path: root/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 and fixing the initial implementation
 * bugs.
 *
 * Copyright (C) 2005 Jens Axboe <axboe@suse.de>
 * Copyright (C) 2005 Linus Torvalds <torvalds@osdl.org>
 *
 */
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/pipe_fs_i.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>

/*
 * Passed to the actors
 */
struct splice_desc {
	unsigned int len, total_len;	/* current and remaining length */
	unsigned int flags;		/* splice flags */
	struct file *file;		/* file to read/write */
	loff_t pos;			/* file position */
};

/*
 * 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 *info,
				     struct pipe_buffer *buf)
{
	struct page *page = buf->page;
	struct address_space *mapping = page_mapping(page);

	WARN_ON(!PageLocked(page));
	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, mapping_gfp_mask(mapping));

	if (!remove_mapping(mapping, page))
		return 1;

	buf->flags |= PIPE_BUF_FLAG_STOLEN | PIPE_BUF_FLAG_LRU;
	return 0;
}

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

static void *page_cache_pipe_buf_map(struct file *file,
				     struct pipe_inode_info *info,
				     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, fall through to mapping
		 */
		unlock_page(page);
	}

	return kmap(page);
error:
	unlock_page(page);
	return ERR_PTR(err);
}

static void page_cache_pipe_buf_unmap(struct pipe_inode_info *info,
				      struct pipe_buffer *buf)
{
	kunmap(buf->page);
}

static struct pipe_buf_operations page_cache_pipe_buf_ops = {
	.can_merge = 0,
	.map = page_cache_pipe_buf_map,
	.unmap = page_cache_pipe_buf_unmap,
	.release = page_cache_pipe_buf_release,
	.steal = page_cache_pipe_buf_steal,
};

/*
 * Pipe output worker. This sets up our pipe format with the page cache
 * pipe buffer operations. Otherwise very similar to the regular pipe_writev().
 */
static ssize_t move_to_pipe(struct pipe_inode_info *pipe, struct page **pages,
			    int nr_pages, unsigned long offset,
			    unsigned long len, unsigned int flags)
{
	int ret, do_wakeup, i;

	ret = 0;
	do_wakeup = 0;
	i = 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;
			struct page *page = pages[i++];
			unsigned long this_len;

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

			buf->page = page;
			buf->offset = offset;
			buf->len = this_len;
			buf->ops = &page_cache_pipe_buf_ops;
			pipe->nrbufs++;
			if (pipe->inode)
				do_wakeup = 1;

			ret += this_len;
			len -= this_len;
			offset