kernel-fxtec-pro1x/arch/x86/kvm/lapic.h

227 lines
6.9 KiB
C
Raw Normal View History

#ifndef __KVM_X86_LAPIC_H
#define __KVM_X86_LAPIC_H
#include <kvm/iodev.h>
#include <linux/kvm_host.h>
#define KVM_APIC_INIT 0
#define KVM_APIC_SIPI 1
#define KVM_APIC_LVT_NUM 6
#define KVM_APIC_SHORT_MASK 0xc0000
#define KVM_APIC_DEST_MASK 0x800
struct kvm_timer {
struct hrtimer timer;
s64 period; /* unit: ns */
u32 timer_mode;
u32 timer_mode_mask;
u64 tscdeadline;
u64 expired_tscdeadline;
atomic_t pending; /* accumulated triggered timers */
bool hv_timer_in_use;
};
struct kvm_lapic {
unsigned long base_address;
struct kvm_io_device dev;
struct kvm_timer lapic_timer;
u32 divide_count;
struct kvm_vcpu *vcpu;
KVM: x86: detect SPIV changes under APICv APIC-write VM exits are "trap-like": they save CS:RIP values for the instruction after the write, and more importantly, the handler will already see the new value in the virtual-APIC page. This caused a bug if you used KVM_SET_IRQCHIP to set the SW-enabled bit in the SPIV register. The chain of events is as follows: * When the irqchip is added to the destination VM, the apic_sw_disabled static key is incremented (1) * When the KVM_SET_IRQCHIP ioctl is invoked, it is decremented (0) * When the guest disables the bit in the SPIV register, e.g. as part of shutdown, apic_set_spiv does not notice the change and the static key is _not_ incremented. * When the guest is destroyed, the static key is decremented (-1), resulting in this trace: WARNING: at kernel/jump_label.c:81 __static_key_slow_dec+0xa6/0xb0() jump label: negative count! [<ffffffff816bf898>] dump_stack+0x19/0x1b [<ffffffff8107c6f1>] warn_slowpath_common+0x61/0x80 [<ffffffff8107c76c>] warn_slowpath_fmt+0x5c/0x80 [<ffffffff811931e6>] __static_key_slow_dec+0xa6/0xb0 [<ffffffff81193226>] static_key_slow_dec_deferred+0x16/0x20 [<ffffffffa0637698>] kvm_free_lapic+0x88/0xa0 [kvm] [<ffffffffa061c63e>] kvm_arch_vcpu_uninit+0x2e/0xe0 [kvm] [<ffffffffa05ff301>] kvm_vcpu_uninit+0x21/0x40 [kvm] [<ffffffffa067cec7>] vmx_free_vcpu+0x47/0x70 [kvm_intel] [<ffffffffa061bc50>] kvm_arch_vcpu_free+0x50/0x60 [kvm] [<ffffffffa061ca22>] kvm_arch_destroy_vm+0x102/0x260 [kvm] [<ffffffff810b68fd>] ? synchronize_srcu+0x1d/0x20 [<ffffffffa06030d1>] kvm_put_kvm+0xe1/0x1c0 [kvm] [<ffffffffa06036f8>] kvm_vcpu_release+0x18/0x20 [kvm] [<ffffffff81215c62>] __fput+0x102/0x310 [<ffffffff81215f4e>] ____fput+0xe/0x10 [<ffffffff810ab664>] task_work_run+0xb4/0xe0 [<ffffffff81083944>] do_exit+0x304/0xc60 [<ffffffff816c8dfc>] ? _raw_spin_unlock_irq+0x2c/0x50 [<ffffffff810fd22d>] ? trace_hardirqs_on_caller+0xfd/0x1c0 [<ffffffff8108432c>] do_group_exit+0x4c/0xc0 [<ffffffff810843b4>] SyS_exit_group+0x14/0x20 [<ffffffff816d33a9>] system_call_fastpath+0x16/0x1b Signed-off-by: Radim Krčmář <rkrcmar@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2014-10-30 08:06:45 -06:00
bool sw_enabled;
bool irr_pending;
bool lvt0_in_nmi_mode;
/* Number of bits set in ISR. */
s16 isr_count;
/* The highest vector set in ISR; if -1 - invalid, must scan ISR. */
int highest_isr_cache;
/**
* APIC register page. The layout matches the register layout seen by
* the guest 1:1, because it is accessed by the vmx microcode.
* Note: Only one register, the TPR, is used by the microcode.
*/
void *regs;
gpa_t vapic_addr;
struct gfn_to_hva_cache vapic_cache;
unsigned long pending_events;
unsigned int sipi_vector;
};
struct dest_map;
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_get_apic_interrupt(struct kvm_vcpu *vcpu);
void kvm_apic_accept_events(struct kvm_vcpu *vcpu);
void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event);
u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu);
void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu);
void kvm_apic_set_version(struct kvm_vcpu *vcpu);
int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val);
int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
void *data);
bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, unsigned int dest, int dest_mode);
void __kvm_apic_update_irr(u32 *pir, void *regs);
void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
struct dest_map *dest_map);
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, struct dest_map *dest_map);
u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
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);
int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
{
return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE;
}
int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
void kvm_lapic_init(void);
#define VEC_POS(v) ((v) & (32 - 1))
#define REG_POS(v) (((v) >> 5) << 4)
static inline void kvm_lapic_set_vector(int vec, void *bitmap)
{
set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}
static inline void kvm_lapic_set_irr(int vec, struct kvm_lapic *apic)
{
kvm_lapic_set_vector(vec, apic->regs + APIC_IRR);
/*
* irr_pending must be true if any interrupt is pending; set it after
* APIC_IRR to avoid race with apic_clear_irr
*/
apic->irr_pending = true;
}
static inline u32 kvm_lapic_get_reg(struct kvm_lapic *apic, int reg_off)
{
return *((u32 *) (apic->regs + reg_off));
}
static inline void kvm_lapic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
{
*((u32 *) (apic->regs + reg_off)) = val;
}
extern struct static_key kvm_no_apic_vcpu;
static inline bool lapic_in_kernel(struct kvm_vcpu *vcpu)
{
if (static_key_false(&kvm_no_apic_vcpu))
return vcpu->arch.apic;
return true;
}
extern struct static_key_deferred apic_hw_disabled;
static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic)
{
if (static_key_false(&apic_hw_disabled.key))
return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
return MSR_IA32_APICBASE_ENABLE;
}
extern struct static_key_deferred apic_sw_disabled;
static inline bool kvm_apic_sw_enabled(struct kvm_lapic *apic)
{
if (static_key_false(&apic_sw_disabled.key))
return apic->sw_enabled;
return true;
}
static inline bool kvm_apic_present(struct kvm_vcpu *vcpu)
{
return lapic_in_kernel(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic);
}
static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
{
return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic);
}
static inline int apic_x2apic_mode(struct kvm_lapic *apic)
{
return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
}
static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu)
{
return vcpu->arch.apic && vcpu->arch.apicv_active;
}
static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
{
return lapic_in_kernel(vcpu) && vcpu->arch.apic->pending_events;
}
static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq)
{
return (irq->delivery_mode == APIC_DM_LOWEST ||
irq->msi_redir_hint);
}
static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
{
return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
}
static inline u32 kvm_apic_id(struct kvm_lapic *apic)
kvm/x86: Hyper-V synthetic interrupt controller SynIC (synthetic interrupt controller) is a lapic extension, which is controlled via MSRs and maintains for each vCPU - 16 synthetic interrupt "lines" (SINT's); each can be configured to trigger a specific interrupt vector optionally with auto-EOI semantics - a message page in the guest memory with 16 256-byte per-SINT message slots - an event flag page in the guest memory with 16 2048-bit per-SINT event flag areas The host triggers a SINT whenever it delivers a new message to the corresponding slot or flips an event flag bit in the corresponding area. The guest informs the host that it can try delivering a message by explicitly asserting EOI in lapic or writing to End-Of-Message (EOM) MSR. The userspace (qemu) triggers interrupts and receives EOM notifications via irqfd with resampler; for that, a GSI is allocated for each configured SINT, and irq_routing api is extended to support GSI-SINT mapping. Changes v4: * added activation of SynIC by vcpu KVM_ENABLE_CAP * added per SynIC active flag * added deactivation of APICv upon SynIC activation Changes v3: * added KVM_CAP_HYPERV_SYNIC and KVM_IRQ_ROUTING_HV_SINT notes into docs Changes v2: * do not use posted interrupts for Hyper-V SynIC AutoEOI vectors * add Hyper-V SynIC vectors into EOI exit bitmap * Hyper-V SyniIC SINT msr write logic simplified Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com> Reviewed-by: Roman Kagan <rkagan@virtuozzo.com> Signed-off-by: Denis V. Lunev <den@openvz.org> CC: Gleb Natapov <gleb@kernel.org> CC: Paolo Bonzini <pbonzini@redhat.com> CC: Roman Kagan <rkagan@virtuozzo.com> CC: Denis V. Lunev <den@openvz.org> CC: qemu-devel@nongnu.org Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2015-11-10 05:36:34 -07:00
{
/* To avoid a race between apic_base and following APIC_ID update when
* switching to x2apic_mode, the x2apic mode returns initial x2apic id.
*/
if (apic_x2apic_mode(apic))
return apic->vcpu->vcpu_id;
return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
kvm/x86: Hyper-V synthetic interrupt controller SynIC (synthetic interrupt controller) is a lapic extension, which is controlled via MSRs and maintains for each vCPU - 16 synthetic interrupt "lines" (SINT's); each can be configured to trigger a specific interrupt vector optionally with auto-EOI semantics - a message page in the guest memory with 16 256-byte per-SINT message slots - an event flag page in the guest memory with 16 2048-bit per-SINT event flag areas The host triggers a SINT whenever it delivers a new message to the corresponding slot or flips an event flag bit in the corresponding area. The guest informs the host that it can try delivering a message by explicitly asserting EOI in lapic or writing to End-Of-Message (EOM) MSR. The userspace (qemu) triggers interrupts and receives EOM notifications via irqfd with resampler; for that, a GSI is allocated for each configured SINT, and irq_routing api is extended to support GSI-SINT mapping. Changes v4: * added activation of SynIC by vcpu KVM_ENABLE_CAP * added per SynIC active flag * added deactivation of APICv upon SynIC activation Changes v3: * added KVM_CAP_HYPERV_SYNIC and KVM_IRQ_ROUTING_HV_SINT notes into docs Changes v2: * do not use posted interrupts for Hyper-V SynIC AutoEOI vectors * add Hyper-V SynIC vectors into EOI exit bitmap * Hyper-V SyniIC SINT msr write logic simplified Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com> Reviewed-by: Roman Kagan <rkagan@virtuozzo.com> Signed-off-by: Denis V. Lunev <den@openvz.org> CC: Gleb Natapov <gleb@kernel.org> CC: Paolo Bonzini <pbonzini@redhat.com> CC: Roman Kagan <rkagan@virtuozzo.com> CC: Denis V. Lunev <den@openvz.org> CC: qemu-devel@nongnu.org Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2015-11-10 05:36:34 -07:00
}
bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
void wait_lapic_expire(struct kvm_vcpu *vcpu);
bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu);
int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
const unsigned long *bitmap, u32 bitmap_size);
void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu);
void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu);
void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu);
bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu);
#endif