linux-stable/net/dccp/ipv6.c

1139 lines
29 KiB
C
Raw Normal View History

/*
* DCCP over IPv6
* Linux INET6 implementation
*
* Based on net/dccp6/ipv6.c
*
* Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
#include <linux/random.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 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/xfrm.h>
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/inet_sock.h>
#include <net/inet6_connection_sock.h>
#include <net/inet6_hashtables.h>
#include <net/ip6_route.h>
#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <net/secure_seq.h>
#include "dccp.h"
#include "ipv6.h"
#include "feat.h"
/* The per-net dccp.v6_ctl_sk is used for sending RSTs and ACKs */
static const struct inet_connection_sock_af_ops dccp_ipv6_mapped;
static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops;
/* add pseudo-header to DCCP checksum stored in skb->csum */
static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb,
const struct in6_addr *saddr,
const struct in6_addr *daddr)
{
return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum);
}
static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_hdr *dh = dccp_hdr(skb);
dccp_csum_outgoing(skb);
dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &sk->sk_v6_daddr);
}
static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb)
{
return secure_dccpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
ipv6_hdr(skb)->saddr.s6_addr32,
dccp_hdr(skb)->dccph_dport,
dccp_hdr(skb)->dccph_sport );
}
static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct ipv6_pinfo *np;
struct sock *sk;
int err;
__u64 seq;
struct net *net = dev_net(skb->dev);
/* Only need dccph_dport & dccph_sport which are the first
* 4 bytes in dccp header.
* Our caller (icmpv6_notify()) 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 = __inet6_lookup_established(net, &dccp_hashinfo,
&hdr->daddr, dh->dccph_dport,
&hdr->saddr, ntohs(dh->dccph_sport),
inet6_iif(skb));
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
seq = dccp_hdr_seq(dh);
if (sk->sk_state == DCCP_NEW_SYN_RECV)
return dccp_req_err(sk, seq);
bh_lock_sock(sk);
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;
}
np = inet6_sk(sk);
if (type == NDISC_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 05:40:33 +00:00
if (!sock_owned_by_user(sk)) {
struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
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 05:40:33 +00:00
if (dst)
dst->ops->redirect(dst, sk, skb);
}
goto out;
}
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
if (!ip6_sk_accept_pmtu(sk))
goto out;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
goto out;
dst = inet6_csk_update_pmtu(sk, ntohl(info));
if (!dst)
goto out;
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst))
dccp_sync_mss(sk, dst_mtu(dst));
goto out;
}
icmpv6_err_convert(type, code, &err);
/* Might be for an request_sock */
switch (sk->sk_state) {
case DCCP_REQUESTING:
case DCCP_RESPOND: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
/*
* Wake people up to see the error
* (see connect in sock.c)
*/
sk->sk_error_report(sk);
dccp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req)
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
struct in6_addr *final_p, final;
struct flowi6 fl6;
int err = -1;
struct dst_entry *dst;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = ireq->ir_v6_rmt_addr;
fl6.saddr = ireq->ir_v6_loc_addr;
fl6.flowlabel = 0;
fl6.flowi6_oif = ireq->ir_iif;
fl6.fl6_dport = ireq->ir_rmt_port;
fl6.fl6_sport = htons(ireq->ir_num);
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
rcu_read_lock();
final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
rcu_read_unlock();
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
dst = NULL;
goto done;
}
skb = dccp_make_response(sk, dst, req);
if (skb != NULL) {
struct dccp_hdr *dh = dccp_hdr(skb);
struct ipv6_txoptions *opt;
dh->dccph_checksum = dccp_v6_csum_finish(skb,
&ireq->ir_v6_loc_addr,
&ireq->ir_v6_rmt_addr);
fl6.daddr = ireq->ir_v6_rmt_addr;
rcu_read_lock();
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass);
rcu_read_unlock();
err = net_xmit_eval(err);
}
done:
dst_release(dst);
return err;
}
static void dccp_v6_reqsk_destructor(struct request_sock *req)
{
dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
kfree(inet_rsk(req)->ipv6_opt);
kfree_skb(inet_rsk(req)->pktopts);
}
static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
{
const struct ipv6hdr *rxip6h;
struct sk_buff *skb;
struct flowi6 fl6;
struct net *net = dev_net(skb_dst(rxskb)->dev);
struct sock *ctl_sk = net->dccp.v6_ctl_sk;
struct dst_entry *dst;
if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET)
return;
if (!ipv6_unicast_destination(rxskb))
return;
skb = dccp_ctl_make_reset(ctl_sk, rxskb);
if (skb == NULL)
return;
rxip6h = ipv6_hdr(rxskb);
dccp_hdr(skb)->dccph_checksum = dccp_v6_csum_finish(skb, &rxip6h->saddr,
&rxip6h->daddr);
memset(&fl6, 0, sizeof(fl6));
fl6.daddr = rxip6h->saddr;
fl6.saddr = rxip6h->daddr;
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.flowi6_oif = inet6_iif(rxskb);
fl6.fl6_dport = dccp_hdr(skb)->dccph_dport;
fl6.fl6_sport = dccp_hdr(skb)->dccph_sport;
security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6));
/* sk = NULL, but it is safe for now. RST socket required. */
dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
if (!IS_ERR(dst)) {
skb_dst_set(skb, dst);
ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
DCCP_INC_STATS(DCCP_MIB_OUTRSTS);
return;
}
kfree_skb(skb);
}
static struct request_sock_ops dccp6_request_sock_ops = {
.family = AF_INET6,
.obj_size = sizeof(struct dccp6_request_sock),
.rtx_syn_ack = dccp_v6_send_response,
.send_ack = dccp_reqsk_send_ack,
.destructor = dccp_v6_reqsk_destructor,
.send_reset = dccp_v6_ctl_send_reset,
.syn_ack_timeout = dccp_syn_ack_timeout,
};
static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct request_sock *req;
struct dccp_request_sock *dreq;
struct inet_request_sock *ireq;
struct ipv6_pinfo *np = inet6_sk(sk);
const __be32 service = dccp_hdr_request(skb)->dccph_req_service;
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
if (skb->protocol == htons(ETH_P_IP))
return dccp_v4_conn_request(sk, skb);
if (!ipv6_unicast_destination(skb))
[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>
2007-10-04 21:52:28 +00:00
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>
2007-10-04 21:52:28 +00:00
dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE;
goto drop;
}
/*
* There are no SYN attacks on IPv6, yet...
*/
[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>
2007-10-04 21:52:28 +00:00
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(&dccp6_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);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
ireq->ireq_family = AF_INET6;
if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
atomic_inc(&skb->users);
ireq->pktopts = skb;
}
ireq->ir_iif = sk->sk_bound_dev_if;
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq->ir_iif = inet6_iif(skb);
/*
* 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_v6_init_sequence(skb);
dreq->dreq_gss = dreq->dreq_iss;
dreq->dreq_service = service;
if (dccp_v6_send_response(sk, req))
goto drop_and_free;
inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
return 0;
drop_and_free:
reqsk_free(req);
drop:
__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
return -1;
}
static struct sock *dccp_v6_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 = inet_rsk(req);
struct ipv6_pinfo *newnp;
const struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_txoptions *opt;
struct inet_sock *newinet;
struct dccp6_sock *newdp6;
struct sock *newsk;
if (skb->protocol == htons(ETH_P_IP)) {
/*
* v6 mapped
*/
newsk = dccp_v4_request_recv_sock(sk, skb, req, dst,
req_unhash, own_req);
if (newsk == NULL)
return NULL;
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newnp->saddr = newsk->sk_v6_rcv_saddr;
inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
newsk->sk_backlog_rcv = dccp_v4_do_rcv;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
* here, dccp_create_openreq_child now does this for us, see the comment in
* that function for the gory details. -acme
*/
/* It is tricky place. Until this moment IPv4 tcp
worked with IPv6 icsk.icsk_af_ops.
Sync it now.
*/
dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
return newsk;
}
if (sk_acceptq_is_full(sk))
goto out_overflow;
if (!dst) {
struct flowi6 fl6;
dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_DCCP);
if (!dst)
goto out;
}
newsk = dccp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
goto out_nonewsk;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks
* count here, dccp_create_openreq_child now does this for us, see the
* comment in that function for the gory details. -acme
*/
ip6_dst_store(newsk, dst, NULL, NULL);
newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
NETIF_F_TSO);
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
newnp->saddr = ireq->ir_v6_loc_addr;
newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
newsk->sk_bound_dev_if = ireq->ir_iif;
/* Now IPv6 options...
First: no IPv4 options.
*/
newinet->inet_opt = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* Clone native IPv6 options from listening socket (if any)
*
* Yes, keeping reference count would be much more clever, but we make
* one more one thing there: reattach optmem to newsk.
*/
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
if (opt) {
opt = ipv6_dup_options(newsk, opt);
RCU_INIT_POINTER(newnp->opt, opt);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (opt)
inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
opt->opt_flen;
dccp_sync_mss(newsk, dst_mtu(dst));
newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
if (__inet_inherit_port(sk, newsk) < 0) {
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 04:07:58 +00:00
inet_csk_prepare_forced_close(newsk);
dccp_done(newsk);
goto out;
}
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
/* Clone pktoptions received with SYN, if we own the req */
if (*own_req && ireq->pktopts) {
newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
consume_skb(ireq->pktopts);
ireq->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
return newsk;
out_overflow:
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out_nonewsk:
dst_release(dst);
out:
__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
return NULL;
}
/* The socket must have it's spinlock held when we get
* here.
*
* We have a potential double-lock case here, so even when
* doing backlog processing we use the BH locking scheme.
* This is because we cannot sleep with the original spinlock
* held.
*/
static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *opt_skb = NULL;
/* Imagine: socket is IPv6. IPv4 packet arrives,
goes to IPv4 receive handler and backlogged.
From backlog it always goes here. Kerboom...
Fortunately, dccp_rcv_established and rcv_established
handle them correctly, but it is not case with
dccp_v6_hnd_req and dccp_v6_ctl_send_reset(). --ANK
*/
if (skb->protocol == htons(ETH_P_IP))
return dccp_v4_do_rcv(sk, skb);
if (sk_filter(sk, skb))
goto discard;
/*
* socket locking is here for SMP purposes as backlog rcv is currently
* called with bh processing disabled.
*/
/* Do Stevens' IPV6_PKTOPTIONS.
Yes, guys, it is the only place in our code, where we
may make it not affecting IPv4.
The rest of code is protocol independent,
and I do not like idea to uglify IPv4.
Actually, all the idea behind IPV6_PKTOPTIONS
looks not very well thought. For now we latch
options, received in the last packet, enqueued
by tcp. Feel free to propose better solution.
--ANK (980728)
*/
if (np->rxopt.all)
/*
* FIXME: Add handling of IPV6_PKTOPTIONS skb. See the comments below
* (wrt ipv6_pktopions) and net/ipv6/tcp_ipv6.c for an example.
*/
opt_skb = skb_clone(skb, GFP_ATOMIC);
if (sk->sk_state == DCCP_OPEN) { /* Fast path */
if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len))
goto reset;
if (opt_skb) {
/* XXX This is where we would goto ipv6_pktoptions. */
__kfree_skb(opt_skb);
}
return 0;
}
/*
* Step 3: Process LISTEN state
* If S.state == LISTEN,
* 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, dccp_hdr(skb), skb->len))
goto reset;
if (opt_skb) {
/* XXX This is where we would goto ipv6_pktoptions. */
__kfree_skb(opt_skb);
}
return 0;
reset:
dccp_v6_ctl_send_reset(sk, skb);
discard:
if (opt_skb != NULL)
__kfree_skb(opt_skb);
kfree_skb(skb);
return 0;
}
static int dccp_v6_rcv(struct sk_buff *skb)
{
const struct dccp_hdr *dh;
bool refcounted;
struct sock *sk;
int min_cov;
/* Step 1: Check header basics */
if (dccp_invalid_packet(skb))
goto discard_it;
/* Step 1: If header checksum is incorrect, drop packet and return. */
if (dccp_v6_csum_finish(skb, &ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->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;
if (dccp_packet_without_ack(skb))
DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ;
else
DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb);
lookup:
sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
dh->dccph_sport, dh->dccph_dport,
inet6_iif(skb), &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_v6_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: send Data Dropped option (see also dccp_v4_rcv) */
goto discard_and_relse;
}
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
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 00:14:41 +00:00
return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4,
refcounted) ? -1 : 0;
no_dccp_socket:
if (!xfrm6_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_v6_ctl_send_reset(sk, skb);
}
discard_it:
kfree_skb(skb);
return 0;
discard_and_relse:
if (refcounted)
sock_put(sk);
goto discard_it;
}
static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr;
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct ipv6_txoptions *opt;
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl6, 0, sizeof(fl6));
if (np->sndflow) {
fl6.flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
IP6_ECN_flow_init(fl6.flowlabel);
if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) {
struct ip6_flowlabel *flowlabel;
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
fl6_sock_release(flowlabel);
}
}
/*
* connect() to INADDR_ANY means loopback (BSD'ism).
*/
if (ipv6_addr_any(&usin->sin6_addr))
usin->sin6_addr.s6_addr[15] = 1;
addr_type = ipv6_addr_type(&usin->sin6_addr);
if (addr_type & IPV6_ADDR_MULTICAST)
return -ENETUNREACH;
if (addr_type & IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
/* If interface is set while binding, indices
* must coincide.
*/
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id)
return -EINVAL;
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
return -EINVAL;
}
sk->sk_v6_daddr = usin->sin6_addr;
np->flow_label = fl6.flowlabel;
/*
* DCCP over IPv4
*/
if (addr_type == IPV6_ADDR_MAPPED) {
u32 exthdrlen = icsk->icsk_ext_hdr_len;
struct sockaddr_in sin;
SOCK_DEBUG(sk, "connect: ipv4 mapped\n");
if (__ipv6_only_sock(sk))
return -ENETUNREACH;
sin.sin_family = AF_INET;
sin.sin_port = usin->sin6_port;
sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];
icsk->icsk_af_ops = &dccp_ipv6_mapped;
sk->sk_backlog_rcv = dccp_v4_do_rcv;
err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));
if (err) {
icsk->icsk_ext_hdr_len = exthdrlen;
icsk->icsk_af_ops = &dccp_ipv6_af_ops;
sk->sk_backlog_rcv = dccp_v6_do_rcv;
goto failure;
}
np->saddr = sk->sk_v6_rcv_saddr;
return err;
}
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr))
saddr = &sk->sk_v6_rcv_saddr;
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = sk->sk_v6_daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = usin->sin6_port;
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
final_p = fl6_update_dst(&fl6, opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
}
if (saddr == NULL) {
saddr = &fl6.saddr;
sk->sk_v6_rcv_saddr = *saddr;
}
/* set the source address */
np->saddr = *saddr;
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
ip6_dst_store(sk, dst, NULL, NULL);
icsk->icsk_ext_hdr_len = 0;
if (opt)
icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
inet->inet_dport = usin->sin6_port;
dccp_set_state(sk, DCCP_REQUESTING);
err = inet6_hash_connect(&dccp_death_row, sk);
if (err)
goto late_failure;
dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32,
inet->inet_sport,
inet->inet_dport);
err = dccp_connect(sk);
if (err)
goto late_failure;
return 0;
late_failure:
dccp_set_state(sk, DCCP_CLOSED);
__sk_dst_reset(sk);
failure:
inet->inet_dport = 0;
sk->sk_route_caps = 0;
return err;
}
static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = {
.queue_xmit = inet6_csk_xmit,
.send_check = dccp_v6_send_check,
.rebuild_header = inet6_sk_rebuild_header,
.conn_request = dccp_v6_conn_request,
.syn_recv_sock = dccp_v6_request_recv_sock,
.net_header_len = sizeof(struct ipv6hdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
};
/*
* DCCP over IPv4 via INET6 API
*/
static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = {
.queue_xmit = ip_queue_xmit,
.send_check = dccp_v4_send_check,
.rebuild_header = inet_sk_rebuild_header,
.conn_request = dccp_v6_conn_request,
.syn_recv_sock = dccp_v6_request_recv_sock,
.net_header_len = sizeof(struct iphdr),
.setsockopt = ipv6_setsockopt,
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
};
/* NOTE: A lot of things set to zero explicitly by call to
* sk_alloc() so need not be done here.
*/
static int dccp_v6_init_sock(struct sock *sk)
{
static __u8 dccp_v6_ctl_sock_initialized;
int err = dccp_init_sock(sk, dccp_v6_ctl_sock_initialized);
if (err == 0) {
if (unlikely(!dccp_v6_ctl_sock_initialized))
dccp_v6_ctl_sock_initialized = 1;
inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops;
}
return err;
}
static void dccp_v6_destroy_sock(struct sock *sk)
{
dccp_destroy_sock(sk);
inet6_destroy_sock(sk);
}
static struct timewait_sock_ops dccp6_timewait_sock_ops = {
.twsk_obj_size = sizeof(struct dccp6_timewait_sock),
};
static struct proto dccp_v6_prot = {
.name = "DCCPv6",
.owner = THIS_MODULE,
.close = dccp_close,
.connect = dccp_v6_connect,
.disconnect = dccp_disconnect,
.ioctl = dccp_ioctl,
.init = dccp_v6_init_sock,
.setsockopt = dccp_setsockopt,
.getsockopt = dccp_getsockopt,
.sendmsg = dccp_sendmsg,
.recvmsg = dccp_recvmsg,
.backlog_rcv = dccp_v6_do_rcv,
.hash = inet6_hash,
[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 12:06:04 +00:00
.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 12:06:04 +00:00
.get_port = inet_csk_get_port,
.shutdown = dccp_shutdown,
.destroy = dccp_v6_destroy_sock,
.orphan_count = &dccp_orphan_count,
.max_header = MAX_DCCP_HEADER,
.obj_size = sizeof(struct dccp6_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.rsk_prot = &dccp6_request_sock_ops,
.twsk_prot = &dccp6_timewait_sock_ops,
.h.hashinfo = &dccp_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_dccp_setsockopt,
.compat_getsockopt = compat_dccp_getsockopt,
#endif
};
static const struct inet6_protocol dccp_v6_protocol = {
.handler = dccp_v6_rcv,
.err_handler = dccp_v6_err,
.flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL,
};
static const struct proto_ops inet6_dccp_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
.release = inet6_release,
.bind = inet6_bind,
.connect = inet_stream_connect,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet6_getname,
.poll = dccp_poll,
.ioctl = inet6_ioctl,
.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,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};
static struct inet_protosw dccp_v6_protosw = {
.type = SOCK_DCCP,
.protocol = IPPROTO_DCCP,
.prot = &dccp_v6_prot,
.ops = &inet6_dccp_ops,
.flags = INET_PROTOSW_ICSK,
};
static int __net_init dccp_v6_init_net(struct net *net)
{
if (dccp_hashinfo.bhash == NULL)
return -ESOCKTNOSUPPORT;
return inet_ctl_sock_create(&net->dccp.v6_ctl_sk, PF_INET6,
SOCK_DCCP, IPPROTO_DCCP, net);
}
static void __net_exit dccp_v6_exit_net(struct net *net)
{
inet_ctl_sock_destroy(net->dccp.v6_ctl_sk);
}
net/dccp: fix use after free in tw_timer_handler() DCCP doesn't purge timewait sockets on network namespace shutdown. So, after net namespace destroyed we could still have an active timer which will trigger use after free in tw_timer_handler(): BUG: KASAN: use-after-free in tw_timer_handler+0x4a/0xa0 at addr ffff88010e0d1e10 Read of size 8 by task swapper/1/0 Call Trace: __asan_load8+0x54/0x90 tw_timer_handler+0x4a/0xa0 call_timer_fn+0x127/0x480 expire_timers+0x1db/0x2e0 run_timer_softirq+0x12f/0x2a0 __do_softirq+0x105/0x5b4 irq_exit+0xdd/0xf0 smp_apic_timer_interrupt+0x57/0x70 apic_timer_interrupt+0x90/0xa0 Object at ffff88010e0d1bc0, in cache net_namespace size: 6848 Allocated: save_stack_trace+0x1b/0x20 kasan_kmalloc+0xee/0x180 kasan_slab_alloc+0x12/0x20 kmem_cache_alloc+0x134/0x310 copy_net_ns+0x8d/0x280 create_new_namespaces+0x23f/0x340 unshare_nsproxy_namespaces+0x75/0xf0 SyS_unshare+0x299/0x4f0 entry_SYSCALL_64_fastpath+0x18/0xad Freed: save_stack_trace+0x1b/0x20 kasan_slab_free+0xae/0x180 kmem_cache_free+0xb4/0x350 net_drop_ns+0x3f/0x50 cleanup_net+0x3df/0x450 process_one_work+0x419/0xbb0 worker_thread+0x92/0x850 kthread+0x192/0x1e0 ret_from_fork+0x2e/0x40 Add .exit_batch hook to dccp_v4_ops()/dccp_v6_ops() which will purge timewait sockets on net namespace destruction and prevent above issue. Fixes: f2bf415cfed7 ("mib: add net to NET_ADD_STATS_BH") Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-22 09:35:27 +00:00
static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list)
{
inet_twsk_purge(&dccp_hashinfo, AF_INET6);
}
static struct pernet_operations dccp_v6_ops = {
.init = dccp_v6_init_net,
.exit = dccp_v6_exit_net,
net/dccp: fix use after free in tw_timer_handler() DCCP doesn't purge timewait sockets on network namespace shutdown. So, after net namespace destroyed we could still have an active timer which will trigger use after free in tw_timer_handler(): BUG: KASAN: use-after-free in tw_timer_handler+0x4a/0xa0 at addr ffff88010e0d1e10 Read of size 8 by task swapper/1/0 Call Trace: __asan_load8+0x54/0x90 tw_timer_handler+0x4a/0xa0 call_timer_fn+0x127/0x480 expire_timers+0x1db/0x2e0 run_timer_softirq+0x12f/0x2a0 __do_softirq+0x105/0x5b4 irq_exit+0xdd/0xf0 smp_apic_timer_interrupt+0x57/0x70 apic_timer_interrupt+0x90/0xa0 Object at ffff88010e0d1bc0, in cache net_namespace size: 6848 Allocated: save_stack_trace+0x1b/0x20 kasan_kmalloc+0xee/0x180 kasan_slab_alloc+0x12/0x20 kmem_cache_alloc+0x134/0x310 copy_net_ns+0x8d/0x280 create_new_namespaces+0x23f/0x340 unshare_nsproxy_namespaces+0x75/0xf0 SyS_unshare+0x299/0x4f0 entry_SYSCALL_64_fastpath+0x18/0xad Freed: save_stack_trace+0x1b/0x20 kasan_slab_free+0xae/0x180 kmem_cache_free+0xb4/0x350 net_drop_ns+0x3f/0x50 cleanup_net+0x3df/0x450 process_one_work+0x419/0xbb0 worker_thread+0x92/0x850 kthread+0x192/0x1e0 ret_from_fork+0x2e/0x40 Add .exit_batch hook to dccp_v4_ops()/dccp_v6_ops() which will purge timewait sockets on net namespace destruction and prevent above issue. Fixes: f2bf415cfed7 ("mib: add net to NET_ADD_STATS_BH") Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-22 09:35:27 +00:00
.exit_batch = dccp_v6_exit_batch,
};
static int __init dccp_v6_init(void)
{
int err = proto_register(&dccp_v6_prot, 1);
if (err != 0)
goto out;
err = inet6_add_protocol(&dccp_v6_protocol, IPPROTO_DCCP);
if (err != 0)
goto out_unregister_proto;
inet6_register_protosw(&dccp_v6_protosw);
err = register_pernet_subsys(&dccp_v6_ops);
if (err != 0)
goto out_destroy_ctl_sock;
out:
return err;
out_destroy_ctl_sock:
inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP);
inet6_unregister_protosw(&dccp_v6_protosw);
out_unregister_proto:
proto_unregister(&dccp_v6_prot);
goto out;
}
static void __exit dccp_v6_exit(void)
{
unregister_pernet_subsys(&dccp_v6_ops);
inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP);
inet6_unregister_protosw(&dccp_v6_protosw);
proto_unregister(&dccp_v6_prot);
}
module_init(dccp_v6_init);
module_exit(dccp_v6_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_INET6-proto-0-type-SOCK_DCCP
*/
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 33, 6);
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 0, 6);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>");
MODULE_DESCRIPTION("DCCPv6 - Datagram Congestion Controlled Protocol");