Use a proper C tokenizer to implement the obsolete typedefs test.

The test for obsolete typedefs in installed headers was implemented
using grep, and could therefore get false positives on e.g. “ulong”
in a comment.  It was also scanning all of the headers included by
our headers, and therefore testing headers we don’t control, e.g.
Linux kernel headers.

This patch splits the obsolete-typedef test from
scripts/check-installed-headers.sh to a separate program,
scripts/check-obsolete-constructs.py.  Being implemented in Python,
it is feasible to make it tokenize C accurately enough to avoid false
positives on the contents of comments and strings.  It also only
examines $(headers) in each subdirectory--all the headers we install,
but not any external dependencies of those headers.  Headers whose
installed name starts with finclude/ are ignored, on the assumption
that they contain Fortran.

It is also feasible to make the new test understand the difference
between _defining_ the obsolete typedefs and _using_ the obsolete
typedefs, which means posix/{bits,sys}/types.h no longer need to be
exempted.  This uncovered an actual bug in bits/types.h: __quad_t and
__u_quad_t were being used to define __S64_TYPE, __U64_TYPE,
__SQUAD_TYPE and __UQUAD_TYPE.  These are changed to __int64_t and
__uint64_t respectively.  This is a safe change, despite the comments
in bits/types.h claiming a difference between __quad_t and __int64_t,
because those comments are incorrect.  In all current ABIs, both
__quad_t and __int64_t are ‘long’ when ‘long’ is a 64-bit type, and
‘long long’ when ‘long’ is a 32-bit type, and similarly for __u_quad_t
and __uint64_t.  (Changing the types to be what the comments say they
are would be an ABI break, as it affects C++ name mangling.)  This
patch includes a minimal change to make the comments not completely
wrong.

sys/types.h was defining the legacy BSD u_intN_t typedefs using a
construct that was not necessarily consistent with how the C99 uintN_t
typedefs are defined, and is also too complicated for the new script to
understand (it lexes C relatively accurately, but it does not attempt
to expand preprocessor macros, nor does it do any actual parsing).
This patch cuts all of that out and uses bits/types.h's __uintN_t typedefs
to define u_intN_t instead.  This is verified to not change the ABI on
any supported architecture, via the c++-types test, which means u_intN_t
and uintN_t were, in fact, consistent on all supported architectures.

Reviewed-by: Carlos O'Donell <carlos@redhat.com>

	* scripts/check-obsolete-constructs.py: New test script.
	* scripts/check-installed-headers.sh: Remove tests for
	obsolete typedefs, superseded by check-obsolete-constructs.py.
	* Rules: Run scripts/check-obsolete-constructs.py over $(headers)
	as a special test.  Update commentary.
	* posix/bits/types.h (__SQUAD_TYPE, __S64_TYPE): Define as __int64_t.
	(__UQUAD_TYPE, __U64_TYPE): Define as __uint64_t.
	Update commentary.
	* posix/sys/types.h (__u_intN_t): Remove.
	(u_int8_t): Typedef using __uint8_t.
	(u_int16_t): Typedef using __uint16_t.
	(u_int32_t): Typedef using __uint32_t.
	(u_int64_t): Typedef using __uint64_t.

2 files changed, 13 insertions, 30 deletions

diff --git a/posix/bits/types.h b/posix/bits/types.h
index 27e065c3be..0de6c59bb4 100644
--- a/posix/bits/types.h
+++ b/posix/bits/types.h
@@ -87,7 +87,7 @@ __extension__ typedef unsigned long long int __uintmax_t;
 	32		-- "natural" 32-bit type (always int)
 	64		-- "natural" 64-bit type (long or long long)
 	LONG32		-- 32-bit type, traditionally long
-	QUAD		-- 64-bit type, always long long
+	QUAD		-- 64-bit type, traditionally long long
 	WORD		-- natural type of __WORDSIZE bits (int or long)
 	LONGWORD	-- type of __WORDSIZE bits, traditionally long
 
@@ -113,14 +113,14 @@ __extension__ typedef unsigned long long int __uintmax_t;
 #define __SLONGWORD_TYPE	long int
 #define __ULONGWORD_TYPE	unsigned long int
 #if __WORDSIZE == 32
-# define __SQUAD_TYPE		__quad_t
-# define __UQUAD_TYPE		__u_quad_t
+# define __SQUAD_TYPE		__int64_t
+# define __UQUAD_TYPE		__uint64_t
 # define __SWORD_TYPE		int
 # define __UWORD_TYPE		unsigned int
 # define __SLONG32_TYPE		long int
 # define __ULONG32_TYPE		unsigned long int
-# define __S64_TYPE		__quad_t
-# define __U64_TYPE		__u_quad_t
+# define __S64_TYPE		__int64_t
+# define __U64_TYPE		__uint64_t
 /* We want __extension__ before typedef's that use nonstandard base types
    such as `long long' in C89 mode.  */
 # define __STD_TYPE		__extension__ typedef
diff --git a/posix/sys/types.h b/posix/sys/types.h
index 27129c5c23..0e37b1ce6a 100644
--- a/posix/sys/types.h
+++ b/posix/sys/types.h
@@ -154,37 +154,20 @@ typedef unsigned int uint;
 
 #include <bits/stdint-intn.h>
 
-#if !__GNUC_PREREQ (2, 7)
-
 /* These were defined by ISO C without the first `_'.  */
-typedef	unsigned char u_int8_t;
-typedef	unsigned short int u_int16_t;
-typedef	unsigned int u_int32_t;
-# if __WORDSIZE == 64
-typedef unsigned long int u_int64_t;
-# else
-__extension__ typedef unsigned long long int u_int64_t;
-# endif
-
-typedef int register_t;
-
-#else
-
-/* For GCC 2.7 and later, we can use specific type-size attributes.  */
-# define __u_intN_t(N, MODE) \
-  typedef unsigned int u_int##N##_t __attribute__ ((__mode__ (MODE)))
-
-__u_intN_t (8, __QI__);
-__u_intN_t (16, __HI__);
-__u_intN_t (32, __SI__);
-__u_intN_t (64, __DI__);
+typedef __uint8_t u_int8_t;
+typedef __uint16_t u_int16_t;
+typedef __uint32_t u_int32_t;
+typedef __uint64_t u_int64_t;
 
+#if __GNUC_PREREQ (2, 7)
 typedef int register_t __attribute__ ((__mode__ (__word__)));
-
+#else
+typedef int register_t;
+#endif
 
 /* Some code from BIND tests this macro to see if the types above are
    defined.  */
-#endif
 #define __BIT_TYPES_DEFINED__	1