Merge branch 'vfs-6.15.eventpoll' of https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs into for-6.15/io_uring-epoll-wait

Merge epoll changes from the VFS tree, which the io_uring changes depend
on.

* 'vfs-6.15.eventpoll' of https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  eventpoll: add epoll_sendevents() helper
  eventpoll: abstract out ep_try_send_events() helper
  eventpoll: abstract out parameter sanity checking

Author: axboe

fs/eventpoll.c

@@ -1980,6 +1980,22 @@ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry,
 	return ret;
 }
 
+static int ep_try_send_events(struct eventpoll *ep,
+			      struct epoll_event __user *events, int maxevents)
+{
+	int res;
+
+	/*
+	 * Try to transfer events to user space. In case we get 0 events and
+	 * there's still timeout left over, we go trying again in search of
+	 * more luck.
+	 */
+	res = ep_send_events(ep, events, maxevents);
+	if (res > 0)
+		ep_suspend_napi_irqs(ep);
+	return res;
+}
+
 /**
  * ep_poll - Retrieves ready events, and delivers them to the caller-supplied
  *           event buffer.
@@ -2031,17 +2047,9 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 
 	while (1) {
 		if (eavail) {
-			/*
-			 * Try to transfer events to user space. In case we get
-			 * 0 events and there's still timeout left over, we go
-			 * trying again in search of more luck.
-			 */
-			res = ep_send_events(ep, events, maxevents);
-			if (res) {
-				if (res > 0)
-					ep_suspend_napi_irqs(ep);
+			res = ep_try_send_events(ep, events, maxevents);
+			if (res)
 				return res;
-			}
 		}
 
 		if (timed_out)
@@ -2445,6 +2453,47 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	return do_epoll_ctl(epfd, op, fd, &epds, false);
 }
 
+static int ep_check_params(struct file *file, struct epoll_event __user *evs,
+			   int maxevents)
+{
+	/* The maximum number of event must be greater than zero */
+	if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
+		return -EINVAL;
+
+	/* Verify that the area passed by the user is writeable */
+	if (!access_ok(evs, maxevents * sizeof(struct epoll_event)))
+		return -EFAULT;
+
+	/*
+	 * We have to check that the file structure underneath the fd
+	 * the user passed to us _is_ an eventpoll file.
+	 */
+	if (!is_file_epoll(file))
+		return -EINVAL;
+
+	return 0;
+}
+
+int epoll_sendevents(struct file *file, struct epoll_event __user *events,
+		     int maxevents)
+{
+	struct eventpoll *ep;
+	int ret;
+
+	ret = ep_check_params(file, events, maxevents);
+	if (unlikely(ret))
+		return ret;
+
+	ep = file->private_data;
+	/*
+	 * Racy call, but that's ok - it should get retried based on
+	 * poll readiness anyway.
+	 */
+	if (ep_events_available(ep))
+		return ep_try_send_events(ep, events, maxevents);
+	return 0;
+}
+
 /*
  * Implement the event wait interface for the eventpoll file. It is the kernel
  * part of the user space epoll_wait(2).
@@ -2453,26 +2502,16 @@ static int do_epoll_wait(int epfd, struct epoll_event __user *events,
 			 int maxevents, struct timespec64 *to)
 {
 	struct eventpoll *ep;
-
-	/* The maximum number of event must be greater than zero */
-	if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
-		return -EINVAL;
-
-	/* Verify that the area passed by the user is writeable */
-	if (!access_ok(events, maxevents * sizeof(struct epoll_event)))
-		return -EFAULT;
+	int ret;
 
 	/* Get the "struct file *" for the eventpoll file */
 	CLASS(fd, f)(epfd);
 	if (fd_empty(f))
 		return -EBADF;
 
-	/*
-	 * We have to check that the file structure underneath the fd
-	 * the user passed to us _is_ an eventpoll file.
-	 */
-	if (!is_file_epoll(fd_file(f)))
-		return -EINVAL;
+	ret = ep_check_params(fd_file(f), events, maxevents);
+	if (unlikely(ret))
+		return ret;
 
 	/*
 	 * At this point it is safe to assume that the "private_data" contains

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);
 
+/* Copy ready events to userspace */
+int epoll_sendevents(struct file *file, struct epoll_event __user *events,
+		     int maxevents);
+
 /*
  * 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