void dccp_send_sync(struct sock *sk, const u64 ackno,
const enum dccp_pkt_type pkt_type)
{
/*
* We are not putting this on the write queue, so
* dccp_transmit_skb() will set the ownership to this
* sock.
*/
struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC);
if (skb == NULL) {
/* FIXME: how to make sure the sync is sent? */
DCCP_CRIT("could not send %s", dccp_packet_name(pkt_type));
return;
}
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = pkt_type;
DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno;
/*
* Clear the flag in case the Sync was scheduled for out-of-band data,
* such as carrying a long Ack Vector.
*/
dccp_sk(sk)->dccps_sync_scheduled = 0;
dccp_transmit_skb(sk, skb);
}
void dccp_send_sync(struct sock *sk, const u64 ackno,
const enum dccp_pkt_type pkt_type)
{
struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC);
if (skb == NULL) {
DCCP_CRIT("could not send %s", dccp_packet_name(pkt_type));
return;
}
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = pkt_type;
DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno;
dccp_transmit_skb(sk, skb);
}
static int __dccp_feat_activate(struct sock *sk, const int idx,
const bool is_local, dccp_feat_val const *fval)
{
bool rx;
u64 val;
if (idx < 0 || idx >= DCCP_FEAT_SUPPORTED_MAX)
return -1;
if (dccp_feat_table[idx].activation_hdlr == NULL)
return 0;
if (fval == NULL) {
val = dccp_feat_table[idx].default_value;
} else if (dccp_feat_table[idx].reconciliation == FEAT_SP) {
if (fval->sp.vec == NULL) {
/*
* This can happen when an empty Confirm is sent
* for an SP (i.e. known) feature. In this case
* we would be using the default anyway.
*/
DCCP_CRIT("Feature #%d undefined: using default", idx);
val = dccp_feat_table[idx].default_value;
} else {
val = fval->sp.vec[0];
}
} else {
val = fval->nn;
}
/* Location is RX if this is a local-RX or remote-TX feature */
rx = (is_local == (dccp_feat_table[idx].rxtx == FEAT_AT_RX));
dccp_debug(" -> activating %s %s, %sval=%llu\n", rx ? "RX" : "TX",
dccp_feat_fname(dccp_feat_table[idx].feat_num),
fval ? "" : "default ", (unsigned long long)val);
return dccp_feat_table[idx].activation_hdlr(sk, val, rx);
}
void dccp_send_sync(struct sock *sk, const u64 ackno,
const enum dccp_pkt_type pkt_type)
{
/*
* We are not putting this on the write queue, so
* dccp_transmit_skb() will set the ownership to this
* sock.
*/
struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC);
if (skb == NULL) {
/* FIXME: how to make sure the sync is sent? */
DCCP_CRIT("could not send %s", dccp_packet_name(pkt_type));
return;
}
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = pkt_type;
DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno;
dccp_transmit_skb(sk, skb);
}
/**
* dccp_parse_options - Parse DCCP options present in @skb
* @sk: client|server|listening dccp socket (when @dreq != NULL)
* @dreq: request socket to use during connection setup, or NULL
*/
int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
const struct dccp_hdr *dh = dccp_hdr(skb);
const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type;
unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
unsigned char *opt_ptr = options;
const unsigned char *opt_end = (unsigned char *)dh +
(dh->dccph_doff * 4);
struct dccp_options_received *opt_recv = &dp->dccps_options_received;
unsigned char opt, len;
unsigned char *uninitialized_var(value);
u32 elapsed_time;
__be32 opt_val;
int rc;
int mandatory = 0;
memset(opt_recv, 0, sizeof(*opt_recv));
opt = len = 0;
while (opt_ptr != opt_end) {
opt = *opt_ptr++;
len = 0;
value = NULL;
/* Check if this isn't a single byte option */
if (opt > DCCPO_MAX_RESERVED) {
if (opt_ptr == opt_end)
goto out_nonsensical_length;
len = *opt_ptr++;
if (len < 2)
goto out_nonsensical_length;
/*
* Remove the type and len fields, leaving
* just the value size
*/
len -= 2;
value = opt_ptr;
opt_ptr += len;
if (opt_ptr > opt_end)
goto out_nonsensical_length;
}
/*
* CCID-specific options are ignored during connection setup, as
* negotiation may still be in progress (see RFC 4340, 10.3).
* The same applies to Ack Vectors, as these depend on the CCID.
*/
if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC ||
opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1))
goto ignore_option;
switch (opt) {
case DCCPO_PADDING:
break;
case DCCPO_MANDATORY:
if (mandatory)
goto out_invalid_option;
if (pkt_type != DCCP_PKT_DATA)
mandatory = 1;
break;
case DCCPO_NDP_COUNT:
if (len > 6)
goto out_invalid_option;
opt_recv->dccpor_ndp = dccp_decode_value_var(value, len);
dccp_pr_debug("%s opt: NDP count=%llu\n", dccp_role(sk),
(unsigned long long)opt_recv->dccpor_ndp);
break;
case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R:
if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */
break;
if (len == 0)
goto out_invalid_option;
rc = dccp_feat_parse_options(sk, dreq, mandatory, opt,
*value, value + 1, len - 1);
if (rc)
goto out_featneg_failed;
break;
case DCCPO_TIMESTAMP:
if (len != 4)
goto out_invalid_option;
/*
* RFC 4340 13.1: "The precise time corresponding to
* Timestamp Value zero is not specified". We use
* zero to indicate absence of a meaningful timestamp.
*/
opt_val = get_unaligned((__be32 *)value);
if (unlikely(opt_val == 0)) {
DCCP_WARN("Timestamp with zero value\n");
break;
}
if (dreq != NULL) {
dreq->dreq_timestamp_echo = ntohl(opt_val);
dreq->dreq_timestamp_time = dccp_timestamp();
} else {
opt_recv->dccpor_timestamp =
dp->dccps_timestamp_echo = ntohl(opt_val);
dp->dccps_timestamp_time = dccp_timestamp();
}
dccp_pr_debug("%s rx opt: TIMESTAMP=%u, ackno=%llu\n",
dccp_role(sk), ntohl(opt_val),
(unsigned long long)
DCCP_SKB_CB(skb)->dccpd_ack_seq);
/* schedule an Ack in case this sender is quiescent */
inet_csk_schedule_ack(sk);
break;
case DCCPO_TIMESTAMP_ECHO:
if (len != 4 && len != 6 && len != 8)
goto out_invalid_option;
opt_val = get_unaligned((__be32 *)value);
opt_recv->dccpor_timestamp_echo = ntohl(opt_val);
dccp_pr_debug("%s rx opt: TIMESTAMP_ECHO=%u, len=%d, "
"ackno=%llu", dccp_role(sk),
opt_recv->dccpor_timestamp_echo,
len + 2,
(unsigned long long)
DCCP_SKB_CB(skb)->dccpd_ack_seq);
value += 4;
if (len == 4) { /* no elapsed time included */
dccp_pr_debug_cat("\n");
break;
}
if (len == 6) { /* 2-byte elapsed time */
__be16 opt_val2 = get_unaligned((__be16 *)value);
elapsed_time = ntohs(opt_val2);
} else { /* 4-byte elapsed time */
opt_val = get_unaligned((__be32 *)value);
elapsed_time = ntohl(opt_val);
}
dccp_pr_debug_cat(", ELAPSED_TIME=%u\n", elapsed_time);
/* Give precedence to the biggest ELAPSED_TIME */
if (elapsed_time > opt_recv->dccpor_elapsed_time)
opt_recv->dccpor_elapsed_time = elapsed_time;
break;
case DCCPO_ELAPSED_TIME:
if (dccp_packet_without_ack(skb)) /* RFC 4340, 13.2 */
break;
if (len == 2) {
__be16 opt_val2 = get_unaligned((__be16 *)value);
elapsed_time = ntohs(opt_val2);
} else if (len == 4) {
opt_val = get_unaligned((__be32 *)value);
elapsed_time = ntohl(opt_val);
} else {
goto out_invalid_option;
}
if (elapsed_time > opt_recv->dccpor_elapsed_time)
opt_recv->dccpor_elapsed_time = elapsed_time;
dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n",
dccp_role(sk), elapsed_time);
break;
case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC:
if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk,
pkt_type, opt, value, len))
goto out_invalid_option;
break;
case DCCPO_ACK_VECTOR_0:
case DCCPO_ACK_VECTOR_1:
if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */
break;
/*
* Ack vectors are processed by the TX CCID if it is
* interested. The RX CCID need not parse Ack Vectors,
* since it is only interested in clearing old state.
* Fall through.
*/
case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC:
if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk,
pkt_type, opt, value, len))
goto out_invalid_option;
break;
default:
DCCP_CRIT("DCCP(%p): option %d(len=%d) not "
"implemented, ignoring", sk, opt, len);
break;
}
ignore_option:
if (opt != DCCPO_MANDATORY)
mandatory = 0;
}
/* mandatory was the last byte in option list -> reset connection */
if (mandatory)
goto out_invalid_option;
out_nonsensical_length:
/* RFC 4340, 5.8: ignore option and all remaining option space */
return 0;
out_invalid_option:
DCCP_INC_STATS_BH(DCCP_MIB_INVALIDOPT);
rc = DCCP_RESET_CODE_OPTION_ERROR;
out_featneg_failed:
DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc);
DCCP_SKB_CB(skb)->dccpd_reset_code = rc;
DCCP_SKB_CB(skb)->dccpd_reset_data[0] = opt;
DCCP_SKB_CB(skb)->dccpd_reset_data[1] = len > 0 ? value[0] : 0;
DCCP_SKB_CB(skb)->dccpd_reset_data[2] = len > 1 ? value[1] : 0;
return -1;
}
int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
const struct dccp_hdr *dh = dccp_hdr(skb);
const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type;
unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
unsigned char *opt_ptr = options;
const unsigned char *opt_end = (unsigned char *)dh +
(dh->dccph_doff * 4);
struct dccp_options_received *opt_recv = &dp->dccps_options_received;
unsigned char opt, len;
unsigned char *uninitialized_var(value);
u32 elapsed_time;
__be32 opt_val;
int rc;
int mandatory = 0;
memset(opt_recv, 0, sizeof(*opt_recv));
opt = len = 0;
while (opt_ptr != opt_end) {
opt = *opt_ptr++;
len = 0;
value = NULL;
if (opt > DCCPO_MAX_RESERVED) {
if (opt_ptr == opt_end)
goto out_nonsensical_length;
len = *opt_ptr++;
if (len < 2)
goto out_nonsensical_length;
len -= 2;
value = opt_ptr;
opt_ptr += len;
if (opt_ptr > opt_end)
goto out_nonsensical_length;
}
if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC ||
opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1))
goto ignore_option;
switch (opt) {
case DCCPO_PADDING:
break;
case DCCPO_MANDATORY:
if (mandatory)
goto out_invalid_option;
if (pkt_type != DCCP_PKT_DATA)
mandatory = 1;
break;
case DCCPO_NDP_COUNT:
if (len > 6)
goto out_invalid_option;
opt_recv->dccpor_ndp = dccp_decode_value_var(value, len);
dccp_pr_debug("%s opt: NDP count=%llu\n", dccp_role(sk),
(unsigned long long)opt_recv->dccpor_ndp);
break;
case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R:
if (pkt_type == DCCP_PKT_DATA)
break;
if (len == 0)
goto out_invalid_option;
rc = dccp_feat_parse_options(sk, dreq, mandatory, opt,
*value, value + 1, len - 1);
if (rc)
goto out_featneg_failed;
break;
case DCCPO_TIMESTAMP:
if (len != 4)
goto out_invalid_option;
opt_val = get_unaligned((__be32 *)value);
if (unlikely(opt_val == 0)) {
DCCP_WARN("Timestamp with zero value\n");
break;
}
if (dreq != NULL) {
dreq->dreq_timestamp_echo = ntohl(opt_val);
dreq->dreq_timestamp_time = dccp_timestamp();
} else {
opt_recv->dccpor_timestamp =
dp->dccps_timestamp_echo = ntohl(opt_val);
dp->dccps_timestamp_time = dccp_timestamp();
}
dccp_pr_debug("%s rx opt: TIMESTAMP=%u, ackno=%llu\n",
dccp_role(sk), ntohl(opt_val),
(unsigned long long)
DCCP_SKB_CB(skb)->dccpd_ack_seq);
inet_csk_schedule_ack(sk);
break;
case DCCPO_TIMESTAMP_ECHO:
if (len != 4 && len != 6 && len != 8)
goto out_invalid_option;
opt_val = get_unaligned((__be32 *)value);
opt_recv->dccpor_timestamp_echo = ntohl(opt_val);
dccp_pr_debug("%s rx opt: TIMESTAMP_ECHO=%u, len=%d, "
"ackno=%llu", dccp_role(sk),
opt_recv->dccpor_timestamp_echo,
len + 2,
(unsigned long long)
DCCP_SKB_CB(skb)->dccpd_ack_seq);
value += 4;
if (len == 4) {
dccp_pr_debug_cat("\n");
break;
}
if (len == 6) {
__be16 opt_val2 = get_unaligned((__be16 *)value);
elapsed_time = ntohs(opt_val2);
} else {
opt_val = get_unaligned((__be32 *)value);
elapsed_time = ntohl(opt_val);
}
dccp_pr_debug_cat(", ELAPSED_TIME=%u\n", elapsed_time);
if (elapsed_time > opt_recv->dccpor_elapsed_time)
opt_recv->dccpor_elapsed_time = elapsed_time;
break;
case DCCPO_ELAPSED_TIME:
if (dccp_packet_without_ack(skb))
break;
if (len == 2) {
__be16 opt_val2 = get_unaligned((__be16 *)value);
elapsed_time = ntohs(opt_val2);
} else if (len == 4) {
opt_val = get_unaligned((__be32 *)value);
elapsed_time = ntohl(opt_val);
} else {
goto out_invalid_option;
}
if (elapsed_time > opt_recv->dccpor_elapsed_time)
opt_recv->dccpor_elapsed_time = elapsed_time;
dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n",
dccp_role(sk), elapsed_time);
break;
case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC:
if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk,
pkt_type, opt, value, len))
goto out_invalid_option;
break;
case DCCPO_ACK_VECTOR_0:
case DCCPO_ACK_VECTOR_1:
if (dccp_packet_without_ack(skb))
break;
case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC:
if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk,
pkt_type, opt, value, len))
goto out_invalid_option;
break;
default:
DCCP_CRIT("DCCP(%p): option %d(len=%d) not "
"implemented, ignoring", sk, opt, len);
break;
}
ignore_option:
if (opt != DCCPO_MANDATORY)
mandatory = 0;
}
if (mandatory)
goto out_invalid_option;
out_nonsensical_length:
return 0;
out_invalid_option:
DCCP_INC_STATS_BH(DCCP_MIB_INVALIDOPT);
rc = DCCP_RESET_CODE_OPTION_ERROR;
out_featneg_failed:
DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc);
DCCP_SKB_CB(skb)->dccpd_reset_code = rc;
DCCP_SKB_CB(skb)->dccpd_reset_data[0] = opt;
DCCP_SKB_CB(skb)->dccpd_reset_data[1] = len > 0 ? value[0] : 0;
DCCP_SKB_CB(skb)->dccpd_reset_data[2] = len > 1 ? value[1] : 0;
return -1;
}
static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len)
{
struct dccp_sock *dp = dccp_sk(sk);
struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
struct ccid2_seq *next;
hctx->ccid2hctx_pipe++;
hctx->ccid2hctx_seqh->ccid2s_seq = dp->dccps_gss;
hctx->ccid2hctx_seqh->ccid2s_acked = 0;
hctx->ccid2hctx_seqh->ccid2s_sent = jiffies;
next = hctx->ccid2hctx_seqh->ccid2s_next;
/* check if we need to alloc more space */
if (next == hctx->ccid2hctx_seqt) {
if (ccid2_hc_tx_alloc_seq(hctx)) {
DCCP_CRIT("packet history - out of memory!");
/* FIXME: find a more graceful way to bail out */
return;
}
next = hctx->ccid2hctx_seqh->ccid2s_next;
BUG_ON(next == hctx->ccid2hctx_seqt);
}
hctx->ccid2hctx_seqh = next;
ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd,
hctx->ccid2hctx_pipe);
/*
* FIXME: The code below is broken and the variables have been removed
* from the socket struct. The `ackloss' variable was always set to 0,
* and with arsent there are several problems:
* (i) it doesn't just count the number of Acks, but all sent packets;
* (ii) it is expressed in # of packets, not # of windows, so the
* comparison below uses the wrong formula: Appendix A of RFC 4341
* comes up with the number K = cwnd / (R^2 - R) of consecutive windows
* of data with no lost or marked Ack packets. If arsent were the # of
* consecutive Acks received without loss, then Ack Ratio needs to be
* decreased by 1 when
* arsent >= K * cwnd / R = cwnd^2 / (R^3 - R^2)
* where cwnd / R is the number of Acks received per window of data
* (cf. RFC 4341, App. A). The problems are that
* - arsent counts other packets as well;
* - the comparison uses a formula different from RFC 4341;
* - computing a cubic/quadratic equation each time is too complicated.
* Hence a different algorithm is needed.
*/
#if 0
/* Ack Ratio. Need to maintain a concept of how many windows we sent */
hctx->ccid2hctx_arsent++;
/* We had an ack loss in this window... */
if (hctx->ccid2hctx_ackloss) {
if (hctx->ccid2hctx_arsent >= hctx->ccid2hctx_cwnd) {
hctx->ccid2hctx_arsent = 0;
hctx->ccid2hctx_ackloss = 0;
}
} else {
/* No acks lost up to now... */
/* decrease ack ratio if enough packets were sent */
if (dp->dccps_l_ack_ratio > 1) {
/* XXX don't calculate denominator each time */
int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio -
dp->dccps_l_ack_ratio;
denom = hctx->ccid2hctx_cwnd * hctx->ccid2hctx_cwnd / denom;
if (hctx->ccid2hctx_arsent >= denom) {
ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1);
hctx->ccid2hctx_arsent = 0;
}
} else {
/* we can't increase ack ratio further [1] */
hctx->ccid2hctx_arsent = 0; /* or maybe set it to cwnd*/
}
}
#endif
/* setup RTO timer */
if (!timer_pending(&hctx->ccid2hctx_rtotimer))
ccid2_start_rto_timer(sk);
#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
do {
struct ccid2_seq *seqp = hctx->ccid2hctx_seqt;
while (seqp != hctx->ccid2hctx_seqh) {
ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n",
(unsigned long long)seqp->ccid2s_seq,
seqp->ccid2s_acked, seqp->ccid2s_sent);
seqp = seqp->ccid2s_next;
}
} while (0);
ccid2_pr_debug("=========\n");
ccid2_hc_tx_check_sanity(hctx);
#endif
}