Merge 5.10-rc3 into android-mainline

Linux 5.10-rc3 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: I7884051ea7b86204b2685b51462368e122ad0772
2020-11-09 12:49:27 +01:00
parent aca265111a f8394f232b
commit 2cfc344f81
340 changed files with 2666 additions and 1708 deletions
--- a/Documentation/ABI/stable/sysfs-driver-dma-ioatdma
+++ b/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
--- a/Documentation/ABI/testing/sysfs-class-net
+++ b/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
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,sci-inta.yaml
+++ b/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:
+    $ref: /schemas/types.yaml#definitions/phandle-array
+    description:
+      Array of phandles to DMA controllers where the unmapped events originate.
+
 required:
  - compatible
  - reg
--- a/Documentation/devicetree/bindings/net/can/can-controller.yaml
+++ b/Documentation/devicetree/bindings/net/can/can-controller.yaml
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$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
+
+...
--- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
+++ b/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>;
+    };
--- a/Documentation/devicetree/bindings/net/can/fsl-flexcan.txt
+++ b/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
-	};
--- a/Documentation/leds/index.rst
+++ b/Documentation/leds/index.rst
@@ -25,3 +25,4 @@ LEDs
   leds-lp5562
   leds-lp55xx
   leds-mlxcpld
+   leds-sc27xx
--- a/Documentation/misc-devices/index.rst
+++ b/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
--- a/Documentation/networking/j1939.rst
+++ b/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)
-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
-socket or use send(2), sendto(2), sendmsg(2) and the recv*() counterpart
+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
+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
 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,
-without it's 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
+Different from CAN is that the payload data is just the data that get sends,
+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
 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
-sending packages. If a PGN during bind(2) is set, it's used as a RX filter.
+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.
 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
-address. The PGN from connect(2) is used as the default PGN when sending
+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
 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
-the remote address from connect(2). Use sendto(2) to overwrite the destination
+Both ``write(2)`` and ``send(2)`` will send a packet with local address from ``bind(2)`` and the
+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
-the corresponding ADDR is used. If can_addr.j1939.name is not set (== 0),
-can_addr.j1939.addr is used.
+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),
+``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_PROMISC - disable filters set by bind(2) and connect(2)
+- ``SO_J1939_FILTER`` - configure array of filters
+- ``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
-recvfrom(2) can provide. For example package priority and timestamp. The
+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
 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,
-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
-priority and dst_addr, and uint64_t for dst_name.
+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``,
+``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``.

 .. 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
-only j1939.addr changed to the new SA, and must then send a valid address claim
+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
 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,
-at this point we can use only sendto(2) or sendmsg(2).
+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)``.

 Send:

@@ -414,8 +414,8 @@ Send:
 		.can_family = AF_CAN,
 		.can_addr.j1939 = {
 			.name = J1939_NO_NAME;
-			.pgn = 0x30,
-			.addr = 0x12300,
+			.addr = 0x30,
+			.pgn = 0x12300,
 		},
 	};

--- a/4
+++ b/4
@@ -934,7 +934,7 @@ M:	Evan Quan <evan.quan@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
 T:	git git://people.freedesktop.org/~agd5f/linux
-F:	drivers/gpu/drm/amd/powerplay/
+F:	drivers/gpu/drm/amd/pm/powerplay/

 AMD SEATTLE DEVICE TREE SUPPORT
 M:	Brijesh Singh <brijeshkumar.singh@amd.com>
@@ -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
--- a/2
+++ b/2
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Kleptomaniac Octopus

 # *DOCUMENTATION*
--- a/arch/arc/kernel/head.S
+++ b/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
--- a/arch/arc/kernel/stacktrace.c
+++ b/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 */
--- a/arch/arc/plat-hsdk/platform.c
+++ b/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
--- a/arch/arm64/Kconfig
+++ b/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
--- a/arch/arm64/include/asm/brk-imm.h
+++ b/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
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/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))

--- a/arch/arm64/include/asm/kprobes.h
+++ b/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
--- a/arch/arm64/kernel/kexec_image.c
+++ b/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);
-	if (ret)
-		return ERR_PTR(ret);
+	kernel_segment_number = image->nr_segments;

-	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 */
-	ret = load_other_segments(image,
-				kernel_segment->mem, kernel_segment->memsz,
-				initrd, initrd_len, cmdline);
-
-	return ERR_PTR(ret);
+	return 0;
 }

 #ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/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;
 }
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/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 */
-	patch_text(p->ainsn.api.insn, p->opcode);
+	kprobe_opcode_t *addr = p->ainsn.api.insn;
+	void *addrs[] = {addr, addr + 1};
+	u32 insns[] = {p->opcode, BRK64_OPCODE_KPROBES_SS};

-	flush_icache_range((uintptr_t) (p->ainsn.api.insn),
-			   (uintptr_t) (p->ainsn.api.insn) +
-			   MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	/* prepare insn slot */
+	aarch64_insn_patch_text(addrs, insns, 2);
+
+	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
- * reenabled until after single-step mode ends.
- * Without disabling interrupt on local CPU, there is a chance of
- * 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.
+ * Mask all of DAIF while executing the instruction out-of-line, to keep things
+ * simple and avoid nesting exceptions. Interrupts do have to be disabled since
+ * the kprobe state is per-CPU and doesn't get migrated.
 */
 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;
-	/* Unmask PSTATE.D for enabling software step exceptions. */
-	regs->pstate &= ~PSR_D_BIT;
+	regs->pstate |= DAIF_MASK;
 }

 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)	{
-		/* post_handler can hit breakpoint and single step
-		 * again, so we enable D-flag for recursive exception.
-		 */
+	if (cur->post_handler)
 		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 = {
-	.fn = kprobe_single_step_handler,
+static struct break_hook kprobes_break_ss_hook = {
+	.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;
 }
--- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h
+++ b/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 !");
 }

--- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
+++ b/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
- * 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
+ * _PAGE_ACCESSED is also managed via APG. When _PAGE_ACCESSED is not set, say
+ * "all User" rules, that will lead to NA for all.
+ * Therefore, we define 4 APG groups. lsb is _PAGE_ACCESSED
+ * 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
-
-/*
- * 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
+#define MI_APG_INIT	0xdc000000
+#define MI_APG_KUEP	0xde000000

 /* 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 */

-/*
- * All pages' PP data bits are set to either 000 or 011 or 001, which means
- * respectively RW for Supervisor and no access for User, or RO for
- * 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
+/* See explanation above at the definition of MI_APG_INIT */
+#define MD_APG_INIT	0xdc000000
+#define MD_APG_KUAP	0xde000000

 /* The effective page number register.  When read, contains the information
 * about the last instruction TLB miss.  When MD_RPN is written, bits in
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/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

--- a/arch/powerpc/include/asm/topology.h
+++ b/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;
-int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+#endif /* CONFIG_NUMA */

 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
 extern int find_and_online_cpu_nid(int cpu);
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/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)				\
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/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;
 }
--- a/arch/powerpc/kernel/head_40x.S
+++ b/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

--- a/arch/powerpc/kernel/head_8xx.S
+++ b/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 | \
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/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 */
--- a/arch/powerpc/kernel/smp.c
+++ b/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;

--- a/arch/riscv/include/asm/uaccess.h
+++ b/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)
--- a/arch/riscv/kernel/ftrace.c
+++ b/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>
--- a/arch/riscv/kernel/head.S
+++ b/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
--- a/arch/riscv/kernel/vdso/.gitignore
+++ b/arch/riscv/kernel/vdso/.gitignore
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 vdso.lds
 *.tmp
+vdso-syms.S
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/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.
-
-SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
-	-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
-	$(call if_changed,ld)
+$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE
+	$(call if_changed,so2s)

 # 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 $(MODLIB)/vdso/$@
--- a/arch/riscv/kernel/vdso/so2s.sh
+++ b/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 '^\.'
--- a/arch/riscv/mm/fault.c
+++ b/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)) {
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -154,9 +154,8 @@ disable:

 void __init setup_bootmem(void)
 {
-	phys_addr_t mem_size = 0;
-	phys_addr_t total_mem = 0;
-	phys_addr_t mem_start, start, end = 0;
+	phys_addr_t mem_start = 0;
+	phys_addr_t 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
-	 * end of region
+	 * The maximal physical memory size is -PAGE_OFFSET.
+	 * 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);
-	if (mem_start + mem_size < end)
-		memblock_remove(mem_start + mem_size,
-				end - mem_start - mem_size);
+	memblock_enforce_memory_limit(mem_start - PAGE_OFFSET);

 	/* 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;

 	/*
--- a/arch/s390/configs/debug_defconfig
+++ b/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
--- a/arch/s390/configs/defconfig
+++ b/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
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/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
--- a/arch/s390/include/asm/pgtable.h
+++ b/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
--- a/arch/s390/include/asm/vdso/vdso.h
+++ b/arch/s390/include/asm/vdso/vdso.h
--- a/arch/s390/kernel/asm-offsets.c
+++ b/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);
--- a/arch/s390/kernel/smp.c
+++ b/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();
--- a/arch/s390/pci/pci_event.c
+++ b/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;
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/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)
-			uv_hubless_system = 0x11;
+		else if (strncmp(uv_archtype, "NSGI4", 5) == 0)
+			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 */
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/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
-		 * mode. It can neither be enabled if it was force-disabled
-		 * by a  previous prctl call.
+		 * With strict mode for both IBPB and STIBP, the instruction
+		 * code paths avoid checking this task flag and instead,
+		 * 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 ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
+		if (!is_spec_ib_user_controlled() ||
 		    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 ||
-		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+
+		if (!is_spec_ib_user_controlled())
 			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 ||
-	    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) {
+	else if (is_spec_ib_user_controlled()) {
 		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;
 }

--- a/arch/x86/lib/memcpy_64.S
+++ b/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

--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -24,9 +24,7 @@
 * Output:
 * rax: dest
 */
-.weak memmove
-
-SYM_FUNC_START_ALIAS(memmove)
+SYM_FUNC_START_WEAK(memmove)
 SYM_FUNC_START(__memmove)

 	mov %rdi, %rax
--- a/arch/x86/lib/memset_64.S
+++ b/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
--- a/drivers/block/null_blk.h
+++ b/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 */
--- a/drivers/block/null_blk_zoned.c
+++ b/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);

--- a/drivers/char/tpm/eventlog/efi.c
+++ b/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) {
--- a/drivers/char/tpm/tpm_tis.c
+++ b/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;
-module_param(interrupts, bool, 0444);
+static int interrupts = -1;
+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;
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -80,6 +80,7 @@ MODULE_FIRMWARE("amdgpu/renoir_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_gpu_info.bin");

 #define AMDGPU_RESUME_MS		2000

@@ -1805,7 +1806,10 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 		chip_name = "arcturus";
 		break;
 	case CHIP_RENOIR:
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
 			chip_name = "renoir";
+		else
+			chip_name = "green_sardine";
 		break;
 	case CHIP_NAVI10:
 		chip_name = "navi10";
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2524,6 +2524,7 @@ int parse_ta_bin_descriptor(struct psp_context *psp,
 		psp->asd_feature_version   = le32_to_cpu(desc->fw_version);
 		psp->asd_ucode_size 	   = le32_to_cpu(desc->size_bytes);
 		psp->asd_start_addr 	   = ucode_start_addr;
+		psp->asd_fw                = psp->ta_fw;
 		break;
 	case TA_FW_TYPE_PSP_XGMI:
 		psp->ta_xgmi_ucode_version = le32_to_cpu(desc->fw_version);
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -39,6 +39,7 @@
 #define FIRMWARE_RAVEN2		"amdgpu/raven2_vcn.bin"
 #define FIRMWARE_ARCTURUS 	"amdgpu/arcturus_vcn.bin"
 #define FIRMWARE_RENOIR 	"amdgpu/renoir_vcn.bin"
+#define FIRMWARE_GREEN_SARDINE 	"amdgpu/green_sardine_vcn.bin"
 #define FIRMWARE_NAVI10 	"amdgpu/navi10_vcn.bin"
 #define FIRMWARE_NAVI14 	"amdgpu/navi14_vcn.bin"
 #define FIRMWARE_NAVI12 	"amdgpu/navi12_vcn.bin"
@@ -50,6 +51,7 @@ MODULE_FIRMWARE(FIRMWARE_PICASSO);
 MODULE_FIRMWARE(FIRMWARE_RAVEN2);
 MODULE_FIRMWARE(FIRMWARE_ARCTURUS);
 MODULE_FIRMWARE(FIRMWARE_RENOIR);
+MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE);
 MODULE_FIRMWARE(FIRMWARE_NAVI10);
 MODULE_FIRMWARE(FIRMWARE_NAVI14);
 MODULE_FIRMWARE(FIRMWARE_NAVI12);
@@ -89,7 +91,11 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 			adev->vcn.indirect_sram = true;
 		break;
 	case CHIP_RENOIR:
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
 			fw_name = FIRMWARE_RENOIR;
+		else
+			fw_name = FIRMWARE_GREEN_SARDINE;
+
 		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
 		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
 			adev->vcn.indirect_sram = true;
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1336,11 +1336,13 @@ cik_asic_reset_method(struct amdgpu_device *adev)

 	switch (adev->asic_type) {
 	case CHIP_BONAIRE:
-	case CHIP_HAWAII:
 		/* disable baco reset until it works */
 		/* smu7_asic_get_baco_capability(adev, &baco_reset); */
 		baco_reset = false;
 		break;
+	case CHIP_HAWAII:
+		baco_reset = cik_asic_supports_baco(adev);
+		break;
 	default:
 		baco_reset = false;
 		break;
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -1071,22 +1071,19 @@ static int cik_sdma_soft_reset(void *handle)
 {
 	u32 srbm_soft_reset = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	u32 tmp = RREG32(mmSRBM_STATUS2);
+	u32 tmp;

-	if (tmp & SRBM_STATUS2__SDMA_BUSY_MASK) {
 	/* sdma0 */
 	tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
 	tmp |= SDMA0_F32_CNTL__HALT_MASK;
 	WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
 	srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
-	}
-	if (tmp & SRBM_STATUS2__SDMA1_BUSY_MASK) {
+
 	/* sdma1 */
 	tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
 	tmp |= SDMA0_F32_CNTL__HALT_MASK;
 	WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
 	srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
-	}

 	if (srbm_soft_reset) {
 		tmp = RREG32(mmSRBM_SOFT_RESET);
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -128,6 +128,9 @@
 #define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO__SHIFT 0x3
 #define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO_MASK   0x00000008L

+#define mmCGTT_SPI_CS_CLK_CTRL			0x507c
+#define mmCGTT_SPI_CS_CLK_CTRL_BASE_IDX         1
+
 MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
 MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -3094,6 +3097,7 @@ static const struct soc15_reg_golden golden_settings_gc_rlc_spm_10_1_2_nv12[] =

 static const struct soc15_reg_golden golden_settings_gc_10_3[] =
 {
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CS_CLK_CTRL, 0x78000000, 0x78000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_PS_CLK_CTRL, 0xff7f0fff, 0x78000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA0_CLK_CTRL, 0xff7f0fff, 0x30000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA1_CLK_CTRL, 0xff7f0fff, 0x7e000100),
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -117,6 +117,13 @@ MODULE_FIRMWARE("amdgpu/renoir_mec.bin");
 MODULE_FIRMWARE("amdgpu/renoir_mec2.bin");
 MODULE_FIRMWARE("amdgpu/renoir_rlc.bin");

+MODULE_FIRMWARE("amdgpu/green_sardine_ce.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_pfp.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_me.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_mec.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_mec2.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_rlc.bin");
+
 #define mmTCP_CHAN_STEER_0_ARCT								0x0b03
 #define mmTCP_CHAN_STEER_0_ARCT_BASE_IDX							0
 #define mmTCP_CHAN_STEER_1_ARCT								0x0b04
@@ -1630,7 +1637,10 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 		chip_name = "arcturus";
 		break;
 	case CHIP_RENOIR:
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
 			chip_name = "renoir";
+		else
+			chip_name = "green_sardine";
 		break;
 	default:
 		BUG();
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -455,10 +455,11 @@ void nv_set_virt_ops(struct amdgpu_device *adev)
 	adev->virt.ops = &xgpu_nv_virt_ops;
 }

-static bool nv_is_blockchain_sku(struct pci_dev *pdev)
+static bool nv_is_headless_sku(struct pci_dev *pdev)
 {
-	if (pdev->device == 0x731E &&
-	    (pdev->revision == 0xC6 || pdev->revision == 0xC7))
+	if ((pdev->device == 0x731E &&
+	    (pdev->revision == 0xC6 || pdev->revision == 0xC7)) ||
+	    (pdev->device == 0x7340 && pdev->revision == 0xC9))
 		return true;
 	return false;
 }
@@ -492,7 +493,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
 		else if (amdgpu_device_has_dc_support(adev) &&
-			 !nv_is_blockchain_sku(adev->pdev))
+			 !nv_is_headless_sku(adev->pdev))
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
@@ -500,7 +501,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
 		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
-		if (!nv_is_blockchain_sku(adev->pdev))
+		if (!nv_is_headless_sku(adev->pdev))
 			amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 		if (adev->enable_mes)
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -39,6 +39,7 @@

 MODULE_FIRMWARE("amdgpu/renoir_asd.bin");
 MODULE_FIRMWARE("amdgpu/renoir_ta.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_asd.bin");

 /* address block */
 #define smnMP1_FIRMWARE_FLAGS		0x3010024
@@ -54,7 +55,10 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)

 	switch (adev->asic_type) {
 	case CHIP_RENOIR:
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
 			chip_name = "renoir";
+		else
+			chip_name = "green_sardine";
 		break;
 	default:
 		BUG();
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -69,6 +69,7 @@ MODULE_FIRMWARE("amdgpu/picasso_sdma.bin");
 MODULE_FIRMWARE("amdgpu/raven2_sdma.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_sdma.bin");
 MODULE_FIRMWARE("amdgpu/renoir_sdma.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_sdma.bin");

 #define SDMA0_POWER_CNTL__ON_OFF_CONDITION_HOLD_TIME_MASK  0x000000F8L
 #define SDMA0_POWER_CNTL__ON_OFF_STATUS_DURATION_TIME_MASK 0xFC000000L
@@ -619,7 +620,10 @@ static int sdma_v4_0_init_microcode(struct amdgpu_device *adev)
 		chip_name = "arcturus";
 		break;
 	case CHIP_RENOIR:
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
 			chip_name = "renoir";
+		else
+			chip_name = "green_sardine";
 		break;
 	default:
 		BUG();
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1195,8 +1195,7 @@ static int soc15_common_early_init(void *handle)

 			adev->pg_flags = AMD_PG_SUPPORT_SDMA |
 				AMD_PG_SUPPORT_MMHUB |
-				AMD_PG_SUPPORT_VCN |
-				AMD_PG_SUPPORT_VCN_DPG;
+				AMD_PG_SUPPORT_VCN;
 		} else {
 			adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 				AMD_CG_SUPPORT_GFX_MGLS |
@@ -1243,7 +1242,15 @@ static int soc15_common_early_init(void *handle)
 		break;
 	case CHIP_RENOIR:
 		adev->asic_funcs = &soc15_asic_funcs;
+		if (adev->pdev->device == 0x1636)
 			adev->apu_flags |= AMD_APU_IS_RENOIR;
+		else
+			adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
+
+		if (adev->apu_flags & AMD_APU_IS_RENOIR)
+			adev->external_rev_id = adev->rev_id + 0x91;
+		else
+			adev->external_rev_id = adev->rev_id + 0xa1;
 		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 				 AMD_CG_SUPPORT_GFX_MGLS |
 				 AMD_CG_SUPPORT_GFX_3D_CGCG |
@@ -1268,7 +1275,6 @@ static int soc15_common_early_init(void *handle)
 				 AMD_PG_SUPPORT_VCN |
 				 AMD_PG_SUPPORT_JPEG |
 				 AMD_PG_SUPPORT_VCN_DPG;
-		adev->external_rev_id = adev->rev_id + 0x91;
 		break;
 	default:
 		/* FIXME: not supported yet */
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -798,10 +798,10 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size)
 	}

 	pcrat_image = kvmalloc(crat_table->length, GFP_KERNEL);
-	memcpy(pcrat_image, crat_table, crat_table->length);
 	if (!pcrat_image)
 		return -ENOMEM;

+	memcpy(pcrat_image, crat_table, crat_table->length);
 	*crat_image = pcrat_image;
 	*size = crat_table->length;

--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -100,6 +100,8 @@ MODULE_FIRMWARE(FIRMWARE_SIENNA_CICHLID_DMUB);
 #define FIRMWARE_NAVY_FLOUNDER_DMUB "amdgpu/navy_flounder_dmcub.bin"
 MODULE_FIRMWARE(FIRMWARE_NAVY_FLOUNDER_DMUB);
 #endif
+#define FIRMWARE_GREEN_SARDINE_DMUB "amdgpu/green_sardine_dmcub.bin"
+MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE_DMUB);

 #define FIRMWARE_RAVEN_DMCU		"amdgpu/raven_dmcu.bin"
 MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU);
@@ -973,6 +975,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:
 		init_data.flags.gpu_vm_support = true;
+		if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id))
+			init_data.flags.disable_dmcu = true;
 		break;
 	default:
 		break;
@@ -1267,6 +1271,8 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev)
 	case CHIP_RENOIR:
 		dmub_asic = DMUB_ASIC_DCN21;
 		fw_name_dmub = FIRMWARE_RENOIR_DMUB;
+		if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id))
+			fw_name_dmub = FIRMWARE_GREEN_SARDINE_DMUB;
 		break;
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 	case CHIP_SIENNA_CICHLID:
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -166,6 +166,11 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 			rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 			break;
 		}
+
+		if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev)) {
+			rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
+			break;
+		}
 		if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev)) {
 			rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu);
 			break;
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -120,6 +120,8 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 			dc_version = DCN_VERSION_1_01;
 		if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev))
 			dc_version = DCN_VERSION_2_1;
+		if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev))
+			dc_version = DCN_VERSION_2_1;
 		break;
 #endif

--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -205,6 +205,10 @@ enum {
 #if defined(CONFIG_DRM_AMD_DC_DCN3_0)
 #define ASICREV_IS_SIENNA_CICHLID_P(eChipRev)        ((eChipRev >= NV_SIENNA_CICHLID_P_A0))
 #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
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -45,6 +45,7 @@ enum amd_apu_flags {
 	AMD_APU_IS_RAVEN2 = 0x00000002UL,
 	AMD_APU_IS_PICASSO = 0x00000004UL,
 	AMD_APU_IS_RENOIR = 0x00000008UL,
+	AMD_APU_IS_GREEN_SARDINE = 0x00000010UL,
 };

 /**
--- a/drivers/gpu/drm/amd/pm/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/hwmgr.h
@@ -229,6 +229,7 @@ struct pp_smumgr_func {
 	bool (*is_hw_avfs_present)(struct pp_hwmgr  *hwmgr);
 	int (*update_dpm_settings)(struct pp_hwmgr *hwmgr, void *profile_setting);
 	int (*smc_table_manager)(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw); /*rw: true for read, false for write */
+	int (*stop_smc)(struct pp_hwmgr *hwmgr);
 };

 struct pp_hwmgr_func {
--- a/drivers/gpu/drm/amd/pm/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/pm/inc/smumgr.h
@@ -113,4 +113,6 @@ extern int smum_update_dpm_settings(struct pp_hwmgr *hwmgr, void *profile_settin

 extern int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw);

+extern int smum_stop_smc(struct pp_hwmgr *hwmgr);
+
 #endif
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c
@@ -142,12 +142,12 @@ static const struct baco_cmd_entry exit_baco_tbl[] =
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK,           BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK,          BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 },
 	{ CMD_DELAY_MS, 0, 0, 0, 20, 0 },
-	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x20 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 },
-	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 },
-	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x10 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 },
 	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 },
 	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 }
 };
@@ -155,6 +155,7 @@ static const struct baco_cmd_entry exit_baco_tbl[] =
 static const struct baco_cmd_entry clean_baco_tbl[] =
 {
 	{ CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 },
 	{ CMD_WRITE, mmCP_PFP_UCODE_ADDR, 0, 0, 0, 0 }
 };

--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -1541,6 +1541,10 @@ static int smu7_disable_dpm_tasks(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE((tmp_result == 0),
 			"Failed to reset to default!", result = tmp_result);

+	tmp_result = smum_stop_smc(hwmgr);
+	PP_ASSERT_WITH_CODE((tmp_result == 0),
+			"Failed to stop smc!", result = tmp_result);
+
 	tmp_result = smu7_force_switch_to_arbf0(hwmgr);
 	PP_ASSERT_WITH_CODE((tmp_result == 0),
 			"Failed to force to switch arbf0!", result = tmp_result);
@@ -1585,6 +1589,7 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 	data->current_profile_setting.sclk_down_hyst = 100;
 	data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT;
 	data->current_profile_setting.bupdate_mclk = 1;
+	if (hwmgr->chip_id >= CHIP_POLARIS10) {
 		if (adev->gmc.vram_width == 256) {
 			data->current_profile_setting.mclk_up_hyst = 10;
 			data->current_profile_setting.mclk_down_hyst = 60;
@@ -1598,6 +1603,11 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 			data->current_profile_setting.mclk_down_hyst = 16;
 			data->current_profile_setting.mclk_activity = 20;
 		}
+	} else {
+		data->current_profile_setting.mclk_up_hyst = 0;
+		data->current_profile_setting.mclk_down_hyst = 100;
+		data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT;
+	}
 	hwmgr->workload_mask = 1 << hwmgr->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
 	hwmgr->power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
 	hwmgr->default_power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c
@@ -2726,10 +2726,7 @@ static int ci_initialize_mc_reg_table(struct pp_hwmgr *hwmgr)

 static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr)
 {
-	return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
-					     CGS_IND_REG__SMC, FEATURE_STATUS,
-					     VOLTAGE_CONTROLLER_ON))
-		? true : false;
+	return ci_is_smc_ram_running(hwmgr);
 }

 static int ci_smu_init(struct pp_hwmgr *hwmgr)
@@ -2939,6 +2936,29 @@ static int ci_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 	return 0;
 }

+static void ci_reset_smc(struct pp_hwmgr *hwmgr)
+{
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+				  SMC_SYSCON_RESET_CNTL,
+				  rst_reg, 1);
+}
+
+
+static void ci_stop_smc_clock(struct pp_hwmgr *hwmgr)
+{
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+				  SMC_SYSCON_CLOCK_CNTL_0,
+				  ck_disable, 1);
+}
+
+static int ci_stop_smc(struct pp_hwmgr *hwmgr)
+{
+	ci_reset_smc(hwmgr);
+	ci_stop_smc_clock(hwmgr);
+
+	return 0;
+}
+
 const struct pp_smumgr_func ci_smu_funcs = {
 	.name = "ci_smu",
 	.smu_init = ci_smu_init,
@@ -2964,4 +2984,5 @@ const struct pp_smumgr_func ci_smu_funcs = {
 	.is_dpm_running = ci_is_dpm_running,
 	.update_dpm_settings = ci_update_dpm_settings,
 	.update_smc_table = ci_update_smc_table,
+	.stop_smc = ci_stop_smc,
 };
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c
@@ -245,3 +245,11 @@ int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t tabl

 	return -EINVAL;
 }
+
+int smum_stop_smc(struct pp_hwmgr *hwmgr)
+{
+	if (hwmgr->smumgr_funcs->stop_smc)
+		return hwmgr->smumgr_funcs->stop_smc(hwmgr);
+
+	return 0;
+}
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1029,17 +1029,6 @@ static int smu_smc_hw_setup(struct smu_context *smu)
 		return ret;
 	}

-	/*
-	 * Set initialized values (get from vbios) to dpm tables context such as
-	 * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each
-	 * type of clks.
-	 */
-	ret = smu_set_default_dpm_table(smu);
-	if (ret) {
-		dev_err(adev->dev, "Failed to setup default dpm clock tables!\n");
-		return ret;
-	}
-
 	ret = smu_notify_display_change(smu);
 	if (ret)
 		return ret;
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1754,7 +1754,7 @@ void intel_psr_atomic_check(struct drm_connector *connector,
 		return;

 	intel_connector = to_intel_connector(connector);
-	dig_port = enc_to_dig_port(intel_attached_encoder(intel_connector));
+	dig_port = enc_to_dig_port(to_intel_encoder(new_state->best_encoder));
 	if (dev_priv->psr.dp != &dig_port->dp)
 		return;

--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/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;
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/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++ = gtt_offset;
+	*cs++ = flags1 | PIPE_CONTROL_QW_WRITE;
+	*cs++ = offset;
 	*cs++ = 0;
 	*cs++ = value;
-	/* We're thrashing one dword of HWS. */
-	*cs++ = 0;
+	*cs++ = 0; /* We're thrashing one extra dword. */

 	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;
-	*cs++ = gtt_offset | MI_FLUSH_DW_USE_GTT;
-	*cs++ = 0;
-	*cs++ = value;
-
-	return cs;
+	return __gen8_emit_flush_dw(cs,
+				    value,
+				    gtt_offset | MI_FLUSH_DW_USE_GTT,
+				    flags | MI_FLUSH_DW_OP_STOREDW);
 }

 static inline void __intel_engine_reset(struct intel_engine_cs *engine,
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/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, request->fence.seqno, addr, 0);
+	return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 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 |
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/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) +
-		ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) * CACHELINE_BYTES;
-
+	*hwsp = cl->ggtt_offset;
 out:
 	i915_active_release(&cl->active);
 	return err;
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/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;
 };

--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/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;
 }

--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -1277,7 +1277,7 @@ void intel_vgpu_clean_submission(struct intel_vgpu *vgpu)

 	i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(s->shadow[0]->vm));
 	for_each_engine(engine, vgpu->gvt->gt, id)
-		intel_context_unpin(s->shadow[id]);
+		intel_context_put(s->shadow[id]);

 	kmem_cache_destroy(s->workloads);
 }
@@ -1369,11 +1369,6 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 			ce->ring = __intel_context_ring_size(ring_size);
 		}

-		ret = intel_context_pin(ce);
-		intel_context_put(ce);
-		if (ret)
-			goto out_shadow_ctx;
-
 		s->shadow[i] = ce;
 	}

@@ -1405,7 +1400,6 @@ out_shadow_ctx:
 		if (IS_ERR(s->shadow[i]))
 			break;

-		intel_context_unpin(s->shadow[i]);
 		intel_context_put(s->shadow[i]);
 	}
 	i915_vm_put(&ppgtt->vm);
@@ -1479,6 +1473,7 @@ void intel_vgpu_destroy_workload(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu_submission *s = &workload->vgpu->submission;

+	intel_context_unpin(s->shadow[workload->engine->id]);
 	release_shadow_batch_buffer(workload);
 	release_shadow_wa_ctx(&workload->wa_ctx);

@@ -1724,6 +1719,12 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu,
 		return ERR_PTR(ret);
 	}

+	ret = intel_context_pin(s->shadow[engine->id]);
+	if (ret) {
+		intel_vgpu_destroy_workload(workload);
+		return ERR_PTR(ret);
+	}
+
 	return workload;
 }

--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -314,8 +314,10 @@ static void __vma_release(struct dma_fence_work *work)
 {
 	struct i915_vma_work *vw = container_of(work, typeof(*vw), base);

-	if (vw->pinned)
+	if (vw->pinned) {
 		__i915_gem_object_unpin_pages(vw->pinned);
+		i915_gem_object_put(vw->pinned);
+	}

 	i915_vm_free_pt_stash(vw->vm, &vw->stash);
 	i915_vm_put(vw->vm);
@@ -431,7 +433,7 @@ int i915_vma_bind(struct i915_vma *vma,

 		if (vma->obj) {
 			__i915_gem_object_pin_pages(vma->obj);
-			work->pinned = vma->obj;
+			work->pinned = i915_gem_object_get(vma->obj);
 		}
 	} else {
 		vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags);
--- a/drivers/gpu/drm/imx/dw_hdmi-imx.c
+++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c
@@ -111,10 +111,6 @@ static int dw_hdmi_imx_parse_dt(struct imx_hdmi *hdmi)
 	return 0;
 }

-static void dw_hdmi_imx_encoder_disable(struct drm_encoder *encoder)
-{
-}
-
 static void dw_hdmi_imx_encoder_enable(struct drm_encoder *encoder)
 {
 	struct imx_hdmi *hdmi = enc_to_imx_hdmi(encoder);
@@ -140,7 +136,6 @@ static int dw_hdmi_imx_atomic_check(struct drm_encoder *encoder,

 static const struct drm_encoder_helper_funcs dw_hdmi_imx_encoder_helper_funcs = {
 	.enable     = dw_hdmi_imx_encoder_enable,
-	.disable    = dw_hdmi_imx_encoder_disable,
 	.atomic_check = dw_hdmi_imx_atomic_check,
 };

@@ -219,15 +214,9 @@ static int dw_hdmi_imx_bind(struct device *dev, struct device *master,
 	hdmi->dev = &pdev->dev;
 	encoder = &hdmi->encoder;

-	encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node);
-	/*
-	 * If we failed to find the CRTC(s) which this encoder is
-	 * supposed to be connected to, it's because the CRTC has
-	 * not been registered yet.  Defer probing, and hope that
-	 * the required CRTC is added later.
-	 */
-	if (encoder->possible_crtcs == 0)
-		return -EPROBE_DEFER;
+	ret = imx_drm_encoder_parse_of(drm, encoder, dev->of_node);
+	if (ret)
+		return ret;

 	ret = dw_hdmi_imx_parse_dt(hdmi);
 	if (ret < 0)
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -20,6 +20,7 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_managed.h>
 #include <drm/drm_of.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_probe_helper.h>
@@ -212,7 +213,9 @@ static int imx_drm_bind(struct device *dev)
 	drm->mode_config.allow_fb_modifiers = true;
 	drm->mode_config.normalize_zpos = true;

-	drm_mode_config_init(drm);
+	ret = drmm_mode_config_init(drm);
+	if (ret)
+		return ret;

 	ret = drm_vblank_init(drm, MAX_CRTC);
 	if (ret)
@@ -251,7 +254,6 @@ err_poll_fini:
 	drm_kms_helper_poll_fini(drm);
 	component_unbind_all(drm->dev, drm);
 err_kms:
-	drm_mode_config_cleanup(drm);
 	drm_dev_put(drm);

 	return ret;
@@ -267,11 +269,9 @@ static void imx_drm_unbind(struct device *dev)

 	component_unbind_all(drm->dev, drm);

-	drm_mode_config_cleanup(drm);
+	drm_dev_put(drm);

 	dev_set_drvdata(dev, NULL);
-
-	drm_dev_put(drm);
 }

 static const struct component_master_ops imx_drm_ops = {
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -62,7 +62,6 @@ struct imx_ldb_channel {
 	struct i2c_adapter *ddc;
 	int chno;
 	void *edid;
-	int edid_len;
 	struct drm_display_mode mode;
 	int mode_valid;
 	u32 bus_format;
@@ -536,15 +535,14 @@ static int imx_ldb_panel_ddc(struct device *dev,
 	}

 	if (!channel->ddc) {
+		int edid_len;
+
 		/* if no DDC available, fallback to hardcoded EDID */
 		dev_dbg(dev, "no ddc available\n");

-		edidp = of_get_property(child, "edid",
-					&channel->edid_len);
+		edidp = of_get_property(child, "edid", &edid_len);
 		if (edidp) {
-			channel->edid = kmemdup(edidp,
-						channel->edid_len,
-						GFP_KERNEL);
+			channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL);
 		} else if (!channel->panel) {
 			/* fallback to display-timings node */
 			ret = of_get_drm_display_mode(child,
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -13,7 +13,6 @@
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
-#include <linux/spinlock.h>
 #include <linux/videodev2.h>

 #include <video/imx-ipu-v3.h>
@@ -104,8 +103,6 @@ struct imx_tve {
 	struct drm_connector connector;
 	struct drm_encoder encoder;
 	struct device *dev;
-	spinlock_t lock;	/* register lock */
-	bool enabled;
 	int mode;
 	int di_hsync_pin;
 	int di_vsync_pin;
@@ -129,30 +126,10 @@ static inline struct imx_tve *enc_to_tve(struct drm_encoder *e)
 	return container_of(e, struct imx_tve, encoder);
 }

-static void tve_lock(void *__tve)
-__acquires(&tve->lock)
-{
-	struct imx_tve *tve = __tve;
-
-	spin_lock(&tve->lock);
-}
-
-static void tve_unlock(void *__tve)
-__releases(&tve->lock)
-{
-	struct imx_tve *tve = __tve;
-
-	spin_unlock(&tve->lock);
-}
-
 static void tve_enable(struct imx_tve *tve)
 {
-	if (!tve->enabled) {
-		tve->enabled = true;
 	clk_prepare_enable(tve->clk);
-		regmap_update_bits(tve->regmap, TVE_COM_CONF_REG,
-				   TVE_EN, TVE_EN);
-	}
+	regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, TVE_EN);

 	/* clear interrupt status register */
 	regmap_write(tve->regmap, TVE_STAT_REG, 0xffffffff);
@@ -169,12 +146,9 @@ static void tve_enable(struct imx_tve *tve)

 static void tve_disable(struct imx_tve *tve)
 {
-	if (tve->enabled) {
-		tve->enabled = false;
 	regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0);
 	clk_disable_unprepare(tve->clk);
 }
-}

 static int tve_setup_tvout(struct imx_tve *tve)
 {
@@ -500,8 +474,7 @@ static struct regmap_config tve_regmap_config = {

 	.readable_reg = imx_tve_readable_reg,

-	.lock = tve_lock,
-	.unlock = tve_unlock,
+	.fast_io = true,

 	.max_register = 0xdc,
 };
@@ -511,7 +484,7 @@ static const char * const imx_tve_modes[] = {
 	[TVE_MODE_VGA] = "vga",
 };

-static const int of_get_tve_mode(struct device_node *np)
+static int of_get_tve_mode(struct device_node *np)
 {
 	const char *bm;
 	int ret, i;
@@ -544,7 +517,6 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data)
 	memset(tve, 0, sizeof(*tve));

 	tve->dev = dev;
-	spin_lock_init(&tve->lock);

 	ddc_node = of_parse_phandle(np, "ddc-i2c-bus", 0);
 	if (ddc_node) {
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -28,7 +28,6 @@ struct imx_parallel_display {
 	struct drm_bridge bridge;
 	struct device *dev;
 	void *edid;
-	int edid_len;
 	u32 bus_format;
 	u32 bus_flags;
 	struct drm_display_mode mode;
@@ -41,11 +40,6 @@ static inline struct imx_parallel_display *con_to_imxpd(struct drm_connector *c)
 	return container_of(c, struct imx_parallel_display, connector);
 }

-static inline struct imx_parallel_display *enc_to_imxpd(struct drm_encoder *e)
-{
-	return container_of(e, struct imx_parallel_display, encoder);
-}
-
 static inline struct imx_parallel_display *bridge_to_imxpd(struct drm_bridge *b)
 {
 	return container_of(b, struct imx_parallel_display, bridge);
@@ -310,6 +304,7 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 	struct device_node *np = dev->of_node;
 	const u8 *edidp;
 	struct imx_parallel_display *imxpd;
+	int edid_len;
 	int ret;
 	u32 bus_format = 0;
 	const char *fmt;
@@ -323,9 +318,9 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 	if (ret && ret != -ENODEV)
 		return ret;

-	edidp = of_get_property(np, "edid", &imxpd->edid_len);
+	edidp = of_get_property(np, "edid", &edid_len);
 	if (edidp)
-		imxpd->edid = kmemdup(edidp, imxpd->edid_len, GFP_KERNEL);
+		imxpd->edid = devm_kmemdup(dev, edidp, edid_len, GFP_KERNEL);

 	ret = of_property_read_string(np, "interface-pix-fmt", &fmt);
 	if (!ret) {
@@ -349,17 +344,8 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 	return 0;
 }

-static void imx_pd_unbind(struct device *dev, struct device *master,
-	void *data)
-{
-	struct imx_parallel_display *imxpd = dev_get_drvdata(dev);
-
-	kfree(imxpd->edid);
-}
-
 static const struct component_ops imx_pd_ops = {
 	.bind	= imx_pd_bind,
-	.unbind	= imx_pd_unbind,
 };

 static int imx_pd_probe(struct platform_device *pdev)
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -626,6 +626,7 @@ static int panfrost_probe(struct platform_device *pdev)
 err_out1:
 	pm_runtime_disable(pfdev->dev);
 	panfrost_device_fini(pfdev);
+	pm_runtime_set_suspended(pfdev->dev);
 err_out0:
 	drm_dev_put(ddev);
 	return err;
@@ -640,9 +641,9 @@ static int panfrost_remove(struct platform_device *pdev)
 	panfrost_gem_shrinker_cleanup(ddev);

 	pm_runtime_get_sync(pfdev->dev);
-	panfrost_device_fini(pfdev);
-	pm_runtime_put_sync_suspend(pfdev->dev);
 	pm_runtime_disable(pfdev->dev);
+	panfrost_device_fini(pfdev);
+	pm_runtime_set_suspended(pfdev->dev);

 	drm_dev_put(ddev);
 	return 0;
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -105,14 +105,12 @@ void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping)
 	kref_put(&mapping->refcount, panfrost_gem_mapping_release);
 }

-void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo)
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo)
 {
 	struct panfrost_gem_mapping *mapping;

-	mutex_lock(&bo->mappings.lock);
 	list_for_each_entry(mapping, &bo->mappings.list, node)
 		panfrost_gem_teardown_mapping(mapping);
-	mutex_unlock(&bo->mappings.lock);
 }

 int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
--- a/drivers/gpu/drm/panfrost/panfrost_gem.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
@@ -82,7 +82,7 @@ struct panfrost_gem_mapping *
 panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
 			 struct panfrost_file_priv *priv);
 void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping);
-void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo);
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo);

 void panfrost_gem_shrinker_init(struct drm_device *dev);
 void panfrost_gem_shrinker_cleanup(struct drm_device *dev);
--- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
@@ -40,18 +40,26 @@ static bool panfrost_gem_purge(struct drm_gem_object *obj)
 {
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 	struct panfrost_gem_object *bo = to_panfrost_bo(obj);
+	bool ret = false;

 	if (atomic_read(&bo->gpu_usecount))
 		return false;

-	if (!mutex_trylock(&shmem->pages_lock))
+	if (!mutex_trylock(&bo->mappings.lock))
 		return false;

-	panfrost_gem_teardown_mappings(bo);
+	if (!mutex_trylock(&shmem->pages_lock))
+		goto unlock_mappings;
+
+	panfrost_gem_teardown_mappings_locked(bo);
 	drm_gem_shmem_purge_locked(obj);
+	ret = true;

 	mutex_unlock(&shmem->pages_lock);
-	return true;
+
+unlock_mappings:
+	mutex_unlock(&bo->mappings.lock);
+	return ret;
 }

 static unsigned long
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -449,7 +449,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 	}

 	if (IS_ERR(cma_obj)) {
-		struct drm_printer p = drm_info_printer(vc4->dev->dev);
+		struct drm_printer p = drm_info_printer(vc4->base.dev);
 		DRM_ERROR("Failed to allocate from CMA:\n");
 		vc4_bo_stats_print(&p, vc4);
 		return ERR_PTR(-ENOMEM);
@@ -590,7 +590,7 @@ static void vc4_bo_cache_time_work(struct work_struct *work)
 {
 	struct vc4_dev *vc4 =
 		container_of(work, struct vc4_dev, bo_cache.time_work);
-	struct drm_device *dev = vc4->dev;
+	struct drm_device *dev = &vc4->base;

 	mutex_lock(&vc4->bo_lock);
 	vc4_bo_cache_free_old(dev);
@@ -1005,6 +1005,7 @@ int vc4_get_tiling_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }

+static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused);
 int vc4_bo_cache_init(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
@@ -1033,10 +1034,10 @@ int vc4_bo_cache_init(struct drm_device *dev)
 	INIT_WORK(&vc4->bo_cache.time_work, vc4_bo_cache_time_work);
 	timer_setup(&vc4->bo_cache.time_timer, vc4_bo_cache_time_timer, 0);

-	return 0;
+	return drmm_add_action_or_reset(dev, vc4_bo_cache_destroy, NULL);
 }

-void vc4_bo_cache_destroy(struct drm_device *dev)
+static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	int i;
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -257,37 +257,37 @@ static int vc4_drm_bind(struct device *dev)

 	dev->coherent_dma_mask = DMA_BIT_MASK(32);

-	vc4 = devm_kzalloc(dev, sizeof(*vc4), GFP_KERNEL);
-	if (!vc4)
-		return -ENOMEM;
-
 	/* If VC4 V3D is missing, don't advertise render nodes. */
 	node = of_find_matching_node_and_match(NULL, vc4_v3d_dt_match, NULL);
 	if (!node || !of_device_is_available(node))
 		vc4_drm_driver.driver_features &= ~DRIVER_RENDER;
 	of_node_put(node);

-	drm = drm_dev_alloc(&vc4_drm_driver, dev);
-	if (IS_ERR(drm))
-		return PTR_ERR(drm);
+	vc4 = devm_drm_dev_alloc(dev, &vc4_drm_driver, struct vc4_dev, base);
+	if (IS_ERR(vc4))
+		return PTR_ERR(vc4);
+
+	drm = &vc4->base;
 	platform_set_drvdata(pdev, drm);
-	vc4->dev = drm;
-	drm->dev_private = vc4;
 	INIT_LIST_HEAD(&vc4->debugfs_list);

 	mutex_init(&vc4->bin_bo_lock);

 	ret = vc4_bo_cache_init(drm);
 	if (ret)
-		goto dev_put;
+		return ret;

-	drm_mode_config_init(drm);
+	ret = drmm_mode_config_init(drm);
+	if (ret)
+		return ret;

-	vc4_gem_init(drm);
+	ret = vc4_gem_init(drm);
+	if (ret)
+		return ret;

 	ret = component_bind_all(dev, drm);
 	if (ret)
-		goto gem_destroy;
+		return ret;

 	ret = vc4_plane_create_additional_planes(drm);
 	if (ret)
@@ -312,30 +312,17 @@ static int vc4_drm_bind(struct device *dev)

 unbind_all:
 	component_unbind_all(dev, drm);
-gem_destroy:
-	vc4_gem_destroy(drm);
-	drm_mode_config_cleanup(drm);
-	vc4_bo_cache_destroy(drm);
-dev_put:
-	drm_dev_put(drm);
+
 	return ret;
 }

 static void vc4_drm_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct vc4_dev *vc4 = to_vc4_dev(drm);

 	drm_dev_unregister(drm);

 	drm_atomic_helper_shutdown(drm);
-
-	drm_mode_config_cleanup(drm);
-
-	drm_atomic_private_obj_fini(&vc4->load_tracker);
-	drm_atomic_private_obj_fini(&vc4->ctm_manager);
-
-	drm_dev_put(drm);
 }

 static const struct component_master_ops vc4_drm_ops = {
--- a/Show More
+++ b/Show More