summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2
diff options
context:
space:
mode:
authorGang He <ghe@suse.com>2021-09-02 14:50:17 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-09-03 09:58:09 -0700
commit9673e0050c39b0534d0e2ca431223f52089f4959 (patch)
treef3bf42d01e97b713932282dcf74df9daa5468f39 /fs/ocfs2
parent6c85c2c728193d19d6a908ae9fb312d0325e65ca (diff)
downloadlinux-9673e0050c39b0534d0e2ca431223f52089f4959.tar.gz
linux-9673e0050c39b0534d0e2ca431223f52089f4959.tar.bz2
linux-9673e0050c39b0534d0e2ca431223f52089f4959.zip
ocfs2: ocfs2_downconvert_lock failure results in deadlock
Usually, ocfs2_downconvert_lock() function always downconverts dlm lock to the expected level for satisfy dlm bast requests from the other nodes. But there is a rare situation. When dlm lock conversion is being canceled, ocfs2_downconvert_lock() function will return -EBUSY. You need to be aware that ocfs2_cancel_convert() function is asynchronous in fsdlm implementation. If we does not requeue this lockres entry, ocfs2 downconvert thread no longer handles this dlm lock bast request. Then, the other nodes will not get the dlm lock again, the current node's process will be blocked when acquire this dlm lock again. Link: https://lkml.kernel.org/r/20210830044621.12544-1-ghe@suse.com Signed-off-by: Gang He <ghe@suse.com> Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Mark Fasheh <mark@fasheh.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Junxiao Bi <junxiao.bi@oracle.com> Cc: Changwei Ge <gechangwei@live.cn> Cc: Gang He <ghe@suse.com> Cc: Jun Piao <piaojun@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/ocfs2')
-rw-r--r--fs/ocfs2/dlmglue.c12
1 files changed, 12 insertions, 0 deletions
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 33fbdc823278..359524b7341f 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -16,6 +16,7 @@
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/time.h>
+#include <linux/delay.h>
#include <linux/quotaops.h>
#include <linux/sched/signal.h>
@@ -3912,6 +3913,17 @@ downconvert:
spin_unlock_irqrestore(&lockres->l_lock, flags);
ret = ocfs2_downconvert_lock(osb, lockres, new_level, set_lvb,
gen);
+ /* The dlm lock convert is being cancelled in background,
+ * ocfs2_cancel_convert() is asynchronous in fs/dlm,
+ * requeue it, try again later.
+ */
+ if (ret == -EBUSY) {
+ ctl->requeue = 1;
+ mlog(ML_BASTS, "lockres %s, ReQ: Downconvert busy\n",
+ lockres->l_name);
+ ret = 0;
+ msleep(20);
+ }
leave:
if (ret)