Hi Oliver,
On Tue, Aug 30, 2022 at 07:41:27PM +0000, Oliver Upton wrote:
> 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/kvm/mmu.c | 35 ++++++++++++++++++++++++++++++++++-
> 1 file changed, 34 insertions(+), 1 deletion(-)
>
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index 91521f4aab97..265951c05879 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -97,6 +97,38 @@ static void *stage2_memcache_zalloc_page(void *arg)
> return kvm_mmu_memory_cache_alloc(mc);
> }
>
> +#define STAGE2_PAGE_PRIVATE_LEVEL_MASK GENMASK_ULL(2, 0)
> +
> +static inline unsigned long stage2_page_private(u32 level, void *arg)
> +{
> + unsigned long pvt = (unsigned long)arg;
> +
> + BUILD_BUG_ON(KVM_PGTABLE_MAX_LEVELS > STAGE2_PAGE_PRIVATE_LEVEL_MASK);
> + WARN_ON_ONCE(pvt & STAGE2_PAGE_PRIVATE_LEVEL_MASK);
If the pgt pointer (arg) is not aligned for some reason, I think it
might be better to BUG_ON(). Alternatively, why not trying to pass a new
struct (with level and arg) that's freed by the rcu callback.
> +
> + return pvt | level;
> +}
> +
> +static void stage2_free_removed_table_rcu_cb(struct rcu_head *head)
> +{
> + struct page *page = container_of(head, struct page, rcu_head);
> + unsigned long pvt = page_private(page);
> + void *arg = (void *)(pvt & ~STAGE2_PAGE_PRIVATE_LEVEL_MASK);
> + u32 level = (u32)(pvt & STAGE2_PAGE_PRIVATE_LEVEL_MASK);
> + void *pgtable = page_to_virt(page);
> +
> + kvm_pgtable_stage2_free_removed(pgtable, level, arg);
> +}
> +
> +static void stage2_free_removed_table(void *pgtable, u32 level, void *arg)
> +{
> + unsigned long pvt = stage2_page_private(level, arg);
> + struct page *page = virt_to_page(pgtable);
> +
> + set_page_private(page, (unsigned long)pvt);
> + call_rcu(&page->rcu_head, stage2_free_removed_table_rcu_cb);
> +}
> +
> static void *kvm_host_zalloc_pages_exact(size_t size)
> {
> return alloc_pages_exact(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
> @@ -627,7 +659,7 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
> .zalloc_page = stage2_memcache_zalloc_page,
> .zalloc_pages_exact = kvm_host_zalloc_pages_exact,
> .free_pages_exact = free_pages_exact,
> - .free_removed_table = kvm_pgtable_stage2_free_removed,
> + .free_removed_table = stage2_free_removed_table,
> .get_page = kvm_host_get_page,
> .put_page = kvm_host_put_page,
> .page_count = kvm_host_page_count,
> @@ -770,6 +802,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
> if (pgt) {
> kvm_pgtable_stage2_destroy(pgt);
> kfree(pgt);
> + rcu_barrier();
> }
> }
>
> --
> 2.37.2.672.g94769d06f0-goog
>
