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

Pull kvm fixes from Paolo Bonzini:
 "All bugfixes except for a couple cleanup patches"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: VMX: Remove vcpu_vmx's defunct copy of host_pkru
  KVM: x86: allow TSC to differ by NTP correction bounds without TSC scaling
  KVM: X86: Fix MSR range of APIC registers in X2APIC mode
  KVM: VMX: Stop context switching MSR_IA32_UMWAIT_CONTROL
  KVM: nVMX: Plumb L2 GPA through to PML emulation
  KVM: x86/mmu: Avoid mixing gpa_t with gfn_t in walk_addr_generic()
  KVM: LAPIC: ensure APIC map is up to date on concurrent update requests
  kvm: lapic: fix broken vcpu hotplug
  Revert "KVM: VMX: Micro-optimize vmexit time when not exposing PMU"
  KVM: VMX: Add helpers to identify interrupt type from intr_info
  kvm/svm: disable KCSAN for svm_vcpu_run()
  KVM: MIPS: Fix a build error for !CPU_LOONGSON64

arch/mips/kvm/mips.c

@@ -67,7 +67,9 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("vz_ghfc", vz_ghfc_exits),
 	VCPU_STAT("vz_gpa", vz_gpa_exits),
 	VCPU_STAT("vz_resvd", vz_resvd_exits),
+#ifdef CONFIG_CPU_LOONGSON64
 	VCPU_STAT("vz_cpucfg", vz_cpucfg_exits),
+#endif
 #endif
 	VCPU_STAT("halt_successful_poll", halt_successful_poll),
 	VCPU_STAT("halt_attempted_poll", halt_attempted_poll),

arch/x86/include/asm/kvm_host.h

@@ -943,7 +943,7 @@ struct kvm_arch {
 	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
 	struct kvm_apic_map *apic_map;
-	bool apic_map_dirty;
+	atomic_t apic_map_dirty;
 
 	bool apic_access_page_done;
 	unsigned long apicv_inhibit_reasons;
@@ -1220,7 +1220,7 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
-	int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;

arch/x86/include/asm/mwait.h

@@ -25,8 +25,6 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-u32 get_umwait_control_msr(void);
-
 static inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
 {

arch/x86/kernel/cpu/umwait.c

@@ -18,12 +18,6 @@
  */
 static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
 
-u32 get_umwait_control_msr(void)
-{
-	return umwait_control_cached;
-}
-EXPORT_SYMBOL_GPL(get_umwait_control_msr);
-
 /*
  * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by
  * hardware or BIOS before kernel boot.

arch/x86/kvm/lapic.c

@@ -169,6 +169,18 @@ static void kvm_apic_map_free(struct rcu_head *rcu)
 	kvfree(map);
 }
 
+/*
+ * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock.
+ *
+ * DIRTY -> UPDATE_IN_PROGRESS and UPDATE_IN_PROGRESS -> CLEAN happen with
+ * apic_map_lock_held.
+ */
+enum {
+	CLEAN,
+	UPDATE_IN_PROGRESS,
+	DIRTY
+};
+
 void kvm_recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
@@ -176,17 +188,17 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 	int i;
 	u32 max_id = 255; /* enough space for any xAPIC ID */
 
-	if (!kvm->arch.apic_map_dirty) {
-		/*
-		 * Read kvm->arch.apic_map_dirty before
-		 * kvm->arch.apic_map
-		 */
-		smp_rmb();
+	/* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map.  */
+	if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN)
 		return;
-	}
 
 	mutex_lock(&kvm->arch.apic_map_lock);
-	if (!kvm->arch.apic_map_dirty) {
+	/*
+	 * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map
+	 * (if clean) or the APIC registers (if dirty).
+	 */
+	if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty,
+				   DIRTY, UPDATE_IN_PROGRESS) == CLEAN) {
 		/* Someone else has updated the map. */
 		mutex_unlock(&kvm->arch.apic_map_lock);
 		return;
@@ -256,11 +268,11 @@ void kvm_recalculate_apic_map(struct kvm *kvm)
 			lockdep_is_held(&kvm->arch.apic_map_lock));
 	rcu_assign_pointer(kvm->arch.apic_map, new);
 	/*
-	 * Write kvm->arch.apic_map before
-	 * clearing apic->apic_map_dirty
+	 * Write kvm->arch.apic_map before clearing apic->apic_map_dirty.
+	 * If another update has come in, leave it DIRTY.
 	 */
-	smp_wmb();
-	kvm->arch.apic_map_dirty = false;
+	atomic_cmpxchg_release(&kvm->arch.apic_map_dirty,
+			       UPDATE_IN_PROGRESS, CLEAN);
 	mutex_unlock(&kvm->arch.apic_map_lock);
 
 	if (old)
@@ -282,20 +294,20 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
 		else
 			static_key_slow_inc(&apic_sw_disabled.key);
 
-		apic->vcpu->kvm->arch.apic_map_dirty = true;
+		atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 	}
 }
 
 static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id)
 {
 	kvm_lapic_set_reg(apic, APIC_ID, id << 24);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 {
 	kvm_lapic_set_reg(apic, APIC_LDR, id);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
@@ -311,7 +323,7 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
 
 	kvm_lapic_set_reg(apic, APIC_ID, id);
 	kvm_lapic_set_reg(apic, APIC_LDR, ldr);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
@@ -1976,7 +1988,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_DFR:
 		if (!apic_x2apic_mode(apic)) {
 			kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
-			apic->vcpu->kvm->arch.apic_map_dirty = true;
+			atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 		} else
 			ret = 1;
 		break;
@@ -2232,7 +2244,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 			static_key_slow_dec_deferred(&apic_hw_disabled);
 		} else {
 			static_key_slow_inc(&apic_hw_disabled.key);
-			vcpu->kvm->arch.apic_map_dirty = true;
+			atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 		}
 	}
 
@@ -2273,7 +2285,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	if (!apic)
 		return;
 
-	vcpu->kvm->arch.apic_map_dirty = false;
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
@@ -2567,6 +2578,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 	}
 	memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s));
 
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 	kvm_recalculate_apic_map(vcpu->kvm);
 	kvm_apic_set_version(vcpu);
 

arch/x86/kvm/mmu.h

@@ -222,7 +222,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 int kvm_mmu_post_init_vm(struct kvm *kvm);
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm);

arch/x86/kvm/mmu/mmu.c

@@ -1745,10 +1745,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
  * Emulate arch specific page modification logging for the
  * nested hypervisor
  */
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
 {
 	if (kvm_x86_ops.write_log_dirty)
-		return kvm_x86_ops.write_log_dirty(vcpu);
+		return kvm_x86_ops.write_log_dirty(vcpu, l2_gpa);
 
 	return 0;
 }

arch/x86/kvm/mmu/paging_tmpl.h

@@ -235,7 +235,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte)
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
-					     int write_fault)
+					     gpa_t addr, int write_fault)
 {
 	unsigned level, index;
 	pt_element_t pte, orig_pte;
@@ -260,7 +260,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
 #if PTTYPE == PTTYPE_EPT
-			if (kvm_arch_write_log_dirty(vcpu))
+			if (kvm_arch_write_log_dirty(vcpu, addr))
 				return -EINVAL;
 #endif
 			pte |= PT_GUEST_DIRTY_MASK;
@@ -360,7 +360,6 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	++walker->level;
 
 	do {
-		gfn_t real_gfn;
 		unsigned long host_addr;
 
 		pt_access = pte_access;
@@ -375,7 +374,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
-		real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
+		real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
 					      nested_access,
 					      &walker->fault);
 
@@ -389,12 +388,10 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 		 * information to fix the exit_qualification or exit_info_1
 		 * fields.
 		 */
-		if (unlikely(real_gfn == UNMAPPED_GVA))
+		if (unlikely(real_gpa == UNMAPPED_GVA))
 			return 0;
 
-		real_gfn = gpa_to_gfn(real_gfn);
-
-		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn,
+		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa),
 					    &walker->pte_writable[walker->level - 1]);
 		if (unlikely(kvm_is_error_hva(host_addr)))
 			goto error;
@@ -457,7 +454,8 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
-		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
+		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker,
+							addr, write_fault);
 		if (unlikely(ret < 0))
 			goto error;
 		else if (ret)

arch/x86/kvm/svm/svm.c

@@ -3344,7 +3344,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 
 void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
 
-static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
+static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	fastpath_t exit_fastpath;
 	struct vcpu_svm *svm = to_svm(vcpu);

arch/x86/kvm/vmx/vmcs.h

@@ -72,11 +72,24 @@ struct loaded_vmcs {
 	struct vmcs_controls_shadow controls_shadow;
 };
 
+static inline bool is_intr_type(u32 intr_info, u32 type)
+{
+	const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK;
+
+	return (intr_info & mask) == (INTR_INFO_VALID_MASK | type);
+}
+
+static inline bool is_intr_type_n(u32 intr_info, u32 type, u8 vector)
+{
+	const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK |
+			 INTR_INFO_VECTOR_MASK;
+
+	return (intr_info & mask) == (INTR_INFO_VALID_MASK | type | vector);
+}
+
 static inline bool is_exception_n(u32 intr_info, u8 vector)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+	return is_intr_type_n(intr_info, INTR_TYPE_HARD_EXCEPTION, vector);
 }
 
 static inline bool is_debug(u32 intr_info)
@@ -106,28 +119,23 @@ static inline bool is_gp_fault(u32 intr_info)
 
 static inline bool is_machine_check(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
+	return is_exception_n(intr_info, MC_VECTOR);
 }
 
 /* Undocumented: icebp/int1 */
 static inline bool is_icebp(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+	return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION);
 }
 
 static inline bool is_nmi(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
+	return is_intr_type(intr_info, INTR_TYPE_NMI_INTR);
 }
 
 static inline bool is_external_intr(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
-		== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR);
+	return is_intr_type(intr_info, INTR_TYPE_EXT_INTR);
 }
 
 enum vmcs_field_width {

arch/x86/kvm/vmx/vmx.c

@@ -6606,23 +6606,6 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host, false);
 }
 
-static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx)
-{
-	u32 host_umwait_control;
-
-	if (!vmx_has_waitpkg(vmx))
-		return;
-
-	host_umwait_control = get_umwait_control_msr();
-
-	if (vmx->msr_ia32_umwait_control != host_umwait_control)
-		add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL,
-			vmx->msr_ia32_umwait_control,
-			host_umwait_control, false);
-	else
-		clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL);
-}
-
 static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6728,9 +6711,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	pt_guest_enter(vmx);
 
-	if (vcpu_to_pmu(vcpu)->version)
-		atomic_switch_perf_msrs(vmx);
-	atomic_switch_umwait_control_msr(vmx);
+	atomic_switch_perf_msrs(vmx);
 
 	if (enable_preemption_timer)
 		vmx_update_hv_timer(vcpu);
@@ -7501,11 +7482,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm)
 	kvm_flush_pml_buffers(kvm);
 }
 
-static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t gpa, dst;
+	gpa_t dst;
 
 	if (is_guest_mode(vcpu)) {
 		WARN_ON_ONCE(vmx->nested.pml_full);
@@ -7524,7 +7505,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
 			return 1;
 		}
 
-		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+		gpa &= ~0xFFFull;
 		dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index;
 
 		if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,

arch/x86/kvm/vmx/vmx.h

@@ -288,8 +288,6 @@ struct vcpu_vmx {
 
 	u64 current_tsc_ratio;
 
-	u32 host_pkru;
-
 	unsigned long host_debugctlmsr;
 
 	/*

arch/x86/kvm/x86.c

@@ -2856,7 +2856,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
 		return kvm_set_apic_base(vcpu, msr_info);
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSCDEADLINE:
 		kvm_set_lapic_tscdeadline_msr(vcpu, data);
@@ -3196,7 +3196,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_APICBASE:
 		msr_info->data = kvm_get_apic_base(vcpu);
 		break;
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
 	case MSR_IA32_TSCDEADLINE:
 		msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu);
@@ -4603,7 +4603,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EINVAL;
 		user_tsc_khz = (u32)arg;
 
-		if (user_tsc_khz >= kvm_max_guest_tsc_khz)
+		if (kvm_has_tsc_control &&
+		    user_tsc_khz >= kvm_max_guest_tsc_khz)
 			goto out;
 
 		if (user_tsc_khz == 0)