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, 90 insertions, 0 deletions

diff --git a/io_uring/nop.c b/io_uring/nop.c
new file mode 100644
index 000000000..60ab19604
--- /dev/null
+++ b/io_uring/nop.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "rsrc.h"
+#include "nop.h"
+
+struct io_nop {
+	struct file     *file;
+	int             result;
+	int		fd;
+	unsigned int	flags;
+	__u64		extra1;
+	__u64		extra2;
+};
+
+#define NOP_FLAGS	(IORING_NOP_INJECT_RESULT | IORING_NOP_FIXED_FILE | \
+			 IORING_NOP_FIXED_BUFFER | IORING_NOP_FILE | \
+			 IORING_NOP_TW | IORING_NOP_CQE32)
+
+int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop);
+
+	nop->flags = READ_ONCE(sqe->nop_flags);
+	if (nop->flags & ~NOP_FLAGS)
+		return -EINVAL;
+
+	if (nop->flags & IORING_NOP_INJECT_RESULT)
+		nop->result = READ_ONCE(sqe->len);
+	else
+		nop->result = 0;
+	if (nop->flags & IORING_NOP_FILE)
+		nop->fd = READ_ONCE(sqe->fd);
+	else
+		nop->fd = -1;
+	if (nop->flags & IORING_NOP_FIXED_FILE)
+		req->flags |= REQ_F_FIXED_FILE;
+	if (nop->flags & IORING_NOP_FIXED_BUFFER)
+		req->buf_index = READ_ONCE(sqe->buf_index);
+	if (nop->flags & IORING_NOP_CQE32) {
+		struct io_ring_ctx *ctx = req->ctx;
+
+		if (!(ctx->flags & (IORING_SETUP_CQE32|IORING_SETUP_CQE_MIXED)))
+			return -EINVAL;
+		nop->extra1 = READ_ONCE(sqe->off);
+		nop->extra2 = READ_ONCE(sqe->addr);
+	}
+	return 0;
+}
+
+int io_nop(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_nop *nop = io_kiocb_to_cmd(req, struct io_nop);
+	int ret = nop->result;
+
+	if (nop->flags & IORING_NOP_FILE) {
+		if (req->flags & REQ_F_FIXED_FILE)
+			req->file = io_file_get_fixed(req, nop->fd, issue_flags);
+		else
+			req->file = io_file_get_normal(req, nop->fd);
+		if (!req->file) {
+			ret = -EBADF;
+			goto done;
+		}
+	}
+	if (nop->flags & IORING_NOP_FIXED_BUFFER) {
+		if (!io_find_buf_node(req, issue_flags))
+			ret = -EFAULT;
+	}
+done:
+	if (ret < 0)
+		req_set_fail(req);
+	if (nop->flags & IORING_NOP_CQE32)
+		io_req_set_res32(req, ret, 0, nop->extra1, nop->extra2);
+	else
+		io_req_set_res(req, ret, 0);
+	if (nop->flags & IORING_NOP_TW) {
+		req->io_task_work.func = io_req_task_complete;
+		io_req_task_work_add(req);
+		return IOU_ISSUE_SKIP_COMPLETE;
+	}
+	return IOU_COMPLETE;
+}