1 files changed, 162 insertions, 57 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e3a6f7647474..32896c845ffe 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -168,7 +168,7 @@ __weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
 {
 }
 
-bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
+bool kvm_is_zone_device_page(struct page *page)
 {
 	/*
 	 * The metadata used by is_zone_device_page() to determine whether or
@@ -176,25 +176,42 @@ bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
 	 * the device has been pinned, e.g. by get_user_pages().  WARN if the
 	 * page_count() is zero to help detect bad usage of this helper.
 	 */
-	if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn))))
+	if (WARN_ON_ONCE(!page_count(page)))
 		return false;
 
-	return is_zone_device_page(pfn_to_page(pfn));
+	return is_zone_device_page(page);
 }
 
-bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
+/*
+ * Returns a 'struct page' if the pfn is "valid" and backed by a refcounted
+ * page, NULL otherwise.  Note, the list of refcounted PG_reserved page types
+ * is likely incomplete, it has been compiled purely through people wanting to
+ * back guest with a certain type of memory and encountering issues.
+ */
+struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn)
 {
+	struct page *page;
+
+	if (!pfn_valid(pfn))
+		return NULL;
+
+	page = pfn_to_page(pfn);
+	if (!PageReserved(page))
+		return page;
+
+	/* The ZERO_PAGE(s) is marked PG_reserved, but is refcounted. */
+	if (is_zero_pfn(pfn))
+		return page;
+
 	/*
 	 * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
 	 * perspective they are "normal" pages, albeit with slightly different
 	 * usage rules.
 	 */
-	if (pfn_valid(pfn))
-		return PageReserved(pfn_to_page(pfn)) &&
-		       !is_zero_pfn(pfn) &&
-		       !kvm_is_zone_device_pfn(pfn);
+	if (kvm_is_zone_device_page(page))
+		return page;
 
-	return true;
+	return NULL;
 }
 
 /*
@@ -239,7 +256,7 @@ static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req)
 	return mode == IN_GUEST_MODE;
 }
 
-static void ack_flush(void *_completed)
+static void ack_kick(void *_completed)
 {
 }
 
@@ -248,7 +265,7 @@ static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait)
 	if (cpumask_empty(cpus))
 		return false;
 
-	smp_call_function_many(cpus, ack_flush, NULL, wait);
+	smp_call_function_many(cpus, ack_kick, NULL, wait);
 	return true;
 }
 
@@ -379,16 +396,31 @@ static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc,
 		return (void *)__get_free_page(gfp_flags);
 }
 
-int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
+int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min)
 {
+	gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT;
 	void *obj;
 
 	if (mc->nobjs >= min)
 		return 0;
-	while (mc->nobjs < ARRAY_SIZE(mc->objects)) {
-		obj = mmu_memory_cache_alloc_obj(mc, (mc->gfp_custom) ?
-						 mc->gfp_custom :
-						 GFP_KERNEL_ACCOUNT);
+
+	if (unlikely(!mc->objects)) {
+		if (WARN_ON_ONCE(!capacity))
+			return -EIO;
+
+		mc->objects = kvmalloc_array(sizeof(void *), capacity, gfp);
+		if (!mc->objects)
+			return -ENOMEM;
+
+		mc->capacity = capacity;
+	}
+
+	/* It is illegal to request a different capacity across topups. */
+	if (WARN_ON_ONCE(mc->capacity != capacity))
+		return -EIO;
+
+	while (mc->nobjs < mc->capacity) {
+		obj = mmu_memory_cache_alloc_obj(mc, gfp);
 		if (!obj)
 			return mc->nobjs >= min ? 0 : -ENOMEM;
 		mc->objects[mc->nobjs++] = obj;
@@ -396,6 +428,11 @@ int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
 	return 0;
 }
 
+int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min)
+{
+	return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min);
+}
+
 int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc)
 {
 	return mc->nobjs;
@@ -409,6 +446,11 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc)
 		else
 			free_page((unsigned long)mc->objects[--mc->nobjs]);
 	}
+
+	kvfree(mc->objects);
+
+	mc->objects = NULL;
+	mc->capacity = 0;
 }
 
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
@@ -726,6 +768,15 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	kvm->mn_active_invalidate_count++;
 	spin_unlock(&kvm->mn_invalidate_lock);
 
+	/*
+	 * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e.
+	 * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring
+	 * each cache's lock.  There are relatively few caches in existence at
+	 * any given time, and the caches themselves can check for hva overlap,
+	 * i.e. don't need to rely on memslot overlap checks for performance.
+	 * Because this runs without holding mmu_lock, the pfn caches must use
+	 * mn_active_invalidate_count (see above) instead of mmu_notifier_count.
+	 */
 	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
 					  hva_range.may_block);
 
@@ -2494,9 +2545,12 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
 
 static int kvm_try_get_pfn(kvm_pfn_t pfn)
 {
-	if (kvm_is_reserved_pfn(pfn))
+	struct page *page = kvm_pfn_to_refcounted_page(pfn);
+
+	if (!page)
 		return 1;
-	return get_page_unless_zero(pfn_to_page(pfn));
+
+	return get_page_unless_zero(page);
 }
 
 static int hva_to_pfn_remapped(struct vm_area_struct *vma,
@@ -2582,7 +2636,7 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
 		     bool write_fault, bool *writable)
 {
 	struct vm_area_struct *vma;
-	kvm_pfn_t pfn = 0;
+	kvm_pfn_t pfn;
 	int npages, r;
 
 	/* we can do it either atomically or asynchronously, not both */
@@ -2713,34 +2767,32 @@ int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
 }
 EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
 
-static struct page *kvm_pfn_to_page(kvm_pfn_t pfn)
-{
-	if (is_error_noslot_pfn(pfn))
-		return KVM_ERR_PTR_BAD_PAGE;
-
-	if (kvm_is_reserved_pfn(pfn)) {
-		WARN_ON(1);
-		return KVM_ERR_PTR_BAD_PAGE;
-	}
-
-	return pfn_to_page(pfn);
-}
-
+/*
+ * Do not use this helper unless you are absolutely certain the gfn _must_ be
+ * backed by 'struct page'.  A valid example is if the backing memslot is
+ * controlled by KVM.  Note, if the returned page is valid, it's refcount has
+ * been elevated by gfn_to_pfn().
+ */
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {
+	struct page *page;
 	kvm_pfn_t pfn;
 
 	pfn = gfn_to_pfn(kvm, gfn);
 
-	return kvm_pfn_to_page(pfn);
+	if (is_error_noslot_pfn(pfn))
+		return KVM_ERR_PTR_BAD_PAGE;
+
+	page = kvm_pfn_to_refcounted_page(pfn);
+	if (!page)
+		return KVM_ERR_PTR_BAD_PAGE;
+
+	return page;
 }
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
 void kvm_release_pfn(kvm_pfn_t pfn, bool dirty)
 {
-	if (pfn == 0)
-		return;
-
 	if (dirty)
 		kvm_release_pfn_dirty(pfn);
 	else
@@ -2806,28 +2858,48 @@ void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
-struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
+static bool kvm_is_ad_tracked_page(struct page *page)
 {
-	kvm_pfn_t pfn;
+	/*
+	 * Per page-flags.h, pages tagged PG_reserved "should in general not be
+	 * touched (e.g. set dirty) except by its owner".
+	 */
+	return !PageReserved(page);
+}
 
-	pfn = kvm_vcpu_gfn_to_pfn(vcpu, gfn);
+static void kvm_set_page_dirty(struct page *page)
+{
+	if (kvm_is_ad_tracked_page(page))
+		SetPageDirty(page);
+}
 
-	return kvm_pfn_to_page(pfn);
+static void kvm_set_page_accessed(struct page *page)
+{
+	if (kvm_is_ad_tracked_page(page))
+		mark_page_accessed(page);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_page);
 
 void kvm_release_page_clean(struct page *page)
 {
 	WARN_ON(is_error_page(page));
 
-	kvm_release_pfn_clean(page_to_pfn(page));
+	kvm_set_page_accessed(page);
+	put_page(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(kvm_pfn_t pfn)
 {
-	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn))
-		put_page(pfn_to_page(pfn));
+	struct page *page;
+
+	if (is_error_noslot_pfn(pfn))
+		return;
+
+	page = kvm_pfn_to_refcounted_page(pfn);
+	if (!page)
+		return;
+
+	kvm_release_page_clean(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
 
@@ -2835,28 +2907,48 @@ void kvm_release_page_dirty(struct page *page)
 {
 	WARN_ON(is_error_page(page));
 
-	kvm_release_pfn_dirty(page_to_pfn(page));
+	kvm_set_page_dirty(page);
+	kvm_release_page_clean(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
 
 void kvm_release_pfn_dirty(kvm_pfn_t pfn)
 {
-	kvm_set_pfn_dirty(pfn);
-	kvm_release_pfn_clean(pfn);
+	struct page *page;
+
+	if (is_error_noslot_pfn(pfn))
+		return;
+
+	page = kvm_pfn_to_refcounted_page(pfn);
+	if (!page)
+		return;
+
+	kvm_release_page_dirty(page);
 }
 EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
 
+/*
+ * Note, checking for an error/noslot pfn is the caller's responsibility when
+ * directly marking a page dirty/accessed.  Unlike the "release" helpers, the
+ * "set" helpers are not to be used when the pfn might point at garbage.
+ */
 void kvm_set_pfn_dirty(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
-		SetPageDirty(pfn_to_page(pfn));
+	if (WARN_ON(is_error_noslot_pfn(pfn)))
+		return;
+
+	if (pfn_valid(pfn))
+		kvm_set_page_dirty(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
 void kvm_set_pfn_accessed(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
-		mark_page_accessed(pfn_to_page(pfn));
+	if (WARN_ON(is_error_noslot_pfn(pfn)))
+		return;
+
+	if (pfn_valid(pfn))
+		kvm_set_page_accessed(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
 
@@ -3730,9 +3822,18 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 	return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
 }
 
+#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
+static int vcpu_get_pid(void *data, u64 *val)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
+	*val = pid_nr(rcu_access_pointer(vcpu->pid));
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_get_pid_fops, vcpu_get_pid, NULL, "%llu\n");
+
 static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 {
-#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
 	struct dentry *debugfs_dentry;
 	char dir_name[ITOA_MAX_LEN * 2];
 
@@ -3742,10 +3843,12 @@ static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 	snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id);
 	debugfs_dentry = debugfs_create_dir(dir_name,
 					    vcpu->kvm->debugfs_dentry);
+	debugfs_create_file("pid", 0444, debugfs_dentry, vcpu,
+			    &vcpu_get_pid_fops);
 
 	kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry);
-#endif
 }
+#endif
 
 /*
  * Creates some virtual cpus.  Good luck creating more than one.
@@ -3765,13 +3868,15 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 		return -EINVAL;
 	}
 
+	r = kvm_arch_vcpu_precreate(kvm, id);
+	if (r) {
+		mutex_unlock(&kvm->lock);
+		return r;
+	}
+
 	kvm->created_vcpus++;
 	mutex_unlock(&kvm->lock);
 
-	r = kvm_arch_vcpu_precreate(kvm, id);
-	if (r)
-		goto vcpu_decrement;
-
 	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
 	if (!vcpu) {
 		r = -ENOMEM;