Re: [PATCH v5 27/34] KVM: SVM: Add support for booting APs for an SEV-ES guest

[Paolo Bonzini <pbonzini@redhat.com>]

On 10/12/20 18:10, Tom Lendacky wrote:
> From: Tom Lendacky <thomas.lendacky@amd.com>
> 
> 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.
> 
> The GHCB specification also requires the hypervisor to save the address of
> an AP Jump Table so that, for example, vCPUs that have been parked by UEFI
> can be started by the OS. Provide support for the AP Jump Table set/get
> exit code.
> 
> Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
> ---
>   arch/x86/include/asm/kvm_host.h |  2 ++
>   arch/x86/kvm/svm/sev.c          | 50 +++++++++++++++++++++++++++++++++
>   arch/x86/kvm/svm/svm.c          |  7 +++++
>   arch/x86/kvm/svm/svm.h          |  3 ++
>   arch/x86/kvm/x86.c              |  9 ++++++
>   5 files changed, 71 insertions(+)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 048b08437c33..60a3b9d33407 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1286,6 +1286,8 @@ struct kvm_x86_ops {
>   
>   	void (*migrate_timers)(struct kvm_vcpu *vcpu);
>   	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
> +
> +	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
>   };
>   
>   struct kvm_x86_nested_ops {
> diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> index a7531de760b5..b47285384b1f 100644
> --- a/arch/x86/kvm/svm/sev.c
> +++ b/arch/x86/kvm/svm/sev.c
> @@ -17,6 +17,8 @@
>   #include <linux/processor.h>
>   #include <linux/trace_events.h>
>   
> +#include <asm/trapnr.h>
> +
>   #include "x86.h"
>   #include "svm.h"
>   #include "cpuid.h"
> @@ -1449,6 +1451,8 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
>   		if (!ghcb_sw_scratch_is_valid(ghcb))
>   			goto vmgexit_err;
>   		break;
> +	case SVM_VMGEXIT_AP_HLT_LOOP:
> +	case SVM_VMGEXIT_AP_JUMP_TABLE:
>   	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
>   		break;
>   	default:
> @@ -1770,6 +1774,35 @@ int sev_handle_vmgexit(struct vcpu_svm *svm)
>   					    control->exit_info_2,
>   					    svm->ghcb_sa);
>   		break;
> +	case SVM_VMGEXIT_AP_HLT_LOOP:
> +		svm->ap_hlt_loop = true;

This value needs to be communicated to userspace.  Let's get this right 
from the beginning and use a new KVM_MP_STATE_* value instead (perhaps 
reuse KVM_MP_STATE_STOPPED but for x86 #define it as 
KVM_MP_STATE_AP_HOLD_RECEIVED?).

> @@ -68,6 +68,7 @@ struct kvm_sev_info {
>  	int fd;			/* SEV device fd */
>  	unsigned long pages_locked; /* Number of pages locked */
>  	struct list_head regions_list;  /* List of registered regions */
> +	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */

Do you have any plans for migration of this value?  How does the guest 
ensure that the hypervisor does not screw with it?

Paolo

> +		ret = kvm_emulate_halt(&svm->vcpu);
> +		break;
> +	case SVM_VMGEXIT_AP_JUMP_TABLE: {
> +		struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
> +
> +		switch (control->exit_info_1) {
> +		case 0:
> +			/* Set AP jump table address */
> +			sev->ap_jump_table = control->exit_info_2;
> +			break;
> +		case 1:
> +			/* Get AP jump table address */
> +			ghcb_set_sw_exit_info_2(ghcb, sev->ap_jump_table);
> +			break;
> +		default:
> +			pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n",
> +			       control->exit_info_1);
> +			ghcb_set_sw_exit_info_1(ghcb, 1);
> +			ghcb_set_sw_exit_info_2(ghcb,
> +						X86_TRAP_UD |
> +						SVM_EVTINJ_TYPE_EXEPT |
> +						SVM_EVTINJ_VALID);
> +		}
> +
> +		ret = 1;
> +		break;
> +	}
>   	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
>   		vcpu_unimpl(&svm->vcpu,
>   			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
> @@ -1790,3 +1823,20 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
>   	return kvm_sev_es_string_io(&svm->vcpu, size, port,
>   				    svm->ghcb_sa, svm->ghcb_sa_len, in);
>   }
> +
> +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->ap_hlt_loop)
> +		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);
> +	svm->ap_hlt_loop = false;
> +}
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index 8d22ae25a0f8..2dbc20701ef5 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -4400,6 +4400,11 @@ 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)
> +{
> +	sev_vcpu_deliver_sipi_vector(vcpu, vector);
> +}
> +
>   static void svm_vm_destroy(struct kvm *kvm)
>   {
>   	avic_vm_destroy(kvm);
> @@ -4541,6 +4546,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
>   	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
>   
>   	.msr_filter_changed = svm_msr_filter_changed,
> +
> +	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
>   };
>   
>   static struct kvm_x86_init_ops svm_init_ops __initdata = {
> diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
> index b3f03dede6ac..5d570d5a6a2c 100644
> --- a/arch/x86/kvm/svm/svm.h
> +++ b/arch/x86/kvm/svm/svm.h
> @@ -68,6 +68,7 @@ struct kvm_sev_info {
>   	int fd;			/* SEV device fd */
>   	unsigned long pages_locked; /* Number of pages locked */
>   	struct list_head regions_list;  /* List of registered regions */
> +	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
>   };
>   
>   struct kvm_svm {
> @@ -174,6 +175,7 @@ struct vcpu_svm {
>   	struct vmcb_save_area *vmsa;
>   	struct ghcb *ghcb;
>   	struct kvm_host_map ghcb_map;
> +	bool ap_hlt_loop;
>   
>   	/* SEV-ES scratch area support */
>   	void *ghcb_sa;
> @@ -574,5 +576,6 @@ void sev_hardware_teardown(void);
>   void sev_free_vcpu(struct kvm_vcpu *vcpu);
>   int sev_handle_vmgexit(struct vcpu_svm *svm);
>   int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
> +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
>   
>   #endif
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index ddd614a76744..4fd216b61a89 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -10144,6 +10144,15 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
>   {
>   	struct kvm_segment cs;
>   
> +	/*
> +	 * Guests with protected state can't have their state altered by KVM,
> +	 * call the vcpu_deliver_sipi_vector() x86 op for processing.
> +	 */
> +	if (vcpu->arch.guest_state_protected) {
> +		kvm_x86_ops.vcpu_deliver_sipi_vector(vcpu, vector);
> +		return;
> +	}
> +
>   	kvm_get_segment(vcpu, &cs, VCPU_SREG_CS);
>   	cs.selector = vector << 8;
>   	cs.base = vector << 12;
>