Merge branch 'for-2.6.32' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.32' of git://git.kernel.dk/linux-2.6-block: (29 commits)
  block: use blkdev_issue_discard in blk_ioctl_discard
  Make DISCARD_BARRIER and DISCARD_NOBARRIER writes instead of reads
  block: don't assume device has a request list backing in nr_requests store
  block: Optimal I/O limit wrapper
  cfq: choose a new next_req when a request is dispatched
  Seperate read and write statistics of in_flight requests
  aoe: end barrier bios with EOPNOTSUPP
  block: trace bio queueing trial only when it occurs
  block: enable rq CPU completion affinity by default
  cfq: fix the log message after dispatched a request
  block: use printk_once
  cciss: memory leak in cciss_init_one()
  splice: update mtime and atime on files
  block: make blk_iopoll_prep_sched() follow normal 0/1 return convention
  cfq-iosched: get rid of must_alloc flag
  block: use interrupts disabled version of raise_softirq_irqoff()
  block: fix comment in blk-iopoll.c
  block: adjust default budget for blk-iopoll
  block: fix long lines in block/blk-iopoll.c
  block: add blk-iopoll, a NAPI like approach for block devices
  ...

6 files changed, 131 insertions, 56 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 2892b71..5be93f1 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -142,56 +142,51 @@ struct bio {
  *
  * bit 0 -- data direction
  *	If not set, bio is a read from device. If set, it's a write to device.
- * bit 1 -- rw-ahead when set
- * bit 2 -- barrier
+ * bit 1 -- fail fast device errors
+ * bit 2 -- fail fast transport errors
+ * bit 3 -- fail fast driver errors
+ * bit 4 -- rw-ahead when set
+ * bit 5 -- 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.
- * bit 4 -- Unplug the device immediately after submitting this bio.
- * bit 5 -- metadata request
+ * bit 6 -- synchronous I/O hint.
+ * bit 7 -- Unplug the device immediately after submitting this bio.
+ * bit 8 -- metadata request
  *	Used for tracing to differentiate metadata and data IO. May also
  *	get some preferential treatment in the IO scheduler
- * bit 6 -- discard sectors
+ * bit 9 -- 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 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 */
-#define BIO_RW_BARRIER	2
-#define BIO_RW_SYNCIO	3
-#define BIO_RW_UNPLUG	4
-#define BIO_RW_META	5
-#define BIO_RW_DISCARD	6
-#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)))
+enum bio_rw_flags {
+	BIO_RW,
+	BIO_RW_FAILFAST_DEV,
+	BIO_RW_FAILFAST_TRANSPORT,
+	BIO_RW_FAILFAST_DRIVER,
+	/* above flags must match REQ_* */
+	BIO_RW_AHEAD,
+	BIO_RW_BARRIER,
+	BIO_RW_SYNCIO,
+	BIO_RW_UNPLUG,
+	BIO_RW_META,
+	BIO_RW_DISCARD,
+	BIO_RW_NOIDLE,
+};
 
 /*
- * Old defines, these should eventually be replaced by direct usage of
- * bio_rw_flagged()
+ * First four bits must match between bio->bi_rw and rq->cmd_flags, make
+ * that explicit here.
  */
-#define bio_barrier(bio)	bio_rw_flagged(bio, BIO_RW_BARRIER)
-#define bio_sync(bio)		bio_rw_flagged(bio, BIO_RW_SYNCIO)
-#define bio_unplug(bio)		bio_rw_flagged(bio, BIO_RW_UNPLUG)
-#define bio_failfast_dev(bio)	bio_rw_flagged(bio, BIO_RW_FAILFAST_DEV)
-#define bio_failfast_transport(bio)	\
-		bio_rw_flagged(bio, BIO_RW_FAILFAST_TRANSPORT)
-#define bio_failfast_driver(bio) 	\
-		bio_rw_flagged(bio, BIO_RW_FAILFAST_DRIVER)
-#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)
+#define BIO_RW_RQ_MASK		0xf
+
+static inline bool bio_rw_flagged(struct bio *bio, enum bio_rw_flags flag)
+{
+	return (bio->bi_rw & (1 << flag)) != 0;
+}
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
@@ -216,7 +211,7 @@ struct bio {
 #define bio_offset(bio)		bio_iovec((bio))->bv_offset
 #define bio_segments(bio)	((bio)->bi_vcnt - (bio)->bi_idx)
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
-#define bio_empty_barrier(bio)	(bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))
+#define bio_empty_barrier(bio)	(bio_rw_flagged(bio, BIO_RW_BARRIER) && !bio_has_data(bio) && !bio_rw_flagged(bio, BIO_RW_DISCARD))
 
 static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
diff --git a/include/linux/blk-iopoll.h b/include/linux/blk-iopoll.h
new file mode 100644
index 0000000..308734d
--- /dev/null
+++ b/include/linux/blk-iopoll.h
@@ -0,0 +1,48 @@
+#ifndef BLK_IOPOLL_H
+#define BLK_IOPOLL_H
+
+struct blk_iopoll;
+typedef int (blk_iopoll_fn)(struct blk_iopoll *, int);
+
+struct blk_iopoll {
+	struct list_head list;
+	unsigned long state;
+	unsigned long data;
+	int weight;
+	int max;
+	blk_iopoll_fn *poll;
+};
+
+enum {
+	IOPOLL_F_SCHED		= 0,
+	IOPOLL_F_DISABLE	= 1,
+};
+
+/*
+ * Returns 0 if we successfully set the IOPOLL_F_SCHED bit, indicating
+ * that we were the first to acquire this iop for scheduling. If this iop
+ * is currently disabled, return "failure".
+ */
+static inline int blk_iopoll_sched_prep(struct blk_iopoll *iop)
+{
+	if (!test_bit(IOPOLL_F_DISABLE, &iop->state))
+		return test_and_set_bit(IOPOLL_F_SCHED, &iop->state);
+
+	return 1;
+}
+
+static inline int blk_iopoll_disable_pending(struct blk_iopoll *iop)
+{
+	return test_bit(IOPOLL_F_DISABLE, &iop->state);
+}
+
+extern void blk_iopoll_sched(struct blk_iopoll *);
+extern void blk_iopoll_init(struct blk_iopoll *, int, blk_iopoll_fn *);
+extern void blk_iopoll_complete(struct blk_iopoll *);
+extern void __blk_iopoll_complete(struct blk_iopoll *);
+extern void blk_iopoll_enable(struct blk_iopoll *);
+extern void blk_iopoll_disable(struct blk_iopoll *);
+
+extern int blk_iopoll_enabled;
+
+#endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 69103e0..e23a86c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -86,13 +86,14 @@ enum {
 };
 
 /*
- * request type modified bits. first two bits match BIO_RW* bits, important
+ * request type modified bits. first four bits match BIO_RW* bits, important
  */
 enum rq_flag_bits {
 	__REQ_RW,		/* not set, read. set, write */
 	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
 	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
 	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
+	/* above flags must match BIO_RW_* */
 	__REQ_DISCARD,		/* request to discard sectors */
 	__REQ_SORTED,		/* elevator knows about this request */
 	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
@@ -114,6 +115,7 @@ enum rq_flag_bits {
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
 	__REQ_NOIDLE,		/* Don't anticipate more IO after this one */
 	__REQ_IO_STAT,		/* account I/O stat */
+	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -142,6 +144,10 @@ enum rq_flag_bits {
 #define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
 #define REQ_NOIDLE	(1 << __REQ_NOIDLE)
 #define REQ_IO_STAT	(1 << __REQ_IO_STAT)
+#define REQ_MIXED_MERGE	(1 << __REQ_MIXED_MERGE)
+
+#define REQ_FAILFAST_MASK	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | \
+				 REQ_FAILFAST_DRIVER)
 
 #define BLK_MAX_CDB	16
 
@@ -453,10 +459,12 @@ struct request_queue
 #define QUEUE_FLAG_NONROT      14	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 #define QUEUE_FLAG_IO_STAT     15	/* do IO stats */
+#define QUEUE_FLAG_CQ	       16	/* hardware does queuing */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_CLUSTER) |		\
-				 (1 << QUEUE_FLAG_STACKABLE))
+				 (1 << QUEUE_FLAG_STACKABLE)	|	\
+				 (1 << QUEUE_FLAG_SAME_COMP))
 
 static inline int queue_is_locked(struct request_queue *q)
 {
@@ -575,6 +583,7 @@ enum {
 
 #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_queuing(q)	test_bit(QUEUE_FLAG_CQ, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
@@ -828,11 +837,13 @@ static inline void blk_run_address_space(struct address_space *mapping)
 }
 
 /*
- * blk_rq_pos()		: the current sector
- * blk_rq_bytes()	: bytes left in the entire request
- * blk_rq_cur_bytes()	: bytes left in the current segment
- * blk_rq_sectors()	: sectors left in the entire request
- * blk_rq_cur_sectors()	: sectors left in the current segment
+ * blk_rq_pos()			: the current sector
+ * blk_rq_bytes()		: bytes left in the entire request
+ * blk_rq_cur_bytes()		: bytes left in the current segment
+ * blk_rq_err_bytes()		: bytes left till the next error boundary
+ * blk_rq_sectors()		: sectors left in the entire request
+ * blk_rq_cur_sectors()		: sectors left in the current segment
+ * blk_rq_err_sectors()		: sectors left till the next error boundary
  */
 static inline sector_t blk_rq_pos(const struct request *rq)
 {
@@ -849,6 +860,8 @@ static inline int blk_rq_cur_bytes(const struct request *rq)
 	return rq->bio ? bio_cur_bytes(rq->bio) : 0;
 }
 
+extern unsigned int blk_rq_err_bytes(const struct request *rq);
+
 static inline unsigned int blk_rq_sectors(const struct request *rq)
 {
 	return blk_rq_bytes(rq) >> 9;
@@ -859,6 +872,11 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> 9;
 }
 
+static inline unsigned int blk_rq_err_sectors(const struct request *rq)
+{
+	return blk_rq_err_bytes(rq) >> 9;
+}
+
 /*
  * Request issue related functions.
  */
@@ -885,10 +903,12 @@ extern bool blk_end_request(struct request *rq, int error,
 			    unsigned int nr_bytes);
 extern void blk_end_request_all(struct request *rq, int error);
 extern bool blk_end_request_cur(struct request *rq, int error);
+extern bool blk_end_request_err(struct request *rq, int error);
 extern bool __blk_end_request(struct request *rq, int error,
 			      unsigned int nr_bytes);
 extern void __blk_end_request_all(struct request *rq, int error);
 extern bool __blk_end_request_cur(struct request *rq, int error);
+extern bool __blk_end_request_err(struct request *rq, int error);
 
 extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
@@ -915,6 +935,7 @@ extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
+extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
 extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
 extern void blk_set_default_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
@@ -977,15 +998,18 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 }
 
 extern int blkdev_issue_flush(struct block_device *, sector_t *);
-extern int blkdev_issue_discard(struct block_device *,
-				sector_t sector, sector_t nr_sects, gfp_t);
+#define DISCARD_FL_WAIT		0x01	/* wait for completion */
+#define DISCARD_FL_BARRIER	0x02	/* issue DISCARD_BARRIER request */
+extern int blkdev_issue_discard(struct block_device *, sector_t sector,
+		sector_t nr_sects, gfp_t, int 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_KERNEL);
+	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
+				    DISCARD_FL_BARRIER);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 37f5321..b21cf6b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -161,8 +161,8 @@ struct inodes_stat_t {
  * 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 (1 << BIO_RW_DISCARD)
-#define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER))
+#define DISCARD_NOBARRIER (WRITE | (1 << BIO_RW_DISCARD))
+#define DISCARD_BARRIER (DISCARD_NOBARRIER | (1 << BIO_RW_BARRIER))
 
 #define SEL_IN		1
 #define SEL_OUT		2
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 45fc320..44263cb 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -98,7 +98,7 @@ struct hd_struct {
 	int make_it_fail;
 #endif
 	unsigned long stamp;
-	int in_flight;
+	int in_flight[2];
 #ifdef	CONFIG_SMP
 	struct disk_stats *dkstats;
 #else
@@ -322,18 +322,23 @@ static inline void free_part_stats(struct hd_struct *part)
 #define part_stat_sub(cpu, gendiskp, field, subnd)			\
 	part_stat_add(cpu, gendiskp, field, -subnd)
 
-static inline void part_inc_in_flight(struct hd_struct *part)
+static inline void part_inc_in_flight(struct hd_struct *part, int rw)
 {
-	part->in_flight++;
+	part->in_flight[rw]++;
 	if (part->partno)
-		part_to_disk(part)->part0.in_flight++;
+		part_to_disk(part)->part0.in_flight[rw]++;
 }
 
-static inline void part_dec_in_flight(struct hd_struct *part)
+static inline void part_dec_in_flight(struct hd_struct *part, int rw)
 {
-	part->in_flight--;
+	part->in_flight[rw]--;
 	if (part->partno)
-		part_to_disk(part)->part0.in_flight--;
+		part_to_disk(part)->part0.in_flight[rw]--;
+}
+
+static inline int part_in_flight(struct hd_struct *part)
+{
+	return part->in_flight[0] + part->in_flight[1];
 }
 
 /* block/blk-core.c */
@@ -546,6 +551,8 @@ extern ssize_t part_size_show(struct device *dev,
 			      struct device_attribute *attr, char *buf);
 extern ssize_t part_stat_show(struct device *dev,
 			      struct device_attribute *attr, char *buf);
+extern ssize_t part_inflight_show(struct device *dev,
+			      struct device_attribute *attr, char *buf);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 extern ssize_t part_fail_show(struct device *dev,
 			      struct device_attribute *attr, char *buf);
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 1ac57e5..8e9e151 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -348,6 +348,7 @@ enum
 	NET_TX_SOFTIRQ,
 	NET_RX_SOFTIRQ,
 	BLOCK_SOFTIRQ,
+	BLOCK_IOPOLL_SOFTIRQ,
 	TASKLET_SOFTIRQ,
 	SCHED_SOFTIRQ,
 	HRTIMER_SOFTIRQ,