* published by the Free Software Foundation.
*/
-#include <linux/config.h>
#include <linux/dccp.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/random.h>
#include <net/checksum.h>
-#include <net/inet_common.h>
-#include <net/ip.h>
-#include <net/protocol.h>
+#include <net/inet_sock.h>
#include <net/sock.h>
#include <net/xfrm.h>
-#include <asm/semaphore.h>
+#include <asm/ioctls.h>
#include <linux/spinlock.h>
#include <linux/timer.h>
#include <linux/delay.h>
#include <linux/poll.h>
-#include <linux/dccp.h>
#include "ccid.h"
#include "dccp.h"
+#include "feat.h"
+
+DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;
-DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics);
+EXPORT_SYMBOL_GPL(dccp_statistics);
atomic_t dccp_orphan_count = ATOMIC_INIT(0);
-static struct net_protocol dccp_protocol = {
- .handler = dccp_v4_rcv,
- .err_handler = dccp_v4_err,
+EXPORT_SYMBOL_GPL(dccp_orphan_count);
+
+struct inet_hashinfo __cacheline_aligned dccp_hashinfo = {
+ .lhash_lock = RW_LOCK_UNLOCKED,
+ .lhash_users = ATOMIC_INIT(0),
+ .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait),
};
+EXPORT_SYMBOL_GPL(dccp_hashinfo);
+
+/* the maximum queue length for tx in packets. 0 is no limit */
+int sysctl_dccp_tx_qlen __read_mostly = 5;
+
+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);
+ 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;
+}
+
+EXPORT_SYMBOL_GPL(dccp_set_state);
+
+static void dccp_finish_passive_close(struct sock *sk)
+{
+ switch (sk->sk_state) {
+ case DCCP_PASSIVE_CLOSE:
+ /* Node (client or server) has received Close packet. */
+ dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED);
+ dccp_set_state(sk, DCCP_CLOSED);
+ break;
+ case DCCP_PASSIVE_CLOSEREQ:
+ /*
+ * Client received CloseReq. We set the `active' flag so that
+ * dccp_send_close() retransmits the Close as per RFC 4340, 8.3.
+ */
+ dccp_send_close(sk, 1);
+ dccp_set_state(sk, DCCP_CLOSING);
+ }
+}
+
+void dccp_done(struct sock *sk)
+{
+ dccp_set_state(sk, DCCP_CLOSED);
+ dccp_clear_xmit_timers(sk);
+
+ sk->sk_shutdown = SHUTDOWN_MASK;
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk->sk_state_change(sk);
+ else
+ inet_csk_destroy_sock(sk);
+}
+
+EXPORT_SYMBOL_GPL(dccp_done);
+
const char *dccp_packet_name(const int type)
{
static const char *dccp_packet_names[] = {
const char *dccp_state_name(const int state)
{
static char *dccp_state_names[] = {
- [DCCP_OPEN] = "OPEN",
- [DCCP_REQUESTING] = "REQUESTING",
- [DCCP_PARTOPEN] = "PARTOPEN",
- [DCCP_LISTEN] = "LISTEN",
- [DCCP_RESPOND] = "RESPOND",
- [DCCP_CLOSING] = "CLOSING",
- [DCCP_TIME_WAIT] = "TIME_WAIT",
- [DCCP_CLOSED] = "CLOSED",
+ [DCCP_OPEN] = "OPEN",
+ [DCCP_REQUESTING] = "REQUESTING",
+ [DCCP_PARTOPEN] = "PARTOPEN",
+ [DCCP_LISTEN] = "LISTEN",
+ [DCCP_RESPOND] = "RESPOND",
+ [DCCP_CLOSING] = "CLOSING",
+ [DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ",
+ [DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE",
+ [DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ",
+ [DCCP_TIME_WAIT] = "TIME_WAIT",
+ [DCCP_CLOSED] = "CLOSED",
};
if (state >= DCCP_MAX_STATES)
EXPORT_SYMBOL_GPL(dccp_state_name);
-static inline int dccp_listen_start(struct sock *sk)
+int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
+{
+ struct dccp_sock *dp = dccp_sk(sk);
+ struct dccp_minisock *dmsk = dccp_msk(sk);
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ dccp_minisock_init(&dp->dccps_minisock);
+
+ 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_l_ack_ratio = dp->dccps_r_ack_ratio = 1;
+
+ dccp_init_xmit_timers(sk);
+
+ INIT_LIST_HEAD(&dp->dccps_featneg);
+ /*
+ * FIXME: We're hardcoding the CCID, and doing this at this point makes
+ * the listening (master) sock get CCID control blocks, which is not
+ * necessary, but for now, to not mess with the test userspace apps,
+ * lets leave it here, later the real solution is to do this in a
+ * setsockopt(CCIDs-I-want/accept). -acme
+ */
+ if (likely(ctl_sock_initialized)) {
+ int rc = dccp_feat_init(sk);
+
+ if (rc)
+ return rc;
+
+ if (dmsk->dccpms_send_ack_vector) {
+ dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(GFP_KERNEL);
+ if (dp->dccps_hc_rx_ackvec == NULL)
+ return -ENOMEM;
+ }
+ dp->dccps_hc_rx_ccid = ccid_hc_rx_new(dmsk->dccpms_rx_ccid,
+ sk, GFP_KERNEL);
+ dp->dccps_hc_tx_ccid = ccid_hc_tx_new(dmsk->dccpms_tx_ccid,
+ sk, GFP_KERNEL);
+ if (unlikely(dp->dccps_hc_rx_ccid == NULL ||
+ dp->dccps_hc_tx_ccid == NULL)) {
+ ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
+ ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
+ if (dmsk->dccpms_send_ack_vector) {
+ dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
+ dp->dccps_hc_rx_ackvec = NULL;
+ }
+ dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
+ return -ENOMEM;
+ }
+ } else {
+ /* control socket doesn't need feat nego */
+ INIT_LIST_HEAD(&dmsk->dccpms_pending);
+ INIT_LIST_HEAD(&dmsk->dccpms_conf);
+ }
+
+ return 0;
+}
+
+EXPORT_SYMBOL_GPL(dccp_init_sock);
+
+void dccp_destroy_sock(struct sock *sk)
+{
+ struct dccp_sock *dp = dccp_sk(sk);
+ struct dccp_minisock *dmsk = dccp_msk(sk);
+
+ /*
+ * DCCP doesn't use sk_write_queue, just sk_send_head
+ * for retransmissions
+ */
+ if (sk->sk_send_head != NULL) {
+ kfree_skb(sk->sk_send_head);
+ sk->sk_send_head = NULL;
+ }
+
+ /* Clean up a referenced DCCP bind bucket. */
+ if (inet_csk(sk)->icsk_bind_hash != NULL)
+ inet_put_port(sk);
+
+ kfree(dp->dccps_service_list);
+ dp->dccps_service_list = NULL;
+
+ if (dmsk->dccpms_send_ack_vector) {
+ dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
+ dp->dccps_hc_rx_ackvec = NULL;
+ }
+ ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
+ ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
+ dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
+
+ /* clean up feature negotiation state */
+ dccp_feat_list_purge(&dp->dccps_featneg);
+}
+
+EXPORT_SYMBOL_GPL(dccp_destroy_sock);
+
+static inline int dccp_listen_start(struct sock *sk, int backlog)
+{
+ struct dccp_sock *dp = dccp_sk(sk);
+
+ dp->dccps_role = DCCP_ROLE_LISTEN;
+ /* do not start to listen if feature negotiation setup fails */
+ if (dccp_feat_finalise_settings(dp))
+ return -EPROTO;
+ return inet_csk_listen_start(sk, backlog);
+}
+
+static inline int dccp_need_reset(int state)
{
- dccp_sk(sk)->dccps_role = DCCP_ROLE_LISTEN;
- return inet_csk_listen_start(sk, TCP_SYNQ_HSIZE);
+ return state != DCCP_CLOSED && state != DCCP_LISTEN &&
+ state != DCCP_REQUESTING;
}
int dccp_disconnect(struct sock *sk, int flags)
if (old_state != DCCP_CLOSED)
dccp_set_state(sk, DCCP_CLOSED);
- /* ABORT function of RFC793 */
+ /*
+ * This corresponds to the ABORT function of RFC793, sec. 3.8
+ * TCP uses a RST segment, DCCP a Reset packet with Code 2, "Aborted".
+ */
if (old_state == DCCP_LISTEN) {
inet_csk_listen_stop(sk);
- /* FIXME: do the active reset thing */
+ } else if (dccp_need_reset(old_state)) {
+ dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
+ sk->sk_err = ECONNRESET;
} else if (old_state == DCCP_REQUESTING)
sk->sk_err = ECONNRESET;
dccp_clear_xmit_timers(sk);
+
__skb_queue_purge(&sk->sk_receive_queue);
+ __skb_queue_purge(&sk->sk_write_queue);
if (sk->sk_send_head != NULL) {
__kfree_skb(sk->sk_send_head);
sk->sk_send_head = NULL;
inet_csk_delack_init(sk);
__sk_dst_reset(sk);
- BUG_TRAP(!inet->num || icsk->icsk_bind_hash);
+ WARN_ON(inet->num && !icsk->icsk_bind_hash);
sk->sk_error_report(sk);
return err;
}
+EXPORT_SYMBOL_GPL(dccp_disconnect);
+
+/*
+ * Wait for a DCCP event.
+ *
+ * Note that we don't need to lock the socket, as the upper poll layers
+ * take care of normal races (between the test and the event) and we don't
+ * go look at any of the socket buffers directly.
+ */
+unsigned int dccp_poll(struct file *file, struct socket *sock,
+ poll_table *wait)
+{
+ unsigned int mask;
+ struct sock *sk = sock->sk;
+
+ poll_wait(file, sk->sk_sleep, wait);
+ if (sk->sk_state == DCCP_LISTEN)
+ return inet_csk_listen_poll(sk);
+
+ /* Socket is not locked. We are protected from async events
+ by poll logic and correct handling of state changes
+ made by another threads is impossible in any case.
+ */
+
+ mask = 0;
+ if (sk->sk_err)
+ mask = POLLERR;
+
+ if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED)
+ mask |= POLLHUP;
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ mask |= POLLIN | POLLRDNORM | POLLRDHUP;
+
+ /* Connected? */
+ if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
+ if (atomic_read(&sk->sk_rmem_alloc) > 0)
+ mask |= POLLIN | POLLRDNORM;
+
+ if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
+ if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
+ mask |= POLLOUT | POLLWRNORM;
+ } else { /* send SIGIO later */
+ set_bit(SOCK_ASYNC_NOSPACE,
+ &sk->sk_socket->flags);
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+
+ /* Race breaker. If space is freed after
+ * wspace test but before the flags are set,
+ * IO signal will be lost.
+ */
+ if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
+ mask |= POLLOUT | POLLWRNORM;
+ }
+ }
+ }
+ return mask;
+}
+
+EXPORT_SYMBOL_GPL(dccp_poll);
+
int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
- dccp_pr_debug("entry\n");
- return -ENOIOCTLCMD;
+ int rc = -ENOTCONN;
+
+ lock_sock(sk);
+
+ if (sk->sk_state == DCCP_LISTEN)
+ goto out;
+
+ switch (cmd) {
+ case SIOCINQ: {
+ struct sk_buff *skb;
+ unsigned long amount = 0;
+
+ skb = skb_peek(&sk->sk_receive_queue);
+ if (skb != NULL) {
+ /*
+ * We will only return the amount of this packet since
+ * that is all that will be read.
+ */
+ amount = skb->len;
+ }
+ rc = put_user(amount, (int __user *)arg);
+ }
+ break;
+ default:
+ rc = -ENOIOCTLCMD;
+ break;
+ }
+out:
+ release_sock(sk);
+ return rc;
+}
+
+EXPORT_SYMBOL_GPL(dccp_ioctl);
+
+static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
+ char __user *optval, int optlen)
+{
+ struct dccp_sock *dp = dccp_sk(sk);
+ struct dccp_service_list *sl = NULL;
+
+ if (service == DCCP_SERVICE_INVALID_VALUE ||
+ optlen > DCCP_SERVICE_LIST_MAX_LEN * sizeof(u32))
+ return -EINVAL;
+
+ if (optlen > sizeof(service)) {
+ sl = kmalloc(optlen, GFP_KERNEL);
+ if (sl == NULL)
+ return -ENOMEM;
+
+ sl->dccpsl_nr = optlen / sizeof(u32) - 1;
+ if (copy_from_user(sl->dccpsl_list,
+ optval + sizeof(service),
+ optlen - sizeof(service)) ||
+ dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) {
+ kfree(sl);
+ return -EFAULT;
+ }
+ }
+
+ lock_sock(sk);
+ dp->dccps_service = service;
+
+ kfree(dp->dccps_service_list);
+
+ dp->dccps_service_list = sl;
+ release_sock(sk);
+ return 0;
+}
+
+static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx)
+{
+ u8 *list, len;
+ int i, rc;
+
+ if (cscov < 0 || cscov > 15)
+ return -EINVAL;
+ /*
+ * Populate a list of permissible values, in the range cscov...15. This
+ * is necessary since feature negotiation of single values only works if
+ * both sides incidentally choose the same value. Since the list starts
+ * lowest-value first, negotiation will pick the smallest shared value.
+ */
+ if (cscov == 0)
+ return 0;
+ len = 16 - cscov;
+
+ list = kmalloc(len, GFP_KERNEL);
+ if (list == NULL)
+ return -ENOBUFS;
+
+ for (i = 0; i < len; i++)
+ list[i] = cscov++;
+
+ rc = dccp_feat_register_sp(sk, DCCPF_MIN_CSUM_COVER, rx, list, len);
+
+ if (rc == 0) {
+ if (rx)
+ dccp_sk(sk)->dccps_pcrlen = cscov;
+ else
+ dccp_sk(sk)->dccps_pcslen = cscov;
+ }
+ kfree(list);
+ return rc;
+}
+
+static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int optlen)
+{
+ struct dccp_sock *dp = dccp_sk(sk);
+ int val, err = 0;
+
+ 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);
+ switch (optname) {
+ case DCCP_SOCKOPT_PACKET_SIZE:
+ DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
+ err = 0;
+ break;
+ case DCCP_SOCKOPT_CHANGE_L:
+ case DCCP_SOCKOPT_CHANGE_R:
+ DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n");
+ err = 0;
+ break;
+ case DCCP_SOCKOPT_SERVER_TIMEWAIT:
+ if (dp->dccps_role != DCCP_ROLE_SERVER)
+ err = -EOPNOTSUPP;
+ else
+ dp->dccps_server_timewait = (val != 0);
+ break;
+ case DCCP_SOCKOPT_SEND_CSCOV:
+ err = dccp_setsockopt_cscov(sk, val, false);
+ break;
+ case DCCP_SOCKOPT_RECV_CSCOV:
+ err = dccp_setsockopt_cscov(sk, val, true);
+ break;
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ release_sock(sk);
+ return err;
}
int dccp_setsockopt(struct sock *sk, int level, int optname,
- char *optval, int optlen)
+ char __user *optval, int optlen)
{
- dccp_pr_debug("entry\n");
+ if (level != SOL_DCCP)
+ return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level,
+ optname, optval,
+ optlen);
+ return do_dccp_setsockopt(sk, level, optname, optval, optlen);
+}
+EXPORT_SYMBOL_GPL(dccp_setsockopt);
+
+#ifdef CONFIG_COMPAT
+int compat_dccp_setsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int optlen)
+{
if (level != SOL_DCCP)
- return ip_setsockopt(sk, level, optname, optval, optlen);
+ return inet_csk_compat_setsockopt(sk, level, optname,
+ optval, optlen);
+ return do_dccp_setsockopt(sk, level, optname, optval, optlen);
+}
+
+EXPORT_SYMBOL_GPL(compat_dccp_setsockopt);
+#endif
- return -EOPNOTSUPP;
+static int dccp_getsockopt_service(struct sock *sk, int len,
+ __be32 __user *optval,
+ int __user *optlen)
+{
+ const struct dccp_sock *dp = dccp_sk(sk);
+ const struct dccp_service_list *sl;
+ int err = -ENOENT, slen = 0, total_len = sizeof(u32);
+
+ lock_sock(sk);
+ if ((sl = dp->dccps_service_list) != NULL) {
+ slen = sl->dccpsl_nr * sizeof(u32);
+ total_len += slen;
+ }
+
+ err = -EINVAL;
+ if (total_len > len)
+ goto out;
+
+ err = 0;
+ if (put_user(total_len, optlen) ||
+ put_user(dp->dccps_service, optval) ||
+ (sl != NULL && copy_to_user(optval + 1, sl->dccpsl_list, slen)))
+ err = -EFAULT;
+out:
+ release_sock(sk);
+ return err;
}
-int dccp_getsockopt(struct sock *sk, int level, int optname,
- char *optval, int *optlen)
+static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int __user *optlen)
{
- dccp_pr_debug("entry\n");
+ 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;
+ break;
+ case DCCP_SOCKOPT_AVAILABLE_CCIDS:
+ return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen);
+ case DCCP_SOCKOPT_SERVER_TIMEWAIT:
+ val = dp->dccps_server_timewait;
+ break;
+ case DCCP_SOCKOPT_SEND_CSCOV:
+ val = dp->dccps_pcslen;
+ break;
+ case DCCP_SOCKOPT_RECV_CSCOV:
+ val = dp->dccps_pcrlen;
+ 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;
+ }
+
+ len = sizeof(val);
+ if (put_user(len, optlen) || copy_to_user(optval, &val, len))
+ return -EFAULT;
+ return 0;
+}
+
+int dccp_getsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
if (level != SOL_DCCP)
- return ip_getsockopt(sk, level, optname, optval, optlen);
+ return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level,
+ optname, optval,
+ optlen);
+ return do_dccp_getsockopt(sk, level, optname, optval, optlen);
+}
+
+EXPORT_SYMBOL_GPL(dccp_getsockopt);
- return -EOPNOTSUPP;
+#ifdef CONFIG_COMPAT
+int compat_dccp_getsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ if (level != SOL_DCCP)
+ return inet_csk_compat_getsockopt(sk, level, optname,
+ optval, optlen);
+ return do_dccp_getsockopt(sk, level, optname, optval, optlen);
}
+EXPORT_SYMBOL_GPL(compat_dccp_getsockopt);
+#endif
+
int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
{
return -EMSGSIZE;
lock_sock(sk);
+
+ if (sysctl_dccp_tx_qlen &&
+ (sk->sk_write_queue.qlen >= sysctl_dccp_tx_qlen)) {
+ rc = -EAGAIN;
+ goto out_release;
+ }
+
timeo = sock_sndtimeo(sk, noblock);
/*
* so that the trick in dccp_rcv_request_sent_state_process.
*/
/* Wait for a connection to finish. */
- if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN | DCCPF_CLOSING))
+ if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN))
if ((rc = sk_stream_wait_connect(sk, &timeo)) != 0)
goto out_release;
if (rc != 0)
goto out_discard;
- rc = dccp_write_xmit(sk, skb, len);
+ skb_queue_tail(&sk->sk_write_queue, skb);
+ dccp_write_xmit(sk,0);
out_release:
release_sock(sk);
return rc ? : len;
goto out_release;
}
+EXPORT_SYMBOL_GPL(dccp_sendmsg);
+
int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len, int nonblock, int flags, int *addr_len)
{
dh = dccp_hdr(skb);
- if (dh->dccph_type == DCCP_PKT_DATA ||
- dh->dccph_type == DCCP_PKT_DATAACK)
+ switch (dh->dccph_type) {
+ case DCCP_PKT_DATA:
+ case DCCP_PKT_DATAACK:
goto found_ok_skb;
- if (dh->dccph_type == DCCP_PKT_RESET ||
- dh->dccph_type == DCCP_PKT_CLOSE) {
- dccp_pr_debug("found fin ok!\n");
+ case DCCP_PKT_CLOSE:
+ case DCCP_PKT_CLOSEREQ:
+ if (!(flags & MSG_PEEK))
+ dccp_finish_passive_close(sk);
+ /* fall through */
+ case DCCP_PKT_RESET:
+ dccp_pr_debug("found fin (%s) ok!\n",
+ dccp_packet_name(dh->dccph_type));
len = 0;
goto found_fin_ok;
+ default:
+ dccp_pr_debug("packet_type=%s\n",
+ dccp_packet_name(dh->dccph_type));
+ sk_eat_skb(sk, skb, 0);
}
- dccp_pr_debug("packet_type=%s\n",
- dccp_packet_name(dh->dccph_type));
- sk_eat_skb(sk, skb);
verify_sock_status:
if (sock_flag(sk, SOCK_DONE)) {
len = 0;
}
found_fin_ok:
if (!(flags & MSG_PEEK))
- sk_eat_skb(sk, skb);
+ sk_eat_skb(sk, skb, 0);
break;
} while (1);
out:
return len;
}
-static int inet_dccp_listen(struct socket *sock, int backlog)
+EXPORT_SYMBOL_GPL(dccp_recvmsg);
+
+int inet_dccp_listen(struct socket *sock, int backlog)
{
struct sock *sk = sock->sk;
unsigned char old_state;
* FIXME: here it probably should be sk->sk_prot->listen_start
* see tcp_listen_start
*/
- err = dccp_listen_start(sk);
+ err = dccp_listen_start(sk, backlog);
if (err)
goto out;
}
return err;
}
-static const unsigned char dccp_new_state[] = {
- /* current state: new state: action: */
- [0] = DCCP_CLOSED,
- [DCCP_OPEN] = DCCP_CLOSING | DCCP_ACTION_FIN,
- [DCCP_REQUESTING] = DCCP_CLOSED,
- [DCCP_PARTOPEN] = DCCP_CLOSING | DCCP_ACTION_FIN,
- [DCCP_LISTEN] = DCCP_CLOSED,
- [DCCP_RESPOND] = DCCP_CLOSED,
- [DCCP_CLOSING] = DCCP_CLOSED,
- [DCCP_TIME_WAIT] = DCCP_CLOSED,
- [DCCP_CLOSED] = DCCP_CLOSED,
-};
+EXPORT_SYMBOL_GPL(inet_dccp_listen);
-static int dccp_close_state(struct sock *sk)
+static void dccp_terminate_connection(struct sock *sk)
{
- const int next = dccp_new_state[sk->sk_state];
- const int ns = next & DCCP_STATE_MASK;
-
- if (ns != sk->sk_state)
- dccp_set_state(sk, ns);
+ u8 next_state = DCCP_CLOSED;
- return next & DCCP_ACTION_FIN;
+ switch (sk->sk_state) {
+ case DCCP_PASSIVE_CLOSE:
+ case DCCP_PASSIVE_CLOSEREQ:
+ dccp_finish_passive_close(sk);
+ break;
+ case DCCP_PARTOPEN:
+ dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk);
+ inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
+ /* fall through */
+ case DCCP_OPEN:
+ dccp_send_close(sk, 1);
+
+ if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER &&
+ !dccp_sk(sk)->dccps_server_timewait)
+ next_state = DCCP_ACTIVE_CLOSEREQ;
+ else
+ next_state = DCCP_CLOSING;
+ /* fall through */
+ default:
+ dccp_set_state(sk, next_state);
+ }
}
void dccp_close(struct sock *sk, long timeout)
{
+ struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
+ u32 data_was_unread = 0;
+ int state;
lock_sock(sk);
goto adjudge_to_death;
}
+ sk_stop_timer(sk, &dp->dccps_xmit_timer);
+
/*
* We need to flush the recv. buffs. We do this only on the
* descriptor close, not protocol-sourced closes, because the
*reader process may not have drained the data yet!
*/
- /* FIXME: check for unread data */
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
+ data_was_unread += skb->len;
__kfree_skb(skb);
}
- if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
+ if (data_was_unread) {
+ /* Unread data was tossed, send an appropriate Reset Code */
+ DCCP_WARN("DCCP: ABORT -- %u bytes unread\n", data_was_unread);
+ dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
+ dccp_set_state(sk, DCCP_CLOSED);
+ } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
- } else if (dccp_close_state(sk)) {
- dccp_send_close(sk);
+ } else if (sk->sk_state != DCCP_CLOSED) {
+ dccp_terminate_connection(sk);
}
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
+ state = sk->sk_state;
+ sock_hold(sk);
+ sock_orphan(sk);
+ atomic_inc(sk->sk_prot->orphan_count);
+
+ /*
+ * It is the last release_sock in its life. It will remove backlog.
+ */
release_sock(sk);
/*
* Now socket is owned by kernel and we acquire BH lock
*/
local_bh_disable();
bh_lock_sock(sk);
- BUG_TRAP(!sock_owned_by_user(sk));
+ WARN_ON(sock_owned_by_user(sk));
- sock_hold(sk);
- sock_orphan(sk);
-
- if (sk->sk_state != DCCP_CLOSED)
- dccp_set_state(sk, DCCP_CLOSED);
+ /* Have we already been destroyed by a softirq or backlog? */
+ if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
+ goto out;
- atomic_inc(&dccp_orphan_count);
if (sk->sk_state == DCCP_CLOSED)
inet_csk_destroy_sock(sk);
/* Otherwise, socket is reprieved until protocol close. */
+out:
bh_unlock_sock(sk);
local_bh_enable();
sock_put(sk);
}
+EXPORT_SYMBOL_GPL(dccp_close);
+
void dccp_shutdown(struct sock *sk, int how)
{
- dccp_pr_debug("entry\n");
+ dccp_pr_debug("called shutdown(%x)\n", how);
}
-struct proto_ops inet_dccp_ops = {
- .family = PF_INET,
- .owner = THIS_MODULE,
- .release = inet_release,
- .bind = inet_bind,
- .connect = inet_stream_connect,
- .socketpair = sock_no_socketpair,
- .accept = inet_accept,
- .getname = inet_getname,
- .poll = sock_no_poll,
- .ioctl = inet_ioctl,
- /* FIXME: work on inet_listen to rename it to sock_common_listen */
- .listen = inet_dccp_listen,
- .shutdown = inet_shutdown,
- .setsockopt = sock_common_setsockopt,
- .getsockopt = sock_common_getsockopt,
- .sendmsg = inet_sendmsg,
- .recvmsg = sock_common_recvmsg,
- .mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
-};
-
-extern struct net_proto_family inet_family_ops;
+EXPORT_SYMBOL_GPL(dccp_shutdown);
-static struct inet_protosw dccp_v4_protosw = {
- .type = SOCK_DCCP,
- .protocol = IPPROTO_DCCP,
- .prot = &dccp_v4_prot,
- .ops = &inet_dccp_ops,
- .capability = -1,
- .no_check = 0,
- .flags = 0,
-};
-
-/*
- * This is the global socket data structure used for responding to
- * the Out-of-the-blue (OOTB) packets. A control sock will be created
- * for this socket at the initialization time.
- */
-struct socket *dccp_ctl_socket;
-
-static char dccp_ctl_socket_err_msg[] __initdata =
- KERN_ERR "DCCP: Failed to create the control socket.\n";
-
-static int __init dccp_ctl_sock_init(void)
+static inline int dccp_mib_init(void)
{
- int rc = sock_create_kern(PF_INET, SOCK_DCCP, IPPROTO_DCCP,
- &dccp_ctl_socket);
- if (rc < 0)
- printk(dccp_ctl_socket_err_msg);
- else {
- dccp_ctl_socket->sk->sk_allocation = GFP_ATOMIC;
- inet_sk(dccp_ctl_socket->sk)->uc_ttl = -1;
-
- /* Unhash it so that IP input processing does not even
- * see it, we do not wish this socket to see incoming
- * packets.
- */
- dccp_ctl_socket->sk->sk_prot->unhash(dccp_ctl_socket->sk);
- }
-
- return rc;
+ return snmp_mib_init((void**)dccp_statistics, sizeof(struct dccp_mib));
}
-static void __exit dccp_ctl_sock_exit(void)
+static inline void dccp_mib_exit(void)
{
- if (dccp_ctl_socket != NULL)
- sock_release(dccp_ctl_socket);
-}
-
-static int __init init_dccp_v4_mibs(void)
-{
- int rc = -ENOMEM;
-
- dccp_statistics[0] = alloc_percpu(struct dccp_mib);
- if (dccp_statistics[0] == NULL)
- goto out;
-
- dccp_statistics[1] = alloc_percpu(struct dccp_mib);
- if (dccp_statistics[1] == NULL)
- goto out_free_one;
-
- rc = 0;
-out:
- return rc;
-out_free_one:
- free_percpu(dccp_statistics[0]);
- dccp_statistics[0] = NULL;
- goto out;
-
+ snmp_mib_free((void**)dccp_statistics);
}
static int thash_entries;
module_param(thash_entries, int, 0444);
MODULE_PARM_DESC(thash_entries, "Number of ehash buckets");
+#ifdef CONFIG_IP_DCCP_DEBUG
int dccp_debug;
-module_param(dccp_debug, int, 0444);
+module_param(dccp_debug, bool, 0644);
MODULE_PARM_DESC(dccp_debug, "Enable debug messages");
+EXPORT_SYMBOL_GPL(dccp_debug);
+#endif
+
static int __init dccp_init(void)
{
unsigned long goal;
int ehash_order, bhash_order, i;
- int rc = proto_register(&dccp_v4_prot, 1);
+ int rc = -ENOBUFS;
- if (rc)
- goto out;
+ BUILD_BUG_ON(sizeof(struct dccp_skb_cb) >
+ FIELD_SIZEOF(struct sk_buff, cb));
dccp_hashinfo.bind_bucket_cachep =
kmem_cache_create("dccp_bind_bucket",
sizeof(struct inet_bind_bucket), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
+ SLAB_HWCACHE_ALIGN, NULL);
if (!dccp_hashinfo.bind_bucket_cachep)
- goto out_proto_unregister;
+ goto out;
/*
* Size and allocate the main established and bind bucket
do {
dccp_hashinfo.ehash_size = (1UL << ehash_order) * PAGE_SIZE /
sizeof(struct inet_ehash_bucket);
- dccp_hashinfo.ehash_size >>= 1;
while (dccp_hashinfo.ehash_size &
(dccp_hashinfo.ehash_size - 1))
dccp_hashinfo.ehash_size--;
} while (!dccp_hashinfo.ehash && --ehash_order > 0);
if (!dccp_hashinfo.ehash) {
- printk(KERN_CRIT "Failed to allocate DCCP "
- "established hash table\n");
+ DCCP_CRIT("Failed to allocate DCCP established hash table");
goto out_free_bind_bucket_cachep;
}
- for (i = 0; i < (dccp_hashinfo.ehash_size << 1); i++) {
- rwlock_init(&dccp_hashinfo.ehash[i].lock);
+ for (i = 0; i < dccp_hashinfo.ehash_size; i++) {
INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].chain);
+ INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].twchain);
}
+ if (inet_ehash_locks_alloc(&dccp_hashinfo))
+ goto out_free_dccp_ehash;
+
bhash_order = ehash_order;
do {
} while (!dccp_hashinfo.bhash && --bhash_order >= 0);
if (!dccp_hashinfo.bhash) {
- printk(KERN_CRIT "Failed to allocate DCCP bind hash table\n");
- goto out_free_dccp_ehash;
+ DCCP_CRIT("Failed to allocate DCCP bind hash table");
+ goto out_free_dccp_locks;
}
for (i = 0; i < dccp_hashinfo.bhash_size; i++) {
INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain);
}
- if (init_dccp_v4_mibs())
+ rc = dccp_mib_init();
+ if (rc)
goto out_free_dccp_bhash;
- rc = -EAGAIN;
- if (inet_add_protocol(&dccp_protocol, IPPROTO_DCCP))
- goto out_free_dccp_v4_mibs;
-
- inet_register_protosw(&dccp_v4_protosw);
+ rc = dccp_ackvec_init();
+ if (rc)
+ goto out_free_dccp_mib;
- rc = dccp_ctl_sock_init();
+ rc = dccp_sysctl_init();
if (rc)
- goto out_unregister_protosw;
+ goto out_ackvec_exit;
+
+ dccp_timestamping_init();
out:
return rc;
-out_unregister_protosw:
- inet_unregister_protosw(&dccp_v4_protosw);
- inet_del_protocol(&dccp_protocol, IPPROTO_DCCP);
-out_free_dccp_v4_mibs:
- free_percpu(dccp_statistics[0]);
- free_percpu(dccp_statistics[1]);
- dccp_statistics[0] = dccp_statistics[1] = NULL;
+out_ackvec_exit:
+ dccp_ackvec_exit();
+out_free_dccp_mib:
+ dccp_mib_exit();
out_free_dccp_bhash:
free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
dccp_hashinfo.bhash = NULL;
+out_free_dccp_locks:
+ inet_ehash_locks_free(&dccp_hashinfo);
out_free_dccp_ehash:
free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
dccp_hashinfo.ehash = NULL;
out_free_bind_bucket_cachep:
kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
dccp_hashinfo.bind_bucket_cachep = NULL;
-out_proto_unregister:
- proto_unregister(&dccp_v4_prot);
goto out;
}
-static const char dccp_del_proto_err_msg[] __exitdata =
- KERN_ERR "can't remove dccp net_protocol\n";
-
static void __exit dccp_fini(void)
{
- dccp_ctl_sock_exit();
-
- inet_unregister_protosw(&dccp_v4_protosw);
-
- if (inet_del_protocol(&dccp_protocol, IPPROTO_DCCP) < 0)
- printk(dccp_del_proto_err_msg);
-
- /* Free the control endpoint. */
- sock_release(dccp_ctl_socket);
-
- proto_unregister(&dccp_v4_prot);
-
+ dccp_mib_exit();
+ free_pages((unsigned long)dccp_hashinfo.bhash,
+ get_order(dccp_hashinfo.bhash_size *
+ sizeof(struct inet_bind_hashbucket)));
+ free_pages((unsigned long)dccp_hashinfo.ehash,
+ get_order(dccp_hashinfo.ehash_size *
+ sizeof(struct inet_ehash_bucket)));
+ inet_ehash_locks_free(&dccp_hashinfo);
kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
+ dccp_ackvec_exit();
+ dccp_sysctl_exit();
}
module_init(dccp_init);
module_exit(dccp_fini);
-/*
- * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33)
- * values directly, Also cover the case where the protocol is not specified,
- * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP
- */
-MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-33-type-6");
-MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-0-type-6");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@conectiva.com.br>");
MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff