--- zzzz-none-000/linux-3.10.107/net/sctp/protocol.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/sctp/protocol.c 2021-02-04 17:41:59.000000000 +0000 @@ -23,16 +23,12 @@ * See the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with GNU CC; see the file COPYING. If not, write to - * the Free Software Foundation, 59 Temple Place - Suite 330, - * Boston, MA 02111-1307, USA. + * along with GNU CC; see the file COPYING. If not, see + * . * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers - * - * Or submit a bug report through the following website: - * http://www.sf.net/projects/lksctp + * lksctp developers * * Written or modified by: * La Monte H.P. Yarroll @@ -41,9 +37,6 @@ * Sridhar Samudrala * Daisy Chang * Ardelle Fan - * - * Any bugs reported given to us we will try to fix... any fixes shared will - * be incorporated into the next SCTP release. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -67,6 +60,8 @@ #include #include +#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) + /* Global data structures. */ struct sctp_globals sctp_globals __read_mostly; @@ -153,7 +148,7 @@ for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { /* Add the address to the local list. */ - addr = t_new(struct sctp_sockaddr_entry, GFP_ATOMIC); + addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v4.sin_family = AF_INET; addr->a.v4.sin_port = 0; @@ -178,7 +173,7 @@ rcu_read_lock(); for_each_netdev_rcu(net, dev) { - __list_for_each(pos, &sctp_address_families) { + list_for_each(pos, &sctp_address_families) { af = list_entry(pos, struct sctp_af, list); af->copy_addrlist(&net->sctp.local_addr_list, dev); } @@ -373,7 +368,7 @@ if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && - !sysctl_ip_nonlocal_bind) + !net->ipv4.sysctl_ip_nonlocal_bind) return 0; if (ipv6_only_sock(sctp_opt2sk(sp))) @@ -451,8 +446,8 @@ fl4->fl4_sport = saddr->v4.sin_port; } - SCTP_DEBUG_PRINTK("%s: DST:%pI4, SRC:%pI4 - ", - __func__, &fl4->daddr, &fl4->saddr); + pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr, + &fl4->saddr); rt = ip_route_output_key(sock_net(sk), fl4); if (!IS_ERR(rt)) @@ -494,23 +489,43 @@ */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { + struct net_device *odev; + if (!laddr->valid) continue; - if ((laddr->state == SCTP_ADDR_SRC) && - (AF_INET == laddr->a.sa.sa_family)) { - fl4->fl4_sport = laddr->a.v4.sin_port; - flowi4_update_output(fl4, - asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS(asoc->base.sk), - daddr->v4.sin_addr.s_addr, - laddr->a.v4.sin_addr.s_addr); - - rt = ip_route_output_key(sock_net(sk), fl4); - if (!IS_ERR(rt)) { - dst = &rt->dst; - goto out_unlock; - } + if (laddr->state != SCTP_ADDR_SRC || + AF_INET != laddr->a.sa.sa_family) + continue; + + fl4->fl4_sport = laddr->a.v4.sin_port; + flowi4_update_output(fl4, + asoc->base.sk->sk_bound_dev_if, + RT_CONN_FLAGS(asoc->base.sk), + daddr->v4.sin_addr.s_addr, + laddr->a.v4.sin_addr.s_addr); + + rt = ip_route_output_key(sock_net(sk), fl4); + if (IS_ERR(rt)) + continue; + + if (!dst) + dst = &rt->dst; + + /* Ensure the src address belongs to the output + * interface. + */ + odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr, + false); + if (!odev || odev->ifindex != fl4->flowi4_oif) { + if (&rt->dst != dst) + dst_release(&rt->dst); + continue; } + + if (dst != &rt->dst) + dst_release(dst); + dst = &rt->dst; + break; } out_unlock: @@ -518,10 +533,10 @@ out: t->dst = dst; if (dst) - SCTP_DEBUG_PRINTK("rt_dst:%pI4, rt_src:%pI4\n", - &fl4->daddr, &fl4->saddr); + pr_debug("rt_dst:%pI4, rt_src:%pI4\n", + &fl4->daddr, &fl4->saddr); else - SCTP_DEBUG_PRINTK("NO ROUTE\n"); + pr_debug("no route\n"); } /* For v4, the source address is cached in the route entry(dst). So no need @@ -557,7 +572,7 @@ struct sctp_association *asoc) { struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, - sk->sk_prot); + sk->sk_prot, 0); struct inet_sock *newinet; if (!newsk) @@ -583,10 +598,10 @@ return newsk; } -/* Map address, empty for v4 family */ -static void sctp_v4_addr_v4map(struct sctp_sock *sp, union sctp_addr *addr) +static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { - /* Empty */ + /* No address mapping for V4 sockets */ + return sizeof(struct sockaddr_in); } /* Dump the v4 addr to the seq file. */ @@ -609,9 +624,9 @@ spin_lock_bh(&net->sctp.addr_wq_lock); list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) { - SCTP_DEBUG_PRINTK_IPADDR("sctp_addrwq_timo_handler: the first ent in wq %p is ", - " for cmd %d at entry %p\n", &net->sctp.addr_waitq, &addrw->a, addrw->state, - addrw); + pr_debug("%s: the first ent in wq:%p is addr:%pISc for cmd:%d at " + "entry:%p\n", __func__, &net->sctp.addr_waitq, &addrw->a.sa, + addrw->state, addrw); #if IS_ENABLED(CONFIG_IPV6) /* Now we send an ASCONF for each association */ @@ -628,8 +643,10 @@ addrw->state == SCTP_ADDR_NEW) { unsigned long timeo_val; - SCTP_DEBUG_PRINTK("sctp_timo_handler: this is on DAD, trying %d sec later\n", - SCTP_ADDRESS_TICK_DELAY); + pr_debug("%s: this is on DAD, trying %d sec " + "later\n", __func__, + SCTP_ADDRESS_TICK_DELAY); + timeo_val = jiffies; timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY); mod_timer(&net->sctp.addr_wq_timer, timeo_val); @@ -644,10 +661,10 @@ /* ignore bound-specific endpoints */ if (!sctp_is_ep_boundall(sk)) continue; - sctp_bh_lock_sock(sk); + bh_lock_sock(sk); if (sctp_asconf_mgmt(sp, addrw) < 0) - SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: sctp_asconf_mgmt failed\n"); - sctp_bh_unlock_sock(sk); + pr_debug("%s: sctp_asconf_mgmt failed\n", __func__); + bh_unlock_sock(sk); } #if IS_ENABLED(CONFIG_IPV6) free_next: @@ -712,9 +729,10 @@ addrw = sctp_addr_wq_lookup(net, addr); if (addrw) { if (addrw->state != cmd) { - SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt offsets existing entry for %d ", - " in wq %p\n", addrw->state, &addrw->a, - &net->sctp.addr_waitq); + pr_debug("%s: offsets existing entry for %d, addr:%pISc " + "in wq:%p\n", __func__, addrw->state, &addrw->a.sa, + &net->sctp.addr_waitq); + list_del(&addrw->list); kfree(addrw); } @@ -730,8 +748,9 @@ } addrw->state = cmd; list_add_tail(&addrw->list, &net->sctp.addr_waitq); - SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt add new entry for cmd:%d ", - " in wq %p\n", addrw->state, &addrw->a, &net->sctp.addr_waitq); + + pr_debug("%s: add new entry for cmd:%d, addr:%pISc in wq:%p\n", + __func__, addrw->state, &addrw->a.sa, &net->sctp.addr_waitq); if (!timer_pending(&net->sctp.addr_wq_timer)) { timeo_val = jiffies; @@ -957,16 +976,15 @@ { struct inet_sock *inet = inet_sk(skb->sk); - SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", - __func__, skb, skb->len, - &transport->fl.u.ip4.saddr, - &transport->fl.u.ip4.daddr); + pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb, + skb->len, &transport->fl.u.ip4.saddr, &transport->fl.u.ip4.daddr); inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO : IP_PMTUDISC_DONT; SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS); - return ip_queue_xmit(skb, &transport->fl); + + return ip_queue_xmit(&inet->sk, skb, &transport->fl); } static struct sctp_af sctp_af_inet; @@ -980,7 +998,9 @@ .send_verify = sctp_inet_send_verify, .supported_addrs = sctp_inet_supported_addrs, .create_accept_sk = sctp_v4_create_accept_sk, - .addr_v4map = sctp_v4_addr_v4map, + .addr_to_user = sctp_v4_addr_to_user, + .to_sk_saddr = sctp_v4_to_sk_saddr, + .to_sk_daddr = sctp_v4_to_sk_daddr, .af = &sctp_af_inet }; @@ -1021,7 +1041,6 @@ .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, - .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; static struct inet_protosw sctp_stream_protosw = { @@ -1029,7 +1048,6 @@ .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, - .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; @@ -1039,6 +1057,7 @@ .err_handler = sctp_v4_err, .no_policy = 1, .netns_ok = 1, + .icmp_strict_tag_validation = 1, }; /* IPv4 address related functions. */ @@ -1052,8 +1071,6 @@ .copy_addrlist = sctp_v4_copy_addrlist, .from_skb = sctp_v4_from_skb, .from_sk = sctp_v4_from_sk, - .to_sk_saddr = sctp_v4_to_sk_saddr, - .to_sk_daddr = sctp_v4_to_sk_daddr, .from_addr_param = sctp_v4_from_addr_param, .to_addr_param = sctp_v4_to_addr_param, .cmp_addr = sctp_v4_cmp_addr, @@ -1074,8 +1091,8 @@ #endif }; -struct sctp_pf *sctp_get_pf_specific(sa_family_t family) { - +struct sctp_pf *sctp_get_pf_specific(sa_family_t family) +{ switch (family) { case PF_INET: return sctp_pf_inet_specific; @@ -1108,14 +1125,15 @@ static inline int init_sctp_mibs(struct net *net) { - return snmp_mib_init((void __percpu **)net->sctp.sctp_statistics, - sizeof(struct sctp_mib), - __alignof__(struct sctp_mib)); + net->sctp.sctp_statistics = alloc_percpu(struct sctp_mib); + if (!net->sctp.sctp_statistics) + return -ENOMEM; + return 0; } static inline void cleanup_sctp_mibs(struct net *net) { - snmp_mib_free((void __percpu **)net->sctp.sctp_statistics); + free_percpu(net->sctp.sctp_statistics); } static void sctp_v4_pf_init(void) @@ -1328,7 +1346,7 @@ }; /* Initialize the universe into something sensible. */ -SCTP_STATIC __init int sctp_init(void) +static __init int sctp_init(void) { int i; int status = -EINVAL; @@ -1336,10 +1354,10 @@ unsigned long limit; int max_share; int order; + int num_entries; + int max_entry_order; - /* SCTP_DEBUG sanity check. */ - if (!sctp_sanity_check()) - goto out; + sock_skb_cb_check_size(sizeof(struct sctp_ulpevent)); /* Allocate bind_bucket and chunk caches. */ status = -ENOBUFS; @@ -1357,7 +1375,7 @@ if (!sctp_chunk_cachep) goto err_chunk_cachep; - status = percpu_counter_init(&sctp_sockets_allocated, 0); + status = percpu_counter_init(&sctp_sockets_allocated, 0, GFP_KERNEL); if (status) goto err_percpu_counter_init; @@ -1390,14 +1408,24 @@ /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. + * Though not identical. Start by getting a goal size */ if (totalram_pages >= (128 * 1024)) goal = totalram_pages >> (22 - PAGE_SHIFT); else goal = totalram_pages >> (24 - PAGE_SHIFT); - for (order = 0; (1UL << order) < goal; order++) - ; + /* Then compute the page order for said goal */ + order = get_order(goal); + + /* Now compute the required page order for the maximum sized table we + * want to create + */ + max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES * + sizeof(struct sctp_bind_hashbucket)); + + /* Limit the page order by that maximum hash table size */ + order = min(order, max_entry_order); do { sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE / @@ -1431,20 +1459,35 @@ INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } - /* Allocate and initialize the SCTP port hash table. */ + /* Allocate and initialize the SCTP port hash table. + * Note that order is initalized to start at the max sized + * table we want to support. If we can't get that many pages + * reduce the order and try again + */ do { - sctp_port_hashsize = (1UL << order) * PAGE_SIZE / - sizeof(struct sctp_bind_hashbucket); - if ((sctp_port_hashsize > (64 * 1024)) && order > 0) - continue; sctp_port_hashtable = (struct sctp_bind_hashbucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); + if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); status = -ENOMEM; goto err_bhash_alloc; } + + /* Now compute the number of entries that will fit in the + * port hash space we allocated + */ + num_entries = (1UL << order) * PAGE_SIZE / + sizeof(struct sctp_bind_hashbucket); + + /* And finish by rounding it down to the nearest power of two + * this wastes some memory of course, but its needed because + * the hash function operates based on the assumption that + * that the number of entries is a power of two + */ + sctp_port_hashsize = rounddown_pow_of_two(num_entries); + for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); @@ -1484,7 +1527,6 @@ if (status) goto err_v6_add_protocol; - status = 0; out: return status; err_v6_add_protocol: @@ -1520,7 +1562,7 @@ } /* Exit handler for the SCTP protocol. */ -SCTP_STATIC __exit void sctp_exit(void) +static __exit void sctp_exit(void) { /* BUG. This should probably do something useful like clean * up all the remaining associations and all that memory. @@ -1568,7 +1610,7 @@ */ MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-132"); MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-132"); -MODULE_AUTHOR("Linux Kernel SCTP developers "); +MODULE_AUTHOR("Linux Kernel SCTP developers "); MODULE_DESCRIPTION("Support for the SCTP protocol (RFC2960)"); module_param_named(no_checksums, sctp_checksum_disable, bool, 0644); MODULE_PARM_DESC(no_checksums, "Disable checksums computing and verification");