[PATCH] drm/amdkfd: Add VRAM accounting for SVM migration

[Mukul Joshi <mukul.joshi@xxxxxxx>]

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@xxxxxxx>
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 16 +++++++++++++++-
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c     |  2 +-
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index bdc01ca9609a..a6bfc00c0310 100644
--- 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 allocate VRAM, size exceeds VRAM limit\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 f7d75b432cc6..bfab16b43fec 100644
--- 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)
-- 
2.35.1