Commit 3ebfd221 authored by Philip Yang's avatar Philip Yang Committed by Alex Deucher
Browse files

drm/amdkfd: Store xcp partition id to amdgpu bo 



For memory accounting per compute partition and export drm amdgpu bo and
then import to KFD, we need the xcp id to account the memory usage or
find the KFD node of the original amdgpu bo to create the KFD bo on the
correct adev KFD node.

Set xcp_id_plus1 of amdgpu_bo_param to create bo and store xcp_id to
amddgpu bo. Add helper macro to get the mem_id from adev and xcp_id.

v2: squash in fix ("drm/amdgpu: Fix BO creation failure on GFX 9.4.3 dGPU")

Signed-off-by: default avatarPhilip Yang <Philip.Yang@amd.com>
Reviewed-by: default avatarFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 6cfba94a

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

+4 −0
Original line number Diff line number Diff line
@@ -330,6 +330,10 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, 
void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev,

		uint64_t size, u32 alloc_flag);



#define KFD_XCP_MEM_ID(adev, xcp_id) \

		((adev)->xcp_mgr && (xcp_id) >= 0 ?\

		(adev)->xcp_mgr->xcp[(xcp_id)].mem_id : -1)



#define KFD_XCP_MEMORY_SIZE(n) ((n)->adev->gmc.num_mem_partitions ?\

		(n)->adev->gmc.mem_partitions[(n)->xcp->mem_id].size /\

		(n)->adev->xcp_mgr->num_xcp_per_mem_partition :\

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

+6 −5
Original line number Diff line number Diff line
@@ -1634,6 +1634,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( 
		uint64_t *offset, uint32_t flags, bool criu_resume)

{

	struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv);

	struct amdgpu_fpriv *fpriv = container_of(avm, struct amdgpu_fpriv, vm);

	enum ttm_bo_type bo_type = ttm_bo_type_device;

	struct sg_table *sg = NULL;

	uint64_t user_addr = 0;
@@ -1641,7 +1642,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( 
	struct drm_gem_object *gobj = NULL;

	u32 domain, alloc_domain;

	uint64_t aligned_size;

	int8_t mem_id = -1;

	int8_t xcp_id = -1;

	u64 alloc_flags;

	int ret;
@@ -1660,7 +1661,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( 
			alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ?

			AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0;

		}

		mem_id = avm->mem_id;

		xcp_id = fpriv->xcp_id == ~0 ? 0 : fpriv->xcp_id;

	} else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) {

		domain = alloc_domain = AMDGPU_GEM_DOMAIN_GTT;

		alloc_flags = 0;
@@ -1718,12 +1719,12 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( 
		goto err_reserve_limit;

	}



	pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s mem_id %d\n",

	pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s xcp_id %d\n",

		 va, (*mem)->aql_queue ? size << 1 : size,

		 domain_string(alloc_domain), mem_id);

		 domain_string(alloc_domain), xcp_id);



	ret = amdgpu_gem_object_create(adev, aligned_size, 1, alloc_domain, alloc_flags,

				       bo_type, NULL, &gobj, mem_id + 1);

				       bo_type, NULL, &gobj, xcp_id + 1);

	if (ret) {

		pr_debug("Failed to create BO on domain %s. ret %d\n",

			 domain_string(alloc_domain), ret);

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

+2 −2
Original line number Diff line number Diff line
@@ -98,7 +98,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, 
			     int alignment, u32 initial_domain,

			     u64 flags, enum ttm_bo_type type,

			     struct dma_resv *resv,

			     struct drm_gem_object **obj, int8_t mem_id_plus1)

			     struct drm_gem_object **obj, int8_t xcp_id_plus1)

{

	struct amdgpu_bo *bo;

	struct amdgpu_bo_user *ubo;
@@ -116,7 +116,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, 
	bp.flags = flags;

	bp.domain = initial_domain;

	bp.bo_ptr_size = sizeof(struct amdgpu_bo);

	bp.mem_id_plus1 = mem_id_plus1;

	bp.xcp_id_plus1 = xcp_id_plus1;



	r = amdgpu_bo_create_user(adev, &bp, &ubo);

	if (r)

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

+1 −1
Original line number Diff line number Diff line
@@ -43,7 +43,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, 
			     int alignment, u32 initial_domain,

			     u64 flags, enum ttm_bo_type type,

			     struct dma_resv *resv,

			     struct drm_gem_object **obj, int8_t mem_id_plus1);

			     struct drm_gem_object **obj, int8_t xcp_id_plus1);

int amdgpu_mode_dumb_create(struct drm_file *file_priv,

			    struct drm_device *dev,

			    struct drm_mode_create_dumb *args);

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

+10 −5
Original line number Diff line number Diff line
@@ -131,14 +131,15 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) 


	if (domain & AMDGPU_GEM_DOMAIN_VRAM) {

		unsigned int visible_pfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;

		int8_t mem_id = KFD_XCP_MEM_ID(adev, abo->xcp_id);



		if (adev->gmc.mem_partitions && abo->mem_id >= 0) {

			places[c].fpfn = adev->gmc.mem_partitions[abo->mem_id].range.fpfn;

		if (adev->gmc.mem_partitions && mem_id >= 0) {

			places[c].fpfn = adev->gmc.mem_partitions[mem_id].range.fpfn;

			/*

			 * memory partition range lpfn is inclusive start + size - 1

			 * TTM place lpfn is exclusive start + size

			 */

			places[c].lpfn = adev->gmc.mem_partitions[abo->mem_id].range.lpfn + 1;

			places[c].lpfn = adev->gmc.mem_partitions[mem_id].range.lpfn + 1;

		} else {

			places[c].fpfn = 0;

			places[c].lpfn = 0;
@@ -583,8 +584,12 @@ int amdgpu_bo_create(struct amdgpu_device *adev, 


	bo->flags = bp->flags;



	/* bo->mem_id -1 means any partition */

	bo->mem_id = bp->mem_id_plus1 - 1;

	if (adev->gmc.mem_partitions)

		/* For GPUs with spatial partitioning, bo->xcp_id=-1 means any partition */

		bo->xcp_id = bp->xcp_id_plus1 - 1;

	else

		/* For GPUs without spatial partitioning */

		bo->xcp_id = 0;



	if (!amdgpu_bo_support_uswc(bo->flags))

		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;