Block: use a freezable workqueue for disk-event polling

This patch (as1519) fixes a bug in the block layer's disk-events
polling.  The polling is done by a work routine queued on the
system_nrt_wq workqueue.  Since that workqueue isn't freezable, the
polling continues even in the middle of a system sleep transition.

Obviously, polling a suspended drive for media changes and such isn't
a good thing to do; in the case of USB mass-storage devices it can
lead to real problems requiring device resets and even re-enumeration.

The patch fixes things by creating a new system-wide, non-reentrant,
freezable workqueue and using it for disk-events polling.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
CC: <stable@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 15 insertions, 6 deletions

diff --git a/block/genhd.c b/block/genhd.c
index b26c4085590d..df9816ede75b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1478,9 +1478,9 @@ static void __disk_unblock_events(struct gendisk *disk, bool check_now)
         intv = disk_events_poll_jiffies(disk);
         set_timer_slack(&ev->dwork.timer, intv / 4);
         if (check_now)
-                queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
+                queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0);
         else if (intv)
-                queue_delayed_work(system_nrt_wq, &ev->dwork, intv);
+                queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, intv);
 out_unlock:
         spin_unlock_irqrestore(&ev->lock, flags);
 }
@@ -1524,7 +1524,7 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask)
         ev->clearing |= mask;
         if (!ev->block) {
                 cancel_delayed_work(&ev->dwork);
-                queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
+                queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0);
         }
         spin_unlock_irq(&ev->lock);
 }
@@ -1561,7 +1561,7 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask)
 
         /* uncondtionally schedule event check and wait for it to finish */
         disk_block_events(disk);
-        queue_delayed_work(system_nrt_wq, &ev->dwork, 0);
+        queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0);
         flush_delayed_work(&ev->dwork);
         __disk_unblock_events(disk, false);
 
@@ -1598,7 +1598,7 @@ static void disk_events_workfn(struct work_struct *work)
 
         intv = disk_events_poll_jiffies(disk);
         if (!ev->block && intv)
-                queue_delayed_work(system_nrt_wq, &ev->dwork, intv);
+                queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, intv);
 
         spin_unlock_irq(&ev->lock);
 
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index eb8b9f15f2e0..af155450cabb 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -289,12 +289,16 @@ enum {
  *
  * system_freezable_wq is equivalent to system_wq except that it's
  * freezable.
+ *
+ * system_nrt_freezable_wq is equivalent to system_nrt_wq except that
+ * it's freezable.
  */
 extern struct workqueue_struct *system_wq;
 extern struct workqueue_struct *system_long_wq;
 extern struct workqueue_struct *system_nrt_wq;
 extern struct workqueue_struct *system_unbound_wq;
 extern struct workqueue_struct *system_freezable_wq;
+extern struct workqueue_struct *system_nrt_freezable_wq;
 
 extern struct workqueue_struct *
 __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index bec7b5b53e03..f2c5638bb5ab 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -253,11 +253,13 @@ struct workqueue_struct *system_long_wq __read_mostly;
 struct workqueue_struct *system_nrt_wq __read_mostly;
 struct workqueue_struct *system_unbound_wq __read_mostly;
 struct workqueue_struct *system_freezable_wq __read_mostly;
+struct workqueue_struct *system_nrt_freezable_wq __read_mostly;
 EXPORT_SYMBOL_GPL(system_wq);
 EXPORT_SYMBOL_GPL(system_long_wq);
 EXPORT_SYMBOL_GPL(system_nrt_wq);
 EXPORT_SYMBOL_GPL(system_unbound_wq);
 EXPORT_SYMBOL_GPL(system_freezable_wq);
+EXPORT_SYMBOL_GPL(system_nrt_freezable_wq);
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/workqueue.h>
@@ -3833,8 +3835,11 @@ static int __init init_workqueues(void)
                                             WQ_UNBOUND_MAX_ACTIVE);
         system_freezable_wq = alloc_workqueue("events_freezable",
                                               WQ_FREEZABLE, 0);
+        system_nrt_freezable_wq = alloc_workqueue("events_nrt_freezable",
+                        WQ_NON_REENTRANT | WQ_FREEZABLE, 0);
         BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq ||
-               !system_unbound_wq || !system_freezable_wq);
+               !system_unbound_wq || !system_freezable_wq ||
+                !system_nrt_freezable_wq);
         return 0;
 }
 early_initcall(init_workqueues);