10:04 a.m.
When building with clang 4.0.0, virsh build fails like this:
gmake[3]: Entering directory '/usr/home/novel/code/libvirt/tools'
CC virsh-virsh.o
In file included from virsh.c:45:
In file included from /usr/local/include/readline/readline.h:31:
/usr/local/include/readline/rltypedefs.h:35:22: error: this function declaration is not a
prototype [-Werror,-Wstrict-prototypes]
typedef int Function () __attribute__ ((deprecated));
^
void
/usr/local/include/readline/rltypedefs.h:36:24: error: this function declaration is not a
prototype [-Werror,-Wstrict-prototypes]
typedef void VFunction () __attribute__ ((deprecated));
^
void
/usr/local/include/readline/rltypedefs.h:37:26: error: this function declaration is not a
prototype [-Werror,-Wstrict-prototypes]
typedef char *CPFunction () __attribute__ ((deprecated));
^
void
/usr/local/include/readline/rltypedefs.h:38:28: error: this function declaration is not a
prototype [-Werror,-Wstrict-prototypes]
typedef char **CPPFunction () __attribute__ ((deprecated));
^
void
In file included from virsh.c:45:
/usr/local/include/readline/readline.h:385:23: error: this function declaration is not a
prototype [-Werror,-Wstrict-prototypes]
extern int rl_message ();
^
void
5 errors generated.
gmake[3]: *** [Makefile:2823: virsh-virsh.o] Error 1
Fix that by adding -D_FUNCTION_DEF to READLINE_CFLAGS to fix *Function
related warnings and add a check for stdarg.h so readline headers
use proper rl_message declaration.
Bug report on the readline mailing list:
http://lists.gnu.org/archive/html/bug-readline/2017-05/msg00004.html
---
configure.ac | 2 +-
m4/virt-readline.m4 | 4 +++-
tools/Makefile.am | 3 ++-
3 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/configure.ac b/configure.ac
index 1af5538ee..1a73b3466 100644
--- a/configure.ac
+++ b/configure.ac
@@ -328,7 +328,7 @@ dnl Availability of various common headers (non-fatal if missing).
AC_CHECK_HEADERS([pwd.h regex.h sys/un.h \
sys/poll.h syslog.h mntent.h net/ethernet.h linux/magic.h \
sys/un.h sys/syscall.h sys/sysctl.h netinet/tcp.h ifaddrs.h \
- libtasn1.h sys/ucred.h sys/mount.h])
+ libtasn1.h sys/ucred.h sys/mount.h stdarg.h])
dnl Check whether endian provides handy macros.
AC_CHECK_DECLS([htole64], [], [], [[#include <endian.h>]])
AC_CHECK_FUNCS([stat stat64 __xstat __xstat64 lstat lstat64 __lxstat __lxstat64])
diff --git a/m4/virt-readline.m4 b/m4/virt-readline.m4
index ee70ea36b..9fba5148a 100644
--- a/m4/virt-readline.m4
+++ b/m4/virt-readline.m4
@@ -45,7 +45,9 @@ AC_DEFUN([LIBVIRT_CHECK_READLINE],[
# function, to ensure we aren't being confused by caching.
LIBS=$lv_saved_libs
AC_CHECK_LIB([readline], [rl_initialize],
- [], [READLINE_LIBS="$READLINE_LIBS $extra_LIBS"])
+ [READLINE_CFLAGS="-D_FUNCTION_DEF $READLINE_CFLAGS"
+ AC_SUBST(READLINE_CFLAGS)],
+ [READLINE_LIBS="$READLINE_LIBS $extra_LIBS"])
LIBS=$lv_saved_libs
])
diff --git a/tools/Makefile.am b/tools/Makefile.am
index 56691c289..345521457 100644
--- a/tools/Makefile.am
+++ b/tools/Makefile.am
@@ -244,7 +244,8 @@ virsh_CFLAGS = \
$(WARN_CFLAGS) \
$(PIE_CFLAGS) \
$(COVERAGE_CFLAGS) \
- $(LIBXML_CFLAGS)
+ $(LIBXML_CFLAGS) \
+ $(READLINE_CFLAGS)
virt_admin_SOURCES = \
virt-admin.c virt-admin.h \
--
2.13.0
3:10 a.m.
On Fri, Jun 02, 2017 at 07:04:23PM +0400, Roman Bogorodskiy wrote:
When building with clang 4.0.0, virsh build fails like this:
[...]
Bug report on the readline mailing list:
http://lists.gnu.org/archive/html/bug-readline/2017-05/msg00004.html
---
configure.ac | 2 +-
m4/virt-readline.m4 | 4 +++-
tools/Makefile.am | 3 ++-
3 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/configure.ac b/configure.ac
index 1af5538ee..1a73b3466 100644
--- a/configure.ac
+++ b/configure.ac
@@ -328,7 +328,7 @@ dnl Availability of various common headers (non-fatal if missing).
AC_CHECK_HEADERS([pwd.h regex.h sys/un.h \
sys/poll.h syslog.h mntent.h net/ethernet.h linux/magic.h \
sys/un.h sys/syscall.h sys/sysctl.h netinet/tcp.h ifaddrs.h \
- libtasn1.h sys/ucred.h sys/mount.h])
+ libtasn1.h sys/ucred.h sys/mount.h stdarg.h])
dnl Check whether endian provides handy macros.
AC_CHECK_DECLS([htole64], [], [], [[#include <endian.h>]])
AC_CHECK_FUNCS([stat stat64 __xstat __xstat64 lstat lstat64 __lxstat __lxstat64])
What is the purpose of checking for stdarg.h?
ACK with this hunk removed or explained.
Jan
8:20 a.m.
Ján Tomko wrote:
On Fri, Jun 02, 2017 at 07:04:23PM +0400, Roman Bogorodskiy wrote:
>When building with clang 4.0.0, virsh build fails like this:
>
[...]
>
>Bug report on the readline mailing list:
>
> http://lists.gnu.org/archive/html/bug-readline/2017-05/msg00004.html
>---
> configure.ac | 2 +-
> m4/virt-readline.m4 | 4 +++-
> tools/Makefile.am | 3 ++-
> 3 files changed, 6 insertions(+), 3 deletions(-)
>
>diff --git a/configure.ac b/configure.ac
>index 1af5538ee..1a73b3466 100644
>--- a/configure.ac
>+++ b/configure.ac
>@@ -328,7 +328,7 @@ dnl Availability of various common headers (non-fatal if
missing).
> AC_CHECK_HEADERS([pwd.h regex.h sys/un.h \
> sys/poll.h syslog.h mntent.h net/ethernet.h linux/magic.h \
> sys/un.h sys/syscall.h sys/sysctl.h netinet/tcp.h ifaddrs.h \
>- libtasn1.h sys/ucred.h sys/mount.h])
>+ libtasn1.h sys/ucred.h sys/mount.h stdarg.h])
> dnl Check whether endian provides handy macros.
> AC_CHECK_DECLS([htole64], [], [], [[#include <endian.h>]])
> AC_CHECK_FUNCS([stat stat64 __xstat __xstat64 lstat lstat64 __lxstat __lxstat64])
What is the purpose of checking for stdarg.h?
As the commit message says: "... and add a check for stdarg.h so readline headers
use proper rl_message declaration." I thought that's enough details, but
obviously it's not as you're asking :-)
The thing is that there's a following code in readline.h:
#if defined (USE_VARARGS) && defined (PREFER_STDARG)
extern int rl_message (const char *, ...) __attribute__((__format__ (printf, 1, 2)));
#else
extern int rl_message ();
#endif
The latter generates the described warning and the former does not.
PREFER_STDARG and USE_VARARGS come from another readline header,
rlstdc.h, and it contains the following:
#if defined (__STDC__) && defined (HAVE_STDARG_H)
# define PREFER_STDARG
# define USE_VARARGS
#else
# if defined (HAVE_VARARGS_H)
# define PREFER_VARARGS
# define USE_VARARGS
# endif
#endif
So we need to have HAVE_STDARG_H defined to have a proper declaration.
How do you like if I rephrase it like "... and add a check for stdarg.h so
we have HAVE_STDARG_H defined that's needed by the readline headers to use
proper rl_message declaration"?
ACK with this hunk removed or explained.
Jan
Roman Bogorodskiy
9:21 a.m.
On Thu, Jun 08, 2017 at 05:20:35PM +0400, Roman Bogorodskiy wrote:
Ján Tomko wrote:
> On Fri, Jun 02, 2017 at 07:04:23PM +0400, Roman Bogorodskiy wrote:
> >When building with clang 4.0.0, virsh build fails like this:
> >
>
> [...]
>
> >
> >Bug report on the readline mailing list:
> >
> > http://lists.gnu.org/archive/html/bug-readline/2017-05/msg00004.html
> >---
> > configure.ac | 2 +-
> > m4/virt-readline.m4 | 4 +++-
> > tools/Makefile.am | 3 ++-
> > 3 files changed, 6 insertions(+), 3 deletions(-)
> >
> >diff --git a/configure.ac b/configure.ac
> >index 1af5538ee..1a73b3466 100644
> >--- a/configure.ac
> >+++ b/configure.ac
> >@@ -328,7 +328,7 @@ dnl Availability of various common headers (non-fatal if
missing).
> > AC_CHECK_HEADERS([pwd.h regex.h sys/un.h \
> > sys/poll.h syslog.h mntent.h net/ethernet.h linux/magic.h \
> > sys/un.h sys/syscall.h sys/sysctl.h netinet/tcp.h ifaddrs.h \
> >- libtasn1.h sys/ucred.h sys/mount.h])
> >+ libtasn1.h sys/ucred.h sys/mount.h stdarg.h])
> > dnl Check whether endian provides handy macros.
> > AC_CHECK_DECLS([htole64], [], [], [[#include <endian.h>]])
> > AC_CHECK_FUNCS([stat stat64 __xstat __xstat64 lstat lstat64 __lxstat
__lxstat64])
>
> What is the purpose of checking for stdarg.h?
As the commit message says: "... and add a check for stdarg.h so readline headers
use proper rl_message declaration." I thought that's enough details, but
obviously it's not as you're asking :-)
I skipped that part of the commit message. I did not expect that other
checks would be influenced by this AC_CHECK_HEADERS.
The thing is that there's a following code in readline.h:
#if defined (USE_VARARGS) && defined (PREFER_STDARG)
extern int rl_message (const char *, ...) __attribute__((__format__ (printf, 1, 2)));
#else
extern int rl_message ();
#endif
The latter generates the described warning and the former does not.
PREFER_STDARG and USE_VARARGS come from another readline header,
rlstdc.h, and it contains the following:
#if defined (__STDC__) && defined (HAVE_STDARG_H)
# define PREFER_STDARG
# define USE_VARARGS
#else
# if defined (HAVE_VARARGS_H)
# define PREFER_VARARGS
# define USE_VARARGS
# endif
#endif
So we need to have HAVE_STDARG_H defined to have a proper declaration.
How do you like if I rephrase it like "... and add a check for stdarg.h so
we have HAVE_STDARG_H defined that's needed by the readline headers to use
proper rl_message declaration"?
Yes, that is clear enough even for me :)
Jan
12:12 p.m.
Ján Tomko wrote:
>> What is the purpose of checking for stdarg.h?
>
>As the commit message says: "... and add a check for stdarg.h so readline
headers
>use proper rl_message declaration." I thought that's enough details, but
>obviously it's not as you're asking :-)
>
I skipped that part of the commit message. I did not expect that other
checks would be influenced by this AC_CHECK_HEADERS.
>The thing is that there's a following code in readline.h:
>
>#if defined (USE_VARARGS) && defined (PREFER_STDARG)
>extern int rl_message (const char *, ...) __attribute__((__format__ (printf, 1,
2)));
>#else
>extern int rl_message ();
>#endif
>
>The latter generates the described warning and the former does not.
>
>PREFER_STDARG and USE_VARARGS come from another readline header,
>rlstdc.h, and it contains the following:
>
>#if defined (__STDC__) && defined (HAVE_STDARG_H)
># define PREFER_STDARG
># define USE_VARARGS
>#else
># if defined (HAVE_VARARGS_H)
># define PREFER_VARARGS
># define USE_VARARGS
># endif
>#endif
>
>So we need to have HAVE_STDARG_H defined to have a proper declaration.
>
>How do you like if I rephrase it like "... and add a check for stdarg.h so
>we have HAVE_STDARG_H defined that's needed by the readline headers to use
>proper rl_message declaration"?
>
Yes, that is clear enough even for me :)
Jan
Pushed with the commit message updated, thanks!
Roman Bogorodskiy
2727
days inactive
2733
days old
4 comments
2 participants
participants (2)
-
Ján Tomko -
Roman Bogorodskiy