WSL2-Linux-Kernel/net/dccp/ipv4.c

1087 строки
28 KiB
C
Исходник Обычный вид История

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/dccp/ipv4.c
*
* An implementation of the DCCP protocol
* Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*/
#include <linux/dccp.h>
#include <linux/icmp.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/random.h>
#include <net/icmp.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/inet_sock.h>
#include <net/protocol.h>
#include <net/sock.h>
#include <net/timewait_sock.h>
#include <net/tcp_states.h>
#include <net/xfrm.h>
#include <net/secure_seq.h>
#include <net/netns/generic.h>
#include "ackvec.h"
#include "ccid.h"
#include "dccp.h"
#include "feat.h"
struct dccp_v4_pernet {
struct sock *v4_ctl_sk;
};
static unsigned int dccp_v4_pernet_id __read_mostly;
/*
* The per-net v4_ctl_sk socket is used for responding to
* the Out-of-the-blue (OOTB) packets. A control sock will be created
* for this socket at the initialization time.
*/
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
__be16 orig_sport, orig_dport;
__be32 daddr, nexthop;
struct flowi4 *fl4;
struct rtable *rt;
int err;
struct ip_options_rcu *inet_opt;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
inet_opt = rcu_dereference_protected(inet->inet_opt,
lockdep_sock_is_held(sk));
if (inet_opt != NULL && inet_opt->opt.srr) {
if (daddr == 0)
return -EINVAL;
nexthop = inet_opt->opt.faddr;
}
orig_sport = inet->inet_sport;
orig_dport = usin->sin_port;
fl4 = &inet->cork.fl.u.ip4;
rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
ipv4: Avoid using RTO_ONLINK with ip_route_connect(). Now that ip_rt_fix_tos() doesn't reset ->flowi4_scope unconditionally, we don't have to rely on the RTO_ONLINK bit to properly set the scope of a flowi4 structure. We can just set ->flowi4_scope explicitly and avoid using RTO_ONLINK in ->flowi4_tos. This patch converts callers of ip_route_connect(). Instead of setting the tos parameter with RT_CONN_FLAGS(sk), as all callers do, we can: 1- Drop the tos parameter from ip_route_connect(): its value was entirely based on sk, which is also passed as parameter. 2- Set ->flowi4_scope depending on the SOCK_LOCALROUTE socket option instead of always initialising it with RT_SCOPE_UNIVERSE (let's define ip_sock_rt_scope() for this purpose). 3- Avoid overloading ->flowi4_tos with RTO_ONLINK: since the scope is now properly initialised, we don't need to tell ip_rt_fix_tos() to adjust ->flowi4_scope for us. So let's define ip_sock_rt_tos(), which is the same as RT_CONN_FLAGS() but without the RTO_ONLINK bit overload. Note: In the original ip_route_connect() code, __ip_route_output_key() might clear the RTO_ONLINK bit of fl4->flowi4_tos (because of ip_rt_fix_tos()). Therefore flowi4_update_output() had to reuse the original tos variable. Now that we don't set RTO_ONLINK any more, this is not a problem and we can use fl4->flowi4_tos in flowi4_update_output(). Signed-off-by: Guillaume Nault <gnault@redhat.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-04-21 02:21:33 +03:00
sk->sk_bound_dev_if, IPPROTO_DCCP, orig_sport,
orig_dport, sk);
if (IS_ERR(rt))
return PTR_ERR(rt);
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (inet_opt == NULL || !inet_opt->opt.srr)
daddr = fl4->daddr;
if (inet->inet_saddr == 0)
inet->inet_saddr = fl4->saddr;
sk_rcv_saddr_set(sk, inet->inet_saddr);
inet->inet_dport = usin->sin_port;
sk_daddr_set(sk, daddr);
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet_opt)
inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
/*
* Socket identity is still unknown (sport may be zero).
* However we set state to DCCP_REQUESTING and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
dccp_set_state(sk, DCCP_REQUESTING);
err = inet_hash_connect(&dccp_death_row, sk);
if (err != 0)
goto failure;
rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
inet->inet_sport, inet->inet_dport, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
goto failure;
}
/* OK, now commit destination to socket. */
sk_setup_caps(sk, &rt->dst);
dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr,
inet->inet_daddr,
inet->inet_sport,
inet->inet_dport);
inet->inet_id = prandom_u32();
err = dccp_connect(sk);
rt = NULL;
if (err != 0)
goto failure;
out:
return err;
failure:
/*
* This unhashes the socket and releases the local port, if necessary.
*/
dccp_set_state(sk, DCCP_CLOSED);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
goto out;
}
EXPORT_SYMBOL_GPL(dccp_v4_connect);
/*
* This routine does path mtu discovery as defined in RFC1191.
*/
static inline void dccp_do_pmtu_discovery(struct sock *sk,
const struct iphdr *iph,
u32 mtu)
{
struct dst_entry *dst;
const struct inet_sock *inet = inet_sk(sk);
const struct dccp_sock *dp = dccp_sk(sk);
/* We are not interested in DCCP_LISTEN and request_socks (RESPONSEs
* send out by Linux are always < 576bytes so they should go through
* unfragmented).
*/
if (sk->sk_state == DCCP_LISTEN)
return;
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
/* Something is about to be wrong... Remember soft error
* for the case, if this connection will not able to recover.
*/
if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
sk->sk_err_soft = EMSGSIZE;
mtu = dst_mtu(dst);
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
ipv4: introduce new IP_MTU_DISCOVER mode IP_PMTUDISC_INTERFACE Sockets marked with IP_PMTUDISC_INTERFACE won't do path mtu discovery, their sockets won't accept and install new path mtu information and they will always use the interface mtu for outgoing packets. It is guaranteed that the packet is not fragmented locally. But we won't set the DF-Flag on the outgoing frames. Florian Weimer had the idea to use this flag to ensure DNS servers are never generating outgoing fragments. They may well be fragmented on the path, but the server never stores or usees path mtu values, which could well be forged in an attack. (The root of the problem with path MTU discovery is that there is no reliable way to authenticate ICMP Fragmentation Needed But DF Set messages because they are sent from intermediate routers with their source addresses, and the IMCP payload will not always contain sufficient information to identify a flow.) Recent research in the DNS community showed that it is possible to implement an attack where DNS cache poisoning is feasible by spoofing fragments. This work was done by Amir Herzberg and Haya Shulman: <https://sites.google.com/site/hayashulman/files/fragmentation-poisoning.pdf> This issue was previously discussed among the DNS community, e.g. <http://www.ietf.org/mail-archive/web/dnsext/current/msg01204.html>, without leading to fixes. This patch depends on the patch "ipv4: fix DO and PROBE pmtu mode regarding local fragmentation with UFO/CORK" for the enforcement of the non-fragmentable checks. If other users than ip_append_page/data should use this semantic too, we have to add a new flag to IPCB(skb)->flags to suppress local fragmentation and check for this in ip_finish_output. Many thanks to Florian Weimer for the idea and feedback while implementing this patch. Cc: David S. Miller <davem@davemloft.net> Suggested-by: Florian Weimer <fweimer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-05 05:24:17 +04:00
ip_sk_accept_pmtu(sk) &&
inet_csk(sk)->icsk_pmtu_cookie > mtu) {
dccp_sync_mss(sk, mtu);
/*
* From RFC 4340, sec. 14.1:
*
* DCCP-Sync packets are the best choice for upward
* probing, since DCCP-Sync probes do not risk application
* data loss.
*/
dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
} /* else let the usual retransmit timer handle it */
}
static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk)
{
struct dst_entry *dst = __sk_dst_check(sk, 0);
if (dst)
dst->ops->redirect(dst, sk, skb);
}
void dccp_req_err(struct sock *sk, u64 seq)
{
struct request_sock *req = inet_reqsk(sk);
struct net *net = sock_net(sk);
/*
* ICMPs are not backlogged, hence we cannot get an established
* socket here.
*/
if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) {
__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
} else {
/*
* Still in RESPOND, just remove it silently.
* There is no good way to pass the error to the newly
* created socket, and POSIX does not want network
* errors returned from accept().
*/
inet_csk_reqsk_queue_drop(req->rsk_listener, req);
}
reqsk_put(req);
}
EXPORT_SYMBOL(dccp_req_err);
/*
* This routine is called by the ICMP module when it gets some sort of error
* condition. If err < 0 then the socket should be closed and the error
* returned to the user. If err > 0 it's just the icmp type << 8 | icmp code.
* After adjustment header points to the first 8 bytes of the tcp header. We
* need to find the appropriate port.
*
* The locking strategy used here is very "optimistic". When someone else
* accesses the socket the ICMP is just dropped and for some paths there is no
* check at all. A more general error queue to queue errors for later handling
* is probably better.
*/
static int dccp_v4_err(struct sk_buff *skb, u32 info)
{
const struct iphdr *iph = (struct iphdr *)skb->data;
const u8 offset = iph->ihl << 2;
const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct inet_sock *inet;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct sock *sk;
__u64 seq;
int err;
struct net *net = dev_net(skb->dev);
/* Only need dccph_dport & dccph_sport which are the first
* 4 bytes in dccp header.
* Our caller (icmp_socket_deliver()) already pulled 8 bytes for us.
*/
BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8);
BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
dh = (struct dccp_hdr *)(skb->data + offset);
sk = __inet_lookup_established(net, &dccp_hashinfo,
iph->daddr, dh->dccph_dport,
iph->saddr, ntohs(dh->dccph_sport),
inet_iif(skb), 0);
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
return -ENOENT;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return 0;
}
seq = dccp_hdr_seq(dh);
if (sk->sk_state == DCCP_NEW_SYN_RECV) {
dccp_req_err(sk, seq);
return 0;
}
bh_lock_sock(sk);
/* If too many ICMPs get dropped on busy
* servers this needs to be solved differently.
*/
if (sock_owned_by_user(sk))
__NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == DCCP_CLOSED)
goto out;
dp = dccp_sk(sk);
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
!between48(seq, dp->dccps_awl, dp->dccps_awh)) {
__NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
switch (type) {
case ICMP_REDIRECT:
dccp/tcp: fix routing redirect race As Eric Dumazet pointed out this also needs to be fixed in IPv6. v2: Contains the IPv6 tcp/Ipv6 dccp patches as well. We have seen a few incidents lately where a dst_enty has been freed with a dangling TCP socket reference (sk->sk_dst_cache) pointing to that dst_entry. If the conditions/timings are right a crash then ensues when the freed dst_entry is referenced later on. A Common crashing back trace is: #8 [] page_fault at ffffffff8163e648 [exception RIP: __tcp_ack_snd_check+74] . . #9 [] tcp_rcv_established at ffffffff81580b64 #10 [] tcp_v4_do_rcv at ffffffff8158b54a #11 [] tcp_v4_rcv at ffffffff8158cd02 #12 [] ip_local_deliver_finish at ffffffff815668f4 #13 [] ip_local_deliver at ffffffff81566bd9 #14 [] ip_rcv_finish at ffffffff8156656d #15 [] ip_rcv at ffffffff81566f06 #16 [] __netif_receive_skb_core at ffffffff8152b3a2 #17 [] __netif_receive_skb at ffffffff8152b608 #18 [] netif_receive_skb at ffffffff8152b690 #19 [] vmxnet3_rq_rx_complete at ffffffffa015eeaf [vmxnet3] #20 [] vmxnet3_poll_rx_only at ffffffffa015f32a [vmxnet3] #21 [] net_rx_action at ffffffff8152bac2 #22 [] __do_softirq at ffffffff81084b4f #23 [] call_softirq at ffffffff8164845c #24 [] do_softirq at ffffffff81016fc5 #25 [] irq_exit at ffffffff81084ee5 #26 [] do_IRQ at ffffffff81648ff8 Of course it may happen with other NIC drivers as well. It's found the freed dst_entry here: 224 static bool tcp_in_quickack_mode(struct sock *sk)↩ 225 {↩ 226 ▹ const struct inet_connection_sock *icsk = inet_csk(sk);↩ 227 ▹ const struct dst_entry *dst = __sk_dst_get(sk);↩ 228 ↩ 229 ▹ return (dst && dst_metric(dst, RTAX_QUICKACK)) ||↩ 230 ▹ ▹ (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong);↩ 231 }↩ But there are other backtraces attributed to the same freed dst_entry in netfilter code as well. All the vmcores showed 2 significant clues: - Remote hosts behind the default gateway had always been redirected to a different gateway. A rtable/dst_entry will be added for that host. Making more dst_entrys with lower reference counts. Making this more probable. - All vmcores showed a postitive LockDroppedIcmps value, e.g: LockDroppedIcmps 267 A closer look at the tcp_v4_err() handler revealed that do_redirect() will run regardless of whether user space has the socket locked. This can result in a race condition where the same dst_entry cached in sk->sk_dst_entry can be decremented twice for the same socket via: do_redirect()->__sk_dst_check()-> dst_release(). Which leads to the dst_entry being prematurely freed with another socket pointing to it via sk->sk_dst_cache and a subsequent crash. To fix this skip do_redirect() if usespace has the socket locked. Instead let the redirect take place later when user space does not have the socket locked. The dccp/IPv6 code is very similar in this respect, so fixing it there too. As Eric Garver pointed out the following commit now invalidates routes. Which can set the dst->obsolete flag so that ipv4_dst_check() returns null and triggers the dst_release(). Fixes: ceb3320610d6 ("ipv4: Kill routes during PMTU/redirect updates.") Cc: Eric Garver <egarver@redhat.com> Cc: Hannes Sowa <hsowa@redhat.com> Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-10 08:40:33 +03:00
if (!sock_owned_by_user(sk))
dccp_do_redirect(skb, sk);
goto out;
case ICMP_SOURCE_QUENCH:
/* Just silently ignore these. */
goto out;
case ICMP_PARAMETERPROB:
err = EPROTO;
break;
case ICMP_DEST_UNREACH:
if (code > NR_ICMP_UNREACH)
goto out;
if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
if (!sock_owned_by_user(sk))
dccp_do_pmtu_discovery(sk, iph, info);
goto out;
}
err = icmp_err_convert[code].errno;
break;
case ICMP_TIME_EXCEEDED:
err = EHOSTUNREACH;
break;
default:
goto out;
}
switch (sk->sk_state) {
case DCCP_REQUESTING:
case DCCP_RESPOND:
if (!sock_owned_by_user(sk)) {
__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
sk_error_report(sk);
dccp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
/* If we've already connected we will keep trying
* until we time out, or the user gives up.
*
* rfc1122 4.2.3.9 allows to consider as hard errors
* only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too,
* but it is obsoleted by pmtu discovery).
*
* Note, that in modern internet, where routing is unreliable
* and in each dark corner broken firewalls sit, sending random
* errors ordered by their masters even this two messages finally lose
* their original sense (even Linux sends invalid PORT_UNREACHs)
*
* Now we are in compliance with RFCs.
* --ANK (980905)
*/
inet = inet_sk(sk);
if (!sock_owned_by_user(sk) && inet->recverr) {
sk->sk_err = err;
sk_error_report(sk);
} else /* Only an error on timeout */
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
return 0;
}
static inline __sum16 dccp_v4_csum_finish(struct sk_buff *skb,
__be32 src, __be32 dst)
{
return csum_tcpudp_magic(src, dst, skb->len, IPPROTO_DCCP, skb->csum);
}
void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb)
{
const struct inet_sock *inet = inet_sk(sk);
struct dccp_hdr *dh = dccp_hdr(skb);
dccp_csum_outgoing(skb);
dh->dccph_checksum = dccp_v4_csum_finish(skb,
inet->inet_saddr,
inet->inet_daddr);
}
EXPORT_SYMBOL_GPL(dccp_v4_send_check);
static inline u64 dccp_v4_init_sequence(const struct sk_buff *skb)
{
return secure_dccp_sequence_number(ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr,
dccp_hdr(skb)->dccph_dport,
dccp_hdr(skb)->dccph_sport);
}
/*
* The three way handshake has completed - we got a valid ACK or DATAACK -
* now create the new socket.
*
* This is the equivalent of TCP's tcp_v4_syn_recv_sock
*/
struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
struct request_sock *req_unhash,
bool *own_req)
{
struct inet_request_sock *ireq;
struct inet_sock *newinet;
struct sock *newsk;
if (sk_acceptq_is_full(sk))
goto exit_overflow;
newsk = dccp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
goto exit_nonewsk;
newinet = inet_sk(newsk);
ireq = inet_rsk(req);
sk_daddr_set(newsk, ireq->ir_rmt_addr);
sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
newinet->inet_saddr = ireq->ir_loc_addr;
tcp/dccp: fix ireq->opt races syzkaller found another bug in DCCP/TCP stacks [1] For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix ireq->pktopts race"), we need to make sure we do not access ireq->opt unless we own the request sock. Note the opt field is renamed to ireq_opt to ease grep games. [1] BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295 CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x25b/0x340 mm/kasan/report.c:409 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427 ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135 tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557 __tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072 tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline] tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071 tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816 tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe RIP: 0033:0x40c341 RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341 RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015 RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000 R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1 R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000 Allocated by task 3295: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 __do_kmalloc mm/slab.c:3725 [inline] __kmalloc+0x162/0x760 mm/slab.c:3734 kmalloc include/linux/slab.h:498 [inline] tcp_v4_save_options include/net/tcp.h:1962 [inline] tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271 tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283 tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313 tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857 tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482 tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3306: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kfree+0xca/0x250 mm/slab.c:3820 inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157 __sk_destruct+0xfd/0x910 net/core/sock.c:1560 sk_destruct+0x47/0x80 net/core/sock.c:1595 __sk_free+0x57/0x230 net/core/sock.c:1603 sk_free+0x2a/0x40 net/core/sock.c:1614 sock_put include/net/sock.h:1652 [inline] inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959 tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765 tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-20 19:04:13 +03:00
RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = ip_hdr(skb)->ttl;
newinet->inet_id = prandom_u32();
if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL)
goto put_and_exit;
sk_setup_caps(newsk, dst);
dccp_sync_mss(newsk, dst_mtu(dst));
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
tcp/dccp: fix ireq->opt races syzkaller found another bug in DCCP/TCP stacks [1] For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix ireq->pktopts race"), we need to make sure we do not access ireq->opt unless we own the request sock. Note the opt field is renamed to ireq_opt to ease grep games. [1] BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295 CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x25b/0x340 mm/kasan/report.c:409 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427 ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135 tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557 __tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072 tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline] tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071 tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816 tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe RIP: 0033:0x40c341 RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341 RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015 RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000 R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1 R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000 Allocated by task 3295: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 __do_kmalloc mm/slab.c:3725 [inline] __kmalloc+0x162/0x760 mm/slab.c:3734 kmalloc include/linux/slab.h:498 [inline] tcp_v4_save_options include/net/tcp.h:1962 [inline] tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271 tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283 tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313 tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857 tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482 tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3306: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kfree+0xca/0x250 mm/slab.c:3820 inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157 __sk_destruct+0xfd/0x910 net/core/sock.c:1560 sk_destruct+0x47/0x80 net/core/sock.c:1595 __sk_free+0x57/0x230 net/core/sock.c:1603 sk_free+0x2a/0x40 net/core/sock.c:1614 sock_put include/net/sock.h:1652 [inline] inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959 tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765 tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-20 19:04:13 +03:00
if (*own_req)
ireq->ireq_opt = NULL;
else
newinet->inet_opt = NULL;
return newsk;
exit_overflow:
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
exit_nonewsk:
dst_release(dst);
exit:
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL;
put_and_exit:
tcp/dccp: fix ireq->opt races syzkaller found another bug in DCCP/TCP stacks [1] For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix ireq->pktopts race"), we need to make sure we do not access ireq->opt unless we own the request sock. Note the opt field is renamed to ireq_opt to ease grep games. [1] BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295 CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x25b/0x340 mm/kasan/report.c:409 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427 ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135 tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557 __tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072 tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline] tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071 tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816 tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe RIP: 0033:0x40c341 RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341 RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015 RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000 R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1 R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000 Allocated by task 3295: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 __do_kmalloc mm/slab.c:3725 [inline] __kmalloc+0x162/0x760 mm/slab.c:3734 kmalloc include/linux/slab.h:498 [inline] tcp_v4_save_options include/net/tcp.h:1962 [inline] tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271 tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283 tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313 tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857 tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482 tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3306: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kfree+0xca/0x250 mm/slab.c:3820 inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157 __sk_destruct+0xfd/0x910 net/core/sock.c:1560 sk_destruct+0x47/0x80 net/core/sock.c:1595 __sk_free+0x57/0x230 net/core/sock.c:1603 sk_free+0x2a/0x40 net/core/sock.c:1614 sock_put include/net/sock.h:1652 [inline] inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959 tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765 tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-20 19:04:13 +03:00
newinet->inet_opt = NULL;
inet: Fix kmemleak in tcp_v4/6_syn_recv_sock and dccp_v4/6_request_recv_sock If in either of the above functions inet_csk_route_child_sock() or __inet_inherit_port() fails, the newsk will not be freed: unreferenced object 0xffff88022e8a92c0 (size 1592): comm "softirq", pid 0, jiffies 4294946244 (age 726.160s) hex dump (first 32 bytes): 0a 01 01 01 0a 01 01 02 00 00 00 00 a7 cc 16 00 ................ 02 00 03 01 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff8153d190>] kmemleak_alloc+0x21/0x3e [<ffffffff810ab3e7>] kmem_cache_alloc+0xb5/0xc5 [<ffffffff8149b65b>] sk_prot_alloc.isra.53+0x2b/0xcd [<ffffffff8149b784>] sk_clone_lock+0x16/0x21e [<ffffffff814d711a>] inet_csk_clone_lock+0x10/0x7b [<ffffffff814ebbc3>] tcp_create_openreq_child+0x21/0x481 [<ffffffff814e8fa5>] tcp_v4_syn_recv_sock+0x3a/0x23b [<ffffffff814ec5ba>] tcp_check_req+0x29f/0x416 [<ffffffff814e8e10>] tcp_v4_do_rcv+0x161/0x2bc [<ffffffff814eb917>] tcp_v4_rcv+0x6c9/0x701 [<ffffffff814cea9f>] ip_local_deliver_finish+0x70/0xc4 [<ffffffff814cec20>] ip_local_deliver+0x4e/0x7f [<ffffffff814ce9f8>] ip_rcv_finish+0x1fc/0x233 [<ffffffff814cee68>] ip_rcv+0x217/0x267 [<ffffffff814a7bbe>] __netif_receive_skb+0x49e/0x553 [<ffffffff814a7cc3>] netif_receive_skb+0x50/0x82 This happens, because sk_clone_lock initializes sk_refcnt to 2, and thus a single sock_put() is not enough to free the memory. Additionally, things like xfrm, memcg, cookie_values,... may have been initialized. We have to free them properly. This is fixed by forcing a call to tcp_done(), ending up in inet_csk_destroy_sock, doing the final sock_put(). tcp_done() is necessary, because it ends up doing all the cleanup on xfrm, memcg, cookie_values, xfrm,... Before calling tcp_done, we have to set the socket to SOCK_DEAD, to force it entering inet_csk_destroy_sock. To avoid the warning in inet_csk_destroy_sock, inet_num has to be set to 0. As inet_csk_destroy_sock does a dec on orphan_count, we first have to increase it. Calling tcp_done() allows us to remove the calls to tcp_clear_xmit_timer() and tcp_cleanup_congestion_control(). A similar approach is taken for dccp by calling dccp_done(). This is in the kernel since 093d282321 (tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()), thus since version >= 2.6.37. Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-14 08:07:58 +04:00
inet_csk_prepare_forced_close(newsk);
dccp_done(newsk);
goto exit;
}
EXPORT_SYMBOL_GPL(dccp_v4_request_recv_sock);
static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct rtable *rt;
const struct iphdr *iph = ip_hdr(skb);
struct flowi4 fl4 = {
.flowi4_oif = inet_iif(skb),
.daddr = iph->saddr,
.saddr = iph->daddr,
.flowi4_tos = RT_CONN_FLAGS(sk),
.flowi4_proto = sk->sk_protocol,
.fl4_sport = dccp_hdr(skb)->dccph_dport,
.fl4_dport = dccp_hdr(skb)->dccph_sport,
};
security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
if (IS_ERR(rt)) {
IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
return &rt->dst;
}
static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req)
{
int err = -1;
struct sk_buff *skb;
struct dst_entry *dst;
struct flowi4 fl4;
dst = inet_csk_route_req(sk, &fl4, req);
if (dst == NULL)
goto out;
skb = dccp_make_response(sk, dst, req);
if (skb != NULL) {
const struct inet_request_sock *ireq = inet_rsk(req);
struct dccp_hdr *dh = dccp_hdr(skb);
dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr,
ireq->ir_rmt_addr);
rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
rcu_dereference(ireq->ireq_opt),
inet_sk(sk)->tos);
rcu_read_unlock();
err = net_xmit_eval(err);
}
out:
dst_release(dst);
return err;
}
static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
{
int err;
const struct iphdr *rxiph;
struct sk_buff *skb;
struct dst_entry *dst;
struct net *net = dev_net(skb_dst(rxskb)->dev);
struct dccp_v4_pernet *pn;
struct sock *ctl_sk;
/* Never send a reset in response to a reset. */
if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET)
return;
if (skb_rtable(rxskb)->rt_type != RTN_LOCAL)
return;
pn = net_generic(net, dccp_v4_pernet_id);
ctl_sk = pn->v4_ctl_sk;
dst = dccp_v4_route_skb(net, ctl_sk, rxskb);
if (dst == NULL)
return;
skb = dccp_ctl_make_reset(ctl_sk, rxskb);
if (skb == NULL)
goto out;
rxiph = ip_hdr(rxskb);
dccp_hdr(skb)->dccph_checksum = dccp_v4_csum_finish(skb, rxiph->saddr,
rxiph->daddr);
skb_dst_set(skb, dst_clone(dst));
local_bh_disable();
bh_lock_sock(ctl_sk);
err = ip_build_and_send_pkt(skb, ctl_sk,
rxiph->daddr, rxiph->saddr, NULL,
inet_sk(ctl_sk)->tos);
bh_unlock_sock(ctl_sk);
if (net_xmit_eval(err) == 0) {
__DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
__DCCP_INC_STATS(DCCP_MIB_OUTRSTS);
}
local_bh_enable();
out:
dst_release(dst);
}
static void dccp_v4_reqsk_destructor(struct request_sock *req)
{
dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
tcp/dccp: fix ireq->opt races syzkaller found another bug in DCCP/TCP stacks [1] For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix ireq->pktopts race"), we need to make sure we do not access ireq->opt unless we own the request sock. Note the opt field is renamed to ireq_opt to ease grep games. [1] BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295 CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x25b/0x340 mm/kasan/report.c:409 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427 ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474 tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135 tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587 tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557 __tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072 tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline] tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071 tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816 tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe RIP: 0033:0x40c341 RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341 RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015 RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000 R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1 R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000 Allocated by task 3295: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 __do_kmalloc mm/slab.c:3725 [inline] __kmalloc+0x162/0x760 mm/slab.c:3734 kmalloc include/linux/slab.h:498 [inline] tcp_v4_save_options include/net/tcp.h:1962 [inline] tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271 tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283 tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313 tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857 tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482 tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3306: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kfree+0xca/0x250 mm/slab.c:3820 inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157 __sk_destruct+0xfd/0x910 net/core/sock.c:1560 sk_destruct+0x47/0x80 net/core/sock.c:1595 __sk_free+0x57/0x230 net/core/sock.c:1603 sk_free+0x2a/0x40 net/core/sock.c:1614 sock_put include/net/sock.h:1652 [inline] inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959 tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765 tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:249 [inline] ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:464 [inline] ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:249 [inline] ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514 netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587 netif_receive_skb+0xae/0x390 net/core/dev.c:4611 tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372 tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766 tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792 call_write_iter include/linux/fs.h:1770 [inline] new_sync_write fs/read_write.c:468 [inline] __vfs_write+0x68a/0x970 fs/read_write.c:481 vfs_write+0x18f/0x510 fs/read_write.c:543 SYSC_write fs/read_write.c:588 [inline] SyS_write+0xef/0x220 fs/read_write.c:580 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets") Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-20 19:04:13 +03:00
kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1));
}
void dccp_syn_ack_timeout(const struct request_sock *req)
{
}
EXPORT_SYMBOL(dccp_syn_ack_timeout);
static struct request_sock_ops dccp_request_sock_ops __read_mostly = {
.family = PF_INET,
.obj_size = sizeof(struct dccp_request_sock),
.rtx_syn_ack = dccp_v4_send_response,
.send_ack = dccp_reqsk_send_ack,
.destructor = dccp_v4_reqsk_destructor,
.send_reset = dccp_v4_ctl_send_reset,
.syn_ack_timeout = dccp_syn_ack_timeout,
};
int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct inet_request_sock *ireq;
struct request_sock *req;
struct dccp_request_sock *dreq;
const __be32 service = dccp_hdr_request(skb)->dccph_req_service;
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
/* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */
if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
[DCCP]: Twice the wrong reset code in receiving connection-Requests This fixes two bugs in processing of connection-Requests in v{4,6}_conn_request: 1. Due to using the variable `reset_code', the Reset code generated internally by dccp_parse_options() is overwritten with the initialised value ("Too Busy") of reset_code, which is not what is intended. 2. When receiving a connection-Request on a multicast or broadcast address, no Reset should be generated, to avoid storms of such packets. Instead of jumping to the `drop' label, the v{4,6}_conn_request functions now return 0. Below is why in my understanding this is correct: When the conn_request function returns < 0, then the caller, dccp_rcv_state_process(), returns 1. In all instances where dccp_rcv_state_process is called (dccp_v4_do_rcv, dccp_v6_do_rcv, and dccp_child_process), a return value of != 0 from dccp_rcv_state_process() means that a Reset is generated. If on the other hand the conn_request function returns 0, the packet is discarded and no Reset is generated. Note: There may be a related problem when sending the Response, due to the following. if (dccp_v6_send_response(sk, req, NULL)) goto drop_and_free; /* ... */ drop_and_free: return -1; In this case, if send_response fails due to transmission errors, the next thing that is generated is a Reset with a code "Too Busy". I haven't been able to conjure up such a condition, but it might be good to change the behaviour here also (not done by this patch). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-05 01:52:28 +04:00
return 0; /* discard, don't send a reset here */
if (dccp_bad_service_code(sk, service)) {
[DCCP]: Twice the wrong reset code in receiving connection-Requests This fixes two bugs in processing of connection-Requests in v{4,6}_conn_request: 1. Due to using the variable `reset_code', the Reset code generated internally by dccp_parse_options() is overwritten with the initialised value ("Too Busy") of reset_code, which is not what is intended. 2. When receiving a connection-Request on a multicast or broadcast address, no Reset should be generated, to avoid storms of such packets. Instead of jumping to the `drop' label, the v{4,6}_conn_request functions now return 0. Below is why in my understanding this is correct: When the conn_request function returns < 0, then the caller, dccp_rcv_state_process(), returns 1. In all instances where dccp_rcv_state_process is called (dccp_v4_do_rcv, dccp_v6_do_rcv, and dccp_child_process), a return value of != 0 from dccp_rcv_state_process() means that a Reset is generated. If on the other hand the conn_request function returns 0, the packet is discarded and no Reset is generated. Note: There may be a related problem when sending the Response, due to the following. if (dccp_v6_send_response(sk, req, NULL)) goto drop_and_free; /* ... */ drop_and_free: return -1; In this case, if send_response fails due to transmission errors, the next thing that is generated is a Reset with a code "Too Busy". I haven't been able to conjure up such a condition, but it might be good to change the behaviour here also (not done by this patch). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-05 01:52:28 +04:00
dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE;
goto drop;
}
/*
* TW buckets are converted to open requests without
* limitations, they conserve resources and peer is
* evidently real one.
*/
[DCCP]: Twice the wrong reset code in receiving connection-Requests This fixes two bugs in processing of connection-Requests in v{4,6}_conn_request: 1. Due to using the variable `reset_code', the Reset code generated internally by dccp_parse_options() is overwritten with the initialised value ("Too Busy") of reset_code, which is not what is intended. 2. When receiving a connection-Request on a multicast or broadcast address, no Reset should be generated, to avoid storms of such packets. Instead of jumping to the `drop' label, the v{4,6}_conn_request functions now return 0. Below is why in my understanding this is correct: When the conn_request function returns < 0, then the caller, dccp_rcv_state_process(), returns 1. In all instances where dccp_rcv_state_process is called (dccp_v4_do_rcv, dccp_v6_do_rcv, and dccp_child_process), a return value of != 0 from dccp_rcv_state_process() means that a Reset is generated. If on the other hand the conn_request function returns 0, the packet is discarded and no Reset is generated. Note: There may be a related problem when sending the Response, due to the following. if (dccp_v6_send_response(sk, req, NULL)) goto drop_and_free; /* ... */ drop_and_free: return -1; In this case, if send_response fails due to transmission errors, the next thing that is generated is a Reset with a code "Too Busy". I haven't been able to conjure up such a condition, but it might be good to change the behaviour here also (not done by this patch). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-05 01:52:28 +04:00
dcb->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
if (inet_csk_reqsk_queue_is_full(sk))
goto drop;
if (sk_acceptq_is_full(sk))
goto drop;
req = inet_reqsk_alloc(&dccp_request_sock_ops, sk, true);
if (req == NULL)
goto drop;
if (dccp_reqsk_init(req, dccp_sk(sk), skb))
goto drop_and_free;
dreq = dccp_rsk(req);
if (dccp_parse_options(sk, dreq, skb))
goto drop_and_free;
if (security_inet_conn_request(sk, skb, req))
goto drop_and_free;
ireq = inet_rsk(req);
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
dccp: initialize ireq->ir_mark syzbot reported an uninit-value read of skb->mark in iptable_mangle_hook() Thanks to the nice report, I tracked the problem to dccp not caring of ireq->ir_mark for passive sessions. BUG: KMSAN: uninit-value in ipt_mangle_out net/ipv4/netfilter/iptable_mangle.c:66 [inline] BUG: KMSAN: uninit-value in iptable_mangle_hook+0x5e5/0x720 net/ipv4/netfilter/iptable_mangle.c:84 CPU: 0 PID: 5300 Comm: syz-executor3 Not tainted 4.16.0+ #81 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 ipt_mangle_out net/ipv4/netfilter/iptable_mangle.c:66 [inline] iptable_mangle_hook+0x5e5/0x720 net/ipv4/netfilter/iptable_mangle.c:84 nf_hook_entry_hookfn include/linux/netfilter.h:120 [inline] nf_hook_slow+0x158/0x3d0 net/netfilter/core.c:483 nf_hook include/linux/netfilter.h:243 [inline] __ip_local_out net/ipv4/ip_output.c:113 [inline] ip_local_out net/ipv4/ip_output.c:122 [inline] ip_queue_xmit+0x1d21/0x21c0 net/ipv4/ip_output.c:504 dccp_transmit_skb+0x15eb/0x1900 net/dccp/output.c:142 dccp_xmit_packet+0x814/0x9e0 net/dccp/output.c:281 dccp_write_xmit+0x20f/0x480 net/dccp/output.c:363 dccp_sendmsg+0x12ca/0x12d0 net/dccp/proto.c:818 inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmsg net/socket.c:2080 [inline] SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091 SyS_sendmsg+0x54/0x80 net/socket.c:2087 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x455259 RSP: 002b:00007f1a4473dc68 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f1a4473e6d4 RCX: 0000000000455259 RDX: 0000000000000000 RSI: 0000000020b76fc8 RDI: 0000000000000015 RBP: 000000000072bea0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff R13: 00000000000004f0 R14: 00000000006fa720 R15: 0000000000000000 Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_save_stack mm/kmsan/kmsan.c:293 [inline] kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:684 __msan_chain_origin+0x69/0xc0 mm/kmsan/kmsan_instr.c:521 ip_queue_xmit+0x1e35/0x21c0 net/ipv4/ip_output.c:502 dccp_transmit_skb+0x15eb/0x1900 net/dccp/output.c:142 dccp_xmit_packet+0x814/0x9e0 net/dccp/output.c:281 dccp_write_xmit+0x20f/0x480 net/dccp/output.c:363 dccp_sendmsg+0x12ca/0x12d0 net/dccp/proto.c:818 inet_sendmsg+0x48d/0x740 net/ipv4/af_inet.c:764 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmsg net/socket.c:2080 [inline] SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091 SyS_sendmsg+0x54/0x80 net/socket.c:2087 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_save_stack mm/kmsan/kmsan.c:293 [inline] kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:684 __msan_chain_origin+0x69/0xc0 mm/kmsan/kmsan_instr.c:521 inet_csk_clone_lock+0x503/0x580 net/ipv4/inet_connection_sock.c:797 dccp_create_openreq_child+0x7f/0x890 net/dccp/minisocks.c:92 dccp_v4_request_recv_sock+0x22c/0xe90 net/dccp/ipv4.c:408 dccp_v6_request_recv_sock+0x290/0x2000 net/dccp/ipv6.c:414 dccp_check_req+0x7b9/0x8f0 net/dccp/minisocks.c:197 dccp_v4_rcv+0x12e4/0x2630 net/dccp/ipv4.c:840 ip_local_deliver_finish+0x6ed/0xd40 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:288 [inline] ip_local_deliver+0x43c/0x4e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:449 [inline] ip_rcv_finish+0x1253/0x16d0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:288 [inline] ip_rcv+0x119d/0x16f0 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x47cf/0x4a80 net/core/dev.c:4562 __netif_receive_skb net/core/dev.c:4627 [inline] process_backlog+0x62d/0xe20 net/core/dev.c:5307 napi_poll net/core/dev.c:5705 [inline] net_rx_action+0x7c1/0x1a70 net/core/dev.c:5771 __do_softirq+0x56d/0x93d kernel/softirq.c:285 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmem_cache_alloc+0xaab/0xb90 mm/slub.c:2756 reqsk_alloc include/net/request_sock.h:88 [inline] inet_reqsk_alloc+0xc4/0x7f0 net/ipv4/tcp_input.c:6145 dccp_v4_conn_request+0x5cc/0x1770 net/dccp/ipv4.c:600 dccp_v6_conn_request+0x299/0x1880 net/dccp/ipv6.c:317 dccp_rcv_state_process+0x2ea/0x2410 net/dccp/input.c:612 dccp_v4_do_rcv+0x229/0x340 net/dccp/ipv4.c:682 dccp_v6_do_rcv+0x16d/0x1220 net/dccp/ipv6.c:578 sk_backlog_rcv include/net/sock.h:908 [inline] __sk_receive_skb+0x60e/0xf20 net/core/sock.c:513 dccp_v4_rcv+0x24d4/0x2630 net/dccp/ipv4.c:874 ip_local_deliver_finish+0x6ed/0xd40 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:288 [inline] ip_local_deliver+0x43c/0x4e0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:449 [inline] ip_rcv_finish+0x1253/0x16d0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:288 [inline] ip_rcv+0x119d/0x16f0 net/ipv4/ip_input.c:493 __netif_receive_skb_core+0x47cf/0x4a80 net/core/dev.c:4562 __netif_receive_skb net/core/dev.c:4627 [inline] process_backlog+0x62d/0xe20 net/core/dev.c:5307 napi_poll net/core/dev.c:5705 [inline] net_rx_action+0x7c1/0x1a70 net/core/dev.c:5771 __do_softirq+0x56d/0x93d kernel/softirq.c:285 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-07 23:42:41 +03:00
ireq->ir_mark = inet_request_mark(sk, skb);
ireq->ireq_family = AF_INET;
ireq->ir_iif = sk->sk_bound_dev_if;
/*
* Step 3: Process LISTEN state
*
* Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie
*
* Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child().
*/
dreq->dreq_isr = dcb->dccpd_seq;
dreq->dreq_gsr = dreq->dreq_isr;
dreq->dreq_iss = dccp_v4_init_sequence(skb);
dreq->dreq_gss = dreq->dreq_iss;
dreq->dreq_service = service;
if (dccp_v4_send_response(sk, req))
goto drop_and_free;
inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
reqsk_put(req);
return 0;
drop_and_free:
reqsk_free(req);
drop:
__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
return -1;
}
EXPORT_SYMBOL_GPL(dccp_v4_conn_request);
int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
struct dccp_hdr *dh = dccp_hdr(skb);
if (sk->sk_state == DCCP_OPEN) { /* Fast path */
if (dccp_rcv_established(sk, skb, dh, skb->len))
goto reset;
return 0;
}
/*
* Step 3: Process LISTEN state
* If P.type == Request or P contains a valid Init Cookie option,
* (* Must scan the packet's options to check for Init
* Cookies. Only Init Cookies are processed here,
* however; other options are processed in Step 8. This
* scan need only be performed if the endpoint uses Init
* Cookies *)
* (* Generate a new socket and switch to that socket *)
* Set S := new socket for this port pair
* S.state = RESPOND
* Choose S.ISS (initial seqno) or set from Init Cookies
* Initialize S.GAR := S.ISS
* Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies
* Continue with S.state == RESPOND
* (* A Response packet will be generated in Step 11 *)
* Otherwise,
* Generate Reset(No Connection) unless P.type == Reset
* Drop packet and return
*
* NOTE: the check for the packet types is done in
* dccp_rcv_state_process
*/
if (dccp_rcv_state_process(sk, skb, dh, skb->len))
goto reset;
return 0;
reset:
dccp_v4_ctl_send_reset(sk, skb);
kfree_skb(skb);
return 0;
}
EXPORT_SYMBOL_GPL(dccp_v4_do_rcv);
/**
* dccp_invalid_packet - check for malformed packets
* @skb: Packet to validate
*
* Implements RFC 4340, 8.5: Step 1: Check header basics
* Packets that fail these checks are ignored and do not receive Resets.
*/
int dccp_invalid_packet(struct sk_buff *skb)
{
const struct dccp_hdr *dh;
unsigned int cscov;
u8 dccph_doff;
if (skb->pkt_type != PACKET_HOST)
return 1;
/* If the packet is shorter than 12 bytes, drop packet and return */
if (!pskb_may_pull(skb, sizeof(struct dccp_hdr))) {
DCCP_WARN("pskb_may_pull failed\n");
return 1;
}
dh = dccp_hdr(skb);
/* If P.type is not understood, drop packet and return */
if (dh->dccph_type >= DCCP_PKT_INVALID) {
DCCP_WARN("invalid packet type\n");
return 1;
}
/*
* If P.Data Offset is too small for packet type, drop packet and return
*/
dccph_doff = dh->dccph_doff;
if (dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
DCCP_WARN("P.Data Offset(%u) too small\n", dccph_doff);
return 1;
}
/*
* If P.Data Offset is too large for packet, drop packet and return
*/
if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) {
DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff);
return 1;
}
dh = dccp_hdr(skb);
/*
* If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet
* has short sequence numbers), drop packet and return
*/
if ((dh->dccph_type < DCCP_PKT_DATA ||
dh->dccph_type > DCCP_PKT_DATAACK) && dh->dccph_x == 0) {
DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n",
dccp_packet_name(dh->dccph_type));
return 1;
}
/*
* If P.CsCov is too large for the packet size, drop packet and return.
* This must come _before_ checksumming (not as RFC 4340 suggests).
*/
cscov = dccp_csum_coverage(skb);
if (cscov > skb->len) {
DCCP_WARN("P.CsCov %u exceeds packet length %d\n",
dh->dccph_cscov, skb->len);
return 1;
}
/* If header checksum is incorrect, drop packet and return.
* (This step is completed in the AF-dependent functions.) */
skb->csum = skb_checksum(skb, 0, cscov, 0);
return 0;
}
EXPORT_SYMBOL_GPL(dccp_invalid_packet);
/* this is called when real data arrives */
static int dccp_v4_rcv(struct sk_buff *skb)
{
const struct dccp_hdr *dh;
const struct iphdr *iph;
bool refcounted;
struct sock *sk;
int min_cov;
/* Step 1: Check header basics */
if (dccp_invalid_packet(skb))
goto discard_it;
iph = ip_hdr(skb);
/* Step 1: If header checksum is incorrect, drop packet and return */
if (dccp_v4_csum_finish(skb, iph->saddr, iph->daddr)) {
DCCP_WARN("dropped packet with invalid checksum\n");
goto discard_it;
}
dh = dccp_hdr(skb);
DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh);
DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type;
dccp_pr_debug("%8.8s src=%pI4@%-5d dst=%pI4@%-5d seq=%llu",
dccp_packet_name(dh->dccph_type),
&iph->saddr, ntohs(dh->dccph_sport),
&iph->daddr, ntohs(dh->dccph_dport),
(unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq);
if (dccp_packet_without_ack(skb)) {
DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ;
dccp_pr_debug_cat("\n");
} else {
DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb);
dccp_pr_debug_cat(", ack=%llu\n", (unsigned long long)
DCCP_SKB_CB(skb)->dccpd_ack_seq);
}
lookup:
sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
dh->dccph_sport, dh->dccph_dport, 0, &refcounted);
if (!sk) {
dccp_pr_debug("failed to look up flow ID in table and "
"get corresponding socket\n");
goto no_dccp_socket;
}
/*
* Step 2:
* ... or S.state == TIMEWAIT,
* Generate Reset(No Connection) unless P.type == Reset
* Drop packet and return
*/
if (sk->sk_state == DCCP_TIME_WAIT) {
dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n");
inet_twsk_put(inet_twsk(sk));
goto no_dccp_socket;
}
if (sk->sk_state == DCCP_NEW_SYN_RECV) {
struct request_sock *req = inet_reqsk(sk);
struct sock *nsk;
sk = req->rsk_listener;
if (unlikely(sk->sk_state != DCCP_LISTEN)) {
inet_csk_reqsk_queue_drop_and_put(sk, req);
goto lookup;
}
sock_hold(sk);
refcounted = true;
nsk = dccp_check_req(sk, skb, req);
if (!nsk) {
reqsk_put(req);
goto discard_and_relse;
}
if (nsk == sk) {
reqsk_put(req);
} else if (dccp_child_process(sk, nsk, skb)) {
dccp_v4_ctl_send_reset(sk, skb);
goto discard_and_relse;
} else {
sock_put(sk);
return 0;
}
}
/*
* RFC 4340, sec. 9.2.1: Minimum Checksum Coverage
* o if MinCsCov = 0, only packets with CsCov = 0 are accepted
* o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov
*/
min_cov = dccp_sk(sk)->dccps_pcrlen;
if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov)) {
dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n",
dh->dccph_cscov, min_cov);
/* FIXME: "Such packets SHOULD be reported using Data Dropped
* options (Section 11.7) with Drop Code 0, Protocol
* Constraints." */
goto discard_and_relse;
}
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
nf_reset_ct(skb);
dccp: do not release listeners too soon Andrey Konovalov reported following error while fuzzing with syzkaller : IPv4: Attempt to release alive inet socket ffff880068e98940 kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 1 PID: 3905 Comm: a.out Not tainted 4.9.0-rc3+ #333 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88006b9e0000 task.stack: ffff880068770000 RIP: 0010:[<ffffffff819ead5f>] [<ffffffff819ead5f>] selinux_socket_sock_rcv_skb+0xff/0x6a0 security/selinux/hooks.c:4639 RSP: 0018:ffff8800687771c8 EFLAGS: 00010202 RAX: ffff88006b9e0000 RBX: 1ffff1000d0eee3f RCX: 1ffff1000d1d312a RDX: 1ffff1000d1d31a6 RSI: dffffc0000000000 RDI: 0000000000000010 RBP: ffff880068777360 R08: 0000000000000000 R09: 0000000000000002 R10: dffffc0000000000 R11: 0000000000000006 R12: ffff880068e98940 R13: 0000000000000002 R14: ffff880068777338 R15: 0000000000000000 FS: 00007f00ff760700(0000) GS:ffff88006cd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020008000 CR3: 000000006a308000 CR4: 00000000000006e0 Stack: ffff8800687771e0 ffffffff812508a5 ffff8800686f3168 0000000000000007 ffff88006ac8cdfc ffff8800665ea500 0000000041b58ab3 ffffffff847b5480 ffffffff819eac60 ffff88006b9e0860 ffff88006b9e0868 ffff88006b9e07f0 Call Trace: [<ffffffff819c8dd5>] security_sock_rcv_skb+0x75/0xb0 security/security.c:1317 [<ffffffff82c2a9e7>] sk_filter_trim_cap+0x67/0x10e0 net/core/filter.c:81 [<ffffffff82b81e60>] __sk_receive_skb+0x30/0xa00 net/core/sock.c:460 [<ffffffff838bbf12>] dccp_v4_rcv+0xdb2/0x1910 net/dccp/ipv4.c:873 [<ffffffff83069d22>] ip_local_deliver_finish+0x332/0xad0 net/ipv4/ip_input.c:216 [< inline >] NF_HOOK_THRESH ./include/linux/netfilter.h:232 [< inline >] NF_HOOK ./include/linux/netfilter.h:255 [<ffffffff8306abd2>] ip_local_deliver+0x1c2/0x4b0 net/ipv4/ip_input.c:257 [< inline >] dst_input ./include/net/dst.h:507 [<ffffffff83068500>] ip_rcv_finish+0x750/0x1c40 net/ipv4/ip_input.c:396 [< inline >] NF_HOOK_THRESH ./include/linux/netfilter.h:232 [< inline >] NF_HOOK ./include/linux/netfilter.h:255 [<ffffffff8306b82f>] ip_rcv+0x96f/0x12f0 net/ipv4/ip_input.c:487 [<ffffffff82bd9fb7>] __netif_receive_skb_core+0x1897/0x2a50 net/core/dev.c:4213 [<ffffffff82bdb19a>] __netif_receive_skb+0x2a/0x170 net/core/dev.c:4251 [<ffffffff82bdb493>] netif_receive_skb_internal+0x1b3/0x390 net/core/dev.c:4279 [<ffffffff82bdb6b8>] netif_receive_skb+0x48/0x250 net/core/dev.c:4303 [<ffffffff8241fc75>] tun_get_user+0xbd5/0x28a0 drivers/net/tun.c:1308 [<ffffffff82421b5a>] tun_chr_write_iter+0xda/0x190 drivers/net/tun.c:1332 [< inline >] new_sync_write fs/read_write.c:499 [<ffffffff8151bd44>] __vfs_write+0x334/0x570 fs/read_write.c:512 [<ffffffff8151f85b>] vfs_write+0x17b/0x500 fs/read_write.c:560 [< inline >] SYSC_write fs/read_write.c:607 [<ffffffff81523184>] SyS_write+0xd4/0x1a0 fs/read_write.c:599 [<ffffffff83fc02c1>] entry_SYSCALL_64_fastpath+0x1f/0xc2 It turns out DCCP calls __sk_receive_skb(), and this broke when lookups no longer took a reference on listeners. Fix this issue by adding a @refcounted parameter to __sk_receive_skb(), so that sock_put() is used only when needed. Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Andrey Konovalov <andreyknvl@google.com> Tested-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-03 03:14:41 +03:00
return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted);
no_dccp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
/*
* Step 2:
* If no socket ...
* Generate Reset(No Connection) unless P.type == Reset
* Drop packet and return
*/
if (dh->dccph_type != DCCP_PKT_RESET) {
DCCP_SKB_CB(skb)->dccpd_reset_code =
DCCP_RESET_CODE_NO_CONNECTION;
dccp_v4_ctl_send_reset(sk, skb);
}
discard_it:
kfree_skb(skb);
return 0;
discard_and_relse:
if (refcounted)
sock_put(sk);
goto discard_it;
}
static const struct inet_connection_sock_af_ops dccp_ipv4_af_ops = {
.queue_xmit = ip_queue_xmit,
.send_check = dccp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
.conn_request = dccp_v4_conn_request,
.syn_recv_sock = dccp_v4_request_recv_sock,
.net_header_len = sizeof(struct iphdr),
.setsockopt = ip_setsockopt,
.getsockopt = ip_getsockopt,
.addr2sockaddr = inet_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in),
};
static int dccp_v4_init_sock(struct sock *sk)
{
static __u8 dccp_v4_ctl_sock_initialized;
int err = dccp_init_sock(sk, dccp_v4_ctl_sock_initialized);
if (err == 0) {
if (unlikely(!dccp_v4_ctl_sock_initialized))
dccp_v4_ctl_sock_initialized = 1;
inet_csk(sk)->icsk_af_ops = &dccp_ipv4_af_ops;
}
return err;
}
static struct timewait_sock_ops dccp_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct inet_timewait_sock),
};
static struct proto dccp_v4_prot = {
.name = "DCCP",
.owner = THIS_MODULE,
.close = dccp_close,
.connect = dccp_v4_connect,
.disconnect = dccp_disconnect,
.ioctl = dccp_ioctl,
.init = dccp_v4_init_sock,
.setsockopt = dccp_setsockopt,
.getsockopt = dccp_getsockopt,
.sendmsg = dccp_sendmsg,
.recvmsg = dccp_recvmsg,
.backlog_rcv = dccp_v4_do_rcv,
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 15:06:04 +03:00
.hash = inet_hash,
.unhash = inet_unhash,
.accept = inet_csk_accept,
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 15:06:04 +03:00
.get_port = inet_csk_get_port,
.shutdown = dccp_shutdown,
.destroy = dccp_destroy_sock,
.orphan_count = &dccp_orphan_count,
.max_header = MAX_DCCP_HEADER,
.obj_size = sizeof(struct dccp_sock),
.slab_flags = SLAB_TYPESAFE_BY_RCU,
.rsk_prot = &dccp_request_sock_ops,
.twsk_prot = &dccp_timewait_sock_ops,
.h.hashinfo = &dccp_hashinfo,
};
static const struct net_protocol dccp_v4_protocol = {
.handler = dccp_v4_rcv,
.err_handler = dccp_v4_err,
.no_policy = 1,
.icmp_strict_tag_validation = 1,
};
static const struct proto_ops inet_dccp_ops = {
.family = PF_INET,
.owner = THIS_MODULE,
.release = inet_release,
.bind = inet_bind,
.connect = inet_stream_connect,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname,
/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
.poll = dccp_poll,
.ioctl = inet_ioctl,
.gettstamp = sock_gettstamp,
/* FIXME: work on inet_listen to rename it to sock_common_listen */
.listen = inet_dccp_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
.recvmsg = sock_common_recvmsg,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
};
static struct inet_protosw dccp_v4_protosw = {
.type = SOCK_DCCP,
.protocol = IPPROTO_DCCP,
.prot = &dccp_v4_prot,
.ops = &inet_dccp_ops,
.flags = INET_PROTOSW_ICSK,
};
static int __net_init dccp_v4_init_net(struct net *net)
{
struct dccp_v4_pernet *pn = net_generic(net, dccp_v4_pernet_id);
if (dccp_hashinfo.bhash == NULL)
return -ESOCKTNOSUPPORT;
return inet_ctl_sock_create(&pn->v4_ctl_sk, PF_INET,
SOCK_DCCP, IPPROTO_DCCP, net);
}
static void __net_exit dccp_v4_exit_net(struct net *net)
{
struct dccp_v4_pernet *pn = net_generic(net, dccp_v4_pernet_id);
inet_ctl_sock_destroy(pn->v4_ctl_sk);
}
static struct pernet_operations dccp_v4_ops = {
.init = dccp_v4_init_net,
.exit = dccp_v4_exit_net,
.id = &dccp_v4_pernet_id,
.size = sizeof(struct dccp_v4_pernet),
};
static int __init dccp_v4_init(void)
{
int err = proto_register(&dccp_v4_prot, 1);
dccp: call inet_add_protocol after register_pernet_subsys in dccp_v4_init Now dccp_ipv4 works as a kernel module. During loading this module, if one dccp packet is being recieved after inet_add_protocol but before register_pernet_subsys in which v4_ctl_sk is initialized, a null pointer dereference may be triggered because of init_net.dccp.v4_ctl_sk is 0x0. Jianlin found this issue when the following call trace occurred: [ 171.950177] BUG: unable to handle kernel NULL pointer dereference at 0000000000000110 [ 171.951007] IP: [<ffffffffc0558364>] dccp_v4_ctl_send_reset+0xc4/0x220 [dccp_ipv4] [...] [ 171.984629] Call Trace: [ 171.984859] <IRQ> [ 171.985061] [ 171.985213] [<ffffffffc0559a53>] dccp_v4_rcv+0x383/0x3f9 [dccp_ipv4] [ 171.985711] [<ffffffff815ca054>] ip_local_deliver_finish+0xb4/0x1f0 [ 171.986309] [<ffffffff815ca339>] ip_local_deliver+0x59/0xd0 [ 171.986852] [<ffffffff810cd7a4>] ? update_curr+0x104/0x190 [ 171.986956] [<ffffffff815c9cda>] ip_rcv_finish+0x8a/0x350 [ 171.986956] [<ffffffff815ca666>] ip_rcv+0x2b6/0x410 [ 171.986956] [<ffffffff810c83b4>] ? task_cputime+0x44/0x80 [ 171.986956] [<ffffffff81586f22>] __netif_receive_skb_core+0x572/0x7c0 [ 171.986956] [<ffffffff810d2c51>] ? trigger_load_balance+0x61/0x1e0 [ 171.986956] [<ffffffff81587188>] __netif_receive_skb+0x18/0x60 [ 171.986956] [<ffffffff8158841e>] process_backlog+0xae/0x180 [ 171.986956] [<ffffffff8158799d>] net_rx_action+0x16d/0x380 [ 171.986956] [<ffffffff81090b7f>] __do_softirq+0xef/0x280 [ 171.986956] [<ffffffff816b6a1c>] call_softirq+0x1c/0x30 This patch is to move inet_add_protocol after register_pernet_subsys in dccp_v4_init, so that v4_ctl_sk is initialized before any incoming dccp packets are processed. Reported-by: Jianlin Shi <jishi@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-20 10:42:38 +03:00
if (err)
goto out;
inet_register_protosw(&dccp_v4_protosw);
err = register_pernet_subsys(&dccp_v4_ops);
if (err)
goto out_destroy_ctl_sock;
dccp: call inet_add_protocol after register_pernet_subsys in dccp_v4_init Now dccp_ipv4 works as a kernel module. During loading this module, if one dccp packet is being recieved after inet_add_protocol but before register_pernet_subsys in which v4_ctl_sk is initialized, a null pointer dereference may be triggered because of init_net.dccp.v4_ctl_sk is 0x0. Jianlin found this issue when the following call trace occurred: [ 171.950177] BUG: unable to handle kernel NULL pointer dereference at 0000000000000110 [ 171.951007] IP: [<ffffffffc0558364>] dccp_v4_ctl_send_reset+0xc4/0x220 [dccp_ipv4] [...] [ 171.984629] Call Trace: [ 171.984859] <IRQ> [ 171.985061] [ 171.985213] [<ffffffffc0559a53>] dccp_v4_rcv+0x383/0x3f9 [dccp_ipv4] [ 171.985711] [<ffffffff815ca054>] ip_local_deliver_finish+0xb4/0x1f0 [ 171.986309] [<ffffffff815ca339>] ip_local_deliver+0x59/0xd0 [ 171.986852] [<ffffffff810cd7a4>] ? update_curr+0x104/0x190 [ 171.986956] [<ffffffff815c9cda>] ip_rcv_finish+0x8a/0x350 [ 171.986956] [<ffffffff815ca666>] ip_rcv+0x2b6/0x410 [ 171.986956] [<ffffffff810c83b4>] ? task_cputime+0x44/0x80 [ 171.986956] [<ffffffff81586f22>] __netif_receive_skb_core+0x572/0x7c0 [ 171.986956] [<ffffffff810d2c51>] ? trigger_load_balance+0x61/0x1e0 [ 171.986956] [<ffffffff81587188>] __netif_receive_skb+0x18/0x60 [ 171.986956] [<ffffffff8158841e>] process_backlog+0xae/0x180 [ 171.986956] [<ffffffff8158799d>] net_rx_action+0x16d/0x380 [ 171.986956] [<ffffffff81090b7f>] __do_softirq+0xef/0x280 [ 171.986956] [<ffffffff816b6a1c>] call_softirq+0x1c/0x30 This patch is to move inet_add_protocol after register_pernet_subsys in dccp_v4_init, so that v4_ctl_sk is initialized before any incoming dccp packets are processed. Reported-by: Jianlin Shi <jishi@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-20 10:42:38 +03:00
err = inet_add_protocol(&dccp_v4_protocol, IPPROTO_DCCP);
if (err)
goto out_proto_unregister;
out:
return err;
dccp: call inet_add_protocol after register_pernet_subsys in dccp_v4_init Now dccp_ipv4 works as a kernel module. During loading this module, if one dccp packet is being recieved after inet_add_protocol but before register_pernet_subsys in which v4_ctl_sk is initialized, a null pointer dereference may be triggered because of init_net.dccp.v4_ctl_sk is 0x0. Jianlin found this issue when the following call trace occurred: [ 171.950177] BUG: unable to handle kernel NULL pointer dereference at 0000000000000110 [ 171.951007] IP: [<ffffffffc0558364>] dccp_v4_ctl_send_reset+0xc4/0x220 [dccp_ipv4] [...] [ 171.984629] Call Trace: [ 171.984859] <IRQ> [ 171.985061] [ 171.985213] [<ffffffffc0559a53>] dccp_v4_rcv+0x383/0x3f9 [dccp_ipv4] [ 171.985711] [<ffffffff815ca054>] ip_local_deliver_finish+0xb4/0x1f0 [ 171.986309] [<ffffffff815ca339>] ip_local_deliver+0x59/0xd0 [ 171.986852] [<ffffffff810cd7a4>] ? update_curr+0x104/0x190 [ 171.986956] [<ffffffff815c9cda>] ip_rcv_finish+0x8a/0x350 [ 171.986956] [<ffffffff815ca666>] ip_rcv+0x2b6/0x410 [ 171.986956] [<ffffffff810c83b4>] ? task_cputime+0x44/0x80 [ 171.986956] [<ffffffff81586f22>] __netif_receive_skb_core+0x572/0x7c0 [ 171.986956] [<ffffffff810d2c51>] ? trigger_load_balance+0x61/0x1e0 [ 171.986956] [<ffffffff81587188>] __netif_receive_skb+0x18/0x60 [ 171.986956] [<ffffffff8158841e>] process_backlog+0xae/0x180 [ 171.986956] [<ffffffff8158799d>] net_rx_action+0x16d/0x380 [ 171.986956] [<ffffffff81090b7f>] __do_softirq+0xef/0x280 [ 171.986956] [<ffffffff816b6a1c>] call_softirq+0x1c/0x30 This patch is to move inet_add_protocol after register_pernet_subsys in dccp_v4_init, so that v4_ctl_sk is initialized before any incoming dccp packets are processed. Reported-by: Jianlin Shi <jishi@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-20 10:42:38 +03:00
out_proto_unregister:
unregister_pernet_subsys(&dccp_v4_ops);
out_destroy_ctl_sock:
inet_unregister_protosw(&dccp_v4_protosw);
proto_unregister(&dccp_v4_prot);
goto out;
}
static void __exit dccp_v4_exit(void)
{
dccp: call inet_add_protocol after register_pernet_subsys in dccp_v4_init Now dccp_ipv4 works as a kernel module. During loading this module, if one dccp packet is being recieved after inet_add_protocol but before register_pernet_subsys in which v4_ctl_sk is initialized, a null pointer dereference may be triggered because of init_net.dccp.v4_ctl_sk is 0x0. Jianlin found this issue when the following call trace occurred: [ 171.950177] BUG: unable to handle kernel NULL pointer dereference at 0000000000000110 [ 171.951007] IP: [<ffffffffc0558364>] dccp_v4_ctl_send_reset+0xc4/0x220 [dccp_ipv4] [...] [ 171.984629] Call Trace: [ 171.984859] <IRQ> [ 171.985061] [ 171.985213] [<ffffffffc0559a53>] dccp_v4_rcv+0x383/0x3f9 [dccp_ipv4] [ 171.985711] [<ffffffff815ca054>] ip_local_deliver_finish+0xb4/0x1f0 [ 171.986309] [<ffffffff815ca339>] ip_local_deliver+0x59/0xd0 [ 171.986852] [<ffffffff810cd7a4>] ? update_curr+0x104/0x190 [ 171.986956] [<ffffffff815c9cda>] ip_rcv_finish+0x8a/0x350 [ 171.986956] [<ffffffff815ca666>] ip_rcv+0x2b6/0x410 [ 171.986956] [<ffffffff810c83b4>] ? task_cputime+0x44/0x80 [ 171.986956] [<ffffffff81586f22>] __netif_receive_skb_core+0x572/0x7c0 [ 171.986956] [<ffffffff810d2c51>] ? trigger_load_balance+0x61/0x1e0 [ 171.986956] [<ffffffff81587188>] __netif_receive_skb+0x18/0x60 [ 171.986956] [<ffffffff8158841e>] process_backlog+0xae/0x180 [ 171.986956] [<ffffffff8158799d>] net_rx_action+0x16d/0x380 [ 171.986956] [<ffffffff81090b7f>] __do_softirq+0xef/0x280 [ 171.986956] [<ffffffff816b6a1c>] call_softirq+0x1c/0x30 This patch is to move inet_add_protocol after register_pernet_subsys in dccp_v4_init, so that v4_ctl_sk is initialized before any incoming dccp packets are processed. Reported-by: Jianlin Shi <jishi@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-20 10:42:38 +03:00
inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP);
unregister_pernet_subsys(&dccp_v4_ops);
inet_unregister_protosw(&dccp_v4_protosw);
proto_unregister(&dccp_v4_prot);
}
module_init(dccp_v4_init);
module_exit(dccp_v4_exit);
/*
* __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33)
* values directly, Also cover the case where the protocol is not specified,
* i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP
*/
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 33, 6);
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 0, 6);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>");
MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol");