- Introduce arithmetic overflow test helper functions (Rasmus)

- Use overflow helpers in 2-factor allocators (Kees, Rasmus)
 - Introduce overflow test module (Rasmus, Kees)
 - Introduce saturating size helper functions (Matthew, Kees)
 - Treewide use of struct_size() for allocators (Kees)
 -----BEGIN PGP SIGNATURE-----
 Comment: Kees Cook <kees@outflux.net>
 
 iQJKBAABCgA0FiEEpcP2jyKd1g9yPm4TiXL039xtwCYFAlsYJ1gWHGtlZXNjb29r
 QGNocm9taXVtLm9yZwAKCRCJcvTf3G3AJlCTEACwdEeriAd2VwxknnsstojGD/3g
 8TTFA19vSu4Gxa6WiDkjGoSmIlfhXTlZo1Nlmencv16ytSvIVDNLUIB3uDxUIv1J
 2+dyHML9JpXYHHR7zLXXnGFJL0wazqjbsD3NYQgXqmun7EVVYnOsAlBZ7h/Lwiej
 jzEJd8DaHT3TA586uD3uggiFvQU0yVyvkDCDONIytmQx+BdtGdg9TYCzkBJaXuDZ
 YIthyKDvxIw5nh/UaG3L+SKo73tUr371uAWgAfqoaGQQCWe+mxnWL4HkCKsjFzZL
 u9ouxxF/n6pij3E8n6rb0i2fCzlsTDdDF+aqV1rQ4I4hVXCFPpHUZgjDPvBWbj7A
 m6AfRHVNnOgI8HGKqBGOfViV+2kCHlYeQh3pPW33dWzy/4d/uq9NIHKxE63LH+S4
 bY3oO2ela8oxRyvEgXLjqmRYGW1LB/ZU7FS6Rkx2gRzo4k8Rv+8K/KzUHfFVRX61
 jEbiPLzko0xL9D53kcEn0c+BhofK5jgeSWxItdmfuKjLTW4jWhLRlU+bcUXb6kSS
 S3G6aF+L+foSUwoq63AS8QxCuabuhreJSB+BmcGUyjthCbK/0WjXYC6W/IJiRfBa
 3ZTxBC/2vP3uq/AGRNh5YZoxHL8mSxDfn62F+2cqlJTTKR/O+KyDb1cusyvk3H04
 KCDVLYPxwQQqK1Mqig==
 =/3L8
 -----END PGP SIGNATURE-----

Merge tag 'overflow-v4.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull overflow updates from Kees Cook:
 "This adds the new overflow checking helpers and adds them to the
  2-factor argument allocators. And this adds the saturating size
  helpers and does a treewide replacement for the struct_size() usage.
  Additionally this adds the overflow testing modules to make sure
  everything works.

  I'm still working on the treewide replacements for allocators with
  "simple" multiplied arguments:

     *alloc(a * b, ...) -> *alloc_array(a, b, ...)

  and

     *zalloc(a * b, ...) -> *calloc(a, b, ...)

  as well as the more complex cases, but that's separable from this
  portion of the series. I expect to have the rest sent before -rc1
  closes; there are a lot of messy cases to clean up.

  Summary:

   - Introduce arithmetic overflow test helper functions (Rasmus)

   - Use overflow helpers in 2-factor allocators (Kees, Rasmus)

   - Introduce overflow test module (Rasmus, Kees)

   - Introduce saturating size helper functions (Matthew, Kees)

   - Treewide use of struct_size() for allocators (Kees)"

* tag 'overflow-v4.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  treewide: Use struct_size() for devm_kmalloc() and friends
  treewide: Use struct_size() for vmalloc()-family
  treewide: Use struct_size() for kmalloc()-family
  device: Use overflow helpers for devm_kmalloc()
  mm: Use overflow helpers in kvmalloc()
  mm: Use overflow helpers in kmalloc_array*()
  test_overflow: Add memory allocation overflow tests
  overflow.h: Add allocation size calculation helpers
  test_overflow: Report test failures
  test_overflow: macrofy some more, do more tests for free
  lib: add runtime test of check_*_overflow functions
  compiler.h: enable builtin overflow checkers and add fallback code

include/linux/compiler-clang.h

@@ -32,3 +32,17 @@
 #ifdef __noretpoline
 #undef __noretpoline
 #endif
+
+/*
+ * Not all versions of clang implement the the type-generic versions
+ * of the builtin overflow checkers. Fortunately, clang implements
+ * __has_builtin allowing us to avoid awkward version
+ * checks. Unfortunately, we don't know which version of gcc clang
+ * pretends to be, so the macro may or may not be defined.
+ */
+#undef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
+#if __has_builtin(__builtin_mul_overflow) && \
+    __has_builtin(__builtin_add_overflow) && \
+    __has_builtin(__builtin_sub_overflow)
+#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
+#endif

include/linux/compiler-gcc.h

@@ -343,3 +343,7 @@
  * code
  */
 #define uninitialized_var(x) x = x
+
+#if GCC_VERSION >= 50100
+#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
+#endif

include/linux/compiler-intel.h

@@ -44,3 +44,7 @@
 #define __builtin_bswap16 _bswap16
 #endif
 
+/*
+ * icc defines __GNUC__, but does not implement the builtin overflow checkers.
+ */
+#undef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW

include/linux/device.h

@@ -25,6 +25,7 @@
 #include <linux/ratelimit.h>
 #include <linux/uidgid.h>
 #include <linux/gfp.h>
+#include <linux/overflow.h>
 #include <asm/device.h>
 
 struct device;
@@ -672,9 +673,12 @@ static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
 static inline void *devm_kmalloc_array(struct device *dev,
 				       size_t n, size_t size, gfp_t flags)
 {
-	if (size != 0 && n > SIZE_MAX / size)
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
 		return NULL;
-	return devm_kmalloc(dev, n * size, flags);
+
+	return devm_kmalloc(dev, bytes, flags);
 }
 static inline void *devm_kcalloc(struct device *dev,
 				 size_t n, size_t size, gfp_t flags)

include/linux/mm.h

@@ -25,6 +25,7 @@
 #include <linux/err.h>
 #include <linux/page_ref.h>
 #include <linux/memremap.h>
+#include <linux/overflow.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -560,10 +561,12 @@ static inline void *kvzalloc(size_t size, gfp_t flags)
 
 static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags)
 {
-	if (size != 0 && n > SIZE_MAX / size)
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
 		return NULL;
 
-	return kvmalloc(n * size, flags);
+	return kvmalloc(bytes, flags);
 }
 
 extern void kvfree(const void *addr);

include/linux/overflow.h

@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+#ifndef __LINUX_OVERFLOW_H
+#define __LINUX_OVERFLOW_H
+
+#include <linux/compiler.h>
+
+/*
+ * In the fallback code below, we need to compute the minimum and
+ * maximum values representable in a given type. These macros may also
+ * be useful elsewhere, so we provide them outside the
+ * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
+ *
+ * It would seem more obvious to do something like
+ *
+ * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
+ * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
+ *
+ * Unfortunately, the middle expressions, strictly speaking, have
+ * undefined behaviour, and at least some versions of gcc warn about
+ * the type_max expression (but not if -fsanitize=undefined is in
+ * effect; in that case, the warning is deferred to runtime...).
+ *
+ * The slightly excessive casting in type_min is to make sure the
+ * macros also produce sensible values for the exotic type _Bool. [The
+ * overflow checkers only almost work for _Bool, but that's
+ * a-feature-not-a-bug, since people shouldn't be doing arithmetic on
+ * _Bools. Besides, the gcc builtins don't allow _Bool* as third
+ * argument.]
+ *
+ * Idea stolen from
+ * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html -
+ * credit to Christian Biere.
+ */
+#define is_signed_type(type)       (((type)(-1)) < (type)1)
+#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
+#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
+#define type_min(T) ((T)((T)-type_max(T)-(T)1))
+
+
+#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
+/*
+ * For simplicity and code hygiene, the fallback code below insists on
+ * a, b and *d having the same type (similar to the min() and max()
+ * macros), whereas gcc's type-generic overflow checkers accept
+ * different types. Hence we don't just make check_add_overflow an
+ * alias for __builtin_add_overflow, but add type checks similar to
+ * below.
+ */
+#define check_add_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_add_overflow(__a, __b, __d);	\
+})
+
+#define check_sub_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_sub_overflow(__a, __b, __d);	\
+})
+
+#define check_mul_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_mul_overflow(__a, __b, __d);	\
+})
+
+#else
+
+
+/* Checking for unsigned overflow is relatively easy without causing UB. */
+#define __unsigned_add_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = __a + __b;			\
+	*__d < __a;				\
+})
+#define __unsigned_sub_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = __a - __b;			\
+	__a < __b;				\
+})
+/*
+ * If one of a or b is a compile-time constant, this avoids a division.
+ */
+#define __unsigned_mul_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);				\
+	typeof(b) __b = (b);				\
+	typeof(d) __d = (d);				\
+	(void) (&__a == &__b);				\
+	(void) (&__a == __d);				\
+	*__d = __a * __b;				\
+	__builtin_constant_p(__b) ?			\
+	  __b > 0 && __a > type_max(typeof(__a)) / __b : \
+	  __a > 0 && __b > type_max(typeof(__b)) / __a;	 \
+})
+
+/*
+ * For signed types, detecting overflow is much harder, especially if
+ * we want to avoid UB. But the interface of these macros is such that
+ * we must provide a result in *d, and in fact we must produce the
+ * result promised by gcc's builtins, which is simply the possibly
+ * wrapped-around value. Fortunately, we can just formally do the
+ * operations in the widest relevant unsigned type (u64) and then
+ * truncate the result - gcc is smart enough to generate the same code
+ * with and without the (u64) casts.
+ */
+
+/*
+ * Adding two signed integers can overflow only if they have the same
+ * sign, and overflow has happened iff the result has the opposite
+ * sign.
+ */
+#define __signed_add_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = (u64)__a + (u64)__b;		\
+	(((~(__a ^ __b)) & (*__d ^ __a))	\
+		& type_min(typeof(__a))) != 0;	\
+})
+
+/*
+ * Subtraction is similar, except that overflow can now happen only
+ * when the signs are opposite. In this case, overflow has happened if
+ * the result has the opposite sign of a.
+ */
+#define __signed_sub_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = (u64)__a - (u64)__b;		\
+	((((__a ^ __b)) & (*__d ^ __a))		\
+		& type_min(typeof(__a))) != 0;	\
+})
+
+/*
+ * Signed multiplication is rather hard. gcc always follows C99, so
+ * division is truncated towards 0. This means that we can write the
+ * overflow check like this:
+ *
+ * (a > 0 && (b > MAX/a || b < MIN/a)) ||
+ * (a < -1 && (b > MIN/a || b < MAX/a) ||
+ * (a == -1 && b == MIN)
+ *
+ * The redundant casts of -1 are to silence an annoying -Wtype-limits
+ * (included in -Wextra) warning: When the type is u8 or u16, the
+ * __b_c_e in check_mul_overflow obviously selects
+ * __unsigned_mul_overflow, but unfortunately gcc still parses this
+ * code and warns about the limited range of __b.
+ */
+
+#define __signed_mul_overflow(a, b, d) ({				\
+	typeof(a) __a = (a);						\
+	typeof(b) __b = (b);						\
+	typeof(d) __d = (d);						\
+	typeof(a) __tmax = type_max(typeof(a));				\
+	typeof(a) __tmin = type_min(typeof(a));				\
+	(void) (&__a == &__b);						\
+	(void) (&__a == __d);						\
+	*__d = (u64)__a * (u64)__b;					\
+	(__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||	\
+	(__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
+	(__b == (typeof(__b))-1 && __a == __tmin);			\
+})
+
+
+#define check_add_overflow(a, b, d)					\
+	__builtin_choose_expr(is_signed_type(typeof(a)),		\
+			__signed_add_overflow(a, b, d),			\
+			__unsigned_add_overflow(a, b, d))
+
+#define check_sub_overflow(a, b, d)					\
+	__builtin_choose_expr(is_signed_type(typeof(a)),		\
+			__signed_sub_overflow(a, b, d),			\
+			__unsigned_sub_overflow(a, b, d))
+
+#define check_mul_overflow(a, b, d)					\
+	__builtin_choose_expr(is_signed_type(typeof(a)),		\
+			__signed_mul_overflow(a, b, d),			\
+			__unsigned_mul_overflow(a, b, d))
+
+
+#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
+
+/**
+ * array_size() - Calculate size of 2-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ *
+ * Calculates size of 2-dimensional array: @a * @b.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array_size(size_t a, size_t b)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(a, b, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+/**
+ * array3_size() - Calculate size of 3-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ * @c: dimension three
+ *
+ * Calculates size of 3-dimensional array: @a * @b * @c.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array3_size(size_t a, size_t b, size_t c)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(a, b, &bytes))
+		return SIZE_MAX;
+	if (check_mul_overflow(bytes, c, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(n, size, &bytes))
+		return SIZE_MAX;
+	if (check_add_overflow(bytes, c, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+/**
+ * struct_size() - Calculate size of structure with trailing array.
+ * @p: Pointer to the structure.
+ * @member: Name of the array member.
+ * @n: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @p followed by an
+ * array of @n @member elements.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size(p, member, n)					\
+	__ab_c_size(n,							\
+		    sizeof(*(p)->member) + __must_be_array((p)->member),\
+		    sizeof(*(p)))
+
+#endif /* __LINUX_OVERFLOW_H */

include/linux/slab.h

@@ -13,6 +13,7 @@
 #define	_LINUX_SLAB_H
 
 #include <linux/gfp.h>
+#include <linux/overflow.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
@@ -624,11 +625,13 @@ int memcg_update_all_caches(int num_memcgs);
  */
 static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags)
 {
-	if (size != 0 && n > SIZE_MAX / size)
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
 		return NULL;
 	if (__builtin_constant_p(n) && __builtin_constant_p(size))
-		return kmalloc(n * size, flags);
-	return __kmalloc(n * size, flags);
+		return kmalloc(bytes, flags);
+	return __kmalloc(bytes, flags);
 }
 
 /**
@@ -657,11 +660,13 @@ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long);
 static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags,
 				       int node)
 {
-	if (size != 0 && n > SIZE_MAX / size)
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
 		return NULL;
 	if (__builtin_constant_p(n) && __builtin_constant_p(size))
-		return kmalloc_node(n * size, flags, node);
-	return __kmalloc_node(n * size, flags, node);
+		return kmalloc_node(bytes, flags, node);
+	return __kmalloc_node(bytes, flags, node);
 }
 
 static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node)

include/linux/vmalloc.h

@@ -8,6 +8,7 @@
 #include <linux/llist.h>
 #include <asm/page.h>		/* pgprot_t */
 #include <linux/rbtree.h>
+#include <linux/overflow.h>
 
 struct vm_area_struct;		/* vma defining user mapping in mm_types.h */
 struct notifier_block;		/* in notifier.h */