From: Shaohua Li <shli@xxxxxx>
suspend range is controlled by userspace. If userspace doesn't clear suspend
range, it's possible a thread will wait for the range forever, we can't even
kill it. This is bad behavior. Add a timeout in the wait. If timeout happens,
we return IO error. The app controlling suspend range looks like part of disk
firmware, if disk isn't responded for a long time, timed out IO error is
returned.
A simple search in SCSI code shows maximum IO timeout is 120s, so I use this
value here too.
Cc: NeilBrown <neilb@xxxxxxxx>
Cc: Mikulas Patocka <mpatocka@xxxxxxxxxx>
Signed-off-by: Shaohua Li <shli@xxxxxx>
---
drivers/md/md.h | 1 +
drivers/md/raid1.c | 12 +++++++++++-
drivers/md/raid5.c | 10 +++++++++-
3 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 63d342d560b8..11a0ec33e79b 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -29,6 +29,7 @@
#define MaxSector (~(sector_t)0)
+#define MD_SUSPEND_TIMEOUT (120 * HZ)
/*
* These flags should really be called "NO_RETRY" rather than
* "FAILFAST" because they don't make any promise about time lapse,
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index d9e5373444d2..bc6dee0259df 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1326,6 +1326,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
(mddev_is_clustered(mddev) &&
md_cluster_ops->area_resyncing(mddev, WRITE,
bio->bi_iter.bi_sector, bio_end_sector(bio)))) {
+ long remaining = -1;
/*
* As the suspend_* range is controlled by userspace, we want
@@ -1345,10 +1346,19 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
break;
sigfillset(&full);
sigprocmask(SIG_BLOCK, &full, &old);
- schedule();
+ remaining = schedule_timeout(MD_SUSPEND_TIMEOUT);
sigprocmask(SIG_SETMASK, &old, NULL);
+ if (remaining == 0)
+ break;
}
finish_wait(&conf->wait_barrier, &w);
+ if (remaining == 0) {
+ pr_err("md/raid1:%s: suspend range is locked\n",
+ mdname(mddev));
+ bio->bi_error = -ETIMEDOUT;
+ bio_endio(bio);
+ return;
+ }
}
wait_barrier(conf, bio->bi_iter.bi_sector);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index cf1ac2e0f4c8..24297f1530d1 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5685,6 +5685,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
if (rw == WRITE &&
logical_sector >= mddev->suspend_lo &&
logical_sector < mddev->suspend_hi) {
+ long remaining = -1;
raid5_release_stripe(sh);
/* As the suspend_* range is controlled by
* userspace, we want an interruptible
@@ -5697,10 +5698,17 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
sigset_t full, old;
sigfillset(&full);
sigprocmask(SIG_BLOCK, &full, &old);
- schedule();
+ remaining = schedule_timeout(
+ MD_SUSPEND_TIMEOUT);
sigprocmask(SIG_SETMASK, &old, NULL);
do_prepare = true;
}
+ if (remaining == 0) {
+ pr_err("md/raid5:%s: suspend range is locked\n",
+ mdname(mddev));
+ bi->bi_error = -ETIMEDOUT;
+ break;
+ }
goto retry;
}
--
2.11.0
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
