[PATCH] string: Allow 2-argument strscpy()

From: Kees Cook
Date: Wed Jan 31 2024 - 00:55:50 EST


Using sizeof(dst) for the "size" argument in strscpy() is the
overwhelmingly common case. Instead of requiring this everywhere, allow a
2-argument version to be used that will use the sizeof() internally. There
are other functions in the kernel with optional arguments[1], so this
isn't unprecedented, and improves readability. Update and relocate the
kern-doc for strscpy() too.

This could additionally let us save a few hundred lines of code:
1177 files changed, 2455 insertions(+), 3026 deletions(-)
with a treewide cleanup using Coccinelle:

@needless_arg@
expression DST, SRC;
@@

strscpy(DST, SRC
-, sizeof(DST)
)

Link: https://elixir.bootlin.com/linux/v6.7/source/include/linux/pci.h#L1517 [1]
Reviewed-by: Justin Stitt <justinstitt@xxxxxxxxxx>
Cc: Andy Shevchenko <andy@xxxxxxxxxx>
Cc: linux-hardening@xxxxxxxxxxxxxxx
Signed-off-by: Kees Cook <keescook@xxxxxxxxxxxx>
---
rfc:
v1:
- update kern-doc (justin, andy)
- include __must_be_array() for sanity check
---
include/linux/fortify-string.h | 22 ++-------------------
include/linux/string.h | 36 +++++++++++++++++++++++++++++++++-
lib/string.c | 4 ++--
3 files changed, 39 insertions(+), 23 deletions(-)

diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 89a6888f2f9e..06b3aaa63724 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -215,26 +215,8 @@ __kernel_size_t __fortify_strlen(const char * const POS p)
}

/* Defined after fortified strnlen() to reuse it. */
-extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy);
-/**
- * strscpy - Copy a C-string into a sized buffer
- *
- * @p: Where to copy the string to
- * @q: Where to copy the string from
- * @size: Size of destination buffer
- *
- * Copy the source string @q, or as much of it as fits, into the destination
- * @p buffer. The behavior is undefined if the string buffers overlap. The
- * destination @p buffer is always NUL terminated, unless it's zero-sized.
- *
- * Preferred to strncpy() since it always returns a valid string, and
- * doesn't unnecessarily force the tail of the destination buffer to be
- * zero padded. If padding is desired please use strscpy_pad().
- *
- * Returns the number of characters copied in @p (not including the
- * trailing %NUL) or -E2BIG if @size is 0 or the copy of @q was truncated.
- */
-__FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, size_t size)
+extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(sized_strscpy);
+__FORTIFY_INLINE ssize_t sized_strscpy(char * const POS p, const char * const POS q, size_t size)
{
/* Use string size rather than possible enclosing struct size. */
const size_t p_size = __member_size(p);
diff --git a/include/linux/string.h b/include/linux/string.h
index ab148d8dbfc1..c16430c7c043 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -67,9 +67,43 @@ extern char * strcpy(char *,const char *);
extern char * strncpy(char *,const char *, __kernel_size_t);
#endif
#ifndef __HAVE_ARCH_STRSCPY
-ssize_t strscpy(char *, const char *, size_t);
+ssize_t sized_strscpy(char *, const char *, size_t);
#endif

+/*
+ * The 2 argument style can only be used when dst is an array with a
+ * known size.
+ */
+#define __strscpy0(dst, src, ...) \
+ sized_strscpy(dst, src, sizeof(dst) + __must_be_array(dst))
+
+#define __strscpy1(dst, src, size) sized_strscpy(dst, src, size)
+
+/**
+ * strscpy - Copy a C-string into a sized buffer
+ * @dst: Where to copy the string to
+ * @src: Where to copy the string from
+ * @...: Size of destination buffer (optional)
+ *
+ * Copy the source string @src, or as much of it as fits, into the
+ * destination @dst buffer. The behavior is undefined if the string
+ * buffers overlap. The destination @dst buffer is always NUL terminated,
+ * unless it's zero-sized.
+ *
+ * The size argument @... is only required when @dst is not an array, or
+ * when the copy needs to be smaller than sizeof(@dst).
+ *
+ * Preferred to strncpy() since it always returns a valid string, and
+ * doesn't unnecessarily force the tail of the destination buffer to be
+ * zero padded. If padding is desired please use strscpy_pad().
+ *
+ * Returns the number of characters copied in @dst (not including the
+ * trailing %NUL) or -E2BIG if @size is 0 or the copy from @src was
+ * truncated.
+ */
+#define strscpy(dst, src, ...) \
+ CONCATENATE(__strscpy, COUNT_ARGS(__VA_ARGS__))(dst, src, __VA_ARGS__)
+
/* Wraps calls to strscpy()/memset(), no arch specific code required */
ssize_t strscpy_pad(char *dest, const char *src, size_t count);

diff --git a/lib/string.c b/lib/string.c
index 6891d15ce991..2869895a1180 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -104,7 +104,7 @@ EXPORT_SYMBOL(strncpy);
#endif

#ifndef __HAVE_ARCH_STRSCPY
-ssize_t strscpy(char *dest, const char *src, size_t count)
+ssize_t sized_strscpy(char *dest, const char *src, size_t count)
{
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
size_t max = count;
@@ -170,7 +170,7 @@ ssize_t strscpy(char *dest, const char *src, size_t count)

return -E2BIG;
}
-EXPORT_SYMBOL(strscpy);
+EXPORT_SYMBOL(sized_strscpy);
#endif

/**
--
2.34.1