[PATCH v3 2/2] arm64: kvm: Introduce MTE VCPU feature

[Steven Price]

Add a new VM feature 'KVM_ARM_CAP_MTE' which enables memory tagging
for a VM. This exposes the feature to the guest and automatically tags
memory pages touched by the VM as PG_mte_tagged (and clears the tags
storage) to ensure that the guest cannot see stale tags, and so that the
tags are correctly saved/restored across swap.

Signed-off-by: Steven Price <steven.price@arm.com>
---
 arch/arm64/include/asm/kvm_emulate.h |  3 +++
 arch/arm64/include/asm/kvm_host.h    |  3 +++
 arch/arm64/kvm/arm.c                 |  9 +++++++++
 arch/arm64/kvm/mmu.c                 | 15 +++++++++++++++
 arch/arm64/kvm/sys_regs.c            |  6 +++++-
 include/uapi/linux/kvm.h             |  1 +
 6 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h 
b/arch/arm64/include/asm/kvm_emulate.h
index 49a55be2b9a2..4923a566ae6e 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -79,6 +79,9 @@ 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 (vcpu->kvm->arch.mte_enabled)
+               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 4f4360dd149e..1379300c1487 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -110,6 +110,9 @@ struct kvm_arch {
         * supported.
         */
        bool return_nisv_io_abort_to_user;
+
+       /* Memory Tagging Extension enabled for the guest */
+       bool mte_enabled;
 };
 
 struct kvm_vcpu_fault_info {
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 46dc3d75cf13..624edca0a1fa 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -87,6 +87,12 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
                r = 0;
                kvm->arch.return_nisv_io_abort_to_user = true;
                break;
+       case KVM_CAP_ARM_MTE:
+               if (!system_supports_mte() || kvm->created_vcpus)
+                       return -EINVAL;
+               r = 0;
+               kvm->arch.mte_enabled = true;
+               break;
        default:
                r = -EINVAL;
                break;
@@ -206,6 +212,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
                 */
                r = 1;
                break;
+       case KVM_CAP_ARM_MTE:
+               r = system_supports_mte();
+               break;
        default:
                r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
                break;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index ba00bcc0c884..befb9e1f0aa6 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1949,6 +1949,21 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, 
phys_addr_t fault_ipa,
        if (vma_pagesize == PAGE_SIZE && !force_pte)
                vma_pagesize = transparent_hugepage_adjust(memslot, hva,
                                                           &pfn, &fault_ipa);
+       if (system_supports_mte() && kvm->arch.mte_enabled && pfn_valid(pfn)) {
+               /*
+                * VM will be able to see the page's tags, so we must ensure
+                * they have been initialised.
+                */
+               struct page *page = pfn_to_page(pfn);
+               long i, nr_pages = compound_nr(page);
+
+               /* if PG_mte_tagged is set, tags have already been initialised 
*/
+               for (i = 0; i < nr_pages; i++, page++) {
+                       if (!test_and_set_bit(PG_mte_tagged, &page->flags))
+                               mte_clear_page_tags(page_address(page));
+               }
+       }
+
        if (writable)
                kvm_set_pfn_dirty(pfn);
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index a655f172b5ad..5010a47152b4 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1132,7 +1132,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
                        val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
                val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
        } else if (id == SYS_ID_AA64PFR1_EL1) {
-               val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT);
+               if (!vcpu->kvm->arch.mte_enabled)
+                       val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT);
        } else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
                val &= ~((0xfUL << ID_AA64ISAR1_APA_SHIFT) |
                         (0xfUL << ID_AA64ISAR1_API_SHIFT) |
@@ -1394,6 +1395,9 @@ static bool access_mte_regs(struct kvm_vcpu *vcpu, struct 
sys_reg_params *p,
 static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
                                   const struct sys_reg_desc *rd)
 {
+       if (vcpu->kvm->arch.mte_enabled)
+               return 0;
+
        return REG_HIDDEN_USER | REG_HIDDEN_GUEST;
 }
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f6d86033c4fa..87678ed82ab4 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1035,6 +1035,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_LAST_CPU 184
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_ARM_MTE 188
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
2.20.1