--- zzzz-none-000/linux-3.10.107/arch/x86/kvm/lapic.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/x86/kvm/lapic.c 2021-02-04 17:41:59.000000000 +0000 @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include "kvm_cache_regs.h" @@ -68,6 +69,9 @@ #define MAX_APIC_VECTOR 256 #define APIC_VECTORS_PER_REG 32 +#define APIC_BROADCAST 0xFF +#define X2APIC_BROADCAST 0xFFFFFFFFul + #define VEC_POS(v) ((v) & (32 - 1)) #define REG_POS(v) (((v) >> 5) << 4) @@ -76,16 +80,6 @@ *((u32 *) (apic->regs + reg_off)) = val; } -static inline int apic_test_and_set_vector(int vec, void *bitmap) -{ - return test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - -static inline int apic_test_and_clear_vector(int vec, void *bitmap) -{ - return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - static inline int apic_test_vector(int vec, void *bitmap) { return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); @@ -122,17 +116,6 @@ struct static_key_deferred apic_hw_disabled __read_mostly; struct static_key_deferred apic_sw_disabled __read_mostly; -static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) -{ - if ((kvm_apic_get_reg(apic, APIC_SPIV) ^ val) & APIC_SPIV_APIC_ENABLED) { - if (val & APIC_SPIV_APIC_ENABLED) - static_key_slow_dec_deferred(&apic_sw_disabled); - else - static_key_slow_inc(&apic_sw_disabled.key); - } - apic_set_reg(apic, APIC_SPIV, val); -} - static inline int apic_enabled(struct kvm_lapic *apic) { return kvm_apic_sw_enabled(apic) && kvm_apic_hw_enabled(apic); @@ -150,7 +133,27 @@ return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; } -#define KVM_X2APIC_CID_BITS 0 +/* The logical map is definitely wrong if we have multiple + * modes at the same time. (Physical map is always right.) + */ +static inline bool kvm_apic_logical_map_valid(struct kvm_apic_map *map) +{ + return !(map->mode & (map->mode - 1)); +} + +static inline void +apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid) +{ + unsigned lid_bits; + + BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_CLUSTER != 4); + BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_FLAT != 8); + BUILD_BUG_ON(KVM_APIC_MODE_X2APIC != 16); + lid_bits = map->mode; + + *cid = dest_id >> lid_bits; + *lid = dest_id & ((1 << lid_bits) - 1); +} static void recalculate_apic_map(struct kvm *kvm) { @@ -165,47 +168,36 @@ if (!new) goto out; - new->ldr_bits = 8; - /* flat mode is default */ - new->cid_shift = 8; - new->cid_mask = 0; - new->lid_mask = 0xff; - kvm_for_each_vcpu(i, vcpu, kvm) { struct kvm_lapic *apic = vcpu->arch.apic; u16 cid, lid; - u32 ldr; + u32 ldr, aid; if (!kvm_apic_present(vcpu)) continue; - /* - * All APICs have to be configured in the same mode by an OS. - * We take advatage of this while building logical id loockup - * table. After reset APICs are in xapic/flat mode, so if we - * find apic with different setting we assume this is the mode - * OS wants all apics to be in; build lookup table accordingly. - */ + aid = kvm_apic_id(apic); + ldr = kvm_apic_get_reg(apic, APIC_LDR); + + if (aid < ARRAY_SIZE(new->phys_map)) + new->phys_map[aid] = apic; + if (apic_x2apic_mode(apic)) { - new->ldr_bits = 32; - new->cid_shift = 16; - new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1; - new->lid_mask = 0xffff; - } else if (kvm_apic_sw_enabled(apic) && - !new->cid_mask /* flat mode */ && - kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) { - new->cid_shift = 4; - new->cid_mask = 0xf; - new->lid_mask = 0xf; + 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) + new->mode |= KVM_APIC_MODE_XAPIC_FLAT; + else + new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER; } - new->phys_map[kvm_apic_id(apic)] = apic; + if (!kvm_apic_logical_map_valid(new)) + continue; - ldr = kvm_apic_get_reg(apic, APIC_LDR); - cid = apic_cluster_id(new, ldr); - lid = apic_logical_id(new, ldr); + apic_logical_id(new, ldr, &cid, &lid); - if (lid) + if (lid && cid < ARRAY_SIZE(new->logical_map)) new->logical_map[cid][ffs(lid) - 1] = apic; } out: @@ -217,7 +209,23 @@ if (old) kfree_rcu(old, rcu); - kvm_vcpu_request_scan_ioapic(kvm); + kvm_make_scan_ioapic_request(kvm); +} + +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); + + if (enabled != apic->sw_enabled) { + apic->sw_enabled = enabled; + if (enabled) { + static_key_slow_dec_deferred(&apic_sw_disabled); + recalculate_apic_map(apic->vcpu->kvm); + } else + static_key_slow_inc(&apic_sw_disabled.key); + } } static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id) @@ -232,6 +240,15 @@ recalculate_apic_map(apic->vcpu->kvm); } +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); + 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); @@ -244,21 +261,17 @@ static inline int apic_lvtt_oneshot(struct kvm_lapic *apic) { - return ((kvm_apic_get_reg(apic, APIC_LVTT) & - apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_ONESHOT); + return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_ONESHOT; } static inline int apic_lvtt_period(struct kvm_lapic *apic) { - return ((kvm_apic_get_reg(apic, APIC_LVTT) & - apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_PERIODIC); + return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_PERIODIC; } static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic) { - return ((kvm_apic_get_reg(apic, APIC_LVTT) & - apic->lapic_timer.timer_mode_mask) == - APIC_LVT_TIMER_TSCDEADLINE); + return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_TSCDEADLINE; } static inline int apic_lvt_nmi_mode(u32 lvt_val) @@ -318,23 +331,36 @@ return count; } -void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) +void __kvm_apic_update_irr(u32 *pir, void *regs) { u32 i, pir_val; - struct kvm_lapic *apic = vcpu->arch.apic; for (i = 0; i <= 7; i++) { pir_val = xchg(&pir[i], 0); if (pir_val) - *((u32 *)(apic->regs + APIC_IRR + i * 0x10)) |= pir_val; + *((u32 *)(regs + APIC_IRR + i * 0x10)) |= pir_val; } } +EXPORT_SYMBOL_GPL(__kvm_apic_update_irr); + +void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + __kvm_apic_update_irr(pir, apic->regs); + + kvm_make_request(KVM_REQ_EVENT, vcpu); +} EXPORT_SYMBOL_GPL(kvm_apic_update_irr); -static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic) +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; - return apic_test_and_set_vector(vec, apic->regs + APIC_IRR); } static inline int apic_search_irr(struct kvm_lapic *apic) @@ -366,13 +392,15 @@ vcpu = apic->vcpu; - apic_clear_vector(vec, apic->regs + APIC_IRR); - if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + if (unlikely(kvm_vcpu_apic_vid_enabled(vcpu))) { /* try to update RVI */ + apic_clear_vector(vec, apic->regs + APIC_IRR); kvm_make_request(KVM_REQ_EVENT, vcpu); - else { - vec = apic_search_irr(apic); - apic->irr_pending = (vec != -1); + } else { + apic->irr_pending = false; + apic_clear_vector(vec, apic->regs + APIC_IRR); + if (apic_search_irr(apic) != -1) + apic->irr_pending = true; } } @@ -390,7 +418,7 @@ * because the processor can modify ISR under the hood. Instead * just set SVI. */ - if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + if (unlikely(kvm_x86_ops->hwapic_isr_update)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec); else { ++apic->isr_count; @@ -438,7 +466,7 @@ * on the other hand isr_count and highest_isr_cache are unused * and must be left alone. */ - if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + if (unlikely(kvm_x86_ops->hwapic_isr_update)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); else { @@ -501,7 +529,7 @@ u8 val; if (pv_eoi_get_user(vcpu, &val) < 0) apic_debug("Can't read EOI MSR value: 0x%llx\n", - (unsigned long long)vcpi->arch.pv_eoi.msr_val); + (unsigned long long)vcpu->arch.pv_eoi.msr_val); return val & 0x1; } @@ -509,7 +537,7 @@ { if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) { apic_debug("Can't set EOI MSR value: 0x%llx\n", - (unsigned long long)vcpi->arch.pv_eoi.msr_val); + (unsigned long long)vcpu->arch.pv_eoi.msr_val); return; } __set_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); @@ -519,21 +547,12 @@ { if (pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) { apic_debug("Can't clear EOI MSR value: 0x%llx\n", - (unsigned long long)vcpi->arch.pv_eoi.msr_val); + (unsigned long long)vcpu->arch.pv_eoi.msr_val); return; } __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - int i; - - for (i = 0; i < 8; i++) - apic_set_reg(apic, APIC_TMR + 0x10 * i, tmr[i]); -} - static void apic_update_ppr(struct kvm_lapic *apic) { u32 tpr, isrv, ppr, old_ppr; @@ -565,47 +584,75 @@ apic_update_ppr(apic); } -int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest) +static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda) { - return dest == 0xff || kvm_apic_id(apic) == dest; + if (apic_x2apic_mode(apic)) + return mda == X2APIC_BROADCAST; + + return GET_APIC_DEST_FIELD(mda) == APIC_BROADCAST; } -int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) +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_apic_id(apic); + + return mda == SET_APIC_DEST_FIELD(kvm_apic_id(apic)); +} + +static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) { - int result = 0; u32 logical_id; - if (apic_x2apic_mode(apic)) { - logical_id = kvm_apic_get_reg(apic, APIC_LDR); - return logical_id & mda; - } + if (kvm_apic_broadcast(apic, mda)) + return true; - logical_id = GET_APIC_LOGICAL_ID(kvm_apic_get_reg(apic, APIC_LDR)); + logical_id = kvm_apic_get_reg(apic, APIC_LDR); + + if (apic_x2apic_mode(apic)) + return ((logical_id >> 16) == (mda >> 16)) + && (logical_id & mda & 0xffff) != 0; + + logical_id = GET_APIC_LOGICAL_ID(logical_id); + mda = GET_APIC_DEST_FIELD(mda); switch (kvm_apic_get_reg(apic, APIC_DFR)) { case APIC_DFR_FLAT: - if (logical_id & mda) - result = 1; - break; + return (logical_id & mda) != 0; case APIC_DFR_CLUSTER: - if (((logical_id >> 4) == (mda >> 0x4)) - && (logical_id & mda & 0xf)) - result = 1; - break; + return ((logical_id >> 4) == (mda >> 4)) + && (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)); - break; + return false; } +} - return result; +/* KVM APIC implementation has two quirks + * - dest always begins at 0 while xAPIC MDA has offset 24, + * - IOxAPIC messages have to be delivered (directly) to x2APIC. + */ +static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source, + struct kvm_lapic *target) +{ + bool ipi = source != NULL; + bool x2apic_mda = apic_x2apic_mode(ipi ? source : target); + + if (!ipi && dest_id == APIC_BROADCAST && x2apic_mda) + return X2APIC_BROADCAST; + + return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id); } -int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, int dest, int dest_mode) +bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, + int short_hand, unsigned int dest, int dest_mode) { - int result = 0; struct kvm_lapic *target = vcpu->arch.apic; + u32 mda = kvm_apic_mda(dest, source, target); apic_debug("target %p, source %p, dest 0x%x, " "dest_mode 0x%x, short_hand 0x%x\n", @@ -614,29 +661,21 @@ ASSERT(target); switch (short_hand) { case APIC_DEST_NOSHORT: - if (dest_mode == 0) - /* Physical mode. */ - result = kvm_apic_match_physical_addr(target, dest); + if (dest_mode == APIC_DEST_PHYSICAL) + return kvm_apic_match_physical_addr(target, mda); else - /* Logical mode. */ - result = kvm_apic_match_logical_addr(target, dest); - break; + return kvm_apic_match_logical_addr(target, mda); case APIC_DEST_SELF: - result = (target == source); - break; + return target == source; case APIC_DEST_ALLINC: - result = 1; - break; + return true; case APIC_DEST_ALLBUT: - result = (target != source); - break; + return target != source; default: apic_debug("kvm: apic: Bad dest shorthand value %x\n", short_hand); - break; + return false; } - - return result; } bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, @@ -646,7 +685,7 @@ unsigned long bitmap = 1; struct kvm_lapic **dst; int i; - bool ret = false; + bool ret, x2apic_ipi; *r = -1; @@ -658,25 +697,40 @@ if (irq->shorthand) return false; + x2apic_ipi = src && apic_x2apic_mode(src); + if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST)) + return false; + + ret = true; rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); - if (!map) + if (!map) { + ret = false; goto out; + } - if (irq->dest_mode == 0) { /* physical mode */ - if (irq->delivery_mode == APIC_DM_LOWEST || - irq->dest_id == 0xff) + if (irq->dest_mode == APIC_DEST_PHYSICAL) { + if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) goto out; - dst = &map->phys_map[irq->dest_id & 0xff]; + + dst = &map->phys_map[irq->dest_id]; } else { - u32 mda = irq->dest_id << (32 - map->ldr_bits); + u16 cid; - dst = map->logical_map[apic_cluster_id(map, mda)]; + if (!kvm_apic_logical_map_valid(map)) { + ret = false; + goto out; + } - bitmap = apic_logical_id(map, mda); + apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); - if (irq->delivery_mode == APIC_DM_LOWEST) { + if (cid >= ARRAY_SIZE(map->logical_map)) + goto out; + + dst = map->logical_map[cid]; + + if (kvm_lowest_prio_delivery(irq)) { int l = -1; for_each_set_bit(i, &bitmap, 16) { if (!dst[i]) @@ -698,6 +752,63 @@ *r = 0; *r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map); } +out: + rcu_read_unlock(); + return ret; +} + +bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu) +{ + struct kvm_apic_map *map; + bool ret = false; + struct kvm_lapic *dst = NULL; + + if (irq->shorthand) + return false; + + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); + + if (!map) + goto out; + + if (irq->dest_mode == APIC_DEST_PHYSICAL) { + if (irq->dest_id == 0xFF) + goto out; + + if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) + goto out; + + dst = map->phys_map[irq->dest_id]; + if (dst && kvm_apic_present(dst->vcpu)) + *dest_vcpu = dst->vcpu; + else + goto out; + } else { + u16 cid; + unsigned long bitmap = 1; + int i, r = 0; + + if (!kvm_apic_logical_map_valid(map)) + goto out; + + apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); + + if (cid >= ARRAY_SIZE(map->logical_map)) + goto out; + + for_each_set_bit(i, &bitmap, 16) { + dst = map->logical_map[cid][i]; + if (++r == 2) + goto out; + } + + if (dst && kvm_apic_present(dst->vcpu)) + *dest_vcpu = dst->vcpu; + else + goto out; + } ret = true; out: @@ -716,44 +827,52 @@ int result = 0; struct kvm_vcpu *vcpu = apic->vcpu; + trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector); switch (delivery_mode) { case APIC_DM_LOWEST: vcpu->arch.apic_arb_prio++; case APIC_DM_FIXED: + if (unlikely(trig_mode && !level)) + break; + /* FIXME add logic for vcpu on reset */ if (unlikely(!apic_enabled(apic))) break; + result = 1; + if (dest_map) __set_bit(vcpu->vcpu_id, dest_map); - if (kvm_x86_ops->deliver_posted_interrupt) { - result = 1; - kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); - } else { - result = !apic_test_and_set_irr(vector, apic); + if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) { + if (trig_mode) + apic_set_vector(vector, apic->regs + APIC_TMR); + else + apic_clear_vector(vector, apic->regs + APIC_TMR); + } - if (!result) { - if (trig_mode) - apic_debug("level trig mode repeatedly " - "for vector %d", vector); - goto out; - } + if (kvm_x86_ops->deliver_posted_interrupt) + kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); + else { + apic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } -out: - trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode, - trig_mode, vector, !result); break; case APIC_DM_REMRD: - apic_debug("Ignoring delivery mode 3\n"); + result = 1; + vcpu->arch.pv.pv_unhalted = 1; + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); break; case APIC_DM_SMI: - apic_debug("Ignoring guest SMI\n"); + result = 1; + kvm_make_request(KVM_REQ_SMI, vcpu); + kvm_vcpu_kick(vcpu); break; case APIC_DM_NMI: @@ -811,17 +930,32 @@ return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; } +static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector) +{ + return test_bit(vector, (ulong *)apic->vcpu->arch.eoi_exit_bitmap); +} + static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) { - if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) && - kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { - int trigger_mode; - if (apic_test_vector(vector, apic->regs + APIC_TMR)) - trigger_mode = IOAPIC_LEVEL_TRIG; - else - trigger_mode = IOAPIC_EDGE_TRIG; - kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); + int trigger_mode; + + /* Eoi the ioapic only if the ioapic doesn't own the vector. */ + if (!kvm_ioapic_handles_vector(apic, vector)) + return; + + /* Request a KVM exit to inform the userspace IOAPIC. */ + if (irqchip_split(apic->vcpu->kvm)) { + apic->vcpu->arch.pending_ioapic_eoi = vector; + kvm_make_request(KVM_REQ_IOAPIC_EOI_EXIT, apic->vcpu); + return; } + + if (apic_test_vector(vector, apic->regs + APIC_TMR)) + trigger_mode = IOAPIC_LEVEL_TRIG; + else + trigger_mode = IOAPIC_EDGE_TRIG; + + kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); } static int apic_set_eoi(struct kvm_lapic *apic) @@ -869,9 +1003,10 @@ irq.vector = icr_low & APIC_VECTOR_MASK; irq.delivery_mode = icr_low & APIC_MODE_MASK; irq.dest_mode = icr_low & APIC_DEST_MASK; - irq.level = icr_low & APIC_INT_ASSERT; + irq.level = (icr_low & APIC_INT_ASSERT) != 0; irq.trig_mode = icr_low & APIC_INT_LEVELTRIG; irq.shorthand = icr_low & APIC_SHORT_MASK; + irq.msi_redir_hint = false; if (apic_x2apic_mode(apic)) irq.dest_id = icr_high; else @@ -881,10 +1016,11 @@ apic_debug("icr_high 0x%x, icr_low 0x%x, " "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, " - "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n", + "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x, " + "msi_redir_hint 0x%x\n", icr_high, icr_low, irq.shorthand, irq.dest_id, irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, - irq.vector); + irq.vector, irq.msi_redir_hint); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL); } @@ -1018,7 +1154,7 @@ addr < apic->base_address + LAPIC_MMIO_LENGTH; } -static int apic_mmio_read(struct kvm_io_device *this, +static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1045,9 +1181,87 @@ apic->divide_count); } +static void apic_update_lvtt(struct kvm_lapic *apic) +{ + u32 timer_mode = kvm_apic_get_reg(apic, APIC_LVTT) & + apic->lapic_timer.timer_mode_mask; + + if (apic->lapic_timer.timer_mode != timer_mode) { + apic->lapic_timer.timer_mode = timer_mode; + hrtimer_cancel(&apic->lapic_timer.timer); + } +} + +static void apic_timer_expired(struct kvm_lapic *apic) +{ + struct kvm_vcpu *vcpu = apic->vcpu; + wait_queue_head_t *q = &vcpu->wq; + struct kvm_timer *ktimer = &apic->lapic_timer; + + if (atomic_read(&apic->lapic_timer.pending)) + return; + + atomic_inc(&apic->lapic_timer.pending); + kvm_set_pending_timer(vcpu); + + if (waitqueue_active(q)) + wake_up_interruptible(q); + + if (apic_lvtt_tscdeadline(apic)) + ktimer->expired_tscdeadline = ktimer->tscdeadline; +} + +/* + * On APICv, this test will cause a busy wait + * during a higher-priority task. + */ + +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); + + if (kvm_apic_hw_enabled(apic)) { + int vec = reg & APIC_VECTOR_MASK; + void *bitmap = apic->regs + APIC_ISR; + + if (kvm_x86_ops->deliver_posted_interrupt) + bitmap = apic->regs + APIC_IRR; + + if (apic_test_vector(vec, bitmap)) + return true; + } + return false; +} + +void wait_lapic_expire(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + u64 guest_tsc, tsc_deadline; + + if (!kvm_vcpu_has_lapic(vcpu)) + return; + + if (apic->lapic_timer.expired_tscdeadline == 0) + return; + + if (!lapic_timer_int_injected(vcpu)) + return; + + tsc_deadline = apic->lapic_timer.expired_tscdeadline; + apic->lapic_timer.expired_tscdeadline = 0; + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); + + /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ + if (guest_tsc < tsc_deadline) + __delay(tsc_deadline - guest_tsc); +} + static void start_apic_timer(struct kvm_lapic *apic) { ktime_t now; + atomic_set(&apic->lapic_timer.pending, 0); if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { @@ -1093,6 +1307,7 @@ /* lapic timer in tsc deadline mode */ u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; u64 ns = 0; + ktime_t expire; struct kvm_vcpu *vcpu = apic->vcpu; unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz; unsigned long flags; @@ -1103,13 +1318,16 @@ local_irq_save(flags); now = apic->lapic_timer.timer.base->get_time(); - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc()); + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); if (likely(tscdeadline > guest_tsc)) { ns = (tscdeadline - guest_tsc) * 1000000ULL; do_div(ns, this_tsc_khz); - } - hrtimer_start(&apic->lapic_timer.timer, - ktime_add_ns(now, ns), HRTIMER_MODE_ABS); + 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); + } else + apic_timer_expired(apic); local_irq_restore(flags); } @@ -1117,16 +1335,17 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) { - int nmi_wd_enabled = apic_lvt_nmi_mode(kvm_apic_get_reg(apic, APIC_LVT0)); + bool lvt0_in_nmi_mode = apic_lvt_nmi_mode(lvt0_val); - if (apic_lvt_nmi_mode(lvt0_val)) { - if (!nmi_wd_enabled) { + if (apic->lvt0_in_nmi_mode != lvt0_in_nmi_mode) { + apic->lvt0_in_nmi_mode = lvt0_in_nmi_mode; + if (lvt0_in_nmi_mode) { apic_debug("Receive NMI setting on APIC_LVT0 " "for cpu %d\n", apic->vcpu->vcpu_id); atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); - } - } else if (nmi_wd_enabled) - atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); + } else + atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); + } } static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) @@ -1182,6 +1401,7 @@ apic_set_reg(apic, APIC_LVTT + 0x10 * i, lvt_val | APIC_LVT_MASKED); } + apic_update_lvtt(apic); atomic_set(&apic->lapic_timer.pending, 0); } @@ -1215,15 +1435,11 @@ break; case APIC_LVTT: - if ((kvm_apic_get_reg(apic, APIC_LVTT) & - apic->lapic_timer.timer_mode_mask) != - (val & apic->lapic_timer.timer_mode_mask)) - hrtimer_cancel(&apic->lapic_timer.timer); - 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); + apic_update_lvtt(apic); break; case APIC_TMICT: @@ -1264,7 +1480,7 @@ return ret; } -static int apic_mmio_write(struct kvm_io_device *this, +static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, const void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1331,7 +1547,7 @@ if (!(vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE)) static_key_slow_dec_deferred(&apic_hw_disabled); - if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED)) + if (!apic->sw_enabled) static_key_slow_dec_deferred(&apic_sw_disabled); if (apic->regs) @@ -1404,8 +1620,6 @@ return; } - if (!kvm_vcpu_is_bsp(apic->vcpu)) - value &= ~MSR_IA32_APICBASE_BSP; vcpu->arch.apic_base = value; /* update jump label if enable bit changes */ @@ -1419,9 +1633,7 @@ if ((old_value ^ value) & X2APIC_ENABLE) { if (value & X2APIC_ENABLE) { - u32 id = kvm_apic_id(apic); - u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); - kvm_apic_set_ldr(apic, ldr); + kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true); } else kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false); @@ -1430,13 +1642,17 @@ apic->base_address = apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; + if ((value & MSR_IA32_APICBASE_ENABLE) && + apic->base_address != APIC_DEFAULT_PHYS_BASE) + pr_warn_once("APIC base relocation is unsupported by KVM"); + /* with FSB delivery interrupt, we can restart APIC functionality */ apic_debug("apic base msr is 0x%016" PRIx64 ", and base address is " "0x%lx.\n", apic->vcpu->arch.apic_base, apic->base_address); } -void kvm_lapic_reset(struct kvm_vcpu *vcpu) +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic; int i; @@ -1450,18 +1666,23 @@ /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); - kvm_apic_set_id(apic, vcpu->vcpu_id); + if (!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); - apic_set_reg(apic, APIC_LVT0, - SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); + apic_update_lvtt(apic); + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) + apic_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_set_reg(apic, APIC_DFR, 0xffffffffU); apic_set_spiv(apic, 0xff); apic_set_reg(apic, APIC_TASKPRI, 0); - kvm_apic_set_ldr(apic, 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); @@ -1472,8 +1693,8 @@ apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } - apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm); - apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm); + apic->irr_pending = kvm_vcpu_apic_vid_enabled(vcpu); + apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0; apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -1486,7 +1707,7 @@ vcpu->arch.apic_arb_prio = 0; vcpu->arch.apic_attention = 0; - apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr=" + apic_debug("%s: vcpu=%p, id=%d, base_msr=" "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__, vcpu, kvm_apic_id(apic), vcpu->arch.apic_base, apic->base_address); @@ -1546,23 +1767,8 @@ { struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer); - struct kvm_vcpu *vcpu = apic->vcpu; - wait_queue_head_t *q = &vcpu->wq; - /* - * There is a race window between reading and incrementing, but we do - * not care about potentially losing timer events in the !reinject - * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked - * in vcpu_enter_guest. - */ - if (!atomic_read(&ktimer->pending)) { - atomic_inc(&ktimer->pending); - /* FIXME: this code should not know anything about vcpus */ - kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu); - } - - if (waitqueue_active(q)) - wake_up_interruptible(q); + apic_timer_expired(apic); if (lapic_is_periodic(apic)) { hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); @@ -1605,7 +1811,7 @@ APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE); static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ - kvm_lapic_reset(vcpu); + kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; @@ -1652,8 +1858,10 @@ return; if (atomic_read(&apic->lapic_timer.pending) > 0) { - if (kvm_apic_local_deliver(apic, APIC_LVTT)) - atomic_dec(&apic->lapic_timer.pending); + kvm_apic_local_deliver(apic, APIC_LVTT); + if (apic_lvtt_tscdeadline(apic)) + apic->lapic_timer.tscdeadline = 0; + atomic_set(&apic->lapic_timer.pending, 0); } } @@ -1693,15 +1901,25 @@ 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)); update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; - apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ? + apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; - kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); + if (kvm_x86_ops->hwapic_irr_update) + kvm_x86_ops->hwapic_irr_update(vcpu, + apic_find_highest_irr(apic)); + if (unlikely(kvm_x86_ops->hwapic_isr_update)) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, + apic_find_highest_isr(apic)); kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_rtc_eoi_tracking_restore_one(vcpu); + if (ioapic_in_kernel(vcpu->kvm)) + kvm_rtc_eoi_tracking_restore_one(vcpu); + + vcpu->arch.apic_arb_prio = 0; } void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) @@ -1763,8 +1981,9 @@ if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, - sizeof(u32)); + if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32))) + return; apic_set_tpr(vcpu->arch.apic, data & 0xff); } @@ -1784,7 +2003,7 @@ /* Cache not set: could be safe but we don't bother. */ apic->highest_isr_cache == -1 || /* Need EOI to update ioapic. */ - kvm_ioapic_handles_vector(vcpu->kvm, apic->highest_isr_cache)) { + kvm_ioapic_handles_vector(apic, apic->highest_isr_cache)) { /* * PV EOI was disabled by apic_sync_pv_eoi_from_guest * so we need not do anything here. @@ -1840,11 +2059,14 @@ struct kvm_lapic *apic = vcpu->arch.apic; u32 reg = (msr - APIC_BASE_MSR) << 4; - if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic)) + if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) + return 1; + + if (reg == APIC_ICR2) return 1; /* if this is ICR write vector before command */ - if (msr == 0x830) + if (reg == APIC_ICR) apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32)); return apic_reg_write(apic, reg, (u32)data); } @@ -1854,12 +2076,18 @@ struct kvm_lapic *apic = vcpu->arch.apic; u32 reg = (msr - APIC_BASE_MSR) << 4, low, high = 0; - if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic)) + if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) + return 1; + + if (reg == APIC_DFR || reg == APIC_ICR2) { + apic_debug("KVM_APIC_READ: read x2apic reserved register %x\n", + reg); return 1; + } if (apic_reg_read(apic, reg, 4, &low)) return 1; - if (msr == 0x830) + if (reg == APIC_ICR) apic_reg_read(apic, APIC_ICR2, 4, &high); *data = (((u64)high) << 32) | low; @@ -1914,17 +2142,28 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - unsigned int sipi_vector; + u8 sipi_vector; unsigned long pe; if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events) return; - pe = xchg(&apic->pending_events, 0); + /* + * INITs are latched while in SMM. Because an SMM CPU cannot + * be in KVM_MP_STATE_INIT_RECEIVED state, just eat SIPIs + * and delay processing of INIT until the next RSM. + */ + if (is_smm(vcpu)) { + WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); + if (test_bit(KVM_APIC_SIPI, &apic->pending_events)) + clear_bit(KVM_APIC_SIPI, &apic->pending_events); + return; + } + pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { - kvm_lapic_reset(vcpu); - kvm_vcpu_reset(vcpu); + kvm_lapic_reset(vcpu, true); + kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else @@ -1935,7 +2174,7 @@ /* evaluate pending_events before reading the vector */ smp_rmb(); sipi_vector = apic->sipi_vector; - pr_debug("vcpu %d received sipi with vector # %x\n", + apic_debug("vcpu %d received sipi with vector # %x\n", vcpu->vcpu_id, sipi_vector); kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector); vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -1948,3 +2187,9 @@ jump_label_rate_limit(&apic_hw_disabled, HZ); jump_label_rate_limit(&apic_sw_disabled, HZ); } + +void kvm_lapic_exit(void) +{ + static_key_deferred_flush(&apic_hw_disabled); + static_key_deferred_flush(&apic_sw_disabled); +}