Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:
	Documentation/feature-removal-schedule.txt
	drivers/scsi/fcoe/fcoe.c
	net/core/drop_monitor.c
	net/core/net-traces.c

1 files changed, 318 insertions, 20 deletions

diff --git a/fs/splice.c b/fs/splice.c
index 666953d59a35..73766d24f97b 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -507,9 +507,131 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 
 	return ret;
 }
-
 EXPORT_SYMBOL(generic_file_splice_read);
 
+static const struct pipe_buf_operations default_pipe_buf_ops = {
+	.can_merge = 0,
+	.map = generic_pipe_buf_map,
+	.unmap = generic_pipe_buf_unmap,
+	.confirm = generic_pipe_buf_confirm,
+	.release = generic_pipe_buf_release,
+	.steal = generic_pipe_buf_steal,
+	.get = generic_pipe_buf_get,
+};
+
+static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
+			    unsigned long vlen, loff_t offset)
+{
+	mm_segment_t old_fs;
+	loff_t pos = offset;
+	ssize_t res;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	/* The cast to a user pointer is valid due to the set_fs() */
+	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos);
+	set_fs(old_fs);
+
+	return res;
+}
+
+static ssize_t kernel_write(struct file *file, const char *buf, size_t count,
+			    loff_t pos)
+{
+	mm_segment_t old_fs;
+	ssize_t res;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	/* The cast to a user pointer is valid due to the set_fs() */
+	res = vfs_write(file, (const char __user *)buf, count, &pos);
+	set_fs(old_fs);
+
+	return res;
+}
+
+ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
+				 struct pipe_inode_info *pipe, size_t len,
+				 unsigned int flags)
+{
+	unsigned int nr_pages;
+	unsigned int nr_freed;
+	size_t offset;
+	struct page *pages[PIPE_BUFFERS];
+	struct partial_page partial[PIPE_BUFFERS];
+	struct iovec vec[PIPE_BUFFERS];
+	pgoff_t index;
+	ssize_t res;
+	size_t this_len;
+	int error;
+	int i;
+	struct splice_pipe_desc spd = {
+		.pages = pages,
+		.partial = partial,
+		.flags = flags,
+		.ops = &default_pipe_buf_ops,
+		.spd_release = spd_release_page,
+	};
+
+	index = *ppos >> PAGE_CACHE_SHIFT;
+	offset = *ppos & ~PAGE_CACHE_MASK;
+	nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+	for (i = 0; i < nr_pages && i < PIPE_BUFFERS && len; i++) {
+		struct page *page;
+
+		page = alloc_page(GFP_USER);
+		error = -ENOMEM;
+		if (!page)
+			goto err;
+
+		this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset);
+		vec[i].iov_base = (void __user *) page_address(page);
+		vec[i].iov_len = this_len;
+		pages[i] = page;
+		spd.nr_pages++;
+		len -= this_len;
+		offset = 0;
+	}
+
+	res = kernel_readv(in, vec, spd.nr_pages, *ppos);
+	if (res < 0) {
+		error = res;
+		goto err;
+	}
+
+	error = 0;
+	if (!res)
+		goto err;
+
+	nr_freed = 0;
+	for (i = 0; i < spd.nr_pages; i++) {
+		this_len = min_t(size_t, vec[i].iov_len, res);
+		partial[i].offset = 0;
+		partial[i].len = this_len;
+		if (!this_len) {
+			__free_page(pages[i]);
+			pages[i] = NULL;
+			nr_freed++;
+		}
+		res -= this_len;
+	}
+	spd.nr_pages -= nr_freed;
+
+	res = splice_to_pipe(pipe, &spd);
+	if (res > 0)
+		*ppos += res;
+
+	return res;
+
+err:
+	for (i = 0; i < spd.nr_pages; i++)
+		__free_page(pages[i]);
+
+	return error;
+}
+EXPORT_SYMBOL(default_file_splice_read);
+
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -881,6 +1003,36 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_file_splice_write);
 
+static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
+			  struct splice_desc *sd)
+{
+	int ret;
+	void *data;
+
+	ret = buf->ops->confirm(pipe, buf);
+	if (ret)
+		return ret;
+
+	data = buf->ops->map(pipe, buf, 0);
+	ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
+	buf->ops->unmap(pipe, buf, data);
+
+	return ret;
+}
+
+static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
+					 struct file *out, loff_t *ppos,
+					 size_t len, unsigned int flags)
+{
+	ssize_t ret;
+
+	ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
+	if (ret > 0)
+		*ppos += ret;
+
+	return ret;
+}
+
 /**
  * generic_splice_sendpage - splice data from a pipe to a socket
  * @pipe:	pipe to splice from
@@ -908,11 +1060,10 @@ EXPORT_SYMBOL(generic_splice_sendpage);
 static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 			   loff_t *ppos, size_t len, unsigned int flags)
 {
+	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *,
+				loff_t *, size_t, unsigned int);
 	int ret;
 
-	if (unlikely(!out->f_op || !out->f_op->splice_write))
-		return -EINVAL;
-
 	if (unlikely(!(out->f_mode & FMODE_WRITE)))
 		return -EBADF;
 
@@ -923,7 +1074,11 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 	if (unlikely(ret < 0))
 		return ret;
 
-	return out->f_op->splice_write(pipe, out, ppos, len, flags);
+	splice_write = out->f_op->splice_write;
+	if (!splice_write)
+		splice_write = default_file_splice_write;
+
+	return splice_write(pipe, out, ppos, len, flags);
 }
 
 /*
@@ -933,11 +1088,10 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 			 struct pipe_inode_info *pipe, size_t len,
 			 unsigned int flags)
 {
+	ssize_t (*splice_read)(struct file *, loff_t *,
+			       struct pipe_inode_info *, size_t, unsigned int);
 	int ret;
 
-	if (unlikely(!in->f_op || !in->f_op->splice_read))
-		return -EINVAL;
-
 	if (unlikely(!(in->f_mode & FMODE_READ)))
 		return -EBADF;
 
@@ -945,7 +1099,11 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(ret < 0))
 		return ret;
 
-	return in->f_op->splice_read(in, ppos, pipe, len, flags);
+	splice_read = in->f_op->splice_read;
+	if (!splice_read)
+		splice_read = default_file_splice_read;
+
+	return splice_read(in, ppos, pipe, len, flags);
 }
 
 /**
@@ -1112,6 +1270,9 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 	return ret;
 }
 
+static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
+			       struct pipe_inode_info *opipe,
+			       size_t len, unsigned int flags);
 /*
  * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same
  * location, so checking ->i_pipe is not enough to verify that this is a
@@ -1132,12 +1293,32 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		      struct file *out, loff_t __user *off_out,
 		      size_t len, unsigned int flags)
 {
-	struct pipe_inode_info *pipe;
+	struct pipe_inode_info *ipipe;
+	struct pipe_inode_info *opipe;
 	loff_t offset, *off;
 	long ret;
 
-	pipe = pipe_info(in->f_path.dentry->d_inode);
-	if (pipe) {
+	ipipe = pipe_info(in->f_path.dentry->d_inode);
+	opipe = pipe_info(out->f_path.dentry->d_inode);
+
+	if (ipipe && opipe) {
+		if (off_in || off_out)
+			return -ESPIPE;
+
+		if (!(in->f_mode & FMODE_READ))
+			return -EBADF;
+
+		if (!(out->f_mode & FMODE_WRITE))
+			return -EBADF;
+
+		/* Splicing to self would be fun, but... */
+		if (ipipe == opipe)
+			return -EINVAL;
+
+		return splice_pipe_to_pipe(ipipe, opipe, len, flags);
+	}
+
+	if (ipipe) {
 		if (off_in)
 			return -ESPIPE;
 		if (off_out) {
@@ -1149,7 +1330,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		} else
 			off = &out->f_pos;
 
-		ret = do_splice_from(pipe, out, off, len, flags);
+		ret = do_splice_from(ipipe, out, off, len, flags);
 
 		if (off_out && copy_to_user(off_out, off, sizeof(loff_t)))
 			ret = -EFAULT;
@@ -1157,8 +1338,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		return ret;
 	}
 
-	pipe = pipe_info(out->f_path.dentry->d_inode);
-	if (pipe) {
+	if (opipe) {
 		if (off_out)
 			return -ESPIPE;
 		if (off_in) {
@@ -1170,7 +1350,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		} else
 			off = &in->f_pos;
 
-		ret = do_splice_to(in, off, pipe, len, flags);
+		ret = do_splice_to(in, off, opipe, len, flags);
 
 		if (off_in && copy_to_user(off_in, off, sizeof(loff_t)))
 			ret = -EFAULT;
@@ -1511,7 +1691,7 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
  * Make sure there's data to read. Wait for input if we can, otherwise
  * return an appropriate error.
  */
-static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
+static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 {
 	int ret;
 
@@ -1549,7 +1729,7 @@ static int link_ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
  * Make sure there's writeable room. Wait for room if we can, otherwise
  * return an appropriate error.
  */
-static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
+static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 {
 	int ret;
 
@@ -1587,6 +1767,124 @@ static int link_opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 }
 
 /*
+ * Splice contents of ipipe to opipe.
+ */
+static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
+			       struct pipe_inode_info *opipe,
+			       size_t len, unsigned int flags)
+{
+	struct pipe_buffer *ibuf, *obuf;
+	int ret = 0, nbuf;
+	bool input_wakeup = false;
+
+
+retry:
+	ret = ipipe_prep(ipipe, flags);
+	if (ret)
+		return ret;
+
+	ret = opipe_prep(opipe, flags);
+	if (ret)
+		return ret;
+
+	/*
+	 * Potential ABBA deadlock, work around it by ordering lock
+	 * grabbing by pipe info address. Otherwise two different processes
+	 * could deadlock (one doing tee from A -> B, the other from B -> A).
+	 */
+	pipe_double_lock(ipipe, opipe);
+
+	do {
+		if (!opipe->readers) {
+			send_sig(SIGPIPE, current, 0);
+			if (!ret)
+				ret = -EPIPE;
+			break;
+		}
+
+		if (!ipipe->nrbufs && !ipipe->writers)
+			break;
+
+		/*
+		 * Cannot make any progress, because either the input
+		 * pipe is empty or the output pipe is full.
+		 */
+		if (!ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS) {
+			/* Already processed some buffers, break */
+			if (ret)
+				break;
+
+			if (flags & SPLICE_F_NONBLOCK) {
+				ret = -EAGAIN;
+				break;
+			}
+
+			/*
+			 * We raced with another reader/writer and haven't
+			 * managed to process any buffers.  A zero return
+			 * value means EOF, so retry instead.
+			 */
+			pipe_unlock(ipipe);
+			pipe_unlock(opipe);
+			goto retry;
+		}
+
+		ibuf = ipipe->bufs + ipipe->curbuf;
+		nbuf = (opipe->curbuf + opipe->nrbufs) % PIPE_BUFFERS;
+		obuf = opipe->bufs + nbuf;
+
+		if (len >= ibuf->len) {
+			/*
+			 * Simply move the whole buffer from ipipe to opipe
+			 */
+			*obuf = *ibuf;
+			ibuf->ops = NULL;
+			opipe->nrbufs++;
+			ipipe->curbuf = (ipipe->curbuf + 1) % PIPE_BUFFERS;
+			ipipe->nrbufs--;
+			input_wakeup = true;
+		} else {
+			/*
+			 * Get a reference to this pipe buffer,
+			 * so we can copy the contents over.
+			 */
+			ibuf->ops->get(ipipe, ibuf);
+			*obuf = *ibuf;
+
+			/*
+			 * Don't inherit the gift flag, we need to
+			 * prevent multiple steals of this page.
+			 */
+			obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
+
+			obuf->len = len;
+			opipe->nrbufs++;
+			ibuf->offset += obuf->len;
+			ibuf->len -= obuf->len;
+		}
+		ret += obuf->len;
+		len -= obuf->len;
+	} while (len);
+
+	pipe_unlock(ipipe);
+	pipe_unlock(opipe);
+
+	/*
+	 * If we put data in the output pipe, wakeup any potential readers.
+	 */
+	if (ret > 0) {
+		smp_mb();
+		if (waitqueue_active(&opipe->wait))
+			wake_up_interruptible(&opipe->wait);
+		kill_fasync(&opipe->fasync_readers, SIGIO, POLL_IN);
+	}
+	if (input_wakeup)
+		wakeup_pipe_writers(ipipe);
+
+	return ret;
+}
+
+/*
  * Link contents of ipipe to opipe.
  */
 static int link_pipe(struct pipe_inode_info *ipipe,
@@ -1690,9 +1988,9 @@ static long do_tee(struct file *in, struct file *out, size_t len,
 		 * Keep going, unless we encounter an error. The ipipe/opipe
 		 * ordering doesn't really matter.
 		 */
-		ret = link_ipipe_prep(ipipe, flags);
+		ret = ipipe_prep(ipipe, flags);
 		if (!ret) {
-			ret = link_opipe_prep(opipe, flags);
+			ret = opipe_prep(opipe, flags);
 			if (!ret)
 				ret = link_pipe(ipipe, opipe, len, flags);
 		}