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, 117 insertions, 0 deletions

diff --git a/io_uring/tw.h b/io_uring/tw.h
new file mode 100644
index 000000000..3ade5ad57
--- /dev/null
+++ b/io_uring/tw.h
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_TW_H
+#define IOU_TW_H
+
+#include <linux/sched.h>
+#include <linux/percpu-refcount.h>
+#include <linux/io_uring_types.h>
+
+#include "mpscq.h"
+
+#define IO_LOCAL_TW_DEFAULT_MAX		20
+
+/*
+ * Terminate the request if either of these conditions are true:
+ *
+ * 1) It's being executed by the original task, but that task is marked
+ *    with PF_EXITING as it's exiting.
+ * 2) PF_KTHREAD is set, in which case the invoker of the task_work is
+ *    our fallback task_work.
+ * 3) The ring has been closed and is going away.
+ */
+static inline bool io_should_terminate_tw(struct io_ring_ctx *ctx)
+{
+	return (current->flags & (PF_EXITING | PF_KTHREAD)) || percpu_ref_is_dying(&ctx->refs);
+}
+
+void io_req_task_work_add_remote(struct io_kiocb *req, unsigned flags);
+void tctx_task_work(struct callback_head *cb);
+void io_tctx_fallback_work(struct work_struct *work);
+int io_run_local_work(struct io_ring_ctx *ctx, int min_events, int max_events);
+int io_run_task_work_sig(struct io_ring_ctx *ctx);
+
+__cold void io_cancel_local_task_work(struct io_ring_ctx *ctx);
+int io_run_local_work_locked(struct io_ring_ctx *ctx, int min_events);
+
+void io_req_local_work_add(struct io_kiocb *req, unsigned flags);
+void io_req_normal_work_add(struct io_kiocb *req);
+void tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
+
+static inline void __io_req_task_work_add(struct io_kiocb *req, unsigned flags)
+{
+	if (req->ctx->flags & IORING_SETUP_DEFER_TASKRUN)
+		io_req_local_work_add(req, flags);
+	else
+		io_req_normal_work_add(req);
+}
+
+static inline void io_req_task_work_add(struct io_kiocb *req)
+{
+	__io_req_task_work_add(req, 0);
+}
+
+static inline int io_run_task_work(void)
+{
+	bool ret = false;
+
+	/*
+	 * Always check-and-clear the task_work notification signal. With how
+	 * signaling works for task_work, we can find it set with nothing to
+	 * run. We need to clear it for that case, like get_signal() does.
+	 */
+	if (test_thread_flag(TIF_NOTIFY_SIGNAL))
+		clear_notify_signal();
+	/*
+	 * PF_IO_WORKER never returns to userspace, so check here if we have
+	 * notify work that needs processing.
+	 */
+	if (current->flags & PF_IO_WORKER) {
+		if (test_thread_flag(TIF_NOTIFY_RESUME)) {
+			__set_current_state(TASK_RUNNING);
+			resume_user_mode_work(NULL);
+		}
+		if (current->io_uring) {
+			unsigned int count = 0;
+
+			__set_current_state(TASK_RUNNING);
+			tctx_task_work_run(current->io_uring, UINT_MAX, &count);
+			if (count)
+				ret = true;
+		}
+	}
+	if (task_work_pending(current)) {
+		__set_current_state(TASK_RUNNING);
+		task_work_run();
+		ret = true;
+	}
+
+	return ret;
+}
+
+static inline bool io_local_work_pending(struct io_ring_ctx *ctx)
+{
+	return !mpscq_empty(&ctx->work_list);
+}
+
+static inline bool io_task_work_pending(struct io_ring_ctx *ctx)
+{
+	return task_work_pending(current) || io_local_work_pending(ctx);
+}
+
+static inline void io_tw_lock(struct io_ring_ctx *ctx, io_tw_token_t tw)
+{
+	lockdep_assert_held(&ctx->uring_lock);
+}
+
+static inline bool io_allowed_defer_tw_run(struct io_ring_ctx *ctx)
+{
+	return likely(ctx->submitter_task == current);
+}
+
+static inline bool io_allowed_run_tw(struct io_ring_ctx *ctx)
+{
+	return likely(!(ctx->flags & IORING_SETUP_DEFER_TASKRUN) ||
+		      ctx->submitter_task == current);
+}
+
+#endif