Merge tag 'amd-drm-fixes-6.9-2024-04-10' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.9-2024-04-10:

amdgpu:
- GPU reset fixes
- Fix some confusing logging
- UMSCH fix
- Aborted suspend fix
- DCN 3.5 fixes
- S4 fix
- MES logging fixes
- SMU 14 fixes
- SDMA 4.4.2 fix
- KASAN fix
- SMU 13.0.10 fix
- VCN partition fix
- GFX11 fixes
- DWB fixes
- Plane handling fix
- FAMS fix
- DCN 3.1.6 fix
- VSC SDP fixes
- OLED panel fix
- GFX 11.5 fix

amdkfd:
- GPU reset fixes

Signed-off-by: Dave Airlie <[email protected]>

From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

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

@@ -210,6 +210,7 @@ extern int amdgpu_async_gfx_ring;
 extern int amdgpu_mcbp;
 extern int amdgpu_discovery;
 extern int amdgpu_mes;
+extern int amdgpu_mes_log_enable;
 extern int amdgpu_mes_kiq;
 extern int amdgpu_noretry;
 extern int amdgpu_force_asic_type;

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

@@ -4135,18 +4135,22 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 					adev->ip_blocks[i].status.hw = true;
 				}
 			}
+		} else if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) &&
+				   !amdgpu_device_has_display_hardware(adev)) {
+					r = psp_gpu_reset(adev);
 		} else {
-			tmp = amdgpu_reset_method;
-			/* It should do a default reset when loading or reloading the driver,
-			 * regardless of the module parameter reset_method.
-			 */
-			amdgpu_reset_method = AMD_RESET_METHOD_NONE;
-			r = amdgpu_asic_reset(adev);
-			amdgpu_reset_method = tmp;
-			if (r) {
-				dev_err(adev->dev, "asic reset on init failed\n");
-				goto failed;
-			}
+				tmp = amdgpu_reset_method;
+				/* It should do a default reset when loading or reloading the driver,
+				 * regardless of the module parameter reset_method.
+				 */
+				amdgpu_reset_method = AMD_RESET_METHOD_NONE;
+				r = amdgpu_asic_reset(adev);
+				amdgpu_reset_method = tmp;
+		}
+
+		if (r) {
+		  dev_err(adev->dev, "asic reset on init failed\n");
+		  goto failed;
 		}
 	}
 

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

@@ -1896,6 +1896,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
 		break;
 	case IP_VERSION(14, 0, 0):
+	case IP_VERSION(14, 0, 1):
 		amdgpu_device_ip_block_add(adev, &smu_v14_0_ip_block);
 		break;
 	default:

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

@@ -195,6 +195,7 @@ int amdgpu_async_gfx_ring = 1;
 int amdgpu_mcbp = -1;
 int amdgpu_discovery = -1;
 int amdgpu_mes;
+int amdgpu_mes_log_enable = 0;
 int amdgpu_mes_kiq;
 int amdgpu_noretry = -1;
 int amdgpu_force_asic_type = -1;
@@ -667,6 +668,15 @@ MODULE_PARM_DESC(mes,
 	"Enable Micro Engine Scheduler (0 = disabled (default), 1 = enabled)");
 module_param_named(mes, amdgpu_mes, int, 0444);
 
+/**
+ * DOC: mes_log_enable (int)
+ * Enable Micro Engine Scheduler log. This is used to enable/disable MES internal log.
+ * (0 = disabled (default), 1 = enabled)
+ */
+MODULE_PARM_DESC(mes_log_enable,
+	"Enable Micro Engine Scheduler log (0 = disabled (default), 1 = enabled)");
+module_param_named(mes_log_enable, amdgpu_mes_log_enable, int, 0444);
+
 /**
  * DOC: mes_kiq (int)
  * Enable Micro Engine Scheduler KIQ. This is a new engine pipe for kiq.

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

@@ -304,12 +304,15 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 		dma_fence_set_error(finished, -ECANCELED);
 
 	if (finished->error < 0) {
-		DRM_INFO("Skip scheduling IBs!\n");
+		dev_dbg(adev->dev, "Skip scheduling IBs in ring(%s)",
+			ring->name);
 	} else {
 		r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job,
 				       &fence);
 		if (r)
-			DRM_ERROR("Error scheduling IBs (%d)\n", r);
+			dev_err(adev->dev,
+				"Error scheduling IBs (%d) in ring(%s)", r,
+				ring->name);
 	}
 
 	job->job_run_counter++;

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

@@ -102,7 +102,10 @@ static int amdgpu_mes_event_log_init(struct amdgpu_device *adev)
 {
 	int r;
 
-	r = amdgpu_bo_create_kernel(adev, PAGE_SIZE, PAGE_SIZE,
+	if (!amdgpu_mes_log_enable)
+		return 0;
+
+	r = amdgpu_bo_create_kernel(adev, AMDGPU_MES_LOG_BUFFER_SIZE, PAGE_SIZE,
 				    AMDGPU_GEM_DOMAIN_GTT,
 				    &adev->mes.event_log_gpu_obj,
 				    &adev->mes.event_log_gpu_addr,
@@ -1549,12 +1552,11 @@ static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused)
 	uint32_t *mem = (uint32_t *)(adev->mes.event_log_cpu_addr);
 
 	seq_hex_dump(m, "", DUMP_PREFIX_OFFSET, 32, 4,
-		     mem, PAGE_SIZE, false);
+		     mem, AMDGPU_MES_LOG_BUFFER_SIZE, false);
 
 	return 0;
 }
 
-
 DEFINE_SHOW_ATTRIBUTE(amdgpu_debugfs_mes_event_log);
 
 #endif
@@ -1565,7 +1567,7 @@ void amdgpu_debugfs_mes_event_log_init(struct amdgpu_device *adev)
 #if defined(CONFIG_DEBUG_FS)
 	struct drm_minor *minor = adev_to_drm(adev)->primary;
 	struct dentry *root = minor->debugfs_root;
-	if (adev->enable_mes)
+	if (adev->enable_mes && amdgpu_mes_log_enable)
 		debugfs_create_file("amdgpu_mes_event_log", 0444, root,
 				    adev, &amdgpu_debugfs_mes_event_log_fops);
 

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

@@ -52,6 +52,7 @@ enum amdgpu_mes_priority_level {
 
 #define AMDGPU_MES_PROC_CTX_SIZE 0x1000 /* one page area */
 #define AMDGPU_MES_GANG_CTX_SIZE 0x1000 /* one page area */
+#define AMDGPU_MES_LOG_BUFFER_SIZE 0x4000 /* Maximu log buffer size for MES */
 
 struct amdgpu_mes_funcs;
 

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

@@ -62,6 +62,11 @@ void aqua_vanjaram_doorbell_index_init(struct amdgpu_device *adev)
 	adev->doorbell_index.max_assignment = AMDGPU_DOORBELL_LAYOUT1_MAX_ASSIGNMENT << 1;
 }
 
+static bool aqua_vanjaram_xcp_vcn_shared(struct amdgpu_device *adev)
+{
+	return (adev->xcp_mgr->num_xcps > adev->vcn.num_vcn_inst);
+}
+
 static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev,
 			     uint32_t inst_idx, struct amdgpu_ring *ring)
 {
@@ -87,7 +92,7 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev,
 	case AMDGPU_RING_TYPE_VCN_ENC:
 	case AMDGPU_RING_TYPE_VCN_JPEG:
 		ip_blk = AMDGPU_XCP_VCN;
-		if (adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE)
+		if (aqua_vanjaram_xcp_vcn_shared(adev))
 			inst_mask = 1 << (inst_idx * 2);
 		break;
 	default:
@@ -140,10 +145,12 @@ static int aqua_vanjaram_xcp_sched_list_update(
 
 		aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id);
 
-		/* VCN is shared by two partitions under CPX MODE */
+		/* VCN may be shared by two partitions under CPX MODE in certain
+		 * configs.
+		 */
 		if ((ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC ||
-			ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) &&
-			adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE)
+		     ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) &&
+		    aqua_vanjaram_xcp_vcn_shared(adev))
 			aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id + 1);
 	}
 

drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c

@@ -1635,7 +1635,7 @@ static void gfx_v11_0_setup_rb(struct amdgpu_device *adev)
 			active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa));
 	}
 
-	active_rb_bitmap |= global_active_rb_bitmap;
+	active_rb_bitmap &= global_active_rb_bitmap;
 	adev->gfx.config.backend_enable_mask = active_rb_bitmap;
 	adev->gfx.config.num_rbs = hweight32(active_rb_bitmap);
 }
@@ -5465,6 +5465,7 @@ static void gfx_v11_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	/* Make sure that we can't skip the SET_Q_MODE packets when the VM
 	 * changed in any way.
 	 */
+	ring->set_q_mode_offs = 0;
 	ring->set_q_mode_ptr = NULL;
 }
 

drivers/gpu/drm/amd/amdgpu/mes_v11_0.c

@@ -411,8 +411,11 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
 	mes_set_hw_res_pkt.oversubscription_timer = 50;
-	mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
-	mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr;
+	if (amdgpu_mes_log_enable) {
+		mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
+		mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr =
+					mes->event_log_gpu_addr;
+	}
 
 	return mes_v11_0_submit_pkt_and_poll_completion(mes,
 			&mes_set_hw_res_pkt, sizeof(mes_set_hw_res_pkt),