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]>
---
For more information, see '[PATCH v5 00/38] DRM: fix struct sg_table nents
vs. orig_nents misuse' thread:
https://lore.kernel.org/linux-iommu/[email protected]/T/
---
drivers/gpu/drm/lima/lima_gem.c | 11 ++++++++---
drivers/gpu/drm/lima/lima_vm.c | 5 ++---
2 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c
index 5404e0d..cda43f6 100644
--- a/drivers/gpu/drm/lima/lima_gem.c
+++ b/drivers/gpu/drm/lima/lima_gem.c
@@ -69,8 +69,7 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm)
return ret;
if (bo->base.sgt) {
- dma_unmap_sg(dev, bo->base.sgt->sgl,
- bo->base.sgt->nents, DMA_BIDIRECTIONAL);
+ dma_unmap_sgtable(dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0);
sg_free_table(bo->base.sgt);
} else {
bo->base.sgt = kmalloc(sizeof(*bo->base.sgt), GFP_KERNEL);
@@ -80,7 +79,13 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm)
}
}
- dma_map_sg(dev, sgt.sgl, sgt.nents, DMA_BIDIRECTIONAL);
+ ret = dma_map_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0);
+ if (ret) {
+ sg_free_table(&sgt);
+ kfree(bo->base.sgt);
+ bo->base.sgt = NULL;
+ return ret;
+ }
*bo->base.sgt = sgt;
diff --git a/drivers/gpu/drm/lima/lima_vm.c b/drivers/gpu/drm/lima/lima_vm.c
index 5b92fb8..2b2739a 100644
--- a/drivers/gpu/drm/lima/lima_vm.c
+++ b/drivers/gpu/drm/lima/lima_vm.c
@@ -124,7 +124,7 @@ int lima_vm_bo_add(struct lima_vm *vm, struct lima_bo *bo, bool create)
if (err)
goto err_out1;
- for_each_sg_dma_page(bo->base.sgt->sgl, &sg_iter, bo->base.sgt->nents, 0) {
+ for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, 0) {
err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter),
bo_va->node.start + offset);
if (err)
@@ -298,8 +298,7 @@ int lima_vm_map_bo(struct lima_vm *vm, struct lima_bo *bo, int pageoff)
mutex_lock(&vm->lock);
base = bo_va->node.start + (pageoff << PAGE_SHIFT);
- for_each_sg_dma_page(bo->base.sgt->sgl, &sg_iter,
- bo->base.sgt->nents, pageoff) {
+ for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, pageoff) {
err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter),
base + offset);
if (err)
--
1.9.1
Looks good for me, patch is:
Reviewed-by: Qiang Yu <[email protected]>
Regards,
Qiang
On Wed, May 13, 2020 at 9:33 PM Marek Szyprowski
<[email protected]> 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]>
> ---
> For more information, see '[PATCH v5 00/38] DRM: fix struct sg_table nents
> vs. orig_nents misuse' thread:
> https://lore.kernel.org/linux-iommu/[email protected]/T/
> ---
> drivers/gpu/drm/lima/lima_gem.c | 11 ++++++++---
> drivers/gpu/drm/lima/lima_vm.c | 5 ++---
> 2 files changed, 10 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c
> index 5404e0d..cda43f6 100644
> --- a/drivers/gpu/drm/lima/lima_gem.c
> +++ b/drivers/gpu/drm/lima/lima_gem.c
> @@ -69,8 +69,7 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm)
> return ret;
>
> if (bo->base.sgt) {
> - dma_unmap_sg(dev, bo->base.sgt->sgl,
> - bo->base.sgt->nents, DMA_BIDIRECTIONAL);
> + dma_unmap_sgtable(dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0);
> sg_free_table(bo->base.sgt);
> } else {
> bo->base.sgt = kmalloc(sizeof(*bo->base.sgt), GFP_KERNEL);
> @@ -80,7 +79,13 @@ int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm)
> }
> }
>
> - dma_map_sg(dev, sgt.sgl, sgt.nents, DMA_BIDIRECTIONAL);
> + ret = dma_map_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0);
> + if (ret) {
> + sg_free_table(&sgt);
> + kfree(bo->base.sgt);
> + bo->base.sgt = NULL;
> + return ret;
> + }
>
> *bo->base.sgt = sgt;
>
> diff --git a/drivers/gpu/drm/lima/lima_vm.c b/drivers/gpu/drm/lima/lima_vm.c
> index 5b92fb8..2b2739a 100644
> --- a/drivers/gpu/drm/lima/lima_vm.c
> +++ b/drivers/gpu/drm/lima/lima_vm.c
> @@ -124,7 +124,7 @@ int lima_vm_bo_add(struct lima_vm *vm, struct lima_bo *bo, bool create)
> if (err)
> goto err_out1;
>
> - for_each_sg_dma_page(bo->base.sgt->sgl, &sg_iter, bo->base.sgt->nents, 0) {
> + for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, 0) {
> err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter),
> bo_va->node.start + offset);
> if (err)
> @@ -298,8 +298,7 @@ int lima_vm_map_bo(struct lima_vm *vm, struct lima_bo *bo, int pageoff)
> mutex_lock(&vm->lock);
>
> base = bo_va->node.start + (pageoff << PAGE_SHIFT);
> - for_each_sg_dma_page(bo->base.sgt->sgl, &sg_iter,
> - bo->base.sgt->nents, pageoff) {
> + for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, pageoff) {
> err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter),
> base + offset);
> if (err)
> --
> 1.9.1
>