@@ -1454,6 +1454,7 @@ struct kvm_arch {
* tdp_mmu_page set.
*
* For reads, this list is protected by:
+ * RCU alone or
* the MMU lock in read mode + RCU or
* the MMU lock in write mode
*
@@ -23,6 +23,7 @@ config KVM
depends on X86_LOCAL_APIC
select KVM_COMMON
select KVM_GENERIC_MMU_NOTIFIER
+ select KVM_MMU_NOTIFIER_YOUNG_LOCKLESS
select HAVE_KVM_IRQCHIP
select HAVE_KVM_PFNCACHE
select HAVE_KVM_DIRTY_RING_TSO
@@ -1649,8 +1649,11 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
bool young = false;
- if (kvm_memslots_have_rmaps(kvm))
+ if (kvm_memslots_have_rmaps(kvm)) {
+ write_lock(&kvm->mmu_lock);
young = kvm_rmap_age_gfn_range(kvm, range, false);
+ write_unlock(&kvm->mmu_lock);
+ }
if (tdp_mmu_enabled)
young |= kvm_tdp_mmu_age_gfn_range(kvm, range);
@@ -1662,8 +1665,11 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
bool young = false;
- if (kvm_memslots_have_rmaps(kvm))
+ if (kvm_memslots_have_rmaps(kvm)) {
+ write_lock(&kvm->mmu_lock);
young = kvm_rmap_age_gfn_range(kvm, range, true);
+ write_unlock(&kvm->mmu_lock);
+ }
if (tdp_mmu_enabled)
young |= kvm_tdp_mmu_test_age_gfn(kvm, range);
@@ -39,10 +39,11 @@ static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
}
/*
- * SPTEs must be modified atomically if they are shadow-present, leaf
- * SPTEs, and have volatile bits, i.e. has bits that can be set outside
- * of mmu_lock. The Writable bit can be set by KVM's fast page fault
- * handler, and Accessed and Dirty bits can be set by the CPU.
+ * SPTEs must be modified atomically if they have bits that can be set outside
+ * of the mmu_lock. This can happen for any shadow-present leaf SPTEs, as the
+ * Writable bit can be set by KVM's fast page fault handler, the Accessed and
+ * Dirty bits can be set by the CPU, and the Accessed and R/X bits can be
+ * cleared by age_gfn_range.
*
* Note, non-leaf SPTEs do have Accessed bits and those bits are
* technically volatile, but KVM doesn't consume the Accessed bit of
@@ -53,8 +54,7 @@ static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte)
static inline bool kvm_tdp_mmu_spte_need_atomic_write(u64 old_spte, int level)
{
return is_shadow_present_pte(old_spte) &&
- is_last_spte(old_spte, level) &&
- spte_has_volatile_bits(old_spte);
+ is_last_spte(old_spte, level);
}
static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte,
@@ -70,8 +70,6 @@ static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte,
static inline u64 tdp_mmu_clear_spte_bits(tdp_ptep_t sptep, u64 old_spte,
u64 mask, int level)
{
- atomic64_t *sptep_atomic;
-
if (kvm_tdp_mmu_spte_need_atomic_write(old_spte, level))
return tdp_mmu_clear_spte_bits_atomic(sptep, mask);
@@ -178,6 +178,15 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
((_only_valid) && (_root)->role.invalid))) { \
} else
+/*
+ * Iterate over all TDP MMU roots in an RCU read-side critical section.
+ */
+#define for_each_valid_tdp_mmu_root_rcu(_kvm, _root, _as_id) \
+ list_for_each_entry_rcu(_root, &_kvm->arch.tdp_mmu_roots, link) \
+ if ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) || \
+ (_root)->role.invalid) { \
+ } else
+
#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \
__for_each_tdp_mmu_root(_kvm, _root, _as_id, false)
@@ -1222,6 +1231,26 @@ static __always_inline bool kvm_tdp_mmu_handle_gfn(struct kvm *kvm,
return ret;
}
+static __always_inline bool kvm_tdp_mmu_handle_gfn_lockless(struct kvm *kvm,
+ struct kvm_gfn_range *range,
+ tdp_handler_t handler)
+{
+ struct kvm_mmu_page *root;
+ struct tdp_iter iter;
+ bool ret = false;
+
+ rcu_read_lock();
+
+ for_each_valid_tdp_mmu_root_rcu(kvm, root, range->slot->as_id) {
+ tdp_root_for_each_leaf_pte(iter, root, range->start, range->end)
+ ret |= handler(kvm, &iter, range);
+ }
+
+ rcu_read_unlock();
+
+ return ret;
+}
+
/*
* Mark the SPTEs range of GFNs [start, end) unaccessed and return non-zero
* if any of the GFNs in the range have been accessed.
@@ -1240,23 +1269,21 @@ static bool age_gfn_range(struct kvm *kvm, struct tdp_iter *iter,
return false;
if (spte_ad_enabled(iter->old_spte)) {
- iter->old_spte = tdp_mmu_clear_spte_bits(iter->sptep,
- iter->old_spte,
- shadow_accessed_mask,
- iter->level);
+ iter->old_spte = tdp_mmu_clear_spte_bits_atomic(iter->sptep,
+ shadow_accessed_mask);
new_spte = iter->old_spte & ~shadow_accessed_mask;
} else {
- /*
- * Capture the dirty status of the page, so that it doesn't get
- * lost when the SPTE is marked for access tracking.
- */
+ new_spte = mark_spte_for_access_track(iter->old_spte);
+ if (__tdp_mmu_set_spte_atomic(iter, new_spte))
+ /*
+ * The cmpxchg failed. Even if we had cleared the
+ * Accessed bit, it likely would have been set again,
+ * so this spte is probably young.
+ */
+ return true;
+
if (is_writable_pte(iter->old_spte))
kvm_set_pfn_dirty(spte_to_pfn(iter->old_spte));
-
- new_spte = mark_spte_for_access_track(iter->old_spte);
- iter->old_spte = kvm_tdp_mmu_write_spte(iter->sptep,
- iter->old_spte, new_spte,
- iter->level);
}
trace_kvm_tdp_mmu_spte_changed(iter->as_id, iter->gfn, iter->level,
@@ -1266,7 +1293,7 @@ static bool age_gfn_range(struct kvm *kvm, struct tdp_iter *iter,
bool kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
- return kvm_tdp_mmu_handle_gfn(kvm, range, age_gfn_range);
+ return kvm_tdp_mmu_handle_gfn_lockless(kvm, range, age_gfn_range);
}
static bool test_age_gfn(struct kvm *kvm, struct tdp_iter *iter,
@@ -1277,7 +1304,7 @@ static bool test_age_gfn(struct kvm *kvm, struct tdp_iter *iter,
bool kvm_tdp_mmu_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
- return kvm_tdp_mmu_handle_gfn(kvm, range, test_age_gfn);
+ return kvm_tdp_mmu_handle_gfn_lockless(kvm, range, test_age_gfn);
}
/*
Walk the TDP MMU in an RCU read-side critical section without holding mmu_lock when harvesting and potentially updating age information on sptes. This requires a way to do RCU-safe walking of the tdp_mmu_roots; do this with a new macro. The PTE modifications are now done atomically, and kvm_tdp_mmu_spte_need_atomic_write() has been updated to account for the fact that kvm_age_gfn can now lockless update the accessed bit and the W/R/X bits). If the cmpxchg for marking the spte for access tracking fails, leave it as is and treat it as if it were young, as if the spte is being actively modified, it is most likely young. Harvesting age information from the shadow MMU is still done while holding the MMU write lock. Suggested-by: Yu Zhao <yuzhao@google.com> Signed-off-by: James Houghton <jthoughton@google.com> --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/mmu/mmu.c | 10 ++++-- arch/x86/kvm/mmu/tdp_iter.h | 14 ++++---- arch/x86/kvm/mmu/tdp_mmu.c | 57 ++++++++++++++++++++++++--------- 5 files changed, 58 insertions(+), 25 deletions(-)