KVM: Don't pre-reserve xarray entries when storing empty/NULL attributesgrafted

Skip the xarray reservation loop when clearing all memory attributes, as
storing NULL only erases the entry and never needs to allocate, so no
reservation (and no cleanup of a failed one) is required in that case.

Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: David Ballesteros <davimaba.v@proton.me>
Signed-off-by: Zeng Chi <zengchi@kylinos.cn>
Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>

1 files changed, 103 insertions, 0 deletions

diff --git a/io_uring/epoll.c b/io_uring/epoll.c
new file mode 100644
index 000000000..b9db8bde2
--- /dev/null
+++ b/io_uring/epoll.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/io_uring.h>
+#include <linux/eventpoll.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "epoll.h"
+
+struct io_epoll {
+	struct file			*file;
+	int				epfd;
+	int				op;
+	int				fd;
+	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);
+
+	if (sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+
+	epoll->epfd = READ_ONCE(sqe->fd);
+	epoll->op = READ_ONCE(sqe->len);
+	epoll->fd = READ_ONCE(sqe->off);
+
+	if (ep_op_has_event(epoll->op)) {
+		struct epoll_event __user *ev;
+
+		ev = u64_to_user_ptr(READ_ONCE(sqe->addr));
+		if (copy_from_user(&epoll->event, ev, sizeof(*ev)))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_epoll *ie = io_kiocb_to_cmd(req, struct io_epoll);
+	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+	struct epoll_key key;
+	int ret;
+
+	CLASS(fd, f)(ie->epfd);
+	if (fd_empty(f))
+		return -EBADF;
+
+	CLASS(fd, tf)(ie->fd);
+	if (fd_empty(tf))
+		return -EBADF;
+
+	key.file = fd_file(tf);
+	key.fd = ie->fd;
+	ret = do_epoll_ctl_file(fd_file(f), ie->op, &key, &ie->event, force_nonblock);
+	if (force_nonblock && ret == -EAGAIN)
+		return -EAGAIN;
+
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
+
+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_COMPLETE;
+}