cgroup: limit the amount of dirty file pages

index 8274f5e..9c40a16 100644
@@ -718,6 +718,7 @@ static int __set_page_dirty(struct page *page,
 		WARN_ON_ONCE(warn && !PageUptodate(page));
 
 		if (mapping_cap_account_dirty(mapping)) {
+			mem_cgroup_charge_file_dirty(page, 1);
 			__inc_zone_page_state(page, NR_FILE_DIRTY);
 			__inc_bdi_stat(mapping->backing_dev_info,
 					BDI_RECLAIMABLE);

index decb9eb..671432a 100644
@@ -82,9 +82,11 @@ int reiser4_set_page_dirty(struct page *page)
 			/* check for race with truncate */
 			if (page->mapping) {
 				assert("vs-1652", page->mapping == mapping);
-				if (mapping_cap_account_dirty(mapping))
+				if (mapping_cap_account_dirty(mapping)) {
+					mem_cgroup_charge_file_dirty(page, 1);
 					inc_zone_page_state(page,
 							NR_FILE_DIRTY);
+				}
 				radix_tree_tag_set(&mapping->page_tree,
 						   page->index,
 						   PAGECACHE_TAG_REISER4_MOVED);

index 654e7ae..2d5dfac 100644
@@ -467,8 +467,10 @@ int reiser4_set_page_dirty_internal(struct page *page)
 	BUG_ON(mapping == NULL);
 
 	if (!TestSetPageDirty(page)) {
-		if (mapping_cap_account_dirty(mapping))
+		if (mapping_cap_account_dirty(mapping)) {
+			mem_cgroup_charge_file_dirty(page, 1);
 			inc_zone_page_state(page, NR_FILE_DIRTY);
+		}
 
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 	}

index ee1b2fc..6677097 100644
@@ -29,6 +29,9 @@ struct mm_struct;
 
 #define page_reset_bad_cgroup(page)	((page)->page_cgroup = 0)
 
+extern void mem_cgroup_charge_file_dirty(struct page *page, int charge);
+extern s64 mem_cgroup_check_file_dirty(void);
+
 extern struct page_cgroup *page_get_page_cgroup(struct page *page);
 extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask);

@@ -132,6 +135,15 @@ static inline void mem_cgroup_end_migration(struct page *page)
 {
 }
 
+static inline void mem_cgroup_charge_file_dirty(struct page *page, int charge)
+{
+}
+
+static inline s64 mem_cgroup_check_file_dirty(void)
+{
+	return 0;
+}
+
 static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
 {
 	return 0;

index 0df6e1f..ca20f51 100644
@@ -131,6 +131,7 @@ void __remove_from_page_cache(struct page *page)
 	 * having removed the page entirely.
 	 */
 	if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
+		mem_cgroup_charge_file_dirty(page, -1);
 		dec_zone_page_state(page, NR_FILE_DIRTY);
 		dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
 	}

131 lines not on this page · raw message

index c6d6088..ae89950 100644
@@ -25,6 +25,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/blkdev.h>
 #include <linux/mpage.h>
+#include <linux/memcontrol.h>
 #include <linux/rmap.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>

@@ -412,6 +413,34 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
 	}
 }
 
+static void mem_cgroup_balance_dirty_pages(struct address_space *mapping,
+				long long dirty_pages)
+{
+	struct writeback_control wbc = {
+		.bdi		= mapping->backing_dev_info,
+		.sync_mode	= WB_SYNC_NONE,
+		.older_than_this = NULL,
+		.nr_to_write	= 0,
+		.range_cyclic	= 1,
+	};
+	unsigned long write_chunk = sync_writeback_pages();
+
+	while (dirty_pages > 0) {
+		wbc.more_io = 0;
+		wbc.encountered_congestion = 0;
+		wbc.nr_to_write = write_chunk;
+		wbc.pages_skipped = 0;
+		writeback_inodes(&wbc);
+		dirty_pages -= write_chunk - wbc.nr_to_write;
+		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
+			if (wbc.encountered_congestion || wbc.more_io)
+				congestion_wait(WRITE, HZ/10);
+			else
+				break;
+		}
+	}
+}
+
 /*
  * balance_dirty_pages() must be called by processes which are generating dirty
  * data.  It looks at the number of dirty pages in the machine and will force

@@ -556,6 +585,12 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
 	unsigned long ratelimit;
 	unsigned long *p;
+	long long memcg_dirty_pages = mem_cgroup_check_file_dirty();
+
+	if (memcg_dirty_pages) {
+		mem_cgroup_balance_dirty_pages(mapping, memcg_dirty_pages);
+		return;
+	}
 
 	ratelimit = ratelimit_pages;
 	if (mapping->backing_dev_info->dirty_exceeded)

@@ -1090,6 +1125,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 			BUG_ON(mapping2 != mapping);
 			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
 			if (mapping_cap_account_dirty(mapping)) {
+				mem_cgroup_charge_file_dirty(page, 1);
 				__inc_zone_page_state(page, NR_FILE_DIRTY);
 				__inc_bdi_stat(mapping->backing_dev_info,
 						BDI_RECLAIMABLE);

@@ -1234,6 +1270,7 @@ int clear_page_dirty_for_io(struct page *page)
 		 * for more comments.
 		 */
 		if (TestClearPageDirty(page)) {
+			mem_cgroup_charge_file_dirty(page, -1);
 			dec_zone_page_state(page, NR_FILE_DIRTY);
 			dec_bdi_stat(mapping->backing_dev_info,
 					BDI_RECLAIMABLE);

index e2bdd70..8ca6893 100644
@@ -72,7 +72,9 @@ void cancel_dirty_page(struct page *page, unsigned int account_size)
 {
 	if (TestClearPageDirty(page)) {
 		struct address_space *mapping = page->mapping;
+
 		if (mapping && mapping_cap_account_dirty(mapping)) {
+			mem_cgroup_charge_file_dirty(page, -1);
 			dec_zone_page_state(page, NR_FILE_DIRTY);
 			dec_bdi_stat(mapping->backing_dev_info,
 					BDI_RECLAIMABLE);