linux-toradex.git/net/ipv4/tcp_illinois.c, branch v3.14.16

remove extra definitions of U32_MAX

2014-01-24T00:36:55+00:00

Now that the definition is centralized in , the
definitions of U32_MAX (and related) elsewhere in the kernel can be
removed.

Signed-off-by: Alex Elder 
Acked-by: Sage Weil 
Acked-by: David S. Miller 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

conditionally define U32_MAX

2014-01-24T00:36:54+00:00

The symbol U32_MAX is defined in several spots.  Change these
definitions to be conditional.  This is in preparation for the next
patch, which centralizes the definition in .

Signed-off-by: Alex Elder 
Cc: Sage Weil 
Cc: David Miller 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

tcp: properly handle stretch acks in slow start

2013-11-05T00:57:59+00:00

Slow start now increases cwnd by 1 if an ACK acknowledges some packets,
regardless the number of packets. Consequently slow start performance
is highly dependent on the degree of the stretch ACKs caused by
receiver or network ACK compression mechanisms (e.g., delayed-ACK,
GRO, etc).  But slow start algorithm is to send twice the amount of
packets of packets left so it should process a stretch ACK of degree
N as if N ACKs of degree 1, then exits when cwnd exceeds ssthresh. A
follow up patch will use the remainder of the N (if greater than 1)
to adjust cwnd in the congestion avoidance phase.

In addition this patch retires the experimental limited slow start
(LSS) feature. LSS has multiple drawbacks but questionable benefit. The
fractional cwnd increase in LSS requires a loop in slow start even
though it's rarely used. Configuring such an increase step via a global
sysctl on different BDPS seems hard. Finally and most importantly the
slow start overshoot concern is now better covered by the Hybrid slow
start (hystart) enabled by default.

Signed-off-by: Yuchung Cheng 
Signed-off-by: Neal Cardwell 
Signed-off-by: Eric Dumazet 
Signed-off-by: David S. Miller

net: fix divide by zero in tcp algorithm illinois

2012-11-01T15:55:59+00:00

Reading TCP stats when using TCP Illinois congestion control algorithm
can cause a divide by zero kernel oops.

The division by zero occur in tcp_illinois_info() at:
 do_div(t, ca->cnt_rtt);
where ca->cnt_rtt can become zero (when rtt_reset is called)

Steps to Reproduce:
 1. Register tcp_illinois:
     # sysctl -w net.ipv4.tcp_congestion_control=illinois
 2. Monitor internal TCP information via command "ss -i"
     # watch -d ss -i
 3. Establish new TCP conn to machine

Either it fails at the initial conn, or else it needs to wait
for a loss or a reset.

This is only related to reading stats.  The function avg_delay() also
performs the same divide, but is guarded with a (ca->cnt_rtt > 0) at its
calling point in update_params().  Thus, simply fix tcp_illinois_info().

Function tcp_illinois_info() / get_info() is called without
socket lock.  Thus, eliminate any race condition on ca->cnt_rtt
by using a local stack variable.  Simply reuse info.tcpv_rttcnt,
as its already set to ca->cnt_rtt.
Function avg_delay() is not affected by this race condition, as
its called with the socket lock.

Cc: Petr Matousek 
Signed-off-by: Jesper Dangaard Brouer 
Acked-by: Eric Dumazet 
Acked-by: Stephen Hemminger 
Signed-off-by: David S. Miller

tcp: mark tcp_congestion_ops read_mostly

2011-03-10T08:40:17+00:00

Signed-off-by: Stephen Hemminger 
Signed-off-by: David S. Miller

Update broken web addresses in the kernel.

2010-10-18T09:03:14+00:00

The patch below updates broken web addresses in the kernel

Signed-off-by: Justin P. Mattock 
Cc: Maciej W. Rozycki 
Cc: Geert Uytterhoeven 
Cc: Finn Thain 
Cc: Randy Dunlap 
Cc: Matt Turner 
Cc: Dimitry Torokhov 
Cc: Mike Frysinger 
Acked-by: Ben Pfaff 
Acked-by: Hans J. Koch 
Reviewed-by: Finn Thain 
Signed-off-by: Jiri Kosina

[TCP]: Cong.ctrl modules: remove unused good_ack from cong_avoid

2008-01-28T22:55:41+00:00

Signed-off-by: Ilpo Järvinen 
Signed-off-by: Herbert Xu 
Signed-off-by: David S. Miller

[TCP] illinois: Incorrect beta usage

2007-11-29T14:10:55+00:00

Lachlan Andrew observed that my TCP-Illinois implementation uses the
beta value incorrectly:
  The parameter  beta  in the paper specifies the amount to decrease
  *by*:  that is, on loss,
     W <-  W -  beta*W
  but in   tcp_illinois_ssthresh() uses  beta  as the amount
  to decrease  *to*: W <- beta*W

This bug makes the Linux TCP-Illinois get less-aggressive on uncongested network,
hurting performance. Note: since the base beta value is .5, it has no
impact on a congested network.

Signed-off-by: Stephen Hemminger 
Signed-off-by: Herbert Xu

[TCP]: congestion control API pass RTT in microseconds

2007-07-31T09:27:57+00:00

This patch changes the API for the callback that is done after an ACK is
received. It solves a couple of issues:

  * Some congestion controls want higher resolution value of RTT
    (controlled by TCP_CONG_RTT_SAMPLE flag). These don't really want a ktime, but
    all compute a RTT in microseconds.

  * Other congestion control could use RTT at jiffies resolution.

To keep API consistent the units should be the same for both cases, just the
resolution should change.

Signed-off-by: Stephen Hemminger 
Signed-off-by: David S. Miller

[TCP]: remove unused argument to cong_avoid op

2007-07-18T08:46:58+00:00

None of the existing TCP congestion controls use the rtt value pased
in the ca_ops->cong_avoid interface.  Which is lucky because seq_rtt
could have been -1 when handling a duplicate ack.

Signed-off-by: Stephen Hemminger 
Signed-off-by: David S. Miller