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

Pull KVM fixes from Paolo Bonzini:
 "s390:
   - SRCU fix

  PPC:
   - host crash fixes

  x86:
   - bugfixes, including making nested posted interrupts really work

  Generic:
   - tweaks to kvm_stat and to uevents"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: LAPIC: Fix reentrancy issues with preempt notifiers
  tools/kvm_stat: add '-f help' to get the available event list
  tools/kvm_stat: use variables instead of hard paths in help output
  KVM: nVMX: Fix loss of L2's NMI blocking state
  KVM: nVMX: Fix posted intr delivery when vcpu is in guest mode
  x86: irq: Define a global vector for nested posted interrupts
  KVM: x86: do mask out upper bits of PAE CR3
  KVM: make pid available for uevents without debugfs
  KVM: s390: take srcu lock when getting/setting storage keys
  KVM: VMX: remove unused field
  KVM: PPC: Book3S HV: Fix host crash on changing HPT size
  KVM: PPC: Book3S HV: Enable TM before accessing TM registers

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -164,8 +164,10 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
 		goto out;
 	}
 
-	if (kvm->arch.hpt.virt)
+	if (kvm->arch.hpt.virt) {
 		kvmppc_free_hpt(&kvm->arch.hpt);
+		kvmppc_rmap_reset(kvm);
+	}
 
 	err = kvmppc_allocate_hpt(&info, order);
 	if (err < 0)

arch/powerpc/kvm/book3s_hv.c

@@ -3211,6 +3211,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			run->fail_entry.hardware_entry_failure_reason = 0;
 			return -EINVAL;
 		}
+		/* Enable TM so we can read the TM SPRs */
+		mtmsr(mfmsr() | MSR_TM);
 		current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
 		current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
 		current->thread.tm_texasr = mfspr(SPRN_TEXASR);

arch/s390/kvm/kvm-s390.c

@@ -1324,7 +1324,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 {
 	uint8_t *keys;
 	uint64_t hva;
-	int i, r = 0;
+	int srcu_idx, i, r = 0;
 
 	if (args->flags != 0)
 		return -EINVAL;
@@ -1342,6 +1342,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 		return -ENOMEM;
 
 	down_read(&current->mm->mmap_sem);
+	srcu_idx = srcu_read_lock(&kvm->srcu);
 	for (i = 0; i < args->count; i++) {
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
 		if (kvm_is_error_hva(hva)) {
@@ -1353,6 +1354,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 		if (r)
 			break;
 	}
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	up_read(&current->mm->mmap_sem);
 
 	if (!r) {
@@ -1370,7 +1372,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 {
 	uint8_t *keys;
 	uint64_t hva;
-	int i, r = 0;
+	int srcu_idx, i, r = 0;
 
 	if (args->flags != 0)
 		return -EINVAL;
@@ -1396,6 +1398,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 		goto out;
 
 	down_read(&current->mm->mmap_sem);
+	srcu_idx = srcu_read_lock(&kvm->srcu);
 	for (i = 0; i < args->count; i++) {
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
 		if (kvm_is_error_hva(hva)) {
@@ -1413,6 +1416,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 		if (r)
 			break;
 	}
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	up_read(&current->mm->mmap_sem);
 out:
 	kvfree(keys);

arch/x86/entry/entry_64.S

@@ -705,6 +705,7 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR		x86_platform_ipi		smp_x86_platform_ipi
 #ifdef CONFIG_HAVE_KVM
 apicinterrupt3 POSTED_INTR_VECTOR		kvm_posted_intr_ipi		smp_kvm_posted_intr_ipi
 apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR	kvm_posted_intr_wakeup_ipi	smp_kvm_posted_intr_wakeup_ipi
+apicinterrupt3 POSTED_INTR_NESTED_VECTOR	kvm_posted_intr_nested_ipi	smp_kvm_posted_intr_nested_ipi
 #endif
 
 #ifdef CONFIG_X86_MCE_THRESHOLD

arch/x86/include/asm/entry_arch.h

@@ -25,6 +25,8 @@ BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
 		 smp_kvm_posted_intr_ipi)
 BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR,
 		 smp_kvm_posted_intr_wakeup_ipi)
+BUILD_INTERRUPT3(kvm_posted_intr_nested_ipi, POSTED_INTR_NESTED_VECTOR,
+		 smp_kvm_posted_intr_nested_ipi)
 #endif
 
 /*

arch/x86/include/asm/hardirq.h

@@ -15,6 +15,7 @@ typedef struct {
 #ifdef CONFIG_HAVE_KVM
 	unsigned int kvm_posted_intr_ipis;
 	unsigned int kvm_posted_intr_wakeup_ipis;
+	unsigned int kvm_posted_intr_nested_ipis;
 #endif
 	unsigned int x86_platform_ipis;	/* arch dependent */
 	unsigned int apic_perf_irqs;

arch/x86/include/asm/hw_irq.h

@@ -30,6 +30,7 @@ extern asmlinkage void apic_timer_interrupt(void);
 extern asmlinkage void x86_platform_ipi(void);
 extern asmlinkage void kvm_posted_intr_ipi(void);
 extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
+extern asmlinkage void kvm_posted_intr_nested_ipi(void);
 extern asmlinkage void error_interrupt(void);
 extern asmlinkage void irq_work_interrupt(void);
 
@@ -62,6 +63,7 @@ extern void trace_call_function_single_interrupt(void);
 #define trace_reboot_interrupt  reboot_interrupt
 #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
 #define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi
+#define trace_kvm_posted_intr_nested_ipi kvm_posted_intr_nested_ipi
 #endif /* CONFIG_TRACING */
 
 #ifdef	CONFIG_X86_LOCAL_APIC

arch/x86/include/asm/irq_vectors.h

@@ -83,7 +83,6 @@
  */
 #define X86_PLATFORM_IPI_VECTOR		0xf7
 
-#define POSTED_INTR_WAKEUP_VECTOR	0xf1
 /*
  * IRQ work vector:
  */
@@ -98,6 +97,8 @@
 /* Vector for KVM to deliver posted interrupt IPI */
 #ifdef CONFIG_HAVE_KVM
 #define POSTED_INTR_VECTOR		0xf2
+#define POSTED_INTR_WAKEUP_VECTOR	0xf1
+#define POSTED_INTR_NESTED_VECTOR	0xf0
 #endif
 
 /*

arch/x86/kernel/irq.c

@@ -155,6 +155,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
 	seq_puts(p, "  Posted-interrupt notification event\n");
 
+	seq_printf(p, "%*s: ", prec, "NPI");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ",
+			   irq_stats(j)->kvm_posted_intr_nested_ipis);
+	seq_puts(p, "  Nested posted-interrupt event\n");
+
 	seq_printf(p, "%*s: ", prec, "PIW");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ",
@@ -313,6 +319,19 @@ __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
 	exiting_irq();
 	set_irq_regs(old_regs);
 }
+
+/*
+ * Handler for POSTED_INTERRUPT_NESTED_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	entering_ack_irq();
+	inc_irq_stat(kvm_posted_intr_nested_ipis);
+	exiting_irq();
+	set_irq_regs(old_regs);
+}
 #endif
 
 __visible void __irq_entry smp_trace_x86_platform_ipi(struct pt_regs *regs)

arch/x86/kernel/irqinit.c

@@ -150,6 +150,8 @@ static void __init apic_intr_init(void)
 	alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
 	/* IPI for KVM to deliver interrupt to wake up tasks */
 	alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi);
+	/* IPI for KVM to deliver nested posted interrupt */
+	alloc_intr_gate(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi);
 #endif
 
 	/* IPI vectors for APIC spurious and error interrupts */

arch/x86/kvm/lapic.c

@@ -1495,11 +1495,10 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
 
 static void cancel_hv_timer(struct kvm_lapic *apic)
 {
+	WARN_ON(preemptible());
 	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
-	preempt_disable();
 	kvm_x86_ops->cancel_hv_timer(apic->vcpu);
 	apic->lapic_timer.hv_timer_in_use = false;
-	preempt_enable();
 }
 
 static bool start_hv_timer(struct kvm_lapic *apic)
@@ -1507,6 +1506,7 @@ static bool start_hv_timer(struct kvm_lapic *apic)
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 	int r;
 
+	WARN_ON(preemptible());
 	if (!kvm_x86_ops->set_hv_timer)
 		return false;
 
@@ -1538,6 +1538,8 @@ static bool start_hv_timer(struct kvm_lapic *apic)
 static void start_sw_timer(struct kvm_lapic *apic)
 {
 	struct kvm_timer *ktimer = &apic->lapic_timer;
+
+	WARN_ON(preemptible());
 	if (apic->lapic_timer.hv_timer_in_use)
 		cancel_hv_timer(apic);
 	if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending))
@@ -1552,15 +1554,20 @@ static void start_sw_timer(struct kvm_lapic *apic)
 
 static void restart_apic_timer(struct kvm_lapic *apic)
 {
+	preempt_disable();
 	if (!start_hv_timer(apic))
 		start_sw_timer(apic);
+	preempt_enable();
 }
 
 void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	WARN_ON(!apic->lapic_timer.hv_timer_in_use);
+	preempt_disable();
+	/* If the preempt notifier has already run, it also called apic_timer_expired */
+	if (!apic->lapic_timer.hv_timer_in_use)
+		goto out;
 	WARN_ON(swait_active(&vcpu->wq));
 	cancel_hv_timer(apic);
 	apic_timer_expired(apic);
@@ -1569,6 +1576,8 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu)
 		advance_periodic_target_expiration(apic);
 		restart_apic_timer(apic);
 	}
+out:
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer);
 
@@ -1582,9 +1591,11 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
+	preempt_disable();
 	/* Possibly the TSC deadline timer is not enabled yet */
 	if (apic->lapic_timer.hv_timer_in_use)
 		start_sw_timer(apic);
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer);
 

arch/x86/kvm/vmx.c

@@ -563,7 +563,6 @@ struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
 	u8                    fail;
-	bool                  nmi_known_unmasked;
 	u32                   exit_intr_info;
 	u32                   idt_vectoring_info;
 	ulong                 rflags;
@@ -4988,9 +4987,12 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	}
 }
 
-static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
+static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
+						     bool nested)
 {
 #ifdef CONFIG_SMP
+	int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
+
 	if (vcpu->mode == IN_GUEST_MODE) {
 		struct vcpu_vmx *vmx = to_vmx(vcpu);
 
@@ -5008,8 +5010,7 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
 		 */
 		WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
 
-		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
-				POSTED_INTR_VECTOR);
+		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
 		return true;
 	}
 #endif
@@ -5024,7 +5025,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 	if (is_guest_mode(vcpu) &&
 	    vector == vmx->nested.posted_intr_nv) {
 		/* the PIR and ON have been set by L1. */
-		kvm_vcpu_trigger_posted_interrupt(vcpu);
+		kvm_vcpu_trigger_posted_interrupt(vcpu, true);
 		/*
 		 * If a posted intr is not recognized by hardware,
 		 * we will accomplish it in the next vmentry.
@@ -5058,7 +5059,7 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 	if (pi_test_and_set_on(&vmx->pi_desc))
 		return;
 
-	if (!kvm_vcpu_trigger_posted_interrupt(vcpu))
+	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
 }
 
@@ -10041,6 +10042,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			     vmcs12->vm_entry_instruction_len);
 		vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
 			     vmcs12->guest_interruptibility_info);
+		vmx->loaded_vmcs->nmi_known_unmasked =
+			!(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
 	} else {
 		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
 	}
@@ -10065,13 +10068,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	/* Posted interrupts setting is only taken from vmcs12.  */
 	if (nested_cpu_has_posted_intr(vmcs12)) {
-		/*
-		 * Note that we use L0's vector here and in
-		 * vmx_deliver_nested_posted_interrupt.
-		 */
 		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
 		vmx->nested.pi_pending = false;
-		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
+		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
 	} else {
 		exec_control &= ~PIN_BASED_POSTED_INTR;
 	}
@@ -10942,7 +10941,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 		 */
 		vmx_flush_tlb(vcpu);
 	}
-
+	/* Restore posted intr vector. */
+	if (nested_cpu_has_posted_intr(vmcs12))
+		vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
 
 	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
 	vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);

arch/x86/kvm/x86.c

@@ -597,8 +597,8 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
 		      (unsigned long *)&vcpu->arch.regs_avail))
 		return true;
 
-	gfn = (kvm_read_cr3(vcpu) & ~31ul) >> PAGE_SHIFT;
-	offset = (kvm_read_cr3(vcpu) & ~31ul) & (PAGE_SIZE - 1);
+	gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT;
+	offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1);
 	r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
 				       PFERR_USER_MASK | PFERR_WRITE_MASK);
 	if (r < 0)

include/linux/kvm_host.h

@@ -445,6 +445,7 @@ struct kvm {
 	struct kvm_stat_data **debugfs_stat_data;
 	struct srcu_struct srcu;
 	struct srcu_struct irq_srcu;
+	pid_t userspace_pid;
 };
 
 #define kvm_err(fmt, ...) \

tools/kvm/kvm_stat/kvm_stat

@@ -474,7 +474,7 @@ class Provider(object):
     @staticmethod
     def is_field_wanted(fields_filter, field):
         """Indicate whether field is valid according to fields_filter."""
-        if not fields_filter:
+        if not fields_filter or fields_filter == "help":
             return True
         return re.match(fields_filter, field) is not None
 
@@ -1413,8 +1413,8 @@ performance.
 
 Requirements:
 - Access to:
-    /sys/kernel/debug/kvm
-    /sys/kernel/debug/trace/events/*
+    %s
+    %s/events/*
     /proc/pid/task
 - /proc/sys/kernel/perf_event_paranoid < 1 if user has no
   CAP_SYS_ADMIN and perf events are used.
@@ -1434,7 +1434,7 @@ Interactive Commands:
    s     set update interval
    x     toggle reporting of stats for individual child trace events
 Press any other key to refresh statistics immediately.
-"""
+""" % (PATH_DEBUGFS_KVM, PATH_DEBUGFS_TRACING)
 
     class PlainHelpFormatter(optparse.IndentedHelpFormatter):
         def format_description(self, description):
@@ -1496,7 +1496,8 @@ Press any other key to refresh statistics immediately.
                          action='store',
                          default=DEFAULT_REGEX,
                          dest='fields',
-                         help='fields to display (regex)',
+                         help='''fields to display (regex)
+                                 "-f help" for a list of available events''',
                          )
     optparser.add_option('-p', '--pid',
                          action='store',
@@ -1559,6 +1560,17 @@ def main():
 
     stats = Stats(options)
 
+    if options.fields == "help":
+        event_list = "\n"
+        s = stats.get()
+        for key in s.keys():
+            if key.find('(') != -1:
+                key = key[0:key.find('(')]
+            if event_list.find('\n' + key + '\n') == -1:
+                event_list += key + '\n'
+        sys.stdout.write(event_list)
+        return ""
+
     if options.log:
         log(stats)
     elif not options.once:

virt/kvm/kvm_main.c

@@ -3883,7 +3883,6 @@ static const struct file_operations *stat_fops[] = {
 static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 {
 	struct kobj_uevent_env *env;
-	char *tmp, *pathbuf = NULL;
 	unsigned long long created, active;
 
 	if (!kvm_dev.this_device || !kvm)
@@ -3907,38 +3906,28 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
 	add_uevent_var(env, "CREATED=%llu", created);
 	add_uevent_var(env, "COUNT=%llu", active);
 
-	if (type == KVM_EVENT_CREATE_VM)
+	if (type == KVM_EVENT_CREATE_VM) {
 		add_uevent_var(env, "EVENT=create");
-	else if (type == KVM_EVENT_DESTROY_VM)
+		kvm->userspace_pid = task_pid_nr(current);
+	} else if (type == KVM_EVENT_DESTROY_VM) {
 		add_uevent_var(env, "EVENT=destroy");
+	}
+	add_uevent_var(env, "PID=%d", kvm->userspace_pid);
 
 	if (kvm->debugfs_dentry) {
-		char p[ITOA_MAX_LEN];
-
-		snprintf(p, sizeof(p), "%s", kvm->debugfs_dentry->d_name.name);
-		tmp = strchrnul(p + 1, '-');
-		*tmp = '\0';
-		add_uevent_var(env, "PID=%s", p);
-		pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
-		if (pathbuf) {
-			/* sizeof counts the final '\0' */
-			int len = sizeof("STATS_PATH=") - 1;
-			const char *pvar = "STATS_PATH=";
-
-			tmp = dentry_path_raw(kvm->debugfs_dentry,
-					      pathbuf + len,
-					      PATH_MAX - len);
-			if (!IS_ERR(tmp)) {
-				memcpy(tmp - len, pvar, len);
-				env->envp[env->envp_idx++] = tmp - len;
-			}
+		char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL);
+
+		if (p) {
+			tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX);
+			if (!IS_ERR(tmp))
+				add_uevent_var(env, "STATS_PATH=%s", tmp);
+			kfree(p);
 		}
 	}
 	/* no need for checks, since we are adding at most only 5 keys */
 	env->envp[env->envp_idx++] = NULL;
 	kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp);
 	kfree(env);
-	kfree(pathbuf);
 }
 
 static int kvm_init_debug(void)