mm, vmstat: allow WQ concurrency to discover memory reclaim doesn't make any progress

[karo-tx-linux.git] / mm / backing-dev.c

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 8ed2ffd963c53b910f91e1b60b04c56385a3129f..7340353f8aea08ef428edcf7b287c45b312aeb1a 100644 (file)
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -957,8 +957,9 @@ EXPORT_SYMBOL(congestion_wait);
  * jiffies for either a BDI to exit congestion of the given @sync queue
  * or a write to complete.
  *
- * In the absence of zone congestion, cond_resched() is called to yield
- * the processor if necessary but otherwise does not sleep.
+ * In the absence of zone congestion, a short sleep or a cond_resched is
+ * performed to yield the processor and to allow other subsystems to make
+ * a forward progress.
  *
  * The return value is 0 if the sleep is for the full timeout. Otherwise,
  * it is the number of jiffies that were still remaining when the function
@@ -978,7 +979,19 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
         */
        if (atomic_read(&nr_wb_congested[sync]) == 0 ||
            !test_bit(ZONE_CONGESTED, &zone->flags)) {
-               cond_resched();
+
+               /*
+                * Memory allocation/reclaim might be called from a WQ
+                * context and the current implementation of the WQ
+                * concurrency control doesn't recognize that a particular
+                * WQ is congested if the worker thread is looping without
+                * ever sleeping. Therefore we have to do a short sleep
+                * here rather than calling cond_resched().
+                */
+               if (current->flags & PF_WQ_WORKER)
+                       schedule_timeout(1);
+               else
+                       cond_resched();
 
                /* In case we scheduled, work out time remaining */
                ret = timeout - (jiffies - start);