diff options
Diffstat (limited to 'arch/x86/kvm/lapic.c')
| -rw-r--r-- | arch/x86/kvm/lapic.c | 741 |
1 files changed, 421 insertions, 320 deletions
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 1a2da0e5a373..23b99f305382 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -25,7 +25,7 @@ #include <linux/smp.h> #include <linux/hrtimer.h> #include <linux/io.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/math64.h> #include <linux/slab.h> #include <asm/processor.h> @@ -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)); @@ -129,26 +115,43 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -/* 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 bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, + u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) { + switch (map->mode) { + case KVM_APIC_MODE_X2APIC: { + u32 offset = (dest_id >> 16) * 16; + u32 max_apic_id = map->max_apic_id; + + if (offset <= max_apic_id) { + u8 cluster_size = min(max_apic_id - offset + 1, 16U); + + *cluster = &map->phys_map[offset]; + *mask = dest_id & (0xffff >> (16 - cluster_size)); + } else { + *mask = 0; + } + + return true; + } + case KVM_APIC_MODE_XAPIC_FLAT: + *cluster = map->xapic_flat_map; + *mask = dest_id & 0xff; + return true; + case KVM_APIC_MODE_XAPIC_CLUSTER: + *cluster = map->xapic_cluster_map[dest_id >> 4]; + *mask = dest_id & 0xf; + return true; + default: + /* Not optimized. */ + return false; + } } -static inline void -apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid) +static void kvm_apic_map_free(struct rcu_head *rcu) { - 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; + struct kvm_apic_map *map = container_of(rcu, struct kvm_apic_map, rcu); - *cid = dest_id >> lid_bits; - *lid = dest_id & ((1 << lid_bits) - 1); + kvfree(map); } static void recalculate_apic_map(struct kvm *kvm) @@ -156,45 +159,52 @@ static void recalculate_apic_map(struct kvm *kvm) struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; int i; - - new = kzalloc(sizeof(struct kvm_apic_map), GFP_KERNEL); + u32 max_id = 255; mutex_lock(&kvm->arch.apic_map_lock); + kvm_for_each_vcpu(i, vcpu, kvm) + if (kvm_apic_present(vcpu)) + max_id = max(max_id, kvm_apic_id(vcpu->arch.apic)); + + new = kvm_kvzalloc(sizeof(struct kvm_apic_map) + + sizeof(struct kvm_lapic *) * ((u64)max_id + 1)); + if (!new) goto out; + new->max_apic_id = max_id; + kvm_for_each_vcpu(i, vcpu, kvm) { struct kvm_lapic *apic = vcpu->arch.apic; - u16 cid, lid; + struct kvm_lapic **cluster; + u16 mask; u32 ldr, aid; if (!kvm_apic_present(vcpu)) 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)) + if (aid <= new->max_apic_id) new->phys_map[aid] = apic; if (apic_x2apic_mode(apic)) { 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; } - if (!kvm_apic_logical_map_valid(new)) + if (!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask)) continue; - apic_logical_id(new, ldr, &cid, &lid); - - if (lid && cid < ARRAY_SIZE(new->logical_map)) - new->logical_map[cid][ffs(lid) - 1] = apic; + if (mask) + cluster[ffs(mask) - 1] = apic; } out: old = rcu_dereference_protected(kvm->arch.apic_map, @@ -203,7 +213,7 @@ out: mutex_unlock(&kvm->arch.apic_map_lock); if (old) - kfree_rcu(old, rcu); + call_rcu(&old->rcu, kvm_apic_map_free); kvm_make_scan_ioapic_request(kvm); } @@ -212,7 +222,7 @@ 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; @@ -224,35 +234,35 @@ 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) +static inline void kvm_apic_set_xapic_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); } -static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id) +static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 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); + 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 +297,10 @@ 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 +359,6 @@ 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 +416,7 @@ 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 +464,7 @@ 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 +549,8 @@ 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 +563,7 @@ 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 +571,7 @@ 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 +601,7 @@ 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 +610,7 @@ 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: @@ -618,22 +618,35 @@ 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; } } -/* 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. +/* The KVM local APIC implementation has two quirks: + * + * - the xAPIC MDA stores the destination at bits 24-31, while this + * is not true of struct kvm_lapic_irq's dest_id field. This is + * just a quirk in the API and is not problematic. + * + * - in-kernel IOAPIC messages have to be delivered directly to + * x2APIC, because the kernel does not support interrupt remapping. + * In order to support broadcast without interrupt remapping, x2APIC + * rewrites the destination of non-IPI messages from APIC_BROADCAST + * to X2APIC_BROADCAST. + * + * The broadcast quirk can be disabled with KVM_CAP_X2APIC_API. This is + * important when userspace wants to use x2APIC-format MSIs, because + * APIC_BROADCAST (0xff) is a legal route for "cluster 0, CPUs 0-7". */ -static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source, - struct kvm_lapic *target) +static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, 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) + if (!vcpu->kvm->arch.x2apic_broadcast_quirk_disabled && + !ipi && dest_id == APIC_BROADCAST && x2apic_mda) return X2APIC_BROADCAST; return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id); @@ -643,7 +656,7 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode) { struct kvm_lapic *target = vcpu->arch.apic; - u32 mda = kvm_apic_mda(dest, source, target); + u32 mda = kvm_apic_mda(vcpu, dest, source, target); apic_debug("target %p, source %p, dest 0x%x, " "dest_mode 0x%x, short_hand 0x%x\n", @@ -668,6 +681,7 @@ 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) @@ -694,102 +708,126 @@ static void kvm_apic_disabled_lapic_found(struct kvm *kvm) } } -bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, - struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map) +static bool kvm_apic_is_broadcast_dest(struct kvm *kvm, struct kvm_lapic **src, + struct kvm_lapic_irq *irq, struct kvm_apic_map *map) { - struct kvm_apic_map *map; - unsigned long bitmap = 1; - struct kvm_lapic **dst; - int i; - bool ret, x2apic_ipi; + if (kvm->arch.x2apic_broadcast_quirk_disabled) { + if ((irq->dest_id == APIC_BROADCAST && + map->mode != KVM_APIC_MODE_X2APIC)) + return true; + if (irq->dest_id == X2APIC_BROADCAST) + return true; + } else { + bool x2apic_ipi = src && *src && apic_x2apic_mode(*src); + if (irq->dest_id == (x2apic_ipi ? + X2APIC_BROADCAST : APIC_BROADCAST)) + return true; + } - *r = -1; + return false; +} - if (irq->shorthand == APIC_DEST_SELF) { - *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); - return true; - } +/* Return true if the interrupt can be handled by using *bitmap as index mask + * for valid destinations in *dst array. + * Return false if kvm_apic_map_get_dest_lapic did nothing useful. + * Note: we may have zero kvm_lapic destinations when we return true, which + * means that the interrupt should be dropped. In this case, *bitmap would be + * zero and *dst undefined. + */ +static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm, + struct kvm_lapic **src, struct kvm_lapic_irq *irq, + struct kvm_apic_map *map, struct kvm_lapic ***dst, + unsigned long *bitmap) +{ + int i, lowest; - if (irq->shorthand) + if (irq->shorthand == APIC_DEST_SELF && src) { + *dst = src; + *bitmap = 1; + return true; + } else if (irq->shorthand) return false; - x2apic_ipi = src && apic_x2apic_mode(src); - if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST)) + if (!map || kvm_apic_is_broadcast_dest(kvm, src, irq, map)) return false; - ret = true; - rcu_read_lock(); - map = rcu_dereference(kvm->arch.apic_map); - - if (!map) { - ret = false; - goto out; + if (irq->dest_mode == APIC_DEST_PHYSICAL) { + if (irq->dest_id > map->max_apic_id) { + *bitmap = 0; + } else { + *dst = &map->phys_map[irq->dest_id]; + *bitmap = 1; + } + return true; } - if (irq->dest_mode == APIC_DEST_PHYSICAL) { - if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) - goto out; + *bitmap = 0; + if (!kvm_apic_map_get_logical_dest(map, irq->dest_id, dst, + (u16 *)bitmap)) + return false; - dst = &map->phys_map[irq->dest_id]; - } else { - u16 cid; + if (!kvm_lowest_prio_delivery(irq)) + return true; - if (!kvm_apic_logical_map_valid(map)) { - ret = false; - goto out; + if (!kvm_vector_hashing_enabled()) { + lowest = -1; + for_each_set_bit(i, bitmap, 16) { + if (!(*dst)[i]) + continue; + if (lowest < 0) + lowest = i; + else if (kvm_apic_compare_prio((*dst)[i]->vcpu, + (*dst)[lowest]->vcpu) < 0) + lowest = i; } + } else { + if (!*bitmap) + return true; - apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); + lowest = kvm_vector_to_index(irq->vector, hweight16(*bitmap), + bitmap, 16); - if (cid >= ARRAY_SIZE(map->logical_map)) - goto out; + if (!(*dst)[lowest]) { + kvm_apic_disabled_lapic_found(kvm); + *bitmap = 0; + return true; + } + } - dst = map->logical_map[cid]; + *bitmap = (lowest >= 0) ? 1 << lowest : 0; - if (!kvm_lowest_prio_delivery(irq)) - goto set_irq; + return true; +} - if (!kvm_vector_hashing_enabled()) { - int l = -1; - for_each_set_bit(i, &bitmap, 16) { - if (!dst[i]) - continue; - if (l < 0) - l = i; - else if (kvm_apic_compare_prio(dst[i]->vcpu, - dst[l]->vcpu) < 0) - l = i; - } - bitmap = (l >= 0) ? 1 << l : 0; - } else { - int idx; - unsigned int dest_vcpus; +bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, + struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map) +{ + struct kvm_apic_map *map; + unsigned long bitmap; + struct kvm_lapic **dst = NULL; + int i; + bool ret; - dest_vcpus = hweight16(bitmap); - if (dest_vcpus == 0) - goto out; + *r = -1; - idx = kvm_vector_to_index(irq->vector, - dest_vcpus, &bitmap, 16); + if (irq->shorthand == APIC_DEST_SELF) { + *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); + return true; + } - if (!dst[idx]) { - kvm_apic_disabled_lapic_found(kvm); - goto out; - } + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); - bitmap = (idx >= 0) ? 1 << idx : 0; + ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dst, &bitmap); + if (ret) + for_each_set_bit(i, &bitmap, 16) { + if (!dst[i]) + continue; + if (*r < 0) + *r = 0; + *r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map); } - } -set_irq: - for_each_set_bit(i, &bitmap, 16) { - if (!dst[i]) - continue; - if (*r < 0) - *r = 0; - *r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map); - } -out: rcu_read_unlock(); return ret; } @@ -812,8 +850,9 @@ 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; + unsigned long bitmap; + struct kvm_lapic **dst = NULL; bool ret = false; - struct kvm_lapic *dst = NULL; if (irq->shorthand) return false; @@ -821,69 +860,16 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, 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 (kvm_apic_map_get_dest_lapic(kvm, NULL, irq, map, &dst, &bitmap) && + hweight16(bitmap) == 1) { + unsigned long i = find_first_bit(&bitmap, 16); - 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; - - if (kvm_vector_hashing_enabled() && - kvm_lowest_prio_delivery(irq)) { - int idx; - unsigned int dest_vcpus; - - dest_vcpus = hweight16(bitmap); - if (dest_vcpus == 0) - goto out; - - idx = kvm_vector_to_index(irq->vector, dest_vcpus, - &bitmap, 16); - - dst = map->logical_map[cid][idx]; - if (!dst) { - kvm_apic_disabled_lapic_found(kvm); - goto out; - } - - *dest_vcpu = dst->vcpu; - } else { - 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; + if (dst[i]) { + *dest_vcpu = dst[i]->vcpu; + ret = true; } } - ret = true; -out: rcu_read_unlock(); return ret; } @@ -921,7 +907,7 @@ 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 +915,7 @@ 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 +1059,8 @@ 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 +1097,7 @@ 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; @@ -1150,12 +1136,6 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) return 0; switch (offset) { - case APIC_ID: - if (apic_x2apic_mode(apic)) - val = kvm_apic_id(apic); - else - val = kvm_apic_id(apic) << 24; - break; case APIC_ARBPRI: apic_debug("Access APIC ARBPRI register which is for P6\n"); break; @@ -1168,13 +1148,13 @@ 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 +1166,7 @@ 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 +1203,7 @@ 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 +1221,7 @@ 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 +1230,7 @@ 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 +1241,7 @@ 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 +1277,7 @@ 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; @@ -1332,9 +1313,115 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(tsc_deadline - guest_tsc); + __delay(min(tsc_deadline - guest_tsc, + nsec_to_cycles(vcpu, lapic_timer_advance_ns))); +} + +static void start_sw_tscdeadline(struct kvm_lapic *apic) +{ + 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; + ktime_t now; + + if (unlikely(!tscdeadline || !this_tsc_khz)) + return; + + local_irq_save(flags); + + now = apic->lapic_timer.timer.base->get_time(); + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); + if (likely(tscdeadline > guest_tsc)) { + ns = (tscdeadline - guest_tsc) * 1000000ULL; + do_div(ns, this_tsc_khz); + 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_PINNED); + } else + apic_timer_expired(apic); + + local_irq_restore(flags); +} + +bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) +{ + if (!lapic_in_kernel(vcpu)) + return false; + + return vcpu->arch.apic->lapic_timer.hv_timer_in_use; +} +EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use); + +static void cancel_hv_tscdeadline(struct kvm_lapic *apic) +{ + kvm_x86_ops->cancel_hv_timer(apic->vcpu); + apic->lapic_timer.hv_timer_in_use = false; } +void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + WARN_ON(!apic->lapic_timer.hv_timer_in_use); + WARN_ON(swait_active(&vcpu->wq)); + cancel_hv_tscdeadline(apic); + apic_timer_expired(apic); +} +EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer); + +static bool start_hv_tscdeadline(struct kvm_lapic *apic) +{ + u64 tscdeadline = apic->lapic_timer.tscdeadline; + + if (atomic_read(&apic->lapic_timer.pending) || + kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) { + if (apic->lapic_timer.hv_timer_in_use) + cancel_hv_tscdeadline(apic); + } else { + apic->lapic_timer.hv_timer_in_use = true; + hrtimer_cancel(&apic->lapic_timer.timer); + + /* In case the sw timer triggered in the window */ + if (atomic_read(&apic->lapic_timer.pending)) + cancel_hv_tscdeadline(apic); + } + trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, + apic->lapic_timer.hv_timer_in_use); + return apic->lapic_timer.hv_timer_in_use; +} + +void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + WARN_ON(apic->lapic_timer.hv_timer_in_use); + + if (apic_lvtt_tscdeadline(apic)) + start_hv_tscdeadline(apic); +} +EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer); + +void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + /* Possibly the TSC deadline timer is not enabled yet */ + if (!apic->lapic_timer.hv_timer_in_use) + return; + + cancel_hv_tscdeadline(apic); + + if (atomic_read(&apic->lapic_timer.pending)) + return; + + start_sw_tscdeadline(apic); +} +EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); + static void start_apic_timer(struct kvm_lapic *apic) { ktime_t now; @@ -1344,7 +1431,7 @@ 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) @@ -1376,37 +1463,13 @@ 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))); } else if (apic_lvtt_tscdeadline(apic)) { - /* 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; - - if (unlikely(!tscdeadline || !this_tsc_khz)) - return; - - local_irq_save(flags); - - now = apic->lapic_timer.timer.base->get_time(); - guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); - if (likely(tscdeadline > guest_tsc)) { - ns = (tscdeadline - guest_tsc) * 1000000ULL; - do_div(ns, this_tsc_khz); - 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_PINNED); - } else - apic_timer_expired(apic); - - local_irq_restore(flags); + if (!(kvm_x86_ops->set_hv_timer && start_hv_tscdeadline(apic))) + start_sw_tscdeadline(apic); } } @@ -1425,7 +1488,7 @@ 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; @@ -1434,7 +1497,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) switch (reg) { case APIC_ID: /* Local APIC ID */ if (!apic_x2apic_mode(apic)) - kvm_apic_set_id(apic, val >> 24); + kvm_apic_set_xapic_id(apic, val >> 24); else ret = 1; break; @@ -1457,7 +1520,7 @@ 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 +1528,17 @@ 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 +1549,14 @@ 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 +1570,7 @@ 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 +1578,7 @@ 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 +1587,14 @@ 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 +1607,7 @@ 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 +1619,7 @@ 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 +1649,14 @@ 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 +1668,10 @@ 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 +1731,14 @@ 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; } @@ -1694,11 +1758,13 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) /* update jump label if enable bit changes */ if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) { - if (value & MSR_IA32_APICBASE_ENABLE) + if (value & MSR_IA32_APICBASE_ENABLE) { + kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); static_key_slow_dec_deferred(&apic_hw_disabled); - else + } else { static_key_slow_inc(&apic_hw_disabled.key); - recalculate_apic_map(vcpu->kvm); + recalculate_apic_map(vcpu->kvm); + } } if ((old_value ^ value) & X2APIC_ENABLE) { @@ -1736,32 +1802,35 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); - if (!init_event) - kvm_apic_set_id(apic, vcpu->vcpu_id); + if (!init_event) { + kvm_lapic_set_base(vcpu, APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE); + kvm_apic_set_xapic_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 +1875,7 @@ 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)) { @@ -1876,9 +1945,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) * thinking that APIC satet has changed. */ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; - kvm_lapic_set_base(vcpu, - APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE); - static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); @@ -1901,14 +1967,14 @@ 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)) @@ -1958,23 +2024,54 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) return vector; } -void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, - struct kvm_lapic_state *s) +static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, + struct kvm_lapic_state *s, bool set) +{ + if (apic_x2apic_mode(vcpu->arch.apic)) { + u32 *id = (u32 *)(s->regs + APIC_ID); + + if (vcpu->kvm->arch.x2apic_format) { + if (*id != vcpu->vcpu_id) + return -EINVAL; + } else { + if (set) + *id >>= 24; + else + *id <<= 24; + } + } + + return 0; +} + +int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) +{ + memcpy(s->regs, vcpu->arch.apic->regs, sizeof(*s)); + return kvm_apic_state_fixup(vcpu, s, false); +} + +int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { struct kvm_lapic *apic = vcpu->arch.apic; + int r; + 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))); + + r = kvm_apic_state_fixup(vcpu, s, true); + if (r) + return r; memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s); - /* call kvm_apic_set_id() to put apic into apic_map */ - kvm_apic_set_id(apic, kvm_apic_id(apic)); + + recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(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 +2079,11 @@ 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); @@ -1992,6 +2091,8 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, kvm_rtc_eoi_tracking_restore_one(vcpu); vcpu->arch.apic_arb_prio = 0; + + return 0; } void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) @@ -2097,7 +2198,7 @@ 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 +2240,8 @@ 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 +2258,10 @@ 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 +2277,8 @@ 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 +2289,10 @@ 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; |