Commit 647daca2 authored by Tom Lendacky's avatar Tom Lendacky Committed by Paolo Bonzini
Browse files

KVM: SVM: Add support for booting APs in an SEV-ES guest 



Typically under KVM, an AP is booted using the INIT-SIPI-SIPI sequence,
where the guest vCPU register state is updated and then the vCPU is VMRUN
to begin execution of the AP. For an SEV-ES guest, this won't work because
the guest register state is encrypted.

Following the GHCB specification, the hypervisor must not alter the guest
register state, so KVM must track an AP/vCPU boot. Should the guest want
to park the AP, it must use the AP Reset Hold exit event in place of, for
example, a HLT loop.

First AP boot (first INIT-SIPI-SIPI sequence):
  Execute the AP (vCPU) as it was initialized and measured by the SEV-ES
  support. It is up to the guest to transfer control of the AP to the
  proper location.

Subsequent AP boot:
  KVM will expect to receive an AP Reset Hold exit event indicating that
  the vCPU is being parked and will require an INIT-SIPI-SIPI sequence to
  awaken it. When the AP Reset Hold exit event is received, KVM will place
  the vCPU into a simulated HLT mode. Upon receiving the INIT-SIPI-SIPI
  sequence, KVM will make the vCPU runnable. It is again up to the guest
  to then transfer control of the AP to the proper location.

  To differentiate between an actual HLT and an AP Reset Hold, a new MP
  state is introduced, KVM_MP_STATE_AP_RESET_HOLD, which the vCPU is
  placed in upon receiving the AP Reset Hold exit event. Additionally, to
  communicate the AP Reset Hold exit event up to userspace (if needed), a
  new exit reason is introduced, KVM_EXIT_AP_RESET_HOLD.

A new x86 ops function is introduced, vcpu_deliver_sipi_vector, in order
to accomplish AP booting. For VMX, vcpu_deliver_sipi_vector is set to the
original SIPI delivery function, kvm_vcpu_deliver_sipi_vector(). SVM adds
a new function that, for non SEV-ES guests, invokes the original SIPI
delivery function, kvm_vcpu_deliver_sipi_vector(), but for SEV-ES guests,
implements the logic above.

Signed-off-by: default avatarTom Lendacky <thomas.lendacky@amd.com>
Message-Id: <e8fbebe8eb161ceaabdad7c01a5859a78b424d5e.1609791600.git.thomas.lendacky@amd.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent f2c7ef3b

arch/x86/include/asm/kvm_host.h

+3 −0
Original line number Diff line number Diff line
@@ -1299,6 +1299,8 @@ struct kvm_x86_ops { 
	void (*migrate_timers)(struct kvm_vcpu *vcpu);

	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);

	int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);



	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);

};



struct kvm_x86_nested_ops {
@@ -1480,6 +1482,7 @@ int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); 
int kvm_emulate_cpuid(struct kvm_vcpu *vcpu);

int kvm_emulate_halt(struct kvm_vcpu *vcpu);

int kvm_vcpu_halt(struct kvm_vcpu *vcpu);

int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu);

int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);



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

arch/x86/kvm/lapic.c

+1 −1
Original line number Diff line number Diff line
@@ -2898,7 +2898,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) 
			/* evaluate pending_events before reading the vector */

			smp_rmb();

			sipi_vector = apic->sipi_vector;

			kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector);

			kvm_x86_ops.vcpu_deliver_sipi_vector(vcpu, sipi_vector);

			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;

		}

	}

arch/x86/kvm/svm/sev.c

+22 −0
Original line number Diff line number Diff line
@@ -1563,6 +1563,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) 
			goto vmgexit_err;

		break;

	case SVM_VMGEXIT_NMI_COMPLETE:

	case SVM_VMGEXIT_AP_HLT_LOOP:

	case SVM_VMGEXIT_AP_JUMP_TABLE:

	case SVM_VMGEXIT_UNSUPPORTED_EVENT:

		break;
@@ -1888,6 +1889,9 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) 
	case SVM_VMGEXIT_NMI_COMPLETE:

		ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET);

		break;

	case SVM_VMGEXIT_AP_HLT_LOOP:

		ret = kvm_emulate_ap_reset_hold(&svm->vcpu);

		break;

	case SVM_VMGEXIT_AP_JUMP_TABLE: {

		struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
@@ -2040,3 +2044,21 @@ void sev_es_vcpu_put(struct vcpu_svm *svm) 
		wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]);

	}

}



void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)

{

	struct vcpu_svm *svm = to_svm(vcpu);



	/* First SIPI: Use the values as initially set by the VMM */

	if (!svm->received_first_sipi) {

		svm->received_first_sipi = true;

		return;

	}



	/*

	 * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where

	 * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a

	 * non-zero value.

	 */

	ghcb_set_sw_exit_info_2(svm->ghcb, 1);

}

arch/x86/kvm/svm/svm.c

+10 −0
Original line number Diff line number Diff line
@@ -4382,6 +4382,14 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) 
		   (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT));

}



static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)

{

	if (!sev_es_guest(vcpu->kvm))

		return kvm_vcpu_deliver_sipi_vector(vcpu, vector);



	sev_vcpu_deliver_sipi_vector(vcpu, vector);

}



static void svm_vm_destroy(struct kvm *kvm)

{

	avic_vm_destroy(kvm);
@@ -4524,6 +4532,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { 


	.msr_filter_changed = svm_msr_filter_changed,

	.complete_emulated_msr = svm_complete_emulated_msr,



	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,

};



static struct kvm_x86_init_ops svm_init_ops __initdata = {

arch/x86/kvm/svm/svm.h

+2 −0
Original line number Diff line number Diff line
@@ -185,6 +185,7 @@ struct vcpu_svm { 
	struct vmcb_save_area *vmsa;

	struct ghcb *ghcb;

	struct kvm_host_map ghcb_map;

	bool received_first_sipi;



	/* SEV-ES scratch area support */

	void *ghcb_sa;
@@ -591,6 +592,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm); 
void sev_es_create_vcpu(struct vcpu_svm *svm);

void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu);

void sev_es_vcpu_put(struct vcpu_svm *svm);

void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);



/* vmenter.S */