Merge tag 'amd-drm-fixes-6.10-2024-05-30' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.10-2024-05-30:

amdgpu:
- RAS fix
- Fix colorspace property for MST connectors
- Fix for PCIe DPM
- Silence UBSAN warning
- GPUVM robustness fix
- Partition fix
- Drop deprecated I2C_CLASS_SPD

amdkfd:
- Revert unused changes for certain 11.0.3 devices
- Simplify APU VRAM handling

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240530202316.2246826-1-alexander.deucher@amd.com

12 files changed, 36 insertions, 35 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 8975cf41a91a..48ad0c04aa72 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -196,7 +196,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 			return -EINVAL;
 
 		vram_size = KFD_XCP_MEMORY_SIZE(adev, xcp_id);
-		if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+		if (adev->flags & AMD_IS_APU) {
 			system_mem_needed = size;
 			ttm_mem_needed = size;
 		}
@@ -233,7 +233,7 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	if (adev && xcp_id >= 0) {
 		adev->kfd.vram_used[xcp_id] += vram_needed;
 		adev->kfd.vram_used_aligned[xcp_id] +=
-				(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) ?
+				(adev->flags & AMD_IS_APU) ?
 				vram_needed :
 				ALIGN(vram_needed, VRAM_AVAILABLITY_ALIGN);
 	}
@@ -261,7 +261,7 @@ void amdgpu_amdkfd_unreserve_mem_limit(struct amdgpu_device *adev,
 
 		if (adev) {
 			adev->kfd.vram_used[xcp_id] -= size;
-			if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+			if (adev->flags & AMD_IS_APU) {
 				adev->kfd.vram_used_aligned[xcp_id] -= size;
 				kfd_mem_limit.system_mem_used -= size;
 				kfd_mem_limit.ttm_mem_used -= size;
@@ -890,7 +890,7 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 	 * if peer device has large BAR. In contrast, access over xGMI is
 	 * allowed for both small and large BAR configurations of peer device
 	 */
-	if ((adev != bo_adev && !(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU)) &&
+	if ((adev != bo_adev && !(adev->flags & AMD_IS_APU)) &&
 	    ((mem->domain == AMDGPU_GEM_DOMAIN_VRAM) ||
 	     (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL) ||
 	     (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP))) {
@@ -1658,7 +1658,7 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev,
 		- atomic64_read(&adev->vram_pin_size)
 		- reserved_for_pt;
 
-	if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+	if (adev->flags & AMD_IS_APU) {
 		system_mem_available = no_system_mem_limit ?
 					kfd_mem_limit.max_system_mem_limit :
 					kfd_mem_limit.max_system_mem_limit -
@@ -1706,7 +1706,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) {
 		domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM;
 
-		if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) {
+		if (adev->flags & AMD_IS_APU) {
 			domain = AMDGPU_GEM_DOMAIN_GTT;
 			alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
 			alloc_flags = 0;
@@ -1953,7 +1953,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	if (size) {
 		if (!is_imported &&
 		   (mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_VRAM ||
-		   ((adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) &&
+		   ((adev->flags & AMD_IS_APU) &&
 		    mem->bo->preferred_domains == AMDGPU_GEM_DOMAIN_GTT)))
 			*size = bo_size;
 		else
@@ -2376,7 +2376,7 @@ static int import_obj_create(struct amdgpu_device *adev,
 	(*mem)->bo = bo;
 	(*mem)->va = va;
 	(*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) &&
-			 !(adev->gmc.is_app_apu || adev->flags & AMD_IS_APU) ?
+			 !(adev->flags & AMD_IS_APU) ?
 			 AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT;
 
 	(*mem)->mapped_to_gpu_memory = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 861ccff78af9..932dc93b2e63 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5944,13 +5944,18 @@ static void amdgpu_device_partner_bandwidth(struct amdgpu_device *adev,
 	*speed = PCI_SPEED_UNKNOWN;
 	*width = PCIE_LNK_WIDTH_UNKNOWN;
 
-	while ((parent = pci_upstream_bridge(parent))) {
-		/* skip upstream/downstream switches internal to dGPU*/
-		if (parent->vendor == PCI_VENDOR_ID_ATI)
-			continue;
-		*speed = pcie_get_speed_cap(parent);
-		*width = pcie_get_width_cap(parent);
-		break;
+	if (amdgpu_device_pcie_dynamic_switching_supported(adev)) {
+		while ((parent = pci_upstream_bridge(parent))) {
+			/* skip upstream/downstream switches internal to dGPU*/
+			if (parent->vendor == PCI_VENDOR_ID_ATI)
+				continue;
+			*speed = pcie_get_speed_cap(parent);
+			*width = pcie_get_width_cap(parent);
+			break;
+		}
+	} else {
+		/* use the current speeds rather than max if switching is not supported */
+		pcie_bandwidth_available(adev->pdev, NULL, speed, width);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index c8980d5f6540..7021c4a66fb5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -46,7 +46,7 @@ struct amdgpu_iv_entry;
 #define AMDGPU_RAS_GPU_ERR_HBM_BIST_TEST(x)		AMDGPU_GET_REG_FIELD(x, 7, 7)
 #define AMDGPU_RAS_GPU_ERR_SOCKET_ID(x)			AMDGPU_GET_REG_FIELD(x, 10, 8)
 #define AMDGPU_RAS_GPU_ERR_AID_ID(x)			AMDGPU_GET_REG_FIELD(x, 12, 11)
-#define AMDGPU_RAS_GPU_ERR_HBM_ID(x)			AMDGPU_GET_REG_FIELD(x, 13, 13)
+#define AMDGPU_RAS_GPU_ERR_HBM_ID(x)			AMDGPU_GET_REG_FIELD(x, 14, 13)
 #define AMDGPU_RAS_GPU_ERR_BOOT_STATUS(x)		AMDGPU_GET_REG_FIELD(x, 31, 31)
 
 #define AMDGPU_RAS_BOOT_STATUS_POLLING_LIMIT	1000
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index 7fdd306a48a0..f07647a9a9d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -706,11 +706,15 @@ int amdgpu_vm_pde_update(struct amdgpu_vm_update_params *params,
 			 struct amdgpu_vm_bo_base *entry)
 {
 	struct amdgpu_vm_bo_base *parent = amdgpu_vm_pt_parent(entry);
-	struct amdgpu_bo *bo = parent->bo, *pbo;
+	struct amdgpu_bo *bo, *pbo;
 	struct amdgpu_vm *vm = params->vm;
 	uint64_t pde, pt, flags;
 	unsigned int level;
 
+	if (WARN_ON(!parent))
+		return -EINVAL;
+
+	bo = parent->bo;
 	for (level = 0, pbo = bo->parent; pbo; ++level)
 		pbo = pbo->parent;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index 414ea3f560a7..d4e2aed2efa3 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -422,7 +422,7 @@ __aqua_vanjaram_get_auto_mode(struct amdgpu_xcp_mgr *xcp_mgr)
 
 	if (adev->gmc.num_mem_partitions == num_xcc / 2)
 		return (adev->flags & AMD_IS_APU) ? AMDGPU_TPX_PARTITION_MODE :
-						    AMDGPU_QPX_PARTITION_MODE;
+						    AMDGPU_CPX_PARTITION_MODE;
 
 	if (adev->gmc.num_mem_partitions == 2 && !(adev->flags & AMD_IS_APU))
 		return AMDGPU_DPX_PARTITION_MODE;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 9596bca57212..afc57df421cd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -408,15 +408,8 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf)
 			f2g = &gfx_v11_kfd2kgd;
 			break;
 		case IP_VERSION(11, 0, 3):
-			if ((adev->pdev->device == 0x7460 &&
-			     adev->pdev->revision == 0x00) ||
-			    (adev->pdev->device == 0x7461 &&
-			     adev->pdev->revision == 0x00))
-				/* Note: Compiler version is 11.0.5 while HW version is 11.0.3 */
-				gfx_target_version = 110005;
-			else
-				/* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */
-				gfx_target_version = 110001;
+			/* Note: Compiler version is 11.0.1 while HW version is 11.0.3 */
+			gfx_target_version = 110001;
 			f2g = &gfx_v11_kfd2kgd;
 			break;
 		case IP_VERSION(11, 5, 0):
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 4816fcb9803a..8ee3d07ffbdf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -1023,7 +1023,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 0, 1))
 		return -EINVAL;
 
-	if (adev->gmc.is_app_apu || adev->flags & AMD_IS_APU)
+	if (adev->flags & AMD_IS_APU)
 		return 0;
 
 	pgmap = &kfddev->pgmap;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 069b81eeea03..31e500859ab0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -2619,8 +2619,7 @@ svm_range_best_restore_location(struct svm_range *prange,
 		return -1;
 	}
 
-	if (node->adev->gmc.is_app_apu ||
-	    node->adev->flags & AMD_IS_APU)
+	if (node->adev->flags & AMD_IS_APU)
 		return 0;
 
 	if (prange->preferred_loc == gpuid ||
@@ -3338,8 +3337,7 @@ svm_range_best_prefetch_location(struct svm_range *prange)
 		goto out;
 	}
 
-	if (bo_node->adev->gmc.is_app_apu ||
-	    bo_node->adev->flags & AMD_IS_APU) {
+	if (bo_node->adev->flags & AMD_IS_APU) {
 		best_loc = 0;
 		goto out;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 9c37bd0567ef..70c1776611c4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -201,7 +201,6 @@ void svm_range_list_lock_and_flush_work(struct svm_range_list *svms, struct mm_s
  * is initialized to not 0 when page migration register device memory.
  */
 #define KFD_IS_SVM_API_SUPPORTED(adev) ((adev)->kfd.pgmap.type != 0 ||\
-					(adev)->gmc.is_app_apu ||\
 					((adev)->flags & AMD_IS_APU))
 
 void svm_range_bo_unref_async(struct svm_range_bo *svm_bo);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 35733d5c5193..a5e1a93ddaea 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -613,6 +613,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		&connector->base,
 		dev->mode_config.tile_property,
 		0);
+	connector->colorspace_property = master->base.colorspace_property;
+	if (connector->colorspace_property)
+		drm_connector_attach_colorspace_property(connector);
 
 	drm_connector_set_path_property(connector, pathprop);
 
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 1acb2d2c5597..571691837200 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -3583,7 +3583,7 @@ struct atom_gpio_voltage_object_v4
    uint8_t  phase_delay_us;                      // phase delay in unit of micro second
    uint8_t  reserved;   
    uint32_t gpio_mask_val;                         // GPIO Mask value
-   struct atom_voltage_gpio_map_lut voltage_gpio_lut[1];
+   struct atom_voltage_gpio_map_lut voltage_gpio_lut[] __counted_by(gpio_entry_num);
 };
 
 struct  atom_svid2_voltage_object_v4
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 706265220292..90703f4542ab 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -1562,7 +1562,6 @@ static int smu_v14_0_2_i2c_control_init(struct smu_context *smu)
 		smu_i2c->port = i;
 		mutex_init(&smu_i2c->mutex);
 		control->owner = THIS_MODULE;
-		control->class = I2C_CLASS_SPD;
 		control->dev.parent = &adev->pdev->dev;
 		control->algo = &smu_v14_0_2_i2c_algo;
 		snprintf(control->name, sizeof(control->name), "AMDGPU SMU %d", i);