| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <566f272b-39e3-5da0-6b94-5f992a77adbe@arm.com>
Date: Mon, 21 Jun 2021 10:07:56 +0100
From: Steven Price <steven.price@....com>
To: Marc Zyngier <maz@...nel.org>
Cc: Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will@...nel.org>,
James Morse <james.morse@....com>,
Julien Thierry <julien.thierry.kdev@...il.com>,
Suzuki K Poulose <suzuki.poulose@....com>,
kvmarm@...ts.cs.columbia.edu, linux-arm-kernel@...ts.infradead.org,
linux-kernel@...r.kernel.org, Dave Martin <Dave.Martin@....com>,
Mark Rutland <mark.rutland@....com>,
Thomas Gleixner <tglx@...utronix.de>, qemu-devel@...gnu.org,
Juan Quintela <quintela@...hat.com>,
"Dr. David Alan Gilbert" <dgilbert@...hat.com>,
Richard Henderson <richard.henderson@...aro.org>,
Peter Maydell <peter.maydell@...aro.org>,
Andrew Jones <drjones@...hat.com>
Subject: Re: [PATCH v16 3/7] KVM: arm64: Introduce MTE VM feature
On 21/06/2021 10:01, Marc Zyngier wrote:
> On Fri, 18 Jun 2021 14:28:22 +0100,
> Steven Price <steven.price@....com> wrote:
>>
>> Add a new VM feature 'KVM_ARM_CAP_MTE' which enables memory tagging
>> for a VM. This will expose the feature to the guest and automatically
>> tag memory pages touched by the VM as PG_mte_tagged (and clear the tag
>> storage) to ensure that the guest cannot see stale tags, and so that
>> the tags are correctly saved/restored across swap.
>>
>> Actually exposing the new capability to user space happens in a later
>> patch.
>>
>> Signed-off-by: Steven Price <steven.price@....com>
>> ---
>> arch/arm64/include/asm/kvm_emulate.h | 3 ++
>> arch/arm64/include/asm/kvm_host.h | 3 ++
>> arch/arm64/kvm/hyp/exception.c | 3 +-
>> arch/arm64/kvm/mmu.c | 62 +++++++++++++++++++++++++++-
>> arch/arm64/kvm/sys_regs.c | 7 ++++
>> include/uapi/linux/kvm.h | 1 +
>> 6 files changed, 77 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
>> index f612c090f2e4..6bf776c2399c 100644
>> --- a/arch/arm64/include/asm/kvm_emulate.h
>> +++ b/arch/arm64/include/asm/kvm_emulate.h
>> @@ -84,6 +84,9 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
>> if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) ||
>> vcpu_el1_is_32bit(vcpu))
>> vcpu->arch.hcr_el2 |= HCR_TID2;
>> +
>> + if (kvm_has_mte(vcpu->kvm))
>> + vcpu->arch.hcr_el2 |= HCR_ATA;
>> }
>>
>> static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
>> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
>> index 7cd7d5c8c4bc..afaa5333f0e4 100644
>> --- a/arch/arm64/include/asm/kvm_host.h
>> +++ b/arch/arm64/include/asm/kvm_host.h
>> @@ -132,6 +132,8 @@ struct kvm_arch {
>>
>> u8 pfr0_csv2;
>> u8 pfr0_csv3;
>> + /* Memory Tagging Extension enabled for the guest */
>> + bool mte_enabled;
>> };
>>
>> struct kvm_vcpu_fault_info {
>> @@ -769,6 +771,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
>> #define kvm_arm_vcpu_sve_finalized(vcpu) \
>> ((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED)
>>
>> +#define kvm_has_mte(kvm) (system_supports_mte() && (kvm)->arch.mte_enabled)
>> #define kvm_vcpu_has_pmu(vcpu) \
>> (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
>>
>> diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
>> index 73629094f903..56426565600c 100644
>> --- a/arch/arm64/kvm/hyp/exception.c
>> +++ b/arch/arm64/kvm/hyp/exception.c
>> @@ -112,7 +112,8 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
>> new |= (old & PSR_C_BIT);
>> new |= (old & PSR_V_BIT);
>>
>> - // TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests)
>> + if (kvm_has_mte(vcpu->kvm))
>> + new |= PSR_TCO_BIT;
>>
>> new |= (old & PSR_DIT_BIT);
>>
>> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
>> index c5d1f3c87dbd..f5305b7561ad 100644
>> --- a/arch/arm64/kvm/mmu.c
>> +++ b/arch/arm64/kvm/mmu.c
>> @@ -822,6 +822,45 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
>> return PAGE_SIZE;
>> }
>>
>> +/*
>> + * The page will be mapped in stage 2 as Normal Cacheable, so the VM will be
>> + * able to see the page's tags and therefore they must be initialised first. If
>> + * PG_mte_tagged is set, tags have already been initialised.
>> + *
>> + * The race in the test/set of the PG_mte_tagged flag is handled by:
>> + * - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs
>> + * racing to santise the same page
>> + * - mmap_lock protects between a VM faulting a page in and the VMM performing
>> + * an mprotect() to add VM_MTE
>> + */
>> +static int sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,
>> + unsigned long size)
>> +{
>> + unsigned long i, nr_pages = size >> PAGE_SHIFT;
>> + struct page *page;
>> +
>> + if (!kvm_has_mte(kvm))
>> + return 0;
>> +
>> + /*
>> + * pfn_to_online_page() is used to reject ZONE_DEVICE pages
>> + * that may not support tags.
>> + */
>> + page = pfn_to_online_page(pfn);
>> +
>> + if (!page)
>> + return -EFAULT;
>> +
>> + for (i = 0; i < nr_pages; i++, page++) {
>> + if (!test_bit(PG_mte_tagged, &page->flags)) {
>> + mte_clear_page_tags(page_address(page));
>> + set_bit(PG_mte_tagged, &page->flags);
>> + }
>> + }
>> +
>> + return 0;
>> +}
>> +
>> static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>> struct kvm_memory_slot *memslot, unsigned long hva,
>> unsigned long fault_status)
>> @@ -971,8 +1010,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
>> if (writable)
>> prot |= KVM_PGTABLE_PROT_W;
>>
>> - if (fault_status != FSC_PERM && !device)
>> + if (fault_status != FSC_PERM && !device) {
>> + /* Check the VMM hasn't introduced a new VM_SHARED VMA */
>> + if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED)
>> + return -EINVAL;
>
> nit: I'd rather we return -EFAULT here. That's consistent with other
> cases where we can't satisfy the mapping.
Sure, and it would be even better if I dropped the lock (goto
out_unlock) - I'll fix that too!
Thanks,
Steve
Powered by blists - more mailing lists