KVM: PPC: Book3S HV: Handle memory slot deletion and modification correctly

This adds an implementation of kvm_arch_flush_shadow_memslot for
Book3S HV, and arranges for kvmppc_core_commit_memory_region to
flush the dirty log when modifying an existing slot.  With this,
we can handle deletion and modification of memory slots.

kvm_arch_flush_shadow_memslot calls kvmppc_core_flush_memslot, which
on Book3S HV now traverses the reverse map chains to remove any HPT
(hashed page table) entries referring to pages in the memslot.  This
gets called by generic code whenever deleting a memslot or changing
the guest physical address for a memslot.

We flush the dirty log in kvmppc_core_commit_memory_region for
consistency with what x86 does.  We only need to flush when an
existing memslot is being modified, because for a new memslot the
rmap array (which stores the dirty bits) is all zero, meaning that
every page is considered clean already, and when deleting a memslot
we obviously don't care about the dirty bits any more.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/include/asm/kvm_book3s.h

@@ -160,7 +160,7 @@ extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 extern long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 			long pte_index, unsigned long pteh, unsigned long ptel);
 extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
-			struct kvm_memory_slot *memslot);
+			struct kvm_memory_slot *memslot, unsigned long *map);
 
 extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);

arch/powerpc/include/asm/kvm_ppc.h

@@ -151,9 +151,12 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_userspace_memory_region *mem);
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem);
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old);
 extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
 				      struct kvm_ppc_smmu_info *info);
+extern void kvmppc_core_flush_memslot(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot);
 
 extern int kvmppc_bookehv_init(void);
 extern void kvmppc_bookehv_exit(void);

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -851,7 +851,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 		psize = hpte_page_size(hptep[0], ptel);
 		if ((hptep[0] & HPTE_V_VALID) &&
 		    hpte_rpn(ptel, psize) == gfn) {
-			hptep[0] |= HPTE_V_ABSENT;
+			if (kvm->arch.using_mmu_notifiers)
+				hptep[0] |= HPTE_V_ABSENT;
 			kvmppc_invalidate_hpte(kvm, hptep, i);
 			/* Harvest R and C */
 			rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
@@ -878,6 +879,28 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 	return 0;
 }
 
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+	unsigned long *rmapp;
+	unsigned long gfn;
+	unsigned long n;
+
+	rmapp = memslot->arch.rmap;
+	gfn = memslot->base_gfn;
+	for (n = memslot->npages; n; --n) {
+		/*
+		 * Testing the present bit without locking is OK because
+		 * the memslot has been marked invalid already, and hence
+		 * no new HPTEs referencing this page can be created,
+		 * thus the present bit can't go from 0 to 1.
+		 */
+		if (*rmapp & KVMPPC_RMAP_PRESENT)
+			kvm_unmap_rmapp(kvm, rmapp, gfn);
+		++rmapp;
+		++gfn;
+	}
+}
+
 static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			 unsigned long gfn)
 {
@@ -1031,16 +1054,16 @@ static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
 	return ret;
 }
 
-long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
+long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			     unsigned long *map)
 {
 	unsigned long i;
-	unsigned long *rmapp, *map;
+	unsigned long *rmapp;
 
 	preempt_disable();
 	rmapp = memslot->arch.rmap;
-	map = memslot->dirty_bitmap;
 	for (i = 0; i < memslot->npages; ++i) {
-		if (kvm_test_clear_dirty(kvm, rmapp))
+		if (kvm_test_clear_dirty(kvm, rmapp) && map)
 			__set_bit_le(i, map);
 		++rmapp;
 	}

arch/powerpc/kvm/book3s_hv.c

@@ -1288,7 +1288,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	n = kvm_dirty_bitmap_bytes(memslot);
 	memset(memslot->dirty_bitmap, 0, n);
 
-	r = kvmppc_hv_get_dirty_log(kvm, memslot);
+	r = kvmppc_hv_get_dirty_log(kvm, memslot, memslot->dirty_bitmap);
 	if (r)
 		goto out;
 
@@ -1378,8 +1378,22 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
+				      struct kvm_userspace_memory_region *mem,
+				      struct kvm_memory_slot old)
 {
+	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	if (npages && old.npages) {
+		/*
+		 * If modifying a memslot, reset all the rmap dirty bits.
+		 * If this is a new memslot, we don't need to do anything
+		 * since the rmap array starts out as all zeroes,
+		 * i.e. no pages are dirty.
+		 */
+		memslot = id_to_memslot(kvm->memslots, mem->slot);
+		kvmppc_hv_get_dirty_log(kvm, memslot, NULL);
+	}
 }
 
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -81,7 +81,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 	ptel = rev->guest_rpte |= rcbits;
 	gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
 	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
-	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+	if (!memslot)
 		return;
 
 	rmap = real_vmalloc_addr(&memslot->arch.rmap[gfn - memslot->base_gfn]);

arch/powerpc/kvm/book3s_pr.c

@@ -1239,7 +1239,12 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old)
+{
+}
+
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 

arch/powerpc/kvm/booke.c

@@ -1457,7 +1457,12 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old)
+{
+}
+
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 

arch/powerpc/kvm/powerpc.c

@@ -411,7 +411,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
                struct kvm_memory_slot old,
                int user_alloc)
 {
-	kvmppc_core_commit_memory_region(kvm, mem);
+	kvmppc_core_commit_memory_region(kvm, mem, old);
 }
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
@@ -421,6 +421,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	kvmppc_core_flush_memslot(kvm, slot);
 }
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)