Hi
This approach is OK, I will stage the patches when 7.2-rc1 comes out and
when I'll fork the dm git branches.
I suggest one change - it is kind of hacky when multiple I/O completion
callbacks write into io->orig_bio->bi_status concurrently - so it would be
better to not do it and maintain and return separate bit mask for
non-retryable errors.
For example:
static void complete_io(struct io *io)
{
unsigned long error_bits = io->error_bits;
unsigned long nonretryable_error_bits = io->nonretryable_error_bits;
io_notify_fn fn = io->callback;
void *context = io->context;
if (io->vma_invalidate_size)
invalidate_kernel_vmap_range(io->vma_invalidate_address,
io->vma_invalidate_size);
mempool_free(io, &io->client->pool);
fn(error_bits, nonretryable_error_bits, context);
}
static void dec_count(struct io *io, unsigned int region, blk_status_t error)
{
if (unlikely(error == BLK_STS_NOTSUPP) || unlikely(error ==
BLK_STS_INVAL))
set_bit(region, &io->nonretryable_error_bits);
else if (unlikely(error != BLK_STS_OK))
set_bit(region, &io->error_bits);
if (atomic_dec_and_test(&io->count))
complete_io(io);
}
Please send the updated patch that uses this approach.
BTW. I think that blk_path_error should also test for BLK_STS_INVAL and
return false, otherwise, dm-multipath would be suffering from this bug
too. Ben, could you test it?
Mikulas
On Tue, 16 Jun 2026, Keith Busch wrote:
> BLK_STS_INVAL indicates the I/O request itself was invalid (for example a
> misaligned direct I/O), not that the device has failed. dm-raid1 treated
> any read or write completion error as a device failure: it failed the
> mirror leg, retried on the alternatives - which fail identically - and
> eventually returned EIO while spuriously degrading the array.
>
> Since commit 5ff3f74e145a ("block: simplify direct io validity check") the
> direct I/O path no longer rejects misaligned buffers up front, so an
> invalid bio now reaches the lower block layers, which fail it with
> BLK_STS_INVAL. dm-io collapses the block status into a per-region error
> bit before invoking the completion callback, so record BLK_STS_INVAL on
> the originating bio and have the dm-raid1 read, write and end_io paths
> propagate it instead of failing the device.
>
> This mirrors the raid1/raid10 fix in commit f7b24c7b41f23
> ("md/raid1,raid10: don't fail devices for invalid IO errors") for the
> device-mapper mirror target.
>
> Fixes: 7eac33186957 ("iomap: simplify direct io validity check")
> Fixes: 5ff3f74e145a ("block: simplify direct io validity check")
> Reported-by: Dr. David Alan Gilbert <[email protected]>
> Reported-by: Vjaceslavs Klimovs <[email protected]>
> Signed-off-by: Keith Busch <[email protected]>
> ---
> Resending patch 2/2 from a different machine. For some reason, only 1/2
> is getting through with git-send-email, so manually replying to the
> thread with the missing second patch.
>
> drivers/md/dm-io.c | 14 +++++++++++++-
> drivers/md/dm-raid1.c | 28 +++++++++++++++++++++++++++-
> 2 files changed, 40 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
> index 28adfeb58f240..f382e9f9be059 100644
> --- a/drivers/md/dm-io.c
> +++ b/drivers/md/dm-io.c
> @@ -37,6 +37,7 @@ struct io {
> struct dm_io_client *client;
> io_notify_fn callback;
> void *context;
> + struct bio *orig_bio;
> void *vma_invalidate_address;
> unsigned long vma_invalidate_size;
> } __aligned(DM_IO_MAX_REGIONS);
> @@ -132,8 +133,18 @@ static void complete_io(struct io *io)
>
> static void dec_count(struct io *io, unsigned int region, blk_status_t error)
> {
> - if (error)
> + if (error) {
> set_bit(region, &io->error_bits);
> + /*
> + * BLK_STS_INVAL means the bio was not valid for the underlying
> + * device (e.g. a misaligned direct I/O), which is a caller
> error
> + * rather than a device failure. Record it on the original bio
> so
> + * bio-based targets can propagate it instead of treating it as
> a
> + * media error and failing the device.
> + */
> + if (error == BLK_STS_INVAL && io->orig_bio)
> + io->orig_bio->bi_status = error;
> + }
>
> if (atomic_dec_and_test(&io->count))
> complete_io(io);
> @@ -398,6 +409,7 @@ static void async_io(struct dm_io_client *client,
> unsigned int num_regions,
> io->client = client;
> io->callback = fn;
> io->context = context;
> + io->orig_bio = dp->orig_bio;
>
> io->vma_invalidate_address = dp->vma_invalidate_address;
> io->vma_invalidate_size = dp->vma_invalidate_size;
> diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
> index de5c00704e69c..022ad791c2957 100644
> --- a/drivers/md/dm-raid1.c
> +++ b/drivers/md/dm-raid1.c
> @@ -524,6 +524,17 @@ static void read_callback(unsigned long error, void
> *context)
> return;
> }
>
> + /*
> + * BLK_STS_INVAL means the bio was not valid for the underlying device,
> + * e.g. a misaligned direct I/O. That is a caller error, not a device
> + * failure, so propagate it rather than failing the mirror and retrying
> + * on the other legs, which would fail the same way.
> + */
> + if (bio->bi_status == BLK_STS_INVAL) {
> + bio_endio(bio);
> + return;
> + }
> +
> fail_mirror(m, DM_RAID1_READ_ERROR);
>
> if (likely(default_ok(m)) || mirror_available(m->ms, bio)) {
> @@ -622,6 +633,16 @@ static void write_callback(unsigned long error, void
> *context)
> return;
> }
>
> + /*
> + * BLK_STS_INVAL means the bio was not valid for the underlying device,
> + * e.g. a misaligned direct I/O. Propagate the error without degrading
> + * the array.
> + */
> + if (bio->bi_status == BLK_STS_INVAL) {
> + bio_endio(bio);
> + return;
> + }
> +
> /*
> * If the bio is discard, return an error, but do not
> * degrade the array.
> @@ -1262,7 +1283,12 @@ static int mirror_end_io(struct dm_target *ti, struct
> bio *bio,
> return DM_ENDIO_DONE;
> }
>
> - if (*error == BLK_STS_NOTSUPP)
> + /*
> + * BLK_STS_INVAL means the bio was not valid for the underlying device,
> + * e.g. a misaligned direct I/O. Propagate it rather than failing the
> + * mirror and retrying, which would fail the same way on every leg.
> + */
> + if (*error == BLK_STS_NOTSUPP || *error == BLK_STS_INVAL)
> goto out;
>
> if (bio->bi_opf & REQ_RAHEAD)
> --
> 2.52.0
>
>
