[Intel-gfx] [PATCH 6/6] drm/amdgpu: add independent DMA-buf import v7
Instead of relying on the DRM functions just implement our own import functions. This prepares support for taking care of unpinned DMA-buf. v2: enable for all exporters, not just amdgpu, fix invalidation handling, lock reservation object while setting callback v3: change to new dma_buf attach interface v4: split out from unpinned DMA-buf work v5: rebased and cleanup on new DMA-buf interface v6: squash with invalidation callback change, stop using _(map|unmap)_locked v7: drop invalidations when the BO is already in system domain Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 68 - drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h | 4 -- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 32 -- 5 files changed, 86 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 4541eae7aadb..2630393da35c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -423,31 +423,28 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj, } /** - * amdgpu_gem_prime_import_sg_table - &drm_driver.gem_prime_import_sg_table - * implementation + * amdgpu_dma_buf_create_obj - create BO for DMA-buf import + * * @dev: DRM device - * @attach: DMA-buf attachment - * @sg: Scatter/gather table + * @dma_buf: DMA-buf * - * Imports shared DMA buffer memory exported by another device. + * Creates an empty SG BO for DMA-buf import. * * Returns: * A new GEM BO of the given DRM device, representing the memory * described by the given DMA-buf attachment and scatter/gather table. */ -struct drm_gem_object * -amdgpu_gem_prime_import_sg_table(struct drm_device *dev, -struct dma_buf_attachment *attach, -struct sg_table *sg) +static struct drm_gem_object * +amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) { - struct reservation_object *resv = attach->dmabuf->resv; + struct reservation_object *resv = dma_buf->resv; struct amdgpu_device *adev = dev->dev_private; struct amdgpu_bo *bo; struct amdgpu_bo_param bp; int ret; memset(&bp, 0, sizeof(bp)); - bp.size = attach->dmabuf->size; + bp.size = dma_buf->size; bp.byte_align = PAGE_SIZE; bp.domain = AMDGPU_GEM_DOMAIN_CPU; bp.flags = 0; @@ -458,11 +455,9 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, if (ret) goto error; - bo->tbo.sg = sg; - bo->tbo.ttm->sg = sg; bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT; bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT; - if (attach->dmabuf->ops != &amdgpu_dmabuf_ops) + if (dma_buf->ops != &amdgpu_dmabuf_ops) bo->prime_shared_count = 1; ww_mutex_unlock(&resv->lock); @@ -473,6 +468,35 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, return ERR_PTR(ret); } +/** + * amdgpu_gem_prime_move_notify - &attach.move_notify implementation + * + * @attach: the DMA-buf attachment + * + * Invalidate the DMA-buf attachment, making sure that the we re-create the + * mapping before the next use. + */ +static void +amdgpu_gem_prime_move_notify(struct dma_buf_attachment *attach) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct drm_gem_object *obj = attach->importer_priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + struct ttm_placement placement = {}; + int r; + + if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM) + return; + + r = ttm_bo_validate(&bo->tbo, &placement, &ctx); + if (r) + DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r); +} + +static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = { + .move_notify = amdgpu_gem_prime_move_notify +}; + /** * amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation * @dev: DRM device @@ -487,6 +511,7 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf) { + struct dma_buf_attachment *attach; struct drm_gem_object *obj; if (dma_buf->ops == &amdgpu_dmabuf_ops) { @@ -501,5 +526,18 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, } } - return drm_gem_prime_import(dev, dma_buf); + obj = amdgpu_dma_buf_create_obj(dev, dma_buf); + if (IS_ERR(obj)) + return obj; + + attach = dma_buf_dynamic_attach(dma_buf, dev->dev, + &amdgpu_dma_buf_attach_ops, obj); + if (IS_ERR(attach)) { +
[Intel-gfx] [PATCH 6/6] drm/amdgpu: add independent DMA-buf import v7
Instead of relying on the DRM functions just implement our own import functions. This prepares support for taking care of unpinned DMA-buf. v2: enable for all exporters, not just amdgpu, fix invalidation handling, lock reservation object while setting callback v3: change to new dma_buf attach interface v4: split out from unpinned DMA-buf work v5: rebased and cleanup on new DMA-buf interface v6: squash with invalidation callback change, stop using _(map|unmap)_locked v7: drop invalidations when the BO is already in system domain Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 68 - drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h | 4 -- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 32 -- 5 files changed, 86 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 4541eae7aadb..2630393da35c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -423,31 +423,28 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj, } /** - * amdgpu_gem_prime_import_sg_table - &drm_driver.gem_prime_import_sg_table - * implementation + * amdgpu_dma_buf_create_obj - create BO for DMA-buf import + * * @dev: DRM device - * @attach: DMA-buf attachment - * @sg: Scatter/gather table + * @dma_buf: DMA-buf * - * Imports shared DMA buffer memory exported by another device. + * Creates an empty SG BO for DMA-buf import. * * Returns: * A new GEM BO of the given DRM device, representing the memory * described by the given DMA-buf attachment and scatter/gather table. */ -struct drm_gem_object * -amdgpu_gem_prime_import_sg_table(struct drm_device *dev, -struct dma_buf_attachment *attach, -struct sg_table *sg) +static struct drm_gem_object * +amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) { - struct reservation_object *resv = attach->dmabuf->resv; + struct reservation_object *resv = dma_buf->resv; struct amdgpu_device *adev = dev->dev_private; struct amdgpu_bo *bo; struct amdgpu_bo_param bp; int ret; memset(&bp, 0, sizeof(bp)); - bp.size = attach->dmabuf->size; + bp.size = dma_buf->size; bp.byte_align = PAGE_SIZE; bp.domain = AMDGPU_GEM_DOMAIN_CPU; bp.flags = 0; @@ -458,11 +455,9 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, if (ret) goto error; - bo->tbo.sg = sg; - bo->tbo.ttm->sg = sg; bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT; bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT; - if (attach->dmabuf->ops != &amdgpu_dmabuf_ops) + if (dma_buf->ops != &amdgpu_dmabuf_ops) bo->prime_shared_count = 1; ww_mutex_unlock(&resv->lock); @@ -473,6 +468,35 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, return ERR_PTR(ret); } +/** + * amdgpu_gem_prime_move_notify - &attach.move_notify implementation + * + * @attach: the DMA-buf attachment + * + * Invalidate the DMA-buf attachment, making sure that the we re-create the + * mapping before the next use. + */ +static void +amdgpu_gem_prime_move_notify(struct dma_buf_attachment *attach) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct drm_gem_object *obj = attach->importer_priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + struct ttm_placement placement = {}; + int r; + + if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM) + return; + + r = ttm_bo_validate(&bo->tbo, &placement, &ctx); + if (r) + DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r); +} + +static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = { + .move_notify = amdgpu_gem_prime_move_notify +}; + /** * amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation * @dev: DRM device @@ -487,6 +511,7 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf) { + struct dma_buf_attachment *attach; struct drm_gem_object *obj; if (dma_buf->ops == &amdgpu_dmabuf_ops) { @@ -501,5 +526,18 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, } } - return drm_gem_prime_import(dev, dma_buf); + obj = amdgpu_dma_buf_create_obj(dev, dma_buf); + if (IS_ERR(obj)) + return obj; + + attach = dma_buf_dynamic_attach(dma_buf, dev->dev, + &amdgpu_dma_buf_attach_ops, obj); + if (IS_ERR(attach)) { +
[Intel-gfx] [PATCH 6/6] drm/amdgpu: add independent DMA-buf import v7
Instead of relying on the DRM functions just implement our own import functions. This prepares support for taking care of unpinned DMA-buf. v2: enable for all exporters, not just amdgpu, fix invalidation handling, lock reservation object while setting callback v3: change to new dma_buf attach interface v4: split out from unpinned DMA-buf work v5: rebased and cleanup on new DMA-buf interface v6: squash with invalidation callback change, stop using _(map|unmap)_locked v7: drop invalidations when the BO is already in system domain Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 68 - drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h | 4 -- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 32 -- 5 files changed, 86 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 579e33b31f2d..b5972e0631f6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -424,31 +424,28 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev, } /** - * amdgpu_gem_prime_import_sg_table - &drm_driver.gem_prime_import_sg_table - * implementation + * amdgpu_dma_buf_create_obj - create BO for DMA-buf import + * * @dev: DRM device - * @attach: DMA-buf attachment - * @sg: Scatter/gather table + * @dma_buf: DMA-buf * - * Imports shared DMA buffer memory exported by another device. + * Creates an empty SG BO for DMA-buf import. * * Returns: * A new GEM BO of the given DRM device, representing the memory * described by the given DMA-buf attachment and scatter/gather table. */ -struct drm_gem_object * -amdgpu_gem_prime_import_sg_table(struct drm_device *dev, -struct dma_buf_attachment *attach, -struct sg_table *sg) +static struct drm_gem_object * +amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) { - struct reservation_object *resv = attach->dmabuf->resv; + struct reservation_object *resv = dma_buf->resv; struct amdgpu_device *adev = dev->dev_private; struct amdgpu_bo *bo; struct amdgpu_bo_param bp; int ret; memset(&bp, 0, sizeof(bp)); - bp.size = attach->dmabuf->size; + bp.size = dma_buf->size; bp.byte_align = PAGE_SIZE; bp.domain = AMDGPU_GEM_DOMAIN_CPU; bp.flags = 0; @@ -459,11 +456,9 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, if (ret) goto error; - bo->tbo.sg = sg; - bo->tbo.ttm->sg = sg; bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT; bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT; - if (attach->dmabuf->ops != &amdgpu_dmabuf_ops) + if (dma_buf->ops != &amdgpu_dmabuf_ops) bo->prime_shared_count = 1; ww_mutex_unlock(&resv->lock); @@ -474,6 +469,35 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, return ERR_PTR(ret); } +/** + * amdgpu_gem_prime_invalidate_mappings - &attach.invalidate implementation + * + * @attach: the DMA-buf attachment + * + * Invalidate the DMA-buf attachment, making sure that the we re-create the + * mapping before the next use. + */ +static void +amdgpu_gem_prime_invalidate_mappings(struct dma_buf_attachment *attach) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct drm_gem_object *obj = attach->importer_priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + struct ttm_placement placement = {}; + int r; + + if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM) + return; + + r = ttm_bo_validate(&bo->tbo, &placement, &ctx); + if (r) + DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r); +} + +static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = { + .invalidate = amdgpu_gem_prime_invalidate_mappings +}; + /** * amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation * @dev: DRM device @@ -488,6 +512,7 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev, struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf) { + struct dma_buf_attachment *attach; struct drm_gem_object *obj; if (dma_buf->ops == &amdgpu_dmabuf_ops) { @@ -502,5 +527,18 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, } } - return drm_gem_prime_import(dev, dma_buf); + obj = amdgpu_dma_buf_create_obj(dev, dma_buf); + if (IS_ERR(obj)) + return obj; + + attach = dma_buf_dynamic_attach(dma_buf, dev->dev, + &amdgpu_dma_buf_attach_ops, obj); + if (IS_ERR(att