writeback: Initial tracing support

Trace queue/sched/exec parts of the writeback loop. This provides
insight into when and why flusher threads are scheduled to run. e.g
a sync invocation leaves traces like:

     sync-[...]: writeback_queue: bdi 8:0: sb_dev 8:1 nr_pages=7712 sync_mode=0 kupdate=0 range_cyclic=0 background=0
flush-8:0-[...]: writeback_exec: bdi 8:0: sb_dev 8:1 nr_pages=7712 sync_mode=0 kupdate=0 range_cyclic=0 background=0

This also lays the foundation for adding more writeback tracing to
provide deeper insight into the whole writeback path.

The original tracing code is from Jens Axboe, though this version is
a rewrite as a result of the code being traced changing
significantly.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index c8471b3..73acab4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -26,15 +26,9 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
+#include <linux/tracepoint.h>
 #include "internal.h"
 
-#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
-
-/*
- * We don't actually have pdflush, but this one is exported though /proc...
- */
-int nr_pdflush_threads;
-
 /*
  * Passed into wb_writeback(), essentially a subset of writeback_control
  */
@@ -50,6 +44,21 @@
 	struct completion *done;	/* set if the caller waits */
 };
 
+/*
+ * Include the creation of the trace points after defining the
+ * wb_writeback_work structure so that the definition remains local to this
+ * file.
+ */
+#define CREATE_TRACE_POINTS
+#include <trace/events/writeback.h>
+
+#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)
+
+/*
+ * We don't actually have pdflush, but this one is exported though /proc...
+ */
+int nr_pdflush_threads;
+
 /**
  * writeback_in_progress - determine whether there is writeback in progress
  * @bdi: the device's backing_dev_info structure.
@@ -65,6 +74,8 @@
 static void bdi_queue_work(struct backing_dev_info *bdi,
 		struct wb_writeback_work *work)
 {
+	trace_writeback_queue(bdi, work);
+
 	spin_lock(&bdi->wb_lock);
 	list_add_tail(&work->list, &bdi->work_list);
 	spin_unlock(&bdi->wb_lock);
@@ -74,6 +85,7 @@
 	 * it gets created and wakes up, we'll run this work.
 	 */
 	if (unlikely(!bdi->wb.task)) {
+		trace_writeback_nothread(bdi, work);
 		wake_up_process(default_backing_dev_info.wb.task);
 	} else {
 		struct bdi_writeback *wb = &bdi->wb;
@@ -95,8 +107,10 @@
 	 */
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
-		if (bdi->wb.task)
+		if (bdi->wb.task) {
+			trace_writeback_nowork(bdi);
 			wake_up_process(bdi->wb.task);
+		}
 		return;
 	}
 
@@ -751,6 +765,8 @@
 		if (force_wait)
 			work->sync_mode = WB_SYNC_ALL;
 
+		trace_writeback_exec(bdi, work);
+
 		wrote += wb_writeback(wb, work);
 
 		/*
@@ -805,9 +821,13 @@
 	smp_mb__after_clear_bit();
 	wake_up_bit(&bdi->state, BDI_pending);
 
+	trace_writeback_thread_start(bdi);
+
 	while (!kthread_should_stop()) {
 		pages_written = wb_do_writeback(wb, 0);
 
+		trace_writeback_pages_written(pages_written);
+
 		if (pages_written)
 			last_active = jiffies;
 		else if (wait_jiffies != -1UL) {
@@ -845,6 +865,8 @@
 	 */
 	if (!list_empty(&bdi->work_list))
 		wb_do_writeback(wb, 1);
+
+	trace_writeback_thread_stop(bdi);
 	return 0;
 }
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
new file mode 100644
index 0000000..562fcae
--- /dev/null
+++ b/include/trace/events/writeback.h
@@ -0,0 +1,91 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM writeback
+
+#if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WRITEBACK_H
+
+#include <linux/backing-dev.h>
+#include <linux/writeback.h>
+
+struct wb_writeback_work;
+
+DECLARE_EVENT_CLASS(writeback_work_class,
+	TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work),
+	TP_ARGS(bdi, work),
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(long, nr_pages)
+		__field(dev_t, sb_dev)
+		__field(int, sync_mode)
+		__field(int, for_kupdate)
+		__field(int, range_cyclic)
+		__field(int, for_background)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->nr_pages = work->nr_pages;
+		__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
+		__entry->sync_mode = work->sync_mode;
+		__entry->for_kupdate = work->for_kupdate;
+		__entry->range_cyclic = work->range_cyclic;
+		__entry->for_background	= work->for_background;
+	),
+	TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d "
+		  "kupdate=%d range_cyclic=%d background=%d",
+		  __entry->name,
+		  MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev),
+		  __entry->nr_pages,
+		  __entry->sync_mode,
+		  __entry->for_kupdate,
+		  __entry->range_cyclic,
+		  __entry->for_background
+	)
+);
+#define DEFINE_WRITEBACK_WORK_EVENT(name) \
+DEFINE_EVENT(writeback_work_class, name, \
+	TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), \
+	TP_ARGS(bdi, work))
+DEFINE_WRITEBACK_WORK_EVENT(writeback_nothread);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_queue);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_exec);
+
+TRACE_EVENT(writeback_pages_written,
+	TP_PROTO(long pages_written),
+	TP_ARGS(pages_written),
+	TP_STRUCT__entry(
+		__field(long,		pages)
+	),
+	TP_fast_assign(
+		__entry->pages		= pages_written;
+	),
+	TP_printk("%ld", __entry->pages)
+);
+
+DECLARE_EVENT_CLASS(writeback_class,
+	TP_PROTO(struct backing_dev_info *bdi),
+	TP_ARGS(bdi),
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+	),
+	TP_printk("bdi %s",
+		  __entry->name
+	)
+);
+#define DEFINE_WRITEBACK_EVENT(name) \
+DEFINE_EVENT(writeback_class, name, \
+	TP_PROTO(struct backing_dev_info *bdi), \
+	TP_ARGS(bdi))
+
+DEFINE_WRITEBACK_EVENT(writeback_nowork);
+DEFINE_WRITEBACK_EVENT(writeback_bdi_register);
+DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister);
+DEFINE_WRITEBACK_EVENT(writeback_thread_start);
+DEFINE_WRITEBACK_EVENT(writeback_thread_stop);
+
+#endif /* _TRACE_WRITEBACK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index bceac64..ac78a333 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/device.h>
+#include <trace/events/writeback.h>
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
@@ -518,6 +519,7 @@
 
 	bdi_debug_register(bdi, dev_name(dev));
 	set_bit(BDI_registered, &bdi->state);
+	trace_writeback_bdi_register(bdi);
 exit:
 	return ret;
 }
@@ -578,6 +580,7 @@
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
 
 		if (!bdi_cap_flush_forker(bdi))