| Message ID | 20200826063316.23486-6-m.szyprowski@samsung.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [v9,01/32] drm: prime: add common helper to check scatterlist contiguity | expand |
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 <m.szyprowski@samsung.com> > --- > drivers/gpu/drm/etnaviv/etnaviv_gem.c | 12 +++++------- > drivers/gpu/drm/etnaviv/etnaviv_mmu.c | 13 +++---------- > 2 files changed, 8 insertions(+), 17 deletions(-) > > diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > index f06e19e7be04..eaf1949bc2e4 100644 > --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c > +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c > @@ -27,7 +27,7 @@ static void etnaviv_gem_scatter_map(struct etnaviv_gem_object *etnaviv_obj) > * because display controller, GPU, etc. are not coherent. > */ > if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK) > - dma_map_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); > + dma_map_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0); > } > > static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj) > @@ -51,7 +51,7 @@ static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj > * discard those writes. > */ > if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK) > - dma_unmap_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); > + dma_unmap_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0); > } > > /* called with etnaviv_obj->lock held */ > @@ -404,9 +404,8 @@ int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op, > } > > if (etnaviv_obj->flags & ETNA_BO_CACHED) { > - dma_sync_sg_for_cpu(dev->dev, etnaviv_obj->sgt->sgl, > - etnaviv_obj->sgt->nents, > - etnaviv_op_to_dma_dir(op)); > + dma_sync_sgtable_for_cpu(dev->dev, etnaviv_obj->sgt, > + etnaviv_op_to_dma_dir(op)); > etnaviv_obj->last_cpu_prep_op = op; > } > > @@ -421,8 +420,7 @@ int etnaviv_gem_cpu_fini(struct drm_gem_object *obj) > if (etnaviv_obj->flags & ETNA_BO_CACHED) { > /* fini without a prep is almost certainly a userspace error */ > WARN_ON(etnaviv_obj->last_cpu_prep_op == 0); > - dma_sync_sg_for_device(dev->dev, etnaviv_obj->sgt->sgl, > - etnaviv_obj->sgt->nents, > + dma_sync_sgtable_for_device(dev->dev, etnaviv_obj->sgt, > etnaviv_op_to_dma_dir(etnaviv_obj->last_cpu_prep_op)); > etnaviv_obj->last_cpu_prep_op = 0; > } > diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c > index 3607d348c298..13b100553a0b 100644 > --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c > +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c > @@ -79,7 +79,7 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova, > if (!context || !sgt) > return -EINVAL; > > - for_each_sg(sgt->sgl, sg, sgt->nents, i) { > + for_each_sgtable_dma_sg(sgt, sg, i) { > u32 pa = sg_dma_address(sg) - sg->offset; > size_t bytes = sg_dma_len(sg) + sg->offset; > > @@ -95,14 +95,7 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova, > return 0; > > fail: > - da = iova; > - > - for_each_sg(sgt->sgl, sg, i, j) { > - size_t bytes = sg_dma_len(sg) + sg->offset; > - > - etnaviv_context_unmap(context, da, bytes); > - da += bytes; > - } > + etnaviv_context_unmap(context, iova, da - iova); I had to take a closer look to figure this out, but AFAICS it does indeed work out as a simpler way of achieving the exact same result, and in fact neatly mirrors how etnaviv_context_map() itself cleans up. Reviewed-by: Robin Murphy <robin.murphy@arm.com> > return ret; > } > > @@ -113,7 +106,7 @@ static void etnaviv_iommu_unmap(struct etnaviv_iommu_context *context, u32 iova, > unsigned int da = iova; > int i; > > - for_each_sg(sgt->sgl, sg, sgt->nents, i) { > + for_each_sgtable_dma_sg(sgt, sg, i) { > size_t bytes = sg_dma_len(sg) + sg->offset; > > etnaviv_context_unmap(context, da, bytes); >
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index f06e19e7be04..eaf1949bc2e4 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -27,7 +27,7 @@ static void etnaviv_gem_scatter_map(struct etnaviv_gem_object *etnaviv_obj) * because display controller, GPU, etc. are not coherent. */ if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK) - dma_map_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); + dma_map_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0); } static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj) @@ -51,7 +51,7 @@ static void etnaviv_gem_scatterlist_unmap(struct etnaviv_gem_object *etnaviv_obj * discard those writes. */ if (etnaviv_obj->flags & ETNA_BO_CACHE_MASK) - dma_unmap_sg(dev->dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); + dma_unmap_sgtable(dev->dev, sgt, DMA_BIDIRECTIONAL, 0); } /* called with etnaviv_obj->lock held */ @@ -404,9 +404,8 @@ int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op, } if (etnaviv_obj->flags & ETNA_BO_CACHED) { - dma_sync_sg_for_cpu(dev->dev, etnaviv_obj->sgt->sgl, - etnaviv_obj->sgt->nents, - etnaviv_op_to_dma_dir(op)); + dma_sync_sgtable_for_cpu(dev->dev, etnaviv_obj->sgt, + etnaviv_op_to_dma_dir(op)); etnaviv_obj->last_cpu_prep_op = op; } @@ -421,8 +420,7 @@ int etnaviv_gem_cpu_fini(struct drm_gem_object *obj) if (etnaviv_obj->flags & ETNA_BO_CACHED) { /* fini without a prep is almost certainly a userspace error */ WARN_ON(etnaviv_obj->last_cpu_prep_op == 0); - dma_sync_sg_for_device(dev->dev, etnaviv_obj->sgt->sgl, - etnaviv_obj->sgt->nents, + dma_sync_sgtable_for_device(dev->dev, etnaviv_obj->sgt, etnaviv_op_to_dma_dir(etnaviv_obj->last_cpu_prep_op)); etnaviv_obj->last_cpu_prep_op = 0; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c index 3607d348c298..13b100553a0b 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c @@ -79,7 +79,7 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova, if (!context || !sgt) return -EINVAL; - for_each_sg(sgt->sgl, sg, sgt->nents, i) { + for_each_sgtable_dma_sg(sgt, sg, i) { u32 pa = sg_dma_address(sg) - sg->offset; size_t bytes = sg_dma_len(sg) + sg->offset; @@ -95,14 +95,7 @@ static int etnaviv_iommu_map(struct etnaviv_iommu_context *context, u32 iova, return 0; fail: - da = iova; - - for_each_sg(sgt->sgl, sg, i, j) { - size_t bytes = sg_dma_len(sg) + sg->offset; - - etnaviv_context_unmap(context, da, bytes); - da += bytes; - } + etnaviv_context_unmap(context, iova, da - iova); return ret; } @@ -113,7 +106,7 @@ static void etnaviv_iommu_unmap(struct etnaviv_iommu_context *context, u32 iova, unsigned int da = iova; int i; - for_each_sg(sgt->sgl, sg, sgt->nents, i) { + for_each_sgtable_dma_sg(sgt, sg, i) { size_t bytes = sg_dma_len(sg) + sg->offset; etnaviv_context_unmap(context, da, bytes);
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/etnaviv/etnaviv_gem.c | 12 +++++------- drivers/gpu/drm/etnaviv/etnaviv_mmu.c | 13 +++---------- 2 files changed, 8 insertions(+), 17 deletions(-)