Merge branch kvm-arm64/mmu-rwlock into kvmarm-master/next

* kvm-arm64/mmu-rwlock:
  : .
  : MMU locking optimisations from Jing Zhang, allowing permission
  : relaxations to occur in parallel.
  : .
  KVM: selftests: Add vgic initialization for dirty log perf test for ARM
  KVM: arm64: Add fast path to handle permission relaxation during dirty logging
  KVM: arm64: Use read/write spin lock for MMU protection
Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/kvm_host.h

@@ -50,6 +50,8 @@
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
 
+#define KVM_HAVE_MMU_RWLOCK
+
 /*
  * Mode of operation configurable with kvm-arm.mode early param.
  * See Documentation/admin-guide/kernel-parameters.txt for more information.

arch/arm64/kvm/mmu.c

@@ -58,7 +58,7 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr,
 			break;
 
 		if (resched && next != end)
-			cond_resched_lock(&kvm->mmu_lock);
+			cond_resched_rwlock_write(&kvm->mmu_lock);
 	} while (addr = next, addr != end);
 
 	return ret;
@@ -179,7 +179,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
 	phys_addr_t end = start + size;
 
-	assert_spin_locked(&kvm->mmu_lock);
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	WARN_ON(size & ~PAGE_MASK);
 	WARN_ON(stage2_apply_range(kvm, start, end, kvm_pgtable_stage2_unmap,
 				   may_block));
@@ -213,13 +213,13 @@ static void stage2_flush_vm(struct kvm *kvm)
 	int idx, bkt;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_flush_memslot(kvm, memslot);
 
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -720,13 +720,13 @@ void stage2_unmap_vm(struct kvm *kvm)
 
 	idx = srcu_read_lock(&kvm->srcu);
 	mmap_read_lock(current->mm);
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, bkt, slots)
 		stage2_unmap_memslot(kvm, memslot);
 
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 	mmap_read_unlock(current->mm);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
@@ -736,14 +736,14 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
 	struct kvm_pgtable *pgt = NULL;
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 	pgt = mmu->pgt;
 	if (pgt) {
 		mmu->pgd_phys = 0;
 		mmu->pgt = NULL;
 		free_percpu(mmu->last_vcpu_ran);
 	}
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 
 	if (pgt) {
 		kvm_pgtable_stage2_destroy(pgt);
@@ -783,10 +783,10 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 		if (ret)
 			break;
 
-		spin_lock(&kvm->mmu_lock);
+		write_lock(&kvm->mmu_lock);
 		ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot,
 					     &cache);
-		spin_unlock(&kvm->mmu_lock);
+		write_unlock(&kvm->mmu_lock);
 		if (ret)
 			break;
 
@@ -834,9 +834,9 @@ static void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 	start = memslot->base_gfn << PAGE_SHIFT;
 	end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 	stage2_wp_range(&kvm->arch.mmu, start, end);
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 	kvm_flush_remote_tlbs(kvm);
 }
 
@@ -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);
 	}
@@ -1212,7 +1214,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (exec_fault && device)
 		return -ENOEXEC;
 
-	spin_lock(&kvm->mmu_lock);
+	/*
+	 * 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))
 		goto out_unlock;
@@ -1271,7 +1281,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 out_unlock:
-	spin_unlock(&kvm->mmu_lock);
+	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);
 	return ret != -EAGAIN ? ret : 0;
@@ -1286,10 +1299,10 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 
 	trace_kvm_access_fault(fault_ipa);
 
-	spin_lock(&vcpu->kvm->mmu_lock);
+	write_lock(&vcpu->kvm->mmu_lock);
 	mmu = vcpu->arch.hw_mmu;
 	kpte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa);
-	spin_unlock(&vcpu->kvm->mmu_lock);
+	write_unlock(&vcpu->kvm->mmu_lock);
 
 	pte = __pte(kpte);
 	if (pte_valid(pte))
@@ -1692,9 +1705,9 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
 	phys_addr_t size = slot->npages << PAGE_SHIFT;
 
-	spin_lock(&kvm->mmu_lock);
+	write_lock(&kvm->mmu_lock);
 	unmap_stage2_range(&kvm->arch.mmu, gpa, size);
-	spin_unlock(&kvm->mmu_lock);
+	write_unlock(&kvm->mmu_lock);
 }
 
 /*

tools/testing/selftests/kvm/dirty_log_perf_test.c

@@ -18,6 +18,12 @@
 #include "test_util.h"
 #include "perf_test_util.h"
 #include "guest_modes.h"
+#ifdef __aarch64__
+#include "aarch64/vgic.h"
+
+#define GICD_BASE_GPA			0x8000000ULL
+#define GICR_BASE_GPA			0x80A0000ULL
+#endif
 
 /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
 #define TEST_HOST_LOOP_N		2UL
@@ -200,6 +206,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
+#ifdef __aarch64__
+	vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+#endif
+
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;