drm/amdgpu/bu: Add use_mtype_cc_wa module param

By default, set use_mtype_cc_wa to 1 to set PTE coherence flag MTYPE_CC
instead of MTYPE_RW by default. This is required for the time being to
mitigate a bug causing XCCs to hit stale data due to TCC marking fully
dirty lines as exclusive.

Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Reviewed-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

4 files changed, 20 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index cb9373f8c25a..cd2a29a7e26d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -212,6 +212,7 @@ extern int amdgpu_noretry;
 extern int amdgpu_force_asic_type;
 extern int amdgpu_smartshift_bias;
 extern int amdgpu_use_xgmi_p2p;
+extern bool amdgpu_use_mtype_cc_wa;
 #ifdef CONFIG_HSA_AMD
 extern int sched_policy;
 extern bool debug_evictions;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index da4e50aef95a..8bc37826a99f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -823,6 +823,13 @@ module_param_named(no_queue_eviction_on_vm_fault, amdgpu_no_queue_eviction_on_vm
 #endif
 
 /**
+ * DOC: use_mtype_cc_wa (bool)
+ */
+bool amdgpu_use_mtype_cc_wa = true;
+MODULE_PARM_DESC(use_mtype_cc_wa, "Use MTYPE_CC workaround (0 = use MTYPE_RW where applicable, 1 = use MTYPE_CC where applicable (default))");
+module_param_named(use_mtype_cc_wa, amdgpu_use_mtype_cc_wa, bool, 0444);
+
+/**
  * DOC: pcie_p2p (bool)
  * Enable PCIe P2P (requires large-BAR). Default value: true (on)
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 2eb67b53e497..8623b93c05ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1187,6 +1187,7 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 	bool coherent = bo->flags & AMDGPU_GEM_CREATE_COHERENT;
 	bool uncached = bo->flags & AMDGPU_GEM_CREATE_UNCACHED;
 	unsigned int mtype;
+	unsigned int mtype_default;
 	bool snoop = false;
 
 	switch (adev->ip_versions[GC_HWIP][0]) {
@@ -1230,7 +1231,10 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 		/* FIXME: Needs more work for handling multiple memory
 		 * partitions (> NPS1 mode) e.g. NPS4 for both APU and dGPU
 		 * modes.
+		 * FIXME: Temporarily using MTYPE_CC instead of MTYPE_RW where applicable.
+		 * To force use of MTYPE_RW, set use_mtype_cc_wa=0
 		 */
+		mtype_default = amdgpu_use_mtype_cc_wa ? MTYPE_CC : MTYPE_RW;
 		snoop = true;
 		if (uncached) {
 			mtype = MTYPE_UC;
@@ -1245,14 +1249,14 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 			 * socket should be treated as remote access so MTYPE_RW
 			 * cannot be used always.
 			 */
-			mtype = MTYPE_RW;
+			mtype = mtype_default;
 		} else if (adev->flags & AMD_IS_APU) {
 			/* APU on carve out mode */
-			mtype = MTYPE_RW;
+			mtype = mtype_default;
 		} else {
 			/* dGPU */
 			if (is_vram && bo_adev == adev)
-				mtype = MTYPE_RW;
+				mtype = mtype_default;
 			else if (is_vram)
 				mtype = MTYPE_NC;
 			else
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 2b2129dd1e4a..477ef9294203 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1198,9 +1198,12 @@ svm_range_get_pte_flags(struct kfd_node *node,
 		if (uncached) {
 			mapping_flags |= AMDGPU_VM_MTYPE_UC;
 		} else if (domain == SVM_RANGE_VRAM_DOMAIN) {
-			/* local HBM region close to partition */
+			/* local HBM region close to partition
+			 * FIXME: Temporarily using MTYPE_CC instead of MTYPE_RW where applicable.
+			 * To force use of MTYPE_RW, set use_mtype_cc_wa=0
+			 */
 			if (bo_node == node)
-				mapping_flags |= AMDGPU_VM_MTYPE_RW;
+				mapping_flags |= amdgpu_use_mtype_cc_wa ? 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))
 				mapping_flags |= AMDGPU_VM_MTYPE_NC;