Commit bcbede6f authored by Dave Airlie's avatar Dave Airlie
Browse files

Merge tag 'amd-drm-next-6.5-2023-06-16' of https://gitlab.freedesktop.org/agd5f/linux into drm-next 

amd-drm-next-6.5-2023-06-16:

amdgpu:
- Misc display fixes
- W=1 fixes
- Improve scheduler naming
- DCN 3.1.4 fixes
- kdoc fixes
- Enable W=1
- VCN 4.0 fix
- xgmi fixes
- TOPDOWN fix for large BAR systems
- eDP fix
- PSR fixes
- SubVP fixes
- Freesync fix
- DPIA fix
- SMU 13.0.5 fixes
- vblflash fix
- RAS fixes
- SDMA 4 fix
- BO locking fix
- BO backing store fix
- NBIO 7.9 fixes
- GC 9.4.3 fixes
- GPU reset recovery fixes
- HMM fix

amdkfd:
- Fix NULL check
- Trap fixes
- Queue count fix
- Add event age tracking

radeon:
- fbdev client fix

scheduler:
- Avoid an infinite loop

UAPI:
- Add KFD event age tracking:
  Proposed ROCT-Thunk-Interface:
  https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/efdbf6cfbc026bd68ac3c35d00dacf84370eb81e
  https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/1820ae0a2db85b6f584611dc0cde1a00e7c22915
  Proposed ROCR-Runtime:
  https://github.com/RadeonOpenCompute/ROCR-Runtime/compare/master...zhums:ROCR-Runtime:new_event_wait_review
  https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/e1f5bdb88eb882ac798aeca2c00ea3fbb2dba459
  https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/7d26afd14107b5c2a754c1a3f415d89f3aabb503



drm:
- DP MST fix

Signed-off-by: default avatarDave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230616163548.7706-1-alexander.deucher@amd.com
parents 4e237d84 72f1de49

drivers/gpu/drm/amd/amdgpu/Makefile

+12 −1
Original line number Diff line number Diff line
@@ -40,7 +40,18 @@ ccflags-y := -I$(FULL_AMD_PATH)/include/asic_reg \ 
	-I$(FULL_AMD_PATH)/amdkfd



subdir-ccflags-y := -Wextra

subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable)

subdir-ccflags-y += -Wunused

subdir-ccflags-y += -Wmissing-prototypes

subdir-ccflags-y += -Wmissing-declarations

subdir-ccflags-y += -Wmissing-include-dirs

subdir-ccflags-y += -Wold-style-definition

subdir-ccflags-y += -Wmissing-format-attribute

# Need this to avoid recursive variable evaluation issues

cond-flags := $(call cc-option, -Wunused-but-set-variable) \

	$(call cc-option, -Wunused-const-variable) \

	$(call cc-option, -Wstringop-truncation) \

	$(call cc-option, -Wpacked-not-aligned)

subdir-ccflags-y += $(cond-flags)

subdir-ccflags-y += -Wno-unused-parameter

subdir-ccflags-y += -Wno-type-limits

subdir-ccflags-y += -Wno-sign-compare

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

+1 −1
Original line number Diff line number Diff line
@@ -309,7 +309,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, 
	}

	p->gang_leader = p->jobs[p->gang_leader_idx];



	if (p->ctx->vram_lost_counter != p->gang_leader->vram_lost_counter) {

	if (p->ctx->generation != p->gang_leader->generation) {

		ret = -ECANCELED;

		goto free_all_kdata;

	}

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

+11 −3
Original line number Diff line number Diff line
@@ -333,7 +333,7 @@ static int amdgpu_ctx_init(struct amdgpu_ctx_mgr *mgr, int32_t priority, 


	ctx->reset_counter = atomic_read(&mgr->adev->gpu_reset_counter);

	ctx->reset_counter_query = ctx->reset_counter;

	ctx->vram_lost_counter = atomic_read(&mgr->adev->vram_lost_counter);

	ctx->generation = amdgpu_vm_generation(mgr->adev, &fpriv->vm);

	ctx->init_priority = priority;

	ctx->override_priority = AMDGPU_CTX_PRIORITY_UNSET;
@@ -432,6 +432,7 @@ int amdgpu_ctx_get_entity(struct amdgpu_ctx *ctx, u32 hw_ip, u32 instance, 
			  u32 ring, struct drm_sched_entity **entity)

{

	int r;

	struct drm_sched_entity *ctx_entity;



	if (hw_ip >= AMDGPU_HW_IP_NUM) {

		DRM_ERROR("unknown HW IP type: %d\n", hw_ip);
@@ -455,7 +456,14 @@ int amdgpu_ctx_get_entity(struct amdgpu_ctx *ctx, u32 hw_ip, u32 instance, 
			return r;

	}



	*entity = &ctx->entities[hw_ip][ring]->entity;

	ctx_entity = &ctx->entities[hw_ip][ring]->entity;

	r = drm_sched_entity_error(ctx_entity);

	if (r) {

		DRM_DEBUG("error entity %p\n", ctx_entity);

		return r;

	}



	*entity = ctx_entity;

	return 0;

}
@@ -586,7 +594,7 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev, 
	if (ctx->reset_counter != atomic_read(&adev->gpu_reset_counter))

		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RESET;



	if (ctx->vram_lost_counter != atomic_read(&adev->vram_lost_counter))

	if (ctx->generation != amdgpu_vm_generation(adev, &fpriv->vm))

		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_VRAMLOST;



	if (atomic_read(&ctx->guilty))

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

+1 −1
Original line number Diff line number Diff line
@@ -47,7 +47,7 @@ struct amdgpu_ctx { 
	struct amdgpu_ctx_mgr		*mgr;

	unsigned			reset_counter;

	unsigned			reset_counter_query;

	uint32_t			vram_lost_counter;

	uint64_t			generation;

	spinlock_t			ring_lock;

	struct amdgpu_ctx_entity	*entities[AMDGPU_HW_IP_NUM][AMDGPU_MAX_ENTITY_NUM];

	bool				preamble_presented;

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

+3 −0
Original line number Diff line number Diff line
@@ -1515,6 +1515,7 @@ static int amdgpu_discovery_get_mall_info(struct amdgpu_device *adev) 
				mall_size += mall_size_per_umc;

		}

		adev->gmc.mall_size = mall_size;

		adev->gmc.m_half_use = half_use;

		break;

	default:

		dev_err(adev->dev,
@@ -1896,6 +1897,8 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev) 
		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);

		break;

	case IP_VERSION(9, 4, 3):

		if (!amdgpu_exp_hw_support)

			return -EINVAL;

		amdgpu_device_ip_block_add(adev, &gfx_v9_4_3_ip_block);

		break;

	case IP_VERSION(10, 1, 10):