workqueue: Fix spruious data race in __flush_work()

When flushing a work item for cancellation, __flush_work() knows that it
exclusively owns the work item through its PENDING bit. 134874e2eee9
("workqueue: Allow cancel_work_sync() and disable_work() from atomic
contexts on BH work items") added a read of @work->data to determine whether
to use busy wait for BH work items that are being canceled. While the read
is safe when @from_cancel, @work->data was read before testing @from_cancel
to simplify code structure:

	data = *work_data_bits(work);
	if (from_cancel &&
	    !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) {

While the read data was never used if !@from_cancel, this could trigger
KCSAN data race detection spuriously:

  ==================================================================
  BUG: KCSAN: data-race in __flush_work / __flush_work

  write to 0xffff8881223aa3e8 of 8 bytes by task 3998 on cpu 0:
   instrument_write include/linux/instrumented.h:41 [inline]
   ___set_bit include/asm-generic/bitops/instrumented-non-atomic.h:28 [inline]
   insert_wq_barrier kernel/workqueue.c:3790 [inline]
   start_flush_work kernel/workqueue.c:4142 [inline]
   __flush_work+0x30b/0x570 kernel/workqueue.c:4178
   flush_work kernel/workqueue.c:4229 [inline]
   ...

  read to 0xffff8881223aa3e8 of 8 bytes by task 50 on cpu 1:
   __flush_work+0x42a/0x570 kernel/workqueue.c:4188
   flush_work kernel/workqueue.c:4229 [inline]
   flush_delayed_work+0x66/0x70 kernel/workqueue.c:4251
   ...

  value changed: 0x0000000000400000 -> 0xffff88810006c00d

Reorganize the code so that @from_cancel is tested before @work->data is
accessed. The only problem is triggering KCSAN detection spuriously. This
shouldn't need READ_ONCE() or other access qualifiers.

No functional changes.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: syzbot+b3e4f2f51ed645fd5df2@syzkaller.appspotmail.com
Fixes: 134874e2eee9 ("workqueue: Allow cancel_work_sync() and disable_work() from atomic contexts on BH work items")
Link: http://lkml.kernel.org/r/000000000000ae429e061eea2157@google.com
Cc: Jens Axboe <axboe@kernel.dk>

1 files changed, 25 insertions, 20 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index d56bd2277e58..ef174d8c1f63 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4166,7 +4166,6 @@ already_gone:
 static bool __flush_work(struct work_struct *work, bool from_cancel)
 {
 	struct wq_barrier barr;
-	unsigned long data;
 
 	if (WARN_ON(!wq_online))
 		return false;
@@ -4184,29 +4183,35 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
 	 * was queued on a BH workqueue, we also know that it was running in the
 	 * BH context and thus can be busy-waited.
 	 */
-	data = *work_data_bits(work);
-	if (from_cancel &&
-	    !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) {
-		/*
-		 * On RT, prevent a live lock when %current preempted soft
-		 * interrupt processing or prevents ksoftirqd from running by
-		 * keeping flipping BH. If the BH work item runs on a different
-		 * CPU then this has no effect other than doing the BH
-		 * disable/enable dance for nothing. This is copied from
-		 * kernel/softirq.c::tasklet_unlock_spin_wait().
-		 */
-		while (!try_wait_for_completion(&barr.done)) {
-			if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
-				local_bh_disable();
-				local_bh_enable();
-			} else {
-				cpu_relax();
+	if (from_cancel) {
+		unsigned long data = *work_data_bits(work);
+
+		if (!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) &&
+		    (data & WORK_OFFQ_BH)) {
+			/*
+			 * On RT, prevent a live lock when %current preempted
+			 * soft interrupt processing or prevents ksoftirqd from
+			 * running by keeping flipping BH. If the BH work item
+			 * runs on a different CPU then this has no effect other
+			 * than doing the BH disable/enable dance for nothing.
+			 * This is copied from
+			 * kernel/softirq.c::tasklet_unlock_spin_wait().
+			 */
+			while (!try_wait_for_completion(&barr.done)) {
+				if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+					local_bh_disable();
+					local_bh_enable();
+				} else {
+					cpu_relax();
+				}
 			}
+			goto out_destroy;
 		}
-	} else {
-		wait_for_completion(&barr.done);
 	}
 
+	wait_for_completion(&barr.done);
+
+out_destroy:
 	destroy_work_on_stack(&barr.work);
 	return true;
 }