On Wed, Apr 8, 2026 at 12:35 PM Benjamin Marzinski <[email protected]> wrote:
>
> If make_stripe_request() returns STRIPE_WAIT_RESHAPE,
> raid5_make_request() will free the cloned bio. But raid5_make_request()
> can call make_stripe_request() multiple times, writing to the various
> stripes. If that bio got added to the toread or towrite lists of a
> stripe disk in an earlier call to make_stripe_request(), then it's not
> safe to just free the bio if a later part of it is found to cross the
> reshape position. Doing so can lead to a UAF error, when bio_endio()
> is called on the bio for the earlier stripes.
>
> Instead, raid5_make_request() needs to wait until all parts of the bio
> have called bio_endio(). To do this, bios that cross the reshape
> position while the reshape can't make progress are flagged as needing to
> wait for all parts to complete. When raid5_make_request() has a bio that
> failed make_stripe_request() with STRIPE_WAIT_RESHAPE, it sets
> bi->bi_private to a completion struct and waits for completion after
> ending the bio.  When the bio_endio() is called for the last time on a
> clone bio with bi->bi_private set, it wakes up the waiter. This
> guarantees that raid5_make_request() doesn't return until the cloned bio
> needing a retry for io across the reshape boundary is safely cleaned up.
>
> There is a simple reproducer available at [1]. Compile the kernel with
> KASAN for more useful reporting when the error is triggered (this is not
> necessary to see the bug).
>
> [1] https://gist.github.com/bmarzins/e48598824305cf2171289e47d7241fa5
>
> Signed-off-by: Benjamin Marzinski <[email protected]>
> ---
>
> Changes from v1:
> - Removed mddev->pending_retry_bios, mddev->retry_bios_wait, and
>   md_io_clone->must_retry. Instead, use a completion struct
>   pointed to by bi->bi_private, as suggested by Xiao Ni and Yu Kuai.
>
>  drivers/md/md.c    | 31 ++++++++-----------------------
>  drivers/md/md.h    |  1 -
>  drivers/md/raid5.c |  7 ++++++-
>  3 files changed, 14 insertions(+), 25 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 3ce6f9e9d38e..4318d875a5f6 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -9215,9 +9215,11 @@ static void md_bitmap_end(struct mddev *mddev, struct 
> md_io_clone *md_io_clone)
>
>  static void md_end_clone_io(struct bio *bio)
>  {
> -       struct md_io_clone *md_io_clone = bio->bi_private;
> +       struct md_io_clone *md_io_clone = container_of(bio, struct 
> md_io_clone,
> +                                                      bio_clone);
>         struct bio *orig_bio = md_io_clone->orig_bio;
>         struct mddev *mddev = md_io_clone->mddev;
> +       struct completion *reshape_completion = bio->bi_private;
>
>         if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, 
> false))
>                 md_bitmap_end(mddev, md_io_clone);
> @@ -9229,7 +9231,10 @@ static void md_end_clone_io(struct bio *bio)
>                 bio_end_io_acct(orig_bio, md_io_clone->start_time);
>
>         bio_put(bio);
> -       bio_endio(orig_bio);
> +       if (unlikely(reshape_completion))
> +               complete(reshape_completion);
> +       else
> +               bio_endio(orig_bio);
>         percpu_ref_put(&mddev->active_io);
>  }
>
> @@ -9254,7 +9259,7 @@ static void md_clone_bio(struct mddev *mddev, struct 
> bio **bio)
>         }
>
>         clone->bi_end_io = md_end_clone_io;
> -       clone->bi_private = md_io_clone;
> +       clone->bi_private = NULL;
>         *bio = clone;
>  }
>
> @@ -9265,26 +9270,6 @@ void md_account_bio(struct mddev *mddev, struct bio 
> **bio)
>  }
>  EXPORT_SYMBOL_GPL(md_account_bio);
>
> -void md_free_cloned_bio(struct bio *bio)
> -{
> -       struct md_io_clone *md_io_clone = bio->bi_private;
> -       struct bio *orig_bio = md_io_clone->orig_bio;
> -       struct mddev *mddev = md_io_clone->mddev;
> -
> -       if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, 
> false))
> -               md_bitmap_end(mddev, md_io_clone);
> -
> -       if (bio->bi_status && !orig_bio->bi_status)
> -               orig_bio->bi_status = bio->bi_status;
> -
> -       if (md_io_clone->start_time)
> -               bio_end_io_acct(orig_bio, md_io_clone->start_time);
> -
> -       bio_put(bio);
> -       percpu_ref_put(&mddev->active_io);
> -}
> -EXPORT_SYMBOL_GPL(md_free_cloned_bio);
> -
>  /* md_allow_write(mddev)
>   * Calling this ensures that the array is marked 'active' so that writes
>   * may proceed without blocking.  It is important to call this before
> diff --git a/drivers/md/md.h b/drivers/md/md.h
> index ac84289664cd..5d57fee22901 100644
> --- a/drivers/md/md.h
> +++ b/drivers/md/md.h
> @@ -917,7 +917,6 @@ extern void md_finish_reshape(struct mddev *mddev);
>  void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
>                         struct bio *bio, sector_t start, sector_t size);
>  void md_account_bio(struct mddev *mddev, struct bio **bio);
> -void md_free_cloned_bio(struct bio *bio);
>
>  extern bool __must_check md_flush_request(struct mddev *mddev, struct bio 
> *bio);
>  void md_write_metadata(struct mddev *mddev, struct md_rdev *rdev,
> diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
> index a8e8d431071b..dc0c680ca199 100644
> --- a/drivers/md/raid5.c
> +++ b/drivers/md/raid5.c
> @@ -6217,7 +6217,12 @@ static bool raid5_make_request(struct mddev *mddev, 
> struct bio * bi)
>
>         mempool_free(ctx, conf->ctx_pool);
>         if (res == STRIPE_WAIT_RESHAPE) {
> -               md_free_cloned_bio(bi);
> +               DECLARE_COMPLETION_ONSTACK(done);
> +               WRITE_ONCE(bi->bi_private, &done);
> +
> +               bio_endio(bi);

Hi Ben

You gave an explanation why it doesn't need WRITE_ONCE. As you said,
bio_endio uses atomic_dec_and_test, so it guarantees a full memory
barrier. Why do you use WRITE_ONCE here?

Regards
Xiao


> +
> +               wait_for_completion(&done);
>                 return false;
>         }
>
> --
> 2.53.0
>


Reply via email to