memcg: mem+swap controller core

[net-next-2.6.git] / fs / splice.c

/*
 * "splice": joining two ropes together by interweaving their strands.
 *
 * This is the "extended pipe" functionality, where a pipe is used as
 * an arbitrary in-memory buffer. Think of a pipe as a small kernel
 * buffer that you can use to transfer data from one end to the other.
 *
 * The traditional unix read/write is extended with a "splice()" operation
 * that transfers data buffers to or from a pipe buffer.
 *
 * Named by Larry McVoy, original implementation from Linus, extended by
 * Jens to support splicing to files, network, direct splicing, etc and
 * fixing lots of bugs.
 *
 * Copyright (C) 2005-2006 Jens Axboe <axboe@kernel.dk>
 * Copyright (C) 2005-2006 Linus Torvalds <torvalds@osdl.org>
 * Copyright (C) 2006 Ingo Molnar <mingo@elte.hu>
 *
 */
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/splice.h>
#include <linux/mm_inline.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/uio.h>
#include <linux/security.h>

/*
 * Attempt to steal a page from a pipe buffer. This should perhaps go into
 * a vm helper function, it's already simplified quite a bit by the
 * addition of remove_mapping(). If success is returned, the caller may
 * attempt to reuse this page for another destination.
 */
static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
				     struct pipe_buffer *buf)
{
	struct page *page = buf->page;
	struct address_space *mapping;

	lock_page(page);

	mapping = page_mapping(page);
	if (mapping) {
		WARN_ON(!PageUptodate(page));

		/*
		 * At least for ext2 with nobh option, we need to wait on
		 * writeback completing on this page, since we'll remove it
		 * from the pagecache.  Otherwise truncate wont wait on the
		 * page, allowing the disk blocks to be reused by someone else
		 * before we actually wrote our data to them. fs corruption
		 * ensues.
		 */
		wait_on_page_writeback(page);

		if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
			goto out_unlock;

		/*
		 * If we succeeded in removing the mapping, set LRU flag
		 * and return good.
		 */
		if (remove_mapping(mapping, page)) {
			buf->flags |= PIPE_BUF_FLAG_LRU;
			return 0;
		}
	}

	/*
	 * Raced with truncate or failed to remove page from current
	 * address space, unlock and return failure.
	 */
out_unlock:
	unlock_page(page);
	return 1;
}

static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe,
					struct pipe_buffer *buf)
{
	page_cache_release(buf->page);
	buf->flags &= ~PIPE_BUF_FLAG_LRU;
}

/*
 * Check whether the contents of buf is OK to access. Since the content
 * is a page cache page, IO may be in flight.
 */
static int page_cache_pipe_buf_confirm(struct pipe_inode_info *pipe,
				       struct pipe_buffer *buf)
{
	struct page *page = buf->page;
	int err;

	if (!PageUptodate(page)) {
		lock_page(page);

		/*
		 * Page got truncated/unhashed. This will cause a 0-byte
		 * splice, if this is the first page.
		 */
		if (!page->mapping) {
			err = -ENODATA;
			goto error;
		}

		/*
		 * Uh oh, read-error from disk.
		 */
		if (!PageUptodate(page)) {
			err = -EIO;
			goto error;
		}

		/*
		 * Page is ok afterall, we are done.
		 */
		unlock_page(page);
	}

	return 0;
error:
	unlock_page(page);
	return err;
}

static const struct pipe_buf_operations page_cache_pipe_buf_ops = {
	.can_merge = 0,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.confirm = page_cache_pipe_buf_confirm,
	.release = page_cache_pipe_buf_release,
	.steal = page_cache_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe,
				    struct pipe_buffer *buf)
{
	if (!(buf->flags & PIPE_BUF_FLAG_GIFT))
		return 1;

	buf->flags |= PIPE_BUF_FLAG_LRU;
	return generic_pipe_buf_steal(pipe, buf);
}

static const struct pipe_buf_operations user_page_pipe_buf_ops = {
	.can_merge = 0,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.confirm = generic_pipe_buf_confirm,
	.release = page_cache_pipe_buf_release,
	.steal = user_page_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

/**
 * splice_to_pipe - fill passed data into a pipe
 * @pipe:	pipe to fill
 * @spd:	data to fill
 *
 * Description:
 *    @spd contains a map of pages and len/offset tuples, along with
 *    the struct pipe_buf_operations associated with these pages. This
 *    function will link that data to the pipe.
 *
 */
ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
		       struct splice_pipe_desc *spd)
{
	unsigned int spd_pages = spd->nr_pages;
	int ret, do_wakeup, page_nr;

	ret = 0;
	do_wakeup = 0;
	page_nr = 0;

	if (pipe->inode)
		mutex_lock(&pipe->inode->i_mutex);

	for (;;) {
		if (!pipe->readers) {
			send_sig(SIGPIPE, current, 0);
			if (!ret)
				ret = -EPIPE;
			break;
		}

		if (pipe->nrbufs < PIPE_BUFFERS) {
			int newbuf = (pipe->curbuf + pipe->nrbufs) & (PIPE_BUFFERS - 1);
			struct pipe_buffer *buf = pipe->bufs + newbuf;

			buf->page = spd->pages[page_nr];
			buf->offset = spd->partial[page_nr].offset;
			buf->len = spd->partial[page_nr].len;
			buf->private = spd->partial[page_nr].private;
			buf->ops = spd->ops;
			if (spd->flags & SPLICE_F_GIFT)
				buf->flags |= PIPE_BUF_FLAG_GIFT;

			pipe->nrbufs++;
			page_nr++;
			ret += buf->len;

			if (pipe->inode)
				do_wakeup = 1;

			if (!--spd->nr_pages)
				break;
			if (pipe->nrbufs < PIPE_BUFFERS)
				continue;

			break;
		}

		if (spd->flags & SPLICE_F_NONBLOCK) {
			if (!ret)
				ret = -EAGAIN;
			break;
		}

		if (signal_pending(current)) {
			if (!ret)
				ret = -ERESTARTSYS;
			break;
		}

		if (do_wakeup) {
			smp_mb();
			if (waitqueue_active(&pipe->wait))
				wake_up_interruptible_sync(&pipe->wait);
			kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
			do_wakeup = 0;
		}

		pipe->waiting_writers++;
		pipe_wait(pipe);
		pipe->waiting_writers--;
	}

	if (pipe->inode) {
		mutex_unlock(&pipe->inode->i_mutex);

		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)
		spd->spd_release(spd, page_nr++);

	return ret;
}

static void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
{
	page_cache_release(spd->pages[i]);
}

static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
			   struct pipe_inode_info *pipe, size_t len,
			   unsigned int flags)
{
	struct address_space *mapping = in->f_mapping;
	unsigned int loff, nr_pages, req_pages;
	struct page *pages[PIPE_BUFFERS];
	struct partial_page partial[PIPE_BUFFERS];
	struct page *page;
	pgoff_t index, end_index;
	loff_t isize;
	int error, page_nr;
	struct splice_pipe_desc spd = {
		.pages = pages,
		.partial = partial,
		.flags = flags,
		.ops = &page_cache_pipe_buf_ops,
		.spd_release = spd_release_page,
	};

	index = *ppos >> PAGE_CACHE_SHIFT;
	loff = *ppos & ~PAGE_CACHE_MASK;
	req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	nr_pages = min(req_pages, (unsigned)PIPE_BUFFERS);

	/*
	 * Lookup the (hopefully) full range of pages we need.
	 */
	spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages);
	index += spd.nr_pages;

	/*
	 * If find_get_pages_contig() returned fewer pages than we needed,
	 * readahead/allocate the rest and fill in the holes.
	 */
	if (spd.nr_pages < nr_pages)
		page_cache_sync_readahead(mapping, &in->f_ra, in,
				index, req_pages - spd.nr_pages);

	error = 0;
	while (spd.nr_pages < nr_pages) {
		/*
		 * Page could be there, find_get_pages_contig() breaks on
		 * the first hole.
		 */
		page = find_get_page(mapping, index);
		if (!page) {
			/*
			 * page didn't exist, allocate one.
			 */
			page = page_cache_alloc_cold(mapping);
			if (!page)
				break;

			error = add_to_page_cache_lru(page, mapping, index,
						mapping_gfp_mask(mapping));
			if (unlikely(error)) {
				page_cache_release(page);
				if (error == -EEXIST)
					continue;
				break;
			}
			/*
			 * add_to_page_cache() locks the page, unlock it
			 * to avoid convoluting the logic below even more.
			 */
			unlock_page(page);
		}

		pages[spd.nr_pages++] = page;
		index++;
	}

	/*
	 * Now loop over the map and see if we need to start IO on any
	 * pages, fill in the partial map, etc.
	 */
	index = *ppos >> PAGE_CACHE_SHIFT;
	nr_pages = spd.nr_pages;
	spd.nr_pages = 0;
	for (page_nr = 0; page_nr < nr_pages; page_nr++) {
		unsigned int this_len;

		if (!len)
			break;

		/*
		 * this_len is the max we'll use from this page
		 */
		this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
		page = pages[page_nr];

		if (PageReadahead(page))
			page_cache_async_readahead(mapping, &in->f_ra, in,
					page, index, req_pages - page_nr);

		/*
		 * If the page isn't uptodate, we may need to start io on it
		 */
		if (!PageUptodate(page)) {
			/*
			 * If in nonblock mode then dont block on waiting
			 * for an in-flight io page
			 */
			if (flags & SPLICE_F_NONBLOCK) {
				if (!trylock_page(page)) {
					error = -EAGAIN;
					break;
				}
			} else
				lock_page(page);

			/*
			 * Page was truncated, or invalidated by the
			 * filesystem.  Redo the find/create, but this time the
			 * page is kept locked, so there's no chance of another
			 * race with truncate/invalidate.
			 */
			if (!page->mapping) {
				unlock_page(page);
				page = find_or_create_page(mapping, index,
						mapping_gfp_mask(mapping));

				if (!page) {
					error = -ENOMEM;
					break;
				}
				page_cache_release(pages[page_nr]);
				pages[page_nr] = page;
			}
			/*
			 * page was already under io and is now done, great
			 */
			if (PageUptodate(page)) {
				unlock_page(page);
				goto fill_it;
			}

			/*
			 * need to read in the page
			 */
			error = mapping->a_ops->readpage(in, page);
			if (unlikely(error)) {
				/*
				 * We really should re-lookup the page here,
				 * but it complicates things a lot. Instead
				 * lets just do what we already stored, and
				 * we'll get it the next time we are called.
				 */
				if (error == AOP_TRUNCATED_PAGE)
					error = 0;

				break;
			}
		}
fill_it:
		/*
		 * i_size must be checked after PageUptodate.
		 */
		isize = i_size_read(mapping->host);
		end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
		if (unlikely(!isize || index > end_index))
			break;

		/*
		 * if this is the last page, see if we need to shrink
		 * the length and stop
		 */
		if (end_index == index) {
			unsigned int plen;

			/*
			 * max good bytes in this page
			 */
			plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
			if (plen <= loff)
				break;

			/*
			 * force quit after adding this page
			 */
			this_len = min(this_len, plen - loff);
			len = this_len;
		}

		partial[page_nr].offset = loff;
		partial[page_nr].len = this_len;
		len -= this_len;
		loff = 0;
		spd.nr_pages++;
		index++;
	}

	/*
	 * Release any pages at the end, if we quit early. 'page_nr' is how far
	 * we got, 'nr_pages' is how many pages are in the map.
	 */
	while (page_nr < nr_pages)
		page_cache_release(pages[page_nr++]);
	in->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;

	if (spd.nr_pages)
		return splice_to_pipe(pipe, &spd);

	return error;
}

/**
 * generic_file_splice_read - splice data from file to a pipe
 * @in:		file to splice from
 * @ppos:	position in @in
 * @pipe:	pipe to splice to
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Description:
 *    Will read pages from given file and fill them into a pipe. Can be
 *    used as long as the address_space operations for the source implements
 *    a readpage() hook.
 *
 */
ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
				 struct pipe_inode_info *pipe, size_t len,
				 unsigned int flags)
{
	loff_t isize, left;
	int ret;

	isize = i_size_read(in->f_mapping->host);
	if (unlikely(*ppos >= isize))
		return 0;

	left = isize - *ppos;
	if (unlikely(left < len))
		len = left;

	ret = __generic_file_splice_read(in, ppos, pipe, len, flags);
	if (ret > 0)
		*ppos += ret;

	return ret;
}

EXPORT_SYMBOL(generic_file_splice_read);

/*
 * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
 * using sendpage(). Return the number of bytes sent.
 */
static int pipe_to_sendpage(struct pipe_inode_info *pipe,
			    struct pipe_buffer *buf, struct splice_desc *sd)
{
	struct file *file = sd->u.file;
	loff_t pos = sd->pos;
	int ret, more;

	ret = buf->ops->confirm(pipe, buf);
	if (!ret) {
		more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len;

		ret = file->f_op->sendpage(file, buf->page, buf->offset,
					   sd->len, &pos, more);
	}

	return ret;
}

/*
 * This is a little more tricky than the file -> pipe splicing. There are
 * basically three cases:
 *
 *	- Destination page already exists in the address space and there
 *	  are users of it. For that case we have no other option that
 *	  copying the data. Tough luck.
 *	- Destination page already exists in the address space, but there
 *	  are no users of it. Make sure it's uptodate, then drop it. Fall
 *	  through to last case.
 *	- Destination page does not exist, we can add the pipe page to
 *	  the page cache and avoid the copy.
 *
 * If asked to move pages to the output file (SPLICE_F_MOVE is set in
 * sd->flags), we attempt to migrate pages from the pipe to the output
 * file address space page cache. This is possible if no one else has
 * the pipe page referenced outside of the pipe and page cache. If
 * 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)
{
	struct file *file = sd->u.file;
	struct address_space *mapping = file->f_mapping;
	unsigned int offset, this_len;
	struct page *page;
	void *fsdata;
	int ret;

	/*
	 * make sure the data in this buffer is uptodate
	 */
	ret = buf->ops->confirm(pipe, buf);
	if (unlikely(ret))
		return ret;

	offset = sd->pos & ~PAGE_CACHE_MASK;

	this_len = sd->len;
	if (this_len + offset > PAGE_CACHE_SIZE)
		this_len = PAGE_CACHE_SIZE - offset;

	ret = pagecache_write_begin(file, mapping, sd->pos, this_len,
				AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
	if (unlikely(ret))
		goto out;

	if (buf->page != page) {
		/*
		 * Careful, ->map() uses KM_USER0!
		 */
		char *src = buf->ops->map(pipe, buf, 1);
		char *dst = kmap_atomic(page, KM_USER1);

		memcpy(dst + offset, src + buf->offset, this_len);
		flush_dcache_page(page);
		kunmap_atomic(dst, KM_USER1);
		buf->ops->unmap(pipe, buf, src);
	}
	ret = pagecache_write_end(file, mapping, sd->pos, this_len, this_len,
				page, fsdata);
out:
	return ret;
}

/**
 * __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, 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;

			sd->len = buf->len;
			if (sd->len > sd->total_len)
				sd->len = sd->total_len;

			err = actor(pipe, buf, sd);
			if (err <= 0) {
				if (!ret && err != -ENODATA)
					ret = err;

				break;
			}

			ret += err;
			buf->offset += err;
			buf->len -= err;

			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)
					do_wakeup = 1;
			}

			if (!sd->total_len)
				break;
		}

		if (pipe->nrbufs)
			continue;
		if (!pipe->writers)
			break;
		if (!pipe->waiting_writers) {
			if (ret)
				break;
		}

		if (sd->flags & SPLICE_F_NONBLOCK) {
			if (!ret)
				ret = -EAGAIN;
			break;
		}

		if (signal_pending(current)) {
			if (!ret)
				ret = -ERESTARTSYS;
			break;
		}

		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;
		}

		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 ret;
}
EXPORT_SYMBOL(__splice_from_pipe);

/**
 * splice_from_pipe - splice data from a pipe to a file
 * @pipe:	pipe to splice from
 * @out:	file to splice to
 * @ppos:	position in @out
 * @len:	how many bytes to splice
 * @flags:	splice modifier flags
 * @actor:	handler that splices the data
 *
 * Description:
 *    See __splice_from_pipe. This function locks the input and output inodes,
 *    otherwise it's identical to __splice_from_pipe().
 *
 */
ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
			 loff_t *ppos, size_t len, unsigned int flags,
			 splice_actor *actor)
{
	ssize_t ret;
	struct inode *inode = out->f_mapping->host;
	struct splice_desc sd = {
		.total_len = len,
		.flags = flags,
		.pos = *ppos,
		.u.file = out,
	};

	/*
	 * The actor worker might be calling ->write_begin and
	 * ->write_end. Most of the time, these expect i_mutex to
	 * be held. Since this may result in an ABBA deadlock with
	 * pipe->inode, we have to order lock acquiry here.
	 */
	inode_double_lock(inode, pipe->inode);
	ret = __splice_from_pipe(pipe, &sd, actor);
	inode_double_unlock(inode, pipe->inode);

	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
 * @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.
 *
 */
ssize_t
generic_file_splice_write(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;

	inode_double_lock(inode, pipe->inode);
	ret = file_remove_suid(out);
	if (likely(!ret))
		ret = __splice_from_pipe(pipe, &sd, pipe_to_file);
	inode_double_unlock(inode, pipe->inode);
	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 = generic_osync_inode(inode, mapping,
						  OSYNC_METADATA|OSYNC_DATA);
			mutex_unlock(&inode->i_mutex);

			if (err)
				ret = err;
		}
		balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
	}

	return ret;
}

EXPORT_SYMBOL(generic_file_splice_write);

/**
 * generic_splice_sendpage - splice data from a pipe to a socket
 * @pipe:	pipe to splice from
 * @out:	socket to write to
 * @ppos:	position in @out
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Description:
 *    Will send @len bytes from the pipe to a network socket. No data copying
 *    is involved.
 *
 */
ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
				loff_t *ppos, size_t len, unsigned int flags)
{
	return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_sendpage);
}

EXPORT_SYMBOL(generic_splice_sendpage);

/*
 * Attempt to initiate a splice from pipe to file.
 */
static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
			   loff_t *ppos, size_t len, unsigned int flags)
{
	int ret;

	if (unlikely(!out->f_op || !out->f_op->splice_write))
		return -EINVAL;

	if (unlikely(!(out->f_mode & FMODE_WRITE)))
		return -EBADF;

	if (unlikely(out->f_flags & O_APPEND))
		return -EINVAL;

	ret = rw_verify_area(WRITE, out, ppos, len);
	if (unlikely(ret < 0))
		return ret;

	return out->f_op->splice_write(pipe, out, ppos, len, flags);
}

/*
 * Attempt to initiate a splice from a file to a pipe.
 */
static long do_splice_to(struct file *in, loff_t *ppos,
			 struct pipe_inode_info *pipe, size_t len,
			 unsigned int flags)
{
	int ret;

	if (unlikely(!in->f_op || !in->f_op->splice_read))
		return -EINVAL;

	if (unlikely(!(in->f_mode & FMODE_READ)))
		return -EBADF;

	ret = rw_verify_area(READ, in, ppos, len);
	if (unlikely(ret < 0))
		return ret;

	return in->f_op->splice_read(in, ppos, pipe, len, flags);
}

/**
 * splice_direct_to_actor - splices data directly between two non-pipes
 * @in:		file to splice from
 * @sd:		actor information on where to splice to
 * @actor:	handles the data splicing
 *
 * Description:
 *    This is a special case helper to splice directly between two
 *    points, without requiring an explicit pipe. Internally an allocated
 *    pipe is cached in the process, and reused during the lifetime of
 *    that process.
 *
 */
ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
			       splice_direct_actor *actor)
{
	struct pipe_inode_info *pipe;
	long ret, bytes;
	umode_t i_mode;
	size_t len;
	int i, flags;

	/*
	 * We require the input being a regular file, as we don't want to
	 * randomly drop data for eg socket -> socket splicing. Use the
	 * piped splicing for that!
	 */
	i_mode = in->f_path.dentry->d_inode->i_mode;
	if (unlikely(!S_ISREG(i_mode) && !S_ISBLK(i_mode)))
		return -EINVAL;

	/*
	 * neither in nor out is a pipe, setup an internal pipe attached to
	 * 'out' and transfer the wanted data from 'in' to 'out' through that
	 */
	pipe = current->splice_pipe;
	if (unlikely(!pipe)) {
		pipe = alloc_pipe_info(NULL);
		if (!pipe)
			return -ENOMEM;

		/*
		 * We don't have an immediate reader, but we'll read the stuff
		 * out of the pipe right after the splice_to_pipe(). So set
		 * PIPE_READERS appropriately.
		 */
		pipe->readers = 1;

		current->splice_pipe = pipe;
	}

	/*
	 * Do the splice.
	 */
	ret = 0;
	bytes = 0;
	len = sd->total_len;
	flags = sd->flags;

	/*
	 * Don't block on output, we have to drain the direct pipe.
	 */
	sd->flags &= ~SPLICE_F_NONBLOCK;

	while (len) {
		size_t read_len;
		loff_t pos = sd->pos, prev_pos = pos;

		ret = do_splice_to(in, &pos, pipe, len, flags);
		if (unlikely(ret <= 0))
			goto out_release;

		read_len = ret;
		sd->total_len = read_len;

		/*
		 * NOTE: nonblocking mode only applies to the input. We
		 * must not do the output in nonblocking mode as then we
		 * could get stuck data in the internal pipe:
		 */
		ret = actor(pipe, sd);
		if (unlikely(ret <= 0)) {
			sd->pos = prev_pos;
			goto out_release;
		}

		bytes += ret;
		len -= ret;
		sd->pos = pos;

		if (ret < read_len) {
			sd->pos = prev_pos + ret;
			goto out_release;
		}
	}

done:
	pipe->nrbufs = pipe->curbuf = 0;
	file_accessed(in);
	return bytes;

out_release:
	/*
	 * If we did an incomplete transfer we must release
	 * the pipe buffers in question:
	 */
	for (i = 0; i < PIPE_BUFFERS; i++) {
		struct pipe_buffer *buf = pipe->bufs + i;

		if (buf->ops) {
			buf->ops->release(pipe, buf);
			buf->ops = NULL;
		}
	}

	if (!bytes)
		bytes = ret;

	goto done;
}
EXPORT_SYMBOL(splice_direct_to_actor);

static int direct_splice_actor(struct pipe_inode_info *pipe,
			       struct splice_desc *sd)
{
	struct file *file = sd->u.file;

	return do_splice_from(pipe, file, &sd->pos, sd->total_len, sd->flags);
}

/**
 * do_splice_direct - splices data directly between two files
 * @in:		file to splice from
 * @ppos:	input file offset
 * @out:	file to splice to
 * @len:	number of bytes to splice
 * @flags:	splice modifier flags
 *
 * Description:
 *    For use by do_sendfile(). splice can easily emulate sendfile, but
 *    doing it in the application would incur an extra system call
 *    (splice in + splice out, as compared to just sendfile()). So this helper
 *    can splice directly through a process-private pipe.
 *
 */
long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
		      size_t len, unsigned int flags)
{
	struct splice_desc sd = {
		.len		= len,
		.total_len	= len,
		.flags		= flags,
		.pos		= *ppos,
		.u.file		= out,
	};
	long ret;

	ret = splice_direct_to_actor(in, &sd, direct_splice_actor);
	if (ret > 0)
		*ppos = sd.pos;

	return ret;
}

/*
 * 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
 * pipe.
 */
static inline struct pipe_inode_info *pipe_info(struct inode *inode)
{
	if (S_ISFIFO(inode->i_mode))
		return inode->i_pipe;

	return NULL;
}

/*
 * Determine where to splice to/from.
 */
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;
	loff_t offset, *off;
	long ret;

	pipe = pipe_info(in->f_path.dentry->d_inode);
	if (pipe) {
		if (off_in)
			return -ESPIPE;
		if (off_out) {
			if (out->f_op->llseek == no_llseek)
				return -EINVAL;
			if (copy_from_user(&offset, off_out, sizeof(loff_t)))
				return -EFAULT;
			off = &offset;
		} else
			off = &out->f_pos;

		ret = do_splice_from(pipe, out, off, len, flags);

		if (off_out && copy_to_user(off_out, off, sizeof(loff_t)))
			ret = -EFAULT;

		return ret;
	}

	pipe = pipe_info(out->f_path.dentry->d_inode);
	if (pipe) {
		if (off_out)
			return -ESPIPE;
		if (off_in) {
			if (in->f_op->llseek == no_llseek)
				return -EINVAL;
			if (copy_from_user(&offset, off_in, sizeof(loff_t)))
				return -EFAULT;
			off = &offset;
		} else
			off = &in->f_pos;

		ret = do_splice_to(in, off, pipe, len, flags);

		if (off_in && copy_to_user(off_in, off, sizeof(loff_t)))
			ret = -EFAULT;

		return ret;
	}

	return -EINVAL;
}

/*
 * Map an iov into an array of pages and offset/length tupples. With the
 * partial_page structure, we can map several non-contiguous ranges into
 * our ones pages[] map instead of splitting that operation into pieces.
 * Could easily be exported as a generic helper for other users, in which
 * case one would probably want to add a 'max_nr_pages' parameter as well.
 */
static int get_iovec_page_array(const struct iovec __user *iov,
				unsigned int nr_vecs, struct page **pages,
				struct partial_page *partial, int aligned)
{
	int buffers = 0, error = 0;

	while (nr_vecs) {
		unsigned long off, npages;
		struct iovec entry;
		void __user *base;
		size_t len;
		int i;

		error = -EFAULT;
		if (copy_from_user(&entry, iov, sizeof(entry)))
			break;

		base = entry.iov_base;
		len = entry.iov_len;

		/*
		 * Sanity check this iovec. 0 read succeeds.
		 */
		error = 0;
		if (unlikely(!len))
			break;
		error = -EFAULT;
		if (!access_ok(VERIFY_READ, base, len))
			break;

		/*
		 * Get this base offset and number of pages, then map
		 * in the user pages.
		 */
		off = (unsigned long) base & ~PAGE_MASK;

		/*
		 * If asked for alignment, the offset must be zero and the
		 * length a multiple of the PAGE_SIZE.
		 */
		error = -EINVAL;
		if (aligned && (off || len & ~PAGE_MASK))
			break;

		npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
		if (npages > PIPE_BUFFERS - buffers)
			npages = PIPE_BUFFERS - buffers;

		error = get_user_pages_fast((unsigned long)base, npages,
					0, &pages[buffers]);

		if (unlikely(error <= 0))
			break;

		/*
		 * Fill this contiguous range into the partial page map.
		 */
		for (i = 0; i < error; i++) {
			const int plen = min_t(size_t, len, PAGE_SIZE - off);

			partial[buffers].offset = off;
			partial[buffers].len = plen;

			off = 0;
			len -= plen;
			buffers++;
		}

		/*
		 * We didn't complete this iov, stop here since it probably
		 * means we have to move some of this into a pipe to
		 * be able to continue.
		 */
		if (len)
			break;

		/*
		 * Don't continue if we mapped fewer pages than we asked for,
		 * or if we mapped the max number of pages that we have
		 * room for.
		 */
		if (error < npages || buffers == PIPE_BUFFERS)
			break;

		nr_vecs--;
		iov++;
	}

	if (buffers)
		return buffers;

	return error;
}

static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
			struct splice_desc *sd)
{
	char *src;
	int ret;

	ret = buf->ops->confirm(pipe, buf);
	if (unlikely(ret))
		return ret;

	/*
	 * See if we can use the atomic maps, by prefaulting in the
	 * pages and doing an atomic copy
	 */
	if (!fault_in_pages_writeable(sd->u.userptr, sd->len)) {
		src = buf->ops->map(pipe, buf, 1);
		ret = __copy_to_user_inatomic(sd->u.userptr, src + buf->offset,
							sd->len);
		buf->ops->unmap(pipe, buf, src);
		if (!ret) {
			ret = sd->len;
			goto out;
		}
	}

	/*
	 * No dice, use slow non-atomic map and copy
 	 */
	src = buf->ops->map(pipe, buf, 0);

	ret = sd->len;
	if (copy_to_user(sd->u.userptr, src + buf->offset, sd->len))
		ret = -EFAULT;

	buf->ops->unmap(pipe, buf, src);
out:
	if (ret > 0)
		sd->u.userptr += ret;
	return ret;
}

/*
 * For lack of a better implementation, implement vmsplice() to userspace
 * as a simple copy of the pipes pages to the user iov.
 */
static long vmsplice_to_user(struct file *file, const struct iovec __user *iov,
			     unsigned long nr_segs, unsigned int flags)
{
	struct pipe_inode_info *pipe;
	struct splice_desc sd;
	ssize_t size;
	int error;
	long ret;

	pipe = pipe_info(file->f_path.dentry->d_inode);
	if (!pipe)
		return -EBADF;

	if (pipe->inode)
		mutex_lock(&pipe->inode->i_mutex);

	error = ret = 0;
	while (nr_segs) {
		void __user *base;
		size_t len;

		/*
		 * Get user address base and length for this iovec.
		 */
		error = get_user(base, &iov->iov_base);
		if (unlikely(error))
			break;
		error = get_user(len, &iov->iov_len);
		if (unlikely(error))
			break;

		/*
		 * Sanity check this iovec. 0 read succeeds.
		 */
		if (unlikely(!len))
			break;
		if (unlikely(!base)) {
			error = -EFAULT;
			break;
		}

		if (unlikely(!access_ok(VERIFY_WRITE, base, len))) {
			error = -EFAULT;
			break;
		}

		sd.len = 0;
		sd.total_len = len;
		sd.flags = flags;
		sd.u.userptr = base;
		sd.pos = 0;

		size = __splice_from_pipe(pipe, &sd, pipe_to_user);
		if (size < 0) {
			if (!ret)
				ret = size;

			break;
		}

		ret += size;

		if (size < len)
			break;

		nr_segs--;
		iov++;
	}

	if (pipe->inode)
		mutex_unlock(&pipe->inode->i_mutex);

	if (!ret)
		ret = error;

	return ret;
}

/*
 * vmsplice splices a user address range into a pipe. It can be thought of
 * as splice-from-memory, where the regular splice is splice-from-file (or
 * to file). In both cases the output is a pipe, naturally.
 */
static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
			     unsigned long nr_segs, unsigned int flags)
{
	struct pipe_inode_info *pipe;
	struct page *pages[PIPE_BUFFERS];
	struct partial_page partial[PIPE_BUFFERS];
	struct splice_pipe_desc spd = {
		.pages = pages,
		.partial = partial,
		.flags = flags,
		.ops = &user_page_pipe_buf_ops,
		.spd_release = spd_release_page,
	};

	pipe = pipe_info(file->f_path.dentry->d_inode);
	if (!pipe)
		return -EBADF;

	spd.nr_pages = get_iovec_page_array(iov, nr_segs, pages, partial,
					    flags & SPLICE_F_GIFT);
	if (spd.nr_pages <= 0)
		return spd.nr_pages;

	return splice_to_pipe(pipe, &spd);
}

/*
 * Note that vmsplice only really supports true splicing _from_ user memory
 * to a pipe, not the other way around. Splicing from user memory is a simple
 * operation that can be supported without any funky alignment restrictions
 * or nasty vm tricks. We simply map in the user memory and fill them into
 * a pipe. The reverse isn't quite as easy, though. There are two possible
 * solutions for that:
 *
 *	- memcpy() the data internally, at which point we might as well just
 *	  do a regular read() on the buffer anyway.
 *	- Lots of nasty vm tricks, that are neither fast nor flexible (it
 *	  has restriction limitations on both ends of the pipe).
 *
 * Currently we punt and implement it as a normal copy, see pipe_to_user().
 *
 */
asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov,
			     unsigned long nr_segs, unsigned int flags)
{
	struct file *file;
	long error;
	int fput;

	if (unlikely(nr_segs > UIO_MAXIOV))
		return -EINVAL;
	else if (unlikely(!nr_segs))
		return 0;

	error = -EBADF;
	file = fget_light(fd, &fput);
	if (file) {
		if (file->f_mode & FMODE_WRITE)
			error = vmsplice_to_pipe(file, iov, nr_segs, flags);
		else if (file->f_mode & FMODE_READ)
			error = vmsplice_to_user(file, iov, nr_segs, flags);

		fput_light(file, fput);
	}

	return error;
}

asmlinkage long sys_splice(int fd_in, loff_t __user *off_in,
			   int fd_out, loff_t __user *off_out,
			   size_t len, unsigned int flags)
{
	long error;
	struct file *in, *out;
	int fput_in, fput_out;

	if (unlikely(!len))
		return 0;

	error = -EBADF;
	in = fget_light(fd_in, &fput_in);
	if (in) {
		if (in->f_mode & FMODE_READ) {
			out = fget_light(fd_out, &fput_out);
			if (out) {
				if (out->f_mode & FMODE_WRITE)
					error = do_splice(in, off_in,
							  out, off_out,
							  len, flags);
				fput_light(out, fput_out);
			}
		}

		fput_light(in, fput_in);
	}

	return error;
}

/*
 * 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)
{
	int ret;

	/*
	 * Check ->nrbufs without the inode lock first. This function
	 * is speculative anyways, so missing one is ok.
	 */
	if (pipe->nrbufs)
		return 0;

	ret = 0;
	mutex_lock(&pipe->inode->i_mutex);

	while (!pipe->nrbufs) {
		if (signal_pending(current)) {
			ret = -ERESTARTSYS;
			break;
		}
		if (!pipe->writers)
			break;
		if (!pipe->waiting_writers) {
			if (flags & SPLICE_F_NONBLOCK) {
				ret = -EAGAIN;
				break;
			}
		}
		pipe_wait(pipe);
	}

	mutex_unlock(&pipe->inode->i_mutex);
	return ret;
}

/*
 * 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)
{
	int ret;

	/*
	 * Check ->nrbufs without the inode lock first. This function
	 * is speculative anyways, so missing one is ok.
	 */
	if (pipe->nrbufs < PIPE_BUFFERS)
		return 0;

	ret = 0;
	mutex_lock(&pipe->inode->i_mutex);

	while (pipe->nrbufs >= PIPE_BUFFERS) {
		if (!pipe->readers) {
			send_sig(SIGPIPE, current, 0);
			ret = -EPIPE;
			break;
		}
		if (flags & SPLICE_F_NONBLOCK) {
			ret = -EAGAIN;
			break;
		}
		if (signal_pending(current)) {
			ret = -ERESTARTSYS;
			break;
		}
		pipe->waiting_writers++;
		pipe_wait(pipe);
		pipe->waiting_writers--;
	}

	mutex_unlock(&pipe->inode->i_mutex);
	return ret;
}

/*
 * Link contents of ipipe to opipe.
 */
static int link_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, i = 0, nbuf;

	/*
	 * Potential ABBA deadlock, work around it by ordering lock
	 * grabbing by inode 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);

	do {
		if (!opipe->readers) {
			send_sig(SIGPIPE, current, 0);
			if (!ret)
				ret = -EPIPE;
			break;
		}

		/*
		 * If we have iterated all input buffers or ran out of
		 * output room, break.
		 */
		if (i >= ipipe->nrbufs || opipe->nrbufs >= PIPE_BUFFERS)
			break;

		ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (PIPE_BUFFERS - 1));
		nbuf = (opipe->curbuf + opipe->nrbufs) & (PIPE_BUFFERS - 1);

		/*
		 * Get a reference to this pipe buffer,
		 * so we can copy the contents over.
		 */
		ibuf->ops->get(ipipe, ibuf);

		obuf = opipe->bufs + nbuf;
		*obuf = *ibuf;

		/*
		 * Don't inherit the gift flag, we need to
		 * prevent multiple steals of this page.
		 */
		obuf->flags &= ~PIPE_BUF_FLAG_GIFT;

		if (obuf->len > len)
			obuf->len = len;

		opipe->nrbufs++;
		ret += obuf->len;
		len -= obuf->len;
		i++;
	} while (len);

	/*
	 * return EAGAIN if we have the potential of some data in the
	 * future, otherwise just return 0
	 */
	if (!ret && ipipe->waiting_writers && (flags & SPLICE_F_NONBLOCK))
		ret = -EAGAIN;

	inode_double_unlock(ipipe->inode, opipe->inode);

	/*
	 * 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);
	}

	return ret;
}

/*
 * This is a tee(1) implementation that works on pipes. It doesn't copy
 * any data, it simply references the 'in' pages on the 'out' pipe.
 * The 'flags' used are the SPLICE_F_* variants, currently the only
 * applicable one is SPLICE_F_NONBLOCK.
 */
static long do_tee(struct file *in, struct file *out, size_t len,
		   unsigned int flags)
{
	struct pipe_inode_info *ipipe = pipe_info(in->f_path.dentry->d_inode);
	struct pipe_inode_info *opipe = pipe_info(out->f_path.dentry->d_inode);
	int ret = -EINVAL;

	/*
	 * Duplicate the contents of ipipe to opipe without actually
	 * copying the data.
	 */
	if (ipipe && opipe && ipipe != opipe) {
		/*
		 * Keep going, unless we encounter an error. The ipipe/opipe
		 * ordering doesn't really matter.
		 */
		ret = link_ipipe_prep(ipipe, flags);
		if (!ret) {
			ret = link_opipe_prep(opipe, flags);
			if (!ret)
				ret = link_pipe(ipipe, opipe, len, flags);
		}
	}

	return ret;
}

asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags)
{
	struct file *in;
	int error, fput_in;

	if (unlikely(!len))
		return 0;

	error = -EBADF;
	in = fget_light(fdin, &fput_in);
	if (in) {
		if (in->f_mode & FMODE_READ) {
			int fput_out;
			struct file *out = fget_light(fdout, &fput_out);

			if (out) {
				if (out->f_mode & FMODE_WRITE)
					error = do_tee(in, out, len, flags);
				fput_light(out, fput_out);
			}
		}
 		fput_light(in, fput_in);
 	}

	return error;
}