*/
was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage);
for (;;) {
- unsigned int head = pipe->head;
+ /* Read ->head with a barrier vs post_one_notification() */
+ unsigned int head = smp_load_acquire(&pipe->head);
unsigned int tail = pipe->tail;
unsigned int mask = pipe->ring_size - 1;
* _very_ unlikely case that the pipe was full, but we got
* no data.
*/
- if (unlikely(was_full)) {
+ if (unlikely(was_full))
wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM);
- kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
- }
+ kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
/*
* But because we didn't read anything, at this point we can
wake_next_reader = false;
__pipe_unlock(pipe);
- if (was_full) {
+ if (was_full)
wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM);
- kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
- }
if (wake_next_reader)
wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
+ kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
if (ret > 0)
file_accessed(filp);
return ret;
#endif
/*
- * Epoll nonsensically wants a wakeup whether the pipe
- * was already empty or not.
- *
* If it wasn't empty we try to merge new data into
* the last buffer.
*
* spanning multiple pages.
*/
head = pipe->head;
- was_empty = true;
+ was_empty = pipe_empty(head, pipe->tail);
chars = total_len & (PAGE_SIZE-1);
- if (chars && !pipe_empty(head, pipe->tail)) {
+ if (chars && !was_empty) {
unsigned int mask = pipe->ring_size - 1;
struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask];
int offset = buf->offset + buf->len;
* become empty while we dropped the lock.
*/
__pipe_unlock(pipe);
- if (was_empty) {
+ if (was_empty)
wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
- kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
- }
+ kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe));
__pipe_lock(pipe);
was_empty = pipe_empty(pipe->head, pipe->tail);
* This is particularly important for small writes, because of
* how (for example) the GNU make jobserver uses small writes to
* wake up pending jobs
+ *
+ * Epoll nonsensically wants a wakeup whether the pipe
+ * was already empty or not.
*/
- if (was_empty) {
+ if (was_empty || pipe->poll_usage)
wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
- kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
- }
+ kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
if (wake_next_writer)
wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM);
if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) {
struct pipe_inode_info *pipe = filp->private_data;
unsigned int head, tail;
+ /* Epoll has some historical nasty semantics, this enables them */
+ WRITE_ONCE(pipe->poll_usage, true);
+
/*
* Reading pipe state only -- no need for acquiring the semaphore.
*
int i;
#ifdef CONFIG_WATCH_QUEUE
- if (pipe->watch_queue) {
+ if (pipe->watch_queue)
watch_queue_clear(pipe->watch_queue);
- put_watch_queue(pipe->watch_queue);
- }
#endif
(void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0);
if (buf->ops)
pipe_buf_release(pipe, buf);
}
+#ifdef CONFIG_WATCH_QUEUE
+ if (pipe->watch_queue)
+ put_watch_queue(pipe->watch_queue);
+#endif
if (pipe->tmp_page)
__free_page(pipe->tmp_page);
kfree(pipe->bufs);
/*
* Resize the pipe ring to a number of slots.
+ *
+ * Note the pipe can be reduced in capacity, but only if the current
+ * occupancy doesn't exceed nr_slots; if it does, EBUSY will be
+ * returned instead.
*/
int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots)
{
struct pipe_buffer *bufs;
unsigned int head, tail, mask, n;
- /*
- * We can shrink the pipe, if arg is greater than the ring occupancy.
- * 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.
- */
- mask = pipe->ring_size - 1;
- head = pipe->head;
- tail = pipe->tail;
- n = pipe_occupancy(pipe->head, pipe->tail);
- if (nr_slots < n)
- return -EBUSY;
-
bufs = kcalloc(nr_slots, sizeof(*bufs),
GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (unlikely(!bufs))
return -ENOMEM;
+ spin_lock_irq(&pipe->rd_wait.lock);
+ mask = pipe->ring_size - 1;
+ head = pipe->head;
+ tail = pipe->tail;
+
+ n = pipe_occupancy(head, tail);
+ if (nr_slots < n) {
+ spin_unlock_irq(&pipe->rd_wait.lock);
+ kfree(bufs);
+ return -EBUSY;
+ }
+
/*
* The pipe array wraps around, so just start the new one at zero
* and adjust the indices.
pipe->tail = tail;
pipe->head = head;
+ spin_unlock_irq(&pipe->rd_wait.lock);
+
/* This might have made more room for writers */
wake_up_interruptible(&pipe->wr_wait);
return 0;