From: Xiao Ni <xni@xxxxxxxxxx> commit 46d4703b1db4c86ab5acb2331b10df999f005e8e upstream. We are seeing the following warning in raid10_handle_discard. [ 695.110751] ============================= [ 695.131439] WARNING: suspicious RCU usage [ 695.151389] 4.18.0-319.el8.x86_64+debug #1 Not tainted [ 695.174413] ----------------------------- [ 695.192603] drivers/md/raid10.c:1776 suspicious rcu_dereference_check() usage! [ 695.225107] other info that might help us debug this: [ 695.260940] rcu_scheduler_active = 2, debug_locks = 1 [ 695.290157] no locks held by mkfs.xfs/10186. In the first loop of function raid10_handle_discard. It already determines which disk need to handle discard request and add the rdev reference count rdev->nr_pending. So the conf->mirrors will not change until all bios come back from underlayer disks. It doesn't need to use rcu_dereference to get rdev. Cc: stable@xxxxxxxxxxxxxxx Fixes: d30588b2731f ('md/raid10: improve raid10 discard request') Signed-off-by: Xiao Ni <xni@xxxxxxxxxx> Acked-by: Guoqing Jiang <guoqing.jiang@xxxxxxxxx> Signed-off-by: Song Liu <songliubraving@xxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/md/raid10.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1712,6 +1712,11 @@ retry_discard: } else r10_bio->master_bio = (struct bio *)first_r10bio; + /* + * first select target devices under rcu_lock and + * inc refcount on their rdev. Record them by setting + * bios[x] to bio + */ rcu_read_lock(); for (disk = 0; disk < geo->raid_disks; disk++) { struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); @@ -1743,9 +1748,6 @@ retry_discard: for (disk = 0; disk < geo->raid_disks; disk++) { sector_t dev_start, dev_end; struct bio *mbio, *rbio = NULL; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[disk].rdev); - struct md_rdev *rrdev = rcu_dereference( - conf->mirrors[disk].replacement); /* * Now start to calculate the start and end address for each disk. @@ -1775,9 +1777,12 @@ retry_discard: /* * It only handles discard bio which size is >= stripe size, so - * dev_end > dev_start all the time + * dev_end > dev_start all the time. + * It doesn't need to use rcu lock to get rdev here. We already + * add rdev->nr_pending in the first loop. */ if (r10_bio->devs[disk].bio) { + struct md_rdev *rdev = conf->mirrors[disk].rdev; mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); mbio->bi_end_io = raid10_end_discard_request; mbio->bi_private = r10_bio; @@ -1790,6 +1795,7 @@ retry_discard: bio_endio(mbio); } if (r10_bio->devs[disk].repl_bio) { + struct md_rdev *rrdev = conf->mirrors[disk].replacement; rbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set); rbio->bi_end_io = raid10_end_discard_request; rbio->bi_private = r10_bio;