+	if (blk_cgroup_congested())
+		return;
+
 	/* do read-ahead */
 	ondemand_readahead(mapping, ra, filp, true, offset, req_size);
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index 41b9bbf24e16..06ebe17bb924 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1239,8 +1239,8 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
 	 * Charged back to the user (not to caller) when swap account is used.
 	 */
-	error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg,
-			false);
+	error = mem_cgroup_try_charge_delay(page, current->mm, GFP_KERNEL,
+					    &memcg, false);
 	if (error)
 		goto out;
 	/* No radix_tree_preload: swap entry keeps a place for page in tree */
@@ -1713,7 +1713,7 @@ repeat:
 				goto failed;
 		}
 
-		error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg,
+		error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 				false);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
@@ -1819,7 +1819,7 @@ alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, inode,
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 
-		error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg,
+		error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 				PageTransHuge(page));
 		if (error)
 			goto unacct;
@@ -2292,7 +2292,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	__SetPageSwapBacked(page);
 	__SetPageUptodate(page);
 
-	ret = mem_cgroup_try_charge(page, dst_mm, gfp, &memcg, false);
+	ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false);
 	if (ret)
 		goto out_release;
 
@@ -3897,18 +3897,11 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
 /* common code */
 
-static const struct dentry_operations anon_ops = {
-	.d_dname = simple_dname
-};
-
 static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size,
 				       unsigned long flags, unsigned int i_flags)
 {
-	struct file *res;
 	struct inode *inode;
-	struct path path;
-	struct super_block *sb;
-	struct qstr this;
+	struct file *res;
 
 	if (IS_ERR(mnt))
 		return ERR_CAST(mnt);
@@ -3919,41 +3912,21 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
 	if (shmem_acct_size(flags, size))
 		return ERR_PTR(-ENOMEM);
 
-	res = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0; /* will go */
-	sb = mnt->mnt_sb;
-	path.mnt = mntget(mnt);
-	path.dentry = d_alloc_pseudo(sb, &this);
-	if (!path.dentry)
-		goto put_memory;
-	d_set_d_op(path.dentry, &anon_ops);
-
-	res = ERR_PTR(-ENOSPC);
-	inode = shmem_get_inode(sb, NULL, S_IFREG | 0777, 0, flags);
-	if (!inode)
-		goto put_memory;
-
+	inode = shmem_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0,
+				flags);
+	if (unlikely(!inode)) {
+		shmem_unacct_size(flags, size);
+		return ERR_PTR(-ENOSPC);
+	}
 	inode->i_flags |= i_flags;
-	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
 	clear_nlink(inode);	/* It is unlinked */
 	res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size));
+	if (!IS_ERR(res))
+		res = alloc_file_pseudo(inode, mnt, name, O_RDWR,
+				&shmem_file_operations);
 	if (IS_ERR(res))
-		goto put_path;
-
-	res = alloc_file(&path, FMODE_WRITE | FMODE_READ,
-		  &shmem_file_operations);
-	if (IS_ERR(res))
-		goto put_path;
-
-	return res;
-
-put_memory:
-	shmem_unacct_size(flags, size);
-put_path:
-	path_put(&path);
+		iput(inode);
 	return res;
 }
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2cc2972eedaf..8837b22c848d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2909,6 +2909,35 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 	return 0;
 }
 
+
+/*
+ * Find out how many pages are allowed for a single swap device. There
+ * are two limiting factors:
+ * 1) the number of bits for the swap offset in the swp_entry_t type, and
+ * 2) the number of bits in the swap pte, as defined by the different
+ * architectures.
+ *
+ * In order to find the largest possible bit mask, a swap entry with
+ * swap type 0 and swap offset ~0UL is created, encoded to a swap pte,
+ * decoded to a swp_entry_t again, and finally the swap offset is
+ * extracted.
+ *
+ * This will mask all the bits from the initial ~0UL mask that can't
+ * be encoded in either the swp_entry_t or the architecture definition
+ * of a swap pte.
+ */
+unsigned long generic_max_swapfile_size(void)
+{
+	return swp_offset(pte_to_swp_entry(
+			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+}
+
+/* Can be overridden by an architecture for additional checks. */
+__weak unsigned long max_swapfile_size(void)
+{
+	return generic_max_swapfile_size();
+}
+
 static unsigned long read_swap_header(struct swap_info_struct *p,
 					union swap_header *swap_header,
 					struct inode *inode)
@@ -2944,22 +2973,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 	p->cluster_next = 1;
 	p->cluster_nr = 0;
 
-	/*
-	 * Find out how many pages are allowed for a single swap
-	 * device. There are two limiting factors: 1) the number
-	 * of bits for the swap offset in the swp_entry_t type, and
-	 * 2) the number of bits in the swap pte as defined by the
-	 * different architectures. In order to find the
-	 * largest possible bit mask, a swap entry with swap type 0
-	 * and swap offset ~0UL is created, encoded to a swap pte,
-	 * decoded to a swp_entry_t again, and finally the swap
-	 * offset is extracted. This will mask all the bits from
-	 * the initial ~0UL mask that can't be encoded in either
-	 * the swp_entry_t or the architecture definition of a
-	 * swap pte.
-	 */
-	maxpages = swp_offset(pte_to_swp_entry(
-			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+	maxpages = max_swapfile_size();
 	last_page = swap_header->info.last_page;
 	if (!last_page) {
 		pr_warn("Empty swap-file\n");
@@ -3731,6 +3745,37 @@ static void free_swap_count_continuations(struct swap_info_struct *si)
 	}
 }
 
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
+				  gfp_t gfp_mask)
+{
+	struct swap_info_struct *si, *next;
+	if (!(gfp_mask & __GFP_IO) || !memcg)
+		return;
+
+	if (!blk_cgroup_congested())
+		return;
+
+	/*
+	 * We've already scheduled a throttle, avoid taking the global swap
+	 * lock.
+	 */
+	if (current->throttle_queue)
+		return;
+
+	spin_lock(&swap_avail_lock);
+	plist_for_each_entry_safe(si, next, &swap_avail_heads[node],
+				  avail_lists[node]) {
+		if (si->bdev) {
+			blkcg_schedule_throttle(bdev_get_queue(si->bdev),
+						true);
+			break;
+		}
+	}
+	spin_unlock(&swap_avail_lock);
+}
+#endif
+
 static int __init swapfile_init(void)
 {
 	int nid;
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index af8c4b38b746..d84227d75717 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -244,7 +244,7 @@ static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size)
 	 * the packet count limit, so...
 	 */
 	if (atm_may_send(pvcc->atmvcc, size) &&
-	    atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT))
+	    atomic_inc_not_zero(&pvcc->inflight))
 		return 1;
 
 	/*
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 2b75df469220..842a9c7c73a3 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -229,14 +229,16 @@ static void ccid2_cwnd_restart(struct sock *sk, const u32 now)
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
 	u32 cwnd = hc->tx_cwnd, restart_cwnd,
 	    iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache);
+	s32 delta = now - hc->tx_lsndtime;
 
 	hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2));
 
 	/* don't reduce cwnd below the initial window (IW) */
 	restart_cwnd = min(cwnd, iwnd);
-	cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto;
-	hc->tx_cwnd = max(cwnd, restart_cwnd);
 
+	while ((delta -= hc->tx_rto) >= 0 && cwnd > restart_cwnd)
+		cwnd >>= 1;
+	hc->tx_cwnd = max(cwnd, restart_cwnd);
 	hc->tx_cwnd_stamp = now;
 	hc->tx_cwnd_used  = 0;
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 732369c80644..9864bcd3d317 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -639,7 +639,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev)
+	if (!dev->phydev && !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->set_mac_eee)
@@ -659,7 +659,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e)
 	int ret;
 
 	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev)
+	if (!dev->phydev && !dp->pl)
 		return -ENODEV;
 
 	if (!ds->ops->get_mac_eee)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 00e138a44cbb..1cc9650af9fb 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1133,12 +1133,8 @@ route_lookup:
 		max_headroom += 8;
 		mtu -= 8;
 	}
-	if (skb->protocol == htons(ETH_P_IPV6)) {
-		if (mtu < IPV6_MIN_MTU)
-			mtu = IPV6_MIN_MTU;
-	} else if (mtu < 576) {
-		mtu = 576;
-	}
+	mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
+		       IPV6_MIN_MTU : IPV4_MIN_MTU);
 
 	skb_dst_update_pmtu(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ec18b3ce8b6d..7208c16302f6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -978,10 +978,6 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
 	rt->rt6i_flags &= ~RTF_EXPIRES;
 	rcu_assign_pointer(rt->from, from);
 	dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
-	if (from->fib6_metrics != &dst_default_metrics) {
-		rt->dst._metrics |= DST_METRICS_REFCOUNTED;
-		refcount_inc(&from->fib6_metrics->refcnt);
-	}
 }
 
 /* Caller must already hold reference to @ort */
diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c
index 89041260784c..260b3dc1b4a2 100644
--- a/net/llc/llc_core.c
+++ b/net/llc/llc_core.c
@@ -73,8 +73,8 @@ struct llc_sap *llc_sap_find(unsigned char sap_value)
 
 	rcu_read_lock_bh();
 	sap = __llc_sap_find(sap_value);
-	if (sap)
-		llc_sap_hold(sap);
+	if (!sap || !llc_sap_hold_safe(sap))
+		sap = NULL;
 	rcu_read_unlock_bh();
 	return sap;
 }
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9b27d0cd766d..e6445d8f3f57 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4226,6 +4226,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	}
 
 	if (req->tp_block_nr) {
+		unsigned int min_frame_size;
+
 		/* Sanity tests and some calculations */
 		err = -EBUSY;
 		if (unlikely(rb->pg_vec))
@@ -4248,12 +4250,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 		if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
 			goto out;
+		min_frame_size = po->tp_hdrlen + po->tp_reserve;
 		if (po->tp_version >= TPACKET_V3 &&
-		    req->tp_block_size <=
-		    BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr))
+		    req->tp_block_size <
+		    BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size)
 			goto out;
-		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
-					po->tp_reserve))
+		if (unlikely(req->tp_frame_size < min_frame_size))
 			goto out;
 		if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1)))
 			goto out;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5fb7d3254d9e..707630ab4713 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -104,9 +104,9 @@ struct rxrpc_net {
 
 #define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */
 	u8			peer_keepalive_cursor;
-	ktime_t			peer_keepalive_base;
-	struct hlist_head	peer_keepalive[RXRPC_KEEPALIVE_TIME + 1];
-	struct hlist_head	peer_keepalive_new;
+	time64_t		peer_keepalive_base;
+	struct list_head	peer_keepalive[32];
+	struct list_head	peer_keepalive_new;
 	struct timer_list	peer_keepalive_timer;
 	struct work_struct	peer_keepalive_work;
 };
@@ -295,7 +295,7 @@ struct rxrpc_peer {
 	struct hlist_head	error_targets;	/* targets for net error distribution */
 	struct work_struct	error_distributor;
 	struct rb_root		service_conns;	/* Service connections */
-	struct hlist_node	keepalive_link;	/* Link in net->peer_keepalive[] */
+	struct list_head	keepalive_link;	/* Link in net->peer_keepalive[] */
 	time64_t		last_tx_at;	/* Last time packet sent here */
 	seqlock_t		service_conn_lock;
 	spinlock_t		lock;		/* access lock */
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index f6734d8cb01a..9486293fef5c 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -415,7 +415,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
 bool rxrpc_queue_call(struct rxrpc_call *call)
 {
 	const void *here = __builtin_return_address(0);
-	int n = __atomic_add_unless(&call->usage, 1, 0);
+	int n = atomic_fetch_add_unless(&call->usage, 1, 0);
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&call->processor))
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 8229a52c2acd..3fde001fcc39 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -136,7 +136,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 	}
 
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_final_resend);
@@ -245,7 +245,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 
 	_leave(" = 0");
 	return 0;
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 4c77a78a252a..77440a356b14 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -266,7 +266,7 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn)
 bool rxrpc_queue_conn(struct rxrpc_connection *conn)
 {
 	const void *here = __builtin_return_address(0);
-	int n = __atomic_add_unless(&conn->usage, 1, 0);
+	int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&conn->processor))
@@ -309,7 +309,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn)
 	const void *here = __builtin_return_address(0);
 
 	if (conn) {
-		int n = __atomic_add_unless(&conn->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here);
 		else
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index b493e6b62740..777c3ed4cfc0 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -305,7 +305,7 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
 	const void *here = __builtin_return_address(0);
 
 	if (local) {
-		int n = __atomic_add_unless(&local->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&local->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_local(local, rxrpc_local_got, n + 1, here);
 		else
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index 5d6a773db973..417d80867c4f 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -85,12 +85,12 @@ static __net_init int rxrpc_init_net(struct net *net)
 	hash_init(rxnet->peer_hash);
 	spin_lock_init(&rxnet->peer_hash_lock);
 	for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++)
-		INIT_HLIST_HEAD(&rxnet->peer_keepalive[i]);
-	INIT_HLIST_HEAD(&rxnet->peer_keepalive_new);
+		INIT_LIST_HEAD(&rxnet->peer_keepalive[i]);
+	INIT_LIST_HEAD(&rxnet->peer_keepalive_new);
 	timer_setup(&rxnet->peer_keepalive_timer,
 		    rxrpc_peer_keepalive_timeout, 0);
 	INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker);
-	rxnet->peer_keepalive_base = ktime_add(ktime_get_real(), NSEC_PER_SEC);
+	rxnet->peer_keepalive_base = ktime_get_seconds();
 
 	ret = -ENOMEM;
 	rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index f03de1c59ba3..4774c8f5634d 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -209,7 +209,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	now = ktime_get_real();
 	if (ping)
 		call->ping_time = now;
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_ack);
@@ -296,7 +296,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 
 	ret = kernel_sendmsg(conn->params.local->socket,
 			     &msg, iov, 1, sizeof(pkt));
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
 				    rxrpc_tx_fail_call_abort);
@@ -391,7 +391,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	 *     message and update the peer record
 	 */
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 
 	up_read(&conn->params.local->defrag_sem);
 	if (ret < 0)
@@ -457,7 +457,7 @@ send_fragmentable:
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
 					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_real();
+			conn->params.peer->last_tx_at = ktime_get_seconds();
 
 			opt = IP_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket, SOL_IP,
@@ -475,7 +475,7 @@ send_fragmentable:
 		if (ret == 0) {
 			ret = kernel_sendmsg(conn->params.local->socket, &msg,
 					     iov, 2, len);
-			conn->params.peer->last_tx_at = ktime_get_real();
+			conn->params.peer->last_tx_at = ktime_get_seconds();
 
 			opt = IPV6_PMTUDISC_DO;
 			kernel_setsockopt(conn->params.local->socket,
@@ -599,6 +599,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer)
 		trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
 				    rxrpc_tx_fail_version_keepalive);
 
-	peer->last_tx_at = ktime_get_real();
+	peer->last_tx_at = ktime_get_seconds();
 	_leave("");
 }
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 0ed8b651cec2..4f9da2f51c69 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -350,97 +350,117 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
 }
 
 /*
- * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ * Perform keep-alive pings.
  */
-void rxrpc_peer_keepalive_worker(struct work_struct *work)
+static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
+					  struct list_head *collector,
+					  time64_t base,
+					  u8 cursor)
 {
-	struct rxrpc_net *rxnet =
-		container_of(work, struct rxrpc_net, peer_keepalive_work);
 	struct rxrpc_peer *peer;
-	unsigned long delay;
-	ktime_t base, now = ktime_get_real();
-	s64 diff;
-	u8 cursor, slot;
+	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+	time64_t keepalive_at;
+	int slot;
 
-	base = rxnet->peer_keepalive_base;
-	cursor = rxnet->peer_keepalive_cursor;
+	spin_lock_bh(&rxnet->peer_hash_lock);
 
-	_enter("%u,%lld", cursor, ktime_sub(now, base));
+	while (!list_empty(collector)) {
+		peer = list_entry(collector->next,
+				  struct rxrpc_peer, keepalive_link);
 
-next_bucket:
-	diff = ktime_to_ns(ktime_sub(now, base));
-	if (diff < 0)
-		goto resched;
+		list_del_init(&peer->keepalive_link);
+		if (!rxrpc_get_peer_maybe(peer))
+			continue;
 
-	_debug("at %u", cursor);
-	spin_lock_bh(&rxnet->peer_hash_lock);
-next_peer:
-	if (!rxnet->live) {
 		spin_unlock_bh(&rxnet->peer_hash_lock);
-		goto out;
-	}
 
-	/* Everything in the bucket at the cursor is processed this second; the
-	 * bucket at cursor + 1 goes now + 1s and so on...
-	 */
-	if (hlist_empty(&rxnet->peer_keepalive[cursor])) {
-		if (hlist_empty(&rxnet->peer_keepalive_new)) {
-			spin_unlock_bh(&rxnet->peer_hash_lock);
-			goto emptied_bucket;
+		keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+		slot = keepalive_at - base;
+		_debug("%02x peer %u t=%d {%pISp}",
+		       cursor, peer->debug_id, slot, &peer->srx.transport);
+
+		if (keepalive_at <= base ||
+		    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+			rxrpc_send_keepalive(peer);
+			slot = RXRPC_KEEPALIVE_TIME;
 		}
 
-		hlist_move_list(&rxnet->peer_keepalive_new,
-				&rxnet->peer_keepalive[cursor]);
+		/* A transmission to this peer occurred since last we examined
+		 * it so put it into the appropriate future bucket.
+		 */
+		slot += cursor;
+		slot &= mask;
+		spin_lock_bh(&rxnet->peer_hash_lock);
+		list_add_tail(&peer->keepalive_link,
+			      &rxnet->peer_keepalive[slot & mask]);
+		rxrpc_put_peer(peer);
 	}
 
-	peer = hlist_entry(rxnet->peer_keepalive[cursor].first,
-			   struct rxrpc_peer, keepalive_link);
-	hlist_del_init(&peer->keepalive_link);
-	if (!rxrpc_get_peer_maybe(peer))
-		goto next_peer;
-
 	spin_unlock_bh(&rxnet->peer_hash_lock);
+}
 
-	_debug("peer %u {%pISp}", peer->debug_id, &peer->srx.transport);
+/*
+ * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ */
+void rxrpc_peer_keepalive_worker(struct work_struct *work)
+{
+	struct rxrpc_net *rxnet =
+		container_of(work, struct rxrpc_net, peer_keepalive_work);
+	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
+	time64_t base, now, delay;
+	u8 cursor, stop;
+	LIST_HEAD(collector);
 
-recalc:
-	diff = ktime_divns(ktime_sub(peer->last_tx_at, base), NSEC_PER_SEC);
-	if (diff < -30 || diff > 30)
-		goto send; /* LSW of 64-bit time probably wrapped on 32-bit */
-	diff += RXRPC_KEEPALIVE_TIME - 1;
-	if (diff < 0)
-		goto send;
+	now = ktime_get_seconds();
+	base = rxnet->peer_keepalive_base;
+	cursor = rxnet->peer_keepalive_cursor;
+	_enter("%lld,%u", base - now, cursor);
 
-	slot = (diff > RXRPC_KEEPALIVE_TIME - 1) ? RXRPC_KEEPALIVE_TIME - 1 : diff;
-	if (slot == 0)
-		goto send;
+	if (!rxnet->live)
+		return;
 
-	/* A transmission to this peer occurred since last we examined it so
-	 * put it into the appropriate future bucket.
+	/* Remove to a temporary list all the peers that are currently lodged
+	 * in expired buckets plus all new peers.
+	 *
+	 * Everything in the bucket at the cursor is processed this
+	 * second; the bucket at cursor + 1 goes at now + 1s and so
+	 * on...
 	 */
-	slot = (slot + cursor) % ARRAY_SIZE(rxnet->peer_keepalive);
 	spin_lock_bh(&rxnet->peer_hash_lock);
-	hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive[slot]);
-	rxrpc_put_peer(peer);
-	goto next_peer;
-
-send:
-	rxrpc_send_keepalive(peer);
-	now = ktime_get_real();
-	goto recalc;
+	list_splice_init(&rxnet->peer_keepalive_new, &collector);
+
+	stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive);
+	while (base <= now && (s8)(cursor - stop) < 0) {
+		list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask],
+				      &collector);
+		base++;
+		cursor++;
+	}
 
-emptied_bucket:
-	cursor++;
-	if (cursor >= ARRAY_SIZE(rxnet->peer_keepalive))
-		cursor = 0;
-	base = ktime_add_ns(base, NSEC_PER_SEC);
-	goto next_bucket;
+	base = now;
+	spin_unlock_bh(&rxnet->peer_hash_lock);
 
-resched:
 	rxnet->peer_keepalive_base = base;
 	rxnet->peer_keepalive_cursor = cursor;
-	delay = nsecs_to_jiffies(-diff) + 1;
-	timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
-out:
+	rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor);
+	ASSERT(list_empty(&collector));
+
+	/* Schedule the timer for the next occupied timeslot. */
+	cursor = rxnet->peer_keepalive_cursor;
+	stop = cursor + RXRPC_KEEPALIVE_TIME - 1;
+	for (; (s8)(cursor - stop) < 0; cursor++) {
+		if (!list_empty(&rxnet->peer_keepalive[cursor & mask]))
+			break;
+		base++;
+	}
+
+	now = ktime_get_seconds();
+	delay = base - now;
+	if (delay < 1)
+		delay = 1;
+	delay *= HZ;
+	if (rxnet->live)
+		timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
+
 	_leave("");
 }
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 1b7e8107b3ae..1dc7648e3eff 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -322,7 +322,7 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local,
 	if (!peer) {
 		peer = prealloc;
 		hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
-		hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive_new);
+		list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
 	}
 
 	spin_unlock(&rxnet->peer_hash_lock);
@@ -367,8 +367,8 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
 		if (!peer) {
 			hash_add_rcu(rxnet->peer_hash,
 				     &candidate->hash_link, hash_key);
-			hlist_add_head(&candidate->keepalive_link,
-				       &rxnet->peer_keepalive_new);
+			list_add_tail(&candidate->keepalive_link,
+				      &rxnet->peer_keepalive_new);
 		}
 
 		spin_unlock_bh(&rxnet->peer_hash_lock);
@@ -406,7 +406,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
 	const void *here = __builtin_return_address(0);
 
 	if (peer) {
-		int n = __atomic_add_unless(&peer->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&peer->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here);
 		else
@@ -441,7 +441,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
 
 	spin_lock_bh(&rxnet->peer_hash_lock);
 	hash_del_rcu(&peer->hash_link);
-	hlist_del_init(&peer->keepalive_link);
+	list_del_init(&peer->keepalive_link);
 	spin_unlock_bh(&rxnet->peer_hash_lock);
 
 	kfree_rcu(peer, rcu);
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 278ac0807a60..47cb019c521a 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -669,7 +669,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	_leave(" = 0");
 	return 0;
 }
@@ -725,7 +725,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 		return -EAGAIN;
 	}
 
-	conn->params.peer->last_tx_at = ktime_get_real();
+	conn->params.peer->last_tx_at = ktime_get_seconds();
 	_leave(" = 0");
 	return 0;
 }
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 05e4ffe5aabd..e7de5f282722 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1122,6 +1122,8 @@ static void smc_tcp_listen_work(struct work_struct *work)
 		sock_hold(lsk); /* sock_put in smc_listen_work */
 		INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
 		smc_copy_sock_settings_to_smc(new_smc);
+		new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf;
+		new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf;
 		sock_hold(&new_smc->sk); /* sock_put in passive closing */
 		if (!schedule_work(&new_smc->smc_listen_work))
 			sock_put(&new_smc->sk);
@@ -1397,8 +1399,7 @@ static int smc_shutdown(struct socket *sock, int how)
 	lock_sock(sk);
 
 	rc = -ENOTCONN;
-	if ((sk->sk_state != SMC_LISTEN) &&
-	    (sk->sk_state != SMC_ACTIVE) &&
+	if ((sk->sk_state != SMC_ACTIVE) &&
 	    (sk->sk_state != SMC_PEERCLOSEWAIT1) &&
 	    (sk->sk_state != SMC_PEERCLOSEWAIT2) &&
 	    (sk->sk_state != SMC_APPCLOSEWAIT1) &&
@@ -1521,12 +1522,16 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 
 	smc = smc_sk(sock->sk);
 	conn = &smc->conn;
+	lock_sock(&smc->sk);
 	if (smc->use_fallback) {
-		if (!smc->clcsock)
+		if (!smc->clcsock) {
+			release_sock(&smc->sk);
 			return -EBADF;
-		return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+		}
+		answ = smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
+		release_sock(&smc->sk);
+		return answ;
 	}
-	lock_sock(&smc->sk);
 	switch (cmd) {
 	case SIOCINQ: /* same as FIONREAD */
 		if (smc->sk.sk_state == SMC_LISTEN) {
diff --git a/net/socket.c b/net/socket.c
index 8c24d5dc4bc8..792f0313ea91 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -388,39 +388,20 @@ static struct file_system_type sock_fs_type = {
 
 struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 {
-	struct qstr name = { .name = "" };
-	struct path path;
 	struct file *file;
 
-	if (dname) {
-		name.name = dname;
-		name.len = strlen(name.name);
-	} else if (sock->sk) {
-		name.name = sock->sk->sk_prot_creator->name;
-		name.len = strlen(name.name);
-	}
-	path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
-	if (unlikely(!path.dentry)) {
-		sock_release(sock);
-		return ERR_PTR(-ENOMEM);
-	}
-	path.mnt = mntget(sock_mnt);
-
-	d_instantiate(path.dentry, SOCK_INODE(sock));
+	if (!dname)
+		dname = sock->sk ? sock->sk->sk_prot_creator->name : "";
 
-	file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
-		  &socket_file_ops);
+	file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname,
+				O_RDWR | (flags & O_NONBLOCK),
+				&socket_file_ops);
 	if (IS_ERR(file)) {
-		/* drop dentry, keep inode for a bit */
-		ihold(d_inode(path.dentry));
-		path_put(&path);
-		/* ... and now kill it properly */
 		sock_release(sock);
 		return file;
 	}
 
 	sock->file = file;
-	file->f_flags = O_RDWR | (flags & O_NONBLOCK);
 	file->private_data = sock;
 	return file;
 }
diff --git a/net/tipc/net.c b/net/tipc/net.c
index a7f6964c3a4b..62199cf5a56c 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -123,15 +123,13 @@ void tipc_net_finalize(struct net *net, u32 addr)
 {
 	struct tipc_net *tn = tipc_net(net);
 
-	spin_lock_bh(&tn->node_list_lock);
-	if (!tipc_own_addr(net)) {
+	if (!cmpxchg(&tn->node_addr, 0, addr)) {
 		tipc_set_node_addr(net, addr);
 		tipc_named_reinit(net);
 		tipc_sk_reinit(net);
 		tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
 				     TIPC_CLUSTER_SCOPE, 0, addr);
 	}
-	spin_unlock_bh(&tn->node_list_lock);
 }
 
 void tipc_net_stop(struct net *net)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index c1076c19b858..ab27a2872935 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -451,14 +451,14 @@ static int vsock_send_shutdown(struct sock *sk, int mode)
 	return transport->shutdown(vsock_sk(sk), mode);
 }
 
-void vsock_pending_work(struct work_struct *work)
+static void vsock_pending_work(struct work_struct *work)
 {
 	struct sock *sk;
 	struct sock *listener;
 	struct vsock_sock *vsk;
 	bool cleanup;
 
-	vsk = container_of(work, struct vsock_sock, dwork.work);
+	vsk = container_of(work, struct vsock_sock, pending_work.work);
 	sk = sk_vsock(vsk);
 	listener = vsk->listener;
 	cleanup = true;
@@ -498,7 +498,6 @@ out:
 	sock_put(sk);
 	sock_put(listener);
 }
-EXPORT_SYMBOL_GPL(vsock_pending_work);
 
 /**** SOCKET OPERATIONS ****/
 
@@ -597,6 +596,8 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
 	return retval;
 }
 
+static void vsock_connect_timeout(struct work_struct *work);
+
 struct sock *__vsock_create(struct net *net,
 			    struct socket *sock,
 			    struct sock *parent,
@@ -638,6 +639,8 @@ struct sock *__vsock_create(struct net *net,
 	vsk->sent_request = false;
 	vsk->ignore_connecting_rst = false;
 	vsk->peer_shutdown = 0;
+	INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout);
+	INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work);
 
 	psk = parent ? vsock_sk(parent) : NULL;
 	if (parent) {
@@ -1117,7 +1120,7 @@ static void vsock_connect_timeout(struct work_struct *work)
 	struct vsock_sock *vsk;
 	int cancel = 0;
 
-	vsk = container_of(work, struct vsock_sock, dwork.work);
+	vsk = container_of(work, struct vsock_sock, connect_work.work);
 	sk = sk_vsock(vsk);
 
 	lock_sock(sk);
@@ -1221,9 +1224,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 			 * timeout fires.
 			 */
 			sock_hold(sk);
-			INIT_DELAYED_WORK(&vsk->dwork,
-					  vsock_connect_timeout);
-			schedule_delayed_work(&vsk->dwork, timeout);
+			schedule_delayed_work(&vsk->connect_work, timeout);
 
 			/* Skip ahead to preserve error code set above. */
 			goto out_wait;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index a7a73ffe675b..cb332adb84cd 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1094,8 +1094,7 @@ static int vmci_transport_recv_listen(struct sock *sk,
 	vpending->listener = sk;
 	sock_hold(sk);
 	sock_hold(pending);
-	INIT_DELAYED_WORK(&vpending->dwork, vsock_pending_work);
-	schedule_delayed_work(&vpending->dwork, HZ);
+	schedule_delayed_work(&vpending->pending_work, HZ);
 
 out:
 	return err;
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index 303e9e7161f3..4938dcbaecbf 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -14,7 +14,7 @@
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
 
-#define MAX_CPUS 12 /* WARNING - sync with _user.c */
+#define MAX_CPUS 64 /* WARNING - sync with _user.c */
 
 /* Special map type that can XDP_REDIRECT frames to another CPU */
 struct bpf_map_def SEC("maps") cpu_map = {
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index f6efaefd485b..4b4d78fffe30 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -19,7 +19,7 @@ static const char *__doc__ =
 #include <arpa/inet.h>
 #include <linux/if_link.h>
 
-#define MAX_CPUS 12 /* WARNING - sync with _kern.c */
+#define MAX_CPUS 64 /* WARNING - sync with _kern.c */
 
 /* How many xdp_progs are defined in _kern.c */
 #define MAX_PROG 5
@@ -527,7 +527,7 @@ static void stress_cpumap(void)
 	 * procedure.
 	 */
 	create_cpu_entry(1,  1024, 0, false);
-	create_cpu_entry(1,   128, 0, false);
+	create_cpu_entry(1,     8, 0, false);
 	create_cpu_entry(1, 16000, 0, false);
 }
 
diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan
index b593b36ccff8..38b2b4818e8e 100644
--- a/scripts/Makefile.ubsan
+++ b/scripts/Makefile.ubsan
@@ -14,10 +14,6 @@ ifdef CONFIG_UBSAN_ALIGNMENT
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=alignment)
 endif
 
-ifdef CONFIG_UBSAN_NULL
-      CFLAGS_UBSAN += $(call cc-option, -fsanitize=null)
-endif
-
       # -fsanitize=* options makes GCC less smart than usual and
       # increase number of 'maybe-uninitialized false-positives
       CFLAGS_UBSAN += $(call cc-option, -Wno-maybe-uninitialized)
diff --git a/security/Kconfig b/security/Kconfig
index c4302067a3ad..afa91c6f06bb 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -57,7 +57,7 @@ config SECURITY_NETWORK
 config PAGE_TABLE_ISOLATION
 	bool "Remove the kernel mapping in user mode"
 	default y
-	depends on X86_64 && !UML
+	depends on X86 && !UML
 	help
 	  This feature reduces the number of hardware side channels by
 	  ensuring that the majority of kernel addresses are not mapped
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 74f17376202b..8b8b70620bbe 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -395,7 +395,7 @@ static int apparmor_inode_getattr(const struct path *path)
 	return common_perm_cond(OP_GETATTR, path, AA_MAY_GETATTR);
 }
 
-static int apparmor_file_open(struct file *file, const struct cred *cred)
+static int apparmor_file_open(struct file *file)
 {
 	struct aa_file_ctx *fctx = file_ctx(file);
 	struct aa_label *label;
@@ -414,7 +414,7 @@ static int apparmor_file_open(struct file *file, const struct cred *cred)
 		return 0;
 	}
 
-	label = aa_get_newest_cred_label(cred);
+	label = aa_get_newest_cred_label(file->f_cred);
 	if (!unconfined(label)) {
 		struct inode *inode = file_inode(file);
 		struct path_cond cond = { inode->i_uid, inode->i_mode };
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 354bb5716ce3..e4c1a236976c 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -238,7 +238,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 			     struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len, int opened);
+			     int xattr_len);
 int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
 void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
 enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
@@ -254,7 +254,7 @@ static inline int ima_appraise_measurement(enum ima_hooks func,
 					   struct file *file,
 					   const unsigned char *filename,
 					   struct evm_ima_xattr_data *xattr_value,
-					   int xattr_len, int opened)
+					   int xattr_len)
 {
 	return INTEGRITY_UNKNOWN;
 }
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 8bd7a0733e51..deec1804a00a 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -212,7 +212,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 			     struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len, int opened)
+			     int xattr_len)
 {
 	static const char op[] = "appraise_data";
 	const char *cause = "unknown";
@@ -231,7 +231,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 		cause = iint->flags & IMA_DIGSIG_REQUIRED ?
 				"IMA-signature-required" : "missing-hash";
 		status = INTEGRITY_NOLABEL;
-		if (opened & FILE_CREATED)
+		if (file->f_mode & FMODE_CREATED)
 			iint->flags |= IMA_NEW_FILE;
 		if ((iint->flags & IMA_NEW_FILE) &&
 		    (!(iint->flags & IMA_DIGSIG_REQUIRED) ||
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index dca44cf7838e..b286f37712d5 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -168,7 +168,7 @@ void ima_file_free(struct file *file)
 
 static int process_measurement(struct file *file, const struct cred *cred,
 			       u32 secid, char *buf, loff_t size, int mask,
-			       enum ima_hooks func, int opened)
+			       enum ima_hooks func)
 {
 	struct inode *inode = file_inode(file);
 	struct integrity_iint_cache *iint = NULL;
@@ -294,7 +294,7 @@ static int process_measurement(struct file *file, const struct cred *cred,
 	if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) {
 		inode_lock(inode);
 		rc = ima_appraise_measurement(func, iint, file, pathname,
-					      xattr_value, xattr_len, opened);
+					      xattr_value, xattr_len);
 		inode_unlock(inode);
 	}
 	if (action & IMA_AUDIT)
@@ -338,7 +338,7 @@ int ima_file_mmap(struct file *file, unsigned long prot)
 	if (file && (prot & PROT_EXEC)) {
 		security_task_getsecid(current, &secid);
 		return process_measurement(file, current_cred(), secid, NULL,
-					   0, MAY_EXEC, MMAP_CHECK, 0);
+					   0, MAY_EXEC, MMAP_CHECK);
 	}
 
 	return 0;
@@ -364,13 +364,13 @@ int ima_bprm_check(struct linux_binprm *bprm)
 
 	security_task_getsecid(current, &secid);
 	ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0,
-				  MAY_EXEC, BPRM_CHECK, 0);
+				  MAY_EXEC, BPRM_CHECK);
 	if (ret)
 		return ret;
 
 	security_cred_getsecid(bprm->cred, &secid);
 	return process_measurement(bprm->file, bprm->cred, secid, NULL, 0,
-				   MAY_EXEC, CREDS_CHECK, 0);
+				   MAY_EXEC, CREDS_CHECK);
 }
 
 /**
@@ -383,14 +383,14 @@ int ima_bprm_check(struct linux_binprm *bprm)
  * On success return 0.  On integrity appraisal error, assuming the file
  * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
  */
-int ima_file_check(struct file *file, int mask, int opened)
+int ima_file_check(struct file *file, int mask)
 {
 	u32 secid;
 
 	security_task_getsecid(current, &secid);
 	return process_measurement(file, current_cred(), secid, NULL, 0,
 				   mask & (MAY_READ | MAY_WRITE | MAY_EXEC |
-					   MAY_APPEND), FILE_CHECK, opened);
+					   MAY_APPEND), FILE_CHECK);
 }
 EXPORT_SYMBOL_GPL(ima_file_check);
 
@@ -493,7 +493,7 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
 	func = read_idmap[read_id] ?: FILE_CHECK;
 	security_task_getsecid(current, &secid);
 	return process_measurement(file, current_cred(), secid, buf, size,
-				   MAY_READ, func, 0);
+				   MAY_READ, func);
 }
 
 static int __init init_ima(void)
diff --git a/security/security.c b/security/security.c
index 68f46d849abe..5dce67070cdf 100644
--- a/security/security.c
+++ b/security/security.c
@@ -970,11 +970,11 @@ int security_file_receive(struct file *file)
 	return call_int_hook(file_receive, 0, file);
 }
 
-int security_file_open(struct file *file, const struct cred *cred)
+int security_file_open(struct file *file)
 {
 	int ret;
 
-	ret = call_int_hook(file_open, 0, file, cred);
+	ret = call_int_hook(file_open, 0, file);
 	if (ret)
 		return ret;
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 2b5ee5fbd652..18006be15713 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3862,7 +3862,7 @@ static int selinux_file_receive(struct file *file)
 	return file_has_perm(cred, file, file_to_av(file));
 }
 
-static int selinux_file_open(struct file *file, const struct cred *cred)
+static int selinux_file_open(struct file *file)
 {
 	struct file_security_struct *fsec;
 	struct inode_security_struct *isec;
@@ -3886,7 +3886,7 @@ static int selinux_file_open(struct file *file, const struct cred *cred)
 	 * new inode label or new policy.
 	 * This check is not redundant - do not remove.
 	 */
-	return file_path_has_perm(cred, file, open_file_to_av(file));
+	return file_path_has_perm(file->f_cred, file, open_file_to_av(file));
 }
 
 /* task security operations */
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 19de675d4504..9ab8097dab7c 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1927,9 +1927,9 @@ static int smack_file_receive(struct file *file)
  *
  * Returns 0
  */
-static int smack_file_open(struct file *file, const struct cred *cred)
+static int smack_file_open(struct file *file)
 {
-	struct task_smack *tsp = cred->security;
+	struct task_smack *tsp = file->f_cred->security;
 	struct inode *inode = file_inode(file);
 	struct smk_audit_info ad;
 	int rc;
@@ -1937,7 +1937,7 @@ static int smack_file_open(struct file *file, const struct cred *cred)
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 	smk_ad_setfield_u_fs_path(&ad, file->f_path);
 	rc = smk_tskacc(tsp, smk_of_inode(inode), MAY_READ, &ad);
-	rc = smk_bu_credfile(cred, file, MAY_READ, rc);
+	rc = smk_bu_credfile(file->f_cred, file, MAY_READ, rc);
 
 	return rc;
 }
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index 213b8c593668..9f932e2d6852 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -320,7 +320,7 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd,
  *
  * Returns 0 on success, negative value otherwise.
  */
-static int tomoyo_file_open(struct file *f, const struct cred *cred)
+static int tomoyo_file_open(struct file *f)
 {
 	int flags = f->f_flags;
 	/* Don't check read permission here if called from do_execve(). */
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5072cbd15c82
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#define __ARCH_WANT_RENAMEAT
+
+#include <asm-generic/unistd.h>
diff --git a/tools/arch/parisc/include/uapi/asm/errno.h b/tools/arch/parisc/include/uapi/asm/errno.h
index fc0df353ff0d..87245c584784 100644
--- a/tools/arch/parisc/include/uapi/asm/errno.h
+++ b/tools/arch/parisc/include/uapi/asm/errno.h
@@ -113,7 +113,6 @@
 #define	ELOOP		249	/* Too many symbolic links encountered */
 #define	ENOSYS		251	/* Function not implemented */
 
-#define ENOTSUP		252	/* Function not implemented (POSIX.4 / HPUX) */
 #define ECANCELLED	253	/* aio request was canceled before complete (POSIX.4 / HPUX) */
 #define ECANCELED	ECANCELLED	/* SuSv3 and Solaris wants one 'L' */
 
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 5701f5cecd31..64aaa3f5f36c 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -219,6 +219,7 @@
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -341,6 +342,7 @@
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
@@ -373,5 +375,6 @@
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
new file mode 100644
index 000000000000..42990676a55e
--- /dev/null
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -0,0 +1,783 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#include <asm/bitsperlong.h>
+
+/*
+ * This file contains the system call numbers, based on the
+ * layout of the x86-64 architecture, which embeds the
+ * pointer to the syscall in the table.
+ *
+ * As a basic principle, no duplication of functionality
+ * should be added, e.g. we don't use lseek when llseek
+ * is present. New architectures should use this file
+ * and implement the less feature-full calls in user space.
+ */
+
+#ifndef __SYSCALL
+#define __SYSCALL(x, y)
+#endif
+
+#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32)
+#else
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
+#endif
+
+#ifdef __SYSCALL_COMPAT
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp)
+#else
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64)
+#endif
+
+#define __NR_io_setup 0
+__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 1
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_submit 2
+__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 3
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_io_getevents 4
+__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
+
+/* fs/xattr.c */
+#define __NR_setxattr 5
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 6
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 7
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 8
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 9
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 10
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 11
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 12
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 13
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 14
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 15
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 16
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+
+/* fs/dcache.c */
+#define __NR_getcwd 17
+__SYSCALL(__NR_getcwd, sys_getcwd)
+
+/* fs/cookies.c */
+#define __NR_lookup_dcookie 18
+__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
+
+/* fs/eventfd.c */
+#define __NR_eventfd2 19
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+
+/* fs/eventpoll.c */
+#define __NR_epoll_create1 20
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_epoll_ctl 21
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_pwait 22
+__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait)
+
+/* fs/fcntl.c */
+#define __NR_dup 23
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_dup3 24
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR3264_fcntl 25
+__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64)
+
+/* fs/inotify_user.c */
+#define __NR_inotify_init1 26
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_inotify_add_watch 27
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 28
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+
+/* fs/ioctl.c */
+#define __NR_ioctl 29
+__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)
+
+/* fs/ioprio.c */
+#define __NR_ioprio_set 30
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 31
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+
+/* fs/locks.c */
+#define __NR_flock 32
+__SYSCALL(__NR_flock, sys_flock)
+
+/* fs/namei.c */
+#define __NR_mknodat 33
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_mkdirat 34
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_unlinkat 35
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_symlinkat 36
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_linkat 37
+__SYSCALL(__NR_linkat, sys_linkat)
+#ifdef __ARCH_WANT_RENAMEAT
+/* renameat is superseded with flags by renameat2 */
+#define __NR_renameat 38
+__SYSCALL(__NR_renameat, sys_renameat)
+#endif /* __ARCH_WANT_RENAMEAT */
+
+/* fs/namespace.c */
+#define __NR_umount2 39
+__SYSCALL(__NR_umount2, sys_umount)
+#define __NR_mount 40
+__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+#define __NR_pivot_root 41
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+
+/* fs/nfsctl.c */
+#define __NR_nfsservctl 42
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+
+/* fs/open.c */
+#define __NR3264_statfs 43
+__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \
+	       compat_sys_statfs64)
+#define __NR3264_fstatfs 44
+__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \
+	       compat_sys_fstatfs64)
+#define __NR3264_truncate 45
+__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \
+	       compat_sys_truncate64)
+#define __NR3264_ftruncate 46
+__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \
+	       compat_sys_ftruncate64)
+
+#define __NR_fallocate 47
+__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate)
+#define __NR_faccessat 48
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_chdir 49
+__SYSCALL(__NR_chdir, sys_chdir)
+#define __NR_fchdir 50
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_chroot 51
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_fchmod 52
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchmodat 53
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_fchownat 54
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_fchown 55
+__SYSCALL(__NR_fchown, sys_fchown)
+#define __NR_openat 56
+__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
+#define __NR_close 57
+__SYSCALL(__NR_close, sys_close)
+#define __NR_vhangup 58
+__SYSCALL(__NR_vhangup, sys_vhangup)
+
+/* fs/pipe.c */
+#define __NR_pipe2 59
+__SYSCALL(__NR_pipe2, sys_pipe2)
+
+/* fs/quota.c */
+#define __NR_quotactl 60
+__SYSCALL(__NR_quotactl, sys_quotactl)
+
+/* fs/readdir.c */
+#define __NR_getdents64 61
+__SYSCALL(__NR_getdents64, sys_getdents64)
+
+/* fs/read_write.c */
+#define __NR3264_lseek 62
+__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek)
+#define __NR_read 63
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 64
+__SYSCALL(__NR_write, sys_write)
+#define __NR_readv 65
+__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+#define __NR_writev 66
+__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+#define __NR_pread64 67
+__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
+#define __NR_pwrite64 68
+__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
+#define __NR_preadv 69
+__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
+#define __NR_pwritev 70
+__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
+
+/* fs/sendfile.c */
+#define __NR3264_sendfile 71
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
+
+/* fs/select.c */
+#define __NR_pselect6 72
+__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
+#define __NR_ppoll 73
+__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
+
+/* fs/signalfd.c */
+#define __NR_signalfd4 74
+__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
+
+/* fs/splice.c */
+#define __NR_vmsplice 75
+__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+#define __NR_splice 76
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee 77
+__SYSCALL(__NR_tee, sys_tee)
+
+/* fs/stat.c */
+#define __NR_readlinkat 78
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR3264_fstatat 79
+__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
+#define __NR3264_fstat 80
+__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+
+/* fs/sync.c */
+#define __NR_sync 81
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_fsync 82
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_fdatasync 83
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#ifdef __ARCH_WANT_SYNC_FILE_RANGE2
+#define __NR_sync_file_range2 84
+__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \
+	  compat_sys_sync_file_range2)
+#else
+#define __NR_sync_file_range 84
+__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
+	  compat_sys_sync_file_range)
+#endif
+
+/* fs/timerfd.c */
+#define __NR_timerfd_create 85
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_timerfd_settime 86
+__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
+	  compat_sys_timerfd_settime)
+#define __NR_timerfd_gettime 87
+__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
+	  compat_sys_timerfd_gettime)
+
+/* fs/utimes.c */
+#define __NR_utimensat 88
+__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
+
+/* kernel/acct.c */
+#define __NR_acct 89
+__SYSCALL(__NR_acct, sys_acct)
+
+/* kernel/capability.c */
+#define __NR_capget 90
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 91
+__SYSCALL(__NR_capset, sys_capset)
+
+/* kernel/exec_domain.c */
+#define __NR_personality 92
+__SYSCALL(__NR_personality, sys_personality)
+
+/* kernel/exit.c */
+#define __NR_exit 93
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_exit_group 94
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_waitid 95
+__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid)
+
+/* kernel/fork.c */
+#define __NR_set_tid_address 96
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_unshare 97
+__SYSCALL(__NR_unshare, sys_unshare)
+
+/* kernel/futex.c */
+#define __NR_futex 98
+__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
+#define __NR_set_robust_list 99
+__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
+	  compat_sys_set_robust_list)
+#define __NR_get_robust_list 100
+__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
+	  compat_sys_get_robust_list)
+
+/* kernel/hrtimer.c */
+#define __NR_nanosleep 101
+__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
+
+/* kernel/itimer.c */
+#define __NR_getitimer 102
+__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer)
+#define __NR_setitimer 103
+__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer)
+
+/* kernel/kexec.c */
+#define __NR_kexec_load 104
+__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load)
+
+/* kernel/module.c */
+#define __NR_init_module 105
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 106
+__SYSCALL(__NR_delete_module, sys_delete_module)
+
+/* kernel/posix-timers.c */
+#define __NR_timer_create 107
+__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+#define __NR_timer_gettime 108
+__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
+#define __NR_timer_getoverrun 109
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_settime 110
+__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
+#define __NR_timer_delete 111
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime 112
+__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
+#define __NR_clock_gettime 113
+__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
+#define __NR_clock_getres 114
+__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
+#define __NR_clock_nanosleep 115
+__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
+	  compat_sys_clock_nanosleep)
+
+/* kernel/printk.c */
+#define __NR_syslog 116
+__SYSCALL(__NR_syslog, sys_syslog)
+
+/* kernel/ptrace.c */
+#define __NR_ptrace 117
+__SYSCALL(__NR_ptrace, sys_ptrace)
+
+/* kernel/sched/core.c */
+#define __NR_sched_setparam 118
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_setscheduler 119
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 120
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_getparam 121
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setaffinity 122
+__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \
+	  compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 123
+__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \
+	  compat_sys_sched_getaffinity)
+#define __NR_sched_yield 124
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 125
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 126
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval 127
+__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
+	  compat_sys_sched_rr_get_interval)
+
+/* kernel/signal.c */
+#define __NR_restart_syscall 128
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_kill 129
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_tkill 130
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_tgkill 131
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_sigaltstack 132
+__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack)
+#define __NR_rt_sigsuspend 133
+__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_rt_sigaction 134
+__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 135
+__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 136
+__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+#define __NR_rt_sigtimedwait 137
+__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
+	  compat_sys_rt_sigtimedwait)
+#define __NR_rt_sigqueueinfo 138
+__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
+	  compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigreturn 139
+__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn)
+
+/* kernel/sys.c */
+#define __NR_setpriority 140
+__SYSCALL(__NR_setpriority, sys_setpriority)
+#define __NR_getpriority 141
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_reboot 142
+__SYSCALL(__NR_reboot, sys_reboot)
+#define __NR_setregid 143
+__SYSCALL(__NR_setregid, sys_setregid)
+#define __NR_setgid 144
+__SYSCALL(__NR_setgid, sys_setgid)
+#define __NR_setreuid 145
+__SYSCALL(__NR_setreuid, sys_setreuid)
+#define __NR_setuid 146
+__SYSCALL(__NR_setuid, sys_setuid)
+#define __NR_setresuid 147
+__SYSCALL(__NR_setresuid, sys_setresuid)
+#define __NR_getresuid 148
+__SYSCALL(__NR_getresuid, sys_getresuid)
+#define __NR_setresgid 149
+__SYSCALL(__NR_setresgid, sys_setresgid)
+#define __NR_getresgid 150
+__SYSCALL(__NR_getresgid, sys_getresgid)
+#define __NR_setfsuid 151
+__SYSCALL(__NR_setfsuid, sys_setfsuid)
+#define __NR_setfsgid 152
+__SYSCALL(__NR_setfsgid, sys_setfsgid)
+#define __NR_times 153
+__SC_COMP(__NR_times, sys_times, compat_sys_times)
+#define __NR_setpgid 154
+__SYSCALL(__NR_setpgid, sys_setpgid)
+#define __NR_getpgid 155
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_getsid 156
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_setsid 157
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_getgroups 158
+__SYSCALL(__NR_getgroups, sys_getgroups)
+#define __NR_setgroups 159
+__SYSCALL(__NR_setgroups, sys_setgroups)
+#define __NR_uname 160
+__SYSCALL(__NR_uname, sys_newuname)
+#define __NR_sethostname 161
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setdomainname 162
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+#define __NR_getrlimit 163
+__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
+#define __NR_setrlimit 164
+__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#define __NR_getrusage 165
+__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
+#define __NR_umask 166
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_prctl 167
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_getcpu 168
+__SYSCALL(__NR_getcpu, sys_getcpu)
+
+/* kernel/time.c */
+#define __NR_gettimeofday 169
+__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 170
+__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
+#define __NR_adjtimex 171
+__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
+
+/* kernel/timer.c */
+#define __NR_getpid 172
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_getppid 173
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getuid 174
+__SYSCALL(__NR_getuid, sys_getuid)
+#define __NR_geteuid 175
+__SYSCALL(__NR_geteuid, sys_geteuid)
+#define __NR_getgid 176
+__SYSCALL(__NR_getgid, sys_getgid)
+#define __NR_getegid 177
+__SYSCALL(__NR_getegid, sys_getegid)
+#define __NR_gettid 178
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_sysinfo 179
+__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
+
+/* ipc/mqueue.c */
+#define __NR_mq_open 180
+__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 181
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend 182
+__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
+#define __NR_mq_timedreceive 183
+__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
+	  compat_sys_mq_timedreceive)
+#define __NR_mq_notify 184
+__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 185
+__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr)
+
+/* ipc/msg.c */
+#define __NR_msgget 186
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 187
+__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl)
+#define __NR_msgrcv 188
+__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv)
+#define __NR_msgsnd 189
+__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
+
+/* ipc/sem.c */
+#define __NR_semget 190
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 191
+__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+#define __NR_semtimedop 192
+__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
+#define __NR_semop 193
+__SYSCALL(__NR_semop, sys_semop)
+
+/* ipc/shm.c */
+#define __NR_shmget 194
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 195
+__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl)
+#define __NR_shmat 196
+__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat)
+#define __NR_shmdt 197
+__SYSCALL(__NR_shmdt, sys_shmdt)
+
+/* net/socket.c */
+#define __NR_socket 198
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_socketpair 199
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_bind 200
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_listen 201
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 202
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_connect 203
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_getsockname 204
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 205
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_sendto 206
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recvfrom 207
+__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
+#define __NR_setsockopt 208
+__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
+#define __NR_getsockopt 209
+__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
+#define __NR_shutdown 210
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_sendmsg 211
+__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 212
+__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg)
+
+/* mm/filemap.c */
+#define __NR_readahead 213
+__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead)
+
+/* mm/nommu.c, also with MMU */
+#define __NR_brk 214
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_munmap 215
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_mremap 216
+__SYSCALL(__NR_mremap, sys_mremap)
+
+/* security/keys/keyctl.c */
+#define __NR_add_key 217
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 218
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 219
+__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl)
+
+/* arch/example/kernel/sys_example.c */
+#define __NR_clone 220
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_execve 221
+__SC_COMP(__NR_execve, sys_execve, compat_sys_execve)
+
+#define __NR3264_mmap 222
+__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
+/* mm/fadvise.c */
+#define __NR3264_fadvise64 223
+__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64)
+
+/* mm/, CONFIG_MMU only */
+#ifndef __ARCH_NOMMU
+#define __NR_swapon 224
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_swapoff 225
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_mprotect 226
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_msync 227
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_mlock 228
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 229
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 230
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 231
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_mincore 232
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 233
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_remap_file_pages 234
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+#define __NR_mbind 235
+__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind)
+#define __NR_get_mempolicy 236
+__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy)
+#define __NR_set_mempolicy 237
+__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy)
+#define __NR_migrate_pages 238
+__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages)
+#define __NR_move_pages 239
+__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages)
+#endif
+
+#define __NR_rt_tgsigqueueinfo 240
+__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
+	  compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 241
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_accept4 242
+__SYSCALL(__NR_accept4, sys_accept4)
+#define __NR_recvmmsg 243
+__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
+
+/*
+ * Architectures may provide up to 16 syscalls of their own
+ * starting with this value.
+ */
+#define __NR_arch_specific_syscall 244
+
+#define __NR_wait4 260
+__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#define __NR_prlimit64 261
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_fanotify_init 262
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 263
+__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at         264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at         265
+__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
+	  compat_sys_open_by_handle_at)
+#define __NR_clock_adjtime 266
+__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
+#define __NR_syncfs 267
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_setns 268
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
+#define __NR_process_vm_readv 270
+__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
+          compat_sys_process_vm_readv)
+#define __NR_process_vm_writev 271
+__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
+          compat_sys_process_vm_writev)
+#define __NR_kcmp 272
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 273
+__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 276
+__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
+#define __NR_getrandom 278
+__SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 279
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
+#define __NR_bpf 280
+__SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
+__SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 284
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 285
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 286
+__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 287
+__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 288
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 289
+__SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
+#define __NR_pkey_free 290
+__SYSCALL(__NR_pkey_free,     sys_pkey_free)
+#define __NR_statx 291
+__SYSCALL(__NR_statx,     sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+
+#undef __NR_syscalls
+#define __NR_syscalls 293
+
+/*
+ * 32 bit systems traditionally used different
+ * syscalls for off_t and loff_t arguments, while
+ * 64 bit systems only need the off_t version.
+ * For new 32 bit platforms, there is no need to
+ * implement the old 32 bit off_t syscalls, so
+ * they take different names.
+ * Here we map the numbers so that both versions
+ * use the same syscall table layout.
+ */
+#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT)
+#define __NR_fcntl __NR3264_fcntl
+#define __NR_statfs __NR3264_statfs
+#define __NR_fstatfs __NR3264_fstatfs
+#define __NR_truncate __NR3264_truncate
+#define __NR_ftruncate __NR3264_ftruncate
+#define __NR_lseek __NR3264_lseek
+#define __NR_sendfile __NR3264_sendfile
+#define __NR_newfstatat __NR3264_fstatat
+#define __NR_fstat __NR3264_fstat
+#define __NR_mmap __NR3264_mmap
+#define __NR_fadvise64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat __NR3264_stat
+#define __NR_lstat __NR3264_lstat
+#endif
+#else
+#define __NR_fcntl64 __NR3264_fcntl
+#define __NR_statfs64 __NR3264_statfs
+#define __NR_fstatfs64 __NR3264_fstatfs
+#define __NR_truncate64 __NR3264_truncate
+#define __NR_ftruncate64 __NR3264_ftruncate
+#define __NR_llseek __NR3264_lseek
+#define __NR_sendfile64 __NR3264_sendfile
+#define __NR_fstatat64 __NR3264_fstatat
+#define __NR_fstat64 __NR3264_fstat
+#define __NR_mmap2 __NR3264_mmap
+#define __NR_fadvise64_64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat64 __NR3264_stat
+#define __NR_lstat64 __NR3264_lstat
+#endif
+#endif
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
new file mode 100644
index 000000000000..48e8a225b985
--- /dev/null
+++ b/tools/include/uapi/linux/in.h
@@ -0,0 +1,301 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions of the Internet Protocol.
+ *
+ * Version:	@(#)in.h	1.0.1	04/21/93
+ *
+ * Authors:	Original taken from the GNU Project <netinet/in.h> file.
+ *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_LINUX_IN_H
+#define _UAPI_LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols.  */
+enum {
+  IPPROTO_IP = 0,		/* Dummy protocol for TCP		*/
+#define IPPROTO_IP		IPPROTO_IP
+  IPPROTO_ICMP = 1,		/* Internet Control Message Protocol	*/
+#define IPPROTO_ICMP		IPPROTO_ICMP
+  IPPROTO_IGMP = 2,		/* Internet Group Management Protocol	*/
+#define IPPROTO_IGMP		IPPROTO_IGMP
+  IPPROTO_IPIP = 4,		/* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP		IPPROTO_IPIP
+  IPPROTO_TCP = 6,		/* Transmission Control Protocol	*/
+#define IPPROTO_TCP		IPPROTO_TCP
+  IPPROTO_EGP = 8,		/* Exterior Gateway Protocol		*/
+#define IPPROTO_EGP		IPPROTO_EGP
+  IPPROTO_PUP = 12,		/* PUP protocol				*/
+#define IPPROTO_PUP		IPPROTO_PUP
+  IPPROTO_UDP = 17,		/* User Datagram Protocol		*/
+#define IPPROTO_UDP		IPPROTO_UDP
+  IPPROTO_IDP = 22,		/* XNS IDP protocol			*/
+#define IPPROTO_IDP		IPPROTO_IDP
+  IPPROTO_TP = 29,		/* SO Transport Protocol Class 4	*/
+#define IPPROTO_TP		IPPROTO_TP
+  IPPROTO_DCCP = 33,		/* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP		IPPROTO_DCCP
+  IPPROTO_IPV6 = 41,		/* IPv6-in-IPv4 tunnelling		*/
+#define IPPROTO_IPV6		IPPROTO_IPV6
+  IPPROTO_RSVP = 46,		/* RSVP Protocol			*/
+#define IPPROTO_RSVP		IPPROTO_RSVP
+  IPPROTO_GRE = 47,		/* Cisco GRE tunnels (rfc 1701,1702)	*/
+#define IPPROTO_GRE		IPPROTO_GRE
+  IPPROTO_ESP = 50,		/* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP		IPPROTO_ESP
+  IPPROTO_AH = 51,		/* Authentication Header protocol	*/
+#define IPPROTO_AH		IPPROTO_AH
+  IPPROTO_MTP = 92,		/* Multicast Transport Protocol		*/
+#define IPPROTO_MTP		IPPROTO_MTP
+  IPPROTO_BEETPH = 94,		/* IP option pseudo header for BEET	*/
+#define IPPROTO_BEETPH		IPPROTO_BEETPH
+  IPPROTO_ENCAP = 98,		/* Encapsulation Header			*/
+#define IPPROTO_ENCAP		IPPROTO_ENCAP
+  IPPROTO_PIM = 103,		/* Protocol Independent Multicast	*/
+#define IPPROTO_PIM		IPPROTO_PIM
+  IPPROTO_COMP = 108,		/* Compression Header Protocol		*/
+#define IPPROTO_COMP		IPPROTO_COMP
+  IPPROTO_SCTP = 132,		/* Stream Control Transport Protocol	*/
+#define IPPROTO_SCTP		IPPROTO_SCTP
+  IPPROTO_UDPLITE = 136,	/* UDP-Lite (RFC 3828)			*/
+#define IPPROTO_UDPLITE		IPPROTO_UDPLITE
+  IPPROTO_MPLS = 137,		/* MPLS in IP (RFC 4023)		*/
+#define IPPROTO_MPLS		IPPROTO_MPLS
+  IPPROTO_RAW = 255,		/* Raw IP packets			*/
+#define IPPROTO_RAW		IPPROTO_RAW
+  IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+	__be32	s_addr;
+};
+#endif
+
+#define IP_TOS		1
+#define IP_TTL		2
+#define IP_HDRINCL	3
+#define IP_OPTIONS	4
+#define IP_ROUTER_ALERT	5
+#define IP_RECVOPTS	6
+#define IP_RETOPTS	7
+#define IP_PKTINFO	8
+#define IP_PKTOPTIONS	9
+#define IP_MTU_DISCOVER	10
+#define IP_RECVERR	11
+#define IP_RECVTTL	12
+#define	IP_RECVTOS	13
+#define IP_MTU		14
+#define IP_FREEBIND	15
+#define IP_IPSEC_POLICY	16
+#define IP_XFRM_POLICY	17
+#define IP_PASSSEC	18
+#define IP_TRANSPARENT	19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS	IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR       20
+#define IP_RECVORIGDSTADDR   IP_ORIGDSTADDR
+
+#define IP_MINTTL       21
+#define IP_NODEFRAG     22
+#define IP_CHECKSUM	23
+#define IP_BIND_ADDRESS_NO_PORT	24
+#define IP_RECVFRAGSIZE	25
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT		0	/* Never send DF frames */
+#define IP_PMTUDISC_WANT		1	/* Use per route hints	*/
+#define IP_PMTUDISC_DO			2	/* Always DF		*/
+#define IP_PMTUDISC_PROBE		3       /* Ignore dst pmtu      */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE		4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT		5
+
+#define IP_MULTICAST_IF			32
+#define IP_MULTICAST_TTL 		33
+#define IP_MULTICAST_LOOP 		34
+#define IP_ADD_MEMBERSHIP		35
+#define IP_DROP_MEMBERSHIP		36
+#define IP_UNBLOCK_SOURCE		37
+#define IP_BLOCK_SOURCE			38
+#define IP_ADD_SOURCE_MEMBERSHIP	39
+#define IP_DROP_SOURCE_MEMBERSHIP	40
+#define IP_MSFILTER			41
+#define MCAST_JOIN_GROUP		42
+#define MCAST_BLOCK_SOURCE		43
+#define MCAST_UNBLOCK_SOURCE		44
+#define MCAST_LEAVE_GROUP		45
+#define MCAST_JOIN_SOURCE_GROUP		46
+#define MCAST_LEAVE_SOURCE_GROUP	47
+#define MCAST_MSFILTER			48
+#define IP_MULTICAST_ALL		49
+#define IP_UNICAST_IF			50
+
+#define MCAST_EXCLUDE	0
+#define MCAST_INCLUDE	1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL        1
+#define IP_DEFAULT_MULTICAST_LOOP       1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq  {
+	struct in_addr imr_multiaddr;	/* IP multicast address of group */
+	struct in_addr imr_interface;	/* local IP address of interface */
+};
+
+struct ip_mreqn {
+	struct in_addr	imr_multiaddr;		/* IP multicast address of group */
+	struct in_addr	imr_address;		/* local IP address of interface */
+	int		imr_ifindex;		/* Interface index */
+};
+
+struct ip_mreq_source {
+	__be32		imr_multiaddr;
+	__be32		imr_interface;
+	__be32		imr_sourceaddr;
+};
+
+struct ip_msfilter {
+	__be32		imsf_multiaddr;
+	__be32		imsf_interface;
+	__u32		imsf_fmode;
+	__u32		imsf_numsrc;
+	__be32		imsf_slist[1];
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+	(sizeof(struct ip_msfilter) - sizeof(__u32) \
+	+ (numsrc) * sizeof(__u32))
+
+struct group_req {
+	__u32				 gr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gr_group;	/* group address */
+};
+
+struct group_source_req {
+	__u32				 gsr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gsr_group;	/* group address */
+	struct __kernel_sockaddr_storage gsr_source;	/* source address */
+};
+
+struct group_filter {
+	__u32				 gf_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gf_group;	/* multicast address */
+	__u32				 gf_fmode;	/* filter mode */
+	__u32				 gf_numsrc;	/* number of sources */
+	struct __kernel_sockaddr_storage gf_slist[1];	/* interface index */
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+	(sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+	+ (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+	int		ipi_ifindex;
+	struct in_addr	ipi_spec_dst;
+	struct in_addr	ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if  __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__	16		/* sizeof(struct sockaddr)	*/
+struct sockaddr_in {
+  __kernel_sa_family_t	sin_family;	/* Address family		*/
+  __be16		sin_port;	/* Port number			*/
+  struct in_addr	sin_addr;	/* Internet address		*/
+
+  /* Pad to size of `struct sockaddr'. */
+  unsigned char		__pad[__SOCK_SIZE__ - sizeof(short int) -
+			sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero	__pad		/* for BSD UNIX comp. -FvK	*/
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define	IN_CLASSA(a)		((((long int) (a)) & 0x80000000) == 0)
+#define	IN_CLASSA_NET		0xff000000
+#define	IN_CLASSA_NSHIFT	24
+#define	IN_CLASSA_HOST		(0xffffffff & ~IN_CLASSA_NET)
+#define	IN_CLASSA_MAX		128
+
+#define	IN_CLASSB(a)		((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define	IN_CLASSB_NET		0xffff0000
+#define	IN_CLASSB_NSHIFT	16
+#define	IN_CLASSB_HOST		(0xffffffff & ~IN_CLASSB_NET)
+#define	IN_CLASSB_MAX		65536
+
+#define	IN_CLASSC(a)		((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define	IN_CLASSC_NET		0xffffff00
+#define	IN_CLASSC_NSHIFT	8
+#define	IN_CLASSC_HOST		(0xffffffff & ~IN_CLASSC_NET)
+
+#define	IN_CLASSD(a)		((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define	IN_MULTICAST(a)		IN_CLASSD(a)
+#define IN_MULTICAST_NET	0xF0000000
+
+#define	IN_EXPERIMENTAL(a)	((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define	IN_BADCLASS(a)		IN_EXPERIMENTAL((a))
+
+/* Address to accept any incoming messages. */
+#define	INADDR_ANY		((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define	INADDR_BROADCAST	((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define	INADDR_NONE		((unsigned long int) 0xffffffff)
+
+/* Network number for local host loopback. */
+#define	IN_LOOPBACKNET		127
+
+/* Address to loopback in software to local host.  */
+#define	INADDR_LOOPBACK		0x7f000001	/* 127.0.0.1   */
+#define	IN_LOOPBACK(a)		((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP   	0xe0000000U	/* 224.0.0.0   */
+#define INADDR_ALLHOSTS_GROUP 	0xe0000001U	/* 224.0.0.1   */
+#define INADDR_ALLRTRS_GROUP    0xe0000002U	/* 224.0.0.2 */
+#define INADDR_MAX_LOCAL_GROUP  0xe00000ffU	/* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h> 
+
+
+#endif /* _UAPI_LINUX_IN_H */
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 2d270c560df3..c36a3a76986a 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: LGPL-2.1
 /* Copyright (c) 2018 Facebook */
 
 #include <stdlib.h>
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index e2a09a155f84..caac3a404dc5 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: LGPL-2.1 */
 /* Copyright (c) 2018 Facebook */
 
 #ifndef __BPF_BTF_H
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 1b09f3175a1f..0cbd1ef8f86d 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -804,7 +804,7 @@ type of fence:
 Second, some types of fence affect the way the memory subsystem
 propagates stores.  When a fence instruction is executed on CPU C:
 
-	For each other CPU C', smb_wmb() forces all po-earlier stores
+	For each other CPU C', smp_wmb() forces all po-earlier stores
 	on C to propagate to C' before any po-later stores do.
 
 	For each other CPU C', any store which propagates to C before
diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt
index ee4309a87fc4..af72700cc20a 100644
--- a/tools/memory-model/Documentation/recipes.txt
+++ b/tools/memory-model/Documentation/recipes.txt
@@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by
 locking will be seen as ordered by CPUs not holding that lock.
 Consider this example:
 
-	/* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */
+	/* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */
 	void CPU0(void)
 	{
 		spin_lock(&mylock);
@@ -292,7 +292,7 @@ and to use smp_load_acquire() instead of smp_rmb().  However, the older
 smp_wmb() and smp_rmb() APIs are still heavily used, so it is important
 to understand their use cases.  The general approach is shown below:
 
-	/* See MP+wmbonceonce+rmbonceonce.litmus. */
+	/* See MP+fencewmbonceonce+fencermbonceonce.litmus. */
 	void CPU0(void)
 	{
 		WRITE_ONCE(x, 1);
@@ -322,9 +322,9 @@ the following write-side code fragment:
 And the xlog_valid_lsn() function in fs/xfs/xfs_log_priv.h contains
 the corresponding read-side code fragment:
 
-	cur_cycle = ACCESS_ONCE(log->l_curr_cycle);
+	cur_cycle = READ_ONCE(log->l_curr_cycle);
 	smp_rmb();
-	cur_block = ACCESS_ONCE(log->l_curr_block);
+	cur_block = READ_ONCE(log->l_curr_block);
 
 Alternatively, consider the following comment in function
 perf_output_put_handle() in kernel/events/ring_buffer.c:
@@ -360,7 +360,7 @@ can be seen in the LB+poonceonces.litmus litmus test.
 One way of avoiding the counter-intuitive outcome is through the use of a
 control dependency paired with a full memory barrier:
 
-	/* See LB+ctrlonceonce+mbonceonce.litmus. */
+	/* See LB+fencembonceonce+ctrlonceonce.litmus. */
 	void CPU0(void)
 	{
 		r0 = READ_ONCE(x);
@@ -476,7 +476,7 @@ that one CPU first stores to one variable and then loads from a second,
 while another CPU stores to the second variable and then loads from the
 first.  Preserving order requires nothing less than full barriers:
 
-	/* See SB+mbonceonces.litmus. */
+	/* See SB+fencembonceonces.litmus. */
 	void CPU0(void)
 	{
 		WRITE_ONCE(x, 1);
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 734f7feaa5dc..ee987ce20aae 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -35,13 +35,13 @@ BASIC USAGE: HERD7
 The memory model is used, in conjunction with "herd7", to exhaustively
 explore the state space of small litmus tests.
 
-For example, to run SB+mbonceonces.litmus against the memory model:
+For example, to run SB+fencembonceonces.litmus against the memory model:
 
-  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+mbonceonces.litmus
+  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+fencembonceonces.litmus
 
 Here is the corresponding output:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   States 3
   0:r0=0; 1:r0=1;
   0:r0=1; 1:r0=0;
@@ -50,8 +50,8 @@ Here is the corresponding output:
   Witnesses
   Positive: 0 Negative: 3
   Condition exists (0:r0=0 /\ 1:r0=0)
-  Observation SB+mbonceonces Never 0 3
-  Time SB+mbonceonces 0.01
+  Observation SB+fencembonceonces Never 0 3
+  Time SB+fencembonceonces 0.01
   Hash=d66d99523e2cac6b06e66f4c995ebb48
 
 The "Positive: 0 Negative: 3" and the "Never 0 3" each indicate that
@@ -67,16 +67,16 @@ BASIC USAGE: KLITMUS7
 The "klitmus7" tool converts a litmus test into a Linux kernel module,
 which may then be loaded and run.
 
-For example, to run SB+mbonceonces.litmus against hardware:
+For example, to run SB+fencembonceonces.litmus against hardware:
 
   $ mkdir mymodules
-  $ klitmus7 -o mymodules litmus-tests/SB+mbonceonces.litmus
+  $ klitmus7 -o mymodules litmus-tests/SB+fencembonceonces.litmus
   $ cd mymodules ; make
   $ sudo sh run.sh
 
 The corresponding output includes:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   Histogram (3 states)
   644580  :>0:r0=1; 1:r0=0;
   644328  :>0:r0=0; 1:r0=1;
@@ -86,8 +86,8 @@ The corresponding output includes:
   Positive: 0, Negative: 2000000
   Condition exists (0:r0=0 /\ 1:r0=0) is NOT validated
   Hash=d66d99523e2cac6b06e66f4c995ebb48
-  Observation SB+mbonceonces Never 0 2000000
-  Time SB+mbonceonces 0.16
+  Observation SB+fencembonceonces Never 0 2000000
+  Time SB+fencembonceonces 0.16
 
 The "Positive: 0 Negative: 2000000" and the "Never 0 2000000" indicate
 that during two million trials, the state specified in this litmus
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 64f5740e0e75..b84fb2f67109 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -13,7 +13,7 @@
 
 "Linux-kernel memory consistency model"
 
-enum Accesses = 'once (*READ_ONCE,WRITE_ONCE,ACCESS_ONCE*) ||
+enum Accesses = 'once (*READ_ONCE,WRITE_ONCE*) ||
 		'release (*smp_store_release*) ||
 		'acquire (*smp_load_acquire*) ||
 		'noreturn (* R of non-return RMW *)
diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
index 98a3716efa37..e729d2776e89 100644
--- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
+++ b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
@@ -1,4 +1,4 @@
-C IRIW+mbonceonces+OnceOnce
+C IRIW+fencembonceonces+OnceOnce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
index 7a39a0aaa976..0f749e419b34 100644
--- a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
+++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
@@ -1,4 +1,4 @@
-C ISA2+pooncelock+pooncelock+pombonce.litmus
+C ISA2+pooncelock+pooncelock+pombonce
 
 (*
  * Result: Sometimes
diff --git a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
index de6708229dd1..4727f5aaf03b 100644
--- a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
@@ -1,4 +1,4 @@
-C LB+ctrlonceonce+mbonceonce
+C LB+fencembonceonce+ctrlonceonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
index c078f38ff27a..a273da9faa6d 100644
--- a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
@@ -1,4 +1,4 @@
-C MP+wmbonceonce+rmbonceonce
+C MP+fencewmbonceonce+fencermbonceonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/R+mbonceonces.litmus b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
index a0e884ad2132..222a0b850b4a 100644
--- a/tools/memory-model/litmus-tests/R+mbonceonces.litmus
+++ b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
@@ -1,4 +1,4 @@
-C R+mbonceonces
+C R+fencembonceonces
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 17eb9a8c222d..4581ec2d3c57 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -18,7 +18,7 @@ CoWW+poonceonce.litmus
 	Test of write-write coherence, that is, whether or not two
 	successive writes to the same variable are ordered.
 
-IRIW+mbonceonces+OnceOnce.litmus
+IRIW+fencembonceonces+OnceOnce.litmus
 	Test of independent reads from independent writes with smp_mb()
 	between each pairs of reads.  In other words, is smp_mb()
 	sufficient to cause two different reading processes to agree on
@@ -47,7 +47,7 @@ ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
 	Can a release-acquire chain order a prior store against
 	a later load?
 
-LB+ctrlonceonce+mbonceonce.litmus
+LB+fencembonceonce+ctrlonceonce.litmus
 	Does a control dependency and an smp_mb() suffice for the
 	load-buffering litmus test, where each process reads from one
 	of two variables then writes to the other?
@@ -88,14 +88,14 @@ MP+porevlocks.litmus
 	As below, but with the first access of the writer process
 	and the second access of reader process protected by a lock.
 
-MP+wmbonceonce+rmbonceonce.litmus
+MP+fencewmbonceonce+fencermbonceonce.litmus
 	Does a smp_wmb() (between the stores) and an smp_rmb() (between
 	the loads) suffice for the message-passing litmus test, where one
 	process writes data and then a flag, and the other process reads
 	the flag and then the data.  (This is similar to the ISA2 tests,
 	but with two processes instead of three.)
 
-R+mbonceonces.litmus
+R+fencembonceonces.litmus
 	This is the fully ordered (via smp_mb()) version of one of
 	the classic counterintuitive litmus tests that illustrates the
 	effects of store propagation delays.
@@ -103,7 +103,7 @@ R+mbonceonces.litmus
 R+poonceonces.litmus
 	As above, but without the smp_mb() invocations.
 
-SB+mbonceonces.litmus
+SB+fencembonceonces.litmus
 	This is the fully ordered (again, via smp_mb() version of store
 	buffering, which forms the core of Dekker's mutual-exclusion
 	algorithm.
@@ -111,15 +111,24 @@ SB+mbonceonces.litmus
 SB+poonceonces.litmus
 	As above, but without the smp_mb() invocations.
 
+SB+rfionceonce-poonceonces.litmus
+	This litmus test demonstrates that LKMM is not fully multicopy
+	atomic.  (Neither is it other multicopy atomic.)  This litmus test
+	also demonstrates the "locations" debugging aid, which designates
+	additional registers and locations to be printed out in the dump
+	of final states in the herd7 output.  Without the "locations"
+	statement, only those registers and locations mentioned in the
+	"exists" clause will be printed.
+
 S+poonceonces.litmus
 	As below, but without the smp_wmb() and acquire load.
 
-S+wmbonceonce+poacquireonce.litmus
+S+fencewmbonceonce+poacquireonce.litmus
 	Can a smp_wmb(), instead of a release, and an acquire order
 	a prior store against a subsequent store?
 
 WRC+poonceonces+Once.litmus
-WRC+pooncerelease+rmbonceonce+Once.litmus
+WRC+pooncerelease+fencermbonceonce+Once.litmus
 	These two are members of an extension of the MP litmus-test
 	class in which the first write is moved to a separate process.
 	The second is forbidden because smp_store_release() is
@@ -134,7 +143,7 @@ Z6.0+pooncelock+poonceLock+pombonce.litmus
 	As above, but with smp_mb__after_spinlock() immediately
 	following the spin_lock().
 
-Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
 	Is the ordering provided by a release-acquire chain sufficient
 	to make ordering apparent to accesses by a process that does
 	not participate in that release-acquire chain?
diff --git a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
index c53350205d28..18479823cd6c 100644
--- a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus
+++ b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
@@ -1,4 +1,4 @@
-C S+wmbonceonce+poacquireonce
+C S+fencewmbonceonce+poacquireonce
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
index 74b874ffa8da..ed5fff18d223 100644
--- a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus
+++ b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
@@ -1,4 +1,4 @@
-C SB+mbonceonces
+C SB+fencembonceonces
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
new file mode 100644
index 000000000000..04a16603660b
--- /dev/null
+++ b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
@@ -0,0 +1,32 @@
+C SB+rfionceonce-poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test demonstrates that LKMM is not fully multicopy atomic.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	int r1;
+	int r2;
+
+	WRITE_ONCE(*x, 1);
+	r1 = READ_ONCE(*x);
+	r2 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+	int r3;
+	int r4;
+
+	WRITE_ONCE(*y, 1);
+	r3 = READ_ONCE(*y);
+	r4 = READ_ONCE(*x);
+}
+
+locations [0:r1; 1:r3; x; y] (* Debug aid: Print things not in "exists". *)
+exists (0:r2=0 /\ 1:r4=0)
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
index ad3448b941e6..e9947250d7de 100644
--- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
+++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
@@ -1,4 +1,4 @@
-C WRC+pooncerelease+rmbonceonce+Once
+C WRC+pooncerelease+fencermbonceonce+Once
 
 (*
  * Result: Never
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
index a20fc3fafb53..88e70b87a683 100644
--- a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
@@ -1,4 +1,4 @@
-C Z6.0+pooncerelease+poacquirerelease+mbonceonce
+C Z6.0+pooncerelease+poacquirerelease+fencembonceonce
 
 (*
  * Result: Sometimes
diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh
index af0aa15ab84e..ca528f9a24d4 100644..100755
--- a/tools/memory-model/scripts/checkalllitmus.sh
+++ b/tools/memory-model/scripts/checkalllitmus.sh
@@ -9,7 +9,7 @@
 # appended.
 #
 # Usage:
-#	sh checkalllitmus.sh [ directory ]
+#	checkalllitmus.sh [ directory ]
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, whose default is defined by the checklitmus.sh script.
diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh
index e2e477472844..bf12a75c0719 100644..100755
--- a/tools/memory-model/scripts/checklitmus.sh
+++ b/tools/memory-model/scripts/checklitmus.sh
@@ -8,7 +8,7 @@
 # with ".out" appended.
 #
 # Usage:
-#	sh checklitmus.sh file.litmus
+#	checklitmus.sh file.litmus
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, which default to "-conf linux-kernel.cfg".  Thus,
diff --git a/tools/objtool/arch/x86/include/asm/orc_types.h b/tools/objtool/arch/x86/include/asm/orc_types.h
index 9c9dc579bd7d..46f516dd80ce 100644
--- a/tools/objtool/arch/x86/include/asm/orc_types.h
+++ b/tools/objtool/arch/x86/include/asm/orc_types.h
@@ -88,6 +88,7 @@ struct orc_entry {
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
+	unsigned	end:1;
 } __packed;
 
 /*
@@ -101,6 +102,7 @@ struct unwind_hint {
 	s16		sp_offset;
 	u8		sp_reg;
 	u8		type;
+	u8		end;
 };
 #endif /* __ASSEMBLY__ */
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f4a25bd1871f..2928939b98ec 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1157,6 +1157,7 @@ static int read_unwind_hints(struct objtool_file *file)
 
 		cfa->offset = hint->sp_offset;
 		insn->state.type = hint->type;
+		insn->state.end = hint->end;
 	}
 
 	return 0;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index c6b68fcb926f..95700a2bcb7c 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -31,7 +31,7 @@ struct insn_state {
 	int stack_size;
 	unsigned char type;
 	bool bp_scratch;
-	bool drap;
+	bool drap, end;
 	int drap_reg, drap_offset;
 	struct cfi_reg vals[CFI_NUM_REGS];
 };
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index c3343820916a..faa444270ee3 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -203,7 +203,8 @@ int orc_dump(const char *_objname)
 
 		print_reg(orc[i].bp_reg, orc[i].bp_offset);
 
-		printf(" type:%s\n", orc_type_name(orc[i].type));
+		printf(" type:%s end:%d\n",
+		       orc_type_name(orc[i].type), orc[i].end);
 	}
 
 	elf_end(elf);
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 18384d9be4e1..3f98dcfbc177 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -31,6 +31,8 @@ int create_orc(struct objtool_file *file)
 		struct cfi_reg *cfa = &insn->state.cfa;
 		struct cfi_reg *bp = &insn->state.regs[CFI_BP];
 
+		orc->end = insn->state.end;
+
 		if (cfa->base == CFI_UNDEFINED) {
 			orc->sp_reg = ORC_REG_UNDEFINED;
 			continue;
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 11300dbe35c5..236b9b97dfdb 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -18,6 +18,10 @@ various perf commands with the -e option.
 
 OPTIONS
 -------
+-d::
+--desc::
+Print extra event descriptions. (default)
+
 --no-desc::
 Don't print descriptions.
 
@@ -25,11 +29,13 @@ Don't print descriptions.
 --long-desc::
 Print longer event descriptions.
 
+--debug::
+Enable debugging output.
+
 --details::
 Print how named events are resolved internally into perf events, and also
 any extra expressions computed by perf stat.
 
-
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
@@ -234,7 +240,7 @@ perf also supports group leader sampling using the :S specifier.
   perf record -e '{cycles,instructions}:S' ...
   perf report --group
 
-Normally all events in a event group sample, but with :S only
+Normally all events in an event group sample, but with :S only
 the first event (the leader) samples, and it only reads the values of the
 other events in the group.
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 04168da4268e..246dee081efd 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -94,7 +94,7 @@ OPTIONS
 	  "perf report" to view group events together.
 
 --filter=<filter>::
-        Event filter. This option should follow a event selector (-e) which
+        Event filter. This option should follow an event selector (-e) which
 	selects either tracepoint event(s) or a hardware trace PMU
 	(e.g. Intel PT or CoreSight).
 
@@ -153,7 +153,7 @@ OPTIONS
 
 --exclude-perf::
 	Don't record events issued by perf itself. This option should follow
-	a event selector (-e) which selects tracepoint event(s). It adds a
+	an event selector (-e) which selects tracepoint event(s). It adds a
 	filter expression 'common_pid != $PERFPID' to filters. If other
 	'--filter' exists, the new filter expression will be combined with
 	them by '&&'.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f5a3b402589e..f6d1a03c7523 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -54,6 +54,8 @@ endif
 
 ifeq ($(SRCARCH),arm64)
   NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -I$(OUTPUT)arch/arm64/include/generated
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
@@ -905,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
-perf_include_dir = lib/include/perf
-perf_examples_dir = lib/examples/perf
+perf_include_dir = lib/perf/include
+perf_examples_dir = lib/perf/examples
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ecc9fc952655..b3d1b12a5081 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -384,6 +384,8 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
 drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
@@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
 $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
 	$(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
 
+socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c
+socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh
+
+$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
+	$(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
+
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
 vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
 vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(sndrv_ctl_ioctl_array) \
 	$(kcmp_type_array) \
 	$(kvm_ioctl_array) \
+	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
 	$(perf_ioctl_array) \
@@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(sndrv_pcm_ioctl_array) \
 		$(OUTPUT)$(kvm_ioctl_array) \
 		$(OUTPUT)$(kcmp_type_array) \
+		$(OUTPUT)$(socket_ipproto_array) \
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 91de4860faad..f013b115dc86 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -4,3 +4,24 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/arm64/include/generated/asm
+header := $(out)/syscalls.c
+sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, arm64) $(RM) $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000000..52e197317d3e
--- /dev/null
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+# Changed by: Kim Phillips <kim.phillips@arm.com>
+
+gcc=$1
+hostcc=$2
+input=$3
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table_from_c()
+{
+	local sc nr last_sc
+
+	create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+
+	{
+
+	cat <<-_EoHEADER
+		#include <stdio.h>
+		#define __ARCH_WANT_RENAMEAT
+		#include "$input"
+		int main(int argc, char *argv[])
+		{
+	_EoHEADER
+
+	while read sc nr; do
+		printf "%s\n" "	printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);"
+		last_sc=$sc
+	done
+
+	printf "%s\n" "	printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
+	printf "}\n"
+
+	} | $hostcc -o $create_table_exe -x c -
+
+	$create_table_exe
+
+	rm -f $create_table_exe
+}
+
+create_table()
+{
+	echo "static const char *syscalltbl_arm64[] = {"
+	create_table_from_c
+	echo "};"
+}
+
+$gcc -E -dM -x c  $input	       \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -nu	       \
+	|create_table
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index ef5d59a5742e..7c6eeb4633fe 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
 	}
 
 	/*
-	 * Check if return address is on the stack.
+	 * Check if return address is on the stack. If return address
+	 * is in a register (typically R0), it is yet to be saved on
+	 * the stack.
 	 */
-	if (nops != 0 || ops != NULL)
+	if ((nops != 0 || ops != NULL) &&
+		!(nops == 1 && ops[0].atom == DW_OP_regx &&
+			ops[0].number2 == 0 && ops[0].offset == 0))
 		return 0;
 
 	/*
@@ -246,7 +250,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	if (!chain || chain->nr < 3)
 		return skip_slot;
 
-	ip = chain->ips[2];
+	ip = chain->ips[1];
 
 	thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index d233e2eb9592..aaabab5e2830 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = {
 
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
 {
-	if (strstr(cpuid, "IBM/S390")) {
+	if (strstr(cpuid, "IBM")) {
 		kvm->exit_reasons = sie_exit_reasons;
 		kvm->exit_reasons_isa = "SIE";
 	} else
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 6a8738f7ead3..f3aa9d02a5ab 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2193,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists,
 	fprintf(out, "%s\n", bf);
 	fprintf(out, "  -------------------------------------------------------------\n");
 
-	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true);
+	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false);
 }
 
 static void print_pareto(FILE *out)
@@ -2268,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session)
 	fprintf(out, "=================================================\n");
 	fprintf(out, "#\n");
 
-	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false);
+	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true);
 
 	fprintf(out, "\n");
 	fprintf(out, "=================================================\n");
@@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	" s             Toggle full length of symbol and source line columns \n"
 	" q             Return back to cacheline list \n";
 
+	if (!he)
+		return 0;
+
 	/* Display compact version first. */
 	c2c.symbol_full = false;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index d660cb7b222b..39db2ee32d48 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -696,7 +696,7 @@ static void hists__process(struct hists *hists)
 	hists__output_resort(hists, NULL);
 
 	hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
-		       symbol_conf.use_callchain);
+		       !symbol_conf.use_callchain);
 }
 
 static void data__fprintf(void)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c04dc7b53797..02f7a3c27761 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -478,8 +478,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
 		hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
-			       symbol_conf.use_callchain ||
-			       symbol_conf.show_branchflag_count);
+			       !(symbol_conf.use_callchain ||
+			         symbol_conf.show_branchflag_count));
 		fprintf(stdout, "\n\n");
 	}
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 05be023c3f0e..d097b5b47eb8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,18 +296,6 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
-/*
- * Does the counter have nsecs as a unit?
- */
-static inline int nsec_counter(struct perf_evsel *evsel)
-{
-	if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
-	    perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		return 1;
-
-	return 0;
-}
-
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -1058,34 +1046,6 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused,
 		fprintf(os->fh, "%*s ", metric_only_len, unit);
 }
 
-static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
-	FILE *output = stat_config.output;
-	double msecs = avg / NSEC_PER_MSEC;
-	const char *fmt_v, *fmt_n;
-	char name[25];
-
-	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
-	fmt_n = csv_output ? "%s" : "%-25s";
-
-	aggr_printout(evsel, id, nr);
-
-	scnprintf(name, sizeof(name), "%s%s",
-		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-
-	fprintf(output, fmt_v, msecs, csv_sep);
-
-	if (csv_output)
-		fprintf(output, "%s%s", evsel->unit, csv_sep);
-	else
-		fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
-
-	fprintf(output, fmt_n, name);
-
-	if (evsel->cgrp)
-		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-}
-
 static int first_shadow_cpu(struct perf_evsel *evsel, int id)
 {
 	int i;
@@ -1241,11 +1201,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		return;
 	}
 
-	if (metric_only)
-		/* nothing */;
-	else if (nsec_counter(counter))
-		nsec_printout(id, nr, counter, uval);
-	else
+	if (!metric_only)
 		abs_printout(id, nr, counter, uval);
 
 	out.print_metric = pm;
@@ -1331,7 +1287,7 @@ static void collect_all_aliases(struct perf_evsel *counter,
 		    alias->scale != counter->scale ||
 		    alias->cgrp != counter->cgrp ||
 		    strcmp(alias->unit, counter->unit) ||
-		    nsec_counter(alias) != nsec_counter(counter))
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
 			break;
 		alias->merged_stat = true;
 		cb(alias, data, false);
@@ -2449,6 +2405,18 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (transaction_run) {
+		/* Handle -T as -M transaction. Once platform specific metrics
+		 * support has been added to the json files, all archictures
+		 * will use this approach. To determine transaction support
+		 * on an architecture test for such a metric name.
+		 */
+		if (metricgroup__has_metric("transaction")) {
+			struct option opt = { .value = &evsel_list };
+
+			return metricgroup__parse_groups(&opt, "transaction",
+							 &metric_events);
+		}
+
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
 			err = parse_events(evsel_list, transaction_attrs,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ffdc2769ff9f..d21d8751e749 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -307,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
 	hists__fprintf(hists, false, top->print_entries - printed, win_width,
-		       top->min_percent, stdout, symbol_conf.use_callchain);
+		       top->min_percent, stdout, !symbol_conf.use_callchain);
 }
 
 static void prompt_integer(int *target, const char *msg)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6a748eca2edb..88561eed7950 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -291,7 +291,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha
 {
 	int idx = val - sa->offset;
 
-	if (idx < 0 || idx >= sa->nr_entries)
+	if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
 		return scnprintf(bf, size, intfmt, val);
 
 	return scnprintf(bf, size, "%s", sa->entries[idx]);
@@ -761,10 +761,12 @@ static struct syscall_fmt {
 	  .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
 	{ .name	    = "socket",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "socketpair",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "stat", .alias = "newstat", },
 	{ .name	    = "statx",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT,	 /* fdat */ },
@@ -2990,6 +2992,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 
 		if (trace__validate_ev_qualifier(trace))
 			goto out;
+		trace->trace_syscalls = true;
 	}
 
 	err = 0;
@@ -3045,7 +3048,7 @@ int cmd_trace(int argc, const char **argv)
 		},
 		.output = stderr,
 		.show_comm = true,
-		.trace_syscalls = true,
+		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
 	};
@@ -3191,13 +3194,7 @@ int cmd_trace(int argc, const char **argv)
 
 	if (!trace.trace_syscalls && !trace.trace_pgfaults &&
 	    trace.evlist->nr_entries == 0 /* Was --events used? */) {
-		pr_err("Please specify something to trace.\n");
-		return -1;
-	}
-
-	if (!trace.trace_syscalls && trace.ev_qualifier) {
-		pr_err("The -e option can't be used with --no-syscalls.\n");
-		goto out;
+		trace.trace_syscalls = true;
 	}
 
 	if (output_name != NULL) {
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 10f333e2e825..de28466c0186 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
+include/uapi/linux/in.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
@@ -35,6 +36,7 @@ arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
+arch/arm64/include/uapi/asm/unistd.h
 arch/alpha/include/uapi/asm/errno.h
 arch/mips/include/asm/errno.h
 arch/mips/include/uapi/asm/errno.h
@@ -53,6 +55,7 @@ include/uapi/asm-generic/errno.h
 include/uapi/asm-generic/errno-base.h
 include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
+include/uapi/asm-generic/unistd.h
 '
 
 check_2 () {
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index dd764ad5efdf..a63aa6241b7f 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #ifndef _PERF_BPF_H
 #define _PERF_BPF_H
+
+#include <uapi/linux/bpf.h>
+
 #define SEC(NAME) __attribute__((section(NAME),  used))
 
 #define probe(function, vars) \
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index d215714f48df..21bf7f5a3cf5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -25,7 +25,9 @@ static inline unsigned long long rdclock(void)
 	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
+#ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS			1024
+#endif
 
 extern const char *input_name;
 extern bool perf_host, perf_guest;
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
index bc03c06c3918..752e47eb6977 100644
--- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
@@ -12,6 +12,21 @@
         "ArchStdEvent": "L1D_CACHE_REFILL_WR",
     },
     {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
         "ArchStdEvent": "L1D_TLB_REFILL_RD",
     },
     {
@@ -24,9 +39,75 @@
         "ArchStdEvent": "L1D_TLB_WR",
     },
     {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR",
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_WR",
-   }
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_SMC",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
index 0feedb40f30f..b6b7f29ca831 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
@@ -1,107 +1,125 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1I_L3_LOCAL_WRITES",
 		"BriefDescription": "L1I L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1D_L3_LOCAL_WRITES",
 		"BriefDescription": "L1D L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1I_L3_REMOTE_WRITES",
 		"BriefDescription": "L1I L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L3_REMOTE_WRITES",
 		"BriefDescription": "L1D L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_CACHELINE_INVALIDATES",
 		"BriefDescription": "L1I Cacheline Invalidates",
 		"PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
index 9a002b6967f1..436ce33f1182 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
@@ -1,335 +1,391 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB1_GPAGE_WRITES",
 		"BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
 		"PublicDescription": "Counter:132	Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB1_MISSES",
 		"BriefDescription": "L1C TLB1 Misses",
 		"PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "176",
 		"EventName": "L1I_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "218",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "219",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "220",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
index 8f653c9d899d..17fb5241928b 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
@@ -1,47 +1,55 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index aa4dfb46b65b..e7a3524b748f 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -1,317 +1,370 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "Counter:128	Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB2_WRITES",
 		"BriefDescription": "DTLB2 Writes",
 		"PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB2_MISSES",
 		"BriefDescription": "DTLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB2_HPAGE_WRITES",
 		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB2_GPAGE_WRITES",
 		"BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
 		"PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB2_WRITES",
 		"BriefDescription": "ITLB2 Writes",
 		"PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB2_MISSES",
 		"BriefDescription": "ITLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_ENGINES_BUSY",
 		"BriefDescription": "TLB2 Engines Busy",
 		"PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB2_MISSES",
 		"BriefDescription": "L1C TLB2 Misses",
 		"PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "224",
 		"EventName": "BCD_DFP_EXECUTION_SLOTS",
 		"BriefDescription": "BCD DFP Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "225",
 		"EventName": "VX_BCD_EXECUTION_SLOTS",
 		"BriefDescription": "VX BCD Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "226",
 		"EventName": "DECIMAL_INSTRUCTIONS",
 		"BriefDescription": "Decimal Instructions",
 		"PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "232",
 		"EventName": "LAST_HOST_TRANSLATIONS",
 		"BriefDescription": "Last host translation done",
 		"PublicDescription": "Last Host Translation done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "243",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "244",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "245",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
index b6d7fec7c2e7..b7b42a870bb0 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
@@ -1,143 +1,167 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
 		"PublicDescription": "Incremented by one for every store sent to Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
index 8682126aabb2..162251037219 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
@@ -1,209 +1,244 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1D_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1D L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index db3a594ee1e4..68c92bb599ee 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -233,6 +233,8 @@ static struct map {
 	{ "QPI LL", "uncore_qpi" },
 	{ "SBO", "uncore_sbox" },
 	{ "iMPH-U", "uncore_arb" },
+	{ "CPU-M-CF", "cpum_cf" },
+	{ "CPU-M-SF", "cpum_sf" },
 	{}
 };
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index dd850a26d579..d7a5e1b9aa6f 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
 	if (!t->subtest.get_nr)
 		pr_debug("%s:", t->desc);
 	else
-		pr_debug("%s subtest %d:", t->desc, subtest);
+		pr_debug("%s subtest %d:", t->desc, subtest + 1);
 
 	switch (err) {
 	case TEST_OK:
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 61211918bfba..3b97ac018d5a 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1322,6 +1322,14 @@ static int test__intel_pt(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_complex_name(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
@@ -1658,6 +1666,11 @@ static struct evlist_test test__events[] = {
 		.check = test__intel_pt,
 		.id    = 52,
 	},
+	{
+		.name  = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk",
+		.check = test__checkevent_complex_name,
+		.id    = 53
+	}
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1676,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = {
 		.check = test__checkevent_pmu_partial_time_callgraph,
 		.id    = 2,
 	},
+	{
+		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",
+		.check = test__checkevent_complex_name,
+		.id    = 3,
+	}
 };
 
 struct terms_test {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 94e513e62b34..3013ac8f83d0 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -13,11 +13,24 @@
 libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
+event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?'
+
+add_libc_inet_pton_event() {
+
+	event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \
+			grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))")
+
+	if [ $? -ne 0 -o -z "$event_name" ] ; then
+		printf "FAIL: could not add event\n"
+		return 1
+	fi
+}
+
 trace_libc_inet_pton_backtrace() {
 
 	expected=`mktemp -u /tmp/expected.XXX`
 
-	echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected
+	echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected
 	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 	case "$(uname -m)" in
 	s390x)
@@ -26,6 +39,12 @@ trace_libc_inet_pton_backtrace() {
 		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
+	ppc64|ppc64le)
+		eventattr='max-stack=4'
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		;;
 	*)
 		eventattr='max-stack=3'
 		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
@@ -35,7 +54,7 @@ trace_libc_inet_pton_backtrace() {
 
 	perf_data=`mktemp -u /tmp/perf.data.XXX`
 	perf_script=`mktemp -u /tmp/perf.script.XXX`
-	perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
 	perf script -i $perf_data > $perf_script
 
 	exec 3<$perf_script
@@ -46,7 +65,7 @@ trace_libc_inet_pton_backtrace() {
 		echo "$line" | egrep -q "$pattern"
 		if [ $? -ne 0 ] ; then
 			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
-			exit 1
+			return 1
 		fi
 	done
 
@@ -56,13 +75,20 @@ trace_libc_inet_pton_backtrace() {
 	# even if the perf script output does not match.
 }
 
+delete_libc_inet_pton_event() {
+
+	if [ -n "$event_name" ] ; then
+		perf probe -q -d $event_name
+	fi
+}
+
 # Check for IPv6 interface existence
 ip a sh lo | fgrep -q inet6 || exit 2
 
 skip_if_no_perf_probe && \
-perf probe -q $libc inet_pton && \
+add_libc_inet_pton_event && \
 trace_libc_inet_pton_backtrace
 err=$?
 rm -f ${perf_data} ${perf_script} ${expected}
-perf probe -q -d probe_libc:inet_pton
+delete_libc_inet_pton_event
 exit $err
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index 66330d4b739b..f528ba35e140 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,4 +7,5 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += socket.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 984a504d335c..9615af5d412b 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
 size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
 
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 2149d3a98e42..9d3816815e60 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,13 +1,14 @@
 #!/bin/sh
 
-drm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
+
 printf "#ifndef DRM_COMMAND_BASE\n"
-grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+grep "#define DRM_COMMAND_BASE" $header_dir/drm.h
 printf "#endif\n"
 
 printf "static const char *drm_ioctl_cmds[] = {\n"
-grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \
 	sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[	 ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/	[\2] = "\1",/g'
-grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $drm_header_dir/i915_drm.h | \
+grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $header_dir/i915_drm.h | \
 	sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[	 ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index 40d063b8c082..a3c304caa336 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kcmp_types[] = {\n"
 regex='^[[:space:]]+(KCMP_(\w+)),'
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index bd28817afced..c4699fd46bb6 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,10 +1,10 @@
 #!/bin/sh
 
-kvm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kvm_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${kvm_header_dir}/kvm.h	| \
+egrep $regex ${header_dir}/kvm.h	| \
 	sed -r "s/$regex/\2 \1/g"	| \
 	egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 60ef8640ee70..431639eb4d29 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *madvise_advices[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index faea4237c793..6492c74df928 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *perf_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index 62e51a02b839..e0a51aeb20b2 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *pkey_alloc_access_rights[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index aad5ab130539..eb511bb5fbd3 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index b7e9ef6b2f55..6818392968b2 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
new file mode 100644
index 000000000000..65227269384b
--- /dev/null
+++ b/tools/perf/trace/beauty/socket.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace/beauty/socket.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <sys/types.h>
+#include <sys/socket.h>
+
+static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size)
+{
+#include "trace/beauty/generated/socket_ipproto_array.c"
+	static DEFINE_STRARRAY(socket_ipproto);
+
+	return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol);
+}
+
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int domain = syscall_arg__val(arg, 0);
+
+	if (domain == AF_INET || domain == AF_INET6)
+		return socket__scnprintf_ipproto(arg->val, bf, size);
+
+	return syscall_arg__scnprintf_int(bf, size, arg);
+}
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
new file mode 100755
index 000000000000..a3cc24633bec
--- /dev/null
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *socket_ipproto[] = {\n"
+regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
+
+egrep $regex ${header_dir}/in.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 76f1de697787..0f6a5197d0be 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,17 +1,17 @@
 #!/bin/sh
 
-vhost_virtio_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 69b7a28f7a1c..74c4ae1f0a05 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -529,7 +529,7 @@ out:
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       char *bf, size_t bfsz, FILE *fp,
-			       bool use_callchain)
+			       bool ignore_callchains)
 {
 	int ret;
 	int callchain_ret = 0;
@@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 
 	ret = fprintf(fp, "%s\n", bf);
 
-	if (hist_entry__has_callchains(he) && use_callchain)
+	if (hist_entry__has_callchains(he) && !ignore_callchains)
 		callchain_ret = hist_entry_callchain__fprintf(he, total_period,
 							      0, fp);
 
@@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp)
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain)
+		      bool ignore_callchains)
 {
 	struct rb_node *nd;
 	size_t ret = 0;
@@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		if (percent < min_pcnt)
 			continue;
 
-		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
+		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains);
 
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index cee658733e2c..3d02ae38ec56 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj)
 
 	err = bpf_object__load(obj);
 	if (err) {
-		pr_debug("bpf: load objects failed\n");
+		char bf[128];
+		libbpf_strerror(err, bf, sizeof(bf));
+		pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
 		return err;
 	}
 	return 0;
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 7798a2cc8a86..31279a7bd919 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,}
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	if (cs)
-		refcount_inc(&cs->refcnt);
-	return cs;
+	if (cs && refcount_inc_not_zero(&cs->refcnt))
+		return cs;
+
+	return NULL;
 }
 
 static void comm_str__put(struct comm_str *cs)
@@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
 		parent = *p;
 		iter = rb_entry(parent, struct comm_str, rb_node);
 
+		/*
+		 * If we race with comm_str__put, iter->refcnt is 0
+		 * and it will be removed within comm_str__put call
+		 * shortly, ignore it in this search.
+		 */
 		cmp = strcmp(str, iter->str);
-		if (!cmp)
-			return comm_str__get(iter);
+		if (!cmp && comm_str__get(iter))
+			return iter;
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 4d5fc374e730..938def6d0bb9 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -31,6 +31,8 @@
 #endif
 #endif
 
+#define CS_ETM_INVAL_ADDR	0xdeadbeefdeadbeefUL
+
 struct cs_etm_decoder {
 	void *data;
 	void (*packet_printer)(const char *msg);
@@ -261,8 +263,8 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 	decoder->tail = 0;
 	decoder->packet_count = 0;
 	for (i = 0; i < MAX_BUFFER; i++) {
-		decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
-		decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
+		decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
+		decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
 		decoder->packet_buffer[i].last_instr_taken_branch = false;
 		decoder->packet_buffer[i].exc = false;
 		decoder->packet_buffer[i].exc_ret = false;
@@ -295,8 +297,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 	decoder->packet_buffer[et].exc = false;
 	decoder->packet_buffer[et].exc_ret = false;
 	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-	decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
-	decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
+	decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
+	decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 743f5f444304..612b5755f742 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -23,6 +23,7 @@ struct cs_etm_buffer {
 };
 
 enum cs_etm_sample_type {
+	CS_ETM_EMPTY = 0,
 	CS_ETM_RANGE = 1 << 0,
 	CS_ETM_TRACE_ON = 1 << 1,
 };
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 822ba915d144..2ae640257fdb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
 
 static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 {
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
 	/*
 	 * The packet records the execution range with an exclusive end address
 	 *
@@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 	return packet->end_addr - A64_INSTR_SIZE;
 }
 
+static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
+{
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
+	return packet->start_addr;
+}
+
 static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
 {
 	/*
@@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
 
 	be       = &bs->entries[etmq->last_branch_pos];
 	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
-	be->to	 = etmq->packet->start_addr;
+	be->to	 = cs_etm__first_executed_instr(etmq->packet);
 	/* No support for mispredict */
 	be->flags.mispred = 0;
 	be->flags.predicted = 1;
@@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
-	sample.addr = etmq->packet->start_addr;
+	sample.addr = cs_etm__first_executed_instr(etmq->packet);
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
@@ -897,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		etmq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches &&
-	    etmq->prev_packet &&
-	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
-	    etmq->prev_packet->last_instr_taken_branch) {
-		ret = cs_etm__synth_branch_sample(etmq);
-		if (ret)
-			return ret;
+	if (etm->sample_branches && etmq->prev_packet) {
+		bool generate_sample = false;
+
+		/* Generate sample for tracing on packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON)
+			generate_sample = true;
+
+		/* Generate sample for branch taken packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+		    etmq->prev_packet->last_instr_taken_branch)
+			generate_sample = true;
+
+		if (generate_sample) {
+			ret = cs_etm__synth_branch_sample(etmq);
+			if (ret)
+				return ret;
+		}
 	}
 
 	if (etm->sample_branches || etm->synth_opts.last_branch) {
@@ -922,10 +945,17 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 static int cs_etm__flush(struct cs_etm_queue *etmq)
 {
 	int err = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
+	if (!etmq->prev_packet)
+		return 0;
+
+	/* Handle start tracing packet */
+	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+		goto swap_packet;
+
 	if (etmq->etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
 		/*
 		 * Generate a last branch event for the branches left in the
@@ -939,8 +969,22 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 		err = cs_etm__synth_instruction_sample(
 			etmq, addr,
 			etmq->period_instructions);
+		if (err)
+			return err;
+
 		etmq->period_instructions = 0;
 
+	}
+
+	if (etm->sample_branches &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+		err = cs_etm__synth_branch_sample(etmq);
+		if (err)
+			return err;
+	}
+
+swap_packet:
+	if (etmq->etm->synth_opts.last_branch) {
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
@@ -1020,6 +1064,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 					 */
 					cs_etm__flush(etmq);
 					break;
+				case CS_ETM_EMPTY:
+					/*
+					 * Should not receive empty packet,
+					 * report error.
+					 */
+					pr_err("CS ETM Trace: empty packet\n");
+					return -EINVAL;
 				default:
 					break;
 				}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 94fce4f537e9..ddf84b941abf 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -260,6 +260,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 		evsel->attr.sample_period = 1;
 	}
 
+	if (perf_evsel__is_clock(evsel)) {
+		/*
+		 * The evsel->unit points to static alias->unit
+		 * so it's ok to use static string in here.
+		 */
+		static const char *unit = "msec";
+
+		evsel->unit = unit;
+		evsel->scale = 1e-6;
+	}
+
 	return evsel;
 }
 
@@ -848,6 +859,12 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	}
 }
 
+static bool is_dummy_event(struct perf_evsel *evsel)
+{
+	return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
+	       (evsel->attr.config == PERF_COUNT_SW_DUMMY);
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1086,6 +1103,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		else
 			perf_evsel__reset_sample_bit(evsel, PERIOD);
 	}
+
+	/*
+	 * For initial_delay, a dummy event is added implicitly.
+	 * The software event will trigger -EOPNOTSUPP error out,
+	 * if BRANCH_STACK bit is set.
+	 */
+	if (opts->initial_delay && is_dummy_event(evsel))
+		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d277930b19a1..973c03167947 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -402,10 +402,13 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel);
 
 static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 {
-	struct perf_event_attr *attr = &evsel->attr;
+	return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
+}
 
-	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
-		(attr->type == PERF_TYPE_SOFTWARE);
+static inline bool perf_evsel__is_clock(struct perf_evsel *evsel)
+{
+	return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+	       perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
 }
 
 struct perf_attr_details {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 653ff65aa2c3..5af58aac91ad 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2587,7 +2587,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(NUMA_TOPOLOGY,	numa_topology,	true),
 	FEAT_OPN(BRANCH_STACK,	branch_stack,	false),
 	FEAT_OPR(PMU_MAPPINGS,	pmu_mappings,	false),
-	FEAT_OPN(GROUP_DESC,	group_desc,	false),
+	FEAT_OPR(GROUP_DESC,	group_desc,	false),
 	FEAT_OPN(AUXTRACE,	auxtrace,	false),
 	FEAT_OPN(STAT,		stat,		false),
 	FEAT_OPN(CACHE,		cache,		true),
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 73049f7f0f60..3badd7f1e1b8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -181,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain);
+		      bool ignore_callchains);
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e7b4a8b513f2..b300a3973448 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -408,23 +408,16 @@ out_err:
 }
 
 /*
- * Caller must eventually drop thread->refcnt returned with a successful
- * lookup/new thread inserted.
+ * Front-end cache - TID lookups come in blocks,
+ * so most of the time we dont have to look up
+ * the full rbtree:
  */
-static struct thread *____machine__findnew_thread(struct machine *machine,
-						  struct threads *threads,
-						  pid_t pid, pid_t tid,
-						  bool create)
+static struct thread*
+__threads__get_last_match(struct threads *threads, struct machine *machine,
+			  int pid, int tid)
 {
-	struct rb_node **p = &threads->entries.rb_node;
-	struct rb_node *parent = NULL;
 	struct thread *th;
 
-	/*
-	 * Front-end cache - TID lookups come in blocks,
-	 * so most of the time we dont have to look up
-	 * the full rbtree:
-	 */
 	th = threads->last_match;
 	if (th != NULL) {
 		if (th->tid == tid) {
@@ -435,12 +428,57 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		threads->last_match = NULL;
 	}
 
+	return NULL;
+}
+
+static struct thread*
+threads__get_last_match(struct threads *threads, struct machine *machine,
+			int pid, int tid)
+{
+	struct thread *th = NULL;
+
+	if (perf_singlethreaded)
+		th = __threads__get_last_match(threads, machine, pid, tid);
+
+	return th;
+}
+
+static void
+__threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	threads->last_match = th;
+}
+
+static void
+threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	if (perf_singlethreaded)
+		__threads__set_last_match(threads, th);
+}
+
+/*
+ * Caller must eventually drop thread->refcnt returned with a successful
+ * lookup/new thread inserted.
+ */
+static struct thread *____machine__findnew_thread(struct machine *machine,
+						  struct threads *threads,
+						  pid_t pid, pid_t tid,
+						  bool create)
+{
+	struct rb_node **p = &threads->entries.rb_node;
+	struct rb_node *parent = NULL;
+	struct thread *th;
+
+	th = threads__get_last_match(threads, machine, pid, tid);
+	if (th)
+		return th;
+
 	while (*p != NULL) {
 		parent = *p;
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			threads->last_match = th;
+			threads__set_last_match(threads, th);
 			machine__update_thread_pid(machine, th, pid);
 			return thread__get(th);
 		}
@@ -477,7 +515,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		threads->last_match = th;
+		threads__set_last_match(threads, th);
 		++threads->nr;
 	}
 
@@ -1635,7 +1673,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	struct threads *threads = machine__threads(machine, th->tid);
 
 	if (threads->last_match == th)
-		threads->last_match = NULL;
+		threads__set_last_match(threads, NULL);
 
 	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
@@ -2272,6 +2310,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
+	u64 addr;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2279,7 +2318,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
 		return 0;
 
-	srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
+	/*
+	 * Convert entry->ip from a virtual address to an offset in
+	 * its corresponding binary.
+	 */
+	addr = map__map_ip(entry->map, entry->ip);
+
+	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym,
 				       false, NULL, 0, 0, 0, srcline);
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 1ddc3d1d0147..a28f9b5cc4ff 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 				if (raw)
 					s = (char *)pe->metric_name;
 				else {
-					if (asprintf(&s, "%s\n\t[%s]",
-						     pe->metric_name, pe->desc) < 0)
+					if (asprintf(&s, "%s\n%*s%s]",
+						     pe->metric_name, 8, "[", pe->desc) < 0)
 						return;
 				}
 
@@ -490,3 +490,25 @@ out:
 	metricgroup__free_egroups(&group_list);
 	return ret;
 }
+
+bool metricgroup__has_metric(const char *metric)
+{
+	struct pmu_events_map *map = perf_pmu__find_map(NULL);
+	struct pmu_event *pe;
+	int i;
+
+	if (!map)
+		return false;
+
+	for (i = 0; ; i++) {
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		if (match_metric(pe->metric_name, metric))
+			return true;
+	}
+	return false;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 06854e125ee7..8a155dba0581 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt,
 			struct rblist *metric_events);
 
 void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+bool metricgroup__has_metric(const char *metric);
 #endif
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 3ba6a1742f91..afd68524ffa9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -652,12 +652,6 @@ static int is_arm_pmu_core(const char *name)
 	if (stat(path, &st) == 0)
 		return 1;
 
-	/* Look for cpu sysfs (specific to s390) */
-	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
-		  sysfs, name);
-	if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
-		return 1;
-
 	return 0;
 }
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 594d14a02b67..99990f5f2512 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -913,11 +913,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
-		   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
+	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
 			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
-				     avg / ratio);
+				     avg / (ratio * evsel->scale));
 		else
 			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 0ee7f568d60c..3393d7ee9401 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_64;
 #include <asm/syscalls_32.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_powerpc_32;
+#elif defined(__aarch64__)
+#include <asm/syscalls.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_arm64;
 #endif
 
 struct syscall {
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 538db4e5d1e6..6f318b15950e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -77,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui)
 	if (__report_module(&al, ip, ui))
 		return -1;
 
-	e->ip  = al.addr;
+	e->ip  = ip;
 	e->map = al.map;
 	e->sym = al.sym;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6a11bc7e6b27..79f521a552cf 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -575,7 +575,7 @@ static int entry(u64 ip, struct thread *thread,
 	struct addr_location al;
 
 	e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
-	e.ip = al.addr;
+	e.ip  = ip;
 	e.map = al.map;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 9e78df207919..0c7d9e556b47 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -354,7 +354,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		while (s->bytes_recvd < total_bytes) {
 			if (txmsg_cork) {
 				timeout.tv_sec = 0;
-				timeout.tv_usec = 1000;
+				timeout.tv_usec = 300000;
 			} else {
 				timeout.tv_sec = 1;
 				timeout.tv_usec = 0;
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index c15f270e121d..65541c21a544 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 #
-# Usage: configinit.sh config-spec-file [ build output dir ]
+# Usage: configinit.sh config-spec-file build-output-dir results-dir
 #
 # Create a .config file from the spec file.  Run from the kernel source tree.
 # Exits with 0 if all went well, with 1 if all went well but the config
@@ -40,20 +40,18 @@ mkdir $T
 
 c=$1
 buildloc=$2
+resdir=$3
 builddir=
-if test -n $buildloc
+if echo $buildloc | grep -q '^O='
 then
-	if echo $buildloc | grep -q '^O='
+	builddir=`echo $buildloc | sed -e 's/^O=//'`
+	if test ! -d $builddir
 	then
-		builddir=`echo $buildloc | sed -e 's/^O=//'`
-		if test ! -d $builddir
-		then
-			mkdir $builddir
-		fi
-	else
-		echo Bad build directory: \"$buildloc\"
-		exit 2
+		mkdir $builddir
 	fi
+else
+	echo Bad build directory: \"$buildloc\"
+	exit 2
 fi
 
 sed -e 's/^\(CONFIG[0-9A-Z_]*\)=.*$/grep -v "^# \1" |/' < $c > $T/u.sh
@@ -61,12 +59,12 @@ sed -e 's/^\(CONFIG[0-9A-Z_]*=\).*$/grep -v \1 |/' < $c >> $T/u.sh
 grep '^grep' < $T/u.sh > $T/upd.sh
 echo "cat - $c" >> $T/upd.sh
 make mrproper
-make $buildloc distclean > $builddir/Make.distclean 2>&1
-make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1
+make $buildloc distclean > $resdir/Make.distclean 2>&1
+make $buildloc $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1
 mv $builddir/.config $builddir/.config.sav
 sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
 cp $builddir/.config $builddir/.config.new
-yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err
+yes '' | make $buildloc oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err
 
 # verify new config matches specification.
 configcheck.sh $builddir/.config $c
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 34d126734cde..9115fcdb5617 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -2,7 +2,7 @@
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
-# Usage: kvm-build.sh config-template build-dir
+# Usage: kvm-build.sh config-template build-dir resdir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -29,6 +29,7 @@ then
 	exit 1
 fi
 builddir=${2}
+resdir=${3}
 
 T=${TMPDIR-/tmp}/test-linux.sh.$$
 trap 'rm -rf $T' 0
@@ -41,19 +42,19 @@ CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_CONSOLE=y
 ___EOF___
 
-configinit.sh $T/config O=$builddir
+configinit.sh $T/config O=$builddir $resdir
 retval=$?
 if test $retval -gt 1
 then
 	exit 2
 fi
 ncpus=`cpus2use.sh`
-make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $builddir/Make.out 2>&1
+make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $resdir/Make.out 2>&1
 retval=$?
-if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out
+if test $retval -ne 0 || grep "rcu[^/]*": < $resdir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $resdir/Make.out
 then
 	echo Kernel build error
-	egrep "Stop|Error|error:|warning:" < $builddir/Make.out
+	egrep "Stop|Error|error:|warning:" < $resdir/Make.out
 	echo Run aborted.
 	exit 3
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 477ecb1293ab..0fa8a61ccb7b 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -70,4 +70,5 @@ else
 	else
 		print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
 	fi
+	echo $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i > $i/console.log.rcu.diags
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index c27e97824163..c9bab57a77eb 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -39,6 +39,7 @@ do
 			head -1 $resdir/log
 		fi
 		TORTURE_SUITE="`cat $i/../TORTURE_SUITE`"
+		rm -f $i/console.log.*.diags
 		kvm-recheck-${TORTURE_SUITE}.sh $i
 		if test -f "$i/console.log"
 		then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index c5b0f94341d9..f7247ee00514 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -98,14 +98,15 @@ then
 	ln -s $base_resdir/.config $resdir  # for kvm-recheck.sh
 	# Arch-independent indicator
 	touch $resdir/builtkernel
-elif kvm-build.sh $T/Kc2 $builddir
+elif kvm-build.sh $T/Kc2 $builddir $resdir
 then
 	# Had to build a kernel for this test.
 	QEMU="`identify_qemu $builddir/vmlinux`"
 	BOOT_IMAGE="`identify_boot_image $QEMU`"
-	cp $builddir/Make*.out $resdir
 	cp $builddir/vmlinux $resdir
 	cp $builddir/.config $resdir
+	cp $builddir/Module.symvers $resdir > /dev/null || :
+	cp $builddir/System.map $resdir > /dev/null || :
 	if test -n "$BOOT_IMAGE"
 	then
 		cp $builddir/$BOOT_IMAGE $resdir
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 56610dbbdf73..5a7a62d76a50 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -347,7 +347,7 @@ function dump(first, pastlast, batchnum)
 	print "needqemurun="
 	jn=1
 	for (j = first; j < pastlast; j++) {
-		builddir=KVM "/b" jn
+		builddir=KVM "/b1"
 		cpusr[jn] = cpus[j];
 		if (cfrep[cf[j]] == "") {
 			cfr[jn] = cf[j];
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 17293436f551..84933f6aed77 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -163,6 +163,13 @@ then
 	print_warning Summary: $summary
 	cat $T.diags >> $file.diags
 fi
+for i in $file.*.diags
+do
+	if test -f "$i"
+	then
+		cat $i >> $file.diags
+	fi
+done
 if ! test -s $file.diags
 then
 	rm -f $file.diags
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
index 5d2cc0bd50a0..5c3213cc3ad7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
@@ -1,5 +1,5 @@
-rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
-rcutree.gp_preinit_delay=3
+rcutorture.onoff_interval=200 rcutorture.onoff_holdoff=30
+rcutree.gp_preinit_delay=12
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
 rcutree.kthread_prio=2
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
deleted file mode 100644
index 883149b5f2d1..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
+++ /dev/null
@@ -1 +0,0 @@
-rcutree.rcu_fanout_exact=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 24ec91041957..7bab8246392b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -39,7 +39,7 @@ rcutorture_param_onoff () {
 	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
 	then
 		echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
-		echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+		echo rcutorture.onoff_interval=1000 rcutorture.onoff_holdoff=30
 	fi
 }
 
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 615252331813..91cf50b2b0e5 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -90,6 +90,30 @@ unsigned int yield_mod_cnt, nr_abort;
 #error "Unsupported architecture"
 #endif
 
+#elif defined(__s390__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1]"m"(loop_cnt[1]) \
+	, [loop_cnt_2]"m"(loop_cnt[2]) \
+	, [loop_cnt_3]"m"(loop_cnt[3]) \
+	, [loop_cnt_4]"m"(loop_cnt[4]) \
+	, [loop_cnt_5]"m"(loop_cnt[5]) \
+	, [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG	"r12"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"l %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"ltr %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG "\n\t" \
+	"je 333f\n\t" \
+	"222:\n\t" \
+	"ahi %%" INJECT_ASM_REG ", -1\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
 #elif defined(__ARMEL__)
 
 #define RSEQ_INJECT_INPUT \
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
new file mode 100644
index 000000000000..1069e85258ce
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -0,0 +1,513 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+
+#define RSEQ_SIG	0x53053053
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("bcr 15,0" ::: "memory")
+#define rseq_smp_rmb()	rseq_smp_mb()
+#define rseq_smp_wmb()	rseq_smp_mb()
+
+#define rseq_smp_load_acquire(p)					\
+__extension__ ({							\
+	__typeof(*p) ____p1 = RSEQ_READ_ONCE(*p);			\
+	rseq_barrier();							\
+	____p1;								\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)					\
+do {									\
+	rseq_barrier();							\
+	RSEQ_WRITE_ONCE(*p, v);						\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#ifdef __s390x__
+
+#define LONG_L			"lg"
+#define LONG_S			"stg"
+#define LONG_LT_R		"ltgr"
+#define LONG_CMP		"cg"
+#define LONG_CMP_R		"cgr"
+#define LONG_ADDI		"aghi"
+#define LONG_ADD_R		"agr"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_table, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"
+
+#elif __s390__
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_table, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"
+
+#define LONG_L			"l"
+#define LONG_S			"st"
+#define LONG_LT_R		"ltr"
+#define LONG_CMP		"c"
+#define LONG_CMP_R		"cr"
+#define LONG_ADDI		"ahi"
+#define LONG_ADD_R		"ar"
+
+#endif
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,		\
+				(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)		\
+		RSEQ_INJECT_ASM(1)					\
+		"larl %%r0, " __rseq_str(cs_label) "\n\t"		\
+		LONG_S " %%r0, %[" __rseq_str(rseq_cs) "]\n\t"		\
+		__rseq_str(label) ":\n\t"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)		\
+		RSEQ_INJECT_ASM(2)					\
+		"c %[" __rseq_str(cpu_id) "], %[" __rseq_str(current_cpu_id) "]\n\t" \
+		"jnz " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		".long " __rseq_str(RSEQ_SIG) "\n\t"			\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"j %l[" __rseq_str(abort_label) "]\n\t"			\
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"j %l[" __rseq_str(cmpfail_label) "]\n\t"		\
+		".popsection\n\t"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/*
+ * Compare @v against @expectnot. When it does _not_ match, load @v
+ * into @load, and store the content of *@v + voffp into @v.
+ */
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       off_t voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " %%r1, %[v]\n\t"
+		LONG_CMP_R " %%r1, %[expectnot]\n\t"
+		"je %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " %%r1, %[v]\n\t"
+		LONG_CMP_R " %%r1, %[expectnot]\n\t"
+		"je %l[error2]\n\t"
+#endif
+		LONG_S " %%r1, %[load]\n\t"
+		LONG_ADD_R " %%r1, %[voffp]\n\t"
+		LONG_L " %%r1, 0(%%r1)\n\t"
+		/* final store */
+		LONG_S " %%r1, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"r" (voffp),
+		  [load]		"m" (*load)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0", "r1"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+		LONG_L " %%r0, %[v]\n\t"
+		LONG_ADD_R " %%r0, %[count]\n\t"
+		/* final store */
+		LONG_S " %%r0, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [count]		"r" (count)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+				 intptr_t *v2, intptr_t newv2,
+				 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* try store */
+		LONG_S " %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+					 intptr_t *v2, intptr_t newv2,
+					 intptr_t newv, int cpu)
+{
+	return rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2, newv, cpu);
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+			      intptr_t *v2, intptr_t expect2,
+			      intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+		LONG_CMP " %[expect2], %[v2]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+		LONG_CMP " %[expect2], %[v2]\n\t"
+		"jnz %l[error3]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+				 void *dst, void *src, size_t len,
+				 intptr_t newv, int cpu)
+{
+	uint64_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		LONG_S " %[src], %[rseq_scratch0]\n\t"
+		LONG_S " %[dst], %[rseq_scratch1]\n\t"
+		LONG_S " %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz 7f\n\t"
+#endif
+		/* try memcpy */
+		LONG_LT_R " %[len], %[len]\n\t"
+		"jz 333f\n\t"
+		"222:\n\t"
+		"ic %%r0,0(%[src])\n\t"
+		"stc %%r0,0(%[dst])\n\t"
+		LONG_ADDI " %[src], 1\n\t"
+		LONG_ADDI " %[dst], 1\n\t"
+		LONG_ADDI " %[len], -1\n\t"
+		"jnz 222b\n\t"
+		"333:\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		LONG_L " %[len], %[rseq_scratch2]\n\t"
+		LONG_L " %[dst], %[rseq_scratch1]\n\t"
+		LONG_L " %[src], %[rseq_scratch0]\n\t"
+		RSEQ_ASM_DEFINE_ABORT(4,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			abort)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			error2)
+#endif
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv),
+		  /* try memcpy input */
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len),
+		  [rseq_scratch0]	"m" (rseq_scratch[0]),
+		  [rseq_scratch1]	"m" (rseq_scratch[1]),
+		  [rseq_scratch2]	"m" (rseq_scratch[2])
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+					 void *dst, void *src, size_t len,
+					 intptr_t newv, int cpu)
+{
+	return rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len,
+					    newv, cpu);
+}
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index 86ce22417e0d..ca332efe9713 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -75,6 +75,8 @@ extern __thread volatile struct rseq __rseq_abi;
 #include <rseq-ppc.h>
 #elif defined(__mips__)
 #include <rseq-mips.h>
+#elif defined(__s390__)
+#include <rseq-s390.h>
 #else
 #error unsupported target
 #endif
diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c
index ca6cd146aafe..dcf73c5dab6e 100644
--- a/tools/testing/selftests/timers/raw_skew.c
+++ b/tools/testing/selftests/timers/raw_skew.c
@@ -134,6 +134,11 @@ int main(int argv, char **argc)
 	printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000)));
 
 	if (llabs(eppm - ppm) > 1000) {
+		if (tx1.offset || tx2.offset ||
+		    tx1.freq != tx2.freq || tx1.tick != tx2.tick) {
+			printf("	[SKIP]\n");
+			return ksft_exit_skip("The clock was adjusted externally. Shutdown NTPd or other time sync daemons\n");
+		}
 		printf("	[FAILED]\n");
 		return ksft_exit_fail();
 	}
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 04e554cae3a2..108250e4d376 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -604,7 +604,7 @@ void kvm_arm_resume_guest(struct kvm *kvm)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		vcpu->arch.pause = false;
-		swake_up(kvm_arch_vcpu_wq(vcpu));
+		swake_up_one(kvm_arch_vcpu_wq(vcpu));
 	}
 }
 
@@ -612,7 +612,7 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 {
 	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
-	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+	swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
 				       (!vcpu->arch.pause)));
 
 	if (vcpu->arch.power_off || vcpu->arch.pause) {
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index c95ab4c5a475..9b73d3ad918a 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -155,7 +155,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
-	swake_up(wq);
+	swake_up_one(wq);
 
 	return PSCI_RET_SUCCESS;
 }
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 57bcb27dcf30..23c2519c5b32 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -107,7 +107,7 @@ static void async_pf_execute(struct work_struct *work)
 	trace_kvm_async_pf_completed(addr, gva);
 
 	if (swq_has_sleeper(&vcpu->wq))
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 
 	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8b47507faab5..3d233ebfbee9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2172,7 +2172,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	kvm_arch_vcpu_blocking(vcpu);
 
 	for (;;) {
-		prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+		prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
@@ -2214,7 +2214,7 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
 	if (swq_has_sleeper(wqp)) {
-		swake_up(wqp);
+		swake_up_one(wqp);
 		++vcpu->stat.halt_wakeup;
 		return true;
 	}