string: Introduce strtomem() and strtomem_pad()

One of the "legitimate" uses of strncpy() is copying a NUL-terminated
string into a fixed-size non-NUL-terminated character array. To avoid
the weaknesses and ambiguity of intent when using strncpy(), provide
replacement functions that explicitly distinguish between trailing
padding and not, and require the destination buffer size be discoverable
by the compiler.

For example:

struct obj {
	int foo;
	char small[4] __nonstring;
	char big[8] __nonstring;
	int bar;
};

struct obj p;

/* This will truncate to 4 chars with no trailing NUL */
strncpy(p.small, "hello", sizeof(p.small));
/* p.small contains 'h', 'e', 'l', 'l' */

/* This will NUL pad to 8 chars. */
strncpy(p.big, "hello", sizeof(p.big));
/* p.big contains 'h', 'e', 'l', 'l', 'o', '\0', '\0', '\0' */

When the "__nonstring" attributes are missing, the intent of the
programmer becomes ambiguous for whether the lack of a trailing NUL
in the p.small copy is a bug. Additionally, it's not clear whether
the trailing padding in the p.big copy is _needed_. Both cases
become unambiguous with:

strtomem(p.small, "hello");
strtomem_pad(p.big, "hello", 0);

See also https://github.com/KSPP/linux/issues/90

Expand the memcpy KUnit tests to include these functions.

Cc: Wolfram Sang <wsa+renesas@sang-engineering.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Kees Cook <keescook@chromium.org>

2 files changed, 75 insertions, 0 deletions

diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 3b401fa0f374..8e8c2c87b1d5 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -77,6 +77,38 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size)
 #define POS	__pass_object_size(1)
 #define POS0	__pass_object_size(0)
 
+/**
+ * strncpy - Copy a string to memory with non-guaranteed NUL padding
+ *
+ * @p: pointer to destination of copy
+ * @q: pointer to NUL-terminated source string to copy
+ * @size: bytes to write at @p
+ *
+ * If strlen(@q) >= @size, the copy of @q will stop after @size bytes,
+ * and @p will NOT be NUL-terminated
+ *
+ * If strlen(@q) < @size, following the copy of @q, trailing NUL bytes
+ * will be written to @p until @size total bytes have been written.
+ *
+ * Do not use this function. While FORTIFY_SOURCE tries to avoid
+ * over-reads of @q, it cannot defend against writing unterminated
+ * results to @p. Using strncpy() remains ambiguous and fragile.
+ * Instead, please choose an alternative, so that the expectation
+ * of @p's contents is unambiguous:
+ *
+ * +--------------------+-----------------+------------+
+ * | @p needs to be:    | padded to @size | not padded |
+ * +====================+=================+============+
+ * |     NUL-terminated | strscpy_pad()   | strscpy()  |
+ * +--------------------+-----------------+------------+
+ * | not NUL-terminated | strtomem_pad()  | strtomem() |
+ * +--------------------+-----------------+------------+
+ *
+ * Note strscpy*()'s differing return values for detecting truncation,
+ * and strtomem*()'s expectation that the destination is marked with
+ * __nonstring when it is a character array.
+ *
+ */
 __FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3)
 char *strncpy(char * const POS p, const char *q, __kernel_size_t size)
 {
diff --git a/include/linux/string.h b/include/linux/string.h
index 61ec7e4f6311..cf7607b32102 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -261,6 +261,49 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count,
 		    int pad);
 
 /**
+ * strtomem_pad - Copy NUL-terminated string to non-NUL-terminated buffer
+ *
+ * @dest: Pointer of destination character array (marked as __nonstring)
+ * @src: Pointer to NUL-terminated string
+ * @pad: Padding character to fill any remaining bytes of @dest after copy
+ *
+ * This is a replacement for strncpy() uses where the destination is not
+ * a NUL-terminated string, but with bounds checking on the source size, and
+ * an explicit padding character. If padding is not required, use strtomem().
+ *
+ * Note that the size of @dest is not an argument, as the length of @dest
+ * must be discoverable by the compiler.
+ */
+#define strtomem_pad(dest, src, pad)	do {				\
+	const size_t _dest_len = __builtin_object_size(dest, 1);	\
+									\
+	BUILD_BUG_ON(!__builtin_constant_p(_dest_len) ||		\
+		     _dest_len == (size_t)-1);				\
+	memcpy_and_pad(dest, _dest_len, src, strnlen(src, _dest_len), pad); \
+} while (0)
+
+/**
+ * strtomem - Copy NUL-terminated string to non-NUL-terminated buffer
+ *
+ * @dest: Pointer of destination character array (marked as __nonstring)
+ * @src: Pointer to NUL-terminated string
+ *
+ * This is a replacement for strncpy() uses where the destination is not
+ * a NUL-terminated string, but with bounds checking on the source size, and
+ * without trailing padding. If padding is required, use strtomem_pad().
+ *
+ * Note that the size of @dest is not an argument, as the length of @dest
+ * must be discoverable by the compiler.
+ */
+#define strtomem(dest, src)	do {					\
+	const size_t _dest_len = __builtin_object_size(dest, 1);	\
+									\
+	BUILD_BUG_ON(!__builtin_constant_p(_dest_len) ||		\
+		     _dest_len == (size_t)-1);				\
+	memcpy(dest, src, min(_dest_len, strnlen(src, _dest_len)));	\
+} while (0)
+
+/**
  * memset_after - Set a value after a struct member to the end of a struct
  *
  * @obj: Address of target struct instance