* -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09
*/
-static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass)
+#define cmp_int(l, r) ((l > r) - (l < r))
+
+#ifdef CONFIG_PROVE_LOCKING
+static int pipe_lock_cmp_fn(const struct lockdep_map *a,
+ const struct lockdep_map *b)
{
- if (pipe->files)
- mutex_lock_nested(&pipe->mutex, subclass);
+ return cmp_int((unsigned long) a, (unsigned long) b);
}
+#endif
void pipe_lock(struct pipe_inode_info *pipe)
{
- /*
- * pipe_lock() nests non-pipe inode locks (for writing to a file)
- */
- pipe_lock_nested(pipe, I_MUTEX_PARENT);
+ if (pipe->files)
+ mutex_lock(&pipe->mutex);
}
EXPORT_SYMBOL(pipe_lock);
}
EXPORT_SYMBOL(pipe_unlock);
-static inline void __pipe_lock(struct pipe_inode_info *pipe)
-{
- mutex_lock_nested(&pipe->mutex, I_MUTEX_PARENT);
-}
-
-static inline void __pipe_unlock(struct pipe_inode_info *pipe)
-{
- mutex_unlock(&pipe->mutex);
-}
-
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);
- }
+ if (pipe1 > pipe2)
+ swap(pipe1, pipe2);
+
+ pipe_lock(pipe1);
+ pipe_lock(pipe2);
}
static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
return !pipe_empty(head, tail) || !writers;
}
+static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf,
+ unsigned int tail)
+{
+ pipe_buf_release(pipe, buf);
+
+ /*
+ * If the pipe has a watch_queue, we need additional protection
+ * by the spinlock because notifications get posted with only
+ * this spinlock, no mutex
+ */
+ if (pipe_has_watch_queue(pipe)) {
+ spin_lock_irq(&pipe->rd_wait.lock);
+#ifdef CONFIG_WATCH_QUEUE
+ if (buf->flags & PIPE_BUF_FLAG_LOSS)
+ pipe->note_loss = true;
+#endif
+ pipe->tail = ++tail;
+ spin_unlock_irq(&pipe->rd_wait.lock);
+ return tail;
+ }
+
+ /*
+ * Without a watch_queue, we can simply increment the tail
+ * without the spinlock - the mutex is enough.
+ */
+ pipe->tail = ++tail;
+ return tail;
+}
+
static ssize_t
pipe_read(struct kiocb *iocb, struct iov_iter *to)
{
return 0;
ret = 0;
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
/*
* We only wake up writers if the pipe was full when we started
buf->len = 0;
}
- if (!buf->len) {
- pipe_buf_release(pipe, buf);
- spin_lock_irq(&pipe->rd_wait.lock);
-#ifdef CONFIG_WATCH_QUEUE
- if (buf->flags & PIPE_BUF_FLAG_LOSS)
- pipe->note_loss = true;
-#endif
- tail++;
- pipe->tail = tail;
- spin_unlock_irq(&pipe->rd_wait.lock);
- }
+ if (!buf->len)
+ tail = pipe_update_tail(pipe, buf, tail);
total_len -= chars;
if (!total_len)
break; /* common path: read succeeded */
break;
if (ret)
break;
- if (filp->f_flags & O_NONBLOCK) {
+ if ((filp->f_flags & O_NONBLOCK) ||
+ (iocb->ki_flags & IOCB_NOWAIT)) {
ret = -EAGAIN;
break;
}
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
/*
* We only get here if we didn't actually read anything.
if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0)
return -ERESTARTSYS;
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage);
wake_next_reader = true;
}
if (pipe_empty(pipe->head, pipe->tail))
wake_next_reader = false;
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
if (was_full)
wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM);
bool was_empty = false;
bool wake_next_writer = false;
+ /*
+ * Reject writing to watch queue pipes before the point where we lock
+ * the pipe.
+ * Otherwise, lockdep would be unhappy if the caller already has another
+ * pipe locked.
+ * If we had to support locking a normal pipe and a notification pipe at
+ * the same time, we could set up lockdep annotations for that, but
+ * since we don't actually need that, it's simpler to just bail here.
+ */
+ if (pipe_has_watch_queue(pipe))
+ return -EXDEV;
+
/* Null write succeeds. */
if (unlikely(total_len == 0))
return 0;
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
if (!pipe->readers) {
send_sig(SIGPIPE, current, 0);
goto out;
}
-#ifdef CONFIG_WATCH_QUEUE
- if (pipe->watch_queue) {
- ret = -EXDEV;
- goto out;
- }
-#endif
-
/*
* If it wasn't empty we try to merge new data into
* the last buffer.
head = pipe->head;
if (!pipe_full(head, pipe->tail, pipe->max_usage)) {
unsigned int mask = pipe->ring_size - 1;
- struct pipe_buffer *buf = &pipe->bufs[head & mask];
+ struct pipe_buffer *buf;
struct page *page = pipe->tmp_page;
int copied;
* it, either the reader will consume it or it'll still
* be there for the next write.
*/
- spin_lock_irq(&pipe->rd_wait.lock);
-
- head = pipe->head;
- if (pipe_full(head, pipe->tail, pipe->max_usage)) {
- spin_unlock_irq(&pipe->rd_wait.lock);
- continue;
- }
-
pipe->head = head + 1;
- spin_unlock_irq(&pipe->rd_wait.lock);
/* Insert it into the buffer array */
buf = &pipe->bufs[head & mask];
break;
}
ret += copied;
- buf->offset = 0;
buf->len = copied;
if (!iov_iter_count(from))
continue;
/* Wait for buffer space to become available. */
- if (filp->f_flags & O_NONBLOCK) {
+ if ((filp->f_flags & O_NONBLOCK) ||
+ (iocb->ki_flags & IOCB_NOWAIT)) {
if (!ret)
ret = -EAGAIN;
break;
* after waiting we need to re-check whether the pipe
* become empty while we dropped the lock.
*/
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
if (was_empty)
wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe));
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
was_empty = pipe_empty(pipe->head, pipe->tail);
wake_next_writer = true;
}
out:
if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
wake_next_writer = false;
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
/*
* If we do do a wakeup event, we do a 'sync' wakeup, because we
switch (cmd) {
case FIONREAD:
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
count = 0;
head = pipe->head;
tail = pipe->tail;
count += pipe->bufs[tail & mask].len;
tail++;
}
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
return put_user(count, (int __user *)arg);
#ifdef CONFIG_WATCH_QUEUE
case IOC_WATCH_QUEUE_SET_SIZE: {
int ret;
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
ret = watch_queue_set_size(pipe, arg);
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
return ret;
}
{
struct pipe_inode_info *pipe = file->private_data;
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
if (file->f_mode & FMODE_READ)
pipe->readers--;
if (file->f_mode & FMODE_WRITE)
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
put_pipe_info(inode, pipe);
return 0;
struct pipe_inode_info *pipe = filp->private_data;
int retval = 0;
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
if (filp->f_mode & FMODE_READ)
retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
if ((filp->f_mode & FMODE_WRITE) && retval >= 0) {
/* this can happen only if on == T */
fasync_helper(-1, filp, 0, &pipe->fasync_readers);
}
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
return retval;
}
pipe->nr_accounted = pipe_bufs;
pipe->user = user;
mutex_init(&pipe->mutex);
+ lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL);
return pipe;
}
kfree(pipe);
}
-static struct vfsmount *pipe_mnt __read_mostly;
+static struct vfsmount *pipe_mnt __ro_after_init;
/*
* 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]",
+ return dynamic_dname(buffer, buflen, "pipe:[%lu]",
d_inode(dentry)->i_ino);
}
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);
+ simple_inode_init_ts(inode);
return inode;
audit_fd_pair(fdr, fdw);
fd[0] = fdr;
fd[1] = fdw;
+ /* pipe groks IOCB_NOWAIT */
+ files[0]->f_mode |= FMODE_NOWAIT;
+ files[1]->f_mode |= FMODE_NOWAIT;
return 0;
err_fdr:
filp->private_data = pipe;
/* OK, we have a pipe and it's pinned down */
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
/* We can only do regular read/write on fifos */
stream_open(inode, filp);
}
/* Ok! */
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
return 0;
err_rd:
goto err;
err:
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
put_pipe_info(inode, pipe);
return ret;
* Currently we rely on the pipe array holding a power-of-2 number
* of pages. Returns 0 on error.
*/
-unsigned int round_pipe_size(unsigned long size)
+unsigned int round_pipe_size(unsigned int size)
{
if (size > (1U << 31))
return 0;
pipe->tail = tail;
pipe->head = head;
+ if (!pipe_has_watch_queue(pipe)) {
+ pipe->max_usage = nr_slots;
+ pipe->nr_accounted = nr_slots;
+ }
+
spin_unlock_irq(&pipe->rd_wait.lock);
/* This might have made more room for writers */
* 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 arg)
+static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg)
{
unsigned long user_bufs;
unsigned int nr_slots, size;
long ret = 0;
-#ifdef CONFIG_WATCH_QUEUE
- if (pipe->watch_queue)
+ if (pipe_has_watch_queue(pipe))
return -EBUSY;
-#endif
size = round_pipe_size(arg);
nr_slots = size >> PAGE_SHIFT;
if (ret < 0)
goto out_revert_acct;
- pipe->max_usage = nr_slots;
- pipe->nr_accounted = nr_slots;
return pipe->max_usage * PAGE_SIZE;
out_revert_acct:
if (file->f_op != &pipefifo_fops || !pipe)
return NULL;
-#ifdef CONFIG_WATCH_QUEUE
- if (for_splice && pipe->watch_queue)
+ if (for_splice && pipe_has_watch_queue(pipe))
return NULL;
-#endif
return pipe;
}
-long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
+long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
{
struct pipe_inode_info *pipe;
long ret;
if (!pipe)
return -EBADF;
- __pipe_lock(pipe);
+ mutex_lock(&pipe->mutex);
switch (cmd) {
case F_SETPIPE_SZ:
break;
}
- __pipe_unlock(pipe);
+ mutex_unlock(&pipe->mutex);
return ret;
}
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
- { }
};
#endif