Merge branch 'mpi-master' into wip-k-fmlpwip-k-fmlp

Conflicts:
	litmus/sched_cedf.c

1 files changed, 149 insertions, 102 deletions

diff --git a/net/dccp/output.c b/net/dccp/output.c
index aadbdb58758b..fab108e51e5a 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -43,7 +43,7 @@ static void dccp_skb_entail(struct sock *sk, struct sk_buff *skb)
 static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 {
         if (likely(skb != NULL)) {
-                const struct inet_sock *inet = inet_sk(sk);
+                struct inet_sock *inet = inet_sk(sk);
                 const struct inet_connection_sock *icsk = inet_csk(sk);
                 struct dccp_sock *dp = dccp_sk(sk);
                 struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
@@ -136,14 +136,14 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 
                 DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
 
-                err = icsk->icsk_af_ops->queue_xmit(skb);
+                err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl);
                 return net_xmit_eval(err);
         }
         return -ENOBUFS;
 }
 
 /**
- * dccp_determine_ccmps  -  Find out about CCID-specfic packet-size limits
+ * dccp_determine_ccmps  -  Find out about CCID-specific packet-size limits
  * We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.),
  * since the RX CCID is restricted to feedback packets (Acks), which are small
  * in comparison with the data traffic. A value of 0 means "no current CCMPS".
@@ -209,108 +209,158 @@ void dccp_write_space(struct sock *sk)
 }
 
 /**
- * dccp_wait_for_ccid - Wait for ccid to tell us we can send a packet
+ * dccp_wait_for_ccid  -  Await CCID send permission
  * @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
+ * @delay: timeout in jiffies
+ * This is used by CCIDs which need to delay the send time in process context.
  */
-static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay)
+static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay)
 {
-        struct dccp_sock *dp = dccp_sk(sk);
         DEFINE_WAIT(wait);
-        unsigned long jiffdelay;
-        int rc;
+        long remaining;
 
-        do {
-                dccp_pr_debug("delayed send by %d msec\n", delay);
-                jiffdelay = msecs_to_jiffies(delay);
+        prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+        sk->sk_write_pending++;
+        release_sock(sk);
 
-                prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+        remaining = schedule_timeout(delay);
 
-                sk->sk_write_pending++;
-                release_sock(sk);
-                schedule_timeout(jiffdelay);
-                lock_sock(sk);
-                sk->sk_write_pending--;
+        lock_sock(sk);
+        sk->sk_write_pending--;
+        finish_wait(sk_sleep(sk), &wait);
 
-                if (sk->sk_err)
-                        goto do_error;
-                if (signal_pending(current))
-                        goto do_interrupted;
+        if (signal_pending(current) || sk->sk_err)
+                return -1;
+        return remaining;
+}
 
-                rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
-        } while ((delay = rc) > 0);
-out:
-        finish_wait(sk_sleep(sk), &wait);
-        return rc;
-
-do_error:
-        rc = -EPIPE;
-        goto out;
-do_interrupted:
-        rc = -EINTR;
-        goto out;
+/**
+ * dccp_xmit_packet  -  Send data packet under control of CCID
+ * Transmits next-queued payload and informs CCID to account for the packet.
+ */
+static void dccp_xmit_packet(struct sock *sk)
+{
+        int err, len;
+        struct dccp_sock *dp = dccp_sk(sk);
+        struct sk_buff *skb = dccp_qpolicy_pop(sk);
+
+        if (unlikely(skb == NULL))
+                return;
+        len = skb->len;
+
+        if (sk->sk_state == DCCP_PARTOPEN) {
+                const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD;
+                /*
+                 * See 8.1.5 - Handshake Completion.
+                 *
+                 * For robustness we resend Confirm options until the client has
+                 * entered OPEN. During the initial feature negotiation, the MPS
+                 * is smaller than usual, reduced by the Change/Confirm options.
+                 */
+                if (!list_empty(&dp->dccps_featneg) && len > cur_mps) {
+                        DCCP_WARN("Payload too large (%d) for featneg.\n", len);
+                        dccp_send_ack(sk);
+                        dccp_feat_list_purge(&dp->dccps_featneg);
+                }
+
+                inet_csk_schedule_ack(sk);
+                inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
+                                              inet_csk(sk)->icsk_rto,
+                                              DCCP_RTO_MAX);
+                DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK;
+        } else if (dccp_ack_pending(sk)) {
+                DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK;
+        } else {
+                DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATA;
+        }
+
+        err = dccp_transmit_skb(sk, skb);
+        if (err)
+                dccp_pr_debug("transmit_skb() returned err=%d\n", err);
+        /*
+         * Register this one as sent even if an error occurred. To the remote
+         * end a local packet drop is indistinguishable from network loss, i.e.
+         * any local drop will eventually be reported via receiver feedback.
+         */
+        ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len);
+
+        /*
+         * If the CCID needs to transfer additional header options out-of-band
+         * (e.g. Ack Vectors or feature-negotiation options), it activates this
+         * flag to schedule a Sync. The Sync will automatically incorporate all
+         * currently pending header options, thus clearing the backlog.
+         */
+        if (dp->dccps_sync_scheduled)
+                dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
 }
 
-void dccp_write_xmit(struct sock *sk, int block)
+/**
+ * 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 ((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);
-                }
+        while (*time_budget > 0 && (skb = skb_peek(&sk->sk_write_queue))) {
+                rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
 
-                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) {
-                                const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD;
-                                /*
-                                 * See 8.1.5 - Handshake Completion.
-                                 *
-                                 * For robustness we resend Confirm options until the client has
-                                 * entered OPEN. During the initial feature negotiation, the MPS
-                                 * is smaller than usual, reduced by the Change/Confirm options.
-                                 */
-                                if (!list_empty(&dp->dccps_featneg) && len > cur_mps) {
-                                        DCCP_WARN("Payload too large (%d) for featneg.\n", len);
-                                        dccp_send_ack(sk);
-                                        dccp_feat_list_purge(&dp->dccps_featneg);
-                                }
-
-                                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);
+                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);
+                }
+        }
+}
+
+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);
                 }
         }
 }
@@ -474,8 +524,9 @@ int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code)
 /*
  * Do all connect socket setups that can be done AF independent.
  */
-static inline void dccp_connect_init(struct sock *sk)
+int dccp_connect(struct sock *sk)
 {
+        struct sk_buff *skb;
         struct dccp_sock *dp = dccp_sk(sk);
         struct dst_entry *dst = __sk_dst_get(sk);
         struct inet_connection_sock *icsk = inet_csk(sk);
@@ -485,22 +536,12 @@ static inline void dccp_connect_init(struct sock *sk)
 
         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;
-}
-
-int dccp_connect(struct sock *sk)
-{
-        struct sk_buff *skb;
-        struct inet_connection_sock *icsk = inet_csk(sk);
-
         /* do not connect if feature negotiation setup fails */
         if (dccp_feat_finalise_settings(dccp_sk(sk)))
                 return -EPROTO;
 
-        dccp_connect_init(sk);
+        /* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */
+        dp->dccps_gar = dp->dccps_iss;
 
         skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation);
         if (unlikely(skb == NULL))
@@ -516,6 +557,7 @@ int dccp_connect(struct sock *sk)
         DCCP_INC_STATS(DCCP_MIB_ACTIVEOPENS);
 
         /* Timer for repeating the REQUEST until an answer. */
+        icsk->icsk_retransmits = 0;
         inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
                                   icsk->icsk_rto, DCCP_RTO_MAX);
         return 0;
@@ -602,6 +644,12 @@ void dccp_send_sync(struct sock *sk, const u64 ackno,
         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);
 }
 
@@ -630,7 +678,6 @@ void dccp_send_close(struct sock *sk, const int active)
                 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));
                 /*