summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
authorAlexandra Kossovsky <Alexandra.Kossovsky@oktetlabs.ru>2005-11-20 13:41:59 -0800
committerDavid S. Miller <davem@davemloft.net>2005-11-20 13:41:59 -0800
commit4909724b5dee8fb7c52bbe90afa40c65b17be9eb (patch)
tree7611a0f01ff0b0a1389928683b4223c160123d2a /net/ipv6
parentfb0d366b0803571f06a5b838f02c6706fc287995 (diff)
[COMPAT] net: SIOCGIFCONF data corruption
From: Alexandra Kossovsky <Alexandra.Kossovsky@oktetlabs.ru> From http://bugzilla.kernel.org/show_bug.cgi?id=4746 There is user data corruption when using ioctl(SIOCGIFCONF) in 32-bit application running amd64 kernel. I do not think that this problem is exploitable, but any data corruption may lead to security problems. Following code demonstrates the problem #include <stdint.h> #include <stdio.h> #include <sys/time.h> #include <sys/socket.h> #include <net/if.h> #include <sys/ioctl.h> char buf[256]; main() { int s = socket(AF_INET, SOCK_DGRAM, 0); struct ifconf req; int i; req.ifc_buf = buf; req.ifc_len = 41; printf("Result %d\n", ioctl(s, SIOCGIFCONF, &req)); printf("Len %d\n", req.ifc_len); for (i = 41; i < 256; i++) if (buf[i] != 0) printf("Byte %d is corrupted\n", i); } Steps to reproduce: Compile the code above into 32-bit elf and run it. You'll get Result 0 Len 32 Byte 48 is corrupted Byte 52 is corrupted Byte 53 is corrupted Byte 54 is corrupted Byte 55 is corrupted Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv6')
0 files changed, 0 insertions, 0 deletions