* [PATCH v4 1/2] file-posix: probe discard alignment on Linux block devices
2025-04-17 15:05 [PATCH v4 0/2] block: discard alignment fixes Stefan Hajnoczi
@ 2025-04-17 15:05 ` Stefan Hajnoczi
2025-04-17 15:05 ` [PATCH v4 2/2] block/io: skip head/tail requests on EINVAL Stefan Hajnoczi
2025-04-25 14:42 ` [PATCH v4 0/2] block: discard alignment fixes Kevin Wolf
2 siblings, 0 replies; 4+ messages in thread
From: Stefan Hajnoczi @ 2025-04-17 15:05 UTC (permalink / raw)
To: qemu-devel
Cc: qemu-block, Stefan Hajnoczi, Fam Zheng, Hanna Reitz, Kevin Wolf
Populate the pdiscard_alignment block limit so the block layer is able
align discard requests correctly.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
block/file-posix.c | 67 +++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 66 insertions(+), 1 deletion(-)
diff --git a/block/file-posix.c b/block/file-posix.c
index 56d1972d15..0d6e12f880 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -1276,10 +1276,10 @@ static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned)
}
#endif /* defined(CONFIG_BLKZONED) */
+#ifdef CONFIG_LINUX
/*
* Get a sysfs attribute value as a long integer.
*/
-#ifdef CONFIG_LINUX
static long get_sysfs_long_val(struct stat *st, const char *attribute)
{
g_autofree char *str = NULL;
@@ -1299,6 +1299,30 @@ static long get_sysfs_long_val(struct stat *st, const char *attribute)
}
return ret;
}
+
+/*
+ * Get a sysfs attribute value as a uint32_t.
+ */
+static int get_sysfs_u32_val(struct stat *st, const char *attribute,
+ uint32_t *u32)
+{
+ g_autofree char *str = NULL;
+ const char *end;
+ unsigned int val;
+ int ret;
+
+ ret = get_sysfs_str_val(st, attribute, &str);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* The file is ended with '\n', pass 'end' to accept that. */
+ ret = qemu_strtoui(str, &end, 10, &val);
+ if (ret == 0 && end && *end == '\0') {
+ *u32 = val;
+ }
+ return ret;
+}
#endif
static int hdev_get_max_segments(int fd, struct stat *st)
@@ -1318,6 +1342,23 @@ static int hdev_get_max_segments(int fd, struct stat *st)
#endif
}
+/*
+ * Fills in *dalign with the discard alignment and returns 0 on success,
+ * -errno otherwise.
+ */
+static int hdev_get_pdiscard_alignment(struct stat *st, uint32_t *dalign)
+{
+#ifdef CONFIG_LINUX
+ /*
+ * Note that Linux "discard_granularity" is QEMU "discard_alignment". Linux
+ * "discard_alignment" is something else.
+ */
+ return get_sysfs_u32_val(st, "discard_granularity", dalign);
+#else
+ return -ENOTSUP;
+#endif
+}
+
#if defined(CONFIG_BLKZONED)
/*
* If the reset_all flag is true, then the wps of zone whose state is
@@ -1527,6 +1568,30 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
}
}
+ if (S_ISBLK(st.st_mode)) {
+ uint32_t dalign = 0;
+ int ret;
+
+ ret = hdev_get_pdiscard_alignment(&st, &dalign);
+ if (ret == 0) {
+ uint32_t ralign = bs->bl.request_alignment;
+
+ /* Probably never happens, but handle it just in case */
+ if (dalign < ralign && (ralign % dalign == 0)) {
+ dalign = ralign;
+ }
+
+ /* The block layer requires a multiple of request_alignment */
+ if (dalign % ralign != 0) {
+ error_setg(errp, "Invalid pdiscard_alignment limit %u is not a "
+ "multiple of request_alignment %u", dalign, ralign);
+ return;
+ }
+
+ bs->bl.pdiscard_alignment = dalign;
+ }
+ }
+
raw_refresh_zoned_limits(bs, &st, errp);
}
--
2.49.0
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH v4 2/2] block/io: skip head/tail requests on EINVAL
2025-04-17 15:05 [PATCH v4 0/2] block: discard alignment fixes Stefan Hajnoczi
2025-04-17 15:05 ` [PATCH v4 1/2] file-posix: probe discard alignment on Linux block devices Stefan Hajnoczi
@ 2025-04-17 15:05 ` Stefan Hajnoczi
2025-04-25 14:42 ` [PATCH v4 0/2] block: discard alignment fixes Kevin Wolf
2 siblings, 0 replies; 4+ messages in thread
From: Stefan Hajnoczi @ 2025-04-17 15:05 UTC (permalink / raw)
To: qemu-devel
Cc: qemu-block, Stefan Hajnoczi, Fam Zheng, Hanna Reitz, Kevin Wolf
When guests send misaligned discard requests, the block layer breaks
them up into a misaligned head, an aligned main body, and a misaligned
tail.
The file-posix block driver on Linux returns -EINVAL on misaligned
discard requests. This causes bdrv_co_pdiscard() to fail and guests
configured with werror=stop will pause.
Add a special case for misaligned head/tail requests. Simply continue
when EINVAL is encountered so that the aligned main body of the request
can be completed and the guest is not paused. This is the best we can do
when guest discard limits do not match the host discard limits.
Fixes: https://issues.redhat.com/browse/RHEL-86032
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Hanna Czenczek <hreitz@redhat.com>
---
block/io.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/block/io.c b/block/io.c
index 1ba8d1aeea..ccec11386b 100644
--- a/block/io.c
+++ b/block/io.c
@@ -3109,11 +3109,12 @@ int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset,
/* Invalidate the cached block-status data range if this discard overlaps */
bdrv_bsc_invalidate_range(bs, offset, bytes);
- /* Discard is advisory, but some devices track and coalesce
+ /*
+ * Discard is advisory, but some devices track and coalesce
* unaligned requests, so we must pass everything down rather than
- * round here. Still, most devices will just silently ignore
- * unaligned requests (by returning -ENOTSUP), so we must fragment
- * the request accordingly. */
+ * round here. Still, most devices reject unaligned requests with
+ * -EINVAL or -ENOTSUP, so we must fragment the request accordingly.
+ */
align = MAX(bs->bl.pdiscard_alignment, bs->bl.request_alignment);
assert(align % bs->bl.request_alignment == 0);
head = offset % align;
@@ -3180,7 +3181,11 @@ int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset,
}
}
if (ret && ret != -ENOTSUP) {
- goto out;
+ if (ret == -EINVAL && (offset % align != 0 || num % align != 0)) {
+ /* Silently skip rejected unaligned head/tail requests */
+ } else {
+ goto out; /* bail out */
+ }
}
offset += num;
--
2.49.0
^ permalink raw reply related [flat|nested] 4+ messages in thread