dccp ccid-3: A lower bound for the inter-packet scheduling algorithm

This fixes a subtle bug in the calculation of the inter-packet gap and shows
that t_delta, as it is currently used, is not needed.

The algorithm from RFC 5348, 8.3 below continually computes a send time t_nom,
which is initialised with the current time t_now; t_gran = 1E6 / HZ specifies
the scheduling granularity, s the packet size, and X the sending rate:

  t_distance = t_nom - t_now;		// in microseconds
  t_delta    = min(t_ipi, t_gran) / 2;	// `delta' parameter in microseconds

  if (t_distance >= t_delta) {
	reschedule after (t_distance / 1000) milliseconds;
  } else {
  	t_ipi  = s / X;			// inter-packet interval in usec
	t_nom += t_ipi;			// compute the next send time
	send packet now;
  }

Problem:
--------
Rescheduling requires a conversion into milliseconds (sk_reset_timer()). The
highest jiffy resolution with HZ=1000 is 1 millisecond, so using a higher
granularity does not make much sense here.

As a consequence, values of t_distance < 1000 are truncated to 0. This issue
has so far been resolved by using instead

  if (t_distance >= t_delta + 1000)
	reschedule after (t_distance / 1000) milliseconds;

This is unnecessarily large, a lower bound is t_delta' = max(t_delta, 1000).
And it implies a further simplification:

 a) when HZ >= 500, then t_delta <= t_gran/2 = 10^6/(2*HZ) <= 1000, so that
    t_delta' = MAX(1000, t_delta) = 1000 (constant value);

 b) when HZ < 500, then t_delta = 1/2*MIN(rtt, t_ipi, t_gran) <= t_gran/2,
    so that 1000 <= t_delta' <= t_gran/2.

The maximum error of using a constant t_delta in (b) is less than half a jiffy.

Fix:
----
The patch replaces t_delta with a constant, whose value depends on CONFIG_HZ,
changing the above algorithm to:

  if (t_distance >= t_delta')
	reschedule after (t_distance / 1000) milliseconds;

where t_delta' = 10^6/(2*HZ) if HZ < 500, and t_delta' = 1000 otherwise.

Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>

1 files changed, 13 insertions, 5 deletions

diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h
index b7e569c22f36..4a00174a97dd 100644
--- a/net/dccp/ccids/ccid3.h
+++ b/net/dccp/ccids/ccid3.h
@@ -45,12 +45,22 @@
 /* Two seconds as per RFC 5348, 4.2 */
 #define TFRC_INITIAL_TIMEOUT       (2 * USEC_PER_SEC)
 
-/* In usecs - half the scheduling granularity as per RFC3448 4.6 */
-#define TFRC_OPSYS_HALF_TIME_GRAN  (USEC_PER_SEC / (2 * HZ))
-
 /* Parameter t_mbi from [RFC 3448, 4.3]: backoff interval in seconds */
 #define TFRC_T_MBI                 64
 
+/*
+ * The t_delta parameter (RFC 5348, 8.3): delays of less than %USEC_PER_MSEC are
+ * rounded down to 0, since sk_reset_timer() here uses millisecond granularity.
+ * Hence we can use a constant t_delta = %USEC_PER_MSEC when HZ >= 500. A coarse
+ * resolution of HZ < 500 means that the error is below one timer tick (t_gran)
+ * when using the constant t_delta  =  t_gran / 2  =  %USEC_PER_SEC / (2 * HZ).
+ */
+#if (HZ >= 500)
+# define TFRC_T_DELTA              USEC_PER_MSEC
+#else
+# define TFRC_T_DELTA              (USEC_PER_SEC / (2 * HZ))
+#endif
+
 enum ccid3_options {
         TFRC_OPT_LOSS_EVENT_RATE = 192,
         TFRC_OPT_LOSS_INTERVALS  = 193,
@@ -90,7 +100,6 @@ enum ccid3_hc_tx_states {
  * @tx_no_feedback_timer: Handle to no feedback timer
  * @tx_t_ld:              Time last doubled during slow start
  * @tx_t_nom:             Nominal send time of next packet
- * @tx_delta:             Send timer delta (RFC 3448, 4.6) in usecs
  * @tx_hist:              Packet history
  * @tx_options_received:  Parsed set of retrieved options
  */
@@ -109,7 +118,6 @@ struct ccid3_hc_tx_sock {
         struct timer_list               tx_no_feedback_timer;
         ktime_t                         tx_t_ld;
         ktime_t                         tx_t_nom;
-        u32                             tx_delta;
         struct tfrc_tx_hist_entry       *tx_hist;
         struct ccid3_options_received   tx_options_received;
 };