On 20/05/2021 13:05, Catalin Marinas wrote:
> On Mon, May 17, 2021 at 01:32:38PM +0100, Steven Price wrote:
>> 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];
>
> I forgot the past discussions, what's the reserved for? Future
> expansion?
Yes - for future expansion. Marc asked for them[1]:
> I'd be keen on a couple of reserved __64s. Just in case...
[1] https://lore.kernel.org/r/87ft14xl9e.wl-maz%40kernel.org
>> 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;
>> +
>> + 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);
>
> Do we need to check if PG_mte_tagged is set? If the page was not faulted
> into the guest address space but the VMM has the page, does the
> gfn_to_pfn_prot() guarantee that a kvm_set_spte_gfn() was called? If
> not, this may read stale tags.
Ah, I hadn't thought about that... No I don't believe gfn_to_pfn_prot()
will fault it into the guest.
>> + } else {
>> + num_tags = mte_copy_tags_from_user(maddr, tags,
>> + num_tags);
>> + kvm_release_pfn_dirty(pfn);
>> + }
>
> Same question here, if the we can't guarantee the stage 2 pte being set,
> we'd need to set PG_mte_tagged.
This is arguably worse as we'll be writing tags into the guest but
without setting PG_mte_tagged - so they'll be lost when the guest then
faults the pages in. Which sounds like it should break migration.
I think the below should be safe, and avoids the overhead of setting the
flag just for reads.
Thanks,
Steve
----8<----
page = pfn_to_page(pfn);
maddr = page_address(page);
if (!write) {
if (test_bit(PG_mte_tagged, &page->flags))
num_tags = mte_copy_tags_to_user(tags, maddr,
MTE_GRANULES_PER_PAGE);
else
/* No tags in memory, so write zeros */
num_tags = MTE_GRANULES_PER_PAGE -
clear_user(tag, MTE_GRANULES_PER_PAGE);
kvm_release_pfn_clean(pfn);
} else {
num_tags = mte_copy_tags_from_user(maddr, tags,
MTE_GRANULES_PER_PAGE);
kvm_release_pfn_dirty(pfn);
}
if (num_tags != MTE_GRANULES_PER_PAGE) {
ret = -EFAULT;
goto out;
}
if (write)
test_and_set_bit(PG_mte_tagged, &page->flags);
_______________________________________________
kvmarm mailing list
kvmarm@xxxxxxxxxxxxxxxxxxxxx
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
