Linux 5.9

Merge misc fixes from Andrew Morton:
 "Five fixes.

  Subsystems affected by this patch series: MAINTAINERS, mm/pagemap,
  mm/swap, and mm/hugetlb"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: khugepaged: recalculate min_free_kbytes after memory hotplug as expected by khugepaged
  mm: validate inode in mapping_set_error()
  mm: mmap: Fix general protection fault in unlink_file_vma()
  MAINTAINERS: Antoine Tenart's email address
  MAINTAINERS: change hardening mailing list

.mailmap

@@ -41,7 +41,8 @@ Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
 Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andy Adamson <andros@citi.umich.edu>
-Antoine Tenart <antoine.tenart@free-electrons.com>
+Antoine Tenart <atenart@kernel.org> <antoine.tenart@bootlin.com>
+Antoine Tenart <atenart@kernel.org> <antoine.tenart@free-electrons.com>
 Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com>
 Archit Taneja <archit@ti.com>
 Ard Biesheuvel <ardb@kernel.org> <ard.biesheuvel@linaro.org>
@@ -169,6 +170,10 @@ Juha Yrjola <juha.yrjola@solidboot.com>
 Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com>
 Kamil Konieczny <k.konieczny@samsung.com> <k.konieczny@partner.samsung.com>
 Kay Sievers <kay.sievers@vrfy.org>
+Kees Cook <keescook@chromium.org> <kees.cook@canonical.com>
+Kees Cook <keescook@chromium.org> <keescook@google.com>
+Kees Cook <keescook@chromium.org> <kees@outflux.net>
+Kees Cook <keescook@chromium.org> <kees@ubuntu.com>
 Kenneth W Chen <kenneth.w.chen@intel.com>
 Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru>
 Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
@@ -184,6 +189,7 @@ Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com>
 Linas Vepstas <linas@austin.ibm.com>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
+<linux-hardening@vger.kernel.org> <kernel-hardening@lists.openwall.com>
 Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
 Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
 Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com>

Documentation/admin-guide/cgroup-v2.rst

@@ -1324,15 +1324,26 @@ PAGE_SIZE multiple when read back.
 	  pgmajfault
 		Number of major page faults incurred
 
-	  workingset_refault
-		Number of refaults of previously evicted pages
+	  workingset_refault_anon
+		Number of refaults of previously evicted anonymous pages.
 
-	  workingset_activate
-		Number of refaulted pages that were immediately activated
+	  workingset_refault_file
+		Number of refaults of previously evicted file pages.
 
-	  workingset_restore
-		Number of restored pages which have been detected as an active
-		workingset before they got reclaimed.
+	  workingset_activate_anon
+		Number of refaulted anonymous pages that were immediately
+		activated.
+
+	  workingset_activate_file
+		Number of refaulted file pages that were immediately activated.
+
+	  workingset_restore_anon
+		Number of restored anonymous pages which have been detected as
+		an active workingset before they got reclaimed.
+
+	  workingset_restore_file
+		Number of restored file pages which have been detected as an
+		active workingset before they got reclaimed.
 
 	  workingset_nodereclaim
 		Number of times a shadow node has been reclaimed

Documentation/admin-guide/device-mapper/dm-crypt.rst

@@ -67,7 +67,7 @@ Parameters::
     the value passed in <key_size>.
 
 <key_type>
-    Either 'logon' or 'user' kernel key type.
+    Either 'logon', 'user' or 'encrypted' kernel key type.
 
 <key_description>
     The kernel keyring key description crypt target should look for
@@ -121,6 +121,14 @@ submit_from_crypt_cpus
     thread because it benefits CFQ to have writes submitted using the
     same context.
 
+no_read_workqueue
+    Bypass dm-crypt internal workqueue and process read requests synchronously.
+
+no_write_workqueue
+    Bypass dm-crypt internal workqueue and process write requests synchronously.
+    This option is automatically enabled for host-managed zoned block devices
+    (e.g. host-managed SMR hard-disks).
+
 integrity:<bytes>:<type>
     The device requires additional <bytes> metadata per-sector stored
     in per-bio integrity structure. This metadata must by provided

Documentation/admin-guide/pm/cpuidle.rst

@@ -690,7 +690,7 @@ which of the two parameters is added to the kernel command line.  In the
 instruction of the CPUs (which, as a rule, suspends the execution of the program
 and causes the hardware to attempt to enter the shallowest available idle state)
 for this purpose, and if ``idle=poll`` is used, idle CPUs will execute a
-more or less ``lightweight'' sequence of instructions in a tight loop.  [Note
+more or less "lightweight" sequence of instructions in a tight loop.  [Note
 that using ``idle=poll`` is somewhat drastic in many cases, as preventing idle
 CPUs from saving almost any energy at all may not be the only effect of it.
 For example, on Intel hardware it effectively prevents CPUs from using

Documentation/bpf/ringbuf.rst

@@ -182,9 +182,6 @@ in the order of reservations, but only after all previous records where
 already committed. It is thus possible for slow producers to temporarily hold
 off submitted records, that were reserved later.
 
-Reservation/commit/consumer protocol is verified by litmus tests in
-Documentation/litmus_tests/bpf-rb/_.
-
 One interesting implementation bit, that significantly simplifies (and thus
 speeds up as well) implementation of both producers and consumers is how data
 area is mapped twice contiguously back-to-back in the virtual memory. This
@@ -200,7 +197,7 @@ a self-pacing notifications of new data being availability.
 being available after commit only if consumer has already caught up right up to
 the record being committed. If not, consumer still has to catch up and thus
 will see new data anyways without needing an extra poll notification.
-Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c_) show that
+Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbufs.c) show that
 this allows to achieve a very high throughput without having to resort to
 tricks like "notify only every Nth sample", which are necessary with perf
 buffer. For extreme cases, when BPF program wants more manual control of

Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml

@@ -23,7 +23,7 @@ properties:
   compatible:
     items:
       - const: raspberrypi,bcm2835-firmware
-      - const: simple-bus
+      - const: simple-mfd
 
   mboxes:
     $ref: '/schemas/types.yaml#/definitions/phandle'
@@ -57,7 +57,7 @@ required:
 examples:
   - |
     firmware {
-        compatible = "raspberrypi,bcm2835-firmware", "simple-bus";
+        compatible = "raspberrypi,bcm2835-firmware", "simple-mfd";
         mboxes = <&mailbox>;
 
         firmware_clocks: clocks {

Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml

@@ -67,7 +67,7 @@ examples:
 
     main_crypto: crypto@4e00000 {
         compatible = "ti,j721-sa2ul";
-        reg = <0x0 0x4e00000 0x0 0x1200>;
+        reg = <0x4e00000 0x1200>;
         power-domains = <&k3_pds 264 TI_SCI_PD_EXCLUSIVE>;
         dmas = <&main_udmap 0xc000>, <&main_udmap 0x4000>,
                <&main_udmap 0x4001>;

Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml

@@ -145,10 +145,10 @@ examples:
 
     display@fd4a0000 {
         compatible = "xlnx,zynqmp-dpsub-1.7";
-        reg = <0x0 0xfd4a0000 0x0 0x1000>,
-              <0x0 0xfd4aa000 0x0 0x1000>,
-              <0x0 0xfd4ab000 0x0 0x1000>,
-              <0x0 0xfd4ac000 0x0 0x1000>;
+        reg = <0xfd4a0000 0x1000>,
+              <0xfd4aa000 0x1000>,
+              <0xfd4ab000 0x1000>,
+              <0xfd4ac000 0x1000>;
         reg-names = "dp", "blend", "av_buf", "aud";
         interrupts = <0 119 4>;
         interrupt-parent = <&gic>;

Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml

@@ -57,7 +57,7 @@ examples:
 
     dma: dma-controller@fd4c0000 {
       compatible = "xlnx,zynqmp-dpdma";
-      reg = <0x0 0xfd4c0000 0x0 0x1000>;
+      reg = <0xfd4c0000 0x1000>;
       interrupts = <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>;
       interrupt-parent = <&gic>;
       clocks = <&dpdma_clk>;

Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt

@@ -20,8 +20,9 @@ Required properties:
 - gpio-controller : Marks the device node as a GPIO controller
 - interrupts : Interrupt specifier, see interrupt-controller/interrupts.txt
 - interrupt-controller : Mark the GPIO controller as an interrupt-controller
-- ngpios : number of GPIO lines, see gpio.txt
-  (should be multiple of 8, up to 80 pins)
+- ngpios : number of *hardware* GPIO lines, see gpio.txt. This will expose
+  2 software GPIOs per hardware GPIO: one for hardware input, one for hardware
+  output. Up to 80 pins, must be a multiple of 8.
 - clocks : A phandle to the APB clock for SGPM clock division
 - bus-frequency : SGPM CLK frequency
 

Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml

@@ -30,7 +30,7 @@ properties:
     const: 0
 
 patternProperties:
-  "^multi-led[0-9a-f]$":
+  "^multi-led@[0-9a-b]$":
     type: object
     allOf:
       - $ref: leds-class-multicolor.yaml#

Documentation/devicetree/bindings/media/i2c/imx274.txt

@@ -1,38 +0,0 @@
-* Sony 1/2.5-Inch 8.51Mp CMOS Digital Image Sensor
-
-The Sony imx274 is a 1/2.5-inch CMOS active pixel digital image sensor with
-an active array size of 3864H x 2202V. It is programmable through I2C
-interface. The I2C address is fixed to 0x1a as per sensor data sheet.
-Image data is sent through MIPI CSI-2, which is configured as 4 lanes
-at 1440 Mbps.
-
-
-Required Properties:
-- compatible: value should be "sony,imx274" for imx274 sensor
-- reg: I2C bus address of the device
-
-Optional Properties:
-- reset-gpios: Sensor reset GPIO
-- clocks: Reference to the input clock.
-- clock-names: Should be "inck".
-- VANA-supply: Sensor 2.8v analog supply.
-- VDIG-supply: Sensor 1.8v digital core supply.
-- VDDL-supply: Sensor digital IO 1.2v supply.
-
-The imx274 device node should contain one 'port' child node with
-an 'endpoint' subnode. For further reading on port node refer to
-Documentation/devicetree/bindings/media/video-interfaces.txt.
-
-Example:
-	sensor@1a {
-		compatible = "sony,imx274";
-		reg = <0x1a>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reset-gpios = <&gpio_sensor 0 0>;
-		port {
-			sensor_out: endpoint {
-				remote-endpoint = <&csiss_in>;
-			};
-		};
-	};

Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml

@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/i2c/sony,imx274.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sony 1/2.5-Inch 8.51MP CMOS Digital Image Sensor
+
+maintainers:
+  - Leon Luo <leonl@leopardimaging.com>
+
+description: |
+  The Sony IMX274 is a 1/2.5-inch CMOS active pixel digital image sensor with an
+  active array size of 3864H x 2202V. It is programmable through I2C interface.
+  Image data is sent through MIPI CSI-2, which is configured as 4 lanes at 1440
+  Mbps.
+
+properties:
+  compatible:
+    const: sony,imx274
+
+  reg:
+    const: 0x1a
+
+  reset-gpios:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: inck
+
+  vana-supply:
+    description: Sensor 2.8 V analog supply.
+    maxItems: 1
+
+  vdig-supply:
+    description: Sensor 1.8 V digital core supply.
+    maxItems: 1
+
+  vddl-supply:
+    description: Sensor digital IO 1.2 V supply.
+    maxItems: 1
+
+  port:
+    type: object
+    description: Output video port. See ../video-interfaces.txt.
+
+required:
+  - compatible
+  - reg
+  - port
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c0 {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        imx274: camera-sensor@1a {
+            compatible = "sony,imx274";
+            reg = <0x1a>;
+            reset-gpios = <&gpio_sensor 0 0>;
+
+            port {
+                sensor_out: endpoint {
+                    remote-endpoint = <&csiss_in>;
+                };
+            };
+        };
+    };
+
+...

Documentation/devicetree/bindings/net/renesas,ravb.txt

@@ -21,6 +21,7 @@ Required properties:
       - "renesas,etheravb-r8a774a1" for the R8A774A1 SoC.
       - "renesas,etheravb-r8a774b1" for the R8A774B1 SoC.
       - "renesas,etheravb-r8a774c0" for the R8A774C0 SoC.
+      - "renesas,etheravb-r8a774e1" for the R8A774E1 SoC.
       - "renesas,etheravb-r8a7795" for the R8A7795 SoC.
       - "renesas,etheravb-r8a7796" for the R8A77960 SoC.
       - "renesas,etheravb-r8a77961" for the R8A77961 SoC.

Documentation/features/debug/debug-vm-pgtable/arch-support.txt

@@ -22,7 +22,7 @@
     |       nios2: | TODO |
     |    openrisc: | TODO |
     |      parisc: | TODO |
-    |     powerpc: |  ok  |
+    |     powerpc: | TODO |
     |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: | TODO |

Documentation/kbuild/llvm.rst

@@ -39,10 +39,10 @@ which can help simplify cross compiling. ::
 	ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- make CC=clang
 
 ``CROSS_COMPILE`` is not used to prefix the Clang compiler binary, instead
-``CROSS_COMPILE`` is used to set a command line flag: ``--target <triple>``. For
+``CROSS_COMPILE`` is used to set a command line flag: ``--target=<triple>``. For
 example: ::
 
-	clang --target aarch64-linux-gnu foo.c
+	clang --target=aarch64-linux-gnu foo.c
 
 LLVM Utilities
 --------------

Documentation/networking/ethtool-netlink.rst

@@ -206,6 +206,7 @@ Userspace to kernel:
   ``ETHTOOL_MSG_TSINFO_GET``		get timestamping info
   ``ETHTOOL_MSG_CABLE_TEST_ACT``        action start cable test
   ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT``    action start raw TDR cable test
+  ``ETHTOOL_MSG_TUNNEL_INFO_GET``       get tunnel offload info
   ===================================== ================================
 
 Kernel to userspace:
@@ -239,6 +240,7 @@ Kernel to userspace:
   ``ETHTOOL_MSG_TSINFO_GET_REPLY``	timestamping info
   ``ETHTOOL_MSG_CABLE_TEST_NTF``        Cable test results
   ``ETHTOOL_MSG_CABLE_TEST_TDR_NTF``    Cable test TDR results
+  ``ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY`` tunnel offload info
   ===================================== =================================
 
 ``GET`` requests are sent by userspace applications to retrieve device
@@ -1363,4 +1365,5 @@ are netlink only.
   ``ETHTOOL_SFECPARAM``               n/a
   n/a                                 ''ETHTOOL_MSG_CABLE_TEST_ACT''
   n/a                                 ''ETHTOOL_MSG_CABLE_TEST_TDR_ACT''
+  n/a                                 ``ETHTOOL_MSG_TUNNEL_INFO_GET``
   =================================== =====================================

Documentation/userspace-api/media/v4l/buffer.rst

@@ -701,23 +701,6 @@ Memory Consistency Flags
     :stub-columns: 0
     :widths:       3 1 4
 
-    * .. _`V4L2-FLAG-MEMORY-NON-CONSISTENT`:
-
-      - ``V4L2_FLAG_MEMORY_NON_CONSISTENT``
-      - 0x00000001
-      - A buffer is allocated either in consistent (it will be automatically
-	coherent between the CPU and the bus) or non-consistent memory. The
-	latter can provide performance gains, for instance the CPU cache
-	sync/flush operations can be avoided if the buffer is accessed by the
-	corresponding device only and the CPU does not read/write to/from that
-	buffer. However, this requires extra care from the driver -- it must
-	guarantee memory consistency by issuing a cache flush/sync when
-	consistency is needed. If this flag is set V4L2 will attempt to
-	allocate the buffer in non-consistent memory. The flag takes effect
-	only if the buffer is used for :ref:`memory mapping <mmap>` I/O and the
-	queue reports the :ref:`V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS
-	<V4L2-BUF-CAP-SUPPORTS-MMAP-CACHE-HINTS>` capability.
-
 .. c:type:: v4l2_memory
 
 enum v4l2_memory

Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst

@@ -120,13 +120,9 @@ than the number requested.
 	If you want to just query the capabilities without making any
 	other changes, then set ``count`` to 0, ``memory`` to
 	``V4L2_MEMORY_MMAP`` and ``format.type`` to the buffer type.
-    * - __u32
-      - ``flags``
-      - Specifies additional buffer management attributes.
-	See :ref:`memory-flags`.
 
     * - __u32
-      - ``reserved``\ [6]
+      - ``reserved``\ [7]
       - A place holder for future extensions. Drivers and applications
 	must set the array to zero.
 

Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst

@@ -112,17 +112,10 @@ aborting or finishing any DMA in progress, an implicit
 	``V4L2_MEMORY_MMAP`` and ``type`` set to the buffer type. This will
 	free any previously allocated buffers, so this is typically something
 	that will be done at the start of the application.
-    * - union {
-      - (anonymous)
-    * - __u32
-      - ``flags``
-      - Specifies additional buffer management attributes.
-	See :ref:`memory-flags`.
     * - __u32
       - ``reserved``\ [1]
-      - Kept for backwards compatibility. Use ``flags`` instead.
-    * - }
-      -
+      - A place holder for future extensions. Drivers and applications
+	must set the array to zero.
 
 .. tabularcolumns:: |p{6.1cm}|p{2.2cm}|p{8.7cm}|
 
@@ -169,7 +162,6 @@ aborting or finishing any DMA in progress, an implicit
       - This capability is set by the driver to indicate that the queue supports
         cache and memory management hints. However, it's only valid when the
         queue is used for :ref:`memory mapping <mmap>` streaming I/O. See
-        :ref:`V4L2_FLAG_MEMORY_NON_CONSISTENT <V4L2-FLAG-MEMORY-NON-CONSISTENT>`,
         :ref:`V4L2_BUF_FLAG_NO_CACHE_INVALIDATE <V4L2-BUF-FLAG-NO-CACHE-INVALIDATE>` and
         :ref:`V4L2_BUF_FLAG_NO_CACHE_CLEAN <V4L2-BUF-FLAG-NO-CACHE-CLEAN>`.
 

Documentation/virt/kvm/api.rst

@@ -6173,3 +6173,23 @@ specific interfaces must be consistent, i.e. if one says the feature
 is supported, than the other should as well and vice versa.  For arm64
 see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
 For x86 see Documentation/virt/kvm/msr.rst "MSR_KVM_STEAL_TIME".
+
+8.25 KVM_CAP_S390_DIAG318
+-------------------------
+
+:Architectures: s390
+
+This capability enables a guest to set information about its control program
+(i.e. guest kernel type and version). The information is helpful during
+system/firmware service events, providing additional data about the guest
+environments running on the machine.
+
+The information is associated with the DIAGNOSE 0x318 instruction, which sets
+an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and
+a 7-byte Control Program Version Code (CPVC). The CPNC determines what
+environment the control program is running in (e.g. Linux, z/VM...), and the
+CPVC is used for information specific to OS (e.g. Linux version, Linux
+distribution...)
+
+If this capability is available, then the CPNC and CPVC can be synchronized
+between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318).

Documentation/x86/boot.rst

@@ -1342,8 +1342,8 @@ follow::
 
 In addition to read/modify/write the setup header of the struct
 boot_params as that of 16-bit boot protocol, the boot loader should
-also fill the additional fields of the struct boot_params as that
-described in zero-page.txt.
+also fill the additional fields of the struct boot_params as
+described in chapter :doc:`zero-page`.
 
 After setting up the struct boot_params, the boot loader can load the
 32/64-bit kernel in the same way as that of 16-bit boot protocol.
@@ -1379,7 +1379,7 @@ can be calculated as follows::
 In addition to read/modify/write the setup header of the struct
 boot_params as that of 16-bit boot protocol, the boot loader should
 also fill the additional fields of the struct boot_params as described
-in zero-page.txt.
+in chapter :doc:`zero-page`.
 
 After setting up the struct boot_params, the boot loader can load
 64-bit kernel in the same way as that of 16-bit boot protocol, but

MAINTAINERS

@@ -1460,6 +1460,11 @@ S:	Odd Fixes
 F:	drivers/amba/
 F:	include/linux/amba/bus.h
 
+ARM PRIMECELL CLCD PL110 DRIVER
+M:	Russell King <linux@armlinux.org.uk>
+S:	Odd Fixes
+F:	drivers/video/fbdev/amba-clcd.*
+
 ARM PRIMECELL KMI PL050 DRIVER
 M:	Russell King <linux@armlinux.org.uk>
 S:	Odd Fixes
@@ -1623,7 +1628,7 @@ N:	meson
 
 ARM/Annapurna Labs ALPINE ARCHITECTURE
 M:	Tsahee Zidenberg <tsahee@annapurnalabs.com>
-M:	Antoine Tenart <antoine.tenart@bootlin.com>
+M:	Antoine Tenart <atenart@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/boot/dts/alpine*
@@ -4408,12 +4413,6 @@ T:	git git://git.infradead.org/users/hch/configfs.git
 F:	fs/configfs/
 F:	include/linux/configfs.h
 
-CONNECTOR
-M:	Evgeniy Polyakov <zbr@ioremap.net>
-L:	netdev@vger.kernel.org
-S:	Maintained
-F:	drivers/connector/
-
 CONSOLE SUBSYSTEM
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Supported
@@ -6180,7 +6179,7 @@ F:	Documentation/devicetree/bindings/edac/aspeed-sdram-edac.txt
 F:	drivers/edac/aspeed_edac.c
 
 EDAC-BLUEFIELD
-M:	Shravan Kumar Ramani <sramani@nvidia.com>
+M:	Shravan Kumar Ramani <shravankr@nvidia.com>
 S:	Supported
 F:	drivers/edac/bluefield_edac.c
 
@@ -7241,7 +7240,7 @@ F:	drivers/staging/gasket/
 GCC PLUGINS
 M:	Kees Cook <keescook@chromium.org>
 R:	Emese Revfy <re.emese@gmail.com>
-L:	kernel-hardening@lists.openwall.com
+L:	linux-hardening@vger.kernel.org
 S:	Maintained
 F:	Documentation/kbuild/gcc-plugins.rst
 F:	scripts/Makefile.gcc-plugins
@@ -8329,8 +8328,9 @@ S:	Supported
 F:	drivers/pci/hotplug/rpaphp*
 
 IBM Power SRIOV Virtual NIC Device Driver
-M:	Thomas Falcon <tlfalcon@linux.ibm.com>
-M:	John Allen <jallen@linux.ibm.com>
+M:	Dany Madden <drt@linux.ibm.com>
+M:	Lijun Pan <ljp@linux.ibm.com>
+M:	Sukadev Bhattiprolu <sukadev@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmvnic.*
@@ -8344,7 +8344,7 @@ F:	arch/powerpc/platforms/powernv/copy-paste.h
 F:	arch/powerpc/platforms/powernv/vas*
 
 IBM Power Virtual Ethernet Device Driver
-M:	Thomas Falcon <tlfalcon@linux.ibm.com>
+M:	Cristobal Forno <cforno12@linux.ibm.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmveth.*
@@ -8678,7 +8678,7 @@ F:	drivers/input/input-mt.c
 K:	\b(ABS|SYN)_MT_
 
 INSIDE SECURE CRYPTO DRIVER
-M:	Antoine Tenart <antoine.tenart@bootlin.com>
+M:	Antoine Tenart <atenart@kernel.org>
 L:	linux-crypto@vger.kernel.org
 S:	Maintained
 F:	drivers/crypto/inside-secure/
@@ -8757,7 +8757,8 @@ F:	include/drm/i915*
 F:	include/uapi/drm/i915_drm.h
 
 INTEL ETHERNET DRIVERS
-M:	Jeff Kirsher <jeffrey.t.kirsher@intel.com>
+M:	Jesse Brandeburg <jesse.brandeburg@intel.com>
+M:	Tony Nguyen <anthony.l.nguyen@intel.com>
 L:	intel-wired-lan@lists.osuosl.org (moderated for non-subscribers)
 S:	Supported
 W:	http://www.intel.com/support/feedback.htm
@@ -9251,7 +9252,7 @@ F:	drivers/firmware/iscsi_ibft*
 
 ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR
 M:	Sagi Grimberg <sagi@grimberg.me>
-M:	Max Gurtovoy <maxg@nvidia.com>
+M:	Max Gurtovoy <mgurtovoy@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.openfabrics.org
@@ -9801,7 +9802,7 @@ F:	drivers/scsi/53c700*
 LEAKING_ADDRESSES
 M:	Tobin C. Harding <me@tobin.cc>
 M:	Tycho Andersen <tycho@tycho.pizza>
-L:	kernel-hardening@lists.openwall.com
+L:	linux-hardening@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tobin/leaks.git
 F:	scripts/leaking_addresses.pl
@@ -11042,6 +11043,7 @@ F:	drivers/char/hw_random/mtk-rng.c
 
 MEDIATEK SWITCH DRIVER
 M:	Sean Wang <sean.wang@mediatek.com>
+M:	Landen Chao <Landen.Chao@mediatek.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/dsa/mt7530.*
@@ -12055,6 +12057,7 @@ Q:	http://patchwork.ozlabs.org/project/netdev/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 F:	Documentation/devicetree/bindings/net/
+F:	drivers/connector/
 F:	drivers/net/
 F:	include/linux/etherdevice.h
 F:	include/linux/fcdevice.h
@@ -12080,6 +12083,7 @@ NETWORKING [DSA]
 M:	Andrew Lunn <andrew@lunn.ch>
 M:	Vivien Didelot <vivien.didelot@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
+M:	Vladimir Oltean <olteanv@gmail.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/dsa/
 F:	drivers/net/dsa/
@@ -13185,6 +13189,7 @@ F:	drivers/firmware/pcdp.*
 
 PCI DRIVER FOR AARDVARK (Marvell Armada 3700)
 M:	Thomas Petazzoni <thomas.petazzoni@bootlin.com>
+M:	Pali Rohár <pali@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -16157,7 +16162,7 @@ M:	Leon Luo <leonl@leopardimaging.com>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 T:	git git://linuxtv.org/media_tree.git
-F:	Documentation/devicetree/bindings/media/i2c/imx274.txt
+F:	Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml
 F:	drivers/media/i2c/imx274.c
 
 SONY IMX290 SENSOR DRIVER
@@ -16727,6 +16732,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/gpio/snps,dw-apb-gpio.yaml
 F:	drivers/gpio/gpio-dwapb.c
 
+SYNOPSYS DESIGNWARE APB SSI DRIVER
+M:	Serge Semin <fancer.lancer@gmail.com>
+L:	linux-spi@vger.kernel.org
+S:	Supported
+F:	Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+F:	drivers/spi/spi-dw*
+
 SYNOPSYS DESIGNWARE AXI DMAC DRIVER
 M:	Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
 S:	Maintained
@@ -18284,7 +18296,8 @@ F:	drivers/gpu/vga/vga_switcheroo.c
 F:	include/linux/vga_switcheroo.h
 
 VIA RHINE NETWORK DRIVER
-S:	Orphan
+S:	Maintained
+M:	Kevin Brace <kevinbrace@bracecomputerlab.com>
 F:	drivers/net/ethernet/via/via-rhine.c
 
 VIA SD/MMC CARD CONTROLLER DRIVER
@@ -18889,10 +18902,10 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm
 F:	arch/x86/mm/
 
 X86 PLATFORM DRIVERS
-M:	Darren Hart <dvhart@infradead.org>
-M:	Andy Shevchenko <andy@infradead.org>
+M:	Hans de Goede <hdegoede@redhat.com>
+M:	Mark Gross <mgross@linux.intel.com>
 L:	platform-driver-x86@vger.kernel.org
-S:	Odd Fixes
+S:	Maintained
 T:	git git://git.infradead.org/linux-platform-drivers-x86.git
 F:	drivers/platform/olpc/
 F:	drivers/platform/x86/

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*

arch/arm/boot/dts/at91-sama5d2_icp.dts

@@ -116,7 +116,6 @@
 		switch0: ksz8563@0 {
 			compatible = "microchip,ksz8563";
 			reg = <0>;
-			phy-mode = "mii";
 			reset-gpios = <&pioA PIN_PD4 GPIO_ACTIVE_LOW>;
 
 			spi-max-frequency = <500000>;
@@ -140,6 +139,7 @@
 					reg = <2>;
 					label = "cpu";
 					ethernet = <&macb0>;
+					phy-mode = "mii";
 					fixed-link {
 						speed = <100>;
 						full-duplex;

arch/arm/boot/dts/bcm2835-rpi.dtsi

@@ -13,7 +13,7 @@
 
 	soc {
 		firmware: firmware {
-			compatible = "raspberrypi,bcm2835-firmware", "simple-bus";
+			compatible = "raspberrypi,bcm2835-firmware", "simple-mfd";
 			#address-cells = <1>;
 			#size-cells = <1>;
 

arch/arm/mach-imx/cpuidle-imx6q.c

@@ -24,7 +24,9 @@ static int imx6q_enter_wait(struct cpuidle_device *dev,
 		imx6_set_lpm(WAIT_UNCLOCKED);
 	raw_spin_unlock(&cpuidle_lock);
 
+	rcu_idle_enter();
 	cpu_do_idle();
+	rcu_idle_exit();
 
 	raw_spin_lock(&cpuidle_lock);
 	if (num_idle_cpus-- == num_online_cpus())
@@ -44,7 +46,7 @@ static struct cpuidle_driver imx6q_cpuidle_driver = {
 		{
 			.exit_latency = 50,
 			.target_residency = 75,
-			.flags = CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIMER_STOP | CPUIDLE_FLAG_RCU_IDLE,
 			.enter = imx6q_enter_wait,
 			.name = "WAIT",
 			.desc = "Clock off",

arch/arm/xen/enlighten.c

@@ -150,7 +150,7 @@ static int xen_starting_cpu(unsigned int cpu)
 	pr_info("Xen: initializing cpu%d\n", cpu);
 	vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
 
-	info.mfn = virt_to_gfn(vcpup);
+	info.mfn = percpu_to_gfn(vcpup);
 	info.offset = xen_offset_in_page(vcpup);
 
 	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu),

arch/arm64/crypto/aes-neonbs-core.S

@@ -788,7 +788,7 @@ SYM_FUNC_START_LOCAL(__xts_crypt8)
 
 0:	mov		bskey, x21
 	mov		rounds, x22
-	br		x7
+	br		x16
 SYM_FUNC_END(__xts_crypt8)
 
 	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
@@ -806,7 +806,7 @@ SYM_FUNC_END(__xts_crypt8)
 	uzp1		v30.4s, v30.4s, v25.4s
 	ld1		{v25.16b}, [x24]
 
-99:	adr		x7, \do8
+99:	adr		x16, \do8
 	bl		__xts_crypt8
 
 	ldp		q16, q17, [sp, #.Lframe_local_offset]

arch/arm64/include/asm/kvm_emulate.h

@@ -298,15 +298,15 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 	return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
-static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
 }
 
+/* Always check for S1PTW *before* using this. */
 static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) ||
-		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR;
 }
 
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
@@ -335,6 +335,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
 }
 
+static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
+}
+
 static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
@@ -372,6 +377,9 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 
 static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 {
+	if (kvm_vcpu_abt_iss1tw(vcpu))
+		return true;
+
 	if (kvm_vcpu_trap_is_iabt(vcpu))
 		return false;
 

arch/arm64/kernel/acpi.c

@@ -298,8 +298,21 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 		case EFI_BOOT_SERVICES_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
 		case EFI_PERSISTENT_MEMORY:
-			pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys);
-			return NULL;
+			if (memblock_is_map_memory(phys) ||
+			    !memblock_is_region_memory(phys, size)) {
+				pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys);
+				return NULL;
+			}
+			/*
+			 * Mapping kernel memory is permitted if the region in
+			 * question is covered by a single memblock with the
+			 * NOMAP attribute set: this enables the use of ACPI
+			 * table overrides passed via initramfs, which are
+			 * reserved in memory using arch_reserve_mem_area()
+			 * below. As this particular use case only requires
+			 * read access, fall through to the R/O mapping case.
+			 */
+			fallthrough;
 
 		case EFI_RUNTIME_SERVICES_CODE:
 			/*
@@ -388,3 +401,8 @@ int apei_claim_sea(struct pt_regs *regs)
 
 	return err;
 }
+
+void arch_reserve_mem_area(acpi_physical_address addr, size_t size)
+{
+	memblock_mark_nomap(addr, size);
+}

arch/arm64/kernel/cpu_errata.c

@@ -910,8 +910,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.desc = "ARM erratum 1418040",
 		.capability = ARM64_WORKAROUND_1418040,
 		ERRATA_MIDR_RANGE_LIST(erratum_1418040_list),
-		.type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU |
-			 ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU),
+		/*
+		 * We need to allow affected CPUs to come in late, but
+		 * also need the non-affected CPUs to be able to come
+		 * in at any point in time. Wonderful.
+		 */
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
 	},
 #endif
 #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT

arch/arm64/kernel/paravirt.c

@@ -50,16 +50,19 @@ static u64 pv_steal_clock(int cpu)
 	struct pv_time_stolen_time_region *reg;
 
 	reg = per_cpu_ptr(&stolen_time_region, cpu);
-	if (!reg->kaddr) {
-		pr_warn_once("stolen time enabled but not configured for cpu %d\n",
-			     cpu);
+
+	/*
+	 * paravirt_steal_clock() may be called before the CPU
+	 * online notification callback runs. Until the callback
+	 * has run we just return zero.
+	 */
+	if (!reg->kaddr)
 		return 0;
-	}
 
 	return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time));
 }
 
-static int stolen_time_dying_cpu(unsigned int cpu)
+static int stolen_time_cpu_down_prepare(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 
@@ -73,7 +76,7 @@ static int stolen_time_dying_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int init_stolen_time_cpu(unsigned int cpu)
+static int stolen_time_cpu_online(unsigned int cpu)
 {
 	struct pv_time_stolen_time_region *reg;
 	struct arm_smccc_res res;
@@ -103,19 +106,20 @@ static int init_stolen_time_cpu(unsigned int cpu)
 	return 0;
 }
 
-static int pv_time_init_stolen_time(void)
+static int __init pv_time_init_stolen_time(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING,
-				"hypervisor/arm/pvtime:starting",
-				init_stolen_time_cpu, stolen_time_dying_cpu);
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				"hypervisor/arm/pvtime:online",
+				stolen_time_cpu_online,
+				stolen_time_cpu_down_prepare);
 	if (ret < 0)
 		return ret;
 	return 0;
 }
 
-static bool has_pv_steal_clock(void)
+static bool __init has_pv_steal_clock(void)
 {
 	struct arm_smccc_res res;
 

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -449,7 +449,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
-			!kvm_vcpu_dabt_iss1tw(vcpu);
+			!kvm_vcpu_abt_iss1tw(vcpu);
 
 		if (valid) {
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);

arch/arm64/kvm/hyp/nvhe/tlb.c

@@ -31,7 +31,14 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
 		isb();
 	}
 
+	/*
+	 * __load_guest_stage2() includes an ISB only when the AT
+	 * workaround is applied. Take care of the opposite condition,
+	 * ensuring that we always have an ISB, but not two ISBs back
+	 * to back.
+	 */
 	__load_guest_stage2(mmu);
+	asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
 }
 
 static void __tlb_switch_to_host(struct tlb_inv_context *cxt)

arch/arm64/kvm/mmu.c

@@ -1849,7 +1849,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
 
 	write_fault = kvm_is_write_fault(vcpu);
-	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
+	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
 	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
@@ -2131,7 +2131,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 
-		if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+		if (kvm_vcpu_abt_iss1tw(vcpu)) {
 			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 			ret = 1;
 			goto out_unlock;

arch/arm64/net/bpf_jit_comp.c

@@ -143,14 +143,17 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val,
 	}
 }
 
-static inline int bpf2a64_offset(int bpf_to, int bpf_from,
+static inline int bpf2a64_offset(int bpf_insn, int off,
 				 const struct jit_ctx *ctx)
 {
-	int to = ctx->offset[bpf_to];
-	/* -1 to account for the Branch instruction */
-	int from = ctx->offset[bpf_from] - 1;
-
-	return to - from;
+	/* BPF JMP offset is relative to the next instruction */
+	bpf_insn++;
+	/*
+	 * Whereas arm64 branch instructions encode the offset
+	 * from the branch itself, so we must subtract 1 from the
+	 * instruction offset.
+	 */
+	return ctx->offset[bpf_insn + off] - (ctx->offset[bpf_insn] - 1);
 }
 
 static void jit_fill_hole(void *area, unsigned int size)
@@ -642,7 +645,7 @@ emit_bswap_uxt:
 
 	/* JUMP off */
 	case BPF_JMP | BPF_JA:
-		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		jmp_offset = bpf2a64_offset(i, off, ctx);
 		check_imm26(jmp_offset);
 		emit(A64_B(jmp_offset), ctx);
 		break;
@@ -669,7 +672,7 @@ emit_bswap_uxt:
 	case BPF_JMP32 | BPF_JSLE | BPF_X:
 		emit(A64_CMP(is64, dst, src), ctx);
 emit_cond_jmp:
-		jmp_offset = bpf2a64_offset(i + off, i, ctx);
+		jmp_offset = bpf2a64_offset(i, off, ctx);
 		check_imm19(jmp_offset);
 		switch (BPF_OP(code)) {
 		case BPF_JEQ:
@@ -908,10 +911,21 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass)
 	const struct bpf_prog *prog = ctx->prog;
 	int i;
 
+	/*
+	 * - offset[0] offset of the end of prologue,
+	 *   start of the 1st instruction.
+	 * - offset[1] - offset of the end of 1st instruction,
+	 *   start of the 2nd instruction
+	 * [....]
+	 * - offset[3] - offset of the end of 3rd instruction,
+	 *   start of 4th instruction
+	 */
 	for (i = 0; i < prog->len; i++) {
 		const struct bpf_insn *insn = &prog->insnsi[i];
 		int ret;
 
+		if (ctx->image == NULL)
+			ctx->offset[i] = ctx->idx;
 		ret = build_insn(insn, ctx, extra_pass);
 		if (ret > 0) {
 			i++;
@@ -919,11 +933,16 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass)
 				ctx->offset[i] = ctx->idx;
 			continue;
 		}
-		if (ctx->image == NULL)
-			ctx->offset[i] = ctx->idx;
 		if (ret)
 			return ret;
 	}
+	/*
+	 * offset is allocated with prog->len + 1 so fill in
+	 * the last element with the offset after the last
+	 * instruction (end of program)
+	 */
+	if (ctx->image == NULL)
+		ctx->offset[i] = ctx->idx;
 
 	return 0;
 }
@@ -1002,7 +1021,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
 
-	ctx.offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
+	ctx.offset = kcalloc(prog->len + 1, sizeof(int), GFP_KERNEL);
 	if (ctx.offset == NULL) {
 		prog = orig_prog;
 		goto out_off;
@@ -1089,7 +1108,7 @@ skip_init_ctx:
 	prog->jited_len = prog_size;
 
 	if (!prog->is_func || extra_pass) {
-		bpf_prog_fill_jited_linfo(prog, ctx.offset);
+		bpf_prog_fill_jited_linfo(prog, ctx.offset + 1);
 out_off:
 		kfree(ctx.offset);
 		kfree(jit_data);

arch/ia64/include/asm/acpi.h

@@ -74,8 +74,6 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf)
 	buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP;
 }
 
-#define acpi_unlazy_tlb(x)
-
 #ifdef CONFIG_ACPI_NUMA
 extern cpumask_t early_cpu_possible_map;
 #define for_each_possible_early_cpu(cpu)  \

arch/ia64/mm/init.c

@@ -538,7 +538,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
 				 args->nid, args->zone, page_to_pfn(map_start),
-				 MEMMAP_EARLY, NULL);
+				 MEMINIT_EARLY, NULL);
 	return 0;
 }
 
@@ -547,8 +547,8 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 	     unsigned long start_pfn)
 {
 	if (!vmem_map) {
-		memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY,
-				NULL);
+		memmap_init_zone(size, nid, zone, start_pfn,
+				 MEMINIT_EARLY, NULL);
 	} else {
 		struct page *start;
 		struct memmap_init_callback_data args;

arch/mips/Kconfig

@@ -877,6 +877,7 @@ config SNI_RM
 	select I8253
 	select I8259
 	select ISA
+	select MIPS_L1_CACHE_SHIFT_6
 	select SWAP_IO_SPACE if CPU_BIG_ENDIAN
 	select SYS_HAS_CPU_R4X00
 	select SYS_HAS_CPU_R5000

arch/mips/bcm47xx/setup.c

@@ -148,7 +148,7 @@ void __init plat_mem_setup(void)
 {
 	struct cpuinfo_mips *c = &current_cpu_data;
 
-	if ((c->cputype == CPU_74K) || (c->cputype == CPU_1074K)) {
+	if (c->cputype == CPU_74K) {
 		pr_info("Using bcma bus\n");
 #ifdef CONFIG_BCM47XX_BCMA
 		bcm47xx_bus_type = BCM47XX_BUS_TYPE_BCMA;

arch/mips/include/asm/cpu-type.h

@@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type)
 	case CPU_34K:
 	case CPU_1004K:
 	case CPU_74K:
+	case CPU_1074K:
 	case CPU_M14KC:
 	case CPU_M14KEC:
 	case CPU_INTERAPTIV:

arch/mips/loongson2ef/Platform

@@ -44,6 +44,10 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS
   endif
 endif
 
+# Some -march= flags enable MMI instructions, and GCC complains about that
+# support being enabled alongside -msoft-float. Thus explicitly disable MMI.
+cflags-y += $(call cc-option,-mno-loongson-mmi)
+
 #
 # Loongson Machines' Support
 #

arch/mips/loongson64/cop2-ex.c

@@ -95,10 +95,8 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 			if (res)
 				goto fault;
 
-			set_fpr64(current->thread.fpu.fpr,
-				insn.loongson3_lswc2_format.rt, value);
-			set_fpr64(current->thread.fpu.fpr,
-				insn.loongson3_lswc2_format.rq, value_next);
+			set_fpr64(&current->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0, value);
+			set_fpr64(&current->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0, value_next);
 			compute_return_epc(regs);
 			own_fpu(1);
 		}
@@ -130,15 +128,13 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 				goto sigbus;
 
 			lose_fpu(1);
-			value_next = get_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lswc2_format.rq);
+			value_next = get_fpr64(&current->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0);
 
 			StoreDW(addr + 8, value_next, res);
 			if (res)
 				goto fault;
 
-			value = get_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lswc2_format.rt);
+			value = get_fpr64(&current->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0);
 
 			StoreDW(addr, value, res);
 			if (res)
@@ -204,8 +200,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 			if (res)
 				goto fault;
 
-			set_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lsdc2_format.rt, value);
+			set_fpr64(&current->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value);
 			compute_return_epc(regs);
 			own_fpu(1);
 
@@ -221,8 +216,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 			if (res)
 				goto fault;
 
-			set_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lsdc2_format.rt, value);
+			set_fpr64(&current->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value);
 			compute_return_epc(regs);
 			own_fpu(1);
 			break;
@@ -286,8 +280,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 				goto sigbus;
 
 			lose_fpu(1);
-			value = get_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lsdc2_format.rt);
+			value = get_fpr64(&current->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0);
 
 			StoreW(addr, value, res);
 			if (res)
@@ -305,8 +298,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
 				goto sigbus;
 
 			lose_fpu(1);
-			value = get_fpr64(current->thread.fpu.fpr,
-					insn.loongson3_lsdc2_format.rt);
+			value = get_fpr64(&current->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0);
 
 			StoreDW(addr, value, res);
 			if (res)

arch/mips/sni/a20r.c

@@ -143,7 +143,10 @@ static struct platform_device sc26xx_pdev = {
 	},
 };
 
-static u32 a20r_ack_hwint(void)
+/*
+ * Trigger chipset to update CPU's CAUSE IP field
+ */
+static u32 a20r_update_cause_ip(void)
 {
 	u32 status = read_c0_status();
 
@@ -205,12 +208,14 @@ static void a20r_hwint(void)
 	int irq;
 
 	clear_c0_status(IE_IRQ0);
-	status = a20r_ack_hwint();
+	status = a20r_update_cause_ip();
 	cause = read_c0_cause();
 
 	irq = ffs(((cause & status) >> 8) & 0xf8);
 	if (likely(irq > 0))
 		do_IRQ(SNI_A20R_IRQ_BASE + irq - 1);
+
+	a20r_update_cause_ip();
 	set_c0_status(IE_IRQ0);
 }
 

arch/powerpc/Kconfig

@@ -116,7 +116,6 @@ config PPC
 	#
 	select ARCH_32BIT_OFF_T if PPC32
 	select ARCH_HAS_DEBUG_VIRTUAL
-	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE

arch/powerpc/configs/pasemi_defconfig

@@ -108,7 +108,6 @@ CONFIG_FB_NVIDIA=y
 CONFIG_FB_NVIDIA_I2C=y
 CONFIG_FB_RADEON=y
 # CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
 CONFIG_SOUND=y
 CONFIG_SND=y

arch/powerpc/configs/ppc6xx_defconfig

@@ -743,7 +743,6 @@ CONFIG_FB_TRIDENT=m
 CONFIG_FB_SM501=m
 CONFIG_FB_IBM_GXT4500=y
 CONFIG_LCD_PLATFORM=m
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
 CONFIG_LOGO=y

arch/powerpc/include/asm/book3s/64/mmu.h

@@ -239,14 +239,14 @@ static inline void early_init_mmu_secondary(void)
 
 extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
 					 phys_addr_t first_memblock_size);
-extern void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
-					 phys_addr_t first_memblock_size);
 static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 					      phys_addr_t first_memblock_size)
 {
-	if (early_radix_enabled())
-		return radix__setup_initial_memory_limit(first_memblock_base,
-						   first_memblock_size);
+	/*
+	 * Hash has more strict restrictions. At this point we don't
+	 * know which translations we will pick. Hence go with hash
+	 * restrictions.
+	 */
 	return hash__setup_initial_memory_limit(first_memblock_base,
 					   first_memblock_size);
 }

arch/powerpc/kernel/dma-iommu.c

@@ -120,7 +120,8 @@ u64 dma_iommu_get_required_mask(struct device *dev)
 	if (!tbl)
 		return 0;
 
-	mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
+	mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) +
+			tbl->it_page_shift - 1);
 	mask += mask - 1;
 
 	return mask;

arch/powerpc/kernel/vdso32/Makefile

@@ -50,7 +50,7 @@ $(obj-vdso32): %.o: %.S FORCE
 
 # actual build commands
 quiet_cmd_vdso32ld = VDSO32L $@
-      cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn) -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
+      cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 quiet_cmd_vdso32as = VDSO32A $@
       cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $<
 

arch/powerpc/kernel/vdso32/vdso32.lds.S

@@ -111,7 +111,6 @@ SECTIONS
 		*(.note.GNU-stack)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
-		*(.glink .iplt .plt .rela*)
 	}
 }
 

arch/powerpc/kernel/vdso64/Makefile

@@ -34,7 +34,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 
 # actual build commands
 quiet_cmd_vdso64ld = VDSO64L $@
-      cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn)
+      cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
 
 # install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@

arch/powerpc/kernel/vdso64/vdso64.lds.S

@@ -30,7 +30,7 @@ SECTIONS
 	. = ALIGN(16);
 	.text		: {
 		*(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*)
-		*(.sfpr)
+		*(.sfpr .glink)
 	}						:text
 	PROVIDE(__etext = .);
 	PROVIDE(_etext = .);
@@ -111,7 +111,6 @@ SECTIONS
 		*(.branch_lt)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
 		*(.bss .sbss .dynbss .dynsbss)
-		*(.glink .iplt .plt .rela*)
 	}
 }
 

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -734,21 +734,6 @@ void radix__mmu_cleanup_all(void)
 	}
 }
 
-void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base,
-				phys_addr_t first_memblock_size)
-{
-	/*
-	 * We don't currently support the first MEMBLOCK not mapping 0
-	 * physical on those processors
-	 */
-	BUG_ON(first_memblock_base != 0);
-
-	/*
-	 * Radix mode is not limited by RMA / VRMA addressing.
-	 */
-	ppc64_rma_size = ULONG_MAX;
-}
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 static void free_pte_table(pte_t *pte_start, pmd_t *pmd)
 {

arch/powerpc/mm/init_64.c

@@ -433,9 +433,16 @@ void __init mmu_early_init_devtree(void)
 	if (!(mfmsr() & MSR_HV))
 		early_check_vec5();
 
-	if (early_radix_enabled())
+	if (early_radix_enabled()) {
 		radix__early_init_devtree();
-	else
+		/*
+		 * We have finalized the translation we are going to use by now.
+		 * Radix mode is not limited by RMA / VRMA addressing.
+		 * Hence don't limit memblock allocations.
+		 */
+		ppc64_rma_size = ULONG_MAX;
+		memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
+	} else
 		hash__early_init_devtree();
 }
 #endif /* CONFIG_PPC_BOOK3S_64 */

arch/powerpc/net/bpf_jit_comp.c

@@ -475,7 +475,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		case BPF_JMP | BPF_JSET | BPF_K:
 		case BPF_JMP | BPF_JSET | BPF_X:
 			true_cond = COND_NE;
-			fallthrough;
 		cond_branch:
 			/* same targets, can avoid doing the test :) */
 			if (filter[i].jt == filter[i].jf) {

arch/powerpc/platforms/pseries/papr_scm.c

@@ -822,7 +822,7 @@ free_stats:
 	kfree(stats);
 	return rc ? rc : seq_buf_used(&s);
 }
-DEVICE_ATTR_RO(perf_stats);
+DEVICE_ATTR_ADMIN_RO(perf_stats);
 
 static ssize_t flags_show(struct device *dev,
 			  struct device_attribute *attr, char *buf)

arch/riscv/Kconfig

@@ -32,6 +32,7 @@ config RISCV
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select CLONE_BACKWARDS
+	select CLINT_TIMER if !MMU
 	select COMMON_CLK
 	select EDAC_SUPPORT
 	select GENERIC_ARCH_TOPOLOGY if SMP

arch/riscv/boot/dts/kendryte/k210.dtsi

@@ -95,10 +95,12 @@
 			#clock-cells = <1>;
 		};
 
-		clint0: interrupt-controller@2000000 {
+		clint0: clint@2000000 {
+			#interrupt-cells = <1>;
 			compatible = "riscv,clint0";
 			reg = <0x2000000 0xC000>;
-			interrupts-extended = <&cpu0_intc 3>,  <&cpu1_intc 3>;
+			interrupts-extended =  <&cpu0_intc 3 &cpu0_intc 7
+						&cpu1_intc 3 &cpu1_intc 7>;
 			clocks = <&sysctl K210_CLK_ACLK>;
 		};
 

arch/riscv/include/asm/clint.h

@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Google, Inc
+ */
+
+#ifndef _ASM_RISCV_CLINT_H
+#define _ASM_RISCV_CLINT_H
+
+#include <linux/types.h>
+#include <asm/mmio.h>
+
+#ifdef CONFIG_RISCV_M_MODE
+/*
+ * This lives in the CLINT driver, but is accessed directly by timex.h to avoid
+ * any overhead when accessing the MMIO timer.
+ *
+ * The ISA defines mtime as a 64-bit memory-mapped register that increments at
+ * a constant frequency, but it doesn't define some other constraints we depend
+ * on (most notably ordering constraints, but also some simpler stuff like the
+ * memory layout).  Thus, this is called "clint_time_val" instead of something
+ * like "riscv_mtime", to signify that these non-ISA assumptions must hold.
+ */
+extern u64 __iomem *clint_time_val;
+#endif
+
+#endif

arch/riscv/include/asm/ftrace.h

@@ -66,6 +66,13 @@ do {									\
  * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here.
  */
 #define MCOUNT_INSN_SIZE 8
+
+#ifndef __ASSEMBLY__
+struct dyn_ftrace;
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
+#define ftrace_init_nop ftrace_init_nop
+#endif
+
 #endif
 
 #endif /* _ASM_RISCV_FTRACE_H */

arch/riscv/include/asm/stackprotector.h

@@ -5,7 +5,6 @@
 
 #include <linux/random.h>
 #include <linux/version.h>
-#include <asm/timex.h>
 
 extern unsigned long __stack_chk_guard;
 
@@ -18,12 +17,9 @@ extern unsigned long __stack_chk_guard;
 static __always_inline void boot_init_stack_canary(void)
 {
 	unsigned long canary;
-	unsigned long tsc;
 
 	/* Try to get a semi random initial value. */
 	get_random_bytes(&canary, sizeof(canary));
-	tsc = get_cycles();
-	canary += tsc + (tsc << BITS_PER_LONG/2);
 	canary ^= LINUX_VERSION_CODE;
 	canary &= CANARY_MASK;
 

arch/riscv/include/asm/timex.h

@@ -10,6 +10,44 @@
 
 typedef unsigned long cycles_t;
 
+#ifdef CONFIG_RISCV_M_MODE
+
+#include <asm/clint.h>
+
+#ifdef CONFIG_64BIT
+static inline cycles_t get_cycles(void)
+{
+	return readq_relaxed(clint_time_val);
+}
+#else /* !CONFIG_64BIT */
+static inline u32 get_cycles(void)
+{
+	return readl_relaxed(((u32 *)clint_time_val));
+}
+#define get_cycles get_cycles
+
+static inline u32 get_cycles_hi(void)
+{
+	return readl_relaxed(((u32 *)clint_time_val) + 1);
+}
+#define get_cycles_hi get_cycles_hi
+#endif /* CONFIG_64BIT */
+
+/*
+ * Much like MIPS, we may not have a viable counter to use at an early point
+ * in the boot process. Unfortunately we don't have a fallback, so instead
+ * we just return 0.
+ */
+static inline unsigned long random_get_entropy(void)
+{
+	if (unlikely(clint_time_val == NULL))
+		return 0;
+	return get_cycles();
+}
+#define random_get_entropy()	random_get_entropy()
+
+#else /* CONFIG_RISCV_M_MODE */
+
 static inline cycles_t get_cycles(void)
 {
 	return csr_read(CSR_TIME);
@@ -41,6 +79,8 @@ static inline u64 get_cycles64(void)
 }
 #endif /* CONFIG_64BIT */
 
+#endif /* !CONFIG_RISCV_M_MODE */
+
 #define ARCH_HAS_READ_CURRENT_TIMER
 static inline int read_current_timer(unsigned long *timer_val)
 {

arch/riscv/kernel/ftrace.c

@@ -97,6 +97,25 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 	return __ftrace_modify_call(rec->ip, addr, false);
 }
 
+
+/*
+ * This is called early on, and isn't wrapped by
+ * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold
+ * text_mutex, which triggers a lockdep failure.  SMP isn't running so we could
+ * just directly poke the text, but it's simpler to just take the lock
+ * ourselves.
+ */
+int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
+{
+	int out;
+
+	ftrace_arch_code_modify_prepare();
+	out = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
+	ftrace_arch_code_modify_post_process();
+
+	return out;
+}
+
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	int ret = __ftrace_modify_call((unsigned long)&ftrace_call,

arch/riscv/kernel/vmlinux.lds.S

@@ -22,13 +22,11 @@ SECTIONS
 	/* Beginning of code and text segment */
 	. = LOAD_OFFSET;
 	_start = .;
-	_stext = .;
 	HEAD_TEXT_SECTION
 	. = ALIGN(PAGE_SIZE);
 
 	__init_begin = .;
 	INIT_TEXT_SECTION(PAGE_SIZE)
-	INIT_DATA_SECTION(16)
 	. = ALIGN(8);
 	__soc_early_init_table : {
 		__soc_early_init_table_start = .;
@@ -55,6 +53,7 @@ SECTIONS
 	. = ALIGN(SECTION_ALIGN);
 	.text : {
 		_text = .;
+		_stext = .;
 		TEXT_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT
@@ -67,6 +66,8 @@ SECTIONS
 		_etext = .;
 	}
 
+	INIT_DATA_SECTION(16)
+
 	/* Start of data section */
 	_sdata = .;
 	RO_DATA(SECTION_ALIGN)

arch/riscv/mm/init.c

@@ -226,12 +226,11 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 
 	ptep = &fixmap_pte[pte_index(addr)];
 
-	if (pgprot_val(prot)) {
+	if (pgprot_val(prot))
 		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, prot));
-	} else {
+	else
 		pte_clear(&init_mm, addr, ptep);
-		local_flush_tlb_page(addr);
-	}
+	local_flush_tlb_page(addr);
 }
 
 static pte_t *__init get_pte_virt(phys_addr_t pa)
@@ -516,6 +515,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 #else
 	dtb_early_va = (void *)dtb_pa;
 #endif
+	dtb_early_pa = dtb_pa;
 }
 
 static inline void setup_vm_final(void)

arch/s390/include/asm/pgtable.h

@@ -1260,26 +1260,44 @@ static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address)
 
 #define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
 
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address)
 {
-	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
-		return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
-	return (p4d_t *) pgd;
+	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+		return (p4d_t *) pgd_deref(pgd) + p4d_index(address);
+	return (p4d_t *) pgdp;
+}
+#define p4d_offset_lockless p4d_offset_lockless
+
+static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address)
+{
+	return p4d_offset_lockless(pgdp, *pgdp, address);
 }
 
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address)
 {
-	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
-		return (pud_t *) p4d_deref(*p4d) + pud_index(address);
-	return (pud_t *) p4d;
+	if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+		return (pud_t *) p4d_deref(p4d) + pud_index(address);
+	return (pud_t *) p4dp;
+}
+#define pud_offset_lockless pud_offset_lockless
+
+static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address)
+{
+	return pud_offset_lockless(p4dp, *p4dp, address);
 }
 #define pud_offset pud_offset
 
-static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address)
 {
-	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
-		return (pmd_t *) pud_deref(*pud) + pmd_index(address);
-	return (pmd_t *) pud;
+	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+		return (pmd_t *) pud_deref(pud) + pmd_index(address);
+	return (pmd_t *) pudp;
+}
+#define pmd_offset_lockless pmd_offset_lockless
+
+static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address)
+{
+	return pmd_offset_lockless(pudp, *pudp, address);
 }
 #define pmd_offset pmd_offset
 

arch/s390/kernel/entry.h

@@ -26,6 +26,7 @@ void do_protection_exception(struct pt_regs *regs);
 void do_dat_exception(struct pt_regs *regs);
 void do_secure_storage_access(struct pt_regs *regs);
 void do_non_secure_storage_access(struct pt_regs *regs);
+void do_secure_storage_violation(struct pt_regs *regs);
 
 void addressing_exception(struct pt_regs *regs);
 void data_exception(struct pt_regs *regs);

arch/s390/kernel/idle.c

@@ -39,14 +39,13 @@ void enabled_wait(void)
 	local_irq_restore(flags);
 
 	/* Account time spent with enabled wait psw loaded as idle time. */
-	/* XXX seqcount has tracepoints that require RCU */
-	write_seqcount_begin(&idle->seqcount);
+	raw_write_seqcount_begin(&idle->seqcount);
 	idle_time = idle->clock_idle_exit - idle->clock_idle_enter;
 	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
 	idle->idle_time += idle_time;
 	idle->idle_count++;
 	account_idle_time(cputime_to_nsecs(idle_time));
-	write_seqcount_end(&idle->seqcount);
+	raw_write_seqcount_end(&idle->seqcount);
 }
 NOKPROBE_SYMBOL(enabled_wait);
 

arch/s390/kernel/pgm_check.S

@@ -80,7 +80,7 @@ PGM_CHECK(do_dat_exception)		/* 3b */
 PGM_CHECK_DEFAULT			/* 3c */
 PGM_CHECK(do_secure_storage_access)	/* 3d */
 PGM_CHECK(do_non_secure_storage_access)	/* 3e */
-PGM_CHECK_DEFAULT			/* 3f */
+PGM_CHECK(do_secure_storage_violation)	/* 3f */
 PGM_CHECK(monitor_event_exception)	/* 40 */
 PGM_CHECK_DEFAULT			/* 41 */
 PGM_CHECK_DEFAULT			/* 42 */

arch/s390/kernel/setup.c

@@ -619,7 +619,7 @@ static struct notifier_block kdump_mem_nb = {
 /*
  * Make sure that the area behind memory_end is protected
  */
-static void reserve_memory_end(void)
+static void __init reserve_memory_end(void)
 {
 	if (memory_end_set)
 		memblock_reserve(memory_end, ULONG_MAX);
@@ -628,7 +628,7 @@ static void reserve_memory_end(void)
 /*
  * Make sure that oldmem, where the dump is stored, is protected
  */
-static void reserve_oldmem(void)
+static void __init reserve_oldmem(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	if (OLDMEM_BASE)
@@ -640,7 +640,7 @@ static void reserve_oldmem(void)
 /*
  * Make sure that oldmem, where the dump is stored, is protected
  */
-static void remove_oldmem(void)
+static void __init remove_oldmem(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	if (OLDMEM_BASE)

arch/s390/mm/fault.c

@@ -859,6 +859,21 @@ void do_non_secure_storage_access(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(do_non_secure_storage_access);
 
+void do_secure_storage_violation(struct pt_regs *regs)
+{
+	/*
+	 * Either KVM messed up the secure guest mapping or the same
+	 * page is mapped into multiple secure guests.
+	 *
+	 * This exception is only triggered when a guest 2 is running
+	 * and can therefore never occur in kernel context.
+	 */
+	printk_ratelimited(KERN_WARNING
+			   "Secure storage violation in task: %s, pid %d\n",
+			   current->comm, current->pid);
+	send_sig(SIGSEGV, current, 0);
+}
+
 #else
 void do_secure_storage_access(struct pt_regs *regs)
 {
@@ -869,4 +884,9 @@ void do_non_secure_storage_access(struct pt_regs *regs)
 {
 	default_trap_handler(regs);
 }
+
+void do_secure_storage_violation(struct pt_regs *regs)
+{
+	default_trap_handler(regs);
+}
 #endif

arch/s390/pci/pci.c

@@ -668,6 +668,10 @@ EXPORT_SYMBOL_GPL(zpci_enable_device);
 int zpci_disable_device(struct zpci_dev *zdev)
 {
 	zpci_dma_exit_device(zdev);
+	/*
+	 * The zPCI function may already be disabled by the platform, this is
+	 * detected in clp_disable_fh() which becomes a no-op.
+	 */
 	return clp_disable_fh(zdev);
 }
 EXPORT_SYMBOL_GPL(zpci_disable_device);

arch/s390/pci/pci_event.c

@@ -143,6 +143,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 			zpci_remove_device(zdev);
 		}
 
+		zdev->fh = ccdf->fh;
+		zpci_disable_device(zdev);
 		zdev->state = ZPCI_FN_STATE_STANDBY;
 		if (!clp_get_state(ccdf->fid, &state) &&
 		    state == ZPCI_FN_STATE_RESERVED) {

arch/sh/include/asm/smp.h

@@ -8,7 +8,6 @@
 
 #ifdef CONFIG_SMP
 
-#include <linux/spinlock.h>
 #include <linux/atomic.h>
 #include <asm/current.h>
 #include <asm/percpu.h>

arch/sh/kernel/entry-common.S

@@ -370,7 +370,6 @@ syscall_trace_entry:
 	 nop
 	cmp/eq	#-1, r0
 	bt	syscall_exit
-	mov.l	r0, @(OFF_R0,r15)	! Save return value
 	!			Reload R0-R4 from kernel stack, where the
 	!   	    	    	parent may have modified them using
 	!   	    	    	ptrace(POKEUSR).  (Note that R0-R2 are

arch/sh/kernel/ptrace_32.c

@@ -455,16 +455,11 @@ long arch_ptrace(struct task_struct *child, long request,
 
 asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 {
-	long ret = 0;
-
 	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
-	    tracehook_report_syscall_entry(regs))
-		/*
-		 * Tracing decided this syscall should not happen.
-		 * We'll return a bogus call number to get an ENOSYS
-		 * error, but leave the original number in regs->regs[0].
-		 */
-		ret = -1L;
+	    tracehook_report_syscall_entry(regs)) {
+		regs->regs[0] = -ENOSYS;
+		return -1;
+	}
 
 	if (secure_computing() == -1)
 		return -1;
@@ -475,7 +470,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 	audit_syscall_entry(regs->regs[3], regs->regs[4], regs->regs[5],
 			    regs->regs[6], regs->regs[7]);
 
-	return ret ?: regs->regs[0];
+	return 0;
 }
 
 asmlinkage void do_syscall_trace_leave(struct pt_regs *regs)

arch/x86/boot/compressed/Makefile

@@ -43,6 +43,8 @@ KBUILD_CFLAGS += -Wno-pointer-sign
 KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS += -D__DISABLE_EXPORTS
+# Disable relocation relaxation in case the link is not PIE.
+KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no)
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n

arch/x86/configs/i386_defconfig

@@ -19,6 +19,7 @@ CONFIG_CGROUP_CPUACCT=y
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_PROFILING=y
+# CONFIG_64BIT is not set
 CONFIG_SMP=y
 CONFIG_X86_GENERIC=y
 CONFIG_HPET_TIMER=y
@@ -186,7 +187,6 @@ CONFIG_DRM_I915=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set

arch/x86/configs/x86_64_defconfig

@@ -181,7 +181,6 @@ CONFIG_DRM_I915=y
 CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_TILEBLITTING=y
 CONFIG_FB_EFI=y
-CONFIG_VGACON_SOFT_SCROLLBACK=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set

arch/x86/entry/common.c

@@ -299,7 +299,7 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
 	old_regs = set_irq_regs(regs);
 
 	instrumentation_begin();
-	run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, NULL, regs);
+	run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);
 	instrumentation_begin();
 
 	set_irq_regs(old_regs);

arch/x86/entry/entry_64.S

@@ -682,6 +682,8 @@ SYM_CODE_END(.Lbad_gs)
  * rdx: Function argument (can be NULL if none)
  */
 SYM_FUNC_START(asm_call_on_stack)
+SYM_INNER_LABEL(asm_call_sysvec_on_stack, SYM_L_GLOBAL)
+SYM_INNER_LABEL(asm_call_irq_on_stack, SYM_L_GLOBAL)
 	/*
 	 * Save the frame pointer unconditionally. This allows the ORC
 	 * unwinder to handle the stack switch.

arch/x86/include/asm/acpi.h

@@ -159,8 +159,6 @@ static inline u64 x86_default_get_root_pointer(void)
 extern int x86_acpi_numa_init(void);
 #endif /* CONFIG_ACPI_NUMA */
 
-#define acpi_unlazy_tlb(x)	leave_mm(x)
-
 #ifdef CONFIG_ACPI_APEI
 static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
 {

arch/x86/include/asm/frame.h

@@ -60,12 +60,26 @@
 #define FRAME_END "pop %" _ASM_BP "\n"
 
 #ifdef CONFIG_X86_64
+
 #define ENCODE_FRAME_POINTER			\
 	"lea 1(%rsp), %rbp\n\t"
+
+static inline unsigned long encode_frame_pointer(struct pt_regs *regs)
+{
+	return (unsigned long)regs + 1;
+}
+
 #else /* !CONFIG_X86_64 */
+
 #define ENCODE_FRAME_POINTER			\
 	"movl %esp, %ebp\n\t"			\
 	"andl $0x7fffffff, %ebp\n\t"
+
+static inline unsigned long encode_frame_pointer(struct pt_regs *regs)
+{
+	return (unsigned long)regs & 0x7fffffff;
+}
+
 #endif /* CONFIG_X86_64 */
 
 #endif /* __ASSEMBLY__ */
@@ -83,6 +97,11 @@
 
 #define ENCODE_FRAME_POINTER
 
+static inline unsigned long encode_frame_pointer(struct pt_regs *regs)
+{
+	return 0;
+}
+
 #endif
 
 #define FRAME_BEGIN

arch/x86/include/asm/idtentry.h

@@ -242,7 +242,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	instrumentation_begin();					\
 	irq_enter_rcu();						\
 	kvm_set_cpu_l1tf_flush_l1d();					\
-	run_on_irqstack_cond(__##func, regs, regs);			\
+	run_sysvec_on_irqstack_cond(__##func, regs);			\
 	irq_exit_rcu();							\
 	instrumentation_end();						\
 	irqentry_exit(regs, state);					\

arch/x86/include/asm/irq_stack.h

@@ -12,20 +12,50 @@ static __always_inline bool irqstack_active(void)
 	return __this_cpu_read(irq_count) != -1;
 }
 
-void asm_call_on_stack(void *sp, void *func, void *arg);
+void asm_call_on_stack(void *sp, void (*func)(void), void *arg);
+void asm_call_sysvec_on_stack(void *sp, void (*func)(struct pt_regs *regs),
+			      struct pt_regs *regs);
+void asm_call_irq_on_stack(void *sp, void (*func)(struct irq_desc *desc),
+			   struct irq_desc *desc);
 
-static __always_inline void __run_on_irqstack(void *func, void *arg)
+static __always_inline void __run_on_irqstack(void (*func)(void))
 {
 	void *tos = __this_cpu_read(hardirq_stack_ptr);
 
 	__this_cpu_add(irq_count, 1);
-	asm_call_on_stack(tos - 8, func, arg);
+	asm_call_on_stack(tos - 8, func, NULL);
+	__this_cpu_sub(irq_count, 1);
+}
+
+static __always_inline void
+__run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs),
+			 struct pt_regs *regs)
+{
+	void *tos = __this_cpu_read(hardirq_stack_ptr);
+
+	__this_cpu_add(irq_count, 1);
+	asm_call_sysvec_on_stack(tos - 8, func, regs);
+	__this_cpu_sub(irq_count, 1);
+}
+
+static __always_inline void
+__run_irq_on_irqstack(void (*func)(struct irq_desc *desc),
+		      struct irq_desc *desc)
+{
+	void *tos = __this_cpu_read(hardirq_stack_ptr);
+
+	__this_cpu_add(irq_count, 1);
+	asm_call_irq_on_stack(tos - 8, func, desc);
 	__this_cpu_sub(irq_count, 1);
 }
 
 #else /* CONFIG_X86_64 */
 static inline bool irqstack_active(void) { return false; }
-static inline void __run_on_irqstack(void *func, void *arg) { }
+static inline void __run_on_irqstack(void (*func)(void)) { }
+static inline void __run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs),
+					    struct pt_regs *regs) { }
+static inline void __run_irq_on_irqstack(void (*func)(struct irq_desc *desc),
+					 struct irq_desc *desc) { }
 #endif /* !CONFIG_X86_64 */
 
 static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs)
@@ -37,17 +67,40 @@ static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs)
 	return !user_mode(regs) && !irqstack_active();
 }
 
-static __always_inline void run_on_irqstack_cond(void *func, void *arg,
+
+static __always_inline void run_on_irqstack_cond(void (*func)(void),
 						 struct pt_regs *regs)
 {
-	void (*__func)(void *arg) = func;
-
 	lockdep_assert_irqs_disabled();
 
 	if (irq_needs_irq_stack(regs))
-		__run_on_irqstack(__func, arg);
+		__run_on_irqstack(func);
 	else
-		__func(arg);
+		func();
+}
+
+static __always_inline void
+run_sysvec_on_irqstack_cond(void (*func)(struct pt_regs *regs),
+			    struct pt_regs *regs)
+{
+	lockdep_assert_irqs_disabled();
+
+	if (irq_needs_irq_stack(regs))
+		__run_sysvec_on_irqstack(func, regs);
+	else
+		func(regs);
+}
+
+static __always_inline void
+run_irq_on_irqstack_cond(void (*func)(struct irq_desc *desc), struct irq_desc *desc,
+			 struct pt_regs *regs)
+{
+	lockdep_assert_irqs_disabled();
+
+	if (irq_needs_irq_stack(regs))
+		__run_irq_on_irqstack(func, desc);
+	else
+		func(desc);
 }
 
 #endif

arch/x86/kernel/apic/io_apic.c

@@ -2243,6 +2243,7 @@ static inline void __init check_timer(void)
 	legacy_pic->init(0);
 	legacy_pic->make_irq(0);
 	apic_write(APIC_LVT0, APIC_DM_EXTINT);
+	legacy_pic->unmask(0);
 
 	unlock_ExtINT_logic();
 

arch/x86/kernel/cpu/mce/core.c

@@ -1904,6 +1904,8 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check;
 
 static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 {
+	bool irq_state;
+
 	WARN_ON_ONCE(user_mode(regs));
 
 	/*
@@ -1914,7 +1916,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 	    mce_check_crashing_cpu())
 		return;
 
-	nmi_enter();
+	irq_state = idtentry_enter_nmi(regs);
 	/*
 	 * The call targets are marked noinstr, but objtool can't figure
 	 * that out because it's an indirect call. Annotate it.
@@ -1925,7 +1927,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 	if (regs->flags & X86_EFLAGS_IF)
 		trace_hardirqs_on_prepare();
 	instrumentation_end();
-	nmi_exit();
+	idtentry_exit_nmi(regs, irq_state);
 }
 
 static __always_inline void exc_machine_check_user(struct pt_regs *regs)

arch/x86/kernel/irq.c

@@ -227,7 +227,7 @@ static __always_inline void handle_irq(struct irq_desc *desc,
 				       struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_X86_64))
-		run_on_irqstack_cond(desc->handle_irq, desc, regs);
+		run_irq_on_irqstack_cond(desc->handle_irq, desc, regs);
 	else
 		__handle_irq(desc, regs);
 }

arch/x86/kernel/irq_64.c

@@ -74,5 +74,5 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 
 void do_softirq_own_stack(void)
 {
-	run_on_irqstack_cond(__do_softirq, NULL, NULL);
+	run_on_irqstack_cond(__do_softirq, NULL);
 }

arch/x86/kernel/kvm.c

@@ -652,6 +652,7 @@ static void __init kvm_guest_init(void)
 	}
 
 	if (pv_tlb_flush_supported()) {
+		pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
 		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 		pr_info("KVM setup pv remote TLB flush\n");
 	}
@@ -764,14 +765,6 @@ static __init int activate_jump_labels(void)
 }
 arch_initcall(activate_jump_labels);
 
-static void kvm_free_pv_cpu_mask(void)
-{
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu)
-		free_cpumask_var(per_cpu(__pv_cpu_mask, cpu));
-}
-
 static __init int kvm_alloc_cpumask(void)
 {
 	int cpu;
@@ -790,20 +783,11 @@ static __init int kvm_alloc_cpumask(void)
 
 	if (alloc)
 		for_each_possible_cpu(cpu) {
-			if (!zalloc_cpumask_var_node(
-				per_cpu_ptr(&__pv_cpu_mask, cpu),
-				GFP_KERNEL, cpu_to_node(cpu))) {
-				goto zalloc_cpumask_fail;
-			}
+			zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu),
+				GFP_KERNEL, cpu_to_node(cpu));
 		}
 
-	apic->send_IPI_mask_allbutself = kvm_send_ipi_mask_allbutself;
-	pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others;
 	return 0;
-
-zalloc_cpumask_fail:
-	kvm_free_pv_cpu_mask();
-	return -ENOMEM;
 }
 arch_initcall(kvm_alloc_cpumask);
 

arch/x86/kernel/process.c

@@ -42,6 +42,7 @@
 #include <asm/spec-ctrl.h>
 #include <asm/io_bitmap.h>
 #include <asm/proto.h>
+#include <asm/frame.h>
 
 #include "process.h"
 
@@ -133,7 +134,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;
 
-	frame->bp = 0;
+	frame->bp = encode_frame_pointer(childregs);
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
 	p->thread.io_bitmap = NULL;

arch/x86/kvm/svm/svm.c

@@ -2183,6 +2183,12 @@ static int iret_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
+static int invd_interception(struct vcpu_svm *svm)
+{
+	/* Treat an INVD instruction as a NOP and just skip it. */
+	return kvm_skip_emulated_instruction(&svm->vcpu);
+}
+
 static int invlpg_interception(struct vcpu_svm *svm)
 {
 	if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
@@ -2774,7 +2780,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_RDPMC]			= rdpmc_interception,
 	[SVM_EXIT_CPUID]			= cpuid_interception,
 	[SVM_EXIT_IRET]                         = iret_interception,
-	[SVM_EXIT_INVD]                         = emulate_on_interception,
+	[SVM_EXIT_INVD]                         = invd_interception,
 	[SVM_EXIT_PAUSE]			= pause_interception,
 	[SVM_EXIT_HLT]				= halt_interception,
 	[SVM_EXIT_INVLPG]			= invlpg_interception,

arch/x86/kvm/vmx/vmx.c

@@ -129,6 +129,9 @@ static bool __read_mostly enable_preemption_timer = 1;
 module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
 #endif
 
+extern bool __read_mostly allow_smaller_maxphyaddr;
+module_param(allow_smaller_maxphyaddr, bool, S_IRUGO);
+
 #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD)
 #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
 #define KVM_VM_CR0_ALWAYS_ON				\
@@ -791,6 +794,18 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	 */
 	if (is_guest_mode(vcpu))
 		eb |= get_vmcs12(vcpu)->exception_bitmap;
+        else {
+		/*
+		 * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched
+		 * between guest and host.  In that case we only care about present
+		 * faults.  For vmcs02, however, PFEC_MASK and PFEC_MATCH are set in
+		 * prepare_vmcs02_rare.
+		 */
+		bool selective_pf_trap = enable_ept && (eb & (1u << PF_VECTOR));
+		int mask = selective_pf_trap ? PFERR_PRESENT_MASK : 0;
+		vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask);
+		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, mask);
+	}
 
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
@@ -4352,16 +4367,6 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 		vmx->pt_desc.guest.output_mask = 0x7F;
 		vmcs_write64(GUEST_IA32_RTIT_CTL, 0);
 	}
-
-	/*
-	 * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched
-	 * between guest and host.  In that case we only care about present
-	 * faults.
-	 */
-	if (enable_ept) {
-		vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, PFERR_PRESENT_MASK);
-		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, PFERR_PRESENT_MASK);
-	}
 }
 
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -4803,6 +4808,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 			 * EPT will cause page fault only if we need to
 			 * detect illegal GPAs.
 			 */
+			WARN_ON_ONCE(!allow_smaller_maxphyaddr);
 			kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code);
 			return 1;
 		} else
@@ -5331,7 +5337,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	 * would also use advanced VM-exit information for EPT violations to
 	 * reconstruct the page fault error code.
 	 */
-	if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa)))
+	if (unlikely(allow_smaller_maxphyaddr && kvm_mmu_is_illegal_gpa(vcpu, gpa)))
 		return kvm_emulate_instruction(vcpu, 0);
 
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
@@ -8305,11 +8311,12 @@ static int __init vmx_init(void)
 	vmx_check_vmcs12_offsets();
 
 	/*
-	 * Intel processors don't have problems with
-	 * GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable
-	 * it for VMX by default
+	 * Shadow paging doesn't have a (further) performance penalty
+	 * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it
+	 * by default
 	 */
-	allow_smaller_maxphyaddr = true;
+	if (!enable_ept)
+		allow_smaller_maxphyaddr = true;
 
 	return 0;
 }

arch/x86/kvm/vmx/vmx.h

@@ -552,7 +552,10 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
 
 static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
 {
-	return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
+	if (!enable_ept)
+		return true;
+
+	return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
 }
 
 void dump_vmcs(void);

arch/x86/kvm/x86.c

@@ -188,7 +188,7 @@ static struct kvm_shared_msrs __percpu *shared_msrs;
 u64 __read_mostly host_efer;
 EXPORT_SYMBOL_GPL(host_efer);
 
-bool __read_mostly allow_smaller_maxphyaddr;
+bool __read_mostly allow_smaller_maxphyaddr = 0;
 EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
 
 static u64 __read_mostly host_xss;
@@ -976,6 +976,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
 				   X86_CR4_SMEP;
+	unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
 
 	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
@@ -1003,7 +1004,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (kvm_x86_ops.set_cr4(vcpu, cr4))
 		return 1;
 
-	if (((cr4 ^ old_cr4) & pdptr_bits) ||
+	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
@@ -3221,9 +3222,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_POWER_CTL:
 		msr_info->data = vcpu->arch.msr_ia32_power_ctl;
 		break;
-	case MSR_IA32_TSC:
-		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+	case MSR_IA32_TSC: {
+		/*
+		 * Intel SDM states that MSR_IA32_TSC read adds the TSC offset
+		 * even when not intercepted. AMD manual doesn't explicitly
+		 * state this but appears to behave the same.
+		 *
+		 * On userspace reads and writes, however, we unconditionally
+		 * operate L1's TSC value to ensure backwards-compatible
+		 * behavior for migration.
+		 */
+		u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset :
+							    vcpu->arch.tsc_offset;
+
+		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset;
 		break;
+	}
 	case MSR_MTRRcap:
 	case 0x200 ... 0x2ff:
 		return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);

arch/x86/lib/usercopy_64.c

@@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
 	 */
 	if (size < 8) {
 		if (!IS_ALIGNED(dest, 4) || size != 4)
-			clean_cache_range(dst, 1);
+			clean_cache_range(dst, size);
 	} else {
 		if (!IS_ALIGNED(dest, 8)) {
 			dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);

block/blk-mq.c

@@ -1412,6 +1412,11 @@ out:
 
 	hctx->dispatched[queued_to_index(queued)]++;
 
+	/* If we didn't flush the entire list, we could have told the driver
+	 * there was more coming, but that turned out to be a lie.
+	 */
+	if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued)
+		q->mq_ops->commit_rqs(hctx);
 	/*
 	 * Any items that need requeuing? Stuff them into hctx->dispatch,
 	 * that is where we will continue on next queue run.
@@ -1425,14 +1430,6 @@ out:
 
 		blk_mq_release_budgets(q, nr_budgets);
 
-		/*
-		 * If we didn't flush the entire list, we could have told
-		 * the driver there was more coming, but that turned out to
-		 * be a lie.
-		 */
-		if (q->mq_ops->commit_rqs && queued)
-			q->mq_ops->commit_rqs(hctx);
-
 		spin_lock(&hctx->lock);
 		list_splice_tail_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
@@ -2079,6 +2076,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list)
 {
 	int queued = 0;
+	int errors = 0;
 
 	while (!list_empty(list)) {
 		blk_status_t ret;
@@ -2095,6 +2093,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 				break;
 			}
 			blk_mq_end_request(rq, ret);
+			errors++;
 		} else
 			queued++;
 	}
@@ -2104,7 +2103,8 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 	 * the driver there was more coming, but that turned out to
 	 * be a lie.
 	 */
-	if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs && queued)
+	if ((!list_empty(list) || errors) &&
+	     hctx->queue->mq_ops->commit_rqs && queued)
 		hctx->queue->mq_ops->commit_rqs(hctx);
 }
 

block/blk-settings.c

@@ -801,6 +801,52 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
 
+/**
+ * blk_queue_set_zoned - configure a disk queue zoned model.
+ * @disk:	the gendisk of the queue to configure
+ * @model:	the zoned model to set
+ *
+ * Set the zoned model of the request queue of @disk according to @model.
+ * When @model is BLK_ZONED_HM (host managed), this should be called only
+ * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option).
+ * If @model specifies BLK_ZONED_HA (host aware), the effective model used
+ * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions
+ * on the disk.
+ */
+void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
+{
+	switch (model) {
+	case BLK_ZONED_HM:
+		/*
+		 * Host managed devices are supported only if
+		 * CONFIG_BLK_DEV_ZONED is enabled.
+		 */
+		WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
+		break;
+	case BLK_ZONED_HA:
+		/*
+		 * Host aware devices can be treated either as regular block
+		 * devices (similar to drive managed devices) or as zoned block
+		 * devices to take advantage of the zone command set, similarly
+		 * to host managed devices. We try the latter if there are no
+		 * partitions and zoned block device support is enabled, else
+		 * we do nothing special as far as the block layer is concerned.
+		 */
+		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
+		    disk_has_partitions(disk))
+			model = BLK_ZONED_NONE;
+		break;
+	case BLK_ZONED_NONE:
+	default:
+		if (WARN_ON_ONCE(model != BLK_ZONED_NONE))
+			model = BLK_ZONED_NONE;
+		break;
+	}
+
+	disk->queue->limits.zoned = model;
+}
+EXPORT_SYMBOL_GPL(blk_queue_set_zoned);
+
 static int __init blk_settings_init(void)
 {
 	blk_max_low_pfn = max_low_pfn - 1;