diff options
| author | Maor Gottlieb <maorg@nvidia.com> | 2020-10-04 18:43:37 +0300 |
|---|---|---|
| committer | Jason Gunthorpe <jgg@nvidia.com> | 2020-10-05 20:45:45 -0300 |
| commit | 07da1223ec939982497db3caccd6215b55acc35c (patch) | |
| tree | 1082e684f27ab2b2750aba537ecbf075242d429d /drivers/gpu/drm | |
| parent | 29d88681fb49f1e8225addd1e783bad1f7d95afc (diff) | |
lib/scatterlist: Add support in dynamic allocation of SG table from pages
Extend __sg_alloc_table_from_pages to support dynamic allocation of
SG table from pages. It should be used by drivers that can't supply
all the pages at one time.
This function returns the last populated SGE in the table. Users should
pass it as an argument to the function from the second call and forward.
As before, nents will be equal to the number of populated SGEs (chunks).
With this new extension, drivers can benefit the optimization of merging
contiguous pages without a need to allocate all pages in advance and
hold them in a large buffer.
E.g. with the Infiniband driver that allocates a single page for hold the
pages. For 1TB memory registration, the temporary buffer would consume only
4KB, instead of 2GB.
Link: https://lore.kernel.org/r/20201004154340.1080481-2-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Diffstat (limited to 'drivers/gpu/drm')
| -rw-r--r-- | drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 12 | ||||
| -rw-r--r-- | drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 15 |
2 files changed, 15 insertions, 12 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 12b30075134a..f2eaed6aca3d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -403,6 +403,7 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj, unsigned int max_segment = i915_sg_segment_size(); struct sg_table *st; unsigned int sg_page_sizes; + struct scatterlist *sg; int ret; st = kmalloc(sizeof(*st), GFP_KERNEL); @@ -410,13 +411,12 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj, return ERR_PTR(-ENOMEM); alloc_table: - ret = __sg_alloc_table_from_pages(st, pvec, num_pages, - 0, num_pages << PAGE_SHIFT, - max_segment, - GFP_KERNEL); - if (ret) { + sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0, + num_pages << PAGE_SHIFT, max_segment, + NULL, 0, GFP_KERNEL); + if (IS_ERR(sg)) { kfree(st); - return ERR_PTR(ret); + return ERR_CAST(sg); } ret = i915_gem_gtt_prepare_pages(obj, st); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index ab524ab3b0b4..f22acd398b1f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -419,6 +419,7 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) int ret = 0; static size_t sgl_size; static size_t sgt_size; + struct scatterlist *sg; if (vmw_tt->mapped) return 0; @@ -441,13 +442,15 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) if (unlikely(ret != 0)) return ret; - ret = __sg_alloc_table_from_pages - (&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0, - (unsigned long) vsgt->num_pages << PAGE_SHIFT, - dma_get_max_seg_size(dev_priv->dev->dev), - GFP_KERNEL); - if (unlikely(ret != 0)) + sg = __sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages, + vsgt->num_pages, 0, + (unsigned long) vsgt->num_pages << PAGE_SHIFT, + dma_get_max_seg_size(dev_priv->dev->dev), + NULL, 0, GFP_KERNEL); + if (IS_ERR(sg)) { + ret = PTR_ERR(sg); goto out_sg_alloc_fail; + } if (vsgt->num_pages > vmw_tt->sgt.nents) { uint64_t over_alloc = |