summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.com>2017-11-17 15:29:13 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-17 16:10:02 -0800
commitecc0c469f27765ed1e2b967be0aa17cee1a60b76 (patch)
treeb5446bc34a9dbf7c0c2ba2016b4479905d85a7c2 /fs
parente4f02fdabd1092065ddd8366fcb3c8483e627fc0 (diff)
autofs: don't fail mount for transient error
Currently if the autofs kernel module gets an error when writing to the pipe which links to the daemon, then it marks the whole moutpoint as catatonic, and it will stop working. It is possible that the error is transient. This can happen if the daemon is slow and more than 16 requests queue up. If a subsequent process tries to queue a request, and is then signalled, the write to the pipe will return -ERESTARTSYS and autofs will take that as total failure. So change the code to assess -ERESTARTSYS and -ENOMEM as transient failures which only abort the current request, not the whole mountpoint. It isn't a crash or a data corruption, but having autofs mountpoints suddenly stop working is rather inconvenient. Ian said: : And given the problems with a half dozen (or so) user space applications : consuming large amounts of CPU under heavy mount and umount activity this : could happen more easily than we expect. Link: http://lkml.kernel.org/r/87y3norvgp.fsf@notabene.neil.brown.name Signed-off-by: NeilBrown <neilb@suse.com> Acked-by: Ian Kent <raven@themaw.net> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs')
-rw-r--r--fs/autofs4/waitq.c15
1 files changed, 14 insertions, 1 deletions
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 4ac49d038bf3..8fc41705c7cd 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -81,7 +81,8 @@ static int autofs4_write(struct autofs_sb_info *sbi,
spin_unlock_irqrestore(&current->sighand->siglock, flags);
}
- return (bytes > 0);
+ /* if 'wr' returned 0 (impossible) we assume -EIO (safe) */
+ return bytes == 0 ? 0 : wr < 0 ? wr : -EIO;
}
static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
@@ -95,6 +96,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
} pkt;
struct file *pipe = NULL;
size_t pktsz;
+ int ret;
pr_debug("wait id = 0x%08lx, name = %.*s, type=%d\n",
(unsigned long) wq->wait_queue_token,
@@ -169,7 +171,18 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
mutex_unlock(&sbi->wq_mutex);
if (autofs4_write(sbi, pipe, &pkt, pktsz))
+ switch (ret = autofs4_write(sbi, pipe, &pkt, pktsz)) {
+ case 0:
+ break;
+ case -ENOMEM:
+ case -ERESTARTSYS:
+ /* Just fail this one */
+ autofs4_wait_release(sbi, wq->wait_queue_token, ret);
+ break;
+ default:
autofs4_catatonic_mode(sbi);
+ break;
+ }
fput(pipe);
}