| Message ID | 20170303172330.83421-1-glider@google.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
On Fri, Mar 3, 2017 at 6:23 PM, Alexander Potapenko <glider@google.com> wrote: > KMSAN (KernelMemorySanitizer, a new error detection tool) reports use of > uninitialized memory in packet_bind_spkt(): Should be "in selinux_socket_bind()", will fix in the next patch version. > ================================================================== > BUG: KMSAN: use of unitialized memory > inter: 0 > CPU: 3 PID: 1074 Comm: packet2 Tainted: G B 4.8.0-rc6+ #1916 > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 > 0000000000000000 ffff8800882ffb08 ffffffff825759c8 ffff8800882ffa48 > ffffffff818bf551 ffffffff85bab870 0000000000000092 ffffffff85bab550 > 0000000000000000 0000000000000092 00000000bb0009bb 0000000000000002 > Call Trace: > [< inline >] __dump_stack lib/dump_stack.c:15 > [<ffffffff825759c8>] dump_stack+0x238/0x290 lib/dump_stack.c:51 > [<ffffffff818bdee6>] kmsan_report+0x276/0x2e0 mm/kmsan/kmsan.c:1008 > [<ffffffff818bf0fb>] __msan_warning+0x5b/0xb0 mm/kmsan/kmsan_instr.c:424 > [<ffffffff822dae71>] selinux_socket_bind+0xf41/0x1080 security/selinux/hooks.c:4288 > [<ffffffff8229357c>] security_socket_bind+0x1ec/0x240 security/security.c:1240 > [<ffffffff84265d98>] SYSC_bind+0x358/0x5f0 net/socket.c:1366 > [<ffffffff84265a22>] SyS_bind+0x82/0xa0 net/socket.c:1356 > [<ffffffff81005678>] do_syscall_64+0x58/0x70 arch/x86/entry/common.c:292 > [<ffffffff8518217c>] entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.o:? > chained origin: 00000000ba6009bb > [<ffffffff810bb7a7>] save_stack_trace+0x27/0x50 arch/x86/kernel/stacktrace.c:67 > [< inline >] kmsan_save_stack_with_flags mm/kmsan/kmsan.c:322 > [< inline >] kmsan_save_stack mm/kmsan/kmsan.c:337 > [<ffffffff818bd2b8>] kmsan_internal_chain_origin+0x118/0x1e0 mm/kmsan/kmsan.c:530 > [<ffffffff818bf033>] __msan_set_alloca_origin4+0xc3/0x130 mm/kmsan/kmsan_instr.c:380 > [<ffffffff84265b69>] SYSC_bind+0x129/0x5f0 net/socket.c:1356 > [<ffffffff84265a22>] SyS_bind+0x82/0xa0 net/socket.c:1356 > [<ffffffff81005678>] do_syscall_64+0x58/0x70 arch/x86/entry/common.c:292 > [<ffffffff8518217c>] return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.o:? > origin description: ----address@SYSC_bind (origin=00000000b8c00900) > ================================================================== > > (the line numbers are relative to 4.8-rc6, but the bug persists upstream) > > , when I run the following program as root: > > ======================================================= > #include <string.h> > #include <sys/socket.h> > #include <netinet/in.h> > > int main(int argc, char *argv[]) { > struct sockaddr addr; > int size = 0; > if (argc > 1) { > size = atoi(argv[1]); > } > memset(&addr, 0, sizeof(addr)); > int fd = socket(PF_INET6, SOCK_DGRAM, IPPROTO_IP); > bind(fd, &addr, size); > return 0; > } > ======================================================= > > (for different values of |size| other error reports are printed). > > This happens because bind() unconditionally copies |size| bytes of > |addr| to the kernel, leaving the rest uninitialized. Then > security_socket_bind() reads the IP address bytes, including the > uninitialized ones, to determine the port, or e.g. pass them further to > sel_netnode_find(), which uses them to calculate a hash. > > Signed-off-by: Alexander Potapenko <glider@google.com> > --- > security/selinux/hooks.c | 9 +++++++++ > 1 file changed, 9 insertions(+) > > diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c > index 0a4b4b040e0a..eba54489b11b 100644 > --- a/security/selinux/hooks.c > +++ b/security/selinux/hooks.c > @@ -4351,10 +4351,19 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in > u32 sid, node_perm; > > if (family == PF_INET) { > + if (addrlen != sizeof(struct sockaddr_in)) { > + err = -EINVAL; > + goto out; > + } > addr4 = (struct sockaddr_in *)address; > snum = ntohs(addr4->sin_port); > addrp = (char *)&addr4->sin_addr.s_addr; > + > } else { > + if (addrlen != sizeof(struct sockaddr_in6)) { > + err = -EINVAL; > + goto out; > + } > addr6 = (struct sockaddr_in6 *)address; > snum = ntohs(addr6->sin6_port); > addrp = (char *)&addr6->sin6_addr.s6_addr; > -- > 2.12.0.rc1.440.g5b76565f74-goog >
On Fri, Mar 3, 2017 at 9:23 AM, Alexander Potapenko <glider@google.com> wrote: > This happens because bind() unconditionally copies |size| bytes of > |addr| to the kernel, leaving the rest uninitialized. Then > security_socket_bind() reads the IP address bytes, including the > uninitialized ones, to determine the port, or e.g. pass them further to > sel_netnode_find(), which uses them to calculate a hash. > > Signed-off-by: Alexander Potapenko <glider@google.com> > --- > security/selinux/hooks.c | 9 +++++++++ > 1 file changed, 9 insertions(+) > > diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c > index 0a4b4b040e0a..eba54489b11b 100644 > --- a/security/selinux/hooks.c > +++ b/security/selinux/hooks.c > @@ -4351,10 +4351,19 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in > u32 sid, node_perm; > > if (family == PF_INET) { > + if (addrlen != sizeof(struct sockaddr_in)) { Please take a look at inet_bind() The correct test would be : if (addrlen < sizeof(struct sockaddr_in)) err = -EINVAL; ... > + err = -EINVAL; > + goto out; > + } > addr4 = (struct sockaddr_in *)address; > snum = ntohs(addr4->sin_port); > addrp = (char *)&addr4->sin_addr.s_addr; > + > } else { > + if (addrlen != sizeof(struct sockaddr_in6)) { Look at inet6_bind() if (addrlen < SIN6_LEN_RFC2133) > + err = -EINVAL; > + goto out; > + } > addr6 = (struct sockaddr_in6 *)address; > snum = ntohs(addr6->sin6_port); > addrp = (char *)&addr6->sin6_addr.s6_addr; > -- > 2.12.0.rc1.440.g5b76565f74-goog >
==================================================================
BUG: KMSAN: use of unitialized memory
inter: 0
CPU: 3 PID: 1074 Comm: packet2 Tainted: G B 4.8.0-rc6+ #1916
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
0000000000000000 ffff8800882ffb08 ffffffff825759c8 ffff8800882ffa48
ffffffff818bf551 ffffffff85bab870 0000000000000092 ffffffff85bab550
0000000000000000 0000000000000092 00000000bb0009bb 0000000000000002
Call Trace:
[< inline >] __dump_stack lib/dump_stack.c:15
[<ffffffff825759c8>] dump_stack+0x238/0x290 lib/dump_stack.c:51
[<ffffffff818bdee6>] kmsan_report+0x276/0x2e0 mm/kmsan/kmsan.c:1008
[<ffffffff818bf0fb>] __msan_warning+0x5b/0xb0 mm/kmsan/kmsan_instr.c:424
[<ffffffff822dae71>] selinux_socket_bind+0xf41/0x1080 security/selinux/hooks.c:4288
[<ffffffff8229357c>] security_socket_bind+0x1ec/0x240 security/security.c:1240
[<ffffffff84265d98>] SYSC_bind+0x358/0x5f0 net/socket.c:1366
[<ffffffff84265a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
[<ffffffff81005678>] do_syscall_64+0x58/0x70 arch/x86/entry/common.c:292
[<ffffffff8518217c>] entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.o:?
chained origin: 00000000ba6009bb
[<ffffffff810bb7a7>] save_stack_trace+0x27/0x50 arch/x86/kernel/stacktrace.c:67
[< inline >] kmsan_save_stack_with_flags mm/kmsan/kmsan.c:322
[< inline >] kmsan_save_stack mm/kmsan/kmsan.c:337
[<ffffffff818bd2b8>] kmsan_internal_chain_origin+0x118/0x1e0 mm/kmsan/kmsan.c:530
[<ffffffff818bf033>] __msan_set_alloca_origin4+0xc3/0x130 mm/kmsan/kmsan_instr.c:380
[<ffffffff84265b69>] SYSC_bind+0x129/0x5f0 net/socket.c:1356
[<ffffffff84265a22>] SyS_bind+0x82/0xa0 net/socket.c:1356
[<ffffffff81005678>] do_syscall_64+0x58/0x70 arch/x86/entry/common.c:292
[<ffffffff8518217c>] return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.o:?
origin description: ----address@SYSC_bind (origin=00000000b8c00900)
==================================================================
(the line numbers are relative to 4.8-rc6, but the bug persists upstream)
, when I run the following program as root:
=======================================================
#include <string.h>
#include <sys/socket.h>
#include <netinet/in.h>
int main(int argc, char *argv[]) {
struct sockaddr addr;
int size = 0;
if (argc > 1) {
size = atoi(argv[1]);
}
memset(&addr, 0, sizeof(addr));
int fd = socket(PF_INET6, SOCK_DGRAM, IPPROTO_IP);
bind(fd, &addr, size);
return 0;
}
=======================================================
(for different values of |size| other error reports are printed).
This happens because bind() unconditionally copies |size| bytes of
|addr| to the kernel, leaving the rest uninitialized. Then
security_socket_bind() reads the IP address bytes, including the
uninitialized ones, to determine the port, or e.g. pass them further to
sel_netnode_find(), which uses them to calculate a hash.
Signed-off-by: Alexander Potapenko <glider@google.com>
---
security/selinux/hooks.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 0a4b4b040e0a..eba54489b11b 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4351,10 +4351,19 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
u32 sid, node_perm;
if (family == PF_INET) {
+ if (addrlen != sizeof(struct sockaddr_in)) {
+ err = -EINVAL;
+ goto out;
+ }
addr4 = (struct sockaddr_in *)address;
snum = ntohs(addr4->sin_port);
addrp = (char *)&addr4->sin_addr.s_addr;
+
} else {
+ if (addrlen != sizeof(struct sockaddr_in6)) {
+ err = -EINVAL;
+ goto out;
+ }
addr6 = (struct sockaddr_in6 *)address;
snum = ntohs(addr6->sin6_port);
addrp = (char *)&addr6->sin6_addr.s6_addr;