On 2023-10-03 12:57, Philip Yang wrote:
If there is no VRAM domain, bo_node is NULL and this causes crash. Move
the EXT_COHERENT support change to VRAM domain path.

Need another patch to support override PTE flag on APU.

Fixes: 55d7e2001c7e ("drm/amdgpu: Add EXT_COHERENT memory allocation flags")
Signed-off-by: Philip Yang <[email protected]>
---
  drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 14 ++++++--------
  1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c 
b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 0d88698ae33f..150a3e88691d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1252,19 +1252,17 @@ svm_range_get_pte_flags(struct kfd_node *node,
                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;
+                               if (ext_coherent)
+                                       mapping_flags |= AMDGPU_VM_MTYPE_CC;
+                               else
+                                       mapping_flags |= mtype_local;

I'd prefer if this did not override the local mtype unless we're using the default. So I'd recommend a patch that changes

                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);

...

-                       /* 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;

Regards,
  Felix


                        /* local HBM region far from partition or remote XGMI 
GPU */
+                       else if (ext_coherent)
+                               mapping_flags |= AMDGPU_VM_MTYPE_UC;
                        else if (svm_nodes_in_same_hive(bo_node, node))
                                mapping_flags |= AMDGPU_VM_MTYPE_NC;
                        /* PCIe P2P */

Reply via email to