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
  ...

4 files changed, 185 insertions, 5 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index b900d2c6..b89cf2d 100644
--- a/include/linux/bio.h
+++ b/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)]))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 562d285..e766be0 100644
--- a/include/linux/fs.h
+++ b/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,
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 8e41202..c8f0385 100644
--- a/include/linux/pipe_fs_i.h
+++ b/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);
 
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 528dcb9..5f3faa9 100644
--- a/include/linux/splice.h
+++ b/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 *,