From 2539d2c07fb8bc44a9a043b0696d3a027ec4d1df Mon Sep 17 00:00:00 2001
From: Xiao Ni <xni@redhat.com>
Date: Wed, 18 Aug 2021 13:57:48 +0800
Subject: [PATCH] md/raid10: Remove unnecessary rcu_dereference in raid10_handle_discard
Git-commit: 46d4703b1db4c86ab5acb2331b10df999f005e8e
Patch-mainline: v5.15-rc1
References: stable-5.14.4
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@vger.kernel.org
Fixes: d30588b2731f ('md/raid10: improve raid10 discard request')
Signed-off-by: Xiao Ni <xni@redhat.com>
Acked-by: Guoqing Jiang <guoqing.jiang@linux.dev>
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Takashi Iwai <tiwai@suse.de>
---
drivers/md/raid10.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 07119d7e0fdf..aa2636582841 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1712,6 +1712,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
} 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 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
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 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
/*
* 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 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
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;
--
2.26.2