1 files changed, 118 insertions, 63 deletions

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0e68b4c937fc..e2ce3556915e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -27,6 +27,7 @@
 #include <linux/math64.h>
 #include <linux/slab.h>
 #include <asm/processor.h>
+#include <asm/mce.h>
 #include <asm/msr.h>
 #include <asm/page.h>
 #include <asm/current.h>
@@ -54,7 +55,7 @@
 #define PRIo64 "o"
 
 /* 14 is the version for Xeon and Pentium 8.4.8*/
-#define APIC_VERSION			(0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16))
+#define APIC_VERSION			0x14UL
 #define LAPIC_MMIO_LENGTH		(1 << 12)
 /* followed define is not in apicdef.h */
 #define MAX_APIC_VECTOR			256
@@ -67,6 +68,8 @@ static bool lapic_timer_advance_dynamic __read_mostly;
 #define LAPIC_TIMER_ADVANCE_NS_MAX     5000
 /* step-by-step approximation to mitigate fluctuation */
 #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
+static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data);
+static int kvm_lapic_msr_write(struct kvm_lapic *apic, u32 reg, u64 data);
 
 static inline void __kvm_lapic_set_reg(char *regs, int reg_off, u32 val)
 {
@@ -398,14 +401,26 @@ static inline int apic_lvt_nmi_mode(u32 lvt_val)
 	return (lvt_val & (APIC_MODE_MASK | APIC_LVT_MASKED)) == APIC_DM_NMI;
 }
 
+static inline bool kvm_lapic_lvt_supported(struct kvm_lapic *apic, int lvt_index)
+{
+	return apic->nr_lvt_entries > lvt_index;
+}
+
+static inline int kvm_apic_calc_nr_lvt_entries(struct kvm_vcpu *vcpu)
+{
+	return KVM_APIC_MAX_NR_LVT_ENTRIES - !(vcpu->arch.mcg_cap & MCG_CMCI_P);
+}
+
 void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	u32 v = APIC_VERSION;
+	u32 v = 0;
 
 	if (!lapic_in_kernel(vcpu))
 		return;
 
+	v = APIC_VERSION | ((apic->nr_lvt_entries - 1) << 16);
+
 	/*
 	 * KVM emulates 82093AA datasheet (with in-kernel IOAPIC implementation)
 	 * which doesn't have EOI register; Some buggy OSes (e.g. Windows with
@@ -419,12 +434,33 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	kvm_lapic_set_reg(apic, APIC_LVR, v);
 }
 
-static const unsigned int apic_lvt_mask[KVM_APIC_LVT_NUM] = {
-	LVT_MASK ,      /* part LVTT mask, timer mode mask added at runtime */
-	LVT_MASK | APIC_MODE_MASK,	/* LVTTHMR */
-	LVT_MASK | APIC_MODE_MASK,	/* LVTPC */
-	LINT_MASK, LINT_MASK,	/* LVT0-1 */
-	LVT_MASK		/* LVTERR */
+void kvm_apic_after_set_mcg_cap(struct kvm_vcpu *vcpu)
+{
+	int nr_lvt_entries = kvm_apic_calc_nr_lvt_entries(vcpu);
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	int i;
+
+	if (!lapic_in_kernel(vcpu) || nr_lvt_entries == apic->nr_lvt_entries)
+		return;
+
+	/* Initialize/mask any "new" LVT entries. */
+	for (i = apic->nr_lvt_entries; i < nr_lvt_entries; i++)
+		kvm_lapic_set_reg(apic, APIC_LVTx(i), APIC_LVT_MASKED);
+
+	apic->nr_lvt_entries = nr_lvt_entries;
+
+	/* The number of LVT entries is reflected in the version register. */
+	kvm_apic_set_version(vcpu);
+}
+
+static const unsigned int apic_lvt_mask[KVM_APIC_MAX_NR_LVT_ENTRIES] = {
+	[LVT_TIMER] = LVT_MASK,      /* timer mode mask added at runtime */
+	[LVT_THERMAL_MONITOR] = LVT_MASK | APIC_MODE_MASK,
+	[LVT_PERFORMANCE_COUNTER] = LVT_MASK | APIC_MODE_MASK,
+	[LVT_LINT0] = LINT_MASK,
+	[LVT_LINT1] = LINT_MASK,
+	[LVT_ERROR] = LVT_MASK,
+	[LVT_CMCI] = LVT_MASK | APIC_MODE_MASK
 };
 
 static int find_highest_vector(void *bitmap)
@@ -518,14 +554,11 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 
 static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 {
-	struct kvm_vcpu *vcpu;
-
-	vcpu = apic->vcpu;
-
-	if (unlikely(vcpu->arch.apicv_active)) {
+	if (unlikely(apic->apicv_active)) {
 		/* need to update RVI */
 		kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
-		static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic));
+		static_call_cond(kvm_x86_hwapic_irr_update)(apic->vcpu,
+							    apic_find_highest_irr(apic));
 	} else {
 		apic->irr_pending = false;
 		kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
@@ -542,20 +575,16 @@ EXPORT_SYMBOL_GPL(kvm_apic_clear_irr);
 
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
-	struct kvm_vcpu *vcpu;
-
 	if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
 		return;
 
-	vcpu = apic->vcpu;
-
 	/*
 	 * With APIC virtualization enabled, all caching is disabled
 	 * because the processor can modify ISR under the hood.  Instead
 	 * just set SVI.
 	 */
-	if (unlikely(vcpu->arch.apicv_active))
-		static_call_cond(kvm_x86_hwapic_isr_update)(vcpu, vec);
+	if (unlikely(apic->apicv_active))
+		static_call_cond(kvm_x86_hwapic_isr_update)(vec);
 	else {
 		++apic->isr_count;
 		BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
@@ -589,12 +618,9 @@ static inline int apic_find_highest_isr(struct kvm_lapic *apic)
 
 static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 {
-	struct kvm_vcpu *vcpu;
 	if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
 		return;
 
-	vcpu = apic->vcpu;
-
 	/*
 	 * We do get here for APIC virtualization enabled if the guest
 	 * uses the Hyper-V APIC enlightenment.  In this case we may need
@@ -602,8 +628,8 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 	 * on the other hand isr_count and highest_isr_cache are unused
 	 * and must be left alone.
 	 */
-	if (unlikely(vcpu->arch.apicv_active))
-		static_call_cond(kvm_x86_hwapic_isr_update)(vcpu, apic_find_highest_isr(apic));
+	if (unlikely(apic->apicv_active))
+		static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic));
 	else {
 		--apic->isr_count;
 		BUG_ON(apic->isr_count < 0);
@@ -801,17 +827,17 @@ static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda)
 	if (kvm_apic_broadcast(apic, mda))
 		return true;
 
-	if (apic_x2apic_mode(apic))
-		return mda == kvm_x2apic_id(apic);
-
 	/*
-	 * Hotplug hack: Make LAPIC in xAPIC mode also accept interrupts as if
-	 * it were in x2APIC mode.  Hotplugged VCPUs start in xAPIC mode and
-	 * this allows unique addressing of VCPUs with APIC ID over 0xff.
-	 * The 0xff condition is needed because writeable xAPIC ID.
+	 * Hotplug hack: Accept interrupts for vCPUs in xAPIC mode as if they
+	 * were in x2APIC mode if the target APIC ID can't be encoded as an
+	 * xAPIC ID.  This allows unique addressing of hotplugged vCPUs (which
+	 * start in xAPIC mode) with an APIC ID that is unaddressable in xAPIC
+	 * mode.  Match the x2APIC ID if and only if the target APIC ID can't
+	 * be encoded in xAPIC to avoid spurious matches against a vCPU that
+	 * changed its (addressable) xAPIC ID (which is writable).
 	 */
-	if (kvm_x2apic_id(apic) > 0xff && mda == kvm_x2apic_id(apic))
-		return true;
+	if (apic_x2apic_mode(apic) || mda > 0xff)
+		return mda == kvm_x2apic_id(apic);
 
 	return mda == kvm_xapic_id(apic);
 }
@@ -1325,7 +1351,7 @@ void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high)
 	if (apic_x2apic_mode(apic))
 		irq.dest_id = icr_high;
 	else
-		irq.dest_id = GET_APIC_DEST_FIELD(icr_high);
+		irq.dest_id = GET_XAPIC_DEST_FIELD(icr_high);
 
 	trace_kvm_apic_ipi(icr_low, irq.dest_id);
 
@@ -1444,6 +1470,9 @@ static int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 		APIC_REG_MASK(APIC_TMCCT) |
 		APIC_REG_MASK(APIC_TDCR);
 
+	if (kvm_lapic_lvt_supported(apic, LVT_CMCI))
+		valid_reg_mask |= APIC_REG_MASK(APIC_LVTCMCI);
+
 	/*
 	 * ARBPRI and ICR2 are not valid in x2APIC mode.  WARN if KVM reads ICR
 	 * in x2APIC mode as it's an 8-byte register in x2APIC and needs to be
@@ -1583,7 +1612,7 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
 		int vec = reg & APIC_VECTOR_MASK;
 		void *bitmap = apic->regs + APIC_ISR;
 
-		if (vcpu->arch.apicv_active)
+		if (apic->apicv_active)
 			bitmap = apic->regs + APIC_IRR;
 
 		if (apic_test_vector(vec, bitmap))
@@ -1602,7 +1631,7 @@ static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles)
 	 * that __delay() uses delay_tsc whenever the hardware has TSC, thus
 	 * always for VMX enabled hardware.
 	 */
-	if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) {
+	if (vcpu->arch.tsc_scaling_ratio == kvm_caps.default_tsc_scaling_ratio) {
 		__delay(min(guest_cycles,
 			nsec_to_cycles(vcpu, timer_advance_ns)));
 	} else {
@@ -1700,7 +1729,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use)
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
 
-	if (!from_timer_fn && vcpu->arch.apicv_active) {
+	if (!from_timer_fn && apic->apicv_active) {
 		WARN_ON(kvm_get_running_vcpu() != vcpu);
 		kvm_apic_inject_pending_timer_irqs(apic);
 		return;
@@ -2052,6 +2081,16 @@ static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic)
 	kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED);
 }
 
+static int get_lvt_index(u32 reg)
+{
+	if (reg == APIC_LVTCMCI)
+		return LVT_CMCI;
+	if (reg < APIC_LVTT || reg > APIC_LVTERR)
+		return -1;
+	return array_index_nospec(
+			(reg - APIC_LVTT) >> 4, KVM_APIC_MAX_NR_LVT_ENTRIES);
+}
+
 static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 {
 	int ret = 0;
@@ -2098,13 +2137,10 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 		apic_set_spiv(apic, val & mask);
 		if (!(val & APIC_SPIV_APIC_ENABLED)) {
 			int i;
-			u32 lvt_val;
 
-			for (i = 0; i < KVM_APIC_LVT_NUM; i++) {
-				lvt_val = kvm_lapic_get_reg(apic,
-						       APIC_LVTT + 0x10 * i);
-				kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i,
-					     lvt_val | APIC_LVT_MASKED);
+			for (i = 0; i < apic->nr_lvt_entries; i++) {
+				kvm_lapic_set_reg(apic, APIC_LVTx(i),
+					kvm_lapic_get_reg(apic, APIC_LVTx(i)) | APIC_LVT_MASKED);
 			}
 			apic_update_lvtt(apic);
 			atomic_set(&apic->lapic_timer.pending, 0);
@@ -2133,16 +2169,15 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_LVTTHMR:
 	case APIC_LVTPC:
 	case APIC_LVT1:
-	case APIC_LVTERR: {
-		/* TODO: Check vector */
-		size_t size;
-		u32 index;
-
+	case APIC_LVTERR:
+	case APIC_LVTCMCI: {
+		u32 index = get_lvt_index(reg);
+		if (!kvm_lapic_lvt_supported(apic, index)) {
+			ret = 1;
+			break;
+		}
 		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
-		size = ARRAY_SIZE(apic_lvt_mask);
-		index = array_index_nospec(
-				(reg - APIC_LVTT) >> 4, size);
 		val &= apic_lvt_mask[index];
 		kvm_lapic_set_reg(apic, reg, val);
 		break;
@@ -2246,10 +2281,26 @@ EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
 /* emulate APIC access in a trap manner */
 void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
 {
-	u32 val = kvm_lapic_get_reg(vcpu->arch.apic, offset);
+	struct kvm_lapic *apic = vcpu->arch.apic;
+	u64 val;
+
+	if (apic_x2apic_mode(apic))
+		kvm_lapic_msr_read(apic, offset, &val);
+	else
+		val = kvm_lapic_get_reg(apic, offset);
 
-	/* TODO: optimize to just emulate side effect w/o one more write */
-	kvm_lapic_reg_write(vcpu->arch.apic, offset, val);
+	/*
+	 * ICR is a single 64-bit register when x2APIC is enabled.  For legacy
+	 * xAPIC, ICR writes need to go down the common (slightly slower) path
+	 * to get the upper half from ICR2.
+	 */
+	if (apic_x2apic_mode(apic) && offset == APIC_ICR) {
+		kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32));
+		trace_kvm_apic_write(APIC_ICR, val);
+	} else {
+		/* TODO: optimize to just emulate side effect w/o one more write */
+		kvm_lapic_reg_write(apic, offset, (u32)val);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode);
 
@@ -2344,8 +2395,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	if (((old_value ^ value) & X2APIC_ENABLE) && (value & X2APIC_ENABLE))
 		kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id);
 
-	if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE))
+	if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) {
+		kvm_vcpu_update_apicv(vcpu);
 		static_call_cond(kvm_x86_set_virtual_apic_mode)(vcpu);
+	}
 
 	apic->base_address = apic->vcpu->arch.apic_base &
 			     MSR_IA32_APICBASE_BASE;
@@ -2361,7 +2414,7 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (vcpu->arch.apicv_active) {
+	if (apic->apicv_active) {
 		/* irr_pending is always true when apicv is activated. */
 		apic->irr_pending = true;
 		apic->isr_count = 1;
@@ -2401,8 +2454,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 		kvm_apic_set_xapic_id(apic, vcpu->vcpu_id);
 	kvm_apic_set_version(apic->vcpu);
 
-	for (i = 0; i < KVM_APIC_LVT_NUM; i++)
-		kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
+	for (i = 0; i < apic->nr_lvt_entries; i++)
+		kvm_lapic_set_reg(apic, APIC_LVTx(i), APIC_LVT_MASKED);
 	apic_update_lvtt(apic);
 	if (kvm_vcpu_is_reset_bsp(vcpu) &&
 	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
@@ -2436,10 +2489,10 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	vcpu->arch.pv_eoi.msr_val = 0;
 	apic_update_ppr(apic);
-	if (vcpu->arch.apicv_active) {
+	if (apic->apicv_active) {
 		static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu);
 		static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, -1);
-		static_call_cond(kvm_x86_hwapic_isr_update)(vcpu, -1);
+		static_call_cond(kvm_x86_hwapic_isr_update)(-1);
 	}
 
 	vcpu->arch.apic_arb_prio = 0;
@@ -2532,6 +2585,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 	}
 	apic->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;
@@ -2716,10 +2771,10 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 	kvm_lapic_set_reg(apic, APIC_TMCCT, 0);
 	kvm_apic_update_apicv(vcpu);
 	apic->highest_isr_cache = -1;
-	if (vcpu->arch.apicv_active) {
+	if (apic->apicv_active) {
 		static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu);
 		static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic));
-		static_call_cond(kvm_x86_hwapic_isr_update)(vcpu, apic_find_highest_isr(apic));
+		static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic));
 	}
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	if (ioapic_in_kernel(vcpu->kvm))