diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/ioapic.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/irq_comm.c | 3 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 193 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 38 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 28 | ||||
-rw-r--r-- | arch/x86/kvm/mtrr.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 670 | ||||
-rw-r--r-- | arch/x86/kvm/trace.h | 57 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 12 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 64 |
10 files changed, 895 insertions, 174 deletions
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 9db47090ead0..5f42d038fcb4 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -443,7 +443,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, spin_lock(&ioapic->lock); if (trigger_mode != IOAPIC_LEVEL_TRIG || - kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) + kvm_lapic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) continue; ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 54ead79e444b..dfb4c6476877 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -382,9 +382,6 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u32 i, nr_ioapic_pins; int idx; - /* kvm->irq_routing must be read after clearing - * KVM_SCAN_IOAPIC. */ - smp_mb(); idx = srcu_read_lock(&kvm->irq_srcu); table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); nr_ioapic_pins = min_t(u32, table->nr_rt_entries, diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 1a2da0e5a373..bbb5b283ff63 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -59,9 +59,8 @@ /* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */ #define apic_debug(fmt, arg...) -#define APIC_LVT_NUM 6 /* 14 is the version for Xeon and Pentium 8.4.8*/ -#define APIC_VERSION (0x14UL | ((APIC_LVT_NUM - 1) << 16)) +#define APIC_VERSION (0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16)) #define LAPIC_MMIO_LENGTH (1 << 12) /* followed define is not in apicdef.h */ #define APIC_SHORT_MASK 0xc0000 @@ -73,14 +72,6 @@ #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul -#define VEC_POS(v) ((v) & (32 - 1)) -#define REG_POS(v) (((v) >> 5) << 4) - -static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val) -{ - *((u32 *) (apic->regs + reg_off)) = val; -} - static inline int apic_test_vector(int vec, void *bitmap) { return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); @@ -94,11 +85,6 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector) apic_test_vector(vector, apic->regs + APIC_IRR); } -static inline void apic_set_vector(int vec, void *bitmap) -{ - set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - static inline void apic_clear_vector(int vec, void *bitmap) { clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); @@ -173,7 +159,7 @@ static void recalculate_apic_map(struct kvm *kvm) continue; aid = kvm_apic_id(apic); - ldr = kvm_apic_get_reg(apic, APIC_LDR); + ldr = kvm_lapic_get_reg(apic, APIC_LDR); if (aid < ARRAY_SIZE(new->phys_map)) new->phys_map[aid] = apic; @@ -182,7 +168,7 @@ static void recalculate_apic_map(struct kvm *kvm) new->mode |= KVM_APIC_MODE_X2APIC; } else if (ldr) { ldr = GET_APIC_LOGICAL_ID(ldr); - if (kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) + if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) new->mode |= KVM_APIC_MODE_XAPIC_FLAT; else new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER; @@ -212,7 +198,7 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) { bool enabled = val & APIC_SPIV_APIC_ENABLED; - apic_set_reg(apic, APIC_SPIV, val); + kvm_lapic_set_reg(apic, APIC_SPIV, val); if (enabled != apic->sw_enabled) { apic->sw_enabled = enabled; @@ -226,13 +212,13 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id) { - apic_set_reg(apic, APIC_ID, id << 24); + kvm_lapic_set_reg(apic, APIC_ID, id << 24); recalculate_apic_map(apic->vcpu->kvm); } static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) { - apic_set_reg(apic, APIC_LDR, id); + kvm_lapic_set_reg(apic, APIC_LDR, id); recalculate_apic_map(apic->vcpu->kvm); } @@ -240,19 +226,19 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id) { u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); - apic_set_reg(apic, APIC_ID, id << 24); - apic_set_reg(apic, APIC_LDR, ldr); + kvm_lapic_set_reg(apic, APIC_ID, id << 24); + kvm_lapic_set_reg(apic, APIC_LDR, ldr); recalculate_apic_map(apic->vcpu->kvm); } static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) { - return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); + return !(kvm_lapic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); } static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type) { - return kvm_apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK; + return kvm_lapic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK; } static inline int apic_lvtt_oneshot(struct kvm_lapic *apic) @@ -287,10 +273,10 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu) feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0); if (feat && (feat->ecx & (1 << (X86_FEATURE_X2APIC & 31)))) v |= APIC_LVR_DIRECTED_EOI; - apic_set_reg(apic, APIC_LVR, v); + kvm_lapic_set_reg(apic, APIC_LVR, v); } -static const unsigned int apic_lvt_mask[APIC_LVT_NUM] = { +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 */ @@ -349,16 +335,6 @@ void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) } EXPORT_SYMBOL_GPL(kvm_apic_update_irr); -static inline void apic_set_irr(int vec, struct kvm_lapic *apic) -{ - apic_set_vector(vec, apic->regs + APIC_IRR); - /* - * irr_pending must be true if any interrupt is pending; set it after - * APIC_IRR to avoid race with apic_clear_irr - */ - apic->irr_pending = true; -} - static inline int apic_search_irr(struct kvm_lapic *apic) { return find_highest_vector(apic->regs + APIC_IRR); @@ -416,7 +392,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * just set SVI. */ if (unlikely(vcpu->arch.apicv_active)) - kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec); + kvm_x86_ops->hwapic_isr_update(vcpu, vec); else { ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -464,7 +440,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * and must be left alone. */ if (unlikely(vcpu->arch.apicv_active)) - kvm_x86_ops->hwapic_isr_update(vcpu->kvm, + kvm_x86_ops->hwapic_isr_update(vcpu, apic_find_highest_isr(apic)); else { --apic->isr_count; @@ -549,8 +525,8 @@ static void apic_update_ppr(struct kvm_lapic *apic) u32 tpr, isrv, ppr, old_ppr; int isr; - old_ppr = kvm_apic_get_reg(apic, APIC_PROCPRI); - tpr = kvm_apic_get_reg(apic, APIC_TASKPRI); + old_ppr = kvm_lapic_get_reg(apic, APIC_PROCPRI); + tpr = kvm_lapic_get_reg(apic, APIC_TASKPRI); isr = apic_find_highest_isr(apic); isrv = (isr != -1) ? isr : 0; @@ -563,7 +539,7 @@ static void apic_update_ppr(struct kvm_lapic *apic) apic, ppr, isr, isrv); if (old_ppr != ppr) { - apic_set_reg(apic, APIC_PROCPRI, ppr); + kvm_lapic_set_reg(apic, APIC_PROCPRI, ppr); if (ppr < old_ppr) kvm_make_request(KVM_REQ_EVENT, apic->vcpu); } @@ -571,7 +547,7 @@ static void apic_update_ppr(struct kvm_lapic *apic) static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) { - apic_set_reg(apic, APIC_TASKPRI, tpr); + kvm_lapic_set_reg(apic, APIC_TASKPRI, tpr); apic_update_ppr(apic); } @@ -601,7 +577,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) if (kvm_apic_broadcast(apic, mda)) return true; - logical_id = kvm_apic_get_reg(apic, APIC_LDR); + logical_id = kvm_lapic_get_reg(apic, APIC_LDR); if (apic_x2apic_mode(apic)) return ((logical_id >> 16) == (mda >> 16)) @@ -610,7 +586,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) logical_id = GET_APIC_LOGICAL_ID(logical_id); mda = GET_APIC_DEST_FIELD(mda); - switch (kvm_apic_get_reg(apic, APIC_DFR)) { + switch (kvm_lapic_get_reg(apic, APIC_DFR)) { case APIC_DFR_FLAT: return (logical_id & mda) != 0; case APIC_DFR_CLUSTER: @@ -618,7 +594,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) && (logical_id & mda & 0xf) != 0; default: apic_debug("Bad DFR vcpu %d: %08x\n", - apic->vcpu->vcpu_id, kvm_apic_get_reg(apic, APIC_DFR)); + apic->vcpu->vcpu_id, kvm_lapic_get_reg(apic, APIC_DFR)); return false; } } @@ -668,6 +644,7 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, return false; } } +EXPORT_SYMBOL_GPL(kvm_apic_match_dest); int kvm_vector_to_index(u32 vector, u32 dest_vcpus, const unsigned long *bitmap, u32 bitmap_size) @@ -921,7 +898,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) { if (trig_mode) - apic_set_vector(vector, apic->regs + APIC_TMR); + kvm_lapic_set_vector(vector, apic->regs + APIC_TMR); else apic_clear_vector(vector, apic->regs + APIC_TMR); } @@ -929,7 +906,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, if (vcpu->arch.apicv_active) kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); else { - apic_set_irr(vector, apic); + kvm_lapic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); @@ -1073,8 +1050,8 @@ EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated); static void apic_send_ipi(struct kvm_lapic *apic) { - u32 icr_low = kvm_apic_get_reg(apic, APIC_ICR); - u32 icr_high = kvm_apic_get_reg(apic, APIC_ICR2); + u32 icr_low = kvm_lapic_get_reg(apic, APIC_ICR); + u32 icr_high = kvm_lapic_get_reg(apic, APIC_ICR2); struct kvm_lapic_irq irq; irq.vector = icr_low & APIC_VECTOR_MASK; @@ -1111,7 +1088,7 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic) ASSERT(apic != NULL); /* if initial count is 0, current count should also be 0 */ - if (kvm_apic_get_reg(apic, APIC_TMICT) == 0 || + if (kvm_lapic_get_reg(apic, APIC_TMICT) == 0 || apic->lapic_timer.period == 0) return 0; @@ -1168,13 +1145,13 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) break; case APIC_PROCPRI: apic_update_ppr(apic); - val = kvm_apic_get_reg(apic, offset); + val = kvm_lapic_get_reg(apic, offset); break; case APIC_TASKPRI: report_tpr_access(apic, false); /* fall thru */ default: - val = kvm_apic_get_reg(apic, offset); + val = kvm_lapic_get_reg(apic, offset); break; } @@ -1186,7 +1163,7 @@ static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev) return container_of(dev, struct kvm_lapic, dev); } -static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len, +int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, void *data) { unsigned char alignment = offset & 0xf; @@ -1223,6 +1200,7 @@ static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len, } return 0; } +EXPORT_SYMBOL_GPL(kvm_lapic_reg_read); static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) { @@ -1240,7 +1218,7 @@ static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; - apic_reg_read(apic, offset, len, data); + kvm_lapic_reg_read(apic, offset, len, data); return 0; } @@ -1249,7 +1227,7 @@ static void update_divide_count(struct kvm_lapic *apic) { u32 tmp1, tmp2, tdcr; - tdcr = kvm_apic_get_reg(apic, APIC_TDCR); + tdcr = kvm_lapic_get_reg(apic, APIC_TDCR); tmp1 = tdcr & 0xf; tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1; apic->divide_count = 0x1 << (tmp2 & 0x7); @@ -1260,7 +1238,7 @@ static void update_divide_count(struct kvm_lapic *apic) static void apic_update_lvtt(struct kvm_lapic *apic) { - u32 timer_mode = kvm_apic_get_reg(apic, APIC_LVTT) & + u32 timer_mode = kvm_lapic_get_reg(apic, APIC_LVTT) & apic->lapic_timer.timer_mode_mask; if (apic->lapic_timer.timer_mode != timer_mode) { @@ -1296,7 +1274,7 @@ static void apic_timer_expired(struct kvm_lapic *apic) static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - u32 reg = kvm_apic_get_reg(apic, APIC_LVTT); + u32 reg = kvm_lapic_get_reg(apic, APIC_LVTT); if (kvm_apic_hw_enabled(apic)) { int vec = reg & APIC_VECTOR_MASK; @@ -1344,7 +1322,7 @@ static void start_apic_timer(struct kvm_lapic *apic) if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { /* lapic timer in oneshot or periodic mode */ now = apic->lapic_timer.timer.base->get_time(); - apic->lapic_timer.period = (u64)kvm_apic_get_reg(apic, APIC_TMICT) + apic->lapic_timer.period = (u64)kvm_lapic_get_reg(apic, APIC_TMICT) * APIC_BUS_CYCLE_NS * apic->divide_count; if (!apic->lapic_timer.period) @@ -1376,7 +1354,7 @@ static void start_apic_timer(struct kvm_lapic *apic) "timer initial count 0x%x, period %lldns, " "expire @ 0x%016" PRIx64 ".\n", __func__, APIC_BUS_CYCLE_NS, ktime_to_ns(now), - kvm_apic_get_reg(apic, APIC_TMICT), + kvm_lapic_get_reg(apic, APIC_TMICT), apic->lapic_timer.period, ktime_to_ns(ktime_add_ns(now, apic->lapic_timer.period))); @@ -1425,7 +1403,7 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) } } -static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) +int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) { int ret = 0; @@ -1457,7 +1435,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_DFR: if (!apic_x2apic_mode(apic)) { - apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); + kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); recalculate_apic_map(apic->vcpu->kvm); } else ret = 1; @@ -1465,17 +1443,17 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_SPIV: { u32 mask = 0x3ff; - if (kvm_apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI) + if (kvm_lapic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI) mask |= APIC_SPIV_DIRECTED_EOI; apic_set_spiv(apic, val & mask); if (!(val & APIC_SPIV_APIC_ENABLED)) { int i; u32 lvt_val; - for (i = 0; i < APIC_LVT_NUM; i++) { - lvt_val = kvm_apic_get_reg(apic, + for (i = 0; i < KVM_APIC_LVT_NUM; i++) { + lvt_val = kvm_lapic_get_reg(apic, APIC_LVTT + 0x10 * i); - apic_set_reg(apic, APIC_LVTT + 0x10 * i, + kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, lvt_val | APIC_LVT_MASKED); } apic_update_lvtt(apic); @@ -1486,14 +1464,14 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) } case APIC_ICR: /* No delay here, so we always clear the pending bit */ - apic_set_reg(apic, APIC_ICR, val & ~(1 << 12)); + kvm_lapic_set_reg(apic, APIC_ICR, val & ~(1 << 12)); apic_send_ipi(apic); break; case APIC_ICR2: if (!apic_x2apic_mode(apic)) val &= 0xff000000; - apic_set_reg(apic, APIC_ICR2, val); + kvm_lapic_set_reg(apic, APIC_ICR2, val); break; case APIC_LVT0: @@ -1507,7 +1485,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) val |= APIC_LVT_MASKED; val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4]; - apic_set_reg(apic, reg, val); + kvm_lapic_set_reg(apic, reg, val); break; @@ -1515,7 +1493,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask); - apic_set_reg(apic, APIC_LVTT, val); + kvm_lapic_set_reg(apic, APIC_LVTT, val); apic_update_lvtt(apic); break; @@ -1524,14 +1502,14 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) break; hrtimer_cancel(&apic->lapic_timer.timer); - apic_set_reg(apic, APIC_TMICT, val); + kvm_lapic_set_reg(apic, APIC_TMICT, val); start_apic_timer(apic); break; case APIC_TDCR: if (val & 4) apic_debug("KVM_WRITE:TDCR %x\n", val); - apic_set_reg(apic, APIC_TDCR, val); + kvm_lapic_set_reg(apic, APIC_TDCR, val); update_divide_count(apic); break; @@ -1544,7 +1522,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_SELF_IPI: if (apic_x2apic_mode(apic)) { - apic_reg_write(apic, APIC_ICR, 0x40000 | (val & 0xff)); + kvm_lapic_reg_write(apic, APIC_ICR, 0x40000 | (val & 0xff)); } else ret = 1; break; @@ -1556,6 +1534,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) apic_debug("Local APIC Write to read-only register %x\n", reg); return ret; } +EXPORT_SYMBOL_GPL(kvm_lapic_reg_write); static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, const void *data) @@ -1585,14 +1564,14 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, apic_debug("%s: offset 0x%x with length 0x%x, and value is " "0x%x\n", __func__, offset, len, val); - apic_reg_write(apic, offset & 0xff0, val); + kvm_lapic_reg_write(apic, offset & 0xff0, val); return 0; } void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) { - apic_reg_write(vcpu->arch.apic, APIC_EOI, 0); + kvm_lapic_reg_write(vcpu->arch.apic, APIC_EOI, 0); } EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); @@ -1604,10 +1583,10 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) /* hw has done the conditional check and inst decode */ offset &= 0xff0; - apic_reg_read(vcpu->arch.apic, offset, 4, &val); + kvm_lapic_reg_read(vcpu->arch.apic, offset, 4, &val); /* TODO: optimize to just emulate side effect w/o one more write */ - apic_reg_write(vcpu->arch.apic, offset, val); + kvm_lapic_reg_write(vcpu->arch.apic, offset, val); } EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode); @@ -1667,14 +1646,14 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) struct kvm_lapic *apic = vcpu->arch.apic; apic_set_tpr(apic, ((cr8 & 0x0f) << 4) - | (kvm_apic_get_reg(apic, APIC_TASKPRI) & 4)); + | (kvm_lapic_get_reg(apic, APIC_TASKPRI) & 4)); } u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) { u64 tpr; - tpr = (u64) kvm_apic_get_reg(vcpu->arch.apic, APIC_TASKPRI); + tpr = (u64) kvm_lapic_get_reg(vcpu->arch.apic, APIC_TASKPRI); return (tpr & 0xf0) >> 4; } @@ -1740,28 +1719,28 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_apic_set_id(apic, vcpu->vcpu_id); kvm_apic_set_version(apic->vcpu); - for (i = 0; i < APIC_LVT_NUM; i++) - apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); + for (i = 0; i < KVM_APIC_LVT_NUM; i++) + kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); apic_update_lvtt(apic); if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) - apic_set_reg(apic, APIC_LVT0, + kvm_lapic_set_reg(apic, APIC_LVT0, SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); - apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0)); + apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); - apic_set_reg(apic, APIC_DFR, 0xffffffffU); + kvm_lapic_set_reg(apic, APIC_DFR, 0xffffffffU); apic_set_spiv(apic, 0xff); - apic_set_reg(apic, APIC_TASKPRI, 0); + kvm_lapic_set_reg(apic, APIC_TASKPRI, 0); if (!apic_x2apic_mode(apic)) kvm_apic_set_ldr(apic, 0); - apic_set_reg(apic, APIC_ESR, 0); - apic_set_reg(apic, APIC_ICR, 0); - apic_set_reg(apic, APIC_ICR2, 0); - apic_set_reg(apic, APIC_TDCR, 0); - apic_set_reg(apic, APIC_TMICT, 0); + kvm_lapic_set_reg(apic, APIC_ESR, 0); + kvm_lapic_set_reg(apic, APIC_ICR, 0); + kvm_lapic_set_reg(apic, APIC_ICR2, 0); + kvm_lapic_set_reg(apic, APIC_TDCR, 0); + kvm_lapic_set_reg(apic, APIC_TMICT, 0); for (i = 0; i < 8; i++) { - apic_set_reg(apic, APIC_IRR + 0x10 * i, 0); - apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); - apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); + kvm_lapic_set_reg(apic, APIC_IRR + 0x10 * i, 0); + kvm_lapic_set_reg(apic, APIC_ISR + 0x10 * i, 0); + kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } apic->irr_pending = vcpu->arch.apicv_active; apic->isr_count = vcpu->arch.apicv_active ? 1 : 0; @@ -1806,7 +1785,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu) int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { - u32 reg = kvm_apic_get_reg(apic, lvt_type); + u32 reg = kvm_lapic_get_reg(apic, lvt_type); int vector, mode, trig_mode; if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) { @@ -1901,14 +1880,14 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) apic_update_ppr(apic); highest_irr = apic_find_highest_irr(apic); if ((highest_irr == -1) || - ((highest_irr & 0xF0) <= kvm_apic_get_reg(apic, APIC_PROCPRI))) + ((highest_irr & 0xF0) <= kvm_lapic_get_reg(apic, APIC_PROCPRI))) return -1; return highest_irr; } int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) { - u32 lvt0 = kvm_apic_get_reg(vcpu->arch.apic, APIC_LVT0); + u32 lvt0 = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LVT0); int r = 0; if (!kvm_apic_hw_enabled(vcpu->arch.apic)) @@ -1974,7 +1953,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, apic_update_ppr(apic); hrtimer_cancel(&apic->lapic_timer.timer); apic_update_lvtt(apic); - apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0)); + apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; @@ -1982,9 +1961,11 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { + if (kvm_x86_ops->apicv_post_state_restore) + kvm_x86_ops->apicv_post_state_restore(vcpu); kvm_x86_ops->hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); - kvm_x86_ops->hwapic_isr_update(vcpu->kvm, + kvm_x86_ops->hwapic_isr_update(vcpu, apic_find_highest_isr(apic)); } kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -2097,7 +2078,7 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - tpr = kvm_apic_get_reg(apic, APIC_TASKPRI) & 0xff; + tpr = kvm_lapic_get_reg(apic, APIC_TASKPRI) & 0xff; max_irr = apic_find_highest_irr(apic); if (max_irr < 0) max_irr = 0; @@ -2139,8 +2120,8 @@ int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data) /* if this is ICR write vector before command */ if (reg == APIC_ICR) - apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32)); - return apic_reg_write(apic, reg, (u32)data); + kvm_lapic_reg_write(apic, APIC_ICR2, (u32)(data >> 32)); + return kvm_lapic_reg_write(apic, reg, (u32)data); } int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data) @@ -2157,10 +2138,10 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data) return 1; } - if (apic_reg_read(apic, reg, 4, &low)) + if (kvm_lapic_reg_read(apic, reg, 4, &low)) return 1; if (reg == APIC_ICR) - apic_reg_read(apic, APIC_ICR2, 4, &high); + kvm_lapic_reg_read(apic, APIC_ICR2, 4, &high); *data = (((u64)high) << 32) | low; @@ -2176,8 +2157,8 @@ int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data) /* if this is ICR write vector before command */ if (reg == APIC_ICR) - apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32)); - return apic_reg_write(apic, reg, (u32)data); + kvm_lapic_reg_write(apic, APIC_ICR2, (u32)(data >> 32)); + return kvm_lapic_reg_write(apic, reg, (u32)data); } int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data) @@ -2188,10 +2169,10 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data) if (!lapic_in_kernel(vcpu)) return 1; - if (apic_reg_read(apic, reg, 4, &low)) + if (kvm_lapic_reg_read(apic, reg, 4, &low)) return 1; if (reg == APIC_ICR) - apic_reg_read(apic, APIC_ICR2, 4, &high); + kvm_lapic_reg_read(apic, APIC_ICR2, 4, &high); *data = (((u64)high) << 32) | low; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index f71183e502ee..891c6da7d4aa 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -7,6 +7,10 @@ #define KVM_APIC_INIT 0 #define KVM_APIC_SIPI 1 +#define KVM_APIC_LVT_NUM 6 + +#define KVM_APIC_SHORT_MASK 0xc0000 +#define KVM_APIC_DEST_MASK 0x800 struct kvm_timer { struct hrtimer timer; @@ -59,6 +63,11 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_apic_set_version(struct kvm_vcpu *vcpu); +int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val); +int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, + void *data); +bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, + int short_hand, unsigned int dest, int dest_mode); void __kvm_apic_update_irr(u32 *pir, void *regs); void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); @@ -99,9 +108,32 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data); void kvm_lapic_init(void); -static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off) +#define VEC_POS(v) ((v) & (32 - 1)) +#define REG_POS(v) (((v) >> 5) << 4) + +static inline void kvm_lapic_set_vector(int vec, void *bitmap) +{ + set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); +} + +static inline void kvm_lapic_set_irr(int vec, struct kvm_lapic *apic) +{ + kvm_lapic_set_vector(vec, apic->regs + APIC_IRR); + /* + * irr_pending must be true if any interrupt is pending; set it after + * APIC_IRR to avoid race with apic_clear_irr + */ + apic->irr_pending = true; +} + +static inline u32 kvm_lapic_get_reg(struct kvm_lapic *apic, int reg_off) +{ + return *((u32 *) (apic->regs + reg_off)); +} + +static inline void kvm_lapic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val) { - return *((u32 *) (apic->regs + reg_off)); + *((u32 *) (apic->regs + reg_off)) = val; } extern struct static_key kvm_no_apic_vcpu; @@ -169,7 +201,7 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) static inline int kvm_apic_id(struct kvm_lapic *apic) { - return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; + return (kvm_lapic_get_reg(apic, APIC_ID) >> 24) & 0xff; } bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 38c0c32926c9..24e800116ab4 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1909,18 +1909,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, * since it has been deleted from active_mmu_pages but still can be found * at hast list. * - * for_each_gfn_indirect_valid_sp has skipped that kind of page and - * kvm_mmu_get_page(), the only user of for_each_gfn_sp(), has skipped - * all the obsolete pages. + * for_each_gfn_valid_sp() has skipped that kind of pages. */ -#define for_each_gfn_sp(_kvm, _sp, _gfn) \ +#define for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ hlist_for_each_entry(_sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ - if ((_sp)->gfn != (_gfn)) {} else + if ((_sp)->gfn != (_gfn) || is_obsolete_sp((_kvm), (_sp)) \ + || (_sp)->role.invalid) {} else #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \ - for_each_gfn_sp(_kvm, _sp, _gfn) \ - if ((_sp)->role.direct || (_sp)->role.invalid) {} else + for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ + if ((_sp)->role.direct) {} else /* @sp->gfn should be write-protected at the call site */ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, @@ -1961,6 +1960,11 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } static void mmu_audit_disable(void) { } #endif +static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); +} + static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { @@ -2105,11 +2109,6 @@ static void clear_sp_write_flooding_count(u64 *spte) __clear_sp_write_flooding_count(sp); } -static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) -{ - return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); -} - static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gaddr, @@ -2136,10 +2135,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; } - for_each_gfn_sp(vcpu->kvm, sp, gfn) { - if (is_obsolete_sp(vcpu->kvm, sp)) - continue; - + for_each_gfn_valid_sp(vcpu->kvm, sp, gfn) { if (!need_sync && sp->unsync) need_sync = true; diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 3f8c732117ec..c146f3c262c3 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -44,8 +44,6 @@ static bool msr_mtrr_valid(unsigned msr) case MSR_MTRRdefType: case MSR_IA32_CR_PAT: return true; - case 0x2f8: - return true; } return false; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index fafd720ce10a..2214214c786b 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -14,6 +14,9 @@ * the COPYING file in the top-level directory. * */ + +#define pr_fmt(fmt) "SVM: " fmt + #include <linux/kvm_host.h> #include "irq.h" @@ -32,6 +35,7 @@ #include <linux/trace_events.h> #include <linux/slab.h> +#include <asm/apic.h> #include <asm/perf_event.h> #include <asm/tlbflush.h> #include <asm/desc.h> @@ -68,6 +72,8 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #define SVM_FEATURE_DECODE_ASSIST (1 << 7) #define SVM_FEATURE_PAUSE_FILTER (1 << 10) +#define SVM_AVIC_DOORBELL 0xc001011b + #define NESTED_EXIT_HOST 0 /* Exit handled on host level */ #define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ #define NESTED_EXIT_CONTINUE 2 /* Further checks needed */ @@ -78,6 +84,18 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #define TSC_RATIO_MIN 0x0000000000000001ULL #define TSC_RATIO_MAX 0x000000ffffffffffULL +#define AVIC_HPA_MASK ~((0xFFFULL << 52) || 0xFFF) + +/* + * 0xff is broadcast, so the max index allowed for physical APIC ID + * table is 0xfe. APIC IDs above 0xff are reserved. + */ +#define AVIC_MAX_PHYSICAL_ID_COUNT 255 + +#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 +#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 +#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF + static bool erratum_383_found __read_mostly; static const u32 host_save_user_msrs[] = { @@ -162,8 +180,21 @@ struct vcpu_svm { /* cached guest cpuid flags for faster access */ bool nrips_enabled : 1; + + u32 ldr_reg; + struct page *avic_backing_page; + u64 *avic_physical_id_cache; + bool avic_is_running; }; +#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) + +#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) +#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) +#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) +#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) + static DEFINE_PER_CPU(u64, current_tsc_ratio); #define TSC_RATIO_DEFAULT 0x0100000000ULL @@ -205,6 +236,10 @@ module_param(npt, int, S_IRUGO); static int nested = true; module_param(nested, int, S_IRUGO); +/* enable / disable AVIC */ +static int avic; +module_param(avic, int, S_IRUGO); + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -228,12 +263,18 @@ enum { VMCB_SEG, /* CS, DS, SS, ES, CPL */ VMCB_CR2, /* CR2 only */ VMCB_LBR, /* DBGCTL, BR_FROM, BR_TO, LAST_EX_FROM, LAST_EX_TO */ + VMCB_AVIC, /* AVIC APIC_BAR, AVIC APIC_BACKING_PAGE, + * AVIC PHYSICAL_TABLE pointer, + * AVIC LOGICAL_TABLE pointer + */ VMCB_DIRTY_MAX, }; /* TPR and CR2 are always written before VMRUN */ #define VMCB_ALWAYS_DIRTY_MASK ((1U << VMCB_INTR) | (1U << VMCB_CR2)) +#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL + static inline void mark_all_dirty(struct vmcb *vmcb) { vmcb->control.clean = 0; @@ -255,6 +296,23 @@ static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_svm, vcpu); } +static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) +{ + svm->vmcb->control.avic_vapic_bar = data & VMCB_AVIC_APIC_BAR_MASK; + mark_dirty(svm->vmcb, VMCB_AVIC); +} + +static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 *entry = svm->avic_physical_id_cache; + + if (!entry) + return false; + + return (READ_ONCE(*entry) & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); +} + static void recalc_intercepts(struct vcpu_svm *svm) { struct vmcb_control_area *c, *h; @@ -923,6 +981,12 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); + if (avic && (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC))) + avic = false; + + if (avic) + pr_info("AVIC enabled\n"); + return 0; err: @@ -1000,6 +1064,22 @@ static void svm_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } +static void avic_init_vmcb(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm- |