diff mbox series

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

Message ID 20200110114540.90713-1-frankja@linux.ibm.com (mailing list archive)
State New, archived
Headers show
Series [v7] KVM: s390: Add new reset vcpu API | expand

Commit Message

Janosch Frank Jan. 10, 2020, 11:45 a.m. UTC
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(-)

Comments

Thomas Huth Jan. 10, 2020, 12:11 p.m. UTC | #1
On 10/01/2020 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;
> +	/* 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;
> +}
> +
> +static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
> +{
> +	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
> +
> +	/* Clear reset is a superset of the initial reset */
> +	kvm_arch_vcpu_ioctl_normal_reset(vcpu);

s/kvm_arch_vcpu_ioctl_normal_reset/kvm_arch_vcpu_ioctl_initial_reset/

> +	memset(&regs->gprs, 0, sizeof(regs->gprs));
> +	/* Will be picked up because of save_fpu_regs() in the initial reset */
> +	memset(&current->thread.fpu.vxrs, 0, sizeof(current->thread.fpu.vxrs));

I'm still not 100% sure about whether current->thread.fpu.vxrs is always
fine here? But I hope Christian can give an ACK for that...

 Thomas
Janosch Frank Jan. 10, 2020, 12:24 p.m. UTC | #2
On 1/10/20 1:11 PM, Thomas Huth wrote:
> On 10/01/2020 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;
>> +	/* 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;
>> +}
>> +
>> +static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
>> +{
>> +	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
>> +
>> +	/* Clear reset is a superset of the initial reset */
>> +	kvm_arch_vcpu_ioctl_normal_reset(vcpu);
> 
> s/kvm_arch_vcpu_ioctl_normal_reset/kvm_arch_vcpu_ioctl_initial_reset/

-_-
It seems like my vacation was not enough...

> 
>> +	memset(&regs->gprs, 0, sizeof(regs->gprs));
>> +	/* Will be picked up because of save_fpu_regs() in the initial reset */
>> +	memset(&current->thread.fpu.vxrs, 0, sizeof(current->thread.fpu.vxrs));
> 
> I'm still not 100% sure about whether current->thread.fpu.vxrs is always
> fine here? But I hope Christian can give an ACK for that...
> 
>  Thomas
>
David Hildenbrand Jan. 10, 2020, 12:50 p.m. UTC | #3
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?
Christian Borntraeger Jan. 10, 2020, 1:47 p.m. UTC | #4
On 10.01.20 13:11, Thomas Huth wrote:
> On 10/01/2020 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;
>> +	/* 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;
>> +}
>> +
>> +static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
>> +{
>> +	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
>> +
>> +	/* Clear reset is a superset of the initial reset */
>> +	kvm_arch_vcpu_ioctl_normal_reset(vcpu);
> 
> s/kvm_arch_vcpu_ioctl_normal_reset/kvm_arch_vcpu_ioctl_initial_reset/
> 
>> +	memset(&regs->gprs, 0, sizeof(regs->gprs));
>> +	/* Will be picked up because of save_fpu_regs() in the initial reset */
>> +	memset(&current->thread.fpu.vxrs, 0, sizeof(current->thread.fpu.vxrs));
> 
> I'm still not 100% sure about whether current->thread.fpu.vxrs is always
> fine here? But I hope Christian can give an ACK for that...

We do not have done the sync reg call for this ioctl, so current->thread.fpu.vxrs
still points to the userspace save area and not the kvm_run structure.
I think we must memset the kvm run structure. This might also imply that the
current code for fpc is wrong and that the initial cpu reset ioctl is clearing
the wrong fpc. 
Need to look at this again.
Christian Borntraeger Jan. 27, 2020, 8:05 a.m. UTC | #5
On 10.01.20 12:45, Janosch Frank wrote:
[...]
> +static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
> +{
> +	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
> +
> +	/* Clear reset is a superset of the initial reset */
> +	kvm_arch_vcpu_ioctl_normal_reset(vcpu);
> +
> +	memset(&regs->gprs, 0, sizeof(regs->gprs));



> +	/* Will be picked up because of save_fpu_regs() in the initial reset */
> +	memset(&current->thread.fpu.vxrs, 0, sizeof(current->thread.fpu.vxrs));

So I checked with a userspace that sets f8(call-saved) to 0x123 during this ioctl.
f8 is 0 afterwards. The guest f8 is also correct, just because QEMU does clear out
its copy of the fprs and syncs that back via synv regs.

So this must be

	/* we have not synced the registers from kvm_run to the thread
	   structure. We must clear out kvm_run*/
	memset(&regs->vrs, 0, sizeof(regs->vrs));


> +	memset(&regs->acrs, 0, sizeof(regs->acrs));
> +
> +	regs->etoken = 0;
> +	regs->etoken_extension = 0;
> +
> +	memset(&regs->gscb, 0, sizeof(regs->gscb));
[....]
Janosch Frank Jan. 27, 2020, 9:52 a.m. UTC | #6
On 1/27/20 9:05 AM, Christian Borntraeger wrote:
> 
> 
> On 10.01.20 12:45, Janosch Frank wrote:
> [...]
>> +static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
>> +{
>> +	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
>> +
>> +	/* Clear reset is a superset of the initial reset */
>> +	kvm_arch_vcpu_ioctl_normal_reset(vcpu);
>> +
>> +	memset(&regs->gprs, 0, sizeof(regs->gprs));
> 
> 
> 
>> +	/* Will be picked up because of save_fpu_regs() in the initial reset */
>> +	memset(&current->thread.fpu.vxrs, 0, sizeof(current->thread.fpu.vxrs));
> 
> So I checked with a userspace that sets f8(call-saved) to 0x123 during this ioctl.
> f8 is 0 afterwards. The guest f8 is also correct, just because QEMU does clear out
> its copy of the fprs and syncs that back via synv regs.
> 
> So this must be
> 
> 	/* we have not synced the registers from kvm_run to the thread
> 	   structure. We must clear out kvm_run*/
> 	memset(&regs->vrs, 0, sizeof(regs->vrs));

Great, thanks!
Meanwhile I had a look at the missing pieces and the guarded storage resets.

> 
> 
>> +	memset(&regs->acrs, 0, sizeof(regs->acrs));
>> +
>> +	regs->etoken = 0;
>> +	regs->etoken_extension = 0;
>> +
>> +	memset(&regs->gscb, 0, sizeof(regs->gscb));
> [....]
>
diff mbox series

Patch

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;
+	/* 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;
+}
+
+static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
+{
+	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
+
+	/* Clear reset is a superset of the initial reset */
+	kvm_arch_vcpu_ioctl_normal_reset(vcpu);
+
+	memset(&regs->gprs, 0, sizeof(regs->gprs));
+	/* Will be picked up because of save_fpu_regs() in the initial reset */
+	memset(&current->thread.fpu.vxrs, 0, sizeof(current->thread.fpu.vxrs));
+	memset(&regs->acrs, 0, sizeof(regs->acrs));
+
+	regs->etoken = 0;
+	regs->etoken_extension = 0;
+
+	memset(&regs->gscb, 0, sizeof(regs->gscb));
+	if (MACHINE_HAS_GS) {
+		preempt_disable();
+		__ctl_set_bit(2, 4);
+		if (current->thread.gs_cb) {
+			vcpu->arch.host_gscb = current->thread.gs_cb;
+			save_gs_cb(vcpu->arch.host_gscb);
+		}
+		if (vcpu->arch.gs_enabled) {
+			current->thread.gs_cb = (struct gs_cb *)
+				&vcpu->run->s.regs.gscb;
+			restore_gs_cb(current->thread.gs_cb);
+		}
+		preempt_enable();
+	}
 }
 
 int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
@@ -4363,8 +4400,17 @@  long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
 		break;
 	}
+	case KVM_S390_CLEAR_RESET:
+		r = 0;
+		kvm_arch_vcpu_ioctl_clear_reset(vcpu);
+		break;
 	case KVM_S390_INITIAL_RESET:
-		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+		r = 0;
+		kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+		break;
+	case KVM_S390_NORMAL_RESET:
+		r = 0;
+		kvm_arch_vcpu_ioctl_normal_reset(vcpu);
 		break;
 	case KVM_SET_ONE_REG:
 	case KVM_GET_ONE_REG: {
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f0a16b4adbbd..4b95f9a31a2f 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1009,6 +1009,7 @@  struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
 #define KVM_CAP_ARM_NISV_TO_USER 177
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
+#define KVM_CAP_S390_VCPU_RESETS 179
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1473,6 +1474,10 @@  struct kvm_enc_region {
 /* Available with KVM_CAP_ARM_SVE */
 #define KVM_ARM_VCPU_FINALIZE	  _IOW(KVMIO,  0xc2, int)
 
+/* Available with  KVM_CAP_S390_VCPU_RESETS */
+#define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
+#define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */