Merge branch 'for-2.6.37/barrier' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.37/barrier' of git://git.kernel.dk/linux-2.6-block: (46 commits)
  xen-blkfront: disable barrier/flush write support
  Added blk-lib.c and blk-barrier.c was renamed to blk-flush.c
  block: remove BLKDEV_IFL_WAIT
  aic7xxx_old: removed unused 'req' variable
  block: remove the BH_Eopnotsupp flag
  block: remove the BLKDEV_IFL_BARRIER flag
  block: remove the WRITE_BARRIER flag
  swap: do not send discards as barriers
  fat: do not send discards as barriers
  ext4: do not send discards as barriers
  jbd2: replace barriers with explicit flush / FUA usage
  jbd2: Modify ASYNC_COMMIT code to not rely on queue draining on barrier
  jbd: replace barriers with explicit flush / FUA usage
  nilfs2: replace barriers with explicit flush / FUA usage
  reiserfs: replace barriers with explicit flush / FUA usage
  gfs2: replace barriers with explicit flush / FUA usage
  btrfs: replace barriers with explicit flush / FUA usage
  xfs: replace barriers with explicit flush / FUA usage
  block: pass gfp_mask and flags to sb_issue_discard
  dm: convey that all flushes are processed as empty
  ...

5 files changed, 36 insertions, 106 deletions

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d3662962..0437ab6 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -146,7 +146,6 @@ enum rq_flag_bits {
 	__REQ_FAILED,		/* set if the request failed */
 	__REQ_QUIET,		/* don't worry about errors */
 	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
-	__REQ_ORDERED_COLOR,	/* is before or after barrier */
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_FLUSH,		/* request for cache flush */
@@ -170,7 +169,8 @@ 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_CLONE_MASK		REQ_COMMON_MASK
 
 #define REQ_UNPLUG		(1 << __REQ_UNPLUG)
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)
@@ -187,7 +187,6 @@ enum rq_flag_bits {
 #define REQ_FAILED		(1 << __REQ_FAILED)
 #define REQ_QUIET		(1 << __REQ_QUIET)
 #define REQ_PREEMPT		(1 << __REQ_PREEMPT)
-#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
 #define REQ_ALLOCED		(1 << __REQ_ALLOCED)
 #define REQ_COPY_USER		(1 << __REQ_COPY_USER)
 #define REQ_FLUSH		(1 << __REQ_FLUSH)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 16f7f1b..009b80e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -360,12 +360,14 @@ struct request_queue
 	struct blk_trace	*blk_trace;
 #endif
 	/*
-	 * reserved for flush operations
+	 * for flush operations
 	 */
-	unsigned int		ordered, next_ordered, ordseq;
-	int			orderr, ordcolor;
-	struct request		pre_flush_rq, bar_rq, post_flush_rq;
-	struct request		*orig_bar_rq;
+	unsigned int		flush_flags;
+	unsigned int		flush_seq;
+	int			flush_err;
+	struct request		flush_rq;
+	struct request		*orig_flush_rq;
+	struct list_head	pending_flushes;
 
 	struct mutex		sysfs_lock;
 
@@ -472,56 +474,6 @@ 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
-	 * TAG		: ordering by tag is enough
-	 * TAG_FLUSH	: ordering by tag w/ pre and post flushes
-	 * TAG_FUA	: ordering by tag w/ pre flush and FUA write
-	 */
-	QUEUE_ORDERED_BY_DRAIN		= 0x01,
-	QUEUE_ORDERED_BY_TAG		= 0x02,
-	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_BY_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,
-
-	QUEUE_ORDERED_TAG		= QUEUE_ORDERED_BY_TAG |
-					  QUEUE_ORDERED_DO_BAR,
-	QUEUE_ORDERED_TAG_FLUSH		= QUEUE_ORDERED_TAG |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_POSTFLUSH,
-	QUEUE_ORDERED_TAG_FUA		= QUEUE_ORDERED_TAG |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_FUA,
-
-	/*
-	 * Ordered operation sequence
-	 */
-	QUEUE_ORDSEQ_STARTED	= 0x01,	/* flushing in progress */
-	QUEUE_ORDSEQ_DRAIN	= 0x02,	/* waiting for the queue to be drained */
-	QUEUE_ORDSEQ_PREFLUSH	= 0x04,	/* pre-flushing in progress */
-	QUEUE_ORDSEQ_BAR	= 0x08,	/* original barrier req in progress */
-	QUEUE_ORDSEQ_POSTFLUSH	= 0x10,	/* post-flushing in progress */
-	QUEUE_ORDSEQ_DONE	= 0x20,
-};
-
 #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)
@@ -531,7 +483,6 @@ enum {
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
-#define blk_queue_flushing(q)	((q)->ordseq)
 #define blk_queue_stackable(q)	\
 	test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
@@ -602,7 +553,8 @@ 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) || \
@@ -891,12 +843,8 @@ extern void blk_queue_update_dma_alignment(struct request_queue *, int);
 extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
 extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
+extern void blk_queue_flush(struct request_queue *q, unsigned int flush);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
-extern int blk_queue_ordered(struct request_queue *, unsigned);
-extern bool blk_do_ordered(struct request_queue *, struct request **);
-extern unsigned blk_ordered_cur_seq(struct request_queue *);
-extern unsigned blk_ordered_req_seq(struct request *);
-extern bool blk_ordered_complete_seq(struct request_queue *, unsigned, int);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
@@ -929,27 +877,20 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 		return NULL;
 	return bqt->tag_index[tag];
 }
-enum{
-	BLKDEV_WAIT,	/* wait for completion */
-	BLKDEV_BARRIER,	/* issue request with barrier */
-	BLKDEV_SECURE,	/* secure discard */
-};
-#define BLKDEV_IFL_WAIT		(1 << BLKDEV_WAIT)
-#define BLKDEV_IFL_BARRIER	(1 << BLKDEV_BARRIER)
-#define BLKDEV_IFL_SECURE	(1 << BLKDEV_SECURE)
-extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *,
-			unsigned long);
+
+#define BLKDEV_DISCARD_SECURE  0x01    /* secure discard */
+
+extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
 extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
-static inline int sb_issue_discard(struct super_block *sb,
-				   sector_t block, sector_t nr_blocks)
-{
-	block <<= (sb->s_blocksize_bits - 9);
-	nr_blocks <<= (sb->s_blocksize_bits - 9);
-	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_NOFS,
-				   BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+			sector_t nr_sects, gfp_t gfp_mask);
+static inline int sb_issue_discard(struct super_block *sb, sector_t block,
+		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
+{
+	return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9),
+				    nr_blocks << (sb->s_blocksize_bits - 9),
+				    gfp_mask, flags);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index ec94c12..dd1b25b 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -32,7 +32,6 @@ 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_Unwritten,	/* Buffer is allocated on disk but not written */
 	BH_Quiet,	/* Buffer Error Prinks to be quiet */
 
@@ -124,7 +123,6 @@ BUFFER_FNS(Async_Write, async_write)
 BUFFER_FNS(Delay, delay)
 BUFFER_FNS(Boundary, boundary)
 BUFFER_FNS(Write_EIO, write_io_error)
-BUFFER_FNS(Eopnotsupp, eopnotsupp)
 BUFFER_FNS(Unwritten, unwritten)
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0a81b87e..4f34ff6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -135,12 +135,12 @@ 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_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
@@ -156,16 +156,12 @@ struct inodes_stat_t {
 #define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
 #define WRITE_ODIRECT_PLUG	(WRITE | REQ_SYNC)
 #define WRITE_META		(WRITE | REQ_META)
-#define WRITE_BARRIER		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
-				 REQ_HARDBARRIER)
-
-/*
- * These aren't really reads or writes, they pass down information about
- * parts of device that are now unused by the file system.
- */
-#define DISCARD_NOBARRIER	(WRITE | REQ_DISCARD)
-#define DISCARD_BARRIER		(WRITE | REQ_DISCARD | REQ_HARDBARRIER)
-#define DISCARD_SECURE		(DISCARD_NOBARRIER | REQ_SECURE)
+#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 SEL_IN		1
 #define SEL_OUT		2
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 1723138..d6e7994 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -97,13 +97,9 @@ static inline void scsi_deactivate_tcq(struct scsi_device *sdev, int depth)
 static inline int scsi_populate_tag_msg(struct scsi_cmnd *cmd, char *msg)
 {
         struct request *req = cmd->request;
-	struct scsi_device *sdev = cmd->device;
 
         if (blk_rq_tagged(req)) {
-		if (sdev->ordered_tags && req->cmd_flags & REQ_HARDBARRIER)
-        	        *msg++ = MSG_ORDERED_TAG;
-        	else
-        	        *msg++ = MSG_SIMPLE_TAG;
+		*msg++ = MSG_SIMPLE_TAG;
         	*msg++ = req->tag;
         	return 2;
 	}