Merge branch 'for-6.15/io_uring-epoll-wait' into for-6.15/io_uring-reg-vec

* for-6.15/io_uring-epoll-wait:
  io_uring/epoll: add support for IORING_OP_EPOLL_WAIT
  io_uring/epoll: remove CONFIG_EPOLL guards
  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

include/uapi/linux/io_uring.h

@@ -280,6 +280,7 @@ enum io_uring_op {
 	IORING_OP_BIND,
 	IORING_OP_LISTEN,
 	IORING_OP_RECV_ZC,
+	IORING_OP_EPOLL_WAIT,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,

io_uring/Makefile

@@ -11,10 +11,11 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o opdef.o kbuf.o rsrc.o notif.o \
 					eventfd.o uring_cmd.o openclose.o \
 					sqpoll.o xattr.o nop.o fs.o splice.o \
 					sync.o msg_ring.o advise.o openclose.o \
-					epoll.o statx.o timeout.o fdinfo.o \
-					cancel.o waitid.o register.o \
-					truncate.o memmap.o alloc_cache.o
+					statx.o timeout.o fdinfo.o cancel.o \
+					waitid.o register.o truncate.o \
+					memmap.o alloc_cache.o
 obj-$(CONFIG_IO_URING_ZCRX)	+= zcrx.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FUTEX)		+= futex.o
-obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
+obj-$(CONFIG_EPOLL)		+= epoll.o
+obj-$(CONFIG_NET_RX_BUSY_POLL)	+= napi.o

io_uring/epoll.c

@@ -12,7 +12,6 @@
 #include "io_uring.h"
 #include "epoll.h"
 
-#if defined(CONFIG_EPOLL)
 struct io_epoll {
 	struct file			*file;
 	int				epfd;
@@ -21,6 +20,12 @@ struct io_epoll {
 	struct epoll_event		event;
 };
 
+struct io_epoll_wait {
+	struct file			*file;
+	int				maxevents;
+	struct epoll_event __user	*events;
+};
+
 int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_epoll *epoll = io_kiocb_to_cmd(req, struct io_epoll);
@@ -58,4 +63,30 @@ int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags)
 	io_req_set_res(req, ret, 0);
 	return IOU_OK;
 }
-#endif
+
+int io_epoll_wait_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+
+	if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+
+	iew->maxevents = READ_ONCE(sqe->len);
+	iew->events = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	return 0;
+}
+
+int io_epoll_wait(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_epoll_wait *iew = io_kiocb_to_cmd(req, struct io_epoll_wait);
+	int ret;
+
+	ret = epoll_sendevents(req->file, iew->events, iew->maxevents);
+	if (ret == 0)
+		return -EAGAIN;
+	if (ret < 0)
+		req_set_fail(req);
+
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}

io_uring/epoll.h

@@ -3,4 +3,6 @@
 #if defined(CONFIG_EPOLL)
 int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
 int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags);
+int io_epoll_wait_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_epoll_wait(struct io_kiocb *req, unsigned int issue_flags);
 #endif

io_uring/opdef.c

@@ -527,6 +527,17 @@ const struct io_issue_def io_issue_defs[] = {
 		.issue			= io_recvzc,
 #else
 		.prep			= io_eopnotsupp_prep,
+#endif
+	},
+	[IORING_OP_EPOLL_WAIT] = {
+		.needs_file		= 1,
+		.audit_skip		= 1,
+		.pollin			= 1,
+#if defined(CONFIG_EPOLL)
+		.prep			= io_epoll_wait_prep,
+		.issue			= io_epoll_wait,
+#else
+		.prep			= io_eopnotsupp_prep,
 #endif
 	},
 };
@@ -761,6 +772,9 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_RECV_ZC] = {
 		.name			= "RECV_ZC",
 	},
+	[IORING_OP_EPOLL_WAIT] = {
+		.name			= "EPOLL_WAIT",
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)