KVM: arm64: Add fast path to handle permission relaxation during dirty logging

To reduce MMU lock contention during dirty logging, all permission
relaxation operations would be performed under read lock.
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220118015703.3630552-3-jingzhangos@google.com

arch/arm64/kvm/mmu.c

@@ -1080,6 +1080,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
+	bool logging_perm_fault = false;
 	unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
 	unsigned long vma_pagesize, fault_granule;
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
@@ -1114,6 +1115,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (logging_active) {
 		force_pte = true;
 		vma_shift = PAGE_SHIFT;
+		logging_perm_fault = (fault_status == FSC_PERM && write_fault);
 	} else {
 		vma_shift = get_vma_page_shift(vma, hva);
 	}
@@ -1212,6 +1214,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && device)
 		return -ENOEXEC;
 
+	/*
+	 * To reduce MMU contentions and enhance concurrency during dirty
+	 * logging dirty logging, only acquire read lock for permission
+	 * relaxation.
+	 */
+	if (logging_perm_fault)
+		read_lock(&kvm->mmu_lock);
+	else
 		write_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_notifier_retry(kvm, mmu_seq))
@@ -1271,6 +1281,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 out_unlock:
+	if (logging_perm_fault)
+		read_unlock(&kvm->mmu_lock);
+	else
 		write_unlock(&kvm->mmu_lock);
 	kvm_set_pfn_accessed(pfn);
 	kvm_release_pfn_clean(pfn);