Commit 66450a21 authored by Jan Kiszka's avatar Jan Kiszka Committed by Gleb Natapov
Browse files

KVM: x86: Rework INIT and SIPI handling 



A VCPU sending INIT or SIPI to some other VCPU races for setting the
remote VCPU's mp_state. When we were unlucky, KVM_MP_STATE_INIT_RECEIVED
was overwritten by kvm_emulate_halt and, thus, got lost.

This introduces APIC events for those two signals, keeping them in
kvm_apic until kvm_apic_accept_events is run over the target vcpu
context. kvm_apic_has_events reports to kvm_arch_vcpu_runnable if there
are pending events, thus if vcpu blocking should end.

The patch comes with the side effect of effectively obsoleting
KVM_MP_STATE_SIPI_RECEIVED. We still accept it from user space, but
immediately translate it to KVM_MP_STATE_INIT_RECEIVED + KVM_APIC_SIPI.
The vcpu itself will no longer enter the KVM_MP_STATE_SIPI_RECEIVED
state. That also means we no longer exit to user space after receiving a
SIPI event.

Furthermore, we already reset the VCPU on INIT, only fixing up the code
segment later on when SIPI arrives. Moreover, we fix INIT handling for
the BSP: it never enter wait-for-SIPI but directly starts over on INIT.

Tested-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: default avatarJan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: default avatarGleb Natapov <gleb@redhat.com>
parent 5d218814

arch/x86/include/asm/kvm_host.h

+2 −1
Original line number Diff line number Diff line
@@ -345,7 +345,6 @@ struct kvm_vcpu_arch { 
	unsigned long apic_attention;

	int32_t apic_arb_prio;

	int mp_state;

	int sipi_vector;

	u64 ia32_misc_enable_msr;

	bool tpr_access_reporting;
@@ -819,6 +818,7 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); 


void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);

int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);

void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector);



int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,

		    int reason, bool has_error_code, u32 error_code);
@@ -1002,6 +1002,7 @@ 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);

void kvm_vcpu_reset(struct kvm_vcpu *vcpu);



void kvm_define_shared_msr(unsigned index, u32 msr);

void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);

arch/x86/kvm/lapic.c

+40 −8
Original line number Diff line number Diff line
@@ -731,7 +731,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, 
	case APIC_DM_INIT:

		if (!trig_mode || level) {

			result = 1;

			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;

			/* assumes that there are only KVM_APIC_INIT/SIPI */

			apic->pending_events = (1UL << KVM_APIC_INIT);

			/* make sure pending_events is visible before sending

			 * the request */

			smp_wmb();

			kvm_make_request(KVM_REQ_EVENT, vcpu);

			kvm_vcpu_kick(vcpu);

		} else {
@@ -743,13 +747,13 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, 
	case APIC_DM_STARTUP:

		apic_debug("SIPI to vcpu %d vector 0x%02x\n",

			   vcpu->vcpu_id, vector);

		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {

		result = 1;

			vcpu->arch.sipi_vector = vector;

			vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;

		apic->sipi_vector = vector;

		/* make sure sipi_vector is visible for the receiver */

		smp_wmb();

		set_bit(KVM_APIC_SIPI, &apic->pending_events);

		kvm_make_request(KVM_REQ_EVENT, vcpu);

		kvm_vcpu_kick(vcpu);

		}

		break;



	case APIC_DM_EXTINT:
@@ -1860,6 +1864,34 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data) 
					 addr);

}



void kvm_apic_accept_events(struct kvm_vcpu *vcpu)

{

	struct kvm_lapic *apic = vcpu->arch.apic;

	unsigned int sipi_vector;



	if (!kvm_vcpu_has_lapic(vcpu))

		return;



	if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) {

		kvm_lapic_reset(vcpu);

		kvm_vcpu_reset(vcpu);

		if (kvm_vcpu_is_bsp(apic->vcpu))

			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;

		else

			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;

	}

	if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events) &&

	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {

		/* evaluate pending_events before reading the vector */

		smp_rmb();

		sipi_vector = apic->sipi_vector;

		pr_debug("vcpu %d received sipi with vector # %x\n",

			 vcpu->vcpu_id, sipi_vector);

		kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector);

		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;

	}

}



void kvm_lapic_init(void)

{

	/* do not patch jump label more than once per second */

arch/x86/kvm/lapic.h

+11 −0
Original line number Diff line number Diff line
@@ -5,6 +5,9 @@ 


#include <linux/kvm_host.h>



#define KVM_APIC_INIT		0

#define KVM_APIC_SIPI		1



struct kvm_timer {

	struct hrtimer timer;

	s64 period; 				/* unit: ns */
@@ -32,6 +35,8 @@ struct kvm_lapic { 
	void *regs;

	gpa_t vapic_addr;

	struct page *vapic_page;

	unsigned long pending_events;

	unsigned int sipi_vector;

};

int kvm_create_lapic(struct kvm_vcpu *vcpu);

void kvm_free_lapic(struct kvm_vcpu *vcpu);
@@ -39,6 +44,7 @@ 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);

u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);

void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
@@ -158,4 +164,9 @@ void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu, 
				struct kvm_lapic_irq *irq,

				u64 *eoi_bitmap);



static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)

{

	return vcpu->arch.apic->pending_events;

}



#endif

arch/x86/kvm/svm.c

+0 −6
Original line number Diff line number Diff line
@@ -1199,12 +1199,6 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu) 


	init_vmcb(svm);



	if (!kvm_vcpu_is_bsp(vcpu)) {

		kvm_rip_write(vcpu, 0);

		svm->vmcb->save.cs.base = svm->vcpu.arch.sipi_vector << 12;

		svm->vmcb->save.cs.selector = svm->vcpu.arch.sipi_vector << 8;

	}



	kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy);

	kvm_register_write(vcpu, VCPU_REGS_RDX, eax);

}

arch/x86/kvm/vmx.c

+2 −10
Original line number Diff line number Diff line
@@ -4119,12 +4119,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) 
	vmx_segment_cache_clear(vmx);



	seg_setup(VCPU_SREG_CS);

	if (kvm_vcpu_is_bsp(&vmx->vcpu))

	vmcs_write16(GUEST_CS_SELECTOR, 0xf000);

	else {

		vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.arch.sipi_vector << 8);

		vmcs_writel(GUEST_CS_BASE, vmx->vcpu.arch.sipi_vector << 12);

	}



	seg_setup(VCPU_SREG_DS);

	seg_setup(VCPU_SREG_ES);
@@ -4147,10 +4142,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) 
	vmcs_writel(GUEST_SYSENTER_EIP, 0);



	vmcs_writel(GUEST_RFLAGS, 0x02);

	if (kvm_vcpu_is_bsp(&vmx->vcpu))

	kvm_rip_write(vcpu, 0xfff0);

	else

		kvm_rip_write(vcpu, 0);



	vmcs_writel(GUEST_GDTR_BASE, 0);

	vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);

CRA Git | Maintained and supported by SUSTech CRA and CCSE