[PATCH] 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>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index fc35e6bdfb93e4bf4d5cac5b50c983e97e846c5a..0c78f7f4a976489064d2508d6e56ae610bf84311 100644 (file)
--- 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 f7e088f5a309eff3a03c8da5ad4ca4b37ecd5518..f469e3cd08e82d47ba3a0aa8d9753081e2c7cc99 100644 (file)
--- 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 0655d5fe73e82c164043bf99958397602d6846c7..db023e2ff3852f544c6a4b0f8cb3b43ecd0d456b 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -952,7 +952,7 @@ 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;