writeback: implement unlocked_inode_to_wb transaction and use it for stat updates

The mechanism for detecting whether an inode should switch its wb
(bdi_writeback) association is now in place.  This patch build the
framework for the actual switching.

This patch adds a new inode flag I_WB_SWITCHING, which has two
functions.  First, the easy one, it ensures that there's only one
switching in progress for a give inode.  Second, it's used as a
mechanism to synchronize wb stat updates.

The two stats, WB_RECLAIMABLE and WB_WRITEBACK, aren't event counters
but track the current number of dirty pages and pages under writeback
respectively.  As such, when an inode is moved from one wb to another,
the inode's portion of those stats have to be transferred together;
unfortunately, this is a bit tricky as those stat updates are percpu
operations which are performed without holding any lock in some
places.

This patch solves the problem in a similar way as memcg.  Each such
lockless stat updates are wrapped in transaction surrounded by
unlocked_inode_to_wb_begin/end().  During normal operation, they map
to rcu_read_lock/unlock(); however, if I_WB_SWITCHING is asserted,
mapping->tree_lock is grabbed across the transaction.

In turn, the switching path sets I_WB_SWITCHING and waits for a RCU
grace period to pass before actually starting to switch, which
guarantees that all stat update paths are synchronizing against
mapping->tree_lock.

This patch still doesn't implement the actual switching.

v3: Updated on top of the recent cancel_dirty_page() updates.
    unlocked_inode_to_wb_begin() now nests inside
    mem_cgroup_begin_page_stat() to match the locking order.

v2: The i_wb access transaction will be used for !stat accesses too.
    Function names and comments updated accordingly.

    s/inode_wb_stat_unlocked_{begin|end}/unlocked_inode_to_wb_{begin|end}/
    s/switch_wb/switch_wbs/

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

2 files changed, 23 insertions, 7 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 2f065b1..bfc1ab053 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -213,7 +213,8 @@ void __delete_from_page_cache(struct page *page, void *shadow,
 	 * anyway will be cleared before returning page into buddy allocator.
 	 */
 	if (WARN_ON_ONCE(PageDirty(page)))
-		account_page_cleaned(page, mapping, memcg);
+		account_page_cleaned(page, mapping, memcg,
+				     inode_to_wb(mapping->host));
 }
 
 /**
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e890335..e1514d5 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2422,12 +2422,12 @@ EXPORT_SYMBOL(account_page_dirtied);
  * Caller must hold mem_cgroup_begin_page_stat().
  */
 void account_page_cleaned(struct page *page, struct address_space *mapping,
-			  struct mem_cgroup *memcg)
+			  struct mem_cgroup *memcg, struct bdi_writeback *wb)
 {
 	if (mapping_cap_account_dirty(mapping)) {
 		mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
 		dec_zone_page_state(page, NR_FILE_DIRTY);
-		dec_wb_stat(inode_to_wb(mapping->host), WB_RECLAIMABLE);
+		dec_wb_stat(wb, WB_RECLAIMABLE);
 		task_io_account_cancelled_write(PAGE_CACHE_SIZE);
 	}
 }
@@ -2490,11 +2490,15 @@ void account_page_redirty(struct page *page)
 	struct address_space *mapping = page->mapping;
 
 	if (mapping && mapping_cap_account_dirty(mapping)) {
-		struct bdi_writeback *wb = inode_to_wb(mapping->host);
+		struct inode *inode = mapping->host;
+		struct bdi_writeback *wb;
+		bool locked;
 
+		wb = unlocked_inode_to_wb_begin(inode, &locked);
 		current->nr_dirtied--;
 		dec_zone_page_state(page, NR_DIRTIED);
 		dec_wb_stat(wb, WB_DIRTIED);
+		unlocked_inode_to_wb_end(inode, locked);
 	}
 }
 EXPORT_SYMBOL(account_page_redirty);
@@ -2597,13 +2601,18 @@ void cancel_dirty_page(struct page *page)
 	struct address_space *mapping = page_mapping(page);
 
 	if (mapping_cap_account_dirty(mapping)) {
+		struct inode *inode = mapping->host;
+		struct bdi_writeback *wb;
 		struct mem_cgroup *memcg;
+		bool locked;
 
 		memcg = mem_cgroup_begin_page_stat(page);
+		wb = unlocked_inode_to_wb_begin(inode, &locked);
 
 		if (TestClearPageDirty(page))
-			account_page_cleaned(page, mapping, memcg);
+			account_page_cleaned(page, mapping, memcg, wb);
 
+		unlocked_inode_to_wb_end(inode, locked);
 		mem_cgroup_end_page_stat(memcg);
 	} else {
 		ClearPageDirty(page);
@@ -2628,12 +2637,16 @@ EXPORT_SYMBOL(cancel_dirty_page);
 int clear_page_dirty_for_io(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
-	struct mem_cgroup *memcg;
 	int ret = 0;
 
 	BUG_ON(!PageLocked(page));
 
 	if (mapping && mapping_cap_account_dirty(mapping)) {
+		struct inode *inode = mapping->host;
+		struct bdi_writeback *wb;
+		struct mem_cgroup *memcg;
+		bool locked;
+
 		/*
 		 * Yes, Virginia, this is indeed insane.
 		 *
@@ -2670,12 +2683,14 @@ int clear_page_dirty_for_io(struct page *page)
 		 * exclusion.
 		 */
 		memcg = mem_cgroup_begin_page_stat(page);
+		wb = unlocked_inode_to_wb_begin(inode, &locked);
 		if (TestClearPageDirty(page)) {
 			mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
 			dec_zone_page_state(page, NR_FILE_DIRTY);
-			dec_wb_stat(inode_to_wb(mapping->host), WB_RECLAIMABLE);
+			dec_wb_stat(wb, WB_RECLAIMABLE);
 			ret = 1;
 		}
+		unlocked_inode_to_wb_end(inode, locked);
 		mem_cgroup_end_page_stat(memcg);
 		return ret;
 	}