Merge tag 'amd-drm-next-6.2-2022-11-25' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.2-2022-11-25:

amdgpu:
- Old GCC fix
- GFX11 fixes
- PSP suspend/resume fix
- PCI ref count fix
- DC KASAN fix
- DCN 3.2.x fixes
- Dell platform suspend/resume fixes
- DCN 3.1.4 fixes
- RAS fixes
- SMU 13.x fixes
- Flex array changes
- VCN 4.0 RAS updates
- Add missing licsense to some files
- Documentation updates
- SR-IOV fixes
- DP MST DSC fix

amdkfd:
- Fix topology locking in error case

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221125180519.6389-1-alexander.deucher@amd.com

10 files changed, 70 insertions, 31 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index e1320edfc527..2ebbc6382a06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -327,7 +327,6 @@ static void amdgpu_connector_free_edid(struct drm_connector *connector)
 
 	kfree(amdgpu_connector->edid);
 	amdgpu_connector->edid = NULL;
-	drm_connector_update_edid_property(connector, NULL);
 }
 
 static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b2b1c66bfe39..9f7741871bb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4181,21 +4181,15 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 
 	r = amdgpu_device_ip_resume(adev);
 
-	/* no matter what r is, always need to properly release full GPU */
-	if (amdgpu_sriov_vf(adev)) {
-		amdgpu_virt_init_data_exchange(adev);
-		amdgpu_virt_release_full_gpu(adev, true);
-	}
-
 	if (r) {
 		dev_err(adev->dev, "amdgpu_device_ip_resume failed (%d).\n", r);
-		return r;
+		goto exit;
 	}
 	amdgpu_fence_driver_hw_init(adev);
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
-		return r;
+		goto exit;
 
 	queue_delayed_work(system_wq, &adev->delayed_init_work,
 			   msecs_to_jiffies(AMDGPU_RESUME_MS));
@@ -4203,12 +4197,19 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 	if (!adev->in_s0ix) {
 		r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
 		if (r)
-			return r;
+			goto exit;
 	}
 
+exit:
+	if (amdgpu_sriov_vf(adev)) {
+		amdgpu_virt_init_data_exchange(adev);
+		amdgpu_virt_release_full_gpu(adev, true);
+	}
+
+	if (r)
+		return r;
+
 	/* Make sure IB tests flushed */
-	if (amdgpu_sriov_vf(adev))
-		amdgpu_irq_gpu_reset_resume_helper(adev);
 	flush_delayed_work(&adev->delayed_init_work);
 
 	if (adev->in_s0ix) {
@@ -5045,6 +5046,8 @@ static void amdgpu_device_resume_display_audio(struct amdgpu_device *adev)
 		pm_runtime_enable(&(p->dev));
 		pm_runtime_resume(&(p->dev));
 	}
+
+	pci_dev_put(p);
 }
 
 static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
@@ -5083,6 +5086,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
 
 		if (expires < ktime_get_mono_fast_ns()) {
 			dev_warn(adev->dev, "failed to suspend display audio\n");
+			pci_dev_put(p);
 			/* TODO: abort the succeeding gpu reset? */
 			return -ETIMEDOUT;
 		}
@@ -5090,6 +5094,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev)
 
 	pm_runtime_disable(&(p->dev));
 
+	pci_dev_put(p);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 6b48178455bc..2509341df92d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -1702,11 +1702,13 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 	return 0;
 }
 
+#if defined(CONFIG_DRM_AMD_DC)
 static void amdgpu_discovery_set_sriov_display(struct amdgpu_device *adev)
 {
 	amdgpu_device_set_sriov_virtual_display(adev);
 	amdgpu_device_ip_block_add(adev, &amdgpu_vkms_ip_block);
 }
+#endif
 
 static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 5697d456d7d0..279715292d69 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -238,8 +238,7 @@ module_param_named(gartsize, amdgpu_gart_size, uint, 0600);
 
 /**
  * DOC: gttsize (int)
- * Restrict the size of GTT domain in MiB for testing. The default is -1 (It's VRAM size if 3GB < VRAM < 3/4 RAM,
- * otherwise 3/4 RAM size).
+ * Restrict the size of GTT domain in MiB for testing. The default is -1 (Use 1/2 RAM, minimum value is 3GB).
  */
 MODULE_PARM_DESC(gttsize, "Size of the GTT domain in megabytes (-1 = auto)");
 module_param_named(gttsize, amdgpu_gtt_size, int, 0600);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 4365ede42855..e970e3760cec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -479,6 +479,12 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 	unsigned i;
 	unsigned vmhub, inv_eng;
 
+	if (adev->enable_mes) {
+		/* reserve engine 5 for firmware */
+		for (vmhub = 0; vmhub < AMDGPU_MAX_VMHUBS; vmhub++)
+			vm_inv_engs[vmhub] &= ~(1 << 5);
+	}
+
 	for (i = 0; i < adev->num_rings; ++i) {
 		ring = adev->rings[i];
 		vmhub = ring->funcs->vmhub;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 032651a655f0..7f1ca90a552c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -174,7 +174,12 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 	drm_sched_job_cleanup(s_job);
 
 	amdgpu_sync_free(&job->explicit_sync);
-	dma_fence_put(&job->hw_fence);
+
+	/* only put the hw fence if has embedded fence */
+	if (!job->hw_fence.ops)
+		kfree(job);
+	else
+		dma_fence_put(&job->hw_fence);
 }
 
 void amdgpu_job_set_gang_leader(struct amdgpu_job *job,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 98dbf4e5aae9..1a3aa0eae591 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -198,6 +198,7 @@ void psp_ta_free_shared_buf(struct ta_mem_context *mem_ctx)
 {
 	amdgpu_bo_free_kernel(&mem_ctx->shared_bo, &mem_ctx->shared_mc_addr,
 			      &mem_ctx->shared_buf);
+	mem_ctx->shared_bo = NULL;
 }
 
 static void psp_free_shared_bufs(struct psp_context *psp)
@@ -208,6 +209,7 @@ static void psp_free_shared_bufs(struct psp_context *psp)
 	/* free TMR memory buffer */
 	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
 	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr);
+	psp->tmr_bo = NULL;
 
 	/* free xgmi shared memory */
 	psp_ta_free_shared_buf(&psp->xgmi_context.context.mem_context);
@@ -769,7 +771,7 @@ static int psp_load_toc(struct psp_context *psp,
 /* Set up Trusted Memory Region */
 static int psp_tmr_init(struct psp_context *psp)
 {
-	int ret;
+	int ret = 0;
 	int tmr_size;
 	void *tmr_buf;
 	void **pptr;
@@ -796,10 +798,12 @@ static int psp_tmr_init(struct psp_context *psp)
 		}
 	}
 
-	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
-	ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT,
-				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->tmr_bo, &psp->tmr_mc_addr, pptr);
+	if (!psp->tmr_bo) {
+		pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
+		ret = amdgpu_bo_create_kernel(psp->adev, tmr_size, PSP_TMR_ALIGNMENT,
+					      AMDGPU_GEM_DOMAIN_VRAM,
+					      &psp->tmr_bo, &psp->tmr_mc_addr, pptr);
+	}
 
 	return ret;
 }
@@ -2727,8 +2731,6 @@ static int psp_suspend(void *handle)
 	}
 
 out:
-	psp_free_shared_bufs(psp);
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h b/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h
index f772bb499f3e..0312c71c3af9 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmsch_v4_0.h
@@ -32,7 +32,6 @@
 
 #define RB_ENABLED (1 << 0)
 #define RB4_ENABLED (1 << 1)
-#define MMSCH_DOORBELL_OFFSET 0x8
 
 #define MMSCH_VF_ENGINE_STATUS__PASS 0x1
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index ce8374ee824d..ec87b00f2e05 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -770,6 +770,33 @@ static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev)
 	}
 }
 
+static void vcn_v2_6_enable_ras(struct amdgpu_device *adev, int inst_idx,
+				bool indirect)
+{
+	uint32_t tmp;
+
+	if (adev->ip_versions[UVD_HWIP][0] != IP_VERSION(2, 6, 0))
+		return;
+
+	tmp = VCN_RAS_CNTL__VCPU_VCODEC_REARM_MASK |
+	      VCN_RAS_CNTL__VCPU_VCODEC_IH_EN_MASK |
+	      VCN_RAS_CNTL__VCPU_VCODEC_PMI_EN_MASK |
+	      VCN_RAS_CNTL__VCPU_VCODEC_STALL_EN_MASK;
+	WREG32_SOC15_DPG_MODE(inst_idx,
+			      SOC15_DPG_MODE_OFFSET(VCN, 0, mmVCN_RAS_CNTL),
+			      tmp, 0, indirect);
+
+	tmp = UVD_VCPU_INT_EN__RASCNTL_VCPU_VCODEC_EN_MASK;
+	WREG32_SOC15_DPG_MODE(inst_idx,
+			      SOC15_DPG_MODE_OFFSET(VCN, 0, mmUVD_VCPU_INT_EN),
+			      tmp, 0, indirect);
+
+	tmp = UVD_SYS_INT_EN__RASCNTL_VCPU_VCODEC_EN_MASK;
+	WREG32_SOC15_DPG_MODE(inst_idx,
+			      SOC15_DPG_MODE_OFFSET(VCN, 0, mmUVD_SYS_INT_EN),
+			      tmp, 0, indirect);
+}
+
 static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
 {
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
@@ -849,6 +876,8 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 		VCN, 0, mmUVD_LMI_CTRL2), 0, 0, indirect);
 
+	vcn_v2_6_enable_ras(adev, inst_idx, indirect);
+
 	/* unblock VCPU register access */
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 		VCN, 0, mmUVD_RB_ARB_CTRL), 0, 0, indirect);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 403d054cf51b..66b3f42764df 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -103,7 +103,6 @@ static int vcn_v4_0_sw_init(void *handle)
 	struct amdgpu_ring *ring;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int i, r;
-	int vcn_doorbell_index = 0;
 
 	r = amdgpu_vcn_sw_init(adev);
 	if (r)
@@ -115,12 +114,6 @@ static int vcn_v4_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	if (amdgpu_sriov_vf(adev)) {
-		vcn_doorbell_index = adev->doorbell_index.vcn.vcn_ring0_1 - MMSCH_DOORBELL_OFFSET;
-		/* get DWORD offset */
-		vcn_doorbell_index = vcn_doorbell_index << 1;
-	}
-
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
 		volatile struct amdgpu_vcn4_fw_shared *fw_shared;
 
@@ -144,7 +137,7 @@ static int vcn_v4_0_sw_init(void *handle)
 		ring = &adev->vcn.inst[i].ring_enc[0];
 		ring->use_doorbell = true;
 		if (amdgpu_sriov_vf(adev))
-			ring->doorbell_index = vcn_doorbell_index + i * (adev->vcn.num_enc_rings + 1) + 1;
+			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + i * (adev->vcn.num_enc_rings + 1) + 1;
 		else
 			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + 8 * i;