From 8f3d8ba20e67991b531e9c0227dcd1f99271a32c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Apr 2009 19:55:13 +0200
Subject: block: move bio list helpers into bio.h

It's used by DM and MD and generally useful, so move the bio list
helpers into bio.h.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 include/linux/bio.h | 109 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 109 insertions(+)

(limited to 'include')

diff --git a/include/linux/bio.h b/include/linux/bio.h
index b900d2c67d29..b89cf2d82898 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)]))
-- 
cgit v1.2.3-58-ga151


From 48e70bc18ac81881dedd3aa327c55b924fc41ecf Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Tue, 14 Apr 2009 08:19:27 +0200
Subject: Document and move the various READ/WRITE types

It's a somewhat twisty maze of hints and behavioural modifiers, try
and clear it up a bit with some documentation.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 include/linux/fs.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 562d2855cf30..b535aec4406b 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))
 
-- 
cgit v1.2.3-58-ga151


From b3c2d2ddd63944ef2a1e4a43077b602288107e01 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <miklos@szeredi.hu>
Date: Tue, 14 Apr 2009 19:48:36 +0200
Subject: splice: split up __splice_from_pipe()

Split up __splice_from_pipe() into four helper functions:

  splice_from_pipe_begin()
  splice_from_pipe_next()
  splice_from_pipe_feed()
  splice_from_pipe_end()

splice_from_pipe_next() will wait (if necessary) for more buffers to
be added to the pipe.  splice_from_pipe_feed() will feed the buffers
to the supplied actor and return when there's no more data available
(or if all of the requested data has been copied).

This is necessary so that implementations can do locking around the
non-waiting splice_from_pipe_feed().

This patch should not cause any change in behavior.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 fs/splice.c            | 217 ++++++++++++++++++++++++++++++++-----------------
 include/linux/splice.h |  10 +++
 2 files changed, 153 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/fs/splice.c b/fs/splice.c
index c18aa7e03e2b..fd6b278d447b 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -601,107 +601,176 @@ out:
 	return ret;
 }
 
+static void wakeup_pipe_writers(struct pipe_inode_info *pipe)
+{
+	smp_mb();
+	if (waitqueue_active(&pipe->wait))
+		wake_up_interruptible(&pipe->wait);
+	kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
+}
+
 /**
- * __splice_from_pipe - splice data from a pipe to given actor
+ * splice_from_pipe_feed - feed available data from a pipe to a file
  * @pipe:	pipe to splice from
  * @sd:		information to @actor
  * @actor:	handler that splices the data
  *
  * Description:
- *    This function does little more than loop over the pipe and call
- *    @actor to do the actual moving of a single struct pipe_buffer to
- *    the desired destination. See pipe_to_file, pipe_to_sendpage, or
- *    pipe_to_user.
+
+ *    This function loops over the pipe and calls @actor to do the
+ *    actual moving of a single struct pipe_buffer to the desired
+ *    destination.  It returns when there's no more buffers left in
+ *    the pipe or if the requested number of bytes (@sd->total_len)
+ *    have been copied.  It returns a positive number (one) if the
+ *    pipe needs to be filled with more data, zero if the required
+ *    number of bytes have been copied and -errno on error.
  *
+ *    This, together with splice_from_pipe_{begin,end,next}, may be
+ *    used to implement the functionality of __splice_from_pipe() when
+ *    locking is required around copying the pipe buffers to the
+ *    destination.
  */
-ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
-			   splice_actor *actor)
+int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
+			  splice_actor *actor)
 {
-	int ret, do_wakeup, err;
-
-	ret = 0;
-	do_wakeup = 0;
-
-	for (;;) {
-		if (pipe->nrbufs) {
-			struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
-			const struct pipe_buf_operations *ops = buf->ops;
+	int ret;
 
-			sd->len = buf->len;
-			if (sd->len > sd->total_len)
-				sd->len = sd->total_len;
+	while (pipe->nrbufs) {
+		struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
+		const struct pipe_buf_operations *ops = buf->ops;
 
-			err = actor(pipe, buf, sd);
-			if (err <= 0) {
-				if (!ret && err != -ENODATA)
-					ret = err;
+		sd->len = buf->len;
+		if (sd->len > sd->total_len)
+			sd->len = sd->total_len;
 
-				break;
-			}
+		ret = actor(pipe, buf, sd);
+		if (ret <= 0) {
+			if (ret == -ENODATA)
+				ret = 0;
+			return ret;
+		}
+		buf->offset += ret;
+		buf->len -= ret;
 
-			ret += err;
-			buf->offset += err;
-			buf->len -= err;
+		sd->num_spliced += ret;
+		sd->len -= ret;
+		sd->pos += ret;
+		sd->total_len -= ret;
 
-			sd->len -= err;
-			sd->pos += err;
-			sd->total_len -= err;
-			if (sd->len)
-				continue;
+		if (!buf->len) {
+			buf->ops = NULL;
+			ops->release(pipe, buf);
+			pipe->curbuf = (pipe->curbuf + 1) & (PIPE_BUFFERS - 1);
+			pipe->nrbufs--;
+			if (pipe->inode)
+				sd->need_wakeup = true;
+		}
 
-			if (!buf->len) {
-				buf->ops = NULL;
-				ops->release(pipe, buf);
-				pipe->curbuf = (pipe->curbuf + 1) & (PIPE_BUFFERS - 1);
-				pipe->nrbufs--;
-				if (pipe->inode)
-					do_wakeup = 1;
-			}
+		if (!sd->total_len)
+			return 0;
+	}
 
-			if (!sd->total_len)
-				break;
-		}
+	return 1;
+}
+EXPORT_SYMBOL(splice_from_pipe_feed);
 
-		if (pipe->nrbufs)
-			continue;
+/**
+ * splice_from_pipe_next - wait for some data to splice from
+ * @pipe:	pipe to splice from
+ * @sd:		information about the splice operation
+ *
+ * Description:
+ *    This function will wait for some data and return a positive
+ *    value (one) if pipe buffers are available.  It will return zero
+ *    or -errno if no more data needs to be spliced.
+ */
+int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd)
+{
+	while (!pipe->nrbufs) {
 		if (!pipe->writers)
-			break;
-		if (!pipe->waiting_writers) {
-			if (ret)
-				break;
-		}
+			return 0;
 
-		if (sd->flags & SPLICE_F_NONBLOCK) {
-			if (!ret)
-				ret = -EAGAIN;
-			break;
-		}
+		if (!pipe->waiting_writers && sd->num_spliced)
+			return 0;
 
-		if (signal_pending(current)) {
-			if (!ret)
-				ret = -ERESTARTSYS;
-			break;
-		}
+		if (sd->flags & SPLICE_F_NONBLOCK)
+			return -EAGAIN;
 
-		if (do_wakeup) {
-			smp_mb();
-			if (waitqueue_active(&pipe->wait))
-				wake_up_interruptible_sync(&pipe->wait);
-			kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
-			do_wakeup = 0;
+		if (signal_pending(current))
+			return -ERESTARTSYS;
+
+		if (sd->need_wakeup) {
+			wakeup_pipe_writers(pipe);
+			sd->need_wakeup = false;
 		}
 
 		pipe_wait(pipe);
 	}
 
-	if (do_wakeup) {
-		smp_mb();
-		if (waitqueue_active(&pipe->wait))
-			wake_up_interruptible(&pipe->wait);
-		kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
-	}
+	return 1;
+}
+EXPORT_SYMBOL(splice_from_pipe_next);
 
-	return ret;
+/**
+ * splice_from_pipe_begin - start splicing from pipe
+ * @pipe:	pipe to splice from
+ *
+ * Description:
+ *    This function should be called before a loop containing
+ *    splice_from_pipe_next() and splice_from_pipe_feed() to
+ *    initialize the necessary fields of @sd.
+ */
+void splice_from_pipe_begin(struct splice_desc *sd)
+{
+	sd->num_spliced = 0;
+	sd->need_wakeup = false;
+}
+EXPORT_SYMBOL(splice_from_pipe_begin);
+
+/**
+ * splice_from_pipe_end - finish splicing from pipe
+ * @pipe:	pipe to splice from
+ * @sd:		information about the splice operation
+ *
+ * Description:
+ *    This function will wake up pipe writers if necessary.  It should
+ *    be called after a loop containing splice_from_pipe_next() and
+ *    splice_from_pipe_feed().
+ */
+void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd)
+{
+	if (sd->need_wakeup)
+		wakeup_pipe_writers(pipe);
+}
+EXPORT_SYMBOL(splice_from_pipe_end);
+
+/**
+ * __splice_from_pipe - splice data from a pipe to given actor
+ * @pipe:	pipe to splice from
+ * @sd:		information to @actor
+ * @actor:	handler that splices the data
+ *
+ * Description:
+ *    This function does little more than loop over the pipe and call
+ *    @actor to do the actual moving of a single struct pipe_buffer to
+ *    the desired destination. See pipe_to_file, pipe_to_sendpage, or
+ *    pipe_to_user.
+ *
+ */
+ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
+			   splice_actor *actor)
+{
+	int ret;
+
+	splice_from_pipe_begin(sd);
+	do {
+		ret = splice_from_pipe_next(pipe, sd);
+		if (ret > 0)
+			ret = splice_from_pipe_feed(pipe, sd, actor);
+	} while (ret > 0);
+	splice_from_pipe_end(pipe, sd);
+
+	return sd->num_spliced ? sd->num_spliced : ret;
 }
 EXPORT_SYMBOL(__splice_from_pipe);
 
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 528dcb93c2f2..8fc2a635586e 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 +68,14 @@ 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 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 *,
-- 
cgit v1.2.3-58-ga151


From 328eaaba4e41a04c1dc4679d65bea3fee4349d86 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <miklos@szeredi.hu>
Date: Tue, 14 Apr 2009 19:48:39 +0200
Subject: ocfs2: fix i_mutex locking in ocfs2_splice_to_file()

Rearrange locking of i_mutex on destination and call to
ocfs2_rw_lock() so locks are only held while buffers are copied with
the pipe_to_file() actor, and not while waiting for more data on the
pipe.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 fs/ocfs2/file.c        | 94 +++++++++++++++++++++++++++++++++++++++-----------
 fs/splice.c            |  5 +--
 include/linux/splice.h |  2 ++
 3 files changed, 79 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 8672b9536039..c2a87c885b73 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1912,6 +1912,22 @@ out_sems:
 	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,
@@ -1919,38 +1935,76 @@ 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) {
-		mlog_errno(ret);
-		goto out_unlock;
-	}
+		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+		ret = ocfs2_rw_lock(inode, 1);
+		if (ret < 0)
+			mlog_errno(ret);
+		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:
-	ocfs2_rw_unlock(inode, 1);
-out:
-	mutex_unlock(&inode->i_mutex);
+	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);
+			}
+			mutex_unlock(&inode->i_mutex);
+
+			if (err)
+				ret = err;
+		}
+		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
+	}
 
 	mlog_exit(ret);
 	return ret;
diff --git a/fs/splice.c b/fs/splice.c
index a1f595b9db40..584b2b7a1dbe 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -555,8 +555,8 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
  * SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create
  * a new page in the output file page cache and fill/dirty that.
  */
-static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
-			struct splice_desc *sd)
+int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
+		 struct splice_desc *sd)
 {
 	struct file *file = sd->u.file;
 	struct address_space *mapping = file->f_mapping;
@@ -600,6 +600,7 @@ static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 out:
 	return ret;
 }
+EXPORT_SYMBOL(pipe_to_file);
 
 static void wakeup_pipe_writers(struct pipe_inode_info *pipe)
 {
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 8fc2a635586e..5f3faa9d15ae 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -75,6 +75,8 @@ extern int splice_from_pipe_next(struct pipe_inode_info *,
 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 *);
-- 
cgit v1.2.3-58-ga151


From f8cc774ce4844811a55e2352f1443055e3994e28 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <miklos@szeredi.hu>
Date: Tue, 14 Apr 2009 19:48:40 +0200
Subject: splice: remove generic_file_splice_write_nolock()

Remove the now unused generic_file_splice_write_nolock() function.
It's conceptually broken anyway, because splice may need to wait for
pipe events so holding locks across the whole operation is wrong.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 fs/splice.c        | 59 ------------------------------------------------------
 include/linux/fs.h |  2 --
 2 files changed, 61 deletions(-)

(limited to 'include')

diff --git a/fs/splice.c b/fs/splice.c
index 584b2b7a1dbe..128ee36a719b 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -810,65 +810,6 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
 	return ret;
 }
 
-/**
- * generic_file_splice_write_nolock - generic_file_splice_write without mutexes
- * @pipe:	pipe info
- * @out:	file to write to
- * @ppos:	position in @out
- * @len:	number of bytes to splice
- * @flags:	splice modifier flags
- *
- * Description:
- *    Will either move or copy pages (determined by @flags options) from
- *    the given pipe inode to the given file. The caller is responsible
- *    for acquiring i_mutex on both inodes.
- *
- */
-ssize_t
-generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out,
-				 loff_t *ppos, size_t len, unsigned int flags)
-{
-	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,
-	};
-	ssize_t ret;
-	int err;
-
-	err = file_remove_suid(out);
-	if (unlikely(err))
-		return err;
-
-	ret = __splice_from_pipe(pipe, &sd, pipe_to_file);
-	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))) {
-			err = generic_osync_inode(inode, mapping,
-						  OSYNC_METADATA|OSYNC_DATA);
-
-			if (err)
-				ret = err;
-		}
-		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
-	}
-
-	return ret;
-}
-
-EXPORT_SYMBOL(generic_file_splice_write_nolock);
-
 /**
  * generic_file_splice_write - splice data from a pipe to a file
  * @pipe:	pipe info
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b535aec4406b..907d8f56c6fa 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2209,8 +2209,6 @@ 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,
-- 
cgit v1.2.3-58-ga151


From 61e0d47c33cc371f725bcda4a47ae0efe652dba8 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <miklos@szeredi.hu>
Date: Tue, 14 Apr 2009 19:48:41 +0200
Subject: splice: add helpers for locking pipe inode

There are lots of sequences like this, especially in splice code:

	if (pipe->inode)
		mutex_lock(&pipe->inode->i_mutex);
	/* do something */
	if (pipe->inode)
		mutex_unlock(&pipe->inode->i_mutex);

so introduce helpers which do the conditional locking and unlocking.
Also replace the inode_double_lock() call with a pipe_double_lock()
helper to avoid spreading the use of this functionality beyond the
pipe code.

This patch is just a cleanup, and should cause no behavioral changes.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 fs/inode.c                | 36 ----------------------------------
 fs/pipe.c                 | 42 +++++++++++++++++++++++++++++++++++----
 fs/splice.c               | 50 ++++++++++++++++++++---------------------------
 include/linux/fs.h        |  3 ---
 include/linux/pipe_fs_i.h |  5 +++++
 5 files changed, 64 insertions(+), 72 deletions(-)

(limited to 'include')

diff --git a/fs/inode.c b/fs/inode.c
index d06d6d268de9..6ad14a1cd8c9 100644
--- a/fs/inode.c
+++ b/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)
 {
diff --git a/fs/pipe.c b/fs/pipe.c
index 4af7aa521813..13414ec45b8d 100644
--- a/fs/pipe.c
+++ b/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
diff --git a/fs/splice.c b/fs/splice.c
index 128ee36a719b..5384a90665d0 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -182,8 +182,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 	do_wakeup = 0;
 	page_nr = 0;
 
-	if (pipe->inode)
-		mutex_lock(&pipe->inode->i_mutex);
+	pipe_lock(pipe);
 
 	for (;;) {
 		if (!pipe->readers) {
@@ -245,15 +244,13 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 		pipe->waiting_writers--;
 	}
 
-	if (pipe->inode) {
-		mutex_unlock(&pipe->inode->i_mutex);
+	pipe_unlock(pipe);
 
-		if (do_wakeup) {
-			smp_mb();
-			if (waitqueue_active(&pipe->wait))
-				wake_up_interruptible(&pipe->wait);
-			kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
-		}
+	if (do_wakeup) {
+		smp_mb();
+		if (waitqueue_active(&pipe->wait))
+			wake_up_interruptible(&pipe->wait);
+		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 	}
 
 	while (page_nr < spd_pages)
@@ -801,11 +798,9 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
 		.u.file = out,
 	};
 
-	if (pipe->inode)
-		mutex_lock(&pipe->inode->i_mutex);
+	pipe_lock(pipe);
 	ret = __splice_from_pipe(pipe, &sd, actor);
-	if (pipe->inode)
-		mutex_unlock(&pipe->inode->i_mutex);
+	pipe_unlock(pipe);
 
 	return ret;
 }
@@ -837,8 +832,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 	};
 	ssize_t ret;
 
-	if (pipe->inode)
-		mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_PARENT);
+	pipe_lock(pipe);
 
 	splice_from_pipe_begin(&sd);
 	do {
@@ -854,8 +848,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 	} while (ret > 0);
 	splice_from_pipe_end(pipe, &sd);
 
-	if (pipe->inode)
-		mutex_unlock(&pipe->inode->i_mutex);
+	pipe_unlock(pipe);
 
 	if (sd.num_spliced)
 		ret = sd.num_spliced;
@@ -1348,8 +1341,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *iov,
 	if (!pipe)
 		return -EBADF;
 
-	if (pipe->inode)
-		mutex_lock(&pipe->inode->i_mutex);
+	pipe_lock(pipe);
 
 	error = ret = 0;
 	while (nr_segs) {
@@ -1404,8 +1396,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *iov,
 		iov++;
 	}
 
-	if (pipe->inode)
-		mutex_unlock(&pipe->inode->i_mutex);
+	pipe_unlock(pipe);
 
 	if (!ret)
 		ret = error;
@@ -1533,7 +1524,7 @@ static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 		return 0;
 
 	ret = 0;
-	mutex_lock(&pipe->inode->i_mutex);
+	pipe_lock(pipe);
 
 	while (!pipe->nrbufs) {
 		if (signal_pending(current)) {
@@ -1551,7 +1542,7 @@ static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 		pipe_wait(pipe);
 	}
 
-	mutex_unlock(&pipe->inode->i_mutex);
+	pipe_unlock(pipe);
 	return ret;
 }
 
@@ -1571,7 +1562,7 @@ static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 		return 0;
 
 	ret = 0;
-	mutex_lock(&pipe->inode->i_mutex);
+	pipe_lock(pipe);
 
 	while (pipe->nrbufs >= PIPE_BUFFERS) {
 		if (!pipe->readers) {
@@ -1592,7 +1583,7 @@ static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 		pipe->waiting_writers--;
 	}
 
-	mutex_unlock(&pipe->inode->i_mutex);
+	pipe_unlock(pipe);
 	return ret;
 }
 
@@ -1608,10 +1599,10 @@ static int link_pipe(struct pipe_inode_info *ipipe,
 
 	/*
 	 * Potential ABBA deadlock, work around it by ordering lock
-	 * grabbing by inode address. Otherwise two different processes
+	 * grabbing by pipe info address. Otherwise two different processes
 	 * could deadlock (one doing tee from A -> B, the other from B -> A).
 	 */
-	inode_double_lock(ipipe->inode, opipe->inode);
+	pipe_double_lock(ipipe, opipe);
 
 	do {
 		if (!opipe->readers) {
@@ -1662,7 +1653,8 @@ static int link_pipe(struct pipe_inode_info *ipipe,
 	if (!ret && ipipe->waiting_writers && (flags & SPLICE_F_NONBLOCK))
 		ret = -EAGAIN;
 
-	inode_double_unlock(ipipe->inode, opipe->inode);
+	pipe_unlock(ipipe);
+	pipe_unlock(opipe);
 
 	/*
 	 * If we put data in the output pipe, wakeup any potential readers.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 907d8f56c6fa..e766be0d4329 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -797,9 +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
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 8e4120285f72..c8f038554e80 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);
 
-- 
cgit v1.2.3-58-ga151