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
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 7eed77a..df5abbf 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 @@
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 @@
* 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 @@
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 @@
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 @@
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 acf7c4d..8e4320040 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -263,9 +263,18 @@
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 @@
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 bb280e6..cc50fbe 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -837,15 +837,16 @@
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 @@
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 @@
.protocol = IPPROTO_SCTP,
.prot = &sctpv6_prot,
.ops = &inet6_seqpacket_ops,
- .capability = -1,
.no_check = 0,
.flags = SCTP_PROTOSW_FLAG
};
@@ -939,7 +941,6 @@
.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 5cbda8f..7c55893 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -429,23 +429,22 @@
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);
+ 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.
- */
+ /* 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 @@
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 @@
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 @@
}
}
- /* 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 @@
/* 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 23e5e97..229690f 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -191,8 +191,8 @@
__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 @@
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 @@
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 @@
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 @@
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 612dc87..a3c8988 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -205,14 +205,14 @@
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 @@
{
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 @@
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 @@
.protocol = IPPROTO_SCTP,
.prot = &sctp_prot,
.ops = &inet_seqpacket_ops,
- .capability = -1,
.no_check = 0,
.flags = SCTP_PROTOSW_FLAG
};
@@ -918,7 +917,6 @@
.protocol = IPPROTO_SCTP,
.prot = &sctp_prot,
.ops = &inet_seqpacket_ops,
- .capability = -1,
.no_check = 0,
.flags = SCTP_PROTOSW_FLAG
};
@@ -1260,6 +1258,9 @@
/* 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 9d881a6..9e73291 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -987,7 +987,10 @@
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 @@
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 efa516b..d771cc1 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -217,8 +217,7 @@
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 @@
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 d4df450..1ef9de9 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -996,14 +996,15 @@
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 @@
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_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 @@
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 @@
* 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_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 @@
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 @@
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 @@
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 @@
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 3a95fcb..89ab66e 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -394,7 +394,7 @@
/* 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 @@
/* 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 @@
}
/* 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 @@
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 @@
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 @@
}
}
- /* 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 @@
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 @@
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 @@
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 @@
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 @@
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 @@
*/
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 @@
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 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 @@
/* 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 @@
/* 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 @@
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 d50a042..419e1e9 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -52,6 +52,7 @@
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 @@
.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 37a1184d..b827d21 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -83,7 +83,6 @@
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 @@
* 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 @@
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 @@
* (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;