| Message ID | c15119b9e8e18d96fbef6592fd7e827883c7bf59.1523977133.git.robin.murphy@arm.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Am 17.04.2018 um 17:58 schrieb Robin Murphy: > For dma_map_sg(), DMA API implementations are free to merge consecutive > segments into a single DMA mapping if conditions are suitable, thus the > resulting DMA addresses which drm_prime_sg_to_page_addr_arrays() > iterates may be packed into fewer entries than ttm->sg->nents implies. > > The current implementation does not account for this, meaning that its > callers either have to reject the 0 < count < nents case or risk getting > bogus DMA addresses beyond the first segment. Fortunately this is quite > easy to handle without having to rejig structures to also store the > mapped count, since the total DMA length should still be equal to the > total buffer length. All we need is a second scatterlist cursor to > iterate through the DMA addresses independently of the page addresses. > > Signed-off-by: Robin Murphy <robin.murphy@arm.com> Reviewed-by: Christian König <christian.koenig@amd.com> for the whole series. > --- > > v2: Remember to iterate dma_len correctly as well. > > drivers/gpu/drm/drm_prime.c | 15 ++++++++++++--- > 1 file changed, 12 insertions(+), 3 deletions(-) > > diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c > index 7856a9b3f8a8..b8ca06ea7d80 100644 > --- a/drivers/gpu/drm/drm_prime.c > +++ b/drivers/gpu/drm/drm_prime.c > @@ -933,16 +933,18 @@ int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages, > dma_addr_t *addrs, int max_entries) > { > unsigned count; > - struct scatterlist *sg; > + struct scatterlist *sg, *dma_sg; > struct page *page; > - u32 len, index; > + u32 len, dma_len, index; > dma_addr_t addr; > > index = 0; > + dma_sg = sgt->sgl; > + dma_len = sg_dma_len(dma_sg); > + addr = sg_dma_address(dma_sg); > for_each_sg(sgt->sgl, sg, sgt->nents, count) { > len = sg->length; > page = sg_page(sg); > - addr = sg_dma_address(sg); > > while (len > 0) { > if (WARN_ON(index >= max_entries)) > @@ -955,8 +957,15 @@ int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages, > page++; > addr += PAGE_SIZE; > len -= PAGE_SIZE; > + dma_len -= PAGE_SIZE; > index++; > } > + > + if (dma_len == 0) { > + dma_sg = sg_next(dma_sg); > + dma_len = sg_dma_len(dma_sg); > + addr = sg_dma_address(dma_sg); > + } > } > return 0; > }
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 7856a9b3f8a8..b8ca06ea7d80 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -933,16 +933,18 @@ int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages, dma_addr_t *addrs, int max_entries) { unsigned count; - struct scatterlist *sg; + struct scatterlist *sg, *dma_sg; struct page *page; - u32 len, index; + u32 len, dma_len, index; dma_addr_t addr; index = 0; + dma_sg = sgt->sgl; + dma_len = sg_dma_len(dma_sg); + addr = sg_dma_address(dma_sg); for_each_sg(sgt->sgl, sg, sgt->nents, count) { len = sg->length; page = sg_page(sg); - addr = sg_dma_address(sg); while (len > 0) { if (WARN_ON(index >= max_entries)) @@ -955,8 +957,15 @@ int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages, page++; addr += PAGE_SIZE; len -= PAGE_SIZE; + dma_len -= PAGE_SIZE; index++; } + + if (dma_len == 0) { + dma_sg = sg_next(dma_sg); + dma_len = sg_dma_len(dma_sg); + addr = sg_dma_address(dma_sg); + } } return 0; }
For dma_map_sg(), DMA API implementations are free to merge consecutive segments into a single DMA mapping if conditions are suitable, thus the resulting DMA addresses which drm_prime_sg_to_page_addr_arrays() iterates may be packed into fewer entries than ttm->sg->nents implies. The current implementation does not account for this, meaning that its callers either have to reject the 0 < count < nents case or risk getting bogus DMA addresses beyond the first segment. Fortunately this is quite easy to handle without having to rejig structures to also store the mapped count, since the total DMA length should still be equal to the total buffer length. All we need is a second scatterlist cursor to iterate through the DMA addresses independently of the page addresses. Signed-off-by: Robin Murphy <robin.murphy@arm.com> --- v2: Remember to iterate dma_len correctly as well. drivers/gpu/drm/drm_prime.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)