Re: [PATCH v3 09/11] KVM: arm/arm64: vgic: Prevent userspace injection of a mapped interrupt

[Marc Zyngier <marc.zyngier@arm.com>]

On 04/08/15 14:45, Christoffer Dall wrote:
> On Fri, Jul 24, 2015 at 04:55:07PM +0100, Marc Zyngier wrote:
>> Virtual interrupts mapped to a HW interrupt should only be triggered
>> from inside the kernel. Otherwise, you could end up confusing the
>> kernel (and the GIC's) state machine.
>>
>> Rearrange the injection path so that kvm_vgic_inject_irq is
>> used for non-mapped interrupts, and kvm_vgic_inject_mapped_irq is
>> used for mapped interrupts. The latter should only be called from
>> inside the kernel (timer, VFIO).
>>
>> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
>> ---
>>  include/kvm/arm_vgic.h |  2 +
>>  virt/kvm/arm/vgic.c    | 99 ++++++++++++++++++++++++++++++++++----------------
>>  2 files changed, 70 insertions(+), 31 deletions(-)
>>
>> diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
>> index 7306b4b..f6bfd79 100644
>> --- a/include/kvm/arm_vgic.h
>> +++ b/include/kvm/arm_vgic.h
>> @@ -351,6 +351,8 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
>>  void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
>>  int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
>>  			bool level);
>> +int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
>> +			       struct irq_phys_map *map, bool level);
>>  void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
>>  int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
>>  int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu);
>> diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
>> index 3f7b690..e40ef70 100644
>> --- a/virt/kvm/arm/vgic.c
>> +++ b/virt/kvm/arm/vgic.c
>> @@ -1533,7 +1533,8 @@ static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
>>  }
>>  
>>  static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
>> -				  unsigned int irq_num, bool level)
>> +				   struct irq_phys_map *map,
>> +				   unsigned int irq_num, bool level)
>>  {
>>  	struct vgic_dist *dist = &kvm->arch.vgic;
>>  	struct kvm_vcpu *vcpu;
>> @@ -1541,6 +1542,9 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
>>  	int enabled;
>>  	bool ret = true, can_inject = true;
>>  
>> +	if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020))
>> +		return -EINVAL;
>> +
>>  	spin_lock(&dist->lock);
>>  
>>  	vcpu = kvm_get_vcpu(kvm, cpuid);
>> @@ -1603,14 +1607,42 @@ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
>>  out:
>>  	spin_unlock(&dist->lock);
>>  
>> -	return ret ? cpuid : -EINVAL;
>> +	if (!ret) {
> 
> don't you mean if (ret) here?  hint: ret is a bool

Ouch. Nice catch!

> 
>> +		/* kick the specified vcpu */
>> +		kvm_vcpu_kick(kvm_get_vcpu(kvm, cpuid));
>> +	}
>> +
>> +	return 0;
> 
> isn't this a change in the internal API?
> Before, we would return -EINVAL when ret is false.  Not sure if this
> has any consequences though?

I don't think this is a change in API. Before this patch, we would
either return a vcpuid or -EINVAL. But the error would not be propagated
beyond kvm_vgic_inject_irq, effectively discarding the error code.

Also, it is a bit odd to return an error because the toggling of the
line wasn't significant (like bringing the line down on an
edge-triggered interrupt).

> 
>> +}
>> +
>> +static int vgic_lazy_init(struct kvm *kvm)
>> +{
>> +	int ret = 0;
>> +
>> +	if (unlikely(!vgic_initialized(kvm))) {
>> +		/*
>> +		 * We only provide the automatic initialization of the VGIC
>> +		 * for the legacy case of a GICv2. Any other type must
>> +		 * be explicitly initialized once setup with the respective
>> +		 * KVM device call.
>> +		 */
>> +		if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2)
>> +			return -EBUSY;
>> +
>> +		mutex_lock(&kvm->lock);
>> +		ret = vgic_init(kvm);
>> +		mutex_unlock(&kvm->lock);
>> +	}
>> +
>> +	return ret;
>>  }
>>  
>>  /**
>>   * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
>>   * @kvm:     The VM structure pointer
>>   * @cpuid:   The CPU for PPIs
>> - * @irq_num: The IRQ number that is assigned to the device
>> + * @irq_num: The IRQ number that is assigned to the device. This IRQ
>> + *           must not be mapped to a HW interrupt.
>>   * @level:   Edge-triggered:  true:  to trigger the interrupt
>>   *			      false: to ignore the call
>>   *	     Level-sensitive  true:  activates an interrupt
>> @@ -1623,39 +1655,44 @@ out:
>>  int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
>>  			bool level)
>>  {
>> -	int ret = 0;
>> -	int vcpu_id;
>> -
>> -	if (unlikely(!vgic_initialized(kvm))) {
>> -		/*
>> -		 * We only provide the automatic initialization of the VGIC
>> -		 * for the legacy case of a GICv2. Any other type must
>> -		 * be explicitly initialized once setup with the respective
>> -		 * KVM device call.
>> -		 */
>> -		if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) {
>> -			ret = -EBUSY;
>> -			goto out;
>> -		}
>> -		mutex_lock(&kvm->lock);
>> -		ret = vgic_init(kvm);
>> -		mutex_unlock(&kvm->lock);
>> +	struct irq_phys_map *map;
>> +	int ret;
>>  
>> -		if (ret)
>> -			goto out;
>> -	}
>> +	ret = vgic_lazy_init(kvm);
>> +	if (ret)
>> +		return ret;
>>  
>> -	if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020))
>> +	map = vgic_irq_map_search(kvm_get_vcpu(kvm, cpuid), irq_num);
>> +	if (map)
>>  		return -EINVAL;
>>  
>> -	vcpu_id = vgic_update_irq_pending(kvm, cpuid, irq_num, level);
>> -	if (vcpu_id >= 0) {
>> -		/* kick the specified vcpu */
>> -		kvm_vcpu_kick(kvm_get_vcpu(kvm, vcpu_id));
>> -	}
>> +	return vgic_update_irq_pending(kvm, cpuid, NULL, irq_num, level);
>> +}
>>  
>> -out:
>> -	return ret;
>> +/**
>> + * kvm_vgic_inject_mapped_irq - Inject a physically mapped IRQ to the vgic
>> + * @kvm:     The VM structure pointer
>> + * @cpuid:   The CPU for PPIs
>> + * @map:     Pointer to a irq_phys_map structure describing the mapping
>> + * @level:   Edge-triggered:  true:  to trigger the interrupt
>> + *			      false: to ignore the call
>> + *	     Level-sensitive  true:  activates an interrupt
>> + *			      false: deactivates an interrupt
> 
> just noticed this unfortunate use of the words 'activate/deactivate'
> here, which is not true, it just raises/lowers the input signal...
> 

I'll clean that up.

>> + *
>> + * The GIC is not concerned with devices being active-LOW or active-HIGH for
>> + * level-sensitive interrupts.  You can think of the level parameter as 1
>> + * being HIGH and 0 being LOW and all devices being active-HIGH.
>> + */
>> +int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
>> +			       struct irq_phys_map *map, bool level)
>> +{
>> +	int ret;
>> +
>> +	ret = vgic_lazy_init(kvm);
>> +	if (ret)
>> +		return ret;
>> +
>> +	return vgic_update_irq_pending(kvm, cpuid, map, map->virt_irq, level);
>>  }
>>  
>>  static irqreturn_t vgic_maintenance_handler(int irq, void *data)
>> -- 
>> 2.1.4
>>
> 
> Thanks,
> -Christoffer
> 

Thanks,

	M.
-- 
Jazz is not dead. It just smells funny...