diff options
Diffstat (limited to 'net/sctp')
| -rw-r--r-- | net/sctp/associola.c | 5 | ||||
| -rw-r--r-- | net/sctp/endpointola.c | 52 | ||||
| -rw-r--r-- | net/sctp/input.c | 200 | ||||
| -rw-r--r-- | net/sctp/ipv6.c | 2 | ||||
| -rw-r--r-- | net/sctp/output.c | 2 | ||||
| -rw-r--r-- | net/sctp/proc.c | 326 | ||||
| -rw-r--r-- | net/sctp/protocol.c | 42 | ||||
| -rw-r--r-- | net/sctp/sm_sideeffect.c | 30 | ||||
| -rw-r--r-- | net/sctp/sm_statefuns.c | 17 | ||||
| -rw-r--r-- | net/sctp/socket.c | 8 | ||||
| -rw-r--r-- | net/sctp/sysctl.c | 7 | ||||
| -rw-r--r-- | net/sctp/transport.c | 8 |
12 files changed, 371 insertions, 328 deletions
diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 559afd0ee..2bf8ec92d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -383,6 +383,7 @@ void sctp_association_free(struct sctp_association *asoc) list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { transport = list_entry(pos, struct sctp_transport, transports); list_del_rcu(pos); + sctp_unhash_transport(transport); sctp_transport_free(transport); } @@ -500,6 +501,8 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, /* Remove this peer from the list. */ list_del_rcu(&peer->transports); + /* Remove this peer from the transport hashtable */ + sctp_unhash_transport(peer); /* Get the first transport of asoc. */ pos = asoc->peer.transport_addr_list.next; @@ -699,6 +702,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, /* Attach the remote transport to our asoc. */ list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list); asoc->peer.transport_count++; + /* Add this peer into the transport hashtable */ + sctp_hash_transport(peer); /* If we do not yet have a primary path, set one. */ if (!asoc->peer.primary_path) { diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 9da76ba4d..2522a6175 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -314,21 +314,16 @@ struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep, } /* Find the association that goes with this chunk. - * We do a linear search of the associations for this endpoint. - * We return the matching transport address too. + * We lookup the transport from hashtable at first, then get association + * through t->assoc. */ -static struct sctp_association *__sctp_endpoint_lookup_assoc( +struct sctp_association *sctp_endpoint_lookup_assoc( const struct sctp_endpoint *ep, const union sctp_addr *paddr, struct sctp_transport **transport) { struct sctp_association *asoc = NULL; - struct sctp_association *tmp; - struct sctp_transport *t = NULL; - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; - int hash; - int rport; + struct sctp_transport *t; *transport = NULL; @@ -337,45 +332,16 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( */ if (!ep->base.bind_addr.port) goto out; + t = sctp_epaddr_lookup_transport(ep, paddr); + if (!t) + goto out; - rport = ntohs(paddr->v4.sin_port); - - hash = sctp_assoc_hashfn(sock_net(ep->base.sk), ep->base.bind_addr.port, - rport); - head = &sctp_assoc_hashtable[hash]; - read_lock(&head->lock); - sctp_for_each_hentry(epb, &head->chain) { - tmp = sctp_assoc(epb); - if (tmp->ep != ep || rport != tmp->peer.port) - continue; - - t = sctp_assoc_lookup_paddr(tmp, paddr); - if (t) { - asoc = tmp; - *transport = t; - break; - } - } - read_unlock(&head->lock); + *transport = t; + asoc = t->asoc; out: return asoc; } -/* Lookup association on an endpoint based on a peer address. BH-safe. */ -struct sctp_association *sctp_endpoint_lookup_assoc( - const struct sctp_endpoint *ep, - const union sctp_addr *paddr, - struct sctp_transport **transport) -{ - struct sctp_association *asoc; - - local_bh_disable(); - asoc = __sctp_endpoint_lookup_assoc(ep, paddr, transport); - local_bh_enable(); - - return asoc; -} - /* Look for any peeled off association from the endpoint that matches the * given peer address. */ diff --git a/net/sctp/input.c b/net/sctp/input.c index b6493b3f1..49d2cc751 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -782,65 +782,149 @@ hit: return ep; } -/* Insert association into the hash table. */ -static void __sctp_hash_established(struct sctp_association *asoc) +/* rhashtable for transport */ +struct sctp_hash_cmp_arg { + const struct sctp_endpoint *ep; + const union sctp_addr *laddr; + const union sctp_addr *paddr; + const struct net *net; +}; + +static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - struct net *net = sock_net(asoc->base.sk); - struct sctp_ep_common *epb; - struct sctp_hashbucket *head; + const struct sctp_hash_cmp_arg *x = arg->key; + const struct sctp_transport *t = ptr; + struct sctp_association *asoc = t->asoc; + const struct net *net = x->net; - epb = &asoc->base; + if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr)) + return 1; + if (!net_eq(sock_net(asoc->base.sk), net)) + return 1; + if (x->ep) { + if (x->ep != asoc->ep) + return 1; + } else { + if (x->laddr->v4.sin_port != htons(asoc->base.bind_addr.port)) + return 1; + if (!sctp_bind_addr_match(&asoc->base.bind_addr, + x->laddr, sctp_sk(asoc->base.sk))) + return 1; + } - /* Calculate which chain this entry will belong to. */ - epb->hashent = sctp_assoc_hashfn(net, epb->bind_addr.port, - asoc->peer.port); + return 0; +} - head = &sctp_assoc_hashtable[epb->hashent]; +static inline u32 sctp_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct sctp_transport *t = data; + const union sctp_addr *paddr = &t->ipaddr; + const struct net *net = sock_net(t->asoc->base.sk); + u16 lport = htons(t->asoc->base.bind_addr.port); + u32 addr; + + if (paddr->sa.sa_family == AF_INET6) + addr = jhash(&paddr->v6.sin6_addr, 16, seed); + else + addr = paddr->v4.sin_addr.s_addr; - write_lock(&head->lock); - hlist_add_head(&epb->node, &head->chain); - write_unlock(&head->lock); + return jhash_3words(addr, ((__u32)paddr->v4.sin_port) << 16 | + (__force __u32)lport, net_hash_mix(net), seed); } -/* Add an association to the hash. Local BH-safe. */ -void sctp_hash_established(struct sctp_association *asoc) +static inline u32 sctp_hash_key(const void *data, u32 len, u32 seed) { - if (asoc->temp) - return; + const struct sctp_hash_cmp_arg *x = data; + const union sctp_addr *paddr = x->paddr; + const struct net *net = x->net; + u16 lport; + u32 addr; + + lport = x->ep ? htons(x->ep->base.bind_addr.port) : + x->laddr->v4.sin_port; + if (paddr->sa.sa_family == AF_INET6) + addr = jhash(&paddr->v6.sin6_addr, 16, seed); + else + addr = paddr->v4.sin_addr.s_addr; - local_bh_disable(); - __sctp_hash_established(asoc); - local_bh_enable(); + return jhash_3words(addr, ((__u32)paddr->v4.sin_port) << 16 | + (__force __u32)lport, net_hash_mix(net), seed); } -/* Remove association from the hash table. */ -static void __sctp_unhash_established(struct sctp_association *asoc) +static const struct rhashtable_params sctp_hash_params = { + .head_offset = offsetof(struct sctp_transport, node), + .hashfn = sctp_hash_key, + .obj_hashfn = sctp_hash_obj, + .obj_cmpfn = sctp_hash_cmp, + .automatic_shrinking = true, +}; + +int sctp_transport_hashtable_init(void) { - struct net *net = sock_net(asoc->base.sk); - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; + return rhashtable_init(&sctp_transport_hashtable, &sctp_hash_params); +} - epb = &asoc->base; +void sctp_transport_hashtable_destroy(void) +{ + rhashtable_destroy(&sctp_transport_hashtable); +} - epb->hashent = sctp_assoc_hashfn(net, epb->bind_addr.port, - asoc->peer.port); +void sctp_hash_transport(struct sctp_transport *t) +{ + struct sctp_hash_cmp_arg arg; - head = &sctp_assoc_hashtable[epb->hashent]; + if (t->asoc->temp) + return; - write_lock(&head->lock); - hlist_del_init(&epb->node); - write_unlock(&head->lock); + arg.ep = t->asoc->ep; + arg.paddr = &t->ipaddr; + arg.net = sock_net(t->asoc->base.sk); + +reinsert: + if (rhashtable_lookup_insert_key(&sctp_transport_hashtable, &arg, + &t->node, sctp_hash_params) == -EBUSY) + goto reinsert; } -/* Remove association from the hash table. Local BH-safe. */ -void sctp_unhash_established(struct sctp_association *asoc) +void sctp_unhash_transport(struct sctp_transport *t) { - if (asoc->temp) + if (t->asoc->temp) return; - local_bh_disable(); - __sctp_unhash_established(asoc); - local_bh_enable(); + rhashtable_remove_fast(&sctp_transport_hashtable, &t->node, + sctp_hash_params); +} + +struct sctp_transport *sctp_addrs_lookup_transport( + struct net *net, + const union sctp_addr *laddr, + const union sctp_addr *paddr) +{ + struct sctp_hash_cmp_arg arg = { + .ep = NULL, + .laddr = laddr, + .paddr = paddr, + .net = net, + }; + + return rhashtable_lookup_fast(&sctp_transport_hashtable, &arg, + sctp_hash_params); +} + +struct sctp_transport *sctp_epaddr_lookup_transport( + const struct sctp_endpoint *ep, + const union sctp_addr *paddr) +{ + struct net *net = sock_net(ep->base.sk); + struct sctp_hash_cmp_arg arg = { + .ep = ep, + .paddr = paddr, + .net = net, + }; + + return rhashtable_lookup_fast(&sctp_transport_hashtable, &arg, + sctp_hash_params); } /* Look up an association. */ @@ -850,38 +934,26 @@ static struct sctp_association *__sctp_lookup_association( const union sctp_addr *peer, struct sctp_transport **pt) { - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; - struct sctp_association *asoc; - struct sctp_transport *transport; - int hash; + struct sctp_transport *t; + struct sctp_association *asoc = NULL; - /* Optimize here for direct hit, only listening connections can - * have wildcards anyways. - */ - hash = sctp_assoc_hashfn(net, ntohs(local->v4.sin_port), - ntohs(peer->v4.sin_port)); - head = &sctp_assoc_hashtable[hash]; - read_lock(&head->lock); - sctp_for_each_hentry(epb, &head->chain) { - asoc = sctp_assoc(epb); - transport = sctp_assoc_is_match(asoc, net, local, peer); - if (transport) - goto hit; - } + rcu_read_lock(); + t = sctp_addrs_lookup_transport(net, local, peer); + if (!t || !sctp_transport_hold(t)) + goto out; - read_unlock(&head->lock); + asoc = t->asoc; + sctp_association_hold(asoc); + *pt = t; - return NULL; + sctp_transport_put(t); -hit: - *pt = transport; - sctp_association_hold(asoc); - read_unlock(&head->lock); +out: + rcu_read_unlock(); return asoc; } -/* Look up an association. BH-safe. */ +/* Look up an association. protected by RCU read lock */ static struct sctp_association *sctp_lookup_association(struct net *net, const union sctp_addr *laddr, @@ -890,9 +962,7 @@ struct sctp_association *sctp_lookup_association(struct net *net, { struct sctp_association *asoc; - local_bh_disable(); asoc = __sctp_lookup_association(net, laddr, paddr, transportp); - local_bh_enable(); return asoc; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index ec529121f..ce46f1c7f 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -526,6 +526,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1, } return 0; } + if (addr1->v6.sin6_port != addr2->v6.sin6_port) + return 0; if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; /* If this is a linklocal address, compare the scope_id. */ diff --git a/net/sctp/output.c b/net/sctp/output.c index abe7c2db2..9d610eddd 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -534,7 +534,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. */ if (!sctp_checksum_disable) { - if (!(dst->dev->features & NETIF_F_SCTP_CSUM) || + if (!(dst->dev->features & NETIF_F_SCTP_CRC) || (dst_xfrm(dst) != NULL) || packet->ipfragok) { sh->checksum = sctp_compute_cksum(nskb, 0); } else { diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 0697eda5a..963dffcc2 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -165,8 +165,6 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa list_for_each_entry_rcu(transport, &assoc->peer.transport_addr_list, transports) { addr = &transport->ipaddr; - if (transport->dead) - continue; af = sctp_get_af_specific(addr->sa.sa_family); if (af->cmp_addr(addr, primary)) { @@ -281,88 +279,140 @@ void sctp_eps_proc_exit(struct net *net) remove_proc_entry("eps", net->sctp.proc_net_sctp); } +struct sctp_ht_iter { + struct seq_net_private p; + struct rhashtable_iter hti; +}; -static void *sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) +static struct sctp_transport *sctp_transport_get_next(struct seq_file *seq) { - if (*pos >= sctp_assoc_hashsize) - return NULL; + struct sctp_ht_iter *iter = seq->private; + struct sctp_transport *t; - if (*pos < 0) - *pos = 0; + t = rhashtable_walk_next(&iter->hti); + for (; t; t = rhashtable_walk_next(&iter->hti)) { + if (IS_ERR(t)) { + if (PTR_ERR(t) == -EAGAIN) + continue; + break; + } - if (*pos == 0) - seq_printf(seq, " ASSOC SOCK STY SST ST HBKT " - "ASSOC-ID TX_QUEUE RX_QUEUE UID INODE LPORT " - "RPORT LADDRS <-> RADDRS " - "HBINT INS OUTS MAXRT T1X T2X RTXC " - "wmema wmemq sndbuf rcvbuf\n"); + if (net_eq(sock_net(t->asoc->base.sk), seq_file_net(seq)) && + t->asoc->peer.primary_path == t) + break; + } - return (void *)pos; + return t; } -static void sctp_assocs_seq_stop(struct seq_file *seq, void *v) +static struct sctp_transport *sctp_transport_get_idx(struct seq_file *seq, + loff_t pos) { + void *obj = SEQ_START_TOKEN; + + while (pos && (obj = sctp_transport_get_next(seq)) && !IS_ERR(obj)) + pos--; + + return obj; } +static int sctp_transport_walk_start(struct seq_file *seq) +{ + struct sctp_ht_iter *iter = seq->private; + int err; + + err = rhashtable_walk_init(&sctp_transport_hashtable, &iter->hti); + if (err) + return err; + + err = rhashtable_walk_start(&iter->hti); + + return err == -EAGAIN ? 0 : err; +} + +static void sctp_transport_walk_stop(struct seq_file *seq) +{ + struct sctp_ht_iter *iter = seq->private; + + rhashtable_walk_stop(&iter->hti); + rhashtable_walk_exit(&iter->hti); +} + +static void *sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) +{ + int err = sctp_transport_walk_start(seq); + + if (err) + return ERR_PTR(err); + + return sctp_transport_get_idx(seq, *pos); +} + +static void sctp_assocs_seq_stop(struct seq_file *seq, void *v) +{ + sctp_transport_walk_stop(seq); +} static void *sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - if (++*pos >= sctp_assoc_hashsize) - return NULL; + ++*pos; - return pos; + return sctp_transport_get_next(seq); } /* Display sctp associations (/proc/net/sctp/assocs). */ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) { - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; + struct sctp_transport *transport; struct sctp_association *assoc; + struct sctp_ep_common *epb; struct sock *sk; - int hash = *(loff_t *)v; - - if (hash >= sctp_assoc_hashsize) - return -ENOMEM; - head = &sctp_assoc_hashtable[hash]; - local_bh_disable(); - read_lock(&head->lock); - sctp_for_each_hentry(epb, &head->chain) { - assoc = sctp_assoc(epb); - sk = epb->sk; - if (!net_eq(sock_net(sk), seq_file_net(seq))) - continue; - seq_printf(seq, - "%8pK %8pK %-3d %-3d %-2d %-4d " - "%4d %8d %8d %7u %5lu %-5d %5d ", - assoc, sk, sctp_sk(sk)->type, sk->sk_state, - assoc->state, hash, - assoc->assoc_id, - assoc->sndbuf_used, - atomic_read(&assoc->rmem_alloc), - from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), - sock_i_ino(sk), - epb->bind_addr.port, - assoc->peer.port); - seq_printf(seq, " "); - sctp_seq_dump_local_addrs(seq, epb); - seq_printf(seq, "<-> "); - sctp_seq_dump_remote_addrs(seq, assoc); - seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d " - "%8d %8d %8d %8d", - assoc->hbinterval, assoc->c.sinit_max_instreams, - assoc->c.sinit_num_ostreams, assoc->max_retrans, - assoc->init_retries, assoc->shutdown_retries, - assoc->rtx_data_chunks, - atomic_read(&sk->sk_wmem_alloc), - sk->sk_wmem_queued, - sk->sk_sndbuf, - sk->sk_rcvbuf); - seq_printf(seq, "\n"); + if (v == SEQ_START_TOKEN) { + seq_printf(seq, " ASSOC SOCK STY SST ST HBKT " + "ASSOC-ID TX_QUEUE RX_QUEUE UID INODE LPORT " + "RPORT LADDRS <-> RADDRS " + "HBINT INS OUTS MAXRT T1X T2X RTXC " + "wmema wmemq sndbuf rcvbuf\n"); + return 0; } - read_unlock(&head->lock); - local_bh_enable(); + + transport = (struct sctp_transport *)v; + if (!sctp_transport_hold(transport)) + return 0; + assoc = transport->asoc; + epb = &assoc->base; + sk = epb->sk; + + seq_printf(seq, + "%8pK %8pK %-3d %-3d %-2d %-4d " + "%4d %8d %8d %7u %5lu %-5d %5d ", + assoc, sk, sctp_sk(sk)->type, sk->sk_state, + assoc->state, 0, + assoc->assoc_id, + assoc->sndbuf_used, + atomic_read(&assoc->rmem_alloc), + from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), + sock_i_ino(sk), + epb->bind_addr.port, + assoc->peer.port); + seq_printf(seq, " "); + sctp_seq_dump_local_addrs(seq, epb); + seq_printf(seq, "<-> "); + sctp_seq_dump_remote_addrs(seq, assoc); + seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d " + "%8d %8d %8d %8d", + assoc->hbinterval, assoc->c.sinit_max_instreams, + assoc->c.sinit_num_ostreams, assoc->max_retrans, + assoc->init_retries, assoc->shutdown_retries, + assoc->rtx_data_chunks, + atomic_read(&sk->sk_wmem_alloc), + sk->sk_wmem_queued, + sk->sk_sndbuf, + sk->sk_rcvbuf); + seq_printf(seq, "\n"); + + sctp_transport_put(transport); return 0; } @@ -378,7 +428,7 @@ static const struct seq_operations sctp_assoc_ops = { static int sctp_assocs_seq_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &sctp_assoc_ops, - sizeof(struct seq_net_private)); + sizeof(struct sctp_ht_iter)); } static const struct file_operations sctp_assocs_seq_fops = { @@ -409,112 +459,96 @@ void sctp_assocs_proc_exit(struct net *net) static void *sctp_remaddr_seq_start(struct seq_file *seq, loff_t *pos) { - if (*pos >= sctp_assoc_hashsize) - return NULL; + int err = sctp_transport_walk_start(seq); - if (*pos < 0) - *pos = 0; - - if (*pos == 0) - seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX " - "REM_ADDR_RTX START STATE\n"); + if (err) + return ERR_PTR(err); - return (void *)pos; + return sctp_transport_get_idx(seq, *pos); } static void *sctp_remaddr_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - if (++*pos >= sctp_assoc_hashsize) - return NULL; + ++*pos; - return pos; + return sctp_transport_get_next(seq); } static void sctp_remaddr_seq_stop(struct seq_file *seq, void *v) { + sctp_transport_walk_stop(seq); } static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) { - struct sctp_hashbucket *head; - struct sctp_ep_common *epb; struct sctp_association *assoc; - struct sctp_transport *tsp; - int hash = *(loff_t *)v; + struct sctp_transport *transport, *tsp; - if (hash >= sctp_assoc_hashsize) - return -ENOMEM; + if (v == SEQ_START_TOKEN) { + seq_printf(seq, "ADDR ASSOC_ID HB_ACT RTO MAX_PATH_RTX " + "REM_ADDR_RTX START STATE\n"); + return 0; + } - head = &sctp_assoc_hashtable[hash]; - local_bh_disable(); - read_lock(&head->lock); - rcu_read_lock(); - sctp_for_each_hentry(epb, &head->chain) { - if (!net_eq(sock_net(epb->sk), seq_file_net(seq))) - continue; - assoc = sctp_assoc(epb); - list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, - transports) { - if (tsp->dead) - continue; + transport = (struct sctp_transport *)v; + if (!sctp_transport_hold(transport)) + return 0; + assoc = transport->asoc; + + list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, + transports) { + /* + * The remote address (ADDR) + */ + tsp->af_specific->seq_dump_addr(seq, &tsp->ipaddr); + seq_printf(seq, " "); + /* + * The association ID (ASSOC_ID) + */ + seq_printf(seq, "%d ", tsp->asoc->assoc_id); + + /* + * If the Heartbeat is active (HB_ACT) + * Note: 1 = Active, 0 = Inactive + */ + seq_printf(seq, "%d ", timer_pending(&tsp->hb_timer)); + + /* + * Retransmit time out (RTO) + */ + seq_printf(seq, "%lu ", tsp->rto); + + /* + * Maximum path retransmit count (PATH_MAX_RTX) + */ + seq_printf(seq, "%d ", tsp->pathmaxrxt); + + /* + * remote address retransmit count (REM_ADDR_RTX) + * Note: We don't have a way to tally this at the moment + * so lets just leave it as zero for the moment + */ + seq_puts(seq, "0 "); + + /* + * remote address start time (START). This is also not + * currently implemented, but we can record it with a + * jiffies marker in a subsequent patch + */ + seq_puts(seq, "0 "); + + /* + * The current state of this destination. I.e. + * SCTP_ACTIVE, SCTP_INACTIVE, ... + */ + seq_printf(seq, "%d", tsp->state); - /* - * The remote address (ADDR) - */ - tsp->af_specific->seq_dump_addr(seq, &tsp->ipaddr); - seq_printf(seq, " "); - - /* - * The association ID (ASSOC_ID) - */ - seq_printf(seq, "%d ", tsp->asoc->assoc_id); - - /* - * If the Heartbeat is active (HB_ACT) - * Note: 1 = Active, 0 = Inactive - */ - seq_printf(seq, "%d ", timer_pending(&tsp->hb_timer)); - - /* - * Retransmit time out (RTO) - */ - seq_printf(seq, "%lu ", tsp->rto); - - /* - * Maximum path retransmit count (PATH_MAX_RTX) - */ - seq_printf(seq, "%d ", tsp->pathmaxrxt); - - /* - * remote address retransmit count (REM_ADDR_RTX) - * Note: We don't have a way to tally this at the moment - * so lets just leave it as zero for the moment - */ - seq_puts(seq, "0 "); - - /* - * remote address start time (START). This is also not - * currently implemented, but we can record it with a - * jiffies marker in a subsequent patch - */ - seq_puts(seq, "0 "); - - /* - * The current state of this destination. I.e. - * SCTP_ACTIVE, SCTP_INACTIVE, ... - */ - seq_printf(seq, "%d", tsp->state); - - seq_printf(seq, "\n"); - } + seq_printf(seq, "\n"); } - rcu_read_unlock(); - read_unlock(&head->lock); - local_bh_enable(); + sctp_transport_put(transport); return 0; - } static const struct seq_operations sctp_remaddr_ops = { @@ -533,7 +567,7 @@ void sctp_remaddr_proc_exit(struct net *net) static int sctp_remaddr_seq_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &sctp_remaddr_ops, - sizeof(struct seq_net_private)); + sizeof(struct sctp_ht_iter)); } static const struct file_operations sctp_remaddr_seq_fops = { diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 8b4ff3156..1099e99a5 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1225,6 +1225,9 @@ static int __net_init sctp_defaults_init(struct net *net) /* Max.Burst - 4 */ net->sctp.max_burst = SCTP_DEFAULT_MAX_BURST; + /* Enable pf state by default */ + net->sctp.pf_enable = 1; + /* Association.Max.Retrans - 10 attempts * Path.Max.Retrans - 5 attempts (per destination address) * Max.Init.Retransmits - 8 attempts @@ -1427,24 +1430,6 @@ static __init int sctp_init(void) /* Limit the page order by that maximum hash table size */ order = min(order, max_entry_order); - do { - sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE / - sizeof(struct sctp_hashbucket); - if ((sctp_assoc_hashsize > (64 * 1024)) && order > 0) - continue; - sctp_assoc_hashtable = (struct sctp_hashbucket *) - __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); - } while (!sctp_assoc_hashtable && --order > 0); - if (!sctp_assoc_hashtable) { - pr_err("Failed association hash alloc\n"); - status = -ENOMEM; - goto err_ahash_alloc; - } - for (i = 0; i < sctp_assoc_hashsize; i++) { - rwlock_init(&sctp_assoc_hashtable[i].lock); - INIT_HLIST_HEAD(&sctp_assoc_hashtable[i].chain); - } - /* Allocate and initialize the endpoint hash table. */ sctp_ep_hashsize = 64; sctp_ep_hashtable = @@ -1466,7 +1451,7 @@ static __init int sctp_init(void) */ do { sctp_port_hashtable = (struct sctp_bind_hashbucket *) - __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); + __get_free_pages(GFP_KERNEL | __GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); if (!sctp_port_hashtable) { @@ -1493,8 +1478,11 @@ static __init int sctp_init(void) INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); } - pr_info("Hash tables configured (established %d bind %d)\n", - sctp_assoc_hashsize, sctp_port_hashsize); + if (sctp_transport_hashtable_init()) + goto err_thash_alloc; + + pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize, + num_entries); sctp_sysctl_register(); @@ -1547,12 +1535,10 @@ err_register_defaults: get_order(sctp_port_hashsize * sizeof(struct sctp_bind_hashbucket))); err_bhash_alloc: + sctp_transport_hashtable_destroy(); +err_thash_alloc: kfree(sctp_ep_hashtable); err_ehash_alloc: - free_pages((unsigned long)sctp_assoc_hashtable, - get_order(sctp_assoc_hashsize * - sizeof(struct sctp_hashbucket))); -err_ahash_alloc: percpu_counter_destroy(&sctp_sockets_allocated); err_percpu_counter_init: kmem_cache_destroy(sctp_chunk_cachep); @@ -1586,13 +1572,11 @@ static __exit void sctp_exit(void) sctp_sysctl_unregister(); - free_pages((unsigned long)sctp_assoc_hashtable, - get_order(sctp_assoc_hashsize * - sizeof(struct sctp_hashbucket))); - kfree(sctp_ep_hashtable); free_pages((unsigned long)sctp_port_hashtable, get_order(sctp_port_hashsize * sizeof(struct sctp_bind_hashbucket))); + kfree(sctp_ep_hashtable); + sctp_transport_hashtable_destroy(); percpu_counter_destroy(&sctp_sockets_allocated); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 6098d4c42..b5327bb77 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -63,7 +63,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, sctp_state_t state, struct sctp_endpoint *ep, - struct sctp_association *asoc, + struct sctp_association **asoc, void *event_arg, sctp_disposition_t status, sctp_cmd_seq_t *commands, @@ -259,12 +259,6 @@ void sctp_generate_t3_rtx_event(unsigned long peer) goto out_unlock; } - /* Is this transport really dead and just waiting around for - * the timer to let go of the reference? - */ - if (transport->dead) - goto out_unlock; - /* Run through the state machine. */ error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_T3_RTX), @@ -380,12 +374,6 @@ void sctp_generate_heartbeat_event(unsigned long data) goto out_unlock; } - /* Is this structure just waiting around for us to actually - * get destroyed? - */ - if (transport->dead) - goto out_unlock; - error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_HEARTBEAT), asoc->state, asoc->ep, asoc, @@ -477,6 +465,8 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, struct sctp_transport *transport, int is_hb) { + struct net *net = sock_net(asoc->base.sk); + /* The check for association's overall error counter exceeding the * threshold is done in the state function. */ @@ -503,7 +493,8 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, * is SCTP_ACTIVE, then mark this transport as Partially Failed, * see SCTP Quick Failover Draft, section 5.1 */ - if ((transport->state == SCTP_ACTIVE) && + if (net->sctp.pf_enable && + (transport->state == SCTP_ACTIVE) && (asoc->pf_retrans < transport->pathmaxrxt) && (transport->error_count > asoc->pf_retrans)) { @@ -863,7 +854,6 @@ static void sctp_cmd_delete_tcb(sctp_cmd_seq_t *cmds, (!asoc->temp) && (sk->sk_shutdown != SHUTDOWN_MASK)) return; - sctp_unhash_established(asoc); sctp_association_free(asoc); } @@ -1123,7 +1113,7 @@ int sctp_do_sm(struct net *net, sctp_event_t event_type, sctp_subtype_t subtype, debug_post_sfn(); error = sctp_side_effects(event_type, subtype, state, - ep, asoc, event_arg, status, + ep, &asoc, event_arg, status, &commands, gfp); debug_post_sfx(); @@ -1136,7 +1126,7 @@ int sctp_do_sm(struct net *net, sctp_event_t event_type, sctp_subtype_t subtype, static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, sctp_state_t state, struct sctp_endpoint *ep, - struct sctp_association *asoc, + struct sctp_association **asoc, void *event_arg, sctp_disposition_t status, sctp_cmd_seq_t *commands, @@ -1151,7 +1141,7 @@ static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, * disposition SCTP_DISPOSITION_CONSUME. */ if (0 != (error = sctp_cmd_interpreter(event_type, subtype, state, - ep, asoc, + ep, *asoc, event_arg, status, commands, gfp))) goto bail; @@ -1174,11 +1164,12 @@ static int sctp_side_effects(sctp_event_t event_type, sctp_subtype_t subtype, break; case SCTP_DISPOSITION_DELETE_TCB: + case SCTP_DISPOSITION_ABORT: /* This should now be a command. */ + *asoc = NULL; break; case SCTP_DISPOSITION_CONSUME: - case SCTP_DISPOSITION_ABORT: /* * We should no longer have much work to do here as the * real work has been done as explicit commands above. @@ -1266,7 +1257,6 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, asoc = cmd->obj.asoc; BUG_ON(asoc->peer.primary_path == NULL); sctp_endpoint_add_asoc(ep, asoc); - sctp_hash_established(asoc); break; case SCTP_CMD_UPDATE_ASSOC: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 22c2bf367..f1f08c8f2 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2976,7 +2976,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_IN_DATA_CHUNK_DISCARDS); goto discard_force; case SCTP_IERROR_NO_DATA: - goto consume; + return SCTP_DISPOSITION_ABORT; case SCTP_IERROR_PROTO_VIOLATION: return sctp_sf_abort_violation(net, ep, asoc, chunk, commands, (u8 *)chunk->subh.data_hdr, sizeof(sctp_datahdr_t)); @@ -3043,9 +3043,6 @@ discard_noforce: sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, force); return SCTP_DISPOSITION_DISCARD; -consume: - return SCTP_DISPOSITION_CONSUME; - } /* @@ -3093,7 +3090,7 @@ sctp_disposition_t sctp_sf_eat_data_fast_4_4(struct net *net, case SCTP_IERROR_BAD_STREAM: break; case SCTP_IERROR_NO_DATA: - goto consume; + return SCTP_DISPOSITION_ABORT; case SCTP_IERROR_PROTO_VIOLATION: return sctp_sf_abort_violation(net, ep, asoc, chunk, commands, (u8 *)chunk->subh.data_hdr, sizeof(sctp_datahdr_t)); @@ -3119,7 +3116,6 @@ sctp_disposition_t sctp_sf_eat_data_fast_4_4(struct net *net, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); } -consume: return SCTP_DISPOSITION_CONSUME; } @@ -4825,9 +4821,6 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort( * if necessary to fill gaps. */ struct sctp_chunk *abort = arg; - sctp_disposition_t retval; - - retval = SCTP_DISPOSITION_CONSUME; if (abort) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); @@ -4845,7 +4838,7 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort( SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); - return retval; + return SCTP_DISPOSITION_ABORT; } /* We tried an illegal operation on an association which is closed. */ @@ -4960,12 +4953,10 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort( sctp_cmd_seq_t *commands) { struct sctp_chunk *abort = arg; - sctp_disposition_t retval; /* Stop T1-init timer */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); - retval = SCTP_DISPOSITION_CONSUME; if (abort) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); @@ -4985,7 +4976,7 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort( sctp_add_cmd_sf(commands, SCTP_CMD_INIT_FAILED, SCTP_PERR(SCTP_ERROR_USER_ABORT)); - return retval; + return SCTP_DISPOSITION_ABORT; } /* diff --git a/net/sctp/socket.c b/net/sctp/socket.c index be1489fc3..e878da094 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1228,7 +1228,6 @@ out_free: * To the hash table, try to unhash it, just in case, its a noop * if it wasn't hashed so we're safe */ - sctp_unhash_established(asoc); sctp_association_free(asoc); } return err; @@ -1504,7 +1503,6 @@ static void sctp_close(struct sock *sk, long timeout) * ABORT or SHUTDOWN based on the linger options. */ if (sctp_state(asoc, CLOSED)) { - sctp_unhash_established(asoc); sctp_association_free(asoc); continue; } @@ -1986,10 +1984,8 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) goto out_unlock; out_free: - if (new_asoc) { - sctp_unhash_established(asoc); + if (new_asoc) sctp_association_free(asoc); - } out_unlock: release_sock(sk); @@ -6987,7 +6983,7 @@ void sctp_data_ready(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); - if (wq_has_sleeper(wq)) + if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 3e0fc5127..daf8554fd 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -308,6 +308,13 @@ static struct ctl_table sctp_net_table[] = { .extra1 = &max_autoclose_min, .extra2 = &max_autoclose_max, }, + { + .procname = "pf_enable", + .data = &init_net.sctp.pf_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { /* sentinel */ } }; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index aab9e3f29..a431c1404 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -132,8 +132,6 @@ fail: */ void sctp_transport_free(struct sctp_transport *transport) { - transport->dead = 1; - /* Try to delete the heartbeat timer. */ if (del_timer(&transport->hb_timer)) sctp_transport_put(transport); @@ -169,7 +167,7 @@ static void sctp_transport_destroy_rcu(struct rcu_head *head) */ static void sctp_transport_destroy(struct sctp_transport *transport) { - if (unlikely(!transport->dead)) { + if (unlikely(atomic_read(&transport->refcnt))) { WARN(1, "Attempt to destroy undead transport %p!\n", transport); return; } @@ -296,9 +294,9 @@ void sctp_transport_route(struct sctp_transport *transport, } /* Hold a reference to a transport. */ -void sctp_transport_hold(struct sctp_transport *transport) +int sctp_transport_hold(struct sctp_transport *transport) { - atomic_inc(&transport->refcnt); + return atomic_add_unless(&transport->refcnt, 1, 0); } /* Release a reference to a transport and clean up |