Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Paolo Bonzini:
 "Selftest changes:

   - Cleanups for the perf test infrastructure and mapping hugepages

   - Avoid contention on mmap_sem when the guests start to run

   - Add event channel upcall support to xen_shinfo_test

  x86 changes:

   - Fixes for Xen emulation

   - Kill kvm_map_gfn() / kvm_unmap_gfn() and broken gfn_to_pfn_cache

   - Fixes for migration of 32-bit nested guests on 64-bit hypervisor

   - Compilation fixes

   - More SEV cleanups

  Generic:

   - Cap the return value of KVM_CAP_NR_VCPUS to both KVM_CAP_MAX_VCPUS
     and num_online_cpus(). Most architectures were only using one of
     the two"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (42 commits)
  KVM: x86: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS
  KVM: s390: Cap KVM_CAP_NR_VCPUS by num_online_cpus()
  KVM: RISC-V: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS
  KVM: PPC: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS
  KVM: MIPS: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS
  KVM: arm64: Cap KVM_CAP_NR_VCPUS by kvm_arm_default_max_vcpus()
  KVM: x86: Assume a 64-bit hypercall for guests with protected state
  selftests: KVM: Add /x86_64/sev_migrate_tests to .gitignore
  riscv: kvm: fix non-kernel-doc comment block
  KVM: SEV: Fix typo in and tweak name of cmd_allowed_from_miror()
  KVM: SEV: Drop a redundant setting of sev->asid during initialization
  KVM: SEV: WARN if SEV-ES is marked active but SEV is not
  KVM: SEV: Set sev_info.active after initial checks in sev_guest_init()
  KVM: SEV: Disallow COPY_ENC_CONTEXT_FROM if target has created vCPUs
  KVM: Kill kvm_map_gfn() / kvm_unmap_gfn() and gfn_to_pfn_cache
  KVM: nVMX: Use a gfn_to_hva_cache for vmptrld
  KVM: nVMX: Use kvm_read_guest_offset_cached() for nested VMCS check
  KVM: x86/xen: Use sizeof_field() instead of open-coding it
  KVM: nVMX: Use kvm_{read,write}_guest_cached() for shadow_vmcs12
  KVM: x86/xen: Fix get_attr of KVM_XEN_ATTR_TYPE_SHARED_INFO
  ...

arch/arm64/kvm/arm.c

@@ -223,7 +223,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		/*
+		 * ARM64 treats KVM_CAP_NR_CPUS differently from all other
+		 * architectures, as it does not always bound it to
+		 * KVM_CAP_MAX_VCPUS. It should not matter much because
+		 * this is just an advisory value.
+		 */
+		r = min_t(unsigned int, num_online_cpus(),
+			  kvm_arm_default_max_vcpus());
 		break;
 	case KVM_CAP_MAX_VCPUS:
 	case KVM_CAP_MAX_VCPU_ID:

arch/mips/kvm/mips.c

@@ -1067,7 +1067,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;

arch/powerpc/kvm/powerpc.c

@@ -641,9 +641,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * implementations just count online CPUs.
 		 */
 		if (hv_enabled)
-			r = num_present_cpus();
+			r = min_t(unsigned int, num_present_cpus(), KVM_MAX_VCPUS);
 		else
-			r = num_online_cpus();
+			r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;

arch/riscv/kvm/vcpu_sbi.c

 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * Copyright (c) 2019 Western Digital Corporation or its affiliates.
  *
  * Authors:

arch/riscv/kvm/vm.c

@@ -74,7 +74,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;

arch/s390/kvm/kvm-s390.c

@@ -585,6 +585,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			r = KVM_MAX_VCPUS;
 		else if (sclp.has_esca && sclp.has_64bscao)
 			r = KVM_S390_ESCA_CPU_SLOTS;
+		if (ext == KVM_CAP_NR_VCPUS)
+			r = min_t(unsigned int, num_online_cpus(), r);
 		break;
 	case KVM_CAP_S390_COW:
 		r = MACHINE_HAS_ESOP;

arch/x86/include/asm/kvm_host.h

@@ -363,6 +363,7 @@ union kvm_mmu_extended_role {
 		unsigned int cr4_smap:1;
 		unsigned int cr4_smep:1;
 		unsigned int cr4_la57:1;
+		unsigned int efer_lma:1;
 	};
 };
 

arch/x86/kvm/cpuid.c

@@ -125,7 +125,7 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu)
 	}
 }
 
-struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
 {
 	u32 base = vcpu->arch.kvm_cpuid_base;
 

arch/x86/kvm/hyperv.c

@@ -2022,7 +2022,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 {
 	bool longmode;
 
-	longmode = is_64_bit_mode(vcpu);
+	longmode = is_64_bit_hypercall(vcpu);
 	if (longmode)
 		kvm_rax_write(vcpu, result);
 	else {
@@ -2171,7 +2171,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	}
 
 #ifdef CONFIG_X86_64
-	if (is_64_bit_mode(vcpu)) {
+	if (is_64_bit_hypercall(vcpu)) {
 		hc.param = kvm_rcx_read(vcpu);
 		hc.ingpa = kvm_rdx_read(vcpu);
 		hc.outgpa = kvm_r8_read(vcpu);

arch/x86/kvm/mmu/mmu.c

@@ -4682,6 +4682,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu,
 		/* PKEY and LA57 are active iff long mode is active. */
 		ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs);
 		ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs);
+		ext.efer_lma = ____is_efer_lma(regs);
 	}
 
 	ext.valid = 1;

arch/x86/kvm/svm/sev.c

@@ -237,7 +237,6 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-	bool es_active = argp->id == KVM_SEV_ES_INIT;
 	int asid, ret;
 
 	if (kvm->created_vcpus)
@@ -247,7 +246,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (unlikely(sev->active))
 		return ret;
 
-	sev->es_active = es_active;
+	sev->active = true;
+	sev->es_active = argp->id == KVM_SEV_ES_INIT;
 	asid = sev_asid_new(sev);
 	if (asid < 0)
 		goto e_no_asid;
@@ -257,8 +257,6 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (ret)
 		goto e_free;
 
-	sev->active = true;
-	sev->asid = asid;
 	INIT_LIST_HEAD(&sev->regions_list);
 
 	return 0;
@@ -268,6 +266,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	sev->asid = 0;
 e_no_asid:
 	sev->es_active = false;
+	sev->active = false;
 	return ret;
 }
 
@@ -1530,7 +1529,7 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
 }
 
-static bool cmd_allowed_from_miror(u32 cmd_id)
+static bool is_cmd_allowed_from_mirror(u32 cmd_id)
 {
 	/*
 	 * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES
@@ -1757,7 +1756,7 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 
 	/* Only the enc_context_owner handles some memory enc operations. */
 	if (is_mirroring_enc_context(kvm) &&
-	    !cmd_allowed_from_miror(sev_cmd.id)) {
+	    !is_cmd_allowed_from_mirror(sev_cmd.id)) {
 		r = -EINVAL;
 		goto out;
 	}
@@ -1990,7 +1989,12 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 	mutex_unlock(&source_kvm->lock);
 	mutex_lock(&kvm->lock);
 
-	if (sev_guest(kvm)) {
+	/*
+	 * Disallow out-of-band SEV/SEV-ES init if the target is already an
+	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
+	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
+	 */
+	if (sev_guest(kvm) || kvm->created_vcpus) {
 		ret = -EINVAL;
 		goto e_mirror_unlock;
 	}

arch/x86/kvm/svm/svm.h

@@ -247,7 +247,7 @@ static __always_inline bool sev_es_guest(struct kvm *kvm)
 #ifdef CONFIG_KVM_AMD_SEV
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 
-	return sev_guest(kvm) && sev->es_active;
+	return sev->es_active && !WARN_ON_ONCE(!sev->active);
 #else
 	return false;
 #endif

arch/x86/kvm/vmx/nested.c

@@ -670,33 +670,39 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
-	struct kvm_host_map map;
-	struct vmcs12 *shadow;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
 
 	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
 	    vmcs12->vmcs_link_pointer == INVALID_GPA)
 		return;
 
-	shadow = get_shadow_vmcs12(vcpu);
-
-	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))
+	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+	    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
 		return;
 
-	memcpy(shadow, map.hva, VMCS12_SIZE);
-	kvm_vcpu_unmap(vcpu, &map, false);
+	kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+			      VMCS12_SIZE);
 }
 
 static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu,
 					      struct vmcs12 *vmcs12)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
 
 	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
 	    vmcs12->vmcs_link_pointer == INVALID_GPA)
 		return;
 
-	kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer,
-			get_shadow_vmcs12(vcpu), VMCS12_SIZE);
+	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+	    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
+		return;
+
+	kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+			       VMCS12_SIZE);
 }
 
 /*
@@ -2830,6 +2836,17 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+#ifdef CONFIG_X86_64
+	if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) !=
+		!!(vcpu->arch.efer & EFER_LMA)))
+		return -EINVAL;
+#endif
+	return 0;
+}
+
 static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
@@ -2854,18 +2871,16 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 #ifdef CONFIG_X86_64
-	ia32e = !!(vcpu->arch.efer & EFER_LMA);
+	ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
 #else
 	ia32e = false;
 #endif
 
 	if (ia32e) {
-		if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) ||
-		    CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
+		if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
 			return -EINVAL;
 	} else {
-		if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) ||
-		    CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
+		if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
 		    CC(vmcs12->host_cr4 & X86_CR4_PCIDE) ||
 		    CC((vmcs12->host_rip) >> 32))
 			return -EINVAL;
@@ -2910,9 +2925,9 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
 					  struct vmcs12 *vmcs12)
 {
-	int r = 0;
-	struct vmcs12 *shadow;
-	struct kvm_host_map map;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
+	struct vmcs_hdr hdr;
 
 	if (vmcs12->vmcs_link_pointer == INVALID_GPA)
 		return 0;
@@ -2920,17 +2935,21 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
 	if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer)))
 		return -EINVAL;
 
-	if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)))
-		return -EINVAL;
+	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+	    CC(kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+					 vmcs12->vmcs_link_pointer, VMCS12_SIZE)))
+                return -EINVAL;
 
-	shadow = map.hva;
+	if (CC(kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
+					    offsetof(struct vmcs12, hdr),
+					    sizeof(hdr))))
+		return -EINVAL;
 
-	if (CC(shadow->hdr.revision_id != VMCS12_REVISION) ||
-	    CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
-		r = -EINVAL;
+	if (CC(hdr.revision_id != VMCS12_REVISION) ||
+	    CC(hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
+		return -EINVAL;
 
-	kvm_vcpu_unmap(vcpu, &map, false);
-	return r;
+	return 0;
 }
 
 /*
@@ -3535,6 +3554,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (nested_vmx_check_controls(vcpu, vmcs12))
 		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 
+	if (nested_vmx_check_address_space_size(vcpu, vmcs12))
+		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
+
 	if (nested_vmx_check_host_state(vcpu, vmcs12))
 		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
 
@@ -5264,10 +5286,11 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		return 1;
 
 	if (vmx->nested.current_vmptr != vmptr) {
-		struct kvm_host_map map;
-		struct vmcs12 *new_vmcs12;
+		struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache;
+		struct vmcs_hdr hdr;
 
-		if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmptr), &map)) {
+		if (ghc->gpa != vmptr &&
+		    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
 			/*
 			 * Reads from an unbacked page return all 1s,
 			 * which means that the 32 bits located at the
@@ -5278,12 +5301,16 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
 		}
 
-		new_vmcs12 = map.hva;
+		if (kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
+						 offsetof(struct vmcs12, hdr),
+						 sizeof(hdr))) {
+			return nested_vmx_fail(vcpu,
+				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+		}
 
-		if (new_vmcs12->hdr.revision_id != VMCS12_REVISION ||
-		    (new_vmcs12->hdr.shadow_vmcs &&
+		if (hdr.revision_id != VMCS12_REVISION ||
+		    (hdr.shadow_vmcs &&
 		     !nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
-			kvm_vcpu_unmap(vcpu, &map, false);
 			return nested_vmx_fail(vcpu,
 				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
 		}
@@ -5294,8 +5321,11 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		 * Load VMCS12 from guest memory since it is not already
 		 * cached.
 		 */
-		memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
-		kvm_vcpu_unmap(vcpu, &map, false);
+		if (kvm_read_guest_cached(vcpu->kvm, ghc, vmx->nested.cached_vmcs12,
+					  VMCS12_SIZE)) {
+			return nested_vmx_fail(vcpu,
+				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+		}
 
 		set_current_vmptr(vmx, vmptr);
 	}

arch/x86/kvm/vmx/vmx.h

@@ -141,6 +141,16 @@ struct nested_vmx {
 	 */
 	struct vmcs12 *cached_shadow_vmcs12;
 
+	/*
+	 * GPA to HVA cache for accessing vmcs12->vmcs_link_pointer
+	 */
+	struct gfn_to_hva_cache shadow_vmcs12_cache;
+
+	/*
+	 * GPA to HVA cache for VMCS12
+	 */
+	struct gfn_to_hva_cache vmcs12_cache;
+
 	/*
 	 * Indicates if the shadow vmcs or enlightened vmcs must be updated
 	 * with the data held by struct vmcs12.

arch/x86/kvm/x86.c

@@ -3307,9 +3307,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 			     "xor %1, %1\n"
 			     "2:\n"
 			     _ASM_EXTABLE_UA(1b, 2b)
-			     : "+r" (st_preempted),
-			       "+&r" (err)
-			     : "m" (st->preempted));
+			     : "+q" (st_preempted),
+			       "+&r" (err),
+			       "+m" (st->preempted));
 		if (err)
 			goto out;
 
@@ -4179,7 +4179,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = !static_call(kvm_x86_cpu_has_accelerated_tpr)();
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
@@ -8848,7 +8848,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 
 	trace_kvm_hypercall(nr, a0, a1, a2, a3);
 
-	op_64_bit = is_64_bit_mode(vcpu);
+	op_64_bit = is_64_bit_hypercall(vcpu);
 	if (!op_64_bit) {
 		nr &= 0xFFFFFFFF;
 		a0 &= 0xFFFFFFFF;
@@ -9547,12 +9547,16 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu)
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		return;
 
-	if (to_hv_vcpu(vcpu))
+	if (to_hv_vcpu(vcpu)) {
 		bitmap_or((ulong *)eoi_exit_bitmap,
 			  vcpu->arch.ioapic_handled_vectors,
 			  to_hv_synic(vcpu)->vec_bitmap, 256);
+		static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+		return;
+	}
 
-	static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+	static_call(kvm_x86_load_eoi_exitmap)(
+		vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors);
 }
 
 void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,

arch/x86/kvm/x86.h

@@ -153,12 +153,24 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu)
 {
 	int cs_db, cs_l;
 
+	WARN_ON_ONCE(vcpu->arch.guest_state_protected);
+
 	if (!is_long_mode(vcpu))
 		return false;
 	static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
 	return cs_l;
 }
 
+static inline bool is_64_bit_hypercall(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * If running with protected guest state, the CS register is not
+	 * accessible. The hypercall register values will have had to been
+	 * provided in 64-bit mode, so assume the guest is in 64-bit.
+	 */
+	return vcpu->arch.guest_state_protected || is_64_bit_mode(vcpu);
+}
+
 static inline bool x86_exception_has_error_code(unsigned int vector)
 {
 	static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |

arch/x86/kvm/xen.c

@@ -127,9 +127,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	state_entry_time = vx->runstate_entry_time;
 	state_entry_time |= XEN_RUNSTATE_UPDATE;
 
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) !=
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) !=
 		     sizeof(state_entry_time));
-	BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) !=
+	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) !=
 		     sizeof(state_entry_time));
 
 	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -144,9 +144,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	 */
 	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) !=
 		     offsetof(struct compat_vcpu_runstate_info, state));
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) !=
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state) !=
 		     sizeof(vx->current_runstate));
-	BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) !=
+	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) !=
 		     sizeof(vx->current_runstate));
 
 	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -163,9 +163,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 		     offsetof(struct vcpu_runstate_info, time) - sizeof(u64));
 	BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) !=
 		     offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64));
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
-		     sizeof(((struct compat_vcpu_runstate_info *)0)->time));
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
+		     sizeof_field(struct compat_vcpu_runstate_info, time));
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
 		     sizeof(vx->runstate_times));
 
 	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -205,9 +205,9 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
 	BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) !=
 		     offsetof(struct compat_vcpu_info, evtchn_upcall_pending));
 	BUILD_BUG_ON(sizeof(rc) !=
-		     sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending));
+		     sizeof_field(struct vcpu_info, evtchn_upcall_pending));
 	BUILD_BUG_ON(sizeof(rc) !=
-		     sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending));
+		     sizeof_field(struct compat_vcpu_info, evtchn_upcall_pending));
 
 	/*
 	 * For efficiency, this mirrors the checks for using the valid
@@ -299,7 +299,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		break;
 
 	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
-		data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn);
+		data->u.shared_info.gfn = kvm->arch.xen.shinfo_gfn;
 		r = 0;
 		break;
 
@@ -698,7 +698,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 	    kvm_hv_hypercall_enabled(vcpu))
 		return kvm_hv_hypercall(vcpu);
 
-	longmode = is_64_bit_mode(vcpu);
+	longmode = is_64_bit_hypercall(vcpu);
 	if (!longmode) {
 		params[0] = (u32)kvm_rbx_read(vcpu);
 		params[1] = (u32)kvm_rcx_read(vcpu);

include/linux/kvm_host.h

@@ -874,7 +874,7 @@ void kvm_release_pfn_dirty(kvm_pfn_t pfn);
 void kvm_set_pfn_dirty(kvm_pfn_t pfn);
 void kvm_set_pfn_accessed(kvm_pfn_t pfn);
 
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache);
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty);
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 			int len);
 int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
@@ -950,12 +950,8 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn
 kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
 kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
-int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
-		struct gfn_to_pfn_cache *cache, bool atomic);
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
-int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
-		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic);
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
 int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,

include/linux/kvm_types.h

@@ -53,13 +53,6 @@ struct gfn_to_hva_cache {
 	struct kvm_memory_slot *memslot;
 };
 
-struct gfn_to_pfn_cache {
-	u64 generation;
-	gfn_t gfn;
-	kvm_pfn_t pfn;
-	bool dirty;
-};
-
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 /*
  * Memory caches are used to preallocate memory ahead of various MMU flows,

tools/testing/selftests/kvm/.gitignore

@@ -23,6 +23,7 @@
 /x86_64/platform_info_test
 /x86_64/set_boot_cpu_id
 /x86_64/set_sregs_test
+/x86_64/sev_migrate_tests
 /x86_64/smm_test
 /x86_64/state_test
 /x86_64/svm_vmcall_test

tools/testing/selftests/kvm/access_tracking_perf_test.c

@@ -47,7 +47,7 @@
 #include "guest_modes.h"
 
 /* Global variable used to synchronize all of the vCPU threads. */
-static int iteration = -1;
+static int iteration;
 
 /* Defines what vCPU threads should do during a given iteration. */
 static enum {
@@ -215,12 +215,11 @@ static bool spin_wait_for_next_iteration(int *current_iteration)
 	return true;
 }
 
-static void *vcpu_thread_main(void *arg)
+static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args)
 {
-	struct perf_test_vcpu_args *vcpu_args = arg;
 	struct kvm_vm *vm = perf_test_args.vm;
 	int vcpu_id = vcpu_args->vcpu_id;
-	int current_iteration = -1;
+	int current_iteration = 0;
 
 	while (spin_wait_for_next_iteration(&current_iteration)) {
 		switch (READ_ONCE(iteration_work)) {
@@ -235,8 +234,6 @@ static void *vcpu_thread_main(void *arg)
 
 		vcpu_last_completed_iteration[vcpu_id] = current_iteration;
 	}
-
-	return NULL;
 }
 
 static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
@@ -277,8 +274,7 @@ static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description)
 static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
 			  const char *description)
 {
-	perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
-	sync_global_to_guest(vm, perf_test_args);
+	perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1);
 	iteration_work = ITERATION_ACCESS_MEMORY;
 	run_iteration(vm, vcpus, description);
 }
@@ -296,48 +292,16 @@ static void mark_memory_idle(struct kvm_vm *vm, int vcpus)
 	run_iteration(vm, vcpus, "Mark memory idle");
 }
 
-static pthread_t *create_vcpu_threads(int vcpus)
-{
-	pthread_t *vcpu_threads;
-	int i;
-
-	vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
-	TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
-
-	for (i = 0; i < vcpus; i++) {
-		vcpu_last_completed_iteration[i] = iteration;
-		pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
-			       &perf_test_args.vcpu_args[i]);
-	}
-
-	return vcpu_threads;
-}
-
-static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
-{
-	int i;
-
-	/* Set done to signal the vCPU threads to exit */
-	done = true;
-
-	for (i = 0; i < vcpus; i++)
-		pthread_join(vcpu_threads[i], NULL);
-}
-
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *params = arg;
 	struct kvm_vm *vm;
-	pthread_t *vcpu_threads;
 	int vcpus = params->vcpus;
 
 	vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1,
-				 params->backing_src);
+				 params->backing_src, !overlap_memory_access);
 
-	perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
-			      !overlap_memory_access);
-
-	vcpu_threads = create_vcpu_threads(vcpus);
+	perf_test_start_vcpu_threads(vcpus, vcpu_thread_main);
 
 	pr_info("\n");
 	access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
@@ -352,8 +316,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	mark_memory_idle(vm, vcpus);
 	access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
 
-	terminate_vcpu_threads(vcpu_threads, vcpus);
-	free(vcpu_threads);
+	/* Set done to signal the vCPU threads to exit */
+	done = true;
+
+	perf_test_join_vcpu_threads(vcpus);
 	perf_test_destroy_vm(vm);
 }
 

tools/testing/selftests/kvm/demand_paging_test.c

@@ -42,10 +42,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 static size_t demand_paging_size;
 static char *guest_data_prototype;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -68,8 +67,6 @@ static void *vcpu_worker(void *data)
 	ts_diff = timespec_elapsed(start);
 	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
-
-	return NULL;
 }
 
 static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
@@ -282,7 +279,6 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	pthread_t *uffd_handler_threads = NULL;
 	struct uffd_handler_args *uffd_args = NULL;
 	struct timespec start;
@@ -293,9 +289,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int r;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 p->src_type);
-
-	perf_test_args.wr_fract = 1;
+				 p->src_type, p->partition_vcpu_memory_access);
 
 	demand_paging_size = get_backing_src_pagesz(p->src_type);
 
@@ -304,12 +298,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		    "Failed to allocate buffer for guest data pattern");
 	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
 	if (p->uffd_mode) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
@@ -322,26 +310,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
 
 		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-			vm_paddr_t vcpu_gpa;
+			struct perf_test_vcpu_args *vcpu_args;
 			void *vcpu_hva;
 			void *vcpu_alias;
-			uint64_t vcpu_mem_size;
-
 
-			if (p->partition_vcpu_memory_access) {
-				vcpu_gpa = guest_test_phys_mem +
-					   (vcpu_id * guest_percpu_mem_size);
-				vcpu_mem_size = guest_percpu_mem_size;
-			} else {
-				vcpu_gpa = guest_test_phys_mem;
-				vcpu_mem_size = guest_percpu_mem_size * nr_vcpus;
-			}
-			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-				       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size);
+			vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
 
 			/* Cache the host addresses of the region */
-			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
-			vcpu_alias = addr_gpa2alias(vm, vcpu_gpa);
+			vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
+			vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa);
 
 			/*
 			 * Set up user fault fd to handle demand paging
@@ -355,32 +332,18 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 					    pipefds[vcpu_id * 2], p->uffd_mode,
 					    p->uffd_delay, &uffd_args[vcpu_id],
 					    vcpu_hva, vcpu_alias,
-					    vcpu_mem_size);
+					    vcpu_args->pages * perf_test_args.guest_page_size);
 		}
 	}
 
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
-
 	pr_info("Finished creating vCPUs and starting uffd threads\n");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
-
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 	pr_info("Started all vCPUs\n");
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-		PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
-	}
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	ts_diff = timespec_elapsed(start);
-
 	pr_info("All vCPU threads joined\n");
 
 	if (p->uffd_mode) {
@@ -404,7 +367,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_destroy_vm(vm);
 
 	free(guest_data_prototype);
-	free(vcpu_threads);
 	if (p->uffd_mode) {
 		free(uffd_handler_threads);
 		free(uffd_args);

tools/testing/selftests/kvm/dirty_log_perf_test.c

@@ -31,7 +31,7 @@ static bool host_quit;
 static int iteration;
 static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
 	struct kvm_vm *vm = perf_test_args.vm;
@@ -41,7 +41,6 @@ static void *vcpu_worker(void *data)
 	struct timespec ts_diff;
 	struct timespec total = (struct timespec){0};
 	struct timespec avg;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 
 	run = vcpu_state(vm, vcpu_id);
@@ -83,8 +82,6 @@ static void *vcpu_worker(void *data)
 	pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
 		vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
 		total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
-
-	return NULL;
 }
 
 struct test_params {
@@ -170,7 +167,6 @@ static void free_bitmaps(unsigned long *bitmaps[], int slots)
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
 	unsigned long **bitmaps;
 	uint64_t guest_num_pages;
@@ -186,9 +182,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct timespec clear_dirty_log_total = (struct timespec){0};
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
-				 p->slots, p->backing_src);
+				 p->slots, p->backing_src,
+				 p->partition_vcpu_memory_access);
 
-	perf_test_args.wr_fract = p->wr_fract;
+	perf_test_set_wr_fract(vm, p->wr_fract);
 
 	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
@@ -203,25 +200,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
-	sync_global_to_guest(vm, perf_test_args);
-
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
 		vcpu_last_completed_iteration[vcpu_id] = -1;
 
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	/* Allow the vCPUs to populate memory */
 	pr_debug("Starting iteration %d - Populating\n", iteration);
@@ -290,8 +277,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
+	perf_test_join_vcpu_threads(nr_vcpus);
 
 	avg = timespec_div(get_dirty_log_total, p->iterations);
 	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
@@ -306,7 +292,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	}
 
 	free_bitmaps(bitmaps, p->slots);
-	free(vcpu_threads);
 	perf_test_destroy_vm(vm);
 }
 

tools/testing/selftests/kvm/dirty_log_test.c

@@ -115,7 +115,7 @@ static void guest_code(void)
 			addr = guest_test_virt_mem;
 			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
-			addr &= ~(host_page_size - 1);
+			addr = align_down(addr, host_page_size);
 			*(uint64_t *)addr = READ_ONCE(iteration);
 		}
 
@@ -737,14 +737,14 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	if (!p->phys_offset) {
 		guest_test_phys_mem = (vm_get_max_gfn(vm) -
 				       guest_num_pages) * guest_page_size;
-		guest_test_phys_mem &= ~(host_page_size - 1);
+		guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size);
 	} else {
 		guest_test_phys_mem = p->phys_offset;
 	}
 
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
 #endif
 
 	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);

tools/testing/selftests/kvm/include/perf_test_util.h

@@ -8,6 +8,8 @@
 #ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
 #define SELFTEST_KVM_PERF_TEST_UTIL_H
 
+#include <pthread.h>
+
 #include "kvm_util.h"
 
 /* Default guest test virtual memory offset */
@@ -18,6 +20,7 @@
 #define PERF_TEST_MEM_SLOT_INDEX	1
 
 struct perf_test_vcpu_args {
+	uint64_t gpa;
 	uint64_t gva;
 	uint64_t pages;
 
@@ -27,7 +30,7 @@ struct perf_test_vcpu_args {
 
 struct perf_test_args {
 	struct kvm_vm *vm;
-	uint64_t host_page_size;
+	uint64_t gpa;
 	uint64_t guest_page_size;
 	int wr_fract;
 
@@ -36,19 +39,15 @@ struct perf_test_args {
 
 extern struct perf_test_args perf_test_args;
 
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-extern uint64_t guest_test_phys_mem;
-
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src);
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access);
 void perf_test_destroy_vm(struct kvm_vm *vm);
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access);
+
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
+void perf_test_join_vcpu_threads(int vcpus);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */

tools/testing/selftests/kvm/include/test_util.h

@@ -104,6 +104,7 @@ size_t get_trans_hugepagesz(void);
 size_t get_def_hugetlb_pagesz(void);
 const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
 size_t get_backing_src_pagesz(uint32_t i);
+bool is_backing_src_hugetlb(uint32_t i);
 void backing_src_help(const char *flag);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
 long get_run_delay(void);
@@ -117,4 +118,29 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t)
 	return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
 }
 
+/* Aligns x up to the next multiple of size. Size must be a power of 2. */
+static inline uint64_t align_up(uint64_t x, uint64_t size)
+{
+	uint64_t mask = size - 1;
+
+	TEST_ASSERT(size != 0 && !(size & (size - 1)),
+		    "size not a power of 2: %lu", size);
+	return ((x + mask) & ~mask);
+}
+
+static inline uint64_t align_down(uint64_t x, uint64_t size)
+{
+	uint64_t x_aligned_up = align_up(x, size);
+
+	if (x == x_aligned_up)
+		return x;
+	else
+		return x_aligned_up - size;
+}
+
+static inline void *align_ptr_up(void *x, size_t size)
+{
+	return (void *)align_up((unsigned long)x, size);
+}
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */

tools/testing/selftests/kvm/kvm_page_table_test.c

@@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 #ifdef __s390x__
 	alignment = max(0x100000, alignment);
 #endif
-	guest_test_phys_mem &= ~(alignment - 1);
+	guest_test_phys_mem = align_down(guest_test_virt_mem, alignment);
 
 	/* Set up the shared data structure test_args */
 	test_args.vm = vm;

tools/testing/selftests/kvm/lib/elf.c

@@ -157,8 +157,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
 			"memsize of 0,\n"
 			"  phdr index: %u p_memsz: 0x%" PRIx64,
 			n1, (uint64_t) phdr.p_memsz);
-		vm_vaddr_t seg_vstart = phdr.p_vaddr;
-		seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1);
+		vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size);
 		vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1;
 		seg_vend |= vm->page_size - 1;
 		size_t seg_size = seg_vend - seg_vstart + 1;

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -22,15 +22,6 @@
 
 static int vcpu_mmap_sz(void);
 
-/* Aligns x up to the next multiple of size. Size must be a power of 2. */
-static void *align(void *x, size_t size)
-{
-	size_t mask = size - 1;
-	TEST_ASSERT(size != 0 && !(size & (size - 1)),
-		    "size not a power of 2: %lu", size);
-	return (void *) (((size_t) x + mask) & ~mask);
-}
-
 int open_path_or_exit(const char *path, int flags)
 {
 	int fd;
@@ -191,15 +182,15 @@ const char *vm_guest_mode_string(uint32_t i)
 }
 
 const struct vm_guest_mode_params vm_guest_mode_params[] = {
-	{ 52, 48,  0x1000, 12 },
-	{ 52, 48, 0x10000, 16 },
-	{ 48, 48,  0x1000, 12 },
-	{ 48, 48, 0x10000, 16 },
-	{ 40, 48,  0x1000, 12 },
-	{ 40, 48, 0x10000, 16 },
-	{  0,  0,  0x1000, 12 },
-	{ 47, 64,  0x1000, 12 },
-	{ 44, 64,  0x1000, 12 },
+	[VM_MODE_P52V48_4K]	= { 52, 48,  0x1000, 12 },
+	[VM_MODE_P52V48_64K]	= { 52, 48, 0x10000, 16 },
+	[VM_MODE_P48V48_4K]	= { 48, 48,  0x1000, 12 },
+	[VM_MODE_P48V48_64K]	= { 48, 48, 0x10000, 16 },
+	[VM_MODE_P40V48_4K]	= { 40, 48,  0x1000, 12 },
+	[VM_MODE_P40V48_64K]	= { 40, 48, 0x10000, 16 },
+	[VM_MODE_PXXV48_4K]	= {  0,  0,  0x1000, 12 },
+	[VM_MODE_P47V64_4K]	= { 47, 64,  0x1000, 12 },
+	[VM_MODE_P44V64_4K]	= { 44, 64,  0x1000, 12 },
 };
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
@@ -879,9 +870,17 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	alignment = 1;
 #endif
 
+	/*
+	 * When using THP mmap is not guaranteed to returned a hugepage aligned
+	 * address so we have to pad the mmap. Padding is not needed for HugeTLB
+	 * because mmap will always return an address aligned to the HugeTLB
+	 * page size.
+	 */
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
+	ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
+
 	/* Add enough memory to align up if necessary */
 	if (alignment > 1)
 		region->mmap_size += alignment;
@@ -914,8 +913,13 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		    "test_malloc failed, mmap_start: %p errno: %i",
 		    region->mmap_start, errno);
 
+	TEST_ASSERT(!is_backing_src_hugetlb(src_type) ||
+		    region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz),
+		    "mmap_start %p is not aligned to HugeTLB page size 0x%lx",
+		    region->mmap_start, backing_src_pagesz);
+
 	/* Align host address */
-	region->host_mem = align(region->mmap_start, alignment);
+	region->host_mem = align_ptr_up(region->mmap_start, alignment);
 
 	/* As needed perform madvise */
 	if ((src_type == VM_MEM_SRC_ANONYMOUS ||
@@ -958,7 +962,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			    "mmap of alias failed, errno: %i", errno);
 
 		/* Align host alias address */
-		region->host_alias = align(region->mmap_alias, alignment);
+		region->host_alias = align_ptr_up(region->mmap_alias, alignment);
 	}
 }
 

tools/testing/selftests/kvm/lib/perf_test_util.c

@@ -10,21 +10,40 @@
 
 struct perf_test_args perf_test_args;
 
-uint64_t guest_test_phys_mem;
-
 /*
  * Guest virtual memory offset of the testing memory slot.
  * Must not conflict with identity mapped test code.
  */
 static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
 
+struct vcpu_thread {
+	/* The id of the vCPU. */
+	int vcpu_id;
+
+	/* The pthread backing the vCPU. */
+	pthread_t thread;
+
+	/* Set to true once the vCPU thread is up and running. */
+	bool running;
+};
+
+/* The vCPU threads involved in this test. */
+static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
+
+/* The function run by each vCPU thread, as provided by the test. */
+static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
+
+/* Set to true once all vCPU threads are up and running. */
+static bool all_vcpu_threads_running;
+
 /*
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
  */
 static void guest_code(uint32_t vcpu_id)
 {
-	struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
 	uint64_t gva;
 	uint64_t pages;
 	int i;
@@ -37,9 +56,9 @@ static void guest_code(uint32_t vcpu_id)
 
 	while (true) {
 		for (i = 0; i < pages; i++) {
-			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+			uint64_t addr = gva + (i * pta->guest_page_size);
 
-			if (i % perf_test_args.wr_fract == 0)
+			if (i % pta->wr_fract == 0)
 				*(uint64_t *)addr = 0x0123456789ABCDEF;
 			else
 				READ_ONCE(*(uint64_t *)addr);
@@ -49,35 +68,81 @@ static void guest_code(uint32_t vcpu_id)
 	}
 }
 
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
+			   uint64_t vcpu_memory_bytes,
+			   bool partition_vcpu_memory_access)
+{
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args;
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vcpu_args = &pta->vcpu_args[vcpu_id];
+
+		vcpu_args->vcpu_id = vcpu_id;
+		if (partition_vcpu_memory_access) {
+			vcpu_args->gva = guest_test_virt_mem +
+					 (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->pages = vcpu_memory_bytes /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
+		} else {
+			vcpu_args->gva = guest_test_virt_mem;
+			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa;
+		}
+
+		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			 vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
+			 (vcpu_args->pages * pta->guest_page_size));
+	}
+}
+
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src)
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access)
 {
+	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
 	uint64_t guest_num_pages;
+	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
 	int i;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	perf_test_args.host_page_size = getpagesize();
-	perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
+	/* By default vCPUs will write to memory. */
+	pta->wr_fract = 1;
+
+	/*
+	 * Snapshot the non-huge page size.  This is used by the guest code to
+	 * access/dirty pages at the logging granularity.
+	 */
+	pta->guest_page_size = vm_guest_mode_params[mode].page_size;
 
 	guest_num_pages = vm_adjust_num_guest_pages(mode,
-				(vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size);
+				(vcpus * vcpu_memory_bytes) / pta->guest_page_size);
 
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0,
 		    "Guest memory size is not host page size aligned.");
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0,
 		    "Guest memory size is not guest page size aligned.");
 	TEST_ASSERT(guest_num_pages % slots == 0,
 		    "Guest memory cannot be evenly divided into %d slots.",
 		    slots);
 
+	/*
+	 * Pass guest_num_pages to populate the page tables for test memory.
+	 * The memory is also added to memslot 0, but that's a benign side
+	 * effect as KVM allows aliasing HVAs in meslots.
+	 */
 	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
-				  0, guest_code, NULL);
+				  guest_num_pages, 0, guest_code, NULL);
 
-	perf_test_args.vm = vm;
+	pta->vm = vm;
 
 	/*
 	 * If there should be more memory in the guest test region than there
@@ -90,20 +155,18 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
 		    vcpu_memory_bytes);
 
-	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      perf_test_args.guest_page_size;
-	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+	pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size;
+	pta->gpa = align_down(pta->gpa, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	pta->gpa = align_down(pta->gpa, 1 << 20);
 #endif
-	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+	pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
 
 	/* Add extra memory slots for testing */
 	for (i = 0; i < slots; i++) {
 		uint64_t region_pages = guest_num_pages / slots;
-		vm_paddr_t region_start = guest_test_phys_mem +
-			region_pages * perf_test_args.guest_page_size * i;
+		vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i;
 
 		vm_userspace_mem_region_add(vm, backing_src, region_start,
 					    PERF_TEST_MEM_SLOT_INDEX + i,
@@ -111,10 +174,15 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	}
 
 	/* Do mapping for the demand paging memory slot */
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages);
+	virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages);
+
+	perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
 
 	ucall_init(vm, NULL);
 
+	/* Export the shared variables to the guest. */
+	sync_global_to_guest(vm, perf_test_args);
+
 	return vm;
 }
 
@@ -124,36 +192,60 @@ void perf_test_destroy_vm(struct kvm_vm *vm)
 	kvm_vm_free(vm);
 }
 
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access)
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
+{
+	perf_test_args.wr_fract = wr_fract;
+	sync_global_to_guest(vm, perf_test_args);
+}
+
+static void *vcpu_thread_main(void *data)
+{
+	struct vcpu_thread *vcpu = data;
+
+	WRITE_ONCE(vcpu->running, true);
+
+	/*
+	 * Wait for all vCPU threads to be up and running before calling the test-
+	 * provided vCPU thread function. This prevents thread creation (which
+	 * requires taking the mmap_sem in write mode) from interfering with the
+	 * guest faulting in its memory.
+	 */
+	while (!READ_ONCE(all_vcpu_threads_running))
+		;
+
+	vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]);
+
+	return NULL;
+}
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *))
 {
-	vm_paddr_t vcpu_gpa;
-	struct perf_test_vcpu_args *vcpu_args;
 	int vcpu_id;
 
+	vcpu_thread_fn = vcpu_fn;
+	WRITE_ONCE(all_vcpu_threads_running, false);
+
 	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+		struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id];
 
-		vcpu_args->vcpu_id = vcpu_id;
-		if (partition_vcpu_memory_access) {
-			vcpu_args->gva = guest_test_virt_mem +
-					 (vcpu_id * vcpu_memory_bytes);
-			vcpu_args->pages = vcpu_memory_bytes /
-					   perf_test_args.guest_page_size;
-			vcpu_gpa = guest_test_phys_mem +
-				   (vcpu_id * vcpu_memory_bytes);
-		} else {
-			vcpu_args->gva = guest_test_virt_mem;
-			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
-					   perf_test_args.guest_page_size;
-			vcpu_gpa = guest_test_phys_mem;
-		}
+		vcpu->vcpu_id = vcpu_id;
+		WRITE_ONCE(vcpu->running, false);
 
-		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+		pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu);
+	}
 
-		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			 vcpu_id, vcpu_gpa, vcpu_gpa +
-			 (vcpu_args->pages * perf_test_args.guest_page_size));
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		while (!READ_ONCE(vcpu_threads[vcpu_id].running))
+			;
 	}
+
+	WRITE_ONCE(all_vcpu_threads_running, true);
+}
+
+void perf_test_join_vcpu_threads(int vcpus)
+{
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+		pthread_join(vcpu_threads[vcpu_id].thread, NULL);
 }

tools/testing/selftests/kvm/lib/test_util.c

@@ -283,6 +283,11 @@ size_t get_backing_src_pagesz(uint32_t i)
 	}
 }
 
+bool is_backing_src_hugetlb(uint32_t i)
+{
+	return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB);
+}
+
 static void print_available_backing_src_types(const char *prefix)
 {
 	int i;

tools/testing/selftests/kvm/memslot_modification_stress_test.c

@@ -36,11 +36,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 
 static bool run_vcpus = true;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args =
-		(struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -59,8 +57,6 @@ static void *vcpu_worker(void *data)
 			    "Invalid guest sync status: exit_reason=%s\n",
 			    exit_reason_str(run->exit_reason));
 	}
-
-	return NULL;
 }
 
 struct memslot_antagonist_args {
@@ -80,7 +76,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
 	 * Add the dummy memslot just below the perf_test_util memslot, which is
 	 * at the top of the guest physical address space.
 	 */
-	gpa = guest_test_phys_mem - pages * vm_get_page_size(vm);
+	gpa = perf_test_args.gpa - pages * vm_get_page_size(vm);
 
 	for (i = 0; i < nr_modifications; i++) {
 		usleep(delay);
@@ -100,29 +96,15 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
-	int vcpu_id;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 VM_MEM_SRC_ANONYMOUS);
-
-	perf_test_args.wr_fract = 1;
-
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
+				 VM_MEM_SRC_ANONYMOUS,
+				 p->partition_vcpu_memory_access);
 
 	pr_info("Finished creating vCPUs\n");
 
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	pr_info("Started all vCPUs\n");
 
@@ -131,16 +113,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	run_vcpus = false;
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	pr_info("All vCPU threads joined\n");
 
-	ucall_uninit(vm);
-	kvm_vm_free(vm);
-
-	free(vcpu_threads);
+	perf_test_destroy_vm(vm);
 }
 
 static void help(char *name)

tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c

@@ -24,8 +24,12 @@
 
 #define PVTIME_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE)
 #define RUNSTATE_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_ADDR	(SHINFO_REGION_GPA + 0x40)
 
 #define RUNSTATE_VADDR	(SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_VADDR	(SHINFO_REGION_GVA + 0x40)
+
+#define EVTCHN_VECTOR	0x10
 
 static struct kvm_vm *vm;
 
@@ -56,15 +60,44 @@ struct vcpu_runstate_info {
     uint64_t time[4];
 };
 
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+struct vcpu_info {
+        uint8_t evtchn_upcall_pending;
+        uint8_t evtchn_upcall_mask;
+        unsigned long evtchn_pending_sel;
+        struct arch_vcpu_info arch;
+        struct pvclock_vcpu_time_info time;
+}; /* 64 bytes (x86) */
+
 #define RUNSTATE_running  0
 #define RUNSTATE_runnable 1
 #define RUNSTATE_blocked  2
 #define RUNSTATE_offline  3
 
+static void evtchn_handler(struct ex_regs *regs)
+{
+	struct vcpu_info *vi = (void *)VCPU_INFO_VADDR;
+	vi->evtchn_upcall_pending = 0;
+
+	GUEST_SYNC(0x20);
+}
+
 static void guest_code(void)
 {
 	struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
 
+	__asm__ __volatile__(
+		"sti\n"
+		"nop\n"
+	);
+
+	/* Trigger an interrupt injection */
+	GUEST_SYNC(0);
+
 	/* Test having the host set runstates manually */
 	GUEST_SYNC(RUNSTATE_runnable);
 	GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0);
@@ -153,7 +186,7 @@ int main(int argc, char *argv[])
 
 	struct kvm_xen_vcpu_attr vi = {
 		.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO,
-		.u.gpa = SHINFO_REGION_GPA + 0x40,
+		.u.gpa = VCPU_INFO_ADDR,
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi);
 
@@ -163,6 +196,16 @@ int main(int argc, char *argv[])
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock);
 
+	struct kvm_xen_hvm_attr vec = {
+		.type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR,
+		.u.vector = EVTCHN_VECTOR,
+	};
+	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler);
+
 	if (do_runstate_tests) {
 		struct kvm_xen_vcpu_attr st = {
 			.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
@@ -171,9 +214,14 @@ int main(int argc, char *argv[])
 		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
 	}
 
+	struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
+	vinfo->evtchn_upcall_pending = 0;
+
 	struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);
 	rs->state = 0x5a;
 
+	bool evtchn_irq_expected = false;
+
 	for (;;) {
 		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
 		struct ucall uc;
@@ -193,16 +241,21 @@ int main(int argc, char *argv[])
 			struct kvm_xen_vcpu_attr rst;
 			long rundelay;
 
-			/* If no runstate support, bail out early */
-			if (!do_runstate_tests)
-				goto done;
-
-			TEST_ASSERT(rs->state_entry_time == rs->time[0] +
-				    rs->time[1] + rs->time[2] + rs->time[3],
-				    "runstate times don't add up");
+			if (do_runstate_tests)
+				TEST_ASSERT(rs->state_entry_time == rs->time[0] +
+					    rs->time[1] + rs->time[2] + rs->time[3],
+					    "runstate times don't add up");
 
 			switch (uc.args[1]) {
-			case RUNSTATE_running...RUNSTATE_offline:
+			case 0:
+				evtchn_irq_expected = true;
+				vinfo->evtchn_upcall_pending = 1;
+				break;
+
+			case RUNSTATE_runnable...RUNSTATE_offline:
+				TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen");
+				if (!do_runstate_tests)
+					goto done;
 				rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
 				rst.u.runstate.state = uc.args[1];
 				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
@@ -236,6 +289,10 @@ int main(int argc, char *argv[])
 					sched_yield();
 				} while (get_run_delay() < rundelay);
 				break;
+			case 0x20:
+				TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ");
+				evtchn_irq_expected = false;
+				break;
 			}
 			break;
 		}

virt/kvm/kvm_main.c

@@ -2548,72 +2548,36 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache)
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty)
 {
 	if (pfn == 0)
 		return;
 
-	if (cache)
-		cache->pfn = cache->gfn = 0;
-
 	if (dirty)
 		kvm_release_pfn_dirty(pfn);
 	else
 		kvm_release_pfn_clean(pfn);
 }
 
-static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn,
-				 struct gfn_to_pfn_cache *cache, u64 gen)
-{
-	kvm_release_pfn(cache->pfn, cache->dirty, cache);
-
-	cache->pfn = gfn_to_pfn_memslot(slot, gfn);
-	cache->gfn = gfn;
-	cache->dirty = false;
-	cache->generation = gen;
-}
-
-static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
-			 struct kvm_host_map *map,
-			 struct gfn_to_pfn_cache *cache,
-			 bool atomic)
+int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
 {
 	kvm_pfn_t pfn;
 	void *hva = NULL;
 	struct page *page = KVM_UNMAPPED_PAGE;
-	struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn);
-	u64 gen = slots->generation;
 
 	if (!map)
 		return -EINVAL;
 
-	if (cache) {
-		if (!cache->pfn || cache->gfn != gfn ||
-			cache->generation != gen) {
-			if (atomic)
-				return -EAGAIN;
-			kvm_cache_gfn_to_pfn(slot, gfn, cache, gen);
-		}
-		pfn = cache->pfn;
-	} else {
-		if (atomic)
-			return -EAGAIN;
-		pfn = gfn_to_pfn_memslot(slot, gfn);
-	}
+	pfn = gfn_to_pfn(vcpu->kvm, gfn);
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
 
 	if (pfn_valid(pfn)) {
 		page = pfn_to_page(pfn);
-		if (atomic)
-			hva = kmap_atomic(page);
-		else
-			hva = kmap(page);
+		hva = kmap(page);
 #ifdef CONFIG_HAS_IOMEM
-	} else if (!atomic) {
-		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
 	} else {
-		return -EINVAL;
+		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
 #endif
 	}
 
@@ -2627,27 +2591,9 @@ static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
 
 	return 0;
 }
-
-int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
-		struct gfn_to_pfn_cache *cache, bool atomic)
-{
-	return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map,
-			cache, atomic);
-}
-EXPORT_SYMBOL_GPL(kvm_map_gfn);
-
-int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
-{
-	return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map,
-		NULL, false);
-}
 EXPORT_SYMBOL_GPL(kvm_vcpu_map);
 
-static void __kvm_unmap_gfn(struct kvm *kvm,
-			struct kvm_memory_slot *memslot,
-			struct kvm_host_map *map,
-			struct gfn_to_pfn_cache *cache,
-			bool dirty, bool atomic)
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
 {
 	if (!map)
 		return;
@@ -2655,45 +2601,21 @@ static void __kvm_unmap_gfn(struct kvm *kvm,
 	if (!map->hva)
 		return;
 
-	if (map->page != KVM_UNMAPPED_PAGE) {
-		if (atomic)
-			kunmap_atomic(map->hva);
-		else
-			kunmap(map->page);
-	}
+	if (map->page != KVM_UNMAPPED_PAGE)
+		kunmap(map->page);
 #ifdef CONFIG_HAS_IOMEM
-	else if (!atomic)
-		memunmap(map->hva);
 	else
-		WARN_ONCE(1, "Unexpected unmapping in atomic context");
+		memunmap(map->hva);
 #endif
 
 	if (dirty)
-		mark_page_dirty_in_slot(kvm, memslot, map->gfn);
+		kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
 
-	if (cache)
-		cache->dirty |= dirty;
-	else
-		kvm_release_pfn(map->pfn, dirty, NULL);
+	kvm_release_pfn(map->pfn, dirty);
 
 	map->hva = NULL;
 	map->page = NULL;
 }
-
-int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, 
-		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
-{
-	__kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map,
-			cache, dirty, atomic);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
-
-void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
-{
-	__kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn),
-			map, NULL, dirty, false);
-}
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)