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

Pull KVM fixes from Paolo Bonzini:
 "Miscellaneous bugfixes.

  The ARM and s390 fixes are for new regressions from the merge window,
  others are usual stable material"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  compiler-gcc: disable -ftracer for __noclone functions
  kvm: x86: make lapic hrtimer pinned
  s390/mm/kvm: fix mis-merge in gmap handling
  kvm: set page dirty only if page has been writable
  KVM: x86: reduce default value of halt_poll_ns parameter
  KVM: Hyper-V: do not do hypercall userspace exits if SynIC is disabled
  KVM: x86: Inject pending interrupt even if pending nmi exist
  arm64: KVM: Register CPU notifiers when the kernel runs at HYP
  arm64: kvm: 4.6-rc1: Fix VTCR_EL2 VS setting

10 files changed, 75 insertions, 41 deletions

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 6accd66d26f0..b5384311dec4 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -1061,15 +1061,27 @@ static void cpu_init_hyp_mode(void *dummy)
 	kvm_arm_init_debug();
 }
 
+static void cpu_hyp_reinit(void)
+{
+	if (is_kernel_in_hyp_mode()) {
+		/*
+		 * cpu_init_stage2() is safe to call even if the PM
+		 * event was cancelled before the CPU was reset.
+		 */
+		cpu_init_stage2(NULL);
+	} else {
+		if (__hyp_get_vectors() == hyp_default_vectors)
+			cpu_init_hyp_mode(NULL);
+	}
+}
+
 static int hyp_init_cpu_notify(struct notifier_block *self,
 			       unsigned long action, void *cpu)
 {
 	switch (action) {
 	case CPU_STARTING:
 	case CPU_STARTING_FROZEN:
-		if (__hyp_get_vectors() == hyp_default_vectors)
-			cpu_init_hyp_mode(NULL);
-		break;
+		cpu_hyp_reinit();
 	}
 
 	return NOTIFY_OK;
@@ -1084,9 +1096,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
 				    unsigned long cmd,
 				    void *v)
 {
-	if (cmd == CPU_PM_EXIT &&
-	    __hyp_get_vectors() == hyp_default_vectors) {
-		cpu_init_hyp_mode(NULL);
+	if (cmd == CPU_PM_EXIT) {
+		cpu_hyp_reinit();
 		return NOTIFY_OK;
 	}
 
@@ -1128,6 +1139,22 @@ static int init_subsystems(void)
 	int err;
 
 	/*
+	 * Register CPU Hotplug notifier
+	 */
+	cpu_notifier_register_begin();
+	err = __register_cpu_notifier(&hyp_init_cpu_nb);
+	cpu_notifier_register_done();
+	if (err) {
+		kvm_err("Cannot register KVM init CPU notifier (%d)\n", err);
+		return err;
+	}
+
+	/*
+	 * Register CPU lower-power notifier
+	 */
+	hyp_cpu_pm_init();
+
+	/*
 	 * Init HYP view of VGIC
 	 */
 	err = kvm_vgic_hyp_init();
@@ -1270,19 +1297,6 @@ static int init_hyp_mode(void)
 	free_boot_hyp_pgd();
 #endif
 
-	cpu_notifier_register_begin();
-
-	err = __register_cpu_notifier(&hyp_init_cpu_nb);
-
-	cpu_notifier_register_done();
-
-	if (err) {
-		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
-		goto out_err;
-	}
-
-	hyp_cpu_pm_init();
-
 	/* set size of VMID supported by CPU */
 	kvm_vmid_bits = kvm_get_vmid_bits();
 	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 0e391dbfc420..4150fd8bae01 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -124,7 +124,9 @@
 #define VTCR_EL2_SL0_LVL1	(1 << 6)
 #define VTCR_EL2_T0SZ_MASK	0x3f
 #define VTCR_EL2_T0SZ_40B	24
-#define VTCR_EL2_VS		19
+#define VTCR_EL2_VS_SHIFT	19
+#define VTCR_EL2_VS_8BIT	(0 << VTCR_EL2_VS_SHIFT)
+#define VTCR_EL2_VS_16BIT	(1 << VTCR_EL2_VS_SHIFT)
 
 /*
  * We configure the Stage-2 page tables to always restrict the IPA space to be
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 1a78d6e2a78b..12874164b0ae 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -141,6 +141,9 @@
 #define ID_AA64MMFR1_VMIDBITS_SHIFT	4
 #define ID_AA64MMFR1_HADBS_SHIFT	0
 
+#define ID_AA64MMFR1_VMIDBITS_8		0
+#define ID_AA64MMFR1_VMIDBITS_16	2
+
 /* id_aa64mmfr2 */
 #define ID_AA64MMFR2_UAO_SHIFT		4
 
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
index bfc54fd82797..5a9f3bf542b0 100644
--- a/arch/arm64/kvm/hyp/s2-setup.c
+++ b/arch/arm64/kvm/hyp/s2-setup.c
@@ -36,8 +36,10 @@ void __hyp_text __init_stage2_translation(void)
 	 * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS
 	 * bit in VTCR_EL2.
 	 */
-	tmp = (read_sysreg(id_aa64mmfr1_el1) >> 4) & 0xf;
-	val |= (tmp == 2) ? VTCR_EL2_VS : 0;
+	tmp = (read_sysreg(id_aa64mmfr1_el1) >> ID_AA64MMFR1_VMIDBITS_SHIFT) & 0xf;
+	val |= (tmp == ID_AA64MMFR1_VMIDBITS_16) ?
+			VTCR_EL2_VS_16BIT :
+			VTCR_EL2_VS_8BIT;
 
 	write_sysreg(val, vtcr_el2);
 }
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 69247b4dcc43..cace818d86eb 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -23,7 +23,7 @@
 /**
  * gmap_alloc - allocate a guest address space
  * @mm: pointer to the parent mm_struct
- * @limit: maximum size of the gmap address space
+ * @limit: maximum address of the gmap address space
  *
  * Returns a guest address space structure.
  */
@@ -292,7 +292,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
 	if ((from | to | len) & (PMD_SIZE - 1))
 		return -EINVAL;
 	if (len == 0 || from + len < from || to + len < to ||
-	    from + len > TASK_MAX_SIZE || to + len > gmap->asce_end)
+	    from + len - 1 > TASK_MAX_SIZE || to + len - 1 > gmap->asce_end)
 		return -EINVAL;
 
 	flush = 0;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f62a9f37f79f..b7e394485a5f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -43,7 +43,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
-#define KVM_HALT_POLL_NS_DEFAULT 500000
+#define KVM_HALT_POLL_NS_DEFAULT 400000
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 5ff3485acb60..01bd7b7a6866 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1116,6 +1116,11 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		break;
 	case HVCALL_POST_MESSAGE:
 	case HVCALL_SIGNAL_EVENT:
+		/* don't bother userspace if it has no way to handle it */
+		if (!vcpu_to_synic(vcpu)->active) {
+			res = HV_STATUS_INVALID_HYPERCALL_CODE;
+			break;
+		}
 		vcpu->run->exit_reason = KVM_EXIT_HYPERV;
 		vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL;
 		vcpu->run->hyperv.u.hcall.input = param;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 443d2a57ad3d..1a2da0e5a373 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1369,7 +1369,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 
 		hrtimer_start(&apic->lapic_timer.timer,
 			      ktime_add_ns(now, apic->lapic_timer.period),
-			      HRTIMER_MODE_ABS);
+			      HRTIMER_MODE_ABS_PINNED);
 
 		apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
 			   PRIx64 ", "
@@ -1402,7 +1402,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 			expire = ktime_add_ns(now, ns);
 			expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
 			hrtimer_start(&apic->lapic_timer.timer,
-				      expire, HRTIMER_MODE_ABS);
+				      expire, HRTIMER_MODE_ABS_PINNED);
 		} else
 			apic_timer_expired(apic);
 
@@ -1868,7 +1868,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	apic->vcpu = vcpu;
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS);
+		     HRTIMER_MODE_ABS_PINNED);
 	apic->lapic_timer.timer.function = apic_timer_fn;
 
 	/*
@@ -2003,7 +2003,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
 
 	timer = &vcpu->arch.apic->lapic_timer.timer;
 	if (hrtimer_cancel(timer))
-		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 70e95d097ef1..1ff4dbb73fb7 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -557,8 +557,15 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte)
 	      !is_writable_pte(new_spte))
 		ret = true;
 
-	if (!shadow_accessed_mask)
+	if (!shadow_accessed_mask) {
+		/*
+		 * We don't set page dirty when dropping non-writable spte.
+		 * So do it now if the new spte is becoming non-writable.
+		 */
+		if (ret)
+			kvm_set_pfn_dirty(spte_to_pfn(old_spte));
 		return ret;
+	}
 
 	/*
 	 * Flush TLB when accessed/dirty bits are changed in the page tables,
@@ -605,7 +612,8 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
 
 	if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
 		kvm_set_pfn_accessed(pfn);
-	if (!shadow_dirty_mask || (old_spte & shadow_dirty_mask))
+	if (old_spte & (shadow_dirty_mask ? shadow_dirty_mask :
+					    PT_WRITABLE_MASK))
 		kvm_set_pfn_dirty(pfn);
 	return 1;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 742d0f7d3556..0a2c70e43bc8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6095,12 +6095,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	}
 
 	/* try to inject new event if pending */
-	if (vcpu->arch.nmi_pending) {
-		if (kvm_x86_ops->nmi_allowed(vcpu)) {
-			--vcpu->arch.nmi_pending;
-			vcpu->arch.nmi_injected = true;
-			kvm_x86_ops->set_nmi(vcpu);
-		}
+	if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+		--vcpu->arch.nmi_pending;
+		vcpu->arch.nmi_injected = true;
+		kvm_x86_ops->set_nmi(vcpu);
 	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
 		/*
 		 * Because interrupts can be injected asynchronously, we are
@@ -6569,10 +6567,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (inject_pending_event(vcpu, req_int_win) != 0)
 			req_immediate_exit = true;
 		/* enable NMI/IRQ window open exits if needed */
-		else if (vcpu->arch.nmi_pending)
-			kvm_x86_ops->enable_nmi_window(vcpu);
-		else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
-			kvm_x86_ops->enable_irq_window(vcpu);
+		else {
+			if (vcpu->arch.nmi_pending)
+				kvm_x86_ops->enable_nmi_window(vcpu);
+			if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
+				kvm_x86_ops->enable_irq_window(vcpu);
+		}
 
 		if (kvm_lapic_enabled(vcpu)) {
 			update_cr8_intercept(vcpu);