[PATCH 3/7] eventpoll: add epoll_queue() interface

[Jens Axboe <axboe@kernel.dk>]

Basic interface that takes a wait_queue_entry rather than post one on
the stack, which can be a persistent callback for when new events
arrive.

Works like regular epoll_wait(), except it doesn't block. If events are
available, they are returned. If none are available, the passed in
wait_queue_entry is added to the callback list. The wait_queue_entry
must be previously initialized, and the callback provided will be called
when events are added to the epoll context.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/eventpoll.c            | 39 +++++++++++++++++++++++++++++++++++++++
 include/linux/eventpoll.h |  4 ++++
 2 files changed, 43 insertions(+)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 14466765b85d..d3ac466ad415 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1996,6 +1996,33 @@ static int ep_try_send_events(struct eventpoll *ep,
 	return res;
 }
 
+static int ep_poll_queue(struct eventpoll *ep,
+			 struct epoll_event __user *events, int maxevents,
+			 struct wait_queue_entry *wait)
+{
+	int res = 0, eavail;
+
+	/* See ep_poll() for commentary */
+	eavail = ep_events_available(ep);
+	while (1) {
+		if (eavail) {
+			res = ep_try_send_events(ep, events, maxevents);
+			if (res)
+				return res;
+		}
+		if (!list_empty_careful(&wait->entry))
+			break;
+		write_lock_irq(&ep->lock);
+		eavail = ep_events_available(ep);
+		if (!eavail)
+			__add_wait_queue_exclusive(&ep->wq, wait);
+		write_unlock_irq(&ep->lock);
+		if (!eavail)
+			break;
+	}
+	return -EIOCBQUEUED;
+}
+
 /**
  * ep_poll - Retrieves ready events, and delivers them to the caller-supplied
  *           event buffer.
@@ -2474,6 +2501,18 @@ static int ep_check_params(struct file *file, struct epoll_event __user *evs,
 	return 0;
 }
 
+int epoll_queue(struct file *file, struct epoll_event __user *events,
+		int maxevents, struct wait_queue_entry *wait)
+{
+	int ret;
+
+	ret = ep_check_params(file, events, maxevents);
+	if (unlikely(ret))
+		return ret;
+
+	return ep_poll_queue(file->private_data, events, maxevents, wait);
+}
+
 /*
  * Implement the event wait interface for the eventpoll file. It is the kernel
  * part of the user space epoll_wait(2).
diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index 0c0d00fcd131..8de16374b8fe 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -25,6 +25,10 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long t
 /* Used to release the epoll bits inside the "struct file" */
 void eventpoll_release_file(struct file *file);
 
+/* Use to reap events, and/or queue for a callback on new events */
+int epoll_queue(struct file *file, struct epoll_event __user *events,
+		int maxevents, struct wait_queue_entry *wait);
+
 /*
  * This is called from inside fs/file_table.c:__fput() to unlink files
  * from the eventpoll interface. We need to have this facility to cleanup
-- 
2.47.2