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, 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/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>
#include <linux/uio.h>

struct partial_page {
	unsigned int offset;
	unsigned int len;
};

/*
 * Passed to splice_to_pipe
 */
struct splice_pipe_desc {
	struct page **pages;		/* page map */
	struct partial_page *partial;	/* pages[] may not be contig */
	int nr_pages;			/* number of pages in map */
	unsigned int flags;		/* splice flags */
	struct pipe_buf_operations *ops;/* ops associated with output pipe */
};

/*
 * 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, mapping_gfp_mask(mapping));

		/*
		 * 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.
	 */
	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;
}

static int page_cache_pipe_buf_pin(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 struct pipe_buf_operations page_cache_pipe_buf_ops = {
	.can_merge = 0,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.pin = page_cache_pipe_buf_pin,
	.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 struct pipe_buf_operations user_page_pipe_buf_ops = {
	.can_merge = 0,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.pin = generic_pipe_buf_pin,
	.release = page_cache_pipe_buf_release,
	.steal = user_page_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

/*
 * 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 splice_to_pipe(struct pipe_inode_info *pipe,
			      struct splice_pipe_desc *spd)
{
	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->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->nr_pages)
		page_cache_release(spd->pages[page_nr++]);

	return ret;
}

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;
	struct page *pages[PIPE_BUFFERS];
	struct partial_page partial[PIPE_BUFFERS];
	struct page *page;
	pgoff_t index, end_index;
	loff_t isize;
	size_t total_len;
	int error, page_nr;
	struct splice_pipe_desc spd = {
		.pages = pages,
		.partial = partial,
		.flags = flags,
		.ops = &page_cache_pipe_buf_ops,
	};

	index = *ppos >> PAGE_CACHE_SHIFT;
	loff = *ppos & ~PAGE_CACHE_MASK;
	nr_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;

	if (nr_pages > PIPE_BUFFERS)
		nr_pages = PIPE_BUFFERS;

	/*
	 * Initiate read-ahead on this page range. however, don't call into
	 * read-ahead if this is a non-zero offset (we are likely doing small
	 * chunk splice and the page is already there) for a single page.
	 */
	if (!loff || nr_pages > 1)
		page_cache_readahead(mapping, &in->f_ra, in, index, nr_pages);

	/*
	 * Now fill in the holes:
	 */
	error = 0;
	total_len = 0;

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

	/*
	 * If find_get_pages_contig() returned fewer pages than we needed,
	 * allocate the