Merge tag 'v4.16-rc4' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

22 files changed, 357 insertions, 65 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-platform-dock b/Documentation/ABI/testing/sysfs-devices-platform-dock
new file mode 100644
index 000000000000..1d8c18f905c7
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-platform-dock
@@ -0,0 +1,39 @@
+What:		/sys/devices/platform/dock.N/docked
+Date:		Dec, 2006
+KernelVersion:	2.6.19
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Value 1 or 0 indicates whether the software believes the
+		laptop is docked in a docking station.
+
+What:		/sys/devices/platform/dock.N/undock
+Date:		Dec, 2006
+KernelVersion:	2.6.19
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(WO) Writing to this file causes the software to initiate an
+		undock request to the firmware.
+
+What:		/sys/devices/platform/dock.N/uid
+Date:		Feb, 2007
+KernelVersion:	v2.6.21
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Displays the docking station the laptop is docked to.
+
+What:		/sys/devices/platform/dock.N/flags
+Date:		May, 2007
+KernelVersion:	v2.6.21
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Show dock station flags, useful for checking if undock
+		request has been made by the user (from the immediate_undock
+		option).
+
+What:		/sys/devices/platform/dock.N/type
+Date:		Aug, 2008
+KernelVersion:	v2.6.27
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Display the dock station type- dock_station, ata_bay or
+		battery_bay.
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index bfd29bc8d37a..4ed63b6cfb15 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -108,6 +108,8 @@ Description:	CPU topology files that describe a logical CPU's relationship
 
 What:		/sys/devices/system/cpu/cpuidle/current_driver
 		/sys/devices/system/cpu/cpuidle/current_governer_ro
+		/sys/devices/system/cpu/cpuidle/available_governors
+		/sys/devices/system/cpu/cpuidle/current_governor
 Date:		September 2007
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Discover cpuidle policy and mechanism
@@ -119,13 +121,84 @@ Description:	Discover cpuidle policy and mechanism
 		Idle policy (governor) is differentiated from idle mechanism
 		(driver)
 
-		current_driver: displays current idle mechanism
+		current_driver: (RO) displays current idle mechanism
 
-		current_governor_ro: displays current idle policy
+		current_governor_ro: (RO) displays current idle policy
+
+		With the cpuidle_sysfs_switch boot option enabled (meant for
+		developer testing), the following three attributes are visible
+		instead:
+
+		current_driver: same as described above
+
+		available_governors: (RO) displays a space separated list of
+		available governors
+
+		current_governor: (RW) displays current idle policy. Users can
+		switch the governor at runtime by writing to this file.
 
 		See files in Documentation/cpuidle/ for more information.
 
 
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/name
+		/sys/devices/system/cpu/cpuX/cpuidle/stateN/latency
+		/sys/devices/system/cpu/cpuX/cpuidle/stateN/power
+		/sys/devices/system/cpu/cpuX/cpuidle/stateN/time
+		/sys/devices/system/cpu/cpuX/cpuidle/stateN/usage
+Date:		September 2007
+KernelVersion:	v2.6.24
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		The directory /sys/devices/system/cpu/cpuX/cpuidle contains per
+		logical CPU specific cpuidle information for each online cpu X.
+		The processor idle states which are available for use have the
+		following attributes:
+
+		name: (RO) Name of the idle state (string).
+
+		latency: (RO) The latency to exit out of this idle state (in
+		microseconds).
+
+		power: (RO) The power consumed while in this idle state (in
+		milliwatts).
+
+		time: (RO) The total time spent in this idle state (in microseconds).
+
+		usage: (RO) Number of times this state was entered (a count).
+
+
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/desc
+Date:		February 2008
+KernelVersion:	v2.6.25
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		(RO) A small description about the idle state (string).
+
+
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/disable
+Date:		March 2012
+KernelVersion:	v3.10
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		(RW) Option to disable this idle state (bool). The behavior and
+		the effect of the disable variable depends on the implementation
+		of a particular governor. In the ladder governor, for example,
+		it is not coherent, i.e. if one is disabling a light state, then
+		all deeper states are disabled as well, but the disable variable
+		does not reflect it. Likewise, if one enables a deep state but a
+		lighter state still is disabled, then this has no effect.
+
+
+What:		/sys/devices/system/cpu/cpuX/cpuidle/stateN/residency
+Date:		March 2014
+KernelVersion:	v3.15
+Contact:	Linux power management list <linux-pm@vger.kernel.org>
+Description:
+		(RO) Display the target residency i.e. the minimum amount of
+		time (in microseconds) this cpu should spend in this idle state
+		to make the transition worth the effort.
+
+
 What:		/sys/devices/system/cpu/cpu#/cpufreq/*
 Date:		pre-git history
 Contact:	linux-pm@vger.kernel.org
diff --git a/Documentation/ABI/testing/sysfs-platform-dptf b/Documentation/ABI/testing/sysfs-platform-dptf
new file mode 100644
index 000000000000..325dc0667dbb
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-platform-dptf
@@ -0,0 +1,40 @@
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/charger_type
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) The charger type - Traditional, Hybrid or NVDC.
+
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/adapter_rating_mw
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Adapter rating in milliwatts (the maximum Adapter power).
+		Must be 0 if no AC Adaptor is plugged in.
+
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/max_platform_power_mw
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Maximum platform power that can be supported by the battery
+		in milliwatts.
+
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/platform_power_source
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) Display the platform power source
+		0x00 = DC
+		0x01 = AC
+		0x02 = USB
+		0x03 = Wireless Charger
+
+What:		/sys/bus/platform/devices/INT3407:00/dptf_power/battery_steady_power
+Date:		Jul, 2016
+KernelVersion:	v4.10
+Contact:	linux-acpi@vger.kernel.org
+Description:
+		(RO) The maximum sustained power for battery in milliwatts.
diff --git a/Documentation/PCI/pci.txt b/Documentation/PCI/pci.txt
index 611a75e4366e..badb26ac33dc 100644
--- a/Documentation/PCI/pci.txt
+++ b/Documentation/PCI/pci.txt
@@ -570,7 +570,9 @@ your driver if they're helpful, or just use plain hex constants.
 The device IDs are arbitrary hex numbers (vendor controlled) and normally used
 only in a single location, the pci_device_id table.
 
-Please DO submit new vendor/device IDs to http://pciids.sourceforge.net/.
+Please DO submit new vendor/device IDs to http://pci-ids.ucw.cz/.
+There are mirrors of the pci.ids file at http://pciids.sourceforge.net/
+and https://github.com/pciutils/pciids.
 
 
 
diff --git a/Documentation/atomic_bitops.txt b/Documentation/atomic_bitops.txt
index 5550bfdcce5f..be70b32c95d9 100644
--- a/Documentation/atomic_bitops.txt
+++ b/Documentation/atomic_bitops.txt
@@ -58,7 +58,12 @@ Like with atomic_t, the rule of thumb is:
 
  - RMW operations that have a return value are fully ordered.
 
-Except for test_and_set_bit_lock() which has ACQUIRE semantics and
+ - RMW operations that are conditional are unordered on FAILURE,
+   otherwise the above rules apply. In the case of test_and_{}_bit() operations,
+   if the bit in memory is unchanged by the operation then it is deemed to have
+   failed.
+
+Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics and
 clear_bit_unlock() which has RELEASE semantics.
 
 Since a platform only has a single means of achieving atomic operations
diff --git a/Documentation/devicetree/bindings/misc/arm-charlcd.txt b/Documentation/devicetree/bindings/auxdisplay/arm-charlcd.txt
index e28e2aac47f1..e28e2aac47f1 100644
--- a/Documentation/devicetree/bindings/misc/arm-charlcd.txt
+++ b/Documentation/devicetree/bindings/auxdisplay/arm-charlcd.txt
diff --git a/Documentation/devicetree/bindings/eeprom/at24.txt b/Documentation/devicetree/bindings/eeprom/at24.txt
index 1812c848e369..abfae1beca2b 100644
--- a/Documentation/devicetree/bindings/eeprom/at24.txt
+++ b/Documentation/devicetree/bindings/eeprom/at24.txt
@@ -38,9 +38,9 @@ Required properties:
 
                 "catalyst",
                 "microchip",
+                "nxp",
                 "ramtron",
                 "renesas",
-                "nxp",
                 "st",
 
                 Some vendors use different model names for chips which are just
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
index 33c9a10fdc91..20f121daa910 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
@@ -14,6 +14,7 @@ Required properties:
     - "renesas,irqc-r8a7794" (R-Car E2)
     - "renesas,intc-ex-r8a7795" (R-Car H3)
     - "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-r8a77995" (R-Car D3)
 - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
diff --git a/Documentation/devicetree/bindings/power/wakeup-source.txt b/Documentation/devicetree/bindings/power/wakeup-source.txt
index 3c81f78b5c27..5d254ab13ebf 100644
--- a/Documentation/devicetree/bindings/power/wakeup-source.txt
+++ b/Documentation/devicetree/bindings/power/wakeup-source.txt
@@ -60,7 +60,7 @@ Examples
 		#size-cells = <0>;
 
 		button@1 {
-			debounce_interval = <50>;
+			debounce-interval = <50>;
 			wakeup-source;
 			linux,code = <116>;
 			label = "POWER";
diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.txt b/Documentation/devicetree/bindings/thermal/imx-thermal.txt
index 28be51afdb6a..379eb763073e 100644
--- a/Documentation/devicetree/bindings/thermal/imx-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/imx-thermal.txt
@@ -22,7 +22,32 @@ Optional properties:
 - clocks : thermal sensor's clock source.
 
 Example:
+ocotp: ocotp@21bc000 {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "fsl,imx6sx-ocotp", "syscon";
+	reg = <0x021bc000 0x4000>;
+	clocks = <&clks IMX6SX_CLK_OCOTP>;
 
+	tempmon_calib: calib@38 {
+		reg = <0x38 4>;
+	};
+
+	tempmon_temp_grade: temp-grade@20 {
+		reg = <0x20 4>;
+	};
+};
+
+tempmon: tempmon {
+	compatible = "fsl,imx6sx-tempmon", "fsl,imx6q-tempmon";
+	interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
+	fsl,tempmon = <&anatop>;
+	nvmem-cells = <&tempmon_calib>, <&tempmon_temp_grade>;
+	nvmem-cell-names = "calib", "temp_grade";
+	clocks = <&clks IMX6SX_CLK_PLL3_USB_OTG>;
+};
+
+Legacy method (Deprecated):
 tempmon {
 	compatible = "fsl,imx6q-tempmon";
 	fsl,tempmon = <&anatop>;
diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
new file mode 100644
index 000000000000..2c815a7f1ba7
--- /dev/null
+++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
@@ -0,0 +1,62 @@
+#
+# Feature name:          membarrier-sync-core
+#         Kconfig:       ARCH_HAS_MEMBARRIER_SYNC_CORE
+#         description:   arch supports core serializing membarrier
+#
+# Architecture requirements
+#
+# * arm64
+#
+# Rely on eret context synchronization when returning from IPI handler, and
+# when returning to user-space.
+#
+# * x86
+#
+# x86-32 uses IRET as return from interrupt, which takes care of the IPI.
+# However, it uses both IRET and SYSEXIT to go back to user-space. The IRET
+# instruction is core serializing, but not SYSEXIT.
+#
+# x86-64 uses IRET as return from interrupt, which takes care of the IPI.
+# However, it can return to user-space through either SYSRETL (compat code),
+# SYSRETQ, or IRET.
+#
+# Given that neither SYSRET{L,Q}, nor SYSEXIT, are core serializing, we rely
+# instead on write_cr3() performed by switch_mm() to provide core serialization
+# after changing the current mm, and deal with the special case of kthread ->
+# uthread (temporarily keeping current mm into active_mm) by issuing a
+# sync_core_before_usermode() in that specific case.
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: |  ok  |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/gpu/tve200.rst b/Documentation/gpu/tve200.rst
index 69b17b324e12..152ea9398f7e 100644
--- a/Documentation/gpu/tve200.rst
+++ b/Documentation/gpu/tve200.rst
@@ -3,4 +3,4 @@
 ==================================
 
 .. kernel-doc:: drivers/gpu/drm/tve200/tve200_drv.c
-   :doc: Faraday TV Encoder 200
+   :doc: Faraday TV Encoder TVE200 DRM Driver
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index d47702456926..65514c251318 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -28,8 +28,10 @@ Supported adapters:
   * Intel Wildcat Point (PCH)
   * Intel Wildcat Point-LP (PCH)
   * Intel BayTrail (SOC)
+  * Intel Braswell (SOC)
   * Intel Sunrise Point-H (PCH)
   * Intel Sunrise Point-LP (PCH)
+  * Intel Kaby Lake-H (PCH)
   * Intel DNV (SOC)
   * Intel Broxton (SOC)
   * Intel Lewisburg (PCH)
diff --git a/Documentation/locking/mutex-design.txt b/Documentation/locking/mutex-design.txt
index 60c482df1a38..818aca19612f 100644
--- a/Documentation/locking/mutex-design.txt
+++ b/Documentation/locking/mutex-design.txt
@@ -21,37 +21,23 @@ Implementation
 --------------
 
 Mutexes are represented by 'struct mutex', defined in include/linux/mutex.h
-and implemented in kernel/locking/mutex.c. These locks use a three
-state atomic counter (->count) to represent the different possible
-transitions that can occur during the lifetime of a lock:
-
-	  1: unlocked
-	  0: locked, no waiters
-   negative: locked, with potential waiters
-
-In its most basic form it also includes a wait-queue and a spinlock
-that serializes access to it. CONFIG_SMP systems can also include
-a pointer to the lock task owner (->owner) as well as a spinner MCS
-lock (->osq), both described below in (ii).
+and implemented in kernel/locking/mutex.c. These locks use an atomic variable
+(->owner) to keep track of the lock state during its lifetime.  Field owner
+actually contains 'struct task_struct *' to the current lock owner and it is
+therefore NULL if not currently owned. Since task_struct pointers are aligned
+at at least L1_CACHE_BYTES, low bits (3) are used to store extra state (e.g.,
+if waiter list is non-empty).  In its most basic form it also includes a
+wait-queue and a spinlock that serializes access to it. Furthermore,
+CONFIG_MUTEX_SPIN_ON_OWNER=y systems use a spinner MCS lock (->osq), described
+below in (ii).
 
 When acquiring a mutex, there are three possible paths that can be
 taken, depending on the state of the lock:
 
-(i) fastpath: tries to atomically acquire the lock by decrementing the
-    counter. If it was already taken by another task it goes to the next
-    possible path. This logic is architecture specific. On x86-64, the
-    locking fastpath is 2 instructions:
-
-    0000000000000e10 <mutex_lock>:
-    e21:   f0 ff 0b                lock decl (%rbx)
-    e24:   79 08                   jns    e2e <mutex_lock+0x1e>
-
-   the unlocking fastpath is equally tight:
-
-    0000000000000bc0 <mutex_unlock>:
-    bc8:   f0 ff 07                lock incl (%rdi)
-    bcb:   7f 0a                   jg     bd7 <mutex_unlock+0x17>
-
+(i) fastpath: tries to atomically acquire the lock by cmpxchg()ing the owner with
+    the current task. This only works in the uncontended case (cmpxchg() checks
+    against 0UL, so all 3 state bits above have to be 0). If the lock is
+    contended it goes to the next possible path.
 
 (ii) midpath: aka optimistic spinning, tries to spin for acquisition
      while the lock owner is running and there are no other tasks ready
@@ -143,11 +129,10 @@ Test if the mutex is taken:
 Disadvantages
 -------------
 
-Unlike its original design and purpose, 'struct mutex' is larger than
-most locks in the kernel. E.g: on x86-64 it is 40 bytes, almost twice
-as large as 'struct semaphore' (24 bytes) and tied, along with rwsems,
-for the largest lock in the kernel. Larger structure sizes mean more
-CPU cache and memory footprint.
+Unlike its original design and purpose, 'struct mutex' is among the largest
+locks in the kernel. E.g: on x86-64 it is 32 bytes, where 'struct semaphore'
+is 24 bytes and rw_semaphore is 40 bytes. Larger structure sizes mean more CPU
+cache and memory footprint.
 
 When to use mutexes
 -------------------
diff --git a/Documentation/media/dmx.h.rst.exceptions b/Documentation/media/dmx.h.rst.exceptions
index 63f55a9ae2b1..a8c4239ed95b 100644
--- a/Documentation/media/dmx.h.rst.exceptions
+++ b/Documentation/media/dmx.h.rst.exceptions
@@ -50,9 +50,15 @@ replace typedef dmx_filter_t :c:type:`dmx_filter`
 replace typedef dmx_pes_type_t :c:type:`dmx_pes_type`
 replace typedef dmx_input_t :c:type:`dmx_input`
 
-ignore symbol DMX_OUT_DECODER
-ignore symbol DMX_OUT_TAP
-ignore symbol DMX_OUT_TS_TAP
-ignore symbol DMX_OUT_TSDEMUX_TAP
+replace symbol DMX_BUFFER_FLAG_HAD_CRC32_DISCARD :c:type:`dmx_buffer_flags`
+replace	symbol DMX_BUFFER_FLAG_TEI :c:type:`dmx_buffer_flags`
+replace	symbol DMX_BUFFER_PKT_COUNTER_MISMATCH :c:type:`dmx_buffer_flags`
+replace	symbol DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED :c:type:`dmx_buffer_flags`
+replace	symbol DMX_BUFFER_FLAG_DISCONTINUITY_INDICATOR :c:type:`dmx_buffer_flags`
+
+replace symbol DMX_OUT_DECODER :c:type:`dmx_output`
+replace symbol DMX_OUT_TAP :c:type:`dmx_output`
+replace symbol DMX_OUT_TS_TAP :c:type:`dmx_output`
+replace symbol DMX_OUT_TSDEMUX_TAP :c:type:`dmx_output`
 
 replace ioctl DMX_DQBUF dmx_qbuf
diff --git a/Documentation/media/uapi/dvb/dmx-qbuf.rst b/Documentation/media/uapi/dvb/dmx-qbuf.rst
index b48c4931658e..be5a4c6f1904 100644
--- a/Documentation/media/uapi/dvb/dmx-qbuf.rst
+++ b/Documentation/media/uapi/dvb/dmx-qbuf.rst
@@ -51,9 +51,10 @@ out to disk. Buffers remain locked until dequeued, until the
 the device is closed.
 
 Applications call the ``DMX_DQBUF`` ioctl to dequeue a filled
-(capturing) buffer from the driver's outgoing queue. They just set the ``reserved`` field array to zero. When ``DMX_DQBUF`` is called with a
-pointer to this structure, the driver fills the remaining fields or
-returns an error code.
+(capturing) buffer from the driver's outgoing queue.
+They just set the ``index`` field withe the buffer ID to be queued.
+When ``DMX_DQBUF`` is called with a pointer to struct :c:type:`dmx_buffer`,
+the driver fills the remaining fields or returns an error code.
 
 By default ``DMX_DQBUF`` blocks when no buffer is in the outgoing
 queue. When the ``O_NONBLOCK`` flag was given to the
diff --git a/Documentation/networking/segmentation-offloads.txt b/Documentation/networking/segmentation-offloads.txt
index 2f09455a993a..d47480b61ac6 100644
--- a/Documentation/networking/segmentation-offloads.txt
+++ b/Documentation/networking/segmentation-offloads.txt
@@ -13,6 +13,7 @@ The following technologies are described:
  * Generic Segmentation Offload - GSO
  * Generic Receive Offload - GRO
  * Partial Generic Segmentation Offload - GSO_PARTIAL
+ * SCTP accelleration with GSO - GSO_BY_FRAGS
 
 TCP Segmentation Offload
 ========================
@@ -49,6 +50,10 @@ datagram into multiple IPv4 fragments.  Many of the requirements for UDP
 fragmentation offload are the same as TSO.  However the IPv4 ID for
 fragments should not increment as a single IPv4 datagram is fragmented.
 
+UFO is deprecated: modern kernels will no longer generate UFO skbs, but can
+still receive them from tuntap and similar devices. Offload of UDP-based
+tunnel protocols is still supported.
+
 IPIP, SIT, GRE, UDP Tunnel, and Remote Checksum Offloads
 ========================================================
 
@@ -83,10 +88,10 @@ SKB_GSO_UDP_TUNNEL_CSUM.  These two additional tunnel types reflect the
 fact that the outer header also requests to have a non-zero checksum
 included in the outer header.
 
-Finally there is SKB_GSO_REMCSUM which indicates that a given tunnel header
-has requested a remote checksum offload.  In this case the inner headers
-will be left with a partial checksum and only the outer header checksum
-will be computed.
+Finally there is SKB_GSO_TUNNEL_REMCSUM which indicates that a given tunnel
+header has requested a remote checksum offload.  In this case the inner
+headers will be left with a partial checksum and only the outer header
+checksum will be computed.
 
 Generic Segmentation Offload
 ============================
@@ -128,3 +133,28 @@ values for if the header was simply duplicated.  The one exception to this
 is the outer IPv4 ID field.  It is up to the device drivers to guarantee
 that the IPv4 ID field is incremented in the case that a given header does
 not have the DF bit set.
+
+SCTP accelleration with GSO
+===========================
+
+SCTP - despite the lack of hardware support - can still take advantage of
+GSO to pass one large packet through the network stack, rather than
+multiple small packets.
+
+This requires a different approach to other offloads, as SCTP packets
+cannot be just segmented to (P)MTU. Rather, the chunks must be contained in
+IP segments, padding respected. So unlike regular GSO, SCTP can't just
+generate a big skb, set gso_size to the fragmentation point and deliver it
+to IP layer.
+
+Instead, the SCTP protocol layer builds an skb with the segments correctly
+padded and stored as chained skbs, and skb_segment() splits based on those.
+To signal this, gso_size is set to the special value GSO_BY_FRAGS.
+
+Therefore, any code in the core networking stack must be aware of the
+possibility that gso_size will be GSO_BY_FRAGS and handle that case
+appropriately. (For size checks, the skb_gso_validate_*_len family of
+helpers do this automatically.)
+
+This also affects drivers with the NETIF_F_FRAGLIST & NETIF_F_GSO_SCTP bits
+set. Note also that NETIF_F_GSO_SCTP is included in NETIF_F_GSO_SOFTWARE.
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 792fa8717d13..d6b3ff51a14f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -123,14 +123,15 @@ memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
 flag KVM_VM_MIPS_VZ.
 
 
-4.3 KVM_GET_MSR_INDEX_LIST
+4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST
 
-Capability: basic
+Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST
 Architectures: x86
-Type: system
+Type: system ioctl
 Parameters: struct kvm_msr_list (in/out)
 Returns: 0 on success; -1 on error
 Errors:
+  EFAULT:    the msr index list cannot be read from or written to
   E2BIG:     the msr index list is to be to fit in the array specified by
              the user.
 
@@ -139,16 +140,23 @@ struct kvm_msr_list {
 	__u32 indices[0];
 };
 
-This ioctl returns the guest msrs that are supported.  The list varies
-by kvm version and host processor, but does not change otherwise.  The
-user fills in the size of the indices array in nmsrs, and in return
-kvm adjusts nmsrs to reflect the actual number of msrs and fills in
-the indices array with their numbers.
+The user fills in the size of the indices array in nmsrs, and in return
+kvm adjusts nmsrs to reflect the actual number of msrs and fills in the
+indices array with their numbers.
+
+KVM_GET_MSR_INDEX_LIST returns the guest msrs that are supported.  The list
+varies by kvm version and host processor, but does not change otherwise.
 
 Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are
 not returned in the MSR list, as different vcpus can have a different number
 of banks, as set via the KVM_X86_SETUP_MCE ioctl.
 
+KVM_GET_MSR_FEATURE_INDEX_LIST returns the list of MSRs that can be passed
+to the KVM_GET_MSRS system ioctl.  This lets userspace probe host capabilities
+and processor features that are exposed via MSRs (e.g., VMX capabilities).
+This list also varies by kvm version and host processor, but does not change
+otherwise.
+
 
 4.4 KVM_CHECK_EXTENSION
 
@@ -475,14 +483,22 @@ Support for this has been removed.  Use KVM_SET_GUEST_DEBUG instead.
 
 4.18 KVM_GET_MSRS
 
-Capability: basic
+Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system)
 Architectures: x86
-Type: vcpu ioctl
+Type: system ioctl, vcpu ioctl
 Parameters: struct kvm_msrs (in/out)
-Returns: 0 on success, -1 on error
+Returns: number of msrs successfully returned;
+        -1 on error
+
+When used as a system ioctl:
+Reads the values of MSR-based features that are available for the VM.  This
+is similar to KVM_GET_SUPPORTED_CPUID, but it returns MSR indices and values.
+The list of msr-based features can be obtained using KVM_GET_MSR_FEATURE_INDEX_LIST
+in a system ioctl.
 
+When used as a vcpu ioctl:
 Reads model-specific registers from the vcpu.  Supported msr indices can
-be obtained using KVM_GET_MSR_INDEX_LIST.
+be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl.
 
 struct kvm_msrs {
 	__u32 nmsrs; /* number of msrs in entries */
diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index dcab6dc11e3b..87a7506f31c2 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -58,6 +58,10 @@ KVM_FEATURE_PV_TLB_FLUSH           ||     9 || guest checks this feature bit
                                    ||       || before enabling paravirtualized
                                    ||       || tlb flush.
 ------------------------------------------------------------------------------
+KVM_FEATURE_ASYNC_PF_VMEXIT        ||    10 || paravirtualized async PF VM exit
+                                   ||       || can be enabled by setting bit 2
+                                   ||       || when writing to msr 0x4b564d02
+------------------------------------------------------------------------------
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
                                    ||       || per-cpu warps are expected in
                                    ||       || kvmclock.
diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
index 1ebecc115dc6..f3f0d57ced8e 100644
--- a/Documentation/virtual/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
@@ -170,7 +170,8 @@ MSR_KVM_ASYNC_PF_EN: 0x4b564d02
 	when asynchronous page faults are enabled on the vcpu 0 when
 	disabled. Bit 1 is 1 if asynchronous page faults can be injected
 	when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults
-	are delivered to L1 as #PF vmexits.
+	are delivered to L1 as #PF vmexits.  Bit 2 can be set only if
+	KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID.
 
 	First 4 byte of 64 byte memory location will be written to by
 	the hypervisor at the time of asynchronous page fault (APF)
diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index 756fd76b78a6..71c30984e94d 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -671,7 +671,7 @@ occupancy of the real time threads on these cores.
 # mkdir p1
 
 Move the cpus 4-7 over to p1
-# echo f0 > p0/cpus
+# echo f0 > p1/cpus
 
 View the llc occupancy snapshot
 
diff --git a/Documentation/x86/topology.txt b/Documentation/x86/topology.txt
index f3e9d7e9ed6c..2953e3ec9a02 100644
--- a/Documentation/x86/topology.txt
+++ b/Documentation/x86/topology.txt
@@ -108,7 +108,7 @@ The topology of a system is described in the units of:
 
     The number of online threads is also printed in /proc/cpuinfo "siblings."
 
-  - topology_sibling_mask():
+  - topology_sibling_cpumask():
 
     The cpumask contains all online threads in the core to which a thread
     belongs.