On Sat, Dec 08, 2012 at 08:04:30PM +0800, Yang Zhang wrote:
> Virtual interrupt delivery avoids KVM to inject vAPIC interrupts
> manually, which is fully taken care of by the hardware. This needs
> some special awareness into existing interrupr injection path:
>
> - for pending interrupt, instead of direct injection, we may need
> update architecture specific indicators before resuming to guest.
>
> - A pending interrupt, which is masked by ISR, should be also
> considered in above update action, since hardware will decide
> when to inject it at right time. Current has_interrupt and
> get_interrupt only returns a valid vector from injection p.o.v.
>
> Signed-off-by: Kevin Tian <kevin.tian@xxxxxxxxx>
> Signed-off-by: Yang Zhang <yang.z.zhang@xxxxxxxxx>
> ---
> arch/x86/include/asm/kvm_host.h | 4 +
> arch/x86/include/asm/vmx.h | 11 ++++
> arch/x86/kvm/irq.c | 79 +++++++++++++++++++++------
> arch/x86/kvm/lapic.c | 101 +++++++++++++++++++++++++++++++---
> arch/x86/kvm/lapic.h | 11 ++++
> arch/x86/kvm/svm.c | 19 ++++++
> arch/x86/kvm/vmx.c | 116 +++++++++++++++++++++++++++++++++++++-
> arch/x86/kvm/x86.c | 18 ++++--
> virt/kvm/ioapic.c | 35 ++++++++++++
> virt/kvm/ioapic.h | 1 +
> 10 files changed, 358 insertions(+), 37 deletions(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index dc87b65..7e26d1a 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -697,6 +697,9 @@ struct kvm_x86_ops {
> void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
> void (*enable_irq_window)(struct kvm_vcpu *vcpu);
> void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
> + int (*has_virtual_interrupt_delivery)(struct kvm_vcpu *vcpu);
> + void (*update_irq)(struct kvm_vcpu *vcpu);
> + void (*update_eoi_exitmap)(struct kvm_vcpu *vcpu, int vector, bool set);
> int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
> int (*get_tdp_level)(void);
> u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
> @@ -991,6 +994,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long hva);
> int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
> void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
> int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
> +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
> int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
> int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
> int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
> diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
> index 21101b6..1003341 100644
> --- a/arch/x86/include/asm/vmx.h
> +++ b/arch/x86/include/asm/vmx.h
> @@ -62,6 +62,7 @@
> #define EXIT_REASON_MCE_DURING_VMENTRY 41
> #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
> #define EXIT_REASON_APIC_ACCESS 44
> +#define EXIT_REASON_EOI_INDUCED 45
> #define EXIT_REASON_EPT_VIOLATION 48
> #define EXIT_REASON_EPT_MISCONFIG 49
> #define EXIT_REASON_WBINVD 54
> @@ -143,6 +144,7 @@
> #define SECONDARY_EXEC_WBINVD_EXITING 0x00000040
> #define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080
> #define SECONDARY_EXEC_APIC_REGISTER_VIRT 0x00000100
> +#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY 0x00000200
> #define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400
> #define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000
>
> @@ -180,6 +182,7 @@ enum vmcs_field {
> GUEST_GS_SELECTOR = 0x0000080a,
> GUEST_LDTR_SELECTOR = 0x0000080c,
> GUEST_TR_SELECTOR = 0x0000080e,
> + GUEST_INTR_STATUS = 0x00000810,
> HOST_ES_SELECTOR = 0x00000c00,
> HOST_CS_SELECTOR = 0x00000c02,
> HOST_SS_SELECTOR = 0x00000c04,
> @@ -207,6 +210,14 @@ enum vmcs_field {
> APIC_ACCESS_ADDR_HIGH = 0x00002015,
> EPT_POINTER = 0x0000201a,
> EPT_POINTER_HIGH = 0x0000201b,
> + EOI_EXIT_BITMAP0 = 0x0000201c,
> + EOI_EXIT_BITMAP0_HIGH = 0x0000201d,
> + EOI_EXIT_BITMAP1 = 0x0000201e,
> + EOI_EXIT_BITMAP1_HIGH = 0x0000201f,
> + EOI_EXIT_BITMAP2 = 0x00002020,
> + EOI_EXIT_BITMAP2_HIGH = 0x00002021,
> + EOI_EXIT_BITMAP3 = 0x00002022,
> + EOI_EXIT_BITMAP3_HIGH = 0x00002023,
> GUEST_PHYSICAL_ADDRESS = 0x00002400,
> GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401,
> VMCS_LINK_POINTER = 0x00002800,
> diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
> index 7e06ba1..5cbc631 100644
> --- a/arch/x86/kvm/irq.c
> +++ b/arch/x86/kvm/irq.c
> @@ -38,50 +38,95 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
> EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
>
> /*
> + * check if there is injectable interrupt:
> + * a. when virtual interrupt delivery enabled,
> + * interrupt from apic will handled by hardware,
> + * we don't need to check it here.
> + * b. without virtual interrupt delivery, handle
> + * it in old way: check apic firstly, then pic.
> + */
Old way is incorrect and after the patch guests with apicv and without
will behave differently. The old way should be fixed separately
though. I'll look into it.
> +int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
> +{
> + if (!irqchip_in_kernel(v->kvm))
> + return v->arch.interrupt.pending;
> +
> + if (kvm_apic_vid_enabled(v))
> + return kvm_cpu_has_extint(v); /* non-APIC */
> + else if (kvm_apic_has_interrupt(v) == -1) /* LAPIC */
> + return kvm_cpu_has_extint(v); /* non-APIC */
> +
> + return 1;
> +}
> +EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr);
Why export it?
> +
> +/*
> * check if there is pending interrupt without
> * intack.
> */
> int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
> {
> - struct kvm_pic *s;
> -
> if (!irqchip_in_kernel(v->kvm))
> return v->arch.interrupt.pending;
>
> - if (kvm_apic_has_interrupt(v) == -1) { /* LAPIC */
> - if (kvm_apic_accept_pic_intr(v)) {
> - s = pic_irqchip(v->kvm); /* PIC */
> - return s->output;
> - } else
> - return 0;
> - }
> + if (kvm_apic_has_interrupt(v) == -1) /* LAPIC */
> + return kvm_cpu_has_extint(v); /* non-APIC */
> return 1;
> }
> EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
>
> /*
> + * check if there is pending interrupt from
> + * non-APIC source without intack.
> + */
> +int kvm_cpu_has_extint(struct kvm_vcpu *v)
static, drop from lapic.h.
> +{
> + struct kvm_pic *s;
> +
> + if (kvm_apic_accept_pic_intr(v)) {
> + s = pic_irqchip(v->kvm); /* PIC */
> + return s->output;
> + } else
> + return 0;
> +}
> +
> +/*
> * Read pending interrupt vector and intack.
> */
> int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
> {
> - struct kvm_pic *s;
> int vector;
>
> if (!irqchip_in_kernel(v->kvm))
> return v->arch.interrupt.nr;
>
> - vector = kvm_get_apic_interrupt(v); /* APIC */
> - if (vector == -1) {
> - if (kvm_apic_accept_pic_intr(v)) {
> - s = pic_irqchip(v->kvm);
> - s->output = 0; /* PIC */
> - vector = kvm_pic_read_irq(v->kvm);
> - }
> + if (kvm_apic_vid_enabled(v))
> + vector = kvm_cpu_get_extint(v); /* non-APIC */
> + else {
> + vector = kvm_get_apic_interrupt(v); /* APIC */
> + if (vector == -1)
> + vector = kvm_cpu_get_extint(v); /* non-APIC */
> }
> return vector;
> }
> EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
>
> +/*
> + * Read pending interrupt(from non-APIC source)
> + * vector and intack.
> + */
> +int kvm_cpu_get_extint(struct kvm_vcpu *v)
static, drop from lapic.h.
> +{
> + struct kvm_pic *s;
> + int vector = -1;
> +
> + if (kvm_apic_accept_pic_intr(v)) {
> + s = pic_irqchip(v->kvm);
> + s->output = 0; /* PIC */
> + vector = kvm_pic_read_irq(v->kvm);
> + }
> + return vector;
> +}
> +
> void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
> {
> kvm_inject_apic_timer_irqs(vcpu);
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index 0664c13..2109a6a 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -236,12 +236,14 @@ static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
> {
> apic_set_reg(apic, APIC_ID, id << 24);
> recalculate_apic_map(apic->vcpu->kvm);
> + ioapic_update_eoi_exitmap(apic->vcpu->kvm);
> }
>
> static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
> {
> apic_set_reg(apic, APIC_LDR, id);
> recalculate_apic_map(apic->vcpu->kvm);
> + ioapic_update_eoi_exitmap(apic->vcpu->kvm);
> }
>
> static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
> @@ -398,6 +400,7 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
>
> return highest_irr;
> }
> +EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr);
>
May be we should pass highest irr to update_irq() instead of exporting
the function.
> static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
> int vector, int level, int trig_mode);
> @@ -577,6 +580,64 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
> return result;
> }
>
> +static void kvm_apic_update_eoi_exitmap(struct kvm_vcpu *vcpu,
> + int vector, bool set)
> +{
> + kvm_x86_ops->update_eoi_exitmap(vcpu, vector, set);
> +}
> +
> +void kvm_update_eoi_exitmap(struct kvm *kvm, struct kvm_lapic_irq *irq)
> +{
> + struct kvm_vcpu *vcpu;
> + struct kvm_lapic **dst;
> + struct kvm_apic_map *map;
> + unsigned long bitmap = 1;
> + bool set;
> + int i;
> + /* KVM only support 255 vcpu*/
Lets use KVM_MAX_VCPUS instead.
> + unsigned long vcpu_map[4];
DECLARE_BITMAP(vcpu_map, KVM_MAX_VCPUS)
> +
> + bitmap_zero(vcpu_map, 255);
> +
> + rcu_read_lock();
> + map = rcu_dereference(kvm->arch.apic_map);
> +
> + if (unlikely(!map)) {
> + bitmap_fill(vcpu_map, 255);
> + goto out;
> + }
> +
> + if (irq->dest_mode == 0) { /* physical mode */
> + if (irq->delivery_mode == APIC_DM_LOWEST ||
> + irq->dest_id == 0xff) {
> + bitmap_fill(vcpu_map, 255);
> + goto out;
> + }
> + dst = &map->phys_map[irq->dest_id & 0xff];
> + } else {
> + u32 mda = irq->dest_id << (32 - map->ldr_bits);
> +
> + dst = map->logical_map[apic_cluster_id(map, mda)];
> +
> + bitmap = apic_logical_id(map, mda);
> + }
> +
> + for_each_set_bit(i, &bitmap, 16) {
> + if (!dst[i])
> + continue;
> + set_bit(dst[i]->vcpu->vcpu_id, vcpu_map);
> + }
> +
> +out:
> + rcu_read_unlock();
> + kvm_for_each_vcpu(i, vcpu, kvm) {
> + if (!kvm_apic_present(vcpu))
> + continue;
> + set = test_bit(vcpu->vcpu_id, vcpu_map);
> + kvm_apic_update_eoi_exitmap(vcpu, irq->vector, set);
> + }
> +
> +}
> bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
> struct kvm_lapic_irq *irq, int *r)
> {
> @@ -740,6 +801,19 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
> return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
> }
>
> +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->kvm, vector, trigger_mode);
> + }
> +}
> +
> static int apic_set_eoi(struct kvm_lapic *apic)
> {
> int vector = apic_find_highest_isr(apic);
> @@ -756,19 +830,26 @@ static int apic_set_eoi(struct kvm_lapic *apic)
> apic_clear_isr(vector, apic);
> apic_update_ppr(apic);
>
> - 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->kvm, vector, trigger_mode);
> - }
> + kvm_ioapic_send_eoi(apic, vector);
> kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
> return vector;
> }
>
> +/*
> + * this interface assumes a trap-like exit, which has already finished
> + * desired side effect including vISR and vPPR update.
> + */
> +void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector)
> +{
> + struct kvm_lapic *apic = vcpu->arch.apic;
> +
> + trace_kvm_eoi(apic, vector);
> +
> + kvm_ioapic_send_eoi(apic, vector);
> + kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
> +}
> +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);
> @@ -1071,6 +1152,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
> if (!apic_x2apic_mode(apic)) {
> apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
> recalculate_apic_map(apic->vcpu->kvm);
> + ioapic_update_eoi_exitmap(apic->vcpu->kvm);
> } else
> ret = 1;
> break;
> @@ -1318,6 +1400,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
> else
> static_key_slow_inc(&apic_hw_disabled.key);
> recalculate_apic_map(vcpu->kvm);
> + ioapic_update_eoi_exitmap(apic->vcpu->kvm);
> }
>
> if (!kvm_vcpu_is_bsp(apic->vcpu))
> diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
> index 9a8ee22..10e3f66 100644
> --- a/arch/x86/kvm/lapic.h
> +++ b/arch/x86/kvm/lapic.h
> @@ -39,6 +39,9 @@ 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_get_apic_interrupt(struct kvm_vcpu *vcpu);
> +int kvm_cpu_has_extint(struct kvm_vcpu *v);
> +int kvm_cpu_get_extint(struct kvm_vcpu *v);
> +int kvm_apic_get_highest_irr(struct kvm_vcpu *vcpu);
> void kvm_lapic_reset(struct kvm_vcpu *vcpu);
> u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
> void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
> @@ -55,6 +58,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type);
> bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
> struct kvm_lapic_irq *irq, int *r);
>
> +void kvm_update_eoi_exitmap(struct kvm *kvm, struct kvm_lapic_irq *irq);
Should provide empty function in ia64 code.
> +
> u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
> void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data);
> void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
> @@ -65,6 +70,7 @@ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
> void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
>
> void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset);
> +void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector);
>
> void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
> void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
> @@ -126,4 +132,9 @@ static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
> return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic);
> }
>
> +static inline bool kvm_apic_vid_enabled(struct kvm_vcpu *vcpu)
> +{
> + return kvm_x86_ops->has_virtual_interrupt_delivery(vcpu);
> +}
> +
> #endif
> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
> index dcb7952..38d7d38 100644
> --- a/arch/x86/kvm/svm.c
> +++ b/arch/x86/kvm/svm.c
> @@ -3573,6 +3573,22 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
> set_cr_intercept(svm, INTERCEPT_CR8_WRITE);
> }
>
> +static int svm_has_virtual_interrupt_delivery(struct kvm_vcpu *vcpu)
> +{
> + return 0;
> +}
> +
> +static void svm_update_irq(struct kvm_vcpu *vcpu)
> +{
> + return ;
> +}
> +
> +static void svm_update_eoi_exitmap(struct kvm_vcpu *vcpu, int vector,
> + int trig_mode, int always_set)
> +{
> + return ;
> +}
> +
> static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
> {
> struct vcpu_svm *svm = to_svm(vcpu);
> @@ -4292,6 +4308,9 @@ static struct kvm_x86_ops svm_x86_ops = {
> .enable_nmi_window = enable_nmi_window,
> .enable_irq_window = enable_irq_window,
> .update_cr8_intercept = update_cr8_intercept,
> + .has_virtual_interrupt_delivery = svm_has_virtual_interrupt_delivery,
> + .update_irq = svm_update_irq;
> + .update_eoi_exitmap = svm_update_eoi_exitmap;
>
> .set_tss_addr = svm_set_tss_addr,
> .get_tdp_level = get_npt_level,
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 4838e4f..cd4148b 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -432,6 +432,9 @@ struct vcpu_vmx {
>
> bool rdtscp_enabled;
>
> + u8 eoi_exitmap_changed;
> + u32 eoi_exit_bitmap[8];
> +
> /* Support for a guest hypervisor (nested VMX) */
> struct nested_vmx nested;
> };
> @@ -770,6 +773,12 @@ static inline bool cpu_has_vmx_apic_register_virt(void)
> SECONDARY_EXEC_APIC_REGISTER_VIRT;
> }
>
> +static inline bool cpu_has_vmx_virtual_intr_delivery(void)
> +{
> + return vmcs_config.cpu_based_2nd_exec_ctrl &
> + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
> +}
> +
> static inline bool cpu_has_vmx_flexpriority(void)
> {
> return cpu_has_vmx_tpr_shadow() &&
> @@ -2508,7 +2517,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
> SECONDARY_EXEC_PAUSE_LOOP_EXITING |
> SECONDARY_EXEC_RDTSCP |
> SECONDARY_EXEC_ENABLE_INVPCID |
> - SECONDARY_EXEC_APIC_REGISTER_VIRT;
> + SECONDARY_EXEC_APIC_REGISTER_VIRT |
> + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
> if (adjust_vmx_controls(min2, opt2,
> MSR_IA32_VMX_PROCBASED_CTLS2,
> &_cpu_based_2nd_exec_control) < 0)
> @@ -2522,7 +2532,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
>
> if (!(_cpu_based_exec_control & CPU_BASED_TPR_SHADOW))
> _cpu_based_2nd_exec_control &= ~(
> - SECONDARY_EXEC_APIC_REGISTER_VIRT);
> + SECONDARY_EXEC_APIC_REGISTER_VIRT |
> + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
>
> if (_cpu_based_2nd_exec_control & SECONDARY_EXEC_ENABLE_EPT) {
> /* CR3 accesses and invlpg don't need to cause VM Exits when EPT
> @@ -2721,9 +2732,13 @@ static __init int hardware_setup(void)
> if (!cpu_has_vmx_ple())
> ple_gap = 0;
>
> - if (!cpu_has_vmx_apic_register_virt())
> + if (!cpu_has_vmx_apic_register_virt() ||
> + !cpu_has_vmx_virtual_intr_delivery())
> enable_apicv_reg_vid = 0;
>
> + if (enable_apicv_reg_vid)
> + kvm_x86_ops->update_cr8_intercept = NULL;
> +
> if (nested)
> nested_vmx_setup_ctls_msrs();
>
> @@ -3838,7 +3853,8 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
> if (!ple_gap)
> exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
> if (!enable_apicv_reg_vid)
> - exec_control &= ~SECONDARY_EXEC_APIC_REGISTER_VIRT;
> + exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
> + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
> return exec_control;
> }
>
> @@ -3883,6 +3899,15 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
> vmx_secondary_exec_control(vmx));
> }
>
> + if (enable_apicv_reg_vid) {
> + vmcs_write64(EOI_EXIT_BITMAP0, 0);
> + vmcs_write64(EOI_EXIT_BITMAP1, 0);
> + vmcs_write64(EOI_EXIT_BITMAP2, 0);
> + vmcs_write64(EOI_EXIT_BITMAP3, 0);
> +
> + vmcs_write16(GUEST_INTR_STATUS, 0);
> + }
> +
> if (ple_gap) {
> vmcs_write32(PLE_GAP, ple_gap);
> vmcs_write32(PLE_WINDOW, ple_window);
> @@ -4806,6 +4831,16 @@ static int handle_apic_access(struct kvm_vcpu *vcpu)
> return emulate_instruction(vcpu, 0) == EMULATE_DONE;
> }
>
> +static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu)
> +{
> + unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
> + int vector = exit_qualification & 0xff;
> +
> + /* EOI-induced VM exit is trap-like and thus no need to adjust IP */
> + kvm_apic_set_eoi_accelerated(vcpu, vector);
> + return 1;
> +}
> +
> static int handle_apic_write(struct kvm_vcpu *vcpu)
> {
> unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
> @@ -5756,6 +5791,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
> [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold,
> [EXIT_REASON_APIC_ACCESS] = handle_apic_access,
> [EXIT_REASON_APIC_WRITE] = handle_apic_write,
> + [EXIT_REASON_EOI_INDUCED] = handle_apic_eoi_induced,
> [EXIT_REASON_WBINVD] = handle_wbinvd,
> [EXIT_REASON_XSETBV] = handle_xsetbv,
> [EXIT_REASON_TASK_SWITCH] = handle_task_switch,
> @@ -6105,6 +6141,75 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
> vmcs_write32(TPR_THRESHOLD, irr);
> }
>
> +static int vmx_has_virtual_interrupt_delivery(struct kvm_vcpu *vcpu)
> +{
> + return irqchip_in_kernel(vcpu->kvm) && enable_apicv_reg_vid;
No need to check irqchip_in_kernel() here. Callers check it.
> +}
> +
> +static void vmx_update_rvi(int vector)
> +{
> + u16 status;
> + u8 old;
> +
> + status = vmcs_read16(GUEST_INTR_STATUS);
> + old = (u8)status & 0xff;
> + if ((u8)vector != old) {
> + status &= ~0xff;
> + status |= (u8)vector;
> + vmcs_write16(GUEST_INTR_STATUS, status);
> + }
> +}
> +
> +static void vmx_update_irq(struct kvm_vcpu *vcpu)
> +{
> + int vector;
> + struct vcpu_vmx *vmx = to_vmx(vcpu);
> +
> + if (!enable_apicv_reg_vid)
> + return ;
> +
> + vector = kvm_lapic_find_highest_irr(vcpu);
> + if (vector == -1)
> + return;
> +
> + vmx_update_rvi(vector);
> +
> + if (vmx->eoi_exitmap_changed) {
As I said in previous reviews define new request bit. When bitmap is recalculated do
kvm_make_request(vcpu, KVM_REQ_EOIBITMAP)
on vcpu entry do
if (kvm_check_request(vcpu, KVM_REQ_EOIBITMAP)
update_eoibitmap(vcpu);
> + int index;
> + for_each_set_bit(index,
> + (unsigned long *)(&vmx->eoi_exitmap_changed), 8)
> + vmcs_write32(EOI_EXIT_BITMAP0 + index,
> + vmx->eoi_exit_bitmap[index]);
> + vmx->eoi_exitmap_changed = 0;
> + }
> +}
> +
> +static void vmx_update_eoi_exitmap(struct kvm_vcpu *vcpu,
> + int vector, bool set)
Caller passes u32 to vector.
> +{
> + struct vcpu_vmx *vmx = to_vmx(vcpu);
> + int index, changed;
> +
> + if (!enable_apicv_reg_vid)
> + return ;
> +
> + if (WARN_ONCE((vector < 0) || (vector > 255),
> + "KVM VMX: vector (%d) out of range\n", vector))
> + return;
> +
> + index = vector >> 5;
> +
> + if (set)
> + changed = !test_and_set_bit(vector,
> + (unsigned long *)&vmx->eoi_exit_bitmap);
> + else
> + changed = !test_and_clear_bit(vector,
> + (unsigned long *)&vmx->eoi_exit_bitmap);
> +
> + if (changed)
> + vmx->eoi_exitmap_changed |= 1 << index;
eoi exit bitmap changes should be rare enough to not care about tracking
changes. If function is called update vmcs on the next entry.
> +}
> +
> static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
> {
> u32 exit_intr_info;
> @@ -7365,6 +7470,9 @@ static struct kvm_x86_ops vmx_x86_ops = {
> .enable_nmi_window = enable_nmi_window,
> .enable_irq_window = enable_irq_window,
> .update_cr8_intercept = update_cr8_intercept,
> + .has_virtual_interrupt_delivery = vmx_has_virtual_interrupt_delivery,
> + .update_irq = vmx_update_irq,
> + .update_eoi_exitmap = vmx_update_eoi_exitmap,
>
> .set_tss_addr = vmx_set_tss_addr,
> .get_tdp_level = get_ept_level,
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 3bdaf29..408445b 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -5534,12 +5534,13 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
> vcpu->arch.nmi_injected = true;
> kvm_x86_ops->set_nmi(vcpu);
> }
> - } else if (kvm_cpu_has_interrupt(vcpu)) {
> - if (kvm_x86_ops->interrupt_allowed(vcpu)) {
> - kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
> - false);
> - kvm_x86_ops->set_irq(vcpu);
> - }
> + } else if (kvm_cpu_has_injectable_intr(vcpu) &&
> + kvm_x86_ops->interrupt_allowed(vcpu)) {
> + int vector;
> + vector = kvm_cpu_get_interrupt(vcpu);
> +
> + kvm_queue_interrupt(vcpu, vector, false);
Why introduce vector variable here? Leave it as it was.
> + kvm_x86_ops->set_irq(vcpu);
> }
> }
>
> @@ -5663,10 +5664,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
> /* enable NMI/IRQ window open exits if needed */
> if (vcpu->arch.nmi_pending)
> kvm_x86_ops->enable_nmi_window(vcpu);
> - else if (kvm_cpu_has_interrupt(vcpu) || req_int_win)
> + else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
> kvm_x86_ops->enable_irq_window(vcpu);
>
> if (kvm_lapic_enabled(vcpu)) {
> + /* update archtecture specific hints for APIC
> + * virtual interrupt delivery */
> + kvm_x86_ops->update_irq(vcpu);
> update_cr8_intercept(vcpu);
> kvm_lapic_sync_to_vapic(vcpu);
> }
> diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
> index cfb7e4d..081225a 100644
> --- a/virt/kvm/ioapic.c
> +++ b/virt/kvm/ioapic.c
> @@ -115,6 +115,40 @@ static void update_handled_vectors(struct kvm_ioapic *ioapic)
> smp_wmb();
> }
>
> +void _ioapic_update_eoi_exitmap(struct kvm_ioapic *ioapic, int pin)
> +{
Bette make is ioapic_update_eoi_exitmap_one() or something. Underscore
is undescriptive.
> + union kvm_ioapic_redirect_entry *e;
> +
> + e = &ioapic->redirtbl[pin];
> +
> + /* PIT is a special case: which is edge trig but have EOI hook.
> + * Always set the eoi exit bitmap for PIT interrupt*/
No hacks please. Check that ack notifier is register for gsi.
> + if (e->fields.mask != 0x1 &&
!e->fields.mask please.
> + (e->fields.trig_mode == IOAPIC_LEVEL_TRIG || (pin == 2))) {
> + struct kvm_lapic_irq irqe;
> +
> + irqe.dest_id = e->fields.dest_id;
> + irqe.vector = e->fields.vector;
> + irqe.dest_mode = e->fields.dest_mode;
> + irqe.delivery_mode = e->fields.delivery_mode << 8;
> + kvm_update_eoi_exitmap(ioapic->kvm, &irqe);
> + }
> +}
> +
> +void ioapic_update_eoi_exitmap(struct kvm *kvm)
> +{
> + struct kvm_ioapic *ioapic = kvm->arch.vioapic;
> + union kvm_ioapic_redirect_entry *e;
> + int index = 0;
> +
> + while (index < IOAPIC_NUM_PINS) {
this if for() loop.
> + e = &ioapic->redirtbl[index];
> + if (e->fields.vector >= 0 && e->fields.vector <= 255)
vector field is u8, the check is always true. Better move mask check
here.
> + _ioapic_update_eoi_exitmap(ioapic, index);
> + index++;
> + }
> +}
> +
> static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
> {
> unsigned index;
> @@ -156,6 +190,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
> if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
> && ioapic->irr & (1 << index))
> ioapic_service(ioapic, index);
> + _ioapic_update_eoi_exitmap(ioapic, index);
> break;
> }
> }
> diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
> index a30abfe..e8d67cf 100644
> --- a/virt/kvm/ioapic.h
> +++ b/virt/kvm/ioapic.h
> @@ -82,5 +82,6 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
> struct kvm_lapic_irq *irq);
> int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
> int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
> +void ioapic_update_eoi_exitmap(struct kvm *kvm);
>
> #endif
> --
> 1.7.1
--
Gleb.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
