memcgroup: fix hang with shmem/tmpfs

The memcgroup regime relies upon a cgroup reclaiming pages from itself within
add_to_page_cache: which may involve some waiting.  Whereas shmem and tmpfs
rely upon using add_to_page_cache while holding a spinlock: when it cannot
wait.  The consequence is that when a cgroup reaches its limit, shmem_getpage
just hangs - unless there is outside memory pressure too, neither kswapd nor
radix_tree_preload get it out of the retry loop.

In most cases we can mem_cgroup_cache_charge the page waitably first, to
attach the page_cgroup in advance, so add_to_page_cache will do no more than
increment a count; then mem_cgroup_uncharge_page after (in both success and
failure cases) to balance the books again.

And where there used to be a congestion_wait for kswapd (recently made
redundant by radix_tree_preload), use mem_cgroup_cache_charge with NULL page
to go through a cycle of allocation and freeing, without accounting to any
particular page, and without updating the statistics vector.  This brings the
cgroup below its limit so the next try usually succeeds.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 27 insertions, 1 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 0f246c44a57..85bed948faf 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -912,9 +912,13 @@ found:
 	error = 1;
 	if (!inode)
 		goto out;
-	error = radix_tree_preload(GFP_KERNEL);
+	/* Precharge page while we can wait, compensate afterwards */
+	error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
 	if (error)
 		goto out;
+	error = radix_tree_preload(GFP_KERNEL);
+	if (error)
+		goto uncharge;
 	error = 1;
 
 	spin_lock(&info->lock);
@@ -947,6 +951,8 @@ found:
 		shmem_swp_unmap(ptr);
 	spin_unlock(&info->lock);
 	radix_tree_preload_end();
+uncharge:
+	mem_cgroup_uncharge_page(page);
 out:
 	unlock_page(page);
 	page_cache_release(page);
@@ -1308,6 +1314,13 @@ repeat:
 			spin_unlock(&info->lock);
 			unlock_page(swappage);
 			page_cache_release(swappage);
+			if (error == -ENOMEM) {
+				/* allow reclaim from this memory cgroup */
+				error = mem_cgroup_cache_charge(NULL,
+					current->mm, gfp & ~__GFP_HIGHMEM);
+				if (error)
+					goto failed;
+			}
 			goto repeat;
 		}
 	} else if (sgp == SGP_READ && !filepage) {
@@ -1353,6 +1366,17 @@ repeat:
 				goto failed;
 			}
 
+			/* Precharge page while we can wait, compensate after */
+			error = mem_cgroup_cache_charge(filepage, current->mm,
+							gfp & ~__GFP_HIGHMEM);
+			if (error) {
+				page_cache_release(filepage);
+				shmem_unacct_blocks(info->flags, 1);
+				shmem_free_blocks(inode, 1);
+				filepage = NULL;
+				goto failed;
+			}
+
 			spin_lock(&info->lock);
 			entry = shmem_swp_alloc(info, idx, sgp);
 			if (IS_ERR(entry))
@@ -1364,6 +1388,7 @@ repeat:
 			if (error || swap.val || 0 != add_to_page_cache_lru(
 					filepage, mapping, idx, GFP_NOWAIT)) {
 				spin_unlock(&info->lock);
+				mem_cgroup_uncharge_page(filepage);
 				page_cache_release(filepage);
 				shmem_unacct_blocks(info->flags, 1);
 				shmem_free_blocks(inode, 1);
@@ -1372,6 +1397,7 @@ repeat:
 					goto failed;
 				goto repeat;
 			}
+			mem_cgroup_uncharge_page(filepage);
 			info->flags |= SHMEM_PAGEIN;
 		}