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
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 Comment: Kees Cook <kees@outflux.net>
 
 iQIcBAABCgAGBQJabvleAAoJEIly9N/cbcAmO1kQAJnjVPutnLSbnUteZxtsv7W4
 43Cggvokfxr6l08Yh3hUowNxZVKjhF9uwMVgRRg9Nl5WdYCN+vCQbHz+ZdzGJXKq
 cGqdKWgexMKX+aBdNDrK7BphUeD46sH7JWR+a/lDV/BgPxBCm9i5ZZCgXbPP89AZ
 NpLBji7gz49wMsnm/x135xtNlZ3dG0oKETzi7MiR+NtKtUGvoIszSKy5JdPZ4m8q
 9fnXmHqmwM6uQFuzDJPt1o+D1fusTuYnjI7EgyrJRRhQ+BB3qEFZApXnKNDRS9Dm
 uB7jtcwefJCjlZVCf2+PWTOEifH2WFZXLPFlC8f44jK6iRW2Nc+wVRisJ3vSNBG1
 gaRUe/FSge68eyfQj5OFiwM/2099MNkKdZ0fSOjEBeubQpiFChjgWgcOXa5Bhlrr
 C4CIhFV2qg/tOuHDAF+Q5S96oZkaTy5qcEEwhBSW15ySDUaRWFSrtboNt6ZVOhug
 d8JJvDCQWoNu1IQozcbv6xW/Rk7miy8c0INZ4q33YUvIZpH862+vgDWfTJ73Zy9H
 jR/8eG6t3kFHKS1vWdKZzOX1bEcnd02CGElFnFYUEewKoV7ZeeLsYX7zodyUAKyi
 Yp5CImsDbWWTsptBg6h9nt2TseXTxYCt2bbmpJcqzsqSCUwOQNQ4/YpuzLeG0ihc
 JgOmUnQNJWCTwUUw5AS1
 =tzmJ
 -----END PGP SIGNATURE-----

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
  ...

include/linux/sched/task.h

@@ -104,6 +104,20 @@ extern int arch_task_struct_size __read_mostly;
 # define arch_task_struct_size (sizeof(struct task_struct))
 #endif
 
+#ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST
+/*
+ * If an architecture has not declared a thread_struct whitelist we
+ * must assume something there may need to be copied to userspace.
+ */
+static inline void arch_thread_struct_whitelist(unsigned long *offset,
+						unsigned long *size)
+{
+	*offset = 0;
+	/* Handle dynamically sized thread_struct. */
+	*size = arch_task_struct_size - offsetof(struct task_struct, thread);
+}
+#endif
+
 #ifdef CONFIG_VMAP_STACK
 static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
 {

include/linux/slab.h

@@ -135,9 +135,15 @@ struct mem_cgroup;
 void __init kmem_cache_init(void);
 bool slab_is_available(void);
 
-struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
-			slab_flags_t,
-			void (*)(void *));
+extern bool usercopy_fallback;
+
+struct kmem_cache *kmem_cache_create(const char *name, size_t size,
+			size_t align, slab_flags_t flags,
+			void (*ctor)(void *));
+struct kmem_cache *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 *));
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 
@@ -153,9 +159,20 @@ void memcg_destroy_kmem_caches(struct mem_cgroup *);
  * f.e. add ____cacheline_aligned_in_smp to the struct declaration
  * then the objects will be properly aligned in SMP configurations.
  */
-#define KMEM_CACHE(__struct, __flags) kmem_cache_create(#__struct,\
-		sizeof(struct __struct), __alignof__(struct __struct),\
-		(__flags), NULL)
+#define KMEM_CACHE(__struct, __flags)					\
+		kmem_cache_create(#__struct, sizeof(struct __struct),	\
+			__alignof__(struct __struct), (__flags), NULL)
+
+/*
+ * To whitelist a single field for copying to/from usercopy, use this
+ * macro instead for KMEM_CACHE() above.
+ */
+#define KMEM_CACHE_USERCOPY(__struct, __flags, __field)			\
+		kmem_cache_create_usercopy(#__struct,			\
+			sizeof(struct __struct),			\
+			__alignof__(struct __struct), (__flags),	\
+			offsetof(struct __struct, __field),		\
+			sizeof_field(struct __struct, __field), NULL)
 
 /*
  * Common kmalloc functions provided by all allocators
@@ -167,15 +184,11 @@ void kzfree(const void *);
 size_t ksize(const void *);
 
 #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
-const char *__check_heap_object(const void *ptr, unsigned long n,
-				struct page *page);
+void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
+			bool to_user);
 #else
-static inline const char *__check_heap_object(const void *ptr,
-					      unsigned long n,
-					      struct page *page)
-{
-	return NULL;
-}
+static inline void __check_heap_object(const void *ptr, unsigned long n,
+				       struct page *page, bool to_user) { }
 #endif
 
 /*

include/linux/slab_def.h

@@ -85,6 +85,9 @@ struct kmem_cache {
 	unsigned int *random_seq;
 #endif
 
+	size_t useroffset;		/* Usercopy region offset */
+	size_t usersize;		/* Usercopy region size */
+
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };
 

include/linux/slub_def.h

@@ -135,6 +135,9 @@ struct kmem_cache {
 	struct kasan_cache kasan_info;
 #endif
 
+	size_t useroffset;		/* Usercopy region offset */
+	size_t usersize;		/* Usercopy region size */
+
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };
 

include/linux/stddef.h

@@ -19,6 +19,14 @@ enum {
 #define offsetof(TYPE, MEMBER)	((size_t)&((TYPE *)0)->MEMBER)
 #endif
 
+/**
+ * sizeof_field(TYPE, MEMBER)
+ *
+ * @TYPE: The structure containing the field of interest
+ * @MEMBER: The field to return the size of
+ */
+#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER))
+
 /**
  * offsetofend(TYPE, MEMBER)
  *
@@ -26,6 +34,6 @@ enum {
  * @MEMBER: The member within the structure to get the end offset of
  */
 #define offsetofend(TYPE, MEMBER) \
-	(offsetof(TYPE, MEMBER)	+ sizeof(((TYPE *)0)->MEMBER))
+	(offsetof(TYPE, MEMBER)	+ sizeof_field(TYPE, MEMBER))
 
 #endif

include/linux/uaccess.h

@@ -273,4 +273,12 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
 #define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0)
 #endif
 
+#ifdef CONFIG_HARDENED_USERCOPY
+void usercopy_warn(const char *name, const char *detail, bool to_user,
+		   unsigned long offset, unsigned long len);
+void __noreturn usercopy_abort(const char *name, const char *detail,
+			       bool to_user, unsigned long offset,
+			       unsigned long len);
+#endif
+
 #endif		/* __LINUX_UACCESS_H__ */