[PATCH 10/11] fs, block: propagate REQ_FLUSH/FUA interface to upper layers

[Tejun Heo <tj@kernel.org>]

Propagate deprecation of REQ_HARDBARRIER and new REQ_FLUSH/FUA
interface to upper layers.

* WRITE_BARRIER is marked deprecated and WRITE_FLUSH, WRITE_FUA and
  WRITE_FLUSH_FUA are added.

* REQ_COMMON_MASK now includes REQ_FLUSH | REQ_FUA so that they are
  copied from bio to request.

* BH_Ordered is marked deprecated and BH_Flush and BH_FUA are added.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
---
 fs/buffer.c                 |   27 ++++++++++++++++-----------
 include/linux/blk_types.h   |    2 +-
 include/linux/buffer_head.h |    8 ++++++--
 include/linux/fs.h          |   20 +++++++++++++-------
 4 files changed, 36 insertions(+), 21 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index d54812b..ec32fbb 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3019,18 +3019,23 @@ int submit_bh(int rw, struct buffer_head * bh)
 	BUG_ON(buffer_delay(bh));
 	BUG_ON(buffer_unwritten(bh));
 
-	/*
-	 * Mask in barrier bit for a write (could be either a WRITE or a
-	 * WRITE_SYNC
-	 */
-	if (buffer_ordered(bh) && (rw & WRITE))
-		rw |= WRITE_BARRIER;
+	if (rw & WRITE) {
+		/* ordered is deprecated, will be removed */
+		if (buffer_ordered(bh))
+			rw |= WRITE_BARRIER;
 
-	/*
-	 * Only clear out a write error when rewriting
-	 */
-	if (test_set_buffer_req(bh) && (rw & WRITE))
-		clear_buffer_write_io_error(bh);
+		if (buffer_flush(bh))
+			rw |= WRITE_FLUSH;
+
+		if (buffer_fua(bh))
+			rw |= WRITE_FUA;
+
+		/*
+		 * Only clear out a write error when rewriting
+		 */
+		if (test_set_buffer_req(bh))
+			clear_buffer_write_io_error(bh);
+	}
 
 	/*
 	 * from here on down, it's all bio -- do the initial mapping,
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 8e9887d..6609fc0 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -164,7 +164,7 @@ enum rq_flag_bits {
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \
-	 REQ_META| REQ_DISCARD | REQ_NOIDLE)
+	 REQ_META | REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
 
 #define REQ_UNPLUG		(1 << __REQ_UNPLUG)
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 1b9ba19..498bd8b 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -32,8 +32,10 @@ enum bh_state_bits {
 	BH_Delay,	/* Buffer is not yet allocated on disk */
 	BH_Boundary,	/* Block is followed by a discontiguity */
 	BH_Write_EIO,	/* I/O error on write */
-	BH_Ordered,	/* ordered write */
-	BH_Eopnotsupp,	/* operation not supported (barrier) */
+	BH_Ordered,	/* DEPRECATED: ordered write */
+	BH_Eopnotsupp,	/* DEPRECATED: operation not supported (barrier) */
+	BH_Flush,	/* Flush device cache before executing IO */
+	BH_FUA,		/* Data should be on non-volatile media on completion */
 	BH_Unwritten,	/* Buffer is allocated on disk but not written */
 	BH_Quiet,	/* Buffer Error Prinks to be quiet */
 
@@ -126,6 +128,8 @@ BUFFER_FNS(Delay, delay)
 BUFFER_FNS(Boundary, boundary)
 BUFFER_FNS(Write_EIO, write_io_error)
 BUFFER_FNS(Ordered, ordered)
+BUFFER_FNS(Flush, flush)
+BUFFER_FNS(FUA, fua)
 BUFFER_FNS(Eopnotsupp, eopnotsupp)
 BUFFER_FNS(Unwritten, unwritten)
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4ebd8eb..6e30b0b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -138,13 +138,13 @@ struct inodes_stat_t {
  * SWRITE_SYNC
  * SWRITE_SYNC_PLUG	Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer.
  *			See SWRITE.
- * WRITE_BARRIER	Like WRITE_SYNC, but tells the block layer that all
- *			previously submitted writes must be safely on storage
- *			before this one is started. Also guarantees that when
- *			this write is complete, it itself is also safely on
- *			storage. Prevents reordering of writes on both sides
- *			of this IO.
- *
+ * WRITE_BARRIER	DEPRECATED. Always fails. Use FLUSH/FUA instead.
+ * WRITE_FLUSH		Like WRITE_SYNC but with preceding cache flush.
+ * WRITE_FUA		Like WRITE_SYNC but data is guaranteed to be on
+ *			non-volatile media on completion.
+ * WRITE_FLUSH_FUA	Combination of WRITE_FLUSH and FUA.  The IO is preceded
+ *			by a cache flush and data is guaranteed to be on
+ *			non-volatile media on completion.
  */
 #define RW_MASK			REQ_WRITE
 #define RWA_MASK		REQ_RAHEAD
@@ -162,6 +162,12 @@ struct inodes_stat_t {
 #define WRITE_META		(WRITE | REQ_META)
 #define WRITE_BARRIER		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
 				 REQ_HARDBARRIER)
+#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH)
+#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FUA)
+#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH | REQ_FUA)
 #define SWRITE_SYNC_PLUG	(SWRITE | REQ_SYNC | REQ_NOIDLE)
 #define SWRITE_SYNC		(SWRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
 
-- 
1.7.1