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

* 'for-linus' of git://git.kernel.dk/linux-2.6-block: (28 commits)
  cfq-iosched: add close cooperator code
  cfq-iosched: log responsible 'cfqq' in idle timer arm
  cfq-iosched: tweak kick logic a bit more
  cfq-iosched: no need to save interrupts in cfq_kick_queue()
  brd: fix cacheflushing
  brd: support barriers
  swap: Remove code handling bio_alloc failure with __GFP_WAIT
  gfs2: Remove code handling bio_alloc failure with __GFP_WAIT
  ext4: Remove code handling bio_alloc failure with __GFP_WAIT
  dio: Remove code handling bio_alloc failure with __GFP_WAIT
  block: Remove code handling bio_alloc failure with __GFP_WAIT
  bio: add documentation to bio_alloc()
  splice: add helpers for locking pipe inode
  splice: remove generic_file_splice_write_nolock()
  ocfs2: fix i_mutex locking in ocfs2_splice_to_file()
  splice: fix i_mutex locking in generic_splice_write()
  splice: remove i_mutex locking in splice_from_pipe()
  splice: split up __splice_from_pipe()
  block: fix SG_IO to return a proper error value
  cfq-iosched: don't delay queue kick for a merged request
  ...

Documentation/block/biodoc.txt

@@ -1040,23 +1040,21 @@ Front merges are handled by the binary trees in AS and deadline schedulers.
 iii. Plugging the queue to batch requests in anticipation of opportunities for
      merge/sort optimizations
 
-This is just the same as in 2.4 so far, though per-device unplugging
-support is anticipated for 2.5. Also with a priority-based i/o scheduler,
-such decisions could be based on request priorities.
-
 Plugging is an approach that the current i/o scheduling algorithm resorts to so
 that it collects up enough requests in the queue to be able to take
 advantage of the sorting/merging logic in the elevator. If the
 queue is empty when a request comes in, then it plugs the request queue
-(sort of like plugging the bottom of a vessel to get fluid to build up)
+(sort of like plugging the bath tub of a vessel to get fluid to build up)
 till it fills up with a few more requests, before starting to service
 the requests. This provides an opportunity to merge/sort the requests before
 passing them down to the device. There are various conditions when the queue is
 unplugged (to open up the flow again), either through a scheduled task or
 could be on demand. For example wait_on_buffer sets the unplugging going
-(by running tq_disk) so the read gets satisfied soon. So in the read case,
-the queue gets explicitly unplugged as part of waiting for completion,
-in fact all queues get unplugged as a side-effect.
+through sync_buffer() running blk_run_address_space(mapping). Or the caller
+can do it explicity through blk_unplug(bdev). So in the read case,
+the queue gets explicitly unplugged as part of waiting for completion on that
+buffer. For page driven IO, the address space ->sync_page() takes care of
+doing the blk_run_address_space().
 
 Aside:
   This is kind of controversial territory, as it's not clear if plugging is
@@ -1067,11 +1065,6 @@ Aside:
   multi-page bios being queued in one shot, we may not need to wait to merge
   a big request from the broken up pieces coming by.
 
-  Per-queue granularity unplugging (still a Todo) may help reduce some of the
-  concerns with just a single tq_disk flush approach. Something like
-  blk_kick_queue() to unplug a specific queue (right away ?)
-  or optionally, all queues, is in the plan.
-
 4.4 I/O contexts
 I/O contexts provide a dynamically allocated per process data area. They may
 be used in I/O schedulers, and in the block layer (could be used for IO statis,

block/blk-barrier.c

@@ -319,9 +319,6 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 		return -ENXIO;
 
 	bio = bio_alloc(GFP_KERNEL, 0);
-	if (!bio)
-		return -ENOMEM;
-
 	bio->bi_end_io = bio_end_empty_barrier;
 	bio->bi_private = &wait;
 	bio->bi_bdev = bdev;

block/blk-sysfs.c

@@ -209,14 +209,14 @@ static ssize_t queue_iostats_store(struct request_queue *q, const char *page,
 	ssize_t ret = queue_var_store(&stats, page, count);
 
 	spin_lock_irq(q->queue_lock);
-	elv_quisce_start(q);
+	elv_quiesce_start(q);
 
 	if (stats)
 		queue_flag_set(QUEUE_FLAG_IO_STAT, q);
 	else
 		queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
 
-	elv_quisce_end(q);
+	elv_quiesce_end(q);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;

block/blk.h

@@ -70,8 +70,8 @@ void blk_queue_congestion_threshold(struct request_queue *q);
 
 int blk_dev_init(void);
 
-void elv_quisce_start(struct request_queue *q);
-void elv_quisce_end(struct request_queue *q);
+void elv_quiesce_start(struct request_queue *q);
+void elv_quiesce_end(struct request_queue *q);
 
 
 /*

block/elevator.c

@@ -590,7 +590,7 @@ void elv_drain_elevator(struct request_queue *q)
 /*
  * Call with queue lock held, interrupts disabled
  */
-void elv_quisce_start(struct request_queue *q)
+void elv_quiesce_start(struct request_queue *q)
 {
 	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
 
@@ -607,7 +607,7 @@ void elv_quisce_start(struct request_queue *q)
 	}
 }
 
-void elv_quisce_end(struct request_queue *q)
+void elv_quiesce_end(struct request_queue *q)
 {
 	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
 }
@@ -1126,7 +1126,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 * Turn on BYPASS and drain all requests w/ elevator private data
 	 */
 	spin_lock_irq(q->queue_lock);
-	elv_quisce_start(q);
+	elv_quiesce_start(q);
 
 	/*
 	 * Remember old elevator.
@@ -1150,7 +1150,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 */
 	elevator_exit(old_elevator);
 	spin_lock_irq(q->queue_lock);
-	elv_quisce_end(q);
+	elv_quiesce_end(q);
 	spin_unlock_irq(q->queue_lock);
 
 	blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);

block/ioctl.c

@@ -146,8 +146,6 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 		struct bio *bio;
 
 		bio = bio_alloc(GFP_KERNEL, 0);
-		if (!bio)
-			return -ENOMEM;
 
 		bio->bi_end_io = blk_ioc_discard_endio;
 		bio->bi_bdev = bdev;

block/scsi_ioctl.c

@@ -217,7 +217,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 				 struct bio *bio)
 {
-	int ret = 0;
+	int r, ret = 0;
 
 	/*
 	 * fill in all the output members
@@ -242,7 +242,9 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 			ret = -EFAULT;
 	}
 
-	blk_rq_unmap_user(bio);
+	r = blk_rq_unmap_user(bio);
+	if (!ret)
+		ret = r;
 	blk_put_request(rq);
 
 	return ret;

drivers/block/brd.c

@@ -275,8 +275,10 @@ static int brd_do_bvec(struct brd_device *brd, struct page *page,
 	if (rw == READ) {
 		copy_from_brd(mem + off, brd, sector, len);
 		flush_dcache_page(page);
-	} else
+	} else {
+		flush_dcache_page(page);
 		copy_to_brd(brd, mem + off, sector, len);
+	}
 	kunmap_atomic(mem, KM_USER0);
 
 out:
@@ -436,6 +438,7 @@ static struct brd_device *brd_alloc(int i)
 	if (!brd->brd_queue)
 		goto out_free_dev;
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
+	blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG, NULL);
 	blk_queue_max_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 

drivers/md/dm-bio-list.h

-/*
- * Copyright (C) 2004 Red Hat UK Ltd.
- *
- * This file is released under the GPL.
- */
-
-#ifndef DM_BIO_LIST_H
-#define DM_BIO_LIST_H
-
-#include <linux/bio.h>
-
-#ifdef CONFIG_BLOCK
-
-struct bio_list {
-	struct bio *head;
-	struct bio *tail;
-};
-
-static inline int bio_list_empty(const struct bio_list *bl)
-{
-	return bl->head == NULL;
-}
-
-static inline void bio_list_init(struct bio_list *bl)
-{
-	bl->head = bl->tail = NULL;
-}
-
-#define bio_list_for_each(bio, bl) \
-	for (bio = (bl)->head; bio; bio = bio->bi_next)
-
-static inline unsigned bio_list_size(const struct bio_list *bl)
-{
-	unsigned sz = 0;
-	struct bio *bio;
-
-	bio_list_for_each(bio, bl)
-		sz++;
-
-	return sz;
-}
-
-static inline void bio_list_add(struct bio_list *bl, struct bio *bio)
-{
-	bio->bi_next = NULL;
-
-	if (bl->tail)
-		bl->tail->bi_next = bio;
-	else
-		bl->head = bio;
-
-	bl->tail = bio;
-}
-
-static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio)
-{
-	bio->bi_next = bl->head;
-
-	bl->head = bio;
-
-	if (!bl->tail)
-		bl->tail = bio;
-}
-
-static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2)
-{
-	if (!bl2->head)
-		return;
-
-	if (bl->tail)
-		bl->tail->bi_next = bl2->head;
-	else
-		bl->head = bl2->head;
-
-	bl->tail = bl2->tail;
-}
-
-static inline void bio_list_merge_head(struct bio_list *bl,
-				       struct bio_list *bl2)
-{
-	if (!bl2->head)
-		return;
-
-	if (bl->head)
-		bl2->tail->bi_next = bl->head;
-	else
-		bl->tail = bl2->tail;
-
-	bl->head = bl2->head;
-}
-
-static inline struct bio *bio_list_pop(struct bio_list *bl)
-{
-	struct bio *bio = bl->head;
-
-	if (bio) {
-		bl->head = bl->head->bi_next;
-		if (!bl->head)
-			bl->tail = NULL;
-
-		bio->bi_next = NULL;
-	}
-
-	return bio;
-}
-
-static inline struct bio *bio_list_get(struct bio_list *bl)
-{
-	struct bio *bio = bl->head;
-
-	bl->head = bl->tail = NULL;
-
-	return bio;
-}
-
-#endif /* CONFIG_BLOCK */
-#endif

drivers/md/dm-delay.c

@@ -15,8 +15,6 @@
 
 #include <linux/device-mapper.h>
 
-#include "dm-bio-list.h"
-
 #define DM_MSG_PREFIX "delay"
 
 struct delay_c {

drivers/md/dm-mpath.c

@@ -8,7 +8,6 @@
 #include <linux/device-mapper.h>
 
 #include "dm-path-selector.h"
-#include "dm-bio-list.h"
 #include "dm-bio-record.h"
 #include "dm-uevent.h"
 

drivers/md/dm-raid1.c

@@ -5,7 +5,6 @@
  * This file is released under the GPL.
  */
 
-#include "dm-bio-list.h"
 #include "dm-bio-record.h"
 
 #include <linux/init.h>

drivers/md/dm-region-hash.c

@@ -14,7 +14,6 @@
 #include <linux/vmalloc.h>
 
 #include "dm.h"
-#include "dm-bio-list.h"
 
 #define	DM_MSG_PREFIX	"region hash"
 

drivers/md/dm-snap.c

@@ -22,7 +22,6 @@
 #include <linux/workqueue.h>
 
 #include "dm-exception-store.h"
-#include "dm-bio-list.h"
 
 #define DM_MSG_PREFIX "snapshots"
 

drivers/md/dm.c

@@ -6,7 +6,6 @@
  */
 
 #include "dm.h"
-#include "dm-bio-list.h"
 #include "dm-uevent.h"
 
 #include <linux/init.h>

drivers/md/raid1.c

@@ -35,7 +35,6 @@
 #include <linux/blkdev.h>
 #include <linux/seq_file.h>
 #include "md.h"
-#include "dm-bio-list.h"
 #include "raid1.h"
 #include "bitmap.h"
 

drivers/md/raid10.c

@@ -22,7 +22,6 @@
 #include <linux/blkdev.h>
 #include <linux/seq_file.h>
 #include "md.h"
-#include "dm-bio-list.h"
 #include "raid10.h"
 #include "bitmap.h"
 

fs/bio.c

@@ -348,6 +348,24 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 	return NULL;
 }
 
+/**
+ * bio_alloc - allocate a bio for I/O
+ * @gfp_mask:   the GFP_ mask given to the slab allocator
+ * @nr_iovecs:	number of iovecs to pre-allocate
+ *
+ * Description:
+ *   bio_alloc will allocate a bio and associated bio_vec array that can hold
+ *   at least @nr_iovecs entries. Allocations will be done from the
+ *   fs_bio_set. Also see @bio_alloc_bioset.
+ *
+ *   If %__GFP_WAIT is set, then bio_alloc will always be able to allocate
+ *   a bio. This is due to the mempool guarantees. To make this work, callers
+ *   must never allocate more than 1 bio at the time from this pool. Callers
+ *   that need to allocate more than 1 bio must always submit the previously
+ *   allocate bio for IO before attempting to allocate a new one. Failure to
+ *   do so can cause livelocks under memory pressure.
+ *
+ **/
 struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
 {
 	struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);

fs/buffer.c

@@ -547,7 +547,7 @@ static int osync_buffers_list(spinlock_t *lock, struct list_head *list)
 	return err;
 }
 
-void do_thaw_all(unsigned long unused)
+void do_thaw_all(struct work_struct *work)
 {
 	struct super_block *sb;
 	char b[BDEVNAME_SIZE];
@@ -567,6 +567,7 @@ void do_thaw_all(unsigned long unused)
 			goto restart;
 	}
 	spin_unlock(&sb_lock);
+	kfree(work);
 	printk(KERN_WARNING "Emergency Thaw complete\n");
 }
 
@@ -577,7 +578,13 @@ void do_thaw_all(unsigned long unused)
  */
 void emergency_thaw_all(void)
 {
-	pdflush_operation(do_thaw_all, 0);
+	struct work_struct *work;
+
+	work = kmalloc(sizeof(*work), GFP_ATOMIC);
+	if (work) {
+		INIT_WORK(work, do_thaw_all);
+		schedule_work(work);
+	}
 }
 
 /**

fs/direct-io.c

@@ -307,8 +307,6 @@ dio_bio_alloc(struct dio *dio, struct block_device *bdev,
 	struct bio *bio;
 
 	bio = bio_alloc(GFP_KERNEL, nr_vecs);
-	if (bio == NULL)
-		return -ENOMEM;
 
 	bio->bi_bdev = bdev;
 	bio->bi_sector = first_sector;

fs/ext4/extents.c

@@ -2416,8 +2416,6 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
 			len = ee_len;
 
 		bio = bio_alloc(GFP_NOIO, len);
-		if (!bio)
-			return -ENOMEM;
 		bio->bi_sector = ee_pblock;
 		bio->bi_bdev   = inode->i_sb->s_bdev;
 

fs/gfs2/ops_fstype.c

@@ -272,11 +272,6 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
 	lock_page(page);
 
 	bio = bio_alloc(GFP_NOFS, 1);
-	if (unlikely(!bio)) {
-		__free_page(page);
-		return -ENOBUFS;
-	}
-
 	bio->bi_sector = sector * (sb->s_blocksize >> 9);
 	bio->bi_bdev = sb->s_bdev;
 	bio_add_page(bio, page, PAGE_SIZE, 0);

fs/inode.c

@@ -1470,42 +1470,6 @@ static void __wait_on_freeing_inode(struct inode *inode)
 	spin_lock(&inode_lock);
 }
 
-/*
- * We rarely want to lock two inodes that do not have a parent/child
- * relationship (such as directory, child inode) simultaneously. The
- * vast majority of file systems should be able to get along fine
- * without this. Do not use these functions except as a last resort.
- */
-void inode_double_lock(struct inode *inode1, struct inode *inode2)
-{
-	if (inode1 == NULL || inode2 == NULL || inode1 == inode2) {
-		if (inode1)
-			mutex_lock(&inode1->i_mutex);
-		else if (inode2)
-			mutex_lock(&inode2->i_mutex);
-		return;
-	}
-
-	if (inode1 < inode2) {
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
-	} else {
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
-	}
-}
-EXPORT_SYMBOL(inode_double_lock);
-
-void inode_double_unlock(struct inode *inode1, struct inode *inode2)
-{
-	if (inode1)
-		mutex_unlock(&inode1->i_mutex);
-
-	if (inode2 && inode2 != inode1)
-		mutex_unlock(&inode2->i_mutex);
-}
-EXPORT_SYMBOL(inode_double_unlock);
-
 static __initdata unsigned long ihash_entries;
 static int __init set_ihash_entries(char *str)
 {

fs/ocfs2/file.c

@@ -1912,6 +1912,22 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	return written ? written : ret;
 }
 
+static int ocfs2_splice_to_file(struct pipe_inode_info *pipe,
+				struct file *out,
+				struct splice_desc *sd)
+{
+	int ret;
+
+	ret = ocfs2_prepare_inode_for_write(out->f_path.dentry,	&sd->pos,
+					    sd->total_len, 0, NULL);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	return splice_from_pipe_feed(pipe, sd, pipe_to_file);
+}
+
 static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
 				       struct file *out,
 				       loff_t *ppos,
@@ -1919,39 +1935,77 @@ static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
 				       unsigned int flags)
 {
 	int ret;
-	struct inode *inode = out->f_path.dentry->d_inode;
+	struct address_space *mapping = out->f_mapping;
+	struct inode *inode = mapping->host;
+	struct splice_desc sd = {
+		.total_len = len,
+		.flags = flags,
+		.pos = *ppos,
+		.u.file = out,
+	};
 
 	mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", out, pipe,
 		   (unsigned int)len,
 		   out->f_path.dentry->d_name.len,
 		   out->f_path.dentry->d_name.name);
 
-	mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
+	if (pipe->inode)
+		mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_PARENT);
 
-	ret = ocfs2_rw_lock(inode, 1);
-	if (ret < 0) {
-		mlog_errno(ret);
-		goto out;
-	}
+	splice_from_pipe_begin(&sd);
+	do {
+		ret = splice_from_pipe_next(pipe, &sd);
+		if (ret <= 0)
+			break;
 
-	ret = ocfs2_prepare_inode_for_write(out->f_path.dentry, ppos, len, 0,
-					    NULL);
-	if (ret < 0) {
+		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+		ret = ocfs2_rw_lock(inode, 1);
+		if (ret < 0)
 			mlog_errno(ret);
-		goto out_unlock;
+		else {
+			ret = ocfs2_splice_to_file(pipe, out, &sd);
+			ocfs2_rw_unlock(inode, 1);
 		}
+		mutex_unlock(&inode->i_mutex);
+	} while (ret > 0);
+	splice_from_pipe_end(pipe, &sd);
 
-	if (pipe->inode)
-		mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_CHILD);
-	ret = generic_file_splice_write_nolock(pipe, out, ppos, len, flags);
 	if (pipe->inode)
 		mutex_unlock(&pipe->inode->i_mutex);
 
-out_unlock:
+	if (sd.num_spliced)
+		ret = sd.num_spliced;
+
+	if (ret > 0) {
+		unsigned long nr_pages;
+
+		*ppos += ret;
+		nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+		/*
+		 * If file or inode is SYNC and we actually wrote some data,
+		 * sync it.
+		 */
+		if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) {
+			int err;
+
+			mutex_lock(&inode->i_mutex);
+			err = ocfs2_rw_lock(inode, 1);
+			if (err < 0) {
+				mlog_errno(err);
+			} else {
+				err = generic_osync_inode(inode, mapping,
+						  OSYNC_METADATA|OSYNC_DATA);
 				ocfs2_rw_unlock(inode, 1);
-out:
+			}
 			mutex_unlock(&inode->i_mutex);
 
+			if (err)
+				ret = err;
+		}
+		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
+	}
+
 	mlog_exit(ret);
 	return ret;
 }

fs/pipe.c

@@ -37,6 +37,42 @@
  * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09
  */
 
+static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass)
+{
+	if (pipe->inode)
+		mutex_lock_nested(&pipe->inode->i_mutex, subclass);
+}
+
+void pipe_lock(struct pipe_inode_info *pipe)
+{
+	/*
+	 * pipe_lock() nests non-pipe inode locks (for writing to a file)
+	 */
+	pipe_lock_nested(pipe, I_MUTEX_PARENT);
+}
+EXPORT_SYMBOL(pipe_lock);
+
+void pipe_unlock(struct pipe_inode_info *pipe)
+{
+	if (pipe->inode)
+		mutex_unlock(&pipe->inode->i_mutex);
+}
+EXPORT_SYMBOL(pipe_unlock);
+
+void pipe_double_lock(struct pipe_inode_info *pipe1,
+		      struct pipe_inode_info *pipe2)
+{
+	BUG_ON(pipe1 == pipe2);
+
+	if (pipe1 < pipe2) {
+		pipe_lock_nested(pipe1, I_MUTEX_PARENT);
+		pipe_lock_nested(pipe2, I_MUTEX_CHILD);
+	} else {
+		pipe_lock_nested(pipe2, I_MUTEX_CHILD);
+		pipe_lock_nested(pipe1, I_MUTEX_PARENT);
+	}
+}
+
 /* Drop the inode semaphore and wait for a pipe event, atomically */
 void pipe_wait(struct pipe_inode_info *pipe)
 {
@@ -47,12 +83,10 @@ void pipe_wait(struct pipe_inode_info *pipe)
 	 * is considered a noninteractive wait:
 	 */
 	prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE);
-	if (pipe->inode)
-		mutex_unlock(&pipe->inode->i_mutex);
+	pipe_unlock(pipe);
 	schedule();
 	finish_wait(&pipe->wait, &wait);
-	if (pipe->inode)
-		mutex_lock(&pipe->inode->i_mutex);
+	pipe_lock(pipe);
 }
 
 static int

include/linux/bio.h

@@ -504,6 +504,115 @@ static inline int bio_has_data(struct bio *bio)
 	return bio && bio->bi_io_vec != NULL;
 }
 
+/*
+ * BIO list managment for use by remapping drivers (e.g. DM or MD).
+ *
+ * A bio_list anchors a singly-linked list of bios chained through the bi_next
+ * member of the bio.  The bio_list also caches the last list member to allow
+ * fast access to the tail.
+ */
+struct bio_list {
+	struct bio *head;
+	struct bio *tail;
+};
+
+static inline int bio_list_empty(const struct bio_list *bl)
+{
+	return bl->head == NULL;
+}
+
+static inline void bio_list_init(struct bio_list *bl)
+{
+	bl->head = bl->tail = NULL;
+}
+
+#define bio_list_for_each(bio, bl) \
+	for (bio = (bl)->head; bio; bio = bio->bi_next)
+
+static inline unsigned bio_list_size(const struct bio_list *bl)
+{
+	unsigned sz = 0;
+	struct bio *bio;
+
+	bio_list_for_each(bio, bl)
+		sz++;
+
+	return sz;
+}
+
+static inline void bio_list_add(struct bio_list *bl, struct bio *bio)
+{
+	bio->bi_next = NULL;
+
+	if (bl->tail)
+		bl->tail->bi_next = bio;
+	else
+		bl->head = bio;
+
+	bl->tail = bio;
+}
+
+static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio)
+{
+	bio->bi_next = bl->head;
+
+	bl->head = bio;
+
+	if (!bl->tail)
+		bl->tail = bio;
+}
+
+static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2)
+{
+	if (!bl2->head)
+		return;
+
+	if (bl->tail)
+		bl->tail->bi_next = bl2->head;
+	else
+		bl->head = bl2->head;
+
+	bl->tail = bl2->tail;
+}
+
+static inline void bio_list_merge_head(struct bio_list *bl,
+				       struct bio_list *bl2)
+{
+	if (!bl2->head)
+		return;
+
+	if (bl->head)
+		bl2->tail->bi_next = bl->head;
+	else
+		bl->tail = bl2->tail;
+
+	bl->head = bl2->head;
+}
+
+static inline struct bio *bio_list_pop(struct bio_list *bl)
+{
+	struct bio *bio = bl->head;
+
+	if (bio) {
+		bl->head = bl->head->bi_next;
+		if (!bl->head)
+			bl->tail = NULL;
+
+		bio->bi_next = NULL;
+	}
+
+	return bio;
+}
+
+static inline struct bio *bio_list_get(struct bio_list *bl)
+{
+	struct bio *bio = bl->head;
+
+	bl->head = bl->tail = NULL;
+
+	return bio;
+}
+
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
 #define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))

include/linux/fs.h

@@ -87,6 +87,60 @@ struct inodes_stat_t {
  */
 #define FMODE_NOCMTIME		((__force fmode_t)2048)
 
+/*
+ * The below are the various read and write types that we support. Some of
+ * them include behavioral modifiers that send information down to the
+ * block layer and IO scheduler. Terminology:
+ *
+ *	The block layer uses device plugging to defer IO a little bit, in
+ *	the hope that we will see more IO very shortly. This increases
+ *	coalescing of adjacent IO and thus reduces the number of IOs we
+ *	have to send to the device. It also allows for better queuing,
+ *	if the IO isn't mergeable. If the caller is going to be waiting
+ *	for the IO, then he must ensure that the device is unplugged so
+ *	that the IO is dispatched to the driver.
+ *
+ *	All IO is handled async in Linux. This is fine for background
+ *	writes, but for reads or writes that someone waits for completion
+ *	on, we want to notify the block layer and IO scheduler so that they
+ *	know about it. That allows them to make better scheduling
+ *	decisions. So when the below references 'sync' and 'async', it
+ *	is referencing this priority hint.
+ *
+ * With that in mind, the available types are:
+ *
+ * READ			A normal read operation. Device will be plugged.
+ * READ_SYNC		A synchronous read. Device is not plugged, caller can
+ *			immediately wait on this read without caring about
+ *			unplugging.
+ * READA		Used for read-ahead operations. Lower priority, and the
+ *			 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.
+ * SWRITE		Like WRITE, but a special case for ll_rw_block() that
+ *			tells it to lock the buffer first. Normally a buffer
+ *			must be locked before doing IO.
+ * WRITE_SYNC_PLUG	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	Special case write for O_DIRECT only.
+ * SWRITE_SYNC
+ * SWRITE_SYNC_PLUG	Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer.
+ *			See SWRITE.
+ * WRITE_BARRIER	Like WRITE, 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.
+ *
+ */
 #define RW_MASK		1
 #define RWA_MASK	2
 #define READ 0
@@ -102,6 +156,11 @@ struct inodes_stat_t {
 			(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))
+
+/*
+ * 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))
 
@@ -738,9 +797,6 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_QUOTA
 };
 
-extern void inode_double_lock(struct inode *inode1, struct inode *inode2);
-extern void inode_double_unlock(struct inode *inode1, struct inode *inode2);
-
 /*
  * NOTE: in a 32bit arch with a preemptable kernel and
  * an UP compile the i_size_read/write must be atomic
@@ -2150,8 +2206,6 @@ extern ssize_t generic_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);
 extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
-extern ssize_t generic_file_splice_write_nolock(struct pipe_inode_info *,
-		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
 		struct file *out, loff_t *, size_t len, unsigned int flags);
 extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,

include/linux/pipe_fs_i.h

@@ -134,6 +134,11 @@ struct pipe_buf_operations {
    memory allocation, whereas PIPE_BUF makes atomicity guarantees.  */
 #define PIPE_SIZE		PAGE_SIZE
 
+/* Pipe lock and unlock operations */
+void pipe_lock(struct pipe_inode_info *);
+void pipe_unlock(struct pipe_inode_info *);
+void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *);
+
 /* Drop the inode semaphore and wait for a pipe event, atomically */
 void pipe_wait(struct pipe_inode_info *pipe);
 

include/linux/splice.h

@@ -36,6 +36,8 @@ struct splice_desc {
 		void *data;		/* cookie */
 	} u;
 	loff_t pos;			/* file position */
+	size_t num_spliced;		/* number of bytes already spliced */
+	bool need_wakeup;		/* need to wake up writer */
 };
 
 struct partial_page {
@@ -66,6 +68,16 @@ extern ssize_t splice_from_pipe(struct pipe_inode_info *, struct file *,
 				splice_actor *);
 extern ssize_t __splice_from_pipe(struct pipe_inode_info *,
 				  struct splice_desc *, splice_actor *);
+extern int splice_from_pipe_feed(struct pipe_inode_info *, struct splice_desc *,
+				 splice_actor *);
+extern int splice_from_pipe_next(struct pipe_inode_info *,
+				 struct splice_desc *);
+extern void splice_from_pipe_begin(struct splice_desc *);
+extern void splice_from_pipe_end(struct pipe_inode_info *,
+				 struct splice_desc *);
+extern int pipe_to_file(struct pipe_inode_info *, struct pipe_buffer *,
+			struct splice_desc *);
+
 extern ssize_t splice_to_pipe(struct pipe_inode_info *,
 			      struct splice_pipe_desc *);
 extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,

kernel/power/swap.c

@@ -64,8 +64,6 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
 	struct bio *bio;
 
 	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
-	if (!bio)
-		return -ENOMEM;
 	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
 	bio->bi_bdev = resume_bdev;
 	bio->bi_end_io = end_swap_bio_read;