[PATCH v2 26/28] KVM: x86/mmu: Allow enabling / disabling dirty logging under MMU read lock
From: Ben Gardon
Date: Tue Feb 02 2021 - 14:06:35 EST
To reduce lock contention and interference with page fault handlers,
allow the TDP MMU functions which enable and disable dirty logging
to operate under the MMU read lock.
Extend dirty logging enable disable functions read lock-ness
Signed-off-by: Ben Gardon <bgardon@xxxxxxxxxx>
---
arch/x86/kvm/mmu/mmu.c | 14 +++---
arch/x86/kvm/mmu/tdp_mmu.c | 93 ++++++++++++++++++++++++++++++--------
arch/x86/kvm/mmu/tdp_mmu.h | 2 +-
3 files changed, 84 insertions(+), 25 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e3cf868be6bd..6ba2a72d4330 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5638,9 +5638,10 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
write_lock(&kvm->mmu_lock);
flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false);
+ write_unlock(&kvm->mmu_lock);
+
if (kvm->arch.tdp_mmu_enabled)
flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
- write_unlock(&kvm->mmu_lock);
/*
* It's also safe to flush TLBs out of mmu lock here as currently this
@@ -5661,9 +5662,10 @@ void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
write_lock(&kvm->mmu_lock);
flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect,
false);
+ write_unlock(&kvm->mmu_lock);
+
if (kvm->arch.tdp_mmu_enabled)
flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_2M);
- write_unlock(&kvm->mmu_lock);
if (flush)
kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
@@ -5677,12 +5679,12 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm,
write_lock(&kvm->mmu_lock);
flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false);
- if (kvm->arch.tdp_mmu_enabled)
- flush |= kvm_tdp_mmu_slot_set_dirty(kvm, memslot);
- write_unlock(&kvm->mmu_lock);
-
if (flush)
kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+ write_unlock(&kvm->mmu_lock);
+
+ if (kvm->arch.tdp_mmu_enabled)
+ kvm_tdp_mmu_slot_set_dirty(kvm, memslot);
}
EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index cfe66b8d39fa..6093926a6bc5 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -553,18 +553,22 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
}
/*
- * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically and handle the
+ * __tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically and handle the
* associated bookkeeping
*
* @kvm: kvm instance
* @iter: a tdp_iter instance currently on the SPTE that should be set
* @new_spte: The value the SPTE should be set to
+ * @record_dirty_log: Record the page as dirty in the dirty bitmap if
+ * appropriate for the change being made. Should be set
+ * unless performing certain dirty logging operations.
+ * Leaving record_dirty_log unset in that case prevents page
+ * writes from being double counted.
* Returns: true if the SPTE was set, false if it was not. If false is returned,
* this function will have no side-effects.
*/
-static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
- struct tdp_iter *iter,
- u64 new_spte)
+static inline bool __tdp_mmu_set_spte_atomic(struct kvm *kvm,
+ struct tdp_iter *iter, u64 new_spte, bool record_dirty_log)
{
u64 *root_pt = tdp_iter_root_pt(iter);
struct kvm_mmu_page *root = sptep_to_sp(root_pt);
@@ -583,12 +587,31 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
new_spte) != iter->old_spte)
return false;
- handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
- iter->level, true);
+ __handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
+ iter->level, true);
+ handle_changed_spte_acc_track(iter->old_spte, new_spte, iter->level);
+ if (record_dirty_log)
+ handle_changed_spte_dirty_log(kvm, as_id, iter->gfn,
+ iter->old_spte, new_spte,
+ iter->level);
return true;
}
+static inline bool tdp_mmu_set_spte_atomic_no_dirty_log(struct kvm *kvm,
+ struct tdp_iter *iter,
+ u64 new_spte)
+{
+ return __tdp_mmu_set_spte_atomic(kvm, iter, new_spte, false);
+}
+
+static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
+ struct tdp_iter *iter,
+ u64 new_spte)
+{
+ return __tdp_mmu_set_spte_atomic(kvm, iter, new_spte, true);
+}
+
static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm,
struct tdp_iter *iter)
{
@@ -1206,7 +1229,8 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
for_each_tdp_pte_min_level(iter, root->spt, root->role.level,
min_level, start, end) {
- if (tdp_mmu_iter_cond_resched(kvm, &iter, false, false))
+retry:
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
continue;
if (!is_shadow_present_pte(iter.old_spte) ||
@@ -1216,7 +1240,15 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
new_spte = iter.old_spte & ~PT_WRITABLE_MASK;
- tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+ if (!tdp_mmu_set_spte_atomic_no_dirty_log(kvm, &iter,
+ new_spte)) {
+ /*
+ * The iter must explicitly re-read the SPTE because
+ * the atomic cmpxchg failed.
+ */
+ iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+ goto retry;
+ }
spte_set = true;
}
@@ -1236,7 +1268,8 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot,
int root_as_id;
bool spte_set = false;
- for_each_tdp_mmu_root_yield_safe(kvm, root, false) {
+ read_lock(&kvm->mmu_lock);
+ for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
root_as_id = kvm_mmu_page_as_id(root);
if (root_as_id != slot->as_id)
continue;
@@ -1244,6 +1277,7 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot,
spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
slot->base_gfn + slot->npages, min_level);
}
+ read_unlock(&kvm->mmu_lock);
return spte_set;
}
@@ -1265,7 +1299,8 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
rcu_read_lock();
tdp_root_for_each_leaf_pte(iter, root, start, end) {
- if (tdp_mmu_iter_cond_resched(kvm, &iter, false, false))
+retry:
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
continue;
if (spte_ad_need_write_protect(iter.old_spte)) {
@@ -1280,7 +1315,15 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
continue;
}
- tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte);
+ if (!tdp_mmu_set_spte_atomic_no_dirty_log(kvm, &iter,
+ new_spte)) {
+ /*
+ * The iter must explicitly re-read the SPTE because
+ * the atomic cmpxchg failed.
+ */
+ iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+ goto retry;
+ }
spte_set = true;
}
@@ -1301,7 +1344,8 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
int root_as_id;
bool spte_set = false;
- for_each_tdp_mmu_root_yield_safe(kvm, root, false) {
+ read_lock(&kvm->mmu_lock);
+ for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
root_as_id = kvm_mmu_page_as_id(root);
if (root_as_id != slot->as_id)
continue;
@@ -1309,6 +1353,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
slot->base_gfn + slot->npages);
}
+ read_unlock(&kvm->mmu_lock);
return spte_set;
}
@@ -1397,7 +1442,8 @@ static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
rcu_read_lock();
tdp_root_for_each_pte(iter, root, start, end) {
- if (tdp_mmu_iter_cond_resched(kvm, &iter, false, false))
+retry:
+ if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
continue;
if (!is_shadow_present_pte(iter.old_spte) ||
@@ -1406,7 +1452,14 @@ static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
new_spte = iter.old_spte | shadow_dirty_mask;
- tdp_mmu_set_spte(kvm, &iter, new_spte);
+ if (!tdp_mmu_set_spte_atomic(kvm, &iter, new_spte)) {
+ /*
+ * The iter must explicitly re-read the SPTE because
+ * the atomic cmpxchg failed.
+ */
+ iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+ goto retry;
+ }
spte_set = true;
}
@@ -1417,15 +1470,15 @@ static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
/*
* Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is
* only used for PML, and so will involve setting the dirty bit on each SPTE.
- * Returns true if an SPTE has been changed and the TLBs need to be flushed.
*/
-bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot)
+void kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot)
{
struct kvm_mmu_page *root;
int root_as_id;
bool spte_set = false;
- for_each_tdp_mmu_root_yield_safe(kvm, root, false) {
+ read_lock(&kvm->mmu_lock);
+ for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
root_as_id = kvm_mmu_page_as_id(root);
if (root_as_id != slot->as_id)
continue;
@@ -1433,7 +1486,11 @@ bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot)
spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn,
slot->base_gfn + slot->npages);
}
- return spte_set;
+
+ if (spte_set)
+ kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+
+ read_unlock(&kvm->mmu_lock);
}
/*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 10ada884270b..848b41b20985 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -38,7 +38,7 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t gfn, unsigned long mask,
bool wrprot);
-bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot);
+void kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot);
void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
const struct kvm_memory_slot *slot);
--
2.30.0.365.g02bc693789-goog