The Documentation/DMA-API-HOWTO.txt states that the dma_map_sg() function returns the number of the created entries in the DMA address space. However the subsequent calls to the dma_sync_sg_for_{device,cpu}() and dma_unmap_sg must be called with the original number of the entries passed to the dma_map_sg().
struct sg_table is a common structure used for describing a non-contiguous memory buffer, used commonly in the DRM and graphics subsystems. It consists of a scatterlist with memory pages and DMA addresses (sgl entry), as well as the number of scatterlist entries: CPU pages (orig_nents entry) and DMA mapped pages (nents entry).
It turned out that it was a common mistake to misuse nents and orig_nents entries, calling DMA-mapping functions with a wrong number of entries or ignoring the number of mapped entries returned by the dma_map_sg() function.
To avoid such issues, lets use a common dma-mapping wrappers operating directly on the struct sg_table objects and use scatterlist page iterators where possible. This, almost always, hides references to the nents and orig_nents entries, making the code robust, easier to follow and copy/paste safe.
Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com --- For more information, see '[PATCH v4 00/38] DRM: fix struct sg_table nents vs. orig_nents misuse' thread: https://lore.kernel.org/dri-devel/20200512085710.14688-1-m.szyprowski@samsun... --- drivers/gpu/drm/tegra/gem.c | 27 ++++++++++----------------- drivers/gpu/drm/tegra/plane.c | 15 +++++---------- 2 files changed, 15 insertions(+), 27 deletions(-)
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 6237681..2169130 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -98,8 +98,8 @@ static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo, * the SG table needs to be copied to avoid overwriting any * other potential users of the original SG table. */ - err = sg_alloc_table_from_sg(sgt, obj->sgt->sgl, obj->sgt->nents, - GFP_KERNEL); + err = sg_alloc_table_from_sg(sgt, obj->sgt->sgl, + obj->sgt->orig_nents, GFP_KERNEL); if (err < 0) goto free; } else { @@ -196,8 +196,7 @@ static int tegra_bo_iommu_map(struct tegra_drm *tegra, struct tegra_bo *bo)
bo->iova = bo->mm->start;
- bo->size = iommu_map_sg(tegra->domain, bo->iova, bo->sgt->sgl, - bo->sgt->nents, prot); + bo->size = iommu_map_sgtable(tegra->domain, bo->iova, bo->sgt, prot); if (!bo->size) { dev_err(tegra->drm->dev, "failed to map buffer\n"); err = -ENOMEM; @@ -264,8 +263,7 @@ static struct tegra_bo *tegra_bo_alloc_object(struct drm_device *drm, static void tegra_bo_free(struct drm_device *drm, struct tegra_bo *bo) { if (bo->pages) { - dma_unmap_sg(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_FROM_DEVICE); + dma_unmap_sgtable(drm->dev, bo->sgt, DMA_FROM_DEVICE, 0); drm_gem_put_pages(&bo->gem, bo->pages, true, true); sg_free_table(bo->sgt); kfree(bo->sgt); @@ -290,12 +288,9 @@ static int tegra_bo_get_pages(struct drm_device *drm, struct tegra_bo *bo) goto put_pages; }
- err = dma_map_sg(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_FROM_DEVICE); - if (err == 0) { - err = -EFAULT; + err = dma_map_sgtable(drm->dev, bo->sgt, DMA_FROM_DEVICE, 0); + if (err) goto free_sgt; - }
return 0;
@@ -571,7 +566,7 @@ int tegra_drm_mmap(struct file *file, struct vm_area_struct *vma) goto free; }
- if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0) + if (dma_map_sgtable(attach->dev, sgt, dir, 0)) goto free;
return sgt; @@ -590,7 +585,7 @@ static void tegra_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach, struct tegra_bo *bo = to_tegra_bo(gem);
if (bo->pages) - dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir); + dma_unmap_sgtable(attach->dev, sgt, dir, 0);
sg_free_table(sgt); kfree(sgt); @@ -609,8 +604,7 @@ static int tegra_gem_prime_begin_cpu_access(struct dma_buf *buf, struct drm_device *drm = gem->dev;
if (bo->pages) - dma_sync_sg_for_cpu(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_FROM_DEVICE); + dma_sync_sgtable_for_cpu(drm->dev, bo->sgt, DMA_FROM_DEVICE);
return 0; } @@ -623,8 +617,7 @@ static int tegra_gem_prime_end_cpu_access(struct dma_buf *buf, struct drm_device *drm = gem->dev;
if (bo->pages) - dma_sync_sg_for_device(drm->dev, bo->sgt->sgl, bo->sgt->nents, - DMA_TO_DEVICE); + dma_sync_sgtable_for_device(drm->dev, bo->sgt, DMA_TO_DEVICE);
return 0; } diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c index 9ccfb56..0d2ef16 100644 --- a/drivers/gpu/drm/tegra/plane.c +++ b/drivers/gpu/drm/tegra/plane.c @@ -130,12 +130,9 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state) }
if (sgt) { - err = dma_map_sg(dc->dev, sgt->sgl, sgt->nents, - DMA_TO_DEVICE); - if (err == 0) { - err = -ENOMEM; + err = dma_map_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); + if (err) goto unpin; - }
/* * The display controller needs contiguous memory, so @@ -143,7 +140,7 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state) * map its SG table to a single contiguous chunk of * I/O virtual memory. */ - if (err > 1) { + if (sgt->nents > 1) { err = -EINVAL; goto unpin; } @@ -165,8 +162,7 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state) struct sg_table *sgt = state->sgt[i];
if (sgt) - dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents, - DMA_TO_DEVICE); + dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0);
host1x_bo_unpin(dc->dev, &bo->base, sgt); state->iova[i] = DMA_MAPPING_ERROR; @@ -185,8 +181,7 @@ static void tegra_dc_unpin(struct tegra_dc *dc, struct tegra_plane_state *state) struct sg_table *sgt = state->sgt[i];
if (sgt) - dma_unmap_sg(dc->dev, sgt->sgl, sgt->nents, - DMA_TO_DEVICE); + dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0);
host1x_bo_unpin(dc->dev, &bo->base, sgt); state->iova[i] = DMA_MAPPING_ERROR;