arm/arm64: KVM: Implement Stage-2 page aging

Until now, KVM/arm didn't care much for page aging (who was swapping
anyway?), and simply provided empty hooks to the core KVM code. With
server-type systems now being available, things are quite different.

This patch implements very simple support for page aging, by clearing
the Access flag in the Stage-2 page tables. On access fault, the current
fault handling will write the PTE or PMD again, putting the Access flag
back on.

It should be possible to implement a much faster handling for Access
faults, but that's left for a later patch.

With this in place, performance in VMs is degraded much more gracefully.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>

2 files changed, 97 insertions, 1 deletions

diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index ffa06e07eed2..1831aa26eef8 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1299,6 +1299,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 out_unlock:
 	spin_unlock(&kvm->mmu_lock);
+	kvm_set_pfn_accessed(pfn);
 	kvm_release_pfn_clean(pfn);
 	return ret;
 }
@@ -1333,7 +1334,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	/* Check the stage-2 fault is trans. fault or write fault */
 	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
-	if (fault_status != FSC_FAULT && fault_status != FSC_PERM) {
+	if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
+	    fault_status != FSC_ACCESS) {
 		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
 			kvm_vcpu_trap_get_class(vcpu),
 			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -1475,6 +1477,67 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte);
 }
 
+static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pmd = stage2_get_pmd(kvm, NULL, gpa);
+	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+		return 0;
+
+	if (kvm_pmd_huge(*pmd)) {	/* THP, HugeTLB */
+		if (pmd_young(*pmd)) {
+			*pmd = pmd_mkold(*pmd);
+			return 1;
+		}
+
+		return 0;
+	}
+
+	pte = pte_offset_kernel(pmd, gpa);
+	if (pte_none(*pte))
+		return 0;
+
+	if (pte_young(*pte)) {
+		*pte = pte_mkold(*pte);	/* Just a page... */
+		return 1;
+	}
+
+	return 0;
+}
+
+static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
+{
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pmd = stage2_get_pmd(kvm, NULL, gpa);
+	if (!pmd || pmd_none(*pmd))	/* Nothing there */
+		return 0;
+
+	if (kvm_pmd_huge(*pmd))		/* THP, HugeTLB */
+		return pmd_young(*pmd);
+
+	pte = pte_offset_kernel(pmd, gpa);
+	if (!pte_none(*pte))		/* Just a page... */
+		return pte_young(*pte);
+
+	return 0;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	trace_kvm_age_hva(start, end);
+	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	trace_kvm_test_age_hva(hva);
+	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
+}
+
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
 {
 	mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index 6817664b46b8..c09f37faff01 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -210,6 +210,39 @@ TRACE_EVENT(kvm_set_spte_hva,
 	TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
 );
 
+TRACE_EVENT(kvm_age_hva,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	start		)
+		__field(	unsigned long,	end		)
+	),
+
+	TP_fast_assign(
+		__entry->start		= start;
+		__entry->end		= end;
+	),
+
+	TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+		  __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_test_age_hva,
+	TP_PROTO(unsigned long hva),
+	TP_ARGS(hva),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	hva		)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+	),
+
+	TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+);
+
 TRACE_EVENT(kvm_hvc,
 	TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm),
 	TP_ARGS(vcpu_pc, r0, imm),