drm/amd: Disable XNACK on SRIOV environment

The purpose of this patch is to disable XNACK or set XNACK OFF mode
on SRIOV platform which doesn't support it.

This will prevent user-space application to fail or result into
unexpected behaviour whenever the application need to run test-case
in XNACK ON mode.
Signed-off-by: Surbhi Kakarya <surbhi.kakarya@amd.com>
Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -826,6 +826,9 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
 				gc_ver == IP_VERSION(9, 4, 3) ||
 				gc_ver >= IP_VERSION(10, 3, 0));
 
+	if (!amdgpu_sriov_xnack_support(adev))
+		gmc->noretry = 1;
+	else
 		gmc->noretry = (amdgpu_noretry == -1) ? noretry_default : amdgpu_noretry;
 }
 

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

@@ -1093,3 +1093,13 @@ u32 amdgpu_sriov_rreg(struct amdgpu_device *adev,
 	else
 		return RREG32(offset);
 }
+
+bool amdgpu_sriov_xnack_support(struct amdgpu_device *adev)
+{
+	bool xnack_mode = true;
+
+	if (amdgpu_sriov_vf(adev) && adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 2))
+		xnack_mode = false;
+
+	return xnack_mode;
+}

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

@@ -365,4 +365,5 @@ u32 amdgpu_sriov_rreg(struct amdgpu_device *adev,
 bool amdgpu_virt_fw_load_skip_check(struct amdgpu_device *adev,
 			uint32_t ucode_id);
 void amdgpu_virt_post_reset(struct amdgpu_device *adev);
+bool amdgpu_sriov_xnack_support(struct amdgpu_device *adev);
 #endif

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

@@ -1416,8 +1416,13 @@ bool kfd_process_xnack_mode(struct kfd_process *p, bool supported)
 		 * per-process XNACK mode selection. But let the dev->noretry
 		 * setting still influence the default XNACK mode.
 		 */
-		if (supported && KFD_SUPPORT_XNACK_PER_PROCESS(dev))
+		if (supported && KFD_SUPPORT_XNACK_PER_PROCESS(dev)) {
+			if (!amdgpu_sriov_xnack_support(dev->kfd->adev)) {
+				pr_debug("SRIOV platform xnack not supported\n");
+				return false;
+			}
 			continue;
+		}
 
 		/* GFXv10 and later GPUs do not support shader preemption
 		 * during page faults. This can lead to poor QoS for queue