From: Philip Yang <Philip.Yang@xxxxxxx>
For dGPU mode VRAM allocation, create amdgpu_bo from amdgpu_vm->mem_id,
to alloc from the correct memory range.
For APU mode VRAM allocation, set alloc domain to GTT, and set
bp->mem_id_plus1 from amdgpu_vm->mem_id + 1 to create amdgpu_bo, to
allocate system memory from correct NUMA node.
For GTT allocation, use mem_id -1 to allocate system memory from any
NUMA nodes.
Remove amdgpu_ttm_tt_set_mem_pool, to avoid the confusion that memory
maybe allocated from different mem_id.
Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
---
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 24 ++++++-------------
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 20 +---------------
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 1 -
3 files changed, 8 insertions(+), 37 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 6d0c25e34af1..71b22d61dd27 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1640,9 +1640,9 @@ 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;
u64 alloc_flags;
int ret;
- int mem_id = 0; /* Fixme : to be changed when mem_id support patch lands, until then NPS1, SPX only */
/*
* Check on which domain to allocate BO
@@ -1652,13 +1652,14 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
if (adev->gmc.is_app_apu) {
domain = AMDGPU_GEM_DOMAIN_GTT;
- alloc_domain = AMDGPU_GEM_DOMAIN_CPU;
+ alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
alloc_flags = 0;
} else {
alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ?
AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0;
}
+ mem_id = avm->mem_id;
} else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) {
domain = alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
alloc_flags = 0;
@@ -1716,11 +1717,12 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
goto err_reserve_limit;
}
- pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s\n",
- va, (*mem)->aql_queue ? size << 1 : size, domain_string(alloc_domain));
+ pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s mem_id %d\n",
+ va, (*mem)->aql_queue ? size << 1 : size,
+ domain_string(alloc_domain), mem_id);
ret = amdgpu_gem_object_create(adev, aligned_size, 1, alloc_domain, alloc_flags,
- bo_type, NULL, &gobj, 0);
+ bo_type, NULL, &gobj, mem_id + 1);
if (ret) {
pr_debug("Failed to create BO on domain %s. ret %d\n",
domain_string(alloc_domain), ret);
@@ -1746,17 +1748,6 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
(*mem)->mapped_to_gpu_memory = 0;
(*mem)->process_info = avm->process_info;
- if (adev->gmc.is_app_apu &&
- ((*mem)->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)) {
- bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
- bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;
- ret = amdgpu_ttm_tt_set_mem_pool(&bo->tbo, mem_id);
- if (ret) {
- pr_debug("failed to set ttm mem pool %d\n", ret);
- goto err_set_mem_partition;
- }
- }
-
add_kgd_mem_to_kfd_bo_list(*mem, avm->process_info, user_addr);
if (user_addr) {
@@ -1783,7 +1774,6 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
allocate_init_user_pages_failed:
err_pin_bo:
remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info);
-err_set_mem_partition:
drm_vma_node_revoke(&gobj->vma_node, drm_priv);
err_node_allow:
/* Don't unreserve system mem limit twice */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 254927c596ba..395edca3b7f9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1064,7 +1064,7 @@ static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
return NULL;
}
gtt->gobj = &bo->base;
- gtt->pool_id = NUMA_NO_NODE;
+ gtt->pool_id = abo->mem_id;
if (abo->flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
caching = ttm_write_combined;
@@ -1159,24 +1159,6 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev,
return ttm_pool_free(pool, ttm);
}
-/**
- * amdgpu_ttm_tt_set_mem_pool - Set the TTM memory pool for the TTM BO
- * @tbo: The ttm_buffer_object that backs the VRAM bo
- * @mem_id: to select the initialized ttm pool corresponding to the memory partition
- */
-int amdgpu_ttm_tt_set_mem_pool(struct ttm_buffer_object *tbo, int mem_id)
-{
- struct ttm_tt *ttm = tbo->ttm;
- struct amdgpu_ttm_tt *gtt;
-
- if (!ttm && !ttm_tt_is_populated(ttm))
- return -EINVAL;
-
- gtt = ttm_to_amdgpu_ttm_tt(ttm);
- gtt->pool_id = mem_id;
- return 0;
-}
-
/**
* amdgpu_ttm_tt_get_userptr - Return the userptr GTT ttm_tt for the current
* task
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index fe32de1bf4d5..8ef048a0a33e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -192,7 +192,6 @@ bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm);
struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm);
bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
unsigned long end, unsigned long *userptr);
-int amdgpu_ttm_tt_set_mem_pool(struct ttm_buffer_object *tbo, int mem_id);
bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm,
int *last_invalidated);
bool amdgpu_ttm_tt_is_userptr(struct ttm_tt *ttm);
--
2.40.1
