[PATCH v2 25/28] KVM: x86/mmu: Allow zapping collapsible SPTEs to use MMU read lock

[Ben Gardon]

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 <bgar...@google.com>
---
 arch/x86/kvm/mmu/mmu.c     |  5 ++---
 arch/x86/kvm/mmu/tdp_mmu.c | 22 +++++++++++++++-------
 2 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 254ff87d2a61..e3cf868be6bd 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5517,8 +5517,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, 
gfn_t gfn_end)
                                                start, end - 1, true);
                }
        }
-
-       kvm_mmu_unlock(kvm);
+       write_unlock(&kvm->mmu_lock);
 
        if (kvm->arch.tdp_mmu_enabled) {
                read_lock(&kvm->mmu_lock);
@@ -5611,10 +5610,10 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
        write_lock(&kvm->mmu_lock);
        slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot,
                         kvm_mmu_zap_collapsible_spte, true);
+       write_unlock(&kvm->mmu_lock);
 
        if (kvm->arch.tdp_mmu_enabled)
                kvm_tdp_mmu_zap_collapsible_sptes(kvm, memslot);
-       write_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 de26762433ea..cfe66b8d39fa 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1451,10 +1451,9 @@ static void 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, false, false)) {
-                       spte_set = false;
+retry:
+               if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
                        continue;
-               }
 
                if (!is_shadow_present_pte(iter.old_spte) ||
                    !is_last_spte(iter.old_spte, iter.level))
@@ -1465,9 +1464,14 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
                    !PageTransCompoundMap(pfn_to_page(pfn)))
                        continue;
 
-               tdp_mmu_set_spte(kvm, &iter, 0);
-
-               spte_set = true;
+               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;
+               }
        }
 
        rcu_read_unlock();
@@ -1485,7 +1489,9 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
        struct kvm_mmu_page *root;
        int root_as_id;
 
-       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;
@@ -1493,6 +1499,8 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
                zap_collapsible_spte_range(kvm, root, slot->base_gfn,
                                           slot->base_gfn + slot->npages);
        }
+
+       read_unlock(&kvm->mmu_lock);
 }
 
 /*
-- 
2.30.0.365.g02bc693789-goog