sync with OpenBSD -current

sys/dev/pci/drm/amd/amdgpu/aldebaran.c

@@ -333,6 +333,7 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 {
 	struct list_head *reset_device_list = reset_context->reset_device_list;
 	struct amdgpu_device *tmp_adev = NULL;
+	struct amdgpu_ras *con;
 	int r;
 
 	if (reset_device_list == NULL)
@@ -358,7 +359,30 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 		 */
 		amdgpu_register_gpu_instance(tmp_adev);
 
-		/* Resume RAS */
+		/* Resume RAS, ecc_irq */
+		con = amdgpu_ras_get_context(tmp_adev);
+		if (!amdgpu_sriov_vf(tmp_adev) && con) {
+			if (tmp_adev->sdma.ras &&
+				tmp_adev->sdma.ras->ras_block.ras_late_init) {
+				r = tmp_adev->sdma.ras->ras_block.ras_late_init(tmp_adev,
+						&tmp_adev->sdma.ras->ras_block.ras_comm);
+				if (r) {
+					dev_err(tmp_adev->dev, "SDMA failed to execute ras_late_init! ret:%d\n", r);
+					goto end;
+				}
+			}
+
+			if (tmp_adev->gfx.ras &&
+				tmp_adev->gfx.ras->ras_block.ras_late_init) {
+				r = tmp_adev->gfx.ras->ras_block.ras_late_init(tmp_adev,
+						&tmp_adev->gfx.ras->ras_block.ras_comm);
+				if (r) {
+					dev_err(tmp_adev->dev, "GFX failed to execute ras_late_init! ret:%d\n", r);
+					goto end;
+				}
+			}
+		}
+
 		amdgpu_ras_resume(tmp_adev);
 
 		/* Update PSP FW topology after reset */

sys/dev/pci/drm/amd/amdgpu/amdgpu_amdkfd_fence.c

@@ -90,7 +90,7 @@ struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f)
 		return NULL;
 
 	fence = container_of(f, struct amdgpu_amdkfd_fence, base);
-	if (fence && f->ops == &amdkfd_fence_ops)
+	if (f->ops == &amdkfd_fence_ops)
 		return fence;
 
 	return NULL;

sys/dev/pci/drm/amd/amdgpu/amdgpu_device.c

@@ -1224,6 +1224,7 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev)
 				return true;
 
 			fw_ver = *((uint32_t *)adev->pm.fw->data + 69);
+			release_firmware(adev->pm.fw);
 			if (fw_ver < 0x00160e00)
 				return true;
 		}

sys/dev/pci/drm/amd/amdgpu/amdgpu_gmc.c

@@ -885,21 +885,28 @@ int amdgpu_gmc_vram_checking(struct amdgpu_device *adev)
 	 * seconds, so here, we just pick up three parts for emulation.
 	 */
 	ret = memcmp(vram_ptr, cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
 	ret = memcmp(vram_ptr + (size / 2), cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
 	ret = memcmp(vram_ptr + size - 10, cptr, 10);
-	if (ret)
-		return ret;
+	if (ret) {
+		ret = -EIO;
+		goto release_buffer;
+	}
 
+release_buffer:
 	amdgpu_bo_free_kernel(&vram_bo, &vram_gpu,
 			&vram_ptr);
 
-	return 0;
+	return ret;
 }
 
 static ssize_t current_memory_partition_show(

sys/dev/pci/drm/amd/amdgpu/amdgpu_mes.c

@@ -885,6 +885,11 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev,
 	op_input.op = MES_MISC_OP_SET_SHADER_DEBUGGER;
 	op_input.set_shader_debugger.process_context_addr = process_context_addr;
 	op_input.set_shader_debugger.flags.u32all = flags;
+
+	/* use amdgpu mes_flush_shader_debugger instead */
+	if (op_input.set_shader_debugger.flags.process_ctx_flush)
+		return -EINVAL;
+
 	op_input.set_shader_debugger.spi_gdbg_per_vmid_cntl = spi_gdbg_per_vmid_cntl;
 	memcpy(op_input.set_shader_debugger.tcp_watch_cntl, tcp_watch_cntl,
 			sizeof(op_input.set_shader_debugger.tcp_watch_cntl));
@@ -904,6 +909,32 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev,
 	return r;
 }
 
+int amdgpu_mes_flush_shader_debugger(struct amdgpu_device *adev,
+				     uint64_t process_context_addr)
+{
+	struct mes_misc_op_input op_input = {0};
+	int r;
+
+	if (!adev->mes.funcs->misc_op) {
+		DRM_ERROR("mes flush shader debugger is not supported!\n");
+		return -EINVAL;
+	}
+
+	op_input.op = MES_MISC_OP_SET_SHADER_DEBUGGER;
+	op_input.set_shader_debugger.process_context_addr = process_context_addr;
+	op_input.set_shader_debugger.flags.process_ctx_flush = true;
+
+	amdgpu_mes_lock(&adev->mes);
+
+	r = adev->mes.funcs->misc_op(&adev->mes, &op_input);
+	if (r)
+		DRM_ERROR("failed to set_shader_debugger\n");
+
+	amdgpu_mes_unlock(&adev->mes);
+
+	return r;
+}
+
 static void
 amdgpu_mes_ring_to_queue_props(struct amdgpu_device *adev,
 			       struct amdgpu_ring *ring,

sys/dev/pci/drm/amd/amdgpu/amdgpu_mes.h

@@ -293,9 +293,10 @@ struct mes_misc_op_input {
 			uint64_t process_context_addr;
 			union {
 				struct {
-					uint64_t single_memop : 1;
-					uint64_t single_alu_op : 1;
-					uint64_t reserved: 30;
+					uint32_t single_memop : 1;
+					uint32_t single_alu_op : 1;
+					uint32_t reserved: 29;
+					uint32_t process_ctx_flush: 1;
 				};
 				uint32_t u32all;
 			} flags;
@@ -371,7 +372,8 @@ int amdgpu_mes_set_shader_debugger(struct amdgpu_device *adev,
 				const uint32_t *tcp_watch_cntl,
 				uint32_t flags,
 				bool trap_en);
-
+int amdgpu_mes_flush_shader_debugger(struct amdgpu_device *adev,
+				uint64_t process_context_addr);
 int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id,
 			int queue_type, int idx,
 			struct amdgpu_mes_ctx_data *ctx_data,

sys/dev/pci/drm/amd/amdgpu/amdgpu_object.c

@@ -1270,19 +1270,15 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
  * amdgpu_bo_move_notify - notification about a memory move
  * @bo: pointer to a buffer object
  * @evict: if this move is evicting the buffer from the graphics address space
- * @new_mem: new information of the bufer object
  *
  * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs
  * bookkeeping.
  * TTM driver callback which is called when ttm moves a buffer.
  */
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
-			   bool evict,
-			   struct ttm_resource *new_mem)
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct amdgpu_bo *abo;
-	struct ttm_resource *old_mem = bo->resource;
 
 	if (!amdgpu_bo_is_amdgpu_bo(bo))
 		return;
@@ -1301,13 +1297,6 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 	/* remember the eviction */
 	if (evict)
 		atomic64_inc(&adev->num_evictions);
-
-	/* update statistics */
-	if (!new_mem)
-		return;
-
-	/* move_notify is called before move happens */
-	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 }
 
 void amdgpu_bo_get_memory(struct amdgpu_bo *bo,

sys/dev/pci/drm/amd/amdgpu/amdgpu_object.h

@@ -345,9 +345,7 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 			   size_t buffer_size, uint32_t *metadata_size,
 			   uint64_t *flags);
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
-			   bool evict,
-			   struct ttm_resource *new_mem);
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict);
 void amdgpu_bo_release_notify(struct ttm_buffer_object *bo);
 vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
 void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,

sys/dev/pci/drm/amd/amdgpu/amdgpu_sync.c

@@ -195,7 +195,8 @@ static bool amdgpu_sync_test_fence(struct amdgpu_device *adev,
 
 	/* Never sync to VM updates either. */
 	if (fence_owner == AMDGPU_FENCE_OWNER_VM &&
-	    owner != AMDGPU_FENCE_OWNER_UNDEFINED)
+	    owner != AMDGPU_FENCE_OWNER_UNDEFINED &&
+	    owner != AMDGPU_FENCE_OWNER_KFD)
 		return false;
 
 	/* Ignore fences depending on the sync mode */

sys/dev/pci/drm/amd/amdgpu/amdgpu_ttm.c

@@ -545,10 +545,11 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 	}
 
+	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 out:
 	/* update statistics */
 	atomic64_add(bo->base.size, &adev->num_bytes_moved);
-	amdgpu_bo_move_notify(bo, evict, new_mem);
+	amdgpu_bo_move_notify(bo, evict);
 	return 0;
 }
 
@@ -1592,7 +1593,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo,
 static void
 amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo)
 {
-	amdgpu_bo_move_notify(bo, false, NULL);
+	amdgpu_bo_move_notify(bo, false);
 }
 
 static struct ttm_device_funcs amdgpu_bo_driver = {

sys/dev/pci/drm/amd/amdgpu/amdgpu_ucode.c

@@ -1330,9 +1330,13 @@ int amdgpu_ucode_request(struct amdgpu_device *adev, const struct firmware **fw,
 
 	if (err)
 		return -ENODEV;
+
 	err = amdgpu_ucode_validate(*fw);
-	if (err)
+	if (err) {
 		dev_dbg(adev->dev, "\"%s\" failed to validate\n", fw_name);
+		release_firmware(*fw);
+		*fw = NULL;
+	}
 
 	return err;
 }

sys/dev/pci/drm/amd/amdgpu/gfxhub_v1_0.c

@@ -102,7 +102,9 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
-		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+		if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+				       AMD_APU_IS_RENOIR |
+				       AMD_APU_IS_GREEN_SARDINE))
 		       /*
 			* Raven2 has a HW issue that it is unable to use the
 			* vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR.

sys/dev/pci/drm/amd/amdgpu/gfxhub_v1_2.c

@@ -139,7 +139,9 @@ gfxhub_v1_2_xcc_init_system_aperture_regs(struct amdgpu_device *adev,
 			WREG32_SOC15_RLC(GC, GET_INST(GC, i), regMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 				min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
-			if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+			if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+					       AMD_APU_IS_RENOIR |
+					       AMD_APU_IS_GREEN_SARDINE))
 			       /*
 				* Raven2 has a HW issue that it is unable to use the
 				* vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR.

sys/dev/pci/drm/amd/amdgpu/gmc_v10_0.c

@@ -1141,6 +1141,10 @@ static int gmc_v10_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 
+	if (adev->gmc.ecc_irq.funcs &&
+		amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+		amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
 	return 0;
 }
 

sys/dev/pci/drm/amd/amdgpu/gmc_v11_0.c

@@ -974,6 +974,11 @@ static int gmc_v11_0_hw_fini(void *handle)
 	}
 
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
+
+	if (adev->gmc.ecc_irq.funcs &&
+		amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+		amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
 	gmc_v11_0_gart_disable(adev);
 
 	return 0;

sys/dev/pci/drm/amd/amdgpu/gmc_v6_0.c

@@ -914,8 +914,8 @@ static int gmc_v6_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v6_0_hw_fini(void *handle)

sys/dev/pci/drm/amd/amdgpu/gmc_v7_0.c

@@ -1103,8 +1103,8 @@ static int gmc_v7_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v7_0_hw_fini(void *handle)

sys/dev/pci/drm/amd/amdgpu/gmc_v8_0.c

@@ -1224,8 +1224,8 @@ static int gmc_v8_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 static int gmc_v8_0_hw_fini(void *handle)

sys/dev/pci/drm/amd/amdgpu/gmc_v9_0.c

@@ -2380,8 +2380,8 @@ static int gmc_v9_0_hw_init(void *handle)
 
 	if (amdgpu_emu_mode == 1)
 		return amdgpu_gmc_vram_checking(adev);
-	else
-		return r;
+
+	return 0;
 }
 
 /**
@@ -2420,6 +2420,10 @@ static int gmc_v9_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 
+	if (adev->gmc.ecc_irq.funcs &&
+		amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC))
+		amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
+
 	return 0;
 }
 

sys/dev/pci/drm/amd/amdgpu/mmhub_v1_0.c

@@ -96,7 +96,9 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 		     min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
 
-	if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+	if (adev->apu_flags & (AMD_APU_IS_RAVEN2 |
+			       AMD_APU_IS_RENOIR |
+			       AMD_APU_IS_GREEN_SARDINE))
 		/*
 		 * Raven2 has a HW issue that it is unable to use the vram which
 		 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the