Merge branch 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull sigingo fix from Eric Biederman:
 "The kbuild test robot found that I accidentally moved si_pkey when I
  was cleaning up siginfo_t. A short followed by an int with the int
  having 8 byte alignment. Sheesh siginfo_t is a weird structure.

  I have now corrected it and added build time checks that with a little
  luck will catch any similar future mistakes. The build time checks
  were sufficient for me to verify the bug and to verify my fix. So they
  are at least useful this once."

* 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  signal/x86: Include the field offsets in the build time checks
  signal: Correct the offset of si_pkey in struct siginfo
diff --git a/.gitignore b/.gitignore
index 705e099..1be78fd 100644
--- a/.gitignore
+++ b/.gitignore
@@ -127,3 +127,7 @@
 
 # Kdevelop4
 *.kdev4
+
+#Automatically generated by ASN.1 compiler
+net/ipv4/netfilter/nf_nat_snmp_basic-asn1.c
+net/ipv4/netfilter/nf_nat_snmp_basic-asn1.h
diff --git a/Documentation/ABI/testing/sysfs-devices-platform-dock b/Documentation/ABI/testing/sysfs-devices-platform-dock
new file mode 100644
index 0000000..1d8c18f
--- /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 bfd29bc..4ed63b6 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -108,6 +108,8 @@
 
 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 @@
 		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 0000000..325dc06
--- /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 611a75e4..badb26a 100644
--- a/Documentation/PCI/pci.txt
+++ b/Documentation/PCI/pci.txt
@@ -570,7 +570,9 @@
 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 5550bfdc..be70b32 100644
--- a/Documentation/atomic_bitops.txt
+++ b/Documentation/atomic_bitops.txt
@@ -58,7 +58,12 @@
 
  - 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
similarity index 100%
rename from Documentation/devicetree/bindings/misc/arm-charlcd.txt
rename to Documentation/devicetree/bindings/auxdisplay/arm-charlcd.txt
diff --git a/Documentation/devicetree/bindings/eeprom/at24.txt b/Documentation/devicetree/bindings/eeprom/at24.txt
index 1812c84..abfae1b 100644
--- a/Documentation/devicetree/bindings/eeprom/at24.txt
+++ b/Documentation/devicetree/bindings/eeprom/at24.txt
@@ -38,9 +38,9 @@
 
                 "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 33c9a10..20f121d 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
@@ -14,6 +14,7 @@
     - "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/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index c902261..92fd4b2 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -18,6 +18,7 @@
       - "renesas,etheravb-r8a7795" for the R8A7795 SoC.
       - "renesas,etheravb-r8a7796" for the R8A7796 SoC.
       - "renesas,etheravb-r8a77970" for the R8A77970 SoC.
+      - "renesas,etheravb-r8a77980" for the R8A77980 SoC.
       - "renesas,etheravb-r8a77995" for the R8A77995 SoC.
       - "renesas,etheravb-rcar-gen3" as a fallback for the above
 		R-Car Gen3 devices.
diff --git a/Documentation/devicetree/bindings/power/mti,mips-cpc.txt b/Documentation/devicetree/bindings/power/mti,mips-cpc.txt
new file mode 100644
index 0000000..c6b8251
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/mti,mips-cpc.txt
@@ -0,0 +1,8 @@
+Binding for MIPS Cluster Power Controller (CPC).
+
+This binding allows a system to specify where the CPC registers are
+located.
+
+Required properties:
+compatible : Should be "mti,mips-cpc".
+regs: Should describe the address & size of the CPC register region.
diff --git a/Documentation/devicetree/bindings/power/wakeup-source.txt b/Documentation/devicetree/bindings/power/wakeup-source.txt
index 3c81f78..5d254ab 100644
--- a/Documentation/devicetree/bindings/power/wakeup-source.txt
+++ b/Documentation/devicetree/bindings/power/wakeup-source.txt
@@ -60,7 +60,7 @@
 		#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 28be51a..379eb76 100644
--- a/Documentation/devicetree/bindings/thermal/imx-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/imx-thermal.txt
@@ -22,7 +22,32 @@
 - 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 0000000..2c815a7
--- /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 69b17b3..152ea93 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 d477024..65514c2 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -28,8 +28,10 @@
   * 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/ia64/serial.txt b/Documentation/ia64/serial.txt
index 6869c73..a63d2c5 100644
--- a/Documentation/ia64/serial.txt
+++ b/Documentation/ia64/serial.txt
@@ -111,7 +111,7 @@
 
 	- If you don't have an HCDP, the kernel doesn't know where
 	  your console lives until the driver discovers serial
-	  devices.  Use "console=uart, io,0x3f8" (or appropriate
+	  devices.  Use "console=uart,io,0x3f8" (or appropriate
 	  address for your machine).
 
     Kernel and init script output works fine, but no "login:" prompt:
diff --git a/Documentation/locking/mutex-design.txt b/Documentation/locking/mutex-design.txt
index 60c482d..818aca1 100644
--- a/Documentation/locking/mutex-design.txt
+++ b/Documentation/locking/mutex-design.txt
@@ -21,37 +21,23 @@
 --------------
 
 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 @@
 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 63f55a9..a8c4239 100644
--- a/Documentation/media/dmx.h.rst.exceptions
+++ b/Documentation/media/dmx.h.rst.exceptions
@@ -50,9 +50,15 @@
 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 b48c493..be5a4c6 100644
--- a/Documentation/media/uapi/dvb/dmx-qbuf.rst
+++ b/Documentation/media/uapi/dvb/dmx-qbuf.rst
@@ -51,9 +51,10 @@
 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 2f09455..d47480b 100644
--- a/Documentation/networking/segmentation-offloads.txt
+++ b/Documentation/networking/segmentation-offloads.txt
@@ -13,6 +13,7 @@
  * 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 @@
 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 @@
 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 @@
 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 792fa87..d6b3ff5 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -123,14 +123,15 @@
 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 @@
 	__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 @@
 
 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 dcab6dc..87a7506 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -58,6 +58,10 @@
                                    ||       || 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 1ebecc1..f3f0d57 100644
--- a/Documentation/virtual/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
@@ -170,7 +170,8 @@
 	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 756fd76..71c3098 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -671,7 +671,7 @@
 # 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 f3e9d7e..2953e3e 100644
--- a/Documentation/x86/topology.txt
+++ b/Documentation/x86/topology.txt
@@ -108,7 +108,7 @@
 
     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.
diff --git a/MAINTAINERS b/MAINTAINERS
index 3bdc260..4623caf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1238,7 +1238,7 @@
 
 ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT
 M:	Nicolas Ferre <nicolas.ferre@microchip.com>
-M:	Alexandre Belloni <alexandre.belloni@free-electrons.com>
+M:	Alexandre Belloni <alexandre.belloni@bootlin.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 W:	http://www.linux4sam.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nferre/linux-at91.git
@@ -1590,7 +1590,7 @@
 M:	Jason Cooper <jason@lakedaemon.net>
 M:	Andrew Lunn <andrew@lunn.ch>
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
-M:	Gregory Clement <gregory.clement@free-electrons.com>
+M:	Gregory Clement <gregory.clement@bootlin.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/soc/dove/
@@ -1604,7 +1604,7 @@
 ARM/Marvell Kirkwood and Armada 370, 375, 38x, 39x, XP, 3700, 7K/8K SOC support
 M:	Jason Cooper <jason@lakedaemon.net>
 M:	Andrew Lunn <andrew@lunn.ch>
-M:	Gregory Clement <gregory.clement@free-electrons.com>
+M:	Gregory Clement <gregory.clement@bootlin.com>
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -1999,8 +1999,10 @@
 M:	Alexandre Torgue <alexandre.torgue@st.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mcoquelin/stm32.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/atorgue/stm32.git stm32-next
 N:	stm32
+F:	arch/arm/boot/dts/stm32*
+F:	arch/arm/mach-stm32/
 F:	drivers/clocksource/armv7m_systick.c
 
 ARM/TANGO ARCHITECTURE
@@ -7600,8 +7602,10 @@
 F:	scripts/Makefile.kasan
 
 KCONFIG
+M:	Masahiro Yamada <yamada.masahiro@socionext.com>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git kconfig
 L:	linux-kbuild@vger.kernel.org
-S:	Orphan
+S:	Maintained
 F:	Documentation/kbuild/kconfig-language.txt
 F:	scripts/kconfig/
 
@@ -7909,7 +7913,6 @@
 F:	scripts/leaking_addresses.pl
 
 LED SUBSYSTEM
-M:	Richard Purdie <rpurdie@rpsys.net>
 M:	Jacek Anaszewski <jacek.anaszewski@gmail.com>
 M:	Pavel Machek <pavel@ucw.cz>
 L:	linux-leds@vger.kernel.org
@@ -9206,6 +9209,7 @@
 M:	Paul Burton <paul.burton@mips.com>
 L:	linux-mips@linux-mips.org
 S:	Supported
+F:	Documentation/devicetree/bindings/power/mti,mips-cpc.txt
 F:	arch/mips/generic/
 F:	arch/mips/tools/generic-board-config.sh
 
@@ -9945,6 +9949,7 @@
 
 OBJTOOL
 M:	Josh Poimboeuf <jpoimboe@redhat.com>
+M:	Peter Zijlstra <peterz@infradead.org>
 S:	Supported
 F:	tools/objtool/
 
@@ -10925,6 +10930,17 @@
 S:	Supported
 F:	drivers/pinctrl/pinctrl-at91-pio4.*
 
+PIN CONTROLLER - FREESCALE
+M:	Dong Aisheng <aisheng.dong@nxp.com>
+M:	Fabio Estevam <festevam@gmail.com>
+M:	Shawn Guo <shawnguo@kernel.org>
+M:	Stefan Agner <stefan@agner.ch>
+R:	Pengutronix Kernel Team <kernel@pengutronix.de>
+L:	linux-gpio@vger.kernel.org
+S:	Maintained
+F:	drivers/pinctrl/freescale/
+F:	Documentation/devicetree/bindings/pinctrl/fsl,*
+
 PIN CONTROLLER - INTEL
 M:	Mika Westerberg <mika.westerberg@linux.intel.com>
 M:	Heikki Krogerus <heikki.krogerus@linux.intel.com>
diff --git a/Makefile b/Makefile
index 79ad2bf..c4322de 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc4
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -388,7 +388,7 @@
 CHECK		= sparse
 
 CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
-		  -Wbitwise -Wno-return-void $(CF)
+		  -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF)
 NOSTDINC_FLAGS  =
 CFLAGS_MODULE   =
 AFLAGS_MODULE   =
@@ -489,6 +489,11 @@
 KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
 endif
 
+RETPOLINE_CFLAGS_GCC := -mindirect-branch=thunk-extern -mindirect-branch-register
+RETPOLINE_CFLAGS_CLANG := -mretpoline-external-thunk
+RETPOLINE_CFLAGS := $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG)))
+export RETPOLINE_CFLAGS
+
 ifeq ($(config-targets),1)
 # ===========================================================================
 # *config targets only - make sure prerequisites are updated, and descend
@@ -579,10 +584,9 @@
 # To avoid any implicit rule to kick in, define an empty command
 $(KCONFIG_CONFIG) include/config/auto.conf.cmd: ;
 
-# If .config is newer than include/config/auto.conf, someone tinkered
-# with it and forgot to run make oldconfig.
-# if auto.conf.cmd is missing then we are probably in a cleaned tree so
-# we execute the config step to be sure to catch updated Kconfig files
+# The actual configuration files used during the build are stored in
+# include/generated/ and include/config/. Update them if .config is newer than
+# include/config/auto.conf (which mirrors .config).
 include/config/%.conf: $(KCONFIG_CONFIG) include/config/auto.conf.cmd
 	$(Q)$(MAKE) -f $(srctree)/Makefile silentoldconfig
 else
@@ -857,8 +861,7 @@
 KBUILD_CFLAGS   += $(ARCH_CFLAGS)   $(KCFLAGS)
 
 # Use --build-id when available.
-LDFLAGS_BUILD_ID := $(patsubst -Wl$(comma)%,%,\
-			      $(call cc-ldoption, -Wl$(comma)--build-id,))
+LDFLAGS_BUILD_ID := $(call ld-option, --build-id)
 KBUILD_LDFLAGS_MODULE += $(LDFLAGS_BUILD_ID)
 LDFLAGS_vmlinux += $(LDFLAGS_BUILD_ID)
 
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
index 46ebf14a..8a2b331 100644
--- a/arch/alpha/include/asm/cmpxchg.h
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -6,7 +6,6 @@
  * Atomic exchange routines.
  */
 
-#define __ASM__MB
 #define ____xchg(type, args...)		__xchg ## type ## _local(args)
 #define ____cmpxchg(type, args...)	__cmpxchg ## type ## _local(args)
 #include <asm/xchg.h>
@@ -33,10 +32,6 @@
 	cmpxchg_local((ptr), (o), (n));					\
 })
 
-#ifdef CONFIG_SMP
-#undef __ASM__MB
-#define __ASM__MB	"\tmb\n"
-#endif
 #undef ____xchg
 #undef ____cmpxchg
 #define ____xchg(type, args...)		__xchg ##type(args)
@@ -64,7 +59,6 @@
 	cmpxchg((ptr), (o), (n));					\
 })
 
-#undef __ASM__MB
 #undef ____cmpxchg
 
 #endif /* _ALPHA_CMPXCHG_H */
diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h
index 68dfb3c..e2b59fa 100644
--- a/arch/alpha/include/asm/xchg.h
+++ b/arch/alpha/include/asm/xchg.h
@@ -12,6 +12,10 @@
  * Atomic exchange.
  * Since it can be used to implement critical sections
  * it must clobber "memory" (also for interrupts in UP).
+ *
+ * The leading and the trailing memory barriers guarantee that these
+ * operations are fully ordered.
+ *
  */
 
 static inline unsigned long
@@ -19,6 +23,7 @@
 {
 	unsigned long ret, tmp, addr64;
 
+	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%4,7,%3\n"
 	"	insbl	%1,%4,%1\n"
@@ -28,12 +33,12 @@
 	"	or	%1,%2,%2\n"
 	"	stq_c	%2,0(%3)\n"
 	"	beq	%2,2f\n"
-		__ASM__MB
 	".subsection 2\n"
 	"2:	br	1b\n"
 	".previous"
 	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
 	: "r" ((long)m), "1" (val) : "memory");
+	smp_mb();
 
 	return ret;
 }
@@ -43,6 +48,7 @@
 {
 	unsigned long ret, tmp, addr64;
 
+	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%4,7,%3\n"
 	"	inswl	%1,%4,%1\n"
@@ -52,12 +58,12 @@
 	"	or	%1,%2,%2\n"
 	"	stq_c	%2,0(%3)\n"
 	"	beq	%2,2f\n"
-		__ASM__MB
 	".subsection 2\n"
 	"2:	br	1b\n"
 	".previous"
 	: "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64)
 	: "r" ((long)m), "1" (val) : "memory");
+	smp_mb();
 
 	return ret;
 }
@@ -67,17 +73,18 @@
 {
 	unsigned long dummy;
 
+	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldl_l %0,%4\n"
 	"	bis $31,%3,%1\n"
 	"	stl_c %1,%2\n"
 	"	beq %1,2f\n"
-		__ASM__MB
 	".subsection 2\n"
 	"2:	br 1b\n"
 	".previous"
 	: "=&r" (val), "=&r" (dummy), "=m" (*m)
 	: "rI" (val), "m" (*m) : "memory");
+	smp_mb();
 
 	return val;
 }
@@ -87,17 +94,18 @@
 {
 	unsigned long dummy;
 
+	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldq_l %0,%4\n"
 	"	bis $31,%3,%1\n"
 	"	stq_c %1,%2\n"
 	"	beq %1,2f\n"
-		__ASM__MB
 	".subsection 2\n"
 	"2:	br 1b\n"
 	".previous"
 	: "=&r" (val), "=&r" (dummy), "=m" (*m)
 	: "rI" (val), "m" (*m) : "memory");
+	smp_mb();
 
 	return val;
 }
@@ -128,10 +136,12 @@
  * store NEW in MEM.  Return the initial value in MEM.  Success is
  * indicated by comparing RETURN with OLD.
  *
- * The memory barrier should be placed in SMP only when we actually
- * make the change. If we don't change anything (so if the returned
- * prev is equal to old) then we aren't acquiring anything new and
- * we don't need any memory barrier as far I can tell.
+ * The leading and the trailing memory barriers guarantee that these
+ * operations are fully ordered.
+ *
+ * The trailing memory barrier is placed in SMP unconditionally, in
+ * order to guarantee that dependency ordering is preserved when a
+ * dependency is headed by an unsuccessful operation.
  */
 
 static inline unsigned long
@@ -139,6 +149,7 @@
 {
 	unsigned long prev, tmp, cmp, addr64;
 
+	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%5,7,%4\n"
 	"	insbl	%1,%5,%1\n"
@@ -150,13 +161,13 @@
 	"	or	%1,%2,%2\n"
 	"	stq_c	%2,0(%4)\n"
 	"	beq	%2,3f\n"
-		__ASM__MB
 	"2:\n"
 	".subsection 2\n"
 	"3:	br	1b\n"
 	".previous"
 	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
 	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
+	smp_mb();
 
 	return prev;
 }
@@ -166,6 +177,7 @@
 {
 	unsigned long prev, tmp, cmp, addr64;
 
+	smp_mb();
 	__asm__ __volatile__(
 	"	andnot	%5,7,%4\n"
 	"	inswl	%1,%5,%1\n"
@@ -177,13 +189,13 @@
 	"	or	%1,%2,%2\n"
 	"	stq_c	%2,0(%4)\n"
 	"	beq	%2,3f\n"
-		__ASM__MB
 	"2:\n"
 	".subsection 2\n"
 	"3:	br	1b\n"
 	".previous"
 	: "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64)
 	: "r" ((long)m), "Ir" (old), "1" (new) : "memory");
+	smp_mb();
 
 	return prev;
 }
@@ -193,6 +205,7 @@
 {
 	unsigned long prev, cmp;
 
+	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldl_l %0,%5\n"
 	"	cmpeq %0,%3,%1\n"
@@ -200,13 +213,13 @@
 	"	mov %4,%1\n"
 	"	stl_c %1,%2\n"
 	"	beq %1,3f\n"
-		__ASM__MB
 	"2:\n"
 	".subsection 2\n"
 	"3:	br 1b\n"
 	".previous"
 	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
 	: "r"((long) old), "r"(new), "m"(*m) : "memory");
+	smp_mb();
 
 	return prev;
 }
@@ -216,6 +229,7 @@
 {
 	unsigned long prev, cmp;
 
+	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldq_l %0,%5\n"
 	"	cmpeq %0,%3,%1\n"
@@ -223,13 +237,13 @@
 	"	mov %4,%1\n"
 	"	stq_c %1,%2\n"
 	"	beq %1,3f\n"
-		__ASM__MB
 	"2:\n"
 	".subsection 2\n"
 	"3:	br 1b\n"
 	".previous"
 	: "=&r"(prev), "=&r"(cmp), "=m"(*m)
 	: "r"((long) old), "r"(new), "m"(*m) : "memory");
+	smp_mb();
 
 	return prev;
 }
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index f3a80cf..d76bf4a 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -484,7 +484,6 @@
 
 config ARC_EMUL_UNALIGNED
 	bool "Emulate unaligned memory access (userspace only)"
-	default N
 	select SYSCTL_ARCH_UNALIGN_NO_WARN
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	depends on ISA_ARCOMPACT
diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts
index 70aec7d..626b694 100644
--- a/arch/arc/boot/dts/axs101.dts
+++ b/arch/arc/boot/dts/axs101.dts
@@ -17,6 +17,6 @@
 	compatible = "snps,axs101", "snps,arc-sdp";
 
 	chosen {
-		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60";
+		bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60 print-fatal-signals=1";
 	};
 };
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index 74d070c..47b74fb 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -214,13 +214,13 @@
 			};
 
 			eeprom@0x54{
-				compatible = "24c01";
+				compatible = "atmel,24c01";
 				reg = <0x54>;
 				pagesize = <0x8>;
 			};
 
 			eeprom@0x57{
-				compatible = "24c04";
+				compatible = "atmel,24c04";
 				reg = <0x57>;
 				pagesize = <0x8>;
 			};
diff --git a/arch/arc/boot/dts/haps_hs_idu.dts b/arch/arc/boot/dts/haps_hs_idu.dts
index 215cddd..0c60330 100644
--- a/arch/arc/boot/dts/haps_hs_idu.dts
+++ b/arch/arc/boot/dts/haps_hs_idu.dts
@@ -22,7 +22,7 @@
 	};
 
 	chosen {
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts
index 5ee96b0..ff2f2c7 100644
--- a/arch/arc/boot/dts/nsim_700.dts
+++ b/arch/arc/boot/dts/nsim_700.dts
@@ -17,7 +17,7 @@
 	interrupt-parent = <&core_intc>;
 
 	chosen {
-		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8";
+		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts
index 8d787b2..8e2489b 100644
--- a/arch/arc/boot/dts/nsim_hs.dts
+++ b/arch/arc/boot/dts/nsim_hs.dts
@@ -24,7 +24,7 @@
 	};
 
 	chosen {
-		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8";
+		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts
index 4f98ebf..ed12f4947 100644
--- a/arch/arc/boot/dts/nsim_hs_idu.dts
+++ b/arch/arc/boot/dts/nsim_hs_idu.dts
@@ -15,7 +15,7 @@
 	interrupt-parent = <&core_intc>;
 
 	chosen {
-		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8";
+		bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index 3c391ba..7842e5e 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -20,7 +20,7 @@
 		/* this is for console on PGU */
 		/* bootargs = "console=tty0 consoleblank=0"; */
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts
index 14a727c..b8838cf 100644
--- a/arch/arc/boot/dts/nsimosci_hs.dts
+++ b/arch/arc/boot/dts/nsimosci_hs.dts
@@ -20,7 +20,7 @@
 		/* this is for console on PGU */
 		/* bootargs = "console=tty0 consoleblank=0"; */
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts
index 5052917..72a2c72 100644
--- a/arch/arc/boot/dts/nsimosci_hs_idu.dts
+++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts
@@ -18,7 +18,7 @@
 
 	chosen {
 		/* this is for console on serial */
-		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24";
+		bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24 print-fatal-signals=1";
 	};
 
 	aliases {
diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h
index ea022d4..21ec824 100644
--- a/arch/arc/include/asm/bug.h
+++ b/arch/arc/include/asm/bug.h
@@ -23,7 +23,8 @@
 
 #define BUG()	do {								\
 	pr_warn("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \
-	dump_stack();								\
+	barrier_before_unreachable();						\
+	__builtin_trap();							\
 } while (0)
 
 #define HAVE_ARCH_BUG
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index 257a68f..309f4e6 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -184,7 +184,7 @@
 .macro FAKE_RET_FROM_EXCPN
 	lr      r9, [status32]
 	bic     r9, r9, (STATUS_U_MASK|STATUS_DE_MASK|STATUS_AE_MASK)
-	or      r9, r9, (STATUS_L_MASK|STATUS_IE_MASK)
+	or      r9, r9, STATUS_IE_MASK
 	kflag   r9
 .endm
 
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index f61a52b..5fe84e4 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -22,10 +22,79 @@
 
 static char smp_cpuinfo_buf[128];
 
+/*
+ * Set mask to halt GFRC if any online core in SMP cluster is halted.
+ * Only works for ARC HS v3.0+, on earlier versions has no effect.
+ */
+static void mcip_update_gfrc_halt_mask(int cpu)
+{
+	struct bcr_generic gfrc;
+	unsigned long flags;
+	u32 gfrc_halt_mask;
+
+	READ_BCR(ARC_REG_GFRC_BUILD, gfrc);
+
+	/*
+	 * CMD_GFRC_SET_CORE and CMD_GFRC_READ_CORE commands were added in
+	 * GFRC 0x3 version.
+	 */
+	if (gfrc.ver < 0x3)
+		return;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	__mcip_cmd(CMD_GFRC_READ_CORE, 0);
+	gfrc_halt_mask = read_aux_reg(ARC_REG_MCIP_READBACK);
+	gfrc_halt_mask |= BIT(cpu);
+	__mcip_cmd_data(CMD_GFRC_SET_CORE, 0, gfrc_halt_mask);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void mcip_update_debug_halt_mask(int cpu)
+{
+	u32 mcip_mask = 0;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	/*
+	 * mcip_mask is same for CMD_DEBUG_SET_SELECT and CMD_DEBUG_SET_MASK
+	 * commands. So read it once instead of reading both CMD_DEBUG_READ_MASK
+	 * and CMD_DEBUG_READ_SELECT.
+	 */
+	__mcip_cmd(CMD_DEBUG_READ_SELECT, 0);
+	mcip_mask = read_aux_reg(ARC_REG_MCIP_READBACK);
+
+	mcip_mask |= BIT(cpu);
+
+	__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, mcip_mask);
+	/*
+	 * Parameter specified halt cause:
+	 * STATUS32[H]/actionpoint/breakpoint/self-halt
+	 * We choose all of them (0xF).
+	 */
+	__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xF, mcip_mask);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
 static void mcip_setup_per_cpu(int cpu)
 {
+	struct mcip_bcr mp;
+
+	READ_BCR(ARC_REG_MCIP_BCR, mp);
+
 	smp_ipi_irq_setup(cpu, IPI_IRQ);
 	smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ);
+
+	/* Update GFRC halt mask as new CPU came online */
+	if (mp.gfrc)
+		mcip_update_gfrc_halt_mask(cpu);
+
+	/* Update MCIP debug mask as new CPU came online */
+	if (mp.dbg)
+		mcip_update_debug_halt_mask(cpu);
 }
 
 static void mcip_ipi_send(int cpu)
@@ -101,11 +170,6 @@
 		IS_AVAIL1(mp.gfrc, "GFRC"));
 
 	cpuinfo_arc700[0].extn.gfrc = mp.gfrc;
-
-	if (mp.dbg) {
-		__mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf);
-		__mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf);
-	}
 }
 
 struct plat_smp_ops plat_smp_ops = {
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 9d27331..b2cae79 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -51,7 +51,7 @@
 	{ 0x51, "R2.0" },
 	{ 0x52, "R2.1" },
 	{ 0x53, "R3.0" },
-	{ 0x54, "R4.0" },
+	{ 0x54, "R3.10a" },
 #endif
 	{ 0x00, NULL   }
 };
@@ -373,7 +373,7 @@
 {
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	int saved = 0, present = 0;
-	char *opt_nm = NULL;;
+	char *opt_nm = NULL;
 
 	if (!cpu->extn.timer0)
 		panic("Timer0 is not present!\n");
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index efe8b42..21d86c3 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -24,6 +24,7 @@
 #include <linux/reboot.h>
 #include <linux/irqdomain.h>
 #include <linux/export.h>
+#include <linux/of_fdt.h>
 
 #include <asm/processor.h>
 #include <asm/setup.h>
@@ -47,6 +48,42 @@
 {
 }
 
+static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask)
+{
+	unsigned long dt_root = of_get_flat_dt_root();
+	const char *buf;
+
+	buf = of_get_flat_dt_prop(dt_root, name, NULL);
+	if (!buf)
+		return -EINVAL;
+
+	if (cpulist_parse(buf, cpumask))
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Read from DeviceTree and setup cpu possible mask. If there is no
+ * "possible-cpus" property in DeviceTree pretend all [0..NR_CPUS-1] exist.
+ */
+static void __init arc_init_cpu_possible(void)
+{
+	struct cpumask cpumask;
+
+	if (arc_get_cpu_map("possible-cpus", &cpumask)) {
+		pr_warn("Failed to get possible-cpus from dtb, pretending all %u cpus exist\n",
+			NR_CPUS);
+
+		cpumask_setall(&cpumask);
+	}
+
+	if (!cpumask_test_cpu(0, &cpumask))
+		panic("Master cpu (cpu[0]) is missed in cpu possible mask!");
+
+	init_cpu_possible(&cpumask);
+}
+
 /*
  * Called from setup_arch() before calling setup_processor()
  *
@@ -58,10 +95,7 @@
  */
 void __init smp_init_cpus(void)
 {
-	unsigned int i;
-
-	for (i = 0; i < NR_CPUS; i++)
-		set_cpu_possible(i, true);
+	arc_init_cpu_possible();
 
 	if (plat_smp_ops.init_early_smp)
 		plat_smp_ops.init_early_smp();
@@ -70,16 +104,12 @@
 /* called from init ( ) =>  process 1 */
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	int i;
-
 	/*
 	 * if platform didn't set the present map already, do it now
 	 * boot cpu is set to present already by init/main.c
 	 */
-	if (num_present_cpus() <= 1) {
-		for (i = 0; i < max_cpus; i++)
-			set_cpu_present(i, true);
-	}
+	if (num_present_cpus() <= 1)
+		init_cpu_present(cpu_possible_mask);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 333daab..183391d 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -366,7 +366,7 @@
 	return;
 
 ret_err:
-	panic("Attention !!! Dwarf FDE parsing errors\n");;
+	panic("Attention !!! Dwarf FDE parsing errors\n");
 }
 
 #ifdef CONFIG_MODULES
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index eee924d..2072f34 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -780,7 +780,10 @@
 
 	write_aux_reg(r, ctrl);
 
-	write_aux_reg(ARC_REG_SLC_INVALIDATE, 1);
+	if (op & OP_INV)	/* Inv or flush-n-inv use same cmd reg */
+		write_aux_reg(ARC_REG_SLC_INVALIDATE, 0x1);
+	else
+		write_aux_reg(ARC_REG_SLC_FLUSH, 0x1);
 
 	/* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */
 	read_aux_reg(r);
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index 18045c3..db7cded 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -55,7 +55,7 @@
 		      <0x3ff00100 0x100>;
 	};
 
-	smc@0x3404c000 {
+	smc@3404c000 {
 		compatible = "brcm,bcm11351-smc", "brcm,kona-smc";
 		reg = <0x3404c000 0x400>; /* 1 KiB in SRAM */
 	};
diff --git a/arch/arm/boot/dts/bcm21664.dtsi b/arch/arm/boot/dts/bcm21664.dtsi
index 6dde95f..266f261 100644
--- a/arch/arm/boot/dts/bcm21664.dtsi
+++ b/arch/arm/boot/dts/bcm21664.dtsi
@@ -55,7 +55,7 @@
 		      <0x3ff00100 0x100>;
 	};
 
-	smc@0x3404e000 {
+	smc@3404e000 {
 		compatible = "brcm,bcm21664-smc", "brcm,kona-smc";
 		reg = <0x3404e000 0x400>; /* 1 KiB in SRAM */
 	};
diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi
index 0e3d2a5..a5c3824 100644
--- a/arch/arm/boot/dts/bcm2835.dtsi
+++ b/arch/arm/boot/dts/bcm2835.dtsi
@@ -18,10 +18,10 @@
 	soc {
 		ranges = <0x7e000000 0x20000000 0x02000000>;
 		dma-ranges = <0x40000000 0x00000000 0x20000000>;
+	};
 
-		arm-pmu {
-			compatible = "arm,arm1176-pmu";
-		};
+	arm-pmu {
+		compatible = "arm,arm1176-pmu";
 	};
 };
 
diff --git a/arch/arm/boot/dts/bcm2836.dtsi b/arch/arm/boot/dts/bcm2836.dtsi
index 1dfd764..c933e84 100644
--- a/arch/arm/boot/dts/bcm2836.dtsi
+++ b/arch/arm/boot/dts/bcm2836.dtsi
@@ -9,19 +9,19 @@
 			 <0x40000000 0x40000000 0x00001000>;
 		dma-ranges = <0xc0000000 0x00000000 0x3f000000>;
 
-		local_intc: local_intc {
+		local_intc: local_intc@40000000 {
 			compatible = "brcm,bcm2836-l1-intc";
 			reg = <0x40000000 0x100>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 			interrupt-parent = <&local_intc>;
 		};
+	};
 
-		arm-pmu {
-			compatible = "arm,cortex-a7-pmu";
-			interrupt-parent = <&local_intc>;
-			interrupts = <9 IRQ_TYPE_LEVEL_HIGH>;
-		};
+	arm-pmu {
+		compatible = "arm,cortex-a7-pmu";
+		interrupt-parent = <&local_intc>;
+		interrupts = <9 IRQ_TYPE_LEVEL_HIGH>;
 	};
 
 	timer {
diff --git a/arch/arm/boot/dts/bcm2837.dtsi b/arch/arm/boot/dts/bcm2837.dtsi
index efa7d33..7704bb0 100644
--- a/arch/arm/boot/dts/bcm2837.dtsi
+++ b/arch/arm/boot/dts/bcm2837.dtsi
@@ -8,7 +8,7 @@
 			 <0x40000000 0x40000000 0x00001000>;
 		dma-ranges = <0xc0000000 0x00000000 0x3f000000>;
 
-		local_intc: local_intc {
+		local_intc: local_intc@40000000 {
 			compatible = "brcm,bcm2836-l1-intc";
 			reg = <0x40000000 0x100>;
 			interrupt-controller;
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 18db25a..9d293de 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -465,7 +465,7 @@
 			status = "disabled";
 		};
 
-		aux: aux@0x7e215000 {
+		aux: aux@7e215000 {
 			compatible = "brcm,bcm2835-aux";
 			#clock-cells = <1>;
 			reg = <0x7e215000 0x8>;
diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts
index 6a44b80..f0e2008 100644
--- a/arch/arm/boot/dts/bcm958625hr.dts
+++ b/arch/arm/boot/dts/bcm958625hr.dts
@@ -49,7 +49,7 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0x60000000 0x80000000>;
+		reg = <0x60000000 0x20000000>;
 	};
 
 	gpio-restart {
diff --git a/arch/arm/boot/dts/gemini-dlink-dns-313.dts b/arch/arm/boot/dts/gemini-dlink-dns-313.dts
index 08568ce..da8bb9d 100644
--- a/arch/arm/boot/dts/gemini-dlink-dns-313.dts
+++ b/arch/arm/boot/dts/gemini-dlink-dns-313.dts
@@ -269,7 +269,7 @@
 
 		sata: sata@46000000 {
 			/* The ROM uses this muxmode */
-			cortina,gemini-ata-muxmode = <3>;
+			cortina,gemini-ata-muxmode = <0>;
 			cortina,gemini-enable-sata-bridge;
 			status = "okay";
 		};
diff --git a/arch/arm/boot/dts/imx6dl-icore-rqs.dts b/arch/arm/boot/dts/imx6dl-icore-rqs.dts
index cf42c2f..1281bc3 100644
--- a/arch/arm/boot/dts/imx6dl-icore-rqs.dts
+++ b/arch/arm/boot/dts/imx6dl-icore-rqs.dts
@@ -42,7 +42,7 @@
 
 /dts-v1/;
 
-#include "imx6q.dtsi"
+#include "imx6dl.dtsi"
 #include "imx6qdl-icore-rqs.dtsi"
 
 / {
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index c1aa7a4..a30ee9f 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -71,6 +71,8 @@
 };
 
 &i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
 	clock-frequency = <2600000>;
 
 	twl: twl@48 {
@@ -189,7 +191,12 @@
 		>;
 	};
 
-
+	i2c1_pins: pinmux_i2c1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0)        /* i2c1_scl.i2c1_scl */
+			OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0)        /* i2c1_sda.i2c1_sda */
+		>;
+	};
 };
 
 &omap3_pmx_wkup {
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index b50b796..4791544 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -66,6 +66,8 @@
 };
 
 &i2c1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c1_pins>;
 	clock-frequency = <2600000>;
 
 	twl: twl@48 {
@@ -136,6 +138,12 @@
 			OMAP3_CORE1_IOPAD(0x21b8, PIN_INPUT | MUX_MODE0)	/* hsusb0_data7.hsusb0_data7 */
 		>;
 	};
+	i2c1_pins: pinmux_i2c1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0)        /* i2c1_scl.i2c1_scl */
+			OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0)        /* i2c1_sda.i2c1_sda */
+		>;
+	};
 };
 
 &uart2 {
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index ec2c8ba..592e17f 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -47,7 +47,7 @@
 			gpios = <&gpio3 19 GPIO_ACTIVE_LOW>;	/* gpio3_83 */
 			wakeup-source;
 			autorepeat;
-			debounce_interval = <50>;
+			debounce-interval = <50>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi
index 3b704cf..a974581 100644
--- a/arch/arm/boot/dts/rk3036.dtsi
+++ b/arch/arm/boot/dts/rk3036.dtsi
@@ -280,7 +280,7 @@
 		max-frequency = <37500000>;
 		clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>,
 			 <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
 		resets = <&cru SRST_SDIO>;
@@ -298,7 +298,7 @@
 		max-frequency = <37500000>;
 		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>,
 			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		default-sample-phase = <158>;
 		disable-wp;
 		dmas = <&pdma 12>;
diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi
index 780ec3a..341deaf 100644
--- a/arch/arm/boot/dts/rk322x.dtsi
+++ b/arch/arm/boot/dts/rk322x.dtsi
@@ -621,7 +621,7 @@
 		interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>,
 			 <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_bus4>;
@@ -634,7 +634,7 @@
 		interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>,
 			 <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&sdio_clk &sdio_cmd &sdio_bus4>;
@@ -649,7 +649,7 @@
 		max-frequency = <37500000>;
 		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>,
 			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		bus-width = <8>;
 		default-sample-phase = <158>;
 		fifo-depth = <0x100>;
diff --git a/arch/arm/boot/dts/rk3288-phycore-som.dtsi b/arch/arm/boot/dts/rk3288-phycore-som.dtsi
index 99cfae8..5eae477 100644
--- a/arch/arm/boot/dts/rk3288-phycore-som.dtsi
+++ b/arch/arm/boot/dts/rk3288-phycore-som.dtsi
@@ -110,26 +110,6 @@
 	};
 };
 
-&cpu0 {
-	cpu0-supply = <&vdd_cpu>;
-	operating-points = <
-		/* KHz    uV */
-		1800000	1400000
-		1608000	1350000
-		1512000 1300000
-		1416000 1200000
-		1200000 1100000
-		1008000 1050000
-		 816000 1000000
-		 696000  950000
-		 600000  900000
-		 408000  900000
-		 312000  900000
-		 216000  900000
-		 126000  900000
-	>;
-};
-
 &emmc {
 	status = "okay";
 	bus-width = <8>;
diff --git a/arch/arm/boot/dts/zx296702.dtsi b/arch/arm/boot/dts/zx296702.dtsi
index 8a74efd..240e7a2 100644
--- a/arch/arm/boot/dts/zx296702.dtsi
+++ b/arch/arm/boot/dts/zx296702.dtsi
@@ -56,7 +56,7 @@
 			clocks = <&topclk ZX296702_A9_PERIPHCLK>;
 		};
 
-		l2cc: l2-cache-controller@0x00c00000 {
+		l2cc: l2-cache-controller@c00000 {
 			compatible = "arm,pl310-cache";
 			reg = <0x00c00000 0x1000>;
 			cache-unified;
@@ -67,30 +67,30 @@
 			arm,double-linefill-incr = <0>;
 		};
 
-		pcu: pcu@0xa0008000 {
+		pcu: pcu@a0008000 {
 			compatible = "zte,zx296702-pcu";
 			reg = <0xa0008000 0x1000>;
 		};
 
-		topclk: topclk@0x09800000 {
+		topclk: topclk@9800000 {
 			compatible = "zte,zx296702-topcrm-clk";
 			reg = <0x09800000 0x1000>;
 			#clock-cells = <1>;
 		};
 
-		lsp1clk: lsp1clk@0x09400000 {
+		lsp1clk: lsp1clk@9400000 {
 			compatible = "zte,zx296702-lsp1crpm-clk";
 			reg = <0x09400000 0x1000>;
 			#clock-cells = <1>;
 		};
 
-		lsp0clk: lsp0clk@0x0b000000 {
+		lsp0clk: lsp0clk@b000000 {
 			compatible = "zte,zx296702-lsp0crpm-clk";
 			reg = <0x0b000000 0x1000>;
 			#clock-cells = <1>;
 		};
 
-		uart0: serial@0x09405000 {
+		uart0: serial@9405000 {
 			compatible = "zte,zx296702-uart";
 			reg = <0x09405000 0x1000>;
 			interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
@@ -98,7 +98,7 @@
 			status = "disabled";
 		};
 
-		uart1: serial@0x09406000 {
+		uart1: serial@9406000 {
 			compatible = "zte,zx296702-uart";
 			reg = <0x09406000 0x1000>;
 			interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
@@ -106,7 +106,7 @@
 			status = "disabled";
 		};
 
-		mmc0: mmc@0x09408000 {
+		mmc0: mmc@9408000 {
 			compatible = "snps,dw-mshc";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -119,7 +119,7 @@
 			status = "disabled";
 		};
 
-		mmc1: mmc@0x0b003000 {
+		mmc1: mmc@b003000 {
 			compatible = "snps,dw-mshc";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -132,7 +132,7 @@
 			status = "disabled";
 		};
 
-		sysctrl: sysctrl@0xa0007000 {
+		sysctrl: sysctrl@a0007000 {
 			compatible = "zte,sysctrl", "syscon";
 			reg = <0xa0007000 0x1000>;
 		};
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 2f145c4..92674f2 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -319,7 +319,7 @@
 CONFIG_RC_CORE=m
 CONFIG_MEDIA_CONTROLLER=y
 CONFIG_VIDEO_V4L2_SUBDEV_API=y
-CONFIG_LIRC=m
+CONFIG_LIRC=y
 CONFIG_RC_DEVICES=y
 CONFIG_IR_RX51=m
 CONFIG_V4L_PLATFORM_DRIVERS=y
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 629f8e9..cf2701c 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -83,7 +83,7 @@
 }
 
 static clock_access_fn __read_persistent_clock = dummy_clock_access;
-static clock_access_fn __read_boot_clock = dummy_clock_access;;
+static clock_access_fn __read_boot_clock = dummy_clock_access;
 
 void read_persistent_clock64(struct timespec64 *ts)
 {
diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile
index 5638ce0..63d6b40 100644
--- a/arch/arm/kvm/hyp/Makefile
+++ b/arch/arm/kvm/hyp/Makefile
@@ -7,6 +7,8 @@
 
 KVM=../../../../virt/kvm
 
+CFLAGS_ARMV7VE		   :=$(call cc-option, -march=armv7ve)
+
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o
@@ -15,7 +17,10 @@
 obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o
 obj-$(CONFIG_KVM_ARM_HOST) += vfp.o
 obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o
+CFLAGS_banked-sr.o	   += $(CFLAGS_ARMV7VE)
+
 obj-$(CONFIG_KVM_ARM_HOST) += entry.o
 obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
 obj-$(CONFIG_KVM_ARM_HOST) += switch.o
+CFLAGS_switch.o		   += $(CFLAGS_ARMV7VE)
 obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c
index 111bda8..be4b8b0 100644
--- a/arch/arm/kvm/hyp/banked-sr.c
+++ b/arch/arm/kvm/hyp/banked-sr.c
@@ -20,6 +20,10 @@
 
 #include <asm/kvm_hyp.h>
 
+/*
+ * gcc before 4.9 doesn't understand -march=armv7ve, so we have to
+ * trick the assembler.
+ */
 __asm__(".arch_extension     virt");
 
 void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt)
diff --git a/arch/arm/mach-clps711x/board-dt.c b/arch/arm/mach-clps711x/board-dt.c
index ee1f83b..4c89a8e 100644
--- a/arch/arm/mach-clps711x/board-dt.c
+++ b/arch/arm/mach-clps711x/board-dt.c
@@ -69,7 +69,7 @@
 	soft_restart(0);
 }
 
-static const char *clps711x_compat[] __initconst = {
+static const char *const clps711x_compat[] __initconst = {
 	"cirrus,ep7209",
 	NULL
 };
diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c
index e457f29..d6b1190 100644
--- a/arch/arm/mach-davinci/board-dm355-evm.c
+++ b/arch/arm/mach-davinci/board-dm355-evm.c
@@ -368,7 +368,7 @@
 	.flags		= EE_ADDR2,
 };
 
-static struct spi_board_info dm355_evm_spi_info[] __initconst = {
+static const struct spi_board_info dm355_evm_spi_info[] __initconst = {
 	{
 		.modalias	= "at25",
 		.platform_data	= &at25640a,
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index be99724..fad9a56 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -217,7 +217,7 @@
 	.flags		= EE_ADDR2,
 };
 
-static struct spi_board_info dm355_leopard_spi_info[] __initconst = {
+static const struct spi_board_info dm355_leopard_spi_info[] __initconst = {
 	{
 		.modalias	= "at25",
 		.platform_data	= &at25640a,
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index e75741f..e378098 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -726,7 +726,7 @@
 	.flags		= EE_ADDR2,
 };
 
-static struct spi_board_info dm365_evm_spi_info[] __initconst = {
+static const struct spi_board_info dm365_evm_spi_info[] __initconst = {
 	{
 		.modalias	= "at25",
 		.platform_data	= &at25640,
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 6b32dc5..2c20599 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -41,7 +41,7 @@
 	depends on ARCH_MULTI_V7
 	select ARMADA_370_XP_IRQ
 	select ARM_ERRATA_720789
-	select ARM_ERRATA_753970
+	select PL310_ERRATA_753970
 	select ARM_GIC
 	select ARMADA_375_CLK
 	select HAVE_ARM_SCU
@@ -57,7 +57,7 @@
 	bool "Marvell Armada 380/385 boards"
 	depends on ARCH_MULTI_V7
 	select ARM_ERRATA_720789
-	select ARM_ERRATA_753970
+	select PL310_ERRATA_753970
 	select ARM_GIC
 	select ARM_GLOBAL_TIMER
 	select CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c
index 43e3e18..fa51241 100644
--- a/arch/arm/mach-omap1/clock.c
+++ b/arch/arm/mach-omap1/clock.c
@@ -1011,17 +1011,17 @@
 		return -ENOMEM;
 	c->dent = d;
 
-	d = debugfs_create_u8("usecount", S_IRUGO, c->dent, (u8 *)&c->usecount);
+	d = debugfs_create_u8("usecount", S_IRUGO, c->dent, &c->usecount);
 	if (!d) {
 		err = -ENOMEM;
 		goto err_out;
 	}
-	d = debugfs_create_u32("rate", S_IRUGO, c->dent, (u32 *)&c->rate);
+	d = debugfs_create_ulong("rate", S_IRUGO, c->dent, &c->rate);
 	if (!d) {
 		err = -ENOMEM;
 		goto err_out;
 	}
-	d = debugfs_create_x32("flags", S_IRUGO, c->dent, (u32 *)&c->flags);
+	d = debugfs_create_x8("flags", S_IRUGO, c->dent, &c->flags);
 	if (!d) {
 		err = -ENOMEM;
 		goto err_out;
diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c
index 4bb6751..fc5fb77 100644
--- a/arch/arm/mach-omap2/omap-wakeupgen.c
+++ b/arch/arm/mach-omap2/omap-wakeupgen.c
@@ -299,8 +299,6 @@
 	if (soc_is_dra7xx())
 		return;
 
-	if (!sar_base)
-		sar_base = omap4_get_sar_ram_base();
 	if (wakeupgen_ops && wakeupgen_ops->save_context)
 		wakeupgen_ops->save_context();
 }
@@ -598,6 +596,8 @@
 	irq_hotplug_init();
 	irq_pm_init();
 
+	sar_base = omap4_get_sar_ram_base();
+
 	return 0;
 }
 IRQCHIP_DECLARE(ti_wakeupgen, "ti,omap4-wugen-mpu", wakeupgen_init);
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 124f9af..34156ec 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -977,6 +977,9 @@
 
 	pr_debug("omap_hwmod: %s: enabling clocks\n", oh->name);
 
+	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+		_enable_optional_clocks(oh);
+
 	if (oh->_clk)
 		clk_enable(oh->_clk);
 
@@ -985,9 +988,6 @@
 			clk_enable(os->_clk);
 	}
 
-	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
-		_enable_optional_clocks(oh);
-
 	/* The opt clocks are controlled by the device driver. */
 
 	return 0;
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 366158a..6f68576 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -186,7 +186,7 @@
 	cpu_idle_poll_ctrl(false);
 }
 
-static void omap_pm_finish(void)
+static void omap_pm_wake(void)
 {
 	if (soc_is_omap34xx())
 		omap_prcm_irq_complete();
@@ -196,7 +196,7 @@
 	.begin		= omap_pm_begin,
 	.end		= omap_pm_end,
 	.enter		= omap_pm_enter,
-	.finish		= omap_pm_finish,
+	.wake		= omap_pm_wake,
 	.valid		= suspend_valid_only_mem,
 };
 
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index ece09c9..d61fbd7 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -156,12 +156,6 @@
 	.tick_resume		= omap2_gp_timer_shutdown,
 };
 
-static struct property device_disabled = {
-	.name = "status",
-	.length = sizeof("disabled"),
-	.value = "disabled",
-};
-
 static const struct of_device_id omap_timer_match[] __initconst = {
 	{ .compatible = "ti,omap2420-timer", },
 	{ .compatible = "ti,omap3430-timer", },
@@ -203,8 +197,17 @@
 				  of_get_property(np, "ti,timer-secure", NULL)))
 			continue;
 
-		if (!of_device_is_compatible(np, "ti,omap-counter32k"))
-			of_add_property(np, &device_disabled);
+		if (!of_device_is_compatible(np, "ti,omap-counter32k")) {
+			struct property *prop;
+
+			prop = kzalloc(sizeof(*prop), GFP_KERNEL);
+			if (!prop)
+				return NULL;
+			prop->name = "status";
+			prop->value = "disabled";
+			prop->length = strlen(prop->value);
+			of_add_property(np, prop);
+		}
 		return np;
 	}
 
diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig
index 2a7bb6c..a810f4d 100644
--- a/arch/arm/mach-orion5x/Kconfig
+++ b/arch/arm/mach-orion5x/Kconfig
@@ -58,7 +58,6 @@
 
 config MACH_DNS323
 	bool "D-Link DNS-323"
-	select GENERIC_NET_UTILS
 	select I2C_BOARDINFO if I2C
 	help
 	  Say 'Y' here if you want your kernel to support the
@@ -66,7 +65,6 @@
 
 config MACH_TS209
 	bool "QNAP TS-109/TS-209"
-	select GENERIC_NET_UTILS
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  QNAP TS-109/TS-209 platform.
@@ -101,7 +99,6 @@
 
 config MACH_TS409
 	bool "QNAP TS-409"
-	select GENERIC_NET_UTILS
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  QNAP TS-409 platform.
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index cd483bf..d13344b 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -173,10 +173,42 @@
 	.phy_addr = MV643XX_ETH_PHY_ADDR(8),
 };
 
+/* dns323_parse_hex_*() taken from tsx09-common.c; should a common copy of these
+ * functions be kept somewhere?
+ */
+static int __init dns323_parse_hex_nibble(char n)
+{
+	if (n >= '0' && n <= '9')
+		return n - '0';
+
+	if (n >= 'A' && n <= 'F')
+		return n - 'A' + 10;
+
+	if (n >= 'a' && n <= 'f')
+		return n - 'a' + 10;
+
+	return -1;
+}
+
+static int __init dns323_parse_hex_byte(const char *b)
+{
+	int hi;
+	int lo;
+
+	hi = dns323_parse_hex_nibble(b[0]);
+	lo = dns323_parse_hex_nibble(b[1]);
+
+	if (hi < 0 || lo < 0)
+		return -1;
+
+	return (hi << 4) | lo;
+}
+
 static int __init dns323_read_mac_addr(void)
 {
 	u_int8_t addr[6];
-	void __iomem *mac_page;
+	int i;
+	char *mac_page;
 
 	/* MAC address is stored as a regular ol' string in /dev/mtdblock4
 	 * (0x007d0000-0x00800000) starting at offset 196480 (0x2ff80).
@@ -185,8 +217,23 @@
 	if (!mac_page)
 		return -ENOMEM;
 
-	if (!mac_pton((__force const char *) mac_page, addr))
-		goto error_fail;
+	/* Sanity check the string we're looking at */
+	for (i = 0; i < 5; i++) {
+		if (*(mac_page + (i * 3) + 2) != ':') {
+			goto error_fail;
+		}
+	}
+
+	for (i = 0; i < 6; i++)	{
+		int byte;
+
+		byte = dns323_parse_hex_byte(mac_page + (i * 3));
+		if (byte < 0) {
+			goto error_fail;
+		}
+
+		addr[i] = byte;
+	}
 
 	iounmap(mac_page);
 	printk("DNS-323: Found ethernet MAC address: %pM\n", addr);
diff --git a/arch/arm/mach-orion5x/tsx09-common.c b/arch/arm/mach-orion5x/tsx09-common.c
index 8977498..905d4f2 100644
--- a/arch/arm/mach-orion5x/tsx09-common.c
+++ b/arch/arm/mach-orion5x/tsx09-common.c
@@ -53,12 +53,53 @@
 	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
 };
 
+static int __init qnap_tsx09_parse_hex_nibble(char n)
+{
+	if (n >= '0' && n <= '9')
+		return n - '0';
+
+	if (n >= 'A' && n <= 'F')
+		return n - 'A' + 10;
+
+	if (n >= 'a' && n <= 'f')
+		return n - 'a' + 10;
+
+	return -1;
+}
+
+static int __init qnap_tsx09_parse_hex_byte(const char *b)
+{
+	int hi;
+	int lo;
+
+	hi = qnap_tsx09_parse_hex_nibble(b[0]);
+	lo = qnap_tsx09_parse_hex_nibble(b[1]);
+
+	if (hi < 0 || lo < 0)
+		return -1;
+
+	return (hi << 4) | lo;
+}
+
 static int __init qnap_tsx09_check_mac_addr(const char *addr_str)
 {
 	u_int8_t addr[6];
+	int i;
 
-	if (!mac_pton(addr_str, addr))
-		return -1;
+	for (i = 0; i < 6; i++) {
+		int byte;
+
+		/*
+		 * Enforce "xx:xx:xx:xx:xx:xx\n" format.
+		 */
+		if (addr_str[(i * 3) + 2] != ((i < 5) ? ':' : '\n'))
+			return -1;
+
+		byte = qnap_tsx09_parse_hex_byte(addr_str + (i * 3));
+		if (byte < 0)
+			return -1;
+		addr[i] = byte;
+	}
 
 	printk(KERN_INFO "tsx09: found ethernet mac address %pM\n", addr);
 
@@ -77,12 +118,12 @@
 	unsigned long addr;
 
 	for (addr = mem_base; addr < (mem_base + size); addr += 1024) {
-		void __iomem *nor_page;
+		char *nor_page;
 		int ret = 0;
 
 		nor_page = ioremap(addr, 1024);
 		if (nor_page != NULL) {
-			ret = qnap_tsx09_check_mac_addr((__force const char *)nor_page);
+			ret = qnap_tsx09_check_mac_addr(nor_page);
 			iounmap(nor_page);
 		}
 
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 57058ac..7e5d7a0 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -23,7 +23,6 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
-#include <linux/perf/arm_pmu.h>
 #include <linux/regulator/machine.h>
 
 #include <asm/outercache.h>
@@ -112,37 +111,6 @@
 	prcmu_system_reset(0);
 }
 
-/*
- * The PMU IRQ lines of two cores are wired together into a single interrupt.
- * Bounce the interrupt to the other core if it's not ours.
- */
-static irqreturn_t db8500_pmu_handler(int irq, void *dev, irq_handler_t handler)
-{
-	irqreturn_t ret = handler(irq, dev);
-	int other = !smp_processor_id();
-
-	if (ret == IRQ_NONE && cpu_online(other))
-		irq_set_affinity(irq, cpumask_of(other));
-
-	/*
-	 * We should be able to get away with the amount of IRQ_NONEs we give,
-	 * while still having the spurious IRQ detection code kick in if the
-	 * interrupt really starts hitting spuriously.
-	 */
-	return ret;
-}
-
-static struct arm_pmu_platdata db8500_pmu_platdata = {
-	.handle_irq		= db8500_pmu_handler,
-	.irq_flags		= IRQF_NOBALANCING | IRQF_NO_THREAD,
-};
-
-static struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = {
-	/* Requires call-back bindings. */
-	OF_DEV_AUXDATA("arm,cortex-a9-pmu", 0, "arm-pmu", &db8500_pmu_platdata),
-	{},
-};
-
 static struct of_dev_auxdata u8540_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("stericsson,db8500-prcmu", 0x80157000, "db8500-prcmu", NULL),
 	{},
@@ -165,9 +133,6 @@
 	if (of_machine_is_compatible("st-ericsson,u8540"))
 		of_platform_populate(NULL, u8500_local_bus_nodes,
 				     u8540_auxdata_lookup, NULL);
-	else
-		of_platform_populate(NULL, u8500_local_bus_nodes,
-				     u8500_auxdata_lookup, NULL);
 }
 
 static const char * stericsson_dt_platform_compat[] = {
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index aff6994..a2399fd 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -472,28 +472,27 @@
 /*****************************************************************************
  * Ethernet switch
  ****************************************************************************/
-static __initconst const char *orion_ge00_mvmdio_bus_name = "orion-mii";
-static __initdata struct mdio_board_info
-		  orion_ge00_switch_board_info;
+static __initdata struct mdio_board_info orion_ge00_switch_board_info = {
+	.bus_id   = "orion-mii",
+	.modalias = "mv88e6085",
+};
 
 void __init orion_ge00_switch_init(struct dsa_chip_data *d)
 {
-	struct mdio_board_info *bd;
 	unsigned int i;
 
 	if (!IS_BUILTIN(CONFIG_PHYLIB))
 		return;
 
-	for (i = 0; i < ARRAY_SIZE(d->port_names); i++)
-		if (!strcmp(d->port_names[i], "cpu"))
+	for (i = 0; i < ARRAY_SIZE(d->port_names); i++) {
+		if (!strcmp(d->port_names[i], "cpu")) {
+			d->netdev[i] = &orion_ge00.dev;
 			break;
+		}
+	}
 
-	bd = &orion_ge00_switch_board_info;
-	bd->bus_id = orion_ge00_mvmdio_bus_name;
-	bd->mdio_addr = d->sw_addr;
-	d->netdev[i] = &orion_ge00.dev;
-	strcpy(bd->modalias, "mv88e6085");
-	bd->platform_data = d;
+	orion_ge00_switch_board_info.mdio_addr = d->sw_addr;
+	orion_ge00_switch_board_info.platform_data = d;
 
 	mdiobus_register_board_info(&orion_ge00_switch_board_info, 1);
 }
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index a806326..70c776e 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -165,14 +165,14 @@
 
 			uart_A: serial@24000 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart";
-				reg = <0x0 0x24000 0x0 0x14>;
+				reg = <0x0 0x24000 0x0 0x18>;
 				interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
 			uart_B: serial@23000 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart";
-				reg = <0x0 0x23000 0x0 0x14>;
+				reg = <0x0 0x23000 0x0 0x18>;
 				interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 6cb3c2a..4ee2e79 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -235,14 +235,14 @@
 
 			uart_A: serial@84c0 {
 				compatible = "amlogic,meson-gx-uart";
-				reg = <0x0 0x84c0 0x0 0x14>;
+				reg = <0x0 0x84c0 0x0 0x18>;
 				interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
 			uart_B: serial@84dc {
 				compatible = "amlogic,meson-gx-uart";
-				reg = <0x0 0x84dc 0x0 0x14>;
+				reg = <0x0 0x84dc 0x0 0x18>;
 				interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
@@ -287,7 +287,7 @@
 
 			uart_C: serial@8700 {
 				compatible = "amlogic,meson-gx-uart";
-				reg = <0x0 0x8700 0x0 0x14>;
+				reg = <0x0 0x8700 0x0 0x18>;
 				interrupts = <GIC_SPI 93 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
@@ -404,14 +404,14 @@
 
 			uart_AO: serial@4c0 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart";
-				reg = <0x0 0x004c0 0x0 0x14>;
+				reg = <0x0 0x004c0 0x0 0x18>;
 				interrupts = <GIC_SPI 193 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
 
 			uart_AO_B: serial@4e0 {
 				compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart";
-				reg = <0x0 0x004e0 0x0 0x14>;
+				reg = <0x0 0x004e0 0x0 0x18>;
 				interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>;
 				status = "disabled";
 			};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index 4f355f1..c851411 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -631,6 +631,7 @@
 
 			internal_phy: ethernet-phy@8 {
 				compatible = "ethernet-phy-id0181.4400", "ethernet-phy-ieee802.3-c22";
+				interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <8>;
 				max-speed = <100>;
 			};
diff --git a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi
index 4220fbd..ff5c4c4 100644
--- a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi
+++ b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi
@@ -98,7 +98,7 @@
 		clock-output-names = "clk125mhz";
 	};
 
-	pci {
+	pcie@30000000 {
 		compatible = "pci-host-ecam-generic";
 		device_type = "pci";
 		#interrupt-cells = <1>;
@@ -118,6 +118,7 @@
 		ranges =
 		  <0x02000000    0 0x40000000    0 0x40000000    0 0x20000000
 		   0x43000000 0x40 0x00000000 0x40 0x00000000 0x20 0x00000000>;
+		bus-range = <0 0xff>;
 		interrupt-map-mask = <0 0 0 7>;
 		interrupt-map =
 		      /* addr  pin  ic   icaddr  icintr */
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index e94fa1a..047641f 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -51,7 +51,7 @@
 		#size-cells = <2>;
 		ranges;
 
-		ramoops@0x21f00000 {
+		ramoops@21f00000 {
 			compatible = "ramoops";
 			reg = <0x0 0x21f00000 0x0 0x00100000>;
 			record-size	= <0x00020000>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 9fbe470..94597e3 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -341,7 +341,7 @@
 			reg = <0 0x10005000 0 0x1000>;
 		};
 
-		pio: pinctrl@0x10005000 {
+		pio: pinctrl@10005000 {
 			compatible = "mediatek,mt8173-pinctrl";
 			reg = <0 0x1000b000 0 0x1000>;
 			mediatek,pctl-regmap = <&syscfg_pctl_a>;
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
index 492a011..1c8f1b8 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
@@ -140,16 +140,16 @@
 		};
 
 		agnoc@0 {
-			qcom,pcie@00600000 {
+			qcom,pcie@600000 {
 				perst-gpio = <&msmgpio 35 GPIO_ACTIVE_LOW>;
 			};
 
-			qcom,pcie@00608000 {
+			qcom,pcie@608000 {
 				status = "okay";
 				perst-gpio = <&msmgpio 130 GPIO_ACTIVE_LOW>;
 			};
 
-			qcom,pcie@00610000 {
+			qcom,pcie@610000 {
 				status = "okay";
 				perst-gpio = <&msmgpio 114 GPIO_ACTIVE_LOW>;
 			};
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 4b2afcc..0a6f795 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -840,7 +840,7 @@
 			#size-cells = <1>;
 			ranges;
 
-			pcie0: qcom,pcie@00600000 {
+			pcie0: qcom,pcie@600000 {
 				compatible = "qcom,pcie-msm8996", "snps,dw-pcie";
 				status = "disabled";
 				power-domains = <&gcc PCIE0_GDSC>;
@@ -893,7 +893,7 @@
 
 			};
 
-			pcie1: qcom,pcie@00608000 {
+			pcie1: qcom,pcie@608000 {
 				compatible = "qcom,pcie-msm8996", "snps,dw-pcie";
 				power-domains = <&gcc PCIE1_GDSC>;
 				bus-range = <0x00 0xff>;
@@ -946,7 +946,7 @@
 						"bus_slave";
 			};
 
-			pcie2: qcom,pcie@00610000 {
+			pcie2: qcom,pcie@610000 {
 				compatible = "qcom,pcie-msm8996", "snps,dw-pcie";
 				power-domains = <&gcc PCIE2_GDSC>;
 				bus-range = <0x00 0xff>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index 3890468..2825772 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -132,17 +132,16 @@
 	assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
 	assigned-clock-parents = <&gmac_clkin>, <&gmac_clkin>;
 	clock_in_out = "input";
-	/* shows instability at 1GBit right now */
-	max-speed = <100>;
 	phy-supply = <&vcc_io>;
 	phy-mode = "rgmii";
 	pinctrl-names = "default";
 	pinctrl-0 = <&rgmiim1_pins>;
+	snps,force_thresh_dma_mode;
 	snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>;
 	snps,reset-active-low;
 	snps,reset-delays-us = <0 10000 50000>;
-	tx_delay = <0x26>;
-	rx_delay = <0x11>;
+	tx_delay = <0x24>;
+	rx_delay = <0x18>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index a037ee5..cae3415 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -730,7 +730,7 @@
 		interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>,
 			 <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		status = "disabled";
 	};
@@ -741,7 +741,7 @@
 		interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>,
 			 <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		status = "disabled";
 	};
@@ -752,7 +752,7 @@
 		interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>,
 			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		status = "disabled";
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index aa4d070..03458ac 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -257,7 +257,7 @@
 		max-frequency = <150000000>;
 		clocks = <&cru HCLK_SDIO0>, <&cru SCLK_SDIO0>,
 			 <&cru SCLK_SDIO0_DRV>, <&cru SCLK_SDIO0_SAMPLE>;
-		clock-names = "biu", "ciu", "ciu_drv", "ciu_sample";
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
 		resets = <&cru SRST_SDIO0>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
index 0f873c8..ce592a4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi
@@ -457,7 +457,7 @@
 	assigned-clocks = <&cru SCLK_PCIEPHY_REF>;
 	assigned-clock-parents = <&cru SCLK_PCIEPHY_REF100M>;
 	assigned-clock-rates = <100000000>;
-	ep-gpios = <&gpio3 RK_PB5 GPIO_ACTIVE_HIGH>;
+	ep-gpios = <&gpio2 RK_PA4 GPIO_ACTIVE_HIGH>;
 	num-lanes = <4>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie_clkreqn_cpm>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 7aa2144..2605118 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -1739,8 +1739,8 @@
 		compatible = "rockchip,rk3399-edp";
 		reg = <0x0 0xff970000 0x0 0x8000>;
 		interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH 0>;
-		clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>;
-		clock-names = "dp", "pclk";
+		clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>, <&cru PCLK_VIO_GRF>;
+		clock-names = "dp", "pclk", "grf";
 		pinctrl-names = "default";
 		pinctrl-0 = <&edp_hpd>;
 		power-domains = <&power RK3399_PD_EDP>;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index be7bd19..350c76a 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -20,7 +20,7 @@
 
 #define MPIDR_UP_BITMASK	(0x1 << 30)
 #define MPIDR_MT_BITMASK	(0x1 << 24)
-#define MPIDR_HWID_BITMASK	0xff00ffffff
+#define MPIDR_HWID_BITMASK	UL(0xff00ffffff)
 
 #define MPIDR_LEVEL_BITS_SHIFT	3
 #define MPIDR_LEVEL_BITS	(1 << MPIDR_LEVEL_BITS_SHIFT)
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 1dca41b..e73f685 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -22,7 +22,7 @@
 
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
-	return *ptep;
+	return READ_ONCE(*ptep);
 }
 
 
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 9679067..7faed6e 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -185,42 +185,42 @@
 	return pmd;
 }
 
-static inline void kvm_set_s2pte_readonly(pte_t *pte)
+static inline void kvm_set_s2pte_readonly(pte_t *ptep)
 {
 	pteval_t old_pteval, pteval;
 
-	pteval = READ_ONCE(pte_val(*pte));
+	pteval = READ_ONCE(pte_val(*ptep));
 	do {
 		old_pteval = pteval;
 		pteval &= ~PTE_S2_RDWR;
 		pteval |= PTE_S2_RDONLY;
-		pteval = cmpxchg_relaxed(&pte_val(*pte), old_pteval, pteval);
+		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
 	} while (pteval != old_pteval);
 }
 
-static inline bool kvm_s2pte_readonly(pte_t *pte)
+static inline bool kvm_s2pte_readonly(pte_t *ptep)
 {
-	return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY;
+	return (READ_ONCE(pte_val(*ptep)) & PTE_S2_RDWR) == PTE_S2_RDONLY;
 }
 
-static inline bool kvm_s2pte_exec(pte_t *pte)
+static inline bool kvm_s2pte_exec(pte_t *ptep)
 {
-	return !(pte_val(*pte) & PTE_S2_XN);
+	return !(READ_ONCE(pte_val(*ptep)) & PTE_S2_XN);
 }
 
-static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
+static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp)
 {
-	kvm_set_s2pte_readonly((pte_t *)pmd);
+	kvm_set_s2pte_readonly((pte_t *)pmdp);
 }
 
-static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
+static inline bool kvm_s2pmd_readonly(pmd_t *pmdp)
 {
-	return kvm_s2pte_readonly((pte_t *)pmd);
+	return kvm_s2pte_readonly((pte_t *)pmdp);
 }
 
-static inline bool kvm_s2pmd_exec(pmd_t *pmd)
+static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
 {
-	return !(pmd_val(*pmd) & PMD_S2_XN);
+	return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
 }
 
 static inline bool kvm_page_empty(void *ptr)
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 8d33319..39ec0b8 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -141,13 +141,13 @@
  * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
  * avoiding the possibility of conflicting TLB entries being allocated.
  */
-static inline void cpu_replace_ttbr1(pgd_t *pgd)
+static inline void cpu_replace_ttbr1(pgd_t *pgdp)
 {
 	typedef void (ttbr_replace_func)(phys_addr_t);
 	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
 	ttbr_replace_func *replace_phys;
 
-	phys_addr_t pgd_phys = virt_to_phys(pgd);
+	phys_addr_t pgd_phys = virt_to_phys(pgdp);
 
 	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
 
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index e9d9f1b..2e05bcd 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -36,23 +36,23 @@
 	return (pmd_t *)__get_free_page(PGALLOC_GFP);
 }
 
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
 {
-	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
-	free_page((unsigned long)pmd);
+	BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+	free_page((unsigned long)pmdp);
 }
 
-static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot)
+static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
 {
-	set_pud(pud, __pud(__phys_to_pud_val(pmd) | prot));
+	set_pud(pudp, __pud(__phys_to_pud_val(pmdp) | prot));
 }
 
-static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp)
 {
-	__pud_populate(pud, __pa(pmd), PMD_TYPE_TABLE);
+	__pud_populate(pudp, __pa(pmdp), PMD_TYPE_TABLE);
 }
 #else
-static inline void __pud_populate(pud_t *pud, phys_addr_t pmd, pudval_t prot)
+static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
 {
 	BUILD_BUG();
 }
@@ -65,30 +65,30 @@
 	return (pud_t *)__get_free_page(PGALLOC_GFP);
 }
 
-static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+static inline void pud_free(struct mm_struct *mm, pud_t *pudp)
 {
-	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
-	free_page((unsigned long)pud);
+	BUG_ON((unsigned long)pudp & (PAGE_SIZE-1));
+	free_page((unsigned long)pudp);
 }
 
-static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot)
+static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot)
 {
-	set_pgd(pgdp, __pgd(__phys_to_pgd_val(pud) | prot));
+	set_pgd(pgdp, __pgd(__phys_to_pgd_val(pudp) | prot));
 }
 
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, pud_t *pudp)
 {
-	__pgd_populate(pgd, __pa(pud), PUD_TYPE_TABLE);
+	__pgd_populate(pgdp, __pa(pudp), PUD_TYPE_TABLE);
 }
 #else
-static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pud, pgdval_t prot)
+static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t pudp, pgdval_t prot)
 {
 	BUILD_BUG();
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
-extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp);
 
 static inline pte_t *
 pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
@@ -114,10 +114,10 @@
 /*
  * Free a PTE table.
  */
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *ptep)
 {
-	if (pte)
-		free_page((unsigned long)pte);
+	if (ptep)
+		free_page((unsigned long)ptep);
 }
 
 static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
@@ -126,10 +126,10 @@
 	__free_page(pte);
 }
 
-static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t pte,
+static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep,
 				  pmdval_t prot)
 {
-	set_pmd(pmdp, __pmd(__phys_to_pmd_val(pte) | prot));
+	set_pmd(pmdp, __pmd(__phys_to_pmd_val(ptep) | prot));
 }
 
 /*
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 094374c..7e2c27e 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -218,7 +218,7 @@
 
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
-	*ptep = pte;
+	WRITE_ONCE(*ptep, pte);
 
 	/*
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
@@ -250,6 +250,8 @@
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
+	pte_t old_pte;
+
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
 		__sync_icache_dcache(pte, addr);
 
@@ -258,14 +260,15 @@
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(*ptep) && pte_valid(pte) &&
+	old_pte = READ_ONCE(*ptep);
+	if (IS_ENABLED(CONFIG_DEBUG_VM) && pte_valid(old_pte) && pte_valid(pte) &&
 	   (mm == current->active_mm || atomic_read(&mm->mm_users) > 1)) {
 		VM_WARN_ONCE(!pte_young(pte),
 			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
-			     __func__, pte_val(*ptep), pte_val(pte));
-		VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte),
+			     __func__, pte_val(old_pte), pte_val(pte));
+		VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte),
 			     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
-			     __func__, pte_val(*ptep), pte_val(pte));
+			     __func__, pte_val(old_pte), pte_val(pte));
 	}
 
 	set_pte(ptep, pte);
@@ -431,7 +434,7 @@
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 	dsb(ishst);
 	isb();
 }
@@ -482,7 +485,7 @@
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
-	*pudp = pud;
+	WRITE_ONCE(*pudp, pud);
 	dsb(ishst);
 	isb();
 }
@@ -500,7 +503,7 @@
 /* Find an entry in the second-level page table. */
 #define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
 
-#define pmd_offset_phys(dir, addr)	(pud_page_paddr(*(dir)) + pmd_index(addr) * sizeof(pmd_t))
+#define pmd_offset_phys(dir, addr)	(pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t))
 #define pmd_offset(dir, addr)		((pmd_t *)__va(pmd_offset_phys((dir), (addr))))
 
 #define pmd_set_fixmap(addr)		((pmd_t *)set_fixmap_offset(FIX_PMD, addr))
@@ -535,7 +538,7 @@
 
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
-	*pgdp = pgd;
+	WRITE_ONCE(*pgdp, pgd);
 	dsb(ishst);
 }
 
@@ -552,7 +555,7 @@
 /* Find an entry in the frst-level page table. */
 #define pud_index(addr)		(((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
 
-#define pud_offset_phys(dir, addr)	(pgd_page_paddr(*(dir)) + pud_index(addr) * sizeof(pud_t))
+#define pud_offset_phys(dir, addr)	(pgd_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t))
 #define pud_offset(dir, addr)		((pud_t *)__va(pud_offset_phys((dir), (addr))))
 
 #define pud_set_fixmap(addr)		((pud_t *)set_fixmap_offset(FIX_PUD, addr))
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 472ef94..902f9ed 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -28,7 +28,7 @@
 	unsigned long fp;
 	unsigned long pc;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	unsigned int graph;
+	int graph;
 #endif
 };
 
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 543e11f..e66b0fc 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -72,15 +72,15 @@
  * This is equivalent to the following test:
  * (u65)addr + (u65)size <= (u65)current->addr_limit + 1
  */
-static inline unsigned long __range_ok(unsigned long addr, unsigned long size)
+static inline unsigned long __range_ok(const void __user *addr, unsigned long size)
 {
-	unsigned long limit = current_thread_info()->addr_limit;
+	unsigned long ret, limit = current_thread_info()->addr_limit;
 
 	__chk_user_ptr(addr);
 	asm volatile(
 	// A + B <= C + 1 for all A,B,C, in four easy steps:
 	// 1: X = A + B; X' = X % 2^64
-	"	adds	%0, %0, %2\n"
+	"	adds	%0, %3, %2\n"
 	// 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4
 	"	csel	%1, xzr, %1, hi\n"
 	// 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X'
@@ -92,9 +92,9 @@
 	//    testing X' - C == 0, subject to the previous adjustments.
 	"	sbcs	xzr, %0, %1\n"
 	"	cset	%0, ls\n"
-	: "+r" (addr), "+r" (limit) : "Ir" (size) : "cc");
+	: "=&r" (ret), "+r" (limit) : "Ir" (size), "0" (addr) : "cc");
 
-	return addr;
+	return ret;
 }
 
 /*
@@ -104,7 +104,7 @@
  */
 #define untagged_addr(addr)		sign_extend64(addr, 55)
 
-#define access_ok(type, addr, size)	__range_ok((unsigned long)(addr), size)
+#define access_ok(type, addr, size)	__range_ok(addr, size)
 #define user_addr_max			get_fs
 
 #define _ASM_EXTABLE(from, to)						\
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index c33b5e4..68450e9 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -370,6 +370,7 @@
 static int swp_handler(struct pt_regs *regs, u32 instr)
 {
 	u32 destreg, data, type, address = 0;
+	const void __user *user_ptr;
 	int rn, rt2, res = 0;
 
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
@@ -401,7 +402,8 @@
 		aarch32_insn_extract_reg_num(instr, A32_RT2_OFFSET), data);
 
 	/* Check access in reasonable access range for both SWP and SWPB */
-	if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) {
+	user_ptr = (const void __user *)(unsigned long)(address & ~3);
+	if (!access_ok(VERIFY_WRITE, user_ptr, 4)) {
 		pr_debug("SWP{B} emulation: access to 0x%08x not allowed!\n",
 			address);
 		goto fault;
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0782359..52f15cd 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -408,6 +408,15 @@
 	},
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
+		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
+		.enable = qcom_enable_link_stack_sanitization,
+	},
+	{
+		.capability = ARM64_HARDEN_BP_POST_GUEST_EXIT,
+		MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
+	},
+	{
+		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
 		MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
 		.enable = enable_smccc_arch_workaround_1,
 	},
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 29b1f87..2985a06 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -199,9 +199,11 @@
 };
 
 static const struct arm64_ftr_bits ftr_ctr[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1),	/* RAO */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1),		/* RES1 */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 29, 1, 1),	/* DIC */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 28, 1, 1),	/* IDC */
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* ERG */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 20, 4, 0),	/* ERG */
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
 	/*
 	 * Linux can handle differing I-cache policies. Userspace JITs will
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index f85ac58..a8bf1c8 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -90,7 +90,7 @@
 				  unsigned long addr, void *data)
 {
 	efi_memory_desc_t *md = data;
-	pte_t pte = *ptep;
+	pte_t pte = READ_ONCE(*ptep);
 
 	if (md->attribute & EFI_MEMORY_RO)
 		pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index f20cf7e..1ec5f28 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -202,10 +202,10 @@
 				 gfp_t mask)
 {
 	int rc = 0;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep;
 	unsigned long dst = (unsigned long)allocator(mask);
 
 	if (!dst) {
@@ -216,38 +216,38 @@
 	memcpy((void *)dst, src_start, length);
 	flush_icache_range(dst, dst + length);
 
-	pgd = pgd_offset_raw(allocator(mask), dst_addr);
-	if (pgd_none(*pgd)) {
-		pud = allocator(mask);
-		if (!pud) {
+	pgdp = pgd_offset_raw(allocator(mask), dst_addr);
+	if (pgd_none(READ_ONCE(*pgdp))) {
+		pudp = allocator(mask);
+		if (!pudp) {
 			rc = -ENOMEM;
 			goto out;
 		}
-		pgd_populate(&init_mm, pgd, pud);
+		pgd_populate(&init_mm, pgdp, pudp);
 	}
 
-	pud = pud_offset(pgd, dst_addr);
-	if (pud_none(*pud)) {
-		pmd = allocator(mask);
-		if (!pmd) {
+	pudp = pud_offset(pgdp, dst_addr);
+	if (pud_none(READ_ONCE(*pudp))) {
+		pmdp = allocator(mask);
+		if (!pmdp) {
 			rc = -ENOMEM;
 			goto out;
 		}
-		pud_populate(&init_mm, pud, pmd);
+		pud_populate(&init_mm, pudp, pmdp);
 	}
 
-	pmd = pmd_offset(pud, dst_addr);
-	if (pmd_none(*pmd)) {
-		pte = allocator(mask);
-		if (!pte) {
+	pmdp = pmd_offset(pudp, dst_addr);
+	if (pmd_none(READ_ONCE(*pmdp))) {
+		ptep = allocator(mask);
+		if (!ptep) {
 			rc = -ENOMEM;
 			goto out;
 		}
-		pmd_populate_kernel(&init_mm, pmd, pte);
+		pmd_populate_kernel(&init_mm, pmdp, ptep);
 	}
 
-	pte = pte_offset_kernel(pmd, dst_addr);
-	set_pte(pte, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC));
+	ptep = pte_offset_kernel(pmdp, dst_addr);
+	set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC));
 
 	/*
 	 * Load our new page tables. A strict BBM approach requires that we
@@ -263,7 +263,7 @@
 	 */
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	write_sysreg(phys_to_ttbr(virt_to_phys(pgd)), ttbr0_el1);
+	write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1);
 	isb();
 
 	*phys_dst_addr = virt_to_phys((void *)dst);
@@ -320,9 +320,9 @@
 	return ret;
 }
 
-static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
+static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
 {
-	pte_t pte = *src_pte;
+	pte_t pte = READ_ONCE(*src_ptep);
 
 	if (pte_valid(pte)) {
 		/*
@@ -330,7 +330,7 @@
 		 * read only (code, rodata). Clear the RDONLY bit from
 		 * the temporary mappings we use during restore.
 		 */
-		set_pte(dst_pte, pte_mkwrite(pte));
+		set_pte(dst_ptep, pte_mkwrite(pte));
 	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
 		/*
 		 * debug_pagealloc will removed the PTE_VALID bit if
@@ -343,112 +343,116 @@
 		 */
 		BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-		set_pte(dst_pte, pte_mkpresent(pte_mkwrite(pte)));
+		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
 	}
 }
 
-static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start,
+static int copy_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start,
 		    unsigned long end)
 {
-	pte_t *src_pte;
-	pte_t *dst_pte;
+	pte_t *src_ptep;
+	pte_t *dst_ptep;
 	unsigned long addr = start;
 
-	dst_pte = (pte_t *)get_safe_page(GFP_ATOMIC);
-	if (!dst_pte)
+	dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC);
+	if (!dst_ptep)
 		return -ENOMEM;
-	pmd_populate_kernel(&init_mm, dst_pmd, dst_pte);
-	dst_pte = pte_offset_kernel(dst_pmd, start);
+	pmd_populate_kernel(&init_mm, dst_pmdp, dst_ptep);
+	dst_ptep = pte_offset_kernel(dst_pmdp, start);
 
-	src_pte = pte_offset_kernel(src_pmd, start);
+	src_ptep = pte_offset_kernel(src_pmdp, start);
 	do {
-		_copy_pte(dst_pte, src_pte, addr);
-	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
+		_copy_pte(dst_ptep, src_ptep, addr);
+	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);
 
 	return 0;
 }
 
-static int copy_pmd(pud_t *dst_pud, pud_t *src_pud, unsigned long start,
+static int copy_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start,
 		    unsigned long end)
 {
-	pmd_t *src_pmd;
-	pmd_t *dst_pmd;
+	pmd_t *src_pmdp;
+	pmd_t *dst_pmdp;
 	unsigned long next;
 	unsigned long addr = start;
 
-	if (pud_none(*dst_pud)) {
-		dst_pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pmd)
+	if (pud_none(READ_ONCE(*dst_pudp))) {
+		dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pmdp)
 			return -ENOMEM;
-		pud_populate(&init_mm, dst_pud, dst_pmd);
+		pud_populate(&init_mm, dst_pudp, dst_pmdp);
 	}
-	dst_pmd = pmd_offset(dst_pud, start);
+	dst_pmdp = pmd_offset(dst_pudp, start);
 
-	src_pmd = pmd_offset(src_pud, start);
+	src_pmdp = pmd_offset(src_pudp, start);
 	do {
+		pmd_t pmd = READ_ONCE(*src_pmdp);
+
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(*src_pmd))
+		if (pmd_none(pmd))
 			continue;
-		if (pmd_table(*src_pmd)) {
-			if (copy_pte(dst_pmd, src_pmd, addr, next))
+		if (pmd_table(pmd)) {
+			if (copy_pte(dst_pmdp, src_pmdp, addr, next))
 				return -ENOMEM;
 		} else {
-			set_pmd(dst_pmd,
-				__pmd(pmd_val(*src_pmd) & ~PMD_SECT_RDONLY));
+			set_pmd(dst_pmdp,
+				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
 		}
-	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
+	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);
 
 	return 0;
 }
 
-static int copy_pud(pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long start,
+static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start,
 		    unsigned long end)
 {
-	pud_t *dst_pud;
-	pud_t *src_pud;
+	pud_t *dst_pudp;
+	pud_t *src_pudp;
 	unsigned long next;
 	unsigned long addr = start;
 
-	if (pgd_none(*dst_pgd)) {
-		dst_pud = (pud_t *)get_safe_page(GFP_ATOMIC);
-		if (!dst_pud)
+	if (pgd_none(READ_ONCE(*dst_pgdp))) {
+		dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pudp)
 			return -ENOMEM;
-		pgd_populate(&init_mm, dst_pgd, dst_pud);
+		pgd_populate(&init_mm, dst_pgdp, dst_pudp);
 	}
-	dst_pud = pud_offset(dst_pgd, start);
+	dst_pudp = pud_offset(dst_pgdp, start);
 
-	src_pud = pud_offset(src_pgd, start);
+	src_pudp = pud_offset(src_pgdp, start);
 	do {
+		pud_t pud = READ_ONCE(*src_pudp);
+
 		next = pud_addr_end(addr, end);
-		if (pud_none(*src_pud))
+		if (pud_none(pud))
 			continue;
-		if (pud_table(*(src_pud))) {
-			if (copy_pmd(dst_pud, src_pud, addr, next))
+		if (pud_table(pud)) {
+			if (copy_pmd(dst_pudp, src_pudp, addr, next))
 				return -ENOMEM;
 		} else {
-			set_pud(dst_pud,
-				__pud(pud_val(*src_pud) & ~PMD_SECT_RDONLY));
+			set_pud(dst_pudp,
+				__pud(pud_val(pud) & ~PMD_SECT_RDONLY));
 		}
-	} while (dst_pud++, src_pud++, addr = next, addr != end);
+	} while (dst_pudp++, src_pudp++, addr = next, addr != end);
 
 	return 0;
 }
 
-static int copy_page_tables(pgd_t *dst_pgd, unsigned long start,
+static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start,
 			    unsigned long end)
 {
 	unsigned long next;
 	unsigned long addr = start;
-	pgd_t *src_pgd = pgd_offset_k(start);
+	pgd_t *src_pgdp = pgd_offset_k(start);
 
-	dst_pgd = pgd_offset_raw(dst_pgd, start);
+	dst_pgdp = pgd_offset_raw(dst_pgdp, start);
 	do {
 		next = pgd_addr_end(addr, end);
-		if (pgd_none(*src_pgd))
+		if (pgd_none(READ_ONCE(*src_pgdp)))
 			continue;
-		if (copy_pud(dst_pgd, src_pgd, addr, next))
+		if (copy_pud(dst_pgdp, src_pgdp, addr, next))
 			return -ENOMEM;
-	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
+	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 75b220b..85a251b 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -908,9 +908,9 @@
 	int pmuver;
 
 	dfr0 = read_sysreg(id_aa64dfr0_el1);
-	pmuver = cpuid_feature_extract_signed_field(dfr0,
+	pmuver = cpuid_feature_extract_unsigned_field(dfr0,
 			ID_AA64DFR0_PMUVER_SHIFT);
-	if (pmuver < 1)
+	if (pmuver == 0xf || pmuver == 0)
 		return;
 
 	probe->present = true;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index ad8aeb0..c0da6ef 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -220,8 +220,15 @@
 
 	show_regs_print_info(KERN_DEFAULT);
 	print_pstate(regs);
-	printk("pc : %pS\n", (void *)regs->pc);
-	printk("lr : %pS\n", (void *)lr);
+
+	if (!user_mode(regs)) {
+		printk("pc : %pS\n", (void *)regs->pc);
+		printk("lr : %pS\n", (void *)lr);
+	} else {
+		printk("pc : %016llx\n", regs->pc);
+		printk("lr : %016llx\n", lr);
+	}
+
 	printk("sp : %016llx\n", sp);
 
 	i = top_reg;
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6618036..9ae31f7 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1419,7 +1419,7 @@
 	u64 addr = 0;
 	u32 ctrl = 0;
 
-	int err, idx = compat_ptrace_hbp_num_to_idx(num);;
+	int err, idx = compat_ptrace_hbp_num_to_idx(num);
 
 	if (num & 1) {
 		err = ptrace_hbp_get_addr(note_type, tsk, idx, &addr);
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 76809cc..d5718a0 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -59,6 +59,11 @@
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk->ret_stack &&
 			(frame->pc == (unsigned long)return_to_handler)) {
+		if (WARN_ON_ONCE(frame->graph == -1))
+			return -EINVAL;
+		if (frame->graph < -1)
+			frame->graph += FTRACE_NOTRACE_DEPTH;
+
 		/*
 		 * This is a case where function graph tracer has
 		 * modified a return address (LR) in a stack frame
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 8b8bbd3..a382b2a 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -57,7 +57,7 @@
 	if (end < start || flags)
 		return -EINVAL;
 
-	if (!access_ok(VERIFY_READ, start, end - start))
+	if (!access_ok(VERIFY_READ, (const void __user *)start, end - start))
 		return -EFAULT;
 
 	return __do_compat_cache_op(start, end);
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index a439128..f258636 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -52,7 +52,7 @@
 	frame.fp = regs->regs[29];
 	frame.pc = regs->pc;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame.graph = -1; /* no task info */
+	frame.graph = current->curr_ret_stack;
 #endif
 	do {
 		int ret = unwind_frame(NULL, &frame);
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index bbb0fde..eb2d151 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -57,7 +57,7 @@
 	"Error"
 };
 
-int show_unhandled_signals = 1;
+int show_unhandled_signals = 0;
 
 static void dump_backtrace_entry(unsigned long where)
 {
@@ -526,14 +526,6 @@
 	}
 #endif
 
-	if (show_unhandled_signals_ratelimited()) {
-		pr_info("%s[%d]: syscall %d\n", current->comm,
-			task_pid_nr(current), regs->syscallno);
-		dump_instr("", regs);
-		if (user_mode(regs))
-			__show_regs(regs);
-	}
-
 	return sys_ni_syscall();
 }
 
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 116252a8..870f4b1 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -407,8 +407,10 @@
 		u32 midr = read_cpuid_id();
 
 		/* Apply BTAC predictors mitigation to all Falkor chips */
-		if ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)
+		if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) ||
+		    ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1)) {
 			__qcom_hyp_sanitize_btac_predictors();
+		}
 	}
 
 	fp_enabled = __fpsimd_enabled();
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 7b60d62..65dfc85 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -286,48 +286,52 @@
 
 }
 
-static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
+static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start)
 {
-	pte_t *pte = pte_offset_kernel(pmd, 0UL);
+	pte_t *ptep = pte_offset_kernel(pmdp, 0UL);
 	unsigned long addr;
 	unsigned i;
 
-	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
+	for (i = 0; i < PTRS_PER_PTE; i++, ptep++) {
 		addr = start + i * PAGE_SIZE;
-		note_page(st, addr, 4, pte_val(*pte));
+		note_page(st, addr, 4, READ_ONCE(pte_val(*ptep)));
 	}
 }
 
-static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
+static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start)
 {
-	pmd_t *pmd = pmd_offset(pud, 0UL);
+	pmd_t *pmdp = pmd_offset(pudp, 0UL);
 	unsigned long addr;
 	unsigned i;
 
-	for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
+	for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) {
+		pmd_t pmd = READ_ONCE(*pmdp);
+
 		addr = start + i * PMD_SIZE;
-		if (pmd_none(*pmd) || pmd_sect(*pmd)) {
-			note_page(st, addr, 3, pmd_val(*pmd));
+		if (pmd_none(pmd) || pmd_sect(pmd)) {
+			note_page(st, addr, 3, pmd_val(pmd));
 		} else {
-			BUG_ON(pmd_bad(*pmd));
-			walk_pte(st, pmd, addr);
+			BUG_ON(pmd_bad(pmd));
+			walk_pte(st, pmdp, addr);
 		}
 	}
 }
 
-static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
+static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start)
 {
-	pud_t *pud = pud_offset(pgd, 0UL);
+	pud_t *pudp = pud_offset(pgdp, 0UL);
 	unsigned long addr;
 	unsigned i;
 
-	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
+	for (i = 0; i < PTRS_PER_PUD; i++, pudp++) {
+		pud_t pud = READ_ONCE(*pudp);
+
 		addr = start + i * PUD_SIZE;
-		if (pud_none(*pud) || pud_sect(*pud)) {
-			note_page(st, addr, 2, pud_val(*pud));
+		if (pud_none(pud) || pud_sect(pud)) {
+			note_page(st, addr, 2, pud_val(pud));
 		} else {
-			BUG_ON(pud_bad(*pud));
-			walk_pmd(st, pud, addr);
+			BUG_ON(pud_bad(pud));
+			walk_pmd(st, pudp, addr);
 		}
 	}
 }
@@ -335,17 +339,19 @@
 static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
 		     unsigned long start)
 {
-	pgd_t *pgd = pgd_offset(mm, 0UL);
+	pgd_t *pgdp = pgd_offset(mm, 0UL);
 	unsigned i;
 	unsigned long addr;
 
-	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
+	for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) {
+		pgd_t pgd = READ_ONCE(*pgdp);
+
 		addr = start + i * PGDIR_SIZE;
-		if (pgd_none(*pgd)) {
-			note_page(st, addr, 1, pgd_val(*pgd));
+		if (pgd_none(pgd)) {
+			note_page(st, addr, 1, pgd_val(pgd));
 		} else {
-			BUG_ON(pgd_bad(*pgd));
-			walk_pud(st, pgd, addr);
+			BUG_ON(pgd_bad(pgd));
+			walk_pud(st, pgdp, addr);
 		}
 	}
 }
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index f76bb2c..bff1155 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -130,7 +130,8 @@
 void show_pte(unsigned long addr)
 {
 	struct mm_struct *mm;
-	pgd_t *pgd;
+	pgd_t *pgdp;
+	pgd_t pgd;
 
 	if (addr < TASK_SIZE) {
 		/* TTBR0 */
@@ -149,33 +150,37 @@
 		return;
 	}
 
-	pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgd = %p\n",
+	pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n",
 		 mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K,
 		 VA_BITS, mm->pgd);
-	pgd = pgd_offset(mm, addr);
-	pr_alert("[%016lx] *pgd=%016llx", addr, pgd_val(*pgd));
+	pgdp = pgd_offset(mm, addr);
+	pgd = READ_ONCE(*pgdp);
+	pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd));
 
 	do {
-		pud_t *pud;
-		pmd_t *pmd;
-		pte_t *pte;
+		pud_t *pudp, pud;
+		pmd_t *pmdp, pmd;
+		pte_t *ptep, pte;
 
-		if (pgd_none(*pgd) || pgd_bad(*pgd))
+		if (pgd_none(pgd) || pgd_bad(pgd))
 			break;
 
-		pud = pud_offset(pgd, addr);
-		pr_cont(", *pud=%016llx", pud_val(*pud));
-		if (pud_none(*pud) || pud_bad(*pud))
+		pudp = pud_offset(pgdp, addr);
+		pud = READ_ONCE(*pudp);
+		pr_cont(", pud=%016llx", pud_val(pud));
+		if (pud_none(pud) || pud_bad(pud))
 			break;
 
-		pmd = pmd_offset(pud, addr);
-		pr_cont(", *pmd=%016llx", pmd_val(*pmd));
-		if (pmd_none(*pmd) || pmd_bad(*pmd))
+		pmdp = pmd_offset(pudp, addr);
+		pmd = READ_ONCE(*pmdp);
+		pr_cont(", pmd=%016llx", pmd_val(pmd));
+		if (pmd_none(pmd) || pmd_bad(pmd))
 			break;
 
-		pte = pte_offset_map(pmd, addr);
-		pr_cont(", *pte=%016llx", pte_val(*pte));
-		pte_unmap(pte);
+		ptep = pte_offset_map(pmdp, addr);
+		pte = READ_ONCE(*ptep);
+		pr_cont(", pte=%016llx", pte_val(pte));
+		pte_unmap(ptep);
 	} while(0);
 
 	pr_cont("\n");
@@ -196,8 +201,9 @@
 			  pte_t entry, int dirty)
 {
 	pteval_t old_pteval, pteval;
+	pte_t pte = READ_ONCE(*ptep);
 
-	if (pte_same(*ptep, entry))
+	if (pte_same(pte, entry))
 		return 0;
 
 	/* only preserve the access flags and write permission */
@@ -210,7 +216,7 @@
 	 * (calculated as: a & b == ~(~a | ~b)).
 	 */
 	pte_val(entry) ^= PTE_RDONLY;
-	pteval = READ_ONCE(pte_val(*ptep));
+	pteval = pte_val(pte);
 	do {
 		old_pteval = pteval;
 		pteval ^= PTE_RDONLY;
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 6cb0fa9..ecc6818 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -54,14 +54,14 @@
 static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, size_t *pgsize)
 {
-	pgd_t *pgd = pgd_offset(mm, addr);
-	pud_t *pud;
-	pmd_t *pmd;
+	pgd_t *pgdp = pgd_offset(mm, addr);
+	pud_t *pudp;
+	pmd_t *pmdp;
 
 	*pgsize = PAGE_SIZE;
-	pud = pud_offset(pgd, addr);
-	pmd = pmd_offset(pud, addr);
-	if ((pte_t *)pmd == ptep) {
+	pudp = pud_offset(pgdp, addr);
+	pmdp = pmd_offset(pudp, addr);
+	if ((pte_t *)pmdp == ptep) {
 		*pgsize = PMD_SIZE;
 		return CONT_PMDS;
 	}
@@ -181,11 +181,8 @@
 
 	clear_flush(mm, addr, ptep, pgsize, ncontig);
 
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
-		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
-			 pte_val(pfn_pte(pfn, hugeprot)));
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
 		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
-	}
 }
 
 void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
@@ -203,20 +200,20 @@
 pte_t *huge_pte_alloc(struct mm_struct *mm,
 		      unsigned long addr, unsigned long sz)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pte_t *pte = NULL;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
+	pte_t *ptep = NULL;
 
-	pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz);
-	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
-	if (!pud)
+	pgdp = pgd_offset(mm, addr);
+	pudp = pud_alloc(mm, pgdp, addr);
+	if (!pudp)
 		return NULL;
 
 	if (sz == PUD_SIZE) {
-		pte = (pte_t *)pud;
+		ptep = (pte_t *)pudp;
 	} else if (sz == (PAGE_SIZE * CONT_PTES)) {
-		pmd_t *pmd = pmd_alloc(mm, pud, addr);
+		pmdp = pmd_alloc(mm, pudp, addr);
 
 		WARN_ON(addr & (sz - 1));
 		/*
@@ -226,60 +223,55 @@
 		 * will be no pte_unmap() to correspond with this
 		 * pte_alloc_map().
 		 */
-		pte = pte_alloc_map(mm, pmd, addr);
+		ptep = pte_alloc_map(mm, pmdp, addr);
 	} else if (sz == PMD_SIZE) {
 		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
-		    pud_none(*pud))
-			pte = huge_pmd_share(mm, addr, pud);
+		    pud_none(READ_ONCE(*pudp)))
+			ptep = huge_pmd_share(mm, addr, pudp);
 		else
-			pte = (pte_t *)pmd_alloc(mm, pud, addr);
+			ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
 	} else if (sz == (PMD_SIZE * CONT_PMDS)) {
-		pmd_t *pmd;
-
-		pmd = pmd_alloc(mm, pud, addr);
+		pmdp = pmd_alloc(mm, pudp, addr);
 		WARN_ON(addr & (sz - 1));
-		return (pte_t *)pmd;
+		return (pte_t *)pmdp;
 	}
 
-	pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr,
-	       sz, pte, pte_val(*pte));
-	return pte;
+	return ptep;
 }
 
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	pgd_t *pgdp;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
 
-	pgd = pgd_offset(mm, addr);
-	pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd);
-	if (!pgd_present(*pgd))
+	pgdp = pgd_offset(mm, addr);
+	if (!pgd_present(READ_ONCE(*pgdp)))
 		return NULL;
 
-	pud = pud_offset(pgd, addr);
-	if (sz != PUD_SIZE && pud_none(*pud))
+	pudp = pud_offset(pgdp, addr);
+	pud = READ_ONCE(*pudp);
+	if (sz != PUD_SIZE && pud_none(pud))
 		return NULL;
 	/* hugepage or swap? */
-	if (pud_huge(*pud) || !pud_present(*pud))
-		return (pte_t *)pud;
+	if (pud_huge(pud) || !pud_present(pud))
+		return (pte_t *)pudp;
 	/* table; check the next level */
 
 	if (sz == CONT_PMD_SIZE)
 		addr &= CONT_PMD_MASK;
 
-	pmd = pmd_offset(pud, addr);
+	pmdp = pmd_offset(pudp, addr);
+	pmd = READ_ONCE(*pmdp);
 	if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
-	    pmd_none(*pmd))
+	    pmd_none(pmd))
 		return NULL;
-	if (pmd_huge(*pmd) || !pmd_present(*pmd))
-		return (pte_t *)pmd;
+	if (pmd_huge(pmd) || !pmd_present(pmd))
+		return (pte_t *)pmdp;
 
-	if (sz == CONT_PTE_SIZE) {
-		pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK));
-		return pte;
-	}
+	if (sz == CONT_PTE_SIZE)
+		return pte_offset_kernel(pmdp, (addr & CONT_PTE_MASK));
 
 	return NULL;
 }
@@ -367,7 +359,7 @@
 	size_t pgsize;
 	pte_t pte;
 
-	if (!pte_cont(*ptep)) {
+	if (!pte_cont(READ_ONCE(*ptep))) {
 		ptep_set_wrprotect(mm, addr, ptep);
 		return;
 	}
@@ -391,7 +383,7 @@
 	size_t pgsize;
 	int ncontig;
 
-	if (!pte_cont(*ptep)) {
+	if (!pte_cont(READ_ONCE(*ptep))) {
 		ptep_clear_flush(vma, addr, ptep);
 		return;
 	}
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 6e02e6f..dabfc1e 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -44,92 +44,92 @@
 	return __pa(p);
 }
 
-static pte_t *__init kasan_pte_offset(pmd_t *pmd, unsigned long addr, int node,
+static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node,
 				      bool early)
 {
-	if (pmd_none(*pmd)) {
+	if (pmd_none(READ_ONCE(*pmdp))) {
 		phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte)
 					     : kasan_alloc_zeroed_page(node);
-		__pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
+		__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
 	}
 
-	return early ? pte_offset_kimg(pmd, addr)
-		     : pte_offset_kernel(pmd, addr);
+	return early ? pte_offset_kimg(pmdp, addr)
+		     : pte_offset_kernel(pmdp, addr);
 }
 
-static pmd_t *__init kasan_pmd_offset(pud_t *pud, unsigned long addr, int node,
+static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node,
 				      bool early)
 {
-	if (pud_none(*pud)) {
+	if (pud_none(READ_ONCE(*pudp))) {
 		phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd)
 					     : kasan_alloc_zeroed_page(node);
-		__pud_populate(pud, pmd_phys, PMD_TYPE_TABLE);
+		__pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE);
 	}
 
-	return early ? pmd_offset_kimg(pud, addr) : pmd_offset(pud, addr);
+	return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr);
 }
 
-static pud_t *__init kasan_pud_offset(pgd_t *pgd, unsigned long addr, int node,
+static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node,
 				      bool early)
 {
-	if (pgd_none(*pgd)) {
+	if (pgd_none(READ_ONCE(*pgdp))) {
 		phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud)
 					     : kasan_alloc_zeroed_page(node);
-		__pgd_populate(pgd, pud_phys, PMD_TYPE_TABLE);
+		__pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE);
 	}
 
-	return early ? pud_offset_kimg(pgd, addr) : pud_offset(pgd, addr);
+	return early ? pud_offset_kimg(pgdp, addr) : pud_offset(pgdp, addr);
 }
 
-static void __init kasan_pte_populate(pmd_t *pmd, unsigned long addr,
+static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	pte_t *pte = kasan_pte_offset(pmd, addr, node, early);
+	pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early);
 
 	do {
 		phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page)
 					      : kasan_alloc_zeroed_page(node);
 		next = addr + PAGE_SIZE;
-		set_pte(pte, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
-	} while (pte++, addr = next, addr != end && pte_none(*pte));
+		set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
+	} while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep)));
 }
 
-static void __init kasan_pmd_populate(pud_t *pud, unsigned long addr,
+static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	pmd_t *pmd = kasan_pmd_offset(pud, addr, node, early);
+	pmd_t *pmdp = kasan_pmd_offset(pudp, addr, node, early);
 
 	do {
 		next = pmd_addr_end(addr, end);
-		kasan_pte_populate(pmd, addr, next, node, early);
-	} while (pmd++, addr = next, addr != end && pmd_none(*pmd));
+		kasan_pte_populate(pmdp, addr, next, node, early);
+	} while (pmdp++, addr = next, addr != end && pmd_none(READ_ONCE(*pmdp)));
 }
 
-static void __init kasan_pud_populate(pgd_t *pgd, unsigned long addr,
+static void __init kasan_pud_populate(pgd_t *pgdp, unsigned long addr,
 				      unsigned long end, int node, bool early)
 {
 	unsigned long next;
-	pud_t *pud = kasan_pud_offset(pgd, addr, node, early);
+	pud_t *pudp = kasan_pud_offset(pgdp, addr, node, early);
 
 	do {
 		next = pud_addr_end(addr, end);
-		kasan_pmd_populate(pud, addr, next, node, early);
-	} while (pud++, addr = next, addr != end && pud_none(*pud));
+		kasan_pmd_populate(pudp, addr, next, node, early);
+	} while (pudp++, addr = next, addr != end && pud_none(READ_ONCE(*pudp)));
 }
 
 static void __init kasan_pgd_populate(unsigned long addr, unsigned long end,
 				      int node, bool early)
 {
 	unsigned long next;
-	pgd_t *pgd;
+	pgd_t *pgdp;
 
-	pgd = pgd_offset_k(addr);
+	pgdp = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		kasan_pud_populate(pgd, addr, next, node, early);
-	} while (pgd++, addr = next, addr != end);
+		kasan_pud_populate(pgdp, addr, next, node, early);
+	} while (pgdp++, addr = next, addr != end);
 }
 
 /* The early shadow maps everything to a single page of zeroes */
@@ -155,14 +155,14 @@
  */
 void __init kasan_copy_shadow(pgd_t *pgdir)
 {
-	pgd_t *pgd, *pgd_new, *pgd_end;
+	pgd_t *pgdp, *pgdp_new, *pgdp_end;
 
-	pgd = pgd_offset_k(KASAN_SHADOW_START);
-	pgd_end = pgd_offset_k(KASAN_SHADOW_END);
-	pgd_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START);
+	pgdp = pgd_offset_k(KASAN_SHADOW_START);
+	pgdp_end = pgd_offset_k(KASAN_SHADOW_END);
+	pgdp_new = pgd_offset_raw(pgdir, KASAN_SHADOW_START);
 	do {
-		set_pgd(pgd_new, *pgd);
-	} while (pgd++, pgd_new++, pgd != pgd_end);
+		set_pgd(pgdp_new, READ_ONCE(*pgdp));
+	} while (pgdp++, pgdp_new++, pgdp != pgdp_end);
 }
 
 static void __init clear_pgds(unsigned long start,
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 4694cda..84a019f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -125,45 +125,48 @@
 	return ((old ^ new) & ~mask) == 0;
 }
 
-static void init_pte(pmd_t *pmd, unsigned long addr, unsigned long end,
+static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot)
 {
-	pte_t *pte;
+	pte_t *ptep;
 
-	pte = pte_set_fixmap_offset(pmd, addr);
+	ptep = pte_set_fixmap_offset(pmdp, addr);
 	do {
-		pte_t old_pte = *pte;
+		pte_t old_pte = READ_ONCE(*ptep);
 
-		set_pte(pte, pfn_pte(__phys_to_pfn(phys), prot));
+		set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
 
 		/*
 		 * After the PTE entry has been populated once, we
 		 * only allow updates to the permission attributes.
 		 */
-		BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte)));
+		BUG_ON(!pgattr_change_is_safe(pte_val(old_pte),
+					      READ_ONCE(pte_val(*ptep))));
 
 		phys += PAGE_SIZE;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
+	} while (ptep++, addr += PAGE_SIZE, addr != end);
 
 	pte_clear_fixmap();
 }
 
-static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr,
+static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
 				phys_addr_t (*pgtable_alloc)(void),
 				int flags)
 {
 	unsigned long next;
+	pmd_t pmd = READ_ONCE(*pmdp);
 
-	BUG_ON(pmd_sect(*pmd));
-	if (pmd_none(*pmd)) {
+	BUG_ON(pmd_sect(pmd));
+	if (pmd_none(pmd)) {
 		phys_addr_t pte_phys;
 		BUG_ON(!pgtable_alloc);
 		pte_phys = pgtable_alloc();
-		__pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
+		__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
+		pmd = READ_ONCE(*pmdp);
 	}
-	BUG_ON(pmd_bad(*pmd));
+	BUG_ON(pmd_bad(pmd));
 
 	do {
 		pgprot_t __prot = prot;
@@ -175,67 +178,69 @@
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pte(pmd, addr, next, phys, __prot);
+		init_pte(pmdp, addr, next, phys, __prot);
 
 		phys += next - addr;
 	} while (addr = next, addr != end);
 }
 
-static void init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
+static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot,
 		     phys_addr_t (*pgtable_alloc)(void), int flags)
 {
 	unsigned long next;
-	pmd_t *pmd;
+	pmd_t *pmdp;
 
-	pmd = pmd_set_fixmap_offset(pud, addr);
+	pmdp = pmd_set_fixmap_offset(pudp, addr);
 	do {
-		pmd_t old_pmd = *pmd;
+		pmd_t old_pmd = READ_ONCE(*pmdp);
 
 		next = pmd_addr_end(addr, end);
 
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
 		    (flags & NO_BLOCK_MAPPINGS) == 0) {
-			pmd_set_huge(pmd, phys, prot);
+			pmd_set_huge(pmdp, phys, prot);
 
 			/*
 			 * After the PMD entry has been populated once, we
 			 * only allow updates to the permission attributes.
 			 */
 			BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
-						      pmd_val(*pmd)));
+						      READ_ONCE(pmd_val(*pmdp))));
 		} else {
-			alloc_init_cont_pte(pmd, addr, next, phys, prot,
+			alloc_init_cont_pte(pmdp, addr, next, phys, prot,
 					    pgtable_alloc, flags);
 
 			BUG_ON(pmd_val(old_pmd) != 0 &&
-			       pmd_val(old_pmd) != pmd_val(*pmd));
+			       pmd_val(old_pmd) != READ_ONCE(pmd_val(*pmdp)));
 		}
 		phys += next - addr;
-	} while (pmd++, addr = next, addr != end);
+	} while (pmdp++, addr = next, addr != end);
 
 	pmd_clear_fixmap();
 }
 
-static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr,
+static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
 				phys_addr_t (*pgtable_alloc)(void), int flags)
 {
 	unsigned long next;
+	pud_t pud = READ_ONCE(*pudp);
 
 	/*
 	 * Check for initial section mappings in the pgd/pud.
 	 */
-	BUG_ON(pud_sect(*pud));
-	if (pud_none(*pud)) {
+	BUG_ON(pud_sect(pud));
+	if (pud_none(pud)) {
 		phys_addr_t pmd_phys;
 		BUG_ON(!pgtable_alloc);
 		pmd_phys = pgtable_alloc();
-		__pud_populate(pud, pmd_phys, PUD_TYPE_TABLE);
+		__pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
+		pud = READ_ONCE(*pudp);
 	}
-	BUG_ON(pud_bad(*pud));
+	BUG_ON(pud_bad(pud));
 
 	do {
 		pgprot_t __prot = prot;
@@ -247,7 +252,7 @@
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pmd(pud, addr, next, phys, __prot, pgtable_alloc, flags);
+		init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);
 
 		phys += next - addr;
 	} while (addr = next, addr != end);
@@ -265,25 +270,27 @@
 	return true;
 }
 
-static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
-				  phys_addr_t phys, pgprot_t prot,
-				  phys_addr_t (*pgtable_alloc)(void),
-				  int flags)
+static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
+			   phys_addr_t phys, pgprot_t prot,
+			   phys_addr_t (*pgtable_alloc)(void),
+			   int flags)
 {
-	pud_t *pud;
 	unsigned long next;
+	pud_t *pudp;
+	pgd_t pgd = READ_ONCE(*pgdp);
 
-	if (pgd_none(*pgd)) {
+	if (pgd_none(pgd)) {
 		phys_addr_t pud_phys;
 		BUG_ON(!pgtable_alloc);
 		pud_phys = pgtable_alloc();
-		__pgd_populate(pgd, pud_phys, PUD_TYPE_TABLE);
+		__pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
+		pgd = READ_ONCE(*pgdp);
 	}
-	BUG_ON(pgd_bad(*pgd));
+	BUG_ON(pgd_bad(pgd));
 
-	pud = pud_set_fixmap_offset(pgd, addr);
+	pudp = pud_set_fixmap_offset(pgdp, addr);
 	do {
-		pud_t old_pud = *pud;
+		pud_t old_pud = READ_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
 
@@ -292,23 +299,23 @@
 		 */
 		if (use_1G_block(addr, next, phys) &&
 		    (flags & NO_BLOCK_MAPPINGS) == 0) {
-			pud_set_huge(pud, phys, prot);
+			pud_set_huge(pudp, phys, prot);
 
 			/*
 			 * After the PUD entry has been populated once, we
 			 * only allow updates to the permission attributes.
 			 */
 			BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
-						      pud_val(*pud)));
+						      READ_ONCE(pud_val(*pudp))));
 		} else {
-			alloc_init_cont_pmd(pud, addr, next, phys, prot,
+			alloc_init_cont_pmd(pudp, addr, next, phys, prot,
 					    pgtable_alloc, flags);
 
 			BUG_ON(pud_val(old_pud) != 0 &&
-			       pud_val(old_pud) != pud_val(*pud));
+			       pud_val(old_pud) != READ_ONCE(pud_val(*pudp)));
 		}
 		phys += next - addr;
-	} while (pud++, addr = next, addr != end);
+	} while (pudp++, addr = next, addr != end);
 
 	pud_clear_fixmap();
 }
@@ -320,7 +327,7 @@
 				 int flags)
 {
 	unsigned long addr, length, end, next;
-	pgd_t *pgd = pgd_offset_raw(pgdir, virt);
+	pgd_t *pgdp = pgd_offset_raw(pgdir, virt);
 
 	/*
 	 * If the virtual and physical address don't have the same offset
@@ -336,10 +343,10 @@
 	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc,
+		alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc,
 			       flags);
 		phys += next - addr;
-	} while (pgd++, addr = next, addr != end);
+	} while (pgdp++, addr = next, addr != end);
 }
 
 static phys_addr_t pgd_pgtable_alloc(void)
@@ -401,10 +408,10 @@
 	flush_tlb_kernel_range(virt, virt + size);
 }
 
-static void __init __map_memblock(pgd_t *pgd, phys_addr_t start,
+static void __init __map_memblock(pgd_t *pgdp, phys_addr_t start,
 				  phys_addr_t end, pgprot_t prot, int flags)
 {
-	__create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start,
+	__create_pgd_mapping(pgdp, start, __phys_to_virt(start), end - start,
 			     prot, early_pgtable_alloc, flags);
 }
 
@@ -418,7 +425,7 @@
 			    PAGE_KERNEL_RO);
 }
 
-static void __init map_mem(pgd_t *pgd)
+static void __init map_mem(pgd_t *pgdp)
 {
 	phys_addr_t kernel_start = __pa_symbol(_text);
 	phys_addr_t kernel_end = __pa_symbol(__init_begin);
@@ -451,7 +458,7 @@
 		if (memblock_is_nomap(reg))
 			continue;
 
-		__map_memblock(pgd, start, end, PAGE_KERNEL, flags);
+		__map_memblock(pgdp, start, end, PAGE_KERNEL, flags);
 	}
 
 	/*
@@ -464,7 +471,7 @@
 	 * Note that contiguous mappings cannot be remapped in this way,
 	 * so we should avoid them here.
 	 */
-	__map_memblock(pgd, kernel_start, kernel_end,
+	__map_memblock(pgdp, kernel_start, kernel_end,
 		       PAGE_KERNEL, NO_CONT_MAPPINGS);
 	memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
 
@@ -475,7 +482,7 @@
 	 * through /sys/kernel/kexec_crash_size interface.
 	 */
 	if (crashk_res.end) {
-		__map_memblock(pgd, crashk_res.start, crashk_res.end + 1,
+		__map_memblock(pgdp, crashk_res.start, crashk_res.end + 1,
 			       PAGE_KERNEL,
 			       NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
 		memblock_clear_nomap(crashk_res.start,
@@ -499,7 +506,7 @@
 	debug_checkwx();
 }
 
-static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
+static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end,
 				      pgprot_t prot, struct vm_struct *vma,
 				      int flags, unsigned long vm_flags)
 {
@@ -509,7 +516,7 @@
 	BUG_ON(!PAGE_ALIGNED(pa_start));
 	BUG_ON(!PAGE_ALIGNED(size));
 
-	__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
+	__create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot,
 			     early_pgtable_alloc, flags);
 
 	if (!(vm_flags & VM_NO_GUARD))
@@ -562,7 +569,7 @@
 /*
  * Create fine-grained mappings for the kernel.
  */
-static void __init map_kernel(pgd_t *pgd)
+static void __init map_kernel(pgd_t *pgdp)
 {
 	static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext,
 				vmlinux_initdata, vmlinux_data;
@@ -578,24 +585,24 @@
 	 * Only rodata will be remapped with different permissions later on,
 	 * all other segments are allowed to use contiguous mappings.
 	 */
-	map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0,
+	map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0,
 			   VM_NO_GUARD);
-	map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL,
+	map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL,
 			   &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD);
-	map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot,
+	map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot,
 			   &vmlinux_inittext, 0, VM_NO_GUARD);
-	map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL,
+	map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL,
 			   &vmlinux_initdata, 0, VM_NO_GUARD);
-	map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
+	map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0);
 
-	if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) {
+	if (!READ_ONCE(pgd_val(*pgd_offset_raw(pgdp, FIXADDR_START)))) {
 		/*
 		 * The fixmap falls in a separate pgd to the kernel, and doesn't
 		 * live in the carveout for the swapper_pg_dir. We can simply
 		 * re-use the existing dir for the fixmap.
 		 */
-		set_pgd(pgd_offset_raw(pgd, FIXADDR_START),
-			*pgd_offset_k(FIXADDR_START));
+		set_pgd(pgd_offset_raw(pgdp, FIXADDR_START),
+			READ_ONCE(*pgd_offset_k(FIXADDR_START)));
 	} else if (CONFIG_PGTABLE_LEVELS > 3) {
 		/*
 		 * The fixmap shares its top level pgd entry with the kernel
@@ -604,14 +611,15 @@
 		 * entry instead.
 		 */
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
-		pud_populate(&init_mm, pud_set_fixmap_offset(pgd, FIXADDR_START),
+		pud_populate(&init_mm,
+			     pud_set_fixmap_offset(pgdp, FIXADDR_START),
 			     lm_alias(bm_pmd));
 		pud_clear_fixmap();
 	} else {
 		BUG();
 	}
 
-	kasan_copy_shadow(pgd);
+	kasan_copy_shadow(pgdp);
 }
 
 /*
@@ -621,10 +629,10 @@
 void __init paging_init(void)
 {
 	phys_addr_t pgd_phys = early_pgtable_alloc();
-	pgd_t *pgd = pgd_set_fixmap(pgd_phys);
+	pgd_t *pgdp = pgd_set_fixmap(pgd_phys);
 
-	map_kernel(pgd);
-	map_mem(pgd);
+	map_kernel(pgdp);
+	map_mem(pgdp);
 
 	/*
 	 * We want to reuse the original swapper_pg_dir so we don't have to
@@ -635,7 +643,7 @@
 	 * To do this we need to go via a temporary pgd.
 	 */
 	cpu_replace_ttbr1(__va(pgd_phys));
-	memcpy(swapper_pg_dir, pgd, PGD_SIZE);
+	memcpy(swapper_pg_dir, pgdp, PGD_SIZE);
 	cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
 
 	pgd_clear_fixmap();
@@ -655,37 +663,40 @@
  */
 int kern_addr_valid(unsigned long addr)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
+	pgd_t *pgdp;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
+	pte_t *ptep, pte;
 
 	if ((((long)addr) >> VA_BITS) != -1UL)
 		return 0;
 
-	pgd = pgd_offset_k(addr);
-	if (pgd_none(*pgd))
+	pgdp = pgd_offset_k(addr);
+	if (pgd_none(READ_ONCE(*pgdp)))
 		return 0;
 
-	pud = pud_offset(pgd, addr);
-	if (pud_none(*pud))
+	pudp = pud_offset(pgdp, addr);
+	pud = READ_ONCE(*pudp);
+	if (pud_none(pud))
 		return 0;
 
-	if (pud_sect(*pud))
-		return pfn_valid(pud_pfn(*pud));
+	if (pud_sect(pud))
+		return pfn_valid(pud_pfn(pud));
 
-	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	pmdp = pmd_offset(pudp, addr);
+	pmd = READ_ONCE(*pmdp);
+	if (pmd_none(pmd))
 		return 0;
 
-	if (pmd_sect(*pmd))
-		return pfn_valid(pmd_pfn(*pmd));
+	if (pmd_sect(pmd))
+		return pfn_valid(pmd_pfn(pmd));
 
-	pte = pte_offset_kernel(pmd, addr);
-	if (pte_none(*pte))
+	ptep = pte_offset_kernel(pmdp, addr);
+	pte = READ_ONCE(*ptep);
+	if (pte_none(pte))
 		return 0;
 
-	return pfn_valid(pte_pfn(*pte));
+	return pfn_valid(pte_pfn(pte));
 }
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 #if !ARM64_SWAPPER_USES_SECTION_MAPS
@@ -700,32 +711,32 @@
 {
 	unsigned long addr = start;
 	unsigned long next;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	pgd_t *pgdp;
+	pud_t *pudp;
+	pmd_t *pmdp;
 
 	do {
 		next = pmd_addr_end(addr, end);
 
-		pgd = vmemmap_pgd_populate(addr, node);
-		if (!pgd)
+		pgdp = vmemmap_pgd_populate(addr, node);
+		if (!pgdp)
 			return -ENOMEM;
 
-		pud = vmemmap_pud_populate(pgd, addr, node);
-		if (!pud)
+		pudp = vmemmap_pud_populate(pgdp, addr, node);
+		if (!pudp)
 			return -ENOMEM;
 
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
+		pmdp = pmd_offset(pudp, addr);
+		if (pmd_none(READ_ONCE(*pmdp))) {
 			void *p = NULL;
 
 			p = vmemmap_alloc_block_buf(PMD_SIZE, node);
 			if (!p)
 				return -ENOMEM;
 
-			pmd_set_huge(pmd, __pa(p), __pgprot(PROT_SECT_NORMAL));
+			pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
 		} else
-			vmemmap_verify((pte_t *)pmd, node, addr, next);
+			vmemmap_verify((pte_t *)pmdp, node, addr, next);
 	} while (addr = next, addr != end);
 
 	return 0;
@@ -739,20 +750,22 @@
 
 static inline pud_t * fixmap_pud(unsigned long addr)
 {
-	pgd_t *pgd = pgd_offset_k(addr);
+	pgd_t *pgdp = pgd_offset_k(addr);
+	pgd_t pgd = READ_ONCE(*pgdp);
 
-	BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd));
+	BUG_ON(pgd_none(pgd) || pgd_bad(pgd));
 
-	return pud_offset_kimg(pgd, addr);
+	return pud_offset_kimg(pgdp, addr);
 }
 
 static inline pmd_t * fixmap_pmd(unsigned long addr)
 {
-	pud_t *pud = fixmap_pud(addr);
+	pud_t *pudp = fixmap_pud(addr);
+	pud_t pud = READ_ONCE(*pudp);
 
-	BUG_ON(pud_none(*pud) || pud_bad(*pud));
+	BUG_ON(pud_none(pud) || pud_bad(pud));
 
-	return pmd_offset_kimg(pud, addr);
+	return pmd_offset_kimg(pudp, addr);
 }
 
 static inline pte_t * fixmap_pte(unsigned long addr)
@@ -768,30 +781,31 @@
  */
 void __init early_fixmap_init(void)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
+	pgd_t *pgdp, pgd;
+	pud_t *pudp;
+	pmd_t *pmdp;
 	unsigned long addr = FIXADDR_START;
 
-	pgd = pgd_offset_k(addr);
+	pgdp = pgd_offset_k(addr);
+	pgd = READ_ONCE(*pgdp);
 	if (CONFIG_PGTABLE_LEVELS > 3 &&
-	    !(pgd_none(*pgd) || pgd_page_paddr(*pgd) == __pa_symbol(bm_pud))) {
+	    !(pgd_none(pgd) || pgd_page_paddr(pgd) == __pa_symbol(bm_pud))) {
 		/*
 		 * We only end up here if the kernel mapping and the fixmap
 		 * share the top level pgd entry, which should only happen on
 		 * 16k/4 levels configurations.
 		 */
 		BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES));
-		pud = pud_offset_kimg(pgd, addr);
+		pudp = pud_offset_kimg(pgdp, addr);
 	} else {
-		if (pgd_none(*pgd))
-			__pgd_populate(pgd, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
-		pud = fixmap_pud(addr);
+		if (pgd_none(pgd))
+			__pgd_populate(pgdp, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
+		pudp = fixmap_pud(addr);
 	}
-	if (pud_none(*pud))
-		__pud_populate(pud, __pa_symbol(bm_pmd), PMD_TYPE_TABLE);
-	pmd = fixmap_pmd(addr);
-	__pmd_populate(pmd, __pa_symbol(bm_pte), PMD_TYPE_TABLE);
+	if (pud_none(READ_ONCE(*pudp)))
+		__pud_populate(pudp, __pa_symbol(bm_pmd), PMD_TYPE_TABLE);
+	pmdp = fixmap_pmd(addr);
+	__pmd_populate(pmdp, __pa_symbol(bm_pte), PMD_TYPE_TABLE);
 
 	/*
 	 * The boot-ioremap range spans multiple pmds, for which
@@ -800,11 +814,11 @@
 	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
 		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
 
-	if ((pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)))
-	     || pmd != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) {
+	if ((pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)))
+	     || pmdp != fixmap_pmd(fix_to_virt(FIX_BTMAP_END))) {
 		WARN_ON(1);
-		pr_warn("pmd %p != %p, %p\n",
-			pmd, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)),
+		pr_warn("pmdp %p != %p, %p\n",
+			pmdp, fixmap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)),
 			fixmap_pmd(fix_to_virt(FIX_BTMAP_END)));
 		pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
 			fix_to_virt(FIX_BTMAP_BEGIN));
@@ -824,16 +838,16 @@
 			       phys_addr_t phys, pgprot_t flags)
 {
 	unsigned long addr = __fix_to_virt(idx);
-	pte_t *pte;
+	pte_t *ptep;
 
 	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
 
-	pte = fixmap_pte(addr);
+	ptep = fixmap_pte(addr);
 
 	if (pgprot_val(flags)) {
-		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
+		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
 	} else {
-		pte_clear(&init_mm, addr, pte);
+		pte_clear(&init_mm, addr, ptep);
 		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
 	}
 }
@@ -915,36 +929,46 @@
 	return 1;
 }
 
-int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
+int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
 {
 	pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
 					pgprot_val(mk_sect_prot(prot)));
+
+	/* ioremap_page_range doesn't honour BBM */
+	if (pud_present(READ_ONCE(*pudp)))
+		return 0;
+
 	BUG_ON(phys & ~PUD_MASK);
-	set_pud(pud, pfn_pud(__phys_to_pfn(phys), sect_prot));
+	set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot));
 	return 1;
 }
 
-int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
+int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
 {
 	pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
 					pgprot_val(mk_sect_prot(prot)));
+
+	/* ioremap_page_range doesn't honour BBM */
+	if (pmd_present(READ_ONCE(*pmdp)))
+		return 0;
+
 	BUG_ON(phys & ~PMD_MASK);
-	set_pmd(pmd, pfn_pmd(__phys_to_pfn(phys), sect_prot));
+	set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot));
 	return 1;
 }
 
-int pud_clear_huge(pud_t *pud)
+int pud_clear_huge(pud_t *pudp)
 {
-	if (!pud_sect(*pud))
+	if (!pud_sect(READ_ONCE(*pudp)))
 		return 0;
-	pud_clear(pud);
+	pud_clear(pudp);
 	return 1;
 }
 
-int pmd_clear_huge(pmd_t *pmd)
+int pmd_clear_huge(pmd_t *pmdp)
 {
-	if (!pmd_sect(*pmd))
+	if (!pmd_sect(READ_ONCE(*pmdp)))
 		return 0;
-	pmd_clear(pmd);
+	pmd_clear(pmdp);
 	return 1;
 }
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index a682a0a..a563593 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -29,7 +29,7 @@
 			void *data)
 {
 	struct page_change_data *cdata = data;
-	pte_t pte = *ptep;
+	pte_t pte = READ_ONCE(*ptep);
 
 	pte = clear_pte_bit(pte, cdata->clear_mask);
 	pte = set_pte_bit(pte, cdata->set_mask);
@@ -156,30 +156,32 @@
  */
 bool kernel_page_present(struct page *page)
 {
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
+	pgd_t *pgdp;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
+	pte_t *ptep;
 	unsigned long addr = (unsigned long)page_address(page);
 
-	pgd = pgd_offset_k(addr);
-	if (pgd_none(*pgd))
+	pgdp = pgd_offset_k(addr);
+	if (pgd_none(READ_ONCE(*pgdp)))
 		return false;
 
-	pud = pud_offset(pgd, addr);
-	if (pud_none(*pud))
+	pudp = pud_offset(pgdp, addr);
+	pud = READ_ONCE(*pudp);
+	if (pud_none(pud))
 		return false;
-	if (pud_sect(*pud))
+	if (pud_sect(pud))
 		return true;
 
-	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	pmdp = pmd_offset(pudp, addr);
+	pmd = READ_ONCE(*pmdp);
+	if (pmd_none(pmd))
 		return false;
-	if (pmd_sect(*pmd))
+	if (pmd_sect(pmd))
 		return true;
 
-	pte = pte_offset_kernel(pmd, addr);
-	return pte_valid(*pte);
+	ptep = pte_offset_kernel(pmdp, addr);
+	return pte_valid(READ_ONCE(*ptep));
 }
 #endif /* CONFIG_HIBERNATION */
 #endif /* CONFIG_DEBUG_PAGEALLOC */
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 71baed7..c0af476 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -205,7 +205,8 @@
 	dc	cvac, cur_\()\type\()p		// Ensure any existing dirty
 	dmb	sy				// lines are written back before
 	ldr	\type, [cur_\()\type\()p]	// loading the entry
-	tbz	\type, #0, next_\()\type	// Skip invalid entries
+	tbz	\type, #0, skip_\()\type	// Skip invalid and
+	tbnz	\type, #11, skip_\()\type	// non-global entries
 	.endm
 
 	.macro __idmap_kpti_put_pgtable_ent_ng, type
@@ -265,8 +266,9 @@
 	add	end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8)
 do_pgd:	__idmap_kpti_get_pgtable_ent	pgd
 	tbnz	pgd, #1, walk_puds
-	__idmap_kpti_put_pgtable_ent_ng	pgd
 next_pgd:
+	__idmap_kpti_put_pgtable_ent_ng	pgd
+skip_pgd:
 	add	cur_pgdp, cur_pgdp, #8
 	cmp	cur_pgdp, end_pgdp
 	b.ne	do_pgd
@@ -294,8 +296,9 @@
 	add	end_pudp, cur_pudp, #(PTRS_PER_PUD * 8)
 do_pud:	__idmap_kpti_get_pgtable_ent	pud
 	tbnz	pud, #1, walk_pmds
-	__idmap_kpti_put_pgtable_ent_ng	pud
 next_pud:
+	__idmap_kpti_put_pgtable_ent_ng	pud
+skip_pud:
 	add	cur_pudp, cur_pudp, 8
 	cmp	cur_pudp, end_pudp
 	b.ne	do_pud
@@ -314,8 +317,9 @@
 	add	end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8)
 do_pmd:	__idmap_kpti_get_pgtable_ent	pmd
 	tbnz	pmd, #1, walk_ptes
-	__idmap_kpti_put_pgtable_ent_ng	pmd
 next_pmd:
+	__idmap_kpti_put_pgtable_ent_ng	pmd
+skip_pmd:
 	add	cur_pmdp, cur_pmdp, #8
 	cmp	cur_pmdp, end_pmdp
 	b.ne	do_pmd
@@ -333,7 +337,7 @@
 	add	end_ptep, cur_ptep, #(PTRS_PER_PTE * 8)
 do_pte:	__idmap_kpti_get_pgtable_ent	pte
 	__idmap_kpti_put_pgtable_ent_ng	pte
-next_pte:
+skip_pte:
 	add	cur_ptep, cur_ptep, #8
 	cmp	cur_ptep, end_ptep
 	b.ne	do_pte
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 1d4f1da..a933504 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -250,8 +250,9 @@
 	off = offsetof(struct bpf_array, map.max_entries);
 	emit_a64_mov_i64(tmp, off, ctx);
 	emit(A64_LDR32(tmp, r2, tmp), ctx);
+	emit(A64_MOV(0, r3, r3), ctx);
 	emit(A64_CMP(0, r3, tmp), ctx);
-	emit(A64_B_(A64_COND_GE, jmp_offset), ctx);
+	emit(A64_B_(A64_COND_CS, jmp_offset), ctx);
 
 	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *     goto out;
@@ -259,7 +260,7 @@
 	 */
 	emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
 	emit(A64_CMP(1, tcc, tmp), ctx);
-	emit(A64_B_(A64_COND_GT, jmp_offset), ctx);
+	emit(A64_B_(A64_COND_HI, jmp_offset), ctx);
 	emit(A64_ADD_I(1, tcc, tcc, 1), ctx);
 
 	/* prog = array->ptrs[index];
diff --git a/arch/cris/include/arch-v10/arch/bug.h b/arch/cris/include/arch-v10/arch/bug.h
index 905afea..06da9d4 100644
--- a/arch/cris/include/arch-v10/arch/bug.h
+++ b/arch/cris/include/arch-v10/arch/bug.h
@@ -44,18 +44,25 @@
  * not be used like this with newer versions of gcc.
  */
 #define BUG()								\
+do {									\
 	__asm__ __volatile__ ("clear.d [" __stringify(BUG_MAGIC) "]\n\t"\
 			      "movu.w " __stringify(__LINE__) ",$r0\n\t"\
 			      "jump 0f\n\t"				\
 			      ".section .rodata\n"			\
 			      "0:\t.string \"" __FILE__ "\"\n\t"	\
-			      ".previous")
+			      ".previous");				\
+	unreachable();							\
+} while (0)
 #endif
 
 #else
 
 /* This just causes an oops. */
-#define BUG() (*(int *)0 = 0)
+#define BUG()								\
+do {									\
+	barrier_before_unreachable();					\
+	__builtin_trap();						\
+} while (0)
 
 #endif
 
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 762eeb0f..2524fb6 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -66,38 +66,35 @@
 ATOMIC_OPS(sub, -)
 
 #ifdef __OPTIMIZE__
-#define __ia64_atomic_const(i)	__builtin_constant_p(i) ?		\
+#define __ia64_atomic_const(i)						\
+	static const int __ia64_atomic_p = __builtin_constant_p(i) ?	\
 		((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 ||	\
-		 (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0
-
-#define atomic_add_return(i, v)						\
-({									\
-	int __i = (i);							\
-	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
-	__ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) :	\
-				ia64_atomic_add(__i, v);		\
-})
-
-#define atomic_sub_return(i, v)						\
-({									\
-	int __i = (i);							\
-	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
-	__ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) :	\
-				ia64_atomic_sub(__i, v);		\
-})
+		 (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0;\
+	__ia64_atomic_p
 #else
-#define atomic_add_return(i, v)	ia64_atomic_add(i, v)
-#define atomic_sub_return(i, v)	ia64_atomic_sub(i, v)
+#define __ia64_atomic_const(i)	0
 #endif
 
+#define atomic_add_return(i,v)						\
+({									\
+	int __ia64_aar_i = (i);						\
+	__ia64_atomic_const(i)						\
+		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
+		: ia64_atomic_add(__ia64_aar_i, v);			\
+})
+
+#define atomic_sub_return(i,v)						\
+({									\
+	int __ia64_asr_i = (i);						\
+	__ia64_atomic_const(i)						\
+		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
+		: ia64_atomic_sub(__ia64_asr_i, v);			\
+})
+
 #define atomic_fetch_add(i,v)						\
 ({									\
 	int __ia64_aar_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
 		: ia64_atomic_fetch_add(__ia64_aar_i, v);		\
 })
@@ -105,11 +102,7 @@
 #define atomic_fetch_sub(i,v)						\
 ({									\
 	int __ia64_asr_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
 		: ia64_atomic_fetch_sub(__ia64_asr_i, v);		\
 })
@@ -170,11 +163,7 @@
 #define atomic64_add_return(i,v)					\
 ({									\
 	long __ia64_aar_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+	__ia64_atomic_const(i)						\
 		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
 		: ia64_atomic64_add(__ia64_aar_i, v);			\
 })
@@ -182,11 +171,7 @@
 #define atomic64_sub_return(i,v)					\
 ({									\
 	long __ia64_asr_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+	__ia64_atomic_const(i)						\
 		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
 		: ia64_atomic64_sub(__ia64_asr_i, v);			\
 })
@@ -194,11 +179,7 @@
 #define atomic64_fetch_add(i,v)						\
 ({									\
 	long __ia64_aar_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
 		: ia64_atomic64_fetch_add(__ia64_aar_i, v);		\
 })
@@ -206,11 +187,7 @@
 #define atomic64_fetch_sub(i,v)						\
 ({									\
 	long __ia64_asr_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
 		: ia64_atomic64_fetch_sub(__ia64_asr_i, v);		\
 })
diff --git a/arch/ia64/include/asm/bug.h b/arch/ia64/include/asm/bug.h
index bd3eeb8..66b37a5 100644
--- a/arch/ia64/include/asm/bug.h
+++ b/arch/ia64/include/asm/bug.h
@@ -4,7 +4,11 @@
 
 #ifdef CONFIG_BUG
 #define ia64_abort()	__builtin_trap()
-#define BUG() do { printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); ia64_abort(); } while (0)
+#define BUG() do {						\
+	printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__);	\
+	barrier_before_unreachable();				\
+	ia64_abort();						\
+} while (0)
 
 /* should this BUG be made generic? */
 #define HAVE_ARCH_BUG
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 0b4c65a..498f3da 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -41,7 +41,6 @@
 obj-y				+= esi_stub.o	# must be in kernel proper
 endif
 obj-$(CONFIG_INTEL_IOMMU)	+= pci-dma.o
-obj-$(CONFIG_SWIOTLB)		+= pci-swiotlb.o
 
 obj-$(CONFIG_BINFMT_ELF)	+= elfcore.o
 
diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c
index 85bba43..8b5b8e6b 100644
--- a/arch/ia64/kernel/err_inject.c
+++ b/arch/ia64/kernel/err_inject.c
@@ -117,7 +117,7 @@
 
 #ifdef ERR_INJ_DEBUG
 	printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]);
-	printk(KERN_DEBUG "capapbilities=%lx,\n", capabilities[cpu]);
+	printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]);
 	printk(KERN_DEBUG "resources=%lx\n", resources[cpu]);
 #endif
 	return size;
@@ -142,7 +142,7 @@
 	u64 virt_addr=simple_strtoull(buf, NULL, 16);
 	int ret;
 
-	ret = get_user_pages(virt_addr, 1, FOLL_WRITE, NULL, NULL);
+	ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL);
 	if (ret<=0) {
 #ifdef ERR_INJ_DEBUG
 		printk("Virtual address %lx is not existing.\n",virt_addr);
diff --git a/arch/ia64/scripts/unwcheck.py b/arch/ia64/scripts/unwcheck.py
index 89f3a148..c55276e 100644
--- a/arch/ia64/scripts/unwcheck.py
+++ b/arch/ia64/scripts/unwcheck.py
@@ -16,7 +16,7 @@
 import sys
 
 if len(sys.argv) != 2:
-    print "Usage: %s FILE" % sys.argv[0]
+    print("Usage: %s FILE" % sys.argv[0])
     sys.exit(2)
 
 readelf = os.getenv("READELF", "readelf")
@@ -29,7 +29,7 @@
         global num_errors
         num_errors += 1
         if not func: func = "[%#x-%#x]" % (start, end)
-        print "ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum)
+        print("ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum))
     return
 
 num_funcs = 0
@@ -43,23 +43,23 @@
         check_func(func, slots, rlen_sum)
 
         func  = m.group(1)
-        start = long(m.group(2), 16)
-        end   = long(m.group(3), 16)
+        start = int(m.group(2), 16)
+        end   = int(m.group(3), 16)
         slots = 3 * (end - start) / 16
-        rlen_sum = 0L
+        rlen_sum = 0
         num_funcs += 1
     else:
         m = rlen_pattern.match(line)
         if m:
-            rlen_sum += long(m.group(1))
+            rlen_sum += int(m.group(1))
 check_func(func, slots, rlen_sum)
 
 if num_errors == 0:
-    print "No errors detected in %u functions." % num_funcs
+    print("No errors detected in %u functions." % num_funcs)
 else:
     if num_errors > 1:
         err="errors"
     else:
         err="error"
-    print "%u %s detected in %u functions." % (num_errors, err, num_funcs)
+    print("%u %s detected in %u functions." % (num_errors, err, num_funcs))
     sys.exit(1)
diff --git a/arch/m68k/include/asm/bug.h b/arch/m68k/include/asm/bug.h
index b7e2bf1..275dca1 100644
--- a/arch/m68k/include/asm/bug.h
+++ b/arch/m68k/include/asm/bug.h
@@ -8,16 +8,19 @@
 #ifndef CONFIG_SUN3
 #define BUG() do { \
 	pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
+	barrier_before_unreachable(); \
 	__builtin_trap(); \
 } while (0)
 #else
 #define BUG() do { \
 	pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
+	barrier_before_unreachable(); \
 	panic("BUG!"); \
 } while (0)
 #endif
 #else
 #define BUG() do { \
+	barrier_before_unreachable(); \
 	__builtin_trap(); \
 } while (0)
 #endif
diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index 1bd5c4f..c22da16 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -126,6 +126,7 @@
 
 quiet_cmd_cpp_its_S = ITS     $@
       cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \
+			-D__ASSEMBLY__ \
 		        -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \
 			-DVMLINUX_BINARY="\"$(3)\"" \
 			-DVMLINUX_COMPRESSION="\"$(2)\"" \
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index 946681d..9a0fa66 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -86,7 +86,6 @@
 	compat_off_t	l_len;
 	s32		l_sysid;
 	compat_pid_t	l_pid;
-	short		__unused;
 	s32		pad[4];
 };
 
diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c
index 19c88d7..fcf9af4 100644
--- a/arch/mips/kernel/mips-cpc.c
+++ b/arch/mips/kernel/mips-cpc.c
@@ -10,6 +10,8 @@
 
 #include <linux/errno.h>
 #include <linux/percpu.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/spinlock.h>
 
 #include <asm/mips-cps.h>
@@ -22,6 +24,17 @@
 
 phys_addr_t __weak mips_cpc_default_phys_base(void)
 {
+	struct device_node *cpc_node;
+	struct resource res;
+	int err;
+
+	cpc_node = of_find_compatible_node(of_root, NULL, "mti,mips-cpc");
+	if (cpc_node) {
+		err = of_address_to_resource(cpc_node, 0, &res);
+		if (!err)
+			return res.start;
+	}
+
 	return 0;
 }
 
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 85bc601..5f8b0a9 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -375,6 +375,7 @@
 	unsigned long reserved_end;
 	unsigned long mapstart = ~0UL;
 	unsigned long bootmap_size;
+	phys_addr_t ramstart = (phys_addr_t)ULLONG_MAX;
 	bool bootmap_valid = false;
 	int i;
 
@@ -395,7 +396,8 @@
 	max_low_pfn = 0;
 
 	/*
-	 * Find the highest page frame number we have available.
+	 * Find the highest page frame number we have available
+	 * and the lowest used RAM address
 	 */
 	for (i = 0; i < boot_mem_map.nr_map; i++) {
 		unsigned long start, end;
@@ -407,6 +409,8 @@
 		end = PFN_DOWN(boot_mem_map.map[i].addr
 				+ boot_mem_map.map[i].size);
 
+		ramstart = min(ramstart, boot_mem_map.map[i].addr);
+
 #ifndef CONFIG_HIGHMEM
 		/*
 		 * Skip highmem here so we get an accurate max_low_pfn if low
@@ -436,6 +440,13 @@
 		mapstart = max(reserved_end, start);
 	}
 
+	/*
+	 * Reserve any memory between the start of RAM and PHYS_OFFSET
+	 */
+	if (ramstart > PHYS_OFFSET)
+		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) {
@@ -664,9 +675,6 @@
 
 	add_memory_region(start, size, BOOT_MEM_RAM);
 
-	if (start && start > PHYS_OFFSET)
-		add_memory_region(PHYS_OFFSET, start - PHYS_OFFSET,
-				BOOT_MEM_RESERVED);
 	return 0;
 }
 early_param("mem", early_parse_mem);
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 87dcac2..9d41732 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -572,7 +572,7 @@
 	 */
 }
 
-void __init bmips_cpu_setup(void)
+void bmips_cpu_setup(void)
 {
 	void __iomem __maybe_unused *cbr = BMIPS_GET_CBR();
 	u32 __maybe_unused cfg;
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index 3742508..bd5ce31 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -26,6 +26,7 @@
 void flush_kernel_icache_range_asm(unsigned long, unsigned long);
 void flush_user_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_range_asm(unsigned long, unsigned long);
+void purge_kernel_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_page_asm(void *);
 void flush_kernel_icache_page(void *);
 
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 0e6ab6e..2dbe558 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -316,6 +316,8 @@
 #define parisc_requires_coherency()	(0)
 #endif
 
+extern int running_on_qemu;
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __ASM_PARISC_PROCESSOR_H */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 19c0c14..7908977 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -465,10 +465,10 @@
 int __flush_tlb_range(unsigned long sid, unsigned long start,
 		      unsigned long end)
 {
-	unsigned long flags, size;
+	unsigned long flags;
 
-	size = (end - start);
-	if (size >= parisc_tlb_flush_threshold) {
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    end - start >= parisc_tlb_flush_threshold) {
 		flush_tlb_all();
 		return 1;
 	}
@@ -539,13 +539,11 @@
 	struct vm_area_struct *vma;
 	pgd_t *pgd;
 
-	/* Flush the TLB to avoid speculation if coherency is required. */
-	if (parisc_requires_coherency())
-		flush_tlb_all();
-
 	/* Flushing the whole cache on each cpu takes forever on
 	   rp3440, etc.  So, avoid it if the mm isn't too big.  */
-	if (mm_total_size(mm) >= parisc_cache_flush_threshold) {
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    mm_total_size(mm) >= parisc_cache_flush_threshold) {
+		flush_tlb_all();
 		flush_cache_all();
 		return;
 	}
@@ -553,9 +551,9 @@
 	if (mm->context == mfsp(3)) {
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			flush_user_dcache_range_asm(vma->vm_start, vma->vm_end);
-			if ((vma->vm_flags & VM_EXEC) == 0)
-				continue;
-			flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+			if (vma->vm_flags & VM_EXEC)
+				flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
+			flush_tlb_range(vma, vma->vm_start, vma->vm_end);
 		}
 		return;
 	}
@@ -581,14 +579,9 @@
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 {
-	BUG_ON(!vma->vm_mm->context);
-
-	/* Flush the TLB to avoid speculation if coherency is required. */
-	if (parisc_requires_coherency())
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    end - start >= parisc_cache_flush_threshold) {
 		flush_tlb_range(vma, start, end);
-
-	if ((end - start) >= parisc_cache_flush_threshold
-	    || vma->vm_mm->context != mfsp(3)) {
 		flush_cache_all();
 		return;
 	}
@@ -596,6 +589,7 @@
 	flush_user_dcache_range_asm(start, end);
 	if (vma->vm_flags & VM_EXEC)
 		flush_user_icache_range_asm(start, end);
+	flush_tlb_range(vma, start, end);
 }
 
 void
@@ -604,8 +598,7 @@
 	BUG_ON(!vma->vm_mm->context);
 
 	if (pfn_valid(pfn)) {
-		if (parisc_requires_coherency())
-			flush_tlb_page(vma, vmaddr);
+		flush_tlb_page(vma, vmaddr);
 		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 	}
 }
@@ -613,21 +606,33 @@
 void flush_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
+	unsigned long end = start + size;
 
-	if ((unsigned long)size > parisc_cache_flush_threshold)
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    (unsigned long)size >= parisc_cache_flush_threshold) {
+		flush_tlb_kernel_range(start, end);
 		flush_data_cache();
-	else
-		flush_kernel_dcache_range_asm(start, start + size);
+		return;
+	}
+
+	flush_kernel_dcache_range_asm(start, end);
+	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(flush_kernel_vmap_range);
 
 void invalidate_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
+	unsigned long end = start + size;
 
-	if ((unsigned long)size > parisc_cache_flush_threshold)
+	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	    (unsigned long)size >= parisc_cache_flush_threshold) {
+		flush_tlb_kernel_range(start, end);
 		flush_data_cache();
-	else
-		flush_kernel_dcache_range_asm(start, start + size);
+		return;
+	}
+
+	purge_kernel_dcache_range_asm(start, end);
+	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index bbbe360..fbb4e43 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -138,6 +138,16 @@
 	std		%dp,0x18(%r10)
 #endif
 
+#ifdef CONFIG_64BIT
+	/* Get PDCE_PROC for monarch CPU. */
+#define MEM_PDC_LO 0x388
+#define MEM_PDC_HI 0x35C
+	ldw             MEM_PDC_LO(%r0),%r3
+	ldw             MEM_PDC_HI(%r0),%r10
+	depd            %r10, 31, 32, %r3        /* move to upper word */
+#endif
+
+
 #ifdef CONFIG_SMP
 	/* Set the smp rendezvous address into page zero.
 	** It would be safer to do this in init_smp_config() but
@@ -196,12 +206,6 @@
         ** Someday, palo might not do this for the Monarch either.
         */
 2:
-#define MEM_PDC_LO 0x388
-#define MEM_PDC_HI 0x35C
-	ldw             MEM_PDC_LO(%r0),%r3
-	ldw             MEM_PDC_HI(%r0),%r6
-	depd            %r6, 31, 32, %r3        /* move to upper word */
-
 	mfctl		%cr30,%r6		/* PCX-W2 firmware bug */
 
 	ldo             PDC_PSW(%r0),%arg0              /* 21 */
@@ -268,6 +272,8 @@
 aligned_rfi:
 	pcxt_ssm_bug
 
+	copy		%r3, %arg0	/* PDCE_PROC for smp_callin() */
+
 	rsm		PSW_SM_QUIET,%r0	/* off troublesome PSW bits */
 	/* Don't need NOPs, have 8 compliant insn before rfi */
 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 2d40c4f..67b0f75 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -1110,6 +1110,28 @@
 	.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
+	ANDCM		%r26, %r21, %r26
+
+1:      cmpb,COND(<<),n	%r26, %r25,1b
+	pdc,m		%r23(%r26)
+
+	sync
+	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
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 30c28ab..4065b5e 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -292,10 +292,15 @@
  * Slaves start using C here. Indirectly called from smp_slave_stext.
  * Do what start_kernel() and main() do for boot strap processor (aka monarch)
  */
-void __init smp_callin(void)
+void __init smp_callin(unsigned long pdce_proc)
 {
 	int slave_id = cpu_now_booting;
 
+#ifdef CONFIG_64BIT
+	WARN_ON(((unsigned long)(PAGE0->mem_pdc_hi) << 32
+			| PAGE0->mem_pdc) != pdce_proc);
+#endif
+
 	smp_cpu_init(slave_id);
 	preempt_disable();
 
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 4b8fd6d..f7e6845 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -76,10 +76,10 @@
 	next_tick = cpuinfo->it_value;
 
 	/* Calculate how many ticks have elapsed. */
+	now = mfctl(16);
 	do {
 		++ticks_elapsed;
 		next_tick += cpt;
-		now = mfctl(16);
 	} while (next_tick - now > cpt);
 
 	/* Store (in CR16 cycles) up to when we are accounting right now. */
@@ -103,16 +103,17 @@
 	 * if one or the other wrapped. If "now" is "bigger" we'll end up
 	 * with a very large unsigned number.
 	 */
-	while (next_tick - mfctl(16) > cpt)
+	now = mfctl(16);
+	while (next_tick - now > cpt)
 		next_tick += cpt;
 
 	/* Program the IT when to deliver the next interrupt.
 	 * Only bottom 32-bits of next_tick are writable in CR16!
 	 * Timer interrupt will be delivered at least a few hundred cycles
-	 * after the IT fires, so if we are too close (<= 500 cycles) to the
+	 * after the IT fires, so if we are too close (<= 8000 cycles) to the
 	 * next cycle, simply skip it.
 	 */
-	if (next_tick - mfctl(16) <= 500)
+	if (next_tick - now <= 8000)
 		next_tick += cpt;
 	mtctl(next_tick, 16);
 
@@ -248,7 +249,7 @@
 	 * different sockets, so mark them unstable and lower rating on
 	 * multi-socket SMP systems.
 	 */
-	if (num_online_cpus() > 1) {
+	if (num_online_cpus() > 1 && !running_on_qemu) {
 		int cpu;
 		unsigned long cpu0_loc;
 		cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 48f4139..cab32ee 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -629,7 +629,12 @@
 #endif
 
 	mem_init_print_info(NULL);
-#ifdef CONFIG_DEBUG_KERNEL /* double-sanity-check paranoia */
+
+#if 0
+	/*
+	 * Do not expose the virtual kernel memory layout to userspace.
+	 * But keep code for debugging purposes.
+	 */
 	printk("virtual kernel memory layout:\n"
 	       "    vmalloc : 0x%px - 0x%px   (%4ld MB)\n"
 	       "    memory  : 0x%px - 0x%px   (%4ld MB)\n"
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 30a155c..c615abd 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -16,6 +16,7 @@
 #define PGD_INDEX_SIZE	(32 - PGDIR_SHIFT)
 
 #define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+#define PUD_CACHE_INDEX	PUD_INDEX_SIZE
 
 #ifndef __ASSEMBLY__
 #define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 949d691..67c5475 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -63,7 +63,8 @@
  * keeping the prototype consistent across the two formats.
  */
 static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
-			unsigned int subpg_index, unsigned long hidx)
+					 unsigned int subpg_index, unsigned long hidx,
+					 int offset)
 {
 	return (hidx << H_PAGE_F_GIX_SHIFT) &
 		(H_PAGE_F_SECOND | H_PAGE_F_GIX);
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 338b7da..3bcf269 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -45,7 +45,7 @@
  * generic accessors and iterators here
  */
 #define __real_pte __real_pte
-static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset)
 {
 	real_pte_t rpte;
 	unsigned long *hidxp;
@@ -59,7 +59,7 @@
 	 */
 	smp_rmb();
 
-	hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+	hidxp = (unsigned long *)(ptep + offset);
 	rpte.hidx = *hidxp;
 	return rpte;
 }
@@ -86,9 +86,10 @@
  * expected to modify the PTE bits accordingly and commit the PTE to memory.
  */
 static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
-		unsigned int subpg_index, unsigned long hidx)
+					 unsigned int subpg_index,
+					 unsigned long hidx, int offset)
 {
-	unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+	unsigned long *hidxp = (unsigned long *)(ptep + offset);
 
 	rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index);
 	*hidxp = rpte.hidx  | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index);
@@ -140,13 +141,18 @@
 }
 
 #define H_PTE_TABLE_SIZE	PTE_FRAG_SIZE
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined (CONFIG_HUGETLB_PAGE)
 #define H_PMD_TABLE_SIZE	((sizeof(pmd_t) << PMD_INDEX_SIZE) + \
 				 (sizeof(unsigned long) << PMD_INDEX_SIZE))
 #else
 #define H_PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
 #endif
+#ifdef CONFIG_HUGETLB_PAGE
+#define H_PUD_TABLE_SIZE	((sizeof(pud_t) << PUD_INDEX_SIZE) +	\
+				 (sizeof(unsigned long) << PUD_INDEX_SIZE))
+#else
 #define H_PUD_TABLE_SIZE	(sizeof(pud_t) << PUD_INDEX_SIZE)
+#endif
 #define H_PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 0920eff..935adcd 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -23,7 +23,8 @@
 				 H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT)
 #define H_PGTABLE_RANGE		(ASM_CONST(1) << H_PGTABLE_EADDR_SIZE)
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) &&  defined(CONFIG_PPC_64K_PAGES)
+#if (defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)) && \
+	defined(CONFIG_PPC_64K_PAGES)
 /*
  * only with hash 64k we need to use the second half of pmd page table
  * to store pointer to deposited pgtable_t
@@ -33,6 +34,16 @@
 #define H_PMD_CACHE_INDEX	H_PMD_INDEX_SIZE
 #endif
 /*
+ * We store the slot details in the second half of page table.
+ * Increase the pud level table so that hugetlb ptes can be stored
+ * at pud level.
+ */
+#if defined(CONFIG_HUGETLB_PAGE) &&  defined(CONFIG_PPC_64K_PAGES)
+#define H_PUD_CACHE_INDEX	(H_PUD_INDEX_SIZE + 1)
+#else
+#define H_PUD_CACHE_INDEX	(H_PUD_INDEX_SIZE)
+#endif
+/*
  * Define the address range of the kernel non-linear virtual area
  */
 #define H_KERN_VIRT_START ASM_CONST(0xD000000000000000)
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 1fcfa42..4746bc6 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -73,10 +73,16 @@
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
+	pgd_t *pgd;
+
 	if (radix_enabled())
 		return radix__pgd_alloc(mm);
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
-		pgtable_gfp_flags(mm, GFP_KERNEL));
+
+	pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+			       pgtable_gfp_flags(mm, GFP_KERNEL));
+	memset(pgd, 0, PGD_TABLE_SIZE);
+
+	return pgd;
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
@@ -93,13 +99,13 @@
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
+	return kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX),
 		pgtable_gfp_flags(mm, GFP_KERNEL));
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
-	kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud);
+	kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud);
 }
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
@@ -115,7 +121,7 @@
 	 * ahead and flush the page walk cache
 	 */
 	flush_tlb_pgtable(tlb, address);
-        pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE);
+	pgtable_free_tlb(tlb, pud, PUD_CACHE_INDEX);
 }
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 5101772..a6b9f1d 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -232,11 +232,13 @@
 extern unsigned long __pud_index_size;
 extern unsigned long __pgd_index_size;
 extern unsigned long __pmd_cache_index;
+extern unsigned long __pud_cache_index;
 #define PTE_INDEX_SIZE  __pte_index_size
 #define PMD_INDEX_SIZE  __pmd_index_size
 #define PUD_INDEX_SIZE  __pud_index_size
 #define PGD_INDEX_SIZE  __pgd_index_size
 #define PMD_CACHE_INDEX __pmd_cache_index
+#define PUD_CACHE_INDEX __pud_cache_index
 /*
  * Because of use of pte fragments and THP, size of page table
  * are not always derived out of index size above.
@@ -348,7 +350,7 @@
  */
 #ifndef __real_pte
 
-#define __real_pte(e,p)		((real_pte_t){(e)})
+#define __real_pte(e, p, o)		((real_pte_t){(e)})
 #define __rpte_to_pte(r)	((r).pte)
 #define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)
 
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 176dfb7..471b227 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -645,7 +645,7 @@
 					  EXC_HV, SOFTEN_TEST_HV, bitmask)
 
 #define MASKABLE_RELON_EXCEPTION_HV_OOL(vec, label, bitmask)		\
-	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec, bitmask);\
+	MASKABLE_EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_TEST_HV, vec, bitmask);\
 	EXCEPTION_RELON_PROLOG_PSERIES_1(label, EXC_HV)
 
 /*
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 511acfd..535add3 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -52,7 +52,7 @@
 #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
 #define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
 #define FW_FEATURE_DRMEM_V2	ASM_CONST(0x0000000400000000)
-#define FW_FEATURE_DRC_INFO	ASM_CONST(0x0000000400000000)
+#define FW_FEATURE_DRC_INFO	ASM_CONST(0x0000000800000000)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 88e5e8f..855e17d 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -30,6 +30,16 @@
 #define PACA_IRQ_PMI		0x40
 
 /*
+ * Some soft-masked interrupts must be hard masked until they are replayed
+ * (e.g., because the soft-masked handler does not clear the exception).
+ */
+#ifdef CONFIG_PPC_BOOK3S
+#define PACA_IRQ_MUST_HARD_MASK	(PACA_IRQ_EE|PACA_IRQ_PMI)
+#else
+#define PACA_IRQ_MUST_HARD_MASK	(PACA_IRQ_EE)
+#endif
+
+/*
  * flags for paca->irq_soft_mask
  */
 #define IRQS_ENABLED		0
@@ -244,7 +254,7 @@
 static inline void may_hard_irq_enable(void)
 {
 	get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS;
-	if (!(get_paca()->irq_happened & PACA_IRQ_EE))
+	if (!(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK))
 		__hard_irq_enable();
 }
 
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 9dcbfa6..d8b1e8e 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -140,6 +140,12 @@
 	return false;
 }
 
+static inline void crash_ipi_callback(struct pt_regs *regs) { }
+
+static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
+{
+}
+
 #endif /* CONFIG_KEXEC_CORE */
 #endif /* ! __ASSEMBLY__ */
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 504a3c36..03bbd11 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -24,6 +24,7 @@
 #define PGD_INDEX_SIZE	(32 - PGDIR_SHIFT)
 
 #define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+#define PUD_CACHE_INDEX	PUD_INDEX_SIZE
 
 #ifndef __ASSEMBLY__
 #define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index abddf58..5c5f75d 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -27,6 +27,7 @@
 #else
 #define PMD_CACHE_INDEX	PMD_INDEX_SIZE
 #endif
+#define PUD_CACHE_INDEX PUD_INDEX_SIZE
 
 /*
  * Define the address range of the kernel non-linear virtual area
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 88187c2..9f42164 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -44,6 +44,11 @@
 extern void sysfs_remove_device_from_node(struct device *dev, int nid);
 extern int numa_update_cpu_topology(bool cpus_locked);
 
+static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node)
+{
+	numa_cpu_lookup_table[cpu] = node;
+}
+
 static inline int early_cpu_to_node(int cpu)
 {
 	int nid;
@@ -76,12 +81,16 @@
 {
 	return 0;
 }
+
+static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {}
+
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
 extern int start_topology_update(void);
 extern int stop_topology_update(void);
 extern int prrn_is_enabled(void);
+extern int find_and_online_cpu_nid(int cpu);
 #else
 static inline int start_topology_update(void)
 {
@@ -95,6 +104,10 @@
 {
 	return 0;
 }
+static inline int find_and_online_cpu_nid(int cpu)
+{
+	return 0;
+}
 #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
 
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES)
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index beea218..0c0b66f 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -384,7 +384,8 @@
 	eeh_pcid_put(dev);
 	pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED);
 #ifdef CONFIG_PCI_IOV
-	eeh_ops->notify_resume(eeh_dev_to_pdn(edev));
+	if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev))
+		eeh_ops->notify_resume(eeh_dev_to_pdn(edev));
 #endif
 	return NULL;
 }
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index ee832d34..9b6e653 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -943,6 +943,8 @@
 /*
  * An interrupt came in while soft-disabled; We mark paca->irq_happened
  * accordingly and if the interrupt is level sensitive, we hard disable
+ * hard disable (full_mask) corresponds to PACA_IRQ_MUST_HARD_MASK, so
+ * keep these in synch.
  */
 
 .macro masked_interrupt_book3e paca_irq full_mask
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 243d072..3ac87e5 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1426,7 +1426,7 @@
  *   triggered and won't automatically refire.
  * - If it was a HMI we return immediately since we handled it in realmode
  *   and it won't refire.
- * - else we hard disable and return.
+ * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return.
  * This is called with r10 containing the value to OR to the paca field.
  */
 #define MASKED_INTERRUPT(_H)				\
@@ -1441,8 +1441,8 @@
 	ori	r10,r10,0xffff;				\
 	mtspr	SPRN_DEC,r10;				\
 	b	MASKED_DEC_HANDLER_LABEL;		\
-1:	andi.	r10,r10,(PACA_IRQ_DBELL|PACA_IRQ_HMI);	\
-	bne	2f;					\
+1:	andi.	r10,r10,PACA_IRQ_MUST_HARD_MASK;	\
+	beq	2f;					\
 	mfspr	r10,SPRN_##_H##SRR1;			\
 	xori	r10,r10,MSR_EE; /* clear MSR_EE */	\
 	mtspr	SPRN_##_H##SRR1,r10;			\
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index adf044d..d22c41c 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -874,7 +874,7 @@
 		.mmu = 0,
 		.hash_ext = 0,
 		.radix_ext = 0,
-		.byte22 = OV5_FEAT(OV5_DRC_INFO),
+		.byte22 = 0,
 	},
 
 	/* option vector 6: IBM PAPR hints */
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 5a8bfee..04d0bbd 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -788,7 +788,8 @@
 	if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
 		device_create_file(s, &dev_attr_pir);
 
-	if (cpu_has_feature(CPU_FTR_ARCH_206))
+	if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+		!firmware_has_feature(FW_FEATURE_LPAR))
 		device_create_file(s, &dev_attr_tscr);
 #endif /* CONFIG_PPC64 */
 
@@ -873,7 +874,8 @@
 	if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
 		device_remove_file(s, &dev_attr_pir);
 
-	if (cpu_has_feature(CPU_FTR_ARCH_206))
+	if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+		!firmware_has_feature(FW_FEATURE_LPAR))
 		device_remove_file(s, &dev_attr_tscr);
 #endif /* CONFIG_PPC64 */
 
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index f0f5cd4..f9818d7 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -188,7 +188,7 @@
 	if (!qpage) {
 		pr_err("Failed to allocate queue %d for VCPU %d\n",
 		       prio, xc->server_num);
-		return -ENOMEM;;
+		return -ENOMEM;
 	}
 	memset(qpage, 0, 1 << xive->q_order);
 
diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
index 1604110..3f18036 100644
--- a/arch/powerpc/mm/drmem.c
+++ b/arch/powerpc/mm/drmem.c
@@ -98,7 +98,7 @@
 	dr_cell->base_addr = cpu_to_be64(lmb->base_addr);
 	dr_cell->drc_index = cpu_to_be32(lmb->drc_index);
 	dr_cell->aa_index = cpu_to_be32(lmb->aa_index);
-	dr_cell->flags = cpu_to_be32(lmb->flags);
+	dr_cell->flags = cpu_to_be32(drmem_lmb_flags(lmb));
 }
 
 static int drmem_update_dt_v2(struct device_node *memory,
@@ -121,7 +121,7 @@
 		}
 
 		if (prev_lmb->aa_index != lmb->aa_index ||
-		    prev_lmb->flags != lmb->flags)
+		    drmem_lmb_flags(prev_lmb) != drmem_lmb_flags(lmb))
 			lmb_sets++;
 
 		prev_lmb = lmb;
@@ -150,7 +150,7 @@
 		}
 
 		if (prev_lmb->aa_index != lmb->aa_index ||
-		    prev_lmb->flags != lmb->flags) {
+		    drmem_lmb_flags(prev_lmb) != drmem_lmb_flags(lmb)) {
 			/* end of one set, start of another */
 			dr_cell->seq_lmbs = cpu_to_be32(seq_lmbs);
 			dr_cell++;
@@ -216,6 +216,8 @@
 	u32 i, n_lmbs;
 
 	n_lmbs = of_read_number(prop++, 1);
+	if (n_lmbs == 0)
+		return;
 
 	for (i = 0; i < n_lmbs; i++) {
 		read_drconf_v1_cell(&lmb, &prop);
@@ -245,6 +247,8 @@
 	u32 i, j, lmb_sets;
 
 	lmb_sets = of_read_number(prop++, 1);
+	if (lmb_sets == 0)
+		return;
 
 	for (i = 0; i < lmb_sets; i++) {
 		read_drconf_v2_cell(&dr_cell, &prop);
@@ -354,6 +358,8 @@
 	struct drmem_lmb *lmb;
 
 	drmem_info->n_lmbs = of_read_number(prop++, 1);
+	if (drmem_info->n_lmbs == 0)
+		return;
 
 	drmem_info->lmbs = kcalloc(drmem_info->n_lmbs, sizeof(*lmb),
 				   GFP_KERNEL);
@@ -373,6 +379,8 @@
 	int lmb_index;
 
 	lmb_sets = of_read_number(prop++, 1);
+	if (lmb_sets == 0)
+		return;
 
 	/* first pass, calculate the number of LMBs */
 	p = prop;
diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c
index 5a69b51..d573d7d 100644
--- a/arch/powerpc/mm/hash64_4k.c
+++ b/arch/powerpc/mm/hash64_4k.c
@@ -55,7 +55,7 @@
 	 * need to add in 0x1 if it's a read-only user page
 	 */
 	rflags = htab_convert_pte_flags(new_pte);
-	rpte = __real_pte(__pte(old_pte), ptep);
+	rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&
 	    !cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
@@ -117,7 +117,7 @@
 			return -1;
 		}
 		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
-		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE);
 	}
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 2253bbc..e601d95 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -86,7 +86,7 @@
 
 	subpg_index = (ea & (PAGE_SIZE - 1)) >> shift;
 	vpn  = hpt_vpn(ea, vsid, ssize);
-	rpte = __real_pte(__pte(old_pte), ptep);
+	rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE);
 	/*
 	 *None of the sub 4k page is hashed
 	 */
@@ -214,7 +214,7 @@
 		return -1;
 	}
 
-	new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot);
+	new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot, PTRS_PER_PTE);
 	new_pte |= H_PAGE_HASHPTE;
 
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
@@ -262,7 +262,7 @@
 	} while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
 	rflags = htab_convert_pte_flags(new_pte);
-	rpte = __real_pte(__pte(old_pte), ptep);
+	rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&
 	    !cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
@@ -327,7 +327,7 @@
 		}
 
 		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
-		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE);
 	}
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 7d07c7e1..cf290d41 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1008,6 +1008,7 @@
 	__pmd_index_size = H_PMD_INDEX_SIZE;
 	__pud_index_size = H_PUD_INDEX_SIZE;
 	__pgd_index_size = H_PGD_INDEX_SIZE;
+	__pud_cache_index = H_PUD_CACHE_INDEX;
 	__pmd_cache_index = H_PMD_CACHE_INDEX;
 	__pte_table_size = H_PTE_TABLE_SIZE;
 	__pmd_table_size = H_PMD_TABLE_SIZE;
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index 12511f5..b320f50 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -27,7 +27,7 @@
 	unsigned long vpn;
 	unsigned long old_pte, new_pte;
 	unsigned long rflags, pa, sz;
-	long slot;
+	long slot, offset;
 
 	BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
 
@@ -63,7 +63,11 @@
 	} while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
 	rflags = htab_convert_pte_flags(new_pte);
-	rpte = __real_pte(__pte(old_pte), ptep);
+	if (unlikely(mmu_psize == MMU_PAGE_16G))
+		offset = PTRS_PER_PUD;
+	else
+		offset = PTRS_PER_PMD;
+	rpte = __real_pte(__pte(old_pte), ptep, offset);
 
 	sz = ((1UL) << shift);
 	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
@@ -104,7 +108,7 @@
 			return -1;
 		}
 
-		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot, offset);
 	}
 
 	/*
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index eb8c6c8..2b656e6 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -100,6 +100,6 @@
 	 * same size as either the pgd or pmd index except with THP enabled
 	 * on book3s 64
 	 */
-	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
-		pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor);
+	if (PUD_CACHE_INDEX && !PGT_CACHE(PUD_CACHE_INDEX))
+		pgtable_cache_add(PUD_CACHE_INDEX, pud_ctor);
 }
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 314d19a..edd8d0b 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -143,11 +143,6 @@
 		numa_cpu_lookup_table[cpu] = -1;
 }
 
-static void update_numa_cpu_lookup_table(unsigned int cpu, int node)
-{
-	numa_cpu_lookup_table[cpu] = node;
-}
-
 static void map_cpu_to_node(int cpu, int node)
 {
 	update_numa_cpu_lookup_table(cpu, node);
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 573a9a2..2e10a96 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -17,9 +17,11 @@
 #include <linux/of_fdt.h>
 #include <linux/mm.h>
 #include <linux/string_helpers.h>
+#include <linux/stop_machine.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
+#include <asm/mmu_context.h>
 #include <asm/dma.h>
 #include <asm/machdep.h>
 #include <asm/mmu.h>
@@ -333,6 +335,22 @@
 		     "r" (TLBIEL_INVAL_SET_LPID), "r" (0));
 	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 	trace_tlbie(0, 0, TLBIEL_INVAL_SET_LPID, 0, 2, 1, 1);
+
+	/*
+	 * The init_mm context is given the first available (non-zero) PID,
+	 * which is the "guard PID" and contains no page table. PIDR should
+	 * never be set to zero because that duplicates the kernel address
+	 * space at the 0x0... offset (quadrant 0)!
+	 *
+	 * An arbitrary PID that may later be allocated by the PID allocator
+	 * for userspace processes must not be used either, because that
+	 * would cause stale user mappings for that PID on CPUs outside of
+	 * the TLB invalidation scheme (because it won't be in mm_cpumask).
+	 *
+	 * So permanently carve out one PID for the purpose of a guard PID.
+	 */
+	init_mm.context.id = mmu_base_pid;
+	mmu_base_pid++;
 }
 
 static void __init radix_init_partition_table(void)
@@ -535,6 +553,7 @@
 	__pmd_index_size = RADIX_PMD_INDEX_SIZE;
 	__pud_index_size = RADIX_PUD_INDEX_SIZE;
 	__pgd_index_size = RADIX_PGD_INDEX_SIZE;
+	__pud_cache_index = RADIX_PUD_INDEX_SIZE;
 	__pmd_cache_index = RADIX_PMD_INDEX_SIZE;
 	__pte_table_size = RADIX_PTE_TABLE_SIZE;
 	__pmd_table_size = RADIX_PMD_TABLE_SIZE;
@@ -579,7 +598,8 @@
 
 	radix_init_iamr();
 	radix_init_pgtable();
-
+	/* Switch to the guard PID before turning on MMU */
+	radix__switch_mmu_context(NULL, &init_mm);
 	if (cpu_has_feature(CPU_FTR_HVMODE))
 		tlbiel_all();
 }
@@ -604,6 +624,7 @@
 	}
 	radix_init_iamr();
 
+	radix__switch_mmu_context(NULL, &init_mm);
 	if (cpu_has_feature(CPU_FTR_HVMODE))
 		tlbiel_all();
 }
@@ -666,6 +687,30 @@
 	pud_clear(pud);
 }
 
+struct change_mapping_params {
+	pte_t *pte;
+	unsigned long start;
+	unsigned long end;
+	unsigned long aligned_start;
+	unsigned long aligned_end;
+};
+
+static int stop_machine_change_mapping(void *data)
+{
+	struct change_mapping_params *params =
+			(struct change_mapping_params *)data;
+
+	if (!data)
+		return -1;
+
+	spin_unlock(&init_mm.page_table_lock);
+	pte_clear(&init_mm, params->aligned_start, params->pte);
+	create_physical_mapping(params->aligned_start, params->start);
+	create_physical_mapping(params->end, params->aligned_end);
+	spin_lock(&init_mm.page_table_lock);
+	return 0;
+}
+
 static void remove_pte_table(pte_t *pte_start, unsigned long addr,
 			     unsigned long end)
 {
@@ -694,6 +739,52 @@
 	}
 }
 
+/*
+ * clear the pte and potentially split the mapping helper
+ */
+static void split_kernel_mapping(unsigned long addr, unsigned long end,
+				unsigned long size, pte_t *pte)
+{
+	unsigned long mask = ~(size - 1);
+	unsigned long aligned_start = addr & mask;
+	unsigned long aligned_end = addr + size;
+	struct change_mapping_params params;
+	bool split_region = false;
+
+	if ((end - addr) < size) {
+		/*
+		 * We're going to clear the PTE, but not flushed
+		 * the mapping, time to remap and flush. The
+		 * effects if visible outside the processor or
+		 * if we are running in code close to the
+		 * mapping we cleared, we are in trouble.
+		 */
+		if (overlaps_kernel_text(aligned_start, addr) ||
+			overlaps_kernel_text(end, aligned_end)) {
+			/*
+			 * Hack, just return, don't pte_clear
+			 */
+			WARN_ONCE(1, "Linear mapping %lx->%lx overlaps kernel "
+				  "text, not splitting\n", addr, end);
+			return;
+		}
+		split_region = true;
+	}
+
+	if (split_region) {
+		params.pte = pte;
+		params.start = addr;
+		params.end = end;
+		params.aligned_start = addr & ~(size - 1);
+		params.aligned_end = min_t(unsigned long, aligned_end,
+				(unsigned long)__va(memblock_end_of_DRAM()));
+		stop_machine(stop_machine_change_mapping, &params, NULL);
+		return;
+	}
+
+	pte_clear(&init_mm, addr, pte);
+}
+
 static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
 			     unsigned long end)
 {
@@ -709,13 +800,7 @@
 			continue;
 
 		if (pmd_huge(*pmd)) {
-			if (!IS_ALIGNED(addr, PMD_SIZE) ||
-			    !IS_ALIGNED(next, PMD_SIZE)) {
-				WARN_ONCE(1, "%s: unaligned range\n", __func__);
-				continue;
-			}
-
-			pte_clear(&init_mm, addr, (pte_t *)pmd);
+			split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd);
 			continue;
 		}
 
@@ -740,13 +825,7 @@
 			continue;
 
 		if (pud_huge(*pud)) {
-			if (!IS_ALIGNED(addr, PUD_SIZE) ||
-			    !IS_ALIGNED(next, PUD_SIZE)) {
-				WARN_ONCE(1, "%s: unaligned range\n", __func__);
-				continue;
-			}
-
-			pte_clear(&init_mm, addr, (pte_t *)pud);
+			split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud);
 			continue;
 		}
 
@@ -772,13 +851,7 @@
 			continue;
 
 		if (pgd_huge(*pgd)) {
-			if (!IS_ALIGNED(addr, PGDIR_SIZE) ||
-			    !IS_ALIGNED(next, PGDIR_SIZE)) {
-				WARN_ONCE(1, "%s: unaligned range\n", __func__);
-				continue;
-			}
-
-			pte_clear(&init_mm, addr, (pte_t *)pgd);
+			split_kernel_mapping(addr, end, PGDIR_SIZE, (pte_t *)pgd);
 			continue;
 		}
 
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index c9a623c..28c980e 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -82,6 +82,8 @@
 EXPORT_SYMBOL(__pgd_index_size);
 unsigned long __pmd_cache_index;
 EXPORT_SYMBOL(__pmd_cache_index);
+unsigned long __pud_cache_index;
+EXPORT_SYMBOL(__pud_cache_index);
 unsigned long __pte_table_size;
 EXPORT_SYMBOL(__pte_table_size);
 unsigned long __pmd_table_size;
@@ -471,6 +473,8 @@
 	if (old & PATB_HR) {
 		asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : :
 			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
+		asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
+			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
 		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1);
 	} else {
 		asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 881ebd5..9b23f12 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -51,7 +51,7 @@
 	unsigned int psize;
 	int ssize;
 	real_pte_t rpte;
-	int i;
+	int i, offset;
 
 	i = batch->index;
 
@@ -67,6 +67,10 @@
 		psize = get_slice_psize(mm, addr);
 		/* Mask the address for the correct page size */
 		addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1);
+		if (unlikely(psize == MMU_PAGE_16G))
+			offset = PTRS_PER_PUD;
+		else
+			offset = PTRS_PER_PMD;
 #else
 		BUG();
 		psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */
@@ -78,6 +82,7 @@
 		 * support 64k pages, this might be different from the
 		 * hardware page size encoded in the slice table. */
 		addr &= PAGE_MASK;
+		offset = PTRS_PER_PTE;
 	}
 
 
@@ -91,7 +96,7 @@
 	}
 	WARN_ON(vsid == 0);
 	vpn = hpt_vpn(addr, vsid, ssize);
-	rpte = __real_pte(__pte(pte), ptep);
+	rpte = __real_pte(__pte(pte), ptep, offset);
 
 	/*
 	 * Check if we have an active batch on this CPU. If not, just
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 872d1f6..a9636d8 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -327,6 +327,9 @@
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
 			PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len));
 			break;
+		case BPF_LDX | BPF_W | BPF_ABS: /* A = *((u32 *)(seccomp_data + K)); */
+			PPC_LWZ_OFFS(r_A, r_skb, K);
+			break;
 		case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */
 			PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len));
 			break;
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 0a34b0c..0ef3d95 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -240,6 +240,7 @@
 	 *   goto out;
 	 */
 	PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries));
+	PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31);
 	PPC_CMPLW(b2p_index, b2p[TMP_REG_1]);
 	PPC_BCC(COND_GE, out);
 
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
index dd4c9b8..f6f55ab 100644
--- a/arch/powerpc/platforms/powernv/opal-imc.c
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -199,9 +199,11 @@
 	const struct cpumask *l_cpumask;
 
 	get_online_cpus();
-	for_each_online_node(nid) {
+	for_each_node_with_cpus(nid) {
 		l_cpumask = cpumask_of_node(nid);
-		cpu = cpumask_first(l_cpumask);
+		cpu = cpumask_first_and(l_cpumask, cpu_online_mask);
+		if (cpu >= nr_cpu_ids)
+			continue;
 		opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
 				       get_hard_smp_processor_id(cpu));
 	}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 496e476..a6c92c7 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1854,7 +1854,7 @@
 	s64 rc;
 
 	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
-		return -ENODEV;;
+		return -ENODEV;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	if (pe->tce_bypass_enabled) {
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 4fb21e1..092715b 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -80,6 +80,10 @@
 		if (np && of_property_read_bool(np, "disabled"))
 			enable--;
 
+		np = of_get_child_by_name(fw_features, "speculation-policy-favor-security");
+		if (np && of_property_read_bool(np, "disabled"))
+			enable = 0;
+
 		of_node_put(np);
 		of_node_put(fw_features);
 	}
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index 2b3eb01..b7c53a5 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -1063,16 +1063,16 @@
 			rc = PTR_ERR(txwin->paste_kaddr);
 			goto free_window;
 		}
+	} else {
+		/*
+		 * A user mapping must ensure that context switch issues
+		 * CP_ABORT for this thread.
+		 */
+		rc = set_thread_uses_vas();
+		if (rc)
+			goto free_window;
 	}
 
-	/*
-	 * Now that we have a send window, ensure context switch issues
-	 * CP_ABORT for this thread.
-	 */
-	rc = -EINVAL;
-	if (set_thread_uses_vas() < 0)
-		goto free_window;
-
 	set_vinst_win(vinst, txwin);
 
 	return txwin;
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index dceb514..652d3e96 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -36,6 +36,7 @@
 #include <asm/xics.h>
 #include <asm/xive.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/topology.h>
 
 #include "pseries.h"
 #include "offline_states.h"
@@ -331,6 +332,7 @@
 			BUG_ON(cpu_online(cpu));
 			set_cpu_present(cpu, false);
 			set_hard_smp_processor_id(cpu, -1);
+			update_numa_cpu_lookup_table(cpu, -1);
 			break;
 		}
 		if (cpu >= nr_cpu_ids)
@@ -340,8 +342,6 @@
 	cpu_maps_update_done();
 }
 
-extern int find_and_online_cpu_nid(int cpu);
-
 static int dlpar_online_cpu(struct device_node *dn)
 {
 	int rc = 0;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 81d8614..5e1ef91 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -49,6 +49,28 @@
 
 
 /*
+ * Enable the hotplug interrupt late because processing them may touch other
+ * devices or systems (e.g. hugepages) that have not been initialized at the
+ * subsys stage.
+ */
+int __init init_ras_hotplug_IRQ(void)
+{
+	struct device_node *np;
+
+	/* Hotplug Events */
+	np = of_find_node_by_path("/event-sources/hot-plug-events");
+	if (np != NULL) {
+		if (dlpar_workqueue_init() == 0)
+			request_event_sources_irqs(np, ras_hotplug_interrupt,
+						   "RAS_HOTPLUG");
+		of_node_put(np);
+	}
+
+	return 0;
+}
+machine_late_initcall(pseries, init_ras_hotplug_IRQ);
+
+/*
  * Initialize handlers for the set of interrupts caused by hardware errors
  * and power system events.
  */
@@ -66,15 +88,6 @@
 		of_node_put(np);
 	}
 
-	/* Hotplug Events */
-	np = of_find_node_by_path("/event-sources/hot-plug-events");
-	if (np != NULL) {
-		if (dlpar_workqueue_init() == 0)
-			request_event_sources_irqs(np, ras_hotplug_interrupt,
-					   "RAS_HOTPLUG");
-		of_node_put(np);
-	}
-
 	/* EPOW Events */
 	np = of_find_node_by_path("/event-sources/epow-events");
 	if (np != NULL) {
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 372d7ad..1a52762 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -482,7 +482,8 @@
 		if (types == L1D_FLUSH_NONE)
 			types = L1D_FLUSH_FALLBACK;
 
-		if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR))
+		if ((!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) ||
+		    (!(result.behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)))
 			enable = false;
 	} else {
 		/* Default to fallback if case hcall is not available */
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index d9c4c93..091f1d0 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -356,7 +356,8 @@
 
 	rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size);
 	if (rc) {
-		pr_err("Error %lld getting queue info prio %d\n", rc, prio);
+		pr_err("Error %lld getting queue info CPU %d prio %d\n", rc,
+		       target, prio);
 		rc = -EIO;
 		goto fail;
 	}
@@ -370,7 +371,8 @@
 	/* Configure and enable the queue in HW */
 	rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order);
 	if (rc) {
-		pr_err("Error %lld setting queue for prio %d\n", rc, prio);
+		pr_err("Error %lld setting queue for CPU %d prio %d\n", rc,
+		       target, prio);
 		rc = -EIO;
 	} else {
 		q->qpage = qpage;
@@ -389,8 +391,8 @@
 	if (IS_ERR(qpage))
 		return PTR_ERR(qpage);
 
-	return xive_spapr_configure_queue(cpu, q, prio, qpage,
-					  xive_queue_shift);
+	return xive_spapr_configure_queue(get_hard_smp_processor_id(cpu),
+					  q, prio, qpage, xive_queue_shift);
 }
 
 static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc,
@@ -399,10 +401,12 @@
 	struct xive_q *q = &xc->queue[prio];
 	unsigned int alloc_order;
 	long rc;
+	int hw_cpu = get_hard_smp_processor_id(cpu);
 
-	rc = plpar_int_set_queue_config(0, cpu, prio, 0, 0);
+	rc = plpar_int_set_queue_config(0, hw_cpu, prio, 0, 0);
 	if (rc)
-		pr_err("Error %ld setting queue for prio %d\n", rc, prio);
+		pr_err("Error %ld setting queue for CPU %d prio %d\n", rc,
+		       hw_cpu, prio);
 
 	alloc_order = xive_alloc_order(xive_queue_shift);
 	free_pages((unsigned long)q->qpage, alloc_order);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index b6722c2..04807c7 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -8,7 +8,6 @@
 	select OF
 	select OF_EARLY_FLATTREE
 	select OF_IRQ
-	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_WANT_FRAME_POINTERS
 	select CLONE_BACKWARDS
 	select COMMON_CLK
@@ -20,7 +19,6 @@
 	select GENERIC_STRNLEN_USER
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A
-	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_DMA_API_DEBUG
@@ -34,7 +32,6 @@
 	select HAVE_ARCH_TRACEHOOK
 	select MODULES_USE_ELF_RELA if MODULES
 	select THREAD_INFO_IN_TASK
-	select RISCV_IRQ_INTC
 	select RISCV_TIMER
 
 config MMU
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index c0319cb..5510366 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -34,9 +34,9 @@
 #define wmb()		RISCV_FENCE(ow,ow)
 
 /* These barriers do not need to enforce ordering on devices, just memory. */
-#define smp_mb()	RISCV_FENCE(rw,rw)
-#define smp_rmb()	RISCV_FENCE(r,r)
-#define smp_wmb()	RISCV_FENCE(w,w)
+#define __smp_mb()	RISCV_FENCE(rw,rw)
+#define __smp_rmb()	RISCV_FENCE(r,r)
+#define __smp_wmb()	RISCV_FENCE(w,w)
 
 /*
  * This is a very specific barrier: it's currently only used in two places in
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 87fc045..56fa592 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -172,6 +172,9 @@
 	move a1, sp /* pt_regs */
 	tail do_IRQ
 1:
+	/* Exceptions run with interrupts enabled */
+	csrs sstatus, SR_SIE
+
 	/* Handle syscalls */
 	li t0, EXC_SYSCALL
 	beq s4, t0, handle_syscall
@@ -198,8 +201,6 @@
 	 */
 	addi s2, s2, 0x4
 	REG_S s2, PT_SEPC(sp)
-	/* System calls run with interrupts enabled */
-	csrs sstatus, SR_SIE
 	/* Trace syscalls, but only if requested by the user. */
 	REG_L t0, TASK_TI_FLAGS(tp)
 	andi t0, t0, _TIF_SYSCALL_TRACE
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 226eeb1..6e07ed3 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -64,7 +64,7 @@
 	/* Start the kernel */
 	mv a0, s0
 	mv a1, s1
-	call sbi_save
+	call parse_dtb
 	tail start_kernel
 
 relocate:
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 09f7064..c11f40c 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -144,7 +144,7 @@
 #endif
 }
 
-void __init sbi_save(unsigned int hartid, void *dtb)
+void __init parse_dtb(unsigned int hartid, void *dtb)
 {
 	early_init_dt_scan(__va(dtb));
 }
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 9c7d707..07c6e81 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -22,22 +22,6 @@
 #include "trace.h"
 #include "trace-s390.h"
 
-
-static const intercept_handler_t instruction_handlers[256] = {
-	[0x01] = kvm_s390_handle_01,
-	[0x82] = kvm_s390_handle_lpsw,
-	[0x83] = kvm_s390_handle_diag,
-	[0xaa] = kvm_s390_handle_aa,
-	[0xae] = kvm_s390_handle_sigp,
-	[0xb2] = kvm_s390_handle_b2,
-	[0xb6] = kvm_s390_handle_stctl,
-	[0xb7] = kvm_s390_handle_lctl,
-	[0xb9] = kvm_s390_handle_b9,
-	[0xe3] = kvm_s390_handle_e3,
-	[0xe5] = kvm_s390_handle_e5,
-	[0xeb] = kvm_s390_handle_eb,
-};
-
 u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block;
@@ -129,16 +113,39 @@
 
 static int handle_instruction(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
 	vcpu->stat.exit_instruction++;
 	trace_kvm_s390_intercept_instruction(vcpu,
 					     vcpu->arch.sie_block->ipa,
 					     vcpu->arch.sie_block->ipb);
-	handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8];
-	if (handler)
-		return handler(vcpu);
-	return -EOPNOTSUPP;
+
+	switch (vcpu->arch.sie_block->ipa >> 8) {
+	case 0x01:
+		return kvm_s390_handle_01(vcpu);
+	case 0x82:
+		return kvm_s390_handle_lpsw(vcpu);
+	case 0x83:
+		return kvm_s390_handle_diag(vcpu);
+	case 0xaa:
+		return kvm_s390_handle_aa(vcpu);
+	case 0xae:
+		return kvm_s390_handle_sigp(vcpu);
+	case 0xb2:
+		return kvm_s390_handle_b2(vcpu);
+	case 0xb6:
+		return kvm_s390_handle_stctl(vcpu);
+	case 0xb7:
+		return kvm_s390_handle_lctl(vcpu);
+	case 0xb9:
+		return kvm_s390_handle_b9(vcpu);
+	case 0xe3:
+		return kvm_s390_handle_e3(vcpu);
+	case 0xe5:
+		return kvm_s390_handle_e5(vcpu);
+	case 0xeb:
+		return kvm_s390_handle_eb(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index aabf46f..b04616b 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -169,8 +169,15 @@
 
 static int ckc_irq_pending(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.sie_block->ckc >= kvm_s390_get_tod_clock_fast(vcpu->kvm))
+	const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+	const u64 ckc = vcpu->arch.sie_block->ckc;
+
+	if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) {
+		if ((s64)ckc >= (s64)now)
+			return 0;
+	} else if (ckc >= now) {
 		return 0;
+	}
 	return ckc_interrupts_enabled(vcpu);
 }
 
@@ -187,12 +194,6 @@
 	return kvm_s390_get_cpu_timer(vcpu) >> 63;
 }
 
-static inline int is_ioirq(unsigned long irq_type)
-{
-	return ((irq_type >= IRQ_PEND_IO_ISC_7) &&
-		(irq_type <= IRQ_PEND_IO_ISC_0));
-}
-
 static uint64_t isc_to_isc_bits(int isc)
 {
 	return (0x80 >> isc) << 24;
@@ -236,10 +237,15 @@
 	return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
 }
 
-static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
+static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->arch.float_int.pending_irqs |
-		vcpu->arch.local_int.pending_irqs |
+		vcpu->arch.local_int.pending_irqs;
+}
+
+static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
+{
+	return pending_irqs_no_gisa(vcpu) |
 		kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7;
 }
 
@@ -337,7 +343,7 @@
 
 static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
 {
-	if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK))
+	if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_IO_MASK))
 		return;
 	else if (psw_ioint_disabled(vcpu))
 		kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT);
@@ -1011,24 +1017,6 @@
 	return rc;
 }
 
-typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu);
-
-static const deliver_irq_t deliver_irq_funcs[] = {
-	[IRQ_PEND_MCHK_EX]        = __deliver_machine_check,
-	[IRQ_PEND_MCHK_REP]       = __deliver_machine_check,
-	[IRQ_PEND_PROG]           = __deliver_prog,
-	[IRQ_PEND_EXT_EMERGENCY]  = __deliver_emergency_signal,
-	[IRQ_PEND_EXT_EXTERNAL]   = __deliver_external_call,
-	[IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc,
-	[IRQ_PEND_EXT_CPU_TIMER]  = __deliver_cpu_timer,
-	[IRQ_PEND_RESTART]        = __deliver_restart,
-	[IRQ_PEND_SET_PREFIX]     = __deliver_set_prefix,
-	[IRQ_PEND_PFAULT_INIT]    = __deliver_pfault_init,
-	[IRQ_PEND_EXT_SERVICE]    = __deliver_service,
-	[IRQ_PEND_PFAULT_DONE]    = __deliver_pfault_done,
-	[IRQ_PEND_VIRTIO]         = __deliver_virtio,
-};
-
 /* Check whether an external call is pending (deliverable or not) */
 int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
 {
@@ -1066,13 +1054,19 @@
 
 static u64 __calculate_sltime(struct kvm_vcpu *vcpu)
 {
-	u64 now, cputm, sltime = 0;
+	const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
+	const u64 ckc = vcpu->arch.sie_block->ckc;
+	u64 cputm, sltime = 0;
 
 	if (ckc_interrupts_enabled(vcpu)) {
-		now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
-		sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
-		/* already expired or overflow? */
-		if (!sltime || vcpu->arch.sie_block->ckc <= now)
+		if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) {
+			if ((s64)now < (s64)ckc)
+				sltime = tod_to_ns((s64)ckc - (s64)now);
+		} else if (now < ckc) {
+			sltime = tod_to_ns(ckc - now);
+		}
+		/* already expired */
+		if (!sltime)
 			return 0;
 		if (cpu_timer_interrupts_enabled(vcpu)) {
 			cputm = kvm_s390_get_cpu_timer(vcpu);
@@ -1192,7 +1186,6 @@
 int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
-	deliver_irq_t func;
 	int rc = 0;
 	unsigned long irq_type;
 	unsigned long irqs;
@@ -1212,16 +1205,57 @@
 	while ((irqs = deliverable_irqs(vcpu)) && !rc) {
 		/* bits are in the reverse order of interrupt priority */
 		irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT);
-		if (is_ioirq(irq_type)) {
+		switch (irq_type) {
+		case IRQ_PEND_IO_ISC_0:
+		case IRQ_PEND_IO_ISC_1:
+		case IRQ_PEND_IO_ISC_2:
+		case IRQ_PEND_IO_ISC_3:
+		case IRQ_PEND_IO_ISC_4:
+		case IRQ_PEND_IO_ISC_5:
+		case IRQ_PEND_IO_ISC_6:
+		case IRQ_PEND_IO_ISC_7:
 			rc = __deliver_io(vcpu, irq_type);
-		} else {
-			func = deliver_irq_funcs[irq_type];
-			if (!func) {
-				WARN_ON_ONCE(func == NULL);
-				clear_bit(irq_type, &li->pending_irqs);
-				continue;
-			}
-			rc = func(vcpu);
+			break;
+		case IRQ_PEND_MCHK_EX:
+		case IRQ_PEND_MCHK_REP:
+			rc = __deliver_machine_check(vcpu);
+			break;
+		case IRQ_PEND_PROG:
+			rc = __deliver_prog(vcpu);
+			break;
+		case IRQ_PEND_EXT_EMERGENCY:
+			rc = __deliver_emergency_signal(vcpu);
+			break;
+		case IRQ_PEND_EXT_EXTERNAL:
+			rc = __deliver_external_call(vcpu);
+			break;
+		case IRQ_PEND_EXT_CLOCK_COMP:
+			rc = __deliver_ckc(vcpu);
+			break;
+		case IRQ_PEND_EXT_CPU_TIMER:
+			rc = __deliver_cpu_timer(vcpu);
+			break;
+		case IRQ_PEND_RESTART:
+			rc = __deliver_restart(vcpu);
+			break;
+		case IRQ_PEND_SET_PREFIX:
+			rc = __deliver_set_prefix(vcpu);
+			break;
+		case IRQ_PEND_PFAULT_INIT:
+			rc = __deliver_pfault_init(vcpu);
+			break;
+		case IRQ_PEND_EXT_SERVICE:
+			rc = __deliver_service(vcpu);
+			break;
+		case IRQ_PEND_PFAULT_DONE:
+			rc = __deliver_pfault_done(vcpu);
+			break;
+		case IRQ_PEND_VIRTIO:
+			rc = __deliver_virtio(vcpu);
+			break;
+		default:
+			WARN_ONCE(1, "Unknown pending irq type %ld", irq_type);
+			clear_bit(irq_type, &li->pending_irqs);
 		}
 	}
 
@@ -1701,7 +1735,8 @@
 		kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT);
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT);
+		if (!(type & KVM_S390_INT_IO_AI_MASK && kvm->arch.gisa))
+			kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT);
 		break;
 	default:
 		kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_EXT_INT);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ba4c709..77d7818 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -179,6 +179,28 @@
 static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
 			      unsigned long end);
 
+static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta)
+{
+	u8 delta_idx = 0;
+
+	/*
+	 * The TOD jumps by delta, we have to compensate this by adding
+	 * -delta to the epoch.
+	 */
+	delta = -delta;
+
+	/* sign-extension - we're adding to signed values below */
+	if ((s64)delta < 0)
+		delta_idx = -1;
+
+	scb->epoch += delta;
+	if (scb->ecd & ECD_MEF) {
+		scb->epdx += delta_idx;
+		if (scb->epoch < delta)
+			scb->epdx += 1;
+	}
+}
+
 /*
  * This callback is executed during stop_machine(). All CPUs are therefore
  * temporarily stopped. In order not to change guest behavior, we have to
@@ -194,13 +216,17 @@
 	unsigned long long *delta = v;
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
-		kvm->arch.epoch -= *delta;
 		kvm_for_each_vcpu(i, vcpu, kvm) {
-			vcpu->arch.sie_block->epoch -= *delta;
+			kvm_clock_sync_scb(vcpu->arch.sie_block, *delta);
+			if (i == 0) {
+				kvm->arch.epoch = vcpu->arch.sie_block->epoch;
+				kvm->arch.epdx = vcpu->arch.sie_block->epdx;
+			}
 			if (vcpu->arch.cputm_enabled)
 				vcpu->arch.cputm_start += *delta;
 			if (vcpu->arch.vsie_block)
-				vcpu->arch.vsie_block->epoch -= *delta;
+				kvm_clock_sync_scb(vcpu->arch.vsie_block,
+						   *delta);
 		}
 	}
 	return NOTIFY_OK;
@@ -902,12 +928,9 @@
 	if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
 		return -EFAULT;
 
-	if (test_kvm_facility(kvm, 139))
-		kvm_s390_set_tod_clock_ext(kvm, &gtod);
-	else if (gtod.epoch_idx == 0)
-		kvm_s390_set_tod_clock(kvm, gtod.tod);
-	else
+	if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx)
 		return -EINVAL;
+	kvm_s390_set_tod_clock(kvm, &gtod);
 
 	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",
 		gtod.epoch_idx, gtod.tod);
@@ -932,13 +955,14 @@
 
 static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
 {
-	u64 gtod;
+	struct kvm_s390_vm_tod_clock gtod = { 0 };
 
-	if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
+	if (copy_from_user(&gtod.tod, (void __user *)attr->addr,
+			   sizeof(gtod.tod)))
 		return -EFAULT;
 
-	kvm_s390_set_tod_clock(kvm, gtod);
-	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod);
+	kvm_s390_set_tod_clock(kvm, &gtod);
+	VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod);
 	return 0;
 }
 
@@ -2389,6 +2413,7 @@
 	mutex_lock(&vcpu->kvm->lock);
 	preempt_disable();
 	vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
+	vcpu->arch.sie_block->epdx = vcpu->kvm->arch.epdx;
 	preempt_enable();
 	mutex_unlock(&vcpu->kvm->lock);
 	if (!kvm_is_ucontrol(vcpu->kvm)) {
@@ -3021,8 +3046,8 @@
 	return 0;
 }
 
-void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
-				 const struct kvm_s390_vm_tod_clock *gtod)
+void kvm_s390_set_tod_clock(struct kvm *kvm,
+			    const struct kvm_s390_vm_tod_clock *gtod)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_s390_tod_clock_ext htod;
@@ -3034,10 +3059,12 @@
 	get_tod_clock_ext((char *)&htod);
 
 	kvm->arch.epoch = gtod->tod - htod.tod;
-	kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx;
-
-	if (kvm->arch.epoch > gtod->tod)
-		kvm->arch.epdx -= 1;
+	kvm->arch.epdx = 0;
+	if (test_kvm_facility(kvm, 139)) {
+		kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx;
+		if (kvm->arch.epoch > gtod->tod)
+			kvm->arch.epdx -= 1;
+	}
 
 	kvm_s390_vcpu_block_all(kvm);
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -3050,22 +3077,6 @@
 	mutex_unlock(&kvm->lock);
 }
 
-void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod)
-{
-	struct kvm_vcpu *vcpu;
-	int i;
-
-	mutex_lock(&kvm->lock);
-	preempt_disable();
-	kvm->arch.epoch = tod - get_tod_clock();
-	kvm_s390_vcpu_block_all(kvm);
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		vcpu->arch.sie_block->epoch = kvm->arch.epoch;
-	kvm_s390_vcpu_unblock_all(kvm);
-	preempt_enable();
-	mutex_unlock(&kvm->lock);
-}
-
 /**
  * kvm_arch_fault_in_page - fault-in guest page if necessary
  * @vcpu: The corresponding virtual cpu
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index bd31b37..f55ac0e 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -19,8 +19,6 @@
 #include <asm/processor.h>
 #include <asm/sclp.h>
 
-typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
-
 /* Transactional Memory Execution related macros */
 #define IS_TE_ENABLED(vcpu)	((vcpu->arch.sie_block->ecb & ECB_TE))
 #define TDB_FORMAT1		1
@@ -283,9 +281,8 @@
 int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
 
 /* implemented in kvm-s390.c */
-void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
-				 const struct kvm_s390_vm_tod_clock *gtod);
-void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod);
+void kvm_s390_set_tod_clock(struct kvm *kvm,
+			    const struct kvm_s390_vm_tod_clock *gtod);
 long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
 int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index c4c4e15..f0b4185 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -85,9 +85,10 @@
 /* Handle SCK (SET CLOCK) interception */
 static int handle_set_clock(struct kvm_vcpu *vcpu)
 {
+	struct kvm_s390_vm_tod_clock gtod = { 0 };
 	int rc;
 	u8 ar;
-	u64 op2, val;
+	u64 op2;
 
 	vcpu->stat.instruction_sck++;
 
@@ -97,12 +98,12 @@
 	op2 = kvm_s390_get_base_disp_s(vcpu, &ar);
 	if (op2 & 7)	/* Operand must be on a doubleword boundary */
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-	rc = read_guest(vcpu, op2, ar, &val, sizeof(val));
+	rc = read_guest(vcpu, op2, ar, &gtod.tod, sizeof(gtod.tod));
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
 
-	VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", val);
-	kvm_s390_set_tod_clock(vcpu->kvm, val);
+	VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod);
+	kvm_s390_set_tod_clock(vcpu->kvm, &gtod);
 
 	kvm_s390_set_psw_cc(vcpu, 0);
 	return 0;
@@ -795,55 +796,60 @@
 	return rc;
 }
 
-static const intercept_handler_t b2_handlers[256] = {
-	[0x02] = handle_stidp,
-	[0x04] = handle_set_clock,
-	[0x10] = handle_set_prefix,
-	[0x11] = handle_store_prefix,
-	[0x12] = handle_store_cpu_address,
-	[0x14] = kvm_s390_handle_vsie,
-	[0x21] = handle_ipte_interlock,
-	[0x29] = handle_iske,
-	[0x2a] = handle_rrbe,
-	[0x2b] = handle_sske,
-	[0x2c] = handle_test_block,
-	[0x30] = handle_io_inst,
-	[0x31] = handle_io_inst,
-	[0x32] = handle_io_inst,
-	[0x33] = handle_io_inst,
-	[0x34] = handle_io_inst,
-	[0x35] = handle_io_inst,
-	[0x36] = handle_io_inst,
-	[0x37] = handle_io_inst,
-	[0x38] = handle_io_inst,
-	[0x39] = handle_io_inst,
-	[0x3a] = handle_io_inst,
-	[0x3b] = handle_io_inst,
-	[0x3c] = handle_io_inst,
-	[0x50] = handle_ipte_interlock,
-	[0x56] = handle_sthyi,
-	[0x5f] = handle_io_inst,
-	[0x74] = handle_io_inst,
-	[0x76] = handle_io_inst,
-	[0x7d] = handle_stsi,
-	[0xb1] = handle_stfl,
-	[0xb2] = handle_lpswe,
-};
-
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
-	/*
-	 * A lot of B2 instructions are priviledged. Here we check for
-	 * the privileged ones, that we can handle in the kernel.
-	 * Anything else goes to userspace.
-	 */
-	handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
-	if (handler)
-		return handler(vcpu);
-
-	return -EOPNOTSUPP;
+	switch (vcpu->arch.sie_block->ipa & 0x00ff) {
+	case 0x02:
+		return handle_stidp(vcpu);
+	case 0x04:
+		return handle_set_clock(vcpu);
+	case 0x10:
+		return handle_set_prefix(vcpu);
+	case 0x11:
+		return handle_store_prefix(vcpu);
+	case 0x12:
+		return handle_store_cpu_address(vcpu);
+	case 0x14:
+		return kvm_s390_handle_vsie(vcpu);
+	case 0x21:
+	case 0x50:
+		return handle_ipte_interlock(vcpu);
+	case 0x29:
+		return handle_iske(vcpu);
+	case 0x2a:
+		return handle_rrbe(vcpu);
+	case 0x2b:
+		return handle_sske(vcpu);
+	case 0x2c:
+		return handle_test_block(vcpu);
+	case 0x30:
+	case 0x31:
+	case 0x32:
+	case 0x33:
+	case 0x34:
+	case 0x35:
+	case 0x36:
+	case 0x37:
+	case 0x38:
+	case 0x39:
+	case 0x3a:
+	case 0x3b:
+	case 0x3c:
+	case 0x5f:
+	case 0x74:
+	case 0x76:
+		return handle_io_inst(vcpu);
+	case 0x56:
+		return handle_sthyi(vcpu);
+	case 0x7d:
+		return handle_stsi(vcpu);
+	case 0xb1:
+		return handle_stfl(vcpu);
+	case 0xb2:
+		return handle_lpswe(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int handle_epsw(struct kvm_vcpu *vcpu)
@@ -1105,25 +1111,22 @@
 	return 0;
 }
 
-static const intercept_handler_t b9_handlers[256] = {
-	[0x8a] = handle_ipte_interlock,
-	[0x8d] = handle_epsw,
-	[0x8e] = handle_ipte_interlock,
-	[0x8f] = handle_ipte_interlock,
-	[0xab] = handle_essa,
-	[0xaf] = handle_pfmf,
-};
-
 int kvm_s390_handle_b9(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
-	/* This is handled just as for the B2 instructions. */
-	handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
-	if (handler)
-		return handler(vcpu);
-
-	return -EOPNOTSUPP;
+	switch (vcpu->arch.sie_block->ipa & 0x00ff) {
+	case 0x8a:
+	case 0x8e:
+	case 0x8f:
+		return handle_ipte_interlock(vcpu);
+	case 0x8d:
+		return handle_epsw(vcpu);
+	case 0xab:
+		return handle_essa(vcpu);
+	case 0xaf:
+		return handle_pfmf(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu)
@@ -1271,22 +1274,20 @@
 	return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0;
 }
 
-static const intercept_handler_t eb_handlers[256] = {
-	[0x2f] = handle_lctlg,
-	[0x25] = handle_stctg,
-	[0x60] = handle_ri,
-	[0x61] = handle_ri,
-	[0x62] = handle_ri,
-};
-
 int kvm_s390_handle_eb(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
-	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
-	if (handler)
-		return handler(vcpu);
-	return -EOPNOTSUPP;
+	switch (vcpu->arch.sie_block->ipb & 0x000000ff) {
+	case 0x25:
+		return handle_stctg(vcpu);
+	case 0x2f:
+		return handle_lctlg(vcpu);
+	case 0x60:
+	case 0x61:
+	case 0x62:
+		return handle_ri(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int handle_tprot(struct kvm_vcpu *vcpu)
@@ -1346,10 +1347,12 @@
 
 int kvm_s390_handle_e5(struct kvm_vcpu *vcpu)
 {
-	/* For e5xx... instructions we only handle TPROT */
-	if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01)
+	switch (vcpu->arch.sie_block->ipa & 0x00ff) {
+	case 0x01:
 		return handle_tprot(vcpu);
-	return -EOPNOTSUPP;
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static int handle_sckpf(struct kvm_vcpu *vcpu)
@@ -1380,17 +1383,14 @@
 	return 0;
 }
 
-static const intercept_handler_t x01_handlers[256] = {
-	[0x04] = handle_ptff,
-	[0x07] = handle_sckpf,
-};
-
 int kvm_s390_handle_01(struct kvm_vcpu *vcpu)
 {
-	intercept_handler_t handler;
-
-	handler = x01_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
-	if (handler)
-		return handler(vcpu);
-	return -EOPNOTSUPP;
+	switch (vcpu->arch.sie_block->ipa & 0x00ff) {
+	case 0x04:
+		return handle_ptff(vcpu);
+	case 0x07:
+		return handle_sckpf(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index ec77270..8961e39 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -821,6 +821,7 @@
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
 	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	int guest_bp_isolation;
 	int rc;
 
 	handle_last_fault(vcpu, vsie_page);
@@ -831,6 +832,20 @@
 		s390_handle_mcck();
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+
+	/* save current guest state of bp isolation override */
+	guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST);
+
+	/*
+	 * The guest is running with BPBC, so we have to force it on for our
+	 * nested guest. This is done by enabling BPBC globally, so the BPBC
+	 * control in the SCB (which the nested guest can modify) is simply
+	 * ignored.
+	 */
+	if (test_kvm_facility(vcpu->kvm, 82) &&
+	    vcpu->arch.sie_block->fpf & FPF_BPBC)
+		set_thread_flag(TIF_ISOLATE_BP_GUEST);
+
 	local_irq_disable();
 	guest_enter_irqoff();
 	local_irq_enable();
@@ -840,6 +855,11 @@
 	local_irq_disable();
 	guest_exit_irqoff();
 	local_irq_enable();
+
+	/* restore guest state for bp isolation override */
+	if (!guest_bp_isolation)
+		clear_thread_flag(TIF_ISOLATE_BP_GUEST);
+
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	if (rc == -EINTR) {
diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile
index 715def0..01d0f7f 100644
--- a/arch/sh/boot/dts/Makefile
+++ b/arch/sh/boot/dts/Makefile
@@ -1 +1,3 @@
-obj-$(CONFIG_USE_BUILTIN_DTB) += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o
+ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"")
+obj-y += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o
+endif
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 6bf594a..8767e45 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -430,6 +430,8 @@
 	depends on SPARC32
 	select USB_EHCI_BIG_ENDIAN_MMIO
 	select USB_EHCI_BIG_ENDIAN_DESC
+	select USB_UHCI_BIG_ENDIAN_MMIO
+	select USB_UHCI_BIG_ENDIAN_DESC
 	---help---
 	  If you say Y here if you are running on a SPARC-LEON processor.
 	  The LEON processor is a synthesizable VHDL model of the
diff --git a/arch/sparc/include/asm/bug.h b/arch/sparc/include/asm/bug.h
index 6f17528..ea53e41 100644
--- a/arch/sparc/include/asm/bug.h
+++ b/arch/sparc/include/asm/bug.h
@@ -9,10 +9,14 @@
 void do_BUG(const char *file, int line);
 #define BUG() do {					\
 	do_BUG(__FILE__, __LINE__);			\
+	barrier_before_unreachable();			\
 	__builtin_trap();				\
 } while (0)
 #else
-#define BUG()		__builtin_trap()
+#define BUG() do {					\
+	barrier_before_unreachable();			\
+	__builtin_trap();				\
+} while (0)
 #endif
 
 #define HAVE_ARCH_BUG
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore
index aff152c..5a82bac 100644
--- a/arch/x86/.gitignore
+++ b/arch/x86/.gitignore
@@ -1,6 +1,7 @@
 boot/compressed/vmlinux
 tools/test_get_len
 tools/insn_sanity
+tools/insn_decoder_test
 purgatory/kexec-purgatory.c
 purgatory/purgatory.ro
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 63bf349..eb7f43f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -423,12 +423,6 @@
 	  For old smp systems that do not have proper acpi support. Newer systems
 	  (esp with 64bit cpus) with acpi support, MADT and DSDT will override it
 
-config X86_BIGSMP
-	bool "Support for big SMP systems with more than 8 CPUs"
-	depends on X86_32 && SMP
-	---help---
-	  This option is needed for the systems that have more than 8 CPUs
-
 config GOLDFISH
        def_bool y
        depends on X86_GOLDFISH
@@ -436,6 +430,7 @@
 config RETPOLINE
 	bool "Avoid speculative indirect branches in kernel"
 	default y
+	select STACK_VALIDATION if HAVE_STACK_VALIDATION
 	help
 	  Compile kernel with the retpoline compiler options to guard against
 	  kernel-to-user data leaks by avoiding speculative indirect
@@ -460,6 +455,12 @@
 	  Say N if unsure.
 
 if X86_32
+config X86_BIGSMP
+	bool "Support for big SMP systems with more than 8 CPUs"
+	depends on SMP
+	---help---
+	  This option is needed for the systems that have more than 8 CPUs
+
 config X86_EXTENDED_PLATFORM
 	bool "Support for extended (non-PC) x86 platforms"
 	default y
@@ -949,25 +950,66 @@
 	  Enable maximum number of CPUS and NUMA Nodes for this architecture.
 	  If unsure, say N.
 
+#
+# The maximum number of CPUs supported:
+#
+# The main config value is NR_CPUS, which defaults to NR_CPUS_DEFAULT,
+# and which can be configured interactively in the
+# [NR_CPUS_RANGE_BEGIN ... NR_CPUS_RANGE_END] range.
+#
+# The ranges are different on 32-bit and 64-bit kernels, depending on
+# hardware capabilities and scalability features of the kernel.
+#
+# ( If MAXSMP is enabled we just use the highest possible value and disable
+#   interactive configuration. )
+#
+
+config NR_CPUS_RANGE_BEGIN
+	int
+	default NR_CPUS_RANGE_END if MAXSMP
+	default    1 if !SMP
+	default    2
+
+config NR_CPUS_RANGE_END
+	int
+	depends on X86_32
+	default   64 if  SMP &&  X86_BIGSMP
+	default    8 if  SMP && !X86_BIGSMP
+	default    1 if !SMP
+
+config NR_CPUS_RANGE_END
+	int
+	depends on X86_64
+	default 8192 if  SMP && ( MAXSMP ||  CPUMASK_OFFSTACK)
+	default  512 if  SMP && (!MAXSMP && !CPUMASK_OFFSTACK)
+	default    1 if !SMP
+
+config NR_CPUS_DEFAULT
+	int
+	depends on X86_32
+	default   32 if  X86_BIGSMP
+	default    8 if  SMP
+	default    1 if !SMP
+
+config NR_CPUS_DEFAULT
+	int
+	depends on X86_64
+	default 8192 if  MAXSMP
+	default   64 if  SMP
+	default    1 if !SMP
+
 config NR_CPUS
 	int "Maximum number of CPUs" if SMP && !MAXSMP
-	range 2 8 if SMP && X86_32 && !X86_BIGSMP
-	range 2 64 if SMP && X86_32 && X86_BIGSMP
-	range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64
-	range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64
-	default "1" if !SMP
-	default "8192" if MAXSMP
-	default "32" if SMP && X86_BIGSMP
-	default "8" if SMP && X86_32
-	default "64" if SMP
+	range NR_CPUS_RANGE_BEGIN NR_CPUS_RANGE_END
+	default NR_CPUS_DEFAULT
 	---help---
 	  This allows you to specify the maximum number of CPUs which this
 	  kernel will support.  If CPUMASK_OFFSTACK is enabled, the maximum
 	  supported value is 8192, otherwise the maximum value is 512.  The
 	  minimum value which makes sense is 2.
 
-	  This is purely to save memory - each supported CPU adds
-	  approximately eight kilobytes to the kernel image.
+	  This is purely to save memory: each supported CPU adds about 8KB
+	  to the kernel image.
 
 config SCHED_SMT
 	bool "SMT (Hyperthreading) scheduler support"
@@ -1363,7 +1405,7 @@
 
 config HIGHMEM64G
 	bool "64GB"
-	depends on !M486
+	depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6
 	select X86_PAE
 	---help---
 	  Select this if you have a 32-bit processor and more than 4
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 65a9a47..8b8d229 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -374,7 +374,7 @@
 
 config X86_CMPXCHG64
 	def_bool y
-	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM
+	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
@@ -385,7 +385,7 @@
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && X86_P6_NOP
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCRUSOE || MCORE2 || MK7 || MK8)
 	default "5" if X86_32 && X86_CMPXCHG64
 	default "4"
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index fad5516..498c1b8 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -232,10 +232,9 @@
 
 # Avoid indirect branches in kernel to deal with Spectre
 ifdef CONFIG_RETPOLINE
-    RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
-    ifneq ($(RETPOLINE_CFLAGS),)
-        KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
-    endif
+ifneq ($(RETPOLINE_CFLAGS),)
+  KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
+endif
 endif
 
 archscripts: scripts_basic
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 353e20c..886a911 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -439,7 +439,7 @@
 	struct efi_uga_draw_protocol *uga = NULL, *first_uga;
 	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
 	unsigned long nr_ugas;
-	u32 *handles = (u32 *)uga_handle;;
+	u32 *handles = (u32 *)uga_handle;
 	efi_status_t status = EFI_INVALID_PARAMETER;
 	int i;
 
@@ -484,7 +484,7 @@
 	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;;
+	u64 *handles = (u64 *)uga_handle;
 	efi_status_t status = EFI_INVALID_PARAMETER;
 	int i;
 
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c
index 36870b2..d088050 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c
@@ -57,10 +57,12 @@
 {
 	unsigned int j;
 
-	state->lens[0] = 0;
-	state->lens[1] = 1;
-	state->lens[2] = 2;
-	state->lens[3] = 3;
+	/* initially all lanes are unused */
+	state->lens[0] = 0xFFFFFFFF00000000;
+	state->lens[1] = 0xFFFFFFFF00000001;
+	state->lens[2] = 0xFFFFFFFF00000002;
+	state->lens[3] = 0xFFFFFFFF00000003;
+
 	state->unused_lanes = 0xFF03020100;
 	for (j = 0; j < 4; j++)
 		state->ldata[j].job_in_lane = NULL;
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 3f48f69..be63330 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -97,80 +97,78 @@
 
 #define SIZEOF_PTREGS	21*8
 
-	.macro ALLOC_PT_GPREGS_ON_STACK
-	addq	$-(15*8), %rsp
-	.endm
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
+	/*
+	 * Push registers and sanitize registers of values that a
+	 * speculation attack might otherwise want to exploit. The
+	 * lower registers are likely clobbered well before they
+	 * could be put to use in a speculative execution gadget.
+	 * Interleave XOR with PUSH for better uop scheduling:
+	 */
+	.if \save_ret
+	pushq	%rsi		/* pt_regs->si */
+	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
+	movq	%rdi, 8(%rsp)	/* pt_regs->di (overwriting original return address) */
+	.else
+	pushq   %rdi		/* pt_regs->di */
+	pushq   %rsi		/* pt_regs->si */
+	.endif
+	pushq	\rdx		/* pt_regs->dx */
+	pushq   %rcx		/* pt_regs->cx */
+	pushq   \rax		/* pt_regs->ax */
+	pushq   %r8		/* pt_regs->r8 */
+	xorl	%r8d, %r8d	/* nospec   r8 */
+	pushq   %r9		/* pt_regs->r9 */
+	xorl	%r9d, %r9d	/* nospec   r9 */
+	pushq   %r10		/* pt_regs->r10 */
+	xorl	%r10d, %r10d	/* nospec   r10 */
+	pushq   %r11		/* pt_regs->r11 */
+	xorl	%r11d, %r11d	/* nospec   r11*/
+	pushq	%rbx		/* pt_regs->rbx */
+	xorl    %ebx, %ebx	/* nospec   rbx*/
+	pushq	%rbp		/* pt_regs->rbp */
+	xorl    %ebp, %ebp	/* nospec   rbp*/
+	pushq	%r12		/* pt_regs->r12 */
+	xorl	%r12d, %r12d	/* nospec   r12*/
+	pushq	%r13		/* pt_regs->r13 */
+	xorl	%r13d, %r13d	/* nospec   r13*/
+	pushq	%r14		/* pt_regs->r14 */
+	xorl	%r14d, %r14d	/* nospec   r14*/
+	pushq	%r15		/* pt_regs->r15 */
+	xorl	%r15d, %r15d	/* nospec   r15*/
+	UNWIND_HINT_REGS
+	.if \save_ret
+	pushq	%rsi		/* return address on top of stack */
+	.endif
+.endm
 
-	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
-	.if \r11
-	movq %r11, 6*8+\offset(%rsp)
-	.endif
-	.if \r8910
-	movq %r10, 7*8+\offset(%rsp)
-	movq %r9,  8*8+\offset(%rsp)
-	movq %r8,  9*8+\offset(%rsp)
-	.endif
-	.if \rax
-	movq %rax, 10*8+\offset(%rsp)
-	.endif
-	.if \rcx
-	movq %rcx, 11*8+\offset(%rsp)
-	.endif
-	movq %rdx, 12*8+\offset(%rsp)
-	movq %rsi, 13*8+\offset(%rsp)
-	movq %rdi, 14*8+\offset(%rsp)
-	UNWIND_HINT_REGS offset=\offset extra=0
-	.endm
-	.macro SAVE_C_REGS offset=0
-	SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0
-	SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_R891011
-	SAVE_C_REGS_HELPER 0, 1, 1, 0, 0
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_RCX_R891011
-	SAVE_C_REGS_HELPER 0, 1, 0, 0, 0
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11
-	SAVE_C_REGS_HELPER 0, 0, 0, 1, 0
-	.endm
-
-	.macro SAVE_EXTRA_REGS offset=0
-	movq %r15, 0*8+\offset(%rsp)
-	movq %r14, 1*8+\offset(%rsp)
-	movq %r13, 2*8+\offset(%rsp)
-	movq %r12, 3*8+\offset(%rsp)
-	movq %rbp, 4*8+\offset(%rsp)
-	movq %rbx, 5*8+\offset(%rsp)
-	UNWIND_HINT_REGS offset=\offset
-	.endm
-
-	.macro POP_EXTRA_REGS
+.macro POP_REGS pop_rdi=1 skip_r11rcx=0
 	popq %r15
 	popq %r14
 	popq %r13
 	popq %r12
 	popq %rbp
 	popq %rbx
-	.endm
-
-	.macro POP_C_REGS
+	.if \skip_r11rcx
+	popq %rsi
+	.else
 	popq %r11
+	.endif
 	popq %r10
 	popq %r9
 	popq %r8
 	popq %rax
+	.if \skip_r11rcx
+	popq %rsi
+	.else
 	popq %rcx
+	.endif
 	popq %rdx
 	popq %rsi
+	.if \pop_rdi
 	popq %rdi
-	.endm
-
-	.macro icebp
-	.byte 0xf1
-	.endm
+	.endif
+.endm
 
 /*
  * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
@@ -178,17 +176,12 @@
  * is just setting the LSB, which makes it an invalid stack address and is also
  * a signal to the unwinder that it's a pt_regs pointer in disguise.
  *
- * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts
+ * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts
  * the original rbp.
  */
 .macro ENCODE_FRAME_POINTER ptregs_offset=0
 #ifdef CONFIG_FRAME_POINTER
-	.if \ptregs_offset
-		leaq \ptregs_offset(%rsp), %rbp
-	.else
-		mov %rsp, %rbp
-	.endif
-	orq	$0x1, %rbp
+	leaq 1+\ptregs_offset(%rsp), %rbp
 #endif
 .endm
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 16c2c02..6ad064c 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -252,8 +252,7 @@
 	 * exist, overwrite the RSB with entries which capture
 	 * speculative execution to prevent attack.
 	 */
-	/* Clobbers %ebx */
-	FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+	FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
 #endif
 
 	/* restore callee-saved registers */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 30c8c53..805f527 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -55,7 +55,7 @@
 
 .macro TRACE_IRQS_FLAGS flags:req
 #ifdef CONFIG_TRACE_IRQFLAGS
-	bt	$9, \flags		/* interrupts off? */
+	btl	$9, \flags		/* interrupts off? */
 	jnc	1f
 	TRACE_IRQS_ON
 1:
@@ -213,7 +213,7 @@
 
 	swapgs
 	/*
-	 * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+	 * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it
 	 * is not required to switch CR3.
 	 */
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)
@@ -227,22 +227,8 @@
 	pushq	%rcx				/* pt_regs->ip */
 GLOBAL(entry_SYSCALL_64_after_hwframe)
 	pushq	%rax				/* pt_regs->orig_ax */
-	pushq	%rdi				/* pt_regs->di */
-	pushq	%rsi				/* pt_regs->si */
-	pushq	%rdx				/* pt_regs->dx */
-	pushq	%rcx				/* pt_regs->cx */
-	pushq	$-ENOSYS			/* pt_regs->ax */
-	pushq	%r8				/* pt_regs->r8 */
-	pushq	%r9				/* pt_regs->r9 */
-	pushq	%r10				/* pt_regs->r10 */
-	pushq	%r11				/* pt_regs->r11 */
-	pushq	%rbx				/* pt_regs->rbx */
-	pushq	%rbp				/* pt_regs->rbp */
-	pushq	%r12				/* pt_regs->r12 */
-	pushq	%r13				/* pt_regs->r13 */
-	pushq	%r14				/* pt_regs->r14 */
-	pushq	%r15				/* pt_regs->r15 */
-	UNWIND_HINT_REGS
+
+	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
 
 	TRACE_IRQS_OFF
 
@@ -321,15 +307,7 @@
 syscall_return_via_sysret:
 	/* rcx and r11 are already restored (see code above) */
 	UNWIND_HINT_EMPTY
-	POP_EXTRA_REGS
-	popq	%rsi	/* skip r11 */
-	popq	%r10
-	popq	%r9
-	popq	%r8
-	popq	%rax
-	popq	%rsi	/* skip rcx */
-	popq	%rdx
-	popq	%rsi
+	POP_REGS pop_rdi=0 skip_r11rcx=1
 
 	/*
 	 * Now all regs are restored except RSP and RDI.
@@ -386,8 +364,7 @@
 	 * exist, overwrite the RSB with entries which capture
 	 * speculative execution to prevent attack.
 	 */
-	/* Clobbers %rbx */
-	FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+	FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
 #endif
 
 	/* restore callee-saved registers */
@@ -471,9 +448,19 @@
  *
  * The invariant is that, if irq_count != -1, then the IRQ stack is in use.
  */
-.macro ENTER_IRQ_STACK regs=1 old_rsp
+.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0
 	DEBUG_ENTRY_ASSERT_IRQS_OFF
+
+	.if \save_ret
+	/*
+	 * If save_ret is set, the original stack contains one additional
+	 * entry -- the return address. Therefore, move the address one
+	 * entry below %rsp to \old_rsp.
+	 */
+	leaq	8(%rsp), \old_rsp
+	.else
 	movq	%rsp, \old_rsp
+	.endif
 
 	.if \regs
 	UNWIND_HINT_REGS base=\old_rsp
@@ -519,6 +506,15 @@
 	.if \regs
 	UNWIND_HINT_REGS indirect=1
 	.endif
+
+	.if \save_ret
+	/*
+	 * Push the return address to the stack. This return address can
+	 * be found at the "real" original RSP, which was offset by 8 at
+	 * the beginning of this macro.
+	 */
+	pushq	-8(\old_rsp)
+	.endif
 .endm
 
 /*
@@ -542,29 +538,65 @@
 .endm
 
 /*
- * Interrupt entry/exit.
+ * Interrupt entry helper function.
  *
- * Interrupt entry points save only callee clobbered registers in fast path.
- *
- * Entry runs with interrupts off.
+ * Entry runs with interrupts off. Stack layout at entry:
+ * +----------------------------------------------------+
+ * | regs->ss						|
+ * | regs->rsp						|
+ * | regs->eflags					|
+ * | regs->cs						|
+ * | regs->ip						|
+ * +----------------------------------------------------+
+ * | regs->orig_ax = ~(interrupt number)		|
+ * +----------------------------------------------------+
+ * | return address					|
+ * +----------------------------------------------------+
  */
-
-/* 0(%rsp): ~(interrupt number) */
-	.macro interrupt func
+ENTRY(interrupt_entry)
+	UNWIND_HINT_FUNC
+	ASM_CLAC
 	cld
 
-	testb	$3, CS-ORIG_RAX(%rsp)
+	testb	$3, CS-ORIG_RAX+8(%rsp)
 	jz	1f
 	SWAPGS
-	call	switch_to_thread_stack
+
+	/*
+	 * Switch to the thread stack. The IRET frame and orig_ax are
+	 * on the stack, as well as the return address. RDI..R12 are
+	 * not (yet) on the stack and space has not (yet) been
+	 * allocated for them.
+	 */
+	pushq	%rdi
+
+	/* Need to switch before accessing the thread stack. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+	 /*
+	  * We have RDI, return address, and orig_ax on the stack on
+	  * top of the IRET frame. That means offset=24
+	  */
+	UNWIND_HINT_IRET_REGS base=%rdi offset=24
+
+	pushq	7*8(%rdi)		/* regs->ss */
+	pushq	6*8(%rdi)		/* regs->rsp */
+	pushq	5*8(%rdi)		/* regs->eflags */
+	pushq	4*8(%rdi)		/* regs->cs */
+	pushq	3*8(%rdi)		/* regs->ip */
+	pushq	2*8(%rdi)		/* regs->orig_ax */
+	pushq	8(%rdi)			/* return address */
+	UNWIND_HINT_FUNC
+
+	movq	(%rdi), %rdi
 1:
 
-	ALLOC_PT_GPREGS_ON_STACK
-	SAVE_C_REGS
-	SAVE_EXTRA_REGS
-	ENCODE_FRAME_POINTER
+	PUSH_AND_CLEAR_REGS save_ret=1
+	ENCODE_FRAME_POINTER 8
 
-	testb	$3, CS(%rsp)
+	testb	$3, CS+8(%rsp)
 	jz	1f
 
 	/*
@@ -572,7 +604,7 @@
 	 *
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode
-	 * (which can take locks).  Since TRACE_IRQS_OFF idempotent,
+	 * (which can take locks).  Since TRACE_IRQS_OFF is idempotent,
 	 * the simplest way to handle it is to just call it twice if
 	 * we enter from user mode.  There's no reason to optimize this since
 	 * TRACE_IRQS_OFF is a no-op if lockdep is off.
@@ -582,12 +614,15 @@
 	CALL_enter_from_user_mode
 
 1:
-	ENTER_IRQ_STACK old_rsp=%rdi
+	ENTER_IRQ_STACK old_rsp=%rdi save_ret=1
 	/* We entered an interrupt context - irqs are off: */
 	TRACE_IRQS_OFF
 
-	call	\func	/* rdi points to pt_regs */
-	.endm
+	ret
+END(interrupt_entry)
+
+
+/* Interrupt entry/exit. */
 
 	/*
 	 * The interrupt stubs push (~vector+0x80) onto the stack and
@@ -595,9 +630,10 @@
 	 */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
-	ASM_CLAC
 	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
-	interrupt do_IRQ
+	call	interrupt_entry
+	UNWIND_HINT_REGS indirect=1
+	call	do_IRQ	/* rdi points to pt_regs */
 	/* 0(%rsp): old RSP */
 ret_from_intr:
 	DISABLE_INTERRUPTS(CLBR_ANY)
@@ -622,15 +658,7 @@
 	ud2
 1:
 #endif
-	POP_EXTRA_REGS
-	popq	%r11
-	popq	%r10
-	popq	%r9
-	popq	%r8
-	popq	%rax
-	popq	%rcx
-	popq	%rdx
-	popq	%rsi
+	POP_REGS pop_rdi=0
 
 	/*
 	 * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
@@ -688,8 +716,7 @@
 	ud2
 1:
 #endif
-	POP_EXTRA_REGS
-	POP_C_REGS
+	POP_REGS
 	addq	$8, %rsp	/* skip regs->orig_ax */
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
@@ -799,10 +826,11 @@
 .macro apicinterrupt3 num sym do_sym
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS
-	ASM_CLAC
 	pushq	$~(\num)
 .Lcommon_\sym:
-	interrupt \do_sym
+	call	interrupt_entry
+	UNWIND_HINT_REGS indirect=1
+	call	\do_sym	/* rdi points to pt_regs */
 	jmp	ret_from_intr
 END(\sym)
 .endm
@@ -865,34 +893,6 @@
  */
 #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
 
-/*
- * Switch to the thread stack.  This is called with the IRET frame and
- * orig_ax on the stack.  (That is, RDI..R12 are not on the stack and
- * space has not been allocated for them.)
- */
-ENTRY(switch_to_thread_stack)
-	UNWIND_HINT_FUNC
-
-	pushq	%rdi
-	/* Need to switch before accessing the thread stack. */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
-	movq	%rsp, %rdi
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-	UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
-
-	pushq	7*8(%rdi)		/* regs->ss */
-	pushq	6*8(%rdi)		/* regs->rsp */
-	pushq	5*8(%rdi)		/* regs->eflags */
-	pushq	4*8(%rdi)		/* regs->cs */
-	pushq	3*8(%rdi)		/* regs->ip */
-	pushq	2*8(%rdi)		/* regs->orig_ax */
-	pushq	8(%rdi)			/* return address */
-	UNWIND_HINT_FUNC
-
-	movq	(%rdi), %rdi
-	ret
-END(switch_to_thread_stack)
-
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
@@ -908,10 +908,8 @@
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	.endif
 
-	ALLOC_PT_GPREGS_ON_STACK
-
 	.if \paranoid < 2
-	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
+	testb	$3, CS-ORIG_RAX(%rsp)		/* If coming from userspace, switch stacks */
 	jnz	.Lfrom_usermode_switch_stack_\@
 	.endif
 
@@ -1121,9 +1119,7 @@
 	addq	$0x30, %rsp
 	UNWIND_HINT_IRET_REGS
 	pushq	$-1 /* orig_ax = -1 => not a system call */
-	ALLOC_PT_GPREGS_ON_STACK
-	SAVE_C_REGS
-	SAVE_EXTRA_REGS
+	PUSH_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 	jmp	error_exit
 END(xen_failsafe_callback)
@@ -1170,8 +1166,7 @@
 ENTRY(paranoid_entry)
 	UNWIND_HINT_FUNC
 	cld
-	SAVE_C_REGS 8
-	SAVE_EXTRA_REGS 8
+	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
 	movl	$1, %ebx
 	movl	$MSR_GS_BASE, %ecx
@@ -1211,21 +1206,20 @@
 	jmp	.Lparanoid_exit_restore
 .Lparanoid_exit_no_swapgs:
 	TRACE_IRQS_IRETQ_DEBUG
+	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 .Lparanoid_exit_restore:
 	jmp restore_regs_and_return_to_kernel
 END(paranoid_exit)
 
 /*
- * Save all registers in pt_regs, and switch gs if needed.
+ * Save all registers in pt_regs, and switch GS if needed.
  * Return: EBX=0: came from user mode; EBX=1: otherwise
  */
 ENTRY(error_entry)
 	UNWIND_HINT_FUNC
 	cld
-	SAVE_C_REGS 8
-	SAVE_EXTRA_REGS 8
+	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
-	xorl	%ebx, %ebx
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
 
@@ -1406,22 +1400,7 @@
 	pushq	1*8(%rdx)	/* pt_regs->rip */
 	UNWIND_HINT_IRET_REGS
 	pushq   $-1		/* pt_regs->orig_ax */
-	pushq   %rdi		/* pt_regs->di */
-	pushq   %rsi		/* pt_regs->si */
-	pushq   (%rdx)		/* pt_regs->dx */
-	pushq   %rcx		/* pt_regs->cx */
-	pushq   %rax		/* pt_regs->ax */
-	pushq   %r8		/* pt_regs->r8 */
-	pushq   %r9		/* pt_regs->r9 */
-	pushq   %r10		/* pt_regs->r10 */
-	pushq   %r11		/* pt_regs->r11 */
-	pushq	%rbx		/* pt_regs->rbx */
-	pushq	%rbp		/* pt_regs->rbp */
-	pushq	%r12		/* pt_regs->r12 */
-	pushq	%r13		/* pt_regs->r13 */
-	pushq	%r14		/* pt_regs->r14 */
-	pushq	%r15		/* pt_regs->r15 */
-	UNWIND_HINT_REGS
+	PUSH_AND_CLEAR_REGS rdx=(%rdx)
 	ENCODE_FRAME_POINTER
 
 	/*
@@ -1631,7 +1610,6 @@
 	 * frame to point back to repeat_nmi.
 	 */
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
-	ALLOC_PT_GPREGS_ON_STACK
 
 	/*
 	 * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
@@ -1655,8 +1633,7 @@
 nmi_swapgs:
 	SWAPGS_UNSAFE_STACK
 nmi_restore:
-	POP_EXTRA_REGS
-	POP_C_REGS
+	POP_REGS
 
 	/*
 	 * Skip orig_ax and the "outermost" frame to point RSP at the "iret"
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 98d5358..e811dd9 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -85,15 +85,25 @@
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorl	%r8d, %r8d		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorl	%r9d, %r9d		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorl	%r10d, %r10d		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorl	%r11d, %r11d		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
+	xorl	%r12d, %r12d		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
+	xorl	%r13d, %r13d		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
+	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
+	xorl	%r15d, %r15d		/* nospec   r15 */
 	cld
 
 	/*
@@ -214,15 +224,25 @@
 	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorl	%r8d, %r8d		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorl	%r9d, %r9d		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorl	%r10d, %r10d		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorl	%r11d, %r11d		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
+	xorl	%r12d, %r12d		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
+	xorl	%r13d, %r13d		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
+	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
+	xorl	%r15d, %r15d		/* nospec   r15 */
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -278,9 +298,9 @@
 	 */
 	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
 
-	xorq	%r8, %r8
-	xorq	%r9, %r9
-	xorq	%r10, %r10
+	xorl	%r8d, %r8d
+	xorl	%r9d, %r9d
+	xorl	%r10d, %r10d
 	swapgs
 	sysretl
 END(entry_SYSCALL_compat)
@@ -327,10 +347,23 @@
 	 */
 	movl	%eax, %eax
 
+	/* switch to thread stack expects orig_ax and rdi to be pushed */
 	pushq	%rax			/* pt_regs->orig_ax */
+	pushq	%rdi			/* pt_regs->di */
 
-	/* switch to thread stack expects orig_ax to be pushed */
-	call	switch_to_thread_stack
+	/* Need to switch before accessing the thread stack. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+	pushq	6*8(%rdi)		/* regs->ss */
+	pushq	5*8(%rdi)		/* regs->rsp */
+	pushq	4*8(%rdi)		/* regs->eflags */
+	pushq	3*8(%rdi)		/* regs->cs */
+	pushq	2*8(%rdi)		/* regs->ip */
+	pushq	1*8(%rdi)		/* regs->orig_ax */
+
+	movq	(%rdi), %rdi		/* restore %rdi */
 
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
@@ -338,15 +371,25 @@
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorl	%r8d, %r8d		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorl	%r9d, %r9d		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorl	%r10d, %r10d		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorl	%r11d, %r11d		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   %r12                    /* pt_regs->r12 */
+	xorl	%r12d, %r12d		/* nospec   r12 */
 	pushq   %r13                    /* pt_regs->r13 */
+	xorl	%r13d, %r13d		/* nospec   r13 */
 	pushq   %r14                    /* pt_regs->r14 */
+	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   %r15                    /* pt_regs->r15 */
+	xorl	%r15d, %r15d		/* nospec   r15 */
 	cld
 
 	/*
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 731153a..56457cb 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3559,7 +3559,7 @@
 		break;
 
 	case INTEL_FAM6_SANDYBRIDGE_X:
-		switch (cpu_data(cpu).x86_mask) {
+		switch (cpu_data(cpu).x86_stepping) {
 		case 6: rev = 0x618; break;
 		case 7: rev = 0x70c; break;
 		}
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index ae64d0b..cf372b9 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1186,7 +1186,7 @@
 	 * on PMU interrupt
 	 */
 	if (boot_cpu_data.x86_model == 28
-	    && boot_cpu_data.x86_mask < 10) {
+	    && boot_cpu_data.x86_stepping < 10) {
 		pr_cont("LBR disabled due to erratum");
 		return;
 	}
diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c
index a5604c3..408879b 100644
--- a/arch/x86/events/intel/p6.c
+++ b/arch/x86/events/intel/p6.c
@@ -234,7 +234,7 @@
 
 static __init void p6_pmu_rdpmc_quirk(void)
 {
-	if (boot_cpu_data.x86_mask < 9) {
+	if (boot_cpu_data.x86_stepping < 9) {
 		/*
 		 * PPro erratum 26; fixed in stepping 9 and above.
 		 */
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 44f5d79..1188172 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -94,7 +94,7 @@
 	if (boot_cpu_data.x86 == 0x0F &&
 	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
 	    boot_cpu_data.x86_model <= 0x05 &&
-	    boot_cpu_data.x86_mask < 0x0A)
+	    boot_cpu_data.x86_stepping < 0x0A)
 		return 1;
 	else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E))
 		return 1;
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index 4d4015d..c356098 100644
--- a/arch/x86/include/asm/apm.h
+++ b/arch/x86/include/asm/apm.h
@@ -7,6 +7,8 @@
 #ifndef _ASM_X86_MACH_DEFAULT_APM_H
 #define _ASM_X86_MACH_DEFAULT_APM_H
 
+#include <asm/nospec-branch.h>
+
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
 		"pushl %%ds\n\t" \
@@ -32,6 +34,7 @@
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -44,6 +47,7 @@
 		  "=S" (*esi)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 }
 
 static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
@@ -56,6 +60,7 @@
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -68,6 +73,7 @@
 		  "=S" (si)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 	return error;
 }
 
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 4d11161..1908214 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -38,7 +38,4 @@
 INDIRECT_THUNK(si)
 INDIRECT_THUNK(di)
 INDIRECT_THUNK(bp)
-asmlinkage void __fill_rsb(void);
-asmlinkage void __clear_rsb(void);
-
 #endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 30d4061..e1259f0 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -40,7 +40,7 @@
 
 	asm ("cmp %1,%2; sbb %0,%0;"
 			:"=r" (mask)
-			:"r"(size),"r" (index)
+			:"g"(size),"r" (index)
 			:"cc");
 	return mask;
 }
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 3fa0398..9f645ba 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -78,7 +78,7 @@
 			: "iq" ((u8)CONST_MASK(nr))
 			: "memory");
 	} else {
-		asm volatile(LOCK_PREFIX "bts %1,%0"
+		asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
 			: BITOP_ADDR(addr) : "Ir" (nr) : "memory");
 	}
 }
@@ -94,7 +94,7 @@
  */
 static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
+	asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
 
 /**
@@ -115,7 +115,7 @@
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" ((u8)~CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX "btr %1,%0"
+		asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
 			: BITOP_ADDR(addr)
 			: "Ir" (nr));
 	}
@@ -137,7 +137,7 @@
 
 static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr));
 }
 
 static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
@@ -182,7 +182,7 @@
  */
 static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr));
 }
 
 /**
@@ -201,7 +201,7 @@
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" ((u8)CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX "btc %1,%0"
+		asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
 			: BITOP_ADDR(addr)
 			: "Ir" (nr));
 	}
@@ -217,7 +217,8 @@
  */
 static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c);
+	GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts),
+	                 *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -246,7 +247,7 @@
 {
 	bool oldbit;
 
-	asm("bts %2,%1"
+	asm(__ASM_SIZE(bts) " %2,%1"
 	    CC_SET(c)
 	    : CC_OUT(c) (oldbit), ADDR
 	    : "Ir" (nr));
@@ -263,7 +264,8 @@
  */
 static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c);
+	GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr),
+	                 *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -286,7 +288,7 @@
 {
 	bool oldbit;
 
-	asm volatile("btr %2,%1"
+	asm volatile(__ASM_SIZE(btr) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr));
@@ -298,7 +300,7 @@
 {
 	bool oldbit;
 
-	asm volatile("btc %2,%1"
+	asm volatile(__ASM_SIZE(btc) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr) : "memory");
@@ -316,7 +318,8 @@
  */
 static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c);
+	GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc),
+	                 *addr, "Ir", nr, "%0", c);
 }
 
 static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
@@ -329,7 +332,7 @@
 {
 	bool oldbit;
 
-	asm volatile("bt %2,%1"
+	asm volatile(__ASM_SIZE(bt) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr));
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 34d99af4..6804d66 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -5,23 +5,20 @@
 #include <linux/stringify.h>
 
 /*
- * Since some emulators terminate on UD2, we cannot use it for WARN.
- * Since various instruction decoders disagree on the length of UD1,
- * we cannot use it either. So use UD0 for WARN.
+ * Despite that some emulators terminate on UD2, we use it for WARN().
  *
- * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas
- *  our kernel decoder thinks it takes a ModRM byte, which seems consistent
- *  with various things like the Intel SDM instruction encoding rules)
+ * Since various instruction decoders/specs disagree on the encoding of
+ * UD0/UD1.
  */
 
-#define ASM_UD0		".byte 0x0f, 0xff"
+#define ASM_UD0		".byte 0x0f, 0xff" /* + ModRM (for Intel) */
 #define ASM_UD1		".byte 0x0f, 0xb9" /* + ModRM */
 #define ASM_UD2		".byte 0x0f, 0x0b"
 
 #define INSN_UD0	0xff0f
 #define INSN_UD2	0x0b0f
 
-#define LEN_UD0		2
+#define LEN_UD2		2
 
 #ifdef CONFIG_GENERIC_BUG
 
@@ -77,7 +74,11 @@
 	unreachable();						\
 } while (0)
 
-#define __WARN_FLAGS(flags)	_BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags))
+#define __WARN_FLAGS(flags)					\
+do {								\
+	_BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags));		\
+	annotate_reachable();					\
+} while (0)
 
 #include <asm-generic/bug.h>
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 70eddb3..736771c 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -148,45 +148,46 @@
  */
 static __always_inline __pure bool _static_cpu_has(u16 bit)
 {
-		asm_volatile_goto("1: jmp 6f\n"
-			 "2:\n"
-			 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
-			         "((5f-4f) - (2b-1b)),0x90\n"
-			 "3:\n"
-			 ".section .altinstructions,\"a\"\n"
-			 " .long 1b - .\n"		/* src offset */
-			 " .long 4f - .\n"		/* repl offset */
-			 " .word %P1\n"			/* always replace */
-			 " .byte 3b - 1b\n"		/* src len */
-			 " .byte 5f - 4f\n"		/* repl len */
-			 " .byte 3b - 2b\n"		/* pad len */
-			 ".previous\n"
-			 ".section .altinstr_replacement,\"ax\"\n"
-			 "4: jmp %l[t_no]\n"
-			 "5:\n"
-			 ".previous\n"
-			 ".section .altinstructions,\"a\"\n"
-			 " .long 1b - .\n"		/* src offset */
-			 " .long 0\n"			/* no replacement */
-			 " .word %P0\n"			/* feature bit */
-			 " .byte 3b - 1b\n"		/* src len */
-			 " .byte 0\n"			/* repl len */
-			 " .byte 0\n"			/* pad len */
-			 ".previous\n"
-			 ".section .altinstr_aux,\"ax\"\n"
-			 "6:\n"
-			 " testb %[bitnum],%[cap_byte]\n"
-			 " jnz %l[t_yes]\n"
-			 " jmp %l[t_no]\n"
-			 ".previous\n"
-			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS),
-			     [bitnum] "i" (1 << (bit & 7)),
-			     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
-			 : : t_yes, t_no);
-	t_yes:
-		return true;
-	t_no:
-		return false;
+	asm_volatile_goto("1: jmp 6f\n"
+		 "2:\n"
+		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
+			 "((5f-4f) - (2b-1b)),0x90\n"
+		 "3:\n"
+		 ".section .altinstructions,\"a\"\n"
+		 " .long 1b - .\n"		/* src offset */
+		 " .long 4f - .\n"		/* repl offset */
+		 " .word %P[always]\n"		/* always replace */
+		 " .byte 3b - 1b\n"		/* src len */
+		 " .byte 5f - 4f\n"		/* repl len */
+		 " .byte 3b - 2b\n"		/* pad len */
+		 ".previous\n"
+		 ".section .altinstr_replacement,\"ax\"\n"
+		 "4: jmp %l[t_no]\n"
+		 "5:\n"
+		 ".previous\n"
+		 ".section .altinstructions,\"a\"\n"
+		 " .long 1b - .\n"		/* src offset */
+		 " .long 0\n"			/* no replacement */
+		 " .word %P[feature]\n"		/* feature bit */
+		 " .byte 3b - 1b\n"		/* src len */
+		 " .byte 0\n"			/* repl len */
+		 " .byte 0\n"			/* pad len */
+		 ".previous\n"
+		 ".section .altinstr_aux,\"ax\"\n"
+		 "6:\n"
+		 " testb %[bitnum],%[cap_byte]\n"
+		 " jnz %l[t_yes]\n"
+		 " jmp %l[t_no]\n"
+		 ".previous\n"
+		 : : [feature]  "i" (bit),
+		     [always]   "i" (X86_FEATURE_ALWAYS),
+		     [bitnum]   "i" (1 << (bit & 7)),
+		     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
+		 : : t_yes, t_no);
+t_yes:
+	return true;
+t_no:
+	return false;
 }
 
 #define static_cpu_has(bit)					\
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 0dfe4d3..f41079d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -213,6 +213,7 @@
 #define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
 
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
+#define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 85f6ccb..a399c1e 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -6,6 +6,7 @@
 #include <asm/pgtable.h>
 #include <asm/processor-flags.h>
 #include <asm/tlb.h>
+#include <asm/nospec-branch.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
@@ -36,8 +37,18 @@
 
 extern asmlinkage unsigned long efi_call_phys(void *, ...);
 
-#define arch_efi_call_virt_setup()	kernel_fpu_begin()
-#define arch_efi_call_virt_teardown()	kernel_fpu_end()
+#define arch_efi_call_virt_setup()					\
+({									\
+	kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
+})
+
+#define arch_efi_call_virt_teardown()					\
+({									\
+	firmware_restrict_branch_speculation_end();			\
+	kernel_fpu_end();						\
+})
+
 
 /*
  * Wrap all the virtual calls in a way that forces the parameters on the stack.
@@ -73,6 +84,7 @@
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
 									\
 	if (efi_scratch.use_pgd) {					\
 		efi_scratch.prev_cr3 = __read_cr3();			\
@@ -91,6 +103,7 @@
 		__flush_tlb_all();					\
 	}								\
 									\
+	firmware_restrict_branch_speculation_end();			\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
 })
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dd6f57a..b605a5b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -507,6 +507,7 @@
 	u64 smi_count;
 	bool tpr_access_reporting;
 	u64 ia32_xss;
+	u64 microcode_version;
 
 	/*
 	 * Paging state of the vcpu
@@ -1095,6 +1096,8 @@
 	int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
 	int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
+
+	int (*get_msr_feature)(struct kvm_msr_entry *entry);
 };
 
 struct kvm_arch_async_pf {
@@ -1464,7 +1467,4 @@
 #define put_smstate(type, buf, offset, val)                      \
 	*(type *)((buf) + (offset) - 0x7e00) = val
 
-void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-		unsigned long start, unsigned long end);
-
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 55520cec..7fb1047 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -37,7 +37,12 @@
 
 struct device;
 
-enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
+enum ucode_state {
+	UCODE_OK	= 0,
+	UCODE_UPDATED,
+	UCODE_NFOUND,
+	UCODE_ERROR,
+};
 
 struct microcode_ops {
 	enum ucode_state (*request_microcode_user) (int cpu,
@@ -54,7 +59,7 @@
 	 * are being called.
 	 * See also the "Synchronization" section in microcode_core.c.
 	 */
-	int (*apply_microcode) (int cpu);
+	enum ucode_state (*apply_microcode) (int cpu);
 	int (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
 };
 
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index c931b88..1de72ce 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -74,6 +74,7 @@
 	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/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 4d57894..d0dabea 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -6,6 +6,51 @@
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
+#include <asm/msr-index.h>
+
+/*
+ * Fill the CPU return stack buffer.
+ *
+ * Each entry in the RSB, if used for a speculative 'ret', contains an
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
+ *
+ * This is required in various cases for retpoline and IBRS-based
+ * mitigations for the Spectre variant 2 vulnerability. Sometimes to
+ * eliminate potentially bogus entries from the RSB, and sometimes
+ * purely to ensure that it doesn't get empty, which on some CPUs would
+ * allow predictions from other (unwanted!) sources to be used.
+ *
+ * We define a CPP macro such that it can be used from both .S files and
+ * inline assembly. It's possible to do a .macro and then include that
+ * from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
+ */
+
+#define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
+#define RSB_FILL_LOOPS		16	/* To avoid underflow */
+
+/*
+ * Google experimented with loop-unrolling and this turned out to be
+ * the optimal version — two calls, each with their own speculation
+ * trap should their return address end up getting used, in a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr, sp)	\
+	mov	$(nr/2), reg;			\
+771:						\
+	call	772f;				\
+773:	/* speculation trap */			\
+	pause;					\
+	lfence;					\
+	jmp	773b;				\
+772:						\
+	call	774f;				\
+775:	/* speculation trap */			\
+	pause;					\
+	lfence;					\
+	jmp	775b;				\
+774:						\
+	dec	reg;				\
+	jnz	771b;				\
+	add	$(BITS_PER_LONG/8) * nr, sp;
 
 #ifdef __ASSEMBLY__
 
@@ -23,6 +68,18 @@
 .endm
 
 /*
+ * This should be used immediately before an indirect jump/call. It tells
+ * objtool the subsequent indirect jump/call is vouched safe for retpoline
+ * builds.
+ */
+.macro ANNOTATE_RETPOLINE_SAFE
+	.Lannotate_\@:
+	.pushsection .discard.retpoline_safe
+	_ASM_PTR .Lannotate_\@
+	.popsection
+.endm
+
+/*
  * These are the bare retpoline primitives for indirect jmp and call.
  * Do not use these directly; they only exist to make the ALTERNATIVE
  * invocation below less ugly.
@@ -58,9 +115,9 @@
 .macro JMP_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
 	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE_2 __stringify(jmp *\reg),				\
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg),	\
 		__stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE,	\
-		__stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
 #else
 	jmp	*\reg
 #endif
@@ -69,18 +126,25 @@
 .macro CALL_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
 	ANNOTATE_NOSPEC_ALTERNATIVE
-	ALTERNATIVE_2 __stringify(call *\reg),				\
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg),	\
 		__stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
-		__stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD
+		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD
 #else
 	call	*\reg
 #endif
 .endm
 
-/* This clobbers the BX register */
-.macro FILL_RETURN_BUFFER nr:req ftr:req
+ /*
+  * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
+  * monstrosity above, manually.
+  */
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
 #ifdef CONFIG_RETPOLINE
-	ALTERNATIVE "", "call __clear_rsb", \ftr
+	ANNOTATE_NOSPEC_ALTERNATIVE
+	ALTERNATIVE "jmp .Lskip_rsb_\@",				\
+		__stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP))	\
+		\ftr
+.Lskip_rsb_\@:
 #endif
 .endm
 
@@ -92,6 +156,12 @@
 	".long 999b - .\n\t"					\
 	".popsection\n\t"
 
+#define ANNOTATE_RETPOLINE_SAFE					\
+	"999:\n\t"						\
+	".pushsection .discard.retpoline_safe\n\t"		\
+	_ASM_PTR " 999b\n\t"					\
+	".popsection\n\t"
+
 #if defined(CONFIG_X86_64) && defined(RETPOLINE)
 
 /*
@@ -101,6 +171,7 @@
 # define CALL_NOSPEC						\
 	ANNOTATE_NOSPEC_ALTERNATIVE				\
 	ALTERNATIVE(						\
+	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
 	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
 	X86_FEATURE_RETPOLINE)
@@ -155,20 +226,90 @@
 static inline void vmexit_fill_RSB(void)
 {
 #ifdef CONFIG_RETPOLINE
-	alternative_input("",
-			  "call __fill_rsb",
-			  X86_FEATURE_RETPOLINE,
-			  ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory"));
+	unsigned long loops;
+
+	asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
+		      ALTERNATIVE("jmp 910f",
+				  __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
+				  X86_FEATURE_RETPOLINE)
+		      "910:"
+		      : "=r" (loops), ASM_CALL_CONSTRAINT
+		      : : "memory" );
 #endif
 }
 
+#define alternative_msr_write(_msr, _val, _feature)		\
+	asm volatile(ALTERNATIVE("",				\
+				 "movl %[msr], %%ecx\n\t"	\
+				 "movl %[val], %%eax\n\t"	\
+				 "movl $0, %%edx\n\t"		\
+				 "wrmsr",			\
+				 _feature)			\
+		     : : [msr] "i" (_msr), [val] "i" (_val)	\
+		     : "eax", "ecx", "edx", "memory")
+
 static inline void indirect_branch_prediction_barrier(void)
 {
-	alternative_input("",
-			  "call __ibp_barrier",
-			  X86_FEATURE_USE_IBPB,
-			  ASM_NO_INPUT_CLOBBER("eax", "ecx", "edx", "memory"));
+	alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
+			      X86_FEATURE_USE_IBPB);
 }
 
+/*
+ * With retpoline, we must use IBRS to restrict branch prediction
+ * before calling into firmware.
+ *
+ * (Implemented as CPP macros due to header hell.)
+ */
+#define firmware_restrict_branch_speculation_start()			\
+do {									\
+	preempt_disable();						\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,	\
+			      X86_FEATURE_USE_IBRS_FW);			\
+} while (0)
+
+#define firmware_restrict_branch_speculation_end()			\
+do {									\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,			\
+			      X86_FEATURE_USE_IBRS_FW);			\
+	preempt_enable();						\
+} while (0)
+
 #endif /* __ASSEMBLY__ */
+
+/*
+ * Below is used in the eBPF JIT compiler and emits the byte sequence
+ * for the following assembly:
+ *
+ * With retpolines configured:
+ *
+ *    callq do_rop
+ *  spec_trap:
+ *    pause
+ *    lfence
+ *    jmp spec_trap
+ *  do_rop:
+ *    mov %rax,(%rsp)
+ *    retq
+ *
+ * Without retpolines configured:
+ *
+ *    jmp *%rax
+ */
+#ifdef CONFIG_RETPOLINE
+# define RETPOLINE_RAX_BPF_JIT_SIZE	17
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
+	/* spec_trap: */					\
+	EMIT2(0xF3, 0x90);       /* pause */			\
+	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
+	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
+	/* do_rop: */						\
+	EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */	\
+	EMIT1(0xC3);             /* retq */
+#else
+# define RETPOLINE_RAX_BPF_JIT_SIZE	2
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT2(0xFF, 0xE0);	 /* jmp *%rax */
+#endif
+
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 4baa6bc..d652a38 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -52,10 +52,6 @@
 
 void copy_page(void *to, void *from);
 
-#ifdef CONFIG_X86_MCE
-#define arch_unmap_kpfn arch_unmap_kpfn
-#endif
-
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 892df37..c83a2f4 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -7,6 +7,7 @@
 #ifdef CONFIG_PARAVIRT
 #include <asm/pgtable_types.h>
 #include <asm/asm.h>
+#include <asm/nospec-branch.h>
 
 #include <asm/paravirt_types.h>
 
@@ -297,9 +298,9 @@
 {
 	PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
 }
-static inline void __flush_tlb_single(unsigned long addr)
+static inline void __flush_tlb_one_user(unsigned long addr)
 {
-	PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
+	PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr);
 }
 
 static inline void flush_tlb_others(const struct cpumask *cpumask,
@@ -879,23 +880,27 @@
 
 #define INTERRUPT_RETURN						\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,	\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret))
+		  ANNOTATE_RETPOLINE_SAFE;					\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);)
 
 #define DISABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
 		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
+		  ANNOTATE_RETPOLINE_SAFE;					\
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);	\
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #define ENABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,	\
 		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
+		  ANNOTATE_RETPOLINE_SAFE;					\
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #ifdef CONFIG_X86_32
 #define GET_CR0_INTO_EAX				\
 	push %ecx; push %edx;				\
+	ANNOTATE_RETPOLINE_SAFE;				\
 	call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0);	\
 	pop %edx; pop %ecx
 #else	/* !CONFIG_X86_32 */
@@ -917,21 +922,25 @@
  */
 #define SWAPGS								\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
-		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs)		\
+		  ANNOTATE_RETPOLINE_SAFE;					\
+		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs);		\
 		 )
 
 #define GET_CR2_INTO_RAX				\
-	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2)
+	ANNOTATE_RETPOLINE_SAFE;				\
+	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);
 
 #define USERGS_SYSRET64							\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
 		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+		  ANNOTATE_RETPOLINE_SAFE;					\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);)
 
 #ifdef CONFIG_DEBUG_ENTRY
 #define SAVE_FLAGS(clobbers)                                        \
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
 		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
+		  ANNOTATE_RETPOLINE_SAFE;				    \
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl);    \
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 #endif
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 6ec54d0..180bc0b 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -43,6 +43,7 @@
 #include <asm/desc_defs.h>
 #include <asm/kmap_types.h>
 #include <asm/pgtable_types.h>
+#include <asm/nospec-branch.h>
 
 struct page;
 struct thread_struct;
@@ -217,7 +218,7 @@
 	/* TLB operations */
 	void (*flush_tlb_user)(void);
 	void (*flush_tlb_kernel)(void);
-	void (*flush_tlb_single)(unsigned long addr);
+	void (*flush_tlb_one_user)(unsigned long addr);
 	void (*flush_tlb_others)(const struct cpumask *cpus,
 				 const struct flush_tlb_info *info);
 
@@ -392,7 +393,9 @@
  * offset into the paravirt_patch_template structure, and can therefore be
  * freely converted back into a structure offset.
  */
-#define PARAVIRT_CALL	"call *%c[paravirt_opptr];"
+#define PARAVIRT_CALL					\
+	ANNOTATE_RETPOLINE_SAFE				\
+	"call *%c[paravirt_opptr];"
 
 /*
  * These macros are intended to wrap calls through one of the paravirt
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index ba3c523..a06b073 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -526,7 +526,7 @@
 {
 	bool oldbit;
 
-	asm volatile("bt "__percpu_arg(2)",%1"
+	asm volatile("btl "__percpu_arg(2)",%1"
 			CC_SET(c)
 			: CC_OUT(c) (oldbit)
 			: "m" (*(unsigned long __percpu *)addr), "Ir" (nr));
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 63c2552..b444d83 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -350,14 +350,14 @@
 {
 	pmdval_t v = native_pmd_val(pmd);
 
-	return __pmd(v | set);
+	return native_make_pmd(v | set);
 }
 
 static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
 {
 	pmdval_t v = native_pmd_val(pmd);
 
-	return __pmd(v & ~clear);
+	return native_make_pmd(v & ~clear);
 }
 
 static inline pmd_t pmd_mkold(pmd_t pmd)
@@ -409,14 +409,14 @@
 {
 	pudval_t v = native_pud_val(pud);
 
-	return __pud(v | set);
+	return native_make_pud(v | set);
 }
 
 static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
 {
 	pudval_t v = native_pud_val(pud);
 
-	return __pud(v & ~clear);
+	return native_make_pud(v & ~clear);
 }
 
 static inline pud_t pud_mkold(pud_t pud)
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index e67c062..b3ec519 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -32,6 +32,7 @@
 static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
 void paging_init(void);
+void sync_initial_page_table(void);
 
 /*
  * Define this if things work differently on an i386 and an i486:
@@ -61,7 +62,7 @@
 #define kpte_clear_flush(ptep, vaddr)		\
 do {						\
 	pte_clear(&init_mm, (vaddr), (ptep));	\
-	__flush_tlb_one((vaddr));		\
+	__flush_tlb_one_kernel((vaddr));		\
 } while (0)
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 81462e9..1149d21 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -28,6 +28,7 @@
 #define swapper_pg_dir init_top_pgt
 
 extern void paging_init(void);
+static inline void sync_initial_page_table(void) { }
 
 #define pte_ERROR(e)					\
 	pr_err("%s:%d: bad pte %p(%016lx)\n",		\
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 3696398..246f15b 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -323,6 +323,11 @@
 #else
 #include <asm-generic/pgtable-nopud.h>
 
+static inline pud_t native_make_pud(pudval_t val)
+{
+	return (pud_t) { .p4d.pgd = native_make_pgd(val) };
+}
+
 static inline pudval_t native_pud_val(pud_t pud)
 {
 	return native_pgd_val(pud.p4d.pgd);
@@ -344,6 +349,11 @@
 #else
 #include <asm-generic/pgtable-nopmd.h>
 
+static inline pmd_t native_make_pmd(pmdval_t val)
+{
+	return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) };
+}
+
 static inline pmdval_t native_pmd_val(pmd_t pmd)
 {
 	return native_pgd_val(pmd.pud.p4d.pgd);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 793bae7..b0ccd48 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -91,7 +91,7 @@
 	__u8			x86;		/* CPU family */
 	__u8			x86_vendor;	/* CPU vendor */
 	__u8			x86_model;
-	__u8			x86_mask;
+	__u8			x86_stepping;
 #ifdef CONFIG_X86_64
 	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
 	int			x86_tlbsize;
@@ -109,7 +109,7 @@
 	char			x86_vendor_id[16];
 	char			x86_model_id[64];
 	/* in KB - valid for CPUS which support this call: */
-	int			x86_cache_size;
+	unsigned int		x86_cache_size;
 	int			x86_cache_alignment;	/* In bytes */
 	/* Cache QoS architectural values: */
 	int			x86_cache_max_rmid;	/* max index */
@@ -977,7 +977,5 @@
 
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
-
-void __ibp_barrier(void);
-
+void microcode_check(void);
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 4e44250..4cf11d8 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -17,7 +17,7 @@
 #define _REFCOUNT_EXCEPTION				\
 	".pushsection .text..refcount\n"		\
 	"111:\tlea %[counter], %%" _ASM_CX "\n"		\
-	"112:\t" ASM_UD0 "\n"				\
+	"112:\t" ASM_UD2 "\n"				\
 	ASM_UNREACHABLE					\
 	".popsection\n"					\
 	"113:\n"					\
@@ -67,13 +67,13 @@
 bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 {
 	GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO,
-				  r->refs.counter, "er", i, "%0", e);
+				  r->refs.counter, "er", i, "%0", e, "cx");
 }
 
 static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
 {
 	GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO,
-				 r->refs.counter, "%0", e);
+				 r->refs.counter, "%0", e, "cx");
 }
 
 static __always_inline __must_check
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index f91c365..4914a3e 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -2,8 +2,7 @@
 #ifndef _ASM_X86_RMWcc
 #define _ASM_X86_RMWcc
 
-#define __CLOBBERS_MEM		"memory"
-#define __CLOBBERS_MEM_CC_CX	"memory", "cc", "cx"
+#define __CLOBBERS_MEM(clb...)	"memory", ## clb
 
 #if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO)
 
@@ -40,18 +39,19 @@
 #endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
 
 #define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
-	__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM)
+	__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())
 
-#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc)		\
+#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\
 	__GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc,			\
-		    __CLOBBERS_MEM_CC_CX)
+		    __CLOBBERS_MEM(clobbers))
 
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc,		\
-		    __CLOBBERS_MEM, vcon (val))
+		    __CLOBBERS_MEM(), vcon (val))
 
-#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc)	\
+#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc,	\
+				  clobbers...)				\
 	__GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc,	\
-		    __CLOBBERS_MEM_CC_CX, vcon (val))
+		    __CLOBBERS_MEM(clobbers), vcon (val))
 
 #endif /* _ASM_X86_RMWcc */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 461f53d..a418976 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -129,6 +129,7 @@
 void cpu_disable_common(void);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
+void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
 void common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 2b8f18c..84137c2 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -140,7 +140,7 @@
 #else
 #define __flush_tlb() __native_flush_tlb()
 #define __flush_tlb_global() __native_flush_tlb_global()
-#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
+#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
 #endif
 
 static inline bool tlb_defer_switch_to_init_mm(void)
@@ -400,7 +400,7 @@
 /*
  * flush one page in the user mapping
  */
-static inline void __native_flush_tlb_single(unsigned long addr)
+static inline void __native_flush_tlb_one_user(unsigned long addr)
 {
 	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
 
@@ -437,18 +437,31 @@
 /*
  * flush one page in the kernel mapping
  */
-static inline void __flush_tlb_one(unsigned long addr)
+static inline void __flush_tlb_one_kernel(unsigned long addr)
 {
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
-	__flush_tlb_single(addr);
+
+	/*
+	 * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its
+	 * paravirt equivalent.  Even with PCID, this is sufficient: we only
+	 * use PCID if we also use global PTEs for the kernel mapping, and
+	 * INVLPG flushes global translations across all address spaces.
+	 *
+	 * If PTI is on, then the kernel is mapped with non-global PTEs, and
+	 * __flush_tlb_one_user() will flush the given address for the current
+	 * kernel address space and for its usermode counterpart, but it does
+	 * not flush it for other address spaces.
+	 */
+	__flush_tlb_one_user(addr);
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	/*
-	 * __flush_tlb_single() will have cleared the TLB entry for this ASID,
-	 * but since kernel space is replicated across all, we must also
-	 * invalidate all others.
+	 * See above.  We need to propagate the flush to all other address
+	 * spaces.  In principle, we only need to propagate it to kernelmode
+	 * address spaces, but the extra bookkeeping we would need is not
+	 * worth it.
 	 */
 	invalidate_other_asid();
 }
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 197c2e6..0994143 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -241,24 +241,24 @@
 #define HV_X64_MSR_REENLIGHTENMENT_CONTROL	0x40000106
 
 struct hv_reenlightenment_control {
-	u64 vector:8;
-	u64 reserved1:8;
-	u64 enabled:1;
-	u64 reserved2:15;
-	u64 target_vp:32;
+	__u64 vector:8;
+	__u64 reserved1:8;
+	__u64 enabled:1;
+	__u64 reserved2:15;
+	__u64 target_vp:32;
 };
 
 #define HV_X64_MSR_TSC_EMULATION_CONTROL	0x40000107
 #define HV_X64_MSR_TSC_EMULATION_STATUS		0x40000108
 
 struct hv_tsc_emulation_control {
-	u64 enabled:1;
-	u64 reserved:63;
+	__u64 enabled:1;
+	__u64 reserved:63;
 };
 
 struct hv_tsc_emulation_status {
-	u64 inprogress:1;
-	u64 reserved:63;
+	__u64 inprogress:1;
+	__u64 reserved:63;
 };
 
 #define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 7a2ade4..6cfa9c8 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -26,6 +26,7 @@
 #define KVM_FEATURE_PV_EOI		6
 #define KVM_FEATURE_PV_UNHALT		7
 #define KVM_FEATURE_PV_TLB_FLUSH	9
+#define KVM_FEATURE_ASYNC_PF_VMEXIT	10
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 6db28f1..c88e0b1 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -235,7 +235,7 @@
 	if (boot_cpu_data.x86 == 0x10 &&
 	    boot_cpu_data.x86_model >= 0x8 &&
 	    (boot_cpu_data.x86_model > 0x9 ||
-	     boot_cpu_data.x86_mask >= 0x1))
+	     boot_cpu_data.x86_stepping >= 0x1))
 		amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE;
 
 	if (boot_cpu_data.x86 == 0x15)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 25ddf02..b203af0 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -546,7 +546,7 @@
 
 static u32 hsx_deadline_rev(void)
 {
-	switch (boot_cpu_data.x86_mask) {
+	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x3a; /* EP */
 	case 0x04: return 0x0f; /* EX */
 	}
@@ -556,7 +556,7 @@
 
 static u32 bdx_deadline_rev(void)
 {
-	switch (boot_cpu_data.x86_mask) {
+	switch (boot_cpu_data.x86_stepping) {
 	case 0x02: return 0x00000011;
 	case 0x03: return 0x0700000e;
 	case 0x04: return 0x0f00000c;
@@ -568,7 +568,7 @@
 
 static u32 skx_deadline_rev(void)
 {
-	switch (boot_cpu_data.x86_mask) {
+	switch (boot_cpu_data.x86_stepping) {
 	case 0x03: return 0x01000136;
 	case 0x04: return 0x02000014;
 	}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 8ad2e41..7c55387 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1603,7 +1603,7 @@
 	do {
 		rep_nop();
 		now = rdtsc();
-	} while ((now - start) < 40000000000UL / HZ &&
+	} while ((now - start) < 40000000000ULL / HZ &&
 		time_before_eq(jiffies, end));
 }
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 3cc471b..bb6f7a2 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -134,21 +134,40 @@
 {
 	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	struct irq_desc *desc = irq_data_to_desc(irqd);
+	bool managed = irqd_affinity_is_managed(irqd);
 
 	lockdep_assert_held(&vector_lock);
 
 	trace_vector_update(irqd->irq, newvec, newcpu, apicd->vector,
 			    apicd->cpu);
 
-	/* Setup the vector move, if required  */
-	if (apicd->vector && cpu_online(apicd->cpu)) {
+	/*
+	 * If there is no vector associated or if the associated vector is
+	 * the shutdown vector, which is associated to make PCI/MSI
+	 * shutdown mode work, then there is nothing to release. Clear out
+	 * prev_vector for this and the offlined target case.
+	 */
+	apicd->prev_vector = 0;
+	if (!apicd->vector || apicd->vector == MANAGED_IRQ_SHUTDOWN_VECTOR)
+		goto setnew;
+	/*
+	 * If the target CPU of the previous vector is online, then mark
+	 * the vector as move in progress and store it for cleanup when the
+	 * first interrupt on the new vector arrives. If the target CPU is
+	 * offline then the regular release mechanism via the cleanup
+	 * vector is not possible and the vector can be immediately freed
+	 * in the underlying matrix allocator.
+	 */
+	if (cpu_online(apicd->cpu)) {
 		apicd->move_in_progress = true;
 		apicd->prev_vector = apicd->vector;
 		apicd->prev_cpu = apicd->cpu;
 	} else {
-		apicd->prev_vector = 0;
+		irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector,
+				managed);
 	}
 
+setnew:
 	apicd->vector = newvec;
 	apicd->cpu = newcpu;
 	BUG_ON(!IS_ERR_OR_NULL(per_cpu(vector_irq, newcpu)[newvec]));
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 46b675a..f11910b 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -1176,16 +1176,25 @@
 
 	uv_gre_table = gre;
 	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
+		unsigned long size = ((unsigned long)(gre->limit - lgre)
+					<< UV_GAM_RANGE_SHFT);
+		int order = 0;
+		char suffix[] = " KMGTPE";
+
+		while (size > 9999 && order < sizeof(suffix)) {
+			size /= 1024;
+			order++;
+		}
+
 		if (!index) {
 			pr_info("UV: GAM Range Table...\n");
 			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
 		}
-		pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x\n",
+		pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d   %04x  %02x %02x\n",
 			index++,
 			(unsigned long)lgre << UV_GAM_RANGE_SHFT,
 			(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
-			((unsigned long)(gre->limit - lgre)) >>
-				(30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */
+			size, suffix[order],
 			gre->type, gre->nasid, gre->sockid, gre->pnode);
 
 		lgre = gre->limit;
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index fa1261e..f91ba53 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -18,7 +18,7 @@
 	OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
 	OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
 	OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
-	OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask);
+	OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping);
 	OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level);
 	OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability);
 	OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 5bddbdc..f0e6456 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -119,7 +119,7 @@
 		return;
 	}
 
-	if (c->x86_model == 6 && c->x86_mask == 1) {
+	if (c->x86_model == 6 && c->x86_stepping == 1) {
 		const int K6_BUG_LOOP = 1000000;
 		int n;
 		void (*f_vide)(void);
@@ -149,7 +149,7 @@
 
 	/* K6 with old style WHCR */
 	if (c->x86_model < 8 ||
-	   (c->x86_model == 8 && c->x86_mask < 8)) {
+	   (c->x86_model == 8 && c->x86_stepping < 8)) {
 		/* We can only write allocate on the low 508Mb */
 		if (mbytes > 508)
 			mbytes = 508;
@@ -168,7 +168,7 @@
 		return;
 	}
 
-	if ((c->x86_model == 8 && c->x86_mask > 7) ||
+	if ((c->x86_model == 8 && c->x86_stepping > 7) ||
 	     c->x86_model == 9 || c->x86_model == 13) {
 		/* The more serious chips .. */
 
@@ -221,7 +221,7 @@
 	 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
 	 * As per AMD technical note 27212 0.2
 	 */
-	if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
+	if ((c->x86_model == 8 && c->x86_stepping >= 1) || (c->x86_model > 8)) {
 		rdmsr(MSR_K7_CLK_CTL, l, h);
 		if ((l & 0xfff00000) != 0x20000000) {
 			pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n",
@@ -241,12 +241,12 @@
 	 * but they are not certified as MP capable.
 	 */
 	/* Athlon 660/661 is valid. */
-	if ((c->x86_model == 6) && ((c->x86_mask == 0) ||
-	    (c->x86_mask == 1)))
+	if ((c->x86_model == 6) && ((c->x86_stepping == 0) ||
+	    (c->x86_stepping == 1)))
 		return;
 
 	/* Duron 670 is valid */
-	if ((c->x86_model == 7) && (c->x86_mask == 0))
+	if ((c->x86_model == 7) && (c->x86_stepping == 0))
 		return;
 
 	/*
@@ -256,8 +256,8 @@
 	 * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for
 	 * more.
 	 */
-	if (((c->x86_model == 6) && (c->x86_mask >= 2)) ||
-	    ((c->x86_model == 7) && (c->x86_mask >= 1)) ||
+	if (((c->x86_model == 6) && (c->x86_stepping >= 2)) ||
+	    ((c->x86_model == 7) && (c->x86_stepping >= 1)) ||
 	     (c->x86_model > 7))
 		if (cpu_has(c, X86_FEATURE_MP))
 			return;
@@ -628,7 +628,7 @@
 	/*  Set MTRR capability flag if appropriate */
 	if (c->x86 == 5)
 		if (c->x86_model == 13 || c->x86_model == 9 ||
-		    (c->x86_model == 8 && c->x86_mask >= 8))
+		    (c->x86_model == 8 && c->x86_stepping >= 8))
 			set_cpu_cap(c, X86_FEATURE_K6_MTRR);
 #endif
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
@@ -795,7 +795,7 @@
 	 * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
 	 * all up to and including B1.
 	 */
-	if (c->x86_model <= 1 && c->x86_mask <= 1)
+	if (c->x86_model <= 1 && c->x86_stepping <= 1)
 		set_cpu_cap(c, X86_FEATURE_CPB);
 }
 
@@ -906,11 +906,11 @@
 	/* AMD errata T13 (order #21922) */
 	if ((c->x86 == 6)) {
 		/* Duron Rev A0 */
-		if (c->x86_model == 3 && c->x86_mask == 0)
+		if (c->x86_model == 3 && c->x86_stepping == 0)
 			size = 64;
 		/* Tbird rev A1/A2 */
 		if (c->x86_model == 4 &&
-			(c->x86_mask == 0 || c->x86_mask == 1))
+			(c->x86_stepping == 0 || c->x86_stepping == 1))
 			size = 256;
 	}
 	return size;
@@ -1047,7 +1047,7 @@
 	}
 
 	/* OSVW unavailable or ID unknown, match family-model-stepping range */
-	ms = (cpu->x86_model << 4) | cpu->x86_mask;
+	ms = (cpu->x86_model << 4) | cpu->x86_stepping;
 	while ((range = *erratum++))
 		if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
 		    (ms >= AMD_MODEL_RANGE_START(range)) &&
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 71949bf..bfca937 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -162,8 +162,7 @@
 	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
 		return SPECTRE_V2_CMD_NONE;
 	else {
-		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
-					  sizeof(arg));
+		ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
 		if (ret < 0)
 			return SPECTRE_V2_CMD_AUTO;
 
@@ -175,8 +174,7 @@
 		}
 
 		if (i >= ARRAY_SIZE(mitigation_options)) {
-			pr_err("unknown option (%s). Switching to AUTO select\n",
-			       mitigation_options[i].option);
+			pr_err("unknown option (%s). Switching to AUTO select\n", arg);
 			return SPECTRE_V2_CMD_AUTO;
 		}
 	}
@@ -185,8 +183,7 @@
 	     cmd == SPECTRE_V2_CMD_RETPOLINE_AMD ||
 	     cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) &&
 	    !IS_ENABLED(CONFIG_RETPOLINE)) {
-		pr_err("%s selected but not compiled in. Switching to AUTO select\n",
-		       mitigation_options[i].option);
+		pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option);
 		return SPECTRE_V2_CMD_AUTO;
 	}
 
@@ -256,14 +253,14 @@
 			goto retpoline_auto;
 		break;
 	}
-	pr_err("kernel not compiled with retpoline; no mitigation available!");
+	pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!");
 	return;
 
 retpoline_auto:
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
 	retpoline_amd:
 		if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
-			pr_err("LFENCE not serializing. Switching to generic retpoline\n");
+			pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
 			goto retpoline_generic;
 		}
 		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
@@ -281,7 +278,7 @@
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If neither SMEP or KPTI are available, there is a risk of
+	 * 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.
@@ -295,21 +292,29 @@
 	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("Filling RSB on context switch\n");
+		pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
 	}
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
-		pr_info("Enabling Indirect Branch Prediction Barrier\n");
+		pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
+	}
+
+	/*
+	 * Retpoline means the kernel is safe because it has no indirect
+	 * branches. But firmware isn't, so use IBRS to protect that.
+	 */
+	if (boot_cpu_has(X86_FEATURE_IBRS)) {
+		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
+		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
 }
 
 #undef pr_fmt
 
 #ifdef CONFIG_SYSFS
-ssize_t cpu_show_meltdown(struct device *dev,
-			  struct device_attribute *attr, char *buf)
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
 		return sprintf(buf, "Not affected\n");
@@ -318,28 +323,21 @@
 	return sprintf(buf, "Vulnerable\n");
 }
 
-ssize_t cpu_show_spectre_v1(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
 		return sprintf(buf, "Not affected\n");
 	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
 }
 
-ssize_t cpu_show_spectre_v2(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
 		return sprintf(buf, "Not affected\n");
 
-	return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+	return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
 		       boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
 		       spectre_v2_module_string());
 }
 #endif
-
-void __ibp_barrier(void)
-{
-	__wrmsr(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, 0);
-}
-EXPORT_SYMBOL_GPL(__ibp_barrier);
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index c578cd2..e5ec0f1 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -140,7 +140,7 @@
 			clear_cpu_cap(c, X86_FEATURE_TSC);
 			break;
 		case 8:
-			switch (c->x86_mask) {
+			switch (c->x86_stepping) {
 			default:
 			name = "2";
 				break;
@@ -215,7 +215,7 @@
 	 *  - Note, it seems this may only be in engineering samples.
 	 */
 	if ((c->x86 == 6) && (c->x86_model == 9) &&
-				(c->x86_mask == 1) && (size == 65))
+				(c->x86_stepping == 1) && (size == 65))
 		size -= 1;
 	return size;
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d63f4b57..348cf48 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -731,7 +731,7 @@
 		cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
 		c->x86		= x86_family(tfms);
 		c->x86_model	= x86_model(tfms);
-		c->x86_mask	= x86_stepping(tfms);
+		c->x86_stepping	= x86_stepping(tfms);
 
 		if (cap0 & (1<<19)) {
 			c->x86_clflush_size = ((misc >> 8) & 0xff) * 8;
@@ -1184,9 +1184,9 @@
 	int i;
 
 	c->loops_per_jiffy = loops_per_jiffy;
-	c->x86_cache_size = -1;
+	c->x86_cache_size = 0;
 	c->x86_vendor = X86_VENDOR_UNKNOWN;
-	c->x86_model = c->x86_mask = 0;	/* So far unknown... */
+	c->x86_model = c->x86_stepping = 0;	/* So far unknown... */
 	c->x86_vendor_id[0] = '\0'; /* Unset */
 	c->x86_model_id[0] = '\0';  /* Unset */
 	c->x86_max_cores = 1;
@@ -1378,8 +1378,8 @@
 
 	pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model);
 
-	if (c->x86_mask || c->cpuid_level >= 0)
-		pr_cont(", stepping: 0x%x)\n", c->x86_mask);
+	if (c->x86_stepping || c->cpuid_level >= 0)
+		pr_cont(", stepping: 0x%x)\n", c->x86_stepping);
 	else
 		pr_cont(")\n");
 }
@@ -1749,3 +1749,33 @@
 	return 0;
 }
 core_initcall(init_cpu_syscore);
+
+/*
+ * The microcode loader calls this upon late microcode load to recheck features,
+ * only when microcode has been updated. Caller holds microcode_mutex and CPU
+ * hotplug lock.
+ */
+void microcode_check(void)
+{
+	struct cpuinfo_x86 info;
+
+	perf_check_microcode();
+
+	/* Reload CPUID max function as it might've changed. */
+	info.cpuid_level = cpuid_eax(0);
+
+	/*
+	 * Copy all capability leafs to pick up the synthetic ones so that
+	 * memcmp() below doesn't fail on that. The ones coming from CPUID will
+	 * get overwritten in get_cpu_cap().
+	 */
+	memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability));
+
+	get_cpu_cap(&info);
+
+	if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)))
+		return;
+
+	pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
+	pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
+}
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 6b4bb33..8949b7a 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -215,7 +215,7 @@
 
 	/* common case step number/rev -- exceptions handled below */
 	c->x86_model = (dir1 >> 4) + 1;
-	c->x86_mask = dir1 & 0xf;
+	c->x86_stepping = dir1 & 0xf;
 
 	/* Now cook; the original recipe is by Channing Corn, from Cyrix.
 	 * We do the same thing for each generation: we work out
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 319bf98..d19e903 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -116,14 +116,13 @@
 	u32 microcode;
 };
 static const struct sku_microcode spectre_bad_microcodes[] = {
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x84 },
-	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x84 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0B,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x0A,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_DESKTOP,	0x09,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x0A,	0x80 },
+	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x80 },
 	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
 	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
-	{ INTEL_FAM6_SKYLAKE_MOBILE,	0x03,	0xc2 },
 	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
 	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
 	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
@@ -136,8 +135,6 @@
 	{ INTEL_FAM6_HASWELL_X,		0x02,	0x3b },
 	{ INTEL_FAM6_HASWELL_X,		0x04,	0x10 },
 	{ INTEL_FAM6_IVYBRIDGE_X,	0x04,	0x42a },
-	/* Updated in the 20180108 release; blacklist until we know otherwise */
-	{ INTEL_FAM6_ATOM_GEMINI_LAKE,	0x01,	0x22 },
 	/* Observed in the wild */
 	{ INTEL_FAM6_SANDYBRIDGE_X,	0x06,	0x61b },
 	{ INTEL_FAM6_SANDYBRIDGE_X,	0x07,	0x712 },
@@ -149,7 +146,7 @@
 
 	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
 		if (c->x86_model == spectre_bad_microcodes[i].model &&
-		    c->x86_mask == spectre_bad_microcodes[i].stepping)
+		    c->x86_stepping == spectre_bad_microcodes[i].stepping)
 			return (c->microcode <= spectre_bad_microcodes[i].microcode);
 	}
 	return false;
@@ -196,7 +193,7 @@
 	 * need the microcode to have already been loaded... so if it is
 	 * not, recommend a BIOS update and disable large pages.
 	 */
-	if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 &&
+	if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_stepping <= 2 &&
 	    c->microcode < 0x20e) {
 		pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n");
 		clear_cpu_cap(c, X86_FEATURE_PSE);
@@ -212,7 +209,7 @@
 
 	/* CPUID workaround for 0F33/0F34 CPU */
 	if (c->x86 == 0xF && c->x86_model == 0x3
-	    && (c->x86_mask == 0x3 || c->x86_mask == 0x4))
+	    && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4))
 		c->x86_phys_bits = 36;
 
 	/*
@@ -310,7 +307,7 @@
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
 	    boot_cpu_data.x86 == 6 &&
 	    boot_cpu_data.x86_model == 1 &&
-	    boot_cpu_data.x86_mask < 8) {
+	    boot_cpu_data.x86_stepping < 8) {
 		pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n");
 		return 1;
 	}
@@ -327,7 +324,7 @@
 	 * Mask B, Pentium, but not Pentium MMX
 	 */
 	if (c->x86 == 5 &&
-	    c->x86_mask >= 1 && c->x86_mask <= 4 &&
+	    c->x86_stepping >= 1 && c->x86_stepping <= 4 &&
 	    c->x86_model <= 3) {
 		/*
 		 * Remember we have B step Pentia with bugs
@@ -370,7 +367,7 @@
 	 * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until
 	 * model 3 mask 3
 	 */
-	if ((c->x86<<8 | c->x86_model<<4 | c->x86_mask) < 0x633)
+	if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633)
 		clear_cpu_cap(c, X86_FEATURE_SEP);
 
 	/*
@@ -388,7 +385,7 @@
 	 * P4 Xeon erratum 037 workaround.
 	 * Hardware prefetcher may cause stale data to be loaded into the cache.
 	 */
-	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
+	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) {
 		if (msr_set_bit(MSR_IA32_MISC_ENABLE,
 				MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) {
 			pr_info("CPU: C0 stepping P4 Xeon detected.\n");
@@ -403,7 +400,7 @@
 	 * Specification Update").
 	 */
 	if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
-	    (c->x86_mask < 0x6 || c->x86_mask == 0xb))
+	    (c->x86_stepping < 0x6 || c->x86_stepping == 0xb))
 		set_cpu_bug(c, X86_BUG_11AP);
 
 
@@ -650,7 +647,7 @@
 		case 6:
 			if (l2 == 128)
 				p = "Celeron (Mendocino)";
-			else if (c->x86_mask == 0 || c->x86_mask == 5)
+			else if (c->x86_stepping == 0 || c->x86_stepping == 5)
 				p = "Celeron-A";
 			break;
 
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 410629f..589b948 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -819,7 +819,7 @@
 			cache_alloc_hsw_probe();
 		break;
 	case INTEL_FAM6_SKYLAKE_X:
-		if (boot_cpu_data.x86_mask <= 4)
+		if (boot_cpu_data.x86_stepping <= 4)
 			set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat");
 	}
 }
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index bdab7d2..fca759d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1804,6 +1804,7 @@
 		goto out_common_fail;
 	}
 	closid = ret;
+	ret = 0;
 
 	rdtgrp->closid = closid;
 	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index aa0d5df..e956eb2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -115,4 +115,19 @@
 
 extern struct mca_config mca_cfg;
 
+#ifndef CONFIG_X86_64
+/*
+ * On 32-bit systems it would be difficult to safely unmap a poison page
+ * from the kernel 1:1 map because there are no non-canonical addresses that
+ * we can use to refer to the address without risking a speculative access.
+ * However, this isn't much of an issue because:
+ * 1) Few unmappable pages are in the 1:1 map. Most are in HIGHMEM which
+ *    are only mapped into the kernel as needed
+ * 2) Few people would run a 32-bit kernel on a machine that supports
+ *    recoverable errors because they have too much memory to boot 32-bit.
+ */
+static inline void mce_unmap_kpfn(unsigned long pfn) {}
+#define mce_unmap_kpfn mce_unmap_kpfn
+#endif
+
 #endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3a8e88a..8ff94d1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -105,6 +105,10 @@
 
 static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
 
+#ifndef mce_unmap_kpfn
+static void mce_unmap_kpfn(unsigned long pfn);
+#endif
+
 /*
  * CPU/chipset specific EDAC code can register a notifier call here to print
  * MCE errors in a human-readable form.
@@ -234,7 +238,7 @@
 			m->cs, m->ip);
 
 		if (m->cs == __KERNEL_CS)
-			pr_cont("{%pS}", (void *)m->ip);
+			pr_cont("{%pS}", (void *)(unsigned long)m->ip);
 		pr_cont("\n");
 	}
 
@@ -590,7 +594,8 @@
 
 	if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) {
 		pfn = mce->addr >> PAGE_SHIFT;
-		memory_failure(pfn, 0);
+		if (!memory_failure(pfn, 0))
+			mce_unmap_kpfn(pfn);
 	}
 
 	return NOTIFY_OK;
@@ -1057,12 +1062,13 @@
 	ret = memory_failure(m->addr >> PAGE_SHIFT, flags);
 	if (ret)
 		pr_err("Memory error not recovered");
+	else
+		mce_unmap_kpfn(m->addr >> PAGE_SHIFT);
 	return ret;
 }
 
-#if defined(arch_unmap_kpfn) && defined(CONFIG_MEMORY_FAILURE)
-
-void arch_unmap_kpfn(unsigned long pfn)
+#ifndef mce_unmap_kpfn
+static void mce_unmap_kpfn(unsigned long pfn)
 {
 	unsigned long decoy_addr;
 
@@ -1073,7 +1079,7 @@
 	 * We would like to just call:
 	 *	set_memory_np((unsigned long)pfn_to_kaddr(pfn), 1);
 	 * but doing that would radically increase the odds of a
-	 * speculative access to the posion page because we'd have
+	 * speculative access to the poison page because we'd have
 	 * the virtual address of the kernel 1:1 mapping sitting
 	 * around in registers.
 	 * Instead we get tricky.  We create a non-canonical address
@@ -1098,7 +1104,6 @@
 
 	if (set_memory_np(decoy_addr, 1))
 		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
-
 }
 #endif
 
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 330b846..a998e1a 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -498,7 +498,7 @@
 	return patch_size;
 }
 
-static int apply_microcode_amd(int cpu)
+static enum ucode_state apply_microcode_amd(int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_amd *mc_amd;
@@ -512,7 +512,7 @@
 
 	p = find_patch(cpu);
 	if (!p)
-		return 0;
+		return UCODE_NFOUND;
 
 	mc_amd  = p->data;
 	uci->mc = p->data;
@@ -523,13 +523,13 @@
 	if (rev >= mc_amd->hdr.patch_id) {
 		c->microcode = rev;
 		uci->cpu_sig.rev = rev;
-		return 0;
+		return UCODE_OK;
 	}
 
 	if (__apply_microcode_amd(mc_amd)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
-		return -1;
+		return UCODE_ERROR;
 	}
 	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
 		mc_amd->hdr.patch_id);
@@ -537,7 +537,7 @@
 	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
 	c->microcode = mc_amd->hdr.patch_id;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static int install_equiv_cpu_table(const u8 *buf)
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 319dd65..aa1b9a4 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -374,7 +374,7 @@
 }
 
 struct apply_microcode_ctx {
-	int err;
+	enum ucode_state err;
 };
 
 static void apply_microcode_local(void *arg)
@@ -489,31 +489,30 @@
 /* fake device for request_firmware */
 static struct platform_device	*microcode_pdev;
 
-static int reload_for_cpu(int cpu)
+static enum ucode_state reload_for_cpu(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	enum ucode_state ustate;
-	int err = 0;
 
 	if (!uci->valid)
-		return err;
+		return UCODE_OK;
 
 	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
-	if (ustate == UCODE_OK)
-		apply_microcode_on_target(cpu);
-	else
-		if (ustate == UCODE_ERROR)
-			err = -EINVAL;
-	return err;
+	if (ustate != UCODE_OK)
+		return ustate;
+
+	return apply_microcode_on_target(cpu);
 }
 
 static ssize_t reload_store(struct device *dev,
 			    struct device_attribute *attr,
 			    const char *buf, size_t size)
 {
+	enum ucode_state tmp_ret = UCODE_OK;
+	bool do_callback = false;
 	unsigned long val;
+	ssize_t ret = 0;
 	int cpu;
-	ssize_t ret = 0, tmp_ret;
 
 	ret = kstrtoul(buf, 0, &val);
 	if (ret)
@@ -526,15 +525,21 @@
 	mutex_lock(&microcode_mutex);
 	for_each_online_cpu(cpu) {
 		tmp_ret = reload_for_cpu(cpu);
-		if (tmp_ret != 0)
+		if (tmp_ret > UCODE_NFOUND) {
 			pr_warn("Error reloading microcode on CPU %d\n", cpu);
 
-		/* save retval of the first encountered reload error */
-		if (!ret)
-			ret = tmp_ret;
+			/* set retval for the first encountered reload error */
+			if (!ret)
+				ret = -EINVAL;
+		}
+
+		if (tmp_ret == UCODE_UPDATED)
+			do_callback = true;
 	}
-	if (!ret)
-		perf_check_microcode();
+
+	if (!ret && do_callback)
+		microcode_check();
+
 	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index f7c55b0..923054a 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -772,7 +772,7 @@
 	return 0;
 }
 
-static int apply_microcode_intel(int cpu)
+static enum ucode_state apply_microcode_intel(int cpu)
 {
 	struct microcode_intel *mc;
 	struct ucode_cpu_info *uci;
@@ -782,7 +782,7 @@
 
 	/* We should bind the task to the CPU */
 	if (WARN_ON(raw_smp_processor_id() != cpu))
-		return -1;
+		return UCODE_ERROR;
 
 	uci = ucode_cpu_info + cpu;
 	mc = uci->mc;
@@ -790,7 +790,7 @@
 		/* Look for a newer patch in our cache: */
 		mc = find_patch(uci);
 		if (!mc)
-			return 0;
+			return UCODE_NFOUND;
 	}
 
 	/* write microcode via MSR 0x79 */
@@ -801,7 +801,7 @@
 	if (rev != mc->hdr.rev) {
 		pr_err("CPU%d update to revision 0x%x failed\n",
 		       cpu, mc->hdr.rev);
-		return -1;
+		return UCODE_ERROR;
 	}
 
 	if (rev != prev_rev) {
@@ -818,7 +818,7 @@
 	uci->cpu_sig.rev = rev;
 	c->microcode = rev;
 
-	return 0;
+	return UCODE_UPDATED;
 }
 
 static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
@@ -921,7 +921,7 @@
 	 */
 	if (c->x86 == 6 &&
 	    c->x86_model == INTEL_FAM6_BROADWELL_X &&
-	    c->x86_mask == 0x01 &&
+	    c->x86_stepping == 0x01 &&
 	    llc_size_per_core > 2621440 &&
 	    c->microcode < 0x0b000021) {
 		pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode);
@@ -944,7 +944,7 @@
 		return UCODE_NFOUND;
 
 	sprintf(name, "intel-ucode/%02x-%02x-%02x",
-		c->x86, c->x86_model, c->x86_mask);
+		c->x86, c->x86_model, c->x86_stepping);
 
 	if (request_firmware_direct(&firmware, name, device)) {
 		pr_debug("data file %s load failed\n", name);
@@ -982,7 +982,7 @@
 
 static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c)
 {
-	u64 llc_size = c->x86_cache_size * 1024;
+	u64 llc_size = c->x86_cache_size * 1024ULL;
 
 	do_div(llc_size, c->x86_max_cores);
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index fdc5521..e12ee86 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -859,7 +859,7 @@
 	 */
 	if (is_cpu(INTEL) && boot_cpu_data.x86 == 6 &&
 	    boot_cpu_data.x86_model == 1 &&
-	    boot_cpu_data.x86_mask <= 7) {
+	    boot_cpu_data.x86_stepping <= 7) {
 		if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) {
 			pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base);
 			return -EINVAL;
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 40d5a8a..7468de4 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -711,8 +711,8 @@
 			if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
 			    boot_cpu_data.x86 == 0xF &&
 			    boot_cpu_data.x86_model == 0x3 &&
-			    (boot_cpu_data.x86_mask == 0x3 ||
-			     boot_cpu_data.x86_mask == 0x4))
+			    (boot_cpu_data.x86_stepping == 0x3 ||
+			     boot_cpu_data.x86_stepping == 0x4))
 				phys_addr = 36;
 
 			size_or_mask = SIZE_OR_MASK_BITS(phys_addr);
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index e7eceda..2c8522a 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -72,8 +72,8 @@
 		   c->x86_model,
 		   c->x86_model_id[0] ? c->x86_model_id : "unknown");
 
-	if (c->x86_mask || c->cpuid_level >= 0)
-		seq_printf(m, "stepping\t: %d\n", c->x86_mask);
+	if (c->x86_stepping || c->cpuid_level >= 0)
+		seq_printf(m, "stepping\t: %d\n", c->x86_stepping);
 	else
 		seq_puts(m, "stepping\t: unknown\n");
 	if (c->microcode)
@@ -91,8 +91,8 @@
 	}
 
 	/* Cache size */
-	if (c->x86_cache_size >= 0)
-		seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
+	if (c->x86_cache_size)
+		seq_printf(m, "cache size\t: %u KB\n", c->x86_cache_size);
 
 	show_cpuinfo_core(m, c, cpu);
 	show_cpuinfo_misc(m, c);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index c290209..b59e4fb 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -37,7 +37,7 @@
 #define X86		new_cpu_data+CPUINFO_x86
 #define X86_VENDOR	new_cpu_data+CPUINFO_x86_vendor
 #define X86_MODEL	new_cpu_data+CPUINFO_x86_model
-#define X86_MASK	new_cpu_data+CPUINFO_x86_mask
+#define X86_STEPPING	new_cpu_data+CPUINFO_x86_stepping
 #define X86_HARD_MATH	new_cpu_data+CPUINFO_hard_math
 #define X86_CPUID	new_cpu_data+CPUINFO_cpuid_level
 #define X86_CAPABILITY	new_cpu_data+CPUINFO_x86_capability
@@ -332,7 +332,7 @@
 	shrb $4,%al
 	movb %al,X86_MODEL
 	andb $0x0f,%cl		# mask mask revision
-	movb %cl,X86_MASK
+	movb %cl,X86_STEPPING
 	movl %edx,X86_CAPABILITY
 
 .Lis486:
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 04a625f..0f545b3 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -23,6 +23,7 @@
 #include <asm/nops.h>
 #include "../entry/calling.h"
 #include <asm/export.h>
+#include <asm/nospec-branch.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -134,6 +135,7 @@
 
 	/* Ensure I am executing from virtual addresses */
 	movq	$1f, %rax
+	ANNOTATE_RETPOLINE_SAFE
 	jmp	*%rax
 1:
 	UNWIND_HINT_EMPTY
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4e37d1a..bc1a272 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -49,7 +49,7 @@
 
 static int kvmapf = 1;
 
-static int parse_no_kvmapf(char *arg)
+static int __init parse_no_kvmapf(char *arg)
 {
         kvmapf = 0;
         return 0;
@@ -58,7 +58,7 @@
 early_param("no-kvmapf", parse_no_kvmapf);
 
 static int steal_acc = 1;
-static int parse_no_stealacc(char *arg)
+static int __init parse_no_stealacc(char *arg)
 {
         steal_acc = 0;
         return 0;
@@ -67,7 +67,7 @@
 early_param("no-steal-acc", parse_no_stealacc);
 
 static int kvmclock_vsyscall = 1;
-static int parse_no_kvmclock_vsyscall(char *arg)
+static int __init parse_no_kvmclock_vsyscall(char *arg)
 {
         kvmclock_vsyscall = 0;
         return 0;
@@ -341,10 +341,10 @@
 #endif
 		pa |= KVM_ASYNC_PF_ENABLED;
 
-		/* Async page fault support for L1 hypervisor is optional */
-		if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN,
-			(pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0)
-			wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
+		if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
+			pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
+
+		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
 		__this_cpu_write(apf_reason.enabled, 1);
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
@@ -545,7 +545,8 @@
 		pv_time_ops.steal_clock = kvm_steal_clock;
 	}
 
-	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH))
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
 		pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -633,7 +634,8 @@
 {
 	int cpu;
 
-	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) {
+	if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+	    !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		for_each_possible_cpu(cpu) {
 			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
 				GFP_KERNEL, cpu_to_node(cpu));
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 1f790cf..3b7427a 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -542,6 +542,7 @@
 				goto overflow;
 			break;
 		case R_X86_64_PC32:
+		case R_X86_64_PLT32:
 			value -= (u64)address;
 			*(u32 *)location = value;
 			break;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index da0c160..f58336a 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -191,6 +191,7 @@
 				goto overflow;
 			break;
 		case R_X86_64_PC32:
+		case R_X86_64_PLT32:
 			if (*(u32 *)loc != 0)
 				goto invalid_relocation;
 			val -= (u64)loc;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 27d0a17..f1c5eb9 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -410,7 +410,7 @@
 	processor.apicver = mpc_default_type > 4 ? 0x10 : 0x01;
 	processor.cpuflag = CPU_ENABLED;
 	processor.cpufeature = (boot_cpu_data.x86 << 8) |
-	    (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask;
+	    (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_stepping;
 	processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX];
 	processor.reserved[0] = 0;
 	processor.reserved[1] = 0;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 041096b..99dc79e 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -200,9 +200,9 @@
 	__native_flush_tlb_global();
 }
 
-static void native_flush_tlb_single(unsigned long addr)
+static void native_flush_tlb_one_user(unsigned long addr)
 {
-	__native_flush_tlb_single(addr);
+	__native_flush_tlb_one_user(addr);
 }
 
 struct static_key paravirt_steal_enabled;
@@ -401,7 +401,7 @@
 
 	.flush_tlb_user = native_flush_tlb,
 	.flush_tlb_kernel = native_flush_tlb_global,
-	.flush_tlb_single = native_flush_tlb_single,
+	.flush_tlb_one_user = native_flush_tlb_one_user,
 	.flush_tlb_others = native_flush_tlb_others,
 
 	.pgd_alloc = __paravirt_pgd_alloc,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 1ae67e9..4c616be 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1204,20 +1204,13 @@
 
 	kasan_init();
 
-#ifdef CONFIG_X86_32
-	/* sync back kernel address range */
-	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
-
 	/*
-	 * sync back low identity map too.  It is used for example
-	 * in the 32-bit EFI stub.
+	 * Sync back kernel address range.
+	 *
+	 * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+	 * this call?
 	 */
-	clone_pgd_range(initial_page_table,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+	sync_initial_page_table();
 
 	tboot_probe();
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 497aa76..ea554f8 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -287,24 +287,15 @@
 	/* Setup cpu initialized, callin, callout masks */
 	setup_cpu_local_masks();
 
-#ifdef CONFIG_X86_32
 	/*
 	 * Sync back kernel address range again.  We already did this in
 	 * setup_arch(), but percpu data also needs to be available in
 	 * the smpboot asm.  We can't reliably pick up percpu mappings
 	 * using vmalloc_fault(), because exception dispatch needs
 	 * percpu data.
+	 *
+	 * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+	 * this call?
 	 */
-	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			KERNEL_PGD_PTRS);
-
-	/*
-	 * sync back low identity map too.  It is used for example
-	 * in the 32-bit EFI stub.
-	 */
-	clone_pgd_range(initial_page_table,
-			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
-			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+	sync_initial_page_table();
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6f27fac..ff99e2b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1281,11 +1281,10 @@
 	cpu_set_state_online(me);
 }
 
-void __init native_smp_cpus_done(unsigned int max_cpus)
+void __init calculate_max_logical_packages(void)
 {
 	int ncpus;
 
-	pr_debug("Boot done\n");
 	/*
 	 * Today neither Intel nor AMD support heterogenous systems so
 	 * extrapolate the boot cpu's data to all packages.
@@ -1293,6 +1292,13 @@
 	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
 	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
+}
+
+void __init native_smp_cpus_done(unsigned int max_cpus)
+{
+	pr_debug("Boot done\n");
+
+	calculate_max_logical_packages();
 
 	if (x86_has_numa_in_package)
 		set_sched_topology(x86_numa_in_package_topology);
@@ -1430,8 +1436,8 @@
 	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(topology_sibling_cpumask(cpu));
 	cpumask_clear(topology_core_cpumask(cpu));
-	c->phys_proc_id = 0;
 	c->cpu_core_id = 0;
+	c->booted_cores = 0;
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
 	recompute_smt_state();
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 446c9ef..3d9b230 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -181,7 +181,7 @@
 		break;
 
 	case BUG_TRAP_TYPE_WARN:
-		regs->ip += LEN_UD0;
+		regs->ip += LEN_UD2;
 		return 1;
 	}
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 1f9188f..feb28fe 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -5,7 +5,6 @@
 #include <asm/unwind.h>
 #include <asm/orc_types.h>
 #include <asm/orc_lookup.h>
-#include <asm/sections.h>
 
 #define orc_warn(fmt, ...) \
 	printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)
@@ -148,7 +147,7 @@
 	}
 
 	/* vmlinux .init slow lookup: */
-	if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext)
+	if (init_kernel_text(ip))
 		return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
 				  __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a0c5a69..b671fc2 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -607,7 +607,8 @@
 			     (1 << KVM_FEATURE_PV_EOI) |
 			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
 			     (1 << KVM_FEATURE_PV_UNHALT) |
-			     (1 << KVM_FEATURE_PV_TLB_FLUSH);
+			     (1 << KVM_FEATURE_PV_TLB_FLUSH) |
+			     (1 << KVM_FEATURE_ASYNC_PF_VMEXIT);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 924ac8c..391dda8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2002,14 +2002,13 @@
 
 void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
-	struct kvm_lapic *apic;
+	struct kvm_lapic *apic = vcpu->arch.apic;
 	int i;
 
-	apic_debug("%s\n", __func__);
+	if (!apic)
+		return;
 
-	ASSERT(vcpu);
-	apic = vcpu->arch.apic;
-	ASSERT(apic != NULL);
+	apic_debug("%s\n", __func__);
 
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
@@ -2165,7 +2164,6 @@
 	 */
 	vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
 	static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
-	kvm_lapic_reset(vcpu, false);
 	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
 
 	return 0;
@@ -2569,7 +2567,6 @@
 
 	pe = xchg(&apic->pending_events, 0);
 	if (test_bit(KVM_APIC_INIT, &pe)) {
-		kvm_lapic_reset(vcpu, true);
 		kvm_vcpu_reset(vcpu, true);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
 			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8eca1d0..f551962 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3029,7 +3029,7 @@
 		return RET_PF_RETRY;
 	}
 
-	return -EFAULT;
+	return RET_PF_EMULATE;
 }
 
 static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
@@ -5080,7 +5080,7 @@
 typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head);
 
 /* The caller should hold mmu-lock before calling this function. */
-static bool
+static __always_inline bool
 slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			slot_level_handler fn, int start_level, int end_level,
 			gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb)
@@ -5110,7 +5110,7 @@
 	return flush;
 }
 
-static bool
+static __always_inline bool
 slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		  slot_level_handler fn, int start_level, int end_level,
 		  bool lock_flush_tlb)
@@ -5121,7 +5121,7 @@
 			lock_flush_tlb);
 }
 
-static bool
+static __always_inline bool
 slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		      slot_level_handler fn, bool lock_flush_tlb)
 {
@@ -5129,7 +5129,7 @@
 				 PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
 }
 
-static bool
+static __always_inline bool
 slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			slot_level_handler fn, bool lock_flush_tlb)
 {
@@ -5137,7 +5137,7 @@
 				 PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
 }
 
-static bool
+static __always_inline bool
 slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		 slot_level_handler fn, bool lock_flush_tlb)
 {
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b3e488a..be9c839 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -49,6 +49,7 @@
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
 #include <asm/irq_remapping.h>
+#include <asm/microcode.h>
 #include <asm/nospec-branch.h>
 
 #include <asm/virtext.h>
@@ -178,6 +179,8 @@
 	uint64_t sysenter_eip;
 	uint64_t tsc_aux;
 
+	u64 msr_decfg;
+
 	u64 next_rip;
 
 	u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
@@ -300,6 +303,8 @@
 static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
 module_param(sev, int, 0444);
 
+static u8 rsm_ins_bytes[] = "\x0f\xaa";
+
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
@@ -1383,6 +1388,7 @@
 	set_intercept(svm, INTERCEPT_SKINIT);
 	set_intercept(svm, INTERCEPT_WBINVD);
 	set_intercept(svm, INTERCEPT_XSETBV);
+	set_intercept(svm, INTERCEPT_RSM);
 
 	if (!kvm_mwait_in_guest()) {
 		set_intercept(svm, INTERCEPT_MONITOR);
@@ -1902,6 +1908,7 @@
 	u32 dummy;
 	u32 eax = 1;
 
+	vcpu->arch.microcode_version = 0x01000065;
 	svm->spec_ctrl = 0;
 
 	if (!init_event) {
@@ -3699,6 +3706,12 @@
 	return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
 }
 
+static int rsm_interception(struct vcpu_svm *svm)
+{
+	return x86_emulate_instruction(&svm->vcpu, 0, 0,
+				       rsm_ins_bytes, 2) == EMULATE_DONE;
+}
+
 static int rdpmc_interception(struct vcpu_svm *svm)
 {
 	int err;
@@ -3860,6 +3873,22 @@
 	return 0;
 }
 
+static int svm_get_msr_feature(struct kvm_msr_entry *msr)
+{
+	msr->data = 0;
+
+	switch (msr->index) {
+	case MSR_F10H_DECFG:
+		if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC))
+			msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE;
+		break;
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
 static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3935,9 +3964,6 @@
 
 		msr_info->data = svm->spec_ctrl;
 		break;
-	case MSR_IA32_UCODE_REV:
-		msr_info->data = 0x01000065;
-		break;
 	case MSR_F15H_IC_CFG: {
 
 		int family, model;
@@ -3955,6 +3981,9 @@
 			msr_info->data = 0x1E;
 		}
 		break;
+	case MSR_F10H_DECFG:
+		msr_info->data = svm->msr_decfg;
+		break;
 	default:
 		return kvm_get_msr_common(vcpu, msr_info);
 	}
@@ -4133,6 +4162,24 @@
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
+	case MSR_F10H_DECFG: {
+		struct kvm_msr_entry msr_entry;
+
+		msr_entry.index = msr->index;
+		if (svm_get_msr_feature(&msr_entry))
+			return 1;
+
+		/* Check the supported bits */
+		if (data & ~msr_entry.data)
+			return 1;
+
+		/* Don't allow the guest to change a bit, #GP */
+		if (!msr->host_initiated && (data ^ msr_entry.data))
+			return 1;
+
+		svm->msr_decfg = data;
+		break;
+	}
 	case MSR_IA32_APICBASE:
 		if (kvm_vcpu_apicv_active(vcpu))
 			avic_update_vapic_bar(to_svm(vcpu), data);
@@ -4541,7 +4588,7 @@
 	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
 	[SVM_EXIT_NPF]				= npf_interception,
-	[SVM_EXIT_RSM]                          = emulate_on_interception,
+	[SVM_EXIT_RSM]                          = rsm_interception,
 	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
 	[SVM_EXIT_AVIC_UNACCELERATED_ACCESS]	= avic_unaccelerated_access_interception,
 };
@@ -5355,7 +5402,7 @@
 	 * being speculatively taken.
 	 */
 	if (svm->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
 
 	asm volatile (
 		"push %%" _ASM_BP "; \n\t"
@@ -5464,11 +5511,11 @@
 	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
 	 * save it.
 	 */
-	if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
-		rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl);
+	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+		svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
 	if (svm->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
 
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
@@ -6236,16 +6283,18 @@
 
 static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
+	void __user *measure = (void __user *)(uintptr_t)argp->data;
 	struct kvm_sev_info *sev = &kvm->arch.sev_info;
 	struct sev_data_launch_measure *data;
 	struct kvm_sev_launch_measure params;
+	void __user *p = NULL;
 	void *blob = NULL;
 	int ret;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
-	if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+	if (copy_from_user(&params, measure, sizeof(params)))
 		return -EFAULT;
 
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
@@ -6256,17 +6305,13 @@
 	if (!params.len)
 		goto cmd;
 
-	if (params.uaddr) {
+	p = (void __user *)(uintptr_t)params.uaddr;
+	if (p) {
 		if (params.len > SEV_FW_BLOB_MAX_SIZE) {
 			ret = -EINVAL;
 			goto e_free;
 		}
 
-		if (!access_ok(VERIFY_WRITE, params.uaddr, params.len)) {
-			ret = -EFAULT;
-			goto e_free;
-		}
-
 		ret = -ENOMEM;
 		blob = kmalloc(params.len, GFP_KERNEL);
 		if (!blob)
@@ -6290,13 +6335,13 @@
 		goto e_free_blob;
 
 	if (blob) {
-		if (copy_to_user((void __user *)(uintptr_t)params.uaddr, blob, params.len))
+		if (copy_to_user(p, blob, params.len))
 			ret = -EFAULT;
 	}
 
 done:
 	params.len = data->len;
-	if (copy_to_user((void __user *)(uintptr_t)argp->data, &params, sizeof(params)))
+	if (copy_to_user(measure, &params, sizeof(params)))
 		ret = -EFAULT;
 e_free_blob:
 	kfree(blob);
@@ -6597,7 +6642,7 @@
 	struct page **pages;
 	void *blob, *hdr;
 	unsigned long n;
-	int ret;
+	int ret, offset;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
@@ -6623,6 +6668,10 @@
 	if (!data)
 		goto e_unpin_memory;
 
+	offset = params.guest_uaddr & (PAGE_SIZE - 1);
+	data->guest_address = __sme_page_pa(pages[0]) + offset;
+	data->guest_len = params.guest_len;
+
 	blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len);
 	if (IS_ERR(blob)) {
 		ret = PTR_ERR(blob);
@@ -6637,8 +6686,8 @@
 		ret = PTR_ERR(hdr);
 		goto e_free_blob;
 	}
-	data->trans_address = __psp_pa(blob);
-	data->trans_len = params.trans_len;
+	data->hdr_address = __psp_pa(hdr);
+	data->hdr_len = params.hdr_len;
 
 	data->handle = sev->handle;
 	ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error);
@@ -6821,6 +6870,7 @@
 	.vcpu_unblocking = svm_vcpu_unblocking,
 
 	.update_bp_intercept = update_bp_intercept,
+	.get_msr_feature = svm_get_msr_feature,
 	.get_msr = svm_get_msr,
 	.set_msr = svm_set_msr,
 	.get_segment_base = svm_get_segment_base,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f427723..051dab7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,6 +51,7 @@
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/mmu_context.h>
+#include <asm/microcode.h>
 #include <asm/nospec-branch.h>
 
 #include "trace.h"
@@ -3226,6 +3227,11 @@
 	return !(val & ~valid_bits);
 }
 
+static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
+{
+	return 1;
+}
+
 /*
  * Reads an msr value (of 'msr_index') into 'pdata'.
  * Returns 0 on success, non-0 otherwise.
@@ -4485,7 +4491,8 @@
 		vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
 			      SECONDARY_EXEC_DESC);
 		hw_cr4 &= ~X86_CR4_UMIP;
-	} else
+	} else if (!is_guest_mode(vcpu) ||
+	           !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
 		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
 				SECONDARY_EXEC_DESC);
 
@@ -5765,6 +5772,7 @@
 	vmx->rmode.vm86_active = 0;
 	vmx->spec_ctrl = 0;
 
+	vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
 	kvm_set_cr8(vcpu, 0);
 
@@ -9452,7 +9460,7 @@
 	 * being speculatively taken.
 	 */
 	if (vmx->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
@@ -9587,11 +9595,11 @@
 	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
 	 * save it.
 	 */
-	if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))
-		rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
 	if (vmx->spec_ctrl)
-		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
 
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
@@ -10136,7 +10144,10 @@
 			(unsigned long)(vmcs12->posted_intr_desc_addr &
 			(PAGE_SIZE - 1)));
 	}
-	if (!nested_vmx_prepare_msr_bitmap(vcpu, vmcs12))
+	if (nested_vmx_prepare_msr_bitmap(vcpu, vmcs12))
+		vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL,
+			      CPU_BASED_USE_MSR_BITMAPS);
+	else
 		vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
 				CPU_BASED_USE_MSR_BITMAPS);
 }
@@ -10224,8 +10235,8 @@
 	 *    updated to reflect this when L1 (or its L2s) actually write to
 	 *    the MSR.
 	 */
-	bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
-	bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
+	bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
+	bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
 
 	/* Nothing to do if the MSR bitmap is not in use.  */
 	if (!cpu_has_vmx_msr_bitmap() ||
@@ -11196,7 +11207,12 @@
 	if (ret)
 		return ret;
 
-	if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT)
+	/*
+	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
+	 * by event injection, halt vcpu.
+	 */
+	if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
+	    !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK))
 		return kvm_vcpu_halt(vcpu);
 
 	vmx->nested.nested_run_pending = 1;
@@ -12287,6 +12303,7 @@
 	.vcpu_put = vmx_vcpu_put,
 
 	.update_bp_intercept = update_exception_bitmap,
+	.get_msr_feature = vmx_get_msr_feature,
 	.get_msr = vmx_get_msr,
 	.set_msr = vmx_set_msr,
 	.get_segment_base = vmx_get_segment_base,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c8a0b54..18b5ca7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1049,6 +1049,45 @@
 
 static unsigned num_emulated_msrs;
 
+/*
+ * List of msr numbers which are used to expose MSR-based features that
+ * can be used by a hypervisor to validate requested CPU features.
+ */
+static u32 msr_based_features[] = {
+	MSR_F10H_DECFG,
+	MSR_IA32_UCODE_REV,
+};
+
+static unsigned int num_msr_based_features;
+
+static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
+{
+	switch (msr->index) {
+	case MSR_IA32_UCODE_REV:
+		rdmsrl(msr->index, msr->data);
+		break;
+	default:
+		if (kvm_x86_ops->get_msr_feature(msr))
+			return 1;
+	}
+	return 0;
+}
+
+static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
+{
+	struct kvm_msr_entry msr;
+	int r;
+
+	msr.index = index;
+	r = kvm_get_msr_feature(&msr);
+	if (r)
+		return r;
+
+	*data = msr.data;
+
+	return 0;
+}
+
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	if (efer & efer_reserved_bits)
@@ -2222,7 +2261,6 @@
 
 	switch (msr) {
 	case MSR_AMD64_NB_CFG:
-	case MSR_IA32_UCODE_REV:
 	case MSR_IA32_UCODE_WRITE:
 	case MSR_VM_HSAVE_PA:
 	case MSR_AMD64_PATCH_LOADER:
@@ -2230,6 +2268,10 @@
 	case MSR_AMD64_DC_CFG:
 		break;
 
+	case MSR_IA32_UCODE_REV:
+		if (msr_info->host_initiated)
+			vcpu->arch.microcode_version = data;
+		break;
 	case MSR_EFER:
 		return set_efer(vcpu, data);
 	case MSR_K7_HWCR:
@@ -2525,7 +2567,7 @@
 		msr_info->data = 0;
 		break;
 	case MSR_IA32_UCODE_REV:
-		msr_info->data = 0x100000000ULL;
+		msr_info->data = vcpu->arch.microcode_version;
 		break;
 	case MSR_MTRRcap:
 	case 0x200 ... 0x2ff:
@@ -2680,13 +2722,11 @@
 		    int (*do_msr)(struct kvm_vcpu *vcpu,
 				  unsigned index, u64 *data))
 {
-	int i, idx;
+	int i;
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	for (i = 0; i < msrs->nmsrs; ++i)
 		if (do_msr(vcpu, entries[i].index, &entries[i].data))
 			break;
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 	return i;
 }
@@ -2785,6 +2825,7 @@
 	case KVM_CAP_SET_BOOT_CPU_ID:
  	case KVM_CAP_SPLIT_IRQCHIP:
 	case KVM_CAP_IMMEDIATE_EXIT:
+	case KVM_CAP_GET_MSR_FEATURES:
 		r = 1;
 		break;
 	case KVM_CAP_ADJUST_CLOCK:
@@ -2899,6 +2940,31 @@
 			goto out;
 		r = 0;
 		break;
+	case KVM_GET_MSR_FEATURE_INDEX_LIST: {
+		struct kvm_msr_list __user *user_msr_list = argp;
+		struct kvm_msr_list msr_list;
+		unsigned int n;
+
+		r = -EFAULT;
+		if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list)))
+			goto out;
+		n = msr_list.nmsrs;
+		msr_list.nmsrs = num_msr_based_features;
+		if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list)))
+			goto out;
+		r = -E2BIG;
+		if (n < msr_list.nmsrs)
+			goto out;
+		r = -EFAULT;
+		if (copy_to_user(user_msr_list->indices, &msr_based_features,
+				 num_msr_based_features * sizeof(u32)))
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_GET_MSRS:
+		r = msr_io(NULL, argp, do_get_msr_feature, 1);
+		break;
 	}
 	default:
 		r = -EINVAL;
@@ -3636,12 +3702,18 @@
 		r = 0;
 		break;
 	}
-	case KVM_GET_MSRS:
+	case KVM_GET_MSRS: {
+		int idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = msr_io(vcpu, argp, do_get_msr, 1);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
-	case KVM_SET_MSRS:
+	}
+	case KVM_SET_MSRS: {
+		int idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = msr_io(vcpu, argp, do_set_msr, 0);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
+	}
 	case KVM_TPR_ACCESS_REPORTING: {
 		struct kvm_tpr_access_ctl tac;
 
@@ -4464,6 +4536,19 @@
 		j++;
 	}
 	num_emulated_msrs = j;
+
+	for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
+		struct kvm_msr_entry msr;
+
+		msr.index = msr_based_features[i];
+		if (kvm_get_msr_feature(&msr))
+			continue;
+
+		if (j < i)
+			msr_based_features[j] = msr_based_features[i];
+		j++;
+	}
+	num_msr_based_features = j;
 }
 
 static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@@ -8017,6 +8102,8 @@
 
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
+	kvm_lapic_reset(vcpu, init_event);
+
 	vcpu->arch.hflags = 0;
 
 	vcpu->arch.smi_pending = 0;
@@ -8460,10 +8547,8 @@
 			return r;
 	}
 
-	if (!size) {
-		r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);
-		WARN_ON(r < 0);
-	}
+	if (!size)
+		vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE);
 
 	return 0;
 }
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 91e9700..25a972c 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -28,7 +28,6 @@
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
 lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
 lib-$(CONFIG_RETPOLINE) += retpoline.o
-OBJECT_FILES_NON_STANDARD_retpoline.o :=y
 
 obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 
diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c
index d6f848d..2dd1fe13 100644
--- a/arch/x86/lib/cpu.c
+++ b/arch/x86/lib/cpu.c
@@ -18,7 +18,7 @@
 {
 	unsigned int fam, model;
 
-	 fam = x86_family(sig);
+	fam = x86_family(sig);
 
 	model = (sig >> 4) & 0xf;
 
diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c
index 7b881d0..3cdf061 100644
--- a/arch/x86/lib/error-inject.c
+++ b/arch/x86/lib/error-inject.c
@@ -7,6 +7,7 @@
 
 asm(
 	".type just_return_func, @function\n"
+	".globl just_return_func\n"
 	"just_return_func:\n"
 	"	ret\n"
 	".size just_return_func, .-just_return_func\n"
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 480edc3..c909961 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -7,7 +7,6 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 #include <asm/nospec-branch.h>
-#include <asm/bitsperlong.h>
 
 .macro THUNK reg
 	.section .text.__x86.indirect_thunk
@@ -47,58 +46,3 @@
 GENERATE_THUNK(r14)
 GENERATE_THUNK(r15)
 #endif
-
-/*
- * Fill the CPU return stack buffer.
- *
- * Each entry in the RSB, if used for a speculative 'ret', contains an
- * infinite 'pause; lfence; jmp' loop to capture speculative execution.
- *
- * This is required in various cases for retpoline and IBRS-based
- * mitigations for the Spectre variant 2 vulnerability. Sometimes to
- * eliminate potentially bogus entries from the RSB, and sometimes
- * purely to ensure that it doesn't get empty, which on some CPUs would
- * allow predictions from other (unwanted!) sources to be used.
- *
- * Google experimented with loop-unrolling and this turned out to be
- * the optimal version - two calls, each with their own speculation
- * trap should their return address end up getting used, in a loop.
- */
-.macro STUFF_RSB nr:req sp:req
-	mov	$(\nr / 2), %_ASM_BX
-	.align 16
-771:
-	call	772f
-773:						/* speculation trap */
-	pause
-	lfence
-	jmp	773b
-	.align 16
-772:
-	call	774f
-775:						/* speculation trap */
-	pause
-	lfence
-	jmp	775b
-	.align 16
-774:
-	dec	%_ASM_BX
-	jnz	771b
-	add	$((BITS_PER_LONG/8) * \nr), \sp
-.endm
-
-#define RSB_FILL_LOOPS		16	/* To avoid underflow */
-
-ENTRY(__fill_rsb)
-	STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP
-	ret
-END(__fill_rsb)
-EXPORT_SYMBOL_GPL(__fill_rsb)
-
-#define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
-
-ENTRY(__clear_rsb)
-	STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP
-	ret
-END(__clear_rsb)
-EXPORT_SYMBOL_GPL(__clear_rsb)
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index b9283cc..476d810 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -163,4 +163,10 @@
 
 	for_each_possible_cpu(cpu)
 		setup_cpu_entry_area(cpu);
+
+	/*
+	 * This is the last essential update to swapper_pgdir which needs
+	 * to be synchronized to initial_page_table on 32bit.
+	 */
+	sync_initial_page_table();
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 800de81..c88573d 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1248,10 +1248,6 @@
 	tsk = current;
 	mm = tsk->mm;
 
-	/*
-	 * Detect and handle instructions that would cause a page fault for
-	 * both a tracked kernel page and a userspace page.
-	 */
 	prefetchw(&mm->mmap_sem);
 
 	if (unlikely(kmmio_fault(regs, address)))
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 79cb066..396e1f0 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -453,6 +453,21 @@
 }
 #endif /* CONFIG_HIGHMEM */
 
+void __init sync_initial_page_table(void)
+{
+	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			KERNEL_PGD_PTRS);
+
+	/*
+	 * sync back low identity map too.  It is used for example
+	 * in the 32-bit EFI stub.
+	 */
+	clone_pgd_range(initial_page_table,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+}
+
 void __init native_pagetable_init(void)
 {
 	unsigned long pfn, va;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 1ab42c8..8b72923 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -256,7 +256,7 @@
 	 * It's enough to flush this one mapping.
 	 * (PGE mappings get flushed as well)
 	 */
-	__flush_tlb_one(vaddr);
+	__flush_tlb_one_kernel(vaddr);
 }
 
 void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte)
@@ -1193,8 +1193,8 @@
 	register_page_bootmem_info();
 
 	/* Register memory areas for /proc/kcore */
-	kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR,
-			 PAGE_SIZE, KCORE_OTHER);
+	if (get_gate_vma(&init_mm))
+		kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER);
 
 	mem_init_print_info(NULL);
 }
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index c45b6ec..e2db83b 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -820,5 +820,5 @@
 		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
 	else
 		pte_clear(&init_mm, addr, pte);
-	__flush_tlb_one(addr);
+	__flush_tlb_one_kernel(addr);
 }
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 58477ec..7c86867 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -168,7 +168,7 @@
 		return -1;
 	}
 
-	__flush_tlb_one(f->addr);
+	__flush_tlb_one_kernel(f->addr);
 	return 0;
 }
 
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 01f682c..40a6085 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -15,6 +15,7 @@
 #include <asm/page.h>
 #include <asm/processor-flags.h>
 #include <asm/msr-index.h>
+#include <asm/nospec-branch.h>
 
 	.text
 	.code64
@@ -59,6 +60,7 @@
 	movq	%rax, %r8		/* Workarea encryption routine */
 	addq	$PAGE_SIZE, %r8		/* Workarea intermediate copy buffer */
 
+	ANNOTATE_RETPOLINE_SAFE
 	call	*%rax			/* Call the encryption routine */
 
 	pop	%r12
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index c3c5274..9bb7f0a 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -63,7 +63,7 @@
 	 * It's enough to flush this one mapping.
 	 * (PGE mappings get flushed as well)
 	 */
-	__flush_tlb_one(vaddr);
+	__flush_tlb_one_kernel(vaddr);
 }
 
 unsigned long __FIXADDR_TOP = 0xfffff000;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 8dcc060..7f1a513 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -498,7 +498,7 @@
 	 *    flush that changes context.tlb_gen from 2 to 3.  If they get
 	 *    processed on this CPU in reverse order, we'll see
 	 *     local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL.
-	 *    If we were to use __flush_tlb_single() and set local_tlb_gen to
+	 *    If we were to use __flush_tlb_one_user() and set local_tlb_gen to
 	 *    3, we'd be break the invariant: we'd update local_tlb_gen above
 	 *    1 without the full flush that's needed for tlb_gen 2.
 	 *
@@ -519,7 +519,7 @@
 
 		addr = f->start;
 		while (addr < f->end) {
-			__flush_tlb_single(addr);
+			__flush_tlb_one_user(addr);
 			addr += PAGE_SIZE;
 		}
 		if (local)
@@ -666,7 +666,7 @@
 
 	/* flush range by one by one 'invlpg' */
 	for (addr = f->start; addr < f->end; addr += PAGE_SIZE)
-		__flush_tlb_one(addr);
+		__flush_tlb_one_kernel(addr);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4923d92..45e4eb5 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -13,6 +13,7 @@
 #include <linux/if_vlan.h>
 #include <asm/cacheflush.h>
 #include <asm/set_memory.h>
+#include <asm/nospec-branch.h>
 #include <linux/bpf.h>
 
 /*
@@ -290,7 +291,7 @@
 	EMIT2(0x89, 0xD2);                        /* mov edx, edx */
 	EMIT3(0x39, 0x56,                         /* cmp dword ptr [rsi + 16], edx */
 	      offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 43 /* number of bytes to jump */
+#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
@@ -299,7 +300,7 @@
 	 */
 	EMIT2_off32(0x8B, 0x85, 36);              /* mov eax, dword ptr [rbp + 36] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 32
+#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
@@ -313,7 +314,7 @@
 	 *   goto out;
 	 */
 	EMIT3(0x48, 0x85, 0xC0);		  /* test rax,rax */
-#define OFFSET3 10
+#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
 	EMIT2(X86_JE, OFFSET3);                   /* je out */
 	label3 = cnt;
 
@@ -326,7 +327,7 @@
 	 * rdi == ctx (1st arg)
 	 * rax == prog->bpf_func + prologue_size
 	 */
-	EMIT2(0xFF, 0xE0);                        /* jmp rax */
+	RETPOLINE_RAX_BPF_JIT();
 
 	/* out: */
 	BUILD_BUG_ON(cnt - label1 != OFFSET1);
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 174c597..a7a7677 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -460,7 +460,7 @@
 		goto fail;
 
 	for_each_possible_cpu(cpu) {
-		if (!cpu)
+		if (!IS_ENABLED(CONFIG_SMP) || !cpu)
 			continue;
 
 		memcpy(per_cpu(cpu_msrs, cpu).counters,
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 2c67bae..fb1df94 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -79,7 +79,7 @@
 
 static void intel_mid_reboot(void)
 {
-	intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
+	intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
 }
 
 static unsigned long __init intel_mid_calibrate_tsc(void)
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index c2e9285..db77e087 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -299,7 +299,7 @@
 		local_flush_tlb();
 		stat->d_alltlb++;
 	} else {
-		__flush_tlb_single(msg->address);
+		__flush_tlb_one_user(msg->address);
 		stat->d_onetlb++;
 	}
 	stat->d_requestee++;
diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index de53bd1..24bb759 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -102,7 +102,7 @@
 	 * don't we'll eventually crash trying to execute encrypted
 	 * instructions.
 	 */
-	bt	$TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags
+	btl	$TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags
 	jnc	.Ldone
 	movl	$MSR_K8_SYSCFG, %ecx
 	rdmsr
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 5d73c44..220e978 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -770,9 +770,12 @@
 		break;
 
 	case R_X86_64_PC32:
+	case R_X86_64_PLT32:
 		/*
 		 * PC relative relocations don't need to be adjusted unless
 		 * referencing a percpu symbol.
+		 *
+		 * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
 		 */
 		if (is_percpu_sym(sym, symname))
 			add_reloc(&relocs32neg, offset);
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index c047f42..3c2c253 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1376,8 +1376,6 @@
 
 	if (!xen_initial_domain()) {
 		add_preferred_console("xenboot", 0, NULL);
-		add_preferred_console("tty", 0, NULL);
-		add_preferred_console("hvc", 0, NULL);
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
 	} else {
@@ -1410,6 +1408,10 @@
 
 		xen_boot_params_init_edd();
 	}
+
+	add_preferred_console("tty", 0, NULL);
+	add_preferred_console("hvc", 0, NULL);
+
 #ifdef CONFIG_PCI
 	/* PCI BIOS service won't work from a PV guest. */
 	pci_probe &= ~PCI_PROBE_BIOS;
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index d850762..aae88fe 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1300,12 +1300,12 @@
 	preempt_enable();
 }
 
-static void xen_flush_tlb_single(unsigned long addr)
+static void xen_flush_tlb_one_user(unsigned long addr)
 {
 	struct mmuext_op *op;
 	struct multicall_space mcs;
 
-	trace_xen_mmu_flush_tlb_single(addr);
+	trace_xen_mmu_flush_tlb_one_user(addr);
 
 	preempt_disable();
 
@@ -2370,7 +2370,7 @@
 
 	.flush_tlb_user = xen_flush_tlb,
 	.flush_tlb_kernel = xen_flush_tlb,
-	.flush_tlb_single = xen_flush_tlb_single,
+	.flush_tlb_one_user = xen_flush_tlb_one_user,
 	.flush_tlb_others = xen_flush_tlb_others,
 
 	.pgd_alloc = xen_pgd_alloc,
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 77c959c..7a43b2a 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -122,6 +122,8 @@
 
 	if (xen_hvm_domain())
 		native_smp_cpus_done(max_cpus);
+	else
+		calculate_max_logical_packages();
 
 	if (xen_have_vcpu_info_placement)
 		return;
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index d9f96cc..1d83152 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -1,12 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 #include <linux/tick.h>
+#include <linux/percpu-defs.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
 #include <xen/grant_table.h>
 #include <xen/events.h>
 
+#include <asm/cpufeatures.h>
+#include <asm/msr-index.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/page.h>
 #include <asm/fixmap.h>
@@ -15,6 +18,8 @@
 #include "mmu.h"
 #include "pmu.h"
 
+static DEFINE_PER_CPU(u64, spec_ctrl);
+
 void xen_arch_pre_suspend(void)
 {
 	xen_save_time_memory_area();
@@ -35,6 +40,9 @@
 
 static void xen_vcpu_notify_restore(void *data)
 {
+	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+		wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
+
 	/* Boot processor notified via generic timekeeping_resume() */
 	if (smp_processor_id() == 0)
 		return;
@@ -44,7 +52,15 @@
 
 static void xen_vcpu_notify_suspend(void *data)
 {
+	u64 tmp;
+
 	tick_suspend_local();
+
+	if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) {
+		rdmsrl(MSR_IA32_SPEC_CTRL, tmp);
+		this_cpu_write(spec_ctrl, tmp);
+		wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+	}
 }
 
 void xen_arch_resume(void)
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 623720a..732631c 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/dma-contiguous.h>
+#include <linux/dma-direct.h>
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
@@ -123,7 +124,7 @@
 			      unsigned long attrs)
 {
 	unsigned long ret;
-	unsigned long uncached = 0;
+	unsigned long uncached;
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	struct page *page = NULL;
 
@@ -144,15 +145,27 @@
 	if (!page)
 		return NULL;
 
+	*handle = phys_to_dma(dev, page_to_phys(page));
+
+#ifdef CONFIG_MMU
+	if (PageHighMem(page)) {
+		void *p;
+
+		p = dma_common_contiguous_remap(page, size, VM_MAP,
+						pgprot_noncached(PAGE_KERNEL),
+						__builtin_return_address(0));
+		if (!p) {
+			if (!dma_release_from_contiguous(dev, page, count))
+				__free_pages(page, get_order(size));
+		}
+		return p;
+	}
+#endif
 	ret = (unsigned long)page_address(page);
-
-	/* We currently don't support coherent memory outside KSEG */
-
 	BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR ||
 	       ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
 	uncached = ret + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR;
-	*handle = virt_to_bus((void *)ret);
 	__invalidate_dcache_range(ret, size);
 
 	return (void *)uncached;
@@ -161,13 +174,20 @@
 static void xtensa_dma_free(struct device *dev, size_t size, void *vaddr,
 			    dma_addr_t dma_handle, unsigned long attrs)
 {
-	unsigned long addr = (unsigned long)vaddr +
-		XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
-	struct page *page = virt_to_page(addr);
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)vaddr;
+	struct page *page;
 
-	BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR ||
-	       addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
+	if (addr >= XCHAL_KSEG_BYPASS_VADDR &&
+	    addr - XCHAL_KSEG_BYPASS_VADDR < XCHAL_KSEG_SIZE) {
+		addr += XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
+		page = virt_to_page(addr);
+	} else {
+#ifdef CONFIG_MMU
+		dma_common_free_remap(vaddr, size, VM_MAP);
+#endif
+		page = pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_handle)));
+	}
 
 	if (!dma_release_from_contiguous(dev, page, count))
 		__free_pages(page, get_order(size));
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index d776ec0..34aead7 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -79,19 +79,75 @@
 	free_area_init_node(0, zones_size, ARCH_PFN_OFFSET, NULL);
 }
 
+#ifdef CONFIG_HIGHMEM
+static void __init free_area_high(unsigned long pfn, unsigned long end)
+{
+	for (; pfn < end; pfn++)
+		free_highmem_page(pfn_to_page(pfn));
+}
+
+static void __init free_highpages(void)
+{
+	unsigned long max_low = max_low_pfn;
+	struct memblock_region *mem, *res;
+
+	reset_all_zones_managed_pages();
+	/* set highmem page free */
+	for_each_memblock(memory, mem) {
+		unsigned long start = memblock_region_memory_base_pfn(mem);
+		unsigned long end = memblock_region_memory_end_pfn(mem);
+
+		/* Ignore complete lowmem entries */
+		if (end <= max_low)
+			continue;
+
+		if (memblock_is_nomap(mem))
+			continue;
+
+		/* Truncate partial highmem entries */
+		if (start < max_low)
+			start = max_low;
+
+		/* Find and exclude any reserved regions */
+		for_each_memblock(reserved, res) {
+			unsigned long res_start, res_end;
+
+			res_start = memblock_region_reserved_base_pfn(res);
+			res_end = memblock_region_reserved_end_pfn(res);
+
+			if (res_end < start)
+				continue;
+			if (res_start < start)
+				res_start = start;
+			if (res_start > end)
+				res_start = end;
+			if (res_end > end)
+				res_end = end;
+			if (res_start != start)
+				free_area_high(start, res_start);
+			start = res_end;
+			if (start == end)
+				break;
+		}
+
+		/* And now free anything which remains */
+		if (start < end)
+			free_area_high(start, end);
+	}
+}
+#else
+static void __init free_highpages(void)
+{
+}
+#endif
+
 /*
  * Initialize memory pages.
  */
 
 void __init mem_init(void)
 {
-#ifdef CONFIG_HIGHMEM
-	unsigned long tmp;
-
-	reset_all_zones_managed_pages();
-	for (tmp = max_low_pfn; tmp < max_pfn; tmp++)
-		free_highmem_page(pfn_to_page(tmp));
-#endif
+	free_highpages();
 
 	max_mapnr = max_pfn - ARCH_PFN_OFFSET;
 	high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4117524..c2033a2 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -812,7 +812,6 @@
 	struct gendisk *disk;
 	struct request_queue *q;
 	struct blkcg_gq *blkg;
-	struct module *owner;
 	unsigned int major, minor;
 	int key_len, part, ret;
 	char *body;
@@ -904,9 +903,7 @@
 	spin_unlock_irq(q->queue_lock);
 	rcu_read_unlock();
 fail:
-	owner = disk->fops->owner;
-	put_disk(disk);
-	module_put(owner);
+	put_disk_and_module(disk);
 	/*
 	 * If queue was bypassing, we should retry.  Do so after a
 	 * short msleep().  It isn't strictly necessary but queue
@@ -931,13 +928,9 @@
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	__releases(ctx->disk->queue->queue_lock) __releases(rcu)
 {
-	struct module *owner;
-
 	spin_unlock_irq(ctx->disk->queue->queue_lock);
 	rcu_read_unlock();
-	owner = ctx->disk->fops->owner;
-	put_disk(ctx->disk);
-	module_put(owner);
+	put_disk_and_module(ctx->disk);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 2d1a7bb..6d82c4f 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2434,7 +2434,7 @@
 		unsigned int count;
 
 		if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
-			count = queue_logical_block_size(bio->bi_disk->queue);
+			count = queue_logical_block_size(bio->bi_disk->queue) >> 9;
 		else
 			count = bio_sectors(bio);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index df93102..16e83e6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -712,7 +712,6 @@
 
 	trace_block_rq_requeue(q, rq);
 	wbt_requeue(q->rq_wb, &rq->issue_stat);
-	blk_mq_sched_requeue_request(rq);
 
 	if (blk_mq_rq_state(rq) != MQ_RQ_IDLE) {
 		blk_mq_rq_update_state(rq, MQ_RQ_IDLE);
@@ -725,6 +724,9 @@
 {
 	__blk_mq_requeue_request(rq);
 
+	/* this request will be re-inserted to io scheduler queue */
+	blk_mq_sched_requeue_request(rq);
+
 	BUG_ON(blk_queued_rq(rq));
 	blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
 }
@@ -3164,6 +3166,7 @@
 		cpu_relax();
 	}
 
+	__set_current_state(TASK_RUNNING);
 	return false;
 }
 
diff --git a/block/genhd.c b/block/genhd.c
index 88a53c1..9656f9e 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -547,7 +547,7 @@
 {
 	struct gendisk *p = data;
 
-	if (!get_disk(p))
+	if (!get_disk_and_module(p))
 		return -1;
 	return 0;
 }
@@ -717,6 +717,11 @@
 	blk_integrity_del(disk);
 	disk_del_events(disk);
 
+	/*
+	 * Block lookups of the disk until all bdevs are unhashed and the
+	 * disk is marked as dead (GENHD_FL_UP cleared).
+	 */
+	down_write(&disk->lookup_sem);
 	/* invalidate stuff */
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
@@ -731,6 +736,7 @@
 	bdev_unhash_inode(disk_devt(disk));
 	set_capacity(disk, 0);
 	disk->flags &= ~GENHD_FL_UP;
+	up_write(&disk->lookup_sem);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN))
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -809,16 +815,28 @@
 
 		spin_lock_bh(&ext_devt_lock);
 		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		if (part && get_disk(part_to_disk(part))) {
+		if (part && get_disk_and_module(part_to_disk(part))) {
 			*partno = part->partno;
 			disk = part_to_disk(part);
 		}
 		spin_unlock_bh(&ext_devt_lock);
 	}
 
-	if (disk && unlikely(disk->flags & GENHD_FL_HIDDEN)) {
-		put_disk(disk);
+	if (!disk)
+		return NULL;
+
+	/*
+	 * Synchronize with del_gendisk() to not return disk that is being
+	 * destroyed.
+	 */
+	down_read(&disk->lookup_sem);
+	if (unlikely((disk->flags & GENHD_FL_HIDDEN) ||
+		     !(disk->flags & GENHD_FL_UP))) {
+		up_read(&disk->lookup_sem);
+		put_disk_and_module(disk);
 		disk = NULL;
+	} else {
+		up_read(&disk->lookup_sem);
 	}
 	return disk;
 }
@@ -1418,6 +1436,7 @@
 			kfree(disk);
 			return NULL;
 		}
+		init_rwsem(&disk->lookup_sem);
 		disk->node_id = node_id;
 		if (disk_expand_part_tbl(disk, 0)) {
 			free_part_stats(&disk->part0);
@@ -1453,7 +1472,7 @@
 }
 EXPORT_SYMBOL(__alloc_disk_node);
 
-struct kobject *get_disk(struct gendisk *disk)
+struct kobject *get_disk_and_module(struct gendisk *disk)
 {
 	struct module *owner;
 	struct kobject *kobj;
@@ -1471,17 +1490,30 @@
 	return kobj;
 
 }
-
-EXPORT_SYMBOL(get_disk);
+EXPORT_SYMBOL(get_disk_and_module);
 
 void put_disk(struct gendisk *disk)
 {
 	if (disk)
 		kobject_put(&disk_to_dev(disk)->kobj);
 }
-
 EXPORT_SYMBOL(put_disk);
 
+/*
+ * This is a counterpart of get_disk_and_module() and thus also of
+ * get_gendisk().
+ */
+void put_disk_and_module(struct gendisk *disk)
+{
+	if (disk) {
+		struct module *owner = disk->fops->owner;
+
+		put_disk(disk);
+		module_put(owner);
+	}
+}
+EXPORT_SYMBOL(put_disk_and_module);
+
 static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 {
 	char event[] = "DISK_RO=1";
diff --git a/block/ioctl.c b/block/ioctl.c
index 1668506..3884d81 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -225,7 +225,7 @@
 
 	if (start + len > i_size_read(bdev->bd_inode))
 		return -EINVAL;
-	truncate_inode_pages_range(mapping, start, start + len);
+	truncate_inode_pages_range(mapping, start, start + len - 1);
 	return blkdev_issue_discard(bdev, start >> 9, len >> 9,
 				    GFP_KERNEL, flags);
 }
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index f95c607..0d6d25e3 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -833,6 +833,7 @@
 		.limit_depth = kyber_limit_depth,
 		.prepare_request = kyber_prepare_request,
 		.finish_request = kyber_finish_request,
+		.requeue_request = kyber_finish_request,
 		.completed_request = kyber_completed_request,
 		.dispatch_request = kyber_dispatch_request,
 		.has_work = kyber_has_work,
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index c56f211..8ec0ba9 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -536,12 +536,21 @@
 }
 
 /*
+ * Nothing to do here. This is defined only to ensure that .finish_request
+ * method is called upon request completion.
+ */
+static void dd_prepare_request(struct request *rq, struct bio *bio)
+{
+}
+
+/*
  * For zoned block devices, write unlock the target zone of
  * completed write requests. Do this while holding the zone lock
  * spinlock so that the zone is never unlocked while deadline_fifo_request()
- * while deadline_next_request() are executing.
+ * or deadline_next_request() are executing. This function is called for
+ * all requests, whether or not these requests complete successfully.
  */
-static void dd_completed_request(struct request *rq)
+static void dd_finish_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
@@ -756,7 +765,8 @@
 	.ops.mq = {
 		.insert_requests	= dd_insert_requests,
 		.dispatch_request	= dd_dispatch_request,
-		.completed_request	= dd_completed_request,
+		.prepare_request	= dd_prepare_request,
+		.finish_request		= dd_finish_request,
 		.next_request		= elv_rb_latter_request,
 		.former_request		= elv_rb_former_request,
 		.bio_merge		= dd_bio_merge,
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 91622db..08dabcd 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -51,6 +51,12 @@
 
 EXPORT_SYMBOL(bdevname);
 
+const char *bio_devname(struct bio *bio, char *buf)
+{
+	return disk_name(bio->bi_disk, bio->bi_partno, buf);
+}
+EXPORT_SYMBOL(bio_devname);
+
 /*
  * There's very little reason to use this, you should really
  * have a struct block_device just about everywhere and use
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 9ed51d0c..e4929ee 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -490,7 +490,7 @@
 
 	if (!found_com_id) {
 		pr_debug("Could not find OPAL comid for device. Returning early\n");
-		return -EOPNOTSUPP;;
+		return -EOPNOTSUPP;
 	}
 
 	dev->comid = comid;
diff --git a/certs/blacklist_nohashes.c b/certs/blacklist_nohashes.c
index 73fd990..753b703 100644
--- a/certs/blacklist_nohashes.c
+++ b/certs/blacklist_nohashes.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "blacklist.h"
 
-const char __initdata *const blacklist_hashes[] = {
+const char __initconst *const blacklist_hashes[] = {
 	NULL
 };
diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c
index 1f4e25f..598906b 100644
--- a/crypto/asymmetric_keys/pkcs7_trust.c
+++ b/crypto/asymmetric_keys/pkcs7_trust.c
@@ -106,6 +106,7 @@
 		pr_devel("sinfo %u: Direct signer is key %x\n",
 			 sinfo->index, key_serial(key));
 		x509 = NULL;
+		sig = sinfo->sig;
 		goto matched;
 	}
 	if (PTR_ERR(key) != -ENOKEY)
diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c
index 39e6de0..97c77f6 100644
--- a/crypto/asymmetric_keys/pkcs7_verify.c
+++ b/crypto/asymmetric_keys/pkcs7_verify.c
@@ -270,7 +270,7 @@
 				sinfo->index);
 			return 0;
 		}
-		ret = public_key_verify_signature(p->pub, p->sig);
+		ret = public_key_verify_signature(p->pub, x509->sig);
 		if (ret < 0)
 			return ret;
 		x509->signer = p;
@@ -366,8 +366,7 @@
  *
  *  (*) -EBADMSG if some part of the message was invalid, or:
  *
- *  (*) 0 if no signature chains were found to be blacklisted or to contain
- *	unsupported crypto, or:
+ *  (*) 0 if a signature chain passed verification, or:
  *
  *  (*) -EKEYREJECTED if a blacklisted key was encountered, or:
  *
@@ -423,8 +422,11 @@
 
 	for (sinfo = pkcs7->signed_infos; sinfo; sinfo = sinfo->next) {
 		ret = pkcs7_verify_one(pkcs7, sinfo);
-		if (sinfo->blacklisted && actual_ret == -ENOPKG)
-			actual_ret = -EKEYREJECTED;
+		if (sinfo->blacklisted) {
+			if (actual_ret == -ENOPKG)
+				actual_ret = -EKEYREJECTED;
+			continue;
+		}
 		if (ret < 0) {
 			if (ret == -ENOPKG) {
 				sinfo->unsupported_crypto = true;
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index de99658..e929fe1 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -79,9 +79,11 @@
 
 	BUG_ON(!pkey);
 	BUG_ON(!sig);
-	BUG_ON(!sig->digest);
 	BUG_ON(!sig->s);
 
+	if (!sig->digest)
+		return -ENOPKG;
+
 	alg_name = sig->pkey_algo;
 	if (strcmp(sig->pkey_algo, "rsa") == 0) {
 		/* The data wangled by the RSA algorithm is typically padded
diff --git a/crypto/asymmetric_keys/restrict.c b/crypto/asymmetric_keys/restrict.c
index 86fb685..7c93c77 100644
--- a/crypto/asymmetric_keys/restrict.c
+++ b/crypto/asymmetric_keys/restrict.c
@@ -67,8 +67,9 @@
  *
  * Returns 0 if the new certificate was accepted, -ENOKEY if we couldn't find a
  * matching parent certificate in the trusted list, -EKEYREJECTED if the
- * signature check fails or the key is blacklisted and some other error if
- * there is a matching certificate but the signature check cannot be performed.
+ * signature check fails or the key is blacklisted, -ENOPKG if the signature
+ * uses unsupported crypto, or some other error if there is a matching
+ * certificate but the signature check cannot be performed.
  */
 int restrict_link_by_signature(struct key *dest_keyring,
 			       const struct key_type *type,
@@ -88,6 +89,8 @@
 		return -EOPNOTSUPP;
 
 	sig = payload->data[asym_auth];
+	if (!sig)
+		return -ENOPKG;
 	if (!sig->auth_ids[0] && !sig->auth_ids[1])
 		return -ENOKEY;
 
@@ -139,6 +142,8 @@
 		return -EOPNOTSUPP;
 
 	sig = payload->data[asym_auth];
+	if (!sig)
+		return -ENOPKG;
 	if (!sig->auth_ids[0] && !sig->auth_ids[1])
 		return -ENOKEY;
 
@@ -222,9 +227,9 @@
  *
  * Returns 0 if the new certificate was accepted, -ENOKEY if we
  * couldn't find a matching parent certificate in the trusted list,
- * -EKEYREJECTED if the signature check fails, and some other error if
- * there is a matching certificate but the signature check cannot be
- * performed.
+ * -EKEYREJECTED if the signature check fails, -ENOPKG if the signature uses
+ * unsupported crypto, or some other error if there is a matching certificate
+ * but the signature check cannot be performed.
  */
 int restrict_link_by_key_or_keyring(struct key *dest_keyring,
 				    const struct key_type *type,
@@ -249,9 +254,9 @@
  *
  * Returns 0 if the new certificate was accepted, -ENOKEY if we
  * couldn't find a matching parent certificate in the trusted list,
- * -EKEYREJECTED if the signature check fails, and some other error if
- * there is a matching certificate but the signature check cannot be
- * performed.
+ * -EKEYREJECTED if the signature check fails, -ENOPKG if the signature uses
+ * unsupported crypto, or some other error if there is a matching certificate
+ * but the signature check cannot be performed.
  */
 int restrict_link_by_key_or_keyring_chain(struct key *dest_keyring,
 					  const struct key_type *type,
diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c
index a965b9d..ded1487 100644
--- a/crypto/sha3_generic.c
+++ b/crypto/sha3_generic.c
@@ -20,6 +20,20 @@
 #include <crypto/sha3.h>
 #include <asm/unaligned.h>
 
+/*
+ * On some 32-bit architectures (mn10300 and h8300), GCC ends up using
+ * over 1 KB of stack if we inline the round calculation into the loop
+ * in keccakf(). On the other hand, on 64-bit architectures with plenty
+ * of [64-bit wide] general purpose registers, not inlining it severely
+ * hurts performance. So let's use 64-bitness as a heuristic to decide
+ * whether to inline or not.
+ */
+#ifdef CONFIG_64BIT
+#define SHA3_INLINE	inline
+#else
+#define SHA3_INLINE	noinline
+#endif
+
 #define KECCAK_ROUNDS 24
 
 static const u64 keccakf_rndc[24] = {
@@ -35,111 +49,115 @@
 
 /* update the state with given number of rounds */
 
-static void __attribute__((__optimize__("O3"))) keccakf(u64 st[25])
+static SHA3_INLINE void keccakf_round(u64 st[25])
 {
 	u64 t[5], tt, bc[5];
+
+	/* Theta */
+	bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20];
+	bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21];
+	bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22];
+	bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23];
+	bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24];
+
+	t[0] = bc[4] ^ rol64(bc[1], 1);
+	t[1] = bc[0] ^ rol64(bc[2], 1);
+	t[2] = bc[1] ^ rol64(bc[3], 1);
+	t[3] = bc[2] ^ rol64(bc[4], 1);
+	t[4] = bc[3] ^ rol64(bc[0], 1);
+
+	st[0] ^= t[0];
+
+	/* Rho Pi */
+	tt = st[1];
+	st[ 1] = rol64(st[ 6] ^ t[1], 44);
+	st[ 6] = rol64(st[ 9] ^ t[4], 20);
+	st[ 9] = rol64(st[22] ^ t[2], 61);
+	st[22] = rol64(st[14] ^ t[4], 39);
+	st[14] = rol64(st[20] ^ t[0], 18);
+	st[20] = rol64(st[ 2] ^ t[2], 62);
+	st[ 2] = rol64(st[12] ^ t[2], 43);
+	st[12] = rol64(st[13] ^ t[3], 25);
+	st[13] = rol64(st[19] ^ t[4],  8);
+	st[19] = rol64(st[23] ^ t[3], 56);
+	st[23] = rol64(st[15] ^ t[0], 41);
+	st[15] = rol64(st[ 4] ^ t[4], 27);
+	st[ 4] = rol64(st[24] ^ t[4], 14);
+	st[24] = rol64(st[21] ^ t[1],  2);
+	st[21] = rol64(st[ 8] ^ t[3], 55);
+	st[ 8] = rol64(st[16] ^ t[1], 45);
+	st[16] = rol64(st[ 5] ^ t[0], 36);
+	st[ 5] = rol64(st[ 3] ^ t[3], 28);
+	st[ 3] = rol64(st[18] ^ t[3], 21);
+	st[18] = rol64(st[17] ^ t[2], 15);
+	st[17] = rol64(st[11] ^ t[1], 10);
+	st[11] = rol64(st[ 7] ^ t[2],  6);
+	st[ 7] = rol64(st[10] ^ t[0],  3);
+	st[10] = rol64(    tt ^ t[1],  1);
+
+	/* Chi */
+	bc[ 0] = ~st[ 1] & st[ 2];
+	bc[ 1] = ~st[ 2] & st[ 3];
+	bc[ 2] = ~st[ 3] & st[ 4];
+	bc[ 3] = ~st[ 4] & st[ 0];
+	bc[ 4] = ~st[ 0] & st[ 1];
+	st[ 0] ^= bc[ 0];
+	st[ 1] ^= bc[ 1];
+	st[ 2] ^= bc[ 2];
+	st[ 3] ^= bc[ 3];
+	st[ 4] ^= bc[ 4];
+
+	bc[ 0] = ~st[ 6] & st[ 7];
+	bc[ 1] = ~st[ 7] & st[ 8];
+	bc[ 2] = ~st[ 8] & st[ 9];
+	bc[ 3] = ~st[ 9] & st[ 5];
+	bc[ 4] = ~st[ 5] & st[ 6];
+	st[ 5] ^= bc[ 0];
+	st[ 6] ^= bc[ 1];
+	st[ 7] ^= bc[ 2];
+	st[ 8] ^= bc[ 3];
+	st[ 9] ^= bc[ 4];
+
+	bc[ 0] = ~st[11] & st[12];
+	bc[ 1] = ~st[12] & st[13];
+	bc[ 2] = ~st[13] & st[14];
+	bc[ 3] = ~st[14] & st[10];
+	bc[ 4] = ~st[10] & st[11];
+	st[10] ^= bc[ 0];
+	st[11] ^= bc[ 1];
+	st[12] ^= bc[ 2];
+	st[13] ^= bc[ 3];
+	st[14] ^= bc[ 4];
+
+	bc[ 0] = ~st[16] & st[17];
+	bc[ 1] = ~st[17] & st[18];
+	bc[ 2] = ~st[18] & st[19];
+	bc[ 3] = ~st[19] & st[15];
+	bc[ 4] = ~st[15] & st[16];
+	st[15] ^= bc[ 0];
+	st[16] ^= bc[ 1];
+	st[17] ^= bc[ 2];
+	st[18] ^= bc[ 3];
+	st[19] ^= bc[ 4];
+
+	bc[ 0] = ~st[21] & st[22];
+	bc[ 1] = ~st[22] & st[23];
+	bc[ 2] = ~st[23] & st[24];
+	bc[ 3] = ~st[24] & st[20];
+	bc[ 4] = ~st[20] & st[21];
+	st[20] ^= bc[ 0];
+	st[21] ^= bc[ 1];
+	st[22] ^= bc[ 2];
+	st[23] ^= bc[ 3];
+	st[24] ^= bc[ 4];
+}
+
+static void __optimize("O3") keccakf(u64 st[25])
+{
 	int round;
 
 	for (round = 0; round < KECCAK_ROUNDS; round++) {
-
-		/* Theta */
-		bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20];
-		bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21];
-		bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22];
-		bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23];
-		bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24];
-
-		t[0] = bc[4] ^ rol64(bc[1], 1);
-		t[1] = bc[0] ^ rol64(bc[2], 1);
-		t[2] = bc[1] ^ rol64(bc[3], 1);
-		t[3] = bc[2] ^ rol64(bc[4], 1);
-		t[4] = bc[3] ^ rol64(bc[0], 1);
-
-		st[0] ^= t[0];
-
-		/* Rho Pi */
-		tt = st[1];
-		st[ 1] = rol64(st[ 6] ^ t[1], 44);
-		st[ 6] = rol64(st[ 9] ^ t[4], 20);
-		st[ 9] = rol64(st[22] ^ t[2], 61);
-		st[22] = rol64(st[14] ^ t[4], 39);
-		st[14] = rol64(st[20] ^ t[0], 18);
-		st[20] = rol64(st[ 2] ^ t[2], 62);
-		st[ 2] = rol64(st[12] ^ t[2], 43);
-		st[12] = rol64(st[13] ^ t[3], 25);
-		st[13] = rol64(st[19] ^ t[4],  8);
-		st[19] = rol64(st[23] ^ t[3], 56);
-		st[23] = rol64(st[15] ^ t[0], 41);
-		st[15] = rol64(st[ 4] ^ t[4], 27);
-		st[ 4] = rol64(st[24] ^ t[4], 14);
-		st[24] = rol64(st[21] ^ t[1],  2);
-		st[21] = rol64(st[ 8] ^ t[3], 55);
-		st[ 8] = rol64(st[16] ^ t[1], 45);
-		st[16] = rol64(st[ 5] ^ t[0], 36);
-		st[ 5] = rol64(st[ 3] ^ t[3], 28);
-		st[ 3] = rol64(st[18] ^ t[3], 21);
-		st[18] = rol64(st[17] ^ t[2], 15);
-		st[17] = rol64(st[11] ^ t[1], 10);
-		st[11] = rol64(st[ 7] ^ t[2],  6);
-		st[ 7] = rol64(st[10] ^ t[0],  3);
-		st[10] = rol64(    tt ^ t[1],  1);
-
-		/* Chi */
-		bc[ 0] = ~st[ 1] & st[ 2];
-		bc[ 1] = ~st[ 2] & st[ 3];
-		bc[ 2] = ~st[ 3] & st[ 4];
-		bc[ 3] = ~st[ 4] & st[ 0];
-		bc[ 4] = ~st[ 0] & st[ 1];
-		st[ 0] ^= bc[ 0];
-		st[ 1] ^= bc[ 1];
-		st[ 2] ^= bc[ 2];
-		st[ 3] ^= bc[ 3];
-		st[ 4] ^= bc[ 4];
-
-		bc[ 0] = ~st[ 6] & st[ 7];
-		bc[ 1] = ~st[ 7] & st[ 8];
-		bc[ 2] = ~st[ 8] & st[ 9];
-		bc[ 3] = ~st[ 9] & st[ 5];
-		bc[ 4] = ~st[ 5] & st[ 6];
-		st[ 5] ^= bc[ 0];
-		st[ 6] ^= bc[ 1];
-		st[ 7] ^= bc[ 2];
-		st[ 8] ^= bc[ 3];
-		st[ 9] ^= bc[ 4];
-
-		bc[ 0] = ~st[11] & st[12];
-		bc[ 1] = ~st[12] & st[13];
-		bc[ 2] = ~st[13] & st[14];
-		bc[ 3] = ~st[14] & st[10];
-		bc[ 4] = ~st[10] & st[11];
-		st[10] ^= bc[ 0];
-		st[11] ^= bc[ 1];
-		st[12] ^= bc[ 2];
-		st[13] ^= bc[ 3];
-		st[14] ^= bc[ 4];
-
-		bc[ 0] = ~st[16] & st[17];
-		bc[ 1] = ~st[17] & st[18];
-		bc[ 2] = ~st[18] & st[19];
-		bc[ 3] = ~st[19] & st[15];
-		bc[ 4] = ~st[15] & st[16];
-		st[15] ^= bc[ 0];
-		st[16] ^= bc[ 1];
-		st[17] ^= bc[ 2];
-		st[18] ^= bc[ 3];
-		st[19] ^= bc[ 4];
-
-		bc[ 0] = ~st[21] & st[22];
-		bc[ 1] = ~st[22] & st[23];
-		bc[ 2] = ~st[23] & st[24];
-		bc[ 3] = ~st[24] & st[20];
-		bc[ 4] = ~st[20] & st[21];
-		st[20] ^= bc[ 0];
-		st[21] ^= bc[ 1];
-		st[22] ^= bc[ 2];
-		st[23] ^= bc[ 3];
-		st[24] ^= bc[ 4];
-
+		keccakf_round(st);
 		/* Iota */
 		st[0] ^= keccakf_rndc[round];
 	}
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 676c978..0dad0bd 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -660,13 +660,15 @@
  * acpi_of_match_device - Match device object using the "compatible" property.
  * @adev: ACPI device object to match.
  * @of_match_table: List of device IDs to match against.
+ * @of_id: OF ID if matched
  *
  * If @dev has an ACPI companion which has ACPI_DT_NAMESPACE_HID in its list of
  * identifiers and a _DSD object with the "compatible" property, use that
  * property to match against the given list of identifiers.
  */
 static bool acpi_of_match_device(struct acpi_device *adev,
-				 const struct of_device_id *of_match_table)
+				 const struct of_device_id *of_match_table,
+				 const struct of_device_id **of_id)
 {
 	const union acpi_object *of_compatible, *obj;
 	int i, nval;
@@ -690,8 +692,11 @@
 		const struct of_device_id *id;
 
 		for (id = of_match_table; id->compatible[0]; id++)
-			if (!strcasecmp(obj->string.pointer, id->compatible))
+			if (!strcasecmp(obj->string.pointer, id->compatible)) {
+				if (of_id)
+					*of_id = id;
 				return true;
+			}
 	}
 
 	return false;
@@ -762,10 +767,11 @@
 	return true;
 }
 
-static const struct acpi_device_id *__acpi_match_device(
-	struct acpi_device *device,
-	const struct acpi_device_id *ids,
-	const struct of_device_id *of_ids)
+static bool __acpi_match_device(struct acpi_device *device,
+				const struct acpi_device_id *acpi_ids,
+				const struct of_device_id *of_ids,
+				const struct acpi_device_id **acpi_id,
+				const struct of_device_id **of_id)
 {
 	const struct acpi_device_id *id;
 	struct acpi_hardware_id *hwid;
@@ -775,30 +781,32 @@
 	 * driver for it.
 	 */
 	if (!device || !device->status.present)
-		return NULL;
+		return false;
 
 	list_for_each_entry(hwid, &device->pnp.ids, list) {
 		/* First, check the ACPI/PNP IDs provided by the caller. */
-		for (id = ids; id->id[0] || id->cls; id++) {
-			if (id->id[0] && !strcmp((char *) id->id, hwid->id))
-				return id;
-			else if (id->cls && __acpi_match_device_cls(id, hwid))
-				return id;
+		if (acpi_ids) {
+			for (id = acpi_ids; id->id[0] || id->cls; id++) {
+				if (id->id[0] && !strcmp((char *)id->id, hwid->id))
+					goto out_acpi_match;
+				if (id->cls && __acpi_match_device_cls(id, hwid))
+					goto out_acpi_match;
+			}
 		}
 
 		/*
 		 * Next, check ACPI_DT_NAMESPACE_HID and try to match the
 		 * "compatible" property if found.
-		 *
-		 * The id returned by the below is not valid, but the only
-		 * caller passing non-NULL of_ids here is only interested in
-		 * whether or not the return value is NULL.
 		 */
-		if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id)
-		    && acpi_of_match_device(device, of_ids))
-			return id;
+		if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id))
+			return acpi_of_match_device(device, of_ids, of_id);
 	}
-	return NULL;
+	return false;
+
+out_acpi_match:
+	if (acpi_id)
+		*acpi_id = id;
+	return true;
 }
 
 /**
@@ -815,32 +823,29 @@
 const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 					       const struct device *dev)
 {
-	return __acpi_match_device(acpi_companion_match(dev), ids, NULL);
+	const struct acpi_device_id *id = NULL;
+
+	__acpi_match_device(acpi_companion_match(dev), ids, NULL, &id, NULL);
+	return id;
 }
 EXPORT_SYMBOL_GPL(acpi_match_device);
 
-void *acpi_get_match_data(const struct device *dev)
+const void *acpi_device_get_match_data(const struct device *dev)
 {
 	const struct acpi_device_id *match;
 
-	if (!dev->driver)
-		return NULL;
-
-	if (!dev->driver->acpi_match_table)
-		return NULL;
-
 	match = acpi_match_device(dev->driver->acpi_match_table, dev);
 	if (!match)
 		return NULL;
 
-	return (void *)match->driver_data;
+	return (const void *)match->driver_data;
 }
-EXPORT_SYMBOL_GPL(acpi_get_match_data);
+EXPORT_SYMBOL_GPL(acpi_device_get_match_data);
 
 int acpi_match_device_ids(struct acpi_device *device,
 			  const struct acpi_device_id *ids)
 {
-	return __acpi_match_device(device, ids, NULL) ? 0 : -ENOENT;
+	return __acpi_match_device(device, ids, NULL, NULL, NULL) ? 0 : -ENOENT;
 }
 EXPORT_SYMBOL(acpi_match_device_ids);
 
@@ -849,10 +854,12 @@
 {
 	if (!drv->acpi_match_table)
 		return acpi_of_match_device(ACPI_COMPANION(dev),
-					    drv->of_match_table);
+					    drv->of_match_table,
+					    NULL);
 
-	return !!__acpi_match_device(acpi_companion_match(dev),
-				     drv->acpi_match_table, drv->of_match_table);
+	return __acpi_match_device(acpi_companion_match(dev),
+				   drv->acpi_match_table, drv->of_match_table,
+				   NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(acpi_driver_match_device);
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index d9f38c6..30a5729 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1927,6 +1927,9 @@
 	    ec->reference_count >= 1)
 		acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_DISABLE);
 
+	if (acpi_sleep_no_ec_events())
+		acpi_ec_enter_noirq(ec);
+
 	return 0;
 }
 
@@ -1934,6 +1937,9 @@
 {
 	struct acpi_ec *ec = acpi_driver_data(to_acpi_device(dev));
 
+	if (acpi_sleep_no_ec_events())
+		acpi_ec_leave_noirq(ec);
+
 	if (ec_no_wakeup && test_bit(EC_FLAGS_STARTED, &ec->flags) &&
 	    ec->reference_count >= 1)
 		acpi_set_gpe(NULL, ec->gpe, ACPI_GPE_ENABLE);
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 466d150..5815356 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1271,11 +1271,11 @@
 	return 0;
 }
 
-static void *
+static const void *
 acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 				  const struct device *dev)
 {
-	return acpi_get_match_data(dev);
+	return acpi_device_get_match_data(dev);
 }
 
 #define DECLARE_ACPI_FWNODE_OPS(ops) \
diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
index 89e97d2..9d52743 100644
--- a/drivers/acpi/spcr.c
+++ b/drivers/acpi/spcr.c
@@ -115,6 +115,7 @@
 			table->serial_port.access_width))) {
 		default:
 			pr_err("Unexpected SPCR Access Width.  Defaulting to byte size\n");
+			/* fall through */
 		case 8:
 			iotype = "mmio";
 			break;
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 15e3d3c..764b63a 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1991,8 +1991,14 @@
 					&target_thread->reply_error.work);
 				wake_up_interruptible(&target_thread->wait);
 			} else {
-				WARN(1, "Unexpected reply error: %u\n",
-						target_thread->reply_error.cmd);
+				/*
+				 * Cannot get here for normal operation, but
+				 * we can if multiple synchronous transactions
+				 * are sent without blocking for responses.
+				 * Just ignore the 2nd error in this case.
+				 */
+				pr_warn("Unexpected reply error: %u\n",
+					target_thread->reply_error.cmd);
 			}
 			binder_inner_proc_unlock(target_thread->proc);
 			binder_thread_dec_tmpref(target_thread);
@@ -2193,7 +2199,7 @@
 	int debug_id = buffer->debug_id;
 
 	binder_debug(BINDER_DEBUG_TRANSACTION,
-		     "%d buffer release %d, size %zd-%zd, failed at %p\n",
+		     "%d buffer release %d, size %zd-%zd, failed at %pK\n",
 		     proc->pid, buffer->debug_id,
 		     buffer->data_size, buffer->offsets_size, failed_at);
 
@@ -3705,7 +3711,7 @@
 				}
 			}
 			binder_debug(BINDER_DEBUG_DEAD_BINDER,
-				     "%d:%d BC_DEAD_BINDER_DONE %016llx found %p\n",
+				     "%d:%d BC_DEAD_BINDER_DONE %016llx found %pK\n",
 				     proc->pid, thread->pid, (u64)cookie,
 				     death);
 			if (death == NULL) {
@@ -4376,6 +4382,15 @@
 
 	binder_inner_proc_unlock(thread->proc);
 
+	/*
+	 * This is needed to avoid races between wake_up_poll() above and
+	 * and ep_remove_waitqueue() called for other reasons (eg the epoll file
+	 * descriptor being closed); ep_remove_waitqueue() holds an RCU read
+	 * lock, so we can be sure it's done after calling synchronize_rcu().
+	 */
+	if (thread->looper & BINDER_LOOPER_STATE_POLL)
+		synchronize_rcu();
+
 	if (send_reply)
 		binder_send_failed_reply(send_reply, BR_DEAD_REPLY);
 	binder_release_work(proc, &thread->todo);
@@ -4391,6 +4406,8 @@
 	bool wait_for_proc_work;
 
 	thread = binder_get_thread(proc);
+	if (!thread)
+		return POLLERR;
 
 	binder_inner_proc_lock(thread->proc);
 	thread->looper |= BINDER_LOOPER_STATE_POLL;
@@ -5034,7 +5051,7 @@
 	spin_lock(&t->lock);
 	to_proc = t->to_proc;
 	seq_printf(m,
-		   "%s %d: %p from %d:%d to %d:%d code %x flags %x pri %ld r%d",
+		   "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %ld r%d",
 		   prefix, t->debug_id, t,
 		   t->from ? t->from->proc->pid : 0,
 		   t->from ? t->from->pid : 0,
@@ -5058,7 +5075,7 @@
 	}
 	if (buffer->target_node)
 		seq_printf(m, " node %d", buffer->target_node->debug_id);
-	seq_printf(m, " size %zd:%zd data %p\n",
+	seq_printf(m, " size %zd:%zd data %pK\n",
 		   buffer->data_size, buffer->offsets_size,
 		   buffer->data);
 }
diff --git a/drivers/base/core.c b/drivers/base/core.c
index b2261f9..5847364 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -310,6 +310,9 @@
 	dev_info(link->consumer, "Dropping the link to %s\n",
 		 dev_name(link->supplier));
 
+	if (link->flags & DL_FLAG_PM_RUNTIME)
+		pm_runtime_drop_link(link->consumer);
+
 	list_del(&link->s_node);
 	list_del(&link->c_node);
 	device_link_free(link);
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index a8ac86e..6637fc3 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -321,7 +321,8 @@
 		return;
 
 	if (device_may_wakeup(wirq->dev)) {
-		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED &&
+		    !pm_runtime_status_suspended(wirq->dev))
 			enable_irq(wirq->irq);
 
 		enable_irq_wake(wirq->irq);
@@ -343,7 +344,8 @@
 	if (device_may_wakeup(wirq->dev)) {
 		disable_irq_wake(wirq->irq);
 
-		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED &&
+		    !pm_runtime_status_suspended(wirq->dev))
 			disable_irq_nosync(wirq->irq);
 	}
 }
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 3022362..8f205f6 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -1410,9 +1410,8 @@
 }
 EXPORT_SYMBOL(fwnode_graph_parse_endpoint);
 
-void *device_get_match_data(struct device *dev)
+const void *device_get_match_data(struct device *dev)
 {
-	return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data,
-				  dev);
+	return fwnode_call_ptr_op(dev_fwnode(dev), device_get_match_data, dev);
 }
 EXPORT_SYMBOL_GPL(device_get_match_data);
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index e5aa62f..3aaf6af 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1758,7 +1758,7 @@
 	if (unit[drive].type->code == FD_NODRIVE)
 		return NULL;
 	*part = 0;
-	return get_disk(unit[drive].gendisk);
+	return get_disk_and_module(unit[drive].gendisk);
 }
 
 static int __init amiga_floppy_probe(struct platform_device *pdev)
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 8bc3b9f..dfb2c26 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1917,7 +1917,7 @@
 	if (drive >= FD_MAX_UNITS || type > NUM_DISK_MINORS)
 		return NULL;
 	*part = 0;
-	return get_disk(unit[drive].disk);
+	return get_disk_and_module(unit[drive].disk);
 }
 
 static int __init atari_floppy_init (void)
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 8028a3a..deea78e 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -456,7 +456,7 @@
 
 	mutex_lock(&brd_devices_mutex);
 	brd = brd_init_one(MINOR(dev) / max_part, &new);
-	kobj = brd ? get_disk(brd->brd_disk) : NULL;
+	kobj = brd ? get_disk_and_module(brd->brd_disk) : NULL;
 	mutex_unlock(&brd_devices_mutex);
 
 	if (new)
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index eae484a..8ec7235 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4505,7 +4505,7 @@
 	if (((*part >> 2) & 0x1f) >= ARRAY_SIZE(floppy_type))
 		return NULL;
 	*part = 0;
-	return get_disk(disks[drive]);
+	return get_disk_and_module(disks[drive]);
 }
 
 static int __init do_floppy_init(void)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d5fe720..87855b5 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1922,7 +1922,7 @@
 	if (err < 0)
 		kobj = NULL;
 	else
-		kobj = get_disk(lo->lo_disk);
+		kobj = get_disk_and_module(lo->lo_disk);
 	mutex_unlock(&loop_index_mutex);
 
 	*part = 0;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 5f2a424..86258b0 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1591,7 +1591,7 @@
 			if (new_index < 0) {
 				mutex_unlock(&nbd_index_mutex);
 				printk(KERN_ERR "nbd: failed to add new device\n");
-				return ret;
+				return new_index;
 			}
 			nbd = idr_find(&nbd_index_idr, new_index);
 		}
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 531a091..c61d20c 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -1122,7 +1122,7 @@
 	pkt->sector = new_sector;
 
 	bio_reset(pkt->bio);
-	bio_set_set(pkt->bio, pd->bdev);
+	bio_set_dev(pkt->bio, pd->bdev);
 	bio_set_op_attrs(pkt->bio, REQ_OP_WRITE, 0);
 	pkt->bio->bi_iter.bi_sector = new_sector;
 	pkt->bio->bi_iter.bi_size = pkt->frames * CD_FRAMESIZE;
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 84434d3..64e066e 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -799,7 +799,7 @@
 		return NULL;
 
 	*part = 0;
-	return get_disk(swd->unit[drive].disk);
+	return get_disk_and_module(swd->unit[drive].disk);
 }
 
 static int swim_add_floppy(struct swim_priv *swd, enum drive_location location)
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index 41c95c9..8f9130a 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -332,7 +332,7 @@
 static struct kobject *z2_find(dev_t dev, int *part, void *data)
 {
 	*part = 0;
-	return get_disk(z2ram_gendisk);
+	return get_disk_and_module(z2ram_gendisk);
 }
 
 static struct request_queue *z2_queue;
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 2a55380..60bf04b 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -21,6 +21,7 @@
  *
  */
 
+#include <linux/dmi.h>
 #include <linux/module.h>
 #include <linux/usb.h>
 #include <linux/usb/quirks.h>
@@ -379,6 +380,21 @@
 	{ }	/* Terminating entry */
 };
 
+/* The Bluetooth USB module build into some devices needs to be reset on resume,
+ * this is a problem with the platform (likely shutting off all power) not with
+ * the module itself. So we use a DMI list to match known broken platforms.
+ */
+static const struct dmi_system_id btusb_needs_reset_resume_table[] = {
+	{
+		/* Lenovo Yoga 920 (QCA Rome device 0cf3:e300) */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo YOGA 920"),
+		},
+	},
+	{}
+};
+
 #define BTUSB_MAX_ISOC_FRAMES	10
 
 #define BTUSB_INTR_RUNNING	0
@@ -2945,6 +2961,9 @@
 	hdev->send   = btusb_send_frame;
 	hdev->notify = btusb_notify;
 
+	if (dmi_check_system(btusb_needs_reset_resume_table))
+		interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
+
 #ifdef CONFIG_PM
 	err = btusb_config_oob_wake(hdev);
 	if (err)
@@ -3031,12 +3050,6 @@
 	if (id->driver_info & BTUSB_QCA_ROME) {
 		data->setup_on_usb = btusb_setup_qca;
 		hdev->set_bdaddr = btusb_set_bdaddr_ath3012;
-
-		/* QCA Rome devices lose their updated firmware over suspend,
-		 * but the USB hub doesn't notice any status change.
-		 * explicitly request a device reset on resume.
-		 */
-		interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME;
 	}
 
 #ifdef CONFIG_BT_HCIBTUSB_RTL
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 0438a64..6314dfb 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -922,12 +922,13 @@
 
 	dev->clk = devm_clk_get(dev->dev, NULL);
 
-	dev->device_wakeup = devm_gpiod_get(dev->dev, "device-wakeup",
-					    GPIOD_OUT_LOW);
+	dev->device_wakeup = devm_gpiod_get_optional(dev->dev, "device-wakeup",
+						     GPIOD_OUT_LOW);
 	if (IS_ERR(dev->device_wakeup))
 		return PTR_ERR(dev->device_wakeup);
 
-	dev->shutdown = devm_gpiod_get(dev->dev, "shutdown", GPIOD_OUT_LOW);
+	dev->shutdown = devm_gpiod_get_optional(dev->dev, "shutdown",
+						GPIOD_OUT_LOW);
 	if (IS_ERR(dev->shutdown))
 		return PTR_ERR(dev->shutdown);
 
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 4d46003..cdaeeea 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -630,7 +630,7 @@
 	for (i = 0; i < ARRAY_SIZE(sysc_dts_quirks); i++) {
 		prop = of_get_property(np, sysc_dts_quirks[i].name, &len);
 		if (!prop)
-			break;
+			continue;
 
 		ddata->cfg.quirks |= sysc_dts_quirks[i].mask;
 	}
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index d1f5bb5..6e9df55 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -162,7 +162,7 @@
 	/* Enable secondary noise source on CPUs where it is present. */
 
 	/* Nehemiah stepping 8 and higher */
-	if ((c->x86_model == 9) && (c->x86_mask > 7))
+	if ((c->x86_model == 9) && (c->x86_stepping > 7))
 		lo |= VIA_NOISESRC2;
 
 	/* Esther */
diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c
index 4d1dc8b..f95b9c7 100644
--- a/drivers/char/tpm/st33zp24/st33zp24.c
+++ b/drivers/char/tpm/st33zp24/st33zp24.c
@@ -457,7 +457,7 @@
 			    size_t count)
 {
 	int size = 0;
-	int expected;
+	u32 expected;
 
 	if (!chip)
 		return -EBUSY;
@@ -474,7 +474,7 @@
 	}
 
 	expected = be32_to_cpu(*(__be32 *)(buf + 2));
-	if (expected > count) {
+	if (expected > count || expected < TPM_HEADER_SIZE) {
 		size = -EIO;
 		goto out;
 	}
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 76df4fb..9e80a95 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -1190,6 +1190,10 @@
 			break;
 
 		recd = be32_to_cpu(tpm_cmd.params.getrandom_out.rng_data_len);
+		if (recd > num_bytes) {
+			total = -EFAULT;
+			break;
+		}
 
 		rlength = be32_to_cpu(tpm_cmd.header.out.length);
 		if (rlength < offsetof(struct tpm_getrandom_out, rng_data) +
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index c17e753..a700f8f 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -683,6 +683,10 @@
 	if (!rc) {
 		data_len = be16_to_cpup(
 			(__be16 *) &buf.data[TPM_HEADER_SIZE + 4]);
+		if (data_len < MIN_KEY_SIZE ||  data_len > MAX_KEY_SIZE + 1) {
+			rc = -EFAULT;
+			goto out;
+		}
 
 		rlength = be32_to_cpu(((struct tpm2_cmd *)&buf)
 					->header.out.length);
diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c
index c1dd39e..6116cd0 100644
--- a/drivers/char/tpm/tpm_i2c_infineon.c
+++ b/drivers/char/tpm/tpm_i2c_infineon.c
@@ -473,7 +473,8 @@
 static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 {
 	int size = 0;
-	int expected, status;
+	int status;
+	u32 expected;
 
 	if (count < TPM_HEADER_SIZE) {
 		size = -EIO;
@@ -488,7 +489,7 @@
 	}
 
 	expected = be32_to_cpu(*(__be32 *)(buf + 2));
-	if ((size_t) expected > count) {
+	if (((size_t) expected > count) || (expected < TPM_HEADER_SIZE)) {
 		size = -EIO;
 		goto out;
 	}
diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c
index c642877..caa86b1 100644
--- a/drivers/char/tpm/tpm_i2c_nuvoton.c
+++ b/drivers/char/tpm/tpm_i2c_nuvoton.c
@@ -281,7 +281,11 @@
 	struct device *dev = chip->dev.parent;
 	struct i2c_client *client = to_i2c_client(dev);
 	s32 rc;
-	int expected, status, burst_count, retries, size = 0;
+	int status;
+	int burst_count;
+	int retries;
+	int size = 0;
+	u32 expected;
 
 	if (count < TPM_HEADER_SIZE) {
 		i2c_nuvoton_ready(chip);    /* return to idle */
@@ -323,7 +327,7 @@
 		 * to machine native
 		 */
 		expected = be32_to_cpu(*(__be32 *) (buf + 2));
-		if (expected > count) {
+		if (expected > count || expected < size) {
 			dev_err(dev, "%s() expected > count\n", __func__);
 			size = -EIO;
 			continue;
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 183a5f5..da074e3 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -270,7 +270,8 @@
 {
 	struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
 	int size = 0;
-	int expected, status;
+	int status;
+	u32 expected;
 
 	if (count < TPM_HEADER_SIZE) {
 		size = -EIO;
@@ -285,7 +286,7 @@
 	}
 
 	expected = be32_to_cpu(*(__be32 *) (buf + 2));
-	if (expected > count) {
+	if (expected > count || expected < TPM_HEADER_SIZE) {
 		size = -EIO;
 		goto out;
 	}
diff --git a/drivers/clocksource/arc_timer.c b/drivers/clocksource/arc_timer.c
index 4927355..471b428 100644
--- a/drivers/clocksource/arc_timer.c
+++ b/drivers/clocksource/arc_timer.c
@@ -251,9 +251,14 @@
 	int irq_reenable = clockevent_state_periodic(evt);
 
 	/*
-	 * Any write to CTRL reg ACks the interrupt, we rewrite the
-	 * Count when [N]ot [H]alted bit.
-	 * And re-arm it if perioid by [I]nterrupt [E]nable bit
+	 * 1. ACK the interrupt
+	 *    - For ARC700, any write to CTRL reg ACKs it, so just rewrite
+	 *      Count when [N]ot [H]alted bit.
+	 *    - For HS3x, it is a bit subtle. On taken count-down interrupt,
+	 *      IP bit [3] is set, which needs to be cleared for ACK'ing.
+	 *      The write below can only update the other two bits, hence
+	 *      explicitly clears IP bit
+	 * 2. Re-arm interrupt if periodic by writing to IE bit [0]
 	 */
 	write_aux_reg(ARC_REG_TIMER0_CTRL, irq_reenable | TIMER_CTRL_NH);
 
diff --git a/drivers/clocksource/fsl_ftm_timer.c b/drivers/clocksource/fsl_ftm_timer.c
index 3ee7e6f..846d18d 100644
--- a/drivers/clocksource/fsl_ftm_timer.c
+++ b/drivers/clocksource/fsl_ftm_timer.c
@@ -281,7 +281,7 @@
 
 static unsigned long __init ftm_clk_init(struct device_node *np)
 {
-	unsigned long freq;
+	long freq;
 
 	freq = __ftm_clk_init(np, "ftm-evt-counter-en", "ftm-evt");
 	if (freq <= 0)
diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c
index a04808a..986b679 100644
--- a/drivers/clocksource/mips-gic-timer.c
+++ b/drivers/clocksource/mips-gic-timer.c
@@ -166,7 +166,7 @@
 
 	/* Set clocksource mask. */
 	count_width = read_gic_config() & GIC_CONFIG_COUNTBITS;
-	count_width >>= __fls(GIC_CONFIG_COUNTBITS);
+	count_width >>= __ffs(GIC_CONFIG_COUNTBITS);
 	count_width *= 4;
 	count_width += 32;
 	gic_clocksource.mask = CLOCKSOURCE_MASK(count_width);
@@ -205,12 +205,12 @@
 	} else if (of_property_read_u32(node, "clock-frequency",
 					&gic_frequency)) {
 		pr_err("GIC frequency not specified.\n");
-		return -EINVAL;;
+		return -EINVAL;
 	}
 	gic_timer_irq = irq_of_parse_and_map(node, 0);
 	if (!gic_timer_irq) {
 		pr_err("GIC timer IRQ not specified.\n");
-		return -EINVAL;;
+		return -EINVAL;
 	}
 
 	ret = __gic_clocksource_init();
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index 2a3fe83..3b56ea3 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -334,7 +334,7 @@
 	timer_base = of_io_request_and_map(node, 0, of_node_full_name(node));
 	if (IS_ERR(timer_base)) {
 		pr_err("Can't map registers\n");
-		return PTR_ERR(timer_base);;
+		return PTR_ERR(timer_base);
 	}
 
 	irq = irq_of_parse_and_map(node, 0);
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 3a88e33..fb586e0 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -44,10 +44,10 @@
 
 config ARM_SCPI_CPUFREQ
 	tristate "SCPI based CPUfreq driver"
-	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
+	depends on ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
 	help
-	  This adds the CPUfreq driver support for ARM big.LITTLE platforms
-	  using SCPI protocol for CPU power management.
+	  This adds the CPUfreq driver support for ARM platforms using SCPI
+	  protocol for CPU power management.
 
 	  This driver uses SCPI Message Protocol driver to interact with the
 	  firmware providing the CPU DVFS functionality.
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 3a2ca0f..d0c34df 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -629,7 +629,7 @@
 	if (c->x86_vendor == X86_VENDOR_INTEL) {
 		if ((c->x86 == 15) &&
 		    (c->x86_model == 6) &&
-		    (c->x86_mask == 8)) {
+		    (c->x86_stepping == 8)) {
 			pr_info("Intel(R) Xeon(R) 7100 Errata AL30, processors may lock up on frequency changes: disabling acpi-cpufreq\n");
 			return -ENODEV;
 		    }
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 942632a..f730b65 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -775,7 +775,7 @@
 		break;
 
 	case 7:
-		switch (c->x86_mask) {
+		switch (c->x86_stepping) {
 		case 0:
 			longhaul_version = TYPE_LONGHAUL_V1;
 			cpu_model = CPU_SAMUEL2;
@@ -787,7 +787,7 @@
 			break;
 		case 1 ... 15:
 			longhaul_version = TYPE_LONGHAUL_V2;
-			if (c->x86_mask < 8) {
+			if (c->x86_stepping < 8) {
 				cpu_model = CPU_SAMUEL2;
 				cpuname = "C3 'Samuel 2' [C5B]";
 			} else {
@@ -814,7 +814,7 @@
 		numscales = 32;
 		memcpy(mults, nehemiah_mults, sizeof(nehemiah_mults));
 		memcpy(eblcr, nehemiah_eblcr, sizeof(nehemiah_eblcr));
-		switch (c->x86_mask) {
+		switch (c->x86_stepping) {
 		case 0 ... 1:
 			cpu_model = CPU_NEHEMIAH;
 			cpuname = "C3 'Nehemiah A' [C5XLOE]";
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index fd77812..a25741b 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -168,7 +168,7 @@
 #endif
 
 	/* Errata workaround */
-	cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_mask;
+	cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_stepping;
 	switch (cpuid) {
 	case 0x0f07:
 	case 0x0f0a:
diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index 80ac313..302e9ce 100644
--- a/drivers/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -131,7 +131,7 @@
 		return 0;
 	}
 
-	if ((c->x86_model == 6) && (c->x86_mask == 0)) {
+	if ((c->x86_model == 6) && (c->x86_stepping == 0)) {
 		pr_info("K7 660[A0] core detected, enabling errata workarounds\n");
 		have_a0 = 1;
 	}
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index 7b596fa..6bebc1f 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -351,7 +351,13 @@
 static int s3c_cpufreq_init(struct cpufreq_policy *policy)
 {
 	policy->clk = clk_arm;
-	return cpufreq_generic_init(policy, ftab, cpu_cur.info->latency);
+
+	policy->cpuinfo.transition_latency = cpu_cur.info->latency;
+
+	if (ftab)
+		return cpufreq_table_validate_and_show(policy, ftab);
+
+	return 0;
 }
 
 static int __init s3c_cpufreq_initclks(void)
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index c32a833..d300a16 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -51,15 +51,23 @@
 static int
 scpi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
+	unsigned long freq = policy->freq_table[index].frequency;
 	struct scpi_data *priv = policy->driver_data;
-	u64 rate = policy->freq_table[index].frequency * 1000;
+	u64 rate = freq * 1000;
 	int ret;
 
 	ret = clk_set_rate(priv->clk, rate);
-	if (!ret && (clk_get_rate(priv->clk) != rate))
-		ret = -EIO;
 
-	return ret;
+	if (ret)
+		return ret;
+
+	if (clk_get_rate(priv->clk) != rate)
+		return -EIO;
+
+	arch_set_freq_scale(policy->related_cpus, freq,
+			    policy->cpuinfo.max_freq);
+
+	return 0;
 }
 
 static int
diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c
index 41bc539..4fa5adf 100644
--- a/drivers/cpufreq/speedstep-centrino.c
+++ b/drivers/cpufreq/speedstep-centrino.c
@@ -37,7 +37,7 @@
 {
 	__u8	x86;            /* CPU family */
 	__u8	x86_model;	/* model */
-	__u8	x86_mask;	/* stepping */
+	__u8	x86_stepping;	/* stepping */
 };
 
 enum {
@@ -277,7 +277,7 @@
 {
 	if ((c->x86 == x->x86) &&
 	    (c->x86_model == x->x86_model) &&
-	    (c->x86_mask == x->x86_mask))
+	    (c->x86_stepping == x->x86_stepping))
 		return 1;
 	return 0;
 }
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index 8085ec9..e3a9962 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -272,9 +272,9 @@
 		ebx = cpuid_ebx(0x00000001);
 		ebx &= 0x000000FF;
 
-		pr_debug("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask);
+		pr_debug("ebx value is %x, x86_stepping is %x\n", ebx, c->x86_stepping);
 
-		switch (c->x86_mask) {
+		switch (c->x86_stepping) {
 		case 4:
 			/*
 			 * B-stepping [M-P4-M]
@@ -361,7 +361,7 @@
 				msr_lo, msr_hi);
 		if ((msr_hi & (1<<18)) &&
 		    (relaxed_check ? 1 : (msr_hi & (3<<24)))) {
-			if (c->x86_mask == 0x01) {
+			if (c->x86_stepping == 0x01) {
 				pr_debug("early PIII version\n");
 				return SPEEDSTEP_CPU_PIII_C_EARLY;
 			} else
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 75d280c..e843cf4 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -228,12 +228,16 @@
 		 * without any error (HW optimizations for later
 		 * CAAM eras), then try again.
 		 */
-		rdsta_val = rd_reg32(&ctrl->r4tst[0].rdsta) & RDSTA_IFMASK;
-		if ((status && status != JRSTA_SSRC_JUMP_HALT_CC) ||
-		    !(rdsta_val & (1 << sh_idx)))
-			ret = -EAGAIN;
 		if (ret)
 			break;
+
+		rdsta_val = rd_reg32(&ctrl->r4tst[0].rdsta) & RDSTA_IFMASK;
+		if ((status && status != JRSTA_SSRC_JUMP_HALT_CC) ||
+		    !(rdsta_val & (1 << sh_idx))) {
+			ret = -EAGAIN;
+			break;
+		}
+
 		dev_info(ctrldev, "Instantiated RNG4 SH%d\n", sh_idx);
 		/* Clear the contents before recreating the descriptor */
 		memset(desc, 0x00, CAAM_CMD_SZ * 7);
diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index fcfa5b1..b3afb6c 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -211,7 +211,7 @@
 {
 	int ret;
 
-	ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, 0, error);
+	ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error);
 	if (ret)
 		return ret;
 
@@ -271,7 +271,7 @@
 			return rc;
 	}
 
-	return __sev_do_cmd_locked(SEV_CMD_FACTORY_RESET, 0, &argp->error);
+	return __sev_do_cmd_locked(SEV_CMD_FACTORY_RESET, NULL, &argp->error);
 }
 
 static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp)
@@ -299,7 +299,7 @@
 			return rc;
 	}
 
-	return __sev_do_cmd_locked(cmd, 0, &argp->error);
+	return __sev_do_cmd_locked(cmd, NULL, &argp->error);
 }
 
 static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp)
@@ -624,7 +624,7 @@
 
 int sev_guest_df_flush(int *error)
 {
-	return sev_do_cmd(SEV_CMD_DF_FLUSH, 0, error);
+	return sev_do_cmd(SEV_CMD_DF_FLUSH, NULL, error);
 }
 EXPORT_SYMBOL_GPL(sev_guest_df_flush);
 
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 4b6642a..1c6cbda 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -512,7 +512,7 @@
 
 	printk(KERN_NOTICE PFX "Using VIA PadLock ACE for AES algorithm.\n");
 
-	if (c->x86 == 6 && c->x86_model == 15 && c->x86_mask == 2) {
+	if (c->x86 == 6 && c->x86_model == 15 && c->x86_stepping == 2) {
 		ecb_fetch_blocks = MAX_ECB_FETCH_BLOCKS;
 		cbc_fetch_blocks = MAX_CBC_FETCH_BLOCKS;
 		printk(KERN_NOTICE PFX "VIA Nano stepping 2 detected: enabling workaround.\n");
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 188f44b..5d64c08 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -1922,15 +1922,21 @@
 	uint32_t aes_control;
 	unsigned long flags;
 	int err;
+	u8 *iv;
 
 	aes_control = SSS_AES_KEY_CHANGE_MODE;
 	if (mode & FLAGS_AES_DECRYPT)
 		aes_control |= SSS_AES_MODE_DECRYPT;
 
-	if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CBC)
+	if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CBC) {
 		aes_control |= SSS_AES_CHAIN_MODE_CBC;
-	else if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CTR)
+		iv = req->info;
+	} else if ((mode & FLAGS_AES_MODE_MASK) == FLAGS_AES_CTR) {
 		aes_control |= SSS_AES_CHAIN_MODE_CTR;
+		iv = req->info;
+	} else {
+		iv = NULL; /* AES_ECB */
+	}
 
 	if (dev->ctx->keylen == AES_KEYSIZE_192)
 		aes_control |= SSS_AES_KEY_SIZE_192;
@@ -1961,7 +1967,7 @@
 		goto outdata_error;
 
 	SSS_AES_WRITE(dev, AES_CONTROL, aes_control);
-	s5p_set_aes(dev, dev->ctx->aes_key, req->info, dev->ctx->keylen);
+	s5p_set_aes(dev, dev->ctx->aes_key, iv, dev->ctx->keylen);
 
 	s5p_set_dma_indata(dev,  dev->sg_src);
 	s5p_set_dma_outdata(dev, dev->sg_dst);
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c b/drivers/crypto/sunxi-ss/sun4i-ss-prng.c
index 0d01d16..63d6364 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-prng.c
@@ -28,7 +28,7 @@
 	algt = container_of(alg, struct sun4i_ss_alg_template, alg.rng);
 	ss = algt->ss;
 
-	spin_lock(&ss->slock);
+	spin_lock_bh(&ss->slock);
 
 	writel(mode, ss->base + SS_CTL);
 
@@ -51,6 +51,6 @@
 	}
 
 	writel(0, ss->base + SS_CTL);
-	spin_unlock(&ss->slock);
-	return dlen;
+	spin_unlock_bh(&ss->slock);
+	return 0;
 }
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 9c80e0c..6882fa2 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -1138,6 +1138,10 @@
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	bool is_sec1 = has_ftr_sec1(priv);
 
+	if (!src) {
+		to_talitos_ptr(ptr, 0, 0, is_sec1);
+		return 1;
+	}
 	if (sg_count == 1) {
 		to_talitos_ptr(ptr, sg_dma_address(src) + offset, len, is_sec1);
 		return sg_count;
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 473af69..ecdc292 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -246,12 +246,6 @@
 {
 	long avail;
 
-	/*
-	 * The device driver is allowed to sleep, in order to make the
-	 * memory directly accessible.
-	 */
-	might_sleep();
-
 	if (!dax_dev)
 		return -EOPNOTSUPP;
 
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 8b16ec5..329cb96 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -3147,7 +3147,7 @@
 	struct amd64_family_type *fam_type = NULL;
 
 	pvt->ext_model  = boot_cpu_data.x86_model >> 4;
-	pvt->stepping	= boot_cpu_data.x86_mask;
+	pvt->stepping	= boot_cpu_data.x86_stepping;
 	pvt->model	= boot_cpu_data.x86_model;
 	pvt->fam	= boot_cpu_data.x86;
 
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index f34430f..8721002 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -279,7 +279,7 @@
  * sbridge structs
  */
 
-#define NUM_CHANNELS		4	/* Max channels per MC */
+#define NUM_CHANNELS		6	/* Max channels per MC */
 #define MAX_DIMMS		3	/* Max DIMMS per channel */
 #define KNL_MAX_CHAS		38	/* KNL max num. of Cache Home Agents */
 #define KNL_MAX_CHANNELS	6	/* KNL max num. of PCI channels */
diff --git a/drivers/extcon/extcon-axp288.c b/drivers/extcon/extcon-axp288.c
index 0a44d43..3ec4c71 100644
--- a/drivers/extcon/extcon-axp288.c
+++ b/drivers/extcon/extcon-axp288.c
@@ -1,7 +1,6 @@
 /*
  * extcon-axp288.c - X-Power AXP288 PMIC extcon cable detection driver
  *
- * Copyright (C) 2016-2017 Hans de Goede <hdegoede@redhat.com>
  * Copyright (C) 2015 Intel Corporation
  * Author: Ramakrishna Pallala <ramakrishna.pallala@intel.com>
  *
@@ -98,15 +97,13 @@
 	struct device *dev;
 	struct regmap *regmap;
 	struct regmap_irq_chip_data *regmap_irqc;
-	struct delayed_work det_work;
 	int irq[EXTCON_IRQ_END];
 	struct extcon_dev *edev;
 	unsigned int previous_cable;
-	bool first_detect_done;
 };
 
 /* Power up/down reason string array */
-static char *axp288_pwr_up_down_info[] = {
+static const char * const axp288_pwr_up_down_info[] = {
 	"Last wake caused by user pressing the power button",
 	"Last wake caused by a charger insertion",
 	"Last wake caused by a battery insertion",
@@ -124,7 +121,7 @@
  */
 static void axp288_extcon_log_rsi(struct axp288_extcon_info *info)
 {
-	char **rsi;
+	const char * const *rsi;
 	unsigned int val, i, clear_mask = 0;
 	int ret;
 
@@ -140,25 +137,6 @@
 	regmap_write(info->regmap, AXP288_PS_BOOT_REASON_REG, clear_mask);
 }
 
-static void axp288_chrg_detect_complete(struct axp288_extcon_info *info)
-{
-	/*
-	 * We depend on other drivers to do things like mux the data lines,
-	 * enable/disable vbus based on the id-pin, etc. Sometimes the BIOS has
-	 * not set these things up correctly resulting in the initial charger
-	 * cable type detection giving a wrong result and we end up not charging
-	 * or charging at only 0.5A.
-	 *
-	 * So we schedule a second cable type detection after 2 seconds to
-	 * give the other drivers time to load and do their thing.
-	 */
-	if (!info->first_detect_done) {
-		queue_delayed_work(system_wq, &info->det_work,
-				   msecs_to_jiffies(2000));
-		info->first_detect_done = true;
-	}
-}
-
 static int axp288_handle_chrg_det_event(struct axp288_extcon_info *info)
 {
 	int ret, stat, cfg, pwr_stat;
@@ -223,8 +201,6 @@
 		info->previous_cable = cable;
 	}
 
-	axp288_chrg_detect_complete(info);
-
 	return 0;
 
 dev_det_ret:
@@ -246,11 +222,8 @@
 	return IRQ_HANDLED;
 }
 
-static void axp288_extcon_det_work(struct work_struct *work)
+static void axp288_extcon_enable(struct axp288_extcon_info *info)
 {
-	struct axp288_extcon_info *info =
-		container_of(work, struct axp288_extcon_info, det_work.work);
-
 	regmap_update_bits(info->regmap, AXP288_BC_GLOBAL_REG,
 						BC_GLOBAL_RUN, 0);
 	/* Enable the charger detection logic */
@@ -272,7 +245,6 @@
 	info->regmap = axp20x->regmap;
 	info->regmap_irqc = axp20x->regmap_irqc;
 	info->previous_cable = EXTCON_NONE;
-	INIT_DELAYED_WORK(&info->det_work, axp288_extcon_det_work);
 
 	platform_set_drvdata(pdev, info);
 
@@ -318,7 +290,7 @@
 	}
 
 	/* Start charger cable type detection */
-	queue_delayed_work(system_wq, &info->det_work, 0);
+	axp288_extcon_enable(info);
 
 	return 0;
 }
diff --git a/drivers/extcon/extcon-intel-int3496.c b/drivers/extcon/extcon-intel-int3496.c
index c8691b5..191e99f 100644
--- a/drivers/extcon/extcon-intel-int3496.c
+++ b/drivers/extcon/extcon-intel-int3496.c
@@ -153,8 +153,9 @@
 		return ret;
 	}
 
-	/* queue initial processing of id-pin */
+	/* process id-pin so that we start with the right status */
 	queue_delayed_work(system_wq, &data->work, 0);
+	flush_delayed_work(&data->work);
 
 	platform_set_drvdata(pdev, data);
 
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 564bb7a..84e5a9d 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -241,6 +241,19 @@
 
 		desc = of_get_named_gpiod_flags(dev->of_node, prop_name, idx,
 						&of_flags);
+		/*
+		 * -EPROBE_DEFER in our case means that we found a
+		 * valid GPIO property, but no controller has been
+		 * registered so far.
+		 *
+		 * This means we don't need to look any further for
+		 * alternate name conventions, and we should really
+		 * preserve the return code for our user to be able to
+		 * retry probing later.
+		 */
+		if (IS_ERR(desc) && PTR_ERR(desc) == -EPROBE_DEFER)
+			return desc;
+
 		if (!IS_ERR(desc) || (PTR_ERR(desc) != -ENOENT))
 			break;
 	}
@@ -250,7 +263,7 @@
 		desc = of_find_spi_gpio(dev, con_id, &of_flags);
 
 	/* Special handling for regulator GPIOs if used */
-	if (IS_ERR(desc))
+	if (IS_ERR(desc) && PTR_ERR(desc) != -EPROBE_DEFER)
 		desc = of_find_regulator_gpio(dev, con_id, &of_flags);
 
 	if (IS_ERR(desc))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d5a2eef..74edba1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1156,7 +1156,7 @@
 /*
  * Writeback
  */
-#define AMDGPU_MAX_WB 512	/* Reserve at most 512 WB slots for amdgpu-owned rings. */
+#define AMDGPU_MAX_WB 128	/* Reserve at most 128 WB slots for amdgpu-owned rings. */
 
 struct amdgpu_wb {
 	struct amdgpu_bo	*wb_obj;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index e2c3c5e..c53095b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -568,6 +568,7 @@
 	/* HG _PR3 doesn't seem to work on this A+A weston board */
 	{ 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX },
+	{ 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0, 0, 0, 0, 0 },
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 8ca3783..74d2efa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -736,9 +736,11 @@
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (encoder) {
 		struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
@@ -757,8 +759,12 @@
 	/* check acpi lid status ??? */
 
 	amdgpu_connector_update_scratch_regs(connector, ret);
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
+
 	return ret;
 }
 
@@ -868,9 +874,11 @@
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	encoder = amdgpu_connector_best_single_encoder(connector);
 	if (!encoder)
@@ -924,8 +932,10 @@
 	amdgpu_connector_update_scratch_regs(connector, ret);
 
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }
@@ -988,9 +998,11 @@
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;
@@ -1115,8 +1127,10 @@
 	amdgpu_connector_update_scratch_regs(connector, ret);
 
 exit:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }
@@ -1359,9 +1373,11 @@
 	struct drm_encoder *encoder = amdgpu_connector_best_single_encoder(connector);
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;
@@ -1429,8 +1445,10 @@
 
 	amdgpu_connector_update_scratch_regs(connector, ret);
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 00a50cc..af1b879 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -492,7 +492,7 @@
 		memset(&adev->wb.used, 0, sizeof(adev->wb.used));
 
 		/* clear wb memory */
-		memset((char *)adev->wb.wb, 0, AMDGPU_MAX_WB * sizeof(uint32_t));
+		memset((char *)adev->wb.wb, 0, AMDGPU_MAX_WB * sizeof(uint32_t) * 8);
 	}
 
 	return 0;
@@ -530,8 +530,9 @@
  */
 void amdgpu_device_wb_free(struct amdgpu_device *adev, u32 wb)
 {
+	wb >>= 3;
 	if (wb < adev->wb.num_wb)
-		__clear_bit(wb >> 3, adev->wb.used);
+		__clear_bit(wb, adev->wb.used);
 }
 
 /**
@@ -1455,11 +1456,6 @@
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.hw)
 			continue;
-		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
-			amdgpu_free_static_csa(adev);
-			amdgpu_device_wb_fini(adev);
-			amdgpu_device_vram_scratch_fini(adev);
-		}
 
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 			adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE) {
@@ -1486,6 +1482,13 @@
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.sw)
 			continue;
+
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
+			amdgpu_free_static_csa(adev);
+			amdgpu_device_wb_fini(adev);
+			amdgpu_device_vram_scratch_fini(adev);
+		}
+
 		r = adev->ip_blocks[i].version->funcs->sw_fini((void *)adev);
 		/* XXX handle errors */
 		if (r) {
@@ -2284,14 +2287,6 @@
 				drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 			}
 			drm_modeset_unlock_all(dev);
-		} else {
-			/*
-			 * There is no equivalent atomic helper to turn on
-			 * display, so we defined our own function for this,
-			 * once suspend resume is supported by the atomic
-			 * framework this will be reworked
-			 */
-			amdgpu_dm_display_resume(adev);
 		}
 	}
 
@@ -2726,7 +2721,6 @@
 	if (amdgpu_device_has_dc_support(adev)) {
 		if (drm_atomic_helper_resume(adev->ddev, state))
 			dev_info(adev->dev, "drm resume failed:%d\n", r);
-		amdgpu_dm_display_resume(adev);
 	} else {
 		drm_helper_resume_force_mode(adev->ddev);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index e14ab34..7c2be32 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -75,7 +75,7 @@
 static int amdgpu_gtt_mgr_fini(struct ttm_mem_type_manager *man)
 {
 	struct amdgpu_gtt_mgr *mgr = man->priv;
-
+	spin_lock(&mgr->lock);
 	drm_mm_takedown(&mgr->mm);
 	spin_unlock(&mgr->lock);
 	kfree(mgr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 56bcd59..36483e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -257,7 +257,8 @@
 	r = drm_irq_install(adev->ddev, adev->ddev->pdev->irq);
 	if (r) {
 		adev->irq.installed = false;
-		flush_work(&adev->hotplug_work);
+		if (!amdgpu_device_has_dc_support(adev))
+			flush_work(&adev->hotplug_work);
 		cancel_work_sync(&adev->reset_work);
 		return r;
 	}
@@ -282,7 +283,8 @@
 		adev->irq.installed = false;
 		if (adev->irq.msi_enabled)
 			pci_disable_msi(adev->pdev);
-		flush_work(&adev->hotplug_work);
+		if (!amdgpu_device_has_dc_support(adev))
+			flush_work(&adev->hotplug_work);
 		cancel_work_sync(&adev->reset_work);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 2719937..3b7e7af 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -634,7 +634,7 @@
 	for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i)
 		BUG_ON(vm_inv_eng[i] > 16);
 
-	if (adev->asic_type == CHIP_VEGA10) {
+	if (adev->asic_type == CHIP_VEGA10 && !amdgpu_sriov_vf(adev)) {
 		r = gmc_v9_0_ecc_available(adev);
 		if (r == 1) {
 			DRM_INFO("ECC is active.\n");
@@ -682,7 +682,10 @@
 	adev->mc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
 	if (!adev->mc.vram_width) {
 		/* hbm memory channel size */
-		chansize = 128;
+		if (adev->flags & AMD_IS_APU)
+			chansize = 64;
+		else
+			chansize = 128;
 
 		tmp = RREG32_SOC15(DF, 0, mmDF_CS_AON0_DramBaseAddress0);
 		tmp &= DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index e92fb37..91cf95a 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -238,31 +238,27 @@
 static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u64 *wptr = NULL;
-	uint64_t local_wptr = 0;
+	u64 wptr;
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = ((u64 *)&adev->wb.wb[ring->wptr_offs]);
-		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", *wptr);
-		*wptr = (*wptr) >> 2;
-		DRM_DEBUG("wptr/doorbell after shift == 0x%016llx\n", *wptr);
+		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
+		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
 		u32 lowbit, highbit;
 		int me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-		wptr = &local_wptr;
 		lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR)) >> 2;
 		highbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
 
 		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
 				me, highbit, lowbit);
-		*wptr = highbit;
-		*wptr = (*wptr) << 32;
-		*wptr |= lowbit;
+		wptr = highbit;
+		wptr = wptr << 32;
+		wptr |= lowbit;
 	}
 
-	return *wptr;
+	return wptr >> 2;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index b2bfeda..9bab484 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -1618,7 +1618,7 @@
 	.set_wptr = uvd_v6_0_enc_ring_set_wptr,
 	.emit_frame_size =
 		4 + /* uvd_v6_0_enc_ring_emit_pipeline_sync */
<