Use proper amdgpu_gem_prime_import function to handle all kinds of imports. Remember the dmabuf reference to enable proper multi-GPU attachment to multiple VMs without erroneously re-exporting the underlying BO multiple times.
Signed-off-by: Felix Kuehling Felix.Kuehling@amd.com --- .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 38 ++++++++++--------- 1 file changed, 21 insertions(+), 17 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index cd89d2e46852..2ac61a1e665e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -2033,30 +2033,27 @@ 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); @@ -2073,7 +2070,8 @@ 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) ? @@ -2085,6 +2083,12 @@ 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; }
/* Evict a userptr BO by stopping the queues if necessary
Exports a DMA buf fd of a given KFD buffer handle. This is intended for the new upstreamable RDMA solution coming to UCX and libfabric.
The corresponding user mode change (Thunk API and kfdtest) is here: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commits/fxkamd/dma...
Signed-off-by: Felix Kuehling Felix.Kuehling@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 2 + .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 45 ++++++++++++---- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 54 +++++++++++++++++++ include/uapi/linux/kfd_ioctl.h | 14 ++++- 4 files changed, 103 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 4cb14c2fe53f..0b8cfe8c72ea 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -294,6 +294,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev, uint64_t va, void *drm_priv, struct kgd_mem **mem, uint64_t *size, uint64_t *mmap_offset); +int amdgpu_amdkfd_gpuvm_export_dmabuf(struct kgd_mem *mem, + struct dma_buf **dmabuf); int amdgpu_amdkfd_get_tile_config(struct amdgpu_device *adev, struct tile_config *config); void amdgpu_amdkfd_ras_poison_consumption_handler(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 2ac61a1e665e..d23fdebd2552 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -641,6 +641,21 @@ kfd_mem_attach_userptr(struct amdgpu_device *adev, struct kgd_mem *mem, return 0; }
+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) @@ -648,16 +663,9 @@ 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)) @@ -2091,6 +2099,23 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev, 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 * * Runs in MMU notifier, may be in RECLAIM_FS context. This means it diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index e1e2362841f8..6f5c5b533862 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1500,6 +1500,58 @@ static int kfd_ioctl_import_dmabuf(struct file *filep, return r; }
+static int kfd_ioctl_export_dmabuf(struct file *filep, + struct kfd_process *p, void *data) +{ + struct kfd_ioctl_export_dmabuf_args *args = data; + struct kfd_process_device *pdd; + struct dma_buf *dmabuf; + struct kfd_dev *dev; + void *mem; + int ret = 0; + + dev = kfd_device_by_id(GET_GPU_ID(args->handle)); + if (!dev) + return -EINVAL; + + mutex_lock(&p->mutex); + + pdd = kfd_get_process_device_data(dev, p); + if (!pdd) { + ret = -EINVAL; + goto err_unlock; + } + + mem = kfd_process_device_translate_handle(pdd, + GET_IDR_HANDLE(args->handle)); + if (!mem) { + ret = -EINVAL; + goto err_unlock; + } + + ret = amdgpu_amdkfd_gpuvm_export_dmabuf(mem, &dmabuf); + mutex_unlock(&p->mutex); + if (ret) + goto err_out; + + ret = dma_buf_fd(dmabuf, args->flags); + if (ret < 0) { + dma_buf_put(dmabuf); + goto err_out; + } + /* dma_buf_fd assigns the reference count to the fd, no need to + * put the reference here. + */ + args->dmabuf_fd = ret; + + return 0; + +err_unlock: + mutex_unlock(&p->mutex); +err_out: + return ret; +} + /* Handle requests for watching SMI events */ static int kfd_ioctl_smi_events(struct file *filep, struct kfd_process *p, void *data) @@ -2656,6 +2708,8 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_CRIU_OP, kfd_ioctl_criu, KFD_IOC_FLAG_CHECKPOINT_RESTORE),
+ AMDKFD_IOCTL_DEF(AMDKFD_IOC_EXPORT_DMABUF, + kfd_ioctl_export_dmabuf, 0), };
#define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index eb9ff85f8556..edf7b1648335 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -34,9 +34,10 @@ * - 1.6 - Query clear flags in SVM get_attr API * - 1.7 - Checkpoint Restore (CRIU) API * - 1.8 - CRIU - Support for SDMA transfers with GTT BOs + * - 1.9 - Add DMA buf export ioctl */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 8 +#define KFD_IOCTL_MINOR_VERSION 9
struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ @@ -452,6 +453,12 @@ struct kfd_ioctl_import_dmabuf_args { __u32 dmabuf_fd; /* to KFD */ };
+struct kfd_ioctl_export_dmabuf_args { + __u64 handle; /* to KFD */ + __u32 flags; /* to KFD */ + __u32 dmabuf_fd; /* from KFD */ +}; + /* * KFD SMI(System Management Interface) events */ @@ -824,7 +831,10 @@ struct kfd_ioctl_set_xnack_mode_args { #define AMDKFD_IOC_CRIU_OP \ AMDKFD_IOWR(0x22, struct kfd_ioctl_criu_args)
+#define AMDKFD_IOC_EXPORT_DMABUF \ + AMDKFD_IOWR(0x23, struct kfd_ioctl_export_dmabuf_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x23 +#define AMDKFD_COMMAND_END 0x24
#endif
dri-devel@lists.freedesktop.org
-
Felix Kuehling