Merge 4.15-rc6 into char-misc-next

We want the fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

13 files changed, 108 insertions, 904 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index b2598cc9834c..7242cbda15dd 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -109,6 +109,7 @@ parameter is applicable::
 	IPV6	IPv6 support is enabled.
 	ISAPNP	ISA PnP code is enabled.
 	ISDN	Appropriate ISDN support is enabled.
+	ISOL	CPU Isolation is enabled.
 	JOY	Appropriate joystick support is enabled.
 	KGDB	Kernel debugger support is enabled.
 	KVM	Kernel Virtual Machine support is enabled.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 6571fbfdb2a1..af7104aaffd9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -328,11 +328,15 @@
 			not play well with APC CPU idle - disable it if you have
 			APC and your system crashes randomly.
 
-	apic=		[APIC,X86-32] Advanced Programmable Interrupt Controller
+	apic=		[APIC,X86] Advanced Programmable Interrupt Controller
 			Change the output verbosity whilst booting
 			Format: { quiet (default) | verbose | debug }
 			Change the amount of debugging information output
 			when initialising the APIC and IO-APIC components.
+			For X86-32, this can also be used to specify an APIC
+			driver name.
+			Format: apic=driver_name
+			Examples: apic=bigsmp
 
 	apic_extnmi=	[APIC,X86] External NMI delivery setting
 			Format: { bsp (default) | all | none }
@@ -1737,7 +1741,7 @@
 	isapnp=		[ISAPNP]
 			Format: <RDP>,<reset>,<pci_scan>,<verbosity>
 
-	isolcpus=	[KNL,SMP] Isolate a given set of CPUs from disturbance.
+	isolcpus=	[KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
 			[Deprecated - use cpusets instead]
 			Format: [flag-list,]<cpu-list>
 
@@ -2662,7 +2666,7 @@
 			Valid arguments: on, off
 			Default: on
 
-	nohz_full=	[KNL,BOOT]
+	nohz_full=	[KNL,BOOT,SMP,ISOL]
 			The argument is a cpu list, as described above.
 			In kernels built with CONFIG_NO_HZ_FULL=y, set
 			the specified list of CPUs whose tick will be stopped
@@ -2708,6 +2712,8 @@
 			steal time is computed, but won't influence scheduler
 			behaviour
 
+	nopti		[X86-64] Disable kernel page table isolation
+
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 
 	nolapic_timer	[X86-32,APIC] Do not use the local APIC timer.
@@ -3282,6 +3288,12 @@
 	pt.		[PARIDE]
 			See Documentation/blockdev/paride.txt.
 
+	pti=		[X86_64]
+			Control user/kernel address space isolation:
+			on - enable
+			off - disable
+			auto - default setting
+
 	pty.legacy_count=
 			[KNL] Number of legacy pty's. Overwrites compiled-in
 			default number.
diff --git a/Documentation/admin-guide/thunderbolt.rst b/Documentation/admin-guide/thunderbolt.rst
index de50a8561774..9b55952039a6 100644
--- a/Documentation/admin-guide/thunderbolt.rst
+++ b/Documentation/admin-guide/thunderbolt.rst
@@ -230,7 +230,7 @@ If supported by your machine this will be exposed by the WMI bus with
 a sysfs attribute called "force_power".
 
 For example the intel-wmi-thunderbolt driver exposes this attribute in:
-  /sys/devices/platform/PNP0C14:00/wmi_bus/wmi_bus-PNP0C14:00/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power
+  /sys/bus/wmi/devices/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power
 
   To force the power to on, write 1 to this attribute file.
   To disable force power, write 0 to this attribute file.
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index 304bf22bb83c..fc1c884fea10 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -75,3 +75,4 @@ stable kernels.
 | Qualcomm Tech. | Falkor v1       | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
 | Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |
+| Qualcomm Tech. | Falkor v{1,2}   | E1041           | QCOM_FALKOR_ERRATUM_1041    |
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index 779211fbb69f..2cddab7efb20 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -898,6 +898,13 @@ controller implements weight and absolute bandwidth limit models for
 normal scheduling policy and absolute bandwidth allocation model for
 realtime scheduling policy.
 
+WARNING: cgroup2 doesn't yet support control of realtime processes and
+the cpu controller can only be enabled when all RT processes are in
+the root cgroup.  Be aware that system management software may already
+have placed RT processes into nonroot cgroups during the system boot
+process, and these processes may need to be moved to the root cgroup
+before the cpu controller can be enabled.
+
 
 CPU Interface Files
 ~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
index 376fa2f50e6b..956bb046e599 100644
--- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
+++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
@@ -13,7 +13,6 @@ Required properties:
                  at25df321a
                  at25df641
                  at26df081a
-                 en25s64
                  mr25h128
                  mr25h256
                  mr25h10
@@ -33,7 +32,6 @@ Required properties:
                  s25fl008k
                  s25fl064k
                  sst25vf040b
-                 sst25wf040b
                  m25p40
                  m25p80
                  m25p16
diff --git a/Documentation/devicetree/bindings/sound/da7218.txt b/Documentation/devicetree/bindings/sound/da7218.txt
index 5ca5a709b6aa..3ab9dfef38d1 100644
--- a/Documentation/devicetree/bindings/sound/da7218.txt
+++ b/Documentation/devicetree/bindings/sound/da7218.txt
@@ -73,7 +73,7 @@ Example:
 		compatible = "dlg,da7218";
 		reg = <0x1a>;
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 		wakeup-source;
 
 		VDD-supply = <&reg_audio>;
diff --git a/Documentation/devicetree/bindings/sound/da7219.txt b/Documentation/devicetree/bindings/sound/da7219.txt
index cf61681826b6..5b54d2d045c3 100644
--- a/Documentation/devicetree/bindings/sound/da7219.txt
+++ b/Documentation/devicetree/bindings/sound/da7219.txt
@@ -77,7 +77,7 @@ Example:
 		reg = <0x1a>;
 
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 
 		VDD-supply = <&reg_audio>;
 		VDDMIC-supply = <&reg_audio>;
diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt
index 5bf13960f7f4..e3c48b20b1a6 100644
--- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt
+++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt
@@ -12,24 +12,30 @@ Required properties:
   - "fsl,imx53-ecspi" for SPI compatible with the one integrated on i.MX53 and later Soc
 - reg : Offset and length of the register set for the device
 - interrupts : Should contain CSPI/eCSPI interrupt
-- cs-gpios : Specifies the gpio pins to be used for chipselects.
 - clocks : Clock specifiers for both ipg and per clocks.
 - clock-names : Clock names should include both "ipg" and "per"
 See the clock consumer binding,
 	Documentation/devicetree/bindings/clock/clock-bindings.txt
-- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
-		Documentation/devicetree/bindings/dma/dma.txt
-- dma-names: DMA request names should include "tx" and "rx" if present.
 
-Obsolete properties:
-- fsl,spi-num-chipselects : Contains the number of the chipselect
+Recommended properties:
+- cs-gpios : GPIOs to use as chip selects, see spi-bus.txt.  While the native chip
+select lines can be used, they appear to always generate a pulse between each
+word of a transfer.  Most use cases will require GPIO based chip selects to
+generate a valid transaction.
 
 Optional properties:
+- num-cs :  Number of total chip selects, see spi-bus.txt.
+- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
+Documentation/devicetree/bindings/dma/dma.txt.
+- dma-names: DMA request names, if present, should include "tx" and "rx".
 - fsl,spi-rdy-drctl: Integer, representing the value of DRCTL, the register
 controlling the SPI_READY handling. Note that to enable the DRCTL consideration,
 the SPI_READY mode-flag needs to be set too.
 Valid values are: 0 (disabled), 1 (edge-triggered burst) and 2 (level-triggered burst).
 
+Obsolete properties:
+- fsl,spi-num-chipselects : Contains the number of the chipselect
+
 Example:
 
 ecspi@70010000 {
diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
index 8caa60734647..e6a5f4912b6d 100644
--- a/Documentation/filesystems/overlayfs.txt
+++ b/Documentation/filesystems/overlayfs.txt
@@ -156,6 +156,40 @@ handle it in two different ways:
    root of the overlay.  Finally the directory is moved to the new
    location.
 
+There are several ways to tune the "redirect_dir" feature.
+
+Kernel config options:
+
+- OVERLAY_FS_REDIRECT_DIR:
+    If this is enabled, then redirect_dir is turned on by  default.
+- OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW:
+    If this is enabled, then redirects are always followed by default. Enabling
+    this results in a less secure configuration.  Enable this option only when
+    worried about backward compatibility with kernels that have the redirect_dir
+    feature and follow redirects even if turned off.
+
+Module options (can also be changed through /sys/module/overlay/parameters/*):
+
+- "redirect_dir=BOOL":
+    See OVERLAY_FS_REDIRECT_DIR kernel config option above.
+- "redirect_always_follow=BOOL":
+    See OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW kernel config option above.
+- "redirect_max=NUM":
+    The maximum number of bytes in an absolute redirect (default is 256).
+
+Mount options:
+
+- "redirect_dir=on":
+    Redirects are enabled.
+- "redirect_dir=follow":
+    Redirects are not created, but followed.
+- "redirect_dir=off":
+    Redirects are not created and only followed if "redirect_always_follow"
+    feature is enabled in the kernel/module config.
+- "redirect_dir=nofollow":
+    Redirects are not created and not followed (equivalent to "redirect_dir=off"
+    if "redirect_always_follow" feature is not enabled).
+
 Non-directories
 ---------------
 
diff --git a/Documentation/locking/crossrelease.txt b/Documentation/locking/crossrelease.txt
deleted file mode 100644
index bdf1423d5f99..000000000000
--- a/Documentation/locking/crossrelease.txt
+++ /dev/null
@@ -1,874 +0,0 @@
-Crossrelease
-============
-
-Started by Byungchul Park <byungchul.park@lge.com>
-
-Contents:
-
- (*) Background
-
-     - What causes deadlock
-     - How lockdep works
-
- (*) Limitation
-
-     - Limit lockdep
-     - Pros from the limitation
-     - Cons from the limitation
-     - Relax the limitation
-
- (*) Crossrelease
-
-     - Introduce crossrelease
-     - Introduce commit
-
- (*) Implementation
-
-     - Data structures
-     - How crossrelease works
-
- (*) Optimizations
-
-     - Avoid duplication
-     - Lockless for hot paths
-
- (*) APPENDIX A: What lockdep does to work aggresively
-
- (*) APPENDIX B: How to avoid adding false dependencies
-
-
-==========
-Background
-==========
-
-What causes deadlock
---------------------
-
-A deadlock occurs when a context is waiting for an event to happen,
-which is impossible because another (or the) context who can trigger the
-event is also waiting for another (or the) event to happen, which is
-also impossible due to the same reason.
-
-For example:
-
-   A context going to trigger event C is waiting for event A to happen.
-   A context going to trigger event A is waiting for event B to happen.
-   A context going to trigger event B is waiting for event C to happen.
-
-A deadlock occurs when these three wait operations run at the same time,
-because event C cannot be triggered if event A does not happen, which in
-turn cannot be triggered if event B does not happen, which in turn
-cannot be triggered if event C does not happen. After all, no event can
-be triggered since any of them never meets its condition to wake up.
-
-A dependency might exist between two waiters and a deadlock might happen
-due to an incorrect releationship between dependencies. Thus, we must
-define what a dependency is first. A dependency exists between them if:
-
-   1. There are two waiters waiting for each event at a given time.
-   2. The only way to wake up each waiter is to trigger its event.
-   3. Whether one can be woken up depends on whether the other can.
-
-Each wait in the example creates its dependency like:
-
-   Event C depends on event A.
-   Event A depends on event B.
-   Event B depends on event C.
-
-   NOTE: Precisely speaking, a dependency is one between whether a
-   waiter for an event can be woken up and whether another waiter for
-   another event can be woken up. However from now on, we will describe
-   a dependency as if it's one between an event and another event for
-   simplicity.
-
-And they form circular dependencies like:
-
-    -> C -> A -> B -
-   /                \
-   \                /
-    ----------------
-
-   where 'A -> B' means that event A depends on event B.
-
-Such circular dependencies lead to a deadlock since no waiter can meet
-its condition to wake up as described.
-
-CONCLUSION
-
-Circular dependencies cause a deadlock.
-
-
-How lockdep works
------------------
-
-Lockdep tries to detect a deadlock by checking dependencies created by
-lock operations, acquire and release. Waiting for a lock corresponds to
-waiting for an event, and releasing a lock corresponds to triggering an
-event in the previous section.
-
-In short, lockdep does:
-
-   1. Detect a new dependency.
-   2. Add the dependency into a global graph.
-   3. Check if that makes dependencies circular.
-   4. Report a deadlock or its possibility if so.
-
-For example, consider a graph built by lockdep that looks like:
-
-   A -> B -
-           \
-            -> E
-           /
-   C -> D -
-
-   where A, B,..., E are different lock classes.
-
-Lockdep will add a dependency into the graph on detection of a new
-dependency. For example, it will add a dependency 'E -> C' when a new
-dependency between lock E and lock C is detected. Then the graph will be:
-
-       A -> B -
-               \
-                -> E -
-               /      \
-    -> C -> D -        \
-   /                   /
-   \                  /
-    ------------------
-
-   where A, B,..., E are different lock classes.
-
-This graph contains a subgraph which demonstrates circular dependencies:
-
-                -> E -
-               /      \
-    -> C -> D -        \
-   /                   /
-   \                  /
-    ------------------
-
-   where C, D and E are different lock classes.
-
-This is the condition under which a deadlock might occur. Lockdep
-reports it on detection after adding a new dependency. This is the way
-how lockdep works.
-
-CONCLUSION
-
-Lockdep detects a deadlock or its possibility by checking if circular
-dependencies were created after adding each new dependency.
-
-
-==========
-Limitation
-==========
-
-Limit lockdep
--------------
-
-Limiting lockdep to work on only typical locks e.g. spin locks and
-mutexes, which are released within the acquire context, the
-implementation becomes simple but its capacity for detection becomes
-limited. Let's check pros and cons in next section.
-
-
-Pros from the limitation
-------------------------
-
-Given the limitation, when acquiring a lock, locks in a held_locks
-cannot be released if the context cannot acquire it so has to wait to
-acquire it, which means all waiters for the locks in the held_locks are
-stuck. It's an exact case to create dependencies between each lock in
-the held_locks and the lock to acquire.
-
-For example:
-
-   CONTEXT X
-   ---------
-   acquire A
-   acquire B /* Add a dependency 'A -> B' */
-   release B
-   release A
-
-   where A and B are different lock classes.
-
-When acquiring lock A, the held_locks of CONTEXT X is empty thus no
-dependency is added. But when acquiring lock B, lockdep detects and adds
-a new dependency 'A -> B' between lock A in the held_locks and lock B.
-They can be simply added whenever acquiring each lock.
-
-And data required by lockdep exists in a local structure, held_locks
-embedded in task_struct. Forcing to access the data within the context,
-lockdep can avoid racy problems without explicit locks while handling
-the local data.
-
-Lastly, lockdep only needs to keep locks currently being held, to build
-a dependency graph. However, relaxing the limitation, it needs to keep
-even locks already released, because a decision whether they created
-dependencies might be long-deferred.
-
-To sum up, we can expect several advantages from the limitation:
-
-   1. Lockdep can easily identify a dependency when acquiring a lock.
-   2. Races are avoidable while accessing local locks in a held_locks.
-   3. Lockdep only needs to keep locks currently being held.
-
-CONCLUSION
-
-Given the limitation, the implementation becomes simple and efficient.
-
-
-Cons from the limitation
-------------------------
-
-Given the limitation, lockdep is applicable only to typical locks. For
-example, page locks for page access or completions for synchronization
-cannot work with lockdep.
-
-Can we detect deadlocks below, under the limitation?
-
-Example 1:
-
-   CONTEXT X	   CONTEXT Y	   CONTEXT Z
-   ---------	   ---------	   ----------
-		   mutex_lock A
-   lock_page B
-		   lock_page B
-				   mutex_lock A /* DEADLOCK */
-				   unlock_page B held by X
-		   unlock_page B
-		   mutex_unlock A
-				   mutex_unlock A
-
-   where A and B are different lock classes.
-
-No, we cannot.
-
-Example 2:
-
-   CONTEXT X		   CONTEXT Y
-   ---------		   ---------
-			   mutex_lock A
-   mutex_lock A
-			   wait_for_complete B /* DEADLOCK */
-   complete B
-			   mutex_unlock A
-   mutex_unlock A
-
-   where A is a lock class and B is a completion variable.
-
-No, we cannot.
-
-CONCLUSION
-
-Given the limitation, lockdep cannot detect a deadlock or its
-possibility caused by page locks or completions.
-
-
-Relax the limitation
---------------------
-
-Under the limitation, things to create dependencies are limited to
-typical locks. However, synchronization primitives like page locks and
-completions, which are allowed to be released in any context, also
-create dependencies and can cause a deadlock. So lockdep should track
-these locks to do a better job. We have to relax the limitation for
-these locks to work with lockdep.
-
-Detecting dependencies is very important for lockdep to work because
-adding a dependency means adding an opportunity to check whether it
-causes a deadlock. The more lockdep adds dependencies, the more it
-thoroughly works. Thus Lockdep has to do its best to detect and add as
-many true dependencies into a graph as possible.
-
-For example, considering only typical locks, lockdep builds a graph like:
-
-   A -> B -
-           \
-            -> E
-           /
-   C -> D -
-
-   where A, B,..., E are different lock classes.
-
-On the other hand, under the relaxation, additional dependencies might
-be created and added. Assuming additional 'FX -> C' and 'E -> GX' are
-added thanks to the relaxation, the graph will be:
-
-         A -> B -
-                 \
-                  -> E -> GX
-                 /
-   FX -> C -> D -
-
-   where A, B,..., E, FX and GX are different lock classes, and a suffix
-   'X' is added on non-typical locks.
-
-The latter graph gives us more chances to check circular dependencies
-than the former. However, it might suffer performance degradation since
-relaxing the limitation, with which design and implementation of lockdep
-can be efficient, might introduce inefficiency inevitably. So lockdep
-should provide two options, strong detection and efficient detection.
-
-Choosing efficient detection:
-
-   Lockdep works with only locks restricted to be released within the
-   acquire context. However, lockdep works efficiently.
-
-Choosing strong detection:
-
-   Lockdep works with all synchronization primitives. However, lockdep
-   suffers performance degradation.
-
-CONCLUSION
-
-Relaxing the limitation, lockdep can add additional dependencies giving
-additional opportunities to check circular dependencies.
-
-
-============
-Crossrelease
-============
-
-Introduce crossrelease
-----------------------
-
-In order to allow lockdep to handle additional dependencies by what
-might be released in any context, namely 'crosslock', we have to be able
-to identify those created by crosslocks. The proposed 'crossrelease'
-feature provoides a way to do that.
-
-Crossrelease feature has to do:
-
-   1. Identify dependencies created by crosslocks.
-   2. Add the dependencies into a dependency graph.
-
-That's all. Once a meaningful dependency is added into graph, then
-lockdep would work with the graph as it did. The most important thing
-crossrelease feature has to do is to correctly identify and add true
-dependencies into the global graph.
-
-A dependency e.g. 'A -> B' can be identified only in the A's release
-context because a decision required to identify the dependency can be
-made only in the release context. That is to decide whether A can be
-released so that a waiter for A can be woken up. It cannot be made in
-other than the A's release context.
-
-It's no matter for typical locks because each acquire context is same as
-its release context, thus lockdep can decide whether a lock can be
-released in the acquire context. However for crosslocks, lockdep cannot
-make the decision in the acquire context but has to wait until the
-release context is identified.
-
-Therefore, deadlocks by crosslocks cannot be detected just when it
-happens, because those cannot be identified until the crosslocks are
-released. However, deadlock possibilities can be detected and it's very
-worth. See 'APPENDIX A' section to check why.
-
-CONCLUSION
-
-Using crossrelease feature, lockdep can work with what might be released
-in any context, namely crosslock.
-
-
-Introduce commit
-----------------
-
-Since crossrelease defers the work adding true dependencies of
-crosslocks until they are actually released, crossrelease has to queue
-all acquisitions which might create dependencies with the crosslocks.
-Then it identifies dependencies using the queued data in batches at a
-proper time. We call it 'commit'.
-
-There are four types of dependencies:
-
-1. TT type: 'typical lock A -> typical lock B'
-
-   Just when acquiring B, lockdep can see it's in the A's release
-   context. So the dependency between A and B can be identified
-   immediately. Commit is unnecessary.
-
-2. TC type: 'typical lock A -> crosslock BX'
-
-   Just when acquiring BX, lockdep can see it's in the A's release
-   context. So the dependency between A and BX can be identified
-   immediately. Commit is unnecessary, too.
-
-3. CT type: 'crosslock AX -> typical lock B'
-
-   When acquiring B, lockdep cannot identify the dependency because
-   there's no way to know if it's in the AX's release context. It has
-   to wait until the decision can be made. Commit is necessary.
-
-4. CC type: 'crosslock AX -> crosslock BX'
-
-   When acquiring BX, lockdep cannot identify the dependency because
-   there's no way to know if it's in the AX's release context. It has
-   to wait until the decision can be made. Commit is necessary.
-   But, handling CC type is not implemented yet. It's a future work.
-
-Lockdep can work without commit for typical locks, but commit step is
-necessary once crosslocks are involved. Introducing commit, lockdep
-performs three steps. What lockdep does in each step is:
-
-1. Acquisition: For typical locks, lockdep does what it originally did
-   and queues the lock so that CT type dependencies can be checked using
-   it at the commit step. For crosslocks, it saves data which will be
-   used at the commit step and increases a reference count for it.
-
-2. Commit: No action is reauired for typical locks. For crosslocks,
-   lockdep adds CT type dependencies using the data saved at the
-   acquisition step.
-
-3. Release: No changes are required for typical locks. When a crosslock
-   is released, it decreases a reference count for it.
-
-CONCLUSION
-
-Crossrelease introduces commit step to handle dependencies of crosslocks
-in batches at a proper time.
-
-
-==============
-Implementation
-==============
-
-Data structures
----------------
-
-Crossrelease introduces two main data structures.
-
-1. hist_lock
-
-   This is an array embedded in task_struct, for keeping lock history so
-   that dependencies can be added using them at the commit step. Since
-   it's local data, it can be accessed locklessly in the owner context.
-   The array is filled at the acquisition step and consumed at the
-   commit step. And it's managed in circular manner.
-
-2. cross_lock
-
-   One per lockdep_map exists. This is for keeping data of crosslocks
-   and used at the commit step.
-
-
-How crossrelease works
-----------------------
-
-It's the key of how crossrelease works, to defer necessary works to an
-appropriate point in time and perform in at once at the commit step.
-Let's take a look with examples step by step, starting from how lockdep
-works without crossrelease for typical locks.
-
-   acquire A /* Push A onto held_locks */
-   acquire B /* Push B onto held_locks and add 'A -> B' */
-   acquire C /* Push C onto held_locks and add 'B -> C' */
-   release C /* Pop C from held_locks */
-   release B /* Pop B from held_locks */
-   release A /* Pop A from held_locks */
-
-   where A, B and C are different lock classes.
-
-   NOTE: This document assumes that readers already understand how
-   lockdep works without crossrelease thus omits details. But there's
-   one thing to note. Lockdep pretends to pop a lock from held_locks
-   when releasing it. But it's subtly different from the original pop
-   operation because lockdep allows other than the top to be poped.
-
-In this case, lockdep adds 'the top of held_locks -> the lock to acquire'
-dependency every time acquiring a lock.
-
-After adding 'A -> B', a dependency graph will be:
-
-   A -> B
-
-   where A and B are different lock classes.
-
-And after adding 'B -> C', the graph will be:
-
-   A -> B -> C
-
-   where A, B and C are different lock classes.
-
-Let's performs commit step even for typical locks to add dependencies.
-Of course, commit step is not necessary for them, however, it would work
-well because this is a more general way.
-
-   acquire A
-   /*
-    * Queue A into hist_locks
-    *
-    * In hist_locks: A
-    * In graph: Empty
-    */
-
-   acquire B
-   /*
-    * Queue B into hist_locks
-    *
-    * In hist_locks: A, B
-    * In graph: Empty
-    */
-
-   acquire C
-   /*
-    * Queue C into hist_locks
-    *
-    * In hist_locks: A, B, C
-    * In graph: Empty
-    */
-
-   commit C
-   /*
-    * Add 'C -> ?'
-    * Answer the following to decide '?'
-    * What has been queued since acquire C: Nothing
-    *
-    * In hist_locks: A, B, C
-    * In graph: Empty
-    */
-
-   release C
-
-   commit B
-   /*
-    * Add 'B -> ?'
-    * Answer the following to decide '?'
-    * What has been queued since acquire B: C
-    *
-    * In hist_locks: A, B, C
-    * In graph: 'B -> C'
-    */
-
-   release B
-
-   commit A
-   /*
-    * Add 'A -> ?'
-    * Answer the following to decide '?'
-    * What has been queued since acquire A: B, C
-    *
-    * In hist_locks: A, B, C
-    * In graph: 'B -> C', 'A -> B', 'A -> C'
-    */
-
-   release A
-
-   where A, B and C are different lock classes.
-
-In this case, dependencies are added at the commit step as described.
-
-After commits for A, B and C, the graph will be:
-
-   A -> B -> C
-
-   where A, B and C are different lock classes.
-
-   NOTE: A dependency 'A -> C' is optimized out.
-
-We can see the former graph built without commit step is same as the
-latter graph built using commit steps. Of course the former way leads to
-earlier finish for building the graph, which means we can detect a
-deadlock or its possibility sooner. So the former way would be prefered
-when possible. But we cannot avoid using the latter way for crosslocks.
-
-Let's look at how commit steps work for crosslocks. In this case, the
-commit step is performed only on crosslock AX as real. And it assumes
-that the AX release context is different from the AX acquire context.
-
-   BX RELEASE CONTEXT		   BX ACQUIRE CONTEXT
-   ------------------		   ------------------
-				   acquire A
-				   /*
-				    * Push A onto held_locks
-				    * Queue A into hist_locks
-				    *
-				    * In held_locks: A
-				    * In hist_locks: A
-				    * In graph: Empty
-				    */
-
-				   acquire BX
-				   /*
-				    * Add 'the top of held_locks -> BX'
-				    *
-				    * In held_locks: A
-				    * In hist_locks: A
-				    * In graph: 'A -> BX'
-				    */
-
-   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-   It must be guaranteed that the following operations are seen after
-   acquiring BX globally. It can be done by things like barrier.
-   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-   acquire C
-   /*
-    * Push C onto held_locks
-    * Queue C into hist_locks
-    *
-    * In held_locks: C
-    * In hist_locks: C
-    * In graph: 'A -> BX'
-    */
-
-   release C
-   /*
-    * Pop C from held_locks
-    *
-    * In held_locks: Empty
-    * In hist_locks: C
-    * In graph: 'A -> BX'
-    */
-				   acquire D
-				   /*
-				    * Push D onto held_locks
-				    * Queue D into hist_locks
-				    * Add 'the top of held_locks -> D'
-				    *
-				    * In held_locks: A, D
-				    * In hist_locks: A, D
-				    * In graph: 'A -> BX', 'A -> D'
-				    */
-   acquire E
-   /*
-    * Push E onto held_locks
-    * Queue E into hist_locks
-    *
-    * In held_locks: E
-    * In hist_locks: C, E
-    * In graph: 'A -> BX', 'A -> D'
-    */
-
-   release E
-   /*
-    * Pop E from held_locks
-    *
-    * In held_locks: Empty
-    * In hist_locks: D, E
-    * In graph: 'A -> BX', 'A -> D'
-    */
-				   release D
-				   /*
-				    * Pop D from held_locks
-				    *
-				    * In held_locks: A
-				    * In hist_locks: A, D
-				    * In graph: 'A -> BX', 'A -> D'
-				    */
-   commit BX
-   /*
-    * Add 'BX -> ?'
-    * What has been queued since acquire BX: C, E
-    *
-    * In held_locks: Empty
-    * In hist_locks: D, E
-    * In graph: 'A -> BX', 'A -> D',
-    *           'BX -> C', 'BX -> E'
-    */
-
-   release BX
-   /*
-    * In held_locks: Empty
-    * In hist_locks: D, E
-    * In graph: 'A -> BX', 'A -> D',
-    *           'BX -> C', 'BX -> E'
-    */
-				   release A
-				   /*
-				    * Pop A from held_locks
-				    *
-				    * In held_locks: Empty
-				    * In hist_locks: A, D
-				    * In graph: 'A -> BX', 'A -> D',
-				    *           'BX -> C', 'BX -> E'
-				    */
-
-   where A, BX, C,..., E are different lock classes, and a suffix 'X' is
-   added on crosslocks.
-
-Crossrelease considers all acquisitions after acqiuring BX are
-candidates which might create dependencies with BX. True dependencies
-will be determined when identifying the release context of BX. Meanwhile,
-all typical locks are queued so that they can be used at the commit step.
-And then two dependencies 'BX -> C' and 'BX -> E' are added at the
-commit step when identifying the release context.
-
-The final graph will be, with crossrelease:
-
-               -> C
-              /
-       -> BX -
-      /       \
-   A -         -> E
-      \
-       -> D
-
-   where A, BX, C,..., E are different lock classes, and a suffix 'X' is
-   added on crosslocks.
-
-However, the final graph will be, without crossrelease:
-
-   A -> D
-
-   where A and D are different lock classes.
-
-The former graph has three more dependencies, 'A -> BX', 'BX -> C' and
-'BX -> E' giving additional opportunities to check if they cause
-deadlocks. This way lockdep can detect a deadlock or its possibility
-caused by crosslocks.
-
-CONCLUSION
-
-We checked how crossrelease works with several examples.
-
-
-=============
-Optimizations
-=============
-
-Avoid duplication
------------------
-
-Crossrelease feature uses a cache like what lockdep already uses for
-dependency chains, but this time it's for caching CT type dependencies.
-Once that dependency is cached, the same will never be added again.
-
-
-Lockless for hot paths
-----------------------
-
-To keep all locks for later use at the commit step, crossrelease adopts
-a local array embedded in task_struct, which makes access to the data
-lockless by forcing it to happen only within the owner context. It's
-like how lockdep handles held_locks. Lockless implmentation is important
-since typical locks are very frequently acquired and released.
-
-
-=================================================
-APPENDIX A: What lockdep does to work aggresively
-=================================================
-
-A deadlock actually occurs when all wait operations creating circular
-dependencies run at the same time. Even though they don't, a potential
-deadlock exists if the problematic dependencies exist. Thus it's
-meaningful to detect not only an actual deadlock but also its potential
-possibility. The latter is rather valuable. When a deadlock occurs
-actually, we can identify what happens in the system by some means or
-other even without lockdep. However, there's no way to detect possiblity
-without lockdep unless the whole code is parsed in head. It's terrible.
-Lockdep does the both, and crossrelease only focuses on the latter.
-
-Whether or not a deadlock actually occurs depends on several factors.
-For example, what order contexts are switched in is a factor. Assuming
-circular dependencies exist, a deadlock would occur when contexts are
-switched so that all wait operations creating the dependencies run
-simultaneously. Thus to detect a deadlock possibility even in the case
-that it has not occured yet, lockdep should consider all possible
-combinations of dependencies, trying to:
-
-1. Use a global dependency graph.
-
-   Lockdep combines all dependencies into one global graph and uses them,
-   regardless of which context generates them or what order contexts are
-   switched in. Aggregated dependencies are only considered so they are
-   prone to be circular if a problem exists.
-
-2. Check dependencies between classes instead of instances.
-
-   What actually causes a deadlock are instances of lock. However,
-   lockdep checks dependencies between classes instead of instances.
-   This way lockdep can detect a deadlock which has not happened but
-   might happen in future by others but the same class.
-
-3. Assume all acquisitions lead to waiting.
-
-   Although locks might be acquired without waiting which is essential
-   to create dependencies, lockdep assumes all acquisitions lead to
-   waiting since it might be true some time or another.
-
-CONCLUSION
-
-Lockdep detects not only an actual deadlock but also its possibility,
-and the latter is more valuable.
-
-
-==================================================
-APPENDIX B: How to avoid adding false dependencies
-==================================================
-
-Remind what a dependency is. A dependency exists if:
-
-   1. There are two waiters waiting for each event at a given time.
-   2. The only way to wake up each waiter is to trigger its event.
-   3. Whether one can be woken up depends on whether the other can.
-
-For example:
-
-   acquire A
-   acquire B /* A dependency 'A -> B' exists */
-   release B
-   release A
-
-   where A and B are different lock classes.
-
-A depedency 'A -> B' exists since:
-
-   1. A waiter for A and a waiter for B might exist when acquiring B.
-   2. Only way to wake up each is to release what it waits for.
-   3. Whether the waiter for A can be woken up depends on whether the
-      other can. IOW, TASK X cannot release A if it fails to acquire B.
-
-For another example:
-
-   TASK X			   TASK Y
-   ------			   ------
-				   acquire AX
-   acquire B /* A dependency 'AX -> B' exists */
-   release B
-   release AX held by Y
-
-   where AX and B are different lock classes, and a suffix 'X' is added
-   on crosslocks.
-
-Even in this case involving crosslocks, the same rule can be applied. A
-depedency 'AX -> B' exists since:
-
-   1. A waiter for AX and a waiter for B might exist when acquiring B.
-   2. Only way to wake up each is to release what it waits for.
-   3. Whether the waiter for AX can be woken up depends on whether the
-      other can. IOW, TASK X cannot release AX if it fails to acquire B.
-
-Let's take a look at more complicated example:
-
-   TASK X			   TASK Y
-   ------			   ------
-   acquire B
-   release B
-   fork Y
-				   acquire AX
-   acquire C /* A dependency 'AX -> C' exists */
-   release C
-   release AX held by Y
-
-   where AX, B and C are different lock classes, and a suffix 'X' is
-   added on crosslocks.
-
-Does a dependency 'AX -> B' exist? Nope.
-
-Two waiters are essential to create a dependency. However, waiters for
-AX and B to create 'AX -> B' cannot exist at the same time in this
-example. Thus the dependency 'AX -> B' cannot be created.
-
-It would be ideal if the full set of true ones can be considered. But
-we can ensure nothing but what actually happened. Relying on what
-actually happens at runtime, we can anyway add only true ones, though
-they might be a subset of true ones. It's similar to how lockdep works
-for typical locks. There might be more true dependencies than what
-lockdep has detected in runtime. Lockdep has no choice but to rely on
-what actually happens. Crossrelease also relies on it.
-
-CONCLUSION
-
-Relying on what actually happens, lockdep can avoid adding false
-dependencies.
diff --git a/Documentation/vm/zswap.txt b/Documentation/vm/zswap.txt
index 89fff7d611cc..0b3a1148f9f0 100644
--- a/Documentation/vm/zswap.txt
+++ b/Documentation/vm/zswap.txt
@@ -98,5 +98,25 @@ request is made for a page in an old zpool, it is uncompressed using its
 original compressor.  Once all pages are removed from an old zpool, the zpool
 and its compressor are freed.
 
+Some of the pages in zswap are same-value filled pages (i.e. contents of the
+page have same value or repetitive pattern). These pages include zero-filled
+pages and they are handled differently. During store operation, a page is
+checked if it is a same-value filled page before compressing it. If true, the
+compressed length of the page is set to zero and the pattern or same-filled
+value is stored.
+
+Same-value filled pages identification feature is enabled by default and can be
+disabled at boot time by setting the "same_filled_pages_enabled" attribute to 0,
+e.g. zswap.same_filled_pages_enabled=0. It can also be enabled and disabled at
+runtime using the sysfs "same_filled_pages_enabled" attribute, e.g.
+
+echo 1 > /sys/module/zswap/parameters/same_filled_pages_enabled
+
+When zswap same-filled page identification is disabled at runtime, it will stop
+checking for the same-value filled pages during store operation. However, the
+existing pages which are marked as same-value filled pages remain stored
+unchanged in zswap until they are either loaded or invalidated.
+
 A debugfs interface is provided for various statistic about pool size, number
-of pages stored, and various counters for the reasons pages are rejected.
+of pages stored, same-value filled pages and various counters for the reasons
+pages are rejected.
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 3448e675b462..ad41b3813f0a 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -1,6 +1,4 @@
 
-<previous description obsolete, deleted>
-
 Virtual memory map with 4 level page tables:
 
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
@@ -14,13 +12,16 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
 ... unused hole ...
+fffffe0000000000 - fffffe7fffffffff (=39 bits) LDT remap for PTI
+fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable)
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - [fixmap start]   (~1526 MB) module mapping space (variable)
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Virtual memory map with 5 level page tables:
@@ -29,26 +30,29 @@ Virtual memory map with 5 level page tables:
 hole caused by [56:63] sign extension
 ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor
 ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory
-ff90000000000000 - ff91ffffffffffff (=49 bits) hole
-ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
+ff90000000000000 - ff9fffffffffffff (=52 bits) LDT remap for PTI
+ffa0000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space (12800 TB)
 ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
 ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
 ... unused hole ...
 ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
 ... unused hole ...
+fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - [fixmap start]   (~1526 MB) module mapping space
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Architecture defines a 64-bit virtual address. Implementations can support
 less. Currently supported are 48- and 57-bit virtual addresses. Bits 63
-through to the most-significant implemented bit are set to either all ones
-or all zero. This causes hole between user space and kernel addresses.
+through to the most-significant implemented bit are sign extended.
+This causes hole between user space and kernel addresses if you interpret them
+as unsigned.
 
 The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
@@ -58,9 +62,6 @@ vmalloc space is lazily synchronized into the different PML4/PML5 pages of
 the processes using the page fault handler, with init_top_pgt as
 reference.
 
-Current X86-64 implementations support up to 46 bits of address space (64 TB),
-which is our current limit. This expands into MBZ space in the page tables.
-
 We map EFI runtime services in the 'efi_pgd' PGD in a 64Gb large virtual
 memory window (this size is arbitrary, it can be raised later if needed).
 The mappings are not part of any other kernel PGD and are only available
@@ -72,5 +73,3 @@ following fixmap section.
 Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all
 physical memory, vmalloc/ioremap space and virtual memory map are randomized.
 Their order is preserved but their base will be offset early at boot time.
-
--Andi Kleen, Jul 2004