Merge tag 'for-6.15/io_uring-epoll-wait-20250325' of git://git.kernel.dk/linux

Pull io_uring epoll support from Jens Axboe:
 "This adds support for reading epoll events via io_uring.

  While this may seem counter-intuitive (and/or productive), the
  reasoning here is that quite a few existing epoll event loops can
  easily do a partial conversion to a completion based model, but are
  still stuck with one (or few) event types that remain readiness based.

  For that case, they then need to add the io_uring fd to the epoll
  context, and continue to rely on epoll_wait(2) for waiting on events.
  This misses out on the finer grained waiting that io_uring can do, to
  reduce context switches and wait for multiple events in one batch
  reliably.

  With adding support for reaping epoll events via io_uring, the whole
  legacy readiness based event types can still be reaped via epoll, with
  the overall waiting in the loop be driven by io_uring"

* tag 'for-6.15/io_uring-epoll-wait-20250325' of git://git.kernel.dk/linux:
  io_uring/epoll: add support for IORING_OP_EPOLL_WAIT
  io_uring/epoll: remove CONFIG_EPOLL guards

Author: torvalds

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)