X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fsctp%2Fsocket.c;h=ca44917872d2553b98f4e2f3601f95fe0f2c414f;hb=b2e75eff5e859d0c294e7405958362b26a423c6e;hp=7cd58ef84eda9ee129680c76971e36a2843a4c43;hpb=06393009000779b00a558fd2f280882cc7dc2008;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 7cd58ef..ca44917 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1,4 +1,4 @@ -/* SCTP kernel reference Implementation +/* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. @@ -6,7 +6,7 @@ * Copyright (c) 2001-2002 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * - * This file is part of the SCTP kernel reference Implementation + * This file is part of the SCTP kernel implementation * * These functions interface with the sockets layer to implement the * SCTP Extensions for the Sockets API. @@ -15,13 +15,13 @@ * functions--this file is the functions which populate the struct proto * for SCTP which is the BOTTOM of the sockets interface. * - * The SCTP reference implementation is free software; + * This SCTP implementation 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, or (at your option) * any later version. * - * The SCTP reference implementation is distributed in the hope that it + * This SCTP implementation is distributed in the hope that it * will be useful, but WITHOUT ANY WARRANTY; without even the implied * ************************ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. @@ -67,6 +67,7 @@ #include #include #include +#include #include #include @@ -114,9 +115,9 @@ extern int sysctl_sctp_wmem[3]; static int sctp_memory_pressure; static atomic_t sctp_memory_allocated; -static atomic_t sctp_sockets_allocated; +struct percpu_counter sctp_sockets_allocated; -static void sctp_enter_memory_pressure(void) +static void sctp_enter_memory_pressure(struct sock *sk) { sctp_memory_pressure = 1; } @@ -130,7 +131,7 @@ static inline int sctp_wspace(struct sctp_association *asoc) if (asoc->ep->sndbuf_policy) amt = asoc->sndbuf_used; else - amt = atomic_read(&asoc->base.sk->sk_wmem_alloc); + amt = sk_wmem_alloc_get(asoc->base.sk); if (amt >= asoc->base.sk->sk_sndbuf) { if (asoc->base.sk->sk_userlocks & SOCK_SNDBUF_LOCK) @@ -174,7 +175,8 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) sizeof(struct sctp_chunk); atomic_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); - sk_charge_skb(sk, chunk->skb); + sk->sk_wmem_queued += chunk->skb->truesize; + sk_mem_charge(sk, chunk->skb->truesize); } /* Verify that this is a valid address. */ @@ -307,9 +309,16 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, if (len < sizeof (struct sockaddr)) return NULL; - /* Does this PF support this AF? */ - if (!opt->pf->af_supported(addr->sa.sa_family, opt)) - return NULL; + /* V4 mapped address are really of AF_INET family */ + if (addr->sa.sa_family == AF_INET6 && + ipv6_addr_v4mapped(&addr->v6.sin6_addr)) { + if (!opt->pf->af_supported(AF_INET, opt)) + return NULL; + } else { + /* Does this PF support this AF? */ + if (!opt->pf->af_supported(addr->sa.sa_family, opt)) + return NULL; + } /* If we get this far, af is valid. */ af = sctp_get_af_specific(addr->sa.sa_family); @@ -369,32 +378,33 @@ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; + /* See if the address matches any of the addresses we may have + * already bound before checking against other endpoints. + */ + if (sctp_bind_addr_match(bp, addr, sp)) + return -EINVAL; + /* Make sure we are allowed to bind here. * The function sctp_get_port_local() does duplicate address * detection. */ addr->v4.sin_port = htons(snum); if ((ret = sctp_get_port_local(sk, addr))) { - if (ret == (long) sk) { - /* This endpoint has a conflicting address. */ - return -EINVAL; - } else { - return -EADDRINUSE; - } + return -EADDRINUSE; } /* Refresh ephemeral port. */ if (!bp->port) - bp->port = inet_sk(sk)->num; + bp->port = inet_sk(sk)->inet_num; /* Add the address to the bind address list. * Use GFP_ATOMIC since BHs will be disabled. */ - ret = sctp_add_bind_addr(bp, addr, 1, GFP_ATOMIC); + ret = sctp_add_bind_addr(bp, addr, SCTP_ADDR_SRC, GFP_ATOMIC); /* Copy back into socket for getsockname() use. */ if (!ret) { - inet_sk(sk)->sport = htons(inet_sk(sk)->num); + inet_sk(sk)->inet_sport = htons(inet_sk(sk)->inet_num); af->to_sk_saddr(addr, sk); } @@ -512,7 +522,6 @@ static int sctp_send_asconf_add_ip(struct sock *sk, union sctp_addr saveaddr; void *addr_buf; struct sctp_af *af; - struct list_head *pos; struct list_head *p; int i; int retval = 0; @@ -524,10 +533,9 @@ static int sctp_send_asconf_add_ip(struct sock *sk, ep = sp->ep; SCTP_DEBUG_PRINTK("%s: (sk: %p, addrs: %p, addrcnt: %d)\n", - __FUNCTION__, sk, addrs, addrcnt); + __func__, sk, addrs, addrcnt); - list_for_each(pos, &ep->asocs) { - asoc = list_entry(pos, struct sctp_association, asocs); + list_for_each_entry(asoc, &ep->asocs, asocs) { if (!asoc->peer.asconf_capable) continue; @@ -585,8 +593,8 @@ static int sctp_send_asconf_add_ip(struct sock *sk, addr = (union sctp_addr *)addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); memcpy(&saveaddr, addr, af->sockaddr_len); - retval = sctp_add_bind_addr(bp, &saveaddr, 0, - GFP_ATOMIC); + retval = sctp_add_bind_addr(bp, &saveaddr, + SCTP_ADDR_NEW, GFP_ATOMIC); addr_buf += af->sockaddr_len; } } @@ -660,7 +668,7 @@ static int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt) * socket routing and failover schemes. Refer to comments in * sctp_do_bind(). -daisy */ - retval = sctp_del_bind_addr(bp, sa_addr, call_rcu); + retval = sctp_del_bind_addr(bp, sa_addr); addr_buf += af->sockaddr_len; err_bindx_rem: @@ -698,7 +706,6 @@ static int sctp_send_asconf_del_ip(struct sock *sk, union sctp_addr *laddr; void *addr_buf; struct sctp_af *af; - struct list_head *pos, *pos1; struct sctp_sockaddr_entry *saddr; int i; int retval = 0; @@ -710,10 +717,9 @@ static int sctp_send_asconf_del_ip(struct sock *sk, ep = sp->ep; SCTP_DEBUG_PRINTK("%s: (sk: %p, addrs: %p, addrcnt: %d)\n", - __FUNCTION__, sk, addrs, addrcnt); + __func__, sk, addrs, addrcnt); - list_for_each(pos, &ep->asocs) { - asoc = list_entry(pos, struct sctp_association, asocs); + list_for_each_entry(asoc, &ep->asocs, asocs) { if (!asoc->peer.asconf_capable) continue; @@ -777,7 +783,7 @@ static int sctp_send_asconf_del_ip(struct sock *sk, af = sctp_get_af_specific(laddr->v4.sin_family); list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, laddr)) - saddr->use_as_src = 0; + saddr->state = SCTP_ADDR_DEL; } addr_buf += af->sockaddr_len; } @@ -786,9 +792,8 @@ static int sctp_send_asconf_del_ip(struct sock *sk, * as some of the addresses in the bind address list are * about to be deleted and cannot be used as source addresses. */ - list_for_each(pos1, &asoc->peer.transport_addr_list) { - transport = list_entry(pos1, struct sctp_transport, - transports); + list_for_each_entry(transport, &asoc->peer.transport_addr_list, + transports) { dst_release(transport->dst); sctp_transport_route(transport, NULL, sctp_sk(asoc->base.sk)); @@ -960,7 +965,8 @@ out: */ static int __sctp_connect(struct sock* sk, struct sockaddr *kaddrs, - int addrs_size) + int addrs_size, + sctp_assoc_t *assoc_id) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -1075,6 +1081,13 @@ static int __sctp_connect(struct sock* sk, err = -ENOMEM; goto out_free; } + + err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, + GFP_KERNEL); + if (err < 0) { + goto out_free; + } + } /* Prime the peer's transport structures. */ @@ -1090,9 +1103,13 @@ static int __sctp_connect(struct sock* sk, walk_size += af->sockaddr_len; } - err = sctp_assoc_set_bind_addr_from_ep(asoc, GFP_KERNEL); - if (err < 0) { - goto out_free; + /* In case the user of sctp_connectx() wants an association + * id back, assign one now. + */ + if (assoc_id) { + err = sctp_assoc_set_id(asoc, GFP_KERNEL); + if (err < 0) + goto out_free; } err = sctp_primitive_ASSOCIATE(asoc, NULL); @@ -1101,7 +1118,7 @@ static int __sctp_connect(struct sock* sk, } /* Initialize sk's dport and daddr for getpeername() */ - inet_sk(sk)->dport = htons(asoc->peer.port); + inet_sk(sk)->inet_dport = htons(asoc->peer.port); af = sctp_get_af_specific(sa_addr->sa.sa_family); af->to_sk_daddr(sa_addr, sk); sk->sk_err = 0; @@ -1115,6 +1132,8 @@ static int __sctp_connect(struct sock* sk, timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK); err = sctp_wait_for_connect(asoc, &timeo); + if ((err == 0 || err == -EINPROGRESS) && assoc_id) + *assoc_id = asoc->assoc_id; /* Don't free association on exit. */ asoc = NULL; @@ -1132,7 +1151,8 @@ out_free: /* Helper for tunneling sctp_connectx() requests through sctp_setsockopt() * * API 8.9 - * int sctp_connectx(int sd, struct sockaddr *addrs, int addrcnt); + * int sctp_connectx(int sd, struct sockaddr *addrs, int addrcnt, + * sctp_assoc_t *asoc); * * If sd is an IPv4 socket, the addresses passed must be IPv4 addresses. * If the sd is an IPv6 socket, the addresses passed can either be IPv4 @@ -1148,8 +1168,10 @@ out_free: * representation is termed a "packed array" of addresses). The caller * specifies the number of addresses in the array with addrcnt. * - * On success, sctp_connectx() returns 0. On failure, sctp_connectx() returns - * -1, and sets errno to the appropriate error code. + * On success, sctp_connectx() returns 0. It also sets the assoc_id to + * the association id of the new association. On failure, sctp_connectx() + * returns -1, and sets errno to the appropriate error code. The assoc_id + * is not touched by the kernel. * * For SCTP, the port given in each socket address must be the same, or * sctp_connectx() will fail, setting errno to EINVAL. @@ -1186,17 +1208,18 @@ out_free: * addrs The pointer to the addresses in user land * addrssize Size of the addrs buffer * - * Returns 0 if ok, <0 errno code on error. + * Returns >=0 if ok, <0 errno code on error. */ -SCTP_STATIC int sctp_setsockopt_connectx(struct sock* sk, +SCTP_STATIC int __sctp_setsockopt_connectx(struct sock* sk, struct sockaddr __user *addrs, - int addrs_size) + int addrs_size, + sctp_assoc_t *assoc_id) { int err = 0; struct sockaddr *kaddrs; SCTP_DEBUG_PRINTK("%s - sk %p addrs %p addrs_size %d\n", - __FUNCTION__, sk, addrs, addrs_size); + __func__, sk, addrs, addrs_size); if (unlikely(addrs_size <= 0)) return -EINVAL; @@ -1213,10 +1236,79 @@ SCTP_STATIC int sctp_setsockopt_connectx(struct sock* sk, if (__copy_from_user(kaddrs, addrs, addrs_size)) { err = -EFAULT; } else { - err = __sctp_connect(sk, kaddrs, addrs_size); + err = __sctp_connect(sk, kaddrs, addrs_size, assoc_id); } kfree(kaddrs); + + return err; +} + +/* + * This is an older interface. It's kept for backward compatibility + * to the option that doesn't provide association id. + */ +SCTP_STATIC int sctp_setsockopt_connectx_old(struct sock* sk, + struct sockaddr __user *addrs, + int addrs_size) +{ + return __sctp_setsockopt_connectx(sk, addrs, addrs_size, NULL); +} + +/* + * New interface for the API. The since the API is done with a socket + * option, to make it simple we feed back the association id is as a return + * indication to the call. Error is always negative and association id is + * always positive. + */ +SCTP_STATIC int sctp_setsockopt_connectx(struct sock* sk, + struct sockaddr __user *addrs, + int addrs_size) +{ + sctp_assoc_t assoc_id = 0; + int err = 0; + + err = __sctp_setsockopt_connectx(sk, addrs, addrs_size, &assoc_id); + + if (err) + return err; + else + return assoc_id; +} + +/* + * New (hopefully final) interface for the API. + * We use the sctp_getaddrs_old structure so that use-space library + * can avoid any unnecessary allocations. The only defferent part + * is that we store the actual length of the address buffer into the + * addrs_num structure member. That way we can re-use the existing + * code. + */ +SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_getaddrs_old param; + sctp_assoc_t assoc_id = 0; + int err = 0; + + if (len < sizeof(param)) + return -EINVAL; + + if (copy_from_user(¶m, optval, sizeof(param))) + return -EFAULT; + + err = __sctp_setsockopt_connectx(sk, + (struct sockaddr __user *)param.addrs, + param.addr_num, &assoc_id); + + if (err == 0 || err == -EINPROGRESS) { + if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) + return -EFAULT; + if (put_user(sizeof(assoc_id), optlen)) + return -EFAULT; + } + return err; } @@ -1280,6 +1372,7 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) sctp_lock_sock(sk); sk->sk_shutdown = SHUTDOWN_MASK; + sk->sk_state = SCTP_SS_CLOSING; ep = sctp_sk(sk)->ep; @@ -1396,7 +1489,6 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, long timeo; __u16 sinfo_flags = 0; struct sctp_datamsg *datamsg; - struct list_head *pos; int msg_flags = msg->msg_flags; SCTP_DEBUG_PRINTK("sctp_sendmsg(sk: %p, msg: %p, msg_len: %zu)\n", @@ -1608,6 +1700,11 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, goto out_unlock; } asoc = new_asoc; + err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL); + if (err < 0) { + err = -ENOMEM; + goto out_free; + } /* If the SCTP_INIT ancillary data is specified, set all * the association init values accordingly. @@ -1637,11 +1734,6 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, err = -ENOMEM; goto out_free; } - err = sctp_assoc_set_bind_addr_from_ep(asoc, GFP_KERNEL); - if (err < 0) { - err = -ENOMEM; - goto out_free; - } } /* ASSERT: we have a valid association at this point. */ @@ -1726,28 +1818,29 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, } /* Now send the (possibly) fragmented message. */ - list_for_each(pos, &datamsg->chunks) { - chunk = list_entry(pos, struct sctp_chunk, frag_list); - sctp_datamsg_track(chunk); + list_for_each_entry(chunk, &datamsg->chunks, frag_list) { + sctp_chunk_hold(chunk); /* Do accounting for the write space. */ sctp_set_owner_w(chunk); chunk->transport = chunk_tp; - - /* Send it to the lower layers. Note: all chunks - * must either fail or succeed. The lower layer - * works that way today. Keep it that way or this - * breaks. - */ - err = sctp_primitive_SEND(asoc, chunk); - /* Did the lower layer accept the chunk? */ - if (err) - sctp_chunk_free(chunk); - SCTP_DEBUG_PRINTK("We sent primitively.\n"); } - sctp_datamsg_free(datamsg); + /* Send it to the lower layers. Note: all chunks + * must either fail or succeed. The lower layer + * works that way today. Keep it that way or this + * breaks. + */ + err = sctp_primitive_SEND(asoc, datamsg); + /* Did the lower layer accept the chunk? */ + if (err) + sctp_datamsg_free(datamsg); + else + sctp_datamsg_put(datamsg); + + SCTP_DEBUG_PRINTK("We sent primitively.\n"); + if (err) goto out_free; else @@ -1802,7 +1895,7 @@ static int sctp_skb_pull(struct sk_buff *skb, int len) len -= skb_len; __skb_pull(skb, skb_len); - for (list = skb_shinfo(skb)->frag_list; list; list = list->next) { + skb_walk_frags(skb, list) { rlen = sctp_skb_pull(list, len); skb->len -= (len-rlen); skb->data_len -= (len-rlen); @@ -1876,7 +1969,7 @@ SCTP_STATIC int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, if (err) goto out_free; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (sctp_ulpevent_is_notification(event)) { msg->msg_flags |= MSG_NOTIFICATION; sp->pf->event_msgname(event, msg->msg_name, addr_len); @@ -1910,7 +2003,8 @@ SCTP_STATIC int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, * rwnd by that amount. If all the data in the skb is read, * rwnd is updated when the event is freed. */ - sctp_assoc_rwnd_increase(event->asoc, copied); + if (!sctp_ulpevent_is_notification(event)) + sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) @@ -1944,7 +2038,8 @@ out: * instead a error will be indicated to the user. */ static int sctp_setsockopt_disable_fragments(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { int val; @@ -1960,9 +2055,9 @@ static int sctp_setsockopt_disable_fragments(struct sock *sk, } static int sctp_setsockopt_events(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { - if (optlen != sizeof(struct sctp_event_subscribe)) + if (optlen > sizeof(struct sctp_event_subscribe)) return -EINVAL; if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen)) return -EFAULT; @@ -1981,7 +2076,7 @@ static int sctp_setsockopt_events(struct sock *sk, char __user *optval, * association is closed. */ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); @@ -1992,6 +2087,8 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, return -EINVAL; if (copy_from_user(&sp->autoclose, optval, optlen)) return -EFAULT; + /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */ + sp->autoclose = min_t(long, sp->autoclose, MAX_SCHEDULE_TIMEOUT / HZ); return 0; } @@ -2160,7 +2257,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, sctp_assoc_sync_pmtu(asoc); } else if (asoc) { asoc->pathmtu = params->spp_pathmtu; - sctp_frag_point(sp, params->spp_pathmtu); + sctp_frag_point(asoc, params->spp_pathmtu); } else { sp->pathmtu = params->spp_pathmtu; } @@ -2217,11 +2314,10 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } } - /* Note that unless the spp_flag is set to SPP_PMTUD_ENABLE the value - * of this field is ignored. Note also that a value of zero - * indicates the current setting should be left unchanged. + /* Note that a value of zero indicates the current setting should be + left unchanged. */ - if ((params->spp_flags & SPP_PMTUD_ENABLE) && params->spp_pathmaxrxt) { + if (params->spp_pathmaxrxt) { if (trans) { trans->pathmaxrxt = params->spp_pathmaxrxt; } else if (asoc) { @@ -2235,7 +2331,8 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } static int sctp_setsockopt_peer_addr_params(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_paddrparams params; struct sctp_transport *trans = NULL; @@ -2259,14 +2356,14 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, pmtud_change == SPP_PMTUD || sackdelay_change == SPP_SACKDELAY || params.spp_sackdelay > 500 || - (params.spp_pathmtu - && params.spp_pathmtu < SCTP_DEFAULT_MINSEGMENT)) + (params.spp_pathmtu && + params.spp_pathmtu < SCTP_DEFAULT_MINSEGMENT)) return -EINVAL; /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ - if (!sctp_is_any(( union sctp_addr *)¶ms.spp_address)) { + if (!sctp_is_any(sk, ( union sctp_addr *)¶ms.spp_address)) { trans = sctp_addr_id2transport(sk, ¶ms.spp_address, params.spp_assoc_id); if (!trans) @@ -2299,11 +2396,8 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, * transport. */ if (!trans && asoc) { - struct list_head *pos; - - list_for_each(pos, &asoc->peer.transport_addr_list) { - trans = list_entry(pos, struct sctp_transport, - transports); + list_for_each_entry(trans, &asoc->peer.transport_addr_list, + transports) { sctp_apply_peer_addr_params(¶ms, trans, asoc, sp, hb_change, pmtud_change, sackdelay_change); @@ -2313,74 +2407,98 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, return 0; } -/* 7.1.23. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME) - * - * This options will get or set the delayed ack timer. The time is set - * in milliseconds. If the assoc_id is 0, then this sets or gets the - * endpoints default delayed ack timer value. If the assoc_id field is - * non-zero, then the set or get effects the specified association. - * - * struct sctp_assoc_value { - * sctp_assoc_t assoc_id; - * uint32_t assoc_value; - * }; +/* + * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) + * + * This option will effect the way delayed acks are performed. This + * option allows you to get or set the delayed ack time, in + * milliseconds. It also allows changing the delayed ack frequency. + * Changing the frequency to 1 disables the delayed sack algorithm. If + * the assoc_id is 0, then this sets or gets the endpoints default + * values. If the assoc_id field is non-zero, then the set or get + * effects the specified association for the one to many model (the + * assoc_id field is ignored by the one to one model). Note that if + * sack_delay or sack_freq are 0 when setting this option, then the + * current values will remain unchanged. + * + * struct sctp_sack_info { + * sctp_assoc_t sack_assoc_id; + * uint32_t sack_delay; + * uint32_t sack_freq; + * }; * - * assoc_id - This parameter, indicates which association the - * user is preforming an action upon. Note that if - * this field's value is zero then the endpoints - * default value is changed (effecting future - * associations only). + * sack_assoc_id - This parameter, indicates which association the user + * is performing an action upon. Note that if this field's value is + * zero then the endpoints default value is changed (effecting future + * associations only). * - * assoc_value - This parameter contains the number of milliseconds - * that the user is requesting the delayed ACK timer - * be set to. Note that this value is defined in - * the standard to be between 200 and 500 milliseconds. + * sack_delay - This parameter contains the number of milliseconds that + * the user is requesting the delayed ACK timer be set to. Note that + * this value is defined in the standard to be between 200 and 500 + * milliseconds. * - * Note: a value of zero will leave the value alone, - * but disable SACK delay. A non-zero value will also - * enable SACK delay. + * sack_freq - This parameter contains the number of packets that must + * be received before a sack is sent without waiting for the delay + * timer to expire. The default value for this is 2, setting this + * value to 1 will disable the delayed sack algorithm. */ -static int sctp_setsockopt_delayed_ack_time(struct sock *sk, - char __user *optval, int optlen) +static int sctp_setsockopt_delayed_ack(struct sock *sk, + char __user *optval, unsigned int optlen) { - struct sctp_assoc_value params; + struct sctp_sack_info params; struct sctp_transport *trans = NULL; struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); - if (optlen != sizeof(struct sctp_assoc_value)) - return - EINVAL; + if (optlen == sizeof(struct sctp_sack_info)) { + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; - if (copy_from_user(¶ms, optval, optlen)) - return -EFAULT; + if (params.sack_delay == 0 && params.sack_freq == 0) + return 0; + } else if (optlen == sizeof(struct sctp_assoc_value)) { + printk(KERN_WARNING "SCTP: Use of struct sctp_assoc_value " + "in delayed_ack socket option deprecated\n"); + printk(KERN_WARNING "SCTP: Use struct sctp_sack_info instead\n"); + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; + + if (params.sack_delay == 0) + params.sack_freq = 1; + else + params.sack_freq = 0; + } else + return - EINVAL; /* Validate value parameter. */ - if (params.assoc_value > 500) + if (params.sack_delay > 500) return -EINVAL; - /* Get association, if assoc_id != 0 and the socket is a one + /* Get association, if sack_assoc_id != 0 and the socket is a one * to many style socket, and an association was not found, then * the id was invalid. */ - asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc && params.assoc_id && sctp_style(sk, UDP)) + asoc = sctp_id2assoc(sk, params.sack_assoc_id); + if (!asoc && params.sack_assoc_id && sctp_style(sk, UDP)) return -EINVAL; - if (params.assoc_value) { + if (params.sack_delay) { if (asoc) { asoc->sackdelay = - msecs_to_jiffies(params.assoc_value); + msecs_to_jiffies(params.sack_delay); asoc->param_flags = (asoc->param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_ENABLE; } else { - sp->sackdelay = params.assoc_value; + sp->sackdelay = params.sack_delay; sp->param_flags = (sp->param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_ENABLE; } - } else { + } + + if (params.sack_freq == 1) { if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_SACKDELAY) | @@ -2390,25 +2508,40 @@ static int sctp_setsockopt_delayed_ack_time(struct sock *sk, (sp->param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_DISABLE; } + } else if (params.sack_freq > 1) { + if (asoc) { + asoc->sackfreq = params.sack_freq; + asoc->param_flags = + (asoc->param_flags & ~SPP_SACKDELAY) | + SPP_SACKDELAY_ENABLE; + } else { + sp->sackfreq = params.sack_freq; + sp->param_flags = + (sp->param_flags & ~SPP_SACKDELAY) | + SPP_SACKDELAY_ENABLE; + } } /* If change is for association, also apply to each transport. */ if (asoc) { - struct list_head *pos; - - list_for_each(pos, &asoc->peer.transport_addr_list) { - trans = list_entry(pos, struct sctp_transport, - transports); - if (params.assoc_value) { + list_for_each_entry(trans, &asoc->peer.transport_addr_list, + transports) { + if (params.sack_delay) { trans->sackdelay = - msecs_to_jiffies(params.assoc_value); + msecs_to_jiffies(params.sack_delay); trans->param_flags = (trans->param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_ENABLE; - } else { + } + if (params.sack_freq == 1) { trans->param_flags = (trans->param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_DISABLE; + } else if (params.sack_freq > 1) { + trans->sackfreq = params.sack_freq; + trans->param_flags = + (trans->param_flags & ~SPP_SACKDELAY) | + SPP_SACKDELAY_ENABLE; } } } @@ -2427,7 +2560,7 @@ static int sctp_setsockopt_delayed_ack_time(struct sock *sk, * by the change). With TCP-style sockets, this option is inherited by * sockets derived from a listener socket. */ -static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_initmsg sinit; struct sctp_sock *sp = sctp_sk(sk); @@ -2464,7 +2597,8 @@ static int sctp_setsockopt_initmsg(struct sock *sk, char __user *optval, int opt * to this call if the caller is using the UDP model. */ static int sctp_setsockopt_default_send_param(struct sock *sk, - char __user *optval, int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_sndrcvinfo info; struct sctp_association *asoc; @@ -2503,7 +2637,7 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, * association peer's addresses. */ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_prim prim; struct sctp_transport *trans; @@ -2532,7 +2666,7 @@ static int sctp_setsockopt_primary_addr(struct sock *sk, char __user *optval, * integer boolean flag. */ static int sctp_setsockopt_nodelay(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { int val; @@ -2557,7 +2691,8 @@ static int sctp_setsockopt_nodelay(struct sock *sk, char __user *optval, * be changed. * */ -static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, int optlen) { +static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigned int optlen) +{ struct sctp_rtoinfo rtoinfo; struct sctp_association *asoc; @@ -2609,7 +2744,7 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, int opt * See [SCTP] for more information. * */ -static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_assocparams assocparams; @@ -2630,18 +2765,15 @@ static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int o if (assocparams.sasoc_asocmaxrxt != 0) { __u32 path_sum = 0; int paths = 0; - struct list_head *pos; struct sctp_transport *peer_addr; - list_for_each(pos, &asoc->peer.transport_addr_list) { - peer_addr = list_entry(pos, - struct sctp_transport, - transports); + list_for_each_entry(peer_addr, &asoc->peer.transport_addr_list, + transports) { path_sum += peer_addr->pathmaxrxt; paths++; } - /* Only validate asocmaxrxt if we have more then + /* Only validate asocmaxrxt if we have more than * one path/transport. We do this because path * retransmissions are only counted when we have more * then one path. @@ -2684,7 +2816,7 @@ static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, int o * addresses and a user will receive both PF_INET6 and PF_INET type * addresses on the socket. */ -static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, unsigned int optlen) { int val; struct sctp_sock *sp = sctp_sk(sk); @@ -2702,34 +2834,72 @@ static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, int op } /* - * 7.1.17 Set the maximum fragrmentation size (SCTP_MAXSEG) - * - * This socket option specifies the maximum size to put in any outgoing - * SCTP chunk. If a message is larger than this size it will be + * 8.1.16. Get or Set the Maximum Fragmentation Size (SCTP_MAXSEG) + * This option will get or set the maximum size to put in any outgoing + * SCTP DATA chunk. If a message is larger than this size it will be * fragmented by SCTP into the specified size. Note that the underlying * SCTP implementation may fragment into smaller sized chunks when the * PMTU of the underlying association is smaller than the value set by - * the user. + * the user. The default value for this option is '0' which indicates + * the user is NOT limiting fragmentation and only the PMTU will effect + * SCTP's choice of DATA chunk size. Note also that values set larger + * than the maximum size of an IP datagram will effectively let SCTP + * control fragmentation (i.e. the same as setting this option to 0). + * + * The following structure is used to access and modify this parameter: + * + * struct sctp_assoc_value { + * sctp_assoc_t assoc_id; + * uint32_t assoc_value; + * }; + * + * assoc_id: This parameter is ignored for one-to-one style sockets. + * For one-to-many style sockets this parameter indicates which + * association the user is performing an action upon. Note that if + * this field's value is zero then the endpoints default value is + * changed (effecting future associations only). + * assoc_value: This parameter specifies the maximum size in bytes. */ -static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, int optlen) +static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_assoc_value params; struct sctp_association *asoc; - struct list_head *pos; struct sctp_sock *sp = sctp_sk(sk); int val; - if (optlen < sizeof(int)) + if (optlen == sizeof(int)) { + printk(KERN_WARNING + "SCTP: Use of int in maxseg socket option deprecated\n"); + printk(KERN_WARNING + "SCTP: Use struct sctp_assoc_value instead\n"); + if (copy_from_user(&val, optval, optlen)) + return -EFAULT; + params.assoc_id = 0; + } else if (optlen == sizeof(struct sctp_assoc_value)) { + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; + val = params.assoc_value; + } else return -EINVAL; - if (get_user(val, (int __user *)optval)) - return -EFAULT; + if ((val != 0) && ((val < 8) || (val > SCTP_MAX_CHUNK_LEN))) return -EINVAL; - sp->user_frag = val; - /* Update the frag_point of the existing associations. */ - list_for_each(pos, &(sp->ep->asocs)) { - asoc = list_entry(pos, struct sctp_association, asocs); - asoc->frag_point = sctp_frag_point(sp, asoc->pathmtu); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id && sctp_style(sk, UDP)) + return -EINVAL; + + if (asoc) { + if (val == 0) { + val = asoc->pathmtu; + val -= sp->pf->af->net_header_len; + val -= sizeof(struct sctphdr) + + sizeof(struct sctp_data_chunk); + } + asoc->user_frag = val; + asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu); + } else { + sp->user_frag = val; } return 0; @@ -2745,7 +2915,7 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, int optl * set primary request: */ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -2796,7 +2966,7 @@ static int sctp_setsockopt_peer_primary_addr(struct sock *sk, char __user *optva } static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_setadaptation adaptation; @@ -2825,7 +2995,7 @@ static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval * saved with outbound messages. */ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_assoc_value params; struct sctp_sock *sp; @@ -2876,7 +3046,7 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, */ static int sctp_setsockopt_fragment_interleave(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { int val; @@ -2891,18 +3061,25 @@ static int sctp_setsockopt_fragment_interleave(struct sock *sk, } /* - * 7.1.25. Set or Get the sctp partial delivery point + * 8.1.21. Set or Get the SCTP Partial Delivery Point * (SCTP_PARTIAL_DELIVERY_POINT) + * * This option will set or get the SCTP partial delivery point. This * point is the size of a message where the partial delivery API will be * invoked to help free up rwnd space for the peer. Setting this to a - * lower value will cause partial delivery's to happen more often. The + * lower value will cause partial deliveries to happen more often. The * calls argument is an integer that sets or gets the partial delivery - * point. + * point. Note also that the call will fail if the user attempts to set + * this value larger than the socket receive buffer size. + * + * Note that any single message having a length smaller than or equal to + * the SCTP partial delivery point will be delivered in one single read + * call as long as the user provided buffer is large enough to hold the + * message. */ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { u32 val; @@ -2911,6 +3088,12 @@ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, if (get_user(val, (int __user *)optval)) return -EFAULT; + /* Note: We double the receive buffer from what the user sets + * it to be, also initial rwnd is based on rcvbuf/2. + */ + if (val > (sk->sk_rcvbuf >> 1)) + return -EINVAL; + sctp_sk(sk)->pd_point = val; return 0; /* is this the right error code? */ @@ -2929,19 +3112,38 @@ static int sctp_setsockopt_partial_delivery_point(struct sock *sk, */ static int sctp_setsockopt_maxburst(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { + struct sctp_assoc_value params; + struct sctp_sock *sp; + struct sctp_association *asoc; int val; - - if (optlen != sizeof(int)) + int assoc_id = 0; + + if (optlen == sizeof(int)) { + printk(KERN_WARNING + "SCTP: Use of int in max_burst socket option deprecated\n"); + printk(KERN_WARNING + "SCTP: Use struct sctp_assoc_value instead\n"); + if (copy_from_user(&val, optval, optlen)) + return -EFAULT; + } else if (optlen == sizeof(struct sctp_assoc_value)) { + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; + val = params.assoc_value; + assoc_id = params.assoc_id; + } else return -EINVAL; - if (get_user(val, (int __user *)optval)) - return -EFAULT; - if (val < 0) - return -EINVAL; + sp = sctp_sk(sk); - sctp_sk(sk)->max_burst = val; + if (assoc_id != 0) { + asoc = sctp_id2assoc(sk, assoc_id); + if (!asoc) + return -EINVAL; + asoc->max_burst = val; + } else + sp->max_burst = val; return 0; } @@ -2954,11 +3156,14 @@ static int sctp_setsockopt_maxburst(struct sock *sk, * will only effect future associations on the socket. */ static int sctp_setsockopt_auth_chunk(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authchunk val; + if (!sctp_auth_enable) + return -EACCES; + if (optlen != sizeof(struct sctp_authchunk)) return -EINVAL; if (copy_from_user(&val, optval, optlen)) @@ -2983,12 +3188,16 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, * endpoint requires the peer to use. */ static int sctp_setsockopt_hmac_ident(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_hmacalgo *hmacs; + u32 idents; int err; + if (!sctp_auth_enable) + return -EACCES; + if (optlen < sizeof(struct sctp_hmacalgo)) return -EINVAL; @@ -3001,8 +3210,9 @@ static int sctp_setsockopt_hmac_ident(struct sock *sk, goto out; } - if (hmacs->shmac_num_idents == 0 || - hmacs->shmac_num_idents > SCTP_AUTH_NUM_HMACS) { + idents = hmacs->shmac_num_idents; + if (idents == 0 || idents > SCTP_AUTH_NUM_HMACS || + (idents * sizeof(u16)) > (optlen - sizeof(struct sctp_hmacalgo))) { err = -EINVAL; goto out; } @@ -3021,12 +3231,15 @@ out: */ static int sctp_setsockopt_auth_key(struct sock *sk, char __user *optval, - int optlen) + unsigned int optlen) { struct sctp_authkey *authkey; struct sctp_association *asoc; int ret; + if (!sctp_auth_enable) + return -EACCES; + if (optlen <= sizeof(struct sctp_authkey)) return -EINVAL; @@ -3039,6 +3252,11 @@ static int sctp_setsockopt_auth_key(struct sock *sk, goto out; } + if (authkey->sca_keylength > optlen - sizeof(struct sctp_authkey)) { + ret = -EINVAL; + goto out; + } + asoc = sctp_id2assoc(sk, authkey->sca_assoc_id); if (!asoc && authkey->sca_assoc_id && sctp_style(sk, UDP)) { ret = -EINVAL; @@ -3058,12 +3276,15 @@ out: * the association shared key. */ static int sctp_setsockopt_active_key(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authkeyid val; struct sctp_association *asoc; + if (!sctp_auth_enable) + return -EACCES; + if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; if (copy_from_user(&val, optval, optlen)) @@ -3083,12 +3304,15 @@ static int sctp_setsockopt_active_key(struct sock *sk, * This set option will delete a shared secret key from use. */ static int sctp_setsockopt_del_key(struct sock *sk, - char __user *optval, - int optlen) + char __user *optval, + unsigned int optlen) { struct sctp_authkeyid val; struct sctp_association *asoc; + if (!sctp_auth_enable) + return -EACCES; + if (optlen != sizeof(struct sctp_authkeyid)) return -EINVAL; if (copy_from_user(&val, optval, optlen)) @@ -3124,7 +3348,7 @@ static int sctp_setsockopt_del_key(struct sock *sk, * optlen - the size of the buffer. */ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { int retval = 0; @@ -3158,10 +3382,18 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname, optlen, SCTP_BINDX_REM_ADDR); break; + case SCTP_SOCKOPT_CONNECTX_OLD: + /* 'optlen' is the size of the addresses buffer. */ + retval = sctp_setsockopt_connectx_old(sk, + (struct sockaddr __user *)optval, + optlen); + break; + case SCTP_SOCKOPT_CONNECTX: /* 'optlen' is the size of the addresses buffer. */ - retval = sctp_setsockopt_connectx(sk, (struct sockaddr __user *)optval, - optlen); + retval = sctp_setsockopt_connectx(sk, + (struct sockaddr __user *)optval, + optlen); break; case SCTP_DISABLE_FRAGMENTS: @@ -3180,8 +3412,8 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname, retval = sctp_setsockopt_peer_addr_params(sk, optval, optlen); break; - case SCTP_DELAYED_ACK_TIME: - retval = sctp_setsockopt_delayed_ack_time(sk, optval, optlen); + case SCTP_DELAYED_ACK: + retval = sctp_setsockopt_delayed_ack(sk, optval, optlen); break; case SCTP_PARTIAL_DELIVERY_POINT: retval = sctp_setsockopt_partial_delivery_point(sk, optval, optlen); @@ -3278,7 +3510,7 @@ SCTP_STATIC int sctp_connect(struct sock *sk, struct sockaddr *addr, sctp_lock_sock(sk); SCTP_DEBUG_PRINTK("%s - sk: %p, sockaddr: %p, addr_len: %d\n", - __FUNCTION__, sk, addr, addr_len); + __func__, sk, addr, addr_len); /* Validate addr_len before calling common connect/connectx routine. */ af = sctp_get_af_specific(addr->sa_family); @@ -3288,7 +3520,7 @@ SCTP_STATIC int sctp_connect(struct sock *sk, struct sockaddr *addr, /* Pass correct addr len to common routine (so it knows there * is only one address being passed. */ - err = __sctp_connect(sk, addr, af->sockaddr_len); + err = __sctp_connect(sk, addr, af->sockaddr_len, NULL); } sctp_release_sock(sk); @@ -3440,6 +3672,7 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) sp->pathmaxrxt = sctp_max_retrans_path; sp->pathmtu = 0; // allow default discovery sp->sackdelay = sctp_sack_timeout; + sp->sackfreq = 2; sp->param_flags = SPP_HB_ENABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; @@ -3486,12 +3719,17 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) sp->hmac = NULL; SCTP_DBG_OBJCNT_INC(sock); - atomic_inc(&sctp_sockets_allocated); + + local_bh_disable(); + percpu_counter_inc(&sctp_sockets_allocated); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + local_bh_enable(); + return 0; } /* Cleanup any SCTP per socket resources. */ -SCTP_STATIC int sctp_destroy_sock(struct sock *sk) +SCTP_STATIC void sctp_destroy_sock(struct sock *sk) { struct sctp_endpoint *ep; @@ -3500,8 +3738,10 @@ SCTP_STATIC int sctp_destroy_sock(struct sock *sk) /* Release our hold on the endpoint. */ ep = sctp_sk(sk)->ep; sctp_endpoint_free(ep); - atomic_dec(&sctp_sockets_allocated); - return 0; + local_bh_disable(); + percpu_counter_dec(&sctp_sockets_allocated); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + local_bh_enable(); } /* API 4.1.7 shutdown() - TCP Style Syntax @@ -3747,7 +3987,6 @@ SCTP_STATIC int sctp_do_peeloff(struct sctp_association *asoc, { struct sock *sk = asoc->base.sk; struct socket *sock; - struct inet_sock *inetsk; struct sctp_af *af; int err = 0; @@ -3762,18 +4001,18 @@ SCTP_STATIC int sctp_do_peeloff(struct sctp_association *asoc, if (err < 0) return err; - /* Populate the fields of the newsk from the oldsk and migrate the - * asoc to the newsk. - */ - sctp_sock_migrate(sk, sock->sk, asoc, SCTP_SOCKET_UDP_HIGH_BANDWIDTH); + sctp_copy_sock(sock->sk, sk, asoc); /* Make peeled-off sockets more like 1-1 accepted sockets. * Set the daddr and initialize id to something more random */ af = sctp_get_af_specific(asoc->peer.primary_addr.sa.sa_family); af->to_sk_daddr(&asoc->peer.primary_addr, sk); - inetsk = inet_sk(sock->sk); - inetsk->id = asoc->next_tsn ^ jiffies; + + /* Populate the fields of the newsk from the oldsk and migrate the + * asoc to the newsk. + */ + sctp_sock_migrate(sk, sock->sk, asoc, SCTP_SOCKET_UDP_HIGH_BANDWIDTH); *sockp = sock; @@ -3799,21 +4038,21 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval goto out; } - SCTP_DEBUG_PRINTK("%s: sk: %p asoc: %p\n", __FUNCTION__, sk, asoc); + SCTP_DEBUG_PRINTK("%s: sk: %p asoc: %p\n", __func__, sk, asoc); retval = sctp_do_peeloff(asoc, &newsock); if (retval < 0) goto out; /* Map the socket to an unused fd that can be returned to the user. */ - retval = sock_map_fd(newsock); + retval = sock_map_fd(newsock, 0); if (retval < 0) { sock_release(newsock); goto out; } SCTP_DEBUG_PRINTK("%s: sk: %p asoc: %p newsk: %p sd: %d\n", - __FUNCTION__, sk, asoc, newsock->sk, retval); + __func__, sk, asoc, newsock->sk, retval); /* Return the fd mapped to the new socket. */ peeloff.sd = retval; @@ -3936,7 +4175,7 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, /* If an address other than INADDR_ANY is specified, and * no transport is found, then the request is invalid. */ - if (!sctp_is_any(( union sctp_addr *)¶ms.spp_address)) { + if (!sctp_is_any(sk, ( union sctp_addr *)¶ms.spp_address)) { trans = sctp_addr_id2transport(sk, ¶ms.spp_address, params.spp_assoc_id); if (!trans) { @@ -3993,70 +4232,91 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, return 0; } -/* 7.1.23. Delayed Ack Timer (SCTP_DELAYED_ACK_TIME) - * - * This options will get or set the delayed ack timer. The time is set - * in milliseconds. If the assoc_id is 0, then this sets or gets the - * endpoints default delayed ack timer value. If the assoc_id field is - * non-zero, then the set or get effects the specified association. - * - * struct sctp_assoc_value { - * sctp_assoc_t assoc_id; - * uint32_t assoc_value; - * }; +/* + * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) + * + * This option will effect the way delayed acks are performed. This + * option allows you to get or set the delayed ack time, in + * milliseconds. It also allows changing the delayed ack frequency. + * Changing the frequency to 1 disables the delayed sack algorithm. If + * the assoc_id is 0, then this sets or gets the endpoints default + * values. If the assoc_id field is non-zero, then the set or get + * effects the specified association for the one to many model (the + * assoc_id field is ignored by the one to one model). Note that if + * sack_delay or sack_freq are 0 when setting this option, then the + * current values will remain unchanged. + * + * struct sctp_sack_info { + * sctp_assoc_t sack_assoc_id; + * uint32_t sack_delay; + * uint32_t sack_freq; + * }; * - * assoc_id - This parameter, indicates which association the - * user is preforming an action upon. Note that if - * this field's value is zero then the endpoints - * default value is changed (effecting future - * associations only). + * sack_assoc_id - This parameter, indicates which association the user + * is performing an action upon. Note that if this field's value is + * zero then the endpoints default value is changed (effecting future + * associations only). * - * assoc_value - This parameter contains the number of milliseconds - * that the user is requesting the delayed ACK timer - * be set to. Note that this value is defined in - * the standard to be between 200 and 500 milliseconds. + * sack_delay - This parameter contains the number of milliseconds that + * the user is requesting the delayed ACK timer be set to. Note that + * this value is defined in the standard to be between 200 and 500 + * milliseconds. * - * Note: a value of zero will leave the value alone, - * but disable SACK delay. A non-zero value will also - * enable SACK delay. + * sack_freq - This parameter contains the number of packets that must + * be received before a sack is sent without waiting for the delay + * timer to expire. The default value for this is 2, setting this + * value to 1 will disable the delayed sack algorithm. */ -static int sctp_getsockopt_delayed_ack_time(struct sock *sk, int len, +static int sctp_getsockopt_delayed_ack(struct sock *sk, int len, char __user *optval, int __user *optlen) { - struct sctp_assoc_value params; + struct sctp_sack_info params; struct sctp_association *asoc = NULL; struct sctp_sock *sp = sctp_sk(sk); - if (len < sizeof(struct sctp_assoc_value)) - return - EINVAL; - - len = sizeof(struct sctp_assoc_value); + if (len >= sizeof(struct sctp_sack_info)) { + len = sizeof(struct sctp_sack_info); - if (copy_from_user(¶ms, optval, len)) - return -EFAULT; + if (copy_from_user(¶ms, optval, len)) + return -EFAULT; + } else if (len == sizeof(struct sctp_assoc_value)) { + printk(KERN_WARNING "SCTP: Use of struct sctp_assoc_value " + "in delayed_ack socket option deprecated\n"); + printk(KERN_WARNING "SCTP: Use struct sctp_sack_info instead\n"); + if (copy_from_user(¶ms, optval, len)) + return -EFAULT; + } else + return - EINVAL; - /* Get association, if assoc_id != 0 and the socket is a one + /* Get association, if sack_assoc_id != 0 and the socket is a one * to many style socket, and an association was not found, then * the id was invalid. */ - asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc && params.assoc_id && sctp_style(sk, UDP)) + asoc = sctp_id2assoc(sk, params.sack_assoc_id); + if (!asoc && params.sack_assoc_id && sctp_style(sk, UDP)) return -EINVAL; if (asoc) { /* Fetch association values. */ - if (asoc->param_flags & SPP_SACKDELAY_ENABLE) - params.assoc_value = jiffies_to_msecs( + if (asoc->param_flags & SPP_SACKDELAY_ENABLE) { + params.sack_delay = jiffies_to_msecs( asoc->sackdelay); - else - params.assoc_value = 0; + params.sack_freq = asoc->sackfreq; + + } else { + params.sack_delay = 0; + params.sack_freq = 1; + } } else { /* Fetch socket values. */ - if (sp->param_flags & SPP_SACKDELAY_ENABLE) - params.assoc_value = sp->sackdelay; - else - params.assoc_value = 0; + if (sp->param_flags & SPP_SACKDELAY_ENABLE) { + params.sack_delay = sp->sackdelay; + params.sack_freq = sp->sackfreq; + } else { + params.sack_delay = 0; + params.sack_freq = 1; + } } if (copy_to_user(optval, ¶ms, len)) @@ -4091,121 +4351,40 @@ static int sctp_getsockopt_initmsg(struct sock *sk, int len, char __user *optval return 0; } -static int sctp_getsockopt_peer_addrs_num_old(struct sock *sk, int len, - char __user *optval, - int __user *optlen) + +static int sctp_getsockopt_peer_addrs(struct sock *sk, int len, + char __user *optval, int __user *optlen) { - sctp_assoc_t id; struct sctp_association *asoc; - struct list_head *pos; int cnt = 0; + struct sctp_getaddrs getaddrs; + struct sctp_transport *from; + void __user *to; + union sctp_addr temp; + struct sctp_sock *sp = sctp_sk(sk); + int addrlen; + size_t space_left; + int bytes_copied; - if (len < sizeof(sctp_assoc_t)) + if (len < sizeof(struct sctp_getaddrs)) return -EINVAL; - if (copy_from_user(&id, optval, sizeof(sctp_assoc_t))) + if (copy_from_user(&getaddrs, optval, sizeof(struct sctp_getaddrs))) return -EFAULT; /* For UDP-style sockets, id specifies the association to query. */ - asoc = sctp_id2assoc(sk, id); + asoc = sctp_id2assoc(sk, getaddrs.assoc_id); if (!asoc) return -EINVAL; - list_for_each(pos, &asoc->peer.transport_addr_list) { - cnt ++; - } - - return cnt; -} + to = optval + offsetof(struct sctp_getaddrs,addrs); + space_left = len - offsetof(struct sctp_getaddrs,addrs); -/* - * Old API for getting list of peer addresses. Does not work for 32-bit - * programs running on a 64-bit kernel - */ -static int sctp_getsockopt_peer_addrs_old(struct sock *sk, int len, - char __user *optval, - int __user *optlen) -{ - struct sctp_association *asoc; - struct list_head *pos; - int cnt = 0; - struct sctp_getaddrs_old getaddrs; - struct sctp_transport *from; - void __user *to; - union sctp_addr temp; - struct sctp_sock *sp = sctp_sk(sk); - int addrlen; - - if (len < sizeof(struct sctp_getaddrs_old)) - return -EINVAL; - - len = sizeof(struct sctp_getaddrs_old); - - if (copy_from_user(&getaddrs, optval, len)) - return -EFAULT; - - if (getaddrs.addr_num <= 0) return -EINVAL; - - /* For UDP-style sockets, id specifies the association to query. */ - asoc = sctp_id2assoc(sk, getaddrs.assoc_id); - if (!asoc) - return -EINVAL; - - to = (void __user *)getaddrs.addrs; - list_for_each(pos, &asoc->peer.transport_addr_list) { - from = list_entry(pos, struct sctp_transport, transports); - memcpy(&temp, &from->ipaddr, sizeof(temp)); - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp); - addrlen = sctp_get_af_specific(sk->sk_family)->sockaddr_len; - if (copy_to_user(to, &temp, addrlen)) - return -EFAULT; - to += addrlen ; - cnt ++; - if (cnt >= getaddrs.addr_num) break; - } - getaddrs.addr_num = cnt; - if (put_user(len, optlen)) - return -EFAULT; - if (copy_to_user(optval, &getaddrs, len)) - return -EFAULT; - - return 0; -} - -static int sctp_getsockopt_peer_addrs(struct sock *sk, int len, - char __user *optval, int __user *optlen) -{ - struct sctp_association *asoc; - struct list_head *pos; - int cnt = 0; - struct sctp_getaddrs getaddrs; - struct sctp_transport *from; - void __user *to; - union sctp_addr temp; - struct sctp_sock *sp = sctp_sk(sk); - int addrlen; - size_t space_left; - int bytes_copied; - - if (len < sizeof(struct sctp_getaddrs)) - return -EINVAL; - - if (copy_from_user(&getaddrs, optval, sizeof(struct sctp_getaddrs))) - return -EFAULT; - - /* For UDP-style sockets, id specifies the association to query. */ - asoc = sctp_id2assoc(sk, getaddrs.assoc_id); - if (!asoc) - return -EINVAL; - - to = optval + offsetof(struct sctp_getaddrs,addrs); - space_left = len - offsetof(struct sctp_getaddrs,addrs); - - list_for_each(pos, &asoc->peer.transport_addr_list) { - from = list_entry(pos, struct sctp_transport, transports); + list_for_each_entry(from, &asoc->peer.transport_addr_list, + transports) { memcpy(&temp, &from->ipaddr, sizeof(temp)); sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp); - addrlen = sctp_get_af_specific(sk->sk_family)->sockaddr_len; + addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; if (space_left < addrlen) return -ENOMEM; if (copy_to_user(to, &temp, addrlen)) @@ -4224,110 +4403,6 @@ static int sctp_getsockopt_peer_addrs(struct sock *sk, int len, return 0; } -static int sctp_getsockopt_local_addrs_num_old(struct sock *sk, int len, - char __user *optval, - int __user *optlen) -{ - sctp_assoc_t id; - struct sctp_bind_addr *bp; - struct sctp_association *asoc; - struct sctp_sockaddr_entry *addr; - int cnt = 0; - - if (len < sizeof(sctp_assoc_t)) - return -EINVAL; - - if (copy_from_user(&id, optval, sizeof(sctp_assoc_t))) - return -EFAULT; - - /* - * For UDP-style sockets, id specifies the association to query. - * If the id field is set to the value '0' then the locally bound - * addresses are returned without regard to any particular - * association. - */ - if (0 == id) { - bp = &sctp_sk(sk)->ep->base.bind_addr; - } else { - asoc = sctp_id2assoc(sk, id); - if (!asoc) - return -EINVAL; - bp = &asoc->base.bind_addr; - } - - /* If the endpoint is bound to 0.0.0.0 or ::0, count the valid - * addresses from the global local address list. - */ - if (sctp_list_single_entry(&bp->address_list)) { - addr = list_entry(bp->address_list.next, - struct sctp_sockaddr_entry, list); - if (sctp_is_any(&addr->a)) { - rcu_read_lock(); - list_for_each_entry_rcu(addr, - &sctp_local_addr_list, list) { - if (!addr->valid) - continue; - - if ((PF_INET == sk->sk_family) && - (AF_INET6 == addr->a.sa.sa_family)) - continue; - - cnt++; - } - rcu_read_unlock(); - } else { - cnt = 1; - } - goto done; - } - - /* Protection on the bound address list is not needed, - * since in the socket option context we hold the socket lock, - * so there is no way that the bound address list can change. - */ - list_for_each_entry(addr, &bp->address_list, list) { - cnt ++; - } -done: - return cnt; -} - -/* Helper function that copies local addresses to user and returns the number - * of addresses copied. - */ -static int sctp_copy_laddrs_old(struct sock *sk, __u16 port, - int max_addrs, void *to, - int *bytes_copied) -{ - struct sctp_sockaddr_entry *addr; - union sctp_addr temp; - int cnt = 0; - int addrlen; - - rcu_read_lock(); - list_for_each_entry_rcu(addr, &sctp_local_addr_list, list) { - if (!addr->valid) - continue; - - if ((PF_INET == sk->sk_family) && - (AF_INET6 == addr->a.sa.sa_family)) - continue; - memcpy(&temp, &addr->a, sizeof(temp)); - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk), - &temp); - addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; - memcpy(to, &temp, addrlen); - - to += addrlen; - *bytes_copied += addrlen; - cnt ++; - if (cnt >= max_addrs) break; - } - rcu_read_unlock(); - - return cnt; -} - static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, size_t space_left, int *bytes_copied) { @@ -4344,7 +4419,14 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, if ((PF_INET == sk->sk_family) && (AF_INET6 == addr->a.sa.sa_family)) continue; + if ((PF_INET6 == sk->sk_family) && + inet_v6_ipv6only(sk) && + (AF_INET == addr->a.sa.sa_family)) + continue; memcpy(&temp, &addr->a, sizeof(temp)); + if (!temp.v4.sin_port) + temp.v4.sin_port = htons(port); + sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk), &temp); addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; @@ -4364,106 +4446,6 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, return cnt; } -/* Old API for getting list of local addresses. Does not work for 32-bit - * programs running on a 64-bit kernel - */ -static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, - char __user *optval, int __user *optlen) -{ - struct sctp_bind_addr *bp; - struct sctp_association *asoc; - int cnt = 0; - struct sctp_getaddrs_old getaddrs; - struct sctp_sockaddr_entry *addr; - void __user *to; - union sctp_addr temp; - struct sctp_sock *sp = sctp_sk(sk); - int addrlen; - int err = 0; - void *addrs; - void *buf; - int bytes_copied = 0; - - if (len < sizeof(struct sctp_getaddrs_old)) - return -EINVAL; - - len = sizeof(struct sctp_getaddrs_old); - if (copy_from_user(&getaddrs, optval, len)) - return -EFAULT; - - if (getaddrs.addr_num <= 0) return -EINVAL; - /* - * For UDP-style sockets, id specifies the association to query. - * If the id field is set to the value '0' then the locally bound - * addresses are returned without regard to any particular - * association. - */ - if (0 == getaddrs.assoc_id) { - bp = &sctp_sk(sk)->ep->base.bind_addr; - } else { - asoc = sctp_id2assoc(sk, getaddrs.assoc_id); - if (!asoc) - return -EINVAL; - bp = &asoc->base.bind_addr; - } - - to = getaddrs.addrs; - - /* Allocate space for a local instance of packed array to hold all - * the data. We store addresses here first and then put write them - * to the user in one shot. - */ - addrs = kmalloc(sizeof(union sctp_addr) * getaddrs.addr_num, - GFP_KERNEL); - if (!addrs) - return -ENOMEM; - - /* If the endpoint is bound to 0.0.0.0 or ::0, get the valid - * addresses from the global local address list. - */ - if (sctp_list_single_entry(&bp->address_list)) { - addr = list_entry(bp->address_list.next, - struct sctp_sockaddr_entry, list); - if (sctp_is_any(&addr->a)) { - cnt = sctp_copy_laddrs_old(sk, bp->port, - getaddrs.addr_num, - addrs, &bytes_copied); - goto copy_getaddrs; - } - } - - buf = addrs; - /* Protection on the bound address list is not needed since - * in the socket option context we hold a socket lock and - * thus the bound address list can't change. - */ - list_for_each_entry(addr, &bp->address_list, list) { - memcpy(&temp, &addr->a, sizeof(temp)); - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp); - addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; - memcpy(buf, &temp, addrlen); - buf += addrlen; - bytes_copied += addrlen; - cnt ++; - if (cnt >= getaddrs.addr_num) break; - } - -copy_getaddrs: - /* copy the entire address list into the user provided space */ - if (copy_to_user(to, addrs, bytes_copied)) { - err = -EFAULT; - goto error; - } - - /* copy the leading structure back to user */ - getaddrs.addr_num = cnt; - if (copy_to_user(optval, &getaddrs, len)) - err = -EFAULT; - -error: - kfree(addrs); - return err; -} static int sctp_getsockopt_local_addrs(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -4517,7 +4499,7 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len, if (sctp_list_single_entry(&bp->address_list)) { addr = list_entry(bp->address_list.next, struct sctp_sockaddr_entry, list); - if (sctp_is_any(&addr->a)) { + if (sctp_is_any(sk, &addr->a)) { cnt = sctp_copy_laddrs(sk, bp->port, addrs, space_left, &bytes_copied); if (cnt < 0) { @@ -4914,30 +4896,69 @@ static int sctp_getsockopt_context(struct sock *sk, int len, } /* - * 7.1.17 Set the maximum fragrmentation size (SCTP_MAXSEG) - * - * This socket option specifies the maximum size to put in any outgoing - * SCTP chunk. If a message is larger than this size it will be + * 8.1.16. Get or Set the Maximum Fragmentation Size (SCTP_MAXSEG) + * This option will get or set the maximum size to put in any outgoing + * SCTP DATA chunk. If a message is larger than this size it will be * fragmented by SCTP into the specified size. Note that the underlying * SCTP implementation may fragment into smaller sized chunks when the * PMTU of the underlying association is smaller than the value set by - * the user. + * the user. The default value for this option is '0' which indicates + * the user is NOT limiting fragmentation and only the PMTU will effect + * SCTP's choice of DATA chunk size. Note also that values set larger + * than the maximum size of an IP datagram will effectively let SCTP + * control fragmentation (i.e. the same as setting this option to 0). + * + * The following structure is used to access and modify this parameter: + * + * struct sctp_assoc_value { + * sctp_assoc_t assoc_id; + * uint32_t assoc_value; + * }; + * + * assoc_id: This parameter is ignored for one-to-one style sockets. + * For one-to-many style sockets this parameter indicates which + * association the user is performing an action upon. Note that if + * this field's value is zero then the endpoints default value is + * changed (effecting future associations only). + * assoc_value: This parameter specifies the maximum size in bytes. */ static int sctp_getsockopt_maxseg(struct sock *sk, int len, char __user *optval, int __user *optlen) { - int val; + struct sctp_assoc_value params; + struct sctp_association *asoc; - if (len < sizeof(int)) + if (len == sizeof(int)) { + printk(KERN_WARNING + "SCTP: Use of int in maxseg socket option deprecated\n"); + printk(KERN_WARNING + "SCTP: Use struct sctp_assoc_value instead\n"); + params.assoc_id = 0; + } else if (len >= sizeof(struct sctp_assoc_value)) { + len = sizeof(struct sctp_assoc_value); + if (copy_from_user(¶ms, optval, sizeof(params))) + return -EFAULT; + } else return -EINVAL; - len = sizeof(int); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id && sctp_style(sk, UDP)) + return -EINVAL; + + if (asoc) + params.assoc_value = asoc->frag_point; + else + params.assoc_value = sctp_sk(sk)->user_frag; - val = sctp_sk(sk)->user_frag; if (put_user(len, optlen)) return -EFAULT; - if (copy_to_user(optval, &val, len)) - return -EFAULT; + if (len == sizeof(int)) { + if (copy_to_user(optval, ¶ms.assoc_value, len)) + return -EFAULT; + } else { + if (copy_to_user(optval, ¶ms, len)) + return -EFAULT; + } return 0; } @@ -4997,38 +5018,71 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, char __user *optval, int __user *optlen) { - int val; + struct sctp_assoc_value params; + struct sctp_sock *sp; + struct sctp_association *asoc; - if (len < sizeof(int)) + if (len == sizeof(int)) { + printk(KERN_WARNING + "SCTP: Use of int in max_burst socket option deprecated\n"); + printk(KERN_WARNING + "SCTP: Use struct sctp_assoc_value instead\n"); + params.assoc_id = 0; + } else if (len >= sizeof(struct sctp_assoc_value)) { + len = sizeof(struct sctp_assoc_value); + if (copy_from_user(¶ms, optval, len)) + return -EFAULT; + } else return -EINVAL; - len = sizeof(int); + sp = sctp_sk(sk); - val = sctp_sk(sk)->max_burst; - if (put_user(len, optlen)) - return -EFAULT; - if (copy_to_user(optval, &val, len)) - return -EFAULT; + if (params.assoc_id != 0) { + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) + return -EINVAL; + params.assoc_value = asoc->max_burst; + } else + params.assoc_value = sp->max_burst; + + if (len == sizeof(int)) { + if (copy_to_user(optval, ¶ms.assoc_value, len)) + return -EFAULT; + } else { + if (copy_to_user(optval, ¶ms, len)) + return -EFAULT; + } + + return 0; - return -ENOTSUPP; } static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, char __user *optval, int __user *optlen) { + struct sctp_hmacalgo __user *p = (void __user *)optval; struct sctp_hmac_algo_param *hmacs; - __u16 param_len; + __u16 data_len = 0; + u32 num_idents; + + if (!sctp_auth_enable) + return -EACCES; hmacs = sctp_sk(sk)->ep->auth_hmacs_list; - param_len = ntohs(hmacs->param_hdr.length); + data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t); - if (len < param_len) + if (len < sizeof(struct sctp_hmacalgo) + data_len) return -EINVAL; + + len = sizeof(struct sctp_hmacalgo) + data_len; + num_idents = data_len / sizeof(u16); + if (put_user(len, optlen)) return -EFAULT; - if (copy_to_user(optval, hmacs->hmac_ids, len)) + if (put_user(num_idents, &p->shmac_num_idents)) + return -EFAULT; + if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len)) return -EFAULT; - return 0; } @@ -5038,6 +5092,9 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, struct sctp_authkeyid val; struct sctp_association *asoc; + if (!sctp_auth_enable) + return -EACCES; + if (len < sizeof(struct sctp_authkeyid)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(struct sctp_authkeyid))) @@ -5052,58 +5109,78 @@ static int sctp_getsockopt_active_key(struct sock *sk, int len, else val.scact_keynumber = sctp_sk(sk)->ep->active_key_id; + len = sizeof(struct sctp_authkeyid); + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; } static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { + struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; struct sctp_chunks_param *ch; + u32 num_chunks = 0; char __user *to; - if (len <= sizeof(struct sctp_authchunks)) + if (!sctp_auth_enable) + return -EACCES; + + if (len < sizeof(struct sctp_authchunks)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(struct sctp_authchunks))) return -EFAULT; - to = val.gauth_chunks; + to = p->gauth_chunks; asoc = sctp_id2assoc(sk, val.gauth_assoc_id); if (!asoc) return -EINVAL; ch = asoc->peer.peer_chunks; + if (!ch) + goto num; /* See if the user provided enough room for all the data */ - if (len < ntohs(ch->param_hdr.length)) + num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t); + if (len < num_chunks) return -EINVAL; - len = ntohs(ch->param_hdr.length); - if (put_user(len, optlen)) + if (copy_to_user(to, ch->chunks, num_chunks)) return -EFAULT; - if (copy_to_user(to, ch->chunks, len)) +num: + len = sizeof(struct sctp_authchunks) + num_chunks; + if (put_user(len, optlen)) return -EFAULT; + if (put_user(num_chunks, &p->gauth_number_of_chunks)) return -EFAULT; - return 0; } static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, char __user *optval, int __user *optlen) { + struct sctp_authchunks __user *p = (void __user *)optval; struct sctp_authchunks val; struct sctp_association *asoc; struct sctp_chunks_param *ch; + u32 num_chunks = 0; char __user *to; - if (len <= sizeof(struct sctp_authchunks)) + if (!sctp_auth_enable) + return -EACCES; + + if (len < sizeof(struct sctp_authchunks)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(struct sctp_authchunks))) return -EFAULT; - to = val.gauth_chunks; + to = p->gauth_chunks; asoc = sctp_id2assoc(sk, val.gauth_assoc_id); if (!asoc && val.gauth_assoc_id && sctp_style(sk, UDP)) return -EINVAL; @@ -5113,13 +5190,52 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, else ch = sctp_sk(sk)->ep->auth_chunk_list; - if (len < ntohs(ch->param_hdr.length)) + if (!ch) + goto num; + + num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t); + if (len < sizeof(struct sctp_authchunks) + num_chunks) + return -EINVAL; + + if (copy_to_user(to, ch->chunks, num_chunks)) + return -EFAULT; +num: + len = sizeof(struct sctp_authchunks) + num_chunks; + if (put_user(len, optlen)) + return -EFAULT; + if (put_user(num_chunks, &p->gauth_number_of_chunks)) + return -EFAULT; + + return 0; +} + +/* + * 8.2.5. Get the Current Number of Associations (SCTP_GET_ASSOC_NUMBER) + * This option gets the current number of associations that are attached + * to a one-to-many style socket. The option value is an uint32_t. + */ +static int sctp_getsockopt_assoc_number(struct sock *sk, int len, + char __user *optval, int __user *optlen) +{ + struct sctp_sock *sp = sctp_sk(sk); + struct sctp_association *asoc; + u32 val = 0; + + if (sctp_style(sk, TCP)) + return -EOPNOTSUPP; + + if (len < sizeof(u32)) return -EINVAL; - len = ntohs(ch->param_hdr.length); + len = sizeof(u32); + + list_for_each_entry(asoc, &(sp->ep->asocs), asocs) { + val++; + } + if (put_user(len, optlen)) return -EFAULT; - if (copy_to_user(to, ch->chunks, len)) + if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; @@ -5173,29 +5289,13 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_peer_addr_params(sk, len, optval, optlen); break; - case SCTP_DELAYED_ACK_TIME: - retval = sctp_getsockopt_delayed_ack_time(sk, len, optval, + case SCTP_DELAYED_ACK: + retval = sctp_getsockopt_delayed_ack(sk, len, optval, optlen); break; case SCTP_INITMSG: retval = sctp_getsockopt_initmsg(sk, len, optval, optlen); break; - case SCTP_GET_PEER_ADDRS_NUM_OLD: - retval = sctp_getsockopt_peer_addrs_num_old(sk, len, optval, - optlen); - break; - case SCTP_GET_LOCAL_ADDRS_NUM_OLD: - retval = sctp_getsockopt_local_addrs_num_old(sk, len, optval, - optlen); - break; - case SCTP_GET_PEER_ADDRS_OLD: - retval = sctp_getsockopt_peer_addrs_old(sk, len, optval, - optlen); - break; - case SCTP_GET_LOCAL_ADDRS_OLD: - retval = sctp_getsockopt_local_addrs_old(sk, len, optval, - optlen); - break; case SCTP_GET_PEER_ADDRS: retval = sctp_getsockopt_peer_addrs(sk, len, optval, optlen); @@ -5204,6 +5304,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_local_addrs(sk, len, optval, optlen); break; + case SCTP_SOCKOPT_CONNECTX3: + retval = sctp_getsockopt_connectx3(sk, len, optval, optlen); + break; case SCTP_DEFAULT_SEND_PARAM: retval = sctp_getsockopt_default_send_param(sk, len, optval, optlen); @@ -5267,6 +5370,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_local_auth_chunks(sk, len, optval, optlen); break; + case SCTP_GET_ASSOC_NUMBER: + retval = sctp_getsockopt_assoc_number(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -5305,6 +5411,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { struct sctp_bind_hashbucket *head; /* hash list */ struct sctp_bind_bucket *pp; /* hash list port iterator */ + struct hlist_node *node; unsigned short snum; int ret; @@ -5315,20 +5422,23 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) if (snum == 0) { /* Search for an available port. */ - unsigned int low = sysctl_local_port_range[0]; - unsigned int high = sysctl_local_port_range[1]; - unsigned int remaining = (high - low) + 1; - unsigned int rover = net_random() % remaining + low; - int index; + int low, high, remaining, index; + unsigned int rover; + + inet_get_local_port_range(&low, &high); + remaining = (high - low) + 1; + rover = net_random() % remaining + low; do { rover++; if ((rover < low) || (rover > high)) rover = low; + if (inet_is_reserved_local_port(rover)) + continue; index = sctp_phashfn(rover); head = &sctp_port_hashtable[index]; sctp_spin_lock(&head->lock); - for (pp = head->chain; pp; pp = pp->next) + sctp_for_each_hentry(pp, node, &head->chain) if (pp->port == rover) goto next; break; @@ -5355,7 +5465,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) */ head = &sctp_port_hashtable[sctp_phashfn(snum)]; sctp_spin_lock(&head->lock); - for (pp = head->chain; pp; pp = pp->next) { + sctp_for_each_hentry(pp, node, &head->chain) { if (pp->port == snum) goto pp_found; } @@ -5371,7 +5481,6 @@ pp_found: */ int reuse = sk->sk_reuse; struct sock *sk2; - struct hlist_node *node; SCTP_DEBUG_PRINTK("sctp_get_port() found a possible match\n"); if (pp->fastreuse && sk->sk_reuse && @@ -5392,12 +5501,13 @@ pp_found: struct sctp_endpoint *ep2; ep2 = sctp_sk(sk2)->ep; - if (reuse && sk2->sk_reuse && - sk2->sk_state != SCTP_SS_LISTENING) + if (sk == sk2 || + (reuse && sk2->sk_reuse && + sk2->sk_state != SCTP_SS_LISTENING)) continue; - if (sctp_bind_addr_match(&ep2->base.bind_addr, addr, - sctp_sk(sk))) { + if (sctp_bind_addr_conflict(&ep2->base.bind_addr, addr, + sctp_sk(sk2), sctp_sk(sk))) { ret = (long)sk2; goto fail_unlock; } @@ -5429,7 +5539,7 @@ pp_not_found: */ success: if (!sctp_sk(sk)->bind_hash) { - inet_sk(sk)->num = snum; + inet_sk(sk)->inet_num = snum; sk_add_bind_node(sk, &pp->owner); sctp_sk(sk)->bind_hash = pp; } @@ -5463,37 +5573,28 @@ static int sctp_get_port(struct sock *sk, unsigned short snum) } /* - * 3.1.3 listen() - UDP Style Syntax - * - * By default, new associations are not accepted for UDP style sockets. - * An application uses listen() to mark a socket as being able to - * accept new associations. + * Move a socket to LISTENING state. */ -SCTP_STATIC int sctp_seqpacket_listen(struct sock *sk, int backlog) +SCTP_STATIC int sctp_listen_start(struct sock *sk, int backlog) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; + struct crypto_hash *tfm = NULL; - /* Only UDP style sockets that are not peeled off are allowed to - * listen(). - */ - if (!sctp_style(sk, UDP)) - return -EINVAL; - - /* If backlog is zero, disable listening. */ - if (!backlog) { - if (sctp_sstate(sk, CLOSED)) - return 0; - - sctp_unhash_endpoint(ep); - sk->sk_state = SCTP_SS_CLOSED; - return 0; + /* Allocate HMAC for generating cookie. */ + if (!sctp_sk(sk)->hmac && sctp_hmac_alg) { + tfm = crypto_alloc_hash(sctp_hmac_alg, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(tfm)) { + if (net_ratelimit()) { + printk(KERN_INFO + "SCTP: failed to load transform for %s: %ld\n", + sctp_hmac_alg, PTR_ERR(tfm)); + } + return -ENOSYS; + } + sctp_sk(sk)->hmac = tfm; } - /* Return if we are already listening. */ - if (sctp_sstate(sk, LISTENING)) - return 0; - /* * If a bind() or sctp_bindx() is not called prior to a listen() * call that allows new associations to be accepted, the system @@ -5504,118 +5605,81 @@ SCTP_STATIC int sctp_seqpacket_listen(struct sock *sk, int backlog) * extensions draft, but follows the practice as seen in TCP * sockets. * - * Additionally, turn off fastreuse flag since we are not listening */ sk->sk_state = SCTP_SS_LISTENING; if (!ep->base.bind_addr.port) { if (sctp_autobind(sk)) return -EAGAIN; - } else - sctp_sk(sk)->bind_hash->fastreuse = 0; - - sctp_hash_endpoint(ep); - return 0; -} - -/* - * 4.1.3 listen() - TCP Style Syntax - * - * Applications uses listen() to ready the SCTP endpoint for accepting - * inbound associations. - */ -SCTP_STATIC int sctp_stream_listen(struct sock *sk, int backlog) -{ - struct sctp_sock *sp = sctp_sk(sk); - struct sctp_endpoint *ep = sp->ep; - - /* If backlog is zero, disable listening. */ - if (!backlog) { - if (sctp_sstate(sk, CLOSED)) - return 0; - - sctp_unhash_endpoint(ep); - sk->sk_state = SCTP_SS_CLOSED; - return 0; + } else { + if (sctp_get_port(sk, inet_sk(sk)->inet_num)) { + sk->sk_state = SCTP_SS_CLOSED; + return -EADDRINUSE; + } } - if (sctp_sstate(sk, LISTENING)) - return 0; - - /* - * If a bind() or sctp_bindx() is not called prior to a listen() - * call that allows new associations to be accepted, the system - * picks an ephemeral port and will choose an address set equivalent - * to binding with a wildcard address. - * - * This is not currently spelled out in the SCTP sockets - * extensions draft, but follows the practice as seen in TCP - * sockets. - */ - sk->sk_state = SCTP_SS_LISTENING; - if (!ep->base.bind_addr.port) { - if (sctp_autobind(sk)) - return -EAGAIN; - } else - sctp_sk(sk)->bind_hash->fastreuse = 0; - sk->sk_max_ack_backlog = backlog; sctp_hash_endpoint(ep); return 0; } /* + * 4.1.3 / 5.1.3 listen() + * + * By default, new associations are not accepted for UDP style sockets. + * An application uses listen() to mark a socket as being able to + * accept new associations. + * + * On TCP style sockets, applications use listen() to ready the SCTP + * endpoint for accepting inbound associations. + * + * On both types of endpoints a backlog of '0' disables listening. + * * Move a socket to LISTENING state. */ int sctp_inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; - struct crypto_hash *tfm = NULL; + struct sctp_endpoint *ep = sctp_sk(sk)->ep; int err = -EINVAL; if (unlikely(backlog < 0)) - goto out; + return err; sctp_lock_sock(sk); + /* Peeled-off sockets are not allowed to listen(). */ + if (sctp_style(sk, UDP_HIGH_BANDWIDTH)) + goto out; + if (sock->state != SS_UNCONNECTED) goto out; - /* Allocate HMAC for generating cookie. */ - if (sctp_hmac_alg) { - tfm = crypto_alloc_hash(sctp_hmac_alg, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) { - if (net_ratelimit()) { - printk(KERN_INFO - "SCTP: failed to load transform for %s: %ld\n", - sctp_hmac_alg, PTR_ERR(tfm)); - } - err = -ENOSYS; + /* If backlog is zero, disable listening. */ + if (!backlog) { + if (sctp_sstate(sk, CLOSED)) goto out; - } - } - switch (sock->type) { - case SOCK_SEQPACKET: - err = sctp_seqpacket_listen(sk, backlog); - break; - case SOCK_STREAM: - err = sctp_stream_listen(sk, backlog); - break; - default: - break; + err = 0; + sctp_unhash_endpoint(ep); + sk->sk_state = SCTP_SS_CLOSED; + if (sk->sk_reuse) + sctp_sk(sk)->bind_hash->fastreuse = 1; + goto out; } - if (err) - goto cleanup; + /* If we are already listening, just update the backlog */ + if (sctp_sstate(sk, LISTENING)) + sk->sk_max_ack_backlog = backlog; + else { + err = sctp_listen_start(sk, backlog); + if (err) + goto out; + } - /* Store away the transform reference. */ - sctp_sk(sk)->hmac = tfm; + err = 0; out: sctp_release_sock(sk); return err; -cleanup: - crypto_free_hash(tfm); - goto out; } /* @@ -5637,7 +5701,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait) struct sctp_sock *sp = sctp_sk(sk); unsigned int mask; - poll_wait(file, sk->sk_sleep, wait); + poll_wait(file, sk_sleep(sk), wait); /* A TCP-style listening socket becomes readable when the accept queue * is not empty. @@ -5694,15 +5758,12 @@ static struct sctp_bind_bucket *sctp_bucket_create( struct sctp_bind_bucket *pp; pp = kmem_cache_alloc(sctp_bucket_cachep, GFP_ATOMIC); - SCTP_DBG_OBJCNT_INC(bind_bucket); if (pp) { + SCTP_DBG_OBJCNT_INC(bind_bucket); pp->port = snum; pp->fastreuse = 0; INIT_HLIST_HEAD(&pp->owner); - if ((pp->next = head->chain) != NULL) - pp->next->pprev = &pp->next; - head->chain = pp; - pp->pprev = &head->chain; + hlist_add_head(&pp->node, &head->chain); } return pp; } @@ -5711,9 +5772,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( static void sctp_bucket_destroy(struct sctp_bind_bucket *pp) { if (pp && hlist_empty(&pp->owner)) { - if (pp->next) - pp->next->pprev = pp->pprev; - *(pp->pprev) = pp->next; + __hlist_del(&pp->node); kmem_cache_free(sctp_bucket_cachep, pp); SCTP_DBG_OBJCNT_DEC(bind_bucket); } @@ -5723,14 +5782,14 @@ static void sctp_bucket_destroy(struct sctp_bind_bucket *pp) static inline void __sctp_put_port(struct sock *sk) { struct sctp_bind_hashbucket *head = - &sctp_port_hashtable[sctp_phashfn(inet_sk(sk)->num)]; + &sctp_port_hashtable[sctp_phashfn(inet_sk(sk)->inet_num)]; struct sctp_bind_bucket *pp; sctp_spin_lock(&head->lock); pp = sctp_sk(sk)->bind_hash; __sk_del_bind_node(sk); sctp_sk(sk)->bind_hash = NULL; - inet_sk(sk)->num = 0; + inet_sk(sk)->inet_num = 0; sctp_bucket_destroy(pp); sctp_spin_unlock(&head->lock); } @@ -5757,7 +5816,7 @@ static int sctp_autobind(struct sock *sk) /* Initialize a local sockaddr structure to INADDR_ANY. */ af = sctp_sk(sk)->pf->af; - port = htons(inet_sk(sk)->num); + port = htons(inet_sk(sk)->inet_num); af->inaddr_any(&autoaddr, port); return sctp_do_bind(sk, &autoaddr, af->sockaddr_len); @@ -5806,11 +5865,12 @@ SCTP_STATIC int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) { struct cmsghdr *cmsg; + struct msghdr *my_msg = (struct msghdr *)msg; for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL; - cmsg = CMSG_NXTHDR((struct msghdr*)msg, cmsg)) { - if (!CMSG_OK(msg, cmsg)) + cmsg = CMSG_NXTHDR(my_msg, cmsg)) { + if (!CMSG_OK(my_msg, cmsg)) return -EINVAL; /* Should we parse this header or ignore? */ @@ -5882,7 +5942,7 @@ static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p) int error; DEFINE_WAIT(wait); - prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* Socket errors? */ error = sock_error(sk); @@ -5919,14 +5979,14 @@ static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p) sctp_lock_sock(sk); ready: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return 0; interrupted: error = sock_intr_errno(*timeo_p); out: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); *err = error; return error; } @@ -6000,16 +6060,17 @@ static void __sctp_write_space(struct sctp_association *asoc) wake_up_interruptible(&asoc->wait); if (sctp_writeable(sk)) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); /* Note that we try to include the Async I/O support * here by modeling from the current TCP/UDP code. * We have not tested with it yet. */ - if (sock->fasync_list && + if (sock->wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) - sock_wake_async(sock, 2, POLL_OUT); + sock_wake_async(sock, + SOCK_WAKE_SPACE, POLL_OUT); } } } @@ -6035,10 +6096,10 @@ static void sctp_wfree(struct sk_buff *skb) atomic_sub(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); /* - * This undoes what is done via sk_charge_skb + * This undoes what is done via sctp_set_owner_w and sk_mem_charge */ sk->sk_wmem_queued -= skb->truesize; - sk->sk_forward_alloc += skb->truesize; + sk_mem_uncharge(sk, skb->truesize); sock_wfree(skb); __sctp_write_space(asoc); @@ -6059,9 +6120,9 @@ void sctp_sock_rfree(struct sk_buff *skb) atomic_sub(event->rmem_len, &sk->sk_rmem_alloc); /* - * Mimic the behavior of sk_stream_rfree + * Mimic the behavior of sock_rfree */ - sk->sk_forward_alloc += event->rmem_len; + sk_mem_uncharge(sk, event->rmem_len); } @@ -6126,15 +6187,26 @@ do_nonblock: goto out; } +void sctp_data_ready(struct sock *sk, int len) +{ + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | + POLLRDNORM | POLLRDBAND); + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + rcu_read_unlock(); +} + /* If socket sndbuf has changed, wake up all per association waiters. */ void sctp_write_space(struct sock *sk) { struct sctp_association *asoc; - struct list_head *pos; /* Wake up the tasks in each wait queue. */ - list_for_each(pos, &((sctp_sk(sk))->ep->asocs)) { - asoc = list_entry(pos, struct sctp_association, asocs); + list_for_each_entry(asoc, &((sctp_sk(sk))->ep->asocs), asocs) { __sctp_write_space(asoc); } } @@ -6154,7 +6226,7 @@ static int sctp_writeable(struct sock *sk) { int amt = 0; - amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + amt = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amt < 0) amt = 0; return amt; @@ -6170,7 +6242,7 @@ static int sctp_wait_for_connect(struct sctp_association *asoc, long *timeo_p) long current_timeo = *timeo_p; DEFINE_WAIT(wait); - SCTP_DEBUG_PRINTK("%s: asoc=%p, timeo=%ld\n", __FUNCTION__, asoc, + SCTP_DEBUG_PRINTK("%s: asoc=%p, timeo=%ld\n", __func__, asoc, (long)(*timeo_p)); /* Increment the association's refcnt. */ @@ -6236,7 +6308,7 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo) for (;;) { - prepare_to_wait_exclusive(sk->sk_sleep, &wait, + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (list_empty(&ep->asocs)) { @@ -6262,7 +6334,7 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo) break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return err; } @@ -6272,7 +6344,7 @@ static void sctp_wait_for_close(struct sock *sk, long timeout) DEFINE_WAIT(wait); do { - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (list_empty(&sctp_sk(sk)->ep->asocs)) break; sctp_release_sock(sk); @@ -6280,22 +6352,7 @@ static void sctp_wait_for_close(struct sock *sk, long timeout) sctp_lock_sock(sk); } while (!signal_pending(current) && timeout); - finish_wait(sk->sk_sleep, &wait); -} - -static void sctp_sock_rfree_frag(struct sk_buff *skb) -{ - struct sk_buff *frag; - - if (!skb->data_len) - goto done; - - /* Don't forget the fragments. */ - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) - sctp_sock_rfree_frag(frag); - -done: - sctp_sock_rfree(skb); + finish_wait(sk_sleep(sk), &wait); } static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk) @@ -6306,13 +6363,55 @@ static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk) goto done; /* Don't forget the fragments. */ - for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) + skb_walk_frags(skb, frag) sctp_skb_set_owner_r_frag(frag, sk); done: sctp_skb_set_owner_r(skb, sk); } +void sctp_copy_sock(struct sock *newsk, struct sock *sk, + struct sctp_association *asoc) +{ + struct inet_sock *inet = inet_sk(sk); + struct inet_sock *newinet; + + newsk->sk_type = sk->sk_type; + newsk->sk_bound_dev_if = sk->sk_bound_dev_if; + newsk->sk_flags = sk->sk_flags; + newsk->sk_no_check = sk->sk_no_check; + newsk->sk_reuse = sk->sk_reuse; + + newsk->sk_shutdown = sk->sk_shutdown; + newsk->sk_destruct = inet_sock_destruct; + newsk->sk_family = sk->sk_family; + newsk->sk_protocol = IPPROTO_SCTP; + newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; + newsk->sk_sndbuf = sk->sk_sndbuf; + newsk->sk_rcvbuf = sk->sk_rcvbuf; + newsk->sk_lingertime = sk->sk_lingertime; + newsk->sk_rcvtimeo = sk->sk_rcvtimeo; + newsk->sk_sndtimeo = sk->sk_sndtimeo; + + newinet = inet_sk(newsk); + + /* Initialize sk's sport, dport, rcv_saddr and daddr for + * getsockname() and getpeername() + */ + newinet->inet_sport = inet->inet_sport; + newinet->inet_saddr = inet->inet_saddr; + newinet->inet_rcv_saddr = inet->inet_rcv_saddr; + newinet->inet_dport = htons(asoc->peer.port); + newinet->pmtudisc = inet->pmtudisc; + newinet->inet_id = asoc->next_tsn ^ jiffies; + + newinet->uc_ttl = inet->uc_ttl; + newinet->mc_loop = 1; + newinet->mc_ttl = 1; + newinet->mc_index = 0; + newinet->mc_list = NULL; +} + /* Populate the fields of the newsk from the oldsk and migrate the assoc * and its messages to the newsk. */ @@ -6326,7 +6425,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_endpoint *newep = newsp->ep; struct sk_buff *skb, *tmp; struct sctp_ulpevent *event; - int flags = 0; + struct sctp_bind_hashbucket *head; /* Migrate socket buffer sizes and all the socket level options to the * new socket. @@ -6343,23 +6442,21 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, newsp->hmac = NULL; /* Hook this new socket in to the bind_hash list. */ + head = &sctp_port_hashtable[sctp_phashfn(inet_sk(oldsk)->inet_num)]; + sctp_local_bh_disable(); + sctp_spin_lock(&head->lock); pp = sctp_sk(oldsk)->bind_hash; sk_add_bind_node(newsk, &pp->owner); sctp_sk(newsk)->bind_hash = pp; - inet_sk(newsk)->num = inet_sk(oldsk)->num; + inet_sk(newsk)->inet_num = inet_sk(oldsk)->inet_num; + sctp_spin_unlock(&head->lock); + sctp_local_bh_enable(); /* Copy the bind_addr list from the original endpoint to the new * endpoint so that we can handle restarts properly */ - if (PF_INET6 == assoc->base.sk->sk_family) - flags = SCTP_ADDR6_ALLOWED; - if (assoc->peer.ipv4_address) - flags |= SCTP_ADDR4_PEERSUPP; - if (assoc->peer.ipv6_address) - flags |= SCTP_ADDR6_PEERSUPP; - sctp_bind_addr_copy(&newsp->ep->base.bind_addr, - &oldsp->ep->base.bind_addr, - SCTP_SCOPE_GLOBAL, GFP_KERNEL, flags); + sctp_bind_addr_dup(&newsp->ep->base.bind_addr, + &oldsp->ep->base.bind_addr, GFP_KERNEL); /* Move any messages in the old socket's receive queue that are for the * peeled off association to the new socket's receive queue. @@ -6367,7 +6464,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { - sctp_sock_rfree_frag(skb); __skb_unlink(skb, &oldsk->sk_receive_queue); __skb_queue_tail(&newsk->sk_receive_queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); @@ -6398,7 +6494,6 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) { event = sctp_skb2event(skb); if (event->asoc == assoc) { - sctp_sock_rfree_frag(skb); __skb_unlink(skb, &oldsp->pd_lobby); __skb_queue_tail(queue, skb); sctp_skb_set_owner_r_frag(skb, newsk); @@ -6413,15 +6508,11 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, } - sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp) { - sctp_sock_rfree_frag(skb); + sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp) sctp_skb_set_owner_r_frag(skb, newsk); - } - sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp) { - sctp_sock_rfree_frag(skb); + sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp) sctp_skb_set_owner_r_frag(skb, newsk); - } /* Set the type of socket to indicate that it is peeled off from the * original UDP-style socket or created with the accept() call on a @@ -6480,9 +6571,11 @@ struct proto sctp_prot = { .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, .memory_allocated = &sctp_memory_allocated, + .sockets_allocated = &sctp_sockets_allocated, }; #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + struct proto sctpv6_prot = { .name = "SCTPv6", .owner = THIS_MODULE, @@ -6510,5 +6603,6 @@ struct proto sctpv6_prot = { .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, .memory_allocated = &sctp_memory_allocated, + .sockets_allocated = &sctp_sockets_allocated, }; #endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */