Linux 5.10-rc3

-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAl+oiOgeHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGKBQIAJw6oad/FA7j9OO2
 dMoaXb8UaBehGWgW2rdfWrFPV5v0DBnp/GkdRpLoZIjV3W4mBfnog7bIa4Eswlxo
 Y8sZxo5/3JlgJQUkHvzR1TYk5z61lHkUw9Kj/cCyx6YdbjSl19AfFsnhQVVMuyp9
 TXL2c7hxkHlw8eBGrymVu0Ip7Zq0x8O2g+8nQpmRcvaR6SBuSHdikDF/iWCtU1YW
 wpk5eWEVaAO67keZOz6b+aCFHqjFX+1dUBBuPnslucYLR73Qi16hfaU9pebe97Gb
 lX/MJ1bR9BeRp314cF0PYbm4WhKjRLudHOFJH8x3dj/BiYNrFK3SJGLiiTwsrAZ8
 kytU0Xs=
 =Ke/D
 -----END PGP SIGNATURE-----

Merge v5.10-rc3 into drm-next

We need commit f8f6ae5d07 ("mm: always have io_remap_pfn_range() set
pgprot_decrypted()") to be able to merge Jason's cleanup patch.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

Documentation/ABI/stable/sysfs-driver-dma-ioatdma

@@ -1,29 +1,29 @@
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap
 Date:           December 3, 2009
 KernelVersion:  2.6.32
 Contact:        dmaengine@vger.kernel.org
 Description:	Capabilities the DMA supports.Currently there are DMA_PQ, DMA_PQ_VAL,
 		DMA_XOR,DMA_XOR_VAL,DMA_INTERRUPT.
 
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active
 Date:           December 3, 2009
 KernelVersion:  2.6.32
 Contact:        dmaengine@vger.kernel.org
 Description:	The number of descriptors active in the ring.
 
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size
 Date:           December 3, 2009
 KernelVersion:  2.6.32
 Contact:        dmaengine@vger.kernel.org
 Description:	Descriptor ring size, total number of descriptors available.
 
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version
 Date:           December 3, 2009
 KernelVersion:  2.6.32
 Contact:        dmaengine@vger.kernel.org
 Description:	Version of ioatdma device.
 
-What:           sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce
+What:           /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce
 Date:           August 8, 2017
 KernelVersion:  4.14
 Contact:        dmaengine@vger.kernel.org

Documentation/ABI/testing/sysfs-class-net

@@ -152,7 +152,7 @@ Description:
 		When an interface is under test, it cannot be expected
 		to pass packets as normal.
 
-What:		/sys/clas/net/<iface>/duplex
+What:		/sys/class/net/<iface>/duplex
 Date:		October 2009
 KernelVersion:	2.6.33
 Contact:	netdev@vger.kernel.org

Documentation/Makefile

@@ -26,6 +26,10 @@ BUILDDIR      = $(obj)/output
 PDFLATEX      = xelatex
 LATEXOPTS     = -interaction=batchmode
 
+ifeq ($(KBUILD_VERBOSE),0)
+SPHINXOPTS    += "-q"
+endif
+
 # User-friendly check for sphinx-build
 HAVE_SPHINX := $(shell if which $(SPHINXBUILD) >/dev/null 2>&1; then echo 1; else echo 0; fi)
 

Documentation/admin-guide/LSM/SafeSetID.rst

@@ -107,7 +107,7 @@ for a UID/GID will prevent that UID/GID from obtaining auxiliary setid
 privileges, such as allowing a user to set up user namespace UID/GID mappings.
 
 Note on GID policies and setgroups()
-==================
+====================================
 In v5.9 we are adding support for limiting CAP_SETGID privileges as was done
 previously for CAP_SETUID. However, for compatibility with common sandboxing
 related code conventions in userspace, we currently allow arbitrary

Documentation/admin-guide/pm/cpuidle.rst

@@ -478,7 +478,7 @@ order to ask the hardware to enter that state.  Also, for each
 statistics of the given idle state.  That information is exposed by the kernel
 via ``sysfs``.
 
-For each CPU in the system, there is a :file:`/sys/devices/system/cpu<N>/cpuidle/`
+For each CPU in the system, there is a :file:`/sys/devices/system/cpu/cpu<N>/cpuidle/`
 directory in ``sysfs``, where the number ``<N>`` is assigned to the given
 CPU at the initialization time.  That directory contains a set of subdirectories
 called :file:`state0`, :file:`state1` and so on, up to the number of idle state
@@ -494,7 +494,7 @@ object corresponding to it, as follows:
 	residency.
 
 ``below``
-	Total number of times this idle state had been asked for, but cerainly
+	Total number of times this idle state had been asked for, but certainly
 	a deeper idle state would have been a better match for the observed idle
 	duration.
 

Documentation/admin-guide/sysctl/net.rst

@@ -300,6 +300,7 @@ Note:
       0:    0     1     2     3     4     5     6     7
   RSS hash key:
   84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
+
 netdev_tstamp_prequeue
 ----------------------
 

Documentation/arm/sunxi.rst

@@ -148,3 +148,13 @@ SunXi family
         * User Manual
 
           http://dl.linux-sunxi.org/A64/Allwinner%20A64%20User%20Manual%20v1.0.pdf
+
+      - Allwinner H6
+
+	* Datasheet
+
+	  https://linux-sunxi.org/images/5/5c/Allwinner_H6_V200_Datasheet_V1.1.pdf
+
+	* User Manual
+
+	  https://linux-sunxi.org/images/4/46/Allwinner_H6_V200_User_Manual_V1.1.pdf

Documentation/conf.py

@@ -51,7 +51,7 @@ if major >= 3:
         support for Sphinx v3.0 and above is brand new. Be prepared for
         possible issues in the generated output.
         ''')
-    if minor > 0 or patch >= 2:
+    if (major > 3) or (minor > 0 or patch >= 2):
         # Sphinx c function parser is more pedantic with regards to type
         # checking. Due to that, having macros at c:function cause problems.
         # Those needed to be scaped by using c_id_attributes[] array

Documentation/dev-tools/kasan.rst

@@ -295,11 +295,13 @@ print the number of the test and the status of the test:
 pass::
 
         ok 28 - kmalloc_double_kzfree
+
 or, if kmalloc failed::
 
         # kmalloc_large_oob_right: ASSERTION FAILED at lib/test_kasan.c:163
         Expected ptr is not null, but is
         not ok 4 - kmalloc_large_oob_right
+
 or, if a KASAN report was expected, but not found::
 
         # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629

Documentation/dev-tools/kunit/start.rst

@@ -197,7 +197,7 @@ Now add the following to ``drivers/misc/Kconfig``:
 
 	config MISC_EXAMPLE_TEST
 		bool "Test for my example"
-		depends on MISC_EXAMPLE && KUNIT
+		depends on MISC_EXAMPLE && KUNIT=y
 
 and the following to ``drivers/misc/Makefile``:
 

Documentation/dev-tools/kunit/usage.rst

@@ -561,6 +561,11 @@ Once the kernel is built and installed, a simple
 
 ...will run the tests.
 
+.. note::
+   Note that you should make sure your test depends on ``KUNIT=y`` in Kconfig
+   if the test does not support module build.  Otherwise, it will trigger
+   compile errors if ``CONFIG_KUNIT`` is ``m``.
+
 Writing new tests for other architectures
 -----------------------------------------
 

Documentation/devicetree/bindings/clock/hi6220-clock.txt

@@ -4,7 +4,7 @@ Clock control registers reside in different Hi6220 system controllers,
 please refer the following document to know more about the binding rules
 for these system controllers:
 
-Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
+Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml
 
 Required Properties:
 

Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml

@@ -32,6 +32,11 @@ description: |
                        | | vint  | bit  |  | 0 |.....|63| vintx  |
                        | +--------------+  +------------+        |
                        |                                         |
+                       |      Unmap                              |
+                       | +--------------+                        |
+  Unmapped events ---->| |   umapidx    |-------------------------> Globalevents
+                       | +--------------+                        |
+                       |                                         |
                        +-----------------------------------------+
 
   Configuration of these Intmap registers that maps global events to vint is
@@ -70,6 +75,11 @@ properties:
         - description: |
             "limit" specifies the limit for translation
 
+  ti,unmapped-event-sources:
+    $ref: /schemas/types.yaml#definitions/phandle-array
+    description:
+      Array of phandles to DMA controllers where the unmapped events originate.
+
 required:
   - compatible
   - reg

Documentation/devicetree/bindings/net/can/can-controller.yaml

@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/can-controller.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: CAN Controller Generic Binding
+
+maintainers:
+  - Marc Kleine-Budde <mkl@pengutronix.de>
+
+properties:
+  $nodename:
+    pattern: "^can(@.*)?$"
+
+additionalProperties: true
+
+...

Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml

@@ -0,0 +1,135 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/fsl,flexcan.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title:
+  Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC).
+
+maintainers:
+  - Marc Kleine-Budde <mkl@pengutronix.de>
+
+allOf:
+  - $ref: can-controller.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - enum:
+          - fsl,imx8qm-flexcan
+          - fsl,imx8mp-flexcan
+          - fsl,imx6q-flexcan
+          - fsl,imx53-flexcan
+          - fsl,imx35-flexcan
+          - fsl,imx28-flexcan
+          - fsl,imx25-flexcan
+          - fsl,p1010-flexcan
+          - fsl,vf610-flexcan
+          - fsl,ls1021ar2-flexcan
+          - fsl,lx2160ar1-flexcan
+      - items:
+          - enum:
+              - fsl,imx7d-flexcan
+              - fsl,imx6ul-flexcan
+              - fsl,imx6sx-flexcan
+          - const: fsl,imx6q-flexcan
+      - items:
+          - enum:
+              - fsl,ls1028ar1-flexcan
+          - const: fsl,lx2160ar1-flexcan
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: ipg
+      - const: per
+
+  clock-frequency:
+    description: |
+      The oscillator frequency driving the flexcan device, filled in by the
+      boot loader. This property should only be used the used operating system
+      doesn't support the clocks and clock-names property.
+
+  xceiver-supply:
+    description: Regulator that powers the CAN transceiver.
+
+  big-endian:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: |
+      This means the registers of FlexCAN controller are big endian. This is
+      optional property.i.e. if this property is not present in device tree
+      node then controller is assumed to be little endian. If this property is
+      present then controller is assumed to be big endian.
+
+  fsl,stop-mode:
+    description: |
+      Register bits of stop mode control.
+
+      The format should be as follows:
+      <gpr req_gpr req_bit>
+      gpr is the phandle to general purpose register node.
+      req_gpr is the gpr register offset of CAN stop request.
+      req_bit is the bit offset of CAN stop request.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      - description: The 'gpr' is the phandle to general purpose register node.
+      - description: The 'req_gpr' is the gpr register offset of CAN stop request.
+        maximum: 0xff
+      - description: The 'req_bit' is the bit offset of CAN stop request.
+        maximum: 0x1f
+
+  fsl,clk-source:
+    description: |
+      Select the clock source to the CAN Protocol Engine (PE). It's SoC
+      implementation dependent. Refer to RM for detailed definition. If this
+      property is not set in device tree node then driver selects clock source 1
+      by default.
+      0: clock source 0 (oscillator clock)
+      1: clock source 1 (peripheral clock)
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 1
+    minimum: 0
+    maximum: 1
+
+  wakeup-source:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      Enable CAN remote wakeup.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    can@1c000 {
+        compatible = "fsl,p1010-flexcan";
+        reg = <0x1c000 0x1000>;
+        interrupts = <48 0x2>;
+        interrupt-parent = <&mpic>;
+        clock-frequency = <200000000>;
+        fsl,clk-source = <0>;
+    };
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    can@2090000 {
+        compatible = "fsl,imx6q-flexcan";
+        reg = <0x02090000 0x4000>;
+        interrupts = <0 110 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&clks 1>, <&clks 2>;
+        clock-names = "ipg", "per";
+        fsl,stop-mode = <&gpr 0x34 28>;
+    };

Documentation/devicetree/bindings/net/can/fsl-flexcan.txt

@@ -1,57 +0,0 @@
-Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC).
-
-Required properties:
-
-- compatible : Should be "fsl,<processor>-flexcan"
-
-  where <processor> is imx8qm, imx6q, imx28, imx53, imx35, imx25, p1010,
-  vf610, ls1021ar2, lx2160ar1, ls1028ar1.
-
-  The ls1028ar1 must be followed by lx2160ar1, e.g.
-   - "fsl,ls1028ar1-flexcan", "fsl,lx2160ar1-flexcan"
-
-  An implementation should also claim any of the following compatibles
-  that it is fully backwards compatible with:
-
-  - fsl,p1010-flexcan
-
-- reg : Offset and length of the register set for this device
-- interrupts : Interrupt tuple for this device
-
-Optional properties:
-
-- clock-frequency : The oscillator frequency driving the flexcan device
-
-- xceiver-supply: Regulator that powers the CAN transceiver
-
-- big-endian: This means the registers of FlexCAN controller are big endian.
-              This is optional property.i.e. if this property is not present in
-              device tree node then controller is assumed to be little endian.
-              if this property is present then controller is assumed to be big
-              endian.
-
-- fsl,stop-mode: register bits of stop mode control, the format is
-		 <&gpr req_gpr req_bit>.
-		 gpr is the phandle to general purpose register node.
-		 req_gpr is the gpr register offset of CAN stop request.
-		 req_bit is the bit offset of CAN stop request.
-
-- fsl,clk-source: Select the clock source to the CAN Protocol Engine (PE).
-		  It's SoC Implementation dependent. Refer to RM for detailed
-		  definition. If this property is not set in device tree node
-		  then driver selects clock source 1 by default.
-		  0: clock source 0 (oscillator clock)
-		  1: clock source 1 (peripheral clock)
-
-- wakeup-source: enable CAN remote wakeup
-
-Example:
-
-	can@1c000 {
-		compatible = "fsl,p1010-flexcan";
-		reg = <0x1c000 0x1000>;
-		interrupts = <48 0x2>;
-		interrupt-parent = <&mpic>;
-		clock-frequency = <200000000>; // filled in by bootloader
-		fsl,clk-source = <0>; // select clock source 0 for PE
-	};

Documentation/filesystems/api-summary.rst

@@ -86,9 +86,6 @@ Other Functions
 .. kernel-doc:: fs/dax.c
    :export:
 
-.. kernel-doc:: fs/direct-io.c
-   :export:
-
 .. kernel-doc:: fs/libfs.c
    :export:
 

Documentation/gpu/amdgpu.rst

@@ -83,10 +83,6 @@ AMDGPU XGMI Support
 ===================
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
-   :doc: AMDGPU XGMI Support
-
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
-   :internal:
 
 AMDGPU RAS Support
 ==================
@@ -124,9 +120,6 @@ RAS VRAM Bad Pages sysfs Interface
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
    :doc: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
 
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
-   :internal:
-
 Sample Code
 -----------
 Sample code for testing error injection can be found here:

Documentation/hwmon/adm1266.rst

@@ -20,7 +20,7 @@ ADM1266 is a sequencer that features voltage readback from 17 channels via an
 integrated 12 bit SAR ADC, accessed using a PMBus interface.
 
 The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Sysfs entries

Documentation/hwmon/index.rst

@@ -132,6 +132,7 @@ Hardware Monitoring Kernel Drivers
    mcp3021
    menf21bmc
    mlxreg-fan
+   mp2975
    nct6683
    nct6775
    nct7802

Documentation/hwmon/mp2975.rst

@@ -20,6 +20,7 @@ This driver implements support for Monolithic Power Systems, Inc. (MPS)
 vendor dual-loop, digital, multi-phase controller MP2975.
 
 This device:
+
 - Supports up to two power rail.
 - Provides 8 pulse-width modulations (PWMs), and can be configured up
   to 8-phase operation for rail 1 and up to 4-phase operation for rail
@@ -32,10 +33,12 @@ This device:
   10-mV DAC, IMVP9 mode with 5-mV DAC.
 
 Device supports:
+
 - SVID interface.
 - AVSBus interface.
 
 Device complaint with:
+
 - PMBus rev 1.3 interface.
 
 Device supports direct format for reading output current, output voltage,
@@ -45,11 +48,14 @@ Device supports VID and direct formats for reading output voltage.
 The below VID modes are supported: VR12, VR13, IMVP9.
 
 The driver provides the next attributes for the current:
+
 - for current in: input, maximum alarm;
 - for current out input, maximum alarm and highest values;
 - for phase current: input and label.
-attributes.
+  attributes.
+
 The driver exports the following attributes via the 'sysfs' files, where
+
 - 'n' is number of telemetry pages (from 1 to 2);
 - 'k' is number of configured phases (from 1 to 8);
 - indexes 1, 1*n for "iin";
@@ -65,11 +71,14 @@ The driver exports the following attributes via the 'sysfs' files, where
 **curr[1-{2n+k}]_label**
 
 The driver provides the next attributes for the voltage:
+
 - for voltage in: input, high critical threshold, high critical alarm, all only
   from page 0;
 - for voltage out: input, low and high critical thresholds, low and high
   critical alarms, from pages 0 and 1;
+
 The driver exports the following attributes via the 'sysfs' files, where
+
 - 'n' is number of telemetry pages (from 1 to 2);
 - indexes 1 for "iin";
 - indexes n+1, n+2 for "vout";
@@ -87,9 +96,12 @@ The driver exports the following attributes via the 'sysfs' files, where
 **in[2-{n+1}1_lcrit_alarm**
 
 The driver provides the next attributes for the power:
+
 - for power in alarm and input.
 - for power out: highest and input.
+
 The driver exports the following attributes via the 'sysfs' files, where
+
 - 'n' is number of telemetry pages (from 1 to 2);
 - indexes 1 for "pin";
 - indexes n+1, n+2 for "pout";

Documentation/leds/index.rst

@@ -25,3 +25,4 @@ LEDs
    leds-lp5562
    leds-lp55xx
    leds-mlxcpld
+   leds-sc27xx

Documentation/locking/lockdep-design.rst

@@ -42,6 +42,7 @@ The validator tracks lock-class usage history and divides the usage into
 (4 usages * n STATEs + 1) categories:
 
 where the 4 usages can be:
+
 - 'ever held in STATE context'
 - 'ever held as readlock in STATE context'
 - 'ever held with STATE enabled'
@@ -49,10 +50,12 @@ where the 4 usages can be:
 
 where the n STATEs are coded in kernel/locking/lockdep_states.h and as of
 now they include:
+
 - hardirq
 - softirq
 
 where the last 1 category is:
+
 - 'ever used'                                       [ == !unused        ]
 
 When locking rules are violated, these usage bits are presented in the
@@ -96,9 +99,9 @@ exact case is for the lock as of the reporting time.
   +--------------+-------------+--------------+
   |              | irq enabled | irq disabled |
   +--------------+-------------+--------------+
-  | ever in irq  |      ?      |       -      |
+  | ever in irq  |     '?'     |      '-'     |
   +--------------+-------------+--------------+
-  | never in irq |      +      |       .      |
+  | never in irq |     '+'     |      '.'     |
   +--------------+-------------+--------------+
 
 The character '-' suggests irq is disabled because if otherwise the
@@ -216,7 +219,7 @@ looks like this::
        BD_MUTEX_PARTITION
   };
 
-mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
+  mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
 
 In this case the locking is done on a bdev object that is known to be a
 partition.
@@ -334,7 +337,7 @@ Troubleshooting:
 ----------------
 
 The validator tracks a maximum of MAX_LOCKDEP_KEYS number of lock classes.
-Exceeding this number will trigger the following lockdep warning:
+Exceeding this number will trigger the following lockdep warning::
 
 	(DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
 
@@ -420,7 +423,8 @@ the critical section of another reader of the same lock instance.
 
 The difference between recursive readers and non-recursive readers is because:
 recursive readers get blocked only by a write lock *holder*, while non-recursive
-readers could get blocked by a write lock *waiter*. Considering the follow example:
+readers could get blocked by a write lock *waiter*. Considering the follow
+example::
 
 	TASK A:			TASK B:
 
@@ -448,20 +452,22 @@ There are simply four block conditions:
 
 Block condition matrix, Y means the row blocks the column, and N means otherwise.
 
-	    | E | r | R |
 	+---+---+---+---+
-	  E | Y | Y | Y |
+	|   | E | r | R |
 	+---+---+---+---+
-	  r | Y | Y | N |
+	| E | Y | Y | Y |
+	+---+---+---+---+
+	| r | Y | Y | N |
+	+---+---+---+---+
+	| R | Y | Y | N |
 	+---+---+---+---+
-	  R | Y | Y | N |
 
 	(W: writers, r: non-recursive readers, R: recursive readers)
 
 
 acquired recursively. Unlike non-recursive read locks, recursive read locks
 only get blocked by current write lock *holders* other than write lock
-*waiters*, for example:
+*waiters*, for example::
 
 	TASK A:			TASK B:
 
@@ -491,7 +497,7 @@ Recursive locks don't block each other, while non-recursive locks do (this is
 even true for two non-recursive read locks). A non-recursive lock can block the
 corresponding recursive lock, and vice versa.
 
-A deadlock case with recursive locks involved is as follow:
+A deadlock case with recursive locks involved is as follow::
 
 	TASK A:			TASK B:
 
@@ -510,7 +516,7 @@ because there are 3 types for lockers, there are, in theory, 9 types of lock
 dependencies, but we can show that 4 types of lock dependencies are enough for
 deadlock detection.
 
-For each lock dependency:
+For each lock dependency::
 
 	L1 -> L2
 
@@ -525,20 +531,25 @@ same types).
 With the above combination for simplification, there are 4 types of dependency edges
 in the lockdep graph:
 
-1) -(ER)->: exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
+1) -(ER)->:
+	    exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
 	    X -> Y and X is a writer and Y is a recursive reader.
 
-2) -(EN)->: exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
+2) -(EN)->:
+	    exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
 	    X -> Y and X is a writer and Y is either a writer or non-recursive reader.
 
-3) -(SR)->: shared reader to recursive reader dependency, "X -(SR)-> Y" means
+3) -(SR)->:
+	    shared reader to recursive reader dependency, "X -(SR)-> Y" means
 	    X -> Y and X is a reader (recursive or not) and Y is a recursive reader.
 
-4) -(SN)->: shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
+4) -(SN)->:
+	    shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
 	    X -> Y and X is a reader (recursive or not) and Y is either a writer or
 	    non-recursive reader.
 
-Note that given two locks, they may have multiple dependencies between them, for example:
+Note that given two locks, they may have multiple dependencies between them,
+for example::
 
 	TASK A:
 
@@ -592,11 +603,11 @@ circles that won't cause deadlocks.
 
 Proof for sufficiency (Lemma 1):
 
-Let's say we have a strong circle:
+Let's say we have a strong circle::
 
 	L1 -> L2 ... -> Ln -> L1
 
-, which means we have dependencies:
+, which means we have dependencies::
 
 	L1 -> L2
 	L2 -> L3
@@ -633,7 +644,7 @@ a lock held by P2, and P2 is waiting for a lock held by P3, ... and Pn is waitin
 for a lock held by P1. Let's name the lock Px is waiting as Lx, so since P1 is waiting
 for L1 and holding Ln, so we will have Ln -> L1 in the dependency graph. Similarly,
 we have L1 -> L2, L2 -> L3, ..., Ln-1 -> Ln in the dependency graph, which means we
-have a circle:
+have a circle::
 
 	Ln -> L1 -> L2 -> ... -> Ln
 

Documentation/misc-devices/index.rst

@@ -24,7 +24,6 @@ fit into other categories.
    isl29003
    lis3lv02d
    max6875
-   mic/index
    pci-endpoint-test
    spear-pcie-gadget
    uacce

Documentation/networking/devlink/ice.rst

@@ -70,6 +70,7 @@ The ``ice`` driver reports the following versions
         that both the name (as reported by ``fw.app.name``) and version are
         required to uniquely identify the package.
     * - ``fw.app.bundle_id``
+      - running
       - 0xc0000001
       - Unique identifier for the DDP package loaded in the device. Also
         referred to as the DDP Track ID. Can be used to uniquely identify

Documentation/networking/j1939.rst

@@ -10,9 +10,9 @@ Overview / What Is J1939
 SAE J1939 defines a higher layer protocol on CAN. It implements a more
 sophisticated addressing scheme and extends the maximum packet size above 8
 bytes. Several derived specifications exist, which differ from the original
-J1939 on the application level, like MilCAN A, NMEA2000 and especially
+J1939 on the application level, like MilCAN A, NMEA2000, and especially
 ISO-11783 (ISOBUS). This last one specifies the so-called ETP (Extended
-Transport Protocol) which is has been included in this implementation. This
+Transport Protocol), which has been included in this implementation. This
 results in a maximum packet size of ((2 ^ 24) - 1) * 7 bytes == 111 MiB.
 
 Specifications used
@@ -32,15 +32,15 @@ sockets, we found some reasons to justify a kernel implementation for the
 addressing and transport methods used by J1939.
 
 * **Addressing:** when a process on an ECU communicates via J1939, it should
-  not necessarily know its source address. Although at least one process per
+  not necessarily know its source address. Although, at least one process per
   ECU should know the source address. Other processes should be able to reuse
   that address. This way, address parameters for different processes
   cooperating for the same ECU, are not duplicated. This way of working is
-  closely related to the UNIX concept where programs do just one thing, and do
+  closely related to the UNIX concept, where programs do just one thing and do
   it well.
 
 * **Dynamic addressing:** Address Claiming in J1939 is time critical.
-  Furthermore data transport should be handled properly during the address
+  Furthermore, data transport should be handled properly during the address
   negotiation. Putting this functionality in the kernel eliminates it as a
   requirement for _every_ user space process that communicates via J1939. This
   results in a consistent J1939 bus with proper addressing.
@@ -58,7 +58,7 @@ Therefore, these parts are left to user space.
 
 The J1939 sockets operate on CAN network devices (see SocketCAN). Any J1939
 user space library operating on CAN raw sockets will still operate properly.
-Since such library does not communicate with the in-kernel implementation, care
+Since such a library does not communicate with the in-kernel implementation, care
 must be taken that these two do not interfere. In practice, this means they
 cannot share ECU addresses. A single ECU (or virtual ECU) address is used by
 the library exclusively, or by the in-kernel system exclusively.
@@ -77,13 +77,13 @@ is composed as follows:
 8 bits : PS (PDU Specific)
 
 In J1939-21 distinction is made between PDU1 format (where PF < 240) and PDU2
-format (where PF >= 240). Furthermore, when using PDU2 format, the PS-field
+format (where PF >= 240). Furthermore, when using the PDU2 format, the PS-field
 contains a so-called Group Extension, which is part of the PGN. When using PDU2
 format, the Group Extension is set in the PS-field.
 
 On the other hand, when using PDU1 format, the PS-field contains a so-called
 Destination Address, which is _not_ part of the PGN. When communicating a PGN
-from user space to kernel (or visa versa) and PDU2 format is used, the PS-field
+from user space to kernel (or vice versa) and PDU2 format is used, the PS-field
 of the PGN shall be set to zero. The Destination Address shall be set
 elsewhere.
 
@@ -96,15 +96,15 @@ Addressing
 
 Both static and dynamic addressing methods can be used.
 
-For static addresses, no extra checks are made by the kernel, and provided
+For static addresses, no extra checks are made by the kernel and provided
 addresses are considered right. This responsibility is for the OEM or system
 integrator.
 
 For dynamic addressing, so-called Address Claiming, extra support is foreseen
-in the kernel. In J1939 any ECU is known by it's 64-bit NAME. At the moment of
+in the kernel. In J1939 any ECU is known by its 64-bit NAME. At the moment of
 a successful address claim, the kernel keeps track of both NAME and source
 address being claimed. This serves as a base for filter schemes. By default,
-packets with a destination that is not locally, will be rejected.
+packets with a destination that is not locally will be rejected.
 
 Mixed mode packets (from a static to a dynamic address or vice versa) are
 allowed. The BSD sockets define separate API calls for getting/setting the
@@ -131,31 +131,31 @@ API Calls
 ---------
 
 On CAN, you first need to open a socket for communicating over a CAN network.
-To use J1939, #include <linux/can/j1939.h>. From there, <linux/can.h> will be
+To use J1939, ``#include <linux/can/j1939.h>``. From there, ``<linux/can.h>`` will be
 included too. To open a socket, use:
 
 .. code-block:: C
 
     s = socket(PF_CAN, SOCK_DGRAM, CAN_J1939);
 
-J1939 does use SOCK_DGRAM sockets. In the J1939 specification, connections are
+J1939 does use ``SOCK_DGRAM`` sockets. In the J1939 specification, connections are
 mentioned in the context of transport protocol sessions. These still deliver
-packets to the other end (using several CAN packets). SOCK_STREAM is not
+packets to the other end (using several CAN packets). ``SOCK_STREAM`` is not
 supported.
 
-After the successful creation of the socket, you would normally use the bind(2)
+After the successful creation of the socket, you would normally use the ``bind(2)``
-and/or connect(2) system call to bind the socket to a CAN interface.  After
+and/or ``connect(2)`` system call to bind the socket to a CAN interface. After
-binding and/or connecting the socket, you can read(2) and write(2) from/to the
+binding and/or connecting the socket, you can ``read(2)`` and ``write(2)`` from/to the
-socket or use send(2), sendto(2), sendmsg(2) and the recv*() counterpart
+socket or use ``send(2)``, ``sendto(2)``, ``sendmsg(2)`` and the ``recv*()`` counterpart
 operations on the socket as usual. There are also J1939 specific socket options
 described below.
 
-In order to send data, a bind(2) must have been successful. bind(2) assigns a
+In order to send data, a ``bind(2)`` must have been successful. ``bind(2)`` assigns a
 local address to a socket.
 
-Different from CAN is that the payload data is just the data that get send,
+Different from CAN is that the payload data is just the data that get sends,
-without it's header info. The header info is derived from the sockaddr supplied
+without its header info. The header info is derived from the sockaddr supplied
-to bind(2), connect(2), sendto(2) and recvfrom(2). A write(2) with size 4 will
+to ``bind(2)``, ``connect(2)``, ``sendto(2)`` and ``recvfrom(2)``. A ``write(2)`` with size 4 will
 result in a packet with 4 bytes.
 
 The sockaddr structure has extensions for use with J1939 as specified below:
@@ -180,47 +180,47 @@ The sockaddr structure has extensions for use with J1939 as specified below:
          } can_addr;
       }
 
-can_family & can_ifindex serve the same purpose as for other SocketCAN sockets.
+``can_family`` & ``can_ifindex`` serve the same purpose as for other SocketCAN sockets.
 
-can_addr.j1939.pgn specifies the PGN (max 0x3ffff). Individual bits are
+``can_addr.j1939.pgn`` specifies the PGN (max 0x3ffff). Individual bits are
 specified above.
 
-can_addr.j1939.name contains the 64-bit J1939 NAME.
+``can_addr.j1939.name`` contains the 64-bit J1939 NAME.
 
-can_addr.j1939.addr contains the address.
+``can_addr.j1939.addr`` contains the address.
 
-The bind(2) system call assigns the local address, i.e. the source address when
+The ``bind(2)`` system call assigns the local address, i.e. the source address when
-sending packages. If a PGN during bind(2) is set, it's used as a RX filter.
+sending packages. If a PGN during ``bind(2)`` is set, it's used as a RX filter.
 I.e. only packets with a matching PGN are received. If an ADDR or NAME is set
 it is used as a receive filter, too. It will match the destination NAME or ADDR
 of the incoming packet. The NAME filter will work only if appropriate Address
 Claiming for this name was done on the CAN bus and registered/cached by the
 kernel.
 
-On the other hand connect(2) assigns the remote address, i.e. the destination
+On the other hand ``connect(2)`` assigns the remote address, i.e. the destination
-address. The PGN from connect(2) is used as the default PGN when sending
+address. The PGN from ``connect(2)`` is used as the default PGN when sending
 packets. If ADDR or NAME is set it will be used as the default destination ADDR
-or NAME. Further a set ADDR or NAME during connect(2) is used as a receive
+or NAME. Further a set ADDR or NAME during ``connect(2)`` is used as a receive
 filter. It will match the source NAME or ADDR of the incoming packet.
 
-Both write(2) and send(2) will send a packet with local address from bind(2) and
+Both ``write(2)`` and ``send(2)`` will send a packet with local address from ``bind(2)`` and the
-the remote address from connect(2). Use sendto(2) to overwrite the destination
+remote address from ``connect(2)``. Use ``sendto(2)`` to overwrite the destination
 address.
 
-If can_addr.j1939.name is set (!= 0) the NAME is looked up by the kernel and
+If ``can_addr.j1939.name`` is set (!= 0) the NAME is looked up by the kernel and
-the corresponding ADDR is used. If can_addr.j1939.name is not set (== 0),
+the corresponding ADDR is used. If ``can_addr.j1939.name`` is not set (== 0),
-can_addr.j1939.addr is used.
+``can_addr.j1939.addr`` is used.
 
 When creating a socket, reasonable defaults are set. Some options can be
-modified with setsockopt(2) & getsockopt(2).
+modified with ``setsockopt(2)`` & ``getsockopt(2)``.
 
 RX path related options:
 
-- SO_J1939_FILTER - configure array of filters
+- ``SO_J1939_FILTER`` - configure array of filters
-- SO_J1939_PROMISC - disable filters set by bind(2) and connect(2)
+- ``SO_J1939_PROMISC`` - disable filters set by ``bind(2)`` and ``connect(2)``
 
 By default no broadcast packets can be send or received. To enable sending or
-receiving broadcast packets use the socket option SO_BROADCAST:
+receiving broadcast packets use the socket option ``SO_BROADCAST``:
 
 .. code-block:: C
 
@@ -261,26 +261,26 @@ The following diagram illustrates the RX path:
      +---------------------------+
 
 TX path related options:
-SO_J1939_SEND_PRIO - change default send priority for the socket
+``SO_J1939_SEND_PRIO`` - change default send priority for the socket
 
 Message Flags during send() and Related System Calls
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-send(2), sendto(2) and sendmsg(2) take a 'flags' argument. Currently
+``send(2)``, ``sendto(2)`` and ``sendmsg(2)`` take a 'flags' argument. Currently
 supported flags are:
 
-* MSG_DONTWAIT, i.e. non-blocking operation.
+* ``MSG_DONTWAIT``, i.e. non-blocking operation.
 
 recvmsg(2)
 ^^^^^^^^^^
 
-In most cases recvmsg(2) is needed if you want to extract more information than
+In most cases ``recvmsg(2)`` is needed if you want to extract more information than
-recvfrom(2) can provide. For example package priority and timestamp. The
+``recvfrom(2)`` can provide. For example package priority and timestamp. The
 Destination Address, name and packet priority (if applicable) are attached to
-the msghdr in the recvmsg(2) call. They can be extracted using cmsg(3) macros,
+the msghdr in the ``recvmsg(2)`` call. They can be extracted using ``cmsg(3)`` macros,
-with cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR,
+with ``cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR``,
-SCM_J1939_DEST_NAME or SCM_J1939_PRIO. The returned data is a uint8_t for
+``SCM_J1939_DEST_NAME`` or ``SCM_J1939_PRIO``. The returned data is a ``uint8_t`` for
-priority and dst_addr, and uint64_t for dst_name.
+``priority`` and ``dst_addr``, and ``uint64_t`` for ``dst_name``.
 
 .. code-block:: C
 
@@ -305,12 +305,12 @@ Dynamic Addressing
 
 Distinction has to be made between using the claimed address and doing an
 address claim. To use an already claimed address, one has to fill in the
-j1939.name member and provide it to bind(2). If the name had claimed an address
+``j1939.name`` member and provide it to ``bind(2)``. If the name had claimed an address
 earlier, all further messages being sent will use that address. And the
-j1939.addr member will be ignored.
+``j1939.addr`` member will be ignored.
 
 An exception on this is PGN 0x0ee00. This is the "Address Claim/Cannot Claim
-Address" message and the kernel will use the j1939.addr member for that PGN if
+Address" message and the kernel will use the ``j1939.addr`` member for that PGN if
 necessary.
 
 To claim an address following code example can be used:
@@ -371,12 +371,12 @@ NAME can send packets.
 
 If another ECU claims the address, the kernel will mark the NAME-SA expired.
 No socket bound to the NAME can send packets (other than address claims). To
-claim another address, some socket bound to NAME, must bind(2) again, but with
+claim another address, some socket bound to NAME, must ``bind(2)`` again, but with
-only j1939.addr changed to the new SA, and must then send a valid address claim
+only ``j1939.addr`` changed to the new SA, and must then send a valid address claim
 packet. This restarts the state machine in the kernel (and any other
 participant on the bus) for this NAME.
 
-can-utils also include the jacd tool, so it can be used as code example or as
+``can-utils`` also include the ``j1939acd`` tool, so it can be used as code example or as
 default Address Claiming daemon.
 
 Send Examples
@@ -403,8 +403,8 @@ Bind:
 
 	bind(sock, (struct sockaddr *)&baddr, sizeof(baddr));
 
-Now, the socket 'sock' is bound to the SA 0x20. Since no connect(2) was called,
+Now, the socket 'sock' is bound to the SA 0x20. Since no ``connect(2)`` was called,
-at this point we can use only sendto(2) or sendmsg(2).
+at this point we can use only ``sendto(2)`` or ``sendmsg(2)``.
 
 Send:
 
@@ -414,8 +414,8 @@ Send:
 		.can_family = AF_CAN,
 		.can_addr.j1939 = {
 			.name = J1939_NO_NAME;
-			.pgn = 0x30,
+			.addr = 0x30,
-			.addr = 0x12300,
+			.pgn = 0x12300,
 		},
 	};
 

Documentation/networking/statistics.rst

@@ -175,5 +175,4 @@ The following structures are internal to the kernel, their members are
 translated to netlink attributes when dumped. Drivers must not overwrite
 the statistics they don't report with 0.
 
-.. kernel-doc:: include/linux/ethtool.h
+- ethtool_pause_stats()
-    :identifiers: ethtool_pause_stats

Documentation/sphinx/automarkup.py

@@ -15,6 +15,14 @@ else:
 import re
 from itertools import chain
 
+#
+# Python 2 lacks re.ASCII...
+#
+try:
+    ascii_p3 = re.ASCII
+except AttributeError:
+    ascii_p3 = 0
+
 #
 # Regex nastiness.  Of course.
 # Try to identify "function()" that's not already marked up some
@@ -22,22 +30,22 @@ from itertools import chain
 # :c:func: block (i.e. ":c:func:`mmap()`s" flakes out), so the last
 # bit tries to restrict matches to things that won't create trouble.
 #
-RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=re.ASCII)
+RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=ascii_p3)
 
 #
 # Sphinx 2 uses the same :c:type role for struct, union, enum and typedef
 #
 RE_generic_type = re.compile(r'\b(struct|union|enum|typedef)\s+([a-zA-Z_]\w+)',
-                             flags=re.ASCII)
+                             flags=ascii_p3)
 
 #
 # Sphinx 3 uses a different C role for each one of struct, union, enum and
 # typedef
 #
-RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
+RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
-RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
+RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
-RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
+RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
-RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
+RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
 
 #
 # Detects a reference to a documentation page of the form Documentation/... with

Documentation/userspace-api/index.rst

@@ -22,6 +22,7 @@ place where this information is gathered.
    spec_ctrl
    accelerators/ocxl
    ioctl/index
+   iommu
    media/index
 
 .. only::  subproject and html

MAINTAINERS

@@ -978,7 +978,7 @@ M:	Michael Hennerich <Michael.Hennerich@analog.com>
 L:	linux-iio@vger.kernel.org
 S:	Supported
 W:	http://ez.analog.com/community/linux-device-drivers
-F:	Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.txt
+F:	Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml
 F:	drivers/iio/adc/ad7768-1.c
 
 ANALOG DEVICES INC AD7780 DRIVER
@@ -3857,7 +3857,7 @@ M:	Roger Quadros <rogerq@ti.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git
-F:	Documentation/devicetree/bindings/usb/cdns-usb3.txt
+F:	Documentation/devicetree/bindings/usb/cdns,usb3.yaml
 F:	drivers/usb/cdns3/
 
 CADET FM/AM RADIO RECEIVER DRIVER
@@ -7923,7 +7923,7 @@ HISILICON LPC BUS DRIVER
 M:	john.garry@huawei.com
 S:	Maintained
 W:	http://www.hisilicon.com
-F:	Documentation/devicetree/bindings/arm/hisilicon/hisilicon-low-pin-count.txt
+F:	Documentation/devicetree/bindings/arm/hisilicon/low-pin-count.yaml
 F:	drivers/bus/hisi_lpc.c
 
 HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3)
@@ -11170,7 +11170,7 @@ F:	Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
 F:	drivers/input/touchscreen/melfas_mip4.c
 
 MELLANOX BLUEFIELD I2C DRIVER
-M:	Khalil Blaiech <kblaiech@mellanox.com>
+M:	Khalil Blaiech <kblaiech@nvidia.com>
 L:	linux-i2c@vger.kernel.org
 S:	Supported
 F:	drivers/i2c/busses/i2c-mlxbf.c
@@ -14534,6 +14534,14 @@ F:	Documentation/devicetree/bindings/mailbox/qcom-ipcc.yaml
 F:	drivers/mailbox/qcom-ipcc.c
 F:	include/dt-bindings/mailbox/qcom-ipcc.h
 
+QUALCOMM IPQ4019 VQMMC REGULATOR DRIVER
+M:	Robert Marko <robert.marko@sartura.hr>
+M:	Luka Perkov <luka.perkov@sartura.hr>
+L:	linux-arm-msm@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/regulator/vqmmc-ipq4019-regulator.yaml
+F:	drivers/regulator/vqmmc-ipq4019-regulator.c
+
 QUALCOMM RMNET DRIVER
 M:	Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
 M:	Sean Tranchetti <stranche@codeaurora.org>
@@ -14889,7 +14897,6 @@ RENESAS ETHERNET DRIVERS
 R:	Sergei Shtylyov <sergei.shtylyov@gmail.com>
 L:	netdev@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
-F:	Documentation/devicetree/bindings/net/renesas,*.txt
 F:	Documentation/devicetree/bindings/net/renesas,*.yaml
 F:	drivers/net/ethernet/renesas/
 F:	include/linux/sh_eth.h
@@ -18090,7 +18097,7 @@ M:	Yu Chen <chenyu56@huawei.com>
 M:	Binghui Wang <wangbinghui@hisilicon.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/phy/phy-hi3660-usb3.txt
+F:	Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml
 F:	drivers/phy/hisilicon/phy-hi3660-usb3.c
 
 USB ISP116X DRIVER

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*

arch/arc/kernel/head.S

@@ -67,7 +67,22 @@
 	sr	r5, [ARC_REG_LPB_CTRL]
 1:
 #endif /* CONFIG_ARC_LPB_DISABLE */
-#endif
+
+	/* On HSDK, CCMs need to remapped super early */
+#ifdef CONFIG_ARC_SOC_HSDK
+	mov	r6, 0x60000000
+	lr	r5, [ARC_REG_ICCM_BUILD]
+	breq	r5, 0, 1f
+	sr	r6, [ARC_REG_AUX_ICCM]
+1:
+	lr	r5, [ARC_REG_DCCM_BUILD]
+	breq	r5, 0, 2f
+	sr	r6, [ARC_REG_AUX_DCCM]
+2:
+#endif	/* CONFIG_ARC_SOC_HSDK */
+
+#endif	/* CONFIG_ISA_ARCV2 */
+
 	; Config DSP_CTRL properly, so kernel may use integer multiply,
 	; multiply-accumulate, and divide operations
 	DSP_EARLY_INIT

arch/arc/kernel/stacktrace.c

@@ -112,7 +112,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 		int (*consumer_fn) (unsigned int, void *), void *arg)
 {
 #ifdef CONFIG_ARC_DW2_UNWIND
-	int ret = 0;
+	int ret = 0, cnt = 0;
 	unsigned int address;
 	struct unwind_frame_info frame_info;
 
@@ -132,6 +132,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
 			break;
 
 		frame_info.regs.r63 = frame_info.regs.r31;
+
+		if (cnt++ > 128) {
+			printk("unwinder looping too long, aborting !\n");
+			return 0;
+		}
 	}
 
 	return address;		/* return the last address it saw */

arch/arc/plat-hsdk/platform.c

@@ -17,22 +17,6 @@ int arc_hsdk_axi_dmac_coherent __section(".data") = 0;
 
 #define ARC_CCM_UNUSED_ADDR	0x60000000
 
-static void __init hsdk_init_per_cpu(unsigned int cpu)
-{
-	/*
-	 * By default ICCM is mapped to 0x7z while this area is used for
-	 * kernel virtual mappings, so move it to currently unused area.
-	 */
-	if (cpuinfo_arc700[cpu].iccm.sz)
-		write_aux_reg(ARC_REG_AUX_ICCM, ARC_CCM_UNUSED_ADDR);
-
-	/*
-	 * By default DCCM is mapped to 0x8z while this area is used by kernel,
-	 * so move it to currently unused area.
-	 */
-	if (cpuinfo_arc700[cpu].dccm.sz)
-		write_aux_reg(ARC_REG_AUX_DCCM, ARC_CCM_UNUSED_ADDR);
-}
 
 #define ARC_PERIPHERAL_BASE	0xf0000000
 #define CREG_BASE		(ARC_PERIPHERAL_BASE + 0x1000)
@@ -339,5 +323,4 @@ static const char *hsdk_compat[] __initconst = {
 MACHINE_START(SIMULATION, "hsdk")
 	.dt_compat	= hsdk_compat,
 	.init_early     = hsdk_init_early,
-	.init_per_cpu	= hsdk_init_per_cpu,
 MACHINE_END

arch/arm/mm/init.c

@@ -354,8 +354,8 @@ static void __init free_highpages(void)
 	/* set highmem page free */
 	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
 				&range_start, &range_end, NULL) {
-		unsigned long start = PHYS_PFN(range_start);
+		unsigned long start = PFN_UP(range_start);
-		unsigned long end = PHYS_PFN(range_end);
+		unsigned long end = PFN_DOWN(range_end);
 
 		/* Ignore complete lowmem entries */
 		if (end <= max_low)

arch/arm64/Kconfig

@@ -1002,7 +1002,7 @@ config NUMA
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)"
 	range 1 10
-	default "2"
+	default "4"
 	depends on NEED_MULTIPLE_NODES
 	help
 	  Specify the maximum number of NUMA Nodes available on the target

arch/arm64/include/asm/brk-imm.h

@@ -10,6 +10,7 @@
  * #imm16 values used for BRK instruction generation
  * 0x004: for installing kprobes
  * 0x005: for installing uprobes
+ * 0x006: for kprobe software single-step
  * Allowed values for kgdb are 0x400 - 0x7ff
  * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
@@ -19,6 +20,7 @@
  */
 #define KPROBES_BRK_IMM			0x004
 #define UPROBES_BRK_IMM			0x005
+#define KPROBES_BRK_SS_IMM		0x006
 #define FAULT_BRK_IMM			0x100
 #define KGDB_DYN_DBG_BRK_IMM		0x400
 #define KGDB_COMPILED_DBG_BRK_IMM	0x401

arch/arm64/include/asm/debug-monitors.h

@@ -53,6 +53,7 @@
 
 /* kprobes BRK opcodes with ESR encoding  */
 #define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5))
+#define BRK64_OPCODE_KPROBES_SS	(AARCH64_BREAK_MON | (KPROBES_BRK_SS_IMM << 5))
 /* uprobes BRK opcodes with ESR encoding  */
 #define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5))
 

arch/arm64/include/asm/kprobes.h

@@ -16,7 +16,7 @@
 #include <linux/percpu.h>
 
 #define __ARCH_WANT_KPROBES_INSN_SLOT
-#define MAX_INSN_SIZE			1
+#define MAX_INSN_SIZE			2
 
 #define flush_insn_slot(p)		do { } while (0)
 #define kretprobe_blacklist_size	0

arch/arm64/kernel/kexec_image.c

@@ -43,7 +43,7 @@ static void *image_load(struct kimage *image,
 	u64 flags, value;
 	bool be_image, be_kernel;
 	struct kexec_buf kbuf;
-	unsigned long text_offset;
+	unsigned long text_offset, kernel_segment_number;
 	struct kexec_segment *kernel_segment;
 	int ret;
 
@@ -88,11 +88,37 @@ static void *image_load(struct kimage *image,
 	/* Adjust kernel segment with TEXT_OFFSET */
 	kbuf.memsz += text_offset;
 
-	ret = kexec_add_buffer(&kbuf);
+	kernel_segment_number = image->nr_segments;
-	if (ret)
-		return ERR_PTR(ret);
 
-	kernel_segment = &image->segment[image->nr_segments - 1];
+	/*
+	 * The location of the kernel segment may make it impossible to satisfy
+	 * the other segment requirements, so we try repeatedly to find a
+	 * location that will work.
+	 */
+	while ((ret = kexec_add_buffer(&kbuf)) == 0) {
+		/* Try to load additional data */
+		kernel_segment = &image->segment[kernel_segment_number];
+		ret = load_other_segments(image, kernel_segment->mem,
+					  kernel_segment->memsz, initrd,
+					  initrd_len, cmdline);
+		if (!ret)
+			break;
+
+		/*
+		 * We couldn't find space for the other segments; erase the
+		 * kernel segment and try the next available hole.
+		 */
+		image->nr_segments -= 1;
+		kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+	}
+
+	if (ret) {
+		pr_err("Could not find any suitable kernel location!");
+		return ERR_PTR(ret);
+	}
+
+	kernel_segment = &image->segment[kernel_segment_number];
 	kernel_segment->mem += text_offset;
 	kernel_segment->memsz -= text_offset;
 	image->start = kernel_segment->mem;
@@ -101,12 +127,7 @@ static void *image_load(struct kimage *image,
 				kernel_segment->mem, kbuf.bufsz,
 				kernel_segment->memsz);
 
-	/* Load additional data */
+	return 0;
-	ret = load_other_segments(image,
-				kernel_segment->mem, kernel_segment->memsz,
-				initrd, initrd_len, cmdline);
-
-	return ERR_PTR(ret);
 }
 
 #ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG

arch/arm64/kernel/machine_kexec_file.c

@@ -240,6 +240,11 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
 	return ret;
 }
 
+/*
+ * Tries to add the initrd and DTB to the image. If it is not possible to find
+ * valid locations, this function will undo changes to the image and return non
+ * zero.
+ */
 int load_other_segments(struct kimage *image,
 			unsigned long kernel_load_addr,
 			unsigned long kernel_size,
@@ -248,7 +253,8 @@ int load_other_segments(struct kimage *image,
 {
 	struct kexec_buf kbuf;
 	void *headers, *dtb = NULL;
-	unsigned long headers_sz, initrd_load_addr = 0, dtb_len;
+	unsigned long headers_sz, initrd_load_addr = 0, dtb_len,
+		      orig_segments = image->nr_segments;
 	int ret = 0;
 
 	kbuf.image = image;
@@ -334,6 +340,7 @@ int load_other_segments(struct kimage *image,
 	return 0;
 
 out_err:
+	image->nr_segments = orig_segments;
 	vfree(dtb);
 	return ret;
 }

arch/arm64/kernel/probes/kprobes.c

@@ -36,25 +36,16 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 static void __kprobes
 post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
 
-static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode)
-{
-	void *addrs[1];
-	u32 insns[1];
-
-	addrs[0] = addr;
-	insns[0] = opcode;
-
-	return aarch64_insn_patch_text(addrs, insns, 1);
-}
-
 static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
 {
-	/* prepare insn slot */
+	kprobe_opcode_t *addr = p->ainsn.api.insn;
-	patch_text(p->ainsn.api.insn, p->opcode);
+	void *addrs[] = {addr, addr + 1};
+	u32 insns[] = {p->opcode, BRK64_OPCODE_KPROBES_SS};
 
-	flush_icache_range((uintptr_t) (p->ainsn.api.insn),
+	/* prepare insn slot */
-			   (uintptr_t) (p->ainsn.api.insn) +
+	aarch64_insn_patch_text(addrs, insns, 2);
-			   MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+
+	flush_icache_range((uintptr_t)addr, (uintptr_t)(addr + MAX_INSN_SIZE));
 
 	/*
 	 * Needs restoring of return address after stepping xol.
@@ -128,13 +119,18 @@ void *alloc_insn_page(void)
 /* arm kprobe: install breakpoint in text */
 void __kprobes arch_arm_kprobe(struct kprobe *p)
 {
-	patch_text(p->addr, BRK64_OPCODE_KPROBES);
+	void *addr = p->addr;
+	u32 insn = BRK64_OPCODE_KPROBES;
+
+	aarch64_insn_patch_text(&addr, &insn, 1);
 }
 
 /* disarm kprobe: remove breakpoint from text */
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-	patch_text(p->addr, p->opcode);
+	void *addr = p->addr;
+
+	aarch64_insn_patch_text(&addr, &p->opcode, 1);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
@@ -163,20 +159,15 @@ static void __kprobes set_current_kprobe(struct kprobe *p)
 }
 
 /*
- * Interrupts need to be disabled before single-step mode is set, and not
+ * Mask all of DAIF while executing the instruction out-of-line, to keep things
- * reenabled until after single-step mode ends.
+ * simple and avoid nesting exceptions. Interrupts do have to be disabled since
- * Without disabling interrupt on local CPU, there is a chance of
+ * the kprobe state is per-CPU and doesn't get migrated.
- * interrupt occurrence in the period of exception return and  start of
- * out-of-line single-step, that result in wrongly single stepping
- * into the interrupt handler.
  */
 static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
 						struct pt_regs *regs)
 {
 	kcb->saved_irqflag = regs->pstate & DAIF_MASK;
-	regs->pstate |= PSR_I_BIT;
+	regs->pstate |= DAIF_MASK;
-	/* Unmask PSTATE.D for enabling software step exceptions. */
-	regs->pstate &= ~PSR_D_BIT;
 }
 
 static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
@@ -219,10 +210,7 @@ static void __kprobes setup_singlestep(struct kprobe *p,
 		slot = (unsigned long)p->ainsn.api.insn;
 
 		set_ss_context(kcb, slot);	/* mark pending ss */
-
-		/* IRQs and single stepping do not mix well. */
 		kprobes_save_local_irqflag(kcb, regs);
-		kernel_enable_single_step(regs);
 		instruction_pointer_set(regs, slot);
 	} else {
 		/* insn simulation */
@@ -273,12 +261,8 @@ post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs)
 	}
 	/* call post handler */
 	kcb->kprobe_status = KPROBE_HIT_SSDONE;
-	if (cur->post_handler)	{
+	if (cur->post_handler)
-		/* post_handler can hit breakpoint and single step
-		 * again, so we enable D-flag for recursive exception.
-		 */
 		cur->post_handler(cur, regs, 0);
-	}
 
 	reset_current_kprobe();
 }
@@ -302,8 +286,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
 		if (!instruction_pointer(regs))
 			BUG();
 
-		kernel_disable_single_step();
-
 		if (kcb->kprobe_status == KPROBE_REENTER)
 			restore_previous_kprobe(kcb);
 		else
@@ -365,10 +347,6 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			 * pre-handler and it returned non-zero, it will
 			 * modify the execution path and no need to single
 			 * stepping. Let's just reset current kprobe and exit.
-			 *
-			 * pre_handler can hit a breakpoint and can step thru
-			 * before return, keep PSTATE D-flag enabled until
-			 * pre_handler return back.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				setup_singlestep(p, regs, kcb, 0);
@@ -399,7 +377,7 @@ kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr)
 }
 
 static int __kprobes
-kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
+kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	int retval;
@@ -409,16 +387,15 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
 
 	if (retval == DBG_HOOK_HANDLED) {
 		kprobes_restore_local_irqflag(kcb, regs);
-		kernel_disable_single_step();
-
 		post_kprobe_handler(kcb, regs);
 	}
 
 	return retval;
 }
 
-static struct step_hook kprobes_step_hook = {
+static struct break_hook kprobes_break_ss_hook = {
-	.fn = kprobe_single_step_handler,
+	.imm = KPROBES_BRK_SS_IMM,
+	.fn = kprobe_breakpoint_ss_handler,
 };
 
 static int __kprobes
@@ -486,7 +463,7 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p)
 int __init arch_init_kprobes(void)
 {
 	register_kernel_break_hook(&kprobes_break_hook);
-	register_kernel_step_hook(&kprobes_step_hook);
+	register_kernel_break_hook(&kprobes_break_ss_hook);
 
 	return 0;
 }

arch/powerpc/include/asm/nohash/32/kup-8xx.h

@@ -63,7 +63,7 @@ static inline void restore_user_access(unsigned long flags)
 static inline bool
 bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
-	return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000),
+	return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xff000000),
 		    "Bug: fault blocked by AP register !");
 }
 

arch/powerpc/include/asm/nohash/32/mmu-8xx.h

@@ -33,19 +33,18 @@
  * respectively NA for All or X for Supervisor and no access for User.
  * Then we use the APG to say whether accesses are according to Page rules or
  * "all Supervisor" rules (Access to all)
- * Therefore, we define 2 APG groups. lsb is _PMD_USER
+ * _PAGE_ACCESSED is also managed via APG. When _PAGE_ACCESSED is not set, say
- * 0 => Kernel => 01 (all accesses performed according to page definition)
+ * "all User" rules, that will lead to NA for all.
- * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
+ * Therefore, we define 4 APG groups. lsb is _PAGE_ACCESSED
- * 2-15 => Not Used
+ * 0 => Kernel => 11 (all accesses performed according as user iaw page definition)
+ * 1 => Kernel+Accessed => 01 (all accesses performed according to page definition)
+ * 2 => User => 11 (all accesses performed according as user iaw page definition)
+ * 3 => User+Accessed => 00 (all accesses performed as supervisor iaw page definition) for INIT
+ *                    => 10 (all accesses performed according to swaped page definition) for KUEP
+ * 4-15 => Not Used
  */
-#define MI_APG_INIT	0x40000000
+#define MI_APG_INIT	0xdc000000
-
+#define MI_APG_KUEP	0xde000000
-/*
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 10 (all accesses performed according to swaped page definition)
- * 2-15 => Not Used
- */
-#define MI_APG_KUEP	0x60000000
 
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MI_RPN is written, bits in
@@ -106,25 +105,9 @@
 #define MD_Ks		0x80000000	/* Should not be set */
 #define MD_Kp		0x40000000	/* Should always be set */
 
-/*
+/* See explanation above at the definition of MI_APG_INIT */
- * All pages' PP data bits are set to either 000 or 011 or 001, which means
+#define MD_APG_INIT	0xdc000000
- * respectively RW for Supervisor and no access for User, or RO for
+#define MD_APG_KUAP	0xde000000
- * Supervisor and no access for user and NA for ALL.
- * Then we use the APG to say whether accesses are according to Page rules or
- * "all Supervisor" rules (Access to all)
- * Therefore, we define 2 APG groups. lsb is _PMD_USER
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
- * 2-15 => Not Used
- */
-#define MD_APG_INIT	0x40000000
-
-/*
- * 0 => No user => 01 (all accesses performed according to page definition)
- * 1 => User => 10 (all accesses performed according to swaped page definition)
- * 2-15 => Not Used
- */
-#define MD_APG_KUAP	0x60000000
 
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MD_RPN is written, bits in

arch/powerpc/include/asm/nohash/32/pte-8xx.h

@@ -39,9 +39,9 @@
  * into the TLB.
  */
 #define _PAGE_GUARDED	0x0010	/* Copied to L1 G entry in DTLB */
-#define _PAGE_SPECIAL	0x0020	/* SW entry */
+#define _PAGE_ACCESSED	0x0020	/* Copied to L1 APG 1 entry in I/DTLB */
 #define _PAGE_EXEC	0x0040	/* Copied to PP (bit 21) in ITLB */
-#define _PAGE_ACCESSED	0x0080	/* software: page referenced */
+#define _PAGE_SPECIAL	0x0080	/* SW entry */
 
 #define _PAGE_NA	0x0200	/* Supervisor NA, User no access */
 #define _PAGE_RO	0x0600	/* Supervisor RO, User no access */
@@ -59,11 +59,12 @@
 
 #define _PMD_PRESENT	0x0001
 #define _PMD_PRESENT_MASK	_PMD_PRESENT
-#define _PMD_BAD	0x0fd0
+#define _PMD_BAD	0x0f90
 #define _PMD_PAGE_MASK	0x000c
 #define _PMD_PAGE_8M	0x000c
 #define _PMD_PAGE_512K	0x0004
-#define _PMD_USER	0x0020	/* APG 1 */
+#define _PMD_ACCESSED	0x0020	/* APG 1 */
+#define _PMD_USER	0x0040	/* APG 2 */
 
 #define _PTE_NONE_MASK	0
 

arch/powerpc/include/asm/topology.h

@@ -6,6 +6,7 @@
 
 struct device;
 struct device_node;
+struct drmem_lmb;
 
 #ifdef CONFIG_NUMA
 
@@ -61,6 +62,9 @@ static inline int early_cpu_to_node(int cpu)
 	 */
 	return (nid < 0) ? 0 : nid;
 }
+
+int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+
 #else
 
 static inline int early_cpu_to_node(int cpu) { return 0; }
@@ -84,10 +88,12 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 	return 0;
 }
 
-#endif /* CONFIG_NUMA */
+static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
+{
+	return first_online_node;
+}
 
-struct drmem_lmb;
+#endif /* CONFIG_NUMA */
-int of_drconf_to_nid_single(struct drmem_lmb *lmb);
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
 extern int find_and_online_cpu_nid(int cpu);

arch/powerpc/include/asm/uaccess.h

@@ -178,7 +178,7 @@ do {								\
  * are no aliasing issues.
  */
 #define __put_user_asm_goto(x, addr, label, op)			\
-	asm volatile goto(					\
+	asm_volatile_goto(					\
 		"1:	" op "%U1%X1 %0,%1	# put_user\n"	\
 		EX_TABLE(1b, %l2)				\
 		:						\
@@ -191,7 +191,7 @@ do {								\
 	__put_user_asm_goto(x, ptr, label, "std")
 #else /* __powerpc64__ */
 #define __put_user_asm2_goto(x, addr, label)			\
-	asm volatile goto(					\
+	asm_volatile_goto(					\
 		"1:	stw%X1 %0, %1\n"			\
 		"2:	stw%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\

arch/powerpc/kernel/eeh_cache.c

@@ -264,8 +264,9 @@ static int eeh_addr_cache_show(struct seq_file *s, void *v)
 {
 	struct pci_io_addr_range *piar;
 	struct rb_node *n;
+	unsigned long flags;
 
-	spin_lock(&pci_io_addr_cache_root.piar_lock);
+	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
 	for (n = rb_first(&pci_io_addr_cache_root.rb_root); n; n = rb_next(n)) {
 		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
 
@@ -273,7 +274,7 @@ static int eeh_addr_cache_show(struct seq_file *s, void *v)
 		       (piar->flags & IORESOURCE_IO) ? "i/o" : "mem",
 		       &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev));
 	}
-	spin_unlock(&pci_io_addr_cache_root.piar_lock);
+	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
 
 	return 0;
 }

arch/powerpc/kernel/head_40x.S

@@ -284,11 +284,7 @@ _ENTRY(saved_ksp_limit)
 
 	rlwimi	r11, r10, 22, 20, 29	/* Compute PTE address */
 	lwz	r11, 0(r11)		/* Get Linux PTE */
-#ifdef CONFIG_SWAP
 	li	r9, _PAGE_PRESENT | _PAGE_ACCESSED
-#else
-	li	r9, _PAGE_PRESENT
-#endif
 	andc.	r9, r9, r11		/* Check permission */
 	bne	5f
 
@@ -369,11 +365,7 @@ _ENTRY(saved_ksp_limit)
 
 	rlwimi	r11, r10, 22, 20, 29	/* Compute PTE address */
 	lwz	r11, 0(r11)		/* Get Linux PTE */
-#ifdef CONFIG_SWAP
 	li	r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#else
-	li	r9, _PAGE_PRESENT | _PAGE_EXEC
-#endif
 	andc.	r9, r9, r11		/* Check permission */
 	bne	5f
 

arch/powerpc/kernel/head_8xx.S

@@ -202,9 +202,7 @@ SystemCall:
 
 InstructionTLBMiss:
 	mtspr	SPRN_SPRG_SCRATCH0, r10
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
 	mtspr	SPRN_SPRG_SCRATCH1, r11
-#endif
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
@@ -224,25 +222,13 @@ InstructionTLBMiss:
 3:
 	mtcr	r11
 #endif
-#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT)
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
 	mtspr	SPRN_MD_TWC, r11
-#else
-	lwz	r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10)	/* Get level 1 entry */
-	mtspr	SPRN_MI_TWC, r10	/* Set segment attributes */
-	mtspr	SPRN_MD_TWC, r10
-#endif
 	mfspr	r10, SPRN_MD_TWC
 	lwz	r10, 0(r10)	/* Get the pte */
-#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT)
+	rlwimi	r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
 	rlwimi	r11, r10, 32 - 9, _PMD_PAGE_512K
 	mtspr	SPRN_MI_TWC, r11
-#endif
-#ifdef CONFIG_SWAP
-	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
-	and	r11, r11, r10
-	rlwimi	r10, r11, 0, _PAGE_PRESENT
-#endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 20 and 23 must be clear.
 	 * Software indicator bits 22, 24, 25, 26, and 27 must be
@@ -256,9 +242,7 @@ InstructionTLBMiss:
 
 	/* Restore registers */
 0:	mfspr	r10, SPRN_SPRG_SCRATCH0
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
 	mfspr	r11, SPRN_SPRG_SCRATCH1
-#endif
 	rfi
 	patch_site	0b, patch__itlbmiss_exit_1
 
@@ -268,9 +252,7 @@ InstructionTLBMiss:
 	addi	r10, r10, 1
 	stw	r10, (itlb_miss_counter - PAGE_OFFSET)@l(0)
 	mfspr	r10, SPRN_SPRG_SCRATCH0
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
 	mfspr	r11, SPRN_SPRG_SCRATCH1
-#endif
 	rfi
 #endif
 
@@ -297,30 +279,16 @@ DataStoreTLBMiss:
 	mfspr	r10, SPRN_MD_TWC
 	lwz	r10, 0(r10)	/* Get the pte */
 
-	/* Insert the Guarded flag into the TWC from the Linux PTE.
+	/* Insert Guarded and Accessed flags into the TWC from the Linux PTE.
 	 * It is bit 27 of both the Linux PTE and the TWC (at least
 	 * I got that right :-).  It will be better when we can put
 	 * this into the Linux pgd/pmd and load it in the operation
 	 * above.
 	 */
-	rlwimi	r11, r10, 0, _PAGE_GUARDED
+	rlwimi	r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
 	rlwimi	r11, r10, 32 - 9, _PMD_PAGE_512K
 	mtspr	SPRN_MD_TWC, r11
 
-	/* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
-	 * We also need to know if the insn is a load/store, so:
-	 * Clear _PAGE_PRESENT and load that which will
-	 * trap into DTLB Error with store bit set accordinly.
-	 */
-	/* PRESENT=0x1, ACCESSED=0x20
-	 * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
-	 * r10 = (r10 & ~PRESENT) | r11;
-	 */
-#ifdef CONFIG_SWAP
-	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
-	and	r11, r11, r10
-	rlwimi	r10, r11, 0, _PAGE_PRESENT
-#endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
@@ -711,7 +679,7 @@ initial_mmu:
 	li	r9, 4				/* up to 4 pages of 8M */
 	mtctr	r9
 	lis	r9, KERNELBASE@h		/* Create vaddr for TLB */
-	li	r10, MI_PS8MEG | MI_SVALID	/* Set 8M byte page */
+	li	r10, MI_PS8MEG | _PMD_ACCESSED | MI_SVALID
 	li	r11, MI_BOOTINIT		/* Create RPN for address 0 */
 1:
 	mtspr	SPRN_MI_CTR, r8	/* Set instruction MMU control */
@@ -775,7 +743,7 @@ _GLOBAL(mmu_pin_tlb)
 #ifdef CONFIG_PIN_TLB_TEXT
 	LOAD_REG_IMMEDIATE(r5, 28 << 8)
 	LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
-	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG)
+	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
 	LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT)
 	LOAD_REG_ADDR(r9, _sinittext)
 	li	r0, 4
@@ -797,7 +765,7 @@ _GLOBAL(mmu_pin_tlb)
 	LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM)
 #ifdef CONFIG_PIN_TLB_DATA
 	LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
-	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG)
+	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
 #ifdef CONFIG_PIN_TLB_IMMR
 	li	r0, 3
 #else
@@ -834,7 +802,7 @@ _GLOBAL(mmu_pin_tlb)
 #endif
 #ifdef CONFIG_PIN_TLB_IMMR
 	LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID)
-	LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED)
+	LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED | _PMD_ACCESSED)
 	mfspr   r8, SPRN_IMMR
 	rlwinm	r8, r8, 0, 0xfff80000
 	ori	r8, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \

arch/powerpc/kernel/head_book3s_32.S

@@ -457,11 +457,7 @@ InstructionTLBMiss:
 	cmplw	0,r1,r3
 #endif
 	mfspr	r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
 	li	r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#else
-	li	r1,_PAGE_PRESENT | _PAGE_EXEC
-#endif
 #if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
@@ -523,11 +519,7 @@ DataLoadTLBMiss:
 	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
 	li	r1, _PAGE_PRESENT | _PAGE_ACCESSED
-#else
-	li	r1, _PAGE_PRESENT
-#endif
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
@@ -603,11 +595,7 @@ DataStoreTLBMiss:
 	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
 	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
-#else
-	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT
-#endif
 	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */

arch/powerpc/kernel/smp.c

@@ -1393,13 +1393,14 @@ static void add_cpu_to_masks(int cpu)
 /* Activate a secondary processor. */
 void start_secondary(void *unused)
 {
-	unsigned int cpu = smp_processor_id();
+	unsigned int cpu = raw_smp_processor_id();
 
 	mmgrab(&init_mm);
 	current->active_mm = &init_mm;
 
 	smp_store_cpu_info(cpu);
 	set_dec(tb_ticks_per_jiffy);
+	rcu_cpu_starting(cpu);
 	preempt_disable();
 	cpu_callin_map[cpu] = 1;
 

arch/riscv/include/asm/uaccess.h

@@ -476,7 +476,7 @@ do {									\
 do {									\
 	long __kr_err;							\
 									\
-	__put_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err);	\
+	__put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err);	\
 	if (unlikely(__kr_err))						\
 		goto err_label;						\
 } while (0)

arch/riscv/kernel/ftrace.c

@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2013 Linaro Limited
  * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>

arch/riscv/kernel/head.S

@@ -35,12 +35,17 @@ ENTRY(_start)
 	.word 0
 #endif
 	.balign 8
+#ifdef CONFIG_RISCV_M_MODE
+	/* Image load offset (0MB) from start of RAM for M-mode */
+	.dword 0
+#else
 #if __riscv_xlen == 64
 	/* Image load offset(2MB) from start of RAM */
 	.dword 0x200000
 #else
 	/* Image load offset(4MB) from start of RAM */
 	.dword 0x400000
+#endif
 #endif
 	/* Effective size of kernel image */
 	.dword _end - _start

arch/riscv/kernel/vdso/.gitignore

@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 vdso.lds
 *.tmp
+vdso-syms.S

arch/riscv/kernel/vdso/Makefile

@@ -43,19 +43,14 @@ $(obj)/vdso.o: $(obj)/vdso.so
 SYSCFLAGS_vdso.so.dbg = $(c_flags)
 $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE
 	$(call if_changed,vdsold)
+SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
+	-Wl,--build-id -Wl,--hash-style=both
 
 # We also create a special relocatable object that should mirror the symbol
 # table and layout of the linked DSO. With ld --just-symbols we can then
 # refer to these symbols in the kernel code rather than hand-coded addresses.
-
+$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE
-SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
+	$(call if_changed,so2s)
-	-Wl,--build-id=sha1 -Wl,--hash-style=both
-$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE
-	$(call if_changed,vdsold)
-
-LDFLAGS_vdso-syms.o := -r --just-symbols
-$(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE
-	$(call if_changed,ld)
 
 # strip rule for the .so file
 $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -73,6 +68,11 @@ quiet_cmd_vdsold = VDSOLD  $@
                            $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
                    rm $@.tmp
 
+# Extracts symbol offsets from the VDSO, converting them into an assembly file
+# that contains the same symbols at the same offsets.
+quiet_cmd_so2s = SO2S    $@
+      cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@
+
 # install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@
       cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@

arch/riscv/kernel/vdso/so2s.sh

@@ -0,0 +1,6 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com>
+
+sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \
+| grep '^\.'

arch/riscv/mm/fault.c

@@ -86,6 +86,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	pmd_t *pmd, *pmd_k;
 	pte_t *pte_k;
 	int index;
+	unsigned long pfn;
 
 	/* User mode accesses just cause a SIGSEGV */
 	if (user_mode(regs))
@@ -100,7 +101,8 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a
 	 * of a task switch.
 	 */
 	index = pgd_index(addr);
-	pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index;
+	pfn = csr_read(CSR_SATP) & SATP_PPN;
+	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
 	pgd_k = init_mm.pgd + index;
 
 	if (!pgd_present(*pgd_k)) {

arch/riscv/mm/init.c

@@ -154,9 +154,8 @@ disable:
 
 void __init setup_bootmem(void)
 {
-	phys_addr_t mem_size = 0;
+	phys_addr_t mem_start = 0;
-	phys_addr_t total_mem = 0;
+	phys_addr_t start, end = 0;
-	phys_addr_t mem_start, start, end = 0;
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
 	u64 i;
@@ -164,21 +163,18 @@ void __init setup_bootmem(void)
 	/* Find the memory region containing the kernel */
 	for_each_mem_range(i, &start, &end) {
 		phys_addr_t size = end - start;
-		if (!total_mem)
+		if (!mem_start)
 			mem_start = start;
 		if (start <= vmlinux_start && vmlinux_end <= end)
 			BUG_ON(size == 0);
-		total_mem = total_mem + size;
 	}
 
 	/*
-	 * Remove memblock from the end of usable area to the
+	 * The maximal physical memory size is -PAGE_OFFSET.
-	 * end of region
+	 * Make sure that any memory beyond mem_start + (-PAGE_OFFSET) is removed
+	 * as it is unusable by kernel.
 	 */
-	mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET);
+	memblock_enforce_memory_limit(mem_start - PAGE_OFFSET);
-	if (mem_start + mem_size < end)
-		memblock_remove(mem_start + mem_size,
-				end - mem_start - mem_size);
 
 	/* Reserve from the start of the kernel to the end of the kernel */
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
@@ -297,6 +293,7 @@ pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
 #define NUM_EARLY_PMDS		(1UL + MAX_EARLY_MAPPING_SIZE / PGDIR_SIZE)
 #endif
 pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE);
+pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
 
 static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
 {
@@ -494,6 +491,18 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 				   load_pa + (va - PAGE_OFFSET),
 				   map_size, PAGE_KERNEL_EXEC);
 
+#ifndef __PAGETABLE_PMD_FOLDED
+	/* Setup early PMD for DTB */
+	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
+			   (uintptr_t)early_dtb_pmd, PGDIR_SIZE, PAGE_TABLE);
+	/* Create two consecutive PMD mappings for FDT early scan */
+	pa = dtb_pa & ~(PMD_SIZE - 1);
+	create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
+			   pa, PMD_SIZE, PAGE_KERNEL);
+	create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE,
+			   pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL);
+	dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1));
+#else
 	/* Create two consecutive PGD mappings for FDT early scan */
 	pa = dtb_pa & ~(PGDIR_SIZE - 1);
 	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
@@ -501,6 +510,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE,
 			   pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL);
 	dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1));
+#endif
 	dtb_early_pa = dtb_pa;
 
 	/*

arch/s390/configs/debug_defconfig

@@ -93,9 +93,10 @@ CONFIG_CLEANCACHE=y
 CONFIG_FRONTSWAP=y
 CONFIG_CMA_DEBUG=y
 CONFIG_CMA_DEBUGFS=y
+CONFIG_CMA_AREAS=7
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
@@ -378,7 +379,6 @@ CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
-# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
 # CONFIG_PCIEASPM is not set
 CONFIG_PCI_DEBUG=y
@@ -386,7 +386,7 @@ CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_DEVTMPFS=y
 CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
+CONFIG_ZRAM=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
@@ -689,6 +689,7 @@ CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_SM2=m
 CONFIG_CRYPTO_CURVE25519=m
 CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -709,7 +710,6 @@ CONFIG_CRYPTO_RMD160=m
 CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -753,6 +753,7 @@ CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_CORDIC=m
 CONFIG_CRC32_SELFTEST=y
 CONFIG_CRC4=m
@@ -829,6 +830,7 @@ CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
 CONFIG_FAULT_INJECTION=y
 CONFIG_FAILSLAB=y
 CONFIG_FAIL_PAGE_ALLOC=y
+CONFIG_FAULT_INJECTION_USERCOPY=y
 CONFIG_FAIL_MAKE_REQUEST=y
 CONFIG_FAIL_IO_TIMEOUT=y
 CONFIG_FAIL_FUTEX=y

arch/s390/configs/defconfig

@@ -87,9 +87,10 @@ CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CLEANCACHE=y
 CONFIG_FRONTSWAP=y
+CONFIG_CMA_AREAS=7
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC=y
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
@@ -371,7 +372,6 @@ CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
-# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
 # CONFIG_PCIEASPM is not set
 CONFIG_HOTPLUG_PCI=y
@@ -379,7 +379,7 @@ CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_UEVENT_HELPER=y
 CONFIG_DEVTMPFS=y
 CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
+CONFIG_ZRAM=y
 CONFIG_BLK_DEV_LOOP=m
 CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
@@ -680,6 +680,7 @@ CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_SM2=m
 CONFIG_CRYPTO_CURVE25519=m
 CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
@@ -701,7 +702,6 @@ CONFIG_CRYPTO_RMD160=m
 CONFIG_CRYPTO_RMD256=m
 CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES_TI=m
@@ -745,6 +745,7 @@ CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_CORDIC=m
 CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC4=m

arch/s390/configs/zfcpdump_defconfig

@@ -17,11 +17,11 @@ CONFIG_HZ_100=y
 # CONFIG_CHSC_SCH is not set
 # CONFIG_SCM_BUS is not set
 CONFIG_CRASH_DUMP=y
-# CONFIG_SECCOMP is not set
 # CONFIG_PFAULT is not set
 # CONFIG_S390_HYPFS_FS is not set
 # CONFIG_VIRTUALIZATION is not set
 # CONFIG_S390_GUEST is not set
+# CONFIG_SECCOMP is not set
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set

arch/s390/include/asm/pgtable.h

@@ -692,16 +692,6 @@ static inline int pud_large(pud_t pud)
 	return !!(pud_val(pud) & _REGION3_ENTRY_LARGE);
 }
 
-static inline unsigned long pud_pfn(pud_t pud)
-{
-	unsigned long origin_mask;
-
-	origin_mask = _REGION_ENTRY_ORIGIN;
-	if (pud_large(pud))
-		origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
-	return (pud_val(pud) & origin_mask) >> PAGE_SHIFT;
-}
-
 #define pmd_leaf	pmd_large
 static inline int pmd_large(pmd_t pmd)
 {
@@ -747,16 +737,6 @@ static inline int pmd_none(pmd_t pmd)
 	return pmd_val(pmd) == _SEGMENT_ENTRY_EMPTY;
 }
 
-static inline unsigned long pmd_pfn(pmd_t pmd)
-{
-	unsigned long origin_mask;
-
-	origin_mask = _SEGMENT_ENTRY_ORIGIN;
-	if (pmd_large(pmd))
-		origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE;
-	return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
-}
-
 #define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
@@ -1238,11 +1218,39 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
 #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
 #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
 
-#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
-#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
 #define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN)
 #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
 
+static inline unsigned long pmd_deref(pmd_t pmd)
+{
+	unsigned long origin_mask;
+
+	origin_mask = _SEGMENT_ENTRY_ORIGIN;
+	if (pmd_large(pmd))
+		origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE;
+	return pmd_val(pmd) & origin_mask;
+}
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+	return pmd_deref(pmd) >> PAGE_SHIFT;
+}
+
+static inline unsigned long pud_deref(pud_t pud)
+{
+	unsigned long origin_mask;
+
+	origin_mask = _REGION_ENTRY_ORIGIN;
+	if (pud_large(pud))
+		origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
+	return pud_val(pud) & origin_mask;
+}
+
+static inline unsigned long pud_pfn(pud_t pud)
+{
+	return pud_deref(pud) >> PAGE_SHIFT;
+}
+
 /*
  * The pgd_offset function *always* adds the index for the top-level
  * region/segment table. This is done to get a sequence like the

arch/s390/kernel/asm-offsets.c

@@ -61,14 +61,6 @@ int main(void)
 	BLANK();
 	OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
 	BLANK();
-	/* constants used by the vdso */
-	DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME);
-	DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC);
-	DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
-	DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
-	DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
-	DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
-	BLANK();
 	/* idle data offsets */
 	OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter);
 	OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit);

arch/s390/kernel/smp.c

@@ -855,13 +855,14 @@ void __init smp_detect_cpus(void)
 
 static void smp_init_secondary(void)
 {
-	int cpu = smp_processor_id();
+	int cpu = raw_smp_processor_id();
 
 	S390_lowcore.last_update_clock = get_tod_clock();
 	restore_access_regs(S390_lowcore.access_regs_save_area);
 	set_cpu_flag(CIF_ASCE_PRIMARY);
 	set_cpu_flag(CIF_ASCE_SECONDARY);
 	cpu_init();
+	rcu_cpu_starting(cpu);
 	preempt_disable();
 	init_cpu_timer();
 	vtime_init();

arch/s390/pci/pci_event.c

@@ -101,6 +101,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		if (ret)
 			break;
 
+		/* the PCI function will be scanned once function 0 appears */
+		if (!zdev->zbus->bus)
+			break;
+
 		pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn);
 		if (!pdev)
 			break;

arch/x86/boot/compressed/ident_map_64.c

@@ -164,6 +164,7 @@ void initialize_identity_maps(void *rmode)
 	add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);
 
 	/* Load the new page-table. */
+	sev_verify_cbit(top_level_pgt);
 	write_cr3(top_level_pgt);
 }
 

arch/x86/boot/compressed/mem_encrypt.S

@@ -68,6 +68,9 @@ SYM_FUNC_START(get_sev_encryption_bit)
 SYM_FUNC_END(get_sev_encryption_bit)
 
 	.code64
+
+#include "../../kernel/sev_verify_cbit.S"
+
 SYM_FUNC_START(set_sev_encryption_mask)
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	push	%rbp
@@ -81,6 +84,19 @@ SYM_FUNC_START(set_sev_encryption_mask)
 
 	bts	%rax, sme_me_mask(%rip)	/* Create the encryption mask */
 
+	/*
+	 * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in
+	 * get_sev_encryption_bit() because this function is 32-bit code and
+	 * shared between 64-bit and 32-bit boot path.
+	 */
+	movl	$MSR_AMD64_SEV, %ecx	/* Read the SEV MSR */
+	rdmsr
+
+	/* Store MSR value in sev_status */
+	shlq	$32, %rdx
+	orq	%rdx, %rax
+	movq	%rax, sev_status(%rip)
+
 .Lno_sev_mask:
 	movq	%rbp, %rsp		/* Restore original stack pointer */
 
@@ -97,4 +113,6 @@ SYM_FUNC_END(set_sev_encryption_mask)
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	.balign	8
 SYM_DATA(sme_me_mask,		.quad 0)
+SYM_DATA(sev_status,		.quad 0)
+SYM_DATA(sev_check_data,	.quad 0)
 #endif

arch/x86/boot/compressed/misc.h

@@ -159,4 +159,6 @@ void boot_page_fault(void);
 void boot_stage1_vc(void);
 void boot_stage2_vc(void);
 
+unsigned long sev_verify_cbit(unsigned long cr3);
+
 #endif /* BOOT_COMPRESSED_MISC_H */

arch/x86/hyperv/hv_apic.c

@@ -273,11 +273,15 @@ void __init hv_apic_init(void)
 		pr_info("Hyper-V: Using enlightened APIC (%s mode)",
 			x2apic_enabled() ? "x2apic" : "xapic");
 		/*
-		 * With x2apic, architectural x2apic MSRs are equivalent to the
+		 * When in x2apic mode, don't use the Hyper-V specific APIC
-		 * respective synthetic MSRs, so there's no need to override
+		 * accessors since the field layout in the ICR register is
-		 * the apic accessors.  The only exception is
+		 * different in x2apic mode. Furthermore, the architectural
-		 * hv_apic_eoi_write, because it benefits from lazy EOI when
+		 * x2apic MSRs function just as well as the Hyper-V
-		 * available, but it works for both xapic and x2apic modes.
+		 * synthetic APIC MSRs, so there's no benefit in having
+		 * separate Hyper-V accessors for x2apic mode. The only
+		 * exception is hv_apic_eoi_write, because it benefits from
+		 * lazy EOI when available, but the same accessor works for
+		 * both xapic and x2apic because the field layout is the same.
 		 */
 		apic_set_eoi_write(hv_apic_eoi_write);
 		if (!x2apic_enabled()) {

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -290,6 +290,9 @@ static void __init uv_stringify(int len, char *to, char *from)
 {
 	/* Relies on 'to' being NULL chars so result will be NULL terminated */
 	strncpy(to, from, len-1);
+
+	/* Trim trailing spaces */
+	(void)strim(to);
 }
 
 /* Find UV arch type entry in UVsystab */
@@ -366,7 +369,7 @@ static int __init early_get_arch_type(void)
 	return ret;
 }
 
-static int __init uv_set_system_type(char *_oem_id)
+static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id)
 {
 	/* Save OEM_ID passed from ACPI MADT */
 	uv_stringify(sizeof(oem_id), oem_id, _oem_id);
@@ -386,13 +389,23 @@ static int __init uv_set_system_type(char *_oem_id)
 			/* (Not hubless), not a UV */
 			return 0;
 
+		/* Is UV hubless system */
+		uv_hubless_system = 0x01;
+
+		/* UV5 Hubless */
+		if (strncmp(uv_archtype, "NSGI5", 5) == 0)
+			uv_hubless_system |= 0x20;
+
 		/* UV4 Hubless: CH */
-		if (strncmp(uv_archtype, "NSGI4", 5) == 0)
+		else if (strncmp(uv_archtype, "NSGI4", 5) == 0)
-			uv_hubless_system = 0x11;
+			uv_hubless_system |= 0x10;
 
 		/* UV3 Hubless: UV300/MC990X w/o hub */
 		else
-			uv_hubless_system = 0x9;
+			uv_hubless_system |= 0x8;
+
+		/* Copy APIC type */
+		uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id);
 
 		pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n",
 			oem_id, oem_table_id, uv_system_type, uv_hubless_system);
@@ -456,7 +469,7 @@ static int __init uv_acpi_madt_oem_check(char *_oem_id, char *_oem_table_id)
 	uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
 
 	/* If not UV, return. */
-	if (likely(uv_set_system_type(_oem_id) == 0))
+	if (uv_set_system_type(_oem_id, _oem_table_id) == 0)
 		return 0;
 
 	/* Save and Decode OEM Table ID */

arch/x86/kernel/cpu/bugs.c

@@ -1254,6 +1254,14 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 	return 0;
 }
 
+static bool is_spec_ib_user_controlled(void)
+{
+	return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
+		spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
+		spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
+		spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP;
+}
+
 static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
 	switch (ctrl) {
@@ -1261,16 +1269,26 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
 		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return 0;
+
 		/*
-		 * Indirect branch speculation is always disabled in strict
+		 * With strict mode for both IBPB and STIBP, the instruction
-		 * mode. It can neither be enabled if it was force-disabled
+		 * code paths avoid checking this task flag and instead,
-		 * by a  previous prctl call.
+		 * unconditionally run the instruction. However, STIBP and IBPB
+		 * are independent and either can be set to conditionally
+		 * enabled regardless of the mode of the other.
+		 *
+		 * If either is set to conditional, allow the task flag to be
+		 * updated, unless it was force-disabled by a previous prctl
+		 * call. Currently, this is possible on an AMD CPU which has the
+		 * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the
+		 * kernel is booted with 'spectre_v2_user=seccomp', then
+		 * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and
+		 * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED.
 		 */
-		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+		if (!is_spec_ib_user_controlled() ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
 		    task_spec_ib_force_disable(task))
 			return -EPERM;
+
 		task_clear_spec_ib_disable(task);
 		task_update_spec_tif(task);
 		break;
@@ -1283,10 +1301,10 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
 		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
 		    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 			return -EPERM;
-		if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+		if (!is_spec_ib_user_controlled())
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
 			return 0;
+
 		task_set_spec_ib_disable(task);
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
 			task_set_spec_ib_force_disable(task);
@@ -1351,20 +1369,17 @@ static int ib_prctl_get(struct task_struct *task)
 	if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
 	    spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
 		return PR_SPEC_ENABLE;
-	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+	else if (is_spec_ib_user_controlled()) {
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
-		return PR_SPEC_DISABLE;
-	else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
-	    spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
-	    spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) {
 		if (task_spec_ib_force_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
 		if (task_spec_ib_disable(task))
 			return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
 		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
-	} else
+	} else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+	    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+		return PR_SPEC_DISABLE;
+	else
 		return PR_SPEC_NOT_AFFECTED;
 }
 

arch/x86/kernel/head_64.S

@@ -161,6 +161,21 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 
 	/* Setup early boot stage 4-/5-level pagetables. */
 	addq	phys_base(%rip), %rax
+
+	/*
+	 * For SEV guests: Verify that the C-bit is correct. A malicious
+	 * hypervisor could lie about the C-bit position to perform a ROP
+	 * attack on the guest by writing to the unencrypted stack and wait for
+	 * the next RET instruction.
+	 * %rsi carries pointer to realmode data and is callee-clobbered. Save
+	 * and restore it.
+	 */
+	pushq	%rsi
+	movq	%rax, %rdi
+	call	sev_verify_cbit
+	popq	%rsi
+
+	/* Switch to new page-table */
 	movq	%rax, %cr3
 
 	/* Ensure I am executing from virtual addresses */
@@ -279,6 +294,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 SYM_CODE_END(secondary_startup_64)
 
 #include "verify_cpu.S"
+#include "sev_verify_cbit.S"
 
 #ifdef CONFIG_HOTPLUG_CPU
 /*

arch/x86/kernel/sev-es-shared.c

@@ -178,6 +178,32 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 		goto fail;
 	regs->dx = val >> 32;
 
+	/*
+	 * This is a VC handler and the #VC is only raised when SEV-ES is
+	 * active, which means SEV must be active too. Do sanity checks on the
+	 * CPUID results to make sure the hypervisor does not trick the kernel
+	 * into the no-sev path. This could map sensitive data unencrypted and
+	 * make it accessible to the hypervisor.
+	 *
+	 * In particular, check for:
+	 *	- Hypervisor CPUID bit
+	 *	- Availability of CPUID leaf 0x8000001f
+	 *	- SEV CPUID bit.
+	 *
+	 * The hypervisor might still report the wrong C-bit position, but this
+	 * can't be checked here.
+	 */
+
+	if ((fn == 1 && !(regs->cx & BIT(31))))
+		/* Hypervisor bit */
+		goto fail;
+	else if (fn == 0x80000000 && (regs->ax < 0x8000001f))
+		/* SEV leaf check */
+		goto fail;
+	else if ((fn == 0x8000001f && !(regs->ax & BIT(1))))
+		/* SEV bit */
+		goto fail;
+
 	/* Skip over the CPUID two-byte opcode */
 	regs->ip += 2;
 

arch/x86/kernel/sev-es.c

@@ -374,7 +374,7 @@ fault:
 	return ES_EXCEPTION;
 }
 
-static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
 					   unsigned long vaddr, phys_addr_t *paddr)
 {
 	unsigned long va = (unsigned long)vaddr;
@@ -394,15 +394,19 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
 		if (user_mode(ctxt->regs))
 			ctxt->fi.error_code |= X86_PF_USER;
 
-		return false;
+		return ES_EXCEPTION;
 	}
 
+	if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
+		/* Emulated MMIO to/from encrypted memory not supported */
+		return ES_UNSUPPORTED;
+
 	pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
 	pa |= va & ~page_level_mask(level);
 
 	*paddr = pa;
 
-	return true;
+	return ES_OK;
 }
 
 /* Include code shared with pre-decompression boot stage */
@@ -731,6 +735,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
 {
 	u64 exit_code, exit_info_1, exit_info_2;
 	unsigned long ghcb_pa = __pa(ghcb);
+	enum es_result res;
 	phys_addr_t paddr;
 	void __user *ref;
 
@@ -740,11 +745,12 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
 
 	exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
 
-	if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) {
+	res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
-		if (!read)
+	if (res != ES_OK) {
+		if (res == ES_EXCEPTION && !read)
 			ctxt->fi.error_code |= X86_PF_WRITE;
 
-		return ES_EXCEPTION;
+		return res;
 	}
 
 	exit_info_1 = paddr;

arch/x86/kernel/sev_verify_cbit.S

@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *	sev_verify_cbit.S - Code for verification of the C-bit position reported
+ *			    by the Hypervisor when running with SEV enabled.
+ *
+ *	Copyright (c) 2020  Joerg Roedel (jroedel@suse.de)
+ *
+ * sev_verify_cbit() is called before switching to a new long-mode page-table
+ * at boot.
+ *
+ * Verify that the C-bit position is correct by writing a random value to
+ * an encrypted memory location while on the current page-table. Then it
+ * switches to the new page-table to verify the memory content is still the
+ * same. After that it switches back to the current page-table and when the
+ * check succeeded it returns. If the check failed the code invalidates the
+ * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to
+ * make sure no interrupt or exception can get the CPU out of the hlt loop.
+ *
+ * New page-table pointer is expected in %rdi (first parameter)
+ *
+ */
+SYM_FUNC_START(sev_verify_cbit)
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+	/* First check if a C-bit was detected */
+	movq	sme_me_mask(%rip), %rsi
+	testq	%rsi, %rsi
+	jz	3f
+
+	/* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */
+	movq	sev_status(%rip), %rsi
+	testq	%rsi, %rsi
+	jz	3f
+
+	/* Save CR4 in %rsi */
+	movq	%cr4, %rsi
+
+	/* Disable Global Pages */
+	movq	%rsi, %rdx
+	andq	$(~X86_CR4_PGE), %rdx
+	movq	%rdx, %cr4
+
+	/*
+	 * Verified that running under SEV - now get a random value using
+	 * RDRAND. This instruction is mandatory when running as an SEV guest.
+	 *
+	 * Don't bail out of the loop if RDRAND returns errors. It is better to
+	 * prevent forward progress than to work with a non-random value here.
+	 */
+1:	rdrand	%rdx
+	jnc	1b
+
+	/* Store value to memory and keep it in %rdx */
+	movq	%rdx, sev_check_data(%rip)
+
+	/* Backup current %cr3 value to restore it later */
+	movq	%cr3, %rcx
+
+	/* Switch to new %cr3 - This might unmap the stack */
+	movq	%rdi, %cr3
+
+	/*
+	 * Compare value in %rdx with memory location. If C-bit is incorrect
+	 * this would read the encrypted data and make the check fail.
+	 */
+	cmpq	%rdx, sev_check_data(%rip)
+
+	/* Restore old %cr3 */
+	movq	%rcx, %cr3
+
+	/* Restore previous CR4 */
+	movq	%rsi, %cr4
+
+	/* Check CMPQ result */
+	je	3f
+
+	/*
+	 * The check failed, prevent any forward progress to prevent ROP
+	 * attacks, invalidate the stack and go into a hlt loop.
+	 */
+	xorq	%rsp, %rsp
+	subq	$0x1000, %rsp
+2:	hlt
+	jmp 2b
+3:
+#endif
+	/* Return page-table pointer */
+	movq	%rdi, %rax
+	ret
+SYM_FUNC_END(sev_verify_cbit)

arch/x86/lib/memcpy_64.S

@@ -16,8 +16,6 @@
  * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
  */
 
-.weak memcpy
-
 /*
  * memcpy - Copy a memory block.
  *
@@ -30,7 +28,7 @@
  * rax original destination
  */
 SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_LOCAL(memcpy)
+SYM_FUNC_START_WEAK(memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 

arch/x86/lib/memmove_64.S

@@ -24,9 +24,7 @@
  * Output:
  * rax: dest
  */
-.weak memmove
+SYM_FUNC_START_WEAK(memmove)
-
-SYM_FUNC_START_ALIAS(memmove)
 SYM_FUNC_START(__memmove)
 
 	mov %rdi, %rax

arch/x86/lib/memset_64.S

@@ -6,8 +6,6 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
-.weak memset
-
 /*
  * ISO C memset - set a memory block to a byte value. This function uses fast
  * string to get better performance than the original function. The code is
@@ -19,7 +17,7 @@
  *
  * rax   original destination
  */
-SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START_WEAK(memset)
 SYM_FUNC_START(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended

arch/x86/mm/mem_encrypt.c

@@ -39,6 +39,7 @@
  */
 u64 sme_me_mask __section(".data") = 0;
 u64 sev_status __section(".data") = 0;
+u64 sev_check_data __section(".data") = 0;
 EXPORT_SYMBOL(sme_me_mask);
 DEFINE_STATIC_KEY_FALSE(sev_enable_key);
 EXPORT_SYMBOL_GPL(sev_enable_key);

arch/xtensa/mm/init.c

@@ -89,8 +89,8 @@ static void __init free_highpages(void)
 	/* set highmem page free */
 	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
 				&range_start, &range_end, NULL) {
-		unsigned long start = PHYS_PFN(range_start);
+		unsigned long start = PFN_UP(range_start);
-		unsigned long end = PHYS_PFN(range_end);
+		unsigned long end = PFN_DOWN(range_end);
 
 		/* Ignore complete lowmem entries */
 		if (end <= max_low)

drivers/base/core.c

@@ -773,8 +773,7 @@ static void __device_link_del(struct kref *kref)
 	dev_dbg(link->consumer, "Dropping the link to %s\n",
 		dev_name(link->supplier));
 
-	if (link->flags & DL_FLAG_PM_RUNTIME)
+	pm_runtime_drop_link(link);
-		pm_runtime_drop_link(link->consumer);
 
 	list_del_rcu(&link->s_node);
 	list_del_rcu(&link->c_node);
@@ -788,8 +787,7 @@ static void __device_link_del(struct kref *kref)
 	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);
-		pm_runtime_drop_link(link->consumer);
 
 	list_del(&link->s_node);
 	list_del(&link->c_node);

drivers/base/dd.c

@@ -1117,6 +1117,8 @@ static void __device_release_driver(struct device *dev, struct device *parent)
 
 	drv = dev->driver;
 	if (drv) {
+		pm_runtime_get_sync(dev);
+
 		while (device_links_busy(dev)) {
 			__device_driver_unlock(dev, parent);
 
@@ -1128,12 +1130,11 @@ static void __device_release_driver(struct device *dev, struct device *parent)
 			 * have released the driver successfully while this one
 			 * was waiting, so check for that.
 			 */
-			if (dev->driver != drv)
+			if (dev->driver != drv) {
+				pm_runtime_put(dev);
 				return;
 			}
-
+		}
-		pm_runtime_get_sync(dev);
-		pm_runtime_clean_up_links(dev);
 
 		driver_sysfs_remove(dev);
 

drivers/base/power/runtime.c

@@ -1642,42 +1642,6 @@ void pm_runtime_remove(struct device *dev)
 	pm_runtime_reinit(dev);
 }
 
-/**
- * pm_runtime_clean_up_links - Prepare links to consumers for driver removal.
- * @dev: Device whose driver is going to be removed.
- *
- * Check links from this device to any consumers and if any of them have active
- * runtime PM references to the device, drop the usage counter of the device
- * (as many times as needed).
- *
- * Links with the DL_FLAG_MANAGED flag unset are ignored.
- *
- * Since the device is guaranteed to be runtime-active at the point this is
- * called, nothing else needs to be done here.
- *
- * Moreover, this is called after device_links_busy() has returned 'false', so
- * the status of each link is guaranteed to be DL_STATE_SUPPLIER_UNBIND and
- * therefore rpm_active can't be manipulated concurrently.
- */
-void pm_runtime_clean_up_links(struct device *dev)
-{
-	struct device_link *link;
-	int idx;
-
-	idx = device_links_read_lock();
-
-	list_for_each_entry_rcu(link, &dev->links.consumers, s_node,
-				device_links_read_lock_held()) {
-		if (!(link->flags & DL_FLAG_MANAGED))
-			continue;
-
-		while (refcount_dec_not_one(&link->rpm_active))
-			pm_runtime_put_noidle(dev);
-	}
-
-	device_links_read_unlock(idx);
-}
-
 /**
  * pm_runtime_get_suppliers - Resume and reference-count supplier devices.
  * @dev: Consumer device.
@@ -1729,7 +1693,7 @@ void pm_runtime_new_link(struct device *dev)
 	spin_unlock_irq(&dev->power.lock);
 }
 
-void pm_runtime_drop_link(struct device *dev)
+static void pm_runtime_drop_link_count(struct device *dev)
 {
 	spin_lock_irq(&dev->power.lock);
 	WARN_ON(dev->power.links_count == 0);
@@ -1737,6 +1701,25 @@ void pm_runtime_drop_link(struct device *dev)
 	spin_unlock_irq(&dev->power.lock);
 }
 
+/**
+ * pm_runtime_drop_link - Prepare for device link removal.
+ * @link: Device link going away.
+ *
+ * Drop the link count of the consumer end of @link and decrement the supplier
+ * device's runtime PM usage counter as many times as needed to drop all of the
+ * PM runtime reference to it from the consumer.
+ */
+void pm_runtime_drop_link(struct device_link *link)
+{
+	if (!(link->flags & DL_FLAG_PM_RUNTIME))
+		return;
+
+	pm_runtime_drop_link_count(link->consumer);
+
+	while (refcount_dec_not_one(&link->rpm_active))
+		pm_runtime_put(link->supplier);
+}
+
 static bool pm_runtime_need_not_resume(struct device *dev)
 {
 	return atomic_read(&dev->power.usage_count) <= 1 &&

drivers/block/null_blk.h

@@ -47,7 +47,7 @@ struct nullb_device {
 	unsigned int nr_zones_closed;
 	struct blk_zone *zones;
 	sector_t zone_size_sects;
-	spinlock_t zone_dev_lock;
+	spinlock_t zone_lock;
 	unsigned long *zone_locks;
 
 	unsigned long size; /* device size in MB */

drivers/block/null_blk_zoned.c

@@ -46,12 +46,21 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 	if (!dev->zones)
 		return -ENOMEM;
 
-	spin_lock_init(&dev->zone_dev_lock);
+	/*
+	 * With memory backing, the zone_lock spinlock needs to be temporarily
+	 * released to avoid scheduling in atomic context. To guarantee zone
+	 * information protection, use a bitmap to lock zones with
+	 * wait_on_bit_lock_io(). Sleeping on the lock is OK as memory backing
+	 * implies that the queue is marked with BLK_MQ_F_BLOCKING.
+	 */
+	spin_lock_init(&dev->zone_lock);
+	if (dev->memory_backed) {
 		dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL);
 		if (!dev->zone_locks) {
 			kvfree(dev->zones);
 			return -ENOMEM;
 		}
+	}
 
 	if (dev->zone_nr_conv >= dev->nr_zones) {
 		dev->zone_nr_conv = dev->nr_zones - 1;
@@ -137,11 +146,16 @@ void null_free_zoned_dev(struct nullb_device *dev)
 
 static inline void null_lock_zone(struct nullb_device *dev, unsigned int zno)
 {
+	if (dev->memory_backed)
 		wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE);
+	spin_lock_irq(&dev->zone_lock);
 }
 
 static inline void null_unlock_zone(struct nullb_device *dev, unsigned int zno)
 {
+	spin_unlock_irq(&dev->zone_lock);
+
+	if (dev->memory_backed)
 		clear_and_wake_up_bit(zno, dev->zone_locks);
 }
 
@@ -322,7 +336,6 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
 
 	null_lock_zone(dev, zno);
-	spin_lock(&dev->zone_dev_lock);
 
 	switch (zone->cond) {
 	case BLK_ZONE_COND_FULL:
@@ -375,9 +388,17 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
 		zone->cond = BLK_ZONE_COND_IMP_OPEN;
 
-	spin_unlock(&dev->zone_dev_lock);
+	/*
+	 * Memory backing allocation may sleep: release the zone_lock spinlock
+	 * to avoid scheduling in atomic context. Zone operation atomicity is
+	 * still guaranteed through the zone_locks bitmap.
+	 */
+	if (dev->memory_backed)
+		spin_unlock_irq(&dev->zone_lock);
 	ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
-	spin_lock(&dev->zone_dev_lock);
+	if (dev->memory_backed)
+		spin_lock_irq(&dev->zone_lock);
+
 	if (ret != BLK_STS_OK)
 		goto unlock;
 
@@ -392,7 +413,6 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 	ret = BLK_STS_OK;
 
 unlock:
-	spin_unlock(&dev->zone_dev_lock);
 	null_unlock_zone(dev, zno);
 
 	return ret;
@@ -516,9 +536,7 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
 			null_lock_zone(dev, i);
 			zone = &dev->zones[i];
 			if (zone->cond != BLK_ZONE_COND_EMPTY) {
-				spin_lock(&dev->zone_dev_lock);
 				null_reset_zone(dev, zone);
-				spin_unlock(&dev->zone_dev_lock);
 				trace_nullb_zone_op(cmd, i, zone->cond);
 			}
 			null_unlock_zone(dev, i);
@@ -530,7 +548,6 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
 	zone = &dev->zones[zone_no];
 
 	null_lock_zone(dev, zone_no);
-	spin_lock(&dev->zone_dev_lock);
 
 	switch (op) {
 	case REQ_OP_ZONE_RESET:
@@ -550,8 +567,6 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
 		break;
 	}
 
-	spin_unlock(&dev->zone_dev_lock);
-
 	if (ret == BLK_STS_OK)
 		trace_nullb_zone_op(cmd, zone_no, zone->cond);
 

drivers/char/tpm/eventlog/efi.c

@@ -41,6 +41,11 @@ int tpm_read_log_efi(struct tpm_chip *chip)
 	log_size = log_tbl->size;
 	memunmap(log_tbl);
 
+	if (!log_size) {
+		pr_warn("UEFI TPM log area empty\n");
+		return -EIO;
+	}
+
 	log_tbl = memremap(efi.tpm_log, sizeof(*log_tbl) + log_size,
 			   MEMREMAP_WB);
 	if (!log_tbl) {

drivers/char/tpm/tpm_tis.c

@@ -27,6 +27,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/kernel.h>
+#include <linux/dmi.h>
 #include "tpm.h"
 #include "tpm_tis_core.h"
 
@@ -49,8 +50,8 @@ static inline struct tpm_tis_tcg_phy *to_tpm_tis_tcg_phy(struct tpm_tis_data *da
 	return container_of(data, struct tpm_tis_tcg_phy, priv);
 }
 
-static bool interrupts = true;
+static int interrupts = -1;
-module_param(interrupts, bool, 0444);
+module_param(interrupts, int, 0444);
 MODULE_PARM_DESC(interrupts, "Enable interrupts");
 
 static bool itpm;
@@ -63,6 +64,28 @@ module_param(force, bool, 0444);
 MODULE_PARM_DESC(force, "Force device probe rather than using ACPI entry");
 #endif
 
+static int tpm_tis_disable_irq(const struct dmi_system_id *d)
+{
+	if (interrupts == -1) {
+		pr_notice("tpm_tis: %s detected: disabling interrupts.\n", d->ident);
+		interrupts = 0;
+	}
+
+	return 0;
+}
+
+static const struct dmi_system_id tpm_tis_dmi_table[] = {
+	{
+		.callback = tpm_tis_disable_irq,
+		.ident = "ThinkPad T490s",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"),
+		},
+	},
+	{}
+};
+
 #if defined(CONFIG_PNP) && defined(CONFIG_ACPI)
 static int has_hid(struct acpi_device *dev, const char *hid)
 {
@@ -192,6 +215,8 @@ static int tpm_tis_init(struct device *dev, struct tpm_info *tpm_info)
 	int irq = -1;
 	int rc;
 
+	dmi_check_system(tpm_tis_dmi_table);
+
 	rc = check_acpi_tpm2(dev);
 	if (rc)
 		return rc;

drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c

@@ -7,7 +7,7 @@
  *
  * This file add support for MD5 and SHA1/SHA224/SHA256/SHA384/SHA512.
  *
- * You could find the datasheet in Documentation/arm/sunxi/README
+ * You could find the datasheet in Documentation/arm/sunxi.rst
  */
 #include <linux/dma-mapping.h>
 #include <linux/pm_runtime.h>

drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c

@@ -7,7 +7,7 @@
  *
  * This file handle the PRNG
  *
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
  */
 #include "sun8i-ce.h"
 #include <linux/dma-mapping.h>

drivers/crypto/allwinner/sun8i-ce/sun8i-ce-trng.c

@@ -7,7 +7,7 @@
  *
  * This file handle the TRNG
  *
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
  */
 #include "sun8i-ce.h"
 #include <linux/dma-mapping.h>

drivers/gpu/drm/amd/display/include/dal_asic_id.h

@@ -217,6 +217,10 @@ enum {
 #ifndef ASICREV_IS_VANGOGH
 #define ASICREV_IS_VANGOGH(eChipRev) ((eChipRev >= VANGOGH_A0) && (eChipRev < VANGOGH_UNKNOWN))
 #endif
+#define GREEN_SARDINE_A0 0xA1
+#ifndef ASICREV_IS_GREEN_SARDINE
+#define ASICREV_IS_GREEN_SARDINE(eChipRev) ((eChipRev >= GREEN_SARDINE_A0) && (eChipRev < 0xFF))
+#endif
 
 /*
  * ASIC chip ID

drivers/gpu/drm/i915/gem/i915_gem_domain.c

@@ -508,21 +508,6 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 	if (!obj)
 		return -ENOENT;
 
-	/*
-	 * Already in the desired write domain? Nothing for us to do!
-	 *
-	 * We apply a little bit of cunning here to catch a broader set of
-	 * no-ops. If obj->write_domain is set, we must be in the same
-	 * obj->read_domains, and only that domain. Therefore, if that
-	 * obj->write_domain matches the request read_domains, we are
-	 * already in the same read/write domain and can skip the operation,
-	 * without having to further check the requested write_domain.
-	 */
-	if (READ_ONCE(obj->write_domain) == read_domains) {
-		err = 0;
-		goto out;
-	}
-
 	/*
 	 * Try to flush the object off the GPU without holding the lock.
 	 * We will repeat the flush holding the lock in the normal manner
@@ -560,6 +545,19 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 	if (err)
 		goto out;
 
+	/*
+	 * Already in the desired write domain? Nothing for us to do!
+	 *
+	 * We apply a little bit of cunning here to catch a broader set of
+	 * no-ops. If obj->write_domain is set, we must be in the same
+	 * obj->read_domains, and only that domain. Therefore, if that
+	 * obj->write_domain matches the request read_domains, we are
+	 * already in the same read/write domain and can skip the operation,
+	 * without having to further check the requested write_domain.
+	 */
+	if (READ_ONCE(obj->write_domain) == read_domains)
+		goto out_unpin;
+
 	err = i915_gem_object_lock_interruptible(obj, NULL);
 	if (err)
 		goto out_unpin;

drivers/gpu/drm/i915/gt/intel_engine.h

@@ -245,22 +245,14 @@ static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u
 }
 
 static inline u32 *
-__gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
+__gen8_emit_write_rcs(u32 *cs, u32 value, u32 offset, u32 flags0, u32 flags1)
 {
-	/* We're using qword write, offset should be aligned to 8 bytes. */
-	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
-
-	/* w/a for post sync ops following a GPGPU operation we
-	 * need a prior CS_STALL, which is emitted by the flush
-	 * following the batch.
-	 */
 	*cs++ = GFX_OP_PIPE_CONTROL(6) | flags0;
-	*cs++ = flags1 | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
+	*cs++ = flags1 | PIPE_CONTROL_QW_WRITE;
-	*cs++ = gtt_offset;
+	*cs++ = offset;
 	*cs++ = 0;
 	*cs++ = value;
-	/* We're thrashing one dword of HWS. */
+	*cs++ = 0; /* We're thrashing one extra dword. */
-	*cs++ = 0;
 
 	return cs;
 }
@@ -268,13 +260,38 @@ __gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 f
 static inline u32*
 gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 {
-	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, 0, flags);
+	/* We're using qword write, offset should be aligned to 8 bytes. */
+	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
+
+	return __gen8_emit_write_rcs(cs,
+				     value,
+				     gtt_offset,
+				     0,
+				     flags | PIPE_CONTROL_GLOBAL_GTT_IVB);
 }
 
 static inline u32*
 gen12_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
 {
-	return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, flags0, flags1);
+	/* We're using qword write, offset should be aligned to 8 bytes. */
+	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
+
+	return __gen8_emit_write_rcs(cs,
+				     value,
+				     gtt_offset,
+				     flags0,
+				     flags1 | PIPE_CONTROL_GLOBAL_GTT_IVB);
+}
+
+static inline u32 *
+__gen8_emit_flush_dw(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
+{
+	*cs++ = (MI_FLUSH_DW + 1) | flags;
+	*cs++ = gtt_offset;
+	*cs++ = 0;
+	*cs++ = value;
+
+	return cs;
 }
 
 static inline u32 *
@@ -285,12 +302,10 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 	/* Offset should be aligned to 8 bytes for both (QW/DW) write types */
 	GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
 
-	*cs++ = (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW | flags;
+	return __gen8_emit_flush_dw(cs,
-	*cs++ = gtt_offset | MI_FLUSH_DW_USE_GTT;
+				    value,
-	*cs++ = 0;
+				    gtt_offset | MI_FLUSH_DW_USE_GTT,
-	*cs++ = value;
+				    flags | MI_FLUSH_DW_OP_STOREDW);
-
-	return cs;
 }
 
 static inline void __intel_engine_reset(struct intel_engine_cs *engine,

drivers/gpu/drm/i915/gt/intel_lrc.c

@@ -3547,6 +3547,19 @@ static const struct intel_context_ops execlists_context_ops = {
 	.destroy = execlists_context_destroy,
 };
 
+static u32 hwsp_offset(const struct i915_request *rq)
+{
+	const struct intel_timeline_cacheline *cl;
+
+	/* Before the request is executed, the timeline/cachline is fixed */
+
+	cl = rcu_dereference_protected(rq->hwsp_cacheline, 1);
+	if (cl)
+		return cl->ggtt_offset;
+
+	return rcu_dereference_protected(rq->timeline, 1)->hwsp_offset;
+}
+
 static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 {
 	u32 *cs;
@@ -3569,7 +3582,7 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 	*cs++ = MI_NOOP;
 
 	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
-	*cs++ = i915_request_timeline(rq)->hwsp_offset;
+	*cs++ = hwsp_offset(rq);
 	*cs++ = 0;
 	*cs++ = rq->fence.seqno - 1;
 
@@ -4886,11 +4899,9 @@ gen8_emit_fini_breadcrumb_tail(struct i915_request *request, u32 *cs)
 	return gen8_emit_wa_tail(request, cs);
 }
 
-static u32 *emit_xcs_breadcrumb(struct i915_request *request, u32 *cs)
+static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs)
 {
-	u32 addr = i915_request_active_timeline(request)->hwsp_offset;
+	return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0);
-
-	return gen8_emit_ggtt_write(cs, request->fence.seqno, addr, 0);
 }
 
 static u32 *gen8_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
@@ -4909,7 +4920,7 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 	/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
-				      i915_request_active_timeline(request)->hwsp_offset,
+				      hwsp_offset(request),
 				      PIPE_CONTROL_FLUSH_ENABLE |
 				      PIPE_CONTROL_CS_STALL);
 
@@ -4921,7 +4932,7 @@ gen11_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
-				      i915_request_active_timeline(request)->hwsp_offset,
+				      hwsp_offset(request),
 				      PIPE_CONTROL_CS_STALL |
 				      PIPE_CONTROL_TILE_CACHE_FLUSH |
 				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
@@ -4983,7 +4994,9 @@ gen12_emit_fini_breadcrumb_tail(struct i915_request *request, u32 *cs)
 
 static u32 *gen12_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
 {
-	return gen12_emit_fini_breadcrumb_tail(rq, emit_xcs_breadcrumb(rq, cs));
+	/* XXX Stalling flush before seqno write; post-sync not */
+	cs = emit_xcs_breadcrumb(rq, __gen8_emit_flush_dw(cs, 0, 0, 0));
+	return gen12_emit_fini_breadcrumb_tail(rq, cs);
 }
 
 static u32 *
@@ -4991,7 +5004,7 @@ gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
 	cs = gen12_emit_ggtt_write_rcs(cs,
 				       request->fence.seqno,
-				       i915_request_active_timeline(request)->hwsp_offset,
+				       hwsp_offset(request),
 				       PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
 				       PIPE_CONTROL_CS_STALL |
 				       PIPE_CONTROL_TILE_CACHE_FLUSH |

drivers/gpu/drm/i915/gt/intel_timeline.c

@@ -188,9 +188,13 @@ cacheline_alloc(struct intel_timeline_hwsp *hwsp, unsigned int cacheline)
 	return cl;
 }
 
-static void cacheline_acquire(struct intel_timeline_cacheline *cl)
+static void cacheline_acquire(struct intel_timeline_cacheline *cl,
+			      u32 ggtt_offset)
 {
-	if (cl)
+	if (!cl)
+		return;
+
+	cl->ggtt_offset = ggtt_offset;
 	i915_active_acquire(&cl->active);
 }
 
@@ -340,7 +344,7 @@ int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww)
 	GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
 		 tl->fence_context, tl->hwsp_offset);
 
-	cacheline_acquire(tl->hwsp_cacheline);
+	cacheline_acquire(tl->hwsp_cacheline, tl->hwsp_offset);
 	if (atomic_fetch_inc(&tl->pin_count)) {
 		cacheline_release(tl->hwsp_cacheline);
 		__i915_vma_unpin(tl->hwsp_ggtt);
@@ -515,7 +519,7 @@ __intel_timeline_get_seqno(struct intel_timeline *tl,
 	GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
 		 tl->fence_context, tl->hwsp_offset);
 
-	cacheline_acquire(cl);
+	cacheline_acquire(cl, tl->hwsp_offset);
 	tl->hwsp_cacheline = cl;
 
 	*seqno = timeline_advance(tl);
@@ -573,9 +577,7 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 	if (err)
 		goto out;
 
-	*hwsp = i915_ggtt_offset(cl->hwsp->vma) +
+	*hwsp = cl->ggtt_offset;
-		ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) * CACHELINE_BYTES;
-
 out:
 	i915_active_release(&cl->active);
 	return err;

drivers/gpu/drm/i915/gt/intel_timeline_types.h

@@ -94,6 +94,8 @@ struct intel_timeline_cacheline {
 	struct intel_timeline_hwsp *hwsp;
 	void *vaddr;
 
+	u32 ggtt_offset;
+
 	struct rcu_head rcu;
 };
 

drivers/gpu/drm/i915/gvt/handlers.c

@@ -1489,7 +1489,8 @@ static int hws_pga_write(struct intel_vgpu *vgpu, unsigned int offset,
 	const struct intel_engine_cs *engine =
 		intel_gvt_render_mmio_to_engine(vgpu->gvt, offset);
 
-	if (!intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) {
+	if (value != 0 &&
+	    !intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) {
 		gvt_vgpu_err("write invalid HWSP address, reg:0x%x, value:0x%x\n",
 			      offset, value);
 		return -EINVAL;
@@ -1650,6 +1651,34 @@ static int edp_psr_imr_iir_write(struct intel_vgpu *vgpu,
 	return 0;
 }
 
+/**
+ * FixMe:
+ * If guest fills non-priv batch buffer on ApolloLake/Broxton as Mesa i965 did:
+ * 717e7539124d (i965: Use a WC map and memcpy for the batch instead of pwrite.)
+ * Due to the missing flush of bb filled by VM vCPU, host GPU hangs on executing
+ * these MI_BATCH_BUFFER.
+ * Temporarily workaround this by setting SNOOP bit for PAT3 used by PPGTT
+ * PML4 PTE: PAT(0) PCD(1) PWT(1).
+ * The performance is still expected to be low, will need further improvement.
+ */
+static int bxt_ppat_low_write(struct intel_vgpu *vgpu, unsigned int offset,
+			      void *p_data, unsigned int bytes)
+{
+	u64 pat =
+		GEN8_PPAT(0, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(1, 0) |
+		GEN8_PPAT(2, 0) |
+		GEN8_PPAT(3, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(4, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(5, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(6, CHV_PPAT_SNOOP) |
+		GEN8_PPAT(7, CHV_PPAT_SNOOP);
+
+	vgpu_vreg(vgpu, offset) = lower_32_bits(pat);
+
+	return 0;
+}
+
 static int guc_status_read(struct intel_vgpu *vgpu,
 			   unsigned int offset, void *p_data,
 			   unsigned int bytes)
@@ -2812,7 +2841,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write);
 
-	MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS);
+	MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS & ~D_BXT);
 	MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS);
 
 	MMIO_D(GAMTARBMODE, D_BDW_PLUS);
@@ -3139,7 +3168,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 		 NULL, NULL);
 
 	MMIO_DFH(GAMT_CHKN_BIT_REG, D_KBL | D_CFL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS);
+	MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS & ~D_BXT);
 
 	return 0;
 }
@@ -3313,9 +3342,21 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(GEN8_PUSHBUS_SHIFT, D_BXT);
 	MMIO_D(GEN6_GFXPAUSE, D_BXT);
 	MMIO_DFH(GEN8_L3SQCREG1, D_BXT, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(GEN8_L3CNTLREG, D_BXT, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x20D8), D_BXT, F_CMD_ACCESS, NULL, NULL);
+	MMIO_F(GEN8_RING_CS_GPR(RENDER_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+	       0, 0, D_BXT, NULL, NULL);
+	MMIO_F(GEN8_RING_CS_GPR(GEN6_BSD_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+	       0, 0, D_BXT, NULL, NULL);
+	MMIO_F(GEN8_RING_CS_GPR(BLT_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+	       0, 0, D_BXT, NULL, NULL);
+	MMIO_F(GEN8_RING_CS_GPR(VEBOX_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+	       0, 0, D_BXT, NULL, NULL);
 
 	MMIO_DFH(GEN9_CTX_PREEMPT_REG, D_BXT, F_CMD_ACCESS, NULL, NULL);
 
+	MMIO_DH(GEN8_PRIVATE_PAT_LO, D_BXT, NULL, bxt_ppat_low_write);
+
 	return 0;
 }