Merge branch 'dccp' of git://eden-feed.erg.abdn.ac.uk/dccp_exp

Conflicts:

	net/dccp/input.c
	net/dccp/options.c

1 files changed, 175 insertions, 106 deletions

diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index d0bd34819761..ecf3be961e11 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -67,6 +67,9 @@ void dccp_set_state(struct sock *sk, const int 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:
@@ -175,63 +178,25 @@ EXPORT_SYMBOL_GPL(dccp_state_name);
 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_mss_cache     = TCP_MIN_RCVMSS;
         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;
+        dp->dccps_tx_qlen       = sysctl_dccp_tx_qlen;
 
         dccp_init_xmit_timers(sk);
 
-        /*
-         * 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(dmsk);
-
-                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);
-        }
-
+        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;
 }
 
@@ -240,7 +205,6 @@ 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
@@ -258,7 +222,7 @@ void dccp_destroy_sock(struct sock *sk)
         kfree(dp->dccps_service_list);
         dp->dccps_service_list = NULL;
 
-        if (dmsk->dccpms_send_ack_vector) {
+        if (dp->dccps_hc_rx_ackvec != NULL) {
                 dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
                 dp->dccps_hc_rx_ackvec = NULL;
         }
@@ -267,7 +231,7 @@ void dccp_destroy_sock(struct sock *sk)
         dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
 
         /* clean up feature negotiation state */
-        dccp_feat_clean(dmsk);
+        dccp_feat_list_purge(&dp->dccps_featneg);
 }
 
 EXPORT_SYMBOL_GPL(dccp_destroy_sock);
@@ -277,6 +241,9 @@ 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);
 }
 
@@ -466,42 +433,70 @@ static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
         return 0;
 }
 
-/* byte 1 is feature.  the rest is the preference list */
-static int dccp_setsockopt_change(struct sock *sk, int type,
-                                  struct dccp_so_feat __user *optval)
+static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx)
 {
-        struct dccp_so_feat opt;
-        u8 *val;
-        int rc;
+        u8 *list, len;
+        int i, rc;
 
-        if (copy_from_user(&opt, optval, sizeof(opt)))
-                return -EFAULT;
+        if (cscov < 0 || cscov > 15)
+                return -EINVAL;
         /*
-         * rfc4340: 6.1. Change Options
+         * 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 (opt.dccpsf_len < 1)
+        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 dccp_setsockopt_ccid(struct sock *sk, int type,
+                                char __user *optval, int optlen)
+{
+        u8 *val;
+        int rc = 0;
+
+        if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS)
                 return -EINVAL;
 
-        val = kmalloc(opt.dccpsf_len, GFP_KERNEL);
-        if (!val)
+        val = kmalloc(optlen, GFP_KERNEL);
+        if (val == NULL)
                 return -ENOMEM;
 
-        if (copy_from_user(val, opt.dccpsf_val, opt.dccpsf_len)) {
-                rc = -EFAULT;
-                goto out_free_val;
+        if (copy_from_user(val, optval, optlen)) {
+                kfree(val);
+                return -EFAULT;
         }
 
-        rc = dccp_feat_change(dccp_msk(sk), type, opt.dccpsf_feat,
-                              val, opt.dccpsf_len, GFP_KERNEL);
-        if (rc)
-                goto out_free_val;
+        lock_sock(sk);
+        if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID)
+                rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen);
 
-out:
-        return rc;
+        if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID))
+                rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen);
+        release_sock(sk);
 
-out_free_val:
         kfree(val);
-        goto out;
+        return rc;
 }
 
 static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
@@ -510,7 +505,21 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
         struct dccp_sock *dp = dccp_sk(sk);
         int val, err = 0;
 
-        if (optlen < sizeof(int))
+        switch (optname) {
+        case DCCP_SOCKOPT_PACKET_SIZE:
+                DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
+                return 0;
+        case DCCP_SOCKOPT_CHANGE_L:
+        case DCCP_SOCKOPT_CHANGE_R:
+                DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n");
+                return 0;
+        case DCCP_SOCKOPT_CCID:
+        case DCCP_SOCKOPT_RX_CCID:
+        case DCCP_SOCKOPT_TX_CCID:
+                return dccp_setsockopt_ccid(sk, optname, optval, optlen);
+        }
+
+        if (optlen < (int)sizeof(int))
                 return -EINVAL;
 
         if (get_user(val, (int __user *)optval))
@@ -521,53 +530,38 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
 
         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:
-                if (optlen != sizeof(struct dccp_so_feat))
-                        err = -EINVAL;
-                else
-                        err = dccp_setsockopt_change(sk, DCCPO_CHANGE_L,
-                                                     (struct dccp_so_feat __user *)
-                                                     optval);
-                break;
-        case DCCP_SOCKOPT_CHANGE_R:
-                if (optlen != sizeof(struct dccp_so_feat))
-                        err = -EINVAL;
-                else
-                        err = dccp_setsockopt_change(sk, DCCPO_CHANGE_R,
-                                                     (struct dccp_so_feat __user *)
-                                                     optval);
-                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:   /* sender side, RFC 4340, sec. 9.2 */
-                if (val < 0 || val > 15)
+        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;
+        case DCCP_SOCKOPT_QPOLICY_ID:
+                if (sk->sk_state != DCCP_CLOSED)
+                        err = -EISCONN;
+                else if (val < 0 || val >= DCCPQ_POLICY_MAX)
                         err = -EINVAL;
                 else
-                        dp->dccps_pcslen = val;
+                        dp->dccps_qpolicy = val;
                 break;
-        case DCCP_SOCKOPT_RECV_CSCOV:   /* receiver side, RFC 4340 sec. 9.2.1 */
-                if (val < 0 || val > 15)
+        case DCCP_SOCKOPT_QPOLICY_TXQLEN:
+                if (val < 0)
                         err = -EINVAL;
-                else {
-                        dp->dccps_pcrlen = val;
-                        /* FIXME: add feature negotiation,
-                         * ChangeL(MinimumChecksumCoverage, val) */
-                }
+                else
+                        dp->dccps_tx_qlen = val;
                 break;
         default:
                 err = -ENOPROTOOPT;
                 break;
         }
-
         release_sock(sk);
+
         return err;
 }
 
@@ -648,6 +642,18 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
         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_TX_CCID:
+                val = ccid_get_current_tx_ccid(dp);
+                if (val < 0)
+                        return -ENOPROTOOPT;
+                break;
+        case DCCP_SOCKOPT_RX_CCID:
+                val = ccid_get_current_rx_ccid(dp);
+                if (val < 0)
+                        return -ENOPROTOOPT;
+                break;
         case DCCP_SOCKOPT_SERVER_TIMEWAIT:
                 val = dp->dccps_server_timewait;
                 break;
@@ -657,6 +663,12 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
         case DCCP_SOCKOPT_RECV_CSCOV:
                 val = dp->dccps_pcrlen;
                 break;
+        case DCCP_SOCKOPT_QPOLICY_ID:
+                val = dp->dccps_qpolicy;
+                break;
+        case DCCP_SOCKOPT_QPOLICY_TXQLEN:
+                val = dp->dccps_tx_qlen;
+                break;
         case 128 ... 191:
                 return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname,
                                              len, (u32 __user *)optval, optlen);
@@ -699,6 +711,47 @@ int compat_dccp_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL_GPL(compat_dccp_getsockopt);
 #endif
 
+static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb)
+{
+        struct cmsghdr *cmsg = CMSG_FIRSTHDR(msg);
+
+        /*
+         * Assign an (opaque) qpolicy priority value to skb->priority.
+         *
+         * We are overloading this skb field for use with the qpolicy subystem.
+         * The skb->priority is normally used for the SO_PRIORITY option, which
+         * is initialised from sk_priority. Since the assignment of sk_priority
+         * to skb->priority happens later (on layer 3), we overload this field
+         * for use with queueing priorities as long as the skb is on layer 4.
+         * The default priority value (if nothing is set) is 0.
+         */
+        skb->priority = 0;
+
+        for (; cmsg != NULL; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+
+                if (!CMSG_OK(msg, cmsg))
+                        return -EINVAL;
+
+                if (cmsg->cmsg_level != SOL_DCCP)
+                        continue;
+
+                if (cmsg->cmsg_type <= DCCP_SCM_QPOLICY_MAX &&
+                    !dccp_qpolicy_param_ok(skb->sk, cmsg->cmsg_type))
+                        return -EINVAL;
+
+                switch (cmsg->cmsg_type) {
+                case DCCP_SCM_PRIORITY:
+                        if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32)))
+                                return -EINVAL;
+                        skb->priority = *(__u32 *)CMSG_DATA(cmsg);
+                        break;
+                default:
+                        return -EINVAL;
+                }
+        }
+        return 0;
+}
+
 int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                  size_t len)
 {
@@ -714,8 +767,7 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
         lock_sock(sk);
 
-        if (sysctl_dccp_tx_qlen &&
-            (sk->sk_write_queue.qlen >= sysctl_dccp_tx_qlen)) {
+        if (dccp_qpolicy_full(sk)) {
                 rc = -EAGAIN;
                 goto out_release;
         }
@@ -743,8 +795,12 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
         if (rc != 0)
                 goto out_discard;
 
-        skb_queue_tail(&sk->sk_write_queue, skb);
-        dccp_write_xmit(sk,0);
+        rc = dccp_msghdr_parse(msg, skb);
+        if (rc != 0)
+                goto out_discard;
+
+        dccp_qpolicy_push(sk, skb);
+        dccp_write_xmit(sk);
 out_release:
         release_sock(sk);
         return rc ? : len;
@@ -967,9 +1023,22 @@ void dccp_close(struct sock *sk, long timeout)
                 /* Check zero linger _after_ checking for unread data. */
                 sk->sk_prot->disconnect(sk, 0);
         } else if (sk->sk_state != DCCP_CLOSED) {
+                /*
+                 * Normal connection termination. May need to wait if there are
+                 * still packets in the TX queue that are delayed by the CCID.
+                 */
+                dccp_flush_write_queue(sk, &timeout);
                 dccp_terminate_connection(sk);
         }
 
+        /*
+         * Flush write queue. This may be necessary in several cases:
+         * - we have been closed by the peer but still have application data;
+         * - abortive termination (unread data or zero linger time),
+         * - normal termination but queue could not be flushed within time limit
+         */
+        __skb_queue_purge(&sk->sk_write_queue);
+
         sk_stream_wait_close(sk, timeout);
 
 adjudge_to_death: