Re: [PATCH v4 1/7] md/raid10: fix r10bio leak in raid10_write_request() error paths

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] Allocation of `r10_bio` with `GFP_NOIO` can sleep, violating `REQ_NOWAIT` semantics.
- [High] Functions in the IO path (`wait_blocked_dev()` and `wait_barrier()`) sleep unconditionally, violating `REQ_NOWAIT` semantics.
--

--- Patch [1]: [PATCH v4 1/7] md/raid10: fix r10bio leak in raid10_write_request() error paths ---
commit d87114f7731cb53cc142eafbf2338e5b721f84ad
Author: Abd-Alrhman Masalkhi <[email protected]>

md/raid10: fix r10bio leak in raid10_write_request() error paths

When raid10_write_request() fails because REQ_NOWAIT is set, the
allocated r10_bio is not freed before returning, resulting in a memory
leak. Free r10_bio before returning from the REQ_NOWAIT error paths.

Closes: https://lore.kernel.org/linux-raid/[email protected]/

> diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
> index 0a3cfdd3f5df8..bd322eccdc3ff 100644
> --- a/drivers/md/raid10.c
> +++ b/drivers/md/raid10.c
> @@ -1365,6 +1365,7 @@ static bool raid10_write_request(struct mddev *mddev, struct bio *bio,
>  		/* Bail out if REQ_NOWAIT is set for the bio */
>  		if (bio->bi_opf & REQ_NOWAIT) {
>  			bio_wouldblock_error(bio);
> +			free_r10bio(r10_bio);
>  			return false;
>  		}

[Severity: High]
This isn't a bug introduced by this patch, but while looking at REQ_NOWAIT
handling, it appears the initial allocation of r10_bio in __make_request()
and raid10_handle_discard() ignores the REQ_NOWAIT flag.

Both functions call:

    r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);

Since GFP_NOIO includes __GFP_DIRECT_RECLAIM, this can sleep if the mempool
is depleted.

Could this violate the strict non-blocking guarantees of REQ_NOWAIT IO and
potentially starve async workers?

>  		for (;;) {

[ ... ]

> @@ -1398,6 +1399,7 @@ static bool raid10_write_request(struct mddev *mddev, struct bio *bio,
>  		if (bio->bi_opf & REQ_NOWAIT) {
>  			allow_barrier(conf);
>  			bio_wouldblock_error(bio);
> +			free_r10bio(r10_bio);
>  			return false;
>  		}

[Severity: High]
This is a pre-existing issue, but further down in the IO path, several
functions seem to sleep unconditionally even for REQ_NOWAIT bios.

For example, wait_blocked_dev() does:

    md_wait_for_blocked_rdev(blocked_rdev, mddev);
    wait_barrier(conf, false);
    goto retry_wait;

Also, in raid10_write_request() and raid10_read_request(), when a bio spans a
chunk boundary and is split, the code unconditionally blocks:

    allow_barrier(conf);
    bio = bio_submit_split_bioset(bio, max_sectors, &conf->bio_split);
    wait_barrier(conf, false);

Could these calls to wait_barrier(conf, false) and md_wait_for_blocked_rdev()
deadlock async submitters that rely on the non-blocking guarantee?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1