throttle_vm_writeout(): don't loop on GFP_NOFS and GFP_NOIO allocations

throttle_vm_writeout() is designed to wait for the dirty levels to subside. 
But if the caller holds IO or FS locks, we might be holding up that writeout.

So change it to take a single nap to give other devices a chance to clean some
memory, then return.

Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Kumar Gala <galak@kernel.crashing.org>
Cc: Pete Zaitcev <zaitcev@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

3 files changed, 13 insertions, 4 deletions

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index fc35e6bdfb93..0c78f7f4a976 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -84,7 +84,7 @@ static inline void wait_on_inode(struct inode *inode)
 int wakeup_pdflush(long nr_pages);
 void laptop_io_completion(void);
 void laptop_sync_completion(void);
-void throttle_vm_writeout(void);
+void throttle_vm_writeout(gfp_t gfp_mask);
 
 /* These are exported to sysctl. */
 extern int dirty_background_ratio;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index be0efbde4994..17255ab1d380 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -296,11 +296,21 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 }
 EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
 
-void throttle_vm_writeout(void)
+void throttle_vm_writeout(gfp_t gfp_mask)
 {
 	long background_thresh;
 	long dirty_thresh;
 
+	if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO)) {
+		/*
+		 * The caller might hold locks which can prevent IO completion
+		 * or progress in the filesystem.  So we cannot just sit here
+		 * waiting for IO to complete.
+		 */
+		congestion_wait(WRITE, HZ/10);
+		return;
+	}
+
         for ( ; ; ) {
 		get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
 
@@ -317,7 +327,6 @@ void throttle_vm_writeout(void)
         }
 }
 
-
 /*
  * writeback at least _min_pages, and keep writing until the amount of dirty
  * memory is less than the background threshold, or until we're all clean.
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7430df68cb64..5b4528a49df4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -949,7 +949,7 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 		}
 	}
 
-	throttle_vm_writeout();
+	throttle_vm_writeout(sc->gfp_mask);
 
 	atomic_dec(&zone->reclaim_in_progress);
 	return nr_reclaimed;