path: root/fs/pipe.c

/*
 *  linux/fs/pipe.c
 *
 *  Copyright (C) 1991, 1992, 1999  Linus Torvalds
 */

#include <linux/mm.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/pipe_fs_i.h>
#include <linux/uio.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>

#include <asm/uaccess.h>
#include <asm/ioctls.h>

/*
 * We use a start+len construction, which provides full use of the 
 * allocated memory.
 * -- Florian Coosmann (FGC)
 * 
 * Reads with count = 0 should always return 0.
 * -- Julian Bradfield 1999-06-07.
 *
 * FIFOs and Pipes now generate SIGIO for both readers and writers.
 * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16
 *
 * pipe_read & write cleanup
 * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09
 */

/* Drop the inode semaphore and wait for a pipe event, atomically */
void pipe_wait(struct pipe_inode_info *pipe)
{
	DEFINE_WAIT(wait);

	/*
	 * Pipes are system-local resources, so sleeping on them
	 * is considered a noninteractive wait:
	 */
	prepare_to_wait(&pipe->wait, &wait,
			TASK_INTERRUPTIBLE | TASK_NONINTERACTIVE);
	if (pipe->inode)
		mutex_unlock(&pipe->inode->i_mutex);
	schedule();
	finish_wait(&pipe->wait, &wait);
	if (pipe->inode)
		mutex_lock(&pipe->inode->i_mutex);
}

static int
pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len)
{
	unsigned long copy;

	while (len > 0) {
		while (!iov->iov_len)
			iov++;
		copy = min_t(unsigned long, len, iov->iov_len);

		if (copy_from_user(to, iov->iov_base, copy))
			return -EFAULT;
		to += copy;
		len -= copy;
		iov->iov_base += copy;
		iov->iov_len -= copy;
	}
	return 0;
}

static int
pipe_iov_copy_to_user(struct iovec *iov, const void *from, unsigned long len)
{
	unsigned long copy;

	while (len > 0) {
		while (!iov->iov_len)
			iov++;
		copy = min_t(unsigned long, len, iov->iov_len);

		if (copy_to_user(iov->iov_base, from, copy))
			return -EFAULT;
		from += copy;
		len -= copy;
		iov->iov_base += copy;
		iov->iov_len -= copy;
	}
	return 0;
}

static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
				  struct pipe_buffer *buf)
{
	struct page *page = buf->page;

	/*
	 * If nobody else uses this page, and we don't already have a
	 * temporary page, let's keep track of it as a one-deep
	 * allocation cache. (Otherwise just release our reference to it)
	 */
	if (page_count(page) == 1 && !pipe->tmp_page)
		pipe->tmp_page = page;
	else
		page_cache_release(page);
}

void *generic_pipe_buf_map(struct pipe_inode_info *pipe,
			   struct pipe_buffer *buf)
{
	return kmap(buf->page);
}

void generic_pipe_buf_unmap(struct pipe_inode_info *pipe,
			    struct pipe_buffer *buf)
{
	kunmap(buf->page);
}

static int anon_pipe_buf_steal(struct pipe_inode_info *pipe,
			       struct pipe_buffer *buf)
{
	struct page *page = buf->page;

	if (page_count(page) == 1) {
		lock_page(page);
		return 0;
	}

	return 1;
}

void generic_pipe_buf_get(struct pipe_inode_info *info, struct pipe_buffer *buf)
{
	page_cache_get(buf->page);
}

int generic_pipe_buf_pin(struct pipe_inode_info *info, struct pipe_buffer *buf)
{
	return 0;
}

static struct pipe_buf_operations anon_pipe_buf_ops = {
	.can_merge = 1,
	.map = generic_pipe_buf_map,
	.unmap = generic_pipe_buf_unmap,
	.pin = generic_pipe_buf_pin,
	.release = anon_pipe_buf_release,
	.steal = anon_pipe_buf_steal,
	.get = generic_pipe_buf_get,
};

static ssize_t
pipe_readv(struct file *filp, const struct iovec *_iov,
	   unsigned long nr_segs, loff_t *ppos)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct pipe_inode_info *pipe;
	int do_wakeup;
	ssize_t ret;
	struct iovec *iov = (struct iovec *)_iov;
	size_t total_len;

	total_len = iov_length(iov, nr_segs);
	/* Null read succeeds. */
	if (unlikely(total_len == 0))
		return 0;

	do_wakeup = 0;
	ret = 0;
	mutex_lock(&inode->i_mutex);
	pipe = inode->i_pipe;
	for (;;) {
		int bufs = pipe->nrbufs;
		if (bufs) {