KVM: SEV: Do cache maintenance on the source VM during intra-host migrationgrafted

Manually perform cache maintenance on the source VM during intra-host
migration to ensure no stale data is left in CPU caches after the VM is
destroyed.  Because the source VM is "converted" to a non-SEV VM, KVM's
memory reclaim flows won't trigger cache maintenance, e.g. when all guest
memory is reclaimed in response to detaching from the mmu_notifier.

Note, relying on the destination VM to do cache maintenance isn't an option
as KVM doesn't require identical guest memory configurations, i.e. the
source VM may have access to memory that the destination VM does not.
Enforcing equivalent memory configurations is infeasible, as it would
require a *deep* comparison of memslots, e.g. to verify that not only are
the memslot identical, but what the memslots point at is also identical.

Fixes: b56639318bb2 ("KVM: SEV: Add support for SEV intra host migration")
Cc: stable@vger.kernel.org
Reported-by: Stefan Teodorescu <fane@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20260923163721.1584779-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.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;
+}