xfs: use dedicated log worker wq to avoid deadlock with cil wq

orabug: 26871913
backport: upstream 696a562072e3c14bcd13ae5acc19cdf27679e865 (no conflict)

The log covering background task used to be part of the xfssyncd
workqueue. That workqueue was removed as of commit 5889608df ("xfs:
syncd workqueue is no more") and the associated work item scheduled
to the xfs-log wq. The latter is used for log buffer I/O completion.

Since xfs_log_worker() can invoke a log flush, a deadlock is
possible between the xfs-log and xfs-cil workqueues. Consider the
following codepath from xfs_log_worker():

xfs_log_worker()
  xfs_log_force()
    _xfs_log_force()
      xlog_cil_force()
        xlog_cil_force_lsn()
          xlog_cil_push_now()
            flush_work()

The above is in xfs-log wq context and blocked waiting on the
completion of an xfs-cil work item. Concurrently, the cil push in
progress can end up blocked here:

xlog_cil_push_work()
  xlog_cil_push()
    xlog_write()
      xlog_state_get_iclog_space()
        xlog_wait(&log->l_flush_wait, ...)

The above is in xfs-cil context waiting on log buffer I/O
completion, which executes in xfs-log wq context. In this scenario
both workqueues are deadlocked waiting on eachother.

Add a new workqueue specifically for the high level log covering and
ail pushing worker, as was the case prior to commit 5889608df.

Diagnosed-by: David Jeffery <djeffery@redhat.com>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Dhaval Giani <dhaval.giani@oracle.com>

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index f5520ea397668ef349eb22eb39781859bf0fb478..4e2204200e5a83ccbb1fc6e962dcfc1e0c96291c 100644 (file)
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1284,7 +1284,7 @@ void
 xfs_log_work_queue(
        struct xfs_mount        *mp)
 {
-       queue_delayed_work(mp->m_log_workqueue, &mp->m_log->l_work,
+       queue_delayed_work(mp->m_sync_workqueue, &mp->m_log->l_work,
                                msecs_to_jiffies(xfs_syncd_centisecs * 10));
 }
 

diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index f742b17a86f6914a963ceb1f0db2b4181b0fcfc0..c9ad9842c96ba0ca7f967e985ebeea23e84aca33 100644 (file)
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -169,6 +169,7 @@ typedef struct xfs_mount {
        struct workqueue_struct *m_reclaim_workqueue;
        struct workqueue_struct *m_log_workqueue;
        struct workqueue_struct *m_eofblocks_workqueue;
+       struct workqueue_struct *m_sync_workqueue;
 
        /*
         * Generation of the filesysyem layout.  This is incremented by each

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 0d3447a4fb94fc3c727a2968128441bc92e4c67c..fcba159976b53f8762648e020e3ac6745302a674 100644 (file)
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -860,8 +860,15 @@ xfs_init_mount_workqueues(
        if (!mp->m_eofblocks_workqueue)
                goto out_destroy_log;
 
+       mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", WQ_FREEZABLE, 0,
+                                              mp->m_fsname);
+       if (!mp->m_sync_workqueue)
+               goto out_destroy_eofb;
+
        return 0;
 
+out_destroy_eofb:
+       destroy_workqueue(mp->m_eofblocks_workqueue);
 out_destroy_log:
        destroy_workqueue(mp->m_log_workqueue);
 out_destroy_reclaim:
@@ -882,6 +889,7 @@ STATIC void
 xfs_destroy_mount_workqueues(
        struct xfs_mount        *mp)
 {
+       destroy_workqueue(mp->m_sync_workqueue);
        destroy_workqueue(mp->m_eofblocks_workqueue);
        destroy_workqueue(mp->m_log_workqueue);
        destroy_workqueue(mp->m_reclaim_workqueue);