Merge drm/drm-next into drm-misc-next

drm-misc-next hasn't been updated in a while and I need a post -rc2
state to merge some vc4 patches.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>

Documentation/admin-guide/README.rst

@@ -259,7 +259,7 @@ Configuring the kernel
 Compiling the kernel
 --------------------
 
- - Make sure you have at least gcc 4.9 available.
+ - Make sure you have at least gcc 5.1 available.
    For more information, refer to :ref:`Documentation/process/changes.rst <changes>`.
 
    Please note that you can still run a.out user programs with this kernel.

Documentation/devicetree/bindings/arm/tegra.yaml

@@ -54,7 +54,7 @@ properties:
           - const: toradex,apalis_t30
           - const: nvidia,tegra30
       - items:
-          - const: toradex,apalis_t30-eval-v1.1
+          - const: toradex,apalis_t30-v1.1-eval
           - const: toradex,apalis_t30-eval
           - const: toradex,apalis_t30-v1.1
           - const: toradex,apalis_t30

Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt

@@ -9,7 +9,7 @@ function block.
 
 All DISP device tree nodes must be siblings to the central MMSYS_CONFIG node.
 For a description of the MMSYS_CONFIG binding, see
-Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.txt.
+Documentation/devicetree/bindings/arm/mediatek/mediatek,mmsys.yaml.
 
 DISP function blocks
 ====================

Documentation/devicetree/bindings/display/renesas,du.yaml

@@ -39,6 +39,7 @@ properties:
       - renesas,du-r8a77980 # for R-Car V3H compatible DU
       - renesas,du-r8a77990 # for R-Car E3 compatible DU
       - renesas,du-r8a77995 # for R-Car D3 compatible DU
+      - renesas,du-r8a779a0 # for R-Car V3U compatible DU
 
   reg:
     maxItems: 1
@@ -773,6 +774,56 @@ allOf:
         - reset-names
         - renesas,vsps
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,du-r8a779a0
+    then:
+      properties:
+        clocks:
+          items:
+            - description: Functional clock
+
+        clock-names:
+          maxItems: 1
+          items:
+            - const: du.0
+
+        interrupts:
+          maxItems: 2
+
+        resets:
+          maxItems: 1
+
+        reset-names:
+          items:
+            - const: du.0
+
+        ports:
+          properties:
+            port@0:
+              description: DSI 0
+            port@1:
+              description: DSI 1
+            port@2: false
+            port@3: false
+
+          required:
+            - port@0
+            - port@1
+
+        renesas,vsps:
+          minItems: 2
+
+      required:
+        - clock-names
+        - interrupts
+        - resets
+        - reset-names
+        - renesas,vsps
+
 additionalProperties: false
 
 examples:

Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml

@@ -19,7 +19,9 @@ properties:
       - const: allwinner,sun8i-v3s-emac
       - const: allwinner,sun50i-a64-emac
       - items:
-          - const: allwinner,sun50i-h6-emac
+          - enum:
+              - allwinner,sun20i-d1-emac
+              - allwinner,sun50i-h6-emac
           - const: allwinner,sun50i-a64-emac
 
   reg:

Documentation/devicetree/bindings/ufs/samsung,exynos-ufs.yaml

@@ -0,0 +1,89 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ufs/samsung,exynos-ufs.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Samsung SoC series UFS host controller Device Tree Bindings
+
+maintainers:
+  - Alim Akhtar <alim.akhtar@samsung.com>
+
+description: |
+  Each Samsung UFS host controller instance should have its own node.
+  This binding define Samsung specific binding other then what is used
+  in the common ufshcd bindings
+  [1] Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt
+
+properties:
+
+  compatible:
+    enum:
+      - samsung,exynos7-ufs
+
+  reg:
+    items:
+      - description: HCI register
+      - description: vendor specific register
+      - description: unipro register
+      - description: UFS protector register
+
+  reg-names:
+    items:
+      - const: hci
+      - const: vs_hci
+      - const: unipro
+      - const: ufsp
+
+  clocks:
+    items:
+      - description: ufs link core clock
+      - description: unipro main clock
+
+  clock-names:
+    items:
+      - const: core_clk
+      - const: sclk_unipro_main
+
+  interrupts:
+    maxItems: 1
+
+  phys:
+    maxItems: 1
+
+  phy-names:
+    const: ufs-phy
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - phys
+  - phy-names
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/exynos7-clk.h>
+
+    ufs: ufs@15570000 {
+       compatible = "samsung,exynos7-ufs";
+       reg = <0x15570000 0x100>,
+             <0x15570100 0x100>,
+             <0x15571000 0x200>,
+             <0x15572000 0x300>;
+       reg-names = "hci", "vs_hci", "unipro", "ufsp";
+       interrupts = <GIC_SPI 200 IRQ_TYPE_LEVEL_HIGH>;
+       clocks = <&clock_fsys1 ACLK_UFS20_LINK>,
+                <&clock_fsys1 SCLK_UFSUNIPRO20_USER>;
+       clock-names = "core_clk", "sclk_unipro_main";
+       pinctrl-names = "default";
+       pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>;
+       phys = <&ufs_phy>;
+       phy-names = "ufs-phy";
+    };
+...

Documentation/gpu/amdgpu.rst

@@ -300,8 +300,8 @@ pcie_replay_count
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
    :doc: pcie_replay_count
 
-+GPU SmartShift Information
+GPU SmartShift Information
-============================
+==========================
 
 GPU SmartShift information via sysfs
 

Documentation/gpu/i915.rst

@@ -183,26 +183,23 @@ Frame Buffer Compression (FBC)
 Display Refresh Rate Switching (DRRS)
 -------------------------------------
 
-.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dp.c
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_drrs.c
    :doc: Display Refresh Rate Switching (DRRS)
 
-.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dp.c
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_drrs.c
-   :functions: intel_dp_set_drrs_state
+   :functions: intel_drrs_enable
 
-.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dp.c
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_drrs.c
-   :functions: intel_edp_drrs_enable
+   :functions: intel_drrs_disable
 
-.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dp.c
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_drrs.c
-   :functions: intel_edp_drrs_disable
+   :functions: intel_drrs_invalidate
 
-.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dp.c
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_drrs.c
-   :functions: intel_edp_drrs_invalidate
+   :functions: intel_drrs_flush
 
-.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dp.c
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_drrs.c
-   :functions: intel_edp_drrs_flush
+   :functions: intel_drrs_init
-
-.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dp.c
-   :functions: intel_dp_drrs_init
 
 DPIO
 ----
@@ -474,6 +471,14 @@ Object Tiling IOCTLs
 .. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_tiling.c
    :doc: buffer object tiling
 
+Protected Objects
+-----------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/pxp/intel_pxp.c
+   :doc: PXP
+
+.. kernel-doc:: drivers/gpu/drm/i915/pxp/intel_pxp_types.h
+
 Microcontrollers
 ================
 
@@ -498,6 +503,8 @@ GuC
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
    :doc: GuC
 
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.h
+
 GuC Firmware Layout
 ~~~~~~~~~~~~~~~~~~~
 

Documentation/gpu/rfc/i915_parallel_execbuf.h

@@ -1,122 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2021 Intel Corporation
- */
-
-#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
-
-/**
- * struct drm_i915_context_engines_parallel_submit - Configure engine for
- * parallel submission.
- *
- * Setup a slot in the context engine map to allow multiple BBs to be submitted
- * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
- * in parallel. Multiple hardware contexts are created internally in the i915
- * run these BBs. Once a slot is configured for N BBs only N BBs can be
- * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
- * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
- * many BBs there are based on the slot's configuration. The N BBs are the last
- * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
- *
- * The default placement behavior is to create implicit bonds between each
- * context if each context maps to more than 1 physical engine (e.g. context is
- * a virtual engine). Also we only allow contexts of same engine class and these
- * contexts must be in logically contiguous order. Examples of the placement
- * behavior described below. Lastly, the default is to not allow BBs to
- * preempted mid BB rather insert coordinated preemption on all hardware
- * contexts between each set of BBs. Flags may be added in the future to change
- * both of these default behaviors.
- *
- * Returns -EINVAL if hardware context placement configuration is invalid or if
- * the placement configuration isn't supported on the platform / submission
- * interface.
- * Returns -ENODEV if extension isn't supported on the platform / submission
- * interface.
- *
- * .. code-block:: none
- *
- *	Example 1 pseudo code:
- *	CS[X] = generic engine of same class, logical instance X
- *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
- *	set_engines(INVALID)
- *	set_parallel(engine_index=0, width=2, num_siblings=1,
- *		     engines=CS[0],CS[1])
- *
- *	Results in the following valid placement:
- *	CS[0], CS[1]
- *
- *	Example 2 pseudo code:
- *	CS[X] = generic engine of same class, logical instance X
- *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
- *	set_engines(INVALID)
- *	set_parallel(engine_index=0, width=2, num_siblings=2,
- *		     engines=CS[0],CS[2],CS[1],CS[3])
- *
- *	Results in the following valid placements:
- *	CS[0], CS[1]
- *	CS[2], CS[3]
- *
- *	This can also be thought of as 2 virtual engines described by 2-D array
- *	in the engines the field with bonds placed between each index of the
- *	virtual engines. e.g. CS[0] is bonded to CS[1], CS[2] is bonded to
- *	CS[3].
- *	VE[0] = CS[0], CS[2]
- *	VE[1] = CS[1], CS[3]
- *
- *	Example 3 pseudo code:
- *	CS[X] = generic engine of same class, logical instance X
- *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
- *	set_engines(INVALID)
- *	set_parallel(engine_index=0, width=2, num_siblings=2,
- *		     engines=CS[0],CS[1],CS[1],CS[3])
- *
- *	Results in the following valid and invalid placements:
- *	CS[0], CS[1]
- *	CS[1], CS[3] - Not logical contiguous, return -EINVAL
- */
-struct drm_i915_context_engines_parallel_submit {
-	/**
-	 * @base: base user extension.
-	 */
-	struct i915_user_extension base;
-
-	/**
-	 * @engine_index: slot for parallel engine
-	 */
-	__u16 engine_index;
-
-	/**
-	 * @width: number of contexts per parallel engine
-	 */
-	__u16 width;
-
-	/**
-	 * @num_siblings: number of siblings per context
-	 */
-	__u16 num_siblings;
-
-	/**
-	 * @mbz16: reserved for future use; must be zero
-	 */
-	__u16 mbz16;
-
-	/**
-	 * @flags: all undefined flags must be zero, currently not defined flags
-	 */
-	__u64 flags;
-
-	/**
-	 * @mbz64: reserved for future use; must be zero
-	 */
-	__u64 mbz64[3];
-
-	/**
-	 * @engines: 2-d array of engine instances to configure parallel engine
-	 *
-	 * length = width (i) * num_siblings (j)
-	 * index = j + i * num_siblings
-	 */
-	struct i915_engine_class_instance engines[0];
-
-} __packed;
-

Documentation/gpu/rfc/i915_scheduler.rst

@@ -135,8 +135,8 @@ Add I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT and
 drm_i915_context_engines_parallel_submit to the uAPI to implement this
 extension.
 
-.. kernel-doc:: Documentation/gpu/rfc/i915_parallel_execbuf.h
+.. kernel-doc:: include/uapi/drm/i915_drm.h
-        :functions: drm_i915_context_engines_parallel_submit
+        :functions: i915_context_engines_parallel_submit
 
 Extend execbuf2 IOCTL to support submitting N BBs in a single IOCTL
 -------------------------------------------------------------------

Documentation/networking/dsa/sja1105.rst

@@ -296,7 +296,7 @@ not available.
 Device Tree bindings and board design
 =====================================
 
-This section references ``Documentation/devicetree/bindings/net/dsa/sja1105.txt``
+This section references ``Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml``
 and aims to showcase some potential switch caveats.
 
 RMII PHY role and out-of-band signaling

Documentation/process/changes.rst

@@ -29,7 +29,7 @@ you probably needn't concern yourself with pcmciautils.
 ====================== ===============  ========================================
         Program        Minimal version       Command to check the version
 ====================== ===============  ========================================
-GNU C                  4.9              gcc --version
+GNU C                  5.1              gcc --version
 Clang/LLVM (optional)  10.0.1           clang --version
 GNU make               3.81             make --version
 binutils               2.23             ld -v

Documentation/translations/zh_CN/admin-guide/README.rst

@@ -223,7 +223,7 @@ Linux内核5.x版本 <http://kernel.org/>
 编译内核
 ---------
 
- - 确保您至少有gcc 4.9可用。
+ - 确保您至少有gcc 5.1可用。
    有关更多信息，请参阅 :ref:`Documentation/process/changes.rst <changes>` 。
 
    请注意，您仍然可以使用此内核运行a.out用户程序。

Documentation/translations/zh_TW/admin-guide/README.rst

@@ -226,7 +226,7 @@ Linux內核5.x版本 <http://kernel.org/>
 編譯內核
 ---------
 
- - 確保您至少有gcc 4.9可用。
+ - 確保您至少有gcc 5.1可用。
    有關更多信息，請參閱 :ref:`Documentation/process/changes.rst <changes>` 。
 
    請注意，您仍然可以使用此內核運行a.out用戶程序。

MAINTAINERS

@@ -977,12 +977,12 @@ L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/amd-pmc.*
 
-AMD POWERPLAY
+AMD POWERPLAY AND SWSMU
 M:	Evan Quan <evan.quan@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
 T:	git https://gitlab.freedesktop.org/agd5f/linux.git
-F:	drivers/gpu/drm/amd/pm/powerplay/
+F:	drivers/gpu/drm/amd/pm/
 
 AMD PTDMA DRIVER
 M:	Sanjay R Mehta <sanju.mehta@amd.com>
@@ -14364,7 +14364,8 @@ F:	Documentation/devicetree/bindings/pci/intel,ixp4xx-pci.yaml
 F:	drivers/pci/controller/pci-ixp4xx.c
 
 PCI DRIVER FOR INTEL VOLUME MANAGEMENT DEVICE (VMD)
-M:	Jonathan Derrick <jonathan.derrick@intel.com>
+M:	Nirmal Patel <nirmal.patel@linux.intel.com>
+R:	Jonathan Derrick <jonathan.derrick@linux.dev>
 L:	linux-pci@vger.kernel.org
 S:	Supported
 F:	drivers/pci/controller/vmd.c

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Opossums on Parade
 
 # *DOCUMENTATION*
@@ -849,12 +849,6 @@ endif
 
 DEBUG_CFLAGS	:=
 
-# Workaround for GCC versions < 5.0
-# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=61801
-ifdef CONFIG_CC_IS_GCC
-DEBUG_CFLAGS	+= $(call cc-ifversion, -lt, 0500, $(call cc-option, -fno-var-tracking-assignments))
-endif
-
 ifdef CONFIG_DEBUG_INFO
 
 ifdef CONFIG_DEBUG_INFO_SPLIT

arch/alpha/Kconfig

@@ -20,7 +20,7 @@ config ALPHA
 	select NEED_SG_DMA_LENGTH
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
-	select GENERIC_PCI_IOMAP if PCI
+	select GENERIC_PCI_IOMAP
 	select AUTO_IRQ_AFFINITY if SMP
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -199,7 +199,6 @@ config ALPHA_EIGER
 
 config ALPHA_JENSEN
 	bool "Jensen"
-	depends on BROKEN
 	select HAVE_EISA
 	help
 	  DEC PC 150 AXP (aka Jensen): This is a very old Digital system - one

arch/alpha/include/asm/asm-prototypes.h

@@ -16,3 +16,4 @@ extern void __divlu(void);
 extern void __remlu(void);
 extern void __divqu(void);
 extern void __remqu(void);
+extern unsigned long __udiv_qrnnd(unsigned long *, unsigned long, unsigned long , unsigned long);

arch/alpha/include/asm/io.h

@@ -60,7 +60,7 @@ extern inline void set_hae(unsigned long new_hae)
  * Change virtual addresses to physical addresses and vv.
  */
 #ifdef USE_48_BIT_KSEG
-static inline unsigned long virt_to_phys(void *address)
+static inline unsigned long virt_to_phys(volatile void *address)
 {
 	return (unsigned long)address - IDENT_ADDR;
 }
@@ -70,7 +70,7 @@ static inline void * phys_to_virt(unsigned long address)
 	return (void *) (address + IDENT_ADDR);
 }
 #else
-static inline unsigned long virt_to_phys(void *address)
+static inline unsigned long virt_to_phys(volatile void *address)
 {
         unsigned long phys = (unsigned long)address;
 
@@ -106,7 +106,7 @@ static inline void * phys_to_virt(unsigned long address)
 extern unsigned long __direct_map_base;
 extern unsigned long __direct_map_size;
 
-static inline unsigned long __deprecated virt_to_bus(void *address)
+static inline unsigned long __deprecated virt_to_bus(volatile void *address)
 {
 	unsigned long phys = virt_to_phys(address);
 	unsigned long bus = phys + __direct_map_base;

arch/alpha/include/asm/jensen.h

@@ -111,18 +111,18 @@ __EXTERN_INLINE void jensen_set_hae(unsigned long addr)
  * convinced that I need one of the newer machines.
  */
 
-static inline unsigned int jensen_local_inb(unsigned long addr)
+__EXTERN_INLINE unsigned int jensen_local_inb(unsigned long addr)
 {
 	return 0xff & *(vuip)((addr << 9) + EISA_VL82C106);
 }
 
-static inline void jensen_local_outb(u8 b, unsigned long addr)
+__EXTERN_INLINE void jensen_local_outb(u8 b, unsigned long addr)
 {
 	*(vuip)((addr << 9) + EISA_VL82C106) = b;
 	mb();
 }
 
-static inline unsigned int jensen_bus_inb(unsigned long addr)
+__EXTERN_INLINE unsigned int jensen_bus_inb(unsigned long addr)
 {
 	long result;
 
@@ -131,7 +131,7 @@ static inline unsigned int jensen_bus_inb(unsigned long addr)
 	return __kernel_extbl(result, addr & 3);
 }
 
-static inline void jensen_bus_outb(u8 b, unsigned long addr)
+__EXTERN_INLINE void jensen_bus_outb(u8 b, unsigned long addr)
 {
 	jensen_set_hae(0);
 	*(vuip)((addr << 7) + EISA_IO + 0x00) = b * 0x01010101;

arch/alpha/include/asm/setup.h

@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ALPHA_SETUP_H
+#define __ALPHA_SETUP_H
+
+#include <uapi/asm/setup.h>
+
+/*
+ * We leave one page for the initial stack page, and one page for
+ * the initial process structure. Also, the console eats 3 MB for
+ * the initial bootloader (one of which we can reclaim later).
+ */
+#define BOOT_PCB	0x20000000
+#define BOOT_ADDR	0x20000000
+/* Remove when official MILO sources have ELF support: */
+#define BOOT_SIZE	(16*1024)
+
+#ifdef CONFIG_ALPHA_LEGACY_START_ADDRESS
+#define KERNEL_START_PHYS	0x300000 /* Old bootloaders hardcoded this.  */
+#else
+#define KERNEL_START_PHYS	0x1000000 /* required: Wildfire/Titan/Marvel */
+#endif
+
+#define KERNEL_START	(PAGE_OFFSET+KERNEL_START_PHYS)
+#define SWAPPER_PGD	KERNEL_START
+#define INIT_STACK	(PAGE_OFFSET+KERNEL_START_PHYS+0x02000)
+#define EMPTY_PGT	(PAGE_OFFSET+KERNEL_START_PHYS+0x04000)
+#define EMPTY_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x08000)
+#define ZERO_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x0A000)
+
+#define START_ADDR	(PAGE_OFFSET+KERNEL_START_PHYS+0x10000)
+
+/*
+ * This is setup by the secondary bootstrap loader.  Because
+ * the zero page is zeroed out as soon as the vm system is
+ * initialized, we need to copy things out into a more permanent
+ * place.
+ */
+#define PARAM			ZERO_PGE
+#define COMMAND_LINE		((char *)(absolute_pointer(PARAM + 0x0000)))
+#define INITRD_START		(*(unsigned long *) (PARAM+0x100))
+#define INITRD_SIZE		(*(unsigned long *) (PARAM+0x108))
+
+#endif

arch/alpha/include/uapi/asm/setup.h

@@ -1,43 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef __ALPHA_SETUP_H
+#ifndef _UAPI__ALPHA_SETUP_H
-#define __ALPHA_SETUP_H
+#define _UAPI__ALPHA_SETUP_H
 
 #define COMMAND_LINE_SIZE	256
 
-/*
+#endif /* _UAPI__ALPHA_SETUP_H */
- * We leave one page for the initial stack page, and one page for
- * the initial process structure. Also, the console eats 3 MB for
- * the initial bootloader (one of which we can reclaim later).
- */
-#define BOOT_PCB	0x20000000
-#define BOOT_ADDR	0x20000000
-/* Remove when official MILO sources have ELF support: */
-#define BOOT_SIZE	(16*1024)
-
-#ifdef CONFIG_ALPHA_LEGACY_START_ADDRESS
-#define KERNEL_START_PHYS	0x300000 /* Old bootloaders hardcoded this.  */
-#else
-#define KERNEL_START_PHYS	0x1000000 /* required: Wildfire/Titan/Marvel */
-#endif
-
-#define KERNEL_START	(PAGE_OFFSET+KERNEL_START_PHYS)
-#define SWAPPER_PGD	KERNEL_START
-#define INIT_STACK	(PAGE_OFFSET+KERNEL_START_PHYS+0x02000)
-#define EMPTY_PGT	(PAGE_OFFSET+KERNEL_START_PHYS+0x04000)
-#define EMPTY_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x08000)
-#define ZERO_PGE	(PAGE_OFFSET+KERNEL_START_PHYS+0x0A000)
-
-#define START_ADDR	(PAGE_OFFSET+KERNEL_START_PHYS+0x10000)
-
-/*
- * This is setup by the secondary bootstrap loader.  Because
- * the zero page is zeroed out as soon as the vm system is
- * initialized, we need to copy things out into a more permanent
- * place.
- */
-#define PARAM			ZERO_PGE
-#define COMMAND_LINE		((char*)(PARAM + 0x0000))
-#define INITRD_START		(*(unsigned long *) (PARAM+0x100))
-#define INITRD_SIZE		(*(unsigned long *) (PARAM+0x108))
-
-#endif

arch/alpha/kernel/sys_jensen.c

@@ -7,6 +7,11 @@
  *
  * Code supporting the Jensen.
  */
+#define __EXTERN_INLINE
+#include <asm/io.h>
+#include <asm/jensen.h>
+#undef  __EXTERN_INLINE
+
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -17,11 +22,6 @@
 
 #include <asm/ptrace.h>
 
-#define __EXTERN_INLINE inline
-#include <asm/io.h>
-#include <asm/jensen.h>
-#undef  __EXTERN_INLINE
-
 #include <asm/dma.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>

arch/alpha/lib/Makefile

@@ -14,6 +14,7 @@ ev6-$(CONFIG_ALPHA_EV6) := ev6-
 ev67-$(CONFIG_ALPHA_EV67) := ev67-
 
 lib-y =	__divqu.o __remqu.o __divlu.o __remlu.o \
+	udiv-qrnnd.o \
 	udelay.o \
 	$(ev6-y)memset.o \
 	$(ev6-y)memcpy.o \

arch/alpha/lib/udiv-qrnnd.S

@@ -25,6 +25,7 @@
  # along with GCC; see the file COPYING.  If not, write to the 
  # Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
  # MA 02111-1307, USA.
+#include <asm/export.h>
 
         .set noreorder
         .set noat
@@ -161,3 +162,4 @@ $Odd:
 	ret	$31,($26),1
 
 	.end	__udiv_qrnnd
+EXPORT_SYMBOL(__udiv_qrnnd)

arch/alpha/math-emu/Makefile

@@ -7,4 +7,4 @@ ccflags-y := -w
 
 obj-$(CONFIG_MATHEMU) += math-emu.o
 
-math-emu-objs := math.o qrnnd.o
+math-emu-objs := math.o

arch/alpha/math-emu/math.c

@@ -403,5 +403,3 @@ alpha_fp_emul_imprecise (struct pt_regs *regs, unsigned long write_mask)
 egress:
 	return si_code;
 }
-
-EXPORT_SYMBOL(__udiv_qrnnd);

arch/arm64/Kconfig

@@ -86,7 +86,7 @@ config ARM64
 	select ARCH_SUPPORTS_LTO_CLANG_THIN
 	select ARCH_SUPPORTS_CFI_CLANG
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
+	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
 	select ARCH_WANT_DEFAULT_BPF_JIT

arch/arm64/kernel/fpsimd.c

@@ -513,7 +513,7 @@ size_t sve_state_size(struct task_struct const *task)
 void sve_alloc(struct task_struct *task)
 {
 	if (task->thread.sve_state) {
-		memset(task->thread.sve_state, 0, sve_state_size(current));
+		memset(task->thread.sve_state, 0, sve_state_size(task));
 		return;
 	}
 

arch/arm64/kernel/process.c

@@ -18,7 +18,6 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/nospec.h>
-#include <linux/sched.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
 #include <linux/unistd.h>
@@ -58,7 +57,7 @@
 
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>
-unsigned long __stack_chk_guard __read_mostly;
+unsigned long __stack_chk_guard __ro_after_init;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 

arch/m68k/include/asm/raw_io.h

@@ -17,21 +17,21 @@
  * two accesses to memory, which may be undesirable for some devices.
  */
 #define in_8(addr) \
-    ({ u8 __v = (*(__force volatile u8 *) (addr)); __v; })
+    ({ u8 __v = (*(__force volatile u8 *) (unsigned long)(addr)); __v; })
 #define in_be16(addr) \
-    ({ u16 __v = (*(__force volatile u16 *) (addr)); __v; })
+    ({ u16 __v = (*(__force volatile u16 *) (unsigned long)(addr)); __v; })
 #define in_be32(addr) \
-    ({ u32 __v = (*(__force volatile u32 *) (addr)); __v; })
+    ({ u32 __v = (*(__force volatile u32 *) (unsigned long)(addr)); __v; })
 #define in_le16(addr) \
-    ({ u16 __v = le16_to_cpu(*(__force volatile __le16 *) (addr)); __v; })
+    ({ u16 __v = le16_to_cpu(*(__force volatile __le16 *) (unsigned long)(addr)); __v; })
 #define in_le32(addr) \
-    ({ u32 __v = le32_to_cpu(*(__force volatile __le32 *) (addr)); __v; })
+    ({ u32 __v = le32_to_cpu(*(__force volatile __le32 *) (unsigned long)(addr)); __v; })
 
-#define out_8(addr,b) (void)((*(__force volatile u8 *) (addr)) = (b))
+#define out_8(addr,b) (void)((*(__force volatile u8 *) (unsigned long)(addr)) = (b))
-#define out_be16(addr,w) (void)((*(__force volatile u16 *) (addr)) = (w))
+#define out_be16(addr,w) (void)((*(__force volatile u16 *) (unsigned long)(addr)) = (w))
-#define out_be32(addr,l) (void)((*(__force volatile u32 *) (addr)) = (l))
+#define out_be32(addr,l) (void)((*(__force volatile u32 *) (unsigned long)(addr)) = (l))
-#define out_le16(addr,w) (void)((*(__force volatile __le16 *) (addr)) = cpu_to_le16(w))
+#define out_le16(addr,w) (void)((*(__force volatile __le16 *) (unsigned long)(addr)) = cpu_to_le16(w))
-#define out_le32(addr,l) (void)((*(__force volatile __le32 *) (addr)) = cpu_to_le32(l))
+#define out_le32(addr,l) (void)((*(__force volatile __le32 *) (unsigned long)(addr)) = cpu_to_le32(l))
 
 #define raw_inb in_8
 #define raw_inw in_be16

arch/m68k/mvme147/config.c

@@ -171,7 +171,6 @@ static int bcd2int (unsigned char b)
 
 int mvme147_hwclk(int op, struct rtc_time *t)
 {
-#warning check me!
 	if (!op) {
 		m147_rtc->ctrl = RTC_READ;
 		t->tm_year = bcd2int (m147_rtc->bcd_year);
@@ -183,6 +182,9 @@ int mvme147_hwclk(int op, struct rtc_time *t)
 		m147_rtc->ctrl = 0;
 		if (t->tm_year < 70)
 			t->tm_year += 100;
+	} else {
+		/* FIXME Setting the time is not yet supported */
+		return -EOPNOTSUPP;
 	}
 	return 0;
 }

arch/m68k/mvme16x/config.c

@@ -436,7 +436,6 @@ int bcd2int (unsigned char b)
 
 int mvme16x_hwclk(int op, struct rtc_time *t)
 {
-#warning check me!
 	if (!op) {
 		rtc->ctrl = RTC_READ;
 		t->tm_year = bcd2int (rtc->bcd_year);
@@ -448,6 +447,9 @@ int mvme16x_hwclk(int op, struct rtc_time *t)
 		rtc->ctrl = 0;
 		if (t->tm_year < 70)
 			t->tm_year += 100;
+	} else {
+		/* FIXME Setting the time is not yet supported */
+		return -EOPNOTSUPP;
 	}
 	return 0;
 }

arch/parisc/include/asm/page.h

@@ -184,7 +184,7 @@ extern int npmem_ranges;
 #include <asm-generic/getorder.h>
 #include <asm/pdc.h>
 
-#define PAGE0   ((struct zeropage *)__PAGE_OFFSET)
+#define PAGE0   ((struct zeropage *)absolute_pointer(__PAGE_OFFSET))
 
 /* DEFINITION OF THE ZERO-PAGE (PAG0) */
 /* based on work by Jason Eckhardt (jason@equator.com) */

arch/parisc/lib/iomap.c

@@ -513,12 +513,15 @@ void ioport_unmap(void __iomem *addr)
 	}
 }
 
+#ifdef CONFIG_PCI
 void pci_iounmap(struct pci_dev *dev, void __iomem * addr)
 {
 	if (!INDIRECT_ADDR(addr)) {
 		iounmap(addr);
 	}
 }
+EXPORT_SYMBOL(pci_iounmap);
+#endif
 
 EXPORT_SYMBOL(ioread8);
 EXPORT_SYMBOL(ioread16);
@@ -544,4 +547,3 @@ EXPORT_SYMBOL(iowrite16_rep);
 EXPORT_SYMBOL(iowrite32_rep);
 EXPORT_SYMBOL(ioport_map);
 EXPORT_SYMBOL(ioport_unmap);
-EXPORT_SYMBOL(pci_iounmap);

arch/powerpc/boot/Makefile

@@ -35,7 +35,6 @@ endif
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		 -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \
 		 -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
-		 -include $(srctree)/include/linux/compiler_attributes.h \
 		 $(LINUXINCLUDE)
 
 ifdef CONFIG_PPC64_BOOT_WRAPPER
@@ -70,6 +69,7 @@ ifeq ($(call cc-option-yn, -fstack-protector),y)
 BOOTCFLAGS	+= -fno-stack-protector
 endif
 
+BOOTCFLAGS	+= -include $(srctree)/include/linux/compiler_attributes.h
 BOOTCFLAGS	+= -I$(objtree)/$(obj) -I$(srctree)/$(obj)
 
 DTC_FLAGS	?= -p 1024

arch/powerpc/include/asm/asm-const.h

@@ -12,16 +12,6 @@
 #  define ASM_CONST(x)		__ASM_CONST(x)
 #endif
 
-/*
- * Inline assembly memory constraint
- *
- * GCC 4.9 doesn't properly handle pre update memory constraint "m<>"
- *
- */
-#if defined(GCC_VERSION) && GCC_VERSION < 50000
-#define UPD_CONSTR ""
-#else
 #define UPD_CONSTR "<>"
-#endif
 
 #endif /* _ASM_POWERPC_ASM_CONST_H */

arch/powerpc/kernel/interrupt.c

@@ -18,6 +18,7 @@
 #include <asm/switch_to.h>
 #include <asm/syscall.h>
 #include <asm/time.h>
+#include <asm/tm.h>
 #include <asm/unistd.h>
 
 #if defined(CONFIG_PPC_ADV_DEBUG_REGS) && defined(CONFIG_PPC32)
@@ -136,6 +137,48 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	 */
 	irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
 
+	/*
+	 * If system call is called with TM active, set _TIF_RESTOREALL to
+	 * prevent RFSCV being used to return to userspace, because POWER9
+	 * TM implementation has problems with this instruction returning to
+	 * transactional state. Final register values are not relevant because
+	 * the transaction will be aborted upon return anyway. Or in the case
+	 * of unsupported_scv SIGILL fault, the return state does not much
+	 * matter because it's an edge case.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+			unlikely(MSR_TM_TRANSACTIONAL(regs->msr)))
+		current_thread_info()->flags |= _TIF_RESTOREALL;
+
+	/*
+	 * If the system call was made with a transaction active, doom it and
+	 * return without performing the system call. Unless it was an
+	 * unsupported scv vector, in which case it's treated like an illegal
+	 * instruction.
+	 */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
+	    !trap_is_unsupported_scv(regs)) {
+		/* Enable TM in the kernel, and disable EE (for scv) */
+		hard_irq_disable();
+		mtmsr(mfmsr() | MSR_TM);
+
+		/* tabort, this dooms the transaction, nothing else */
+		asm volatile(".long 0x7c00071d | ((%0) << 16)"
+				:: "r"(TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT));
+
+		/*
+		 * Userspace will never see the return value. Execution will
+		 * resume after the tbegin. of the aborted transaction with the
+		 * checkpointed register state. A context switch could occur
+		 * or signal delivered to the process before resuming the
+		 * doomed transaction context, but that should all be handled
+		 * as expected.
+		 */
+		return -ENOSYS;
+	}
+#endif // CONFIG_PPC_TRANSACTIONAL_MEM
+
 	local_irq_enable();
 
 	if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) {

arch/powerpc/kernel/interrupt_64.S

@@ -12,7 +12,6 @@
 #include <asm/mmu.h>
 #include <asm/ppc_asm.h>
 #include <asm/ptrace.h>
-#include <asm/tm.h>
 
 	.section	".toc","aw"
 SYS_CALL_TABLE:
@@ -55,12 +54,6 @@ COMPAT_SYS_CALL_TABLE:
 	.globl system_call_vectored_\name
 system_call_vectored_\name:
 _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-BEGIN_FTR_SECTION
-	extrdi.	r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
-	bne	tabort_syscall
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
-#endif
 	SCV_INTERRUPT_TO_KERNEL
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
@@ -247,12 +240,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_common_real)
 	.globl system_call_common
 system_call_common:
 _ASM_NOKPROBE_SYMBOL(system_call_common)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-BEGIN_FTR_SECTION
-	extrdi.	r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
-	bne	tabort_syscall
-END_FTR_SECTION_IFSET(CPU_FTR_TM)
-#endif
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
@@ -425,34 +412,6 @@ SOFT_MASK_TABLE(.Lsyscall_rst_start, 1b)
 RESTART_TABLE(.Lsyscall_rst_start, .Lsyscall_rst_end, syscall_restart)
 #endif
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-tabort_syscall:
-_ASM_NOKPROBE_SYMBOL(tabort_syscall)
-	/* Firstly we need to enable TM in the kernel */
-	mfmsr	r10
-	li	r9, 1
-	rldimi	r10, r9, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r10, 0
-
-	/* tabort, this dooms the transaction, nothing else */
-	li	r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
-	TABORT(R9)
-
-	/*
-	 * Return directly to userspace. We have corrupted user register state,
-	 * but userspace will never see that register state. Execution will
-	 * resume after the tbegin of the aborted transaction with the
-	 * checkpointed register state.
-	 */
-	li	r9, MSR_RI
-	andc	r10, r10, r9
-	mtmsrd	r10, 1
-	mtspr	SPRN_SRR0, r11
-	mtspr	SPRN_SRR1, r12
-	RFI_TO_USER
-	b	.	/* prevent speculative execution */
-#endif
-
 	/*
 	 * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
 	 * touched, no exit work created, then this can be used.

arch/powerpc/kernel/mce.c

@@ -249,6 +249,7 @@ void machine_check_queue_event(void)
 {
 	int index;
 	struct machine_check_event evt;
+	unsigned long msr;
 
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return;
@@ -262,8 +263,20 @@ void machine_check_queue_event(void)
 	memcpy(&local_paca->mce_info->mce_event_queue[index],
 	       &evt, sizeof(evt));
 
-	/* Queue irq work to process this event later. */
+	/*
+	 * Queue irq work to process this event later. Before
+	 * queuing the work enable translation for non radix LPAR,
+	 * as irq_work_queue may try to access memory outside RMO
+	 * region.
+	 */
+	if (!radix_enabled() && firmware_has_feature(FW_FEATURE_LPAR)) {
+		msr = mfmsr();
+		mtmsr(msr | MSR_IR | MSR_DR);
 		irq_work_queue(&mce_event_process_work);
+		mtmsr(msr);
+	} else {
+		irq_work_queue(&mce_event_process_work);
+	}
 }
 
 void mce_common_process_ue(struct pt_regs *regs,

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -2536,7 +2536,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_P9_TM_HV_ASSIST)
 	/* The following code handles the fake_suspend = 1 case */
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
-	stdu	r1, -PPC_MIN_STKFRM(r1)
+	stdu	r1, -TM_FRAME_SIZE(r1)
 
 	/* Turn on TM. */
 	mfmsr	r8
@@ -2551,10 +2551,42 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	nop
 
+	/*
+	 * It's possible that treclaim. may modify registers, if we have lost
+	 * track of fake-suspend state in the guest due to it using rfscv.
+	 * Save and restore registers in case this occurs.
+	 */
+	mfspr	r3, SPRN_DSCR
+	mfspr	r4, SPRN_XER
+	mfspr	r5, SPRN_AMR
+	/* SPRN_TAR would need to be saved here if the kernel ever used it */
+	mfcr	r12
+	SAVE_NVGPRS(r1)
+	SAVE_GPR(2, r1)
+	SAVE_GPR(3, r1)
+	SAVE_GPR(4, r1)
+	SAVE_GPR(5, r1)
+	stw	r12, 8(r1)
+	std	r1, HSTATE_HOST_R1(r13)
+
 	/* We have to treclaim here because that's the only way to do S->N */
 	li	r3, TM_CAUSE_KVM_RESCHED
 	TRECLAIM(R3)
 
+	GET_PACA(r13)
+	ld	r1, HSTATE_HOST_R1(r13)
+	REST_GPR(2, r1)
+	REST_GPR(3, r1)
+	REST_GPR(4, r1)
+	REST_GPR(5, r1)
+	lwz	r12, 8(r1)
+	REST_NVGPRS(r1)
+	mtspr	SPRN_DSCR, r3
+	mtspr	SPRN_XER, r4
+	mtspr	SPRN_AMR, r5
+	mtcr	r12
+	HMT_MEDIUM
+
 	/*
 	 * We were in fake suspend, so we are not going to save the
 	 * register state as the guest checkpointed state (since
@@ -2582,7 +2614,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	std	r5, VCPU_TFHAR(r9)
 	std	r6, VCPU_TFIAR(r9)
 
-	addi	r1, r1, PPC_MIN_STKFRM
+	addi	r1, r1, TM_FRAME_SIZE
 	ld	r0, PPC_LR_STKOFF(r1)
 	mtlr	r0
 	blr

arch/powerpc/sysdev/xics/xics-common.c

@@ -348,9 +348,9 @@ static int xics_host_map(struct irq_domain *domain, unsigned int virq,
 	if (xics_ics->check(xics_ics, hwirq))
 		return -EINVAL;
 
-	/* No chip data for the XICS domain */
+	/* Let the ICS be the chip data for the XICS domain. For ICS native */
 	irq_domain_set_info(domain, virq, hwirq, xics_ics->chip,
-			    NULL, handle_fasteoi_irq, NULL, NULL);
+			    xics_ics, handle_fasteoi_irq, NULL, NULL);
 
 	return 0;
 }

arch/riscv/Kconfig

@@ -236,7 +236,7 @@ config ARCH_RV32I
 config ARCH_RV64I
 	bool "RV64I"
 	select 64BIT
-	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && GCC_VERSION >= 50000
+	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
 	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && $(cc-option,-fpatchable-function-entry=8)
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL

arch/s390/Kconfig

@@ -685,16 +685,6 @@ config STACK_GUARD
 	  The minimum size for the stack guard should be 256 for 31 bit and
 	  512 for 64 bit.
 
-config WARN_DYNAMIC_STACK
-	def_bool n
-	prompt "Emit compiler warnings for function with dynamic stack usage"
-	help
-	  This option enables the compiler option -mwarn-dynamicstack. If the
-	  compiler supports this options generates warnings for functions
-	  that dynamically allocate stack space using alloca.
-
-	  Say N if you are unsure.
-
 endmenu
 
 menu "I/O subsystem"

arch/s390/Makefile

@@ -85,13 +85,6 @@ cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD)
 endif
 endif
 
-ifdef CONFIG_WARN_DYNAMIC_STACK
-  ifneq ($(call cc-option,-mwarn-dynamicstack),)
-    KBUILD_CFLAGS += -mwarn-dynamicstack
-    KBUILD_CFLAGS_DECOMPRESSOR += -mwarn-dynamicstack
-  endif
-endif
-
 ifdef CONFIG_EXPOLINE
   ifneq ($(call cc-option,$(CC_FLAGS_MARCH) -mindirect-branch=thunk),)
     CC_FLAGS_EXPOLINE := -mindirect-branch=thunk

arch/s390/configs/debug_defconfig

@@ -10,6 +10,7 @@ CONFIG_BPF_JIT=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_LSM=y
 CONFIG_PREEMPT=y
+CONFIG_SCHED_CORE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_TASKSTATS=y
@@ -503,6 +504,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MICROSOFT is not set
+# CONFIG_NET_VENDOR_LITEX is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
@@ -661,7 +663,6 @@ CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_NFSD_V4_SECURITY_LABEL=y
 CONFIG_CIFS=m
-CONFIG_CIFS_WEAK_PW_HASH=y
 CONFIG_CIFS_UPCALL=y
 CONFIG_CIFS_XATTR=y
 CONFIG_CIFS_POSIX=y
@@ -720,6 +721,8 @@ CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_BLAKE2S=m
+CONFIG_CRYPTO_MD4=m
+CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
 CONFIG_CRYPTO_SHA3=m
@@ -774,7 +777,6 @@ CONFIG_RANDOM32_SELFTEST=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_DMA_API_DEBUG=y
-CONFIG_STRING_SELFTEST=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_DEBUG_INFO=y
@@ -853,12 +855,12 @@ CONFIG_FAIL_FUNCTION=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LKDTM=m
 CONFIG_TEST_MIN_HEAP=y
-CONFIG_TEST_SORT=y
 CONFIG_KPROBES_SANITY_TEST=y
 CONFIG_RBTREE_TEST=y
 CONFIG_INTERVAL_TREE_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_STRING_SELFTEST=y
 CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m
 CONFIG_TEST_LIVEPATCH=m

arch/s390/configs/defconfig

@@ -8,6 +8,7 @@ CONFIG_BPF_SYSCALL=y
 CONFIG_BPF_JIT=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_LSM=y
+CONFIG_SCHED_CORE=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_TASKSTATS=y
@@ -494,6 +495,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MICROSOFT is not set
+# CONFIG_NET_VENDOR_LITEX is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
@@ -648,7 +650,6 @@ CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_NFSD_V4_SECURITY_LABEL=y
 CONFIG_CIFS=m
-CONFIG_CIFS_WEAK_PW_HASH=y
 CONFIG_CIFS_UPCALL=y
 CONFIG_CIFS_XATTR=y
 CONFIG_CIFS_POSIX=y
@@ -708,6 +709,8 @@ CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
 CONFIG_CRYPTO_BLAKE2S=m
+CONFIG_CRYPTO_MD4=m
+CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD160=m
 CONFIG_CRYPTO_SHA3=m

arch/s390/pci/pci_mmio.c

@@ -159,7 +159,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
 
 	mmap_read_lock(current->mm);
 	ret = -EINVAL;
-	vma = find_vma(current->mm, mmio_addr);
+	vma = vma_lookup(current->mm, mmio_addr);
 	if (!vma)
 		goto out_unlock_mmap;
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
@@ -298,7 +298,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
 
 	mmap_read_lock(current->mm);
 	ret = -EINVAL;
-	vma = find_vma(current->mm, mmio_addr);
+	vma = vma_lookup(current->mm, mmio_addr);
 	if (!vma)
 		goto out_unlock_mmap;
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))

arch/sh/boot/Makefile

@@ -80,30 +80,30 @@ $(obj)/vmlinux.bin.xz: $(obj)/vmlinux.bin FORCE
 $(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,lzo)
 
-$(obj)/uImage.bz2: $(obj)/vmlinux.bin.bz2
+$(obj)/uImage.bz2: $(obj)/vmlinux.bin.bz2 FORCE
 	$(call if_changed,uimage,bzip2)
 
-$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz
+$(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE
 	$(call if_changed,uimage,gzip)
 
-$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma
+$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
 	$(call if_changed,uimage,lzma)
 
-$(obj)/uImage.xz: $(obj)/vmlinux.bin.xz
+$(obj)/uImage.xz: $(obj)/vmlinux.bin.xz FORCE
 	$(call if_changed,uimage,xz)
 
-$(obj)/uImage.lzo: $(obj)/vmlinux.bin.lzo
+$(obj)/uImage.lzo: $(obj)/vmlinux.bin.lzo FORCE
 	$(call if_changed,uimage,lzo)
 
-$(obj)/uImage.bin: $(obj)/vmlinux.bin
+$(obj)/uImage.bin: $(obj)/vmlinux.bin FORCE
 	$(call if_changed,uimage,none)
 
 OBJCOPYFLAGS_vmlinux.srec := -I binary -O srec
-$(obj)/vmlinux.srec: $(obj)/compressed/vmlinux
+$(obj)/vmlinux.srec: $(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
 
 OBJCOPYFLAGS_uImage.srec := -I binary -O srec
-$(obj)/uImage.srec: $(obj)/uImage
+$(obj)/uImage.srec: $(obj)/uImage FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/uImage: $(obj)/uImage.$(suffix-y)

arch/sparc/kernel/ioport.c

@@ -356,7 +356,9 @@ err_nomem:
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs)
 {
-	if (!sparc_dma_free_resource(cpu_addr, PAGE_ALIGN(size)))
+	size = PAGE_ALIGN(size);
+
+	if (!sparc_dma_free_resource(cpu_addr, size))
 		return;
 
 	dma_make_coherent(dma_addr, size);

arch/sparc/kernel/mdesc.c

@@ -39,6 +39,7 @@ struct mdesc_hdr {
 	u32	node_sz; /* node block size */
 	u32	name_sz; /* name block size */
 	u32	data_sz; /* data block size */
+	char	data[];
 } __attribute__((aligned(16)));
 
 struct mdesc_elem {
@@ -612,7 +613,7 @@ EXPORT_SYMBOL(mdesc_get_node_info);
 
 static struct mdesc_elem *node_block(struct mdesc_hdr *mdesc)
 {
-	return (struct mdesc_elem *) (mdesc + 1);
+	return (struct mdesc_elem *) mdesc->data;
 }
 
 static void *name_block(struct mdesc_hdr *mdesc)

arch/x86/Kconfig

@@ -339,6 +339,11 @@ config NEED_PER_CPU_PAGE_FIRST_CHUNK
 config ARCH_HIBERNATION_POSSIBLE
 	def_bool y
 
+config ARCH_NR_GPIO
+	int
+	default 1024 if X86_64
+	default 512
+
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 

arch/x86/Makefile_32.cpu

@@ -4,6 +4,12 @@
 
 tune		= $(call cc-option,-mtune=$(1),$(2))
 
+ifdef CONFIG_CC_IS_CLANG
+align		:= -falign-functions=0 $(call cc-option,-falign-jumps=0) $(call cc-option,-falign-loops=0)
+else
+align		:= -falign-functions=0 -falign-jumps=0 -falign-loops=0
+endif
+
 cflags-$(CONFIG_M486SX)		+= -march=i486
 cflags-$(CONFIG_M486)		+= -march=i486
 cflags-$(CONFIG_M586)		+= -march=i586
@@ -19,11 +25,11 @@ cflags-$(CONFIG_MK6)		+= -march=k6
 # They make zero difference whatsosever to performance at this time.
 cflags-$(CONFIG_MK7)		+= -march=athlon
 cflags-$(CONFIG_MK8)		+= $(call cc-option,-march=k8,-march=athlon)
-cflags-$(CONFIG_MCRUSOE)	+= -march=i686 -falign-functions=0 -falign-jumps=0 -falign-loops=0
+cflags-$(CONFIG_MCRUSOE)	+= -march=i686 $(align)
-cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) -falign-functions=0 -falign-jumps=0 -falign-loops=0
+cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) $(align)
 cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
 cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
-cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) -falign-functions=0 -falign-jumps=0 -falign-loops=0
+cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
 cflags-$(CONFIG_MVIAC7)		+= -march=i686
 cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)

arch/x86/hyperv/hv_apic.c

@@ -99,7 +99,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val)
 /*
  * IPI implementation on Hyper-V.
  */
-static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
+static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
+		bool exclude_self)
 {
 	struct hv_send_ipi_ex **arg;
 	struct hv_send_ipi_ex *ipi_arg;
@@ -123,6 +124,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 
 	if (!cpumask_equal(mask, cpu_present_mask)) {
 		ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+		if (exclude_self)
+			nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask);
+		else
 			nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
 	}
 	if (nr_bank < 0)
@@ -138,15 +142,25 @@ ipi_mask_ex_done:
 	return hv_result_success(status);
 }
 
-static bool __send_ipi_mask(const struct cpumask *mask, int vector)
+static bool __send_ipi_mask(const struct cpumask *mask, int vector,
+		bool exclude_self)
 {
-	int cur_cpu, vcpu;
+	int cur_cpu, vcpu, this_cpu = smp_processor_id();
 	struct hv_send_ipi ipi_arg;
 	u64 status;
+	unsigned int weight;
 
 	trace_hyperv_send_ipi_mask(mask, vector);
 
-	if (cpumask_empty(mask))
+	weight = cpumask_weight(mask);
+
+	/*
+	 * Do nothing if
+	 *   1. the mask is empty
+	 *   2. the mask only contains self when exclude_self is true
+	 */
+	if (weight == 0 ||
+	    (exclude_self && weight == 1 && cpumask_test_cpu(this_cpu, mask)))
 		return true;
 
 	if (!hv_hypercall_pg)
@@ -172,6 +186,8 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	ipi_arg.cpu_mask = 0;
 
 	for_each_cpu(cur_cpu, mask) {
+		if (exclude_self && cur_cpu == this_cpu)
+			continue;
 		vcpu = hv_cpu_number_to_vp_number(cur_cpu);
 		if (vcpu == VP_INVAL)
 			return false;
@@ -191,7 +207,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	return hv_result_success(status);
 
 do_ex_hypercall:
-	return __send_ipi_mask_ex(mask, vector);
+	return __send_ipi_mask_ex(mask, vector, exclude_self);
 }
 
 static bool __send_ipi_one(int cpu, int vector)
@@ -208,7 +224,7 @@ static bool __send_ipi_one(int cpu, int vector)
 		return false;
 
 	if (vp >= 64)
-		return __send_ipi_mask_ex(cpumask_of(cpu), vector);
+		return __send_ipi_mask_ex(cpumask_of(cpu), vector, false);
 
 	status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, vector, BIT_ULL(vp));
 	return hv_result_success(status);
@@ -222,20 +238,13 @@ static void hv_send_ipi(int cpu, int vector)
 
 static void hv_send_ipi_mask(const struct cpumask *mask, int vector)
 {
-	if (!__send_ipi_mask(mask, vector))
+	if (!__send_ipi_mask(mask, vector, false))
 		orig_apic.send_IPI_mask(mask, vector);
 }
 
 static void hv_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
 {
-	unsigned int this_cpu = smp_processor_id();
+	if (!__send_ipi_mask(mask, vector, true))
-	struct cpumask new_mask;
-	const struct cpumask *local_mask;
-
-	cpumask_copy(&new_mask, mask);
-	cpumask_clear_cpu(this_cpu, &new_mask);
-	local_mask = &new_mask;
-	if (!__send_ipi_mask(local_mask, vector))
 		orig_apic.send_IPI_mask_allbutself(mask, vector);
 }
 
@@ -246,7 +255,7 @@ static void hv_send_ipi_allbutself(int vector)
 
 static void hv_send_ipi_all(int vector)
 {
-	if (!__send_ipi_mask(cpu_online_mask, vector))
+	if (!__send_ipi_mask(cpu_online_mask, vector, false))
 		orig_apic.send_IPI_all(vector);
 }
 

arch/x86/include/asm/mce.h

@@ -358,7 +358,7 @@ extern int mce_threshold_remove_device(unsigned int cpu);
 
 void mce_amd_feature_init(struct cpuinfo_x86 *c);
 int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
-
+enum smca_bank_types smca_get_bank_type(unsigned int bank);
 #else
 
 static inline int mce_threshold_create_device(unsigned int cpu)		{ return 0; };

arch/x86/include/asm/uaccess.h

@@ -301,8 +301,8 @@ do {									\
 	unsigned int __gu_low, __gu_high;				\
 	const unsigned int __user *__gu_ptr;				\
 	__gu_ptr = (const void __user *)(ptr);				\
-	__get_user_asm(__gu_low, ptr, "l", "=r", label);		\
+	__get_user_asm(__gu_low, __gu_ptr, "l", "=r", label);		\
-	__get_user_asm(__gu_high, ptr+1, "l", "=r", label);		\
+	__get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label);	\
 	(x) = ((unsigned long long)__gu_high << 32) | __gu_low;		\
 } while (0)
 #else

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

@@ -119,7 +119,7 @@ const char *smca_get_long_name(enum smca_bank_types t)
 }
 EXPORT_SYMBOL_GPL(smca_get_long_name);
 
-static enum smca_bank_types smca_get_bank_type(unsigned int bank)
+enum smca_bank_types smca_get_bank_type(unsigned int bank)
 {
 	struct smca_bank *b;
 
@@ -132,6 +132,7 @@ static enum smca_bank_types smca_get_bank_type(unsigned int bank)
 
 	return b->hwid->bank_type;
 }
+EXPORT_SYMBOL_GPL(smca_get_bank_type);
 
 static struct smca_hwid smca_hwid_mcatypes[] = {
 	/* { bank_type, hwid_mcatype } */

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

@@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin
 
 static void kill_me_now(struct callback_head *ch)
 {
+	struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me);
+
+	p->mce_count = 0;
 	force_sig(SIGBUS);
 }
 
@@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb)
 	int flags = MF_ACTION_REQUIRED;
 	int ret;
 
+	p->mce_count = 0;
 	pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr);
 
 	if (!p->mce_ripv)
@@ -1290,8 +1294,12 @@ static void kill_me_maybe(struct callback_head *cb)
 	}
 }
 
-static void queue_task_work(struct mce *m, int kill_current_task)
+static void queue_task_work(struct mce *m, char *msg, int kill_current_task)
 {
+	int count = ++current->mce_count;
+
+	/* First call, save all the details */
+	if (count == 1) {
 		current->mce_addr = m->addr;
 		current->mce_kflags = m->kflags;
 		current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
@@ -1301,6 +1309,19 @@ static void queue_task_work(struct mce *m, int kill_current_task)
 			current->mce_kill_me.func = kill_me_now;
 		else
 			current->mce_kill_me.func = kill_me_maybe;
+	}
+
+	/* Ten is likely overkill. Don't expect more than two faults before task_work() */
+	if (count > 10)
+		mce_panic("Too many consecutive machine checks while accessing user data", m, msg);
+
+	/* Second or later call, make sure page address matches the one from first call */
+	if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT))
+		mce_panic("Consecutive machine checks to different user pages", m, msg);
+
+	/* Do not call task_work_add() more than once */
+	if (count > 1)
+		return;
 
 	task_work_add(current, &current->mce_kill_me, TWA_RESUME);
 }
@@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		queue_task_work(&m, kill_current_task);
+		queue_task_work(&m, msg, kill_current_task);
 
 	} else {
 		/*
@@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		}
 
 		if (m.kflags & MCE_IN_KERNEL_COPYIN)
-			queue_task_work(&m, kill_current_task);
+			queue_task_work(&m, msg, kill_current_task);
 	}
 out:
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);

arch/x86/kernel/setup_percpu.c

@@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 
 static void __init pcpu_fc_free(void *ptr, size_t size)
 {
-	memblock_free(__pa(ptr), size);
+	memblock_free_ptr(ptr, size);
 }
 
 static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)

arch/x86/mm/init_64.c

@@ -1432,18 +1432,18 @@ int kern_addr_valid(unsigned long addr)
 		return 0;
 
 	p4d = p4d_offset(pgd, addr);
-	if (p4d_none(*p4d))
+	if (!p4d_present(*p4d))
 		return 0;
 
 	pud = pud_offset(p4d, addr);
-	if (pud_none(*pud))
+	if (!pud_present(*pud))
 		return 0;
 
 	if (pud_large(*pud))
 		return pfn_valid(pud_pfn(*pud));
 
 	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	if (!pmd_present(*pmd))
 		return 0;
 
 	if (pmd_large(*pmd))

arch/x86/mm/kasan_init_64.c

@@ -49,8 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
 			p = early_alloc(PMD_SIZE, nid, false);
 			if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
 				return;
-			else if (p)
+			memblock_free_ptr(p, PMD_SIZE);
-				memblock_free(__pa(p), PMD_SIZE);
 		}
 
 		p = early_alloc(PAGE_SIZE, nid, true);
@@ -86,8 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
 			p = early_alloc(PUD_SIZE, nid, false);
 			if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
 				return;
-			else if (p)
+			memblock_free_ptr(p, PUD_SIZE);
-				memblock_free(__pa(p), PUD_SIZE);
 		}
 
 		p = early_alloc(PAGE_SIZE, nid, true);

arch/x86/mm/numa.c

@@ -355,7 +355,7 @@ void __init numa_reset_distance(void)
 
 	/* numa_distance could be 1LU marking allocation failure, test cnt */
 	if (numa_distance_cnt)
-		memblock_free(__pa(numa_distance), size);
+		memblock_free_ptr(numa_distance, size);
 	numa_distance_cnt = 0;
 	numa_distance = NULL;	/* enable table creation */
 }

arch/x86/mm/numa_emulation.c

@@ -517,8 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	}
 
 	/* free the copied physical distance table */
-	if (phys_dist)
+	memblock_free_ptr(phys_dist, phys_size);
-		memblock_free(__pa(phys_dist), phys_size);
 	return;
 
 no_emu:

arch/x86/mm/pat/memtype.c

@@ -583,7 +583,12 @@ int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_type,
 	int err = 0;
 
 	start = sanitize_phys(start);
-	end = sanitize_phys(end);
+
+	/*
+	 * The end address passed into this function is exclusive, but
+	 * sanitize_phys() expects an inclusive address.
+	 */
+	end = sanitize_phys(end - 1) + 1;
 	if (start >= end) {
 		WARN(1, "%s failed: [mem %#010Lx-%#010Lx], req %s\n", __func__,
 				start, end - 1, cattr_name(req_type));

arch/x86/xen/enlighten_pv.c

@@ -1214,6 +1214,11 @@ static void __init xen_dom0_set_legacy_features(void)
 	x86_platform.legacy.rtc = 1;
 }
 
+static void __init xen_domu_set_legacy_features(void)
+{
+	x86_platform.legacy.rtc = 0;
+}
+
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
@@ -1359,6 +1364,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 		add_preferred_console("xenboot", 0, NULL);
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
+		x86_platform.set_legacy_features =
+				xen_domu_set_legacy_features;
 	} else {
 		const struct dom0_vga_console_info *info =
 			(void *)((char *)xen_start_info +

arch/x86/xen/mmu_pv.c

@@ -1518,14 +1518,17 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 	if (pinned) {
 		struct page *page = pfn_to_page(pfn);
 
-		if (static_branch_likely(&xen_struct_pages_ready))
+		pinned = false;
+		if (static_branch_likely(&xen_struct_pages_ready)) {
+			pinned = PagePinned(page);
 			SetPagePinned(page);
+		}
 
 		xen_mc_batch();
 
 		__set_pfn_prot(pfn, PAGE_KERNEL_RO);
 
-		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS)
+		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned)
 			__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
 		xen_mc_issue(PARAVIRT_LAZY_MMU);

block/blk-cgroup.c

@@ -1182,10 +1182,6 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	ret = blk_iolatency_init(q);
-	if (ret)
-		goto err_destroy_all;
-
 	ret = blk_ioprio_init(q);
 	if (ret)
 		goto err_destroy_all;
@@ -1194,6 +1190,12 @@ int blkcg_init_queue(struct request_queue *q)
 	if (ret)
 		goto err_destroy_all;
 
+	ret = blk_iolatency_init(q);
+	if (ret) {
+		blk_throtl_exit(q);
+		goto err_destroy_all;
+	}
+
 	return 0;
 
 err_destroy_all:
@@ -1364,10 +1366,14 @@ enomem:
 	/* alloc failed, nothing's initialized yet, free everything */
 	spin_lock_irq(&q->queue_lock);
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
+		struct blkcg *blkcg = blkg->blkcg;
+
+		spin_lock(&blkcg->lock);
 		if (blkg->pd[pol->plid]) {
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
 		}
+		spin_unlock(&blkcg->lock);
 	}
 	spin_unlock_irq(&q->queue_lock);
 	ret = -ENOMEM;
@@ -1399,12 +1405,16 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	__clear_bit(pol->plid, q->blkcg_pols);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
+		struct blkcg *blkcg = blkg->blkcg;
+
+		spin_lock(&blkcg->lock);
 		if (blkg->pd[pol->plid]) {
 			if (pol->pd_offline_fn)
 				pol->pd_offline_fn(blkg->pd[pol->plid]);
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
 		}
+		spin_unlock(&blkcg->lock);
 	}
 
 	spin_unlock_irq(&q->queue_lock);

block/blk-integrity.c

@@ -426,8 +426,15 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
+	struct blk_integrity *bi = &disk->queue->integrity;
+
+	if (!bi->profile)
+		return;
+
+	/* ensure all bios are off the integrity workqueue */
+	blk_flush_integrity();
 	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
+	memset(bi, 0, sizeof(*bi));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
 

block/blk-mq-tag.c

@@ -208,7 +208,7 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags,
 
 	spin_lock_irqsave(&tags->lock, flags);
 	rq = tags->rqs[bitnr];
-	if (!rq || !refcount_inc_not_zero(&rq->ref))
+	if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref))
 		rq = NULL;
 	spin_unlock_irqrestore(&tags->lock, flags);
 	return rq;

drivers/base/arch_numa.c

@@ -264,7 +264,7 @@ void __init numa_free_distance(void)
 	size = numa_distance_cnt * numa_distance_cnt *
 		sizeof(numa_distance[0]);
 
-	memblock_free(__pa(numa_distance), size);
+	memblock_free_ptr(numa_distance, size);
 	numa_distance_cnt = 0;
 	numa_distance = NULL;
 }

drivers/base/power/trace.c

@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/rtc.h>
 #include <linux/suspend.h>
+#include <linux/init.h>
 
 #include <linux/mc146818rtc.h>
 
@@ -165,6 +166,9 @@ void generate_pm_trace(const void *tracedata, unsigned int user)
 	const char *file = *(const char **)(tracedata + 2);
 	unsigned int user_hash_value, file_hash_value;
 
+	if (!x86_platform.legacy.rtc)
+		return;
+
 	user_hash_value = user % USERHASH;
 	file_hash_value = hash_string(lineno, file, FILEHASH);
 	set_magic_time(user_hash_value, file_hash_value, dev_hash_value);
@@ -267,6 +271,9 @@ static struct notifier_block pm_trace_nb = {
 
 static int __init early_resume_init(void)
 {
+	if (!x86_platform.legacy.rtc)
+		return 0;
+
 	hash_value_early_read = read_magic_time();
 	register_pm_notifier(&pm_trace_nb);
 	return 0;
@@ -277,6 +284,9 @@ static int __init late_resume_init(void)
 	unsigned int val = hash_value_early_read;
 	unsigned int user, file, dev;
 
+	if (!x86_platform.legacy.rtc)
+		return 0;
+
 	user = val % USERHASH;
 	val = val / USERHASH;
 	file = val % FILEHASH;

drivers/cpufreq/cpufreq_governor_attr_set.c

@@ -74,8 +74,8 @@ unsigned int gov_attr_set_put(struct gov_attr_set *attr_set, struct list_head *l
 	if (count)
 		return count;
 
-	kobject_put(&attr_set->kobj);
 	mutex_destroy(&attr_set->update_lock);
+	kobject_put(&attr_set->kobj);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(gov_attr_set_put);

drivers/cpufreq/intel_pstate.c

@@ -3205,11 +3205,15 @@ static int __init intel_pstate_init(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return -ENODEV;
 
-	if (no_load)
-		return -ENODEV;
-
 	id = x86_match_cpu(hwp_support_ids);
 	if (id) {
+		bool hwp_forced = intel_pstate_hwp_is_enabled();
+
+		if (hwp_forced)
+			pr_info("HWP enabled by BIOS\n");
+		else if (no_load)
+			return -ENODEV;
+
 		copy_cpu_funcs(&core_funcs);
 		/*
 		 * Avoid enabling HWP for processors without EPP support,
@@ -3219,8 +3223,7 @@ static int __init intel_pstate_init(void)
 		 * If HWP is enabled already, though, there is no choice but to
 		 * deal with it.
 		 */
-		if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) ||
+		if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || hwp_forced) {
-		    intel_pstate_hwp_is_enabled()) {
 			hwp_active++;
 			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
@@ -3235,7 +3238,11 @@ static int __init intel_pstate_init(void)
 
 			goto hwp_cpu_matched;
 		}
+		pr_info("HWP not enabled\n");
 	} else {
+		if (no_load)
+			return -ENODEV;
+
 		id = x86_match_cpu(intel_pstate_cpu_ids);
 		if (!id) {
 			pr_info("CPU model not supported\n");
@@ -3314,10 +3321,9 @@ static int __init intel_pstate_setup(char *str)
 	else if (!strcmp(str, "passive"))
 		default_driver = &intel_cpufreq;
 
-	if (!strcmp(str, "no_hwp")) {
+	if (!strcmp(str, "no_hwp"))
-		pr_info("HWP disabled\n");
 		no_hwp = 1;
-	}
+
 	if (!strcmp(str, "force"))
 		force_load = 1;
 	if (!strcmp(str, "hwp_only"))

drivers/cpufreq/vexpress-spc-cpufreq.c

@@ -451,7 +451,6 @@ static int ve_spc_cpufreq_init(struct cpufreq_policy *policy)
 static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy)
 {
 	struct device *cpu_dev;
-	int cur_cluster = cpu_to_cluster(policy->cpu);
 
 	cpu_dev = get_cpu_device(policy->cpu);
 	if (!cpu_dev) {

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -744,6 +744,7 @@ enum amd_hw_ip_block_type {
 	UVD_HWIP,
 	VCN_HWIP = UVD_HWIP,
 	JPEG_HWIP = VCN_HWIP,
+	VCN1_HWIP,
 	VCE_HWIP,
 	DF_HWIP,
 	DCE_HWIP,
@@ -755,10 +756,15 @@ enum amd_hw_ip_block_type {
 	CLK_HWIP,
 	UMC_HWIP,
 	RSMU_HWIP,
+	XGMI_HWIP,
+	DCI_HWIP,
 	MAX_HWIP
 };
 
-#define HWIP_MAX_INSTANCE	8
+#define HWIP_MAX_INSTANCE	10
+
+#define HW_ID_MAX		300
+#define IP_VERSION(mj, mn, rv) (((mj) << 16) | ((mn) << 8) | (rv))
 
 struct amd_powerplay {
 	void *pp_handle;
@@ -830,6 +836,7 @@ struct amdgpu_device {
 	struct notifier_block		acpi_nb;
 	struct amdgpu_i2c_chan		*i2c_bus[AMDGPU_MAX_I2C_BUS];
 	struct debugfs_blob_wrapper     debugfs_vbios_blob;
+	struct debugfs_blob_wrapper     debugfs_discovery_blob;
 	struct mutex			srbm_mutex;
 	/* GRBM index mutex. Protects concurrent access to GRBM index */
 	struct mutex                    grbm_idx_mutex;
@@ -1078,8 +1085,6 @@ struct amdgpu_device {
 	char				product_name[32];
 	char				serial[20];
 
-	struct amdgpu_autodump		autodump;
-
 	atomic_t			throttling_logging_enabled;
 	struct ratelimit_state		throttling_logging_rs;
 	uint32_t                        ras_hw_enabled;
@@ -1087,8 +1092,10 @@ struct amdgpu_device {
 
 	bool                            no_hw_access;
 	struct pci_saved_state          *pci_state;
+	pci_channel_state_t		pci_channel_state;
 
 	struct amdgpu_reset_control     *reset_cntl;
+	uint32_t                        ip_versions[HW_ID_MAX][HWIP_MAX_INSTANCE];
 };
 
 static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

@@ -31,6 +31,8 @@
 #include <linux/dma-buf.h>
 #include "amdgpu_xgmi.h"
 #include <uapi/linux/kfd_ioctl.h>
+#include "amdgpu_ras.h"
+#include "amdgpu_umc.h"
 
 /* Total memory size in system memory and all GPU VRAM. Used to
  * estimate worst case amount of memory to reserve for page tables
@@ -70,8 +72,7 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 	if (!kfd_initialized)
 		return;
 
-	adev->kfd.dev = kgd2kfd_probe((struct kgd_dev *)adev,
+	adev->kfd.dev = kgd2kfd_probe((struct kgd_dev *)adev, vf);
-				      adev->pdev, adev->asic_type, vf);
 
 	if (adev->kfd.dev)
 		amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;
@@ -192,6 +193,16 @@ void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm)
 		kgd2kfd_suspend(adev->kfd.dev, run_pm);
 }
 
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd.dev)
+		r = kgd2kfd_resume_iommu(adev->kfd.dev);
+
+	return r;
+}
+
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm)
 {
 	int r = 0;
@@ -770,3 +781,15 @@ bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd)
 
 	return adev->have_atomics_support;
 }
+
+void amdgpu_amdkfd_ras_poison_consumption_handler(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+	struct ras_err_data err_data = {0, 0, 0, NULL};
+
+	/* CPU MCA will handle page retirement if connected_to_cpu is 1 */
+	if (!adev->gmc.xgmi.connected_to_cpu)
+		amdgpu_umc_process_ras_data_cb(adev, &err_data, NULL);
+	else
+		amdgpu_amdkfd_gpu_reset(kgd);
+}

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h

@@ -137,6 +137,7 @@ int amdgpu_amdkfd_init(void);
 void amdgpu_amdkfd_fini(void);
 
 void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm);
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev);
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm);
 void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 			const void *ih_ring_entry);
@@ -289,6 +290,7 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
 				      uint64_t *mmap_offset);
 int amdgpu_amdkfd_get_tile_config(struct kgd_dev *kgd,
 				struct tile_config *config);
+void amdgpu_amdkfd_ras_poison_consumption_handler(struct kgd_dev *kgd);
 #if IS_ENABLED(CONFIG_HSA_AMD)
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
@@ -320,13 +322,13 @@ int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
 #if IS_ENABLED(CONFIG_HSA_AMD)
 int kgd2kfd_init(void);
 void kgd2kfd_exit(void);
-struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, struct pci_dev *pdev,
+struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, bool vf);
-			      unsigned int asic_type, bool vf);
 bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 struct drm_device *ddev,
 			 const struct kgd2kfd_shared_resources *gpu_resources);
 void kgd2kfd_device_exit(struct kfd_dev *kfd);
 void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
+int kgd2kfd_resume_iommu(struct kfd_dev *kfd);
 int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
 int kgd2kfd_pre_reset(struct kfd_dev *kfd);
 int kgd2kfd_post_reset(struct kfd_dev *kfd);
@@ -344,8 +346,7 @@ static inline void kgd2kfd_exit(void)
 }
 
 static inline
-struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, struct pci_dev *pdev,
+struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, bool vf)
-					unsigned int asic_type, bool vf)
 {
 	return NULL;
 }
@@ -365,6 +366,11 @@ static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 {
 }
 
+static int __maybe_unused kgd2kfd_resume_iommu(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
 static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 {
 	return 0;

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -563,6 +563,7 @@ kfd_mem_dmaunmap_userptr(struct kgd_mem *mem,
 
 	dma_unmap_sgtable(adev->dev, ttm->sg, direction, 0);
 	sg_free_table(ttm->sg);
+	kfree(ttm->sg);
 	ttm->sg = NULL;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c

@@ -61,7 +61,7 @@ static void amdgpu_bo_list_free(struct kref *ref)
 
 int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 			  struct drm_amdgpu_bo_list_entry *info,
-			  unsigned num_entries, struct amdgpu_bo_list **result)
+			  size_t num_entries, struct amdgpu_bo_list **result)
 {
 	unsigned last_entry = 0, first_userptr = num_entries;
 	struct amdgpu_bo_list_entry *array;

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h

@@ -61,7 +61,7 @@ int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
 int amdgpu_bo_list_create(struct amdgpu_device *adev,
 				 struct drm_file *filp,
 				 struct drm_amdgpu_bo_list_entry *info,
-				 unsigned num_entries,
+				 size_t num_entries,
 				 struct amdgpu_bo_list **list);
 
 static inline struct amdgpu_bo_list_entry *

drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c

@@ -43,14 +43,61 @@ const unsigned int amdgpu_ctx_num_entities[AMDGPU_HW_IP_NUM] = {
 	[AMDGPU_HW_IP_VCN_JPEG]	=	1,
 };
 
-static int amdgpu_ctx_priority_permit(struct drm_file *filp,
+bool amdgpu_ctx_priority_is_valid(int32_t ctx_prio)
-				      enum drm_sched_priority priority)
 {
-	if (priority < 0 || priority >= DRM_SCHED_PRIORITY_COUNT)
+	switch (ctx_prio) {
+	case AMDGPU_CTX_PRIORITY_UNSET:
+	case AMDGPU_CTX_PRIORITY_VERY_LOW:
+	case AMDGPU_CTX_PRIORITY_LOW:
+	case AMDGPU_CTX_PRIORITY_NORMAL:
+	case AMDGPU_CTX_PRIORITY_HIGH:
+	case AMDGPU_CTX_PRIORITY_VERY_HIGH:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static enum drm_sched_priority
+amdgpu_ctx_to_drm_sched_prio(int32_t ctx_prio)
+{
+	switch (ctx_prio) {
+	case AMDGPU_CTX_PRIORITY_UNSET:
+		return DRM_SCHED_PRIORITY_UNSET;
+
+	case AMDGPU_CTX_PRIORITY_VERY_LOW:
+		return DRM_SCHED_PRIORITY_MIN;
+
+	case AMDGPU_CTX_PRIORITY_LOW:
+		return DRM_SCHED_PRIORITY_MIN;
+
+	case AMDGPU_CTX_PRIORITY_NORMAL:
+		return DRM_SCHED_PRIORITY_NORMAL;
+
+	case AMDGPU_CTX_PRIORITY_HIGH:
+		return DRM_SCHED_PRIORITY_HIGH;
+
+	case AMDGPU_CTX_PRIORITY_VERY_HIGH:
+		return DRM_SCHED_PRIORITY_HIGH;
+
+	/* This should not happen as we sanitized userspace provided priority
+	 * already, WARN if this happens.
+	 */
+	default:
+		WARN(1, "Invalid context priority %d\n", ctx_prio);
+		return DRM_SCHED_PRIORITY_NORMAL;
+	}
+
+}
+
+static int amdgpu_ctx_priority_permit(struct drm_file *filp,
+				      int32_t priority)
+{
+	if (!amdgpu_ctx_priority_is_valid(priority))
 		return -EINVAL;
 
 	/* NORMAL and below are accessible by everyone */
-	if (priority <= DRM_SCHED_PRIORITY_NORMAL)
+	if (priority <= AMDGPU_CTX_PRIORITY_NORMAL)
 		return 0;
 
 	if (capable(CAP_SYS_NICE))
@@ -62,26 +109,51 @@ static int amdgpu_ctx_priority_permit(struct drm_file *filp,
 	return -EACCES;
 }
 
-static enum gfx_pipe_priority amdgpu_ctx_sched_prio_to_compute_prio(enum drm_sched_priority prio)
+static enum amdgpu_gfx_pipe_priority amdgpu_ctx_prio_to_compute_prio(int32_t prio)
 {
 	switch (prio) {
-	case DRM_SCHED_PRIORITY_HIGH:
+	case AMDGPU_CTX_PRIORITY_HIGH:
-	case DRM_SCHED_PRIORITY_KERNEL:
+	case AMDGPU_CTX_PRIORITY_VERY_HIGH:
 		return AMDGPU_GFX_PIPE_PRIO_HIGH;
 	default:
 		return AMDGPU_GFX_PIPE_PRIO_NORMAL;
 	}
 }
 
-static unsigned int amdgpu_ctx_prio_sched_to_hw(struct amdgpu_device *adev,
+static enum amdgpu_ring_priority_level amdgpu_ctx_sched_prio_to_ring_prio(int32_t prio)
-						 enum drm_sched_priority prio,
-						 u32 hw_ip)
 {
+	switch (prio) {
+	case AMDGPU_CTX_PRIORITY_HIGH:
+		return AMDGPU_RING_PRIO_1;
+	case AMDGPU_CTX_PRIORITY_VERY_HIGH:
+		return AMDGPU_RING_PRIO_2;
+	default:
+		return AMDGPU_RING_PRIO_0;
+	}
+}
+
+static unsigned int amdgpu_ctx_get_hw_prio(struct amdgpu_ctx *ctx, u32 hw_ip)
+{
+	struct amdgpu_device *adev = ctx->adev;
+	int32_t ctx_prio;
 	unsigned int hw_prio;
 
-	hw_prio = (hw_ip == AMDGPU_HW_IP_COMPUTE) ?
+	ctx_prio = (ctx->override_priority == AMDGPU_CTX_PRIORITY_UNSET) ?
-			amdgpu_ctx_sched_prio_to_compute_prio(prio) :
+			ctx->init_priority : ctx->override_priority;
-			AMDGPU_RING_PRIO_DEFAULT;
+
+	switch (hw_ip) {
+	case AMDGPU_HW_IP_COMPUTE:
+		hw_prio = amdgpu_ctx_prio_to_compute_prio(ctx_prio);
+		break;
+	case AMDGPU_HW_IP_VCE:
+	case AMDGPU_HW_IP_VCN_ENC:
+		hw_prio = amdgpu_ctx_sched_prio_to_ring_prio(ctx_prio);
+		break;
+	default:
+		hw_prio = AMDGPU_RING_PRIO_DEFAULT;
+		break;
+	}
+
 	hw_ip = array_index_nospec(hw_ip, AMDGPU_HW_IP_NUM);
 	if (adev->gpu_sched[hw_ip][hw_prio].num_scheds == 0)
 		hw_prio = AMDGPU_RING_PRIO_DEFAULT;
@@ -89,6 +161,7 @@ static unsigned int amdgpu_ctx_prio_sched_to_hw(struct amdgpu_device *adev,
 	return hw_prio;
 }
 
+
 static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, u32 hw_ip,
 				  const u32 ring)
 {
@@ -96,8 +169,9 @@ static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, u32 hw_ip,
 	struct amdgpu_ctx_entity *entity;
 	struct drm_gpu_scheduler **scheds = NULL, *sched = NULL;
 	unsigned num_scheds = 0;
+	int32_t ctx_prio;
 	unsigned int hw_prio;
-	enum drm_sched_priority priority;
+	enum drm_sched_priority drm_prio;
 	int r;
 
 	entity = kzalloc(struct_size(entity, fences, amdgpu_sched_jobs),
@@ -105,10 +179,11 @@ static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, u32 hw_ip,
 	if (!entity)
 		return  -ENOMEM;
 
-	entity->sequence = 1;
+	ctx_prio = (ctx->override_priority == AMDGPU_CTX_PRIORITY_UNSET) ?
-	priority = (ctx->override_priority == DRM_SCHED_PRIORITY_UNSET) ?
 			ctx->init_priority : ctx->override_priority;
-	hw_prio = amdgpu_ctx_prio_sched_to_hw(adev, priority, hw_ip);
+	entity->sequence = 1;
+	hw_prio = amdgpu_ctx_get_hw_prio(ctx, hw_ip);
+	drm_prio = amdgpu_ctx_to_drm_sched_prio(ctx_prio);
 
 	hw_ip = array_index_nospec(hw_ip, AMDGPU_HW_IP_NUM);
 	scheds = adev->gpu_sched[hw_ip][hw_prio].sched;
@@ -124,7 +199,7 @@ static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, u32 hw_ip,
 		num_scheds = 1;
 	}
 
-	r = drm_sched_entity_init(&entity->entity, priority, scheds, num_scheds,
+	r = drm_sched_entity_init(&entity->entity, drm_prio, scheds, num_scheds,
 				  &ctx->guilty);
 	if (r)
 		goto error_free_entity;
@@ -139,7 +214,7 @@ error_free_entity:
 }
 
 static int amdgpu_ctx_init(struct amdgpu_device *adev,
-			   enum drm_sched_priority priority,
+			   int32_t priority,
 			   struct drm_file *filp,
 			   struct amdgpu_ctx *ctx)
 {
@@ -161,7 +236,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 	ctx->reset_counter_query = ctx->reset_counter;
 	ctx->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
 	ctx->init_priority = priority;
-	ctx->override_priority = DRM_SCHED_PRIORITY_UNSET;
+	ctx->override_priority = AMDGPU_CTX_PRIORITY_UNSET;
 
 	return 0;
 }
@@ -234,7 +309,7 @@ int amdgpu_ctx_get_entity(struct amdgpu_ctx *ctx, u32 hw_ip, u32 instance,
 static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
 			    struct amdgpu_fpriv *fpriv,
 			    struct drm_file *filp,
-			    enum drm_sched_priority priority,
+			    int32_t priority,
 			    uint32_t *id)
 {
 	struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
@@ -397,19 +472,19 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 {
 	int r;
 	uint32_t id;
-	enum drm_sched_priority priority;
+	int32_t priority;
 
 	union drm_amdgpu_ctx *args = data;
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 
 	id = args->in.ctx_id;
-	r = amdgpu_to_sched_priority(args->in.priority, &priority);
+	priority = args->in.priority;
 
 	/* For backwards compatibility reasons, we need to accept
 	 * ioctls with garbage in the priority field */
-	if (r == -EINVAL)
+	if (!amdgpu_ctx_priority_is_valid(priority))
-		priority = DRM_SCHED_PRIORITY_NORMAL;
+		priority = AMDGPU_CTX_PRIORITY_NORMAL;
 
 	switch (args->in.op) {
 	case AMDGPU_CTX_OP_ALLOC_CTX:
@@ -517,7 +592,7 @@ struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
 static void amdgpu_ctx_set_entity_priority(struct amdgpu_ctx *ctx,
 					   struct amdgpu_ctx_entity *aentity,
 					   int hw_ip,
-					    enum drm_sched_priority priority)
+					   int32_t priority)
 {
 	struct amdgpu_device *adev = ctx->adev;
 	unsigned int hw_prio;
@@ -525,12 +600,12 @@ static void amdgpu_ctx_set_entity_priority(struct amdgpu_ctx *ctx,
 	unsigned num_scheds;
 
 	/* set sw priority */
-	drm_sched_entity_set_priority(&aentity->entity, priority);
+	drm_sched_entity_set_priority(&aentity->entity,
+				      amdgpu_ctx_to_drm_sched_prio(priority));
 
 	/* set hw priority */
 	if (hw_ip == AMDGPU_HW_IP_COMPUTE) {
-		hw_prio = amdgpu_ctx_prio_sched_to_hw(adev, priority,
+		hw_prio = amdgpu_ctx_get_hw_prio(ctx, hw_ip);
-						      AMDGPU_HW_IP_COMPUTE);
 		hw_prio = array_index_nospec(hw_prio, AMDGPU_RING_PRIO_MAX);
 		scheds = adev->gpu_sched[hw_ip][hw_prio].sched;
 		num_scheds = adev->gpu_sched[hw_ip][hw_prio].num_scheds;
@@ -540,14 +615,14 @@ static void amdgpu_ctx_set_entity_priority(struct amdgpu_ctx *ctx,
 }
 
 void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
-				  enum drm_sched_priority priority)
+				  int32_t priority)
 {
-	enum drm_sched_priority ctx_prio;
+	int32_t ctx_prio;
 	unsigned i, j;
 
 	ctx->override_priority = priority;
 
-	ctx_prio = (ctx->override_priority == DRM_SCHED_PRIORITY_UNSET) ?
+	ctx_prio = (ctx->override_priority == AMDGPU_CTX_PRIORITY_UNSET) ?
 			ctx->init_priority : ctx->override_priority;
 	for (i = 0; i < AMDGPU_HW_IP_NUM; ++i) {
 		for (j = 0; j < amdgpu_ctx_num_entities[i]; ++j) {

drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h

@@ -47,8 +47,8 @@ struct amdgpu_ctx {
 	spinlock_t			ring_lock;
 	struct amdgpu_ctx_entity	*entities[AMDGPU_HW_IP_NUM][AMDGPU_MAX_ENTITY_NUM];
 	bool				preamble_presented;
-	enum drm_sched_priority		init_priority;
+	int32_t				init_priority;
-	enum drm_sched_priority		override_priority;
+	int32_t				override_priority;
 	struct mutex			lock;
 	atomic_t			guilty;
 	unsigned long			ras_counter_ce;
@@ -75,8 +75,8 @@ void amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx,
 struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
 				       struct drm_sched_entity *entity,
 				       uint64_t seq);
-void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
+bool amdgpu_ctx_priority_is_valid(int32_t ctx_prio);
-				  enum drm_sched_priority priority);
+void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx, int32_t ctx_prio);
 
 int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 		     struct drm_file *filp);

drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c

@@ -27,7 +27,6 @@
 #include <linux/pci.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
-#include <linux/poll.h>
 
 #include "amdgpu.h"
 #include "amdgpu_pm.h"
@@ -36,87 +35,10 @@
 #include "amdgpu_rap.h"
 #include "amdgpu_securedisplay.h"
 #include "amdgpu_fw_attestation.h"
-
+#include "amdgpu_umr.h"
-int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	unsigned long timeout = 600 * HZ;
-	int ret;
-
-	wake_up_interruptible(&adev->autodump.gpu_hang);
-
-	ret = wait_for_completion_interruptible_timeout(&adev->autodump.dumping, timeout);
-	if (ret == 0) {
-		pr_err("autodump: timeout, move on to gpu recovery\n");
-		return -ETIMEDOUT;
-	}
-#endif
-	return 0;
-}
 
 #if defined(CONFIG_DEBUG_FS)
 
-static int amdgpu_debugfs_autodump_open(struct inode *inode, struct file *file)
-{
-	struct amdgpu_device *adev = inode->i_private;
-	int ret;
-
-	file->private_data = adev;
-
-	ret = down_read_killable(&adev->reset_sem);
-	if (ret)
-		return ret;
-
-	if (adev->autodump.dumping.done) {
-		reinit_completion(&adev->autodump.dumping);
-		ret = 0;
-	} else {
-		ret = -EBUSY;
-	}
-
-	up_read(&adev->reset_sem);
-
-	return ret;
-}
-
-static int amdgpu_debugfs_autodump_release(struct inode *inode, struct file *file)
-{
-	struct amdgpu_device *adev = file->private_data;
-
-	complete_all(&adev->autodump.dumping);
-	return 0;
-}
-
-static unsigned int amdgpu_debugfs_autodump_poll(struct file *file, struct poll_table_struct *poll_table)
-{
-	struct amdgpu_device *adev = file->private_data;
-
-	poll_wait(file, &adev->autodump.gpu_hang, poll_table);
-
-	if (amdgpu_in_reset(adev))
-		return POLLIN | POLLRDNORM | POLLWRNORM;
-
-	return 0;
-}
-
-static const struct file_operations autodump_debug_fops = {
-	.owner = THIS_MODULE,
-	.open = amdgpu_debugfs_autodump_open,
-	.poll = amdgpu_debugfs_autodump_poll,
-	.release = amdgpu_debugfs_autodump_release,
-};
-
-static void amdgpu_debugfs_autodump_init(struct amdgpu_device *adev)
-{
-	init_completion(&adev->autodump.dumping);
-	complete_all(&adev->autodump.dumping);
-	init_waitqueue_head(&adev->autodump.gpu_hang);
-
-	debugfs_create_file("amdgpu_autodump", 0600,
-		adev_to_drm(adev)->primary->debugfs_root,
-		adev, &autodump_debug_fops);
-}
-
 /**
  * amdgpu_debugfs_process_reg_op - Handle MMIO register reads/writes
  *
@@ -279,6 +201,145 @@ static ssize_t amdgpu_debugfs_regs_write(struct file *f, const char __user *buf,
 	return amdgpu_debugfs_process_reg_op(false, f, (char __user *)buf, size, pos);
 }
 
+static int amdgpu_debugfs_regs2_open(struct inode *inode, struct file *file)
+{
+	struct amdgpu_debugfs_regs2_data *rd;
+
+	rd = kzalloc(sizeof *rd, GFP_KERNEL);
+	if (!rd)
+		return -ENOMEM;
+	rd->adev = file_inode(file)->i_private;
+	file->private_data = rd;
+	mutex_init(&rd->lock);
+
+	return 0;
+}
+
+static int amdgpu_debugfs_regs2_release(struct inode *inode, struct file *file)
+{
+	struct amdgpu_debugfs_regs2_data *rd = file->private_data;
+	mutex_destroy(&rd->lock);
+	kfree(file->private_data);
+	return 0;
+}
+
+static ssize_t amdgpu_debugfs_regs2_op(struct file *f, char __user *buf, u32 offset, size_t size, int write_en)
+{
+	struct amdgpu_debugfs_regs2_data *rd = f->private_data;
+	struct amdgpu_device *adev = rd->adev;
+	ssize_t result = 0;
+	int r;
+	uint32_t value;
+
+	if (size & 0x3 || offset & 0x3)
+		return -EINVAL;
+
+	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
+	if (r < 0) {
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		return r;
+	}
+
+	r = amdgpu_virt_enable_access_debugfs(adev);
+	if (r < 0) {
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		return r;
+	}
+
+	mutex_lock(&rd->lock);
+
+	if (rd->id.use_grbm) {
+		if ((rd->id.grbm.sh != 0xFFFFFFFF && rd->id.grbm.sh >= adev->gfx.config.max_sh_per_se) ||
+		    (rd->id.grbm.se != 0xFFFFFFFF && rd->id.grbm.se >= adev->gfx.config.max_shader_engines)) {
+			pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+			pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+			amdgpu_virt_disable_access_debugfs(adev);
+			mutex_unlock(&rd->lock);
+			return -EINVAL;
+		}
+		mutex_lock(&adev->grbm_idx_mutex);
+		amdgpu_gfx_select_se_sh(adev, rd->id.grbm.se,
+								rd->id.grbm.sh,
+								rd->id.grbm.instance);
+	}
+
+	if (rd->id.use_srbm) {
+		mutex_lock(&adev->srbm_mutex);
+		amdgpu_gfx_select_me_pipe_q(adev, rd->id.srbm.me, rd->id.srbm.pipe,
+									rd->id.srbm.queue, rd->id.srbm.vmid);
+	}
+
+	if (rd->id.pg_lock)
+		mutex_lock(&adev->pm.mutex);
+
+	while (size) {
+		if (!write_en) {
+			value = RREG32(offset >> 2);
+			r = put_user(value, (uint32_t *)buf);
+		} else {
+			r = get_user(value, (uint32_t *)buf);
+			if (!r)
+				amdgpu_mm_wreg_mmio_rlc(adev, offset >> 2, value);
+		}
+		if (r) {
+			result = r;
+			goto end;
+		}
+		offset += 4;
+		size -= 4;
+		result += 4;
+		buf += 4;
+	}
+end:
+	if (rd->id.use_grbm) {
+		amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+		mutex_unlock(&adev->grbm_idx_mutex);
+	}
+
+	if (rd->id.use_srbm) {
+		amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0, 0);
+		mutex_unlock(&adev->srbm_mutex);
+	}
+
+	if (rd->id.pg_lock)
+		mutex_unlock(&adev->pm.mutex);
+
+	mutex_unlock(&rd->lock);
+
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+
+	amdgpu_virt_disable_access_debugfs(adev);
+	return result;
+}
+
+static long amdgpu_debugfs_regs2_ioctl(struct file *f, unsigned int cmd, unsigned long data)
+{
+	struct amdgpu_debugfs_regs2_data *rd = f->private_data;
+	int r;
+
+	switch (cmd) {
+	case AMDGPU_DEBUGFS_REGS2_IOC_SET_STATE:
+		mutex_lock(&rd->lock);
+		r = copy_from_user(&rd->id, (struct amdgpu_debugfs_regs2_iocdata *)data, sizeof rd->id);
+		mutex_unlock(&rd->lock);
+		return r ? -EINVAL : 0;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static ssize_t amdgpu_debugfs_regs2_read(struct file *f, char __user *buf, size_t size, loff_t *pos)
+{
+	return amdgpu_debugfs_regs2_op(f, buf, *pos, size, 0);
+}
+
+static ssize_t amdgpu_debugfs_regs2_write(struct file *f, const char __user *buf, size_t size, loff_t *pos)
+{
+	return amdgpu_debugfs_regs2_op(f, (char __user *)buf, *pos, size, 1);
+}
+
 
 /**
  * amdgpu_debugfs_regs_pcie_read - Read from a PCIE register
@@ -1091,6 +1152,16 @@ static ssize_t amdgpu_debugfs_gfxoff_read(struct file *f, char __user *buf,
 	return result;
 }
 
+static const struct file_operations amdgpu_debugfs_regs2_fops = {
+	.owner = THIS_MODULE,
+	.unlocked_ioctl = amdgpu_debugfs_regs2_ioctl,
+	.read = amdgpu_debugfs_regs2_read,
+	.write = amdgpu_debugfs_regs2_write,
+	.open = amdgpu_debugfs_regs2_open,
+	.release = amdgpu_debugfs_regs2_release,
+	.llseek = default_llseek
+};
+
 static const struct file_operations amdgpu_debugfs_regs_fops = {
 	.owner = THIS_MODULE,
 	.read = amdgpu_debugfs_regs_read,
@@ -1148,6 +1219,7 @@ static const struct file_operations amdgpu_debugfs_gfxoff_fops = {
 
 static const struct file_operations *debugfs_regs[] = {
 	&amdgpu_debugfs_regs_fops,
+	&amdgpu_debugfs_regs2_fops,
 	&amdgpu_debugfs_regs_didt_fops,
 	&amdgpu_debugfs_regs_pcie_fops,
 	&amdgpu_debugfs_regs_smc_fops,
@@ -1160,6 +1232,7 @@ static const struct file_operations *debugfs_regs[] = {
 
 static const char *debugfs_regs_names[] = {
 	"amdgpu_regs",
+	"amdgpu_regs2",
 	"amdgpu_regs_didt",
 	"amdgpu_regs_pcie",
 	"amdgpu_regs_smc",
@@ -1206,7 +1279,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 	}
 
 	/* Avoid accidently unparking the sched thread during GPU reset */
-	r = down_read_killable(&adev->reset_sem);
+	r = down_write_killable(&adev->reset_sem);
 	if (r)
 		return r;
 
@@ -1235,7 +1308,7 @@ static int amdgpu_debugfs_test_ib_show(struct seq_file *m, void *unused)
 		kthread_unpark(ring->sched.thread);
 	}
 
-	up_read(&adev->reset_sem);
+	up_write(&adev->reset_sem);
 
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
@@ -1255,7 +1328,7 @@ static int amdgpu_debugfs_evict_vram(void *data, u64 *val)
 		return r;
 	}
 
-	*val = amdgpu_bo_evict_vram(adev);
+	*val = amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM);
 
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
@@ -1268,17 +1341,15 @@ static int amdgpu_debugfs_evict_gtt(void *data, u64 *val)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)data;
 	struct drm_device *dev = adev_to_drm(adev);
-	struct ttm_resource_manager *man;
 	int r;
 
 	r = pm_runtime_get_sync(dev->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		pm_runtime_put_autosuspend(dev->dev);
 		return r;
 	}
 
-	man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
+	*val = amdgpu_ttm_evict_resources(adev, TTM_PL_TT);
-	*val = ttm_resource_manager_evict_all(&adev->mman.bdev, man);
 
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
@@ -1544,20 +1615,21 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	struct dentry *ent;
 	int r, i;
 
-
+	if (!debugfs_initialized())
+		return 0;
 
 	ent = debugfs_create_file("amdgpu_preempt_ib", 0600, root, adev,
 				  &fops_ib_preempt);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	ent = debugfs_create_file("amdgpu_force_sclk", 0200, root, adev,
 				  &fops_sclk_set);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_set_sclk debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	/* Register debugfs entries for amdgpu_ttm */
@@ -1584,13 +1656,10 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 		if (!ring)
 			continue;
 
-		if (amdgpu_debugfs_ring_init(adev, ring)) {
+		amdgpu_debugfs_ring_init(adev, ring);
-			DRM_ERROR("Failed to register debugfs file for rings !\n");
-		}
 	}
 
 	amdgpu_ras_debugfs_create_all(adev);
-	amdgpu_debugfs_autodump_init(adev);
 	amdgpu_rap_debugfs_init(adev);
 	amdgpu_securedisplay_debugfs_init(adev);
 	amdgpu_fw_attestation_debugfs_init(adev);
@@ -1609,6 +1678,11 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	debugfs_create_blob("amdgpu_vbios", 0444, root,
 			    &adev->debugfs_vbios_blob);
 
+	adev->debugfs_discovery_blob.data = adev->mman.discovery_bin;
+	adev->debugfs_discovery_blob.size = adev->mman.discovery_tmr_size;
+	debugfs_create_blob("amdgpu_discovery", 0444, root,
+			    &adev->debugfs_discovery_blob);
+
 	return 0;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h

@@ -22,14 +22,9 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
-
 /*
  * Debugfs
  */
-struct amdgpu_autodump {
-	struct completion		dumping;
-	struct wait_queue_head		gpu_hang;
-};
 
 int amdgpu_debugfs_regs_init(struct amdgpu_device *adev);
 int amdgpu_debugfs_init(struct amdgpu_device *adev);
@@ -37,4 +32,3 @@ void amdgpu_debugfs_fini(struct amdgpu_device *adev);
 void amdgpu_debugfs_fence_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_firmware_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_gem_init(struct amdgpu_device *adev);
-int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev);

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -125,6 +125,7 @@ const char *amdgpu_asic_name[] = {
 	"DIMGREY_CAVEFISH",
 	"BEIGE_GOBY",
 	"YELLOW_CARP",
+	"IP DISCOVERY",
 	"LAST",
 };
 
@@ -305,7 +306,7 @@ void amdgpu_device_mm_access(struct amdgpu_device *adev, loff_t pos,
 	uint64_t last;
 	int idx;
 
-	if (!drm_dev_enter(&adev->ddev, &idx))
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
 		return;
 
 	BUG_ON(!IS_ALIGNED(pos, 4) || !IS_ALIGNED(size, 4));
@@ -2126,46 +2127,11 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 		if (r)
 			return r;
 		break;
-	case CHIP_VEGA10:
-	case CHIP_VEGA12:
-	case CHIP_VEGA20:
-	case CHIP_RAVEN:
-	case CHIP_ARCTURUS:
-	case CHIP_RENOIR:
-	case CHIP_ALDEBARAN:
-		if (adev->flags & AMD_IS_APU)
-			adev->family = AMDGPU_FAMILY_RV;
-		else
-			adev->family = AMDGPU_FAMILY_AI;
-
-		r = soc15_set_ip_blocks(adev);
-		if (r)
-			return r;
-		break;
-	case  CHIP_NAVI10:
-	case  CHIP_NAVI14:
-	case  CHIP_NAVI12:
-	case  CHIP_SIENNA_CICHLID:
-	case  CHIP_NAVY_FLOUNDER:
-	case  CHIP_DIMGREY_CAVEFISH:
-	case  CHIP_BEIGE_GOBY:
-	case CHIP_VANGOGH:
-	case CHIP_YELLOW_CARP:
-	case CHIP_CYAN_SKILLFISH:
-		if (adev->asic_type == CHIP_VANGOGH)
-			adev->family = AMDGPU_FAMILY_VGH;
-		else if (adev->asic_type == CHIP_YELLOW_CARP)
-			adev->family = AMDGPU_FAMILY_YC;
-		else
-			adev->family = AMDGPU_FAMILY_NV;
-
-		r = nv_set_ip_blocks(adev);
-		if (r)
-			return r;
-		break;
 	default:
-		/* FIXME: not supported yet */
+		r = amdgpu_discovery_set_ip_blocks(adev);
-		return -EINVAL;
+		if (r)
+			return r;
+		break;
 	}
 
 	amdgpu_amdkfd_device_probe(adev);
@@ -2432,6 +2398,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		goto init_failed;
+
 	amdgpu_fru_get_product_info(adev);
 
 init_failed:
@@ -2741,6 +2711,11 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.hw = false;
 	}
 
+	if (amdgpu_sriov_vf(adev)) {
+		if (amdgpu_virt_release_full_gpu(adev, false))
+			DRM_ERROR("failed to release exclusive mode on fini\n");
+	}
+
 	return 0;
 }
 
@@ -2801,10 +2776,6 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 
 	amdgpu_ras_fini(adev);
 
-	if (amdgpu_sriov_vf(adev))
-		if (amdgpu_virt_release_full_gpu(adev, false))
-			DRM_ERROR("failed to release exclusive mode on fini\n");
-
 	return 0;
 }
 
@@ -3148,6 +3119,10 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 {
 	int r;
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		return r;
+
 	r = amdgpu_device_ip_resume_phase1(adev);
 	if (r)
 		return r;
@@ -3232,6 +3207,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
 	case CHIP_RENOIR:
+	case CHIP_CYAN_SKILLFISH:
 	case CHIP_SIENNA_CICHLID:
 	case CHIP_NAVY_FLOUNDER:
 	case CHIP_DIMGREY_CAVEFISH:
@@ -3239,13 +3215,15 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	case CHIP_VANGOGH:
 	case CHIP_YELLOW_CARP:
 #endif
+	default:
 		return amdgpu_dc != 0;
-#endif
+#else
 	default:
 		if (amdgpu_dc > 0)
 			DRM_INFO_ONCE("Display Core has been requested via kernel parameter "
 					 "but isn't supported by ASIC, ignoring\n");
 		return false;
+#endif
 	}
 }
 
@@ -3346,6 +3324,8 @@ static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
 				continue;
 			} else if (timeout < 0) {
 				timeout = MAX_SCHEDULE_TIMEOUT;
+				dev_warn(adev->dev, "lockup timeout disabled");
+				add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK);
 			} else {
 				timeout = msecs_to_jiffies(timeout);
 			}
@@ -3530,17 +3510,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	DRM_INFO("register mmio base: 0x%08X\n", (uint32_t)adev->rmmio_base);
 	DRM_INFO("register mmio size: %u\n", (unsigned)adev->rmmio_size);
 
-	/* enable PCIE atomic ops */
-	r = pci_enable_atomic_ops_to_root(adev->pdev,
-					  PCI_EXP_DEVCAP2_ATOMIC_COMP32 |
-					  PCI_EXP_DEVCAP2_ATOMIC_COMP64);
-	if (r) {
-		adev->have_atomics_support = false;
-		DRM_INFO("PCIE atomic ops is not supported\n");
-	} else {
-		adev->have_atomics_support = true;
-	}
-
 	amdgpu_device_get_pcie_info(adev);
 
 	if (amdgpu_mcbp)
@@ -3563,6 +3532,19 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	/* enable PCIE atomic ops */
+	if (amdgpu_sriov_vf(adev))
+		adev->have_atomics_support = ((struct amd_sriov_msg_pf2vf_info *)
+			adev->virt.fw_reserve.p_pf2vf)->pcie_atomic_ops_enabled_flags ==
+			(PCI_EXP_DEVCAP2_ATOMIC_COMP32 | PCI_EXP_DEVCAP2_ATOMIC_COMP64);
+	else
+		adev->have_atomics_support =
+			!pci_enable_atomic_ops_to_root(adev->pdev,
+					  PCI_EXP_DEVCAP2_ATOMIC_COMP32 |
+					  PCI_EXP_DEVCAP2_ATOMIC_COMP64);
+	if (!adev->have_atomics_support)
+		dev_info(adev->dev, "PCIE atomic ops is not supported\n");
+
 	/* doorbell bar mapping and doorbell index init*/
 	amdgpu_device_doorbell_init(adev);
 
@@ -3861,6 +3843,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 
 	amdgpu_device_ip_fini_early(adev);
 
+	ttm_device_clear_dma_mappings(&adev->mman.bdev);
+
 	amdgpu_gart_dummy_page_fini(adev);
 
 	amdgpu_device_unmap_mmio(adev);
@@ -3901,6 +3885,25 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 
 }
 
+/**
+ * amdgpu_device_evict_resources - evict device resources
+ * @adev: amdgpu device object
+ *
+ * Evicts all ttm device resources(vram BOs, gart table) from the lru list
+ * of the vram memory type. Mainly used for evicting device resources
+ * at suspend time.
+ *
+ */
+static void amdgpu_device_evict_resources(struct amdgpu_device *adev)
+{
+	/* No need to evict vram on APUs for suspend to ram */
+	if (adev->in_s3 && (adev->flags & AMD_IS_APU))
+		return;
+
+	if (amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM))
+		DRM_WARN("evicting device resources failed\n");
+
+}
 
 /*
  * Suspend & resume.
@@ -3941,17 +3944,16 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (!adev->in_s0ix)
 		amdgpu_amdkfd_suspend(adev, adev->in_runpm);
 
-	/* evict vram memory */
+	/* First evict vram memory */
-	amdgpu_bo_evict_vram(adev);
+	amdgpu_device_evict_resources(adev);
 
 	amdgpu_fence_driver_hw_fini(adev);
 
 	amdgpu_device_ip_suspend_phase2(adev);
-	/* evict remaining vram memory
+	/* This second call to evict device resources is to evict
-	 * This second call to evict vram is to evict the gart page table
+	 * the gart page table using the CPU.
-	 * using the CPU.
 	 */
-	amdgpu_bo_evict_vram(adev);
+	amdgpu_device_evict_resources(adev);
 
 	return 0;
 }
@@ -4458,10 +4460,6 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 	if (reset_context->reset_req_dev == adev)
 		job = reset_context->job;
 
-	/* no need to dump if device is not in good state during probe period */
-	if (!adev->gmc.xgmi.pending_reset)
-		amdgpu_debugfs_wait_dump(adev);
-
 	if (amdgpu_sriov_vf(adev)) {
 		/* stop the data exchange thread */
 		amdgpu_virt_fini_data_exchange(adev);
@@ -4601,6 +4599,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				dev_warn(tmp_adev->dev, "asic atom init failed!");
 			} else {
 				dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n");
+				r = amdgpu_amdkfd_resume_iommu(tmp_adev);
+				if (r)
+					goto out;
+
 				r = amdgpu_device_ip_resume_phase1(tmp_adev);
 				if (r)
 					goto out;
@@ -5387,6 +5389,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
+	adev->pci_channel_state = state;
+
 	switch (state) {
 	case pci_channel_io_normal:
 		return PCI_ERS_RESULT_CAN_RECOVER;
@@ -5529,6 +5533,10 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 
 	DRM_INFO("PCI error: resume callback!!\n");
 
+	/* Only continue execution for the case of pci_channel_io_frozen */
+	if (adev->pci_channel_state != pci_channel_io_frozen)
+		return;
+
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
 

drivers/gpu/drm/amd/amdgpu/amdgpu_df.h

@@ -52,6 +52,7 @@ struct amdgpu_df_funcs {
 	uint64_t (*get_fica)(struct amdgpu_device *adev, uint32_t ficaa_val);
 	void (*set_fica)(struct amdgpu_device *adev, uint32_t ficaa_val,
 			 uint32_t ficadl_val, uint32_t ficadh_val);
+	bool (*query_ras_poison_mode)(struct amdgpu_device *adev);
 };
 
 struct amdgpu_df {

drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c

@@ -21,16 +21,58 @@
  *
  */
 
+#include <linux/firmware.h>
+
 #include "amdgpu.h"
 #include "amdgpu_discovery.h"
 #include "soc15_hw_ip.h"
 #include "discovery.h"
 
+#include "soc15.h"
+#include "gfx_v9_0.h"
+#include "gmc_v9_0.h"
+#include "df_v1_7.h"
+#include "df_v3_6.h"
+#include "nbio_v6_1.h"
+#include "nbio_v7_0.h"
+#include "nbio_v7_4.h"
+#include "hdp_v4_0.h"
+#include "vega10_ih.h"
+#include "vega20_ih.h"
+#include "sdma_v4_0.h"
+#include "uvd_v7_0.h"
+#include "vce_v4_0.h"
+#include "vcn_v1_0.h"
+#include "vcn_v2_5.h"
+#include "jpeg_v2_5.h"
+#include "smuio_v9_0.h"
+#include "gmc_v10_0.h"
+#include "gfxhub_v2_0.h"
+#include "mmhub_v2_0.h"
+#include "nbio_v2_3.h"
+#include "nbio_v7_2.h"
+#include "hdp_v5_0.h"
+#include "nv.h"
+#include "navi10_ih.h"
+#include "gfx_v10_0.h"
+#include "sdma_v5_0.h"
+#include "sdma_v5_2.h"
+#include "vcn_v2_0.h"
+#include "jpeg_v2_0.h"
+#include "vcn_v3_0.h"
+#include "jpeg_v3_0.h"
+#include "amdgpu_vkms.h"
+#include "mes_v10_1.h"
+#include "smuio_v11_0.h"
+#include "smuio_v11_0_6.h"
+#include "smuio_v13_0.h"
+
+MODULE_FIRMWARE("amdgpu/ip_discovery.bin");
+
 #define mmRCC_CONFIG_MEMSIZE	0xde3
 #define mmMM_INDEX		0x0
 #define mmMM_INDEX_HI		0x6
 #define mmMM_DATA		0x1
-#define HW_ID_MAX		300
 
 static const char *hw_id_names[HW_ID_MAX] = {
 	[MP1_HWID]		= "MP1",
@@ -129,6 +171,8 @@ static int hw_id_map[MAX_HWIP] = {
 	[THM_HWIP]	= THM_HWID,
 	[CLK_HWIP]	= CLKA_HWID,
 	[UMC_HWIP]	= UMC_HWID,
+	[XGMI_HWIP]	= XGMI_HWID,
+	[DCI_HWIP]	= DCI_HWID,
 };
 
 static int amdgpu_discovery_read_binary(struct amdgpu_device *adev, uint8_t *binary)
@@ -164,6 +208,7 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 	struct binary_header *bhdr;
 	struct ip_discovery_header *ihdr;
 	struct gpu_info_header *ghdr;
+	const struct firmware *fw;
 	uint16_t offset;
 	uint16_t size;
 	uint16_t checksum;
@@ -174,11 +219,22 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 	if (!adev->mman.discovery_bin)
 		return -ENOMEM;
 
+	if (amdgpu_discovery == 2) {
+		r = request_firmware(&fw, "amdgpu/ip_discovery.bin", adev->dev);
+		if (r)
+			goto get_from_vram;
+		dev_info(adev->dev, "Using IP discovery from file\n");
+		memcpy((u8 *)adev->mman.discovery_bin, (u8 *)fw->data,
+		       adev->mman.discovery_tmr_size);
+		release_firmware(fw);
+	} else {
+get_from_vram:
 		r = amdgpu_discovery_read_binary(adev, adev->mman.discovery_bin);
 		if (r) {
 			DRM_ERROR("failed to read ip discovery binary\n");
 			goto out;
 		}
+	}
 
 	bhdr = (struct binary_header *)adev->mman.discovery_bin;
 
@@ -245,6 +301,22 @@ void amdgpu_discovery_fini(struct amdgpu_device *adev)
 	adev->mman.discovery_bin = NULL;
 }
 
+static int amdgpu_discovery_validate_ip(const struct ip *ip)
+{
+	if (ip->number_instance >= HWIP_MAX_INSTANCE) {
+		DRM_ERROR("Unexpected number_instance (%d) from ip discovery blob\n",
+			  ip->number_instance);
+		return -EINVAL;
+	}
+	if (le16_to_cpu(ip->hw_id) >= HW_ID_MAX) {
+		DRM_ERROR("Unexpected hw_id (%d) from ip discovery blob\n",
+			  le16_to_cpu(ip->hw_id));
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 {
 	struct binary_header *bhdr;
@@ -290,6 +362,10 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 
 		for (j = 0; j < num_ips; j++) {
 			ip = (struct ip *)(adev->mman.discovery_bin + ip_offset);
+
+			if (amdgpu_discovery_validate_ip(ip))
+				goto next_ip;
+
 			num_base_address = ip->num_base_address;
 
 			DRM_DEBUG("%s(%d) #%d v%d.%d.%d:\n",
@@ -301,6 +377,11 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 
 			if (le16_to_cpu(ip->hw_id) == VCN_HWID)
 				adev->vcn.num_vcn_inst++;
+			if (le16_to_cpu(ip->hw_id) == SDMA0_HWID ||
+			    le16_to_cpu(ip->hw_id) == SDMA1_HWID ||
+			    le16_to_cpu(ip->hw_id) == SDMA2_HWID ||
+			    le16_to_cpu(ip->hw_id) == SDMA3_HWID)
+				adev->sdma.num_instances++;
 
 			for (k = 0; k < num_base_address; k++) {
 				/*
@@ -317,10 +398,21 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 							hw_id_names[le16_to_cpu(ip->hw_id)]);
 					adev->reg_offset[hw_ip][ip->number_instance] =
 						ip->base_address;
+					/* Instance support is somewhat inconsistent.
+					 * SDMA is a good example.  Sienna cichlid has 4 total
+					 * SDMA instances, each enumerated separately (HWIDs
+					 * 42, 43, 68, 69).  Arcturus has 8 total SDMA instances,
+					 * but they are enumerated as multiple instances of the
+					 * same HWIDs (4x HWID 42, 4x HWID 43).  UMC is another
+					 * example.  On most chips there are multiple instances
+					 * with the same HWID.
+					 */
+					adev->ip_versions[hw_ip][ip->number_instance] =
+						IP_VERSION(ip->major, ip->minor, ip->revision);
+				}
 			}
 
-			}
+next_ip:
-
 			ip_offset += sizeof(*ip) + 4 * (ip->num_base_address - 1);
 		}
 	}
@@ -401,6 +493,10 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 		switch (le32_to_cpu(harvest_info->list[i].hw_id)) {
 		case VCN_HWID:
 			vcn_harvest_count++;
+			if (harvest_info->list[i].number_instance == 0)
+				adev->vcn.harvest_config |= AMDGPU_VCN_HARVEST_VCN0;
+			else
+				adev->vcn.harvest_config |= AMDGPU_VCN_HARVEST_VCN1;
 			break;
 		case DMU_HWID:
 			adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK;
@@ -413,6 +509,13 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 		adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK;
 		adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK;
 	}
+	if ((adev->pdev->device == 0x731E &&
+	     (adev->pdev->revision == 0xC6 || adev->pdev->revision == 0xC7)) ||
+	    (adev->pdev->device == 0x7340 && adev->pdev->revision == 0xC9)  ||
+	    (adev->pdev->device == 0x7360 && adev->pdev->revision == 0xC7)) {
+		adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK;
+		adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK;
+	}
 }
 
 int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
@@ -450,3 +553,731 @@ int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
 
 	return 0;
 }
+
+static int amdgpu_discovery_set_common_ip_blocks(struct amdgpu_device *adev)
+{
+	/* what IP to use for this? */
+	switch (adev->ip_versions[GC_HWIP][0]) {
+	case IP_VERSION(9, 0, 1):
+	case IP_VERSION(9, 1, 0):
+	case IP_VERSION(9, 2, 1):
+	case IP_VERSION(9, 2, 2):
+	case IP_VERSION(9, 3, 0):
+	case IP_VERSION(9, 4, 0):
+	case IP_VERSION(9, 4, 1):
+	case IP_VERSION(9, 4, 2):
+		amdgpu_device_ip_block_add(adev, &vega10_common_ip_block);
+		break;
+	case IP_VERSION(10, 1, 10):
+	case IP_VERSION(10, 1, 1):
+	case IP_VERSION(10, 1, 2):
+	case IP_VERSION(10, 1, 3):
+	case IP_VERSION(10, 3, 0):
+	case IP_VERSION(10, 3, 1):
+	case IP_VERSION(10, 3, 2):
+	case IP_VERSION(10, 3, 3):
+	case IP_VERSION(10, 3, 4):
+	case IP_VERSION(10, 3, 5):
+		amdgpu_device_ip_block_add(adev, &nv_common_ip_block);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int amdgpu_discovery_set_gmc_ip_blocks(struct amdgpu_device *adev)
+{
+	/* use GC or MMHUB IP version */
+	switch (adev->ip_versions[GC_HWIP][0]) {
+	case IP_VERSION(9, 0, 1):
+	case IP_VERSION(9, 1, 0):
+	case IP_VERSION(9, 2, 1):
+	case IP_VERSION(9, 2, 2):
+	case IP_VERSION(9, 3, 0):
+	case IP_VERSION(9, 4, 0):
+	case IP_VERSION(9, 4, 1):
+	case IP_VERSION(9, 4, 2):
+		amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block);
+		break;
+	case IP_VERSION(10, 1, 10):
+	case IP_VERSION(10, 1, 1):
+	case IP_VERSION(10, 1, 2):
+	case IP_VERSION(10, 1, 3):
+	case IP_VERSION(10, 3, 0):
+	case IP_VERSION(10, 3, 1):
+	case IP_VERSION(10, 3, 2):
+	case IP_VERSION(10, 3, 3):
+	case IP_VERSION(10, 3, 4):
+	case IP_VERSION(10, 3, 5):
+		amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int amdgpu_discovery_set_ih_ip_blocks(struct amdgpu_device *adev)
+{
+	switch (adev->ip_versions[OSSSYS_HWIP][0]) {
+	case IP_VERSION(4, 0, 0):
+	case IP_VERSION(4, 0, 1):
+	case IP_VERSION(4, 1, 0):
+	case IP_VERSION(4, 1, 1):
+	case IP_VERSION(4, 3, 0):
+		amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
+		break;
+	case IP_VERSION(4, 2, 0):
+	case IP_VERSION(4, 2, 1):
+	case IP_VERSION(4, 4, 0):
+		amdgpu_device_ip_block_add(adev, &vega20_ih_ip_block);
+		break;
+	case IP_VERSION(5, 0, 0):
+	case IP_VERSION(5, 0, 1):
+	case IP_VERSION(5, 0, 2):
+	case IP_VERSION(5, 0, 3):
+	case IP_VERSION(5, 2, 0):
+	case IP_VERSION(5, 2, 1):
+		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev)
+{
+	switch (adev->ip_versions[MP0_HWIP][0]) {
+	case IP_VERSION(9, 0, 0):
+		amdgpu_device_ip_block_add(adev, &psp_v3_1_ip_block);
+		break;
+	case IP_VERSION(10, 0, 0):
+	case IP_VERSION(10, 0, 1):
+		amdgpu_device_ip_block_add(adev, &psp_v10_0_ip_block);
+		break;
+	case IP_VERSION(11, 0, 0):
+	case IP_VERSION(11, 0, 2):
+	case IP_VERSION(11, 0, 4):
+	case IP_VERSION(11, 0, 5):
+	case IP_VERSION(11, 0, 9):
+	case IP_VERSION(11, 0, 7):
+	case IP_VERSION(11, 0, 11):
+	case IP_VERSION(11, 0, 12):
+	case IP_VERSION(11, 0, 13):
+	case IP_VERSION(11, 5, 0):
+		amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
+		break;
+	case IP_VERSION(11, 0, 8):
+		amdgpu_device_ip_block_add(adev, &psp_v11_0_8_ip_block);
+		break;
+	case IP_VERSION(11, 0, 3):
+	case IP_VERSION(12, 0, 1):
+		amdgpu_device_ip_block_add(adev, &psp_v12_0_ip_block);
+		break;
+	case IP_VERSION(13, 0, 1):
+	case IP_VERSION(13, 0, 2):
+	case IP_VERSION(13, 0, 3):
+		amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
+{
+	switch (adev->ip_versions[MP1_HWIP][0]) {
+	case IP_VERSION(9, 0, 0):
+	case IP_VERSION(10, 0, 0):
+	case IP_VERSION(10, 0, 1):
+	case IP_VERSION(11, 0, 2):
+		if (adev->asic_type == CHIP_ARCTURUS)
+			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
+		else
+			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
+		break;
+	case IP_VERSION(11, 0, 0):
+	case IP_VERSION(11, 0, 5):
+	case IP_VERSION(11, 0, 9):
+	case IP_VERSION(11, 0, 7):
+	case IP_VERSION(11, 0, 8):
+	case IP_VERSION(11, 0, 11):
+	case IP_VERSION(11, 0, 12):
+	case IP_VERSION(11, 0, 13):
+	case IP_VERSION(11, 5, 0):
+		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
+		break;
+	case IP_VERSION(12, 0, 0):
+	case IP_VERSION(12, 0, 1):
+		amdgpu_device_ip_block_add(adev, &smu_v12_0_ip_block);
+		break;
+	case IP_VERSION(13, 0, 1):
+	case IP_VERSION(13, 0, 2):
+	case IP_VERSION(13, 0, 3):
+		amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
+{
+	if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) {
+		amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
+#if defined(CONFIG_DRM_AMD_DC)
+	} else if (adev->ip_versions[DCE_HWIP][0]) {
+		switch (adev->ip_versions[DCE_HWIP][0]) {
+		case IP_VERSION(1, 0, 0):
+		case IP_VERSION(1, 0, 1):
+		case IP_VERSION(2, 0, 2):
+		case IP_VERSION(2, 0, 0):
+		case IP_VERSION(2, 1, 0):
+		case IP_VERSION(3, 0, 0):
+		case IP_VERSION(3, 0, 2):
+		case IP_VERSION(3, 0, 3):
+		case IP_VERSION(3, 0, 1):
+		case IP_VERSION(3, 1, 2):
+		case IP_VERSION(3, 1, 3):
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
+			break;
+		case IP_VERSION(2, 0, 3):
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else if (adev->ip_versions[DCI_HWIP][0]) {
+		switch (adev->ip_versions[DCI_HWIP][0]) {
+		case IP_VERSION(12, 0, 0):
+		case IP_VERSION(12, 0, 1):
+		case IP_VERSION(12, 1, 0):
+			amdgpu_device_ip_block_add(adev, &dm_ip_block);
+			break;
+		default:
+			return -EINVAL;
+		}
+#endif
+	}
+	return 0;
+}
+
+static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
+{
+	switch (adev->ip_versions[GC_HWIP][0]) {
+	case IP_VERSION(9, 0, 1):
+	case IP_VERSION(9, 1, 0):
+	case IP_VERSION(9, 2, 1):
+	case IP_VERSION(9, 2, 2):
+	case IP_VERSION(9, 3, 0):
+	case IP_VERSION(9, 4, 0):
+	case IP_VERSION(9, 4, 1):
+	case IP_VERSION(9, 4, 2):
+		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
+		break;
+	case IP_VERSION(10, 1, 10):
+	case IP_VERSION(10, 1, 2):
+	case IP_VERSION(10, 1, 1):
+	case IP_VERSION(10, 1, 3):
+	case IP_VERSION(10, 3, 0):
+	case IP_VERSION(10, 3, 2):
+	case IP_VERSION(10, 3, 1):
+	case IP_VERSION(10, 3, 4):
+	case IP_VERSION(10, 3, 5):
+	case IP_VERSION(10, 3, 3):
+		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int amdgpu_discovery_set_sdma_ip_blocks(struct amdgpu_device *adev)
+{
+	switch (adev->ip_versions[SDMA0_HWIP][0]) {
+	case IP_VERSION(4, 0, 0):
+	case IP_VERSION(4, 0, 1):
+	case IP_VERSION(4, 1, 0):
+	case IP_VERSION(4, 1, 1):
+	case IP_VERSION(4, 1, 2):
+	case IP_VERSION(4, 2, 0):
+	case IP_VERSION(4, 2, 2):
+	case IP_VERSION(4, 4, 0):
+		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
+		break;
+	case IP_VERSION(5, 0, 0):
+	case IP_VERSION(5, 0, 1):
+	case IP_VERSION(5, 0, 2):
+	case IP_VERSION(5, 0, 5):
+		amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block);
+		break;
+	case IP_VERSION(5, 2, 0):
+	case IP_VERSION(5, 2, 2):
+	case IP_VERSION(5, 2, 4):
+	case IP_VERSION(5, 2, 5):
+	case IP_VERSION(5, 2, 3):
+	case IP_VERSION(5, 2, 1):
+		amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
+{
+	if (adev->ip_versions[VCE_HWIP][0]) {
+		switch (adev->ip_versions[UVD_HWIP][0]) {
+		case IP_VERSION(7, 0, 0):
+		case IP_VERSION(7, 2, 0):
+			/* UVD is not supported on vega20 SR-IOV */
+			if (!(adev->asic_type == CHIP_VEGA20 && amdgpu_sriov_vf(adev)))
+				amdgpu_device_ip_block_add(adev, &uvd_v7_0_ip_block);
+			break;
+		default:
+			return -EINVAL;
+		}
+		switch (adev->ip_versions[VCE_HWIP][0]) {
+		case IP_VERSION(4, 0, 0):
+		case IP_VERSION(4, 1, 0):
+			/* VCE is not supported on vega20 SR-IOV */
+			if (!(adev->asic_type == CHIP_VEGA20 && amdgpu_sriov_vf(adev)))
+				amdgpu_device_ip_block_add(adev, &vce_v4_0_ip_block);
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else {
+		switch (adev->ip_versions[UVD_HWIP][0]) {
+		case IP_VERSION(1, 0, 0):
+		case IP_VERSION(1, 0, 1):
+			amdgpu_device_ip_block_add(adev, &vcn_v1_0_ip_block);
+			break;
+		case IP_VERSION(2, 0, 0):
+		case IP_VERSION(2, 0, 2):
+		case IP_VERSION(2, 2, 0):
+			amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
+			break;
+		case IP_VERSION(2, 0, 3):
+			break;
+		case IP_VERSION(2, 5, 0):
+			amdgpu_device_ip_block_add(adev, &vcn_v2_5_ip_block);
+			amdgpu_device_ip_block_add(adev, &jpeg_v2_5_ip_block);
+			break;
+		case IP_VERSION(2, 6, 0):
+			amdgpu_device_ip_block_add(adev, &vcn_v2_6_ip_block);
+			amdgpu_device_ip_block_add(adev, &jpeg_v2_6_ip_block);
+			break;
+		case IP_VERSION(3, 0, 0):
+		case IP_VERSION(3, 0, 16):
+		case IP_VERSION(3, 1, 1):
+		case IP_VERSION(3, 0, 2):
+			amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
+			if (!amdgpu_sriov_vf(adev))
+				amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block);
+			break;
+		case IP_VERSION(3, 0, 33):
+			amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static int amdgpu_discovery_set_mes_ip_blocks(struct amdgpu_device *adev)
+{
+	switch (adev->ip_versions[GC_HWIP][0]) {
+	case IP_VERSION(10, 1, 10):
+	case IP_VERSION(10, 1, 1):
+	case IP_VERSION(10, 1, 2):
+	case IP_VERSION(10, 1, 3):
+	case IP_VERSION(10, 3, 0):
+	case IP_VERSION(10, 3, 1):
+	case IP_VERSION(10, 3, 2):
+	case IP_VERSION(10, 3, 3):
+	case IP_VERSION(10, 3, 4):
+	case IP_VERSION(10, 3, 5):
+		amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block);
+		break;
+	default:
+		break;;
+	}
+	return 0;
+}
+
+int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
+{
+	int r;
+
+	switch (adev->asic_type) {
+	case CHIP_VEGA10:
+		vega10_reg_base_init(adev);
+		adev->sdma.num_instances = 2;
+		adev->ip_versions[MMHUB_HWIP][0] = IP_VERSION(9, 0, 0);
+		adev->ip_versions[ATHUB_HWIP][0] = IP_VERSION(9, 0, 0);
+		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 0, 0);
+		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 0, 0);
+		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 0, 0);
+		adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 1, 0);
+		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(6, 1, 0);
+		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 0, 0);
+		adev->ip_versions[MP0_HWIP][0] = IP_VERSION(9, 0, 0);
+		adev->ip_versions[MP1_HWIP][0] = IP_VERSION(9, 0, 0);
+		adev->ip_versions[THM_HWIP][0] = IP_VERSION(9, 0, 0);
+		adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(9, 0, 0);
+		adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 0, 1);
+		adev->ip_versions[UVD_HWIP][0] = IP_VERSION(7, 0, 0);
+		adev->ip_versions[VCE_HWIP][0] = IP_VERSION(4, 0, 0);
+		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 0, 0);
+		break;
+	case CHIP_VEGA12:
+		vega10_reg_base_init(adev);
+		adev->sdma.num_instances = 2;
+		adev->ip_versions[MMHUB_HWIP][0] = IP_VERSION(9, 3, 0);
+		adev->ip_versions[ATHUB_HWIP][0] = IP_VERSION(9, 3, 0);
+		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 0, 1);
+		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 0, 1);
+		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 0, 1);
+		adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 5, 0);
+		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(6, 2, 0);
+		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 0);
+		adev->ip_versions[MP0_HWIP][0] = IP_VERSION(9, 0, 0);
+		adev->ip_versions[MP1_HWIP][0] = IP_VERSION(9, 0, 0);
+		adev->ip_versions[THM_HWIP][0] = IP_VERSION(9, 0, 0);
+		adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(9, 0, 1);
+		adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 2, 1);
+		adev->ip_versions[UVD_HWIP][0] = IP_VERSION(7, 0, 0);
+		adev->ip_versions[VCE_HWIP][0] = IP_VERSION(4, 0, 0);
+		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 0, 1);
+		break;
+	case CHIP_RAVEN:
+		vega10_reg_base_init(adev);
+		adev->sdma.num_instances = 1;
+		adev->vcn.num_vcn_inst = 1;
+		if (adev->apu_flags & AMD_APU_IS_RAVEN2) {
+			adev->ip_versions[MMHUB_HWIP][0] = IP_VERSION(9, 2, 0);
+			adev->ip_versions[ATHUB_HWIP][0] = IP_VERSION(9, 2, 0);
+			adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 1, 1);
+			adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 1, 1);
+			adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 1, 1);
+			adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 1, 1);
+			adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 0, 1);
+			adev->ip_versions[UMC_HWIP][0] = IP_VERSION(7, 5, 0);
+			adev->ip_versions[MP0_HWIP][0] = IP_VERSION(10, 0, 1);
+			adev->ip_versions[MP1_HWIP][0] = IP_VERSION(10, 0, 1);
+			adev->ip_versions[THM_HWIP][0] = IP_VERSION(10, 1, 0);
+			adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(10, 0, 1);
+			adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 2, 2);
+			adev->ip_versions[UVD_HWIP][0] = IP_VERSION(1, 0, 1);
+			adev->ip_versions[DCE_HWIP][0] = IP_VERSION(1, 0, 1);
+		} else {
+			adev->ip_versions[MMHUB_HWIP][0] = IP_VERSION(9, 1, 0);
+			adev->ip_versions[ATHUB_HWIP][0] = IP_VERSION(9, 1, 0);
+			adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 1, 0);
+			adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 1, 0);
+			adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 1, 0);
+			adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 1, 0);
+			adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 0, 0);
+			adev->ip_versions[UMC_HWIP][0] = IP_VERSION(7, 0, 0);
+			adev->ip_versions[MP0_HWIP][0] = IP_VERSION(10, 0, 0);
+			adev->ip_versions[MP1_HWIP][0] = IP_VERSION(10, 0, 0);
+			adev->ip_versions[THM_HWIP][0] = IP_VERSION(10, 0, 0);
+			adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(10, 0, 0);
+			adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 1, 0);
+			adev->ip_versions[UVD_HWIP][0] = IP_VERSION(1, 0, 0);
+			adev->ip_versions[DCE_HWIP][0] = IP_VERSION(1, 0, 0);
+		}
+		break;
+	case CHIP_VEGA20:
+		vega20_reg_base_init(adev);
+		adev->sdma.num_instances = 2;
+		adev->ip_versions[MMHUB_HWIP][0] = IP_VERSION(9, 4, 0);
+		adev->ip_versions[ATHUB_HWIP][0] = IP_VERSION(9, 4, 0);
+		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 2, 0);
+		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 2, 0);
+		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 2, 0);
+		adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 0);
+		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 0);
+		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 1);
+		adev->ip_versions[MP0_HWIP][0] = IP_VERSION(11, 0, 2);
+		adev->ip_versions[MP1_HWIP][0] = IP_VERSION(11, 0, 2);
+		adev->ip_versions[THM_HWIP][0] = IP_VERSION(11, 0, 2);
+		adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 2);
+		adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 0);
+		adev->ip_versions[UVD_HWIP][0] = IP_VERSION(7, 2, 0);
+		adev->ip_versions[VCE_HWIP][0] = IP_VERSION(4, 1, 0);
+		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 1, 0);
+		break;
+	case CHIP_ARCTURUS:
+		arct_reg_base_init(adev);
+		adev->sdma.num_instances = 8;
+		adev->vcn.num_vcn_inst = 2;
+		adev->ip_versions[MMHUB_HWIP][0] = IP_VERSION(9, 4, 1);
+		adev->ip_versions[ATHUB_HWIP][0] = IP_VERSION(9, 4, 1);
+		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 2, 1);
+		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 2, 1);
+		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 2, 2);
+		adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 1);
+		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 1);
+		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 2);
+		adev->ip_versions[MP0_HWIP][0] = IP_VERSION(11, 0, 4);
+		adev->ip_versions[MP1_HWIP][0] = IP_VERSION(11, 0, 2);
+		adev->ip_versions[THM_HWIP][0] = IP_VERSION(11, 0, 3);
+		adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 3);
+		adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 1);
+		adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 5, 0);
+		break;
+	case CHIP_ALDEBARAN:
+		aldebaran_reg_base_init(adev);
+		adev->sdma.num_instances = 5;
+		adev->vcn.num_vcn_inst = 2;
+		adev->ip_versions[MMHUB_HWIP][0] = IP_VERSION(9, 4, 2);
+		adev->ip_versions[ATHUB_HWIP][0] = IP_VERSION(9, 4, 2);
+		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 4, 0);
+		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 4, 0);
+		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 4, 0);
+		adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 2);
+		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 4);
+		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 7, 0);
+		adev->ip_versions[MP0_HWIP][0] = IP_VERSION(13, 0, 2);
+		adev->ip_versions[MP1_HWIP][0] = IP_VERSION(13, 0, 2);
+		adev->ip_versions[THM_HWIP][0] = IP_VERSION(13, 0, 2);
+		adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(13, 0, 2);
+		adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 2);
+		adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 6, 0);
+		adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0);
+		break;
+	default:
+		r = amdgpu_discovery_reg_base_init(adev);
+		if (r)
+			return -EINVAL;
+
+		amdgpu_discovery_harvest_ip(adev);
+
+		if (!adev->mman.discovery_bin) {
+			DRM_ERROR("ip discovery uninitialized\n");
+			return -EINVAL;
+		}
+		break;
+	}
+
+	switch (adev->ip_versions[GC_HWIP][0]) {
+	case IP_VERSION(9, 0, 1):
+	case IP_VERSION(9, 2, 1):
+	case IP_VERSION(9, 4, 0):
+	case IP_VERSION(9, 4, 1):
+	case IP_VERSION(9, 4, 2):
+		adev->family = AMDGPU_FAMILY_AI;
+		break;
+	case IP_VERSION(9, 1, 0):
+	case IP_VERSION(9, 2, 2):
+	case IP_VERSION(9, 3, 0):
+		adev->family = AMDGPU_FAMILY_RV;
+		break;
+	case IP_VERSION(10, 1, 10):
+	case IP_VERSION(10, 1, 1):
+	case IP_VERSION(10, 1, 2):
+	case IP_VERSION(10, 1, 3):
+	case IP_VERSION(10, 3, 0):
+	case IP_VERSION(10, 3, 2):
+	case IP_VERSION(10, 3, 4):
+	case IP_VERSION(10, 3, 5):
+		adev->family = AMDGPU_FAMILY_NV;
+		break;
+	case IP_VERSION(10, 3, 1):
+		adev->family = AMDGPU_FAMILY_VGH;
+		break;
+	case IP_VERSION(10, 3, 3):
+		adev->family = AMDGPU_FAMILY_YC;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (adev->ip_versions[XGMI_HWIP][0] == IP_VERSION(4, 8, 0))
+		adev->gmc.xgmi.supported = true;
+
+	/* set NBIO version */
+	switch (adev->ip_versions[NBIO_HWIP][0]) {
+	case IP_VERSION(6, 1, 0):
+	case IP_VERSION(6, 2, 0):
+		adev->nbio.funcs = &nbio_v6_1_funcs;
+		adev->nbio.hdp_flush_reg = &nbio_v6_1_hdp_flush_reg;
+		break;
+	case IP_VERSION(7, 0, 0):
+	case IP_VERSION(7, 0, 1):
+	case IP_VERSION(2, 5, 0):
+		adev->nbio.funcs = &nbio_v7_0_funcs;
+		adev->nbio.hdp_flush_reg = &nbio_v7_0_hdp_flush_reg;
+		break;
+	case IP_VERSION(7, 4, 0):
+	case IP_VERSION(7, 4, 1):
+	case IP_VERSION(7, 4, 4):
+		adev->nbio.funcs = &nbio_v7_4_funcs;
+		adev->nbio.hdp_flush_reg = &nbio_v7_4_hdp_flush_reg;
+		break;
+	case IP_VERSION(7, 2, 0):
+	case IP_VERSION(7, 2, 1):
+	case IP_VERSION(7, 5, 0):
+		adev->nbio.funcs = &nbio_v7_2_funcs;
+		adev->nbio.hdp_flush_reg = &nbio_v7_2_hdp_flush_reg;
+		break;
+	case IP_VERSION(2, 1, 1):
+	case IP_VERSION(2, 3, 0):
+	case IP_VERSION(2, 3, 1):
+	case IP_VERSION(2, 3, 2):
+	case IP_VERSION(3, 3, 0):
+	case IP_VERSION(3, 3, 1):
+	case IP_VERSION(3, 3, 2):
+	case IP_VERSION(3, 3, 3):
+		adev->nbio.funcs = &nbio_v2_3_funcs;
+		adev->nbio.hdp_flush_reg = &nbio_v2_3_hdp_flush_reg;
+		break;
+	default:
+		break;
+	}
+
+	switch (adev->ip_versions[HDP_HWIP][0]) {
+	case IP_VERSION(4, 0, 0):
+	case IP_VERSION(4, 0, 1):
+	case IP_VERSION(4, 1, 0):
+	case IP_VERSION(4, 1, 1):
+	case IP_VERSION(4, 1, 2):
+	case IP_VERSION(4, 2, 0):
+	case IP_VERSION(4, 2, 1):
+	case IP_VERSION(4, 4, 0):
+		adev->hdp.funcs = &hdp_v4_0_funcs;
+		break;
+	case IP_VERSION(5, 0, 0):
+	case IP_VERSION(5, 0, 1):
+	case IP_VERSION(5, 0, 2):
+	case IP_VERSION(5, 0, 3):
+	case IP_VERSION(5, 0, 4):
+	case IP_VERSION(5, 2, 0):
+		adev->hdp.funcs = &hdp_v5_0_funcs;
+		break;
+	default:
+		break;
+	}
+
+	switch (adev->ip_versions[DF_HWIP][0]) {
+	case IP_VERSION(3, 6, 0):
+	case IP_VERSION(3, 6, 1):
+	case IP_VERSION(3, 6, 2):
+		adev->df.funcs = &df_v3_6_funcs;
+		break;
+	case IP_VERSION(2, 1, 0):
+	case IP_VERSION(2, 1, 1):
+	case IP_VERSION(2, 5, 0):
+	case IP_VERSION(3, 5, 1):
+	case IP_VERSION(3, 5, 2):
+		adev->df.funcs = &df_v1_7_funcs;
+		break;
+	default:
+		break;
+	}
+
+	switch (adev->ip_versions[SMUIO_HWIP][0]) {
+	case IP_VERSION(9, 0, 0):
+	case IP_VERSION(9, 0, 1):
+	case IP_VERSION(10, 0, 0):
+	case IP_VERSION(10, 0, 1):
+	case IP_VERSION(10, 0, 2):
+		adev->smuio.funcs = &smuio_v9_0_funcs;
+		break;
+	case IP_VERSION(11, 0, 0):
+	case IP_VERSION(11, 0, 2):
+	case IP_VERSION(11, 0, 3):
+	case IP_VERSION(11, 0, 4):
+	case IP_VERSION(11, 0, 7):
+	case IP_VERSION(11, 0, 8):
+		adev->smuio.funcs = &smuio_v11_0_funcs;
+		break;
+	case IP_VERSION(11, 0, 6):
+	case IP_VERSION(11, 0, 10):
+	case IP_VERSION(11, 0, 11):
+	case IP_VERSION(11, 5, 0):
+	case IP_VERSION(13, 0, 1):
+		adev->smuio.funcs = &smuio_v11_0_6_funcs;
+		break;
+	case IP_VERSION(13, 0, 2):
+		adev->smuio.funcs = &smuio_v13_0_funcs;
+		break;
+	default:
+		break;
+	}
+
+	r = amdgpu_discovery_set_common_ip_blocks(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_discovery_set_gmc_ip_blocks(adev);
+	if (r)
+		return r;
+
+	/* For SR-IOV, PSP needs to be initialized before IH */
+	if (amdgpu_sriov_vf(adev)) {
+		r = amdgpu_discovery_set_psp_ip_blocks(adev);
+		if (r)
+			return r;
+		r = amdgpu_discovery_set_ih_ip_blocks(adev);
+		if (r)
+			return r;
+	} else {
+		r = amdgpu_discovery_set_ih_ip_blocks(adev);
+		if (r)
+			return r;
+
+		if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) {
+			r = amdgpu_discovery_set_psp_ip_blocks(adev);
+			if (r)
+				return r;
+		}
+	}
+
+	if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)) {
+		r = amdgpu_discovery_set_smu_ip_blocks(adev);
+		if (r)
+			return r;
+	}
+
+	r = amdgpu_discovery_set_display_ip_blocks(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_discovery_set_gc_ip_blocks(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_discovery_set_sdma_ip_blocks(adev);
+	if (r)
+		return r;
+
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
+	    !amdgpu_sriov_vf(adev)) {
+		r = amdgpu_discovery_set_smu_ip_blocks(adev);
+		if (r)
+			return r;
+	}
+
+	r = amdgpu_discovery_set_mm_ip_blocks(adev);
+	if (r)
+		return r;
+
+	if (adev->enable_mes) {
+		r = amdgpu_discovery_set_mes_ip_blocks(adev);
+		if (r)
+			return r;
+	}
+
+	return 0;
+}
+

drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h

@@ -36,5 +36,6 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int n
 int amdgpu_discovery_get_vcn_version(struct amdgpu_device *adev, int vcn_instance,
 				     int *major, int *minor, int *revision);
 int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev);
+int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev);
 
 #endif /* __AMDGPU_DISCOVERY__ */

drivers/gpu/drm/amd/amdgpu/amdgpu_display.c

@@ -837,6 +837,28 @@ static int convert_tiling_flags_to_modifier(struct amdgpu_framebuffer *afb)
 	return 0;
 }
 
+/* Mirrors the is_displayable check in radeonsi's gfx6_compute_surface */
+static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb)
+{
+	u64 micro_tile_mode;
+
+	/* Zero swizzle mode means linear */
+	if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0)
+		return 0;
+
+	micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE);
+	switch (micro_tile_mode) {
+	case 0: /* DISPLAY */
+	case 3: /* RENDER */
+		return 0;
+	default:
+		drm_dbg_kms(afb->base.dev,
+			    "Micro tile mode %llu not supported for scanout\n",
+			    micro_tile_mode);
+		return -EINVAL;
+	}
+}
+
 static void get_block_dimensions(unsigned int block_log2, unsigned int cpp,
 				 unsigned int *width, unsigned int *height)
 {
@@ -1103,6 +1125,7 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 				    const struct drm_mode_fb_cmd2 *mode_cmd,
 				    struct drm_gem_object *obj)
 {
+	struct amdgpu_device *adev = drm_to_adev(dev);
 	int ret, i;
 
 	/*
@@ -1122,6 +1145,14 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev,
 	if (ret)
 		return ret;
 
+	if (!dev->mode_config.allow_fb_modifiers) {
+		drm_WARN_ONCE(dev, adev->family >= AMDGPU_FAMILY_AI,
+			      "GFX9+ requires FB check based on format modifier\n");
+		ret = check_tiling_flags_gfx6(rfb);
+		if (ret)
+			return ret;
+	}
+
 	if (dev->mode_config.allow_fb_modifiers &&
 	    !(rfb->base.flags & DRM_MODE_FB_MODIFIERS)) {
 		ret = convert_tiling_flags_to_modifier(rfb);

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -96,9 +96,11 @@
  * - 3.40.0 - Add AMDGPU_IDS_FLAGS_TMZ
  * - 3.41.0 - Add video codec query
  * - 3.42.0 - Add 16bpc fixed point display support
+ * - 3.43.0 - Add device hot plug/unplug support
+ * - 3.44.0 - DCN3 supports DCC independent block settings: !64B && 128B, 64B && 128B
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	42
+#define KMS_DRIVER_MINOR	44
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit;
@@ -627,7 +629,7 @@ module_param_named(mcbp, amdgpu_mcbp, int, 0444);
 /**
  * DOC: discovery (int)
  * Allow driver to discover hardware IP information from IP Discovery table at the top of VRAM.
- * (-1 = auto (default), 0 = disabled, 1 = enabled)
+ * (-1 = auto (default), 0 = disabled, 1 = enabled, 2 = use ip_discovery table from file)
  */
 MODULE_PARM_DESC(discovery,
 	"Allow driver to discover hardware IPs from IP Discovery table at the top of VRAM");
@@ -890,6 +892,636 @@ MODULE_PARM_DESC(smu_pptable_id,
 	"specify pptable id to be used (-1 = auto(default) value, 0 = use pptable from vbios, > 0 = soft pptable id)");
 module_param_named(smu_pptable_id, amdgpu_smu_pptable_id, int, 0444);
 
+/* These devices are not supported by amdgpu.
+ * They are supported by the mach64, r128, radeon drivers
+ */
+static const u16 amdgpu_unsupported_pciidlist[] = {
+	/* mach64 */
+	0x4354,
+	0x4358,
+	0x4554,
+	0x4742,
+	0x4744,
+	0x4749,
+	0x474C,
+	0x474D,
+	0x474E,
+	0x474F,
+	0x4750,
+	0x4751,
+	0x4752,
+	0x4753,
+	0x4754,
+	0x4755,
+	0x4756,
+	0x4757,
+	0x4758,
+	0x4759,
+	0x475A,
+	0x4C42,
+	0x4C44,
+	0x4C47,
+	0x4C49,
+	0x4C4D,
+	0x4C4E,
+	0x4C50,
+	0x4C51,
+	0x4C52,
+	0x4C53,
+	0x5654,
+	0x5655,
+	0x5656,
+	/* r128 */
+	0x4c45,
+	0x4c46,
+	0x4d46,
+	0x4d4c,
+	0x5041,
+	0x5042,
+	0x5043,
+	0x5044,
+	0x5045,
+	0x5046,
+	0x5047,
+	0x5048,
+	0x5049,
+	0x504A,
+	0x504B,
+	0x504C,
+	0x504D,
+	0x504E,
+	0x504F,
+	0x5050,
+	0x5051,
+	0x5052,
+	0x5053,
+	0x5054,
+	0x5055,
+	0x5056,
+	0x5057,
+	0x5058,
+	0x5245,
+	0x5246,
+	0x5247,
+	0x524b,
+	0x524c,
+	0x534d,
+	0x5446,
+	0x544C,
+	0x5452,
+	/* radeon */
+	0x3150,
+	0x3151,
+	0x3152,
+	0x3154,
+	0x3155,
+	0x3E50,
+	0x3E54,
+	0x4136,
+	0x4137,
+	0x4144,
+	0x4145,
+	0x4146,
+	0x4147,
+	0x4148,
+	0x4149,
+	0x414A,
+	0x414B,
+	0x4150,
+	0x4151,
+	0x4152,
+	0x4153,
+	0x4154,
+	0x4155,
+	0x4156,
+	0x4237,
+	0x4242,
+	0x4336,
+	0x4337,
+	0x4437,
+	0x4966,
+	0x4967,
+	0x4A48,
+	0x4A49,
+	0x4A4A,
+	0x4A4B,
+	0x4A4C,
+	0x4A4D,
+	0x4A4E,
+	0x4A4F,
+	0x4A50,
+	0x4A54,
+	0x4B48,
+	0x4B49,
+	0x4B4A,
+	0x4B4B,
+	0x4B4C,
+	0x4C57,
+	0x4C58,
+	0x4C59,
+	0x4C5A,
+	0x4C64,
+	0x4C66,
+	0x4C67,
+	0x4E44,
+	0x4E45,
+	0x4E46,
+	0x4E47,
+	0x4E48,
+	0x4E49,
+	0x4E4A,
+	0x4E4B,
+	0x4E50,
+	0x4E51,
+	0x4E52,
+	0x4E53,
+	0x4E54,
+	0x4E56,
+	0x5144,
+	0x5145,
+	0x5146,
+	0x5147,
+	0x5148,
+	0x514C,
+	0x514D,
+	0x5157,
+	0x5158,
+	0x5159,
+	0x515A,
+	0x515E,
+	0x5460,
+	0x5462,
+	0x5464,
+	0x5548,
+	0x5549,
+	0x554A,
+	0x554B,
+	0x554C,
+	0x554D,
+	0x554E,
+	0x554F,
+	0x5550,
+	0x5551,
+	0x5552,
+	0x5554,
+	0x564A,
+	0x564B,
+	0x564F,
+	0x5652,
+	0x5653,
+	0x5657,
+	0x5834,
+	0x5835,
+	0x5954,
+	0x5955,
+	0x5974,
+	0x5975,
+	0x5960,
+	0x5961,
+	0x5962,
+	0x5964,
+	0x5965,
+	0x5969,
+	0x5a41,
+	0x5a42,
+	0x5a61,
+	0x5a62,
+	0x5b60,
+	0x5b62,
+	0x5b63,
+	0x5b64,
+	0x5b65,
+	0x5c61,
+	0x5c63,
+	0x5d48,
+	0x5d49,
+	0x5d4a,
+	0x5d4c,
+	0x5d4d,
+	0x5d4e,
+	0x5d4f,
+	0x5d50,
+	0x5d52,
+	0x5d57,
+	0x5e48,
+	0x5e4a,
+	0x5e4b,
+	0x5e4c,
+	0x5e4d,
+	0x5e4f,
+	0x6700,
+	0x6701,
+	0x6702,
+	0x6703,
+	0x6704,
+	0x6705,
+	0x6706,
+	0x6707,
+	0x6708,
+	0x6709,
+	0x6718,
+	0x6719,
+	0x671c,
+	0x671d,
+	0x671f,
+	0x6720,
+	0x6721,
+	0x6722,
+	0x6723,
+	0x6724,
+	0x6725,
+	0x6726,
+	0x6727,
+	0x6728,
+	0x6729,
+	0x6738,
+	0x6739,
+	0x673e,
+	0x6740,
+	0x6741,
+	0x6742,
+	0x6743,
+	0x6744,
+	0x6745,
+	0x6746,
+	0x6747,
+	0x6748,
+	0x6749,
+	0x674A,
+	0x6750,
+	0x6751,
+	0x6758,
+	0x6759,
+	0x675B,
+	0x675D,
+	0x675F,
+	0x6760,
+	0x6761,
+	0x6762,
+	0x6763,
+	0x6764,
+	0x6765,
+	0x6766,
+	0x6767,
+	0x6768,
+	0x6770,
+	0x6771,
+	0x6772,
+	0x6778,
+	0x6779,
+	0x677B,
+	0x6840,
+	0x6841,
+	0x6842,
+	0x6843,
+	0x6849,
+	0x684C,
+	0x6850,
+	0x6858,
+	0x6859,
+	0x6880,
+	0x6888,
+	0x6889,
+	0x688A,
+	0x688C,
+	0x688D,
+	0x6898,
+	0x6899,
+	0x689b,
+	0x689c,
+	0x689d,
+	0x689e,
+	0x68a0,
+	0x68a1,
+	0x68a8,
+	0x68a9,
+	0x68b0,
+	0x68b8,
+	0x68b9,
+	0x68ba,
+	0x68be,
+	0x68bf,
+	0x68c0,
+	0x68c1,
+	0x68c7,
+	0x68c8,
+	0x68c9,
+	0x68d8,
+	0x68d9,
+	0x68da,
+	0x68de,
+	0x68e0,
+	0x68e1,
+	0x68e4,
+	0x68e5,
+	0x68e8,
+	0x68e9,
+	0x68f1,
+	0x68f2,
+	0x68f8,
+	0x68f9,
+	0x68fa,
+	0x68fe,
+	0x7100,
+	0x7101,
+	0x7102,
+	0x7103,
+	0x7104,
+	0x7105,
+	0x7106,
+	0x7108,
+	0x7109,
+	0x710A,
+	0x710B,
+	0x710C,
+	0x710E,
+	0x710F,
+	0x7140,
+	0x7141,
+	0x7142,
+	0x7143,
+	0x7144,
+	0x7145,
+	0x7146,
+	0x7147,
+	0x7149,
+	0x714A,
+	0x714B,
+	0x714C,
+	0x714D,
+	0x714E,
+	0x714F,
+	0x7151,
+	0x7152,
+	0x7153,
+	0x715E,
+	0x715F,
+	0x7180,
+	0x7181,
+	0x7183,
+	0x7186,
+	0x7187,
+	0x7188,
+	0x718A,
+	0x718B,
+	0x718C,
+	0x718D,
+	0x718F,
+	0x7193,
+	0x7196,
+	0x719B,
+	0x719F,
+	0x71C0,
+	0x71C1,
+	0x71C2,
+	0x71C3,
+	0x71C4,
+	0x71C5,
+	0x71C6,
+	0x71C7,
+	0x71CD,
+	0x71CE,
+	0x71D2,
+	0x71D4,
+	0x71D5,
+	0x71D6,
+	0x71DA,
+	0x71DE,
+	0x7200,
+	0x7210,
+	0x7211,
+	0x7240,
+	0x7243,
+	0x7244,
+	0x7245,
+	0x7246,
+	0x7247,
+	0x7248,
+	0x7249,
+	0x724A,
+	0x724B,
+	0x724C,
+	0x724D,
+	0x724E,
+	0x724F,
+	0x7280,
+	0x7281,
+	0x7283,
+	0x7284,
+	0x7287,
+	0x7288,
+	0x7289,
+	0x728B,
+	0x728C,
+	0x7290,
+	0x7291,
+	0x7293,
+	0x7297,
+	0x7834,
+	0x7835,
+	0x791e,
+	0x791f,
+	0x793f,
+	0x7941,
+	0x7942,
+	0x796c,
+	0x796d,
+	0x796e,
+	0x796f,
+	0x9400,
+	0x9401,
+	0x9402,
+	0x9403,
+	0x9405,
+	0x940A,
+	0x940B,
+	0x940F,
+	0x94A0,
+	0x94A1,
+	0x94A3,
+	0x94B1,
+	0x94B3,
+	0x94B4,
+	0x94B5,
+	0x94B9,
+	0x9440,
+	0x9441,
+	0x9442,
+	0x9443,
+	0x9444,
+	0x9446,
+	0x944A,
+	0x944B,
+	0x944C,
+	0x944E,
+	0x9450,
+	0x9452,
+	0x9456,
+	0x945A,
+	0x945B,
+	0x945E,
+	0x9460,
+	0x9462,
+	0x946A,
+	0x946B,
+	0x947A,
+	0x947B,
+	0x9480,
+	0x9487,
+	0x9488,
+	0x9489,
+	0x948A,
+	0x948F,
+	0x9490,
+	0x9491,
+	0x9495,
+	0x9498,
+	0x949C,
+	0x949E,
+	0x949F,
+	0x94C0,
+	0x94C1,
+	0x94C3,
+	0x94C4,
+	0x94C5,
+	0x94C6,
+	0x94C7,
+	0x94C8,
+	0x94C9,
+	0x94CB,
+	0x94CC,
+	0x94CD,
+	0x9500,
+	0x9501,
+	0x9504,
+	0x9505,
+	0x9506,
+	0x9507,
+	0x9508,
+	0x9509,
+	0x950F,
+	0x9511,
+	0x9515,
+	0x9517,
+	0x9519,
+	0x9540,
+	0x9541,
+	0x9542,
+	0x954E,
+	0x954F,
+	0x9552,
+	0x9553,
+	0x9555,
+	0x9557,
+	0x955f,
+	0x9580,
+	0x9581,
+	0x9583,
+	0x9586,
+	0x9587,
+	0x9588,
+	0x9589,
+	0x958A,
+	0x958B,
+	0x958C,
+	0x958D,
+	0x958E,
+	0x958F,
+	0x9590,
+	0x9591,
+	0x9593,
+	0x9595,
+	0x9596,
+	0x9597,
+	0x9598,
+	0x9599,
+	0x959B,
+	0x95C0,
+	0x95C2,
+	0x95C4,
+	0x95C5,
+	0x95C6,
+	0x95C7,
+	0x95C9,
+	0x95CC,
+	0x95CD,
+	0x95CE,
+	0x95CF,
+	0x9610,
+	0x9611,
+	0x9612,
+	0x9613,
+	0x9614,
+	0x9615,
+	0x9616,
+	0x9640,
+	0x9641,
+	0x9642,
+	0x9643,
+	0x9644,
+	0x9645,
+	0x9647,
+	0x9648,
+	0x9649,
+	0x964a,
+	0x964b,
+	0x964c,
+	0x964e,
+	0x964f,
+	0x9710,
+	0x9711,
+	0x9712,
+	0x9713,
+	0x9714,
+	0x9715,
+	0x9802,
+	0x9803,
+	0x9804,
+	0x9805,
+	0x9806,
+	0x9807,
+	0x9808,
+	0x9809,
+	0x980A,
+	0x9900,
+	0x9901,
+	0x9903,
+	0x9904,
+	0x9905,
+	0x9906,
+	0x9907,
+	0x9908,
+	0x9909,
+	0x990A,
+	0x990B,
+	0x990C,
+	0x990D,
+	0x990E,
+	0x990F,
+	0x9910,
+	0x9913,
+	0x9917,
+	0x9918,
+	0x9919,
+	0x9990,
+	0x9991,
+	0x9992,
+	0x9993,
+	0x9994,
+	0x9995,
+	0x9996,
+	0x9997,
+	0x9998,
+	0x9999,
+	0x999A,
+	0x999B,
+	0x999C,
+	0x999D,
+	0x99A0,
+	0x99A2,
+	0x99A4,
+};
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
@@ -1239,6 +1871,16 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x7423, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
 	{0x1002, 0x743F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
 
+	{ PCI_DEVICE(0x1002, PCI_ANY_ID),
+	  .class = PCI_CLASS_DISPLAY_VGA << 8,
+	  .class_mask = 0xffffff,
+	  .driver_data = CHIP_IP_DISCOVERY },
+
+	{ PCI_DEVICE(0x1002, PCI_ANY_ID),
+	  .class = PCI_CLASS_DISPLAY_OTHER << 8,
+	  .class_mask = 0xffffff,
+	  .driver_data = CHIP_IP_DISCOVERY },
+
 	{0, 0, 0}
 };
 
@@ -1252,9 +1894,20 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	struct drm_device *ddev;
 	struct amdgpu_device *adev;
 	unsigned long flags = ent->driver_data;
-	int ret, retry = 0;
+	int ret, retry = 0, i;
 	bool supports_atomic = false;
 
+	/* skip devices which are owned by radeon */
+	for (i = 0; i < ARRAY_SIZE(amdgpu_unsupported_pciidlist); i++) {
+		if (amdgpu_unsupported_pciidlist[i] == pdev->device)
+			return -ENODEV;
+	}
+
+	if (flags == 0) {
+		DRM_INFO("Unsupported asic.  Remove me when IP discovery init is in place.\n");
+		return -ENODEV;
+	}
+
 	if (amdgpu_virtual_display ||
 	    amdgpu_device_asic_has_dc_support(flags & AMD_ASIC_MASK))
 		supports_atomic = true;
@@ -1508,6 +2161,10 @@ static int amdgpu_pmops_resume(struct device *dev)
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int r;
 
+	/* Avoids registers access if device is physically gone */
+	if (!pci_device_is_present(adev->pdev))
+		adev->no_hw_access = true;
+
 	r = amdgpu_device_resume(drm_dev, true);
 	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = false;

drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c

@@ -550,7 +550,7 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 			drm_sched_stop(&ring->sched, NULL);
 
 		/* You can't wait for HW to signal if it's gone */
-		if (!drm_dev_is_unplugged(&adev->ddev))
+		if (!drm_dev_is_unplugged(adev_to_drm(adev)))
 			r = amdgpu_fence_wait_empty(ring);
 		else
 			r = -ENODEV;

drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c

@@ -34,6 +34,7 @@
 #include <asm/set_memory.h>
 #endif
 #include "amdgpu.h"
+#include <drm/drm_drv.h>
 
 /*
  * GART
@@ -230,12 +231,16 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 	u64 page_base;
 	/* Starting from VEGA10, system bit must be 0 to mean invalid. */
 	uint64_t flags = 0;
+	int idx;
 
 	if (!adev->gart.ready) {
 		WARN(1, "trying to unbind memory from uninitialized GART !\n");
 		return -EINVAL;
 	}
 
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
+		return 0;
+
 	t = offset / AMDGPU_GPU_PAGE_SIZE;
 	p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 	for (i = 0; i < pages; i++, p++) {
@@ -254,6 +259,7 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 	for (i = 0; i < adev->num_vmhubs; i++)
 		amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
 
+	drm_dev_exit(idx);
 	return 0;
 }
 
@@ -276,12 +282,16 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 {
 	uint64_t page_base;
 	unsigned i, j, t;
+	int idx;
 
 	if (!adev->gart.ready) {
 		WARN(1, "trying to bind memory to uninitialized GART !\n");
 		return -EINVAL;
 	}
 
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
+		return 0;
+
 	t = offset / AMDGPU_GPU_PAGE_SIZE;
 
 	for (i = 0; i < pages; i++) {
@@ -291,6 +301,7 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 			page_base += AMDGPU_GPU_PAGE_SIZE;
 		}
 	}
+	drm_dev_exit(idx);
 	return 0;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c

@@ -62,7 +62,6 @@ static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf)
 
 		ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
 					       TTM_BO_VM_NUM_PREFAULT, 1);
-
 		drm_dev_exit(idx);
 	} else {
 		ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);

drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c

@@ -31,6 +31,8 @@
 /* delay 0.1 second to enable gfx off feature */
 #define GFX_OFF_DELAY_ENABLE         msecs_to_jiffies(100)
 
+#define GFX_OFF_NO_DELAY 0
+
 /*
  * GPU GFX IP block helpers function.
  */
@@ -558,6 +560,8 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev)
 
 void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 {
+	unsigned long delay = GFX_OFF_DELAY_ENABLE;
+
 	if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
 		return;
 
@@ -573,8 +577,14 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 		adev->gfx.gfx_off_req_count--;
 
-		if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state)
+		if (adev->gfx.gfx_off_req_count == 0 &&
-			schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
+		    !adev->gfx.gfx_off_state) {
+			/* If going to s2idle, no need to wait */
+			if (adev->in_s0ix)
+				delay = GFX_OFF_NO_DELAY;
+			schedule_delayed_work(&adev->gfx.gfx_off_delay_work,
+					      delay);
+		}
 	} else {
 		if (adev->gfx.gfx_off_req_count == 0) {
 			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);

drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h

@@ -42,10 +42,9 @@
 #define AMDGPU_MAX_GFX_QUEUES KGD_MAX_QUEUES
 #define AMDGPU_MAX_COMPUTE_QUEUES KGD_MAX_QUEUES
 
-enum gfx_pipe_priority {
+enum amdgpu_gfx_pipe_priority {
-	AMDGPU_GFX_PIPE_PRIO_NORMAL = 1,
+	AMDGPU_GFX_PIPE_PRIO_NORMAL = AMDGPU_RING_PRIO_1,
-	AMDGPU_GFX_PIPE_PRIO_HIGH,
+	AMDGPU_GFX_PIPE_PRIO_HIGH = AMDGPU_RING_PRIO_2
-	AMDGPU_GFX_PIPE_PRIO_MAX
 };
 
 /* Argument for PPSMC_MSG_GpuChangeState */

drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c

@@ -153,10 +153,6 @@ int amdgpu_gmc_set_pte_pde(struct amdgpu_device *adev, void *cpu_pt_addr,
 {
 	void __iomem *ptr = (void *)cpu_pt_addr;
 	uint64_t value;
-	int idx;
-
-	if (!drm_dev_enter(&adev->ddev, &idx))
-		return 0;
 
 	/*
 	 * The following is for PTE only. GART does not have PDEs.
@@ -165,8 +161,6 @@ int amdgpu_gmc_set_pte_pde(struct amdgpu_device *adev, void *cpu_pt_addr,
 	value |= flags;
 	writeq(value, ptr + (gpu_page_idx * 8));
 
-	drm_dev_exit(idx);
-
 	return 0;
 }
 
@@ -598,7 +592,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 		break;
 	default:
 		adev->gmc.tmz_enabled = false;
-		dev_warn(adev->dev,
+		dev_info(adev->dev,
 			 "Trusted Memory Zone (TMZ) feature not supported\n");
 		break;
 	}
@@ -749,6 +743,10 @@ void amdgpu_gmc_init_pdb0(struct amdgpu_device *adev)
 		adev->gmc.xgmi.physical_node_id * adev->gmc.xgmi.node_segment_size;
 	u64 vram_end = vram_addr + vram_size;
 	u64 gart_ptb_gpu_pa = amdgpu_gmc_vram_pa(adev, adev->gart.bo);
+	int idx;
+
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
+		return;
 
 	flags |= AMDGPU_PTE_VALID | AMDGPU_PTE_READABLE;
 	flags |= AMDGPU_PTE_WRITEABLE;
@@ -770,6 +768,7 @@ void amdgpu_gmc_init_pdb0(struct amdgpu_device *adev)
 	flags |= AMDGPU_PDE_BFS(0) | AMDGPU_PTE_SNOOPED;
 	/* Requires gart_ptb_gpu_pa to be 4K aligned */
 	amdgpu_gmc_set_pte_pde(adev, adev->gmc.ptr_pdb0, i, gart_ptb_gpu_pa, flags);
+	drm_dev_exit(idx);
 }
 
 /**

drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c

@@ -300,20 +300,15 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
  */
 int amdgpu_ib_pool_init(struct amdgpu_device *adev)
 {
-	unsigned size;
 	int r, i;
 
 	if (adev->ib_pool_ready)
 		return 0;
 
 	for (i = 0; i < AMDGPU_IB_POOL_MAX; i++) {
-		if (i == AMDGPU_IB_POOL_DIRECT)
-			size = PAGE_SIZE * 6;
-		else
-			size = AMDGPU_IB_POOL_SIZE;
-
 		r = amdgpu_sa_bo_manager_init(adev, &adev->ib_pools[i],
-					      size, AMDGPU_GPU_PAGE_SIZE,
+					      AMDGPU_IB_POOL_SIZE,
+					      AMDGPU_GPU_PAGE_SIZE,
 					      AMDGPU_GEM_DOMAIN_GTT);
 		if (r)
 			goto error;

drivers/gpu/drm/amd/amdgpu/amdgpu_job.c

@@ -38,7 +38,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	struct amdgpu_device *adev = ring->adev;
 	int idx;
 
-	if (!drm_dev_enter(&adev->ddev, &idx)) {
+	if (!drm_dev_enter(adev_to_drm(adev), &idx)) {
 		DRM_INFO("%s - device unplugged skipping recovery on scheduler:%s",
 			 __func__, s_job->sched->name);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c

@@ -341,27 +341,34 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		switch (query_fw->index) {
 		case TA_FW_TYPE_PSP_XGMI:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.xgmi.feature_version;
+			fw_info->feature = adev->psp.xgmi_context.context
+						   .bin_desc.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_RAS:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.ras.feature_version;
+			fw_info->feature = adev->psp.ras_context.context
+						   .bin_desc.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_HDCP:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.hdcp.feature_version;
+			fw_info->feature = adev->psp.hdcp_context.context
+						   .bin_desc.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_DTM:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.dtm.feature_version;
+			fw_info->feature = adev->psp.dtm_context.context
+						   .bin_desc.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_RAP:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.rap.feature_version;
+			fw_info->feature = adev->psp.rap_context.context
+						   .bin_desc.feature_version;
 			break;
 		case TA_FW_TYPE_PSP_SECUREDISPLAY:
 			fw_info->ver = adev->psp.ta_fw_version;
-			fw_info->feature = adev->psp.securedisplay.feature_version;
+			fw_info->feature =
+				adev->psp.securedisplay_context.context.bin_desc
+					.feature_version;
 			break;
 		default:
 			return -EINVAL;
@@ -378,8 +385,8 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->feature = adev->psp.sos.feature_version;
 		break;
 	case AMDGPU_INFO_FW_ASD:
-		fw_info->ver = adev->psp.asd.fw_version;
+		fw_info->ver = adev->psp.asd_context.bin_desc.fw_version;
-		fw_info->feature = adev->psp.asd.feature_version;
+		fw_info->feature = adev->psp.asd_context.bin_desc.feature_version;
 		break;
 	case AMDGPU_INFO_FW_DMCU:
 		fw_info->ver = adev->dm.dmcu_fw_version;

drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c

@@ -31,7 +31,7 @@ void amdgpu_mca_query_correctable_error_count(struct amdgpu_device *adev,
 					      uint64_t mc_status_addr,
 					      unsigned long *error_count)
 {
-	uint64_t mc_status = RREG64_PCIE(mc_status_addr * 4);
+	uint64_t mc_status = RREG64_PCIE(mc_status_addr);
 
 	if (REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
 	    REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)
@@ -42,7 +42,7 @@ void amdgpu_mca_query_uncorrectable_error_count(struct amdgpu_device *adev,
 						uint64_t mc_status_addr,
 						unsigned long *error_count)
 {
-	uint64_t mc_status = RREG64_PCIE(mc_status_addr * 4);
+	uint64_t mc_status = RREG64_PCIE(mc_status_addr);
 
 	if ((REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
 	    (REG_GET_FIELD(mc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
@@ -56,7 +56,7 @@ void amdgpu_mca_query_uncorrectable_error_count(struct amdgpu_device *adev,
 void amdgpu_mca_reset_error_count(struct amdgpu_device *adev,
 				  uint64_t mc_status_addr)
 {
-	WREG64_PCIE(mc_status_addr * 4, 0x0ULL);
+	WREG64_PCIE(mc_status_addr, 0x0ULL);
 }
 
 void amdgpu_mca_query_ras_error_count(struct amdgpu_device *adev,
@@ -87,8 +87,8 @@ int amdgpu_mca_ras_late_init(struct amdgpu_device *adev,
 		if (!mca_dev->ras_if)
 			return -ENOMEM;
 		mca_dev->ras_if->block = mca_dev->ras_funcs->ras_block;
+		mca_dev->ras_if->sub_block_index = mca_dev->ras_funcs->ras_sub_block;
 		mca_dev->ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
-		mca_dev->ras_if->sub_block_index = 0;
 	}
 	ih_info.head = fs_info.head = *mca_dev->ras_if;
 	r = amdgpu_ras_late_init(adev, mca_dev->ras_if,