blktrace: add FLUSH/FUA support

Add FLUSH/FUA support to blktrace. As FLUSH precedes WRITE and/or
FUA follows WRITE, use the same 'F' flag for both cases and
distinguish them by their (relative) position. The end results
look like (other flags might be shown also):

 - WRITE:            W
 - WRITE_FLUSH:      FW
 - WRITE_FUA:        WF
 - WRITE_FLUSH_FUA:  FWF

Note that we reuse TC_BARRIER due to lack of bit space of act_mask
so that the older versions of blktrace tools will report flush
requests as barriers from now on.

Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index bf36654..05c5e61 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -8,6 +8,8 @@
 #include <linux/blkdev.h>
 #include <linux/tracepoint.h>
 
+#define RWBS_LEN	8
+
 DECLARE_EVENT_CLASS(block_rq_with_error,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
@@ -19,7 +21,7 @@
 		__field(  sector_t,	sector			)
 		__field(  unsigned int,	nr_sector		)
 		__field(  int,		errors			)
-		__array(  char,		rwbs,	6		)
+		__array(  char,		rwbs,	RWBS_LEN	)
 		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
 	),
 
@@ -104,7 +106,7 @@
 		__field(  sector_t,	sector			)
 		__field(  unsigned int,	nr_sector		)
 		__field(  unsigned int,	bytes			)
-		__array(  char,		rwbs,	6		)
+		__array(  char,		rwbs,	RWBS_LEN	)
 		__array(  char,         comm,   TASK_COMM_LEN   )
 		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
 	),
@@ -183,7 +185,7 @@
 		__field( dev_t,		dev			)
 		__field( sector_t,	sector			)
 		__field( unsigned int,	nr_sector		)
-		__array( char,		rwbs,	6		)
+		__array( char,		rwbs,	RWBS_LEN	)
 		__array( char,		comm,	TASK_COMM_LEN	)
 	),
 
@@ -222,7 +224,7 @@
 		__field( sector_t,	sector		)
 		__field( unsigned,	nr_sector	)
 		__field( int,		error		)
-		__array( char,		rwbs,	6	)
+		__array( char,		rwbs,	RWBS_LEN)
 	),
 
 	TP_fast_assign(
@@ -249,7 +251,7 @@
 		__field( dev_t,		dev			)
 		__field( sector_t,	sector			)
 		__field( unsigned int,	nr_sector		)
-		__array( char,		rwbs,	6		)
+		__array( char,		rwbs,	RWBS_LEN	)
 		__array( char,		comm,	TASK_COMM_LEN	)
 	),
 
@@ -321,7 +323,7 @@
 		__field( dev_t,		dev			)
 		__field( sector_t,	sector			)
 		__field( unsigned int,	nr_sector		)
-		__array( char,		rwbs,	6		)
+		__array( char,		rwbs,	RWBS_LEN	)
 		__array( char,		comm,	TASK_COMM_LEN	)
         ),
 
@@ -456,7 +458,7 @@
 		__field( dev_t,		dev				)
 		__field( sector_t,	sector				)
 		__field( sector_t,	new_sector			)
-		__array( char,		rwbs,		6		)
+		__array( char,		rwbs,		RWBS_LEN	)
 		__array( char,		comm,		TASK_COMM_LEN	)
 	),
 
@@ -498,7 +500,7 @@
 		__field( unsigned int,	nr_sector	)
 		__field( dev_t,		old_dev		)
 		__field( sector_t,	old_sector	)
-		__array( char,		rwbs,	6	)
+		__array( char,		rwbs,	RWBS_LEN)
 	),
 
 	TP_fast_assign(
@@ -542,7 +544,7 @@
 		__field( unsigned int,	nr_sector	)
 		__field( dev_t,		old_dev		)
 		__field( sector_t,	old_sector	)
-		__array( char,		rwbs,	6	)
+		__array( char,		rwbs,	RWBS_LEN)
 	),
 
 	TP_fast_assign(