block: implement REQ_FLUSH/FUA based interface for FLUSH/FUA requests

Now that the backend conversion is complete, export sequenced
FLUSH/FUA capability through REQ_FLUSH/FUA flags.  REQ_FLUSH means the
device cache should be flushed before executing the request.  REQ_FUA
means that the data in the request should be on non-volatile media on
completion.

Block layer will choose the correct way of implementing the semantics
and execute it.  The request may be passed to the device directly if
the device can handle it; otherwise, it will be sequenced using one or
more proxy requests.  Devices will never see REQ_FLUSH and/or FUA
which it doesn't support.

Also, unlike the original REQ_HARDBARRIER, REQ_FLUSH/FUA requests are
never failed with -EOPNOTSUPP.  If the underlying device doesn't
support FLUSH/FUA, the block layer simply make those noop.  IOW, it no
longer distinguishes between writeback cache which doesn't support
cache flush and writethrough/no cache.  Devices which have WB cache
w/o flush are very difficult to come by these days and there's nothing
much we can do anyway, so it doesn't make sense to require everyone to
implement -EOPNOTSUPP handling.  This will simplify filesystems and
block drivers as they can drop -EOPNOTSUPP retry logic for barriers.

* QUEUE_ORDERED_* are removed and QUEUE_FSEQ_* are moved into
  blk-flush.c.

* REQ_FLUSH w/o data can also be directly passed to drivers without
  sequencing but some drivers assume that zero length requests don't
  have rq->bio which isn't true for these requests requiring the use
  of proxy requests.

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

* WRITE_BARRIER is marked deprecated and WRITE_FLUSH, WRITE_FUA and
  WRITE_FLUSH_FUA are added.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

block/blk-core.c

@@ -1204,7 +1204,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (bio->bi_rw & REQ_HARDBARRIER) {
+	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
 		where = ELEVATOR_INSERT_FRONT;
 		goto get_rq;
 	}

block/blk-flush.c

 /*
- * Functions related to barrier IO handling
+ * Functions to sequence FLUSH and FUA writes.
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -9,6 +9,15 @@
 
 #include "blk.h"
 
+/* FLUSH/FUA sequences */
+enum {
+	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
+	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
+	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
+	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
+	QUEUE_FSEQ_DONE		= (1 << 4),
+};
+
 static struct request *queue_next_fseq(struct request_queue *q);
 
 unsigned blk_flush_cur_seq(struct request_queue *q)
@@ -79,6 +88,7 @@ static void queue_flush(struct request_queue *q, struct request *rq,
 
 static struct request *queue_next_fseq(struct request_queue *q)
 {
+	struct request *orig_rq = q->orig_flush_rq;
 	struct request *rq = &q->flush_rq;
 
 	switch (blk_flush_cur_seq(q)) {
@@ -87,12 +97,11 @@ static struct request *queue_next_fseq(struct request_queue *q)
 		break;
 
 	case QUEUE_FSEQ_DATA:
-		/* initialize proxy request and queue it */
+		/* initialize proxy request, inherit FLUSH/FUA and queue it */
 		blk_rq_init(q, rq);
-		init_request_from_bio(rq, q->orig_flush_rq->bio);
-		rq->cmd_flags &= ~REQ_HARDBARRIER;
-		if (q->ordered & QUEUE_ORDERED_DO_FUA)
-			rq->cmd_flags |= REQ_FUA;
+		init_request_from_bio(rq, orig_rq->bio);
+		rq->cmd_flags &= ~(REQ_FLUSH | REQ_FUA);
+		rq->cmd_flags |= orig_rq->cmd_flags & (REQ_FLUSH | REQ_FUA);
 		rq->end_io = flush_data_end_io;
 
 		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
@@ -110,60 +119,58 @@ static struct request *queue_next_fseq(struct request_queue *q)
 
 struct request *blk_do_flush(struct request_queue *q, struct request *rq)
 {
+	unsigned int fflags = q->flush_flags; /* may change, cache it */
+	bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA;
+	bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH);
+	bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA);
 	unsigned skip = 0;
 
-	if (!(rq->cmd_flags & REQ_HARDBARRIER))
+	/*
+	 * Special case.  If there's data but flush is not necessary,
+	 * the request can be issued directly.
+	 *
+	 * Flush w/o data should be able to be issued directly too but
+	 * currently some drivers assume that rq->bio contains
+	 * non-zero data if it isn't NULL and empty FLUSH requests
+	 * getting here usually have bio's without data.
+	 */
+	if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) {
+		rq->cmd_flags &= ~REQ_FLUSH;
+		if (!has_fua)
+			rq->cmd_flags &= ~REQ_FUA;
 		return rq;
+	}
 
+	/*
+	 * Sequenced flushes can't be processed in parallel.  If
+	 * another one is already in progress, queue for later
+	 * processing.
+	 */
 	if (q->flush_seq) {
-		/*
-		 * Sequenced flush is already in progress and they
-		 * can't be processed in parallel.  Queue for later
-		 * processing.
-		 */
 		list_move_tail(&rq->queuelist, &q->pending_flushes);
 		return NULL;
 	}
 
-	if (unlikely(q->next_ordered == QUEUE_ORDERED_NONE)) {
-		/*
-		 * Queue ordering not supported.  Terminate
-		 * with prejudice.
-		 */
-		blk_dequeue_request(rq);
-		__blk_end_request_all(rq, -EOPNOTSUPP);
-		return NULL;
-	}
-
 	/*
 	 * Start a new flush sequence
 	 */
 	q->flush_err = 0;
-	q->ordered = q->next_ordered;
 	q->flush_seq |= QUEUE_FSEQ_STARTED;
 
-	/*
-	 * For an empty barrier, there's no actual BAR request, which
-	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
-	 */
-	if (!blk_rq_sectors(rq))
-		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
-				QUEUE_ORDERED_DO_POSTFLUSH);
-
-	/* stash away the original request */
+	/* adjust FLUSH/FUA of the original request and stash it away */
+	rq->cmd_flags &= ~REQ_FLUSH;
+	if (!has_fua)
+		rq->cmd_flags &= ~REQ_FUA;
 	blk_dequeue_request(rq);
 	q->orig_flush_rq = rq;
 
-	if (!(q->ordered & QUEUE_ORDERED_DO_PREFLUSH))
+	/* skip unneded sequences and return the first one */
+	if (!do_preflush)
 		skip |= QUEUE_FSEQ_PREFLUSH;
-
-	if (!(q->ordered & QUEUE_ORDERED_DO_BAR))
+	if (!blk_rq_sectors(rq))
 		skip |= QUEUE_FSEQ_DATA;
-
-	if (!(q->ordered & QUEUE_ORDERED_DO_POSTFLUSH))
+	if (!do_postflush)
 		skip |= QUEUE_FSEQ_POSTFLUSH;
-
-	/* complete skipped sequences and return the first sequence */
 	return blk_flush_complete_seq(q, skip, 0);
 }
 

block/blk.h

@@ -60,6 +60,9 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 	while (1) {
 		while (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
+			if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) ||
+			    rq == &q->flush_rq)
+				return rq;
 			rq = blk_do_flush(q, rq);
 			if (rq)
 				return rq;

include/linux/blk_types.h

@@ -167,7 +167,7 @@ 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)

include/linux/blkdev.h

@@ -357,7 +357,6 @@ struct request_queue
 	/*
 	 * for flush operations
 	 */
-	unsigned int		ordered, next_ordered;
 	unsigned int		flush_flags;
 	unsigned int		flush_seq;
 	int			flush_err;
@@ -465,40 +464,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 	__clear_bit(flag, &q->queue_flags);
 }
 
-enum {
-	/*
-	 * Hardbarrier is supported with one of the following methods.
-	 *
-	 * NONE		: hardbarrier unsupported
-	 * DRAIN	: ordering by draining is enough
-	 * DRAIN_FLUSH	: ordering by draining w/ pre and post flushes
-	 * DRAIN_FUA	: ordering by draining w/ pre flush and FUA write
-	 */
-	QUEUE_ORDERED_DO_PREFLUSH	= 0x10,
-	QUEUE_ORDERED_DO_BAR		= 0x20,
-	QUEUE_ORDERED_DO_POSTFLUSH	= 0x40,
-	QUEUE_ORDERED_DO_FUA		= 0x80,
-
-	QUEUE_ORDERED_NONE		= 0x00,
-
-	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_DO_BAR,
-	QUEUE_ORDERED_DRAIN_FLUSH	= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_POSTFLUSH,
-	QUEUE_ORDERED_DRAIN_FUA		= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_FUA,
-
-	/*
-	 * FLUSH/FUA sequences.
-	 */
-	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
-	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
-	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
-	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
-	QUEUE_FSEQ_DONE		= (1 << 4),
-};
-
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
@@ -578,7 +543,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync)
  * it already be started by driver.
  */
 #define RQ_NOMERGE_FLAGS	\
-	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER)
+	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER | \
+	 REQ_FLUSH | REQ_FUA)
 #define rq_mergeable(rq)	\
 	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
 	 (((rq)->cmd_flags & REQ_DISCARD) || \

include/linux/buffer_head.h

@@ -32,7 +32,7 @@ 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_Eopnotsupp,	/* operation not supported (barrier) */
+	BH_Eopnotsupp,	/* DEPRECATED: operation not supported (barrier) */
 	BH_Unwritten,	/* Buffer is allocated on disk but not written */
 	BH_Quiet,	/* Buffer Error Prinks to be quiet */
 

include/linux/fs.h

@@ -135,12 +135,13 @@ struct inodes_stat_t {
  *			immediately after submission. The write equivalent
  *			of READ_SYNC.
  * WRITE_ODIRECT_PLUG	Special case write for O_DIRECT only.
- * 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
@@ -158,6 +159,12 @@ 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)
 
 /*
  * These aren't really reads or writes, they pass down information about