md/raid10: free r10bio before ending master_bio in raid_end_bio_io() and raid_end_discard_bio()

origin flow:

      bio_endio(master_bio);   /* may drop active_io to zero */
      allow_barrier(conf);
      free_r10bio(r10_bio);    /* reads conf->geo, returns to pool */

one scenario is:

  CPU A (softirq, raid_end_bio_io)         CPU B (action_store) --> reshape
  ================================         ===============================
  bio_endio(master_bio)
    md_end_clone_io
      percpu_ref_put -> 0
                                           wait_event wakeup, and,
                                           	mddev_suspend return
                                           raid10_start_reshape:
                                             setup_geo(&conf->geo, new)
                                             ...
                                             mempool_destroy(old_pool)
                                             conf->r10bio_pool = new_pool
  allow_barrier(conf)
  free_r10bio(r10_bio)
    put_all_bios:
      for (i=0; i<conf->geo.raid_disks; i++)
          ==> old obj, new geo, OOB
    mempool_free(r10_bio, conf->r10bio_pool)
          ==> old-geometry obj freed into new pool

so .. fix by reorder the flow:

	free_r10bio(r10_bio)
	bio_endio(master_bio)
	allow_barrier(conf)

raid_end_discard_bio() is exactly the same.

Signed-off-by: Chen Cheng <chencheng@fnnas.com>
Link: https://patch.msgid.link/20260711100352.425177-4-chencheng@fnnas.com
Signed-off-by: Yu Kuai <yukuai@fygo.io>
This commit is contained in:
Chen Cheng
2026-07-11 18:03:52 +08:00
committed by Yu Kuai
parent 8e9171decb
commit fe8d6b0187

View File

@@ -331,20 +331,24 @@ static void raid_end_bio_io(struct r10bio *r10_bio)
{
struct bio *bio = r10_bio->master_bio;
struct r10conf *conf = r10_bio->mddev->private;
bool returned = true;
if (!test_and_set_bit(R10BIO_Returned, &r10_bio->state)) {
if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
returned = false;
}
free_r10bio(r10_bio);
if (!returned)
bio_endio(bio);
/*
* Wake up any possible resync thread that waits for the device
* to go idle.
*/
allow_barrier(conf);
free_r10bio(r10_bio);
}
/*
@@ -1537,9 +1541,11 @@ static void raid_end_discard_bio(struct r10bio *r10bio)
free_r10bio(r10bio);
r10bio = first_r10bio;
} else {
struct bio *master_bio = r10bio->master_bio;
md_write_end(r10bio->mddev);
bio_endio(r10bio->master_bio);
free_r10bio(r10bio);
bio_endio(master_bio);
break;
}
}