1 files changed, 110 insertions, 64 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 2098dc689088..73418dc0ebb2 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -221,13 +221,6 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 	}
 }
 
-static void kvm_apic_map_free(struct rcu_head *rcu)
-{
-	struct kvm_apic_map *map = container_of(rcu, struct kvm_apic_map, rcu);
-
-	kvfree(map);
-}
-
 static int kvm_recalculate_phys_map(struct kvm_apic_map *new,
 				    struct kvm_vcpu *vcpu,
 				    bool *xapic_id_mismatch)
@@ -382,7 +375,7 @@ enum {
 	DIRTY
 };
 
-void kvm_recalculate_apic_map(struct kvm *kvm)
+static void kvm_recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
 	struct kvm_vcpu *vcpu;
@@ -489,7 +482,7 @@ out:
 	mutex_unlock(&kvm->arch.apic_map_lock);
 
 	if (old)
-		call_rcu(&old->rcu, kvm_apic_map_free);
+		kvfree_rcu(old, rcu);
 
 	kvm_make_scan_ioapic_request(kvm);
 }
@@ -598,7 +591,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	 * version first and level-triggered interrupts never get EOIed in
 	 * IOAPIC.
 	 */
-	if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) &&
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_X2APIC) &&
 	    !ioapic_in_kernel(vcpu->kvm))
 		v |= APIC_LVR_DIRECTED_EOI;
 	kvm_lapic_set_reg(apic, APIC_LVR, v);
@@ -662,27 +655,29 @@ static u8 count_vectors(void *bitmap)
 	return count;
 }
 
-bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr)
+bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr)
 {
+	unsigned long pir_vals[NR_PIR_WORDS];
+	u32 *__pir = (void *)pir_vals;
 	u32 i, vec;
-	u32 pir_val, irr_val, prev_irr_val;
+	u32 irr_val, prev_irr_val;
 	int max_updated_irr;
 
 	max_updated_irr = -1;
 	*max_irr = -1;
 
+	if (!pi_harvest_pir(pir, pir_vals))
+		return false;
+
 	for (i = vec = 0; i <= 7; i++, vec += 32) {
 		u32 *p_irr = (u32 *)(regs + APIC_IRR + i * 0x10);
 
-		irr_val = *p_irr;
-		pir_val = READ_ONCE(pir[i]);
-
-		if (pir_val) {
-			pir_val = xchg(&pir[i], 0);
+		irr_val = READ_ONCE(*p_irr);
 
+		if (__pir[i]) {
 			prev_irr_val = irr_val;
 			do {
-				irr_val = prev_irr_val | pir_val;
+				irr_val = prev_irr_val | __pir[i];
 			} while (prev_irr_val != irr_val &&
 				 !try_cmpxchg(p_irr, &prev_irr_val, irr_val));
 
@@ -698,7 +693,7 @@ bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr)
 }
 EXPORT_SYMBOL_GPL(__kvm_apic_update_irr);
 
-bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr)
+bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	bool irr_updated = __kvm_apic_update_irr(pir, apic->regs, max_irr);
@@ -734,10 +729,7 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 {
 	if (unlikely(apic->apicv_active)) {
-		/* need to update RVI */
 		kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
-		kvm_x86_call(hwapic_irr_update)(apic->vcpu,
-						apic_find_highest_irr(apic));
 	} else {
 		apic->irr_pending = false;
 		kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
@@ -763,7 +755,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 	 * just set SVI.
 	 */
 	if (unlikely(apic->apicv_active))
-		kvm_x86_call(hwapic_isr_update)(vec);
+		kvm_x86_call(hwapic_isr_update)(apic->vcpu, vec);
 	else {
 		++apic->isr_count;
 		BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
@@ -808,7 +800,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 	 * and must be left alone.
 	 */
 	if (unlikely(apic->apicv_active))
-		kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic));
+		kvm_x86_call(hwapic_isr_update)(apic->vcpu, apic_find_highest_isr(apic));
 	else {
 		--apic->isr_count;
 		BUG_ON(apic->isr_count < 0);
@@ -816,6 +808,17 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 	}
 }
 
+void kvm_apic_update_hwapic_isr(struct kvm_vcpu *vcpu)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	if (WARN_ON_ONCE(!lapic_in_kernel(vcpu)) || !apic->apicv_active)
+		return;
+
+	kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic));
+}
+EXPORT_SYMBOL_GPL(kvm_apic_update_hwapic_isr);
+
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
 {
 	/* This may race with setting of irr in __apic_accept_irq() and
@@ -1458,6 +1461,14 @@ static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 	if (!kvm_ioapic_handles_vector(apic, vector))
 		return;
 
+	/*
+	 * If the intercepted EOI is for an IRQ that was pending from previous
+	 * routing, then re-scan the I/O APIC routes as EOIs for the IRQ likely
+	 * no longer need to be intercepted.
+	 */
+	if (apic->vcpu->arch.highest_stale_pending_ioapic_eoi == vector)
+		kvm_make_request(KVM_REQ_SCAN_IOAPIC, apic->vcpu);
+
 	/* Request a KVM exit to inform the userspace IOAPIC. */
 	if (irqchip_split(apic->vcpu->kvm)) {
 		apic->vcpu->arch.pending_ioapic_eoi = vector;
@@ -1789,8 +1800,17 @@ static void apic_update_lvtt(struct kvm_lapic *apic)
 static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	u32 reg = kvm_lapic_get_reg(apic, APIC_LVTT);
+	u32 reg;
+
+	/*
+	 * Assume a timer IRQ was "injected" if the APIC is protected.  KVM's
+	 * copy of the vIRR is bogus, it's the responsibility of the caller to
+	 * precisely check whether or not a timer IRQ is pending.
+	 */
+	if (apic->guest_apic_protected)
+		return true;
 
+	reg = kvm_lapic_get_reg(apic, APIC_LVTT);
 	if (kvm_apic_hw_enabled(apic)) {
 		int vec = reg & APIC_VECTOR_MASK;
 		void *bitmap = apic->regs + APIC_ISR;
@@ -2357,7 +2377,7 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_LVTT:
 		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
-		val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask);
+		val &= (apic_lvt_mask[LVT_TIMER] | apic->lapic_timer.timer_mode_mask);
 		kvm_lapic_set_reg(apic, APIC_LVTT, val);
 		apic_update_lvtt(apic);
 		break;
@@ -2577,7 +2597,7 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 	return (tpr & 0xf0) >> 4;
 }
 
-void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
+static void __kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value)
 {
 	u64 old_value = vcpu->arch.apic_base;
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -2585,7 +2605,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	vcpu->arch.apic_base = value;
 
 	if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE)
-		kvm_update_cpuid_runtime(vcpu);
+		vcpu->arch.cpuid_dynamic_bits_dirty = true;
 
 	if (!apic)
 		return;
@@ -2625,29 +2645,61 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	}
 }
 
+int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated)
+{
+	enum lapic_mode old_mode = kvm_get_apic_mode(vcpu);
+	enum lapic_mode new_mode = kvm_apic_mode(value);
+
+	if (vcpu->arch.apic_base == value)
+		return 0;
+
+	u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff |
+		(guest_cpu_cap_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
+
+	if ((value & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID)
+		return 1;
+	if (!host_initiated) {
+		if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC)
+			return 1;
+		if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC)
+			return 1;
+	}
+
+	__kvm_apic_set_base(vcpu, value);
+	kvm_recalculate_apic_map(vcpu->kvm);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_apic_set_base);
+
 void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (apic->apicv_active) {
-		/* irr_pending is always true when apicv is activated. */
-		apic->irr_pending = true;
+	/*
+	 * When APICv is enabled, KVM must always search the IRR for a pending
+	 * IRQ, as other vCPUs and devices can set IRR bits even if the vCPU
+	 * isn't running.  If APICv is disabled, KVM _should_ search the IRR
+	 * for a pending IRQ.  But KVM currently doesn't ensure *all* hardware,
+	 * e.g. CPUs and IOMMUs, has seen the change in state, i.e. searching
+	 * the IRR at this time could race with IRQ delivery from hardware that
+	 * still sees APICv as being enabled.
+	 *
+	 * FIXME: Ensure other vCPUs and devices observe the change in APICv
+	 *        state prior to updating KVM's metadata caches, so that KVM
+	 *        can safely search the IRR and set irr_pending accordingly.
+	 */
+	apic->irr_pending = true;
+
+	if (apic->apicv_active)
 		apic->isr_count = 1;
-	} else {
-		/*
-		 * Don't clear irr_pending, searching the IRR can race with
-		 * updates from the CPU as APICv is still active from hardware's
-		 * perspective.  The flag will be cleared as appropriate when
-		 * KVM injects the interrupt.
-		 */
+	else
 		apic->isr_count = count_vectors(apic->regs + APIC_ISR);
-	}
+
 	apic->highest_isr_cache = -1;
 }
 
 int kvm_alloc_apic_access_page(struct kvm *kvm)
 {
-	struct page *page;
 	void __user *hva;
 	int ret = 0;
 
@@ -2663,17 +2715,6 @@ int kvm_alloc_apic_access_page(struct kvm *kvm)
 		goto out;
 	}
 
-	page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
-	if (is_error_page(page)) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	/*
-	 * Do not pin the page in memory, so that memory hot-unplug
-	 * is able to migrate it.
-	 */
-	put_page(page);
 	kvm->arch.apic_access_memslot_enabled = true;
 out:
 	mutex_unlock(&kvm->slots_lock);
@@ -2728,7 +2769,14 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 		msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
 		if (kvm_vcpu_is_reset_bsp(vcpu))
 			msr_val |= MSR_IA32_APICBASE_BSP;
-		kvm_lapic_set_base(vcpu, msr_val);
+
+		/*
+		 * Use the inner helper to avoid an extra recalcuation of the
+		 * optimized APIC map if some other task has dirtied the map.
+		 * The recalculation needed for this vCPU will be done after
+		 * all APIC state has been initialized (see below).
+		 */
+		__kvm_apic_set_base(vcpu, msr_val);
 	}
 
 	if (!apic)
@@ -2778,8 +2826,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	apic_update_ppr(apic);
 	if (apic->apicv_active) {
 		kvm_x86_call(apicv_post_state_restore)(vcpu);
-		kvm_x86_call(hwapic_irr_update)(vcpu, -1);
-		kvm_x86_call(hwapic_isr_update)(-1);
+		kvm_x86_call(hwapic_isr_update)(vcpu, -1);
 	}
 
 	vcpu->arch.apic_arb_prio = 0;
@@ -2887,9 +2934,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 
 	apic->nr_lvt_entries = kvm_apic_calc_nr_lvt_entries(vcpu);
 
-	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS_HARD);
-	apic->lapic_timer.timer.function = apic_timer_fn;
+	hrtimer_setup(&apic->lapic_timer.timer, apic_timer_fn, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_HARD);
 	if (lapic_timer_advance)
 		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
 
@@ -2932,6 +2978,9 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	if (!kvm_apic_present(vcpu))
 		return -1;
 
+	if (apic->guest_apic_protected)
+		return -1;
+
 	__apic_update_ppr(apic, &ppr);
 	return apic_has_interrupt_for_ppr(apic, ppr);
 }
@@ -3069,7 +3118,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 
 	kvm_x86_call(apicv_pre_state_restore)(vcpu);
 
-	kvm_lapic_set_base(vcpu, vcpu->arch.apic_base);
 	/* set SPIV separately to get count of SW disabled APICs right */
 	apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV)));
 
@@ -3095,9 +3143,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 	kvm_apic_update_apicv(vcpu);
 	if (apic->apicv_active) {
 		kvm_x86_call(apicv_post_state_restore)(vcpu);
-		kvm_x86_call(hwapic_irr_update)(vcpu,
-						apic_find_highest_irr(apic));
-		kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic));
+		kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic));
 	}
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	if (ioapic_in_kernel(vcpu->kvm))
@@ -3366,9 +3412,9 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		kvm_vcpu_reset(vcpu, true);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
-			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+			kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 		else
-			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+			kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED);
 	}
 	if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events)) {
 		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
@@ -3377,7 +3423,7 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 			sipi_vector = apic->sipi_vector;
 			kvm_x86_call(vcpu_deliver_sipi_vector)(vcpu,
 							       sipi_vector);
-			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+			kvm_set_mp_state(vcpu, KVM_MP_STATE_RUNNABLE);
 		}
 	}
 	return 0;