This extends the packet dequeuing interface of dccp_write_xmit() to allow
1. CCIDs to take care of timing when the next packet may be sent;
2. delayed sending (as before, with an inter-packet gap up to 65.535 seconds).
The main purpose is to take CCID2 out of its polling mode (when it is network-
limited, it tries every millisecond to send, without interruption).
The interface can also be used to support other CCIDs.
The mode of operation for (2) is as follows:
* new packet is enqueued via dccp_sendmsg() => dccp_write_xmit(),
* ccid_hc_tx_send_packet() detects that it may not send (e.g. window full),
* it signals this condition via `CCID_PACKET_WILL_DEQUEUE_LATER',
* dccp_write_xmit() returns without further action;
* after some time the wait-condition for CCID becomes true,
* that CCID schedules the tasklet,
* tasklet function calls ccid_hc_tx_send_packet() via dccp_write_xmit(),
* since the wait-condition is now true, ccid_hc_tx_packet() returns "send now",
* packet is sent, and possibly more (since dccp_write_xmit() loops).
Code reuse: the taskled function calls dccp_write_xmit(), the timer function
reduces to a wrapper around the same code.
If the tasklet finds that the socket is locked, it re-schedules the tasklet
function (not the tasklet) after one jiffy.
Changed DCCP_BUG to DCCP_WARN when transmit_skb returns an error (e.g. when a
local qdisc is used, NET_XMIT_DROP=1 can be returned for many packets).
Signed-off-by: Gerrit Renker <gerrit@xxxxxxxxxxxxxx>
---
include/linux/dccp.h | 4 +-
net/dccp/ccid.h | 37 ++++++++++++++++-
net/dccp/ccids/ccid3.c | 4 +-
net/dccp/output.c | 103 +++++++++++++++++++++++++++++++----------------
net/dccp/timer.c | 25 ++++++-----
5 files changed, 122 insertions(+), 51 deletions(-)
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -476,7 +476,8 @@ struct dccp_ackvec;
* @dccps_hc_tx_insert_options - sender wants to add options when sending
* @dccps_server_timewait - server holds timewait state on close (RFC 4340, 8.3)
* @dccps_sync_scheduled - flag which signals "send out-of-band message soon"
- * @dccps_xmit_timer - timer for when CCID is not ready to send
+ * @dccps_xmitlet - tasklet scheduled by the TX CCID to dequeue data packets
+ * @dccps_xmit_timer - used by the TX CCID to delay sending (rate-based pacing)
* @dccps_syn_rtt - RTT sample from Request/Response exchange (in usecs)
*/
struct dccp_sock {
@@ -517,6 +518,7 @@ struct dccp_sock {
__u8 dccps_hc_tx_insert_options:1;
__u8 dccps_server_timewait:1;
__u8 dccps_sync_scheduled:1;
+ struct tasklet_struct dccps_xmitlet;
struct timer_list dccps_xmit_timer;
};
--- a/net/dccp/ccid.h
+++ b/net/dccp/ccid.h
@@ -124,13 +124,44 @@ static inline int ccid_get_current_id(struct dccp_sock *dp, bool rx)
extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk);
extern void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk);
+/*
+ * Congestion control of queued data packets via CCID decision.
+ *
+ * The TX CCID performs its congestion-control by indicating whether and when a
+ * queued packet may be sent, using the return code of ccid_hc_tx_send_packet().
+ * The following modes are supported:
+ * - autonomous dequeueing (CCID internally schedules dccps_xmitlet);
+ * - timer-based pacing (CCID returns a delay value in milliseconds).
+ * Modes and error handling are identified using the symbolic constants below.
+ */
+enum ccid_dequeueing_decision {
+ CCID_PACKET_SEND_AT_ONCE = 0x00000,
+ CCID_PACKET_DELAY = 0x10000,
+ CCID_PACKET_WILL_DEQUEUE_LATER = 0x20000,
+ CCID_PACKET_ERR = 0xF0000,
+};
+
+/* maximum possible number of milliseconds to delay a packet (65.535 seconds) */
+#define CCID_PACKET_DELAY_MAX 0xFFFF
+#define CCID_PACKET_DELAY_MAX_USEC (CCID_PACKET_DELAY_MAX * USEC_PER_MSEC)
+
+static inline int ccid_packet_dequeue_eval(int return_code)
+{
+ if (return_code < 0)
+ return CCID_PACKET_ERR;
+ if (return_code == 0)
+ return CCID_PACKET_SEND_AT_ONCE;
+ if (return_code <= CCID_PACKET_DELAY_MAX)
+ return CCID_PACKET_DELAY;
+ return return_code;
+}
+
static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk,
struct sk_buff *skb)
{
- int rc = 0;
if (ccid->ccid_ops->ccid_hc_tx_send_packet != NULL)
- rc = ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb);
- return rc;
+ return ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb);
+ return CCID_PACKET_SEND_AT_ONCE;
}
static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk,
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -346,6 +346,8 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
case TFRC_SSTATE_FBACK:
delay = ktime_us_delta(hctx->ccid3hctx_t_nom, now);
ccid3_pr_debug("delay=%ld\n", (long)delay);
+ if (delay > CCID_PACKET_DELAY_MAX_USEC)
+ delay = CCID_PACKET_DELAY_MAX_USEC;
/*
* Scheduling of packet transmissions [RFC 3448, 4.6]
*
@@ -371,7 +373,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
/* set the nominal send time for the next following packet */
hctx->ccid3hctx_t_nom = ktime_add_us(hctx->ccid3hctx_t_nom,
hctx->ccid3hctx_t_ipi);
- return 0;
+ return CCID_PACKET_SEND_AT_ONCE;
}
static void ccid3_hc_tx_packet_sent(struct sock *sk, int more,
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -249,52 +249,85 @@ do_interrupted:
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 = skb_dequeue(&sk->sk_write_queue);
+
+ if (unlikely(skb == NULL))
+ return;
+ 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);
+ 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_WARN("transmit_skb() returned err=%d\n", err);
+ /*
+ * Register this one as sent even if an error occurred. To the remote
+ * end this error is indistinguishable from loss, so that finally (if
+ * the peer has no bugs) the drop is reported via receiver feedback.
+ */
+ ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len);
+
+ /*
+ * If the CCID needs to transfer additional header options out-of-band
+ * (e.g. Ack Vectors or feature-negotiation options), it activates the
+ * flag to schedule a Sync. The Sync will automatically incorporate all
+ * currently valid header options so that this backlog is now cleared.
+ */
+ if (dp->dccps_sync_scheduled)
+ dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
+}
+
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);
+ int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
- if (err > 0) {
+ switch (ccid_packet_dequeue_eval(rc)) {
+ case CCID_PACKET_WILL_DEQUEUE_LATER:
+ return;
+ case CCID_PACKET_DELAY:
if (!block) {
sk_reset_timer(sk, &dp->dccps_xmit_timer,
- msecs_to_jiffies(err)+jiffies);
+ msecs_to_jiffies(rc)+jiffies);
+ return;
+ }
+ rc = dccp_wait_for_ccid(sk, skb, rc);
+ if (rc && rc != -EINTR) {
+ DCCP_BUG("err=%d after dccp_wait_for_ccid", rc);
+ skb_dequeue(&sk->sk_write_queue);
+ kfree_skb(skb);
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);
- if (dp->dccps_sync_scheduled)
- dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC);
- } else {
- dccp_pr_debug("packet discarded due to err=%d\n", err);
+ }
+ /* fall through */
+ 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=%d\n", rc);
}
}
}
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -249,32 +249,35 @@ out:
sock_put(sk);
}
-/* Transmit-delay timer: used by the CCIDs to delay actual send time */
-static void dccp_write_xmit_timer(unsigned long data)
+/**
+ * dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface
+ * See the comments above %ccid_dequeueing_decision for supported modes.
+ */
+static void dccp_write_xmitlet(unsigned long data)
{
struct sock *sk = (struct sock *)data;
- struct dccp_sock *dp = dccp_sk(sk);
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
- sk_reset_timer(sk, &dp->dccps_xmit_timer, jiffies+1);
+ sk_reset_timer(sk, &dccp_sk(sk)->dccps_xmit_timer, jiffies + 1);
else
dccp_write_xmit(sk, 0);
bh_unlock_sock(sk);
- sock_put(sk);
}
-static void dccp_init_write_xmit_timer(struct sock *sk)
+static void dccp_write_xmit_timer(unsigned long data)
{
- struct dccp_sock *dp = dccp_sk(sk);
-
- setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer,
- (unsigned long)sk);
+ dccp_write_xmitlet(data);
+ sock_put((struct sock *)data);
}
void dccp_init_xmit_timers(struct sock *sk)
{
- dccp_init_write_xmit_timer(sk);
+ struct dccp_sock *dp = dccp_sk(sk);
+
+ tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk);
+ setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer,
+ (unsigned long)sk);
inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer,
&dccp_keepalive_timer);
}
-
To unsubscribe from this list: send the line "unsubscribe dccp" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
