4 files changed, 61 insertions, 33 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index bee52abb8a4d..0ec2c594868e 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -24,8 +24,8 @@ struct dentry;
  */
 enum bdi_state {
 	BDI_pdflush,		/* A pdflush thread is working this device */
-	BDI_write_congested,	/* The write queue is getting full */
-	BDI_read_congested,	/* The read queue is getting full */
+	BDI_async_congested,	/* The async (write) queue is getting full */
+	BDI_sync_congested,	/* The sync queue is getting full */
 	BDI_unused,		/* Available bits start here */
 };
 
@@ -215,18 +215,18 @@ static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits)
 
 static inline int bdi_read_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, 1 << BDI_read_congested);
+	return bdi_congested(bdi, 1 << BDI_sync_congested);
 }
 
 static inline int bdi_write_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, 1 << BDI_write_congested);
+	return bdi_congested(bdi, 1 << BDI_async_congested);
 }
 
 static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, (1 << BDI_read_congested)|
-				  (1 << BDI_write_congested));
+	return bdi_congested(bdi, (1 << BDI_sync_congested) |
+				  (1 << BDI_async_congested));
 }
 
 void clear_bdi_congested(struct backing_dev_info *bdi, int rw);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b05b1d4d17d2..b900d2c67d29 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -145,20 +145,21 @@ struct bio {
  * bit 2 -- barrier
  *	Insert a serialization point in the IO queue, forcing previously
  *	submitted IO to be completed before this one is issued.
- * bit 3 -- synchronous I/O hint: the block layer will unplug immediately
- *	Note that this does NOT indicate that the IO itself is sync, just
- *	that the block layer will not postpone issue of this IO by plugging.
- * bit 4 -- metadata request
+ * bit 3 -- synchronous I/O hint.
+ * bit 4 -- Unplug the device immediately after submitting this bio.
+ * bit 5 -- metadata request
  *	Used for tracing to differentiate metadata and data IO. May also
  *	get some preferential treatment in the IO scheduler
- * bit 5 -- discard sectors
+ * bit 6 -- discard sectors
  *	Informs the lower level device that this range of sectors is no longer
  *	used by the file system and may thus be freed by the device. Used
  *	for flash based storage.
- * bit 6 -- fail fast device errors
- * bit 7 -- fail fast transport errors
- * bit 8 -- fail fast driver errors
+ * bit 7 -- fail fast device errors
+ * bit 8 -- fail fast transport errors
+ * bit 9 -- fail fast driver errors
  *	Don't want driver retries for any fast fail whatever the reason.
+ * bit 10 -- Tell the IO scheduler not to wait for more requests after this
+	one has been submitted, even if it is a SYNC request.
  */
 #define BIO_RW		0	/* Must match RW in req flags (blkdev.h) */
 #define BIO_RW_AHEAD	1	/* Must match FAILFAST in req flags */
@@ -170,6 +171,7 @@ struct bio {
 #define BIO_RW_FAILFAST_DEV		7
 #define BIO_RW_FAILFAST_TRANSPORT	8
 #define BIO_RW_FAILFAST_DRIVER		9
+#define BIO_RW_NOIDLE	10
 
 #define bio_rw_flagged(bio, flag)	((bio)->bi_rw & (1 << (flag)))
 
@@ -188,6 +190,7 @@ struct bio {
 #define bio_rw_ahead(bio)	bio_rw_flagged(bio, BIO_RW_AHEAD)
 #define bio_rw_meta(bio)	bio_rw_flagged(bio, BIO_RW_META)
 #define bio_discard(bio)	bio_rw_flagged(bio, BIO_RW_DISCARD)
+#define bio_noidle(bio)		bio_rw_flagged(bio, BIO_RW_NOIDLE)
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 465d6babc847..e03660964e02 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -38,6 +38,10 @@ struct request;
 typedef void (rq_end_io_fn)(struct request *, int);
 
 struct request_list {
+	/*
+	 * count[], starved[], and wait[] are indexed by
+	 * BLK_RW_SYNC/BLK_RW_ASYNC
+	 */
 	int count[2];
 	int starved[2];
 	int elvpriv;
@@ -66,6 +70,11 @@ enum rq_cmd_type_bits {
 	REQ_TYPE_ATA_PC,
 };
 
+enum {
+	BLK_RW_ASYNC	= 0,
+	BLK_RW_SYNC	= 1,
+};
+
 /*
  * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being
  * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a
@@ -103,12 +112,13 @@ enum rq_flag_bits {
 	__REQ_QUIET,		/* don't worry about errors */
 	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
 	__REQ_ORDERED_COLOR,	/* is before or after barrier */
-	__REQ_RW_SYNC,		/* request is sync (O_DIRECT) */
+	__REQ_RW_SYNC,		/* request is sync (sync write or read) */
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_RW_META,		/* metadata io request */
 	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
 	__REQ_UNPLUG,		/* unplug queue on submission */
+	__REQ_NOIDLE,		/* Don't anticipate more IO after this one */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -136,6 +146,7 @@ enum rq_flag_bits {
 #define REQ_COPY_USER	(1 << __REQ_COPY_USER)
 #define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
 #define REQ_UNPLUG	(1 << __REQ_UNPLUG)
+#define REQ_NOIDLE	(1 << __REQ_NOIDLE)
 
 #define BLK_MAX_CDB	16
 
@@ -438,8 +449,8 @@ struct request_queue
 #define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
 #define QUEUE_FLAG_STOPPED	2	/* queue is stopped */
-#define	QUEUE_FLAG_READFULL	3	/* read queue has been filled */
-#define QUEUE_FLAG_WRITEFULL	4	/* write queue has been filled */
+#define	QUEUE_FLAG_SYNCFULL	3	/* read queue has been filled */
+#define QUEUE_FLAG_ASYNCFULL	4	/* write queue has been filled */
 #define QUEUE_FLAG_DEAD		5	/* queue being torn down */
 #define QUEUE_FLAG_REENTER	6	/* Re-entrancy avoidance */
 #define QUEUE_FLAG_PLUGGED	7	/* queue is plugged */
@@ -611,32 +622,42 @@ enum {
 #define rq_data_dir(rq)		((rq)->cmd_flags & 1)
 
 /*
- * We regard a request as sync, if it's a READ or a SYNC write.
+ * We regard a request as sync, if either a read or a sync write
  */
-#define rq_is_sync(rq)		(rq_data_dir((rq)) == READ || (rq)->cmd_flags & REQ_RW_SYNC)
+static inline bool rw_is_sync(unsigned int rw_flags)
+{
+	return !(rw_flags & REQ_RW) || (rw_flags & REQ_RW_SYNC);
+}
+
+static inline bool rq_is_sync(struct request *rq)
+{
+	return rw_is_sync(rq->cmd_flags);
+}
+
 #define rq_is_meta(rq)		((rq)->cmd_flags & REQ_RW_META)
+#define rq_noidle(rq)		((rq)->cmd_flags & REQ_NOIDLE)
 
-static inline int blk_queue_full(struct request_queue *q, int rw)
+static inline int blk_queue_full(struct request_queue *q, int sync)
 {
-	if (rw == READ)
-		return test_bit(QUEUE_FLAG_READFULL, &q->queue_flags);
-	return test_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags);
+	if (sync)
+		return test_bit(QUEUE_FLAG_SYNCFULL, &q->queue_flags);
+	return test_bit(QUEUE_FLAG_ASYNCFULL, &q->queue_flags);
 }
 
-static inline void blk_set_queue_full(struct request_queue *q, int rw)
+static inline void blk_set_queue_full(struct request_queue *q, int sync)
 {
-	if (rw == READ)
-		queue_flag_set(QUEUE_FLAG_READFULL, q);
+	if (sync)
+		queue_flag_set(QUEUE_FLAG_SYNCFULL, q);
 	else
-		queue_flag_set(QUEUE_FLAG_WRITEFULL, q);
+		queue_flag_set(QUEUE_FLAG_ASYNCFULL, q);
 }
 
-static inline void blk_clear_queue_full(struct request_queue *q, int rw)
+static inline void blk_clear_queue_full(struct request_queue *q, int sync)
 {
-	if (rw == READ)
-		queue_flag_clear(QUEUE_FLAG_READFULL, q);
+	if (sync)
+		queue_flag_clear(QUEUE_FLAG_SYNCFULL, q);
 	else
-		queue_flag_clear(QUEUE_FLAG_WRITEFULL, q);
+		queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q);
 }
 
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a09e17c8f5fd..cae5720f431c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -95,8 +95,12 @@ struct inodes_stat_t {
 #define SWRITE 3	/* for ll_rw_block() - wait for buffer lock */
 #define READ_SYNC	(READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
 #define READ_META	(READ | (1 << BIO_RW_META))
-#define WRITE_SYNC	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
-#define SWRITE_SYNC	(SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
+#define WRITE_SYNC_PLUG	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
+#define WRITE_SYNC	(WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
+#define WRITE_ODIRECT	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
+#define SWRITE_SYNC_PLUG	\
+			(SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
+#define SWRITE_SYNC	(SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
 #define WRITE_BARRIER	(WRITE | (1 << BIO_RW_BARRIER))
 #define DISCARD_NOBARRIER (1 << BIO_RW_DISCARD)
 #define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER))