[PATCH 1/1] pipe: only enable the extra wake_up(rd_wait) when epoll is actually used

[Oleg Nesterov]

pipe_poll() unconditionally sets poll_usage on the first call, forcing
anon_pipe_write() to wake up readers on every write even if the pipe was
not empty. But this is only needed for epoll's "nasty semantics"; poll()
and select() users pay for it for no reason.

Rename it to epoll_usage, and only set it when the caller is actually
using epoll on the read side of the pipe.

Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
---
 fs/pipe.c                 | 23 +++++++++++++++++++----
 include/linux/pipe_fs_i.h |  6 ++++--
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/fs/pipe.c b/fs/pipe.c
index 32140cb00d7e..b45b4b8d0b0b 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -357,6 +357,23 @@ static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe,
 	return tail;
 }
 
+static void pipe_set_epoll_usage(struct file *filp, struct pipe_inode_info *pipe)
+{
+#ifdef CONFIG_EPOLL
+	if ((filp->f_mode & FMODE_READ) && filp->f_ep &&
+	    unlikely(!READ_ONCE(pipe->epoll_usage)))
+		WRITE_ONCE(pipe->epoll_usage, true);
+#endif
+}
+
+static bool pipe_get_epoll_usage(struct pipe_inode_info *pipe)
+{
+#ifdef CONFIG_EPOLL
+	return pipe->epoll_usage;
+#endif
+	return false;
+}
+
 static ssize_t
 anon_pipe_read(struct kiocb *iocb, struct iov_iter *to)
 {
@@ -689,7 +706,7 @@ anon_pipe_write(struct kiocb *iocb, struct iov_iter *from)
 	 * Epoll nonsensically wants a wakeup whether the pipe
 	 * was already empty or not.
 	 */
-	if (was_empty || pipe->poll_usage)
+	if (was_empty || pipe_get_epoll_usage(pipe))
 		wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
 	kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 	if (wake_next_writer)
@@ -761,9 +778,7 @@ pipe_poll(struct file *filp, poll_table *wait)
 	union pipe_index idx;
 
 	/* Epoll has some historical nasty semantics, this enables them */
-	if (unlikely(!READ_ONCE(pipe->poll_usage)))
-		WRITE_ONCE(pipe->poll_usage, true);
-
+	pipe_set_epoll_usage(filp, pipe);
 	/*
 	 * Reading pipe state only -- no need for acquiring the semaphore.
 	 *
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 7f6a92ac9704..d06da9bad3a8 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -74,7 +74,7 @@ union pipe_index {
  *	@files: number of struct file referring this pipe (protected by ->i_lock)
  *	@r_counter: reader counter
  *	@w_counter: writer counter
- *	@poll_usage: is this pipe used for epoll, which has crazy wakeups?
+ *	@epoll_usage: is this pipe used for epoll, which has crazy wakeups?
  *	@fasync_readers: reader side fasync
  *	@fasync_writers: writer side fasync
  *	@bufs: the circular array of pipe buffers
@@ -95,7 +95,9 @@ struct pipe_inode_info {
 	unsigned int files;
 	unsigned int r_counter;
 	unsigned int w_counter;
-	bool poll_usage;
+#ifdef CONFIG_EPOLL
+	bool epoll_usage;
+#endif
 #ifdef CONFIG_WATCH_QUEUE
 	bool note_loss;
 #endif
-- 
2.52.0