Something went wrong. Try again.
(I'm so sorry!) Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
Something went wrong. Try again.
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372// SPDX-License-Identifier: GPL-2.0-or-later/* SCTP kernel implementation * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2003 International Business Machines, Corp. * Copyright (c) 2001 Intel Corp. * Copyright (c) 2001 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * These functions handle all input from the IP layer into SCTP. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Xingang Guo <xingang.guo@intel.com> * Jon Grimm <jgrimm@us.ibm.com> * Hui Huang <hui.huang@nokia.com> * Daisy Chang <daisyc@us.ibm.com> * Sridhar Samudrala <sri@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> */
#include <linux/types.h>#include <linux/list.h> /* For struct list_head */#include <linux/socket.h>#include <linux/ip.h>#include <linux/time.h> /* For struct timeval */#include <linux/slab.h>#include <net/ip.h>#include <net/icmp.h>#include <net/snmp.h>#include <net/sock.h>#include <net/xfrm.h>#include <net/sctp/sctp.h>#include <net/sctp/sm.h>#include <net/sctp/checksum.h>#include <net/net_namespace.h>#include <linux/rhashtable.h>#include <net/sock_reuseport.h>
/* Forward declarations for internal helpers. */static int sctp_rcv_ootb(struct sk_buff *);static struct sctp_association *__sctp_rcv_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *paddr, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif);static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, const union sctp_addr *daddr, int dif, int sdif);static struct sctp_association *__sctp_lookup_association( struct net *net, const union sctp_addr *local, const union sctp_addr *peer, struct sctp_transport **pt, int dif, int sdif);
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb);
/* Calculate the SCTP checksum of an SCTP packet. */static inline int sctp_rcv_checksum(struct net *net, struct sk_buff *skb){ struct sctphdr *sh = sctp_hdr(skb); __le32 cmp = sh->checksum; __le32 val = sctp_compute_cksum(skb, 0);
if (val != cmp) { /* CRC failure, dump it. */ __SCTP_INC_STATS(net, SCTP_MIB_CHECKSUMERRORS); return -1; } return 0;}
/* * This is the routine which IP calls when receiving an SCTP packet. */int sctp_rcv(struct sk_buff *skb){ struct sock *sk; struct sctp_association *asoc; struct sctp_endpoint *ep = NULL; struct sctp_ep_common *rcvr; struct sctp_transport *transport = NULL; struct sctp_chunk *chunk; union sctp_addr src; union sctp_addr dest; int family; struct sctp_af *af; struct net *net = dev_net(skb->dev); bool is_gso = skb_is_gso(skb) && skb_is_gso_sctp(skb); int dif, sdif;
if (skb->pkt_type != PACKET_HOST) goto discard_it;
__SCTP_INC_STATS(net, SCTP_MIB_INSCTPPACKS);
/* If packet is too small to contain a single chunk, let's not * waste time on it anymore. */ if (skb->len < sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr) + skb_transport_offset(skb)) goto discard_it;
/* If the packet is fragmented and we need to do crc checking, * it's better to just linearize it otherwise crc computing * takes longer. */ if (((!is_gso || skb_cloned(skb)) && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it;
/* Pull up the IP header. */ __skb_pull(skb, skb_transport_offset(skb));
skb->csum_valid = 0; /* Previous value not applicable */ if (skb_csum_unnecessary(skb)) __skb_decr_checksum_unnecessary(skb); else if (!sctp_checksum_disable && !is_gso && sctp_rcv_checksum(net, skb) < 0) goto discard_it; skb->csum_valid = 1;
__skb_pull(skb, sizeof(struct sctphdr));
family = ipver2af(ip_hdr(skb)->version); af = sctp_get_af_specific(family); if (unlikely(!af)) goto discard_it; SCTP_INPUT_CB(skb)->af = af;
/* Initialize local addresses for lookups. */ af->from_skb(&src, skb, 1); af->from_skb(&dest, skb, 0); dif = af->skb_iif(skb); sdif = af->skb_sdif(skb);
/* If the packet is to or from a non-unicast address, * silently discard the packet. * * This is not clearly defined in the RFC except in section * 8.4 - OOTB handling. However, based on the book "Stream Control * Transmission Protocol" 2.1, "It is important to note that the * IP address of an SCTP transport address must be a routable * unicast address. In other words, IP multicast addresses and * IP broadcast addresses cannot be used in an SCTP transport * address." */ if (!af->addr_valid(&src, NULL, skb) || !af->addr_valid(&dest, NULL, skb)) goto discard_it;
asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport, dif, sdif);
if (!asoc) ep = __sctp_rcv_lookup_endpoint(net, skb, &dest, &src, dif, sdif);
/* Retrieve the common input handling substructure. */ rcvr = asoc ? &asoc->base : &ep->base; sk = rcvr->sk;
/* * RFC 2960, 8.4 - Handle "Out of the blue" Packets. * An SCTP packet is called an "out of the blue" (OOTB) * packet if it is correctly formed, i.e., passed the * receiver's checksum check, but the receiver is not * able to identify the association to which this * packet belongs. */ if (!asoc) { if (sctp_rcv_ootb(skb)) { __SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); goto discard_release; } }
if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family)) goto discard_release; nf_reset_ct(skb);
if (sk_filter(sk, skb) || skb->len < sizeof(struct sctp_chunkhdr)) goto discard_release;
/* Create an SCTP packet structure. */ chunk = sctp_chunkify(skb, asoc, sk, GFP_ATOMIC); if (!chunk) goto discard_release; SCTP_INPUT_CB(skb)->chunk = chunk;
/* Remember what endpoint is to handle this packet. */ chunk->rcvr = rcvr;
/* Remember the SCTP header. */ chunk->sctp_hdr = sctp_hdr(skb);
/* Set the source and destination addresses of the incoming chunk. */ sctp_init_addrs(chunk, &src, &dest);
/* Remember where we came from. */ chunk->transport = transport;
/* Acquire access to the sock lock. Note: We are safe from other * bottom halves on this lock, but a user may be in the lock too, * so check if it is busy. */ bh_lock_sock(sk);
if (sk != rcvr->sk) { /* Our cached sk is different from the rcvr->sk. This is * because migrate()/accept() may have moved the association * to a new socket and released all the sockets. So now we * are holding a lock on the old socket while the user may * be doing something with the new socket. Switch our veiw * of the current sk. */ bh_unlock_sock(sk); sk = rcvr->sk; bh_lock_sock(sk); }
if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sctp_add_backlog(sk, skb)) { bh_unlock_sock(sk); sctp_chunk_free(chunk); skb = NULL; /* sctp_chunk_free already freed the skb */ goto discard_release; } __SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_BACKLOG); } else { __SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_SOFTIRQ); sctp_inq_push(&chunk->rcvr->inqueue, chunk); }
bh_unlock_sock(sk);
/* Release the asoc/ep ref we took in the lookup calls. */ if (transport) sctp_transport_put(transport); else sctp_endpoint_put(ep);
return 0;
discard_it: __SCTP_INC_STATS(net, SCTP_MIB_IN_PKT_DISCARDS); kfree_skb(skb); return 0;
discard_release: /* Release the asoc/ep ref we took in the lookup calls. */ if (transport) sctp_transport_put(transport); else sctp_endpoint_put(ep);
goto discard_it;}
/* Process the backlog queue of the socket. Every skb on * the backlog holds a ref on an association or endpoint. * We hold this ref throughout the state machine to make * sure that the structure we need is still around. */int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb){ struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; struct sctp_inq *inqueue = &chunk->rcvr->inqueue; struct sctp_transport *t = chunk->transport; struct sctp_ep_common *rcvr = NULL; int backloged = 0;
rcvr = chunk->rcvr;
/* If the rcvr is dead then the association or endpoint * has been deleted and we can safely drop the chunk * and refs that we are holding. */ if (rcvr->dead) { sctp_chunk_free(chunk); goto done; }
if (unlikely(rcvr->sk != sk)) { /* In this case, the association moved from one socket to * another. We are currently sitting on the backlog of the * old socket, so we need to move. * However, since we are here in the process context we * need to take make sure that the user doesn't own * the new socket when we process the packet. * If the new socket is user-owned, queue the chunk to the * backlog of the new socket without dropping any refs. * Otherwise, we can safely push the chunk on the inqueue. */
sk = rcvr->sk; local_bh_disable(); bh_lock_sock(sk);
if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) sctp_chunk_free(chunk); else backloged = 1; } else sctp_inq_push(inqueue, chunk);
bh_unlock_sock(sk); local_bh_enable();
/* If the chunk was backloged again, don't drop refs */ if (backloged) return 0; } else { if (!sctp_newsk_ready(sk)) { if (!sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) return 0; sctp_chunk_free(chunk); } else { sctp_inq_push(inqueue, chunk); } }
done: /* Release the refs we took in sctp_add_backlog */ if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) sctp_transport_put(t); else if (SCTP_EP_TYPE_SOCKET == rcvr->type) sctp_endpoint_put(sctp_ep(rcvr)); else BUG();
return 0;}
static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb){ struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; struct sctp_transport *t = chunk->transport; struct sctp_ep_common *rcvr = chunk->rcvr; int ret;
ret = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)); if (!ret) { /* Hold the assoc/ep while hanging on the backlog queue. * This way, we know structures we need will not disappear * from us */ if (SCTP_EP_TYPE_ASSOCIATION == rcvr->type) sctp_transport_hold(t); else if (SCTP_EP_TYPE_SOCKET == rcvr->type) sctp_endpoint_hold(sctp_ep(rcvr)); else BUG(); } return ret;
}
/* Handle icmp frag needed error. */void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t, __u32 pmtu){ if (!t || (t->pathmtu <= pmtu && t->pl.probe_size + sctp_transport_pl_hlen(t) <= pmtu)) return;
if (sock_owned_by_user(sk)) { atomic_set(&t->mtu_info, pmtu); asoc->pmtu_pending = 1; t->pmtu_pending = 1; return; }
if (!(t->param_flags & SPP_PMTUD_ENABLE)) /* We can't allow retransmitting in such case, as the * retransmission would be sized just as before, and thus we * would get another icmp, and retransmit again. */ return;
/* Update transports view of the MTU. Return if no update was needed. * If an update wasn't needed/possible, it also doesn't make sense to * try to retransmit now. */ if (!sctp_transport_update_pmtu(t, pmtu)) return;
/* Update association pmtu. */ sctp_assoc_sync_pmtu(asoc);
/* Retransmit with the new pmtu setting. */ sctp_retransmit(&asoc->outqueue, t, SCTP_RTXR_PMTUD);}
void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t, struct sk_buff *skb){ struct dst_entry *dst;
if (sock_owned_by_user(sk) || !t) return; dst = sctp_transport_dst_check(t); if (dst) dst->ops->redirect(dst, sk, skb);}
/* * SCTP Implementer's Guide, 2.37 ICMP handling procedures * * ICMP8) If the ICMP code is a "Unrecognized next header type encountered" * or a "Protocol Unreachable" treat this message as an abort * with the T bit set. * * This function sends an event to the state machine, which will abort the * association. * */void sctp_icmp_proto_unreachable(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t){ if (sock_owned_by_user(sk)) { if (timer_pending(&t->proto_unreach_timer)) return; else { sctp_transport_hold(t); if (mod_timer(&t->proto_unreach_timer, jiffies + (HZ / 20))) sctp_transport_put(t); } } else { struct net *net = sock_net(sk);
pr_debug("%s: unrecognized next header type " "encountered!\n", __func__);
if (timer_delete(&t->proto_unreach_timer)) sctp_transport_put(t);
sctp_do_sm(net, SCTP_EVENT_T_OTHER, SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), asoc->state, asoc->ep, asoc, t, GFP_ATOMIC); }}
/* Common lookup code for icmp/icmpv6 error handler. */struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, struct sctphdr *sctphdr, struct sctp_association **app, struct sctp_transport **tpp){ struct sctp_init_chunk *chunkhdr, _chunkhdr; union sctp_addr saddr; union sctp_addr daddr; struct sctp_af *af; struct sock *sk = NULL; struct sctp_association *asoc; struct sctp_transport *transport = NULL; __u32 vtag = ntohl(sctphdr->vtag); int sdif = inet_sdif(skb); int dif = inet_iif(skb);
*app = NULL; *tpp = NULL;
af = sctp_get_af_specific(family); if (unlikely(!af)) { return NULL; }
/* Initialize local addresses for lookups. */ af->from_skb(&saddr, skb, 1); af->from_skb(&daddr, skb, 0);
/* Look for an association that matches the incoming ICMP error * packet. */ asoc = __sctp_lookup_association(net, &saddr, &daddr, &transport, dif, sdif); if (!asoc) return NULL;
sk = asoc->base.sk;
/* RFC 4960, Appendix C. ICMP Handling * * ICMP6) An implementation MUST validate that the Verification Tag * contained in the ICMP message matches the Verification Tag of * the peer. If the Verification Tag is not 0 and does NOT * match, discard the ICMP message. If it is 0 and the ICMP * message contains enough bytes to verify that the chunk type is * an INIT chunk and that the Initiate Tag matches the tag of the * peer, continue with ICMP7. If the ICMP message is too short * or the chunk type or the Initiate Tag does not match, silently * discard the packet. */ if (vtag == 0) { /* chunk header + first 4 octects of init header */ chunkhdr = skb_header_pointer(skb, skb_transport_offset(skb) + sizeof(struct sctphdr), sizeof(struct sctp_chunkhdr) + sizeof(__be32), &_chunkhdr); if (!chunkhdr || chunkhdr->chunk_hdr.type != SCTP_CID_INIT || ntohl(chunkhdr->init_hdr.init_tag) != asoc->c.my_vtag) goto out;
} else if (vtag != asoc->c.peer_vtag) { goto out; }
bh_lock_sock(sk);
/* If too many ICMPs get dropped on busy * servers this needs to be solved differently. */ if (sock_owned_by_user(sk)) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS);
*app = asoc; *tpp = transport; return sk;
out: sctp_transport_put(transport); return NULL;}
/* Common cleanup code for icmp/icmpv6 error handler. */void sctp_err_finish(struct sock *sk, struct sctp_transport *t) __releases(&((__sk)->sk_lock.slock)){ bh_unlock_sock(sk); sctp_transport_put(t);}
static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb, __u8 type, __u8 code, __u32 info){ struct sctp_association *asoc = t->asoc; struct sock *sk = asoc->base.sk; int err = 0;
switch (type) { case ICMP_PARAMETERPROB: err = EPROTO; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) return; if (code == ICMP_FRAG_NEEDED) { sctp_icmp_frag_needed(sk, asoc, t, SCTP_TRUNC4(info)); return; } if (code == ICMP_PROT_UNREACH) { sctp_icmp_proto_unreachable(sk, asoc, t); return; } err = icmp_err_convert[code].errno; break; case ICMP_TIME_EXCEEDED: if (code == ICMP_EXC_FRAGTIME) return;
err = EHOSTUNREACH; break; case ICMP_REDIRECT: sctp_icmp_redirect(sk, t, skb); return; default: return; } if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { sk->sk_err = err; sk_error_report(sk); } else { /* Only an error on timeout */ WRITE_ONCE(sk->sk_err_soft, err); }}
/* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should * be closed and the error returned to the user. If err > 0 * it's just the icmp type << 8 | icmp code. After adjustment * header points to the first 8 bytes of the sctp header. We need * to find the appropriate port. * * The locking strategy used here is very "optimistic". When * someone else accesses the socket the ICMP is just dropped * and for some paths there is no check at all. * A more general error queue to queue errors for later handling * is probably better. * */int sctp_v4_err(struct sk_buff *skb, __u32 info){ const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct net *net = dev_net(skb->dev); struct sctp_transport *transport; struct sctp_association *asoc; __u16 saveip, savesctp; struct sock *sk;
/* Fix up skb to look at the embedded net header. */ saveip = skb->network_header; savesctp = skb->transport_header; skb_reset_network_header(skb); skb_set_transport_header(skb, iph->ihl * 4); sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &transport); /* Put back, the original values. */ skb->network_header = saveip; skb->transport_header = savesctp; if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; }
sctp_v4_err_handle(transport, skb, type, code, info); sctp_err_finish(sk, transport);
return 0;}
int sctp_udp_v4_err(struct sock *sk, struct sk_buff *skb){ struct net *net = dev_net(skb->dev); struct sctp_association *asoc; struct sctp_transport *t; struct icmphdr *hdr; __u32 info = 0;
skb->transport_header += sizeof(struct udphdr); sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &t); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; }
skb->transport_header -= sizeof(struct udphdr); hdr = (struct icmphdr *)(skb_network_header(skb) - sizeof(struct icmphdr)); if (hdr->type == ICMP_REDIRECT) { /* can't be handled without outer iphdr known, leave it to udp_err */ sctp_err_finish(sk, t); return 0; } if (hdr->type == ICMP_DEST_UNREACH && hdr->code == ICMP_FRAG_NEEDED) info = ntohs(hdr->un.frag.mtu); sctp_v4_err_handle(t, skb, hdr->type, hdr->code, info);
sctp_err_finish(sk, t); return 1;}
/* * RFC 2960, 8.4 - Handle "Out of the blue" Packets. * * This function scans all the chunks in the OOTB packet to determine if * the packet should be discarded right away. If a response might be needed * for this packet, or, if further processing is possible, the packet will * be queued to a proper inqueue for the next phase of handling. * * Output: * Return 0 - If further processing is needed. * Return 1 - If the packet can be discarded right away. */static int sctp_rcv_ootb(struct sk_buff *skb){ struct sctp_chunkhdr *ch, _ch; int ch_end, offset = 0;
/* Scan through all the chunks in the packet. */ do { /* Make sure we have at least the header there */ if (offset + sizeof(_ch) > skb->len) break;
ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch);
/* Break out if chunk length is less then minimal. */ if (!ch || ntohs(ch->length) < sizeof(_ch)) break;
ch_end = offset + SCTP_PAD4(ntohs(ch->length)); if (ch_end > skb->len) break;
/* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the * receiver MUST silently discard the OOTB packet and take no * further action. */ if (SCTP_CID_ABORT == ch->type) goto discard;
/* RFC 8.4, 6) If the packet contains a SHUTDOWN COMPLETE * chunk, the receiver should silently discard the packet * and take no further action. */ if (SCTP_CID_SHUTDOWN_COMPLETE == ch->type) goto discard;
/* RFC 4460, 2.11.2 * This will discard packets with INIT chunk bundled as * subsequent chunks in the packet. When INIT is first, * the normal INIT processing will discard the chunk. */ if (SCTP_CID_INIT == ch->type && (void *)ch != skb->data) goto discard;
offset = ch_end; } while (ch_end < skb->len);
return 0;
discard: return 1;}
/* Insert endpoint into the hash table. */static int __sctp_hash_endpoint(struct sctp_endpoint *ep){ struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); struct sctp_hashbucket *head; int err = 0;
ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port); head = &sctp_ep_hashtable[ep->hashent];
write_lock(&head->lock); if (sk->sk_reuseport) { bool any = sctp_is_ep_boundall(sk); struct sctp_endpoint *ep2; struct list_head *list; int cnt = 0;
err = 1;
list_for_each(list, &ep->base.bind_addr.address_list) cnt++;
sctp_for_each_hentry(ep2, &head->chain) { struct sock *sk2 = ep2->base.sk;
if (!net_eq(sock_net(sk2), net) || sk2 == sk || !uid_eq(sk_uid(sk2), sk_uid(sk)) || !sk2->sk_reuseport) continue;
err = sctp_bind_addrs_check(sctp_sk(sk2), sctp_sk(sk), cnt); if (!err) { err = reuseport_add_sock(sk, sk2, any); if (err) goto out; break; } else if (err < 0) { goto out; } }
if (err) { err = reuseport_alloc(sk, any); if (err) goto out; } }
hlist_add_head(&ep->node, &head->chain);out: write_unlock(&head->lock); return err;}
/* Add an endpoint to the hash. Local BH-safe. */int sctp_hash_endpoint(struct sctp_endpoint *ep){ int err;
local_bh_disable(); err = __sctp_hash_endpoint(ep); local_bh_enable();
return err;}
/* Remove endpoint from the hash table. */static void __sctp_unhash_endpoint(struct sctp_endpoint *ep){ struct sock *sk = ep->base.sk; struct sctp_hashbucket *head;
ep->hashent = sctp_ep_hashfn(sock_net(sk), ep->base.bind_addr.port);
head = &sctp_ep_hashtable[ep->hashent];
write_lock(&head->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); hlist_del_init(&ep->node); write_unlock(&head->lock);}
/* Remove endpoint from the hash. Local BH-safe. */void sctp_unhash_endpoint(struct sctp_endpoint *ep){ local_bh_disable(); __sctp_unhash_endpoint(ep); local_bh_enable();}
static inline __u32 sctp_hashfn(const struct net *net, __be16 lport, const union sctp_addr *paddr, __u32 seed){ __u32 addr;
if (paddr->sa.sa_family == AF_INET6) addr = jhash(&paddr->v6.sin6_addr, 16, seed); else addr = (__force __u32)paddr->v4.sin_addr.s_addr;
return jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 | (__force __u32)lport, net_hash_mix(net), seed);}
/* Look up an endpoint. */static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, const union sctp_addr *paddr, int dif, int sdif){ struct sctp_hashbucket *head; struct sctp_endpoint *ep; struct sock *sk; __be16 lport; int hash;
lport = laddr->v4.sin_port; hash = sctp_ep_hashfn(net, ntohs(lport)); head = &sctp_ep_hashtable[hash]; read_lock(&head->lock); sctp_for_each_hentry(ep, &head->chain) { if (sctp_endpoint_is_match(ep, net, laddr, dif, sdif)) goto hit; }
ep = sctp_sk(net->sctp.ctl_sock)->ep;
hit: sk = ep->base.sk; if (sk->sk_reuseport) { __u32 phash = sctp_hashfn(net, lport, paddr, 0);
sk = reuseport_select_sock(sk, phash, skb, sizeof(struct sctphdr)); if (sk) ep = sctp_sk(sk)->ep; } sctp_endpoint_hold(ep); read_unlock(&head->lock); return ep;}
/* rhashtable for transport */struct sctp_hash_cmp_arg { const union sctp_addr *paddr; const struct net *net; __be16 lport;};
static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr){ struct sctp_transport *t = (struct sctp_transport *)ptr; const struct sctp_hash_cmp_arg *x = arg->key; int err = 1;
if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr)) return err; if (!sctp_transport_hold(t)) return err;
if (!net_eq(t->asoc->base.net, x->net)) goto out; if (x->lport != htons(t->asoc->base.bind_addr.port)) goto out;
err = 0;out: sctp_transport_put(t); return err;}
static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed){ const struct sctp_transport *t = data;
return sctp_hashfn(t->asoc->base.net, htons(t->asoc->base.bind_addr.port), &t->ipaddr, seed);}
static inline __u32 sctp_hash_key(const void *data, u32 len, u32 seed){ const struct sctp_hash_cmp_arg *x = data;
return sctp_hashfn(x->net, x->lport, x->paddr, seed);}
static const struct rhashtable_params sctp_hash_params = { .head_offset = offsetof(struct sctp_transport, node), .hashfn = sctp_hash_key, .obj_hashfn = sctp_hash_obj, .obj_cmpfn = sctp_hash_cmp, .automatic_shrinking = true,};
int sctp_transport_hashtable_init(void){ return rhltable_init(&sctp_transport_hashtable, &sctp_hash_params);}
void sctp_transport_hashtable_destroy(void){ rhltable_destroy(&sctp_transport_hashtable);}
int sctp_hash_transport(struct sctp_transport *t){ struct sctp_transport *transport; struct rhlist_head *tmp, *list; struct sctp_hash_cmp_arg arg; int err;
if (t->asoc->temp) return 0;
arg.net = t->asoc->base.net; arg.paddr = &t->ipaddr; arg.lport = htons(t->asoc->base.bind_addr.port);
rcu_read_lock(); list = rhltable_lookup(&sctp_transport_hashtable, &arg, sctp_hash_params);
rhl_for_each_entry_rcu(transport, tmp, list, node) if (transport->asoc->ep == t->asoc->ep) { rcu_read_unlock(); return -EEXIST; } rcu_read_unlock();
err = rhltable_insert_key(&sctp_transport_hashtable, &arg, &t->node, sctp_hash_params); if (err) pr_err_once("insert transport fail, errno %d\n", err);
return err;}
void sctp_unhash_transport(struct sctp_transport *t){ if (t->asoc->temp) return;
rhltable_remove(&sctp_transport_hashtable, &t->node, sctp_hash_params);}
bool sctp_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif){ bool l3mdev_accept = true;
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) l3mdev_accept = !!READ_ONCE(net->sctp.l3mdev_accept);#endif return inet_bound_dev_eq(l3mdev_accept, bound_dev_if, dif, sdif);}
/* return a transport with holding it */struct sctp_transport *sctp_addrs_lookup_transport( struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, int dif, int sdif){ struct rhlist_head *tmp, *list; struct sctp_transport *t; int bound_dev_if; struct sctp_hash_cmp_arg arg = { .paddr = paddr, .net = net, .lport = laddr->v4.sin_port, };
list = rhltable_lookup(&sctp_transport_hashtable, &arg, sctp_hash_params);
rhl_for_each_entry_rcu(t, tmp, list, node) { if (!sctp_transport_hold(t)) continue;
bound_dev_if = READ_ONCE(t->asoc->base.sk->sk_bound_dev_if); if (sctp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif) && sctp_bind_addr_match(&t->asoc->base.bind_addr, laddr, sctp_sk(t->asoc->base.sk))) return t; sctp_transport_put(t); }
return NULL;}
/* return a transport without holding it, as it's only used under sock lock */struct sctp_transport *sctp_epaddr_lookup_transport( const struct sctp_endpoint *ep, const union sctp_addr *paddr){ struct rhlist_head *tmp, *list; struct sctp_transport *t; struct sctp_hash_cmp_arg arg = { .paddr = paddr, .net = ep->base.net, .lport = htons(ep->base.bind_addr.port), };
list = rhltable_lookup(&sctp_transport_hashtable, &arg, sctp_hash_params);
rhl_for_each_entry_rcu(t, tmp, list, node) if (ep == t->asoc->ep) return t;
return NULL;}
/* Look up an association. */static struct sctp_association *__sctp_lookup_association( struct net *net, const union sctp_addr *local, const union sctp_addr *peer, struct sctp_transport **pt, int dif, int sdif){ struct sctp_transport *t; struct sctp_association *asoc = NULL;
t = sctp_addrs_lookup_transport(net, local, peer, dif, sdif); if (!t) goto out;
asoc = t->asoc; *pt = t;
out: return asoc;}
/* Look up an association. protected by RCU read lock */staticstruct sctp_association *sctp_lookup_association(struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, struct sctp_transport **transportp, int dif, int sdif){ struct sctp_association *asoc;
rcu_read_lock(); asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); rcu_read_unlock();
return asoc;}
/* Is there an association matching the given local and peer addresses? */bool sctp_has_association(struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, int dif, int sdif){ struct sctp_transport *transport;
if (sctp_lookup_association(net, laddr, paddr, &transport, dif, sdif)) { sctp_transport_put(transport); return true; }
return false;}
/* * SCTP Implementors Guide, 2.18 Handling of address * parameters within the INIT or INIT-ACK. * * D) When searching for a matching TCB upon reception of an INIT * or INIT-ACK chunk the receiver SHOULD use not only the * source address of the packet (containing the INIT or * INIT-ACK) but the receiver SHOULD also use all valid * address parameters contained within the chunk. * * 2.18.3 Solution description * * This new text clearly specifies to an implementor the need * to look within the INIT or INIT-ACK. Any implementation that * does not do this, may not be able to establish associations * in certain circumstances. * */static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif){ struct sctp_association *asoc; union sctp_addr addr; union sctp_addr *paddr = &addr; struct sctphdr *sh = sctp_hdr(skb); union sctp_params params; struct sctp_init_chunk *init; struct sctp_af *af;
/* * This code will NOT touch anything inside the chunk--it is * strictly READ-ONLY. * * RFC 2960 3 SCTP packet Format * * Multiple chunks can be bundled into one SCTP packet up to * the MTU size, except for the INIT, INIT ACK, and SHUTDOWN * COMPLETE chunks. These chunks MUST NOT be bundled with any * other chunk in a packet. See Section 6.10 for more details * on chunk bundling. */
/* Find the start of the TLVs and the end of the chunk. This is * the region we search for address parameters. */ init = (struct sctp_init_chunk *)skb->data;
/* Walk the parameters looking for embedded addresses. */ sctp_walk_params(params, init) {
/* Note: Ignoring hostname addresses. */ af = sctp_get_af_specific(param_type2af(params.p->type)); if (!af) continue;
if (!af->from_addr_param(paddr, params.addr, sh->source, 0)) continue;
asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); if (asoc) return asoc; }
return NULL;}
/* ADD-IP, Section 5.2 * When an endpoint receives an ASCONF Chunk from the remote peer * special procedures may be needed to identify the association the * ASCONF Chunk is associated with. To properly find the association * the following procedures SHOULD be followed: * * D2) If the association is not found, use the address found in the * Address Parameter TLV combined with the port number found in the * SCTP common header. If found proceed to rule D4. * * D2-ext) If more than one ASCONF Chunks are packed together, use the * address found in the ASCONF Address Parameter TLV of each of the * subsequent ASCONF Chunks. If found, proceed to rule D4. */static struct sctp_association *__sctp_rcv_asconf_lookup( struct net *net, struct sctp_chunkhdr *ch, const union sctp_addr *laddr, __be16 peer_port, struct sctp_transport **transportp, int dif, int sdif){ struct sctp_addip_chunk *asconf = (struct sctp_addip_chunk *)ch; struct sctp_af *af; union sctp_addr_param *param; union sctp_addr paddr;
if (ntohs(ch->length) < sizeof(*asconf) + sizeof(struct sctp_paramhdr)) return NULL;
/* Skip over the ADDIP header and find the Address parameter */ param = (union sctp_addr_param *)(asconf + 1);
/* The whole address parameter must lie within the chunk before * af->from_addr_param() reads the variable-length address; otherwise a * truncated trailing ASCONF chunk lets it read uninitialized bytes past * the parameter. */ if (sizeof(*asconf) + ntohs(param->p.length) > ntohs(ch->length)) return NULL;
af = sctp_get_af_specific(param_type2af(param->p.type)); if (unlikely(!af)) return NULL;
if (!af->from_addr_param(&paddr, param, peer_port, 0)) return NULL;
return __sctp_lookup_association(net, laddr, &paddr, transportp, dif, sdif);}
/* SCTP-AUTH, Section 6.3:* If the receiver does not find a STCB for a packet containing an AUTH* chunk as the first chunk and not a COOKIE-ECHO chunk as the second* chunk, it MUST use the chunks after the AUTH chunk to look up an existing* association.** This means that any chunks that can help us identify the association need* to be looked at to find this association.*/static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif){ struct sctp_association *asoc = NULL; struct sctp_chunkhdr *ch; int have_auth = 0; unsigned int chunk_num = 1; __u8 *ch_end;
/* Walk through the chunks looking for AUTH or ASCONF chunks * to help us find the association. */ ch = (struct sctp_chunkhdr *)skb->data; do { /* Break out if chunk length is less then minimal. */ if (ntohs(ch->length) < sizeof(*ch)) break;
ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); if (ch_end > skb_tail_pointer(skb)) break;
switch (ch->type) { case SCTP_CID_AUTH: have_auth = chunk_num; break;
case SCTP_CID_COOKIE_ECHO: /* If a packet arrives containing an AUTH chunk as * a first chunk, a COOKIE-ECHO chunk as the second * chunk, and possibly more chunks after them, and * the receiver does not have an STCB for that * packet, then authentication is based on * the contents of the COOKIE- ECHO chunk. */ if (have_auth == 1 && chunk_num == 2) return NULL; break;
case SCTP_CID_ASCONF: if (have_auth || net->sctp.addip_noauth) asoc = __sctp_rcv_asconf_lookup( net, ch, laddr, sctp_hdr(skb)->source, transportp, dif, sdif); break; default: break; }
if (asoc) break;
ch = (struct sctp_chunkhdr *)ch_end; chunk_num++; } while (ch_end + sizeof(*ch) < skb_tail_pointer(skb));
return asoc;}
/* * There are circumstances when we need to look inside the SCTP packet * for information to help us find the association. Examples * include looking inside of INIT/INIT-ACK chunks or after the AUTH * chunks. */static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif){ struct sctp_chunkhdr *ch;
/* We do not allow GSO frames here as we need to linearize and * then cannot guarantee frame boundaries. This shouldn't be an * issue as packets hitting this are mostly INIT or INIT-ACK and * those cannot be on GSO-style anyway. */ if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return NULL;
ch = (struct sctp_chunkhdr *)skb->data;
/* The code below will attempt to walk the chunk and extract * parameter information. Before we do that, we need to verify * that the chunk length doesn't cause overflow. Otherwise, we'll * walk off the end. */ if (SCTP_PAD4(ntohs(ch->length)) > skb->len) return NULL;
/* If this is INIT/INIT-ACK look inside the chunk too. */ if (ch->type == SCTP_CID_INIT || ch->type == SCTP_CID_INIT_ACK) return __sctp_rcv_init_lookup(net, skb, laddr, transportp, dif, sdif);
return __sctp_rcv_walk_lookup(net, skb, laddr, transportp, dif, sdif);}
/* Lookup an association for an inbound skb. */static struct sctp_association *__sctp_rcv_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *paddr, const union sctp_addr *laddr, struct sctp_transport **transportp, int dif, int sdif){ struct sctp_association *asoc;
asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); if (asoc) goto out;
/* Further lookup for INIT/INIT-ACK packets. * SCTP Implementors Guide, 2.18 Handling of address * parameters within the INIT or INIT-ACK. */ asoc = __sctp_rcv_lookup_harder(net, skb, laddr, transportp, dif, sdif); if (asoc) goto out;
if (paddr->sa.sa_family == AF_INET) pr_debug("sctp: asoc not found for src:%pI4:%d dst:%pI4:%d\n", &laddr->v4.sin_addr, ntohs(laddr->v4.sin_port), &paddr->v4.sin_addr, ntohs(paddr->v4.sin_port)); else pr_debug("sctp: asoc not found for src:%pI6:%d dst:%pI6:%d\n", &laddr->v6.sin6_addr, ntohs(laddr->v6.sin6_port), &paddr->v6.sin6_addr, ntohs(paddr->v6.sin6_port));
out: return asoc;}