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 <[email protected]>
---
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));
}
--
2.17.1
On 2020-08-26 07:32, Marek Szyprowski wrote:
> 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 <[email protected]>
> ---
> 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;
I think it might be even nicer to get rid of "num" entirely and convert
the cleanup path to for_each_sgtable_sg() for completeness - AFAICS it
should only need an extra "if (sg_page(sg))..." check in that loop. Then
"count" could possibly be squashed into its one remaining use as well,
but maybe it's worth keeping for readability.
Robin.
> 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));
> }
>
>