There is no real urgency to free a stage-2 subtree that was pruned.
Nonetheless, KVM does the tear down in the stage-2 fault path while
holding the MMU lock.
Free removed stage-2 subtrees after an RCU grace period. To guarantee
all stage-2 table pages are freed before killing a VM, add an
rcu_barrier() to the flush path.
Signed-off-by: Oliver Upton <oliver.upton@xxxxxxxxx>
---
arch/arm64/include/asm/kvm_pgtable.h | 2 +-
arch/arm64/kvm/mmu.c | 14 +++++++++++++-
2 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index d1859e8550df..f35e7d4d73f1 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -65,7 +65,7 @@ typedef kvm_pte_t __rcu *kvm_pteref_t;
static inline kvm_pte_t *kvm_dereference_pteref(kvm_pteref_t pteref, bool shared)
{
- return rcu_dereference_check(pteref, shared);
+ return rcu_dereference_check(pteref, !shared);
}
static inline void kvm_pgtable_walk_begin(void)
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 175a0e9a04b6..a1a623c5b069 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -130,9 +130,21 @@ static void kvm_s2_free_pages_exact(void *virt, size_t size)
static struct kvm_pgtable_mm_ops kvm_s2_mm_ops;
+static void stage2_free_removed_table_rcu_cb(struct rcu_head *head)
+{
+ struct page *page = container_of(head, struct page, rcu_head);
+ void *pgtable = page_to_virt(page);
+ u32 level = page_private(page);
+
+ kvm_pgtable_stage2_free_removed(&kvm_s2_mm_ops, pgtable, level);
+}
+
static void stage2_free_removed_table(void *addr, u32 level)
{
- kvm_pgtable_stage2_free_removed(&kvm_s2_mm_ops, addr, level);
+ struct page *page = virt_to_page(addr);
+
+ set_page_private(page, (unsigned long)level);
+ call_rcu(&page->rcu_head, stage2_free_removed_table_rcu_cb);
}
static void kvm_host_get_page(void *addr)
--
2.38.1.273.g43a17bfeac-goog
