writeback: make writeback_control.nr_to_write straight

Pass struct wb_writeback_work all the way down to writeback_sb_inodes(),
and initialize the struct writeback_control there.

struct writeback_control is basically designed to control writeback of a
single file, but we keep abuse it for writing multiple files in
writeback_sb_inodes() and its callers.

It immediately clean things up, e.g. suddenly wbc.nr_to_write vs
work->nr_pages starts to make sense, and instead of saving and restoring
pages_skipped in writeback_sb_inodes it can always start with a clean
zero value.

It also makes a neat IO pattern change: large dirty files are now
written in the full 4MB writeback chunk size, rather than whatever
remained quota in wbc->nr_to_write.

Acked-by: Jan Kara <jack@suse.cz>
Proposed-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>

2 files changed, 8 insertions, 26 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 5f6553e..7ba303b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -260,18 +260,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
 	return wb_has_dirty_io(&bdi->wb);
 }
 
-static void bdi_flush_io(struct backing_dev_info *bdi)
-{
-	struct writeback_control wbc = {
-		.sync_mode		= WB_SYNC_NONE,
-		.older_than_this	= NULL,
-		.range_cyclic		= 1,
-		.nr_to_write		= 1024,
-	};
-
-	writeback_inodes_wb(&bdi->wb, &wbc);
-}
-
 /*
  * kupdated() used to do this. We cannot do it from the bdi_forker_thread()
  * or we risk deadlocking on ->s_umount. The longer term solution would be
@@ -457,9 +445,10 @@ static int bdi_forker_thread(void *ptr)
 			if (IS_ERR(task)) {
 				/*
 				 * If thread creation fails, force writeout of
-				 * the bdi from the thread.
+				 * the bdi from the thread. Hopefully 1024 is
+				 * large enough for efficient IO.
 				 */
-				bdi_flush_io(bdi);
+				writeback_inodes_wb(&bdi->wb, 1024);
 			} else {
 				/*
 				 * The spinlock makes sure we do not lose
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 1965d05..9d6ac2b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -491,13 +491,6 @@ static void balance_dirty_pages(struct address_space *mapping,
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 
 	for (;;) {
-		struct writeback_control wbc = {
-			.sync_mode	= WB_SYNC_NONE,
-			.older_than_this = NULL,
-			.nr_to_write	= write_chunk,
-			.range_cyclic	= 1,
-		};
-
 		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
 					global_page_state(NR_UNSTABLE_NFS);
 		nr_writeback = global_page_state(NR_WRITEBACK);
@@ -559,17 +552,17 @@ static void balance_dirty_pages(struct address_space *mapping,
 		 * threshold otherwise wait until the disk writes catch
 		 * up.
 		 */
-		trace_wbc_balance_dirty_start(&wbc, bdi);
+		trace_balance_dirty_start(bdi);
 		if (bdi_nr_reclaimable > bdi_thresh) {
-			writeback_inodes_wb(&bdi->wb, &wbc);
-			pages_written += write_chunk - wbc.nr_to_write;
-			trace_wbc_balance_dirty_written(&wbc, bdi);
+			pages_written += writeback_inodes_wb(&bdi->wb,
+							     write_chunk);
+			trace_balance_dirty_written(bdi, pages_written);
 			if (pages_written >= write_chunk)
 				break;		/* We've done our duty */
 		}
-		trace_wbc_balance_dirty_wait(&wbc, bdi);
 		__set_current_state(TASK_UNINTERRUPTIBLE);
 		io_schedule_timeout(pause);
+		trace_balance_dirty_wait(bdi);
 
 		/*
 		 * Increase the delay for each loop, up to our previous