Merge branch 'for-2.6.39/stack-plug' into for-2.6.39/core

Conflicts:
	block/blk-core.c
	block/blk-flush.c
	drivers/md/raid1.c
	drivers/md/raid10.c
	drivers/md/raid5.c
	fs/nilfs2/btnode.c
	fs/nilfs2/mdt.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

10 files changed, 72 insertions, 84 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 4ce34fa937d4..96f4094b706d 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -66,8 +66,6 @@ struct backing_dev_info {
 	unsigned int capabilities; /* Device capabilities */
 	congested_fn *congested_fn; /* Function pointer if device is md/dm */
 	void *congested_data;	/* Pointer to aux data for congested func */
-	void (*unplug_io_fn)(struct backing_dev_info *, struct page *);
-	void *unplug_io_data;
 
 	char *name;
 
@@ -251,7 +249,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 
 extern struct backing_dev_info default_backing_dev_info;
 extern struct backing_dev_info noop_backing_dev_info;
-void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page);
 
 int writeback_in_progress(struct backing_dev_info *bdi);
 
@@ -336,17 +333,4 @@ static inline int bdi_sched_wait(void *word)
 	return 0;
 }
 
-static inline void blk_run_backing_dev(struct backing_dev_info *bdi,
-				       struct page *page)
-{
-	if (bdi && bdi->unplug_io_fn)
-		bdi->unplug_io_fn(bdi, page);
-}
-
-static inline void blk_run_address_space(struct address_space *mapping)
-{
-	if (mapping)
-		blk_run_backing_dev(mapping->backing_dev_info, NULL);
-}
-
 #endif		/* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index dddedfc0af81..be50d9e70a7d 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -128,7 +128,6 @@ enum rq_flag_bits {
 	__REQ_NOIDLE,		/* don't anticipate more IO after this one */
 
 	/* bio only flags */
-	__REQ_UNPLUG,		/* unplug the immediately after submission */
 	__REQ_RAHEAD,		/* read ahead, can fail anytime */
 	__REQ_THROTTLED,	/* This bio has already been subjected to
 				 * throttling rules. Don't do it again. */
@@ -152,6 +151,7 @@ enum rq_flag_bits {
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
 	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
+	__REQ_ON_PLUG,		/* on plug list */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -171,7 +171,6 @@ enum rq_flag_bits {
 	 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)
 #define REQ_THROTTLED		(1 << __REQ_THROTTLED)
 
@@ -193,5 +192,6 @@ enum rq_flag_bits {
 #define REQ_IO_STAT		(1 << __REQ_IO_STAT)
 #define REQ_MIXED_MERGE		(1 << __REQ_MIXED_MERGE)
 #define REQ_SECURE		(1 << __REQ_SECURE)
+#define REQ_ON_PLUG		(1 << __REQ_ON_PLUG)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 13b75ca62181..91fa428fa2c1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -196,7 +196,6 @@ typedef void (request_fn_proc) (struct request_queue *q);
 typedef int (make_request_fn) (struct request_queue *q, struct bio *bio);
 typedef int (prep_rq_fn) (struct request_queue *, struct request *);
 typedef void (unprep_rq_fn) (struct request_queue *, struct request *);
-typedef void (unplug_fn) (struct request_queue *);
 
 struct bio_vec;
 struct bvec_merge_data {
@@ -279,7 +278,6 @@ struct request_queue
 	make_request_fn		*make_request_fn;
 	prep_rq_fn		*prep_rq_fn;
 	unprep_rq_fn		*unprep_rq_fn;
-	unplug_fn		*unplug_fn;
 	merge_bvec_fn		*merge_bvec_fn;
 	softirq_done_fn		*softirq_done_fn;
 	rq_timed_out_fn		*rq_timed_out_fn;
@@ -293,12 +291,9 @@ struct request_queue
 	struct request		*boundary_rq;
 
 	/*
-	 * Auto-unplugging state
+	 * Delayed queue handling
 	 */
-	struct timer_list	unplug_timer;
-	int			unplug_thresh;	/* After this many requests */
-	unsigned long		unplug_delay;	/* After this many jiffies */
-	struct work_struct	unplug_work;
+	struct delayed_work	delay_work;
 
 	struct backing_dev_info	backing_dev_info;
 
@@ -394,14 +389,13 @@ struct request_queue
 #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 */
-#define QUEUE_FLAG_ELVSWITCH	8	/* don't use elevator, just do FIFO */
-#define QUEUE_FLAG_BIDI		9	/* queue supports bidi requests */
-#define QUEUE_FLAG_NOMERGES    10	/* disable merge attempts */
-#define QUEUE_FLAG_SAME_COMP   11	/* force complete on same CPU */
-#define QUEUE_FLAG_FAIL_IO     12	/* fake timeout */
-#define QUEUE_FLAG_STACKABLE   13	/* supports request stacking */
-#define QUEUE_FLAG_NONROT      14	/* non-rotational device (SSD) */
+#define QUEUE_FLAG_ELVSWITCH	7	/* don't use elevator, just do FIFO */
+#define QUEUE_FLAG_BIDI		8	/* queue supports bidi requests */
+#define QUEUE_FLAG_NOMERGES     9	/* disable merge attempts */
+#define QUEUE_FLAG_SAME_COMP   10	/* force complete on same CPU */
+#define QUEUE_FLAG_FAIL_IO     11	/* fake timeout */
+#define QUEUE_FLAG_STACKABLE   12	/* supports request stacking */
+#define QUEUE_FLAG_NONROT      13	/* 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_DISCARD     16	/* supports DISCARD */
@@ -479,7 +473,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 	__clear_bit(flag, &q->queue_flags);
 }
 
-#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)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
@@ -674,9 +667,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 extern void blk_rq_unprep_clone(struct request *rq);
 extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
-extern void blk_plug_device(struct request_queue *);
-extern void blk_plug_device_unlocked(struct request_queue *);
-extern int blk_remove_plug(struct request_queue *);
+extern void blk_delay_queue(struct request_queue *, unsigned long);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
 extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 			  unsigned int, void __user *);
@@ -720,7 +711,6 @@ extern int blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
 				  struct request *, int, rq_end_io_fn *);
-extern void blk_unplug(struct request_queue *q);
 
 static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 {
@@ -857,7 +847,6 @@ extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bd
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
-extern void generic_unplug_device(struct request_queue *);
 extern long nr_blockdev_pages(void);
 
 int blk_get_queue(struct request_queue *);
@@ -865,6 +854,31 @@ struct request_queue *blk_alloc_queue(gfp_t);
 struct request_queue *blk_alloc_queue_node(gfp_t, int);
 extern void blk_put_queue(struct request_queue *);
 
+struct blk_plug {
+	unsigned long magic;
+	struct list_head list;
+	unsigned int should_sort;
+};
+
+extern void blk_start_plug(struct blk_plug *);
+extern void blk_finish_plug(struct blk_plug *);
+extern void __blk_flush_plug(struct task_struct *, struct blk_plug *);
+
+static inline void blk_flush_plug(struct task_struct *tsk)
+{
+	struct blk_plug *plug = tsk->plug;
+
+	if (unlikely(plug))
+		__blk_flush_plug(tsk, plug);
+}
+
+static inline bool blk_needs_flush_plug(struct task_struct *tsk)
+{
+	struct blk_plug *plug = tsk->plug;
+
+	return plug && !list_empty(&plug->list);
+}
+
 /*
  * tag stuff
  */
@@ -1283,6 +1297,23 @@ static inline long nr_blockdev_pages(void)
 	return 0;
 }
 
+static inline void blk_start_plug(struct list_head *list)
+{
+}
+
+static inline void blk_finish_plug(struct list_head *list)
+{
+}
+
+static inline void blk_flush_plug(struct task_struct *tsk)
+{
+}
+
+static inline bool blk_needs_flush_plug(struct task_struct *tsk)
+{
+	return false;
+}
+
 #endif /* CONFIG_BLOCK */
 
 #endif
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 68d1fe7b877c..f5df23561b96 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -219,7 +219,6 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size);
 int block_commit_write(struct page *page, unsigned from, unsigned to);
 int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 				get_block_t get_block);
-void block_sync_page(struct page *);
 sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
 int block_truncate_page(struct address_space *, loff_t, get_block_t *);
 int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned,
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 272496d1fae4..e2768834f397 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -286,11 +286,6 @@ void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callback
 int dm_table_complete(struct dm_table *t);
 
 /*
- * Unplug all devices in a table.
- */
-void dm_table_unplug_all(struct dm_table *t);
-
-/*
  * Table reference counting.
  */
 struct dm_table *dm_get_live_table(struct mapped_device *md);
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 39b68edb388d..ec6f72b84477 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -20,7 +20,6 @@ typedef void (elevator_bio_merged_fn) (struct request_queue *,
 typedef int (elevator_dispatch_fn) (struct request_queue *, int);
 
 typedef void (elevator_add_req_fn) (struct request_queue *, struct request *);
-typedef int (elevator_queue_empty_fn) (struct request_queue *);
 typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *);
 typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *);
 typedef int (elevator_may_queue_fn) (struct request_queue *, int);
@@ -46,7 +45,6 @@ struct elevator_ops
 	elevator_activate_req_fn *elevator_activate_req_fn;
 	elevator_deactivate_req_fn *elevator_deactivate_req_fn;
 
-	elevator_queue_empty_fn *elevator_queue_empty_fn;
 	elevator_completed_req_fn *elevator_completed_req_fn;
 
 	elevator_request_list_fn *elevator_former_req_fn;
@@ -101,17 +99,17 @@ struct elevator_queue
  */
 extern void elv_dispatch_sort(struct request_queue *, struct request *);
 extern void elv_dispatch_add_tail(struct request_queue *, struct request *);
-extern void elv_add_request(struct request_queue *, struct request *, int, int);
-extern void __elv_add_request(struct request_queue *, struct request *, int, int);
+extern void elv_add_request(struct request_queue *, struct request *, int);
+extern void __elv_add_request(struct request_queue *, struct request *, int);
 extern void elv_insert(struct request_queue *, struct request *, int);
 extern int elv_merge(struct request_queue *, struct request **, struct bio *);
+extern int elv_try_merge(struct request *, struct bio *);
 extern void elv_merge_requests(struct request_queue *, struct request *,
 			       struct request *);
 extern void elv_merged_request(struct request_queue *, struct request *, int);
 extern void elv_bio_merged(struct request_queue *q, struct request *,
 				struct bio *);
 extern void elv_requeue_request(struct request_queue *, struct request *);
-extern int elv_queue_empty(struct request_queue *);
 extern struct request *elv_former_request(struct request_queue *, struct request *);
 extern struct request *elv_latter_request(struct request_queue *, struct request *);
 extern int elv_register_queue(struct request_queue *q);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e38b50a4b9d2..b95199daa5eb 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -135,16 +135,10 @@ struct inodes_stat_t {
  *			block layer could (in theory) choose to ignore this
  *			request if it runs into resource problems.
  * WRITE		A normal async write. Device will be plugged.
- * WRITE_SYNC_PLUG	Synchronous write. Identical to WRITE, but passes down
+ * WRITE_SYNC		Synchronous write. Identical to WRITE, but passes down
  *			the hint that someone will be waiting on this IO
- *			shortly. The device must still be unplugged explicitly,
- *			WRITE_SYNC_PLUG does not do this as we could be
- *			submitting more writes before we actually wait on any
- *			of them.
- * WRITE_SYNC		Like WRITE_SYNC_PLUG, but also unplugs the device
- *			immediately after submission. The write equivalent
- *			of READ_SYNC.
- * WRITE_ODIRECT_PLUG	Special case write for O_DIRECT only.
+ *			shortly. The write equivalent of READ_SYNC.
+ * WRITE_ODIRECT	Special case write for O_DIRECT only.
  * 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.
@@ -160,18 +154,14 @@ struct inodes_stat_t {
 #define WRITE			RW_MASK
 #define READA			RWA_MASK
 
-#define READ_SYNC		(READ | REQ_SYNC | REQ_UNPLUG)
+#define READ_SYNC		(READ | REQ_SYNC)
 #define READ_META		(READ | REQ_META)
-#define WRITE_SYNC_PLUG		(WRITE | REQ_SYNC | REQ_NOIDLE)
-#define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
-#define WRITE_ODIRECT_PLUG	(WRITE | REQ_SYNC)
+#define WRITE_SYNC		(WRITE | REQ_SYNC | REQ_NOIDLE)
+#define WRITE_ODIRECT		(WRITE | REQ_SYNC)
 #define WRITE_META		(WRITE | REQ_META)
-#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 WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
+#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
+#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
 
 #define SEL_IN		1
 #define SEL_OUT		2
@@ -583,7 +573,6 @@ typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
 struct address_space_operations {
 	int (*writepage)(struct page *page, struct writeback_control *wbc);
 	int (*readpage)(struct file *, struct page *);
-	void (*sync_page)(struct page *);
 
 	/* Write back some dirty pages from this mapping. */
 	int (*writepages)(struct address_space *, struct writeback_control *);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 9c66e994540f..e112b8db2f3c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -298,7 +298,6 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 
 extern void __lock_page(struct page *page);
 extern int __lock_page_killable(struct page *page);
-extern void __lock_page_nosync(struct page *page);
 extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				unsigned int flags);
 extern void unlock_page(struct page *page);
@@ -342,17 +341,6 @@ static inline int lock_page_killable(struct page *page)
 }
 
 /*
- * lock_page_nosync should only be used if we can't pin the page's inode.
- * Doesn't play quite so well with block device plugging.
- */
-static inline void lock_page_nosync(struct page *page)
-{
-	might_sleep();
-	if (!trylock_page(page))
-		__lock_page_nosync(page);
-}
-	
-/*
  * lock_page_or_retry - Lock the page, unless this would block and the
  * caller indicated that it can handle a retry.
  */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 777d8a5ed06b..96ac22643742 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -99,6 +99,7 @@ struct robust_list_head;
 struct bio_list;
 struct fs_struct;
 struct perf_event_context;
+struct blk_plug;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -1429,6 +1430,11 @@ struct task_struct {
 /* stacked block device info */
 	struct bio_list *bio_list;
 
+#ifdef CONFIG_BLOCK
+/* stack plugging */
+	struct blk_plug *plug;
+#endif
+
 /* VM state */
 	struct reclaim_state *reclaim_state;
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4d559325d919..9ee321833b21 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -299,8 +299,6 @@ extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
 					struct page **pagep, swp_entry_t *ent);
 #endif
 
-extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *);
-
 #ifdef CONFIG_SWAP
 /* linux/mm/page_io.c */
 extern int swap_readpage(struct page *);