KVM: arm64: Fix memory leak on stage2 update of a valid PTE

When installing a new leaf PTE onto an invalid ptep, we need to
get_page(ptep) to account for the new mapping.

However, simply updating a valid PTE shouldn't result in any
additional refcounting, as there is new mapping. This otherwise
results in a page being forever wasted.

Address this by fixing-up the refcount in stage2_map_walker_try_leaf()
if the PTE was already valid, balancing out the later get_page()
in stage2_map_walk_leaf().

Signed-off-by: Yanan Wang <wangyanan55@huawei.com>
[maz: update commit message, add comment in the code]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20201201201034.116760-2-wangyanan55@huawei.com

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0271b4a..2beba1d 100644 (file)
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -470,6 +470,15 @@ static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
        if (!kvm_block_mapping_supported(addr, end, phys, level))
                return false;
 
+       /*
+        * If the PTE was already valid, drop the refcount on the table
+        * early, as it will be bumped-up again in stage2_map_walk_leaf().
+        * This ensures that the refcount stays constant across a valid to
+        * valid PTE update.
+        */
+       if (kvm_pte_valid(*ptep))
+               put_page(virt_to_page(ptep));
+
        if (kvm_set_valid_leaf_pte(ptep, phys, data->attr, level))
                goto out;