#include <linux/list.h> /* For struct list_head */
#include <linux/socket.h>
#include <linux/ip.h>
+#include <linux/slab.h>
#include <net/sock.h> /* For skb_set_owner_w */
#include <net/sctp/sctp.h>
static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn);
+static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout);
+
/* Add data to the front of the queue. */
static inline void sctp_outq_head_data(struct sctp_outq *q,
struct sctp_chunk *ch)
__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;
}
INIT_LIST_HEAD(&q->sacked);
INIT_LIST_HEAD(&q->abandoned);
+ q->fast_rtx = 0;
q->outstanding_bytes = 0;
q->empty = 1;
q->cork = 0;
* not be retransmitted
*/
if (!chunk->tsn_gap_acked) {
- chunk->transport->flight_size -=
- sctp_data_size(chunk);
+ if (chunk->transport)
+ chunk->transport->flight_size -=
+ sctp_data_size(chunk);
q->outstanding_bytes -= sctp_data_size(chunk);
q->asoc->peer.rwnd += (sctp_data_size(chunk) +
sizeof(struct sk_buff));
* be added to the retransmit queue.
*/
if ((reason == SCTP_RTXR_FAST_RTX &&
- (chunk->fast_retransmit > 0)) ||
+ (chunk->fast_retransmit == SCTP_NEED_FRTX)) ||
(reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) {
- /* If this chunk was sent less then 1 rto ago, do not
- * retransmit this chunk, but give the peer time
- * to acknowlege it. Do this only when
- * retransmitting due to T3 timeout.
- */
- if (reason == SCTP_RTXR_T3_RTX &&
- (jiffies - chunk->sent_at) < transport->last_rto)
- continue;
-
/* RFC 2960 6.2.1 Processing a Received SACK
*
* C) Any time a DATA chunk is marked for
q->asoc->peer.rwnd += (sctp_data_size(chunk) +
sizeof(struct sk_buff));
q->outstanding_bytes -= sctp_data_size(chunk);
- transport->flight_size -= sctp_data_size(chunk);
+ if (chunk->transport)
+ transport->flight_size -= sctp_data_size(chunk);
/* sctpimpguide-05 Section 2.8.2
* M5) If a T3-rtx timer expires, the
case SCTP_RTXR_FAST_RTX:
SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS);
sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX);
+ q->fast_rtx = 1;
break;
case SCTP_RTXR_PMTUD:
SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS);
* the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by
* following the procedures outlined in C1 - C5.
*/
- sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point);
+ if (reason == SCTP_RTXR_T3_RTX)
+ sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point);
- error = sctp_outq_flush(q, /* rtx_timeout */ 1);
+ /* Flush the queues only on timeout, since fast_rtx is only
+ * triggered during sack processing and the queue
+ * will be flushed at the end.
+ */
+ if (reason != SCTP_RTXR_FAST_RTX)
+ error = sctp_outq_flush(q, /* rtx_timeout */ 1);
if (error)
q->asoc->base.sk->sk_err = -error;
int rtx_timeout, int *start_timer)
{
struct list_head *lqueue;
- struct list_head *lchunk;
struct sctp_transport *transport = pkt->transport;
sctp_xmit_t status;
struct sctp_chunk *chunk, *chunk1;
struct sctp_association *asoc;
+ int fast_rtx;
int error = 0;
+ int timer = 0;
+ int done = 0;
asoc = q->asoc;
lqueue = &q->retransmit;
+ fast_rtx = q->fast_rtx;
- /* RFC 2960 6.3.3 Handle T3-rtx Expiration
+ /* This loop handles time-out retransmissions, fast retransmissions,
+ * and retransmissions due to opening of whindow.
+ *
+ * RFC 2960 6.3.3 Handle T3-rtx Expiration
*
* E3) Determine how many of the earliest (i.e., lowest TSN)
* outstanding DATA chunks for the address for which the
* [Just to be painfully clear, if we are retransmitting
* because a timeout just happened, we should send only ONE
* packet of retransmitted data.]
+ *
+ * For fast retransmissions we also send only ONE packet. However,
+ * if we are just flushing the queue due to open window, we'll
+ * try to send as much as possible.
*/
- lchunk = sctp_list_dequeue(lqueue);
-
- while (lchunk) {
- chunk = list_entry(lchunk, struct sctp_chunk,
- transmitted_list);
+ list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) {
/* Make sure that Gap Acked TSNs are not retransmitted. A
* simple approach is just to move such TSNs out of the
* next chunk.
*/
if (chunk->tsn_gap_acked) {
- list_add_tail(lchunk, &transport->transmitted);
- lchunk = sctp_list_dequeue(lqueue);
+ list_del(&chunk->transmitted_list);
+ list_add_tail(&chunk->transmitted_list,
+ &transport->transmitted);
continue;
}
+ /* If we are doing fast retransmit, ignore non-fast_rtransmit
+ * chunks
+ */
+ if (fast_rtx && !chunk->fast_retransmit)
+ continue;
+
/* Attempt to append this chunk to the packet. */
status = sctp_packet_append_chunk(pkt, chunk);
switch (status) {
case SCTP_XMIT_PMTU_FULL:
/* Send this packet. */
- if ((error = sctp_packet_transmit(pkt)) == 0)
- *start_timer = 1;
+ error = sctp_packet_transmit(pkt);
/* If we are retransmitting, we should only
* send a single packet.
*/
- if (rtx_timeout) {
- list_add(lchunk, lqueue);
- lchunk = NULL;
- }
+ if (rtx_timeout || fast_rtx)
+ done = 1;
- /* Bundle lchunk in the next round. */
+ /* Bundle next chunk in the next round. */
break;
case SCTP_XMIT_RWND_FULL:
/* Send this packet. */
- if ((error = sctp_packet_transmit(pkt)) == 0)
- *start_timer = 1;
+ error = sctp_packet_transmit(pkt);
/* Stop sending DATA as there is no more room
* at the receiver.
*/
- list_add(lchunk, lqueue);
- lchunk = NULL;
+ done = 1;
break;
case SCTP_XMIT_NAGLE_DELAY:
/* Send this packet. */
- if ((error = sctp_packet_transmit(pkt)) == 0)
- *start_timer = 1;
+ error = sctp_packet_transmit(pkt);
/* Stop sending DATA because of nagle delay. */
- list_add(lchunk, lqueue);
- lchunk = NULL;
+ done = 1;
break;
default:
/* The append was successful, so add this chunk to
* the transmitted list.
*/
- list_add_tail(lchunk, &transport->transmitted);
+ list_del(&chunk->transmitted_list);
+ list_add_tail(&chunk->transmitted_list,
+ &transport->transmitted);
/* Mark the chunk as ineligible for fast retransmit
* after it is retransmitted.
*/
- if (chunk->fast_retransmit > 0)
- chunk->fast_retransmit = -1;
+ if (chunk->fast_retransmit == SCTP_NEED_FRTX)
+ chunk->fast_retransmit = SCTP_DONT_FRTX;
- *start_timer = 1;
- q->empty = 0;
+ /* Force start T3-rtx timer when fast retransmitting
+ * the earliest outstanding TSN
+ */
+ if (!timer && fast_rtx &&
+ ntohl(chunk->subh.data_hdr->tsn) ==
+ asoc->ctsn_ack_point + 1)
+ timer = 2;
- /* Retrieve a new chunk to bundle. */
- lchunk = sctp_list_dequeue(lqueue);
+ q->empty = 0;
break;
}
- /* If we are here due to a retransmit timeout or a fast
- * retransmit and if there are any chunks left in the retransmit
- * queue that could not fit in the PMTU sized packet, they need
- * to be marked as ineligible for a subsequent fast retransmit.
- */
- if (rtx_timeout && !lchunk) {
- list_for_each_entry(chunk1, lqueue, transmitted_list) {
- if (chunk1->fast_retransmit > 0)
- chunk1->fast_retransmit = -1;
- }
+ /* Set the timer if there were no errors */
+ if (!error && !timer)
+ timer = 1;
+
+ if (done)
+ break;
+ }
+
+ /* If we are here due to a retransmit timeout or a fast
+ * retransmit and if there are any chunks left in the retransmit
+ * queue that could not fit in the PMTU sized packet, they need
+ * to be marked as ineligible for a subsequent fast retransmit.
+ */
+ if (rtx_timeout || fast_rtx) {
+ list_for_each_entry(chunk1, lqueue, transmitted_list) {
+ if (chunk1->fast_retransmit == SCTP_NEED_FRTX)
+ chunk1->fast_retransmit = SCTP_DONT_FRTX;
}
}
+ *start_timer = timer;
+
+ /* Clear fast retransmit hint */
+ if (fast_rtx)
+ q->fast_rtx = 0;
+
return error;
}
return error;
}
+
/*
* Try to flush an outqueue.
*
* locking concerns must be made. Today we use the sock lock to protect
* this function.
*/
-int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
+static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
{
struct sctp_packet *packet;
struct sctp_packet singleton;
sctp_xmit_t status;
int error = 0;
int start_timer = 0;
+ int one_packet = 0;
/* These transports have chunks to send. */
struct list_head transport_list;
if (sctp_test_T_bit(chunk)) {
packet->vtag = asoc->c.my_vtag;
}
- case SCTP_CID_SACK:
- case SCTP_CID_HEARTBEAT:
+ /* The following chunks are "response" chunks, i.e.
+ * they are generated in response to something we
+ * received. If we are sending these, then we can
+ * send only 1 packet containing these chunks.
+ */
case SCTP_CID_HEARTBEAT_ACK:
- case SCTP_CID_SHUTDOWN:
case SCTP_CID_SHUTDOWN_ACK:
- case SCTP_CID_ERROR:
- case SCTP_CID_COOKIE_ECHO:
case SCTP_CID_COOKIE_ACK:
- case SCTP_CID_ECN_ECNE:
+ case SCTP_CID_COOKIE_ECHO:
+ case SCTP_CID_ERROR:
case SCTP_CID_ECN_CWR:
- case SCTP_CID_ASCONF:
case SCTP_CID_ASCONF_ACK:
+ one_packet = 1;
+ /* Fall throught */
+
+ case SCTP_CID_SACK:
+ case SCTP_CID_HEARTBEAT:
+ case SCTP_CID_SHUTDOWN:
+ case SCTP_CID_ECN_ECNE:
+ case SCTP_CID_ASCONF:
case SCTP_CID_FWD_TSN:
- sctp_packet_transmit_chunk(packet, chunk);
+ status = sctp_packet_transmit_chunk(packet, chunk,
+ one_packet);
+ if (status != SCTP_XMIT_OK) {
+ /* put the chunk back */
+ list_add(&chunk->list, &q->control_chunk_list);
+ }
break;
default:
rtx_timeout, &start_timer);
if (start_timer)
- sctp_transport_reset_timers(transport);
+ sctp_transport_reset_timers(transport,
+ start_timer-1);
/* This can happen on COOKIE-ECHO resend. Only
* one chunk can get bundled with a COOKIE-ECHO.
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. */
- start_timer = 0;
while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
/* RFC 2960 6.5 Every DATA chunk MUST carry a valid
* stream identifier.
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]), ",
atomic_read(&chunk->skb->users) : -1);
/* Add the chunk to the packet. */
- status = sctp_packet_transmit_chunk(packet, chunk);
+ status = sctp_packet_transmit_chunk(packet, chunk, 0);
switch (status) {
case SCTP_XMIT_PMTU_FULL:
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:
list_add_tail(&chunk->transmitted_list,
&transport->transmitted);
- sctp_transport_reset_timers(transport);
+ sctp_transport_reset_timers(transport, 0);
q->empty = 0;
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;
unsigned outstanding;
struct sctp_transport *primary = asoc->peer.primary_path;
int count_of_newacks = 0;
+ int gap_ack_blocks;
/* Grab the association's destination address list. */
transport_list = &asoc->peer.transport_addr_list;
sack_ctsn = ntohl(sack->cum_tsn_ack);
-
+ gap_ack_blocks = ntohs(sack->num_gap_ack_blocks);
/*
* SFR-CACC algorithm:
* On receipt of a SACK the sender SHOULD execute the
* on the current primary, the CHANGEOVER_ACTIVE flag SHOULD be
* cleared. The CYCLING_CHANGEOVER flag SHOULD also be cleared for
* all destinations.
- */
- if (TSN_lte(primary->cacc.next_tsn_at_change, sack_ctsn)) {
- primary->cacc.changeover_active = 0;
- list_for_each_entry(transport, transport_list,
- transports) {
- transport->cacc.cycling_changeover = 0;
- }
- }
-
- /*
- * SFR-CACC algorithm:
* 2) If the SACK contains gap acks and the flag CHANGEOVER_ACTIVE
* is set the receiver of the SACK MUST take the following actions:
*
* A) Initialize the cacc_saw_newack to 0 for all destination
* addresses.
+ *
+ * Only bother if changeover_active is set. Otherwise, this is
+ * totally suboptimal to do on every SACK.
*/
- if (sack->num_gap_ack_blocks &&
- primary->cacc.changeover_active) {
- list_for_each_entry(transport, transport_list, transports) {
- transport->cacc.cacc_saw_newack = 0;
+ if (primary->cacc.changeover_active) {
+ u8 clear_cycling = 0;
+
+ if (TSN_lte(primary->cacc.next_tsn_at_change, sack_ctsn)) {
+ primary->cacc.changeover_active = 0;
+ clear_cycling = 1;
+ }
+
+ if (clear_cycling || gap_ack_blocks) {
+ list_for_each_entry(transport, transport_list,
+ transports) {
+ if (clear_cycling)
+ transport->cacc.cycling_changeover = 0;
+ if (gap_ack_blocks)
+ transport->cacc.cacc_saw_newack = 0;
+ }
}
}
/* Get the highest TSN in the sack. */
highest_tsn = sack_ctsn;
- if (sack->num_gap_ack_blocks)
- highest_tsn +=
- ntohs(frags[ntohs(sack->num_gap_ack_blocks) - 1].gab.end);
+ if (gap_ack_blocks)
+ highest_tsn += ntohs(frags[gap_ack_blocks - 1].gab.end);
if (TSN_lt(asoc->highest_sacked, highest_tsn)) {
highest_new_tsn = highest_tsn;
highest_new_tsn = sctp_highest_new_tsn(sack, asoc);
}
+
/* Run through the retransmit queue. Credit bytes received
* and free those chunks that we can.
*/
sctp_check_transmitted(q, &q->retransmit, NULL, sack, highest_new_tsn);
- sctp_mark_missing(q, &q->retransmit, NULL, highest_new_tsn, 0);
/* Run through the transmitted queue.
* Credit bytes received and free those chunks which we can.
count_of_newacks ++;
}
- list_for_each_entry(transport, transport_list, transports) {
- sctp_mark_missing(q, &transport->transmitted, transport,
- highest_new_tsn, count_of_newacks);
+ if (gap_ack_blocks) {
+ list_for_each_entry(transport, transport_list, transports)
+ sctp_mark_missing(q, &transport->transmitted, transport,
+ highest_new_tsn, count_of_newacks);
}
/* Move the Cumulative TSN Ack Point if appropriate. */
* Make sure the empty queue handler will get run later.
*/
q->empty = (list_empty(&q->out_chunk_list) &&
- list_empty(&q->control_chunk_list) &&
list_empty(&q->retransmit));
if (!q->empty)
goto finish;
__u32 rtt;
__u8 restart_timer = 0;
int bytes_acked = 0;
+ int migrate_bytes = 0;
/* These state variables are for coherent debug output. --xguo */
* considering it as 'outstanding'.
*/
if (!tchunk->tsn_gap_acked) {
- tchunk->transport->flight_size -=
- sctp_data_size(tchunk);
+ if (tchunk->transport)
+ tchunk->transport->flight_size -=
+ sctp_data_size(tchunk);
q->outstanding_bytes -= sctp_data_size(tchunk);
}
continue;
rtt);
}
}
+
+ /* If the chunk hasn't been marked as ACKED,
+ * mark it and account bytes_acked if the
+ * chunk had a valid transport (it will not
+ * have a transport if ASCONF had deleted it
+ * while DATA was outstanding).
+ */
+ if (!tchunk->tsn_gap_acked) {
+ tchunk->tsn_gap_acked = 1;
+ bytes_acked += sctp_data_size(tchunk);
+ if (!tchunk->transport)
+ migrate_bytes += sctp_data_size(tchunk);
+ }
+
if (TSN_lte(tsn, sack_ctsn)) {
/* RFC 2960 6.3.2 Retransmission Timer Rules
*
restart_timer = 1;
if (!tchunk->tsn_gap_acked) {
- tchunk->tsn_gap_acked = 1;
- bytes_acked += sctp_data_size(tchunk);
/*
* SFR-CACC algorithm:
* 2) If the SACK contains gap acks
* older than that newly acknowledged DATA
* chunk, are qualified as 'Stray DATA chunks'.
*/
- if (!tchunk->tsn_gap_acked) {
- tchunk->tsn_gap_acked = 1;
- bytes_acked += sctp_data_size(tchunk);
- }
list_add_tail(lchunk, &tlist);
}
tsn);
tchunk->tsn_gap_acked = 0;
- bytes_acked -= sctp_data_size(tchunk);
+ if (tchunk->transport)
+ bytes_acked -= sctp_data_size(tchunk);
/* RFC 2960 6.3.2 Retransmission Timer Rules
*
#endif /* SCTP_DEBUG */
if (transport) {
if (bytes_acked) {
+ /* We may have counted DATA that was migrated
+ * to this transport due to DEL-IP operation.
+ * Subtract those bytes, since the were never
+ * send on this transport and shouldn't be
+ * credited to this transport.
+ */
+ bytes_acked -= migrate_bytes;
+
/* 8.2. When an outstanding TSN is acknowledged,
* the endpoint shall clear the error counter of
* the destination transport address to which the
bytes_acked);
transport->flight_size -= bytes_acked;
- q->outstanding_bytes -= bytes_acked;
+ if (transport->flight_size == 0)
+ transport->partial_bytes_acked = 0;
+ q->outstanding_bytes -= bytes_acked + migrate_bytes;
} else {
/* RFC 2960 6.1, sctpimpguide-06 2.15.2
* When a sender is doing zero window probing, it
* chunk if it has NOT been fast retransmitted or marked for
* fast retransmit already.
*/
- if (!chunk->fast_retransmit &&
+ if (chunk->fast_retransmit == SCTP_CAN_FRTX &&
!chunk->tsn_gap_acked &&
TSN_lt(tsn, highest_new_tsn_in_sack)) {
*/
if (chunk->tsn_missing_report >= 3) {
- chunk->fast_retransmit = 1;
+ chunk->fast_retransmit = SCTP_NEED_FRTX;
do_fast_retransmit = 1;
}
}
struct sctp_chunk *chunk;
struct list_head *lchunk, *temp;
+ if (!asoc->peer.prsctp_capable)
+ return;
+
/* PR-SCTP C1) Let SackCumAck be the Cumulative TSN ACK carried in the
* received SACK.
*