patches/uClibc/0.9.30/150-getaddrinfo-segfault-ipv6-and-ipv4.patch
author "Yann E. MORIN" <yann.morin.1998@anciens.enib.fr>
Sun Sep 12 23:38:18 2010 +0200 (2010-09-12)
changeset 2120 48de021b3a9e
permissions -rw-r--r--
arch/mips: add experimental mips64 samples

Both toolchains were tested to successfully:
- _build_ busybox, giving respectively an n32 and an n64 binary
although it has not been run-tested.
- build linux-2.6.36-rc3 for Loongson, giving an n64 vmlinux
(which is expected, due to the way the kernel is built),
and the kernel properly boots!

Credits are due to Julien MOUTHINO (julm on freenode#uClibc) for
testing that the kernel boots on his hardware! Cheers! ;-)

Signed-off-by: "Yann E. MORIN" <yann.morin.1998@anciens.enib.fr>
     1 From: Tomoyoshi ASANO <asa@lineo.co.jp>
     2 Message ID: <20081208073522.0AEF.22C34B8C@lineo.co.jp>
     3 
     4 Hello,
     5 
     6 I have SEGV at busybox's telnet with uClibc-0.9.30.
     7 It seem the current uClibc-trunk has the same problem.
     8 
     9 Thanks,
    10 -- Tom
    11 
    12 diff -ru uClibc-0.9.30.orig/libc/inet/getaddrinfo.c uClibc-0.9.30/libc/inet/getaddrinfo.c
    13 --- uClibc-0.9.30.orig/libc/inet/getaddrinfo.c	2008-10-28 17:25:10.000000000 +0100
    14 +++ uClibc-0.9.30/libc/inet/getaddrinfo.c	2009-02-26 14:20:06.000000000 +0100
    15 @@ -186,7 +186,7 @@
    16  			return seen;
    17  		}
    18  
    19 -		for (runp = ifa; runp != NULL; runp = runp->ifa_next)
    20 +		for (runp = ifa; runp != NULL; runp = runp->ifa_next) {
    21  #if defined __UCLIBC_HAS_IPV4__
    22  			if (runp->ifa_addr->sa_family == PF_INET)
    23  				seen |= SEEN_IPV4;
    24 @@ -195,7 +195,7 @@
    25  			if (runp->ifa_addr->sa_family == PF_INET6)
    26  				seen |= SEEN_IPV6;
    27  #endif /* __UCLIBC_HAS_IPV6__ */
    28 -
    29 +                }
    30  		freeifaddrs(ifa);
    31  	}
    32  #else