Linux v6.1 commit 825cf206ed51 ("statx: add direct I/O alignment
information") added an interface to fetch O_DIRECT alignment values for
block devices and file systems.
Prefer STATX_DIOALIGN to older interfaces and probing, but keep them as
fallbacks in case STATX_DIOALIGN cannot provide the information.
STATX_DIOALIGN support as of Linux 6.1:
- btrfs: no
- ext4: yes
- XFS: yes
- block devices: yes
- dm-crypt: yes
This change fixes #1290 ("IO alignment probing delivers incorrect
results on Linux when used with e.g. dm-crypt") on Linux host kernel
version 6.1 or later by avoiding the problematic probing code in
raw_probe_alignment(). It would be nice to fix the probing code but I
have not been able to reproduce it. Stable/LTS distros ship Linux 6.1+,
so the number of users without STATX_DIOALIGN is becoming small.
Resolves: https://gitlab.com/qemu-project/qemu/-/work_items/1290
Cc: Eric Biggers <[email protected]>
Signed-off-by: Stefan Hajnoczi <[email protected]>
---
v3:
- Rebase and update commit description
v2:
- Make sure that XFS_IOC_DIOINFO takes priority over logical blocksize [Eric
Biggers]
---
block/file-posix.c | 56 +++++++++++++++++++++++++++++++---------------
1 file changed, 38 insertions(+), 18 deletions(-)
diff --git a/block/file-posix.c b/block/file-posix.c
index 9aad156aad4..0dedd090068 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -426,28 +426,48 @@ static void raw_probe_alignment(BlockDriverState *bs, int
fd, Error **errp)
bs->bl.request_alignment = 0;
s->buf_align = 0;
- /* Let's try to use the logical blocksize for the alignment. */
- if (probe_logical_blocksize(fd, &bs->bl.request_alignment) < 0) {
- bs->bl.request_alignment = 0;
+
+#if defined(__linux__) && defined(STATX_DIOALIGN)
+ struct statx stx;
+
+ /*
+ * Linux 6.1 introduced an interface for both block devices and file
+ * systems. The system call returns with the STATX_DIOALIGN bit cleared
+ * when the information is unavailable.
+ */
+ if (statx(fd, "", AT_EMPTY_PATH, STATX_DIOALIGN, &stx) == 0 &&
+ (stx.stx_mask & STATX_DIOALIGN)) {
+ bs->bl.request_alignment = stx.stx_dio_offset_align;
+ s->buf_align = stx.stx_dio_mem_align;
}
+#endif /* defined(__linux__) && defined(STATX_DIOALIGN) */
#ifdef __linux__
- /*
- * The XFS ioctl definitions are shipped in extra packages that might
- * not always be available. Since we just need the XFS_IOC_DIOINFO ioctl
- * here, we simply use our own definition instead:
- */
- struct xfs_dioattr {
- uint32_t d_mem;
- uint32_t d_miniosz;
- uint32_t d_maxiosz;
- } da;
- if (ioctl(fd, _IOR('X', 30, struct xfs_dioattr), &da) >= 0) {
- bs->bl.request_alignment = da.d_miniosz;
- /* The kernel returns wrong information for d_mem */
- /* s->buf_align = da.d_mem; */
+ if (!bs->bl.request_alignment) {
+ /*
+ * The XFS ioctl definitions are shipped in extra packages that might
+ * not always be available. Since we just need the XFS_IOC_DIOINFO
ioctl
+ * here, we simply use our own definition instead:
+ */
+ struct xfs_dioattr {
+ uint32_t d_mem;
+ uint32_t d_miniosz;
+ uint32_t d_maxiosz;
+ } da;
+ if (ioctl(fd, _IOR('X', 30, struct xfs_dioattr), &da) >= 0) {
+ bs->bl.request_alignment = da.d_miniosz;
+ /* The kernel returns wrong information for d_mem */
+ /* s->buf_align = da.d_mem; */
+ }
+ }
+#endif /* __linux__ */
+
+ /* Let's try to use the logical blocksize for the alignment. */
+ if (!bs->bl.request_alignment) {
+ if (probe_logical_blocksize(fd, &bs->bl.request_alignment) < 0) {
+ bs->bl.request_alignment = 0;
+ }
}
-#endif
/*
* If we could not get the sizes so far, we can only guess them. First try
--
2.55.0
