[RFC PATCH] fs: Use a seperate wq for do_sync_work() to avoid a potential deadlock

[Aaron Tomlin <atomlin@redhat.com>]

Since do_sync_work() is a deferred function it can block indefinitely by
design. At present do_sync_work() is added to the global system_wq.
As such a deadlock is theoretically possible between sys_unmount() and
sync_filesystems():

  * The current work fn on the system_wq (do_sync_work()) is blocked
    waiting to aquire a sb's s_umount for reading.

  * The "umount" task is the current owner of the s_umount in
    question but is waiting for do_sync_work() to continue.
    Thus we hit a deadlock situation.

This patch introduces a separate workqueue for do_sync_work() to avoid a
the described deadlock.

Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
Reviewed-by: Alexander Viro <viro@zeniv.linux.org.uk>
---
 fs/sync.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/fs/sync.c b/fs/sync.c
index bdc729d..df455d0 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -15,6 +15,7 @@
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
 #include <linux/backing-dev.h>
+#include <linux/kthread.h>
 #include "internal.h"
 
 #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
@@ -114,7 +115,7 @@ SYSCALL_DEFINE0(sync)
 	return 0;
 }
 
-static void do_sync_work(struct work_struct *work)
+static int do_sync_work(void *dummy)
 {
 	int nowait = 0;
 
@@ -129,18 +130,12 @@ static void do_sync_work(struct work_struct *work)
 	iterate_supers(sync_fs_one_sb, &nowait);
 	iterate_bdevs(fdatawrite_one_bdev, NULL);
 	printk("Emergency Sync complete\n");
-	kfree(work);
+	return 0;
 }
 
 void emergency_sync(void)
 {
-	struct work_struct *work;
-
-	work = kmalloc(sizeof(*work), GFP_ATOMIC);
-	if (work) {
-		INIT_WORK(work, do_sync_work);
-		schedule_work(work);
-	}
+	kthread_run(do_sync_work, NULL, "sync_work_thread");
 }
 
 /*
-- 
1.9.3