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 <Philip.Yang@xxxxxxx> --- 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 */