[PATCH v15 3/7] KVM: arm64: 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.

Reviewed-by: Catalin Marinas <catalin.marinas@xxxxxxx>
Signed-off-by: Steven Price <steven.price@xxxxxxx>
---
 arch/arm64/include/asm/kvm_emulate.h |  3 ++
 arch/arm64/include/asm/kvm_host.h    |  3 ++
 arch/arm64/include/asm/mte.h         |  4 +++
 arch/arm64/kernel/mte.c              | 17 +++++++++++
 arch/arm64/kvm/hyp/exception.c       |  3 +-
 arch/arm64/kvm/mmu.c                 | 42 +++++++++++++++++++++++++++-
 arch/arm64/kvm/sys_regs.c            |  7 +++++
 include/uapi/linux/kvm.h             |  1 +
 8 files changed, 78 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/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index 347ef38a35f7..be1de541a11c 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -37,6 +37,7 @@ void mte_free_tag_storage(char *storage);
 /* track which pages have valid allocation tags */
 #define PG_mte_tagged	PG_arch_2
 
+void mte_prepare_page_tags(struct page *page);
 void mte_sync_tags(pte_t old_pte, pte_t pte);
 void mte_copy_page_tags(void *kto, const void *kfrom);
 void mte_thread_init_user(void);
@@ -53,6 +54,9 @@ int mte_ptrace_copy_tags(struct task_struct *child, long request,
 /* unused if !CONFIG_ARM64_MTE, silence the compiler */
 #define PG_mte_tagged	0
 
+static inline void mte_prepare_page_tags(struct page *page)
+{
+}
 static inline void mte_sync_tags(pte_t old_pte, pte_t pte)
 {
 }
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index ae0a3c68fece..b120f82a2258 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -72,6 +72,23 @@ static void mte_sync_page_tags(struct page *page, pte_t old_pte,
 	spin_unlock_irqrestore(&tag_sync_lock, flags);
 }
 
+void mte_prepare_page_tags(struct page *page)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&tag_sync_lock, flags);
+
+	/* Recheck with the lock held */
+	if (test_bit(PG_mte_tagged, &page->flags))
+		goto out;
+
+	mte_clear_page_tags(page_address(page));
+	set_bit(PG_mte_tagged, &page->flags);
+
+out:
+	spin_unlock_irqrestore(&tag_sync_lock, flags);
+}
+
 void mte_sync_tags(pte_t old_pte, pte_t pte)
 {
 	struct page *page = pte_page(pte);
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..ed7c624e7362 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -822,6 +822,36 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
 	return PAGE_SIZE;
 }
 
+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;
+
+	/*
+	 * 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.
+	 * 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_prepare_page_tags(page);
+	}
+
+	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 +1001,13 @@ 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) {
+		ret = sanitise_mte_tags(kvm, pfn, vma_pagesize);
+		if (ret)
+			goto out_unlock;
+
 		clean_dcache_guest_page(pfn, vma_pagesize);
+	}
 
 	if (exec_fault) {
 		prot |= KVM_PGTABLE_PROT_X;
@@ -1168,12 +1203,17 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 {
 	kvm_pfn_t pfn = pte_pfn(range->pte);
+	int ret;
 
 	if (!kvm->arch.mmu.pgt)
 		return 0;
 
 	WARN_ON(range->end - range->start != 1);
 
+	ret = sanitise_mte_tags(kvm, pfn, PAGE_SIZE);
+	if (ret)
+		return false;
+
 	/*
 	 * We've moved a page around, probably through CoW, so let's treat it
 	 * just like a translation fault and clean the cache to the PoC.
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 76ea2800c33e..4a98902eaf1a 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1047,6 +1047,13 @@ 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)) {
+			u64 pfr, mte;
+
+			pfr = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
+			mte = cpuid_feature_extract_unsigned_field(pfr, ID_AA64PFR1_MTE_SHIFT);
+			val |= FIELD_PREP(FEATURE(ID_AA64PFR1_MTE), 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 3fd9a7e9d90c..8c95ba0fadda 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1082,6 +1082,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SGX_ATTRIBUTE 196
 #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197
 #define KVM_CAP_PTP_KVM 198
+#define KVM_CAP_ARM_MTE 199
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
2.20.1