[v2,10/13] KVM: x86/mmu: Allow zapping collapsible SPTEs to use MMU read lock

Commit Message

Ben Gardon April 1, 2021, 11:37 p.m. UTC

To speed the process of disabling dirty logging, change the TDP MMU
function which zaps collapsible SPTEs to run under the MMU read lock.

Signed-off-by: Ben Gardon <[e-mail]>
---
 arch/x86/kvm/mmu/mmu.c     | 14 ++++++++++----
 arch/x86/kvm/mmu/tdp_mmu.c | 17 +++++++++++++----
 2 files changed, 23 insertions(+), 8 deletions(-)

Comments

Paolo Bonzini April 2, 2021, 11:14 a.m. UTC | #1

On 02/04/21 01:37, Ben Gardon wrote:
> To speed the process of disabling dirty logging, change the TDP MMU
> function which zaps collapsible SPTEs to run under the MMU read lock.

Technically it only reduces the impact on the running VM; it doesn't
speed it up right?  Something like:

     To reduce the impact of disabling dirty logging, change the TDP MMU
     function which zaps collapsible SPTEs to run under the MMU read lock.
     This way, page faults on zapped SPTEs can proceed in parallel with
     kvm_mmu_zap_collapsible_sptes.

Paolo

Patch

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d03a7a8b7ea2..5939813e3043 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5612,13 +5612,19 @@  void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	write_lock(&kvm->mmu_lock);
 	flush = slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true);
 
-	if (is_tdp_mmu_enabled(kvm))
-		flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush);
-
 	if (flush)
 		kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
-
 	write_unlock(&kvm->mmu_lock);
+
+	if (is_tdp_mmu_enabled(kvm)) {
+		flush = false;
+
+		read_lock(&kvm->mmu_lock);
+		flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush);
+		if (flush)
+			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+		read_unlock(&kvm->mmu_lock);
+	}
 }
 
 void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 6917403484ce..0e6ffa04e5e1 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1323,7 +1323,8 @@  static bool zap_collapsible_spte_range(struct kvm *kvm,
 	rcu_read_lock();
 
 	tdp_root_for_each_pte(iter, root, start, end) {
-		if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) {
+retry:
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) {
 			flush = false;
 			continue;
 		}
@@ -1338,8 +1339,14 @@  static bool zap_collapsible_spte_range(struct kvm *kvm,
 							    pfn, PG_LEVEL_NUM))
 			continue;
 
-		tdp_mmu_set_spte(kvm, &iter, 0);
-
+		if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) {
+			/*
+			 * The iter must explicitly re-read the SPTE because
+			 * the atomic cmpxchg failed.
+			 */
+			iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
+			goto retry;
+		}
 		flush = true;
 	}
 
@@ -1358,7 +1365,9 @@  bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, false)
+	lockdep_assert_held_read(&kvm->mmu_lock);
+
+	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
 		flush = zap_collapsible_spte_range(kvm, root, slot, flush);
 
 	return flush;