It is a common operation done by DRM drivers to check the contiguity of the DMA-mapped buffer described by a scatterlist in the sg_table object. Let's add a common helper for this operation.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com --- drivers/gpu/drm/drm_gem_cma_helper.c | 23 +++------------------ drivers/gpu/drm/drm_prime.c | 31 ++++++++++++++++++++++++++++ include/drm/drm_prime.h | 2 ++ 3 files changed, 36 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c index 06a5b9ee1fe0..41566a15dabd 100644 --- a/drivers/gpu/drm/drm_gem_cma_helper.c +++ b/drivers/gpu/drm/drm_gem_cma_helper.c @@ -471,26 +471,9 @@ drm_gem_cma_prime_import_sg_table(struct drm_device *dev, { struct drm_gem_cma_object *cma_obj;

- if (sgt->nents != 1) { - /* check if the entries in the sg_table are contiguous */ - dma_addr_t next_addr = sg_dma_address(sgt->sgl); - struct scatterlist *s; - unsigned int i; - - for_each_sg(sgt->sgl, s, sgt->nents, i) { - /* - * sg_dma_address(s) is only valid for entries - * that have sg_dma_len(s) != 0 - */ - if (!sg_dma_len(s)) - continue; - - if (sg_dma_address(s) != next_addr) - return ERR_PTR(-EINVAL); - - next_addr = sg_dma_address(s) + sg_dma_len(s); - } - } + /* check if the entries in the sg_table are contiguous */ + if (drm_prime_get_contiguous_size(sgt) < attach->dmabuf->size) + return ERR_PTR(-EINVAL);

/* Create a CMA GEM buffer. */ cma_obj = __drm_gem_cma_create(dev, attach->dmabuf->size); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index bbfc713bfdc3..226cd6ad3985 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -825,6 +825,37 @@ struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_page } EXPORT_SYMBOL(drm_prime_pages_to_sg);

+/** + * drm_prime_get_contiguous_size - returns the contiguous size of the buffer + * @sgt: sg_table describing the buffer to check + * + * This helper calculates the contiguous size in the DMA address space + * of the the buffer described by the provided sg_table. + * + * This is useful for implementing + * &drm_gem_object_funcs.gem_prime_import_sg_table. + */ +unsigned long drm_prime_get_contiguous_size(struct sg_table *sgt) +{ + dma_addr_t expected = sg_dma_address(sgt->sgl); + struct scatterlist *sg; + unsigned long size = 0; + int i; + + for_each_sgtable_dma_sg(sgt, sg, i) { + unsigned int len = sg_dma_len(sg); + + if (!len) + break; + if (sg_dma_address(sg) != expected) + break; + expected += len; + size += len; + } + return size; +} +EXPORT_SYMBOL(drm_prime_get_contiguous_size); + /** * drm_gem_prime_export - helper library implementation of the export callback * @obj: GEM object to export diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index 9af7422b44cf..47ef11614627 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -92,6 +92,8 @@ struct sg_table *drm_prime_pages_to_sg(struct page **pages, unsigned int nr_page struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj, int flags);

+unsigned long drm_prime_get_contiguous_size(struct sg_table *sgt); + /* helper functions for importing */ struct drm_gem_object *drm_gem_prime_import_dev(struct drm_device *dev, struct dma_buf *dma_buf,

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 --- drivers/gpu/drm/drm_cache.c | 2 +- drivers/gpu/drm/drm_gem_shmem_helper.c | 14 +++++++++----- drivers/gpu/drm/drm_prime.c | 11 ++++++----- 3 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 03e01b000f7a..0fe3c496002a 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -127,7 +127,7 @@ drm_clflush_sg(struct sg_table *st) struct sg_page_iter sg_iter;

mb(); /*CLFLUSH is ordered only by using memory barriers*/ - for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) + for_each_sgtable_page(st, &sg_iter, 0) drm_clflush_page(sg_page_iter_page(&sg_iter)); mb(); /*Make sure that all cache line entry is flushed*/

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 4b7cfbac4daa..47d8211221f2 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -126,8 +126,8 @@ void drm_gem_shmem_free_object(struct drm_gem_object *obj) drm_prime_gem_destroy(obj, shmem->sgt); } else { if (shmem->sgt) { - dma_unmap_sg(obj->dev->dev, shmem->sgt->sgl, - shmem->sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(obj->dev->dev, shmem->sgt, + DMA_BIDIRECTIONAL, 0); sg_free_table(shmem->sgt); kfree(shmem->sgt); } @@ -424,8 +424,7 @@ void drm_gem_shmem_purge_locked(struct drm_gem_object *obj)

WARN_ON(!drm_gem_shmem_is_purgeable(shmem));

- dma_unmap_sg(obj->dev->dev, shmem->sgt->sgl, - shmem->sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(obj->dev->dev, shmem->sgt, DMA_BIDIRECTIONAL, 0); sg_free_table(shmem->sgt); kfree(shmem->sgt); shmem->sgt = NULL; @@ -697,12 +696,17 @@ struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_object *obj) goto err_put_pages; } /* Map the pages for use by the h/w. */ - dma_map_sg(obj->dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); + ret = dma_map_sgtable(obj->dev->dev, sgt, DMA_BIDIRECTIONAL, 0); + if (ret) + goto err_free_sgt;

shmem->sgt = sgt;

return sgt;

+err_free_sgt: + sg_free_table(sgt); + kfree(sgt); err_put_pages: drm_gem_shmem_put_pages(shmem); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index b717e52e909e..d583d6545666 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -617,6 +617,7 @@ struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach, { struct drm_gem_object *obj = attach->dmabuf->priv; struct sg_table *sgt; + int ret;

if (WARN_ON(dir == DMA_NONE)) return ERR_PTR(-EINVAL); @@ -626,11 +627,12 @@ struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach, else sgt = obj->dev->driver->gem_prime_get_sg_table(obj);

- if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir, - DMA_ATTR_SKIP_CPU_SYNC)) { + ret = dma_map_sgtable(attach->dev, sgt, dir, + DMA_ATTR_SKIP_CPU_SYNC); + if (ret) { sg_free_table(sgt); kfree(sgt); - sgt = ERR_PTR(-ENOMEM); + sgt = ERR_PTR(ret); }

return sgt; @@ -652,8 +654,7 @@ void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach, if (!sgt) return;

- dma_unmap_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir, - DMA_ATTR_SKIP_CPU_SYNC); + dma_unmap_sgtable(attach->dev, sgt, dir, DMA_ATTR_SKIP_CPU_SYNC); sg_free_table(sgt); kfree(sgt); }

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 --- drivers/gpu/drm/armada/armada_gem.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index 8005614d2e6b..bedd8937d8a1 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -395,7 +395,7 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,

mapping = dobj->obj.filp->f_mapping;

- for_each_sg(sgt->sgl, sg, count, i) { + for_each_sgtable_sg(sgt, sg, i) { struct page *page;

page = shmem_read_mapping_page(mapping, i); @@ -407,8 +407,8 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, sg_set_page(sg, page, PAGE_SIZE, 0); }

- if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0) { - num = sgt->nents; + if (dma_map_sgtable(attach->dev, sgt, dir, 0)) { + num = count; goto release; } } else if (dobj->page) { @@ -418,7 +418,7 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,

sg_set_page(sgt->sgl, dobj->page, dobj->obj.size, 0);

- if (dma_map_sg(attach->dev, sgt->sgl, sgt->nents, dir) == 0) + if (dma_map_sgtable(attach->dev, sgt, dir, 0)) goto free_table; } else if (dobj->linear) { /* Single contiguous physical region - no struct page */ @@ -449,11 +449,11 @@ static void armada_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach, int i;

if (!dobj->linear) - dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir); + dma_unmap_sgtable(attach->dev, sgt, dir, 0);

if (dobj->obj.filp) { struct scatterlist *sg; - for_each_sg(sgt->sgl, sg, sgt->nents, i) + for_each_sgtable_sg(sgt, sg, i) put_page(sg_page(sg)); }

Use common helper for checking the contiguity of the imported dma-buf.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com --- drivers/gpu/drm/exynos/exynos_drm_gem.c | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index efa476858db5..1716a023bca0 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -431,27 +431,10 @@ exynos_drm_gem_prime_import_sg_table(struct drm_device *dev, { struct exynos_drm_gem *exynos_gem;

- if (sgt->nents < 1) + /* check if the entries in the sg_table are contiguous */ + if (drm_prime_get_contiguous_size(sgt) < attach->dmabuf->size) { + DRM_ERROR("buffer chunks must be mapped contiguously"); return ERR_PTR(-EINVAL); - - /* - * Check if the provided buffer has been mapped as contiguous - * into DMA address space. - */ - if (sgt->nents > 1) { - dma_addr_t next_addr = sg_dma_address(sgt->sgl); - struct scatterlist *s; - unsigned int i; - - for_each_sg(sgt->sgl, s, sgt->nents, i) { - if (!sg_dma_len(s)) - break; - if (sg_dma_address(s) != next_addr) { - DRM_ERROR("buffer chunks must be mapped contiguously"); - return ERR_PTR(-EINVAL); - } - next_addr = sg_dma_address(s) + sg_dma_len(s); - } }

exynos_gem = exynos_drm_gem_init(dev, attach->dmabuf->size);

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 --- drivers/gpu/drm/exynos/exynos_drm_g2d.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index fcee33a43aca..7014a8cd971a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -395,8 +395,8 @@ static void g2d_userptr_put_dma_addr(struct g2d_data *g2d, return;

out: - dma_unmap_sg(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt->sgl, - g2d_userptr->sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt, + DMA_BIDIRECTIONAL, 0);

pages = frame_vector_pages(g2d_userptr->vec); if (!IS_ERR(pages)) { @@ -511,10 +511,10 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,

g2d_userptr->sgt = sgt;

- if (!dma_map_sg(to_dma_dev(g2d->drm_dev), sgt->sgl, sgt->nents, - DMA_BIDIRECTIONAL)) { + ret = dma_map_sgtable(to_dma_dev(g2d->drm_dev), sgt, + DMA_BIDIRECTIONAL, 0); + if (ret) { DRM_DEV_ERROR(g2d->dev, "failed to map sgt with dma region.\n"); - ret = -ENOMEM; goto err_sg_free_table; }

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.

This driver creatively uses sg_table->orig_nents to store the size of the allocated scatterlist and ignores the number of the entries returned by dma_map_sg function. The sg_table->orig_nents is (mis)used to properly free the (over)allocated scatterlist.

This patch only introduces the common DMA-mapping wrappers operating directly on the struct sg_table objects to the dmabuf related functions, so the other drivers, which might share buffers with i915 could rely on the properly set nents and orig_nents values.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com --- drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 11 +++-------- drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c | 7 +++---- 2 files changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index 2679380159fc..8a988592715b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -48,12 +48,9 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme src = sg_next(src); }

- if (!dma_map_sg_attrs(attachment->dev, - st->sgl, st->nents, dir, - DMA_ATTR_SKIP_CPU_SYNC)) { - ret = -ENOMEM; + ret = dma_map_sgtable(attachment->dev, st, dir, DMA_ATTR_SKIP_CPU_SYNC); + if (ret) goto err_free_sg; - }

return st;

@@ -73,9 +70,7 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment, { struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);

- dma_unmap_sg_attrs(attachment->dev, - sg->sgl, sg->nents, dir, - DMA_ATTR_SKIP_CPU_SYNC); + dma_unmap_sgtable(attachment->dev, sg, dir, DMA_ATTR_SKIP_CPU_SYNC); sg_free_table(sg); kfree(sg);

diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c index debaf7b18ab5..be30b27e2926 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c @@ -28,10 +28,9 @@ static struct sg_table *mock_map_dma_buf(struct dma_buf_attachment *attachment, sg = sg_next(sg); }

- if (!dma_map_sg(attachment->dev, st->sgl, st->nents, dir)) { - err = -ENOMEM; + err = dma_map_sgtable(attachment->dev, st, dir, 0); + if (err) goto err_st; - }

return st;

@@ -46,7 +45,7 @@ static void mock_unmap_dma_buf(struct dma_buf_attachment *attachment, struct sg_table *st, enum dma_data_direction dir) { - dma_unmap_sg(attachment->dev, st->sgl, st->nents, dir); + dma_unmap_sgtable(attachment->dev, st, dir, 0); sg_free_table(st); kfree(st); }

Use common helper for checking the contiguity of the imported dma-buf and do this check before allocating resources, so the error path is simpler.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com --- drivers/gpu/drm/mediatek/mtk_drm_gem.c | 28 ++++++-------------------- 1 file changed, 6 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 6190cc3b7b0d..3654ec732029 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -212,37 +212,21 @@ struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg) { struct mtk_drm_gem_obj *mtk_gem; - int ret; - struct scatterlist *s; - unsigned int i; - dma_addr_t expected;

- mtk_gem = mtk_drm_gem_init(dev, attach->dmabuf->size); + /* check if the entries in the sg_table are contiguous */ + if (drm_prime_get_contiguous_size(sg) < attach->dmabuf->size) { + DRM_ERROR("sg_table is not contiguous"); + return ERR_PTR(-EINVAL); + }

+ mtk_gem = mtk_drm_gem_init(dev, attach->dmabuf->size); if (IS_ERR(mtk_gem)) return ERR_CAST(mtk_gem);

- expected = sg_dma_address(sg->sgl); - for_each_sg(sg->sgl, s, sg->nents, i) { - if (!sg_dma_len(s)) - break; - - if (sg_dma_address(s) != expected) { - DRM_ERROR("sg_table is not contiguous"); - ret = -EINVAL; - goto err_gem_free; - } - expected = sg_dma_address(s) + sg_dma_len(s); - } - mtk_gem->dma_addr = sg_dma_address(sg->sgl); mtk_gem->sg = sg;

return &mtk_gem->base; - -err_gem_free: - kfree(mtk_gem); - return ERR_PTR(ret); }

void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj)

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 --- drivers/gpu/drm/msm/msm_gem.c | 13 +++++-------- drivers/gpu/drm/msm/msm_gpummu.c | 14 ++++++-------- drivers/gpu/drm/msm/msm_iommu.c | 2 +- 3 files changed, 12 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 38b0c0e1f83e..e0d5fd36ea8f 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -53,11 +53,10 @@ static void sync_for_device(struct msm_gem_object *msm_obj) struct device *dev = msm_obj->base.dev->dev;

if (get_dma_ops(dev) && IS_ENABLED(CONFIG_ARM64)) { - dma_sync_sg_for_device(dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + dma_sync_sgtable_for_device(dev, msm_obj->sgt, + DMA_BIDIRECTIONAL); } else { - dma_map_sg(dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + dma_map_sgtable(dev, msm_obj->sgt, DMA_BIDIRECTIONAL, 0); } }

@@ -66,11 +65,9 @@ static void sync_for_cpu(struct msm_gem_object *msm_obj) struct device *dev = msm_obj->base.dev->dev;

if (get_dma_ops(dev) && IS_ENABLED(CONFIG_ARM64)) { - dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + dma_sync_sgtable_for_cpu(dev, msm_obj->sgt, DMA_BIDIRECTIONAL); } else { - dma_unmap_sg(dev, msm_obj->sgt->sgl, - msm_obj->sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(dev, msm_obj->sgt, DMA_BIDIRECTIONAL, 0); } }

diff --git a/drivers/gpu/drm/msm/msm_gpummu.c b/drivers/gpu/drm/msm/msm_gpummu.c index 310a31b05faa..319f06c28235 100644 --- a/drivers/gpu/drm/msm/msm_gpummu.c +++ b/drivers/gpu/drm/msm/msm_gpummu.c @@ -30,21 +30,19 @@ static int msm_gpummu_map(struct msm_mmu *mmu, uint64_t iova, { struct msm_gpummu *gpummu = to_msm_gpummu(mmu); unsigned idx = (iova - GPUMMU_VA_START) / GPUMMU_PAGE_SIZE; - struct scatterlist *sg; + struct sg_dma_page_iter dma_iter; unsigned prot_bits = 0; - unsigned i, j;

if (prot & IOMMU_WRITE) prot_bits |= 1; if (prot & IOMMU_READ) prot_bits |= 2;

- for_each_sg(sgt->sgl, sg, sgt->nents, i) { - dma_addr_t addr = sg->dma_address; - for (j = 0; j < sg->length / GPUMMU_PAGE_SIZE; j++, idx++) { - gpummu->table[idx] = addr | prot_bits; - addr += GPUMMU_PAGE_SIZE; - } + for_each_sgtable_dma_page(sgt, &dma_iter, 0) { + dma_addr_t addr = sg_page_iter_dma_address(&dma_iter); + + BUILD_BUG_ON(GPUMMU_PAGE_SIZE != PAGE_SIZE); + gpummu->table[idx++] = addr | prot_bits; }

/* we can improve by deferring flush for multiple map() */ diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 3a381a9674c9..6c31e65834c6 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -36,7 +36,7 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova, struct msm_iommu *iommu = to_msm_iommu(mmu); size_t ret;

- ret = iommu_map_sg(iommu->domain, iova, sgt->sgl, sgt->nents, prot); + ret = iommu_map_sgtable(iommu->domain, iova, sgt, prot); WARN_ON(!ret);

return (ret == len) ? 0 : -EINVAL;

Use common helper for converting a sg_table object into struct page pointer array.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com --- drivers/gpu/drm/omapdrm/omap_gem.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index d0d12d5dd76c..ff0c4b0c3fd0 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -1297,10 +1297,9 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size, omap_obj->dma_addr = sg_dma_address(sgt->sgl); } else { /* Create pages list from sgt */ - struct sg_page_iter iter; struct page **pages; unsigned int npages; - unsigned int i = 0; + unsigned int ret;

npages = DIV_ROUND_UP(size, PAGE_SIZE); pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL); @@ -1311,14 +1310,9 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size, }

omap_obj->pages = pages; - - for_each_sg_page(sgt->sgl, &iter, sgt->orig_nents, 0) { - pages[i++] = sg_page_iter_page(&iter); - if (i > npages) - break; - } - - if (WARN_ON(i != npages)) { + ret = drm_prime_sg_to_page_addr_arrays(sgt, pages, NULL, + npages); + if (WARN_ON(ret)) { omap_gem_free_object(obj); obj = ERR_PTR(-ENOMEM); goto done;

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 Reviewed-by: Steven Price steven.price@arm.com Reviewed-by: Rob Herring robh@kernel.org --- drivers/gpu/drm/panfrost/panfrost_gem.c | 4 ++-- drivers/gpu/drm/panfrost/panfrost_mmu.c | 7 +++---- 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index ac5d0aa80276..ba8450ea04d0 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -41,8 +41,8 @@ static void panfrost_gem_free_object(struct drm_gem_object *obj)

for (i = 0; i < n_sgt; i++) { if (bo->sgts[i].sgl) { - dma_unmap_sg(pfdev->dev, bo->sgts[i].sgl, - bo->sgts[i].nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(pfdev->dev, &bo->sgts[i], + DMA_BIDIRECTIONAL, 0); sg_free_table(&bo->sgts[i]); } } diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 0a339c6fbfaa..fd294f6a7d3b 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -253,7 +253,7 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu, struct io_pgtable_ops *ops = mmu->pgtbl_ops; u64 start_iova = iova;

- for_each_sg(sgt->sgl, sgl, sgt->nents, count) { + for_each_sgtable_dma_sg(sgt, sgl, count) { unsigned long paddr = sg_dma_address(sgl); size_t len = sg_dma_len(sgl);

@@ -517,10 +517,9 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, if (ret) goto err_pages;

- if (!dma_map_sg(pfdev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL)) { - ret = -EINVAL; + ret = dma_map_sgtable(pfdev->dev, sgt, DMA_BIDIRECTIONAL, 0); + if (ret) goto err_map; - }

mmu_map_sg(pfdev, bomapping->mmu, addr, IOMMU_WRITE | IOMMU_READ | IOMMU_NOEXEC, sgt);

Use common helper for checking the contiguity of the imported dma-buf.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com --- drivers/gpu/drm/rockchip/rockchip_drm_gem.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index b9275ba7c5a5..2970e534e2bb 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -460,23 +460,6 @@ struct sg_table *rockchip_gem_prime_get_sg_table(struct drm_gem_object *obj) return sgt; }

-static unsigned long rockchip_sg_get_contiguous_size(struct sg_table *sgt, - int count) -{ - struct scatterlist *s; - dma_addr_t expected = sg_dma_address(sgt->sgl); - unsigned int i; - unsigned long size = 0; - - for_each_sg(sgt->sgl, s, count, i) { - if (sg_dma_address(s) != expected) - break; - expected = sg_dma_address(s) + sg_dma_len(s); - size += sg_dma_len(s); - } - return size; -} - static int rockchip_gem_iommu_map_sg(struct drm_device *drm, struct dma_buf_attachment *attach, @@ -498,7 +481,7 @@ rockchip_gem_dma_map_sg(struct drm_device *drm, if (!count) return -EINVAL;

- if (rockchip_sg_get_contiguous_size(sg, count) < attach->dmabuf->size) { + if (drm_prime_get_contiguous_size(sg) < attach->dmabuf->size) { DRM_ERROR("failed to map sg_table to contiguous linear address.\n"); dma_unmap_sg(drm->dev, sg->sgl, sg->nents, DMA_BIDIRECTIONAL);

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 --- 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 723df142a981..01d94befab11 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 @@ tegra_gem_prime_map_dma_buf(struct dma_buf_attachment *attach, 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 9ccfb56e9b01..0d2ef1662a39 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;

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 Acked-by: Gerd Hoffmann kraxel@redhat.com --- drivers/gpu/drm/virtio/virtgpu_object.c | 36 ++++++++++++++----------- drivers/gpu/drm/virtio/virtgpu_vq.c | 12 ++++----- 2 files changed, 26 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 346cef5ce251..c3b9e3cf786e 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -72,9 +72,8 @@ void virtio_gpu_cleanup_object(struct virtio_gpu_object *bo)

if (shmem->pages) { if (shmem->mapped) { - dma_unmap_sg(vgdev->vdev->dev.parent, - shmem->pages->sgl, shmem->mapped, - DMA_TO_DEVICE); + dma_unmap_sgtable(vgdev->vdev->dev.parent, + shmem->pages, DMA_TO_DEVICE, 0); shmem->mapped = 0; }

@@ -157,13 +156,13 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, }

if (use_dma_api) { - shmem->mapped = dma_map_sg(vgdev->vdev->dev.parent, - shmem->pages->sgl, - shmem->pages->nents, - DMA_TO_DEVICE); - *nents = shmem->mapped; + ret = dma_map_sgtable(vgdev->vdev->dev.parent, + shmem->pages, DMA_TO_DEVICE, 0); + if (ret) + return ret; + *nents = shmem->mapped = shmem->pages->nents; } else { - *nents = shmem->pages->nents; + *nents = shmem->pages->orig_nents; }

*ents = kmalloc_array(*nents, sizeof(struct virtio_gpu_mem_entry), @@ -173,13 +172,20 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, return -ENOMEM; }

- for_each_sg(shmem->pages->sgl, sg, *nents, si) { - (*ents)[si].addr = cpu_to_le64(use_dma_api - ? sg_dma_address(sg) - : sg_phys(sg)); - (*ents)[si].length = cpu_to_le32(sg->length); - (*ents)[si].padding = 0; + if (use_dma_api) { + for_each_sgtable_dma_sg(shmem->pages, sg, si) { + (*ents)[si].addr = cpu_to_le64(sg_dma_address(sg)); + (*ents)[si].length = cpu_to_le32(sg_dma_len(sg)); + (*ents)[si].padding = 0; + } + } else { + for_each_sgtable_sg(shmem->pages, sg, si) { + (*ents)[si].addr = cpu_to_le64(sg_phys(sg)); + (*ents)[si].length = cpu_to_le32(sg->length); + (*ents)[si].padding = 0; + } } + return 0; }

diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index 9e663a5d9952..e5765db85c20 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -302,7 +302,7 @@ static struct sg_table *vmalloc_to_sgt(char *data, uint32_t size, int *sg_ents) return NULL; }

- for_each_sg(sgt->sgl, sg, *sg_ents, i) { + for_each_sgtable_sg(sgt, sg, i) { pg = vmalloc_to_page(data); if (!pg) { sg_free_table(sgt); @@ -603,9 +603,8 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);

if (use_dma_api) - dma_sync_sg_for_device(vgdev->vdev->dev.parent, - shmem->pages->sgl, shmem->pages->nents, - DMA_TO_DEVICE); + dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, + shmem->pages, DMA_TO_DEVICE);

cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); memset(cmd_p, 0, sizeof(*cmd_p)); @@ -1019,9 +1018,8 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);

if (use_dma_api) - dma_sync_sg_for_device(vgdev->vdev->dev.parent, - shmem->pages->sgl, shmem->pages->nents, - DMA_TO_DEVICE); + dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, + shmem->pages, DMA_TO_DEVICE);

cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); memset(cmd_p, 0, sizeof(*cmd_p));

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.

Fix the code to refer to proper nents or orig_nents entries. This driver reports the number of the pages in the imported scatterlist, so it should refer to sg_table->orig_nents entry.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Oleksandr Andrushchenko oleksandr_andrushchenko@epam.com --- drivers/gpu/drm/xen/xen_drm_front_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c index f0b85e094111..ba4bdc5590ea 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_gem.c +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c @@ -215,7 +215,7 @@ xen_drm_front_gem_import_sg_table(struct drm_device *dev, return ERR_PTR(ret);

DRM_DEBUG("Imported buffer of size %zu with nents %u\n", - size, sgt->nents); + size, sgt->orig_nents);

return &xen_obj->base; }

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 --- drivers/gpu/host1x/job.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index a10643aa89aa..4832b57f10c4 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -166,11 +166,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto unpin; }

- err = dma_map_sg(dev, sgt->sgl, sgt->nents, dir); - if (!err) { - err = -ENOMEM; + err = dma_map_sgtable(dev, sgt, dir, 0); + if (err) goto unpin; - }

job->unpins[job->num_unpins].dev = dev; job->unpins[job->num_unpins].dir = dir; @@ -217,7 +215,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) }

if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && host->domain) { - for_each_sg(sgt->sgl, sg, sgt->nents, j) + for_each_sgtable_sg(sgt, sg, j) gather_size += sg->length; gather_size = iova_align(&host->iova, gather_size);

@@ -229,9 +227,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto unpin; }

- err = iommu_map_sg(host->domain, + err = iommu_map_sgtable(host->domain, iova_dma_addr(&host->iova, alloc), - sgt->sgl, sgt->nents, IOMMU_READ); + sgt, IOMMU_READ); if (err == 0) { __free_iova(&host->iova, alloc); err = -EINVAL; @@ -241,12 +239,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) job->unpins[job->num_unpins].size = gather_size; phys_addr = iova_dma_addr(&host->iova, alloc); } else if (sgt) { - err = dma_map_sg(host->dev, sgt->sgl, sgt->nents, - DMA_TO_DEVICE); - if (!err) { - err = -ENOMEM; + err = dma_map_sgtable(host->dev, sgt, DMA_TO_DEVICE, 0); + if (err) goto unpin; - }

job->unpins[job->num_unpins].dir = DMA_TO_DEVICE; job->unpins[job->num_unpins].dev = host->dev; @@ -647,8 +642,7 @@ void host1x_job_unpin(struct host1x_job *job) }

if (unpin->dev && sgt) - dma_unmap_sg(unpin->dev, sgt->sgl, sgt->nents, - unpin->dir); + dma_unmap_sgtable(unpin->dev, sgt, unpin->dir, 0);

host1x_bo_unpin(dev, unpin->bo, sgt); host1x_bo_put(unpin->bo);

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 Acked-by: Gerd Hoffmann kraxel@redhat.com --- drivers/dma-buf/heaps/heap-helpers.c | 13 ++++++------- drivers/dma-buf/udmabuf.c | 7 +++---- 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/dma-buf/heaps/heap-helpers.c b/drivers/dma-buf/heaps/heap-helpers.c index 9f964ca3f59c..d0696cf937af 100644 --- a/drivers/dma-buf/heaps/heap-helpers.c +++ b/drivers/dma-buf/heaps/heap-helpers.c @@ -140,13 +140,12 @@ struct sg_table *dma_heap_map_dma_buf(struct dma_buf_attachment *attachment, enum dma_data_direction direction) { struct dma_heaps_attachment *a = attachment->priv; - struct sg_table *table; - - table = &a->table; + struct sg_table *table = &a->table; + int ret;

- if (!dma_map_sg(attachment->dev, table->sgl, table->nents, - direction)) - table = ERR_PTR(-ENOMEM); + ret = dma_map_sgtable(attachment->dev, table, direction, 0); + if (ret) + table = ERR_PTR(ret); return table; }

@@ -154,7 +153,7 @@ static void dma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment, struct sg_table *table, enum dma_data_direction direction) { - dma_unmap_sg(attachment->dev, table->sgl, table->nents, direction); + dma_unmap_sgtable(attachment->dev, table, direction, 0); }

static vm_fault_t dma_heap_vm_fault(struct vm_fault *vmf) diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index acb26c627d27..89e293bd9252 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -63,10 +63,9 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf, GFP_KERNEL); if (ret < 0) goto err; - if (!dma_map_sg(dev, sg->sgl, sg->nents, direction)) { - ret = -EINVAL; + ret = dma_map_sgtable(dev, sg, direction, 0); + if (ret < 0) goto err; - } return sg;

err: @@ -78,7 +77,7 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf, static void put_sg_table(struct device *dev, struct sg_table *sg, enum dma_data_direction direction) { - dma_unmap_sg(dev, sg->sgl, sg->nents, direction); + dma_unmap_sgtable(dev, sg, direction, 0); sg_free_table(sg); kfree(sg); }

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 --- drivers/staging/android/ion/ion.c | 25 +++++------ drivers/staging/android/ion/ion_heap.c | 44 ++++++------------- drivers/staging/android/ion/ion_system_heap.c | 2 +- 3 files changed, 25 insertions(+), 46 deletions(-)

diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c index 38b51eace4f9..3c9f09506ffa 100644 --- a/drivers/staging/android/ion/ion.c +++ b/drivers/staging/android/ion/ion.c @@ -147,14 +147,14 @@ static struct sg_table *dup_sg_table(struct sg_table *table) if (!new_table) return ERR_PTR(-ENOMEM);

- ret = sg_alloc_table(new_table, table->nents, GFP_KERNEL); + ret = sg_alloc_table(new_table, table->orig_nents, GFP_KERNEL); if (ret) { kfree(new_table); return ERR_PTR(-ENOMEM); }

new_sg = new_table->sgl; - for_each_sg(table->sgl, sg, table->nents, i) { + for_each_sgtable_sg(table, sg, i) { memcpy(new_sg, sg, sizeof(*sg)); new_sg->dma_address = 0; new_sg = sg_next(new_sg); @@ -224,12 +224,13 @@ static struct sg_table *ion_map_dma_buf(struct dma_buf_attachment *attachment, { struct ion_dma_buf_attachment *a = attachment->priv; struct sg_table *table; + int ret;

table = a->table;

- if (!dma_map_sg(attachment->dev, table->sgl, table->nents, - direction)) - return ERR_PTR(-ENOMEM); + ret = dma_map_sgtable(attachment->dev, table, direction, 0); + if (ret) + return ERR_PTR(ret);

return table; } @@ -238,7 +239,7 @@ static void ion_unmap_dma_buf(struct dma_buf_attachment *attachment, struct sg_table *table, enum dma_data_direction direction) { - dma_unmap_sg(attachment->dev, table->sgl, table->nents, direction); + dma_unmap_sgtable(attachment->dev, table, direction, 0); }

static int ion_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma) @@ -296,10 +297,8 @@ static int ion_dma_buf_begin_cpu_access(struct dma_buf *dmabuf, }

mutex_lock(&buffer->lock); - list_for_each_entry(a, &buffer->attachments, list) { - dma_sync_sg_for_cpu(a->dev, a->table->sgl, a->table->nents, - direction); - } + list_for_each_entry(a, &buffer->attachments, list) + dma_sync_sgtable_for_cpu(a->dev, a->table, direction);

unlock: mutex_unlock(&buffer->lock); @@ -319,10 +318,8 @@ static int ion_dma_buf_end_cpu_access(struct dma_buf *dmabuf, }

mutex_lock(&buffer->lock); - list_for_each_entry(a, &buffer->attachments, list) { - dma_sync_sg_for_device(a->dev, a->table->sgl, a->table->nents, - direction); - } + list_for_each_entry(a, &buffer->attachments, list) + dma_sync_sgtable_for_device(a->dev, a->table, direction); mutex_unlock(&buffer->lock);

return 0; diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c index 9c23b2382a1e..79f27949edda 100644 --- a/drivers/staging/android/ion/ion_heap.c +++ b/drivers/staging/android/ion/ion_heap.c @@ -20,8 +20,7 @@ void *ion_heap_map_kernel(struct ion_heap *heap, struct ion_buffer *buffer) { - struct scatterlist *sg; - int i, j; + struct sg_page_iter piter; void *vaddr; pgprot_t pgprot; struct sg_table *table = buffer->sg_table; @@ -38,14 +37,11 @@ void *ion_heap_map_kernel(struct ion_heap *heap, else pgprot = pgprot_writecombine(PAGE_KERNEL);

- for_each_sg(table->sgl, sg, table->nents, i) { - int npages_this_entry = PAGE_ALIGN(sg->length) / PAGE_SIZE; - struct page *page = sg_page(sg); - - BUG_ON(i >= npages); - for (j = 0; j < npages_this_entry; j++) - *(tmp++) = page++; + for_each_sgtable_page(table, &piter, 0) { + BUG_ON(tmp - pages >= npages); + *tmp++ = sg_page_iter_page(&piter); } + vaddr = vmap(pages, npages, VM_MAP, pgprot); vfree(pages);

@@ -64,32 +60,19 @@ void ion_heap_unmap_kernel(struct ion_heap *heap, int ion_heap_map_user(struct ion_heap *heap, struct ion_buffer *buffer, struct vm_area_struct *vma) { + struct sg_page_iter piter; struct sg_table *table = buffer->sg_table; unsigned long addr = vma->vm_start; - unsigned long offset = vma->vm_pgoff * PAGE_SIZE; - struct scatterlist *sg; - int i; int ret;

- for_each_sg(table->sgl, sg, table->nents, i) { - struct page *page = sg_page(sg); - unsigned long remainder = vma->vm_end - addr; - unsigned long len = sg->length; + for_each_sgtable_page(table, &piter, vma->vm_pgoff) { + struct page *page = sg_page_iter_page(&piter);

- if (offset >= sg->length) { - offset -= sg->length; - continue; - } else if (offset) { - page += offset / PAGE_SIZE; - len = sg->length - offset; - offset = 0; - } - len = min(len, remainder); - ret = remap_pfn_range(vma, addr, page_to_pfn(page), len, + ret = remap_pfn_range(vma, addr, page_to_pfn(page), PAGE_SIZE, vma->vm_page_prot); if (ret) return ret; - addr += len; + addr += PAGE_SIZE; if (addr >= vma->vm_end) return 0; } @@ -109,15 +92,14 @@ static int ion_heap_clear_pages(struct page **pages, int num, pgprot_t pgprot) return 0; }

-static int ion_heap_sglist_zero(struct scatterlist *sgl, unsigned int nents, - pgprot_t pgprot) +static int ion_heap_sglist_zero(struct sg_table *sgt, pgprot_t pgprot) { int p = 0; int ret = 0; struct sg_page_iter piter; struct page *pages[32];

- for_each_sg_page(sgl, &piter, nents, 0) { + for_each_sgtable_page(sgt, &piter, 0) { pages[p++] = sg_page_iter_page(&piter); if (p == ARRAY_SIZE(pages)) { ret = ion_heap_clear_pages(pages, p, pgprot); @@ -142,7 +124,7 @@ int ion_heap_buffer_zero(struct ion_buffer *buffer) else pgprot = pgprot_writecombine(PAGE_KERNEL);

- return ion_heap_sglist_zero(table->sgl, table->nents, pgprot); + return ion_heap_sglist_zero(table, pgprot); }

void ion_heap_freelist_add(struct ion_heap *heap, struct ion_buffer *buffer) diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c index b83a1d16bd89..eac0632ab4e8 100644 --- a/drivers/staging/android/ion/ion_system_heap.c +++ b/drivers/staging/android/ion/ion_system_heap.c @@ -162,7 +162,7 @@ static void ion_system_heap_free(struct ion_buffer *buffer) if (!(buffer->private_flags & ION_PRIV_FLAG_SHRINKER_FREE)) ion_heap_buffer_zero(buffer);

- for_each_sg(table->sgl, sg, table->nents, i) + for_each_sgtable_sg(table, sg, i) free_buffer_page(sys_heap, buffer, sg_page(sg)); sg_free_table(table); kfree(table);

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 --- drivers/misc/fastrpc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 7939c55daceb..9d6867749316 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -518,7 +518,7 @@ fastrpc_map_dma_buf(struct dma_buf_attachment *attachment,

table = &a->sgt;

- if (!dma_map_sg(attachment->dev, table->sgl, table->nents, dir)) + if (!dma_map_sgtable(attachment->dev, table, dir, 0)) return ERR_PTR(-ENOMEM);

return table; @@ -528,7 +528,7 @@ static void fastrpc_unmap_dma_buf(struct dma_buf_attachment *attach, struct sg_table *table, enum dma_data_direction dir) { - dma_unmap_sg(attach->dev, table->sgl, table->nents, dir); + dma_unmap_sgtable(attach->dev, table, dir, 0); }

static void fastrpc_release(struct dma_buf *dmabuf)

The Documentation/DMA-API-HOWTO.txt states that dma_map_sg returns the numer of the created entries in the DMA address space. However the subsequent calls to dma_sync_sg_for_{device,cpu} and dma_unmap_sg must be called with the original number of entries passed to dma_map_sg. The sg_table->nents in turn holds the result of the dma_map_sg call as stated in include/linux/scatterlist.h. Adapt the code to obey those rules.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com --- drivers/media/pci/cx23885/cx23885-alsa.c | 2 +- drivers/media/pci/cx25821/cx25821-alsa.c | 2 +- drivers/media/pci/cx88/cx88-alsa.c | 2 +- drivers/media/pci/saa7134/saa7134-alsa.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/media/pci/cx23885/cx23885-alsa.c b/drivers/media/pci/cx23885/cx23885-alsa.c index df44ed7393a0..3f366e4e4685 100644 --- a/drivers/media/pci/cx23885/cx23885-alsa.c +++ b/drivers/media/pci/cx23885/cx23885-alsa.c @@ -129,7 +129,7 @@ static int cx23885_alsa_dma_unmap(struct cx23885_audio_dev *dev) if (!buf->sglen) return 0;

- dma_unmap_sg(&dev->pci->dev, buf->sglist, buf->sglen, PCI_DMA_FROMDEVICE); + dma_unmap_sg(&dev->pci->dev, buf->sglist, buf->nr_pages, PCI_DMA_FROMDEVICE); buf->sglen = 0; return 0; } diff --git a/drivers/media/pci/cx25821/cx25821-alsa.c b/drivers/media/pci/cx25821/cx25821-alsa.c index 301616426d8a..c40304d33776 100644 --- a/drivers/media/pci/cx25821/cx25821-alsa.c +++ b/drivers/media/pci/cx25821/cx25821-alsa.c @@ -193,7 +193,7 @@ static int cx25821_alsa_dma_unmap(struct cx25821_audio_dev *dev) if (!buf->sglen) return 0;

- dma_unmap_sg(&dev->pci->dev, buf->sglist, buf->sglen, PCI_DMA_FROMDEVICE); + dma_unmap_sg(&dev->pci->dev, buf->sglist, buf->nr_pages, PCI_DMA_FROMDEVICE); buf->sglen = 0; return 0; } diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c index 7d7aceecc985..3c6fe6ceb0b7 100644 --- a/drivers/media/pci/cx88/cx88-alsa.c +++ b/drivers/media/pci/cx88/cx88-alsa.c @@ -332,7 +332,7 @@ static int cx88_alsa_dma_unmap(struct cx88_audio_dev *dev) if (!buf->sglen) return 0;

- dma_unmap_sg(&dev->pci->dev, buf->sglist, buf->sglen, + dma_unmap_sg(&dev->pci->dev, buf->sglist, buf->nr_pages, PCI_DMA_FROMDEVICE); buf->sglen = 0; return 0; diff --git a/drivers/media/pci/saa7134/saa7134-alsa.c b/drivers/media/pci/saa7134/saa7134-alsa.c index 544ca57eee75..398c47ff473d 100644 --- a/drivers/media/pci/saa7134/saa7134-alsa.c +++ b/drivers/media/pci/saa7134/saa7134-alsa.c @@ -313,7 +313,7 @@ static int saa7134_alsa_dma_unmap(struct saa7134_dev *dev) if (!dma->sglen) return 0;

- dma_unmap_sg(&dev->pci->dev, dma->sglist, dma->sglen, PCI_DMA_FROMDEVICE); + dma_unmap_sg(&dev->pci->dev, dma->sglist, dma->nr_pages, PCI_DMA_FROMDEVICE); dma->sglen = 0; return 0; }