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, 123 insertions, 0 deletions

diff --git a/tools/testing/vma/shared.c b/tools/testing/vma/shared.c
new file mode 100644
index 000000000..4a39c9d50
--- /dev/null
+++ b/tools/testing/vma/shared.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "shared.h"
+
+
+bool fail_prealloc;
+unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
+
+const struct vm_operations_struct vma_dummy_vm_ops;
+struct anon_vma dummy_anon_vma;
+struct task_struct __current;
+
+struct vm_area_struct *alloc_vma(struct mm_struct *mm,
+		unsigned long start, unsigned long end,
+		pgoff_t pgoff, vma_flags_t vma_flags)
+{
+	struct vm_area_struct *vma = vm_area_alloc(mm);
+
+	if (vma == NULL)
+		return NULL;
+
+	vma->vm_start = start;
+	vma->vm_end = end;
+	vma_set_pgoff(vma, pgoff);
+	vma_set_anon_pgoff(vma, start >> PAGE_SHIFT);
+	vma->flags = vma_flags;
+	vma_assert_detached(vma);
+
+	return vma;
+}
+
+void detach_free_vma(struct vm_area_struct *vma)
+{
+	vma_mark_detached(vma);
+	vm_area_free(vma);
+}
+
+struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
+		unsigned long start, unsigned long end,
+		pgoff_t pgoff, vma_flags_t vma_flags)
+{
+	struct vm_area_struct *vma = alloc_vma(mm, start, end, pgoff, vma_flags);
+
+	if (vma == NULL)
+		return NULL;
+
+	if (attach_vma(mm, vma)) {
+		detach_free_vma(vma);
+		return NULL;
+	}
+
+	/*
+	 * Reset this counter which we use to track whether writes have
+	 * begun. Linking to the tree will have caused this to be incremented,
+	 * which means we will get a false positive otherwise.
+	 */
+	vma->vm_lock_seq = UINT_MAX;
+
+	return vma;
+}
+
+void reset_dummy_anon_vma(void)
+{
+	dummy_anon_vma.was_cloned = false;
+	dummy_anon_vma.was_unlinked = false;
+}
+
+int cleanup_mm(struct mm_struct *mm, struct vma_iterator *vmi)
+{
+	struct vm_area_struct *vma;
+	int count = 0;
+
+	fail_prealloc = false;
+	reset_dummy_anon_vma();
+
+	vma_iter_set(vmi, 0);
+	for_each_vma(*vmi, vma) {
+		detach_free_vma(vma);
+		count++;
+	}
+
+	mtree_destroy(&mm->mm_mt);
+	mm->map_count = 0;
+	return count;
+}
+
+bool vma_write_started(struct vm_area_struct *vma)
+{
+	int seq = vma->vm_lock_seq;
+
+	/* We reset after each check. */
+	vma->vm_lock_seq = UINT_MAX;
+
+	/* The vma_start_write() stub simply increments this value. */
+	return seq > -1;
+}
+
+void __vma_set_dummy_anon_vma(struct vm_area_struct *vma,
+		struct anon_vma_chain *avc, struct anon_vma *anon_vma)
+{
+	vma->anon_vma = anon_vma;
+	INIT_LIST_HEAD(&vma->anon_vma_chain);
+	list_add(&avc->same_vma, &vma->anon_vma_chain);
+	avc->anon_vma = vma->anon_vma;
+}
+
+void vma_set_dummy_anon_vma(struct vm_area_struct *vma,
+		struct anon_vma_chain *avc)
+{
+	__vma_set_dummy_anon_vma(vma, avc, &dummy_anon_vma);
+}
+
+struct task_struct *get_current(void)
+{
+	return &__current;
+}
+
+unsigned long rlimit(unsigned int limit)
+{
+	return (unsigned long)-1;
+}