Currently, in the window between the check for the accessed bit, and actually
dropping the spte, a vcpu can access the page through the spte and set the bit,
which will be ignored by the mmu.
Fix by using an exchange operation to atmoically fetch the spte and drop it.
Signed-off-by: Avi Kivity <avi@xxxxxxxxxx>
---
arch/x86/kvm/mmu.c | 26 +++++++++++++++++++++-----
1 files changed, 21 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f93948d..b565a14 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -290,6 +290,21 @@ static void __set_spte(u64 *sptep, u64 spte)
#endif
}
+static u64 __xchg_spte(u64 *sptep, u64 new_spte)
+{
+#ifdef CONFIG_X86_64
+ return xchg(sptep, new_spte);
+#else
+ u64 old_spte;
+
+ do {
+ old_spte = *sptep;
+ } while (cmpxchg64(sptep, old_spte, new_spte) != old_spte);
+
+ return old;
+#endif
+}
+
static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
struct kmem_cache *base_cache, int min)
{
@@ -661,16 +676,17 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
static void drop_spte(struct kvm *kvm, u64 *sptep, u64 new_spte)
{
pfn_t pfn;
+ u64 old_spte;
- if (!is_rmap_spte(*sptep))
+ old_spte = __xchg_spte(sptep, new_spte);
+ if (!is_rmap_spte(old_spte))
return;
- pfn = spte_to_pfn(*sptep);
- if (*sptep & shadow_accessed_mask)
+ pfn = spte_to_pfn(old_spte);
+ if (old_spte & shadow_accessed_mask)
kvm_set_pfn_accessed(pfn);
- if (is_writable_pte(*sptep))
+ if (is_writable_pte(old_spte))
kvm_set_pfn_dirty(pfn);
rmap_remove(kvm, sptep);
- __set_spte(sptep, new_spte);
}
static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
