Merge tag 'amd-drm-next-6.3-2023-01-13' of https://gitlab.freedesktop…

….org/agd5f/linux into drm-next

amd-drm-next-6.3-2023-01-13:

amdgpu:
- Fix possible segfault in failure case
- Rework FW requests to happen in early_init for all IPs so
  that we don't lose the sbios console if FW is missing
- PSR fixes
- Misc cleanups
- Unload fix
- SMU13 fixes

amdkfd:
- Fix for cleared VRAM BOs
- Fix cleanup if GPUVM creation fails
- Memory accounting fix
- Use resource_size rather than open codeing it
- GC11 mGPU fix

radeon:
- Fix memory leak on shutdown

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230113225911.7776-1-alexander.deucher@amd.com

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

@@ -97,7 +97,7 @@ struct amdgpu_amdkfd_fence {
 
 struct amdgpu_kfd_dev {
 	struct kfd_dev *dev;
-	uint64_t vram_used;
+	int64_t vram_used;
 	uint64_t vram_used_aligned;
 	bool init_complete;
 	struct work_struct reset_work;
@@ -271,9 +271,9 @@ int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_
 		((struct drm_file *)(drm_priv))->driver_priv)->vm)
 
 int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev,
-				     struct file *filp, u32 pasid);
+				     struct amdgpu_vm *avm, u32 pasid);
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev,
-					struct file *filp,
+					struct amdgpu_vm *avm,
 					void **process_info,
 					struct dma_fence **ef);
 void amdgpu_amdkfd_gpuvm_release_process_vm(struct amdgpu_device *adev,

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

@@ -1431,18 +1431,11 @@ static void amdgpu_amdkfd_gpuvm_unpin_bo(struct amdgpu_bo *bo)
 }
 
 int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev,
-				     struct file *filp, u32 pasid)
+				     struct amdgpu_vm *avm, u32 pasid)
 
 {
-	struct amdgpu_fpriv *drv_priv;
-	struct amdgpu_vm *avm;
 	int ret;
 
-	ret = amdgpu_file_to_fpriv(filp, &drv_priv);
-	if (ret)
-		return ret;
-	avm = &drv_priv->vm;
-
 	/* Free the original amdgpu allocated pasid,
 	 * will be replaced with kfd allocated pasid.
 	 */
@@ -1459,19 +1452,12 @@ int amdgpu_amdkfd_gpuvm_set_vm_pasid(struct amdgpu_device *adev,
 }
 
 int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct amdgpu_device *adev,
-					   struct file *filp,
+					   struct amdgpu_vm *avm,
 					   void **process_info,
 					   struct dma_fence **ef)
 {
-	struct amdgpu_fpriv *drv_priv;
-	struct amdgpu_vm *avm;
 	int ret;
 
-	ret = amdgpu_file_to_fpriv(filp, &drv_priv);
-	if (ret)
-		return ret;
-	avm = &drv_priv->vm;
-
 	/* Already a compute VM? */
 	if (avm->process_info)
 		return -EINVAL;
@@ -1613,6 +1599,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	struct amdgpu_bo *bo;
 	struct drm_gem_object *gobj = NULL;
 	u32 domain, alloc_domain;
+	uint64_t aligned_size;
 	u64 alloc_flags;
 	int ret;
 
@@ -1668,22 +1655,23 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	 * the memory.
 	 */
 	if ((*mem)->aql_queue)
-		size = size >> 1;
+		size >>= 1;
+	aligned_size = PAGE_ALIGN(size);
 
 	(*mem)->alloc_flags = flags;
 
 	amdgpu_sync_create(&(*mem)->sync);
 
-	ret = amdgpu_amdkfd_reserve_mem_limit(adev, size, flags);
+	ret = amdgpu_amdkfd_reserve_mem_limit(adev, aligned_size, flags);
 	if (ret) {
 		pr_debug("Insufficient memory\n");
 		goto err_reserve_limit;
 	}
 
 	pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s\n",
-			va, size, domain_string(alloc_domain));
+			va, (*mem)->aql_queue ? size << 1 : size, domain_string(alloc_domain));
 
-	ret = amdgpu_gem_object_create(adev, size, 1, alloc_domain, alloc_flags,
+	ret = amdgpu_gem_object_create(adev, aligned_size, 1, alloc_domain, alloc_flags,
 				       bo_type, NULL, &gobj);
 	if (ret) {
 		pr_debug("Failed to create BO on domain %s. ret %d\n",
@@ -1740,7 +1728,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	/* Don't unreserve system mem limit twice */
 	goto err_reserve_limit;
 err_bo_create:
-	amdgpu_amdkfd_unreserve_mem_limit(adev, size, flags);
+	amdgpu_amdkfd_unreserve_mem_limit(adev, aligned_size, flags);
 err_reserve_limit:
 	mutex_destroy(&(*mem)->lock);
 	if (gobj)
@@ -2100,7 +2088,7 @@ int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_b
 	}
 
 	amdgpu_amdkfd_remove_eviction_fence(
-		bo, bo->kfd_bo->process_info->eviction_fence);
+		bo, bo->vm_bo->vm->process_info->eviction_fence);
 
 	amdgpu_bo_unreserve(bo);
 

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

@@ -411,17 +411,10 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 				return -EINVAL;
 			}
 
-			err = request_firmware(&adev->pm.fw, fw_name, adev->dev);
-			if (err) {
-				DRM_ERROR("Failed to request firmware\n");
-				return err;
-			}
-
-			err = amdgpu_ucode_validate(adev->pm.fw);
+			err = amdgpu_ucode_request(adev, &adev->pm.fw, fw_name);
 			if (err) {
 				DRM_ERROR("Failed to load firmware \"%s\"", fw_name);
-				release_firmware(adev->pm.fw);
-				adev->pm.fw = NULL;
+				amdgpu_ucode_release(&adev->pm.fw);
 				return err;
 			}
 

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

@@ -36,6 +36,7 @@
 #include <generated/utsrelease.h>
 #include <linux/pci-p2pdma.h>
 
+#include <drm/drm_aperture.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_probe_helper.h>
@@ -90,6 +91,8 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
 #define AMDGPU_MAX_RETRY_LIMIT		2
 #define AMDGPU_RETRY_SRIOV_RESET(r) ((r) == -EBUSY || (r) == -ETIMEDOUT || (r) == -EINVAL)
 
+static const struct drm_driver amdgpu_kms_driver;
+
 const char *amdgpu_asic_name[] = {
 	"TAHITI",
 	"PITCAIRN",
@@ -1982,17 +1985,10 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_gpu_info.bin", chip_name);
-	err = request_firmware(&adev->firmware.gpu_info_fw, fw_name, adev->dev);
-	if (err) {
-		dev_err(adev->dev,
-			"Failed to load gpu_info firmware \"%s\"\n",
-			fw_name);
-		goto out;
-	}
-	err = amdgpu_ucode_validate(adev->firmware.gpu_info_fw);
+	err = amdgpu_ucode_request(adev, &adev->firmware.gpu_info_fw, fw_name);
 	if (err) {
 		dev_err(adev->dev,
-			"Failed to validate gpu_info firmware \"%s\"\n",
+			"Failed to get gpu_info firmware \"%s\"\n",
 			fw_name);
 		goto out;
 	}
@@ -3688,6 +3684,11 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	/* Get rid of things like offb */
+	r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
+	if (r)
+		return r;
+
 	/* Enable TMZ based on IP_VERSION */
 	amdgpu_gmc_tmz_set(adev);
 
@@ -4023,8 +4024,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 
 	amdgpu_fence_driver_sw_fini(adev);
 	amdgpu_device_ip_fini(adev);
-	release_firmware(adev->firmware.gpu_info_fw);
-	adev->firmware.gpu_info_fw = NULL;
+	amdgpu_ucode_release(&adev->firmware.gpu_info_fw);
 	adev->accel_working = false;
 	dma_fence_put(rcu_dereference_protected(adev->gang_submit, true));
 

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

@@ -23,7 +23,6 @@
  */
 
 #include <drm/amdgpu_drm.h>
-#include <drm/drm_aperture.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_fbdev_generic.h>
 #include <drm/drm_gem.h>
@@ -2124,11 +2123,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	}
 #endif
 
-	/* Get rid of things like offb */
-	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver);
-	if (ret)
-		return ret;
-
 	adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev);
 	if (IS_ERR(adev))
 		return PTR_ERR(adev);

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

@@ -62,10 +62,10 @@ static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf)
 			goto unlock;
 		}
 
-		 ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
-						TTM_BO_VM_NUM_PREFAULT);
+		ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
+					       TTM_BO_VM_NUM_PREFAULT);
 
-		 drm_dev_exit(idx);
+		drm_dev_exit(idx);
 	} else {
 		ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
 	}

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

@@ -21,6 +21,8 @@
  *
  */
 
+#include <linux/firmware.h>
+
 #include "amdgpu_mes.h"
 #include "amdgpu.h"
 #include "soc15_common.h"
@@ -1423,3 +1425,60 @@ int amdgpu_mes_self_test(struct amdgpu_device *adev)
 	kfree(vm);
 	return 0;
 }
+
+int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe)
+{
+	const struct mes_firmware_header_v1_0 *mes_hdr;
+	struct amdgpu_firmware_info *info;
+	char ucode_prefix[30];
+	char fw_name[40];
+	int r;
+
+	amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix));
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes%s.bin",
+		ucode_prefix,
+		pipe == AMDGPU_MES_SCHED_PIPE ? "" : "1");
+	r = amdgpu_ucode_request(adev, &adev->mes.fw[pipe], fw_name);
+	if (r)
+		goto out;
+
+	mes_hdr = (const struct mes_firmware_header_v1_0 *)
+		adev->mes.fw[pipe]->data;
+	adev->mes.uc_start_addr[pipe] =
+		le32_to_cpu(mes_hdr->mes_uc_start_addr_lo) |
+		((uint64_t)(le32_to_cpu(mes_hdr->mes_uc_start_addr_hi)) << 32);
+	adev->mes.data_start_addr[pipe] =
+		le32_to_cpu(mes_hdr->mes_data_start_addr_lo) |
+		((uint64_t)(le32_to_cpu(mes_hdr->mes_data_start_addr_hi)) << 32);
+
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		int ucode, ucode_data;
+
+		if (pipe == AMDGPU_MES_SCHED_PIPE) {
+			ucode = AMDGPU_UCODE_ID_CP_MES;
+			ucode_data = AMDGPU_UCODE_ID_CP_MES_DATA;
+		} else {
+			ucode = AMDGPU_UCODE_ID_CP_MES1;
+			ucode_data = AMDGPU_UCODE_ID_CP_MES1_DATA;
+		}
+
+		info = &adev->firmware.ucode[ucode];
+		info->ucode_id = ucode;
+		info->fw = adev->mes.fw[pipe];
+		adev->firmware.fw_size +=
+			ALIGN(le32_to_cpu(mes_hdr->mes_ucode_size_bytes),
+			      PAGE_SIZE);
+
+		info = &adev->firmware.ucode[ucode_data];
+		info->ucode_id = ucode_data;
+		info->fw = adev->mes.fw[pipe];
+		adev->firmware.fw_size +=
+			ALIGN(le32_to_cpu(mes_hdr->mes_ucode_data_size_bytes),
+			      PAGE_SIZE);
+	}
+
+	return 0;
+out:
+	amdgpu_ucode_release(&adev->mes.fw[pipe]);
+	return r;
+}

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

@@ -306,6 +306,7 @@ struct amdgpu_mes_funcs {
 
 int amdgpu_mes_ctx_get_offs(struct amdgpu_ring *ring, unsigned int id_offs);
 
+int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe);
 int amdgpu_mes_init(struct amdgpu_device *adev);
 void amdgpu_mes_fini(struct amdgpu_device *adev);
 

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

@@ -470,8 +470,9 @@ static bool amdgpu_bo_validate_size(struct amdgpu_device *adev,
 	return true;
 
 fail:
-	DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
-		  man->size);
+	if (man)
+		DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
+			  man->size);
 	return false;
 }