static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct dccp_sock *dp;
int val, len;
if (get_user(len, optlen))
return -EFAULT;
if (len < (int)sizeof(int))
return -EINVAL;
dp = dccp_sk(sk);
switch (optname) {
case DCCP_SOCKOPT_PACKET_SIZE:
DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
return 0;
case DCCP_SOCKOPT_SERVICE:
return dccp_getsockopt_service(sk, len,
(__be32 __user *)optval, optlen);
case DCCP_SOCKOPT_GET_CUR_MPS:
val = dp->dccps_mss_cache;
len = sizeof(val);
break;
case DCCP_SOCKOPT_SEND_CSCOV:
val = dp->dccps_pcslen;
len = sizeof(val);
break;
case DCCP_SOCKOPT_RECV_CSCOV:
val = dp->dccps_pcrlen;
len = sizeof(val);
break;
case 128 ... 191:
return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname,
len, (u32 __user *)optval, optlen);
case 192 ... 255:
return ccid_hc_tx_getsockopt(dp->dccps_hc_tx_ccid, sk, optname,
len, (u32 __user *)optval, optlen);
default:
return -ENOPROTOOPT;
}
if (put_user(len, optlen) || copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
/*
* This routine does path mtu discovery as defined in RFC1191.
*/
static inline void dccp_do_pmtu_discovery(struct sock *sk,
const struct iphdr *iph,
u32 mtu)
{
struct dst_entry *dst;
const struct inet_sock *inet = inet_sk(sk);
const struct dccp_sock *dp = dccp_sk(sk);
/* We are not interested in DCCP_LISTEN and request_socks (RESPONSEs
* send out by Linux are always < 576bytes so they should go through
* unfragmented).
*/
if (sk->sk_state == DCCP_LISTEN)
return;
/* We don't check in the destentry if pmtu discovery is forbidden
* on this route. We just assume that no packet_to_big packets
* are send back when pmtu discovery is not active.
* There is a small race when the user changes this flag in the
* route, but I think that's acceptable.
*/
if ((dst = __sk_dst_check(sk, 0)) == NULL)
return;
dst->ops->update_pmtu(dst, mtu);
/* Something is about to be wrong... Remember soft error
* for the case, if this connection will not able to recover.
*/
if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
sk->sk_err_soft = EMSGSIZE;
mtu = dst_mtu(dst);
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
inet_csk(sk)->icsk_pmtu_cookie > mtu) {
dccp_sync_mss(sk, mtu);
/*
* From RFC 4340, sec. 14.1:
*
* DCCP-Sync packets are the best choice for upward
* probing, since DCCP-Sync probes do not risk application
* data loss.
*/
dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
} /* else let the usual retransmit timer handle it */
}
static int dccp_hdlr_ackvec(struct sock *sk, u64 enable, bool rx)
{
struct dccp_sock *dp = dccp_sk(sk);
if (rx) {
if (enable && dp->dccps_hc_rx_ackvec == NULL) {
dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(gfp_any());
if (dp->dccps_hc_rx_ackvec == NULL)
return -ENOMEM;
} else if (!enable) {
dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
dp->dccps_hc_rx_ackvec = NULL;
}
}
return 0;
}
/*
* Do all connect socket setups that can be done AF independent.
*/
static inline void dccp_connect_init(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
sk->sk_err = 0;
sock_reset_flag(sk, SOCK_DONE);
dccp_sync_mss(sk, dst_mtu(dst));
/* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */
dp->dccps_gar = dp->dccps_iss;
icsk->icsk_retransmits = 0;
}
void dccp_write_xmit(struct sock *sk, int block)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
while ((skb = skb_peek(&sk->sk_write_queue))) {
int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
if (err > 0) {
if (!block) {
sk_reset_timer(sk, &dp->dccps_xmit_timer,
msecs_to_jiffies(err)+jiffies);
break;
} else
err = dccp_wait_for_ccid(sk, skb, err);
if (err && err != -EINTR)
DCCP_BUG("err=%d after dccp_wait_for_ccid", err);
}
skb_dequeue(&sk->sk_write_queue);
if (err == 0) {
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
const int len = skb->len;
if (sk->sk_state == DCCP_PARTOPEN) {
/* See 8.1.5. Handshake Completion */
inet_csk_schedule_ack(sk);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
inet_csk(sk)->icsk_rto,
DCCP_RTO_MAX);
dcb->dccpd_type = DCCP_PKT_DATAACK;
} else if (dccp_ack_pending(sk))
dcb->dccpd_type = DCCP_PKT_DATAACK;
else
dcb->dccpd_type = DCCP_PKT_DATA;
err = dccp_transmit_skb(sk, skb);
ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len);
if (err)
DCCP_BUG("err=%d after ccid_hc_tx_packet_sent",
err);
} else {
dccp_pr_debug("packet discarded due to err=%d\n", err);
kfree_skb(skb);
}
}
}
/*
* The three way handshake has completed - we got a valid ACK or DATAACK -
* now create the new socket.
*
* This is the equivalent of TCP's tcp_v4_syn_recv_sock
*/
struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
{
struct inet_request_sock *ireq;
struct inet_sock *newinet;
struct dccp_sock *newdp;
struct sock *newsk;
if (sk_acceptq_is_full(sk))
goto exit_overflow;
if (dst == NULL && (dst = inet_csk_route_req(sk, req)) == NULL)
goto exit;
newsk = dccp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
goto exit;
sk_setup_caps(newsk, dst);
newdp = dccp_sk(newsk);
newinet = inet_sk(newsk);
ireq = inet_rsk(req);
newinet->daddr = ireq->rmt_addr;
newinet->rcv_saddr = ireq->loc_addr;
newinet->saddr = ireq->loc_addr;
newinet->opt = ireq->opt;
ireq->opt = NULL;
newinet->mc_index = inet_iif(skb);
newinet->mc_ttl = skb->nh.iph->ttl;
newinet->id = jiffies;
dccp_sync_mss(newsk, dst_mtu(dst));
__inet_hash_nolisten(newsk);
__inet_inherit_port(sk, newsk);
return newsk;
exit_overflow:
NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS);
exit:
NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS);
dst_release(dst);
return NULL;
}
/**
* dccp_wait_for_ccid - Wait for ccid to tell us we can send a packet
* @sk: socket to wait for
* @timeo: for how long
*/
static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb,
long *timeo)
{
struct dccp_sock *dp = dccp_sk(sk);
DEFINE_WAIT(wait);
long delay;
int rc;
while (1) {
prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
if (!*timeo)
goto do_nonblock;
if (signal_pending(current))
goto do_interrupted;
rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb,
skb->len);
if (rc <= 0)
break;
delay = msecs_to_jiffies(rc);
if (delay > *timeo || delay < 0)
goto do_nonblock;
sk->sk_write_pending++;
release_sock(sk);
*timeo -= schedule_timeout(delay);
lock_sock(sk);
sk->sk_write_pending--;
}
out:
finish_wait(sk->sk_sleep, &wait);
return rc;
do_error:
rc = -EPIPE;
goto out;
do_nonblock:
rc = -EAGAIN;
goto out;
do_interrupted:
rc = sock_intr_errno(*timeo);
goto out;
}
static struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst,
const enum dccp_reset_codes code)
{
struct dccp_hdr *dh;
struct dccp_sock *dp = dccp_sk(sk);
const u32 dccp_header_size = sizeof(struct dccp_hdr) +
sizeof(struct dccp_hdr_ext) +
sizeof(struct dccp_hdr_reset);
struct sk_buff *skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1,
GFP_ATOMIC);
if (skb == NULL)
return NULL;
/* Reserve space for headers. */
skb_reserve(skb, sk->sk_prot->max_header);
skb->dst = dst_clone(dst);
dccp_inc_seqno(&dp->dccps_gss);
DCCP_SKB_CB(skb)->dccpd_reset_code = code;
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESET;
DCCP_SKB_CB(skb)->dccpd_seq = dp->dccps_gss;
if (dccp_insert_options(sk, skb)) {
kfree_skb(skb);
return NULL;
}
dh = dccp_zeroed_hdr(skb, dccp_header_size);
dh->dccph_sport = inet_sk(sk)->sport;
dh->dccph_dport = inet_sk(sk)->dport;
dh->dccph_doff = (dccp_header_size +
DCCP_SKB_CB(skb)->dccpd_opt_len) / 4;
dh->dccph_type = DCCP_PKT_RESET;
dh->dccph_x = 1;
dccp_hdr_set_seq(dh, dp->dccps_gss);
dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dp->dccps_gsr);
dccp_hdr_reset(skb)->dccph_reset_code = code;
inet_csk(sk)->icsk_af_ops->send_check(sk, 0, skb);
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
return skb;
}
/*
* Feature activation handlers.
*
* These all use an u64 argument, to provide enough room for NN/SP features. At
* this stage the negotiated values have been checked to be within their range.
*/
static int dccp_hdlr_ccid(struct sock *sk, u64 ccid, bool rx)
{
struct dccp_sock *dp = dccp_sk(sk);
struct ccid *new_ccid = ccid_new(ccid, sk, rx);
if (new_ccid == NULL)
return -ENOMEM;
if (rx) {
ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
dp->dccps_hc_rx_ccid = new_ccid;
} else {
ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
dp->dccps_hc_tx_ccid = new_ccid;
}
return 0;
}
static void dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb)
{
/*
* Step 7: Check for unexpected packet types
* If (S.is_server and P.type == CloseReq)
* Send Sync packet acknowledging P.seqno
* Drop packet and return
*/
if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT) {
dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_PKT_SYNC);
return;
}
if (sk->sk_state != DCCP_CLOSING)
dccp_set_state(sk, DCCP_CLOSING);
dccp_send_close(sk, 0);
}
static int dccp_rcv_close(struct sock *sk, struct sk_buff *skb)
{
int queued = 0;
switch (sk->sk_state) {
/*
* We ignore Close when received in one of the following states:
* - CLOSED (may be a late or duplicate packet)
* - PASSIVE_CLOSEREQ (the peer has sent a CloseReq earlier)
* - RESPOND (already handled by dccp_check_req)
*/
case DCCP_CLOSING:
/*
* Simultaneous-close: receiving a Close after sending one. This
* can happen if both client and server perform active-close and
* will result in an endless ping-pong of crossing and retrans-
* mitted Close packets, which only terminates when one of the
* nodes times out (min. 64 seconds). Quicker convergence can be
* achieved when one of the nodes acts as tie-breaker.
* This is ok as both ends are done with data transfer and each
* end is just waiting for the other to acknowledge termination.
*/
if (dccp_sk(sk)->dccps_role != DCCP_ROLE_CLIENT)
break;
/* fall through */
case DCCP_REQUESTING:
case DCCP_ACTIVE_CLOSEREQ:
dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED);
dccp_done(sk);
break;
case DCCP_OPEN:
case DCCP_PARTOPEN:
/* Give waiting application a chance to read pending data */
queued = 1;
dccp_fin(sk, skb);
dccp_set_state(sk, DCCP_PASSIVE_CLOSE);
/* fall through */
case DCCP_PASSIVE_CLOSE:
/*
* Retransmitted Close: we have already enqueued the first one.
*/
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
}
return queued;
}
static void dccp_get_info(struct sock *sk, struct tcp_info *info)
{
struct dccp_sock *dp = dccp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
memset(info, 0, sizeof(*info));
info->tcpi_state = sk->sk_state;
info->tcpi_retransmits = icsk->icsk_retransmits;
info->tcpi_probes = icsk->icsk_probes_out;
info->tcpi_backoff = icsk->icsk_backoff;
info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
if (dccp_msk(sk)->dccpms_send_ack_vector)
info->tcpi_options |= TCPI_OPT_SACK;
ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info);
ccid_hc_tx_get_info(dp->dccps_hc_tx_ccid, sk, info);
}
int dccp_insert_options(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
DCCP_SKB_CB(skb)->dccpd_opt_len = 0;
if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb))
return -1;
if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) {
/* Feature Negotiation */
if (dccp_feat_insert_opts(dp, NULL, skb))
return -1;
if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) {
/*
* Obtain RTT sample from Request/Response exchange.
* This is currently used for TFRC initialisation.
*/
if (dccp_insert_option_timestamp(skb))
return -1;
} else if (dp->dccps_hc_rx_ackvec != NULL &&
dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) &&
dccp_insert_option_ackvec(sk, skb)) {
return -1;
}
}
if (dp->dccps_hc_rx_insert_options) {
if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb))
return -1;
dp->dccps_hc_rx_insert_options = 0;
}
if (dp->dccps_timestamp_echo != 0 &&
dccp_insert_option_timestamp_echo(dp, NULL, skb))
return -1;
dccp_insert_option_padding(skb);
return 0;
}
static int dccp_rcv_respond_partopen_state_process(struct sock *sk,
struct sk_buff *skb,
const struct dccp_hdr *dh,
const unsigned len)
{
int queued = 0;
switch (dh->dccph_type) {
case DCCP_PKT_RESET:
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
break;
case DCCP_PKT_DATA:
if (sk->sk_state == DCCP_RESPOND)
break;
case DCCP_PKT_DATAACK:
case DCCP_PKT_ACK:
/*
* FIXME: we should be reseting the PARTOPEN (DELACK) timer
* here but only if we haven't used the DELACK timer for
* something else, like sending a delayed ack for a TIMESTAMP
* echo, etc, for now were not clearing it, sending an extra
* ACK when there is nothing else to do in DELACK is not a big
* deal after all.
*/
/* Stop the PARTOPEN timer */
if (sk->sk_state == DCCP_PARTOPEN)
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
dccp_sk(sk)->dccps_osr = DCCP_SKB_CB(skb)->dccpd_seq;
dccp_set_state(sk, DCCP_OPEN);
if (dh->dccph_type == DCCP_PKT_DATAACK ||
dh->dccph_type == DCCP_PKT_DATA) {
__dccp_rcv_established(sk, skb, dh, len);
queued = 1; /* packet was queued
(by __dccp_rcv_established) */
}
break;
}
return queued;
}
/*
* This routine does path mtu discovery as defined in RFC1191.
*/
static inline void dccp_do_pmtu_discovery(struct sock *sk,
const struct iphdr *iph,
u32 mtu)
{
struct dst_entry *dst;
const struct inet_sock *inet = inet_sk(sk);
const struct dccp_sock *dp = dccp_sk(sk);
/* We are not interested in DCCP_LISTEN and request_socks (RESPONSEs
* send out by Linux are always < 576bytes so they should go through
* unfragmented).
*/
if (sk->sk_state == DCCP_LISTEN)
return;
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
/* Something is about to be wrong... Remember soft error
* for the case, if this connection will not able to recover.
*/
if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
sk->sk_err_soft = EMSGSIZE;
mtu = dst_mtu(dst);
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
ip_sk_accept_pmtu(sk) &&
inet_csk(sk)->icsk_pmtu_cookie > mtu) {
dccp_sync_mss(sk, mtu);
/*
* From RFC 4340, sec. 14.1:
*
* DCCP-Sync packets are the best choice for upward
* probing, since DCCP-Sync probes do not risk application
* data loss.
*/
dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
} /* else let the usual retransmit timer handle it */
}
void dccp_insert_option_elapsed_time(struct sock *sk,
struct sk_buff *skb,
u32 elapsed_time)
{
#ifdef CONFIG_IP_DCCP_DEBUG
struct dccp_sock *dp = dccp_sk(sk);
const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ?
"CLIENT TX opt: " : "server TX opt: ";
#endif
const int elapsed_time_len = dccp_elapsed_time_len(elapsed_time);
const int len = 2 + elapsed_time_len;
unsigned char *to;
if (elapsed_time_len == 0)
return;
if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) {
LIMIT_NETDEBUG(KERN_INFO "DCCP: packet too small to "
"insert elapsed time!\n");
return;
}
DCCP_SKB_CB(skb)->dccpd_opt_len += len;
to = skb_push(skb, len);
*to++ = DCCPO_ELAPSED_TIME;
*to++ = len;
if (elapsed_time_len == 2) {
const u16 var16 = htons((u16)elapsed_time);
memcpy(to, &var16, 2);
} else {
const u32 var32 = htonl(elapsed_time);
memcpy(to, &var32, 4);
}
dccp_pr_debug("%sELAPSED_TIME=%u, len=%d, seqno=%llu\n",
debug_prefix, elapsed_time,
len,
(unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq);
}
int dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct dccp_sock *dp;
int val, len;
if (level != SOL_DCCP)
return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level,
optname, optval,
optlen);
if (get_user(len, optlen))
return -EFAULT;
if (len < sizeof(int))
return -EINVAL;
dp = dccp_sk(sk);
switch (optname) {
case DCCP_SOCKOPT_PACKET_SIZE:
val = dp->dccps_packet_size;
len = sizeof(dp->dccps_packet_size);
break;
case DCCP_SOCKOPT_SERVICE:
return dccp_getsockopt_service(sk, len,
(u32 __user *)optval, optlen);
case 128 ... 191:
return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname,
len, (u32 __user *)optval, optlen);
case 192 ... 255:
return ccid_hc_tx_getsockopt(dp->dccps_hc_tx_ccid, sk, optname,
len, (u32 __user *)optval, optlen);
default:
return -ENOPROTOOPT;
}
if (put_user(len, optlen) || copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct dccp_sock *dp = dccp_sk(sk);
u32 ccmps = dccp_determine_ccmps(dp);
u32 cur_mps = ccmps ? min(pmtu, ccmps) : pmtu;
cur_mps -= (icsk->icsk_af_ops->net_header_len + icsk->icsk_ext_hdr_len +
sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext));
cur_mps -= roundup(1 + 6 + 10 + dp->dccps_send_ndp_count * 8 + 6 +
(dp->dccps_hc_rx_ackvec ? DCCPAV_MIN_OPTLEN : 0), 4);
icsk->icsk_pmtu_cookie = pmtu;
dp->dccps_mss_cache = cur_mps;
return cur_mps;
}
int dccp_insert_options(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
DCCP_SKB_CB(skb)->dccpd_opt_len = 0;
if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb))
return -1;
if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) {
if (dccp_feat_insert_opts(dp, NULL, skb))
return -1;
if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) {
if (dccp_insert_option_timestamp(sk, skb))
return -1;
} else if (dp->dccps_hc_rx_ackvec != NULL &&
dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) &&
dccp_insert_option_ackvec(sk, skb)) {
return -1;
}
}
if (dp->dccps_hc_rx_insert_options) {
if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb))
return -1;
dp->dccps_hc_rx_insert_options = 0;
}
if (dp->dccps_timestamp_echo != 0 &&
dccp_insert_option_timestamp_echo(dp, NULL, skb))
return -1;
dccp_insert_option_padding(skb);
return 0;
}
/*
* Send a DCCP_PKT_CLOSE/CLOSEREQ. The caller locks the socket for us. This
* cannot be allowed to fail queueing a DCCP_PKT_CLOSE/CLOSEREQ frame under
* any circumstances.
*/
void dccp_send_close(struct sock *sk, const int active)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
const gfp_t prio = active ? GFP_KERNEL : GFP_ATOMIC;
skb = alloc_skb(sk->sk_prot->max_header, prio);
if (skb == NULL)
return;
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, sk->sk_prot->max_header);
skb->csum = 0;
DCCP_SKB_CB(skb)->dccpd_type = dp->dccps_role == DCCP_ROLE_CLIENT ?
DCCP_PKT_CLOSE : DCCP_PKT_CLOSEREQ;
if (active) {
dccp_skb_entail(sk, skb);
dccp_transmit_skb(sk, skb_clone(skb, prio));
} else
dccp_transmit_skb(sk, skb);
}
void dccp_insert_options(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
DCCP_SKB_CB(skb)->dccpd_opt_len = 0;
if (dp->dccps_options.dccpo_send_ndp_count)
dccp_insert_option_ndp(sk, skb);
if (!dccp_packet_without_ack(skb)) {
if (dp->dccps_options.dccpo_send_ack_vector &&
dccp_ackvec_pending(dp->dccps_hc_rx_ackvec))
dccp_insert_option_ackvec(sk, skb);
if (dp->dccps_timestamp_echo != 0)
dccp_insert_option_timestamp_echo(sk, skb);
}
if (dp->dccps_hc_rx_insert_options) {
ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb);
dp->dccps_hc_rx_insert_options = 0;
}
if (dp->dccps_hc_tx_insert_options) {
ccid_hc_tx_insert_options(dp->dccps_hc_tx_ccid, sk, skb);
dp->dccps_hc_tx_insert_options = 0;
}
/* XXX: insert other options when appropriate */
if (DCCP_SKB_CB(skb)->dccpd_opt_len != 0) {
/* The length of all options has to be a multiple of 4 */
int padding = DCCP_SKB_CB(skb)->dccpd_opt_len % 4;
if (padding != 0) {
padding = 4 - padding;
memset(skb_push(skb, padding), 0, padding);
DCCP_SKB_CB(skb)->dccpd_opt_len += padding;
}
}
}
/**
* dccp_flush_write_queue - Drain queue at end of connection
* Since dccp_sendmsg queues packets without waiting for them to be sent, it may
* happen that the TX queue is not empty at the end of a connection. We give the
* HC-sender CCID a grace period of up to @time_budget jiffies. If this function
* returns with a non-empty write queue, it will be purged later.
*/
void dccp_flush_write_queue(struct sock *sk, long *time_budget)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
long delay, rc;
while (*time_budget > 0 && (skb = skb_peek(&sk->sk_write_queue))) {
rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
switch (ccid_packet_dequeue_eval(rc)) {
case CCID_PACKET_WILL_DEQUEUE_LATER:
/*
* If the CCID determines when to send, the next sending
* time is unknown or the CCID may not even send again
* (e.g. remote host crashes or lost Ack packets).
*/
DCCP_WARN("CCID did not manage to send all packets\n");
return;
case CCID_PACKET_DELAY:
delay = msecs_to_jiffies(rc);
if (delay > *time_budget)
return;
rc = dccp_wait_for_ccid(sk, delay);
if (rc < 0)
return;
*time_budget -= (delay - rc);
/* check again if we can send now */
break;
case CCID_PACKET_SEND_AT_ONCE:
dccp_xmit_packet(sk);
break;
case CCID_PACKET_ERR:
skb_dequeue(&sk->sk_write_queue);
kfree_skb(skb);
dccp_pr_debug("packet discarded due to err=%ld\n", rc);
}
}
}
int dccp_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, int optlen)
{
struct dccp_sock *dp;
int err;
int val;
if (level != SOL_DCCP)
return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level,
optname, optval,
optlen);
if (optlen < sizeof(int))
return -EINVAL;
if (get_user(val, (int __user *)optval))
return -EFAULT;
if (optname == DCCP_SOCKOPT_SERVICE)
return dccp_setsockopt_service(sk, val, optval, optlen);
lock_sock(sk);
dp = dccp_sk(sk);
err = 0;
switch (optname) {
case DCCP_SOCKOPT_PACKET_SIZE:
dp->dccps_packet_size = val;
break;
default:
err = -ENOPROTOOPT;
break;
}
release_sock(sk);
return err;
}
void dccp_set_state(struct sock *sk, const int state)
{
const int oldstate = sk->sk_state;
dccp_pr_debug("%s(%p) %s --> %s\n", dccp_role(sk), sk,
dccp_state_name(oldstate), dccp_state_name(state));
WARN_ON(state == oldstate);
switch (state) {
case DCCP_OPEN:
if (oldstate != DCCP_OPEN)
DCCP_INC_STATS(DCCP_MIB_CURRESTAB);
/* Client retransmits all Confirm options until entering OPEN */
if (oldstate == DCCP_PARTOPEN)
dccp_feat_list_purge(&dccp_sk(sk)->dccps_featneg);
break;
case DCCP_CLOSED:
if (oldstate == DCCP_OPEN || oldstate == DCCP_ACTIVE_CLOSEREQ ||
oldstate == DCCP_CLOSING)
DCCP_INC_STATS(DCCP_MIB_ESTABRESETS);
sk->sk_prot->unhash(sk);
if (inet_csk(sk)->icsk_bind_hash != NULL &&
!(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
inet_put_port(sk);
/* fall through */
default:
if (oldstate == DCCP_OPEN)
DCCP_DEC_STATS(DCCP_MIB_CURRESTAB);
}
/* Change state AFTER socket is unhashed to avoid closed
* socket sitting in hash tables.
*/
sk->sk_state = state;
}
/**
* dccp_wait_for_ccid - Wait for ccid to tell us we can send a packet
* @sk: socket to wait for
* @skb: current skb to pass on for waiting
* @delay: sleep timeout in milliseconds (> 0)
* This function is called by default when the socket is closed, and
* when a non-zero linger time is set on the socket. For consistency
*/
static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay)
{
struct dccp_sock *dp = dccp_sk(sk);
DEFINE_WAIT(wait);
unsigned long jiffdelay;
int rc;
do {
dccp_pr_debug("delayed send by %d msec\n", delay);
jiffdelay = msecs_to_jiffies(delay);
prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
sk->sk_write_pending++;
release_sock(sk);
schedule_timeout(jiffdelay);
lock_sock(sk);
sk->sk_write_pending--;
if (sk->sk_err)
goto do_error;
if (signal_pending(current))
goto do_interrupted;
rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
} while ((delay = rc) > 0);
out:
finish_wait(sk->sk_sleep, &wait);
return rc;
do_error:
rc = -EPIPE;
goto out;
do_interrupted:
rc = -EINTR;
goto out;
}
/*
* Do all connect socket setups that can be done AF independent.
*/
static inline void dccp_connect_init(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
sk->sk_err = 0;
sock_reset_flag(sk, SOCK_DONE);
dccp_sync_mss(sk, dst_mtu(dst));
dccp_update_gss(sk, dp->dccps_iss);
/*
* SWL and AWL are initially adjusted so that they are not less than
* the initial Sequence Numbers received and sent, respectively:
* SWL := max(GSR + 1 - floor(W/4), ISR),
* AWL := max(GSS - W' + 1, ISS).
* These adjustments MUST be applied only at the beginning of the
* connection.
*/
dccp_set_seqno(&dp->dccps_awl, max48(dp->dccps_awl, dp->dccps_iss));
icsk->icsk_retransmits = 0;
}
int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
{
struct dccp_sock *dp = dccp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_rto = DCCP_TIMEOUT_INIT;
icsk->icsk_syn_retries = sysctl_dccp_request_retries;
sk->sk_state = DCCP_CLOSED;
sk->sk_write_space = dccp_write_space;
icsk->icsk_sync_mss = dccp_sync_mss;
dp->dccps_mss_cache = 536;
dp->dccps_rate_last = jiffies;
dp->dccps_role = DCCP_ROLE_UNDEFINED;
dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT;
dp->dccps_tx_qlen = sysctl_dccp_tx_qlen;
dccp_init_xmit_timers(sk);
INIT_LIST_HEAD(&dp->dccps_featneg);
/* control socket doesn't need feat nego */
if (likely(ctl_sock_initialized))
return dccp_feat_init(sk);
return 0;
}
/*
* Send a DCCP_PKT_CLOSE/CLOSEREQ. The caller locks the socket for us. This
* cannot be allowed to fail queueing a DCCP_PKT_CLOSE/CLOSEREQ frame under
* any circumstances.
*/
void dccp_send_close(struct sock *sk, const int active)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
const gfp_t prio = active ? GFP_KERNEL : GFP_ATOMIC;
skb = alloc_skb(sk->sk_prot->max_header, prio);
if (skb == NULL)
return;
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, sk->sk_prot->max_header);
if (dp->dccps_role == DCCP_ROLE_SERVER && !dp->dccps_server_timewait)
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSEREQ;
else
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSE;
if (active) {
dccp_write_xmit(sk, 1);
dccp_skb_entail(sk, skb);
dccp_transmit_skb(sk, skb_clone(skb, prio));
/*
* Retransmission timer for active-close: RFC 4340, 8.3 requires
* to retransmit the Close/CloseReq until the CLOSING/CLOSEREQ
* state can be left. The initial timeout is 2 RTTs.
* Since RTT measurement is done by the CCIDs, there is no easy
* way to get an RTT sample. The fallback RTT from RFC 4340, 3.4
* is too low (200ms); we use a high value to avoid unnecessary
* retransmissions when the link RTT is > 0.2 seconds.
* FIXME: Let main module sample RTTs and use that instead.
*/
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
DCCP_TIMEOUT_INIT, DCCP_RTO_MAX);
} else
dccp_transmit_skb(sk, skb);
}
void dccp_write_xmit(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
while ((skb = dccp_qpolicy_top(sk))) {
int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
switch (ccid_packet_dequeue_eval(rc)) {
case CCID_PACKET_WILL_DEQUEUE_LATER:
return;
case CCID_PACKET_DELAY:
sk_reset_timer(sk, &dp->dccps_xmit_timer,
jiffies + msecs_to_jiffies(rc));
return;
case CCID_PACKET_SEND_AT_ONCE:
dccp_xmit_packet(sk);
break;
case CCID_PACKET_ERR:
dccp_qpolicy_drop(sk, skb);
dccp_pr_debug("packet discarded due to err=%d\n", rc);
}
}
}
static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val)
{
struct dccp_sock *dp = dccp_sk(sk);
u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->ccid2hctx_cwnd, 2);
/*
* Ensure that Ack Ratio does not exceed ceil(cwnd/2), which is (2) from
* RFC 4341, 6.1.2. We ignore the statement that Ack Ratio 2 is always
* acceptable since this causes starvation/deadlock whenever cwnd < 2.
* The same problem arises when Ack Ratio is 0 (ie. Ack Ratio disabled).
*/
if (val == 0 || val > max_ratio) {
DCCP_WARN("Limiting Ack Ratio (%u) to %u\n", val, max_ratio);
val = max_ratio;
}
if (val > DCCPF_ACK_RATIO_MAX)
val = DCCPF_ACK_RATIO_MAX;
if (val == dp->dccps_l_ack_ratio)
return;
ccid2_pr_debug("changing local ack ratio to %u\n", val);
dp->dccps_l_ack_ratio = val;
}
