aboutsummaryrefslogtreecommitdiff
path: root/fs/pipe.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/pipe.c')
-rw-r--r--fs/pipe.c1258
1 files changed, 773 insertions, 485 deletions
diff --git a/fs/pipe.c b/fs/pipe.c
index 66aa0b938d6..21981e58e2a 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -11,14 +11,34 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
+#include <linux/log2.h>
#include <linux/mount.h>
+#include <linux/magic.h>
#include <linux/pipe_fs_i.h>
#include <linux/uio.h>
#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/audit.h>
+#include <linux/syscalls.h>
+#include <linux/fcntl.h>
+#include <linux/aio.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
+#include "internal.h"
+
+/*
+ * The max size that a non-root user is allowed to grow the pipe. Can
+ * be set by root in /proc/sys/fs/pipe-max-size
+ */
+unsigned int pipe_max_size = 1048576;
+
+/*
+ * Minimum pipe size, as required by POSIX
+ */
+unsigned int pipe_min_size = PAGE_SIZE;
+
/*
* We use a start+len construction, which provides full use of the
* allocated memory.
@@ -34,139 +54,236 @@
* -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09
*/
-/* Drop the inode semaphore and wait for a pipe event, atomically */
-void pipe_wait(struct inode * inode)
+static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass)
{
- DEFINE_WAIT(wait);
+ if (pipe->files)
+ mutex_lock_nested(&pipe->mutex, subclass);
+}
+void pipe_lock(struct pipe_inode_info *pipe)
+{
/*
- * Pipes are system-local resources, so sleeping on them
- * is considered a noninteractive wait:
+ * pipe_lock() nests non-pipe inode locks (for writing to a file)
*/
- prepare_to_wait(PIPE_WAIT(*inode), &wait, TASK_INTERRUPTIBLE|TASK_NONINTERACTIVE);
- up(PIPE_SEM(*inode));
- schedule();
- finish_wait(PIPE_WAIT(*inode), &wait);
- down(PIPE_SEM(*inode));
+ pipe_lock_nested(pipe, I_MUTEX_PARENT);
+}
+EXPORT_SYMBOL(pipe_lock);
+
+void pipe_unlock(struct pipe_inode_info *pipe)
+{
+ if (pipe->files)
+ mutex_unlock(&pipe->mutex);
}
+EXPORT_SYMBOL(pipe_unlock);
-static inline int
-pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len)
+static inline void __pipe_lock(struct pipe_inode_info *pipe)
{
- unsigned long copy;
+ mutex_lock_nested(&pipe->mutex, I_MUTEX_PARENT);
+}
- while (len > 0) {
- while (!iov->iov_len)
- iov++;
- copy = min_t(unsigned long, len, iov->iov_len);
+static inline void __pipe_unlock(struct pipe_inode_info *pipe)
+{
+ mutex_unlock(&pipe->mutex);
+}
- if (copy_from_user(to, iov->iov_base, copy))
- return -EFAULT;
- to += copy;
- len -= copy;
- iov->iov_base += copy;
- iov->iov_len -= copy;
+void pipe_double_lock(struct pipe_inode_info *pipe1,
+ struct pipe_inode_info *pipe2)
+{
+ BUG_ON(pipe1 == pipe2);
+
+ if (pipe1 < pipe2) {
+ pipe_lock_nested(pipe1, I_MUTEX_PARENT);
+ pipe_lock_nested(pipe2, I_MUTEX_CHILD);
+ } else {
+ pipe_lock_nested(pipe2, I_MUTEX_PARENT);
+ pipe_lock_nested(pipe1, I_MUTEX_CHILD);
}
- return 0;
}
-static inline int
-pipe_iov_copy_to_user(struct iovec *iov, const void *from, unsigned long len)
+/* Drop the inode semaphore and wait for a pipe event, atomically */
+void pipe_wait(struct pipe_inode_info *pipe)
{
- unsigned long copy;
+ DEFINE_WAIT(wait);
- while (len > 0) {
- while (!iov->iov_len)
- iov++;
- copy = min_t(unsigned long, len, iov->iov_len);
+ /*
+ * Pipes are system-local resources, so sleeping on them
+ * is considered a noninteractive wait:
+ */
+ prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE);
+ pipe_unlock(pipe);
+ schedule();
+ finish_wait(&pipe->wait, &wait);
+ pipe_lock(pipe);
+}
- 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);
}
-static void anon_pipe_buf_release(struct pipe_inode_info *info, struct pipe_buffer *buf)
+/**
+ * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer
+ * @pipe: the pipe that the buffer belongs to
+ * @buf: the buffer to attempt to steal
+ *
+ * Description:
+ * This function attempts to steal the &struct page attached to
+ * @buf. If successful, this function returns 0 and returns with
+ * the page locked. The caller may then reuse the page for whatever
+ * he wishes; the typical use is insertion into a different file
+ * page cache.
+ */
+int generic_pipe_buf_steal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
{
struct page *page = buf->page;
- if (info->tmp_page) {
- __free_page(page);
- return;
+ /*
+ * A reference of one is golden, that means that the owner of this
+ * page is the only one holding a reference to it. lock the page
+ * and return OK.
+ */
+ if (page_count(page) == 1) {
+ lock_page(page);
+ return 0;
}
- info->tmp_page = page;
+
+ return 1;
}
+EXPORT_SYMBOL(generic_pipe_buf_steal);
-static void *anon_pipe_buf_map(struct file *file, struct pipe_inode_info *info, struct pipe_buffer *buf)
+/**
+ * generic_pipe_buf_get - get a reference to a &struct pipe_buffer
+ * @pipe: the pipe that the buffer belongs to
+ * @buf: the buffer to get a reference to
+ *
+ * Description:
+ * This function grabs an extra reference to @buf. It's used in
+ * in the tee() system call, when we duplicate the buffers in one
+ * pipe into another.
+ */
+void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
{
- return kmap(buf->page);
+ page_cache_get(buf->page);
}
+EXPORT_SYMBOL(generic_pipe_buf_get);
-static void anon_pipe_buf_unmap(struct pipe_inode_info *info, struct pipe_buffer *buf)
+/**
+ * generic_pipe_buf_confirm - verify contents of the pipe buffer
+ * @info: the pipe that the buffer belongs to
+ * @buf: the buffer to confirm
+ *
+ * Description:
+ * This function does nothing, because the generic pipe code uses
+ * pages that are always good when inserted into the pipe.
+ */
+int generic_pipe_buf_confirm(struct pipe_inode_info *info,
+ struct pipe_buffer *buf)
{
- kunmap(buf->page);
+ return 0;
}
+EXPORT_SYMBOL(generic_pipe_buf_confirm);
-static struct pipe_buf_operations anon_pipe_buf_ops = {
+/**
+ * generic_pipe_buf_release - put a reference to a &struct pipe_buffer
+ * @pipe: the pipe that the buffer belongs to
+ * @buf: the buffer to put a reference to
+ *
+ * Description:
+ * This function releases a reference to @buf.
+ */
+void generic_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ page_cache_release(buf->page);
+}
+EXPORT_SYMBOL(generic_pipe_buf_release);
+
+static const struct pipe_buf_operations anon_pipe_buf_ops = {
.can_merge = 1,
- .map = anon_pipe_buf_map,
- .unmap = anon_pipe_buf_unmap,
+ .confirm = generic_pipe_buf_confirm,
+ .release = anon_pipe_buf_release,
+ .steal = generic_pipe_buf_steal,
+ .get = generic_pipe_buf_get,
+};
+
+static const struct pipe_buf_operations packet_pipe_buf_ops = {
+ .can_merge = 0,
+ .confirm = generic_pipe_buf_confirm,
.release = anon_pipe_buf_release,
+ .steal = generic_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)
+pipe_read(struct kiocb *iocb, struct iov_iter *to)
{
- struct inode *inode = filp->f_dentry->d_inode;
- struct pipe_inode_info *info;
+ size_t total_len = iov_iter_count(to);
+ struct file *filp = iocb->ki_filp;
+ struct pipe_inode_info *pipe = filp->private_data;
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;
- down(PIPE_SEM(*inode));
- info = inode->i_pipe;
+ __pipe_lock(pipe);
for (;;) {
- int bufs = info->nrbufs;
+ int bufs = pipe->nrbufs;
if (bufs) {
- int curbuf = info->curbuf;
- struct pipe_buffer *buf = info->bufs + curbuf;
- struct pipe_buf_operations *ops = buf->ops;
- void *addr;
+ int curbuf = pipe->curbuf;
+ struct pipe_buffer *buf = pipe->bufs + curbuf;
+ const struct pipe_buf_operations *ops = buf->ops;
size_t chars = buf->len;
+ size_t written;
int error;
if (chars > total_len)
chars = total_len;
- addr = ops->map(filp, info, buf);
- error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars);
- ops->unmap(info, buf);
- if (unlikely(error)) {
- if (!ret) ret = -EFAULT;
+ error = ops->confirm(pipe, buf);
+ if (error) {
+ if (!ret)
+ ret = error;
+ break;
+ }
+
+ written = copy_page_to_iter(buf->page, buf->offset, chars, to);
+ if (unlikely(written < chars)) {
+ if (!ret)
+ ret = -EFAULT;
break;
}
ret += chars;
buf->offset += chars;
buf->len -= chars;
+
+ /* Was it a packet buffer? Clean up and exit */
+ if (buf->flags & PIPE_BUF_FLAG_PACKET) {
+ total_len = chars;
+ buf->len = 0;
+ }
+
if (!buf->len) {
buf->ops = NULL;
- ops->release(info, buf);
- curbuf = (curbuf + 1) & (PIPE_BUFFERS-1);
- info->curbuf = curbuf;
- info->nrbufs = --bufs;
+ ops->release(pipe, buf);
+ curbuf = (curbuf + 1) & (pipe->buffers - 1);
+ pipe->curbuf = curbuf;
+ pipe->nrbufs = --bufs;
do_wakeup = 1;
}
total_len -= chars;
@@ -175,9 +292,9 @@ pipe_readv(struct file *filp, const struct iovec *_iov,
}
if (bufs) /* More to do? */
continue;
- if (!PIPE_WRITERS(*inode))
+ if (!pipe->writers)
break;
- if (!PIPE_WAITING_WRITERS(*inode)) {
+ if (!pipe->waiting_writers) {
/* syscall merging: Usually we must not sleep
* if O_NONBLOCK is set, or if we got some data.
* But if a writer sleeps in kernel space, then
@@ -191,56 +308,50 @@ pipe_readv(struct file *filp, const struct iovec *_iov,
}
}
if (signal_pending(current)) {
- if (!ret) ret = -ERESTARTSYS;
+ if (!ret)
+ ret = -ERESTARTSYS;
break;
}
if (do_wakeup) {
- wake_up_interruptible_sync(PIPE_WAIT(*inode));
- kill_fasync(PIPE_FASYNC_WRITERS(*inode), SIGIO, POLL_OUT);
+ wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT | POLLWRNORM);
+ kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
- pipe_wait(inode);
+ pipe_wait(pipe);
}
- up(PIPE_SEM(*inode));
- /* Signal writers asynchronously that there is more room. */
+ __pipe_unlock(pipe);
+
+ /* Signal writers asynchronously that there is more room. */
if (do_wakeup) {
- wake_up_interruptible(PIPE_WAIT(*inode));
- kill_fasync(PIPE_FASYNC_WRITERS(*inode), SIGIO, POLL_OUT);
+ wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT | POLLWRNORM);
+ kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
if (ret > 0)
file_accessed(filp);
return ret;
}
-static ssize_t
-pipe_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
+static inline int is_packetized(struct file *file)
{
- struct iovec iov = { .iov_base = buf, .iov_len = count };
- return pipe_readv(filp, &iov, 1, ppos);
+ return (file->f_flags & O_DIRECT) != 0;
}
static ssize_t
-pipe_writev(struct file *filp, const struct iovec *_iov,
- unsigned long nr_segs, loff_t *ppos)
+pipe_write(struct kiocb *iocb, struct iov_iter *from)
{
- struct inode *inode = filp->f_dentry->d_inode;
- struct pipe_inode_info *info;
- ssize_t ret;
- int do_wakeup;
- struct iovec *iov = (struct iovec *)_iov;
- size_t total_len;
+ struct file *filp = iocb->ki_filp;
+ struct pipe_inode_info *pipe = filp->private_data;
+ ssize_t ret = 0;
+ int do_wakeup = 0;
+ size_t total_len = iov_iter_count(from);
ssize_t chars;
- total_len = iov_length(iov, nr_segs);
/* Null write succeeds. */
if (unlikely(total_len == 0))
return 0;
- do_wakeup = 0;
- ret = 0;
- down(PIPE_SEM(*inode));
- info = inode->i_pipe;
+ __pipe_lock(pipe);
- if (!PIPE_READERS(*inode)) {
+ if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
ret = -EPIPE;
goto out;
@@ -248,40 +359,46 @@ pipe_writev(struct file *filp, const struct iovec *_iov,
/* We try to merge small writes */
chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */
- if (info->nrbufs && chars != 0) {
- int lastbuf = (info->curbuf + info->nrbufs - 1) & (PIPE_BUFFERS-1);
- struct pipe_buffer *buf = info->bufs + lastbuf;
- struct pipe_buf_operations *ops = buf->ops;
+ if (pipe->nrbufs && chars != 0) {
+ int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) &
+ (pipe->buffers - 1);
+ struct pipe_buffer *buf = pipe->bufs + lastbuf;
+ const struct pipe_buf_operations *ops = buf->ops;
int offset = buf->offset + buf->len;
+
if (ops->can_merge && offset + chars <= PAGE_SIZE) {
- void *addr = ops->map(filp, info, buf);
- int error = pipe_iov_copy_from_user(offset + addr, iov, chars);
- ops->unmap(info, buf);
- ret = error;
- do_wakeup = 1;
+ int error = ops->confirm(pipe, buf);
if (error)
goto out;
+
+ ret = copy_page_from_iter(buf->page, offset, chars, from);
+ if (unlikely(ret < chars)) {
+ error = -EFAULT;
+ goto out;
+ }
+ do_wakeup = 1;
buf->len += chars;
- total_len -= chars;
ret = chars;
- if (!total_len)
+ if (!iov_iter_count(from))
goto out;
}
}
for (;;) {
int bufs;
- if (!PIPE_READERS(*inode)) {
+
+ if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
- if (!ret) ret = -EPIPE;
+ if (!ret)
+ ret = -EPIPE;
break;
}
- bufs = info->nrbufs;
- if (bufs < PIPE_BUFFERS) {
- int newbuf = (info->curbuf + bufs) & (PIPE_BUFFERS-1);
- struct pipe_buffer *buf = info->bufs + newbuf;
- struct page *page = info->tmp_page;
- int error;
+ bufs = pipe->nrbufs;
+ if (bufs < pipe->buffers) {
+ int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1);
+ struct pipe_buffer *buf = pipe->bufs + newbuf;
+ struct page *page = pipe->tmp_page;
+ int copied;
if (!page) {
page = alloc_page(GFP_HIGHUSER);
@@ -289,111 +406,94 @@ pipe_writev(struct file *filp, const struct iovec *_iov,
ret = ret ? : -ENOMEM;
break;
}
- info->tmp_page = page;
+ pipe->tmp_page = page;
}
- /* Always wakeup, even if the copy fails. Otherwise
+ /* Always wake up, even if the copy fails. Otherwise
* we lock up (O_NONBLOCK-)readers that sleep due to
* syscall merging.
* FIXME! Is this really true?
*/
do_wakeup = 1;
- chars = PAGE_SIZE;
- if (chars > total_len)
- chars = total_len;
-
- error = pipe_iov_copy_from_user(kmap(page), iov, chars);
- kunmap(page);
- if (unlikely(error)) {
- if (!ret) ret = -EFAULT;
+ copied = copy_page_from_iter(page, 0, PAGE_SIZE, from);
+ if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) {
+ if (!ret)
+ ret = -EFAULT;
break;
}
- ret += chars;
+ ret += copied;
/* Insert it into the buffer array */
buf->page = page;
buf->ops = &anon_pipe_buf_ops;
buf->offset = 0;
- buf->len = chars;
- info->nrbufs = ++bufs;
- info->tmp_page = NULL;
+ buf->len = copied;
+ buf->flags = 0;
+ if (is_packetized(filp)) {
+ buf->ops = &packet_pipe_buf_ops;
+ buf->flags = PIPE_BUF_FLAG_PACKET;
+ }
+ pipe->nrbufs = ++bufs;
+ pipe->tmp_page = NULL;
- total_len -= chars;
- if (!total_len)
+ if (!iov_iter_count(from))
break;
}
- if (bufs < PIPE_BUFFERS)
+ if (bufs < pipe->buffers)
continue;
if (filp->f_flags & O_NONBLOCK) {
- if (!ret) ret = -EAGAIN;
+ if (!ret)
+ ret = -EAGAIN;
break;
}
if (signal_pending(current)) {
- if (!ret) ret = -ERESTARTSYS;
+ if (!ret)
+ ret = -ERESTARTSYS;
break;
}
if (do_wakeup) {
- wake_up_interruptible_sync(PIPE_WAIT(*inode));
- kill_fasync(PIPE_FASYNC_READERS(*inode), SIGIO, POLL_IN);
+ wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM);
+ kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
do_wakeup = 0;
}
- PIPE_WAITING_WRITERS(*inode)++;
- pipe_wait(inode);
- PIPE_WAITING_WRITERS(*inode)--;
+ pipe->waiting_writers++;
+ pipe_wait(pipe);
+ pipe->waiting_writers--;
}
out:
- up(PIPE_SEM(*inode));
+ __pipe_unlock(pipe);
if (do_wakeup) {
- wake_up_interruptible(PIPE_WAIT(*inode));
- kill_fasync(PIPE_FASYNC_READERS(*inode), SIGIO, POLL_IN);
+ wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM);
+ kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+ }
+ if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) {
+ int err = file_update_time(filp);
+ if (err)
+ ret = err;
+ sb_end_write(file_inode(filp)->i_sb);
}
- if (ret > 0)
- inode_update_time(inode, 1); /* mtime and ctime */
return ret;
}
-static ssize_t
-pipe_write(struct file *filp, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count };
- return pipe_writev(filp, &iov, 1, ppos);
-}
-
-static ssize_t
-bad_pipe_r(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
+static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- return -EBADF;
-}
-
-static ssize_t
-bad_pipe_w(struct file *filp, const char __user *buf, size_t count, loff_t *ppos)
-{
- return -EBADF;
-}
-
-static int
-pipe_ioctl(struct inode *pino, struct file *filp,
- unsigned int cmd, unsigned long arg)
-{
- struct inode *inode = filp->f_dentry->d_inode;
- struct pipe_inode_info *info;
+ struct pipe_inode_info *pipe = filp->private_data;
int count, buf, nrbufs;
switch (cmd) {
case FIONREAD:
- down(PIPE_SEM(*inode));
- info = inode->i_pipe;
+ __pipe_lock(pipe);
count = 0;
- buf = info->curbuf;
- nrbufs = info->nrbufs;
+ buf = pipe->curbuf;
+ nrbufs = pipe->nrbufs;
while (--nrbufs >= 0) {
- count += info->bufs[buf].len;
- buf = (buf+1) & (PIPE_BUFFERS-1);
+ count += pipe->bufs[buf].len;
+ buf = (buf+1) & (pipe->buffers - 1);
}
- up(PIPE_SEM(*inode));
+ __pipe_unlock(pipe);
+
return put_user(count, (int __user *)arg);
default:
- return -EINVAL;
+ return -ENOIOCTLCMD;
}
}
@@ -402,424 +502,619 @@ static unsigned int
pipe_poll(struct file *filp, poll_table *wait)
{
unsigned int mask;
- struct inode *inode = filp->f_dentry->d_inode;
- struct pipe_inode_info *info = inode->i_pipe;
+ struct pipe_inode_info *pipe = filp->private_data;
int nrbufs;
- poll_wait(filp, PIPE_WAIT(*inode), wait);
+ poll_wait(filp, &pipe->wait, wait);
/* Reading only -- no need for acquiring the semaphore. */
- nrbufs = info->nrbufs;
+ nrbufs = pipe->nrbufs;
mask = 0;
if (filp->f_mode & FMODE_READ) {
mask = (nrbufs > 0) ? POLLIN | POLLRDNORM : 0;
- if (!PIPE_WRITERS(*inode) && filp->f_version != PIPE_WCOUNTER(*inode))
+ if (!pipe->writers && filp->f_version != pipe->w_counter)
mask |= POLLHUP;
}
if (filp->f_mode & FMODE_WRITE) {
- mask |= (nrbufs < PIPE_BUFFERS) ? POLLOUT | POLLWRNORM : 0;
+ mask |= (nrbufs < pipe->buffers) ? POLLOUT | POLLWRNORM : 0;
/*
* Most Unices do not set POLLERR for FIFOs but on Linux they
* behave exactly like pipes for poll().
*/
- if (!PIPE_READERS(*inode))
+ if (!pipe->readers)
mask |= POLLERR;
}
return mask;
}
+static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe)
+{
+ int kill = 0;
+
+ spin_lock(&inode->i_lock);
+ if (!--pipe->files) {
+ inode->i_pipe = NULL;
+ kill = 1;
+ }
+ spin_unlock(&inode->i_lock);
+
+ if (kill)
+ free_pipe_info(pipe);
+}
+
static int
-pipe_release(struct inode *inode, int decr, int decw)
+pipe_release(struct inode *inode, struct file *file)
{
- down(PIPE_SEM(*inode));
- PIPE_READERS(*inode) -= decr;
- PIPE_WRITERS(*inode) -= decw;
- if (!PIPE_READERS(*inode) && !PIPE_WRITERS(*inode)) {
- free_pipe_info(inode);
- } else {
- wake_up_interruptible(PIPE_WAIT(*inode));
- kill_fasync(PIPE_FASYNC_READERS(*inode), SIGIO, POLL_IN);
- kill_fasync(PIPE_FASYNC_WRITERS(*inode), SIGIO, POLL_OUT);
+ struct pipe_inode_info *pipe = file->private_data;
+
+ __pipe_lock(pipe);
+ if (file->f_mode & FMODE_READ)
+ pipe->readers--;
+ if (file->f_mode & FMODE_WRITE)
+ pipe->writers--;
+
+ if (pipe->readers || pipe->writers) {
+ wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM | POLLERR | POLLHUP);
+ kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+ kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
- up(PIPE_SEM(*inode));
+ __pipe_unlock(pipe);
+ put_pipe_info(inode, pipe);
return 0;
}
static int
-pipe_read_fasync(int fd, struct file *filp, int on)
+pipe_fasync(int fd, struct file *filp, int on)
{
- struct inode *inode = filp->f_dentry->d_inode;
- int retval;
+ struct pipe_inode_info *pipe = filp->private_data;
+ int retval = 0;
- down(PIPE_SEM(*inode));
- retval = fasync_helper(fd, filp, on, PIPE_FASYNC_READERS(*inode));
- up(PIPE_SEM(*inode));
+ __pipe_lock(pipe);
+ if (filp->f_mode & FMODE_READ)
+ retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
+ if ((filp->f_mode & FMODE_WRITE) && retval >= 0) {
+ retval = fasync_helper(fd, filp, on, &pipe->fasync_writers);
+ if (retval < 0 && (filp->f_mode & FMODE_READ))
+ /* this can happen only if on == T */
+ fasync_helper(-1, filp, 0, &pipe->fasync_readers);
+ }
+ __pipe_unlock(pipe);
+ return retval;
+}
- if (retval < 0)
- return retval;
+struct pipe_inode_info *alloc_pipe_info(void)
+{
+ struct pipe_inode_info *pipe;
+
+ pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
+ if (pipe) {
+ pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL);
+ if (pipe->bufs) {
+ init_waitqueue_head(&pipe->wait);
+ pipe->r_counter = pipe->w_counter = 1;
+ pipe->buffers = PIPE_DEF_BUFFERS;
+ mutex_init(&pipe->mutex);
+ return pipe;
+ }
+ kfree(pipe);
+ }
- return 0;
+ return NULL;
}
-
-static int
-pipe_write_fasync(int fd, struct file *filp, int on)
+void free_pipe_info(struct pipe_inode_info *pipe)
{
- struct inode *inode = filp->f_dentry->d_inode;
- int retval;
+ int i;
- down(PIPE_SEM(*inode));
- retval = fasync_helper(fd, filp, on, PIPE_FASYNC_WRITERS(*inode));
- up(PIPE_SEM(*inode));
+ for (i = 0; i < pipe->buffers; i++) {
+ struct pipe_buffer *buf = pipe->bufs + i;
+ if (buf->ops)
+ buf->ops->release(pipe, buf);
+ }
+ if (pipe->tmp_page)
+ __free_page(pipe->tmp_page);
+ kfree(pipe->bufs);
+ kfree(pipe);
+}
- if (retval < 0)
- return retval;
+static struct vfsmount *pipe_mnt __read_mostly;
- return 0;
+/*
+ * pipefs_dname() is called from d_path().
+ */
+static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+ return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
+ dentry->d_inode->i_ino);
}
+static const struct dentry_operations pipefs_dentry_operations = {
+ .d_dname = pipefs_dname,
+};
-static int
-pipe_rdwr_fasync(int fd, struct file *filp, int on)
+static struct inode * get_pipe_inode(void)
{
- struct inode *inode = filp->f_dentry->d_inode;
- int retval;
+ struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb);
+ struct pipe_inode_info *pipe;
- down(PIPE_SEM(*inode));
+ if (!inode)
+ goto fail_inode;
- retval = fasync_helper(fd, filp, on, PIPE_FASYNC_READERS(*inode));
+ inode->i_ino = get_next_ino();
- if (retval >= 0)
- retval = fasync_helper(fd, filp, on, PIPE_FASYNC_WRITERS(*inode));
+ pipe = alloc_pipe_info();
+ if (!pipe)
+ goto fail_iput;
- up(PIPE_SEM(*inode));
+ inode->i_pipe = pipe;
+ pipe->files = 2;
+ pipe->readers = pipe->writers = 1;
+ inode->i_fop = &pipefifo_fops;
- if (retval < 0)
- return retval;
+ /*
+ * Mark the inode dirty from the very beginning,
+ * that way it will never be moved to the dirty
+ * list because "mark_inode_dirty()" will think
+ * that it already _is_ on the dirty list.
+ */
+ inode->i_state = I_DIRTY;
+ inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR;
+ inode->i_uid = current_fsuid();
+ inode->i_gid = current_fsgid();
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- return 0;
-}
+ return inode;
+fail_iput:
+ iput(inode);
-static int
-pipe_read_release(struct inode *inode, struct file *filp)
-{
- pipe_read_fasync(-1, filp, 0);
- return pipe_release(inode, 1, 0);
+fail_inode:
+ return NULL;
}
-static int
-pipe_write_release(struct inode *inode, struct file *filp)
+int create_pipe_files(struct file **res, int flags)
{
- pipe_write_fasync(-1, filp, 0);
- return pipe_release(inode, 0, 1);
-}
+ int err;
+ struct inode *inode = get_pipe_inode();
+ struct file *f;
+ struct path path;
+ static struct qstr name = { .name = "" };
-static int
-pipe_rdwr_release(struct inode *inode, struct file *filp)
-{
- int decr, decw;
+ if (!inode)
+ return -ENFILE;
- pipe_rdwr_fasync(-1, filp, 0);
- decr = (filp->f_mode & FMODE_READ) != 0;
- decw = (filp->f_mode & FMODE_WRITE) != 0;
- return pipe_release(inode, decr, decw);
-}
+ err = -ENOMEM;
+ path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name);
+ if (!path.dentry)
+ goto err_inode;
+ path.mnt = mntget(pipe_mnt);
-static int
-pipe_read_open(struct inode *inode, struct file *filp)
-{
- /* We could have perhaps used atomic_t, but this and friends
- below are the only places. So it doesn't seem worthwhile. */
- down(PIPE_SEM(*inode));
- PIPE_READERS(*inode)++;
- up(PIPE_SEM(*inode));
+ d_instantiate(path.dentry, inode);
+
+ err = -ENFILE;
+ f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops);
+ if (IS_ERR(f))
+ goto err_dentry;
+
+ f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
+ f->private_data = inode->i_pipe;
+ res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);
+ if (IS_ERR(res[0]))
+ goto err_file;
+
+ path_get(&path);
+ res[0]->private_data = inode->i_pipe;
+ res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK);
+ res[1] = f;
return 0;
+
+err_file:
+ put_filp(f);
+err_dentry:
+ free_pipe_info(inode->i_pipe);
+ path_put(&path);
+ return err;
+
+err_inode:
+ free_pipe_info(inode->i_pipe);
+ iput(inode);
+ return err;
}
-static int
-pipe_write_open(struct inode *inode, struct file *filp)
+static int __do_pipe_flags(int *fd, struct file **files, int flags)
{
- down(PIPE_SEM(*inode));
- PIPE_WRITERS(*inode)++;
- up(PIPE_SEM(*inode));
+ int error;
+ int fdw, fdr;
+
+ if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT))
+ return -EINVAL;
+
+ error = create_pipe_files(files, flags);
+ if (error)
+ return error;
+ error = get_unused_fd_flags(flags);
+ if (error < 0)
+ goto err_read_pipe;
+ fdr = error;
+
+ error = get_unused_fd_flags(flags);
+ if (error < 0)
+ goto err_fdr;
+ fdw = error;
+
+ audit_fd_pair(fdr, fdw);
+ fd[0] = fdr;
+ fd[1] = fdw;
return 0;
+
+ err_fdr:
+ put_unused_fd(fdr);
+ err_read_pipe:
+ fput(files[0]);
+ fput(files[1]);
+ return error;
}
-static int
-pipe_rdwr_open(struct inode *inode, struct file *filp)
+int do_pipe_flags(int *fd, int flags)
{
- down(PIPE_SEM(*inode));
- if (filp->f_mode & FMODE_READ)
- PIPE_READERS(*inode)++;
- if (filp->f_mode & FMODE_WRITE)
- PIPE_WRITERS(*inode)++;
- up(PIPE_SEM(*inode));
-
- return 0;
+ struct file *files[2];
+ int error = __do_pipe_flags(fd, files, flags);
+ if (!error) {
+ fd_install(fd[0], files[0]);
+ fd_install(fd[1], files[1]);
+ }
+ return error;
}
/*
- * The file_operations structs are not static because they
- * are also used in linux/fs/fifo.c to do operations on FIFOs.
+ * sys_pipe() is the normal C calling standard for creating
+ * a pipe. It's not the way Unix traditionally does this, though.
*/
-struct file_operations read_fifo_fops = {
- .llseek = no_llseek,
- .read = pipe_read,
- .readv = pipe_readv,
- .write = bad_pipe_w,
- .poll = pipe_poll,
- .ioctl = pipe_ioctl,
- .open = pipe_read_open,
- .release = pipe_read_release,
- .fasync = pipe_read_fasync,
-};
+SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags)
+{
+ struct file *files[2];
+ int fd[2];
+ int error;
-struct file_operations write_fifo_fops = {
- .llseek = no_llseek,
- .read = bad_pipe_r,
- .write = pipe_write,
- .writev = pipe_writev,
- .poll = pipe_poll,
- .ioctl = pipe_ioctl,
- .open = pipe_write_open,
- .release = pipe_write_release,
- .fasync = pipe_write_fasync,
-};
+ error = __do_pipe_flags(fd, files, flags);
+ if (!error) {
+ if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) {
+ fput(files[0]);
+ fput(files[1]);
+ put_unused_fd(fd[0]);
+ put_unused_fd(fd[1]);
+ error = -EFAULT;
+ } else {
+ fd_install(fd[0], files[0]);
+ fd_install(fd[1], files[1]);
+ }
+ }
+ return error;
+}
-struct file_operations rdwr_fifo_fops = {
- .llseek = no_llseek,
- .read = pipe_read,
- .readv = pipe_readv,
- .write = pipe_write,
- .writev = pipe_writev,
- .poll = pipe_poll,
- .ioctl = pipe_ioctl,
- .open = pipe_rdwr_open,
- .release = pipe_rdwr_release,
- .fasync = pipe_rdwr_fasync,
-};
+SYSCALL_DEFINE1(pipe, int __user *, fildes)
+{
+ return sys_pipe2(fildes, 0);
+}
-struct file_operations read_pipe_fops = {
- .llseek = no_llseek,
- .read = pipe_read,
- .readv = pipe_readv,
- .write = bad_pipe_w,
- .poll = pipe_poll,
- .ioctl = pipe_ioctl,
- .open = pipe_read_open,
- .release = pipe_read_release,
- .fasync = pipe_read_fasync,
-};
+static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt)
+{
+ int cur = *cnt;
-struct file_operations write_pipe_fops = {
- .llseek = no_llseek,
- .read = bad_pipe_r,
- .write = pipe_write,
- .writev = pipe_writev,
- .poll = pipe_poll,
- .ioctl = pipe_ioctl,
- .open = pipe_write_open,
- .release = pipe_write_release,
- .fasync = pipe_write_fasync,
-};
+ while (cur == *cnt) {
+ pipe_wait(pipe);
+ if (signal_pending(current))
+ break;
+ }
+ return cur == *cnt ? -ERESTARTSYS : 0;
+}
-struct file_operations rdwr_pipe_fops = {
- .llseek = no_llseek,
- .read = pipe_read,
- .readv = pipe_readv,
- .write = pipe_write,
- .writev = pipe_writev,
- .poll = pipe_poll,
- .ioctl = pipe_ioctl,
- .open = pipe_rdwr_open,
- .release = pipe_rdwr_release,
- .fasync = pipe_rdwr_fasync,
-};
+static void wake_up_partner(struct pipe_inode_info *pipe)
+{
+ wake_up_interruptible(&pipe->wait);
+}
-void free_pipe_info(struct inode *inode)
+static int fifo_open(struct inode *inode, struct file *filp)
{
- int i;
- struct pipe_inode_info *info = inode->i_pipe;
+ struct pipe_inode_info *pipe;
+ bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC;
+ int ret;
- inode->i_pipe = NULL;
- for (i = 0; i < PIPE_BUFFERS; i++) {
- struct pipe_buffer *buf = info->bufs + i;
- if (buf->ops)
- buf->ops->release(info, buf);
+ filp->f_version = 0;
+
+ spin_lock(&inode->i_lock);
+ if (inode->i_pipe) {
+ pipe = inode->i_pipe;
+ pipe->files++;
+ spin_unlock(&inode->i_lock);
+ } else {
+ spin_unlock(&inode->i_lock);
+ pipe = alloc_pipe_info();
+ if (!pipe)
+ return -ENOMEM;
+ pipe->files = 1;
+ spin_lock(&inode->i_lock);
+ if (unlikely(inode->i_pipe)) {
+ inode->i_pipe->files++;
+ spin_unlock(&inode->i_lock);
+ free_pipe_info(pipe);
+ pipe = inode->i_pipe;
+ } else {
+ inode->i_pipe = pipe;
+ spin_unlock(&inode->i_lock);
+ }
}
- if (info->tmp_page)
- __free_page(info->tmp_page);
- kfree(info);
-}
+ filp->private_data = pipe;
+ /* OK, we have a pipe and it's pinned down */
-struct inode* pipe_new(struct inode* inode)
-{
- struct pipe_inode_info *info;
+ __pipe_lock(pipe);
- info = kmalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
- if (!info)
- goto fail_page;
- memset(info, 0, sizeof(*info));
- inode->i_pipe = info;
+ /* We can only do regular read/write on fifos */
+ filp->f_mode &= (FMODE_READ | FMODE_WRITE);
- init_waitqueue_head(PIPE_WAIT(*inode));
- PIPE_RCOUNTER(*inode) = PIPE_WCOUNTER(*inode) = 1;
+ switch (filp->f_mode) {
+ case FMODE_READ:
+ /*
+ * O_RDONLY
+ * POSIX.1 says that O_NONBLOCK means return with the FIFO
+ * opened, even when there is no process writing the FIFO.
+ */
+ pipe->r_counter++;
+ if (pipe->readers++ == 0)
+ wake_up_partner(pipe);
+
+ if (!is_pipe && !pipe->writers) {
+ if ((filp->f_flags & O_NONBLOCK)) {
+ /* suppress POLLHUP until we have
+ * seen a writer */
+ filp->f_version = pipe->w_counter;
+ } else {
+ if (wait_for_partner(pipe, &pipe->w_counter))
+ goto err_rd;
+ }
+ }
+ break;
+
+ case FMODE_WRITE:
+ /*
+ * O_WRONLY
+ * POSIX.1 says that O_NONBLOCK means return -1 with
+ * errno=ENXIO when there is no process reading the FIFO.
+ */
+ ret = -ENXIO;
+ if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers)
+ goto err;
- return inode;
-fail_page:
- return NULL;
-}
+ pipe->w_counter++;
+ if (!pipe->writers++)
+ wake_up_partner(pipe);
-static struct vfsmount *pipe_mnt;
-static int pipefs_delete_dentry(struct dentry *dentry)
-{
- return 1;
+ if (!is_pipe && !pipe->readers) {
+ if (wait_for_partner(pipe, &pipe->r_counter))
+ goto err_wr;
+ }
+ break;
+
+ case FMODE_READ | FMODE_WRITE:
+ /*
+ * O_RDWR
+ * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set.
+ * This implementation will NEVER block on a O_RDWR open, since
+ * the process can at least talk to itself.
+ */
+
+ pipe->readers++;
+ pipe->writers++;
+ pipe->r_counter++;
+ pipe->w_counter++;
+ if (pipe->readers == 1 || pipe->writers == 1)
+ wake_up_partner(pipe);
+ break;
+
+ default:
+ ret = -EINVAL;
+ goto err;
+ }
+
+ /* Ok! */
+ __pipe_unlock(pipe);
+ return 0;
+
+err_rd:
+ if (!--pipe->readers)
+ wake_up_interruptible(&pipe->wait);
+ ret = -ERESTARTSYS;
+ goto err;
+
+err_wr:
+ if (!--pipe->writers)
+ wake_up_interruptible(&pipe->wait);
+ ret = -ERESTARTSYS;
+ goto err;
+
+err:
+ __pipe_unlock(pipe);
+
+ put_pipe_info(inode, pipe);
+ return ret;
}
-static struct dentry_operations pipefs_dentry_operations = {
- .d_delete = pipefs_delete_dentry,
+
+const struct file_operations pipefifo_fops = {
+ .open = fifo_open,
+ .llseek = no_llseek,
+ .read = new_sync_read,
+ .read_iter = pipe_read,
+ .write = new_sync_write,
+ .write_iter = pipe_write,
+ .poll = pipe_poll,
+ .unlocked_ioctl = pipe_ioctl,
+ .release = pipe_release,
+ .fasync = pipe_fasync,
};
-static struct inode * get_pipe_inode(void)
+/*
+ * Allocate a new array of pipe buffers and copy the info over. Returns the
+ * pipe size if successful, or return -ERROR on error.
+ */
+static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
{
- struct inode *inode = new_inode(pipe_mnt->mnt_sb);
+ struct pipe_buffer *bufs;
- if (!inode)
- goto fail_inode;
+ /*
+ * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't
+ * expect a lot of shrink+grow operations, just free and allocate
+ * again like we would do for growing. If the pipe currently
+ * contains more buffers than arg, then return busy.
+ */
+ if (nr_pages < pipe->nrbufs)
+ return -EBUSY;
- if(!pipe_new(inode))
- goto fail_iput;
- PIPE_READERS(*inode) = PIPE_WRITERS(*inode) = 1;
- inode->i_fop = &rdwr_pipe_fops;
+ bufs = kcalloc(nr_pages, sizeof(*bufs), GFP_KERNEL | __GFP_NOWARN);
+ if (unlikely(!bufs))
+ return -ENOMEM;
/*
- * Mark the inode dirty from the very beginning,
- * that way it will never be moved to the dirty
- * list because "mark_inode_dirty()" will think
- * that it already _is_ on the dirty list.
+ * The pipe array wraps around, so just start the new one at zero
+ * and adjust the indexes.
*/
- inode->i_state = I_DIRTY;
- inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR;
- inode->i_uid = current->fsuid;
- inode->i_gid = current->fsgid;
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- inode->i_blksize = PAGE_SIZE;
- return inode;
+ if (pipe->nrbufs) {
+ unsigned int tail;
+ unsigned int head;
+
+ tail = pipe->curbuf + pipe->nrbufs;
+ if (tail < pipe->buffers)
+ tail = 0;
+ else
+ tail &= (pipe->buffers - 1);
+
+ head = pipe->nrbufs - tail;
+ if (head)
+ memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer));
+ if (tail)
+ memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
+ }
-fail_iput:
- iput(inode);
-fail_inode:
- return NULL;
+ pipe->curbuf = 0;
+ kfree(pipe->bufs);
+ pipe->bufs = bufs;
+ pipe->buffers = nr_pages;
+ return nr_pages * PAGE_SIZE;
}
-int do_pipe(int *fd)
+/*
+ * Currently we rely on the pipe array holding a power-of-2 number
+ * of pages.
+ */
+static inline unsigned int round_pipe_size(unsigned int size)
{
- struct qstr this;
- char name[32];
- struct dentry *dentry;
- struct inode * inode;
- struct file *f1, *f2;
- int error;
- int i,j;
+ unsigned long nr_pages;
- error = -ENFILE;
- f1 = get_empty_filp();
- if (!f1)
- goto no_files;
+ nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ return roundup_pow_of_two(nr_pages) << PAGE_SHIFT;
+}
- f2 = get_empty_filp();
- if (!f2)
- goto close_f1;
+/*
+ * This should work even if CONFIG_PROC_FS isn't set, as proc_dointvec_minmax
+ * will return an error.
+ */
+int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf,
+ size_t *lenp, loff_t *ppos)
+{
+ int ret;
- inode = get_pipe_inode();
- if (!inode)
- goto close_f12;
+ ret = proc_dointvec_minmax(table, write, buf, lenp, ppos);
+ if (ret < 0 || !write)
+ return ret;
- error = get_unused_fd();
- if (error < 0)
- goto close_f12_inode;
- i = error;
+ pipe_max_size = round_pipe_size(pipe_max_size);
+ return ret;
+}
- error = get_unused_fd();
- if (error < 0)
- goto close_f12_inode_i;
- j = error;
-
- error = -ENOMEM;
- sprintf(name, "[%lu]", inode->i_ino);
- this.name = name;
- this.len = strlen(name);
- this.hash = inode->i_ino; /* will go */
- dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &this);
- if (!dentry)
- goto close_f12_inode_i_j;
- dentry->d_op = &pipefs_dentry_operations;
- d_add(dentry, inode);
- f1->f_vfsmnt = f2->f_vfsmnt = mntget(mntget(pipe_mnt));
- f1->f_dentry = f2->f_dentry = dget(dentry);
- f1->f_mapping = f2->f_mapping = inode->i_mapping;
-
- /* read file */
- f1->f_pos = f2->f_pos = 0;
- f1->f_flags = O_RDONLY;
- f1->f_op = &read_pipe_fops;
- f1->f_mode = FMODE_READ;
- f1->f_version = 0;
-
- /* write file */
- f2->f_flags = O_WRONLY;
- f2->f_op = &write_pipe_fops;
- f2->f_mode = FMODE_WRITE;
- f2->f_version = 0;
-
- fd_install(i, f1);
- fd_install(j, f2);
- fd[0] = i;
- fd[1] = j;
- return 0;
+/*
+ * 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.
+ */
+struct pipe_inode_info *get_pipe_info(struct file *file)
+{
+ return file->f_op == &pipefifo_fops ? file->private_data : NULL;
+}
-close_f12_inode_i_j:
- put_unused_fd(j);
-close_f12_inode_i:
- put_unused_fd(i);
-close_f12_inode:
- free_pipe_info(inode);
- iput(inode);
-close_f12:
- put_filp(f2);
-close_f1:
- put_filp(f1);
-no_files:
- return error;
+long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct pipe_inode_info *pipe;
+ long ret;
+
+ pipe = get_pipe_info(file);
+ if (!pipe)
+ return -EBADF;
+
+ __pipe_lock(pipe);
+
+ switch (cmd) {
+ case F_SETPIPE_SZ: {
+ unsigned int size, nr_pages;
+
+ size = round_pipe_size(arg);
+ nr_pages = size >> PAGE_SHIFT;
+
+ ret = -EINVAL;
+ if (!nr_pages)
+ goto out;
+
+ if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
+ ret = -EPERM;
+ goto out;
+ }
+ ret = pipe_set_size(pipe, nr_pages);
+ break;
+ }
+ case F_GETPIPE_SZ:
+ ret = pipe->buffers * PAGE_SIZE;
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+out:
+ __pipe_unlock(pipe);
+ return ret;
}
+static const struct super_operations pipefs_ops = {
+ .destroy_inode = free_inode_nonrcu,
+ .statfs = simple_statfs,
+};
+
/*
* pipefs should _never_ be mounted by userland - too much of security hassle,
* no real gain from having the whole whorehouse mounted. So we don't need
* any operations on the root directory. However, we need a non-trivial
* d_name - pipe: will go nicely and kill the special-casing in procfs.
*/
-
-static struct super_block *pipefs_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static struct dentry *pipefs_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
{
- return get_sb_pseudo(fs_type, "pipe:", NULL, PIPEFS_MAGIC);
+ return mount_pseudo(fs_type, "pipe:", &pipefs_ops,
+ &pipefs_dentry_operations, PIPEFS_MAGIC);
}
static struct file_system_type pipe_fs_type = {
.name = "pipefs",
- .get_sb = pipefs_get_sb,
+ .mount = pipefs_mount,
.kill_sb = kill_anon_super,
};
static int __init init_pipe_fs(void)
{
int err = register_filesystem(&pipe_fs_type);
+
if (!err) {
pipe_mnt = kern_mount(&pipe_fs_type);
if (IS_ERR(pipe_mnt)) {
@@ -830,11 +1125,4 @@ static int __init init_pipe_fs(void)
return err;
}
-static void __exit exit_pipe_fs(void)
-{
- unregister_filesystem(&pipe_fs_type);
- mntput(pipe_mnt);
-}
-
fs_initcall(init_pipe_fs);
-module_exit(exit_pipe_fs);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-05 23:31:21 +0000