Merge tag 'amd-drm-next-6.4-2023-03-17' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.4-2023-03-17:

amdgpu:
- Misc code cleanups
- Documentation fixes
- Make kobj structures const
- Add thermal throttling adjustments for supported APUs
- UMC RAS fixes
- Display reset fixes
- DCN 3.2 fixes
- Freesync fixes
- DC code reorg
- Generalize dmabuf import to work with KFD
- DC DML fixes
- SRIOV fixes
- UVD code cleanups
- IH 4.4.2 updates
- HDP 4.4.2 updates
- SDMA 4.4.2 updates
- PSP 13.0.6 updates
- Add capped/uncapped workload handling for supported APUs
- DCN 3.1.4 updates
- Re-org DC Kconfig
- USB4 fixes
- Reorg DC plane and stream handling
- Register vga_switcheroo for apple-gmux
- SMU 13.0.6 updates
- Fix error checking in read_mm_registers functions for affected families
- VCN 4.0.4 fix
- Drop redundant pci_enable_pcie_error_reporting() call
- RDNA2 SMU OD suspend/resume fix
- Expose additional memory stats via fdinfo
- RAS fixes
- Misc display fixes
- DP MST fixes
- IOMMU regression fix for KFD

amdkfd:
- Make kobj structures const
- Support for exporting buffers via dmabuf
- Multi-VMA page migration fixes
- NBIO fixes
- Misc code cleanups
- Fix possible double free
- Fix possible UAF

radeon:
- iMac fix

UAPI:
- KFD dmabuf export support.  Required for importing KFD buffers into GEM contexts and for RDMA P2P support.
  Proposed user mode changes: https://github.com/fxkamd/ROCT-Thunk-Interface/commits/fxkamd/dmabuf

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

1 files changed, 60 insertions, 28 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index d6320c836251..c87515210c4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -711,6 +711,21 @@ kfd_mem_dmaunmap_attachment(struct kgd_mem *mem,
 	}
 }
 
+static int kfd_mem_export_dmabuf(struct kgd_mem *mem)
+{
+	if (!mem->dmabuf) {
+		struct dma_buf *ret = amdgpu_gem_prime_export(
+			&mem->bo->tbo.base,
+			mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE ?
+				DRM_RDWR : 0);
+		if (IS_ERR(ret))
+			return PTR_ERR(ret);
+		mem->dmabuf = ret;
+	}
+
+	return 0;
+}
+
 static int
 kfd_mem_attach_dmabuf(struct amdgpu_device *adev, struct kgd_mem *mem,
 		      struct amdgpu_bo **bo)
@@ -718,16 +733,9 @@ kfd_mem_attach_dmabuf(struct amdgpu_device *adev, struct kgd_mem *mem,
 	struct drm_gem_object *gobj;
 	int ret;
 
-	if (!mem->dmabuf) {
-		mem->dmabuf = amdgpu_gem_prime_export(&mem->bo->tbo.base,
-			mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE ?
-				DRM_RDWR : 0);
-		if (IS_ERR(mem->dmabuf)) {
-			ret = PTR_ERR(mem->dmabuf);
-			mem->dmabuf = NULL;
-			return ret;
-		}
-	}
+	ret = kfd_mem_export_dmabuf(mem);
+	if (ret)
+		return ret;
 
 	gobj = amdgpu_gem_prime_import(adev_to_drm(adev), mem->dmabuf);
 	if (IS_ERR(gobj))
@@ -1575,7 +1583,7 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev)
 {
 	uint64_t reserved_for_pt =
 		ESTIMATE_PT_SIZE(amdgpu_amdkfd_total_mem_size);
-	size_t available;
+	ssize_t available;
 
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
 	available = adev->gmc.real_vram_size
@@ -1584,6 +1592,9 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev)
 		- reserved_for_pt;
 	spin_unlock(&kfd_mem_limit.mem_limit_lock);
 
+	if (available < 0)
+		available = 0;
+
 	return ALIGN_DOWN(available, VRAM_AVAILABLITY_ALIGN);
 }
 
@@ -2210,30 +2221,27 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev,
 	struct amdgpu_bo *bo;
 	int ret;
 
-	if (dma_buf->ops != &amdgpu_dmabuf_ops)
-		/* Can't handle non-graphics buffers */
-		return -EINVAL;
-
-	obj = dma_buf->priv;
-	if (drm_to_adev(obj->dev) != adev)
-		/* Can't handle buffers from other devices */
-		return -EINVAL;
+	obj = amdgpu_gem_prime_import(adev_to_drm(adev), dma_buf);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
 	bo = gem_to_amdgpu_bo(obj);
 	if (!(bo->preferred_domains & (AMDGPU_GEM_DOMAIN_VRAM |
-				    AMDGPU_GEM_DOMAIN_GTT)))
+				    AMDGPU_GEM_DOMAIN_GTT))) {
 		/* Only VRAM and GTT BOs are supported */
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_put_obj;
+	}
 
 	*mem = kzalloc(sizeof(struct kgd_mem), GFP_KERNEL);
-	if (!*mem)
-		return -ENOMEM;
+	if (!*mem) {
+		ret = -ENOMEM;
+		goto err_put_obj;
+	}
 
 	ret = drm_vma_node_allow(&obj->vma_node, drm_priv);
-	if (ret) {
-		kfree(*mem);
-		return ret;
-	}
+	if (ret)
+		goto err_free_mem;
 
 	if (size)
 		*size = amdgpu_bo_size(bo);
@@ -2250,7 +2258,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev,
 		| KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE
 		| KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE;
 
-	drm_gem_object_get(&bo->tbo.base);
+	get_dma_buf(dma_buf);
+	(*mem)->dmabuf = dma_buf;
 	(*mem)->bo = bo;
 	(*mem)->va = va;
 	(*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ?
@@ -2262,6 +2271,29 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev,
 	(*mem)->is_imported = true;
 
 	return 0;
+
+err_free_mem:
+	kfree(*mem);
+err_put_obj:
+	drm_gem_object_put(obj);
+	return ret;
+}
+
+int amdgpu_amdkfd_gpuvm_export_dmabuf(struct kgd_mem *mem,
+				      struct dma_buf **dma_buf)
+{
+	int ret;
+
+	mutex_lock(&mem->lock);
+	ret = kfd_mem_export_dmabuf(mem);
+	if (ret)
+		goto out;
+
+	get_dma_buf(mem->dmabuf);
+	*dma_buf = mem->dmabuf;
+out:
+	mutex_unlock(&mem->lock);
+	return ret;
 }
 
 /* Evict a userptr BO by stopping the queues if necessary