Re: [PATCH v12 7/8] KVM: arm64: ioctl to fetch/store tags in a guest

[Marc Zyngier]

On Mon, 17 May 2021 13:32:38 +0100,
Steven Price <steven.price@arm.com> wrote:
> 
> The VMM may not wish to have it's own mapping of guest memory mapped
> with PROT_MTE because this causes problems if the VMM has tag checking
> enabled (the guest controls the tags in physical RAM and it's unlikely
> the tags are correct for the VMM).
> 
> Instead add a new ioctl which allows the VMM to easily read/write the
> tags from guest memory, allowing the VMM's mapping to be non-PROT_MTE
> while the VMM can still read/write the tags for the purpose of
> migration.
> 
> Signed-off-by: Steven Price <steven.price@arm.com>
> ---
>  arch/arm64/include/uapi/asm/kvm.h | 11 +++++
>  arch/arm64/kvm/arm.c              | 69 +++++++++++++++++++++++++++++++
>  include/uapi/linux/kvm.h          |  1 +
>  3 files changed, 81 insertions(+)
> 
> diff --git a/arch/arm64/include/uapi/asm/kvm.h 
> b/arch/arm64/include/uapi/asm/kvm.h
> index 24223adae150..b3edde68bc3e 100644
> --- a/arch/arm64/include/uapi/asm/kvm.h
> +++ b/arch/arm64/include/uapi/asm/kvm.h
> @@ -184,6 +184,17 @@ struct kvm_vcpu_events {
>       __u32 reserved[12];
>  };
>  
> +struct kvm_arm_copy_mte_tags {
> +     __u64 guest_ipa;
> +     __u64 length;
> +     void __user *addr;
> +     __u64 flags;
> +     __u64 reserved[2];
> +};
> +
> +#define KVM_ARM_TAGS_TO_GUEST                0
> +#define KVM_ARM_TAGS_FROM_GUEST              1
> +
>  /* If you need to interpret the index values, here is the key: */
>  #define KVM_REG_ARM_COPROC_MASK              0x000000000FFF0000
>  #define KVM_REG_ARM_COPROC_SHIFT     16
> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
> index e89a5e275e25..4b6c83beb75d 100644
> --- a/arch/arm64/kvm/arm.c
> +++ b/arch/arm64/kvm/arm.c
> @@ -1309,6 +1309,65 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm 
> *kvm,
>       }
>  }
>  
> +static int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
> +                                   struct kvm_arm_copy_mte_tags *copy_tags)
> +{
> +     gpa_t guest_ipa = copy_tags->guest_ipa;
> +     size_t length = copy_tags->length;
> +     void __user *tags = copy_tags->addr;
> +     gpa_t gfn;
> +     bool write = !(copy_tags->flags & KVM_ARM_TAGS_FROM_GUEST);
> +     int ret = 0;
> +
> +     if (copy_tags->reserved[0] || copy_tags->reserved[1])
> +             return -EINVAL;
> +
> +     if (copy_tags->flags & ~KVM_ARM_TAGS_FROM_GUEST)
> +             return -EINVAL;
> +
> +     if (length & ~PAGE_MASK || guest_ipa & ~PAGE_MASK)
> +             return -EINVAL;
> +
> +     gfn = gpa_to_gfn(guest_ipa);
> +
> +     mutex_lock(&kvm->slots_lock);
> +
> +     while (length > 0) {
> +             kvm_pfn_t pfn = gfn_to_pfn_prot(kvm, gfn, write, NULL);
> +             void *maddr;
> +             unsigned long num_tags = PAGE_SIZE / MTE_GRANULE_SIZE;

nit: this is a compile time constant, make it a #define. This will
avoid the confusing overloading of "num_tags" as both an input and an
output for the mte_copy_tags-* functions.

> +
> +             if (is_error_noslot_pfn(pfn)) {
> +                     ret = -EFAULT;
> +                     goto out;
> +             }
> +
> +             maddr = page_address(pfn_to_page(pfn));
> +
> +             if (!write) {
> +                     num_tags = mte_copy_tags_to_user(tags, maddr, num_tags);
> +                     kvm_release_pfn_clean(pfn);
> +             } else {
> +                     num_tags = mte_copy_tags_from_user(maddr, tags,
> +                                                        num_tags);
> +                     kvm_release_pfn_dirty(pfn);
> +             }
> +
> +             if (num_tags != PAGE_SIZE / MTE_GRANULE_SIZE) {
> +                     ret = -EFAULT;
> +                     goto out;
> +             }
> +
> +             gfn++;
> +             tags += num_tags;
> +             length -= PAGE_SIZE;
> +     }
> +
> +out:
> +     mutex_unlock(&kvm->slots_lock);
> +     return ret;
> +}
> +

nit again: I'd really prefer it if you moved this to guest.c, where we
already have a bunch of the save/restore stuff.

>  long kvm_arch_vm_ioctl(struct file *filp,
>                      unsigned int ioctl, unsigned long arg)
>  {
> @@ -1345,6 +1404,16 @@ long kvm_arch_vm_ioctl(struct file *filp,
>  
>               return 0;
>       }
> +     case KVM_ARM_MTE_COPY_TAGS: {
> +             struct kvm_arm_copy_mte_tags copy_tags;
> +
> +             if (!kvm_has_mte(kvm))
> +                     return -EINVAL;
> +
> +             if (copy_from_user(&copy_tags, argp, sizeof(copy_tags)))
> +                     return -EFAULT;
> +             return kvm_vm_ioctl_mte_copy_tags(kvm, &copy_tags);
> +     }
>       default:
>               return -EINVAL;
>       }
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 8c95ba0fadda..4c011c60d468 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1428,6 +1428,7 @@ struct kvm_s390_ucas_mapping {
>  /* Available with KVM_CAP_PMU_EVENT_FILTER */
>  #define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct 
> kvm_pmu_event_filter)
>  #define KVM_PPC_SVM_OFF                _IO(KVMIO,  0xb3)
> +#define KVM_ARM_MTE_COPY_TAGS          _IOR(KVMIO,  0xb4, struct 
> kvm_arm_copy_mte_tags)
>  
>  /* ioctl for vm fd */
>  #define KVM_CREATE_DEVICE      _IOWR(KVMIO,  0xe0, struct kvm_create_device)

Thanks,

        M.

-- 
Without deviation from the norm, progress is not possible.