Re: [PATCH v6 23/43] KVM: arm64: Handle Realm PSCI requests

[Gavin Shan]

On 12/13/24 1:55 AM, Steven Price wrote:
> The RMM needs to be informed of the target REC when a PSCI call is made
> with an MPIDR argument. Expose an ioctl to the userspace in case the PSCI
> is handled by it.
>
> Co-developed-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
> Signed-off-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
> Signed-off-by: Steven Price <steven.price@xxxxxxx>
> ---
>   arch/arm64/include/asm/kvm_rme.h |  3 +++
>   arch/arm64/kvm/arm.c             | 25 +++++++++++++++++++++++++
>   arch/arm64/kvm/psci.c            | 29 +++++++++++++++++++++++++++++
>   arch/arm64/kvm/rme.c             | 15 +++++++++++++++
>   4 files changed, 72 insertions(+)
>
> diff --git a/arch/arm64/include/asm/kvm_rme.h b/arch/arm64/include/asm/kvm_rme.h
> index 158f77e24a26..90a4537ad38d 100644
> --- a/arch/arm64/include/asm/kvm_rme.h
> +++ b/arch/arm64/include/asm/kvm_rme.h
> @@ -113,6 +113,9 @@ int realm_set_ipa_state(struct kvm_vcpu *vcpu,
>   			unsigned long addr, unsigned long end,
>   			unsigned long ripas,
>   			unsigned long *top_ipa);
> +int realm_psci_complete(struct kvm_vcpu *calling,
> +			struct kvm_vcpu *target,
> +			unsigned long status);
>   

The 'calling' may be renamed to 'source', consistent to the names in arch/arm64/kvm/psci.c.
Other nitpicks can be found below.

>   #define RMM_RTT_BLOCK_LEVEL	2
>   #define RMM_RTT_MAX_LEVEL	3
> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
> index f588b528c3f9..eff1a4ec892b 100644
> --- a/arch/arm64/kvm/arm.c
> +++ b/arch/arm64/kvm/arm.c
> @@ -1745,6 +1745,22 @@ static int kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
>   	return __kvm_arm_vcpu_set_events(vcpu, events);
>   }
>   
> +static int kvm_arm_vcpu_rmm_psci_complete(struct kvm_vcpu *vcpu,
> +					  struct kvm_arm_rmm_psci_complete *arg)
> +{
> +	struct kvm_vcpu *target = kvm_mpidr_to_vcpu(vcpu->kvm, arg->target_mpidr);
> +
> +	if (!target)
> +		return -EINVAL;
> +
> +	/*
> +	 * RMM v1.0 only supports PSCI_RET_SUCCESS or PSCI_RET_DENIED
> +	 * for the status. But, let us leave it to the RMM to filter
> +	 * for making this future proof.
> +	 */
> +	return realm_psci_complete(vcpu, target, arg->psci_status);
> +}
> +
>   long kvm_arch_vcpu_ioctl(struct file *filp,
>   			 unsigned int ioctl, unsigned long arg)
>   {
> @@ -1867,6 +1883,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
>   
>   		return kvm_arm_vcpu_finalize(vcpu, what);
>   	}
> +	case KVM_ARM_VCPU_RMM_PSCI_COMPLETE: {
> +		struct kvm_arm_rmm_psci_complete req;
> +
> +		if (!kvm_is_realm(vcpu->kvm))
> +			return -EINVAL;

We probably need to check with vcpu_is_rec(). -EPERM seems more precise
than -EINVAL.

> +		if (copy_from_user(&req, argp, sizeof(req)))
> +			return -EFAULT;
> +		return kvm_arm_vcpu_rmm_psci_complete(vcpu, &req);
> +	}
>   	default:
>   		r = -EINVAL;
>   	}
> diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
> index 3b5dbe9a0a0e..9dc161abc30c 100644
> --- a/arch/arm64/kvm/psci.c
> +++ b/arch/arm64/kvm/psci.c
> @@ -103,6 +103,12 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
>   
>   	reset_state->reset = true;
>   	kvm_make_request(KVM_REQ_VCPU_RESET, vcpu);
> +	/*
> +	 * Make sure we issue PSCI_COMPLETE before the VCPU can be
> +	 * scheduled.
> +	 */
> +	if (vcpu_is_rec(vcpu))
> +		realm_psci_complete(source_vcpu, vcpu, PSCI_RET_SUCCESS);
>   
>   	/*
>   	 * Make sure the reset request is observed if the RUNNABLE mp_state is
> @@ -115,6 +121,10 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
>   
>   out_unlock:
>   	spin_unlock(&vcpu->arch.mp_state_lock);
> +	if (vcpu_is_rec(vcpu) && ret != PSCI_RET_SUCCESS)
> +		realm_psci_complete(source_vcpu, vcpu,
> +				    ret == PSCI_RET_ALREADY_ON ?
> +				    PSCI_RET_SUCCESS : PSCI_RET_DENIED);

{} is needed here.

>   	return ret;
>   }
>   
> @@ -142,6 +152,25 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
>   	/* Ignore other bits of target affinity */
>   	target_affinity &= target_affinity_mask;
>   
> +	if (vcpu_is_rec(vcpu)) {
> +		struct kvm_vcpu *target_vcpu;
> +
> +		/* RMM supports only zero affinity level */
> +		if (lowest_affinity_level != 0)
> +			return PSCI_RET_INVALID_PARAMS;
> +
> +		target_vcpu = kvm_mpidr_to_vcpu(kvm, target_affinity);
> +		if (!target_vcpu)
> +			return PSCI_RET_INVALID_PARAMS;
> +
> +		/*
> +		 * Provide the references of running and target RECs to the RMM
                                             ^^^^^^^
                                             the source
> +		 * so that the RMM can complete the PSCI request.
> +		 */
> +		realm_psci_complete(vcpu, target_vcpu, PSCI_RET_SUCCESS);
> +		return PSCI_RET_SUCCESS;
> +	}
> +
>   	/*
>   	 * If one or more VCPU matching target affinity are running
>   	 * then ON else OFF
> diff --git a/arch/arm64/kvm/rme.c b/arch/arm64/kvm/rme.c
> index 146ef598a581..5831d379760a 100644
> --- a/arch/arm64/kvm/rme.c
> +++ b/arch/arm64/kvm/rme.c
> @@ -118,6 +118,21 @@ static void free_delegated_granule(phys_addr_t phys)
>   	free_page((unsigned long)phys_to_virt(phys));
>   }
>   
> +int realm_psci_complete(struct kvm_vcpu *calling, struct kvm_vcpu *target,
> +			unsigned long status)
> +{
> +	int ret;
> +
> +	ret = rmi_psci_complete(virt_to_phys(calling->arch.rec.rec_page),
> +				virt_to_phys(target->arch.rec.rec_page),
> +				status);
> +
        ^^^^^
Unnecessary blank line.

> +	if (ret)
> +		return -EINVAL;
> +
> +	return 0;
> +}
> +
>   static int realm_rtt_create(struct realm *realm,
>   			    unsigned long addr,
>   			    int level,

Thanks,
Gavin