From: Keith Busch <kbusch@xxxxxxxxxx>
Use the address alignment requirements from the block_device for direct
io instead of requiring addresses be aligned to the block size. User
space can discover the alignment requirements from the dma_alignment
queue attribute.
User space can specify any hardware compatible DMA offset for each
segment, but every segment length is still required to be a multiple of
the block size.
Signed-off-by: Keith Busch <kbusch@xxxxxxxxxx>
---
block/bio.c | 9 +++++++++
block/fops.c | 4 ++--
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/block/bio.c b/block/bio.c
index 55d2a9c4e312..44658aa57784 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1219,7 +1219,16 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
+ /*
+ * Each segment in the iov is required to be a block size multiple.
+ * However, we may not be able to get the entire segment if it spans
+ * more pages than bi_max_vecs allows, so we have to ALIGN_DOWN the
+ * result to ensure the bio's total size is correct. The remainder of
+ * the iov data will be picked up in the next bio iteration.
+ */
size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+ if (size > 0)
+ size = ALIGN_DOWN(size, bdev_logical_block_size(bio->bi_bdev));
if (unlikely(size <= 0))
return size ? size : -EFAULT;
diff --git a/block/fops.c b/block/fops.c
index 5aec9a130812..7a02b75009bb 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -45,8 +45,8 @@ static unsigned int dio_bio_write_op(struct kiocb *iocb)
static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
struct iov_iter *iter)
{
- return ((pos | iov_iter_alignment(iter)) &
- (bdev_logical_block_size(bdev) - 1));
+ return pos & (bdev_logical_block_size(bdev) - 1) ||
+ !bvev_iter_is_aligned(bdev, iter);
}
#define DIO_INLINE_BIO_VECS 4
--
2.30.2
