linux-sg2042/net/dccp/ipv6.c

1186 lines
30 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 16:04:11 +08:00
#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;
static void dccp_v6_hash(struct sock *sk)
{
if (sk->sk_state != DCCP_CLOSED) {
if (inet_csk(sk)->icsk_af_ops == &dccp_ipv6_mapped) {
[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 20:06:04 +08:00
inet_hash(sk);
return;
}
local_bh_disable();
__inet6_hash(sk, NULL);
local_bh_enable();
}
}
/* 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, &np->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_hdr *)(skb->data + offset);
struct dccp_sock *dp;
struct ipv6_pinfo *np;
struct sock *sk;
int err;
__u64 seq;
struct net *net = dev_net(skb->dev);
if (skb->len < offset + sizeof(*dh) ||
skb->len < offset + __dccp_basic_hdr_len(dh)) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
sk = inet6_lookup(net, &dccp_hashinfo,
&hdr->daddr, dh->dccph_dport,
&hdr->saddr, dh->dccph_sport, inet6_iif(skb));
if (sk == NULL) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == DCCP_CLOSED)
goto out;
dp = dccp_sk(sk);
seq = dccp_hdr_seq(dh);
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
!between48(seq, dp->dccps_awl, dp->dccps_awh)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == NDISC_REDIRECT) {
struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
if (dst)
dst->ops->redirect(dst, sk, skb);
}
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
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) {
struct request_sock *req, **prev;
case DCCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, dh->dccph_dport,
&hdr->daddr, &hdr->saddr,
inet6_iif(skb));
if (req == NULL)
goto out;
/*
* ICMPs are not backlogged, hence we cannot get an established
* socket here.
*/
WARN_ON(req->sk != NULL);
if (!between48(seq, dccp_rsk(req)->dreq_iss,
dccp_rsk(req)->dreq_gss)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case DCCP_REQUESTING:
case DCCP_RESPOND: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
DCCP_INC_STATS_BH(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(struct sock *sk, struct request_sock *req)
{
struct inet6_request_sock *ireq6 = inet6_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 = ireq6->rmt_addr;
fl6.saddr = ireq6->loc_addr;
fl6.flowlabel = 0;
fl6.flowi6_oif = ireq6->iif;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
fl6.fl6_sport = inet_rsk(req)->loc_port;
security_req_classify_flow(req, flowi6_to_flowi(&fl6));
final_p = fl6_update_dst(&fl6, np->opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
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);
dh->dccph_checksum = dccp_v6_csum_finish(skb,
&ireq6->loc_addr,
&ireq6->rmt_addr);
fl6.daddr = ireq6->rmt_addr;
err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
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);
if (inet6_rsk(req)->pktopts != NULL)
kfree_skb(inet6_rsk(req)->pktopts);
}
static void dccp_v6_ctl_send_reset(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, false);
if (!IS_ERR(dst)) {
skb_dst_set(skb, dst);
ip6_xmit(ctl_sk, skb, &fl6, NULL, 0);
DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS);
DCCP_INC_STATS_BH(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 struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
{
const struct dccp_hdr *dh = dccp_hdr(skb);
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct sock *nsk;
struct request_sock **prev;
/* Find possible connection requests. */
struct request_sock *req = inet6_csk_search_req(sk, &prev,
dh->dccph_sport,
&iph->saddr,
&iph->daddr,
inet6_iif(skb));
if (req != NULL)
return dccp_check_req(sk, skb, req, prev);
nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo,
&iph->saddr, dh->dccph_sport,
&iph->daddr, ntohs(dh->dccph_dport),
inet6_iif(skb));
if (nsk != NULL) {
if (nsk->sk_state != DCCP_TIME_WAIT) {
bh_lock_sock(nsk);
return nsk;
}
inet_twsk_put(inet_twsk(nsk));
return NULL;
}
return sk;
}
static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct request_sock *req;
struct dccp_request_sock *dreq;
struct inet6_request_sock *ireq6;
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>
2007-10-05 05:52:28 +08:00
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 05:52:28 +08:00
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>
2007-10-05 05:52:28 +08:00
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) && inet_csk_reqsk_queue_young(sk) > 1)
goto drop;
[DCCP]: Fix Oops in DCCPv6 I think I got the cause for the Oops observed in http://www.mail-archive.com/dccp@vger.kernel.org/msg00578.html The problem is always with applications listening on PF_INET6 sockets. Apart from the mentioned oops, I observed another one one, triggered at irregular intervals via timer interrupt: run_timer_softirq -> dccp_keepalive_timer -> inet_csk_reqsk_queue_prune -> reqsk_free -> dccp_v6_reqsk_destructor The latter function is the problem and is also the last function to be called in said kernel panic. In any case, there is a real problem with allocating the right request_sock which is what this patch tackles. It fixes the following problem: - application listens on PF_INET6 - DCCPv4 packet comes in, is handed over to dccp_v4_do_rcv, from there to dccp_v4_conn_request Now: socket is PF_INET6, packet is IPv4. The following code then furnishes the connection with IPv6 - request_sock operations: req = reqsk_alloc(sk->sk_prot->rsk_prot); The first problem is that all further incoming packets will get a Reset since the connection can not be looked up. The second problem is worse: --> reqsk_alloc is called instead of inet6_reqsk_alloc --> consequently inet6_rsk_offset is never set (dangling pointer) --> the request_sock_ops are nevertheless still dccp6_request_ops --> destructor is called via reqsk_free --> dccp_v6_reqsk_destructor tries to free random memory location (inet6_rsk_offset not set) --> panic I have tested this for a while, DCCP sockets are now handled correctly in all three scenarios (v4/v6 only/v4-mapped). Commiter note: I've added the dccp_request_sock_ops forward declaration to keep the tree building and to reduce the size of the patch for 2.6.19, later I'll move the functions to the top of the affected source code to match what we have in the TCP counterpart, where this problem hasn't existed in the first place, dumb me not to have done the same thing on DCCP land 8) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
2006-10-11 23:26:54 +08:00
req = inet6_reqsk_alloc(&dccp6_request_sock_ops);
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;
ireq6 = inet6_rsk(req);
ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
ireq6->loc_addr = ipv6_hdr(skb)->daddr;
if (ipv6_opt_accepted(sk, skb) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
atomic_inc(&skb->users);
ireq6->pktopts = skb;
}
ireq6->iif = sk->sk_bound_dev_if;
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq6->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;
inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
return 0;
drop_and_free:
reqsk_free(req);
drop:
DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
return -1;
}
static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
{
struct inet6_request_sock *ireq6 = inet6_rsk(req);
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
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);
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));
ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr);
ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
newnp->rcv_saddr = newnp->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 == NULL) {
struct in6_addr *final_p, final;
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = ireq6->rmt_addr;
final_p = fl6_update_dst(&fl6, np->opt, &final);
fl6.saddr = ireq6->loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
fl6.fl6_sport = inet_rsk(req)->loc_port;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
if (IS_ERR(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));
newnp->daddr = ireq6->rmt_addr;
newnp->saddr = ireq6->loc_addr;
newnp->rcv_saddr = ireq6->loc_addr;
newsk->sk_bound_dev_if = ireq6->iif;
/* Now IPv6 options...
First: no IPv4 options.
*/
newinet->inet_opt = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
/* Clone pktoptions received with SYN */
newnp->pktoptions = NULL;
if (ireq6->pktopts != NULL) {
newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC);
consume_skb(ireq6->pktopts);
ireq6->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
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.
*/
if (np->opt != NULL)
newnp->opt = ipv6_dup_options(newsk, np->opt);
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (newnp->opt != NULL)
inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
newnp->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 12:07:58 +08:00
inet_csk_prepare_forced_close(newsk);
dccp_done(newsk);
goto out;
}
__inet6_hash(newsk, NULL);
return newsk;
out_overflow:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out_nonewsk:
dst_release(dst);
out:
NET_INC_STATS_BH(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 (sk->sk_state == DCCP_LISTEN) {
struct sock *nsk = dccp_v6_hnd_req(sk, skb);
if (nsk == NULL)
goto discard;
/*
* Queue it on the new socket if the new socket is active,
* otherwise we just shortcircuit this and continue with
* the new socket..
*/
if (nsk != sk) {
if (dccp_child_process(sk, nsk, skb))
goto reset;
if (opt_skb != NULL)
__kfree_skb(opt_skb);
return 0;
}
}
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;
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);
/* Step 2:
* Look up flow ID in table and get corresponding socket */
sk = __inet6_lookup_skb(&dccp_hashinfo, skb,
dh->dccph_sport, dh->dccph_dport);
/*
* Step 2:
* If no socket ...
*/
if (sk == NULL) {
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;
}
/*
* 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;
return sk_receive_skb(sk, skb, 1) ? -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:
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 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;
usin->sin6_addr = flowlabel->dst;
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;
}
np->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;
}
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr);
return err;
}
if (!ipv6_addr_any(&np->rcv_saddr))
saddr = &np->rcv_saddr;
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = np->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));
final_p = fl6_update_dst(&fl6, np->opt, &final);
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto failure;
}
if (saddr == NULL) {
saddr = &fl6.saddr;
np->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 (np->opt != NULL)
icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
np->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,
np->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),
[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 20:06:04 +08:00
.bind_conflict = inet6_csk_bind_conflict,
#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 = dccp_v6_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 20:06:04 +08:00
.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 20:06:04 +08:00
.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);
}
static struct pernet_operations dccp_v6_ops = {
.init = dccp_v6_init_net,
.exit = dccp_v6_exit_net,
};
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");