[PATCH v11 2/6] arm64: kvm: Introduce MTE VM feature

[Steven Price]

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@arm.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                 | 20 ++++++++++++++++++++
 arch/arm64/kvm/sys_regs.c            |  3 +++
 include/uapi/linux/kvm.h             |  1 +
 6 files changed, 32 insertions(+), 1 deletion(-)

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 3d10e6527f7d..1170ee137096 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 {
@@ -767,6 +769,7 @@ 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 77cb2d28f2a4..5f8e165ea053 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -879,6 +879,26 @@ 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 (fault_status != FSC_PERM && kvm_has_mte(kvm) && !device &&
+           pfn_valid(pfn)) {
+               /*
+                * VM will be able to see the page's tags, so we must ensure
+                * they have been initialised. if PG_mte_tagged is set, tags
+                * have already been initialised.
+                */
+               unsigned long i, nr_pages = vma_pagesize >> PAGE_SHIFT;
+               struct page *page = pfn_to_online_page(pfn);
+
+               if (!page)
+                       return -EFAULT;
+
+               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)
                prot |= KVM_PGTABLE_PROT_W;
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 4f2f1e3145de..18c87500a7a8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1047,6 +1047,9 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
                break;
        case SYS_ID_AA64PFR1_EL1:
                val &= ~FEATURE(ID_AA64PFR1_MTE);
+               if (kvm_has_mte(vcpu->kvm))
+                       val |= FIELD_PREP(FEATURE(ID_AA64PFR1_MTE),
+                                         ID_AA64PFR1_MTE);
                break;
        case SYS_ID_AA64ISAR1_EL1:
                if (!vcpu_has_ptrauth(vcpu))
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f6afee209620..6dc16c09a2d1 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1078,6 +1078,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_DIRTY_LOG_RING 192
 #define KVM_CAP_X86_BUS_LOCK_EXIT 193
 #define KVM_CAP_PPC_DAWR1 194
+#define KVM_CAP_ARM_MTE 195
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
2.20.1