#include "ccid.h"
#include "dccp.h"
+/* rate-limit for syncs in reply to sequence-invalid packets; RFC 4340, 7.5.4 */
+int sysctl_dccp_sync_ratelimit __read_mostly = HZ / 8;
+
static void dccp_fin(struct sock *sk, struct sk_buff *skb)
{
sk->sk_shutdown |= RCV_SHUTDOWN;
dccp_send_close(sk, 0);
}
+static u8 dccp_reset_code_convert(const u8 code)
+{
+ const u8 error_code[] = {
+ [DCCP_RESET_CODE_CLOSED] = 0, /* normal termination */
+ [DCCP_RESET_CODE_UNSPECIFIED] = 0, /* nothing known */
+ [DCCP_RESET_CODE_ABORTED] = ECONNRESET,
+
+ [DCCP_RESET_CODE_NO_CONNECTION] = ECONNREFUSED,
+ [DCCP_RESET_CODE_CONNECTION_REFUSED] = ECONNREFUSED,
+ [DCCP_RESET_CODE_TOO_BUSY] = EUSERS,
+ [DCCP_RESET_CODE_AGGRESSION_PENALTY] = EDQUOT,
+
+ [DCCP_RESET_CODE_PACKET_ERROR] = ENOMSG,
+ [DCCP_RESET_CODE_BAD_INIT_COOKIE] = EBADR,
+ [DCCP_RESET_CODE_BAD_SERVICE_CODE] = EBADRQC,
+ [DCCP_RESET_CODE_OPTION_ERROR] = EILSEQ,
+ [DCCP_RESET_CODE_MANDATORY_ERROR] = EOPNOTSUPP,
+ };
+
+ return code >= DCCP_MAX_RESET_CODES ? 0 : error_code[code];
+}
+
+static void dccp_rcv_reset(struct sock *sk, struct sk_buff *skb)
+{
+ u8 err = dccp_reset_code_convert(dccp_hdr_reset(skb)->dccph_reset_code);
+
+ sk->sk_err = err;
+
+ /* Queue the equivalent of TCP fin so that dccp_recvmsg exits the loop */
+ dccp_fin(sk, skb);
+
+ if (err && !sock_flag(sk, SOCK_DEAD))
+ sk_wake_async(sk, 0, POLL_ERR);
+ dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
+}
+
static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
DCCP_SKB_CB(skb)->dccpd_ack_seq);
}
+static void dccp_deliver_input_to_ccids(struct sock *sk, struct sk_buff *skb)
+{
+ const struct dccp_sock *dp = dccp_sk(sk);
+
+ /* Don't deliver to RX CCID when node has shut down read end. */
+ if (!(sk->sk_shutdown & RCV_SHUTDOWN))
+ ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
+ /*
+ * Until the TX queue has been drained, we can not honour SHUT_WR, since
+ * we need received feedback as input to adjust congestion control.
+ */
+ if (sk->sk_write_queue.qlen > 0 || !(sk->sk_shutdown & SEND_SHUTDOWN))
+ ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);
+}
+
static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
{
const struct dccp_hdr *dh = dccp_hdr(skb);
struct dccp_sock *dp = dccp_sk(sk);
- u64 lswl, lawl;
+ u64 lswl, lawl, seqno = DCCP_SKB_CB(skb)->dccpd_seq,
+ ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
/*
* Step 5: Prepare sequence numbers for Sync
*/
if (dh->dccph_type == DCCP_PKT_SYNC ||
dh->dccph_type == DCCP_PKT_SYNCACK) {
- if (between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
- dp->dccps_awl, dp->dccps_awh) &&
- dccp_delta_seqno(dp->dccps_swl,
- DCCP_SKB_CB(skb)->dccpd_seq) >= 0)
- dccp_update_gsr(sk, DCCP_SKB_CB(skb)->dccpd_seq);
+ if (between48(ackno, dp->dccps_awl, dp->dccps_awh) &&
+ dccp_delta_seqno(dp->dccps_swl, seqno) >= 0)
+ dccp_update_gsr(sk, seqno);
else
return -1;
}
* Update S.GSR, S.SWL, S.SWH
* If P.type != Sync,
* Update S.GAR
- * Otherwise,
- * Send Sync packet acknowledging P.seqno
- * Drop packet and return
*/
lswl = dp->dccps_swl;
lawl = dp->dccps_awl;
if (dh->dccph_type == DCCP_PKT_CLOSEREQ ||
dh->dccph_type == DCCP_PKT_CLOSE ||
dh->dccph_type == DCCP_PKT_RESET) {
- lswl = dp->dccps_gsr;
- dccp_inc_seqno(&lswl);
+ lswl = ADD48(dp->dccps_gsr, 1);
lawl = dp->dccps_gar;
}
- if (between48(DCCP_SKB_CB(skb)->dccpd_seq, lswl, dp->dccps_swh) &&
- (DCCP_SKB_CB(skb)->dccpd_ack_seq == DCCP_PKT_WITHOUT_ACK_SEQ ||
- between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
- lawl, dp->dccps_awh))) {
- dccp_update_gsr(sk, DCCP_SKB_CB(skb)->dccpd_seq);
+ if (between48(seqno, lswl, dp->dccps_swh) &&
+ (ackno == DCCP_PKT_WITHOUT_ACK_SEQ ||
+ between48(ackno, lawl, dp->dccps_awh))) {
+ dccp_update_gsr(sk, seqno);
if (dh->dccph_type != DCCP_PKT_SYNC &&
- (DCCP_SKB_CB(skb)->dccpd_ack_seq !=
- DCCP_PKT_WITHOUT_ACK_SEQ))
- dp->dccps_gar = DCCP_SKB_CB(skb)->dccpd_ack_seq;
+ (ackno != DCCP_PKT_WITHOUT_ACK_SEQ))
+ dp->dccps_gar = ackno;
} else {
+ unsigned long now = jiffies;
+ /*
+ * Step 6: Check sequence numbers
+ * Otherwise,
+ * If P.type == Reset,
+ * Send Sync packet acknowledging S.GSR
+ * Otherwise,
+ * Send Sync packet acknowledging P.seqno
+ * Drop packet and return
+ *
+ * These Syncs are rate-limited as per RFC 4340, 7.5.4:
+ * at most 1 / (dccp_sync_rate_limit * HZ) Syncs per second.
+ */
+ if (time_before(now, (dp->dccps_rate_last +
+ sysctl_dccp_sync_ratelimit)))
+ return 0;
+
DCCP_WARN("DCCP: Step 6 failed for %s packet, "
"(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and "
"(P.ackno %s or LAWL(%llu) <= P.ackno(%llu) <= S.AWH(%llu), "
"sending SYNC...\n", dccp_packet_name(dh->dccph_type),
- (unsigned long long) lswl,
- (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq,
+ (unsigned long long) lswl, (unsigned long long) seqno,
(unsigned long long) dp->dccps_swh,
- (DCCP_SKB_CB(skb)->dccpd_ack_seq ==
- DCCP_PKT_WITHOUT_ACK_SEQ) ? "doesn't exist" : "exists",
- (unsigned long long) lawl,
- (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq,
+ (ackno == DCCP_PKT_WITHOUT_ACK_SEQ) ? "doesn't exist"
+ : "exists",
+ (unsigned long long) lawl, (unsigned long long) ackno,
(unsigned long long) dp->dccps_awh);
- dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_PKT_SYNC);
+
+ dp->dccps_rate_last = now;
+
+ if (dh->dccph_type == DCCP_PKT_RESET)
+ seqno = dp->dccps_gsr;
+ dccp_send_sync(sk, seqno, DCCP_PKT_SYNC);
return -1;
}
case DCCP_PKT_DATAACK:
case DCCP_PKT_DATA:
/*
- * FIXME: check if sk_receive_queue is full, schedule DATA_DROPPED
- * option if it is.
+ * FIXME: schedule DATA_DROPPED (RFC 4340, 11.7.2) if and when
+ * - sk_shutdown == RCV_SHUTDOWN, use Code 1, "Not Listening"
+ * - sk_receive_queue is full, use Code 2, "Receive Buffer"
*/
__skb_pull(skb, dh->dccph_doff * 4);
__skb_queue_tail(&sk->sk_receive_queue, skb);
* S.state := TIMEWAIT
* Set TIMEWAIT timer
* Drop packet and return
- */
- dccp_fin(sk, skb);
- dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
+ */
+ dccp_rcv_reset(sk, skb);
return 0;
case DCCP_PKT_CLOSEREQ:
dccp_rcv_closereq(sk, skb);
DCCP_SKB_CB(skb)->dccpd_seq,
DCCP_ACKVEC_STATE_RECEIVED))
goto discard;
-
- ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
- ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);
+ dccp_deliver_input_to_ccids(sk, skb);
return __dccp_rcv_established(sk, skb, dh, len);
discard:
if (dh->dccph_type == DCCP_PKT_RESPONSE) {
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
+ long tstamp = dccp_timestamp();
/* Stop the REQUEST timer */
inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
if (dccp_parse_options(sk, skb))
goto out_invalid_packet;
- /* Obtain RTT sample from SYN exchange (used by CCID 3) */
- if (dp->dccps_options_received.dccpor_timestamp_echo) {
- struct timeval now;
-
- dccp_timestamp(sk, &now);
- dp->dccps_syn_rtt = dccp_sample_rtt(sk, &now, NULL);
- }
+ /* Obtain usec RTT sample from SYN exchange (used by CCID 3) */
+ if (likely(dp->dccps_options_received.dccpor_timestamp_echo))
+ dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * (tstamp -
+ dp->dccps_options_received.dccpor_timestamp_echo));
if (dccp_msk(sk)->dccpms_send_ack_vector &&
dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk,
DCCP_ACKVEC_STATE_RECEIVED))
goto discard;
- ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb);
- ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb);
+ dccp_deliver_input_to_ccids(sk, skb);
}
/*
* Drop packet and return
*/
if (dh->dccph_type == DCCP_PKT_RESET) {
- /*
- * Queue the equivalent of TCP fin so that dccp_recvmsg
- * exits the loop
- */
- dccp_fin(sk, skb);
- dccp_time_wait(sk, DCCP_TIME_WAIT, 0);
+ dccp_rcv_reset(sk, skb);
return 0;
/*
* Step 7: Check for unexpected packet types
return 0;
}
- if (unlikely(dh->dccph_type == DCCP_PKT_SYNC)) {
- dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNCACK);
- goto discard;
- }
-
switch (sk->sk_state) {
case DCCP_CLOSED:
dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION;
sk_wake_async(sk, 0, POLL_OUT);
break;
}
+ } else if (unlikely(dh->dccph_type == DCCP_PKT_SYNC)) {
+ dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNCACK);
+ goto discard;
}
if (!queued) {
EXPORT_SYMBOL_GPL(dccp_rcv_state_process);
/**
- * dccp_sample_rtt - Sample RTT from packet exchange
- *
- * @sk: connected dccp_sock
- * @t_recv: receive timestamp of packet with timestamp echo
- * @t_hist: packet history timestamp or NULL
+ * dccp_sample_rtt - Validate and finalise computation of RTT sample
+ * @delta: number of microseconds between packet and acknowledgment
+ * The routine is kept generic to work in different contexts. It should be
+ * called immediately when the ACK used for the RTT sample arrives.
*/
-u32 dccp_sample_rtt(struct sock *sk, struct timeval *t_recv,
- struct timeval *t_hist)
+u32 dccp_sample_rtt(struct sock *sk, long delta)
{
- struct dccp_sock *dp = dccp_sk(sk);
- struct dccp_options_received *or = &dp->dccps_options_received;
- suseconds_t delta;
-
- if (t_hist == NULL) {
- if (!or->dccpor_timestamp_echo) {
- DCCP_WARN("packet without timestamp echo\n");
- return DCCP_SANE_RTT_MAX;
- }
- timeval_sub_usecs(t_recv, or->dccpor_timestamp_echo * 10);
- delta = timeval_usecs(t_recv);
- } else
- delta = timeval_delta(t_recv, t_hist);
-
- delta -= or->dccpor_elapsed_time * 10; /* either set or 0 */
+ /* dccpor_elapsed_time is either zeroed out or set and > 0 */
+ delta -= dccp_sk(sk)->dccps_options_received.dccpor_elapsed_time * 10;
if (unlikely(delta <= 0)) {
- DCCP_WARN("unusable RTT sample %ld, using min\n", (long)delta);
+ DCCP_WARN("unusable RTT sample %ld, using min\n", delta);
return DCCP_SANE_RTT_MIN;
}
- if (unlikely(delta - (suseconds_t)DCCP_SANE_RTT_MAX > 0)) {
- DCCP_WARN("RTT sample %ld too large, using max\n", (long)delta);
+ if (unlikely(delta > DCCP_SANE_RTT_MAX)) {
+ DCCP_WARN("RTT sample %ld too large, using max\n", delta);
return DCCP_SANE_RTT_MAX;
}