Merge tag 'amd-drm-next-6.2-2022-11-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.2-2022-11-18:

amdgpu:
- SR-IOV fixes
- Clean up DC checks
- DCN 3.2.x fixes
- DCN 3.1.x fixes
- Don't enable degamma on asics which don't support it
- IP discovery fixes
- BACO fixes
- Fix vbios allocation handling when vkms is enabled
- Drop buggy tdr advanced mode GPU reset handling
- Fix the build when DCN is not set in kconfig
- MST DSC fixes
- Userptr fixes
- FRU and RAS EEPROM fixes
- VCN 4.x RAS support
- Aldrebaran CU occupancy reporting fix
- PSP ring cleanup

amdkfd:
- Memory limit fix
- Enable cooperative launch on gfx 10.3

amd-drm-next-6.2-2022-11-11:

amdgpu:
- SMU 13.x updates
- GPUVM TLB race fix
- DCN 3.1.4 updates
- DCN 3.2.x updates
- PSR fixes
- Kerneldoc fix
- Vega10 fan fix
- GPUVM locking fixes in error pathes
- BACO fix for Beige Goby
- EEPROM I2C address cleanup
- GFXOFF fix
- Fix DC memory leak in error pathes
- Flexible array updates
- Mtype fix for GPUVM PTEs
- Move Kconfig into amdgpu directory
- SR-IOV updates
- Fix possible memory leak in CS IOCTL error path

amdkfd:
- Fix possible memory overrun
- CRIU fixes

radeon:
- ACPI ref count fix
- HDA audio notifier support
- Move Kconfig into radeon directory

UAPI:
- Add new GEM_CREATE flags to help to transition more KFD functionality to the DRM UAPI.
  These are used internally in the driver to align location based memory coherency
  requirements from memory allocated in the KFD with how we manage GPUVM PTEs.  They
  are currently blocked in the GEM_CREATE IOCTL as we don't have a user right now.
  They are just used internally in the kernel driver for now for existing KFD memory
  allocations. So a change to the UAPI header, but no functional change in the UAPI.

From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Dave Airlie <[email protected]>

Author: airlied

drivers/gpu/drm/Kconfig

@@ -233,64 +233,8 @@ source "drivers/gpu/drm/i2c/Kconfig"
 
 source "drivers/gpu/drm/arm/Kconfig"
 
-config DRM_RADEON
-	tristate "ATI Radeon"
-	depends on DRM && PCI && MMU
-	depends on AGP || !AGP
-	select FW_LOADER
-	select DRM_DISPLAY_DP_HELPER
-	select DRM_DISPLAY_HELPER
-        select DRM_KMS_HELPER
-        select DRM_TTM
-	select DRM_TTM_HELPER
-	select POWER_SUPPLY
-	select HWMON
-	select BACKLIGHT_CLASS_DEVICE
-	select INTERVAL_TREE
-	# radeon depends on ACPI_VIDEO when ACPI is enabled, for select to work
-	# ACPI_VIDEO's dependencies must also be selected.
-	select INPUT if ACPI
-	select ACPI_VIDEO if ACPI
-	# On x86 ACPI_VIDEO also needs ACPI_WMI
-	select X86_PLATFORM_DEVICES if ACPI && X86
-	select ACPI_WMI if ACPI && X86
-	help
-	  Choose this option if you have an ATI Radeon graphics card.  There
-	  are both PCI and AGP versions.  You don't need to choose this to
-	  run the Radeon in plain VGA mode.
-
-	  If M is selected, the module will be called radeon.
-
 source "drivers/gpu/drm/radeon/Kconfig"
 
-config DRM_AMDGPU
-	tristate "AMD GPU"
-	depends on DRM && PCI && MMU
-	select FW_LOADER
-	select DRM_DISPLAY_DP_HELPER
-	select DRM_DISPLAY_HDMI_HELPER
-	select DRM_DISPLAY_HELPER
-	select DRM_KMS_HELPER
-	select DRM_SCHED
-	select DRM_TTM
-	select DRM_TTM_HELPER
-	select POWER_SUPPLY
-	select HWMON
-	select BACKLIGHT_CLASS_DEVICE
-	select INTERVAL_TREE
-	select DRM_BUDDY
-	# amdgpu depends on ACPI_VIDEO when ACPI is enabled, for select to work
-	# ACPI_VIDEO's dependencies must also be selected.
-	select INPUT if ACPI
-	select ACPI_VIDEO if ACPI
-	# On x86 ACPI_VIDEO also needs ACPI_WMI
-	select X86_PLATFORM_DEVICES if ACPI && X86
-	select ACPI_WMI if ACPI && X86
-	help
-	  Choose this option if you have a recent AMD Radeon graphics card.
-
-	  If M is selected, the module will be called amdgpu.
-
 source "drivers/gpu/drm/amd/amdgpu/Kconfig"
 
 source "drivers/gpu/drm/nouveau/Kconfig"

drivers/gpu/drm/amd/amdgpu/Kconfig

@@ -1,4 +1,33 @@
 # SPDX-License-Identifier: MIT
+
+config DRM_AMDGPU
+	tristate "AMD GPU"
+	depends on DRM && PCI && MMU
+	select FW_LOADER
+	select DRM_DISPLAY_DP_HELPER
+	select DRM_DISPLAY_HDMI_HELPER
+	select DRM_DISPLAY_HELPER
+	select DRM_KMS_HELPER
+	select DRM_SCHED
+	select DRM_TTM
+	select DRM_TTM_HELPER
+	select POWER_SUPPLY
+	select HWMON
+	select BACKLIGHT_CLASS_DEVICE
+	select INTERVAL_TREE
+	select DRM_BUDDY
+	# amdgpu depends on ACPI_VIDEO when ACPI is enabled, for select to work
+	# ACPI_VIDEO's dependencies must also be selected.
+	select INPUT if ACPI
+	select ACPI_VIDEO if ACPI
+	# On x86 ACPI_VIDEO also needs ACPI_WMI
+	select X86_PLATFORM_DEVICES if ACPI && X86
+	select ACPI_WMI if ACPI && X86
+	help
+	  Choose this option if you have a recent AMD Radeon graphics card.
+
+	  If M is selected, the module will be called amdgpu.
+
 config DRM_AMDGPU_SI
 	bool "Enable amdgpu support for SI parts"
 	depends on DRM_AMDGPU

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -250,7 +250,7 @@ endif
 amdgpu-$(CONFIG_COMPAT) += amdgpu_ioc32.o
 amdgpu-$(CONFIG_VGA_SWITCHEROO) += amdgpu_atpx_handler.o
 amdgpu-$(CONFIG_ACPI) += amdgpu_acpi.o
-amdgpu-$(CONFIG_HMM_MIRROR) += amdgpu_mn.o
+amdgpu-$(CONFIG_HMM_MIRROR) += amdgpu_hmm.o
 
 include $(FULL_AMD_PATH)/pm/Makefile
 

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

@@ -82,7 +82,6 @@
 #include "amdgpu_vce.h"
 #include "amdgpu_vcn.h"
 #include "amdgpu_jpeg.h"
-#include "amdgpu_mn.h"
 #include "amdgpu_gmc.h"
 #include "amdgpu_gfx.h"
 #include "amdgpu_sdma.h"
@@ -1065,6 +1064,7 @@ struct amdgpu_device {
 	struct work_struct		reset_work;
 
 	bool                            job_hang;
+	bool                            dc_enabled;
 };
 
 static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)
@@ -1122,6 +1122,8 @@ void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev,
 bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type);
 bool amdgpu_device_has_dc_support(struct amdgpu_device *adev);
 
+void amdgpu_device_set_sriov_virtual_display(struct amdgpu_device *adev);
+
 int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 				 struct amdgpu_reset_context *reset_context);
 
@@ -1295,6 +1297,7 @@ void amdgpu_device_pcie_port_wreg(struct amdgpu_device *adev,
 				u32 reg, u32 v);
 struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev,
 					    struct dma_fence *gang);
+bool amdgpu_device_has_display_hardware(struct amdgpu_device *adev);
 
 /* atpx handler */
 #if defined(CONFIG_VGA_SWITCHEROO)

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

@@ -847,7 +847,7 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 	struct amdgpu_atif *atif = &amdgpu_acpi_priv.atif;
 
 	if (atif->notifications.brightness_change) {
-		if (amdgpu_device_has_dc_support(adev)) {
+		if (adev->dc_enabled) {
 #if defined(CONFIG_DRM_AMD_DC)
 			struct amdgpu_display_manager *dm = &adev->dm;
 

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

@@ -41,5 +41,6 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 				kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
+	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
 	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings
 };

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

@@ -29,6 +29,7 @@
 #include "amdgpu_object.h"
 #include "amdgpu_gem.h"
 #include "amdgpu_vm.h"
+#include "amdgpu_hmm.h"
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_dma_buf.h"
 #include <uapi/linux/kfd_ioctl.h>
@@ -171,9 +172,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	    (kfd_mem_limit.ttm_mem_used + ttm_mem_needed >
 	     kfd_mem_limit.max_ttm_mem_limit) ||
 	    (adev && adev->kfd.vram_used + vram_needed >
-	     adev->gmc.real_vram_size -
-	     atomic64_read(&adev->vram_pin_size) -
-	     reserved_for_pt)) {
+	     adev->gmc.real_vram_size - reserved_for_pt)) {
 		ret = -ENOMEM;
 		goto release;
 	}
@@ -405,63 +404,15 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
 
 static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
 {
-	struct amdgpu_device *bo_adev = amdgpu_ttm_adev(mem->bo->tbo.bdev);
-	bool coherent = mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_COHERENT;
-	bool uncached = mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED;
-	uint32_t mapping_flags;
-	uint64_t pte_flags;
-	bool snoop = false;
+	uint32_t mapping_flags = AMDGPU_VM_PAGE_READABLE |
+				 AMDGPU_VM_MTYPE_DEFAULT;
 
-	mapping_flags = AMDGPU_VM_PAGE_READABLE;
 	if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE)
 		mapping_flags |= AMDGPU_VM_PAGE_WRITEABLE;
 	if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE)
 		mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE;
 
-	switch (adev->ip_versions[GC_HWIP][0]) {
-	case IP_VERSION(9, 4, 1):
-	case IP_VERSION(9, 4, 2):
-		if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
-			if (bo_adev == adev) {
-				if (uncached)
-					mapping_flags |= AMDGPU_VM_MTYPE_UC;
-				else if (coherent)
-					mapping_flags |= AMDGPU_VM_MTYPE_CC;
-				else
-					mapping_flags |= AMDGPU_VM_MTYPE_RW;
-				if ((adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2)) &&
-				    adev->gmc.xgmi.connected_to_cpu)
-					snoop = true;
-			} else {
-				if (uncached || coherent)
-					mapping_flags |= AMDGPU_VM_MTYPE_UC;
-				else
-					mapping_flags |= AMDGPU_VM_MTYPE_NC;
-				if (amdgpu_xgmi_same_hive(adev, bo_adev))
-					snoop = true;
-			}
-		} else {
-			if (uncached || coherent)
-				mapping_flags |= AMDGPU_VM_MTYPE_UC;
-			else
-				mapping_flags |= AMDGPU_VM_MTYPE_NC;
-			snoop = true;
-		}
-		break;
-	default:
-		if (uncached || coherent)
-			mapping_flags |= AMDGPU_VM_MTYPE_UC;
-		else
-			mapping_flags |= AMDGPU_VM_MTYPE_NC;
-
-		if (!(mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM))
-			snoop = true;
-	}
-
-	pte_flags = amdgpu_gem_va_map_flags(adev, mapping_flags);
-	pte_flags |= snoop ? AMDGPU_PTE_SNOOPED : 0;
-
-	return pte_flags;
+	return amdgpu_gem_va_map_flags(adev, mapping_flags);
 }
 
 /**
@@ -988,6 +939,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr,
 	struct amdkfd_process_info *process_info = mem->process_info;
 	struct amdgpu_bo *bo = mem->bo;
 	struct ttm_operation_ctx ctx = { true, false };
+	struct hmm_range *range;
 	int ret = 0;
 
 	mutex_lock(&process_info->lock);
@@ -998,7 +950,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr,
 		goto out;
 	}
 
-	ret = amdgpu_mn_register(bo, user_addr);
+	ret = amdgpu_hmm_register(bo, user_addr);
 	if (ret) {
 		pr_err("%s: Failed to register MMU notifier: %d\n",
 		       __func__, ret);
@@ -1017,7 +969,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr,
 		return 0;
 	}
 
-	ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages);
+	ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, &range);
 	if (ret) {
 		pr_err("%s: Failed to get user pages: %d\n", __func__, ret);
 		goto unregister_out;
@@ -1035,10 +987,10 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr,
 	amdgpu_bo_unreserve(bo);
 
 release_out:
-	amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
+	amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range);
 unregister_out:
 	if (ret)
-		amdgpu_mn_unregister(bo);
+		amdgpu_hmm_unregister(bo);
 out:
 	mutex_unlock(&process_info->lock);
 	return ret;
@@ -1673,6 +1625,11 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 		}
 	}
 
+	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_COHERENT)
+		alloc_flags |= AMDGPU_GEM_CREATE_COHERENT;
+	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED)
+		alloc_flags |= AMDGPU_GEM_CREATE_UNCACHED;
+
 	*mem = kzalloc(sizeof(struct kgd_mem), GFP_KERNEL);
 	if (!*mem) {
 		ret = -ENOMEM;
@@ -1817,7 +1774,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	mutex_unlock(&process_info->lock);
 
 	/* No more MMU notifiers */
-	amdgpu_mn_unregister(mem->bo);
+	amdgpu_hmm_unregister(mem->bo);
 
 	ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx);
 	if (unlikely(ret))
@@ -2362,6 +2319,8 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 	/* Go through userptr_inval_list and update any invalid user_pages */
 	list_for_each_entry(mem, &process_info->userptr_inval_list,
 			    validate_list.head) {
+		struct hmm_range *range;
+
 		invalid = atomic_read(&mem->invalid);
 		if (!invalid)
 			/* BO hasn't been invalidated since the last
@@ -2372,7 +2331,8 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 		bo = mem->bo;
 
 		/* Get updated user pages */
-		ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages);
+		ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages,
+						   &range);
 		if (ret) {
 			pr_debug("Failed %d to get user pages\n", ret);
 
@@ -2391,7 +2351,7 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 			 * FIXME: Cannot ignore the return code, must hold
 			 * notifier_lock
 			 */
-			amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
+			amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range);
 		}
 
 		/* Mark the BO as valid unless it was invalidated