[PATCH 11/98] block: check dma alignment of bvec iters in async dio

[Jens Axboe <axboe@kernel.dk>]

From: Josef Bacik <josef@toxicpanda.com>

__blkdev_direct_IO_async() uses bio_iov_iter_set() for an ITER_BVEC
iterator and never gets to the alignment check in
bio_iov_iter_get_pages(), which is the one that exists for io_uring
registered buffers in the first place. A bio based driver has nobody
else to enforce its DMA alignment: a misaligned READ_FIXED from brd
returns the wrong data, and dm-verity with panic_on_error panics.

Move bio_iov_bvec_aligned() to blk.h and check in the async path too,
failing with -EINVAL like the other direct IO paths.

Fixes: 5ff3f74e145a ("block: simplify direct io validity check")
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c  | 33 ---------------------------------
 block/blk.h  | 33 +++++++++++++++++++++++++++++++++
 block/fops.c | 10 ++++++++--
 3 files changed, 41 insertions(+), 35 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 06f805d3866a..57d84ca7170f 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1272,39 +1272,6 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
 	return 0;
 }
 
-#ifdef CONFIG_DEBUG_KERNEL
-static inline bool bio_iov_bvec_aligned(const struct bio *bio,
-					unsigned mem_align_mask)
-{
-	struct bvec_iter iter;
-	struct bio_vec bv;
-
-	/*
-	 * Correct callers never break the alignment requirements, so this
-	 * exhaustive check is only paid for in debug builds.
-	 */
-	for_each_mp_bvec(bv, bio->bi_io_vec, iter, bio->bi_iter)
-		if ((bv.bv_offset | bv.bv_len) & mem_align_mask)
-			return false;
-	return true;
-}
-#else
-static inline bool bio_iov_bvec_aligned(const struct bio *bio,
-					unsigned mem_align_mask)
-{
-	/*
-	 * We forward the bio_vec as-is, so ITER_BVEC callers must provide
-	 * segments already aligned to the device's DMA alignment. The only
-	 * unchecked user-controllable offset that reaches here is an io_uring
-	 * registered buffer where just the first segment can be unaligned
-	 * (the rest is virtually contiguous), so checking only that one is
-	 * sufficient to know if the entire vector is valid.
-	 */
-	return !(mp_bvec_iter_offset(bio->bi_io_vec, bio->bi_iter) &
-							mem_align_mask);
-}
-#endif
-
 /**
  * bio_iov_iter_get_pages - add user or kernel pages to a bio
  * @bio: bio to add pages to
diff --git a/block/blk.h b/block/blk.h
index 2cc03aa54c53..a48665e10994 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -202,6 +202,39 @@ static inline bool rq_mergeable(struct request *rq)
 	return true;
 }
 
+#ifdef CONFIG_DEBUG_KERNEL
+static inline bool bio_iov_bvec_aligned(const struct bio *bio,
+					unsigned int mem_align_mask)
+{
+	struct bvec_iter iter;
+	struct bio_vec bv;
+
+	/*
+	 * Correct callers never break the alignment requirements, so this
+	 * exhaustive check is only paid for in debug builds.
+	 */
+	for_each_mp_bvec(bv, bio->bi_io_vec, iter, bio->bi_iter)
+		if ((bv.bv_offset | bv.bv_len) & mem_align_mask)
+			return false;
+	return true;
+}
+#else
+static inline bool bio_iov_bvec_aligned(const struct bio *bio,
+					unsigned int mem_align_mask)
+{
+	/*
+	 * We forward the bio_vec as-is, so ITER_BVEC callers must provide
+	 * segments already aligned to the device's DMA alignment. The only
+	 * unchecked user-controllable offset that reaches here is an io_uring
+	 * registered buffer where just the first segment can be unaligned
+	 * (the rest is virtually contiguous), so checking only that one is
+	 * sufficient to know if the entire vector is valid.
+	 */
+	return !(mp_bvec_iter_offset(bio->bi_io_vec, bio->bi_iter) &
+							mem_align_mask);
+}
+#endif
+
 /*
  * There are two different ways to handle DISCARD merges:
  *  1) If max_discard_segments > 1, the driver treats every bio as a range and
diff --git a/block/fops.c b/block/fops.c
index 375ec2c15926..dfeac910f126 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -365,9 +365,15 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	 * Users don't rely on the iterator being in any particular
 	 * state for async I/O returning -EIOCBQUEUED, hence we can
 	 * avoid expensive iov_iter_advance(). Bypass
-	 * bio_iov_iter_get_pages() and set the bvec directly.
+	 * bio_iov_iter_get_pages() and set the bvec directly, which leaves
+	 * its alignment check to us.
 	 */
-	if (!bio_iov_iter_set(bio, iter)) {
+	if (bio_iov_iter_set(bio, iter)) {
+		if (!bio_iov_bvec_aligned(bio, bdev_dma_alignment(bdev))) {
+			ret = -EINVAL;
+			goto out_bio_put;
+		}
+	} else {
 		ret = blkdev_iov_iter_get_pages(bio, iter, bdev);
 		if (unlikely(ret))
 			goto out_bio_put;
-- 
2.56.0