1 files changed, 133 insertions, 71 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d9cfb782cb8..7287bf5d1c9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -440,6 +440,15 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 
 #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
 
+static void kvm_init_memslots_id(struct kvm *kvm)
+{
+	int i;
+	struct kvm_memslots *slots = kvm->memslots;
+
+	for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
+		slots->id_to_index[i] = slots->memslots[i].id = i;
+}
+
 static struct kvm *kvm_create_vm(void)
 {
 	int r, i;
@@ -465,6 +474,7 @@ static struct kvm *kvm_create_vm(void)
 	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 	if (!kvm->memslots)
 		goto out_err_nosrcu;
+	kvm_init_memslots_id(kvm);
 	if (init_srcu_struct(&kvm->srcu))
 		goto out_err_nosrcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
@@ -547,11 +557,11 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 
 void kvm_free_physmem(struct kvm *kvm)
 {
-	int i;
 	struct kvm_memslots *slots = kvm->memslots;
+	struct kvm_memory_slot *memslot;
 
-	for (i = 0; i < slots->nmemslots; ++i)
-		kvm_free_physmem_slot(&slots->memslots[i], NULL);
+	kvm_for_each_memslot(memslot, slots)
+		kvm_free_physmem_slot(memslot, NULL);
 
 	kfree(kvm->memslots);
 }
@@ -625,10 +635,69 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 		return -ENOMEM;
 
 	memslot->dirty_bitmap_head = memslot->dirty_bitmap;
+	memslot->nr_dirty_pages = 0;
 	return 0;
 }
 #endif /* !CONFIG_S390 */
 
+static struct kvm_memory_slot *
+search_memslots(struct kvm_memslots *slots, gfn_t gfn)
+{
+	struct kvm_memory_slot *memslot;
+
+	kvm_for_each_memslot(memslot, slots)
+		if (gfn >= memslot->base_gfn &&
+		      gfn < memslot->base_gfn + memslot->npages)
+			return memslot;
+
+	return NULL;
+}
+
+static int cmp_memslot(const void *slot1, const void *slot2)
+{
+	struct kvm_memory_slot *s1, *s2;
+
+	s1 = (struct kvm_memory_slot *)slot1;
+	s2 = (struct kvm_memory_slot *)slot2;
+
+	if (s1->npages < s2->npages)
+		return 1;
+	if (s1->npages > s2->npages)
+		return -1;
+
+	return 0;
+}
+
+/*
+ * Sort the memslots base on its size, so the larger slots
+ * will get better fit.
+ */
+static void sort_memslots(struct kvm_memslots *slots)
+{
+	int i;
+
+	sort(slots->memslots, KVM_MEM_SLOTS_NUM,
+	      sizeof(struct kvm_memory_slot), cmp_memslot, NULL);
+
+	for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
+		slots->id_to_index[slots->memslots[i].id] = i;
+}
+
+void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new)
+{
+	if (new) {
+		int id = new->id;
+		struct kvm_memory_slot *old = id_to_memslot(slots, id);
+		unsigned long npages = old->npages;
+
+		*old = *new;
+		if (new->npages != npages)
+			sort_memslots(slots);
+	}
+
+	slots->generation++;
+}
+
 /*
  * Allocate some memory and give it an address in the guest physical address
  * space.
@@ -662,12 +731,12 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			(void __user *)(unsigned long)mem->userspace_addr,
 			mem->memory_size)))
 		goto out;
-	if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
+	if (mem->slot >= KVM_MEM_SLOTS_NUM)
 		goto out;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		goto out;
 
-	memslot = &kvm->memslots->memslots[mem->slot];
+	memslot = id_to_memslot(kvm->memslots, mem->slot);
 	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	npages = mem->memory_size >> PAGE_SHIFT;
 
@@ -774,15 +843,17 @@ skip_lpage:
 #endif /* not defined CONFIG_S390 */
 
 	if (!npages) {
+		struct kvm_memory_slot *slot;
+
 		r = -ENOMEM;
-		slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+		slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
+				GFP_KERNEL);
 		if (!slots)
 			goto out_free;
-		memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
-		if (mem->slot >= slots->nmemslots)
-			slots->nmemslots = mem->slot + 1;
-		slots->generation++;
-		slots->memslots[mem->slot].flags |= KVM_MEMSLOT_INVALID;
+		slot = id_to_memslot(slots, mem->slot);
+		slot->flags |= KVM_MEMSLOT_INVALID;
+
+		update_memslots(slots, NULL);
 
 		old_memslots = kvm->memslots;
 		rcu_assign_pointer(kvm->memslots, slots);
@@ -810,13 +881,10 @@ skip_lpage:
 	}
 
 	r = -ENOMEM;
-	slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+	slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
+			GFP_KERNEL);
 	if (!slots)
 		goto out_free;
-	memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
-	if (mem->slot >= slots->nmemslots)
-		slots->nmemslots = mem->slot + 1;
-	slots->generation++;
 
 	/* actual memory is freed via old in kvm_free_physmem_slot below */
 	if (!npages) {
@@ -826,7 +894,7 @@ skip_lpage:
 			new.lpage_info[i] = NULL;
 	}
 
-	slots->memslots[mem->slot] = new;
+	update_memslots(slots, &new);
 	old_memslots = kvm->memslots;
 	rcu_assign_pointer(kvm->memslots, slots);
 	synchronize_srcu_expedited(&kvm->srcu);
@@ -888,7 +956,7 @@ int kvm_get_dirty_log(struct kvm *kvm,
 	if (log->slot >= KVM_MEMORY_SLOTS)
 		goto out;
 
-	memslot = &kvm->memslots->memslots[log->slot];
+	memslot = id_to_memslot(kvm->memslots, log->slot);
 	r = -ENOENT;
 	if (!memslot->dirty_bitmap)
 		goto out;
@@ -966,16 +1034,7 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva);
 static struct kvm_memory_slot *__gfn_to_memslot(struct kvm_memslots *slots,
 						gfn_t gfn)
 {
-	int i;
-
-	for (i = 0; i < slots->nmemslots; ++i) {
-		struct kvm_memory_slot *memslot = &slots->memslots[i];
-
-		if (gfn >= memslot->base_gfn
-		    && gfn < memslot->base_gfn + memslot->npages)
-			return memslot;
-	}
-	return NULL;
+	return search_memslots(slots, gfn);
 }
 
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
@@ -986,20 +1045,13 @@ EXPORT_SYMBOL_GPL(gfn_to_memslot);
 
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
-	int i;
-	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);
 
-	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
-		struct kvm_memory_slot *memslot = &slots->memslots[i];
-
-		if (memslot->flags & KVM_MEMSLOT_INVALID)
-			continue;
+	if (!memslot || memslot->id >= KVM_MEMORY_SLOTS ||
+	      memslot->flags & KVM_MEMSLOT_INVALID)
+		return 0;
 
-		if (gfn >= memslot->base_gfn
-		    && gfn < memslot->base_gfn + memslot->npages)
-			return 1;
-	}
-	return 0;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
@@ -1491,7 +1543,8 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	if (memslot && memslot->dirty_bitmap) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 
-		__set_bit_le(rel_gfn, memslot->dirty_bitmap);
+		if (!__test_and_set_bit_le(rel_gfn, memslot->dirty_bitmap))
+			memslot->nr_dirty_pages++;
 	}
 }
 
@@ -1690,10 +1743,6 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	smp_wmb();
 	atomic_inc(&kvm->online_vcpus);
 
-#ifdef CONFIG_KVM_APIC_ARCHITECTURE
-	if (kvm->bsp_vcpu_id == id)
-		kvm->bsp_vcpu = vcpu;
-#endif
 	mutex_unlock(&kvm->lock);
 	return r;
 
@@ -1768,12 +1817,11 @@ out_free1:
 		struct kvm_regs *kvm_regs;
 
 		r = -ENOMEM;
-		kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
-		if (!kvm_regs)
+		kvm_regs = memdup_user(argp, sizeof(*kvm_regs));
+		if (IS_ERR(kvm_regs)) {
+			r = PTR_ERR(kvm_regs);
 			goto out;
-		r = -EFAULT;
-		if (copy_from_user(kvm_regs, argp, sizeof(struct kvm_regs)))
-			goto out_free2;
+		}
 		r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs);
 		if (r)
 			goto out_free2;
@@ -1797,13 +1845,11 @@ out_free2:
 		break;
 	}
 	case KVM_SET_SREGS: {
-		kvm_sregs = kmalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
-		r = -ENOMEM;
-		if (!kvm_sregs)
-			goto out;
-		r = -EFAULT;
-		if (copy_from_user(kvm_sregs, argp, sizeof(struct kvm_sregs)))
+		kvm_sregs = memdup_user(argp, sizeof(*kvm_sregs));
+		if (IS_ERR(kvm_sregs)) {
+			r = PTR_ERR(kvm_sregs);
 			goto out;
+		}
 		r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs);
 		if (r)
 			goto out;
@@ -1899,13 +1945,11 @@ out_free2:
 		break;
 	}
 	case KVM_SET_FPU: {
-		fpu = kmalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
-		r = -ENOMEM;
-		if (!fpu)
-			goto out;
-		r = -EFAULT;
-		if (copy_from_user(fpu, argp, sizeof(struct kvm_fpu)))
+		fpu = memdup_user(argp, sizeof(*fpu));
+		if (IS_ERR(fpu)) {
+			r = PTR_ERR(fpu);
 			goto out;
+		}
 		r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu);
 		if (r)
 			goto out;
@@ -2520,10 +2564,9 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	if (bus->dev_count > NR_IOBUS_DEVS-1)
 		return -ENOSPC;
 
-	new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL);
+	new_bus = kmemdup(bus, sizeof(struct kvm_io_bus), GFP_KERNEL);
 	if (!new_bus)
 		return -ENOMEM;
-	memcpy(new_bus, bus, sizeof(struct kvm_io_bus));
 	kvm_io_bus_insert_dev(new_bus, dev, addr, len);
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
@@ -2539,13 +2582,12 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	int i, r;
 	struct kvm_io_bus *new_bus, *bus;
 
-	new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL);
+	bus = kvm->buses[bus_idx];
+
+	new_bus = kmemdup(bus, sizeof(*bus), GFP_KERNEL);
 	if (!new_bus)
 		return -ENOMEM;
 
-	bus = kvm->buses[bus_idx];
-	memcpy(new_bus, bus, sizeof(struct kvm_io_bus));
-
 	r = -ENOENT;
 	for (i = 0; i < new_bus->dev_count; i++)
 		if (new_bus->range[i].dev == dev) {
@@ -2612,15 +2654,29 @@ static const struct file_operations *stat_fops[] = {
 	[KVM_STAT_VM]   = &vm_stat_fops,
 };
 
-static void kvm_init_debug(void)
+static int kvm_init_debug(void)
 {
+	int r = -EFAULT;
 	struct kvm_stats_debugfs_item *p;
 
 	kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
-	for (p = debugfs_entries; p->name; ++p)
+	if (kvm_debugfs_dir == NULL)
+		goto out;
+
+	for (p = debugfs_entries; p->name; ++p) {
 		p->dentry = debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
 						(void *)(long)p->offset,
 						stat_fops[p->kind]);
+		if (p->dentry == NULL)
+			goto out_dir;
+	}
+
+	return 0;
+
+out_dir:
+	debugfs_remove_recursive(kvm_debugfs_dir);
+out:
+	return r;
 }
 
 static void kvm_exit_debug(void)
@@ -2764,10 +2820,16 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	kvm_preempt_ops.sched_in = kvm_sched_in;
 	kvm_preempt_ops.sched_out = kvm_sched_out;
 
-	kvm_init_debug();
+	r = kvm_init_debug();
+	if (r) {
+		printk(KERN_ERR "kvm: create debugfs files failed\n");
+		goto out_undebugfs;
+	}
 
 	return 0;
 
+out_undebugfs:
+	unregister_syscore_ops(&kvm_syscore_ops);
 out_unreg:
 	kvm_async_pf_deinit();
 out_free: