diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-12-08 07:55:01 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-12-08 07:55:01 -0800 |
commit | d7fc02c7bae7b1cf69269992cf880a43a350cdaa (patch) | |
tree | a43d56fa72913a1cc98a0bbebe054d08581b3a7c /net/sctp | |
parent | ee1262dbc65ce0b6234a915d8432171e8d77f518 (diff) | |
parent | 28b4d5cc17c20786848cdc07b7ea237a309776bb (diff) | |
download | lwn-d7fc02c7bae7b1cf69269992cf880a43a350cdaa.tar.gz lwn-d7fc02c7bae7b1cf69269992cf880a43a350cdaa.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1815 commits)
mac80211: fix reorder buffer release
iwmc3200wifi: Enable wimax core through module parameter
iwmc3200wifi: Add wifi-wimax coexistence mode as a module parameter
iwmc3200wifi: Coex table command does not expect a response
iwmc3200wifi: Update wiwi priority table
iwlwifi: driver version track kernel version
iwlwifi: indicate uCode type when fail dump error/event log
iwl3945: remove duplicated event logging code
b43: fix two warnings
ipw2100: fix rebooting hang with driver loaded
cfg80211: indent regulatory messages with spaces
iwmc3200wifi: fix NULL pointer dereference in pmkid update
mac80211: Fix TX status reporting for injected data frames
ath9k: enable 2GHz band only if the device supports it
airo: Fix integer overflow warning
rt2x00: Fix padding bug on L2PAD devices.
WE: Fix set events not propagated
b43legacy: avoid PPC fault during resume
b43: avoid PPC fault during resume
tcp: fix a timewait refcnt race
...
Fix up conflicts due to sysctl cleanups (dead sysctl_check code and
CTL_UNNUMBERED removed) in
kernel/sysctl_check.c
net/ipv4/sysctl_net_ipv4.c
net/ipv6/addrconf.c
net/sctp/sysctl.c
Diffstat (limited to 'net/sctp')
-rw-r--r-- | net/sctp/associola.c | 27 | ||||
-rw-r--r-- | net/sctp/chunk.c | 15 | ||||
-rw-r--r-- | net/sctp/ipv6.c | 21 | ||||
-rw-r--r-- | net/sctp/output.c | 50 | ||||
-rw-r--r-- | net/sctp/outqueue.c | 26 | ||||
-rw-r--r-- | net/sctp/protocol.c | 19 | ||||
-rw-r--r-- | net/sctp/sm_make_chunk.c | 13 | ||||
-rw-r--r-- | net/sctp/sm_sideeffect.c | 5 | ||||
-rw-r--r-- | net/sctp/sm_statefuns.c | 26 | ||||
-rw-r--r-- | net/sctp/socket.c | 371 | ||||
-rw-r--r-- | net/sctp/sysctl.c | 14 | ||||
-rw-r--r-- | net/sctp/transport.c | 45 |
12 files changed, 201 insertions, 431 deletions
diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 7eed77a39d0d..df5abbff63e2 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -63,6 +63,12 @@ static void sctp_assoc_bh_rcv(struct work_struct *work); static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc); +/* Keep track of the new idr low so that we don't re-use association id + * numbers too fast. It is protected by they idr spin lock is in the + * range of 1 - INT_MAX. + */ +static u32 idr_low = 1; + /* 1st Level Abstractions. */ @@ -167,7 +173,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = - sp->autoclose * HZ; + (unsigned long)sp->autoclose * HZ; /* Initilizes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) @@ -512,7 +518,13 @@ void sctp_assoc_set_primary(struct sctp_association *asoc, * to this destination address earlier. The sender MUST set * CYCLING_CHANGEOVER to indicate that this switch is a * double switch to the same destination address. + * + * Really, only bother is we have data queued or outstanding on + * the association. */ + if (!asoc->outqueue.outstanding_bytes && !asoc->outqueue.out_qlen) + return; + if (transport->cacc.changeover_active) transport->cacc.cycling_changeover = changeover; @@ -732,6 +744,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, peer->partial_bytes_acked = 0; peer->flight_size = 0; + peer->burst_limited = 0; /* Set the transport's RTO.initial value */ peer->rto = asoc->rto_initial; @@ -1377,8 +1390,9 @@ static inline int sctp_peer_needs_update(struct sctp_association *asoc) case SCTP_STATE_SHUTDOWN_RECEIVED: case SCTP_STATE_SHUTDOWN_SENT: if ((asoc->rwnd > asoc->a_rwnd) && - ((asoc->rwnd - asoc->a_rwnd) >= - min_t(__u32, (asoc->base.sk->sk_rcvbuf >> 1), asoc->pathmtu))) + ((asoc->rwnd - asoc->a_rwnd) >= max_t(__u32, + (asoc->base.sk->sk_rcvbuf >> sctp_rwnd_upd_shift), + asoc->pathmtu))) return 1; break; default: @@ -1545,7 +1559,12 @@ retry: spin_lock_bh(&sctp_assocs_id_lock); error = idr_get_new_above(&sctp_assocs_id, (void *)asoc, - 1, &assoc_id); + idr_low, &assoc_id); + if (!error) { + idr_low = assoc_id + 1; + if (idr_low == INT_MAX) + idr_low = 1; + } spin_unlock_bh(&sctp_assocs_id_lock); if (error == -EAGAIN) goto retry; diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index acf7c4d128f7..8e4320040f05 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -263,9 +263,18 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, if (0 == i) frag |= SCTP_DATA_FIRST_FRAG; - if ((i == (whole - 1)) && !over) + if ((i == (whole - 1)) && !over) { frag |= SCTP_DATA_LAST_FRAG; + /* The application requests to set the I-bit of the + * last DATA chunk of a user message when providing + * the user message to the SCTP implementation. + */ + if ((sinfo->sinfo_flags & SCTP_EOF) || + (sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY)) + frag |= SCTP_DATA_SACK_IMM; + } + chunk = sctp_make_datafrag_empty(asoc, sinfo, len, frag, 0); if (!chunk) @@ -297,6 +306,10 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, else frag = SCTP_DATA_LAST_FRAG; + if ((sinfo->sinfo_flags & SCTP_EOF) || + (sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY)) + frag |= SCTP_DATA_SACK_IMM; + chunk = sctp_make_datafrag_empty(asoc, sinfo, over, frag, 0); if (!chunk) diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index bb280e60e00a..cc50fbe99291 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -837,15 +837,16 @@ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr) if (type & IPV6_ADDR_LINKLOCAL) { if (!addr->v6.sin6_scope_id) return 0; - dev = dev_get_by_index(&init_net, addr->v6.sin6_scope_id); - if (!dev) - return 0; - if (!ipv6_chk_addr(&init_net, &addr->v6.sin6_addr, + rcu_read_lock(); + dev = dev_get_by_index_rcu(&init_net, + addr->v6.sin6_scope_id); + if (!dev || + !ipv6_chk_addr(&init_net, &addr->v6.sin6_addr, dev, 0)) { - dev_put(dev); + rcu_read_unlock(); return 0; } - dev_put(dev); + rcu_read_unlock(); } else if (type == IPV6_ADDR_MAPPED) { if (!opt->v4mapped) return 0; @@ -873,10 +874,12 @@ static int sctp_inet6_send_verify(struct sctp_sock *opt, union sctp_addr *addr) if (type & IPV6_ADDR_LINKLOCAL) { if (!addr->v6.sin6_scope_id) return 0; - dev = dev_get_by_index(&init_net, addr->v6.sin6_scope_id); + rcu_read_lock(); + dev = dev_get_by_index_rcu(&init_net, + addr->v6.sin6_scope_id); + rcu_read_unlock(); if (!dev) return 0; - dev_put(dev); } af = opt->pf->af; } @@ -930,7 +933,6 @@ static struct inet_protosw sctpv6_seqpacket_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctpv6_prot, .ops = &inet6_seqpacket_ops, - .capability = -1, .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; @@ -939,7 +941,6 @@ static struct inet_protosw sctpv6_stream_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctpv6_prot, .ops = &inet6_seqpacket_ops, - .capability = -1, .no_check = 0, .flags = SCTP_PROTOSW_FLAG, }; diff --git a/net/sctp/output.c b/net/sctp/output.c index 5cbda8f1ddfd..7c5589363433 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -429,23 +429,22 @@ int sctp_packet_transmit(struct sctp_packet *packet) list_del_init(&chunk->list); if (sctp_chunk_is_data(chunk)) { - if (!chunk->has_tsn) { - sctp_chunk_assign_ssn(chunk); - sctp_chunk_assign_tsn(chunk); - - /* 6.3.1 C4) When data is in flight and when allowed - * by rule C5, a new RTT measurement MUST be made each - * round trip. Furthermore, new RTT measurements - * SHOULD be made no more than once per round-trip - * for a given destination transport address. - */ + if (!chunk->resent) { + + /* 6.3.1 C4) When data is in flight and when allowed + * by rule C5, a new RTT measurement MUST be made each + * round trip. Furthermore, new RTT measurements + * SHOULD be made no more than once per round-trip + * for a given destination transport address. + */ if (!tp->rto_pending) { chunk->rtt_in_progress = 1; tp->rto_pending = 1; } - } else - chunk->resent = 1; + } + + chunk->resent = 1; has_data = 1; } @@ -557,8 +556,6 @@ int sctp_packet_transmit(struct sctp_packet *packet) struct timer_list *timer; unsigned long timeout; - tp->last_time_used = jiffies; - /* Restart the AUTOCLOSE timer when sending data. */ if (sctp_state(asoc, ESTABLISHED) && asoc->autoclose) { timer = &asoc->timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE]; @@ -617,7 +614,6 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, sctp_xmit_t retval = SCTP_XMIT_OK; size_t datasize, rwnd, inflight, flight_size; struct sctp_transport *transport = packet->transport; - __u32 max_burst_bytes; struct sctp_association *asoc = transport->asoc; struct sctp_outq *q = &asoc->outqueue; @@ -650,28 +646,6 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, } } - /* sctpimpguide-05 2.14.2 - * D) When the time comes for the sender to - * transmit new DATA chunks, the protocol parameter Max.Burst MUST - * first be applied to limit how many new DATA chunks may be sent. - * The limit is applied by adjusting cwnd as follows: - * if ((flightsize + Max.Burst * MTU) < cwnd) - * cwnd = flightsize + Max.Burst * MTU - */ - max_burst_bytes = asoc->max_burst * asoc->pathmtu; - if ((flight_size + max_burst_bytes) < transport->cwnd) { - transport->cwnd = flight_size + max_burst_bytes; - SCTP_DEBUG_PRINTK("%s: cwnd limited by max_burst: " - "transport: %p, cwnd: %d, " - "ssthresh: %d, flight_size: %d, " - "pba: %d\n", - __func__, transport, - transport->cwnd, - transport->ssthresh, - transport->flight_size, - transport->partial_bytes_acked); - } - /* RFC 2960 6.1 Transmission of DATA Chunks * * B) At any given time, the sender MUST NOT transmit new data @@ -747,6 +721,8 @@ static void sctp_packet_append_data(struct sctp_packet *packet, /* Has been accepted for transmission. */ if (!asoc->peer.prsctp_capable) chunk->msg->can_abandon = 0; + sctp_chunk_assign_tsn(chunk); + sctp_chunk_assign_ssn(chunk); } static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 23e5e97aa617..229690f02a1d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -191,8 +191,8 @@ static inline int sctp_cacc_skip(struct sctp_transport *primary, __u32 tsn) { if (primary->cacc.changeover_active && - (sctp_cacc_skip_3_1(primary, transport, count_of_newacks) - || sctp_cacc_skip_3_2(primary, tsn))) + (sctp_cacc_skip_3_1(primary, transport, count_of_newacks) || + sctp_cacc_skip_3_2(primary, tsn))) return 1; return 0; } @@ -921,6 +921,14 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) goto sctp_flush_out; } + /* Apply Max.Burst limitation to the current transport in + * case it will be used for new data. We are going to + * rest it before we return, but we want to apply the limit + * to the currently queued data. + */ + if (transport) + sctp_transport_burst_limited(transport); + /* Finally, transmit new packets. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { /* RFC 2960 6.5 Every DATA chunk MUST carry a valid @@ -966,6 +974,10 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) packet = &transport->packet; sctp_packet_config(packet, vtag, asoc->peer.ecn_capable); + /* We've switched transports, so apply the + * Burst limit to the new transport. + */ + sctp_transport_burst_limited(transport); } SCTP_DEBUG_PRINTK("sctp_outq_flush(%p, %p[%s]), ", @@ -1001,6 +1013,13 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) break; case SCTP_XMIT_OK: + /* The sender is in the SHUTDOWN-PENDING state, + * The sender MAY set the I-bit in the DATA + * chunk header. + */ + if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) + chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM; + break; default: @@ -1053,6 +1072,9 @@ sctp_flush_out: packet = &t->packet; if (!sctp_packet_empty(packet)) error = sctp_packet_transmit(packet); + + /* Clear the burst limited state, if any */ + sctp_transport_burst_reset(t); } return error; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 612dc878e05c..a3c8988758b1 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -205,14 +205,14 @@ static void sctp_get_local_addr_list(void) struct list_head *pos; struct sctp_af *af; - read_lock(&dev_base_lock); - for_each_netdev(&init_net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { __list_for_each(pos, &sctp_address_families) { af = list_entry(pos, struct sctp_af, list); af->copy_addrlist(&sctp_local_addr_list, dev); } } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } /* Free the existing local addresses. */ @@ -296,19 +296,19 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) { addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; - addr->v4.sin_addr.s_addr = inet_sk(sk)->rcv_saddr; + addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ static void sctp_v4_to_sk_saddr(union sctp_addr *addr, struct sock *sk) { - inet_sk(sk)->rcv_saddr = addr->v4.sin_addr.s_addr; + inet_sk(sk)->inet_rcv_saddr = addr->v4.sin_addr.s_addr; } /* Initialize sk->sk_daddr from sctp_addr. */ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk) { - inet_sk(sk)->daddr = addr->v4.sin_addr.s_addr; + inet_sk(sk)->inet_daddr = addr->v4.sin_addr.s_addr; } /* Initialize a sctp_addr from an address parameter. */ @@ -598,7 +598,7 @@ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, newinet = inet_sk(newsk); - newinet->daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; + newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; sk_refcnt_debug_inc(newsk); @@ -909,7 +909,6 @@ static struct inet_protosw sctp_seqpacket_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, - .capability = -1, .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; @@ -918,7 +917,6 @@ static struct inet_protosw sctp_stream_protosw = { .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, - .capability = -1, .no_check = 0, .flags = SCTP_PROTOSW_FLAG }; @@ -1260,6 +1258,9 @@ SCTP_STATIC __init int sctp_init(void) /* Set SCOPE policy to enabled */ sctp_scope_policy = SCTP_SCOPE_POLICY_ENABLE; + /* Set the default rwnd update threshold */ + sctp_rwnd_upd_shift = SCTP_DEFAULT_RWND_SHIFT; + sctp_sysctl_register(); INIT_LIST_HEAD(&sctp_address_families); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 9d881a61ac02..9e732916b671 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -987,7 +987,10 @@ static void *sctp_addto_param(struct sctp_chunk *chunk, int len, target = skb_put(chunk->skb, len); - memcpy(target, data, len); + if (data) + memcpy(target, data, len); + else + memset(target, 0, len); /* Adjust the chunk length field. */ chunk->chunk_hdr->length = htons(chunklen + len); @@ -1129,16 +1132,18 @@ nodata: struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, - size_t paylen) + size_t paylen, size_t reserve_tail) { struct sctp_chunk *retval; - retval = sctp_make_op_error_space(asoc, chunk, paylen); + retval = sctp_make_op_error_space(asoc, chunk, paylen + reserve_tail); if (!retval) goto nodata; - sctp_init_cause(retval, cause_code, paylen); + sctp_init_cause(retval, cause_code, paylen + reserve_tail); sctp_addto_chunk(retval, paylen, payload); + if (reserve_tail) + sctp_addto_param(retval, reserve_tail, NULL); nodata: return retval; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index efa516b47e81..d771cc1b777a 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -217,8 +217,7 @@ static int sctp_gen_sack(struct sctp_association *asoc, int force, sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_SACK)); } else { - if (asoc->a_rwnd > asoc->rwnd) - asoc->a_rwnd = asoc->rwnd; + asoc->a_rwnd = asoc->rwnd; sack = sctp_make_sack(asoc); if (!sack) goto nomem; @@ -1417,6 +1416,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, asoc->init_last_sent_to = t; chunk->transport = t; t->init_sent_count++; + /* Set the new transport as primary */ + sctp_assoc_set_primary(asoc, t); break; case SCTP_CMD_INIT_RESTART: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index d4df45022ffa..1ef9de9bbae9 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -996,14 +996,15 @@ sctp_disposition_t sctp_sf_sendbeat_8_3(const struct sctp_endpoint *ep, sctp_sf_heartbeat(ep, asoc, type, arg, commands)) return SCTP_DISPOSITION_NOMEM; + /* Set transport error counter and association error counter * when sending heartbeat. */ - sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_IDLE, - SCTP_TRANSPORT(transport)); sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_HB_SENT, SCTP_TRANSPORT(transport)); } + sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_IDLE, + SCTP_TRANSPORT(transport)); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMER_UPDATE, SCTP_TRANSPORT(transport)); @@ -1720,7 +1721,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep, err = sctp_make_op_error(asoc, chunk, SCTP_ERROR_COOKIE_IN_SHUTDOWN, - NULL, 0); + NULL, 0, 0); if (err) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err)); @@ -2868,6 +2869,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(const struct sctp_endpoint *ep, sctp_cmd_seq_t *commands) { struct sctp_chunk *chunk = arg; + sctp_arg_t force = SCTP_NOFORCE(); int error; if (!sctp_vtag_verify(chunk, asoc)) { @@ -2901,6 +2903,9 @@ sctp_disposition_t sctp_sf_eat_data_6_2(const struct sctp_endpoint *ep, BUG(); } + if (chunk->chunk_hdr->flags & SCTP_DATA_SACK_IMM) + force = SCTP_FORCE(); + if (asoc->autoclose) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); @@ -2929,7 +2934,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(const struct sctp_endpoint *ep, * more aggressive than the following algorithms allow. */ if (chunk->end_of_packet) - sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_NOFORCE()); + sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, force); return SCTP_DISPOSITION_CONSUME; @@ -2954,7 +2959,7 @@ discard_force: discard_noforce: if (chunk->end_of_packet) - sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_NOFORCE()); + sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, force); return SCTP_DISPOSITION_DISCARD; consume: @@ -3973,7 +3978,7 @@ sctp_disposition_t sctp_sf_eat_auth(const struct sctp_endpoint *ep, err_chunk = sctp_make_op_error(asoc, chunk, SCTP_ERROR_UNSUP_HMAC, &auth_hdr->hmac_id, - sizeof(__u16)); + sizeof(__u16), 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); @@ -4065,7 +4070,8 @@ sctp_disposition_t sctp_sf_unk_chunk(const struct sctp_endpoint *ep, hdr = unk_chunk->chunk_hdr; err_chunk = sctp_make_op_error(asoc, unk_chunk, SCTP_ERROR_UNKNOWN_CHUNK, hdr, - WORD_ROUND(ntohs(hdr->length))); + WORD_ROUND(ntohs(hdr->length)), + 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); @@ -4084,7 +4090,8 @@ sctp_disposition_t sctp_sf_unk_chunk(const struct sctp_endpoint *ep, hdr = unk_chunk->chunk_hdr; err_chunk = sctp_make_op_error(asoc, unk_chunk, SCTP_ERROR_UNKNOWN_CHUNK, hdr, - WORD_ROUND(ntohs(hdr->length))); + WORD_ROUND(ntohs(hdr->length)), + 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); @@ -6048,7 +6055,8 @@ static int sctp_eat_data(const struct sctp_association *asoc, err = sctp_make_op_error(asoc, chunk, SCTP_ERROR_INV_STRM, &data_hdr->stream, - sizeof(data_hdr->stream)); + sizeof(data_hdr->stream), + sizeof(u16)); if (err) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3a95fcb17a9e..89ab66e54740 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -394,7 +394,7 @@ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) /* 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. @@ -403,7 +403,7 @@ SCTP_STATIC int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) /* 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); } @@ -1117,7 +1117,7 @@ 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; @@ -1968,7 +1968,7 @@ 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); @@ -2086,6 +2086,9 @@ 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 */ + if (sp->autoclose > (MAX_SCHEDULE_TIMEOUT / HZ) ) + sp->autoclose = (__u32)(MAX_SCHEDULE_TIMEOUT / HZ) ; return 0; } @@ -2311,11 +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) { @@ -2354,8 +2356,8 @@ 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 @@ -4349,90 +4351,6 @@ 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) -{ - sctp_assoc_t id; - struct sctp_association *asoc; - struct list_head *pos; - int cnt = 0; - - if (len < sizeof(sctp_assoc_t)) - return -EINVAL; - - if (copy_from_user(&id, optval, sizeof(sctp_assoc_t))) - return -EFAULT; - - printk(KERN_WARNING "SCTP: Use of SCTP_GET_PEER_ADDRS_NUM_OLD " - "socket option deprecated\n"); - /* For UDP-style sockets, id specifies the association to query. */ - asoc = sctp_id2assoc(sk, id); - if (!asoc) - return -EINVAL; - - list_for_each(pos, &asoc->peer.transport_addr_list) { - cnt ++; - } - - return cnt; -} - -/* - * 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; - 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; - - printk(KERN_WARNING "SCTP: Use of SCTP_GET_PEER_ADDRS_OLD " - "socket option deprecated\n"); - - /* 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_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; - 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) @@ -4485,125 +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; - - printk(KERN_WARNING "SCTP: Use of SCTP_GET_LOCAL_ADDRS_NUM_OLD " - "socket option deprecated\n"); - - /* - * 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(sk, &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; - - if ((PF_INET6 == sk->sk_family) && - inet_v6_ipv6only(sk) && - (AF_INET == 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; - 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; - 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) { @@ -4647,112 +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 || - getaddrs.addr_num >= (INT_MAX / sizeof(union sctp_addr))) - return -EINVAL; - - printk(KERN_WARNING "SCTP: Use of SCTP_GET_LOCAL_ADDRS_OLD " - "socket option deprecated\n"); - - /* - * 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(sk, &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) @@ -5603,22 +5296,6 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, 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); @@ -5861,7 +5538,7 @@ 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; } @@ -5933,7 +5610,7 @@ SCTP_STATIC int sctp_listen_start(struct sock *sk, int backlog) if (sctp_autobind(sk)) return -EAGAIN; } else { - if (sctp_get_port(sk, inet_sk(sk)->num)) { + if (sctp_get_port(sk, inet_sk(sk)->inet_num)) { sk->sk_state = SCTP_SS_CLOSED; return -EADDRINUSE; } @@ -6104,14 +5781,14 @@ 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); } @@ -6138,7 +5815,7 @@ 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); @@ -6707,12 +6384,12 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, /* Initialize sk's sport, dport, rcv_saddr and daddr for * getsockname() and getpeername() */ - newinet->sport = inet->sport; - newinet->saddr = inet->saddr; - newinet->rcv_saddr = inet->rcv_saddr; - newinet->dport = htons(asoc->peer.port); + 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->id = asoc->next_tsn ^ jiffies; + newinet->inet_id = asoc->next_tsn ^ jiffies; newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; @@ -6751,13 +6428,13 @@ 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)->num)]; + 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(); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index d50a042f9552..419e1e962c55 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -52,6 +52,7 @@ static int int_max = INT_MAX; static int sack_timer_min = 1; static int sack_timer_max = 500; static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */ +static int rwnd_scale_max = 16; extern int sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; @@ -241,7 +242,18 @@ static ctl_table sctp_table[] = { .extra1 = &zero, .extra2 = &addr_scope_max, }, - { } + { + .procname = "rwnd_update_shift", + .data = &sctp_rwnd_upd_shift, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &rwnd_scale_max, + }, + + { /* sentinel */ } }; static struct ctl_path sctp_path[] = { diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 37a1184d789f..b827d21dbe54 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -83,7 +83,6 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, peer->fast_recovery = 0; peer->last_time_heard = jiffies; - peer->last_time_used = jiffies; peer->last_time_ecne_reduced = jiffies; peer->init_sent_count = 0; @@ -564,10 +563,8 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, * to be done every RTO interval, we do it every hearbeat * interval. */ - if (time_after(jiffies, transport->last_time_used + - transport->rto)) - transport->cwnd = max(transport->cwnd/2, - 4*transport->asoc->pathmtu); + transport->cwnd = max(transport->cwnd/2, + 4*transport->asoc->pathmtu); break; } @@ -578,6 +575,43 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, transport->cwnd, transport->ssthresh); } +/* Apply Max.Burst limit to the congestion window: + * sctpimpguide-05 2.14.2 + * D) When the time comes for the sender to + * transmit new DATA chunks, the protocol parameter Max.Burst MUST + * first be applied to limit how many new DATA chunks may be sent. + * The limit is applied by adjusting cwnd as follows: + * if ((flightsize+ Max.Burst * MTU) < cwnd) + * cwnd = flightsize + Max.Burst * MTU + */ + +void sctp_transport_burst_limited(struct sctp_transport *t) +{ + struct sctp_association *asoc = t->asoc; + u32 old_cwnd = t->cwnd; + u32 max_burst_bytes; + + if (t->burst_limited) + return; + + max_burst_bytes = t->flight_size + (asoc->max_burst * asoc->pathmtu); + if (max_burst_bytes < old_cwnd) { + t->cwnd = max_burst_bytes; + t->burst_limited = old_cwnd; + } +} + +/* Restore the old cwnd congestion window, after the burst had it's + * desired effect. + */ +void sctp_transport_burst_reset(struct sctp_transport *t) +{ + if (t->burst_limited) { + t->cwnd = t->burst_limited; + t->burst_limited = 0; + } +} + /* What is the next timeout value for this transport? */ unsigned long sctp_transport_timeout(struct sctp_transport *t) { @@ -600,6 +634,7 @@ void sctp_transport_reset(struct sctp_transport *t) * (see Section 6.2.1) */ t->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); + t->burst_limited = 0; t->ssthresh = asoc->peer.i.a_rwnd; t->rto = asoc->rto_initial; t->rtt = 0; |