[PATCH v2 1/3] mm: kick writeback flusher instead of inline flush for IOCB_DONTCACHE

[Jeff Layton]

The IOCB_DONTCACHE writeback path in generic_write_sync() calls
filemap_flush_range() on every write, submitting writeback inline in
the writer's context.  Perf lock contention profiling shows the
performance problem is not lock contention but the writeback submission
work itself — walking the page tree and submitting I/O blocks the
writer for milliseconds, inflating p99.9 latency from 23ms (buffered)
to 93ms (dontcache).

Replace the inline filemap_flush_range() call with a
wakeup_flusher_threads_bdi() call that kicks the BDI's flusher thread
to drain dirty pages in the background.  This moves writeback
submission completely off the writer's hot path.  The flusher thread
handles writeback asynchronously, naturally coalescing and rate-limiting
I/O without any explicit skip-if-busy or dirty pressure checks.

Add WB_REASON_DONTCACHE as a new writeback reason for tracing
visibility.

Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxx>
---
 fs/fs-writeback.c                | 14 ++++++++++++++
 include/linux/backing-dev-defs.h |  1 +
 include/linux/fs.h               |  6 ++----
 include/trace/events/writeback.h |  3 ++-
 4 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3c75ee025bda..88dc31388a31 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2466,6 +2466,20 @@ void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi,
 	rcu_read_unlock();
 }
 
+/**
+ * filemap_dontcache_kick_writeback - kick flusher for IOCB_DONTCACHE writes
+ * @mapping:	address_space that was just written to
+ *
+ * Wake the BDI flusher thread to start writeback of dirty pages in the
+ * background.
+ */
+void filemap_dontcache_kick_writeback(struct address_space *mapping)
+{
+	wakeup_flusher_threads_bdi(inode_to_bdi(mapping->host),
+				   WB_REASON_DONTCACHE);
+}
+EXPORT_SYMBOL(filemap_dontcache_kick_writeback);
+
 /*
  * Wakeup the flusher threads to start writeback of all currently dirty pages
  */
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index c88fd4d37d1f..4a81c90a8928 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -55,6 +55,7 @@ enum wb_reason {
 	 */
 	WB_REASON_FORKER_THREAD,
 	WB_REASON_FOREIGN_FLUSH,
+	WB_REASON_DONTCACHE,
 
 	WB_REASON_MAX,
 };
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8b3dd145b25e..2fd36608ac73 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2610,6 +2610,7 @@ extern int __must_check file_write_and_wait_range(struct file *file,
 						loff_t start, loff_t end);
 int filemap_flush_range(struct address_space *mapping, loff_t start,
 		loff_t end);
+void filemap_dontcache_kick_writeback(struct address_space *mapping);
 
 static inline int file_write_and_wait(struct file *file)
 {
@@ -2643,10 +2644,7 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 		if (ret)
 			return ret;
 	} else if (iocb->ki_flags & IOCB_DONTCACHE) {
-		struct address_space *mapping = iocb->ki_filp->f_mapping;
-
-		filemap_flush_range(mapping, iocb->ki_pos - count,
-				iocb->ki_pos - 1);
+		filemap_dontcache_kick_writeback(iocb->ki_filp->f_mapping);
 	}
 
 	return count;
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 4d3d8c8f3a1b..9727af542699 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -44,7 +44,8 @@
 	EM( WB_REASON_PERIODIC,			"periodic")		\
 	EM( WB_REASON_FS_FREE_SPACE,		"fs_free_space")	\
 	EM( WB_REASON_FORKER_THREAD,		"forker_thread")	\
-	EMe(WB_REASON_FOREIGN_FLUSH,		"foreign_flush")
+	EM( WB_REASON_FOREIGN_FLUSH,		"foreign_flush")	\
+	EMe(WB_REASON_DONTCACHE,		"dontcache")
 
 WB_WORK_REASON
 

-- 
2.53.0