Re: [PATCH v7] KVM: s390: Add new reset vcpu API

[David Hildenbrand <david@redhat.com>]

On 10.01.20 12:45, Janosch Frank wrote:
> The architecture states that we need to reset local IRQs for all CPU
> resets. Because the old reset interface did not support the normal CPU
> reset we never did that on a normal reset.
> 
> Let's implement an interface for the missing normal and clear resets
> and reset all local IRQs, registers and control structures as stated
> in the architecture.
> 
> Userspace might already reset the registers via the vcpu run struct,
> but as we need the interface for the interrupt clearing part anyway,
> we implement the resets fully and don't rely on userspace to reset the
> rest.
> 
> Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
> Reviewed-by: Cornelia Huck <cohuck@redhat.com>
> ---
>  Documentation/virt/kvm/api.txt |  43 +++++++++++++
>  arch/s390/kvm/kvm-s390.c       | 112 +++++++++++++++++++++++----------
>  include/uapi/linux/kvm.h       |   5 ++
>  3 files changed, 127 insertions(+), 33 deletions(-)
> 
> diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.txt
> index ebb37b34dcfc..73448764f544 100644
> --- a/Documentation/virt/kvm/api.txt
> +++ b/Documentation/virt/kvm/api.txt
> @@ -4168,6 +4168,42 @@ This ioctl issues an ultravisor call to terminate the secure guest,
>  unpins the VPA pages and releases all the device pages that are used to
>  track the secure pages by hypervisor.
>  
> +4.122 KVM_S390_NORMAL_RESET
> +
> +Capability: KVM_CAP_S390_VCPU_RESETS
> +Architectures: s390
> +Type: vcpu ioctl
> +Parameters: none
> +Returns: 0
> +
> +This ioctl resets VCPU registers and control structures according to
> +the cpu reset definition in the POP (Principles Of Operation).
> +
> +4.123 KVM_S390_INITIAL_RESET
> +
> +Capability: none
> +Architectures: s390
> +Type: vcpu ioctl
> +Parameters: none
> +Returns: 0
> +
> +This ioctl resets VCPU registers and control structures according to
> +the initial cpu reset definition in the POP. However, the cpu is not
> +put into ESA mode. This reset is a superset of the normal reset.
> +
> +4.124 KVM_S390_CLEAR_RESET
> +
> +Capability: KVM_CAP_S390_VCPU_RESETS
> +Architectures: s390
> +Type: vcpu ioctl
> +Parameters: none
> +Returns: 0
> +
> +This ioctl resets VCPU registers and control structures according to
> +the clear cpu reset definition in the POP. However, the cpu is not put
> +into ESA mode. This reset is a superset of the initial reset.
> +
> +
>  5. The kvm_run structure
>  ------------------------
>  
> @@ -5396,3 +5432,10 @@ handling by KVM (as some KVM hypercall may be mistakenly treated as TLB
>  flush hypercalls by Hyper-V) so userspace should disable KVM identification
>  in CPUID and only exposes Hyper-V identification. In this case, guest
>  thinks it's running on Hyper-V and only use Hyper-V hypercalls.
> +
> +8.22 KVM_CAP_S390_VCPU_RESETS
> +
> +Architectures: s390
> +
> +This capability indicates that the KVM_S390_NORMAL_RESET and
> +KVM_S390_CLEAR_RESET ioctls are available.
> diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
> index d9e6bf3d54f0..5640f3d6f98d 100644
> --- a/arch/s390/kvm/kvm-s390.c
> +++ b/arch/s390/kvm/kvm-s390.c
> @@ -529,6 +529,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>  	case KVM_CAP_S390_CMMA_MIGRATION:
>  	case KVM_CAP_S390_AIS:
>  	case KVM_CAP_S390_AIS_MIGRATION:
> +	case KVM_CAP_S390_VCPU_RESETS:
>  		r = 1;
>  		break;
>  	case KVM_CAP_S390_HPAGE_1M:
> @@ -2844,35 +2845,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
>  
>  }
>  
> -static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
> -{
> -	/* this equals initial cpu reset in pop, but we don't switch to ESA */
> -	vcpu->arch.sie_block->gpsw.mask = 0UL;
> -	vcpu->arch.sie_block->gpsw.addr = 0UL;
> -	kvm_s390_set_prefix(vcpu, 0);
> -	kvm_s390_set_cpu_timer(vcpu, 0);
> -	vcpu->arch.sie_block->ckc       = 0UL;
> -	vcpu->arch.sie_block->todpr     = 0;
> -	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
> -	vcpu->arch.sie_block->gcr[0]  = CR0_UNUSED_56 |
> -					CR0_INTERRUPT_KEY_SUBMASK |
> -					CR0_MEASUREMENT_ALERT_SUBMASK;
> -	vcpu->arch.sie_block->gcr[14] = CR14_UNUSED_32 |
> -					CR14_UNUSED_33 |
> -					CR14_EXTERNAL_DAMAGE_SUBMASK;
> -	/* make sure the new fpc will be lazily loaded */
> -	save_fpu_regs();
> -	current->thread.fpu.fpc = 0;
> -	vcpu->arch.sie_block->gbea = 1;
> -	vcpu->arch.sie_block->pp = 0;
> -	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
> -	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
> -	kvm_clear_async_pf_completion_queue(vcpu);
> -	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
> -		kvm_s390_vcpu_stop(vcpu);
> -	kvm_s390_clear_local_irqs(vcpu);
> -}
> -
>  void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
>  {
>  	mutex_lock(&vcpu->kvm->lock);
> @@ -3287,10 +3259,75 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
>  	return r;
>  }
>  
> -static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
> +static void kvm_arch_vcpu_ioctl_normal_reset(struct kvm_vcpu *vcpu)
>  {
> -	kvm_s390_vcpu_initial_reset(vcpu);
> -	return 0;
> +	vcpu->arch.sie_block->gpsw.mask = ~PSW_MASK_RI;
> +	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
> +	memset(vcpu->run->s.regs.riccb, 0, sizeof(vcpu->run->s.regs.riccb));
> +
> +	kvm_clear_async_pf_completion_queue(vcpu);
> +	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
> +		kvm_s390_vcpu_stop(vcpu);
> +	kvm_s390_clear_local_irqs(vcpu);
> +}
> +
> +static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
> +{
> +	/* Initial reset is a superset of the normal reset */
> +	kvm_arch_vcpu_ioctl_normal_reset(vcpu);
> +
> +	/* this equals initial cpu reset in pop, but we don't switch to ESA */
> +	vcpu->arch.sie_block->gpsw.mask = 0UL;
> +	vcpu->arch.sie_block->gpsw.addr = 0UL;
> +	kvm_s390_set_prefix(vcpu, 0);
> +	kvm_s390_set_cpu_timer(vcpu, 0);
> +	vcpu->arch.sie_block->ckc       = 0UL;
> +	vcpu->arch.sie_block->todpr     = 0;
> +	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
> +	vcpu->arch.sie_block->gcr[0]  = CR0_UNUSED_56 |
> +					CR0_INTERRUPT_KEY_SUBMASK |
> +					CR0_MEASUREMENT_ALERT_SUBMASK;
> +	vcpu->arch.sie_block->gcr[14] = CR14_UNUSED_32 |
> +					CR14_UNUSED_33 |
> +					CR14_EXTERNAL_DAMAGE_SUBMASK;

I really dislike such alignments. Can we drop that as we move the code?


-- 
Thanks,

David / dhildenb