commit bd744ec9be563741eeb11d432140da05bd9185fb Author: Chris Lalancette Date: Fri Oct 30 07:09:44 2009 -0400 Allow kvm_set_irq to be called from IRQ context, and allow kdump to work. Still needs to be split up and needs to be debugged. Signed-off-by: Chris Lalancette diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 31a7035..8d9adf6 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -10,8 +10,7 @@ kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ assigned-dev.o) kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) -kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ - i8254.o timer.o +kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o i8254.o kvm-intel-y += vmx.o kvm-amd-y += svm.o diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index fab7440..945580c 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -227,37 +227,15 @@ static void pit_latch_status(struct kvm *kvm, int channel) } } -int pit_has_pending_timer(struct kvm_vcpu *vcpu) -{ - struct kvm_pit *pit = vcpu->kvm->arch.vpit; - - if (pit && kvm_vcpu_is_bsp(vcpu) && pit->pit_state.irq_ack) - return atomic_read(&pit->pit_state.pit_timer.pending); - return 0; -} - static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) { struct kvm_kpit_state *ps = container_of(kian, struct kvm_kpit_state, irq_ack_notifier); - spin_lock(&ps->inject_lock); - if (atomic_dec_return(&ps->pit_timer.pending) < 0) - atomic_inc(&ps->pit_timer.pending); - ps->irq_ack = 1; - spin_unlock(&ps->inject_lock); -} + unsigned long flags; -void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) -{ - struct kvm_pit *pit = vcpu->kvm->arch.vpit; - struct hrtimer *timer; - - if (!kvm_vcpu_is_bsp(vcpu) || !pit) - return; - - timer = &pit->pit_state.pit_timer.timer; - if (hrtimer_cancel(timer)) - hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + spin_lock_irqsave(&ps->inject_lock, flags); + ps->irq_ack = 1; + spin_unlock_irqrestore(&ps->inject_lock, flags); } static void destroy_pit_timer(struct kvm_timer *pt) @@ -277,6 +255,38 @@ static struct kvm_timer_ops kpit_ops = { .is_periodic = kpit_is_periodic, }; +static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) +{ + struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); + struct kvm *kvm = ktimer->kvm; + struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; + int inject = 0; + + /* + * There is a race window between reading and incrementing, but we do + * not care about potentially losing timer events in the !reinject + * case anyway. + */ + spin_lock(&ps->inject_lock); + if (ktimer->reinject && ps->irq_ack) { + ps->irq_ack = 0; + inject = 1; + } + spin_unlock(&ps->inject_lock); + + if (inject) { + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); + kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); + } + + if (ktimer->t_ops->is_periodic(ktimer)) { + hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); + return HRTIMER_RESTART; + } + else + return HRTIMER_NORESTART; +} + static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period) { struct kvm_timer *pt = &ps->pit_timer; @@ -291,12 +301,10 @@ static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period) pt->period = interval; ps->is_periodic = is_period; - pt->timer.function = kvm_timer_fn; + pt->timer.function = pit_timer_fn; pt->t_ops = &kpit_ops; pt->kvm = ps->pit->kvm; - pt->vcpu = pt->kvm->bsp_vcpu; - atomic_set(&pt->pending, 0); ps->irq_ack = 1; hrtimer_start(&pt->timer, ktime_add_ns(ktime_get(), interval), @@ -576,17 +584,18 @@ void kvm_pit_reset(struct kvm_pit *pit) } mutex_unlock(&pit->pit_state.lock); - atomic_set(&pit->pit_state.pit_timer.pending, 0); pit->pit_state.irq_ack = 1; } static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask) { struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier); + unsigned long flags; if (!mask) { - atomic_set(&pit->pit_state.pit_timer.pending, 0); + spin_lock_irqsave(&pit->pit_state.inject_lock, flags); pit->pit_state.irq_ack = 1; + spin_unlock_irqrestore(&pit->pit_state.inject_lock, flags); } } @@ -704,27 +713,3 @@ static void __inject_pit_timer_intr(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) kvm_apic_nmi_wd_deliver(vcpu); } - -void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu) -{ - struct kvm_pit *pit = vcpu->kvm->arch.vpit; - struct kvm *kvm = vcpu->kvm; - struct kvm_kpit_state *ps; - - if (pit) { - int inject = 0; - ps = &pit->pit_state; - - /* Try to inject pending interrupts when - * last one has been acked. - */ - spin_lock(&ps->inject_lock); - if (atomic_read(&ps->pit_timer.pending) && ps->irq_ack) { - ps->irq_ack = 0; - inject = 1; - } - spin_unlock(&ps->inject_lock); - if (inject) - __inject_pit_timer_intr(kvm); - } -} diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index d4c1c7f..02a1e3a 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -49,7 +49,6 @@ struct kvm_pit { #define KVM_MAX_PIT_INTR_INTERVAL HZ / 100 #define KVM_PIT_CHANNEL_MASK 0x3 -void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu); void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start); struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags); void kvm_free_pit(struct kvm *kvm); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index d057c0c..0d26f80 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -52,10 +52,12 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq) void kvm_pic_clear_isr_ack(struct kvm *kvm) { struct kvm_pic *s = pic_irqchip(kvm); - spin_lock(&s->lock); + unsigned long flags; + + spin_lock_irqsave(&s->lock, flags); s->pics[0].isr_ack = 0xff; s->pics[1].isr_ack = 0xff; - spin_unlock(&s->lock); + spin_unlock_irqrestore(&s->lock, flags); } /* @@ -156,24 +158,27 @@ static void pic_update_irq(struct kvm_pic *s) void kvm_pic_update_irq(struct kvm_pic *s) { - spin_lock(&s->lock); + unsigned long flags; + + spin_lock_irqsave(&s->lock, flags); pic_update_irq(s); - spin_unlock(&s->lock); + spin_unlock_irqrestore(&s->lock, flags); } int kvm_pic_set_irq(void *opaque, int irq, int level) { struct kvm_pic *s = opaque; int ret = -1; + unsigned long flags; - spin_lock(&s->lock); + spin_lock_irqsave(&s->lock, flags); if (irq >= 0 && irq < PIC_NUM_PINS) { ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); pic_update_irq(s); trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr, s->pics[irq >> 3].imr, ret == 0); } - spin_unlock(&s->lock); + spin_unlock_irqrestore(&s->lock, flags); return ret; } @@ -202,8 +207,9 @@ int kvm_pic_read_irq(struct kvm *kvm) { int irq, irq2, intno; struct kvm_pic *s = pic_irqchip(kvm); + unsigned long flags; - spin_lock(&s->lock); + spin_lock_irqsave(&s->lock, flags); irq = pic_get_irq(&s->pics[0]); if (irq >= 0) { pic_intack(&s->pics[0], irq); @@ -228,16 +234,14 @@ int kvm_pic_read_irq(struct kvm *kvm) intno = s->pics[0].irq_base + irq; } pic_update_irq(s); - spin_unlock(&s->lock); + spin_unlock_irqrestore(&s->lock, flags); return intno; } -void kvm_pic_reset(struct kvm_kpic_state *s) +static void kvm_pic_reset(struct kvm_kpic_state *s) { int irq; - struct kvm *kvm = s->pics_state->irq_request_opaque; - struct kvm_vcpu *vcpu0 = kvm->bsp_vcpu; u8 irr = s->irr, isr = s->imr; s->last_irr = 0; @@ -257,10 +261,8 @@ void kvm_pic_reset(struct kvm_kpic_state *s) s->init4 = 0; for (irq = 0; irq < PIC_NUM_PINS/2; irq++) { - if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) - if (irr & (1 << irq) || isr & (1 << irq)) { - pic_clear_isr(s, irq); - } + if (irr & (1 << irq) || isr & (1 << irq)) + pic_clear_isr(s, irq); } } @@ -434,6 +436,8 @@ static int picdev_write(struct kvm_io_device *this, { struct kvm_pic *s = to_pic(this); unsigned char data = *(unsigned char *)val; + unsigned long flags; + if (!picdev_in_range(addr)) return -EOPNOTSUPP; @@ -442,7 +446,7 @@ static int picdev_write(struct kvm_io_device *this, printk(KERN_ERR "PIC: non byte write\n"); return 0; } - spin_lock(&s->lock); + spin_lock_irqsave(&s->lock, flags); switch (addr) { case 0x20: case 0x21: @@ -455,7 +459,7 @@ static int picdev_write(struct kvm_io_device *this, elcr_ioport_write(&s->pics[addr & 1], addr, data); break; } - spin_unlock(&s->lock); + spin_unlock_irqrestore(&s->lock, flags); return 0; } @@ -464,6 +468,8 @@ static int picdev_read(struct kvm_io_device *this, { struct kvm_pic *s = to_pic(this); unsigned char data = 0; + unsigned long flags; + if (!picdev_in_range(addr)) return -EOPNOTSUPP; @@ -472,7 +478,7 @@ static int picdev_read(struct kvm_io_device *this, printk(KERN_ERR "PIC: non byte read\n"); return 0; } - spin_lock(&s->lock); + spin_lock_irqsave(&s->lock, flags); switch (addr) { case 0x20: case 0x21: @@ -486,7 +492,7 @@ static int picdev_read(struct kvm_io_device *this, break; } *(unsigned char *)val = data; - spin_unlock(&s->lock); + spin_unlock_irqrestore(&s->lock, flags); return 0; } @@ -496,14 +502,13 @@ static int picdev_read(struct kvm_io_device *this, static void pic_irq_request(void *opaque, int level) { struct kvm *kvm = opaque; - struct kvm_vcpu *vcpu = kvm->bsp_vcpu; struct kvm_pic *s = pic_irqchip(kvm); int irq = pic_get_irq(&s->pics[0]); s->output = level; - if (vcpu && level && (s->pics[0].isr_ack & (1 << irq))) { + if (level && (s->pics[0].isr_ack & (1 << irq))) { s->pics[0].isr_ack &= ~(1 << irq); - kvm_vcpu_kick(vcpu); + kvm_irq_kick_vcpus(kvm); } } diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 96dfbb6..b5db0de 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -32,12 +32,7 @@ */ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - int ret; - - ret = pit_has_pending_timer(vcpu); - ret |= apic_has_pending_timer(vcpu); - - return ret; + return apic_has_pending_timer(vcpu); } EXPORT_SYMBOL(kvm_cpu_has_pending_timer); @@ -53,7 +48,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) return v->arch.interrupt.pending; if (kvm_apic_has_interrupt(v) == -1) { /* LAPIC */ - if (kvm_apic_accept_pic_intr(v)) { + if (kvm_apic_in_virtual_wire_mode(v)) { s = pic_irqchip(v->kvm); /* PIC */ return s->output; } else @@ -76,7 +71,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) vector = kvm_get_apic_interrupt(v); /* APIC */ if (vector == -1) { - if (kvm_apic_accept_pic_intr(v)) { + if (kvm_apic_in_virtual_wire_mode(v)) { s = pic_irqchip(v->kvm); s->output = 0; /* PIC */ vector = kvm_pic_read_irq(v->kvm); @@ -89,13 +84,10 @@ EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { kvm_inject_apic_timer_irqs(vcpu); - kvm_inject_pit_timer_irqs(vcpu); - /* TODO: PIT, RTC etc. */ } EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs); void __kvm_migrate_timers(struct kvm_vcpu *vcpu) { __kvm_migrate_apic_timer(vcpu); - __kvm_migrate_pit_timer(vcpu); } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index c025a23..cbc9c8b 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -89,16 +89,12 @@ static inline int irqchip_in_kernel(struct kvm *kvm) return pic_irqchip(kvm) != NULL; } -void kvm_pic_reset(struct kvm_kpic_state *s); - void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu); void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu); void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu); -void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu); void __kvm_migrate_timers(struct kvm_vcpu *vcpu); -int pit_has_pending_timer(struct kvm_vcpu *vcpu); int apic_has_pending_timer(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cd60c0b..0005409 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -435,7 +435,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, /* * Should only be called by kvm_apic_local_deliver() with LVT0, * before NMI watchdog was enabled. Already handled by - * kvm_apic_accept_pic_intr(). + * kvm_apic_in_virtual_wire_mode(). */ break; @@ -1040,6 +1040,37 @@ static const struct kvm_io_device_ops apic_mmio_ops = { .write = apic_mmio_write, }; +static enum hrtimer_restart lapic_timer_fn(struct hrtimer *data) +{ + struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); + struct kvm_vcpu *vcpu; + struct kvm_lapic *lapic; + + vcpu = ktimer->vcpu; + if (!vcpu) + return HRTIMER_NORESTART; + + lapic = vcpu->arch.apic; + + /* + * There is a race window between reading and incrementing, but we do + * not care about potentially losing timer events in the !reinject + * case anyway. + */ + if (ktimer->reinject || !atomic_read(&ktimer->pending)) + atomic_inc(&ktimer->pending); + + if (waitqueue_active(&vcpu->wq)) + wake_up_interruptible(&vcpu->wq); + + if (ktimer->t_ops->is_periodic(ktimer)) { + hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); + return HRTIMER_RESTART; + } + else + return HRTIMER_NORESTART; +} + int kvm_create_lapic(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic; @@ -1065,7 +1096,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - apic->lapic_timer.timer.function = kvm_timer_fn; + apic->lapic_timer.timer.function = lapic_timer_fn; apic->lapic_timer.t_ops = &lapic_timer_ops; apic->lapic_timer.kvm = vcpu->kvm; apic->lapic_timer.vcpu = vcpu; @@ -1099,18 +1130,17 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) return highest_irr; } -int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) +int kvm_apic_in_virtual_wire_mode(struct kvm_vcpu *vcpu) { u32 lvt0 = apic_get_reg(vcpu->arch.apic, APIC_LVT0); int r = 0; - if (kvm_vcpu_is_bsp(vcpu)) { - if (!apic_hw_enabled(vcpu->arch.apic)) - r = 1; - if ((lvt0 & APIC_LVT_MASKED) == 0 && - GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) - r = 1; - } + if (!apic_hw_enabled(vcpu->arch.apic)) + r = 1; + if ((lvt0 & APIC_LVT_MASKED) == 0 && + GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) + r = 1; + return r; } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 40010b0..ce4cd2d 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -22,7 +22,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); -int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); +int kvm_apic_in_virtual_wire_mode(struct kvm_vcpu *vcpu); int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c deleted file mode 100644 index eea4043..0000000 --- a/arch/x86/kvm/timer.c +++ /dev/null @@ -1,50 +0,0 @@ -#include -#include -#include -#include -#include "kvm_timer.h" - -static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) -{ - int restart_timer = 0; - wait_queue_head_t *q = &vcpu->wq; - - /* - * There is a race window between reading and incrementing, but we do - * not care about potentially loosing timer events in the !reinject - * case anyway. - */ - if (ktimer->reinject || !atomic_read(&ktimer->pending)) { - atomic_inc(&ktimer->pending); - /* FIXME: this code should not know anything about vcpus */ - set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); - } - - if (waitqueue_active(q)) - wake_up_interruptible(q); - - if (ktimer->t_ops->is_periodic(ktimer)) { - hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); - restart_timer = 1; - } - - return restart_timer; -} - -enum hrtimer_restart kvm_timer_fn(struct hrtimer *data) -{ - int restart_timer; - struct kvm_vcpu *vcpu; - struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); - - vcpu = ktimer->vcpu; - if (!vcpu) - return HRTIMER_NORESTART; - - restart_timer = __kvm_timer_fn(vcpu, ktimer); - if (restart_timer) - return HRTIMER_RESTART; - else - return HRTIMER_NORESTART; -} - diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2ef3906..93a65b4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3906,7 +3906,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) if (r <= 0) break; - clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests); if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bd5a616..975b0d6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -33,7 +33,6 @@ #define KVM_REQ_REPORT_TPR_ACCESS 2 #define KVM_REQ_MMU_RELOAD 3 #define KVM_REQ_TRIPLE_FAULT 4 -#define KVM_REQ_PENDING_TIMER 5 #define KVM_REQ_UNHALT 6 #define KVM_REQ_MMU_SYNC 7 #define KVM_REQ_KVMCLOCK_UPDATE 8 @@ -543,6 +542,8 @@ int kvm_set_irq_routing(struct kvm *kvm, unsigned flags); void kvm_free_irq_routing(struct kvm *kvm); +void kvm_irq_kick_vcpus(struct kvm *kvm); + #else static inline void kvm_free_irq_routing(struct kvm *kvm) {} diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 38a2d20..2ead0fd 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -144,6 +144,17 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) } } +static int ioapic_dest_multiple_cpus(u8 dest_mode, u8 dest_id) +{ + int lookup_table[] = { 0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4 }; + + /* physical mode is always directed to 1 cpu */ + if (dest_mode == 0 || dest_id == 0) + return 0; + + return (lookup_table[dest_id & 0x0f] + lookup_table[(dest_id >> 4) & 0x0f]) != 1; +} + static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) { union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; @@ -164,14 +175,17 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq) irqe.shorthand = 0; #ifdef CONFIG_X86 - /* Always delivery PIT interrupt to vcpu 0 */ - if (irq == 0) { + /* If this is the PIT interrupt and the dest_id is multiple + * vcpus, re-write to always go to vcpu 0. + */ + if (irq == 0 && ioapic_dest_multiple_cpus(irqe.dest_mode, irqe.dest_id)) { irqe.dest_mode = 0; /* Physical mode. */ - /* need to read apic_id from apic regiest since + /* need to read apic_id from apic register since * it can be rewritten */ irqe.dest_id = ioapic->kvm->bsp_vcpu->vcpu_id; } #endif + return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe); } @@ -181,8 +195,9 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) u32 mask = 1 << irq; union kvm_ioapic_redirect_entry entry; int ret = 1; + unsigned long flags; - mutex_lock(&ioapic->lock); + spin_lock_irqsave(&ioapic->lock, flags); if (irq >= 0 && irq < IOAPIC_NUM_PINS) { entry = ioapic->redirtbl[irq]; level ^= entry.fields.polarity; @@ -199,13 +214,13 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) } trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0); } - mutex_unlock(&ioapic->lock); + spin_unlock_irqrestore(&ioapic->lock, flags); return ret; } static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector, - int trigger_mode) + int trigger_mode) { int i; @@ -223,9 +238,9 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector, * is dropped it will be put into irr and will be delivered * after ack notifier returns. */ - mutex_unlock(&ioapic->lock); + spin_unlock(&ioapic->lock); kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i); - mutex_lock(&ioapic->lock); + spin_lock(&ioapic->lock); if (trigger_mode != IOAPIC_LEVEL_TRIG) continue; @@ -240,10 +255,11 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector, void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; + unsigned long flags; - mutex_lock(&ioapic->lock); + spin_lock_irqsave(&ioapic->lock, flags); __kvm_ioapic_update_eoi(ioapic, vector, trigger_mode); - mutex_unlock(&ioapic->lock); + spin_unlock_irqrestore(&ioapic->lock, flags); } static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev) @@ -262,6 +278,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, { struct kvm_ioapic *ioapic = to_ioapic(this); u32 result; + unsigned long flags; + if (!ioapic_in_range(ioapic, addr)) return -EOPNOTSUPP; @@ -269,7 +287,7 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, ASSERT(!(addr & 0xf)); /* check alignment */ addr &= 0xff; - mutex_lock(&ioapic->lock); + spin_lock_irqsave(&ioapic->lock, flags); switch (addr) { case IOAPIC_REG_SELECT: result = ioapic->ioregsel; @@ -283,7 +301,7 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, result = 0; break; } - mutex_unlock(&ioapic->lock); + spin_unlock_irqrestore(&ioapic->lock, flags); switch (len) { case 8: @@ -305,6 +323,8 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, { struct kvm_ioapic *ioapic = to_ioapic(this); u32 data; + unsigned long flags; + if (!ioapic_in_range(ioapic, addr)) return -EOPNOTSUPP; @@ -320,7 +340,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, } addr &= 0xff; - mutex_lock(&ioapic->lock); + spin_lock_irqsave(&ioapic->lock, flags); switch (addr) { case IOAPIC_REG_SELECT: ioapic->ioregsel = data; @@ -338,7 +358,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, default: break; } - mutex_unlock(&ioapic->lock); + spin_unlock_irqrestore(&ioapic->lock, flags); return 0; } @@ -367,7 +387,7 @@ int kvm_ioapic_init(struct kvm *kvm) ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL); if (!ioapic) return -ENOMEM; - mutex_init(&ioapic->lock); + spin_lock_init(&ioapic->lock); kvm->arch.vioapic = ioapic; kvm_ioapic_reset(ioapic); kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops); @@ -382,23 +402,27 @@ int kvm_ioapic_init(struct kvm *kvm) int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) { struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); + unsigned long flags; + if (!ioapic) return -EINVAL; - mutex_lock(&ioapic->lock); + spin_lock_irqsave(&ioapic->lock, flags); memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); - mutex_unlock(&ioapic->lock); + spin_unlock_irqrestore(&ioapic->lock, flags); return 0; } int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) { struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); + unsigned long flags; + if (!ioapic) return -EINVAL; - mutex_lock(&ioapic->lock); + spin_lock_irqsave(&ioapic->lock, flags); memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); - mutex_unlock(&ioapic->lock); + spin_unlock_irqrestore(&ioapic->lock, flags); return 0; } diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index 419c43b..5b4f756 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -45,7 +45,7 @@ struct kvm_ioapic { struct kvm_io_device dev; struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); - struct mutex lock; + spinlock_t lock; }; #ifdef DEBUG diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 0d454d3..c71cfeb 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -98,6 +98,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, if (r < 0) r = 0; r += kvm_apic_set_irq(vcpu, irq); + kvm_vcpu_kick(vcpu); } else { if (!lowest) lowest = vcpu; @@ -293,6 +294,18 @@ void kvm_free_irq_routing(struct kvm *kvm) kfree(kvm->irq_routing); } +void kvm_irq_kick_vcpus(struct kvm *kvm) +{ + int i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (kvm_apic_in_virtual_wire_mode(vcpu)) + if (waitqueue_active(&vcpu->wq)) + wake_up_interruptible(&vcpu->wq); + } +} + static int setup_routing_entry(struct kvm_irq_routing_table *rt, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue)