KVM: PPC: E500: Implement MMU notifiers

The e500 target has lived without mmu notifiers ever since it got
introduced, but fails for the user space check on them with hugetlbfs.

So in order to get that one working, implement mmu notifiers in a
reasonably dumb fashion and be happy. On embedded hardware, we almost
never end up with mmu notifier calls, since most people don't overcommit.

Signed-off-by: Alexander Graf <agraf@suse.de>

5 files changed, 65 insertions, 7 deletions

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 28e8f5e..cea9d3a 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -46,7 +46,8 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #endif
 
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#if defined(CONFIG_KVM_BOOK3S_64_HV) || defined(CONFIG_KVM_E500V2) || \
+    defined(CONFIG_KVM_E500MC)
 #include <linux/mmu_notifier.h>
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index e006f0b..88de314 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -104,6 +104,7 @@ extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                        struct kvm_interrupt *irq);
 extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
                                          struct kvm_interrupt *irq);
+extern void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu);
 
 extern int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                   unsigned int op, int *advance);
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index f4dacb9..40cad8c 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -123,6 +123,7 @@ config KVM_E500V2
 	depends on EXPERIMENTAL && E500 && !PPC_E500MC
 	select KVM
 	select KVM_MMIO
+	select MMU_NOTIFIER
 	---help---
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500v2 host processors.
@@ -138,6 +139,7 @@ config KVM_E500MC
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV
+	select MMU_NOTIFIER
 	---help---
 	  Support running unmodified E500MC/E5500 (32-bit) guest kernels in
 	  virtual machines on E500MC/E5500 host processors.
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 70a86c0..52f6cbb 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -459,6 +459,10 @@ static void kvmppc_check_requests(struct kvm_vcpu *vcpu)
 	if (vcpu->requests) {
 		if (kvm_check_request(KVM_REQ_PENDING_TIMER, vcpu))
 			update_timer_ints(vcpu);
+#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
+		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
+			kvmppc_core_flush_tlb(vcpu);
+#endif
 	}
 }
 
@@ -579,6 +583,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
 
 	kvm_guest_exit();
+	vcpu->mode = OUTSIDE_GUEST_MODE;
+	smp_wmb();
 
 out:
 	vcpu->mode = OUTSIDE_GUEST_MODE;
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index b56b6e1..de8ea29 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -303,18 +303,15 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 	ref->pfn = pfn;
 	ref->flags = E500_TLB_VALID;
 
-	if (tlbe_is_writable(gtlbe))
+	if (tlbe_is_writable(gtlbe)) {
 		ref->flags |= E500_TLB_DIRTY;
+		kvm_set_pfn_dirty(pfn);
+	}
 }
 
 static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
 {
 	if (ref->flags & E500_TLB_VALID) {
-		if (ref->flags & E500_TLB_DIRTY)
-			kvm_release_pfn_dirty(ref->pfn);
-		else
-			kvm_release_pfn_clean(ref->pfn);
-
 		ref->flags = 0;
 	}
 }
@@ -357,6 +354,13 @@ static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
 	clear_tlb_privs(vcpu_e500);
 }
 
+void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	clear_tlb_refs(vcpu_e500);
+	clear_tlb1_bitmap(vcpu_e500);
+}
+
 static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 		unsigned int eaddr, int as)
 {
@@ -541,6 +545,9 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	/* Clear i-cache for new pages */
 	kvmppc_mmu_flush_icache(pfn);
+
+	/* Drop refcount on page, so that mmu notifiers can clear it */
+	kvm_release_pfn_clean(pfn);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
@@ -1064,6 +1071,47 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 	write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
 }
 
+/************* MMU Notifiers *************/
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	/*
+	 * Flush all shadow tlb entries everywhere. This is slow, but
+	 * we are 100% sure that we catch the to be unmapped page
+	 */
+	kvm_flush_remote_tlbs(kvm);
+
+	return 0;
+}
+
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	/* kvm_unmap_hva flushes everything anyways */
+	kvm_unmap_hva(kvm, start);
+
+	return 0;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	/* The page will get remapped properly on its next fault */
+	kvm_unmap_hva(kvm, hva);
+}
+
+/*****************************************/
+
 static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	int i;