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, 77 insertions, 0 deletions

diff --git a/samples/seccomp/dropper.c b/samples/seccomp/dropper.c
new file mode 100644
index 000000000..4bca4b70f
--- /dev/null
+++ b/samples/seccomp/dropper.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Naive system call dropper built on seccomp_filter.
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_SET_SECCOMP, 2, ...).
+ *
+ * When run, returns the specified errno for the specified
+ * system call number against the given architecture.
+ *
+ */
+
+#include <errno.h>
+#include <linux/audit.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <linux/unistd.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+static int install_filter(int arch, int nr, int error)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
+			 (offsetof(struct seccomp_data, arch))),
+		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, arch, 0, 3),
+		BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
+			 (offsetof(struct seccomp_data, nr))),
+		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1),
+		BPF_STMT(BPF_RET+BPF_K,
+			 SECCOMP_RET_ERRNO|(error & SECCOMP_RET_DATA)),
+		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+		.filter = filter,
+	};
+	if (error == -1) {
+		struct sock_filter kill = BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL);
+		filter[4] = kill;
+	}
+	if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+		perror("prctl(NO_NEW_PRIVS)");
+		return 1;
+	}
+	if (prctl(PR_SET_SECCOMP, 2, &prog)) {
+		perror("prctl(PR_SET_SECCOMP)");
+		return 1;
+	}
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	if (argc < 5) {
+		fprintf(stderr, "Usage:\n"
+			"dropper <arch> <syscall_nr> <errno> <prog> [<args>]\n"
+			"Hint:	AUDIT_ARCH_I386: 0x%X\n"
+			"	AUDIT_ARCH_X86_64: 0x%X\n"
+			"	errno == -1 means SECCOMP_RET_KILL\n"
+			"\n", AUDIT_ARCH_I386, AUDIT_ARCH_X86_64);
+		return 1;
+	}
+	if (install_filter(strtol(argv[1], NULL, 0), strtol(argv[2], NULL, 0),
+			   strtol(argv[3], NULL, 0)))
+		return 1;
+	execv(argv[4], &argv[4]);
+	printf("Failed to execv\n");
+	return 255;
+}