drm/amdkfd: Add VRAM accounting for SVM migration

Do VRAM accounting when doing migrations to vram to make sure
there is enough available VRAM and migrating to VRAM doesn't evict
other possible non-unified memory BOs. If migrating to VRAM fails,
driver can fall back to using system memory seamlessly.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index bdc01ca9609a7e57fac05ee60d6866a5950e2b07..5c8d81bfce7ab14938c9a45cc23f3ab6beac1dd0 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -509,10 +509,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
        start = start_mgr << PAGE_SHIFT;
        end = (last_mgr + 1) << PAGE_SHIFT;
 
+       r = amdgpu_amdkfd_reserve_mem_limit(node->adev,
+                                       prange->npages * PAGE_SIZE,
+                                       KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+                                       node->xcp ? node->xcp->id : 0);
+       if (r) {
+               dev_dbg(node->adev->dev, "failed to reserve VRAM, r: %ld\n", r);
+               return -ENOSPC;
+       }
+
        r = svm_range_vram_node_new(node, prange, true);
        if (r) {
                dev_dbg(node->adev->dev, "fail %ld to alloc vram\n", r);
-               return r;
+               goto out;
        }
        ttm_res_offset = (start_mgr - prange->start + prange->offset) << PAGE_SHIFT;
 
@@ -545,6 +554,11 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
                svm_range_vram_node_free(prange);
        }
 
+out:
+       amdgpu_amdkfd_unreserve_mem_limit(node->adev,
+                                       prange->npages * PAGE_SIZE,
+                                       KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+                                       node->xcp ? node->xcp->id : 0);
        return r < 0 ? r : 0;
 }
 

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f0f7f48af4137acb088e2e903f803c345babc3ec..386875e6eb96bacb6585ae58c5620db1f41fde92 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3426,7 +3426,7 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
                                mm, KFD_MIGRATE_TRIGGER_PREFETCH);
        *migrated = !r;
 
-       return r;
+       return 0;
 }
 
 int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)