drm/amdgpu/bu: add mtype_local as a module parameter

Selects the MTYPE to be used for local memory,
(0 = MTYPE_CC (default), 1 = MTYPE_NC, 2 = MTYPE_RW)

v2: squash in build fix (Alex)
Reviewed-by: Graham Sider <Graham.Sider@amd.com>
Signed-off-by: David Francis <David.Francis@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -212,7 +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;
+extern int amdgpu_mtype_local;
 #ifdef CONFIG_HSA_AMD
 extern int sched_policy;
 extern bool debug_evictions;

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -823,11 +823,11 @@ module_param_named(no_queue_eviction_on_vm_fault, amdgpu_no_queue_eviction_on_vm
 #endif
 
 /**
- * DOC: use_mtype_cc_wa (bool)
+ * DOC: mtype_local (int)
  */
-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);
+int amdgpu_mtype_local;
+MODULE_PARM_DESC(mtype_local, "MTYPE for local memory (0 = MTYPE_CC (default), 1 = MTYPE_NC, 2 = MTYPE_RW)");
+module_param_named(mtype_local, amdgpu_mtype_local, int, 0444);
 
 /**
  * DOC: pcie_p2p (bool)

drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c

@@ -1235,7 +1235,16 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 		 * NUMA systems. Their MTYPE can be overridden per-page in
 		 * gmc_v9_0_override_vm_pte_flags.
 		 */
-		mtype_local = amdgpu_use_mtype_cc_wa ? MTYPE_CC : MTYPE_RW;
+		mtype_local = MTYPE_CC;
+		if (amdgpu_mtype_local == 1) {
+			DRM_INFO_ONCE("Using MTYPE_NC for local memory\n");
+			mtype_local = MTYPE_NC;
+		} else if (amdgpu_mtype_local == 2) {
+			DRM_INFO_ONCE("Using MTYPE_RW for local memory\n");
+			mtype_local = MTYPE_RW;
+		} else {
+			DRM_INFO_ONCE("Using MTYPE_CC for local memory\n");
+		}
 		is_local = (!is_vram && (adev->flags & AMD_IS_APU) &&
 			    num_possible_nodes() <= 1) ||
 			   (is_vram && adev == bo_adev /* TODO: memory partitions &&
@@ -1349,9 +1358,13 @@ static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
 	dev_dbg(adev->dev, "vm->mem_id=%d, local_node=%d, nid=%d\n",
 		/*vm->mem_id*/0, local_node, nid);
 	if (nid == local_node) {
-		unsigned int mtype_local =
-			amdgpu_use_mtype_cc_wa ? MTYPE_CC : MTYPE_RW;
 		uint64_t old_flags = *flags;
+		unsigned int mtype_local = MTYPE_CC;
+
+		if (amdgpu_mtype_local == 1)
+			mtype_local = MTYPE_NC;
+		else if (amdgpu_mtype_local == 2)
+			mtype_local = MTYPE_RW;
 
 		*flags = (*flags & ~AMDGPU_PTE_MTYPE_VG10_MASK) |
 			 AMDGPU_PTE_MTYPE_VG10(mtype_local);

drivers/gpu/drm/amd/amdkfd/kfd_svm.c

@@ -1192,8 +1192,7 @@ svm_range_get_pte_flags(struct kfd_node *node,
 		}
 		break;
 	case IP_VERSION(9, 4, 3):
-		mtype_local = amdgpu_use_mtype_cc_wa ? AMDGPU_VM_MTYPE_CC :
-						       AMDGPU_VM_MTYPE_RW;
+		mtype_local = amdgpu_mtype_local == 1 ? AMDGPU_VM_MTYPE_NC : (amdgpu_mtype_local == 2 ? AMDGPU_VM_MTYPE_RW : AMDGPU_VM_MTYPE_CC);
 		snoop = true;
 		if (uncached) {
 			mapping_flags |= AMDGPU_VM_MTYPE_UC;