Merge tag 'usercopy-v4.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull hardened usercopy whitelisting from Kees Cook:
 "Currently, hardened usercopy performs dynamic bounds checking on slab
  cache objects. This is good, but still leaves a lot of kernel memory
  available to be copied to/from userspace in the face of bugs.

  To further restrict what memory is available for copying, this creates
  a way to whitelist specific areas of a given slab cache object for
  copying to/from userspace, allowing much finer granularity of access
  control.

  Slab caches that are never exposed to userspace can declare no
  whitelist for their objects, thereby keeping them unavailable to
  userspace via dynamic copy operations. (Note, an implicit form of
  whitelisting is the use of constant sizes in usercopy operations and
  get_user()/put_user(); these bypass all hardened usercopy checks since
  these sizes cannot change at runtime.)

  This new check is WARN-by-default, so any mistakes can be found over
  the next several releases without breaking anyone's system.

  The series has roughly the following sections:
   - remove %p and improve reporting with offset
   - prepare infrastructure and whitelist kmalloc
   - update VFS subsystem with whitelists
   - update SCSI subsystem with whitelists
   - update network subsystem with whitelists
   - update process memory with whitelists
   - update per-architecture thread_struct with whitelists
   - update KVM with whitelists and fix ioctl bug
   - mark all other allocations as not whitelisted
   - update lkdtm for more sensible test overage"

* tag 'usercopy-v4.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux: (38 commits)
  lkdtm: Update usercopy tests for whitelisting
  usercopy: Restrict non-usercopy caches to size 0
  kvm: x86: fix KVM_XEN_HVM_CONFIG ioctl
  kvm: whitelist struct kvm_vcpu_arch
  arm: Implement thread_struct whitelist for hardened usercopy
  arm64: Implement thread_struct whitelist for hardened usercopy
  x86: Implement thread_struct whitelist for hardened usercopy
  fork: Provide usercopy whitelisting for task_struct
  fork: Define usercopy region in thread_stack slab caches
  fork: Define usercopy region in mm_struct slab caches
  net: Restrict unwhitelisted proto caches to size 0
  sctp: Copy struct sctp_sock.autoclose to userspace using put_user()
  sctp: Define usercopy region in SCTP proto slab cache
  caif: Define usercopy region in caif proto slab cache
  ip: Define usercopy region in IP proto slab cache
  net: Define usercopy region in struct proto slab cache
  scsi: Define usercopy region in scsi_sense_cache slab cache
  cifs: Define usercopy region in cifs_request slab cache
  vxfs: Define usercopy region in vxfs_inode slab cache
  ufs: Define usercopy region in ufs_inode_cache slab cache
  ...

1 files changed, 51 insertions, 11 deletions

diff --git a/mm/slab_common.c b/mm/slab_common.c
index deeddf95cdcf..10f127b2de7c 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -31,6 +31,14 @@ LIST_HEAD(slab_caches);
 DEFINE_MUTEX(slab_mutex);
 struct kmem_cache *kmem_cache;
 
+#ifdef CONFIG_HARDENED_USERCOPY
+bool usercopy_fallback __ro_after_init =
+		IS_ENABLED(CONFIG_HARDENED_USERCOPY_FALLBACK);
+module_param(usercopy_fallback, bool, 0400);
+MODULE_PARM_DESC(usercopy_fallback,
+		"WARN instead of reject usercopy whitelist violations");
+#endif
+
 static LIST_HEAD(slab_caches_to_rcu_destroy);
 static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work);
 static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
@@ -310,6 +318,9 @@ int slab_unmergeable(struct kmem_cache *s)
 	if (s->ctor)
 		return 1;
 
+	if (s->usersize)
+		return 1;
+
 	/*
 	 * We may have set a slab to be unmergeable during bootstrap.
 	 */
@@ -368,12 +379,16 @@ struct kmem_cache *find_mergeable(size_t size, size_t align,
 
 static struct kmem_cache *create_cache(const char *name,
 		size_t object_size, size_t size, size_t align,
-		slab_flags_t flags, void (*ctor)(void *),
+		slab_flags_t flags, size_t useroffset,
+		size_t usersize, void (*ctor)(void *),
 		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
 {
 	struct kmem_cache *s;
 	int err;
 
+	if (WARN_ON(useroffset + usersize > object_size))
+		useroffset = usersize = 0;
+
 	err = -ENOMEM;
 	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
 	if (!s)
@@ -384,6 +399,8 @@ static struct kmem_cache *create_cache(const char *name,
 	s->size = size;
 	s->align = align;
 	s->ctor = ctor;
+	s->useroffset = useroffset;
+	s->usersize = usersize;
 
 	err = init_memcg_params(s, memcg, root_cache);
 	if (err)
@@ -408,11 +425,13 @@ out_free_cache:
 }
 
 /*
- * kmem_cache_create - Create a cache.
+ * kmem_cache_create_usercopy - Create a cache.
  * @name: A string which is used in /proc/slabinfo to identify this cache.
  * @size: The size of objects to be created in this cache.
  * @align: The required alignment for the objects.
  * @flags: SLAB flags
+ * @useroffset: Usercopy region offset
+ * @usersize: Usercopy region size
  * @ctor: A constructor for the objects.
  *
  * Returns a ptr to the cache on success, NULL on failure.
@@ -432,8 +451,9 @@ out_free_cache:
  * as davem.
  */
 struct kmem_cache *
-kmem_cache_create(const char *name, size_t size, size_t align,
-		  slab_flags_t flags, void (*ctor)(void *))
+kmem_cache_create_usercopy(const char *name, size_t size, size_t align,
+		  slab_flags_t flags, size_t useroffset, size_t usersize,
+		  void (*ctor)(void *))
 {
 	struct kmem_cache *s = NULL;
 	const char *cache_name;
@@ -464,7 +484,13 @@ kmem_cache_create(const char *name, size_t size, size_t align,
 	 */
 	flags &= CACHE_CREATE_MASK;
 
-	s = __kmem_cache_alias(name, size, align, flags, ctor);
+	/* Fail closed on bad usersize of useroffset values. */
+	if (WARN_ON(!usersize && useroffset) ||
+	    WARN_ON(size < usersize || size - usersize < useroffset))
+		usersize = useroffset = 0;
+
+	if (!usersize)
+		s = __kmem_cache_alias(name, size, align, flags, ctor);
 	if (s)
 		goto out_unlock;
 
@@ -476,7 +502,7 @@ kmem_cache_create(const char *name, size_t size, size_t align,
 
 	s = create_cache(cache_name, size, size,
 			 calculate_alignment(flags, align, size),
-			 flags, ctor, NULL, NULL);
+			 flags, useroffset, usersize, ctor, NULL, NULL);
 	if (IS_ERR(s)) {
 		err = PTR_ERR(s);
 		kfree_const(cache_name);
@@ -502,6 +528,15 @@ out_unlock:
 	}
 	return s;
 }
+EXPORT_SYMBOL(kmem_cache_create_usercopy);
+
+struct kmem_cache *
+kmem_cache_create(const char *name, size_t size, size_t align,
+		slab_flags_t flags, void (*ctor)(void *))
+{
+	return kmem_cache_create_usercopy(name, size, align, flags, 0, 0,
+					  ctor);
+}
 EXPORT_SYMBOL(kmem_cache_create);
 
 static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
@@ -614,6 +649,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	s = create_cache(cache_name, root_cache->object_size,
 			 root_cache->size, root_cache->align,
 			 root_cache->flags & CACHE_CREATE_MASK,
+			 root_cache->useroffset, root_cache->usersize,
 			 root_cache->ctor, memcg, root_cache);
 	/*
 	 * If we could not create a memcg cache, do not complain, because
@@ -881,13 +917,15 @@ bool slab_is_available(void)
 #ifndef CONFIG_SLOB
 /* Create a cache during boot when no slab services are available yet */
 void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t size,
-		slab_flags_t flags)
+		slab_flags_t flags, size_t useroffset, size_t usersize)
 {
 	int err;
 
 	s->name = name;
 	s->size = s->object_size = size;
 	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
+	s->useroffset = useroffset;
+	s->usersize = usersize;
 
 	slab_init_memcg_params(s);
 
@@ -901,14 +939,15 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t siz
 }
 
 struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
-				slab_flags_t flags)
+				slab_flags_t flags, size_t useroffset,
+				size_t usersize)
 {
 	struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
 
 	if (!s)
 		panic("Out of memory when creating slab %s\n", name);
 
-	create_boot_cache(s, name, size, flags);
+	create_boot_cache(s, name, size, flags, useroffset, usersize);
 	list_add(&s->list, &slab_caches);
 	memcg_link_cache(s);
 	s->refcount = 1;
@@ -1062,7 +1101,8 @@ void __init setup_kmalloc_cache_index_table(void)
 static void __init new_kmalloc_cache(int idx, slab_flags_t flags)
 {
 	kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name,
-					kmalloc_info[idx].size, flags);
+					kmalloc_info[idx].size, flags, 0,
+					kmalloc_info[idx].size);
 }
 
 /*
@@ -1103,7 +1143,7 @@ void __init create_kmalloc_caches(slab_flags_t flags)
 
 			BUG_ON(!n);
 			kmalloc_dma_caches[i] = create_kmalloc_cache(n,
-				size, SLAB_CACHE_DMA | flags);
+				size, SLAB_CACHE_DMA | flags, 0, 0);
 		}
 	}
 #endif