Merge tag 'amd-drm-next-6.11-2024-07-12' of https://gitlab.freedeskto…

…p.org/agd5f/linux into drm-next amd-drm-next-6.11-2024-07-12: amdgpu: - RAS fixes - SMU fixes - GC 12 updates - SR-IOV fixes - IH 7 updates - DCC fixes - GC 11.5 fixes - DP MST fixes - GFX 9.4.4 fixes - SMU 14 updates - Documentation updates - MAINTAINERS updates - PSR SU fix - Misc small fixes Signed-off-by: Dave Airlie <airlied@redhat.com> From: Alex Deucher <alexander.deucher@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240712171637.2581787-1-alexander.deucher@amd.com
mariux64 · Jul 17, 2024 · 478a527 · 478a527
2 parents c58c391 + 1cff101
commit 478a527
Show file tree

Hide file tree

Showing 40 changed files with 1,039 additions and 134 deletions.
diff --git a/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv b/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
@@ -15,8 +15,8 @@ Radeon (RX/Pro) 500 /540(X) /550 /640 /WX2100 /WX3100 /WX200 Series, POLARIS12,
 Radeon (RX|TM) (PRO|WX) Vega /MI25 /V320 /V340L /8200 /9100 /SSG MxGPU, VEGA10, DCE 12, 9.0.1, VCE 4.0.0 / UVD 7.0.0, 4.0.0
 AMD Radeon (Pro) VII /MI50 /MI60, VEGA20, DCE 12, 9.4.0, VCE 4.1.0 / UVD 7.2.0, 4.2.0
 MI100, ARCTURUS, *, 9.4.1, VCN 2.5.0, 4.2.2
-MI200, ALDEBARAN, *, 9.4.2, VCN 2.6.0, 4.4.0
-MI300, AQUA_VANGARAM, *, 9.4.3, VCN 4.0.3, 4.4.2
+MI200 Series, ALDEBARAN, *, 9.4.2, VCN 2.6.0, 4.4.0
+MI300 Series, AQUA_VANJARAM, *, 9.4.3, VCN 4.0.3, 4.4.2
 AMD Radeon (RX|Pro) 5600(M|XT) /5700 (M|XT|XTB) /W5700, NAVI10, DCN 2.0.0, 10.1.10, VCN 2.0.0, 5.0.0
 AMD Radeon (Pro) 5300 /5500XTB/5500(XT|M) /W5500M /W5500, NAVI14, DCN 2.0.0, 10.1.1, VCN 2.0.2, 5.0.2
 AMD Radeon RX 6800(XT) /6900(XT) /W6800, SIENNA_CICHLID, DCN 3.0.0, 10.3.0, VCN 3.0.0, 5.2.0

diff --git a/MAINTAINERS b/MAINTAINERS
@@ -1092,7 +1092,7 @@ F:	Documentation/ABI/testing/sysfs-amd-pmf
 F:	drivers/platform/x86/amd/pmf/
 
 AMD POWERPLAY AND SWSMU
-M:	Evan Quan <evan.quan@amd.com>
+M:	Kenneth Feng <kenneth.feng@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
 T:	git https://gitlab.freedesktop.org/agd5f/linux.git
@@ -18656,7 +18656,7 @@ F:	drivers/net/wireless/quantenna
 RADEON and AMDGPU DRM DRIVERS
 M:	Alex Deucher <alexander.deucher@amd.com>
 M:	Christian König <christian.koenig@amd.com>
-M:	Pan, Xinhui <Xinhui.Pan@amd.com>
+M:	Xinhui Pan <Xinhui.Pan@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
 B:	https://gitlab.freedesktop.org/drm/amd/-/issues

diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
@@ -316,8 +316,6 @@ static int aldebaran_mode2_restore_ip(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.late_initialized = true;
 	}
 
-	amdgpu_ras_set_error_query_ready(adev, true);
-
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE);
 	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_GATE);
 

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -119,7 +119,7 @@ static struct aca_regs_dump {
 static void aca_smu_bank_dump(struct amdgpu_device *adev, int idx, int total, struct aca_bank *bank,
 			      struct ras_query_context *qctx)
 {
-	u64 event_id = qctx ? qctx->event_id : 0ULL;
+	u64 event_id = qctx ? qctx->evid.event_id : RAS_EVENT_INVALID_ID;
 	int i;
 
 	RAS_EVENT_LOG(adev, event_id, HW_ERR "Accelerator Check Architecture events logged\n");

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1093,6 +1093,21 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	unsigned int i;
 	int r;
 
+	/*
+	 * We can't use gang submit on with reserved VMIDs when the VM changes
+	 * can't be invalidated by more than one engine at the same time.
+	 */
+	if (p->gang_size > 1 && !p->adev->vm_manager.concurrent_flush) {
+		for (i = 0; i < p->gang_size; ++i) {
+			struct drm_sched_entity *entity = p->entities[i];
+			struct drm_gpu_scheduler *sched = entity->rq->sched;
+			struct amdgpu_ring *ring = to_amdgpu_ring(sched);
+
+			if (amdgpu_vmid_uses_reserved(vm, ring->vm_hub))
+				return -EINVAL;
+		}
+	}
+
 	r = amdgpu_vm_clear_freed(adev, vm, NULL);
 	if (r)
 		return r;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3142,7 +3142,8 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	amdgpu_ras_set_error_query_ready(adev, true);
+	if (!amdgpu_in_reset(adev))
+		amdgpu_ras_set_error_query_ready(adev, true);
 
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE);
 	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_GATE);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2161,8 +2161,6 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
 		break;
 	case IP_VERSION(12, 0, 0):
 	case IP_VERSION(12, 0, 1):
-		if (!amdgpu_exp_hw_support)
-			return -EINVAL;
 		amdgpu_device_ip_block_add(adev, &gfx_v12_0_ip_block);
 		break;
 	default:

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -297,6 +297,7 @@ struct amdgpu_gfx_funcs {
 	int (*switch_partition_mode)(struct amdgpu_device *adev,
 				     int num_xccs_per_xcp);
 	int (*ih_node_to_logical_xcc)(struct amdgpu_device *adev, int ih_node);
+	int (*get_xccs_per_xcp)(struct amdgpu_device *adev);
 };
 
 struct sq_work {

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -424,7 +424,7 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 	if (r || !idle)
 		goto error;
 
-	if (vm->reserved_vmid[vmhub] || (enforce_isolation && (vmhub == AMDGPU_GFXHUB(0)))) {
+	if (amdgpu_vmid_uses_reserved(vm, vmhub)) {
 		r = amdgpu_vmid_grab_reserved(vm, ring, job, &id, fence);
 		if (r || !id)
 			goto error;
@@ -474,6 +474,19 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 	return r;
 }
 
+/*
+ * amdgpu_vmid_uses_reserved - check if a VM will use a reserved VMID
+ * @vm: the VM to check
+ * @vmhub: the VMHUB which will be used
+ *
+ * Returns: True if the VM will use a reserved VMID.
+ */
+bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub)
+{
+	return vm->reserved_vmid[vmhub] ||
+		(enforce_isolation && (vmhub == AMDGPU_GFXHUB(0)));
+}
+
 int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
 			       unsigned vmhub)
 {

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
@@ -78,6 +78,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv,
 
 bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
 			       struct amdgpu_vmid *id);
+bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub);
 int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
 				unsigned vmhub);
 void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -41,7 +41,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	int r;
 
 	if (!drm_dev_enter(adev_to_drm(adev), &idx)) {
-		DRM_INFO("%s - device unplugged skipping recovery on scheduler:%s",
+		dev_info(adev->dev, "%s - device unplugged skipping recovery on scheduler:%s",
 			 __func__, s_job->sched->name);
 
 		/* Effectively the job is aborted as the device is gone */
@@ -53,19 +53,20 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 
 	if (amdgpu_gpu_recovery &&
 	    amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
-		DRM_ERROR("ring %s timeout, but soft recovered\n",
-			  s_job->sched->name);
+		dev_err(adev->dev, "ring %s timeout, but soft recovered\n",
+			s_job->sched->name);
 		goto exit;
 	}
 
-	DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n",
-		   job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
-		   ring->fence_drv.sync_seq);
+	dev_err(adev->dev, "ring %s timeout, signaled seq=%u, emitted seq=%u\n",
+		job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
+		ring->fence_drv.sync_seq);
 
 	ti = amdgpu_vm_get_task_info_pasid(ring->adev, job->pasid);
 	if (ti) {
-		DRM_ERROR("Process information: process %s pid %d thread %s pid %d\n",
-			  ti->process_name, ti->tgid, ti->task_name, ti->pid);
+		dev_err(adev->dev,
+			"Process information: process %s pid %d thread %s pid %d\n",
+			ti->process_name, ti->tgid, ti->task_name, ti->pid);
 		amdgpu_vm_put_task_info(ti);
 	}
 
@@ -82,7 +83,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 
 		r = amdgpu_device_gpu_recover(ring->adev, job, &reset_context);
 		if (r)
-			DRM_ERROR("GPU Recovery Failed: %d\n", r);
+			dev_err(adev->dev, "GPU Recovery Failed: %d\n", r);
 	} else {
 		drm_sched_suspend_timeout(&ring->sched);
 		if (amdgpu_sriov_vf(adev))
@@ -274,7 +275,7 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job,
 	while (!fence && job->vm && !job->vmid) {
 		r = amdgpu_vmid_grab(job->vm, ring, job, &fence);
 		if (r) {
-			DRM_ERROR("Error getting VM ID (%d)\n", r);
+			dev_err(ring->adev->dev, "Error getting VM ID (%d)\n", r);
 			goto error;
 		}
 	}

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
@@ -274,7 +274,7 @@ int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable)
 static void amdgpu_mca_smu_mca_bank_dump(struct amdgpu_device *adev, int idx, struct mca_bank_entry *entry,
 					 struct ras_query_context *qctx)
 {
-	u64 event_id = qctx->event_id;
+	u64 event_id = qctx ? qctx->evid.event_id : RAS_EVENT_INVALID_ID;
 
 	RAS_EVENT_LOG(adev, event_id, HW_ERR "Accelerator Check Architecture events logged\n");
 	RAS_EVENT_LOG(adev, event_id, HW_ERR "aca entry[%02d].STATUS=0x%016llx\n",
@@ -543,7 +543,7 @@ static int mca_dump_show(struct seq_file *m, enum amdgpu_mca_error_type type)
 
 	amdgpu_mca_bank_set_init(&mca_set);
 
-	qctx.event_id = 0ULL;
+	qctx.evid.event_id = RAS_EVENT_INVALID_ID;
 	ret = amdgpu_mca_smu_get_mca_set(adev, type, &mca_set, &qctx);
 	if (ret)
 		goto err_free_mca_set;