From: Philip Yang <Philip.Yang@amd.com>
Date: Tue, 3 Oct 2023 15:37:40 +0000 (-0400)
Subject: drm/amdkfd: Fix EXT_COHERENT memory allocation crash
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=23de7616f35800412a2c4e4f7398c5601488d1aa;p=linux.git

drm/amdkfd: Fix EXT_COHERENT memory allocation crash

If there is no VRAM domain, bo_node is NULL and this causes crash.
Refactor the change, and use the module parameter as higher privilege.

Need another patch to support override PTE flag on APU.

Fixes: 5f248462c69d ("drm/amdgpu: Add EXT_COHERENT memory allocation flags")
Signed-off-by: Philip Yang <Philip.Yang@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_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 1d5f91678fa99..760e1acfa28e5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1250,26 +1250,22 @@ svm_range_get_pte_flags(struct kfd_node *node,
 		break;
 	case IP_VERSION(9, 4, 3):
 		mtype_local = amdgpu_mtype_local == 1 ? AMDGPU_VM_MTYPE_NC :
-			     (amdgpu_mtype_local == 2 ? AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW);
+			      (amdgpu_mtype_local == 2 || ext_coherent ?
+					AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW);
 		snoop = true;
 		if (uncached) {
 			mapping_flags |= AMDGPU_VM_MTYPE_UC;
-		} else if (ext_coherent) {
-			/* local HBM region close to partition */
-			if (bo_node->adev == node->adev &&
-			    (!bo_node->xcp || !node->xcp || bo_node->xcp->mem_id == node->xcp->mem_id))
-				mapping_flags |= AMDGPU_VM_MTYPE_CC;
-			else
-				mapping_flags |= AMDGPU_VM_MTYPE_UC;
 		} else if (domain == SVM_RANGE_VRAM_DOMAIN) {
 			/* local HBM region close to partition */
 			if (bo_node->adev == node->adev &&
 			    (!bo_node->xcp || !node->xcp || bo_node->xcp->mem_id == node->xcp->mem_id))
 				mapping_flags |= mtype_local;
-			/* local HBM region far from partition or remote XGMI GPU */
-			else if (svm_nodes_in_same_hive(bo_node, node))
+			/* local HBM region far from partition or remote XGMI GPU
+			 * with regular system scope coherence
+			 */
+			else if (svm_nodes_in_same_hive(bo_node, node) && !ext_coherent)
 				mapping_flags |= AMDGPU_VM_MTYPE_NC;
-			/* PCIe P2P */
+			/* PCIe P2P or extended system scope coherence */
 			else
 				mapping_flags |= AMDGPU_VM_MTYPE_UC;
 		/* system memory accessed by the APU */