Skip to content

R
raspberrypi-kernel

openeuler / raspberrypi-kernel

通知 13
Star 1
Fork 0
R
raspberrypi-kernel
切换分支/标签
  1. 02 7月, 2014 1 次提交
    • E
      inet: move ipv6only in sock_common · 9fe516ba
      由 Eric Dumazet 提交于 
      When an UDP application switches from AF_INET to AF_INET6 sockets, we
have a small performance degradation for IPv4 communications because of
extra cache line misses to access ipv6only information.

This can also be noticed for TCP listeners, as ipv6_only_sock() is also
used from __inet_lookup_listener()->compute_score()

This is magnified when SO_REUSEPORT is used.

Move ipv6only into struct sock_common so that it is available at
no extra cost in lookups.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      9fe516ba
  3. 28 6月, 2014 11 次提交
  5. 26 6月, 2014 1 次提交
    • E
      ipv4: fix dst race in sk_dst_get() · f8864972
      由 Eric Dumazet 提交于 
      When IP route cache had been removed in linux-3.6, we broke assumption
that dst entries were all freed after rcu grace period. DST_NOCACHE
dst were supposed to be freed from dst_release(). But it appears
we want to keep such dst around, either in UDP sockets or tunnels.

In sk_dst_get() we need to make sure dst refcount is not 0
before incrementing it, or else we might end up freeing a dst
twice.

DST_NOCACHE set on a dst does not mean this dst can not be attached
to a socket or a tunnel.

Then, before actual freeing, we need to observe a rcu grace period
to make sure all other cpus can catch the fact the dst is no longer
usable.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: NDormando <dormando@rydia.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      f8864972
  7. 24 6月, 2014 1 次提交
  9. 18 6月, 2014 1 次提交
  11. 16 6月, 2014 1 次提交
  13. 15 6月, 2014 1 次提交
  15. 12 6月, 2014 2 次提交
    • F
      net_sched: drr: warn when qdisc is not work conserving · 6e765a00
      由 Florian Westphal 提交于 
      The DRR scheduler requires that items on the active list are work
conserving, i.e. do not hold on to skbs for throttling purposes, etc.
Attaching e.g. tbf renders DRR useless because all other classes on the
active list are delayed as well.

So, warn users that this configuration won't work as expected; we
already do this in couple of other qdiscs, see e.g.

commit b00355db
('pkt_sched: sch_hfsc: sch_htb: Add non-work-conserving warning handler')

The 'const' change is needed to avoid compiler warning ("discards 'const'
qualifier from pointer target type").

tested with:
drr_hier() {
        parent=$1
        classes=$2
        for i in  $(seq 1 $classes); do
                classid=$parent$(printf %x $i)
                tc class add dev eth0 parent $parent classid $classid drr
		tc qdisc add dev eth0 parent $classid tbf rate 64kbit burst 256kbit limit 64kbit
        done
}
tc qdisc add dev eth0 root handle 1: drr
drr_hier 1: 32
tc filter add dev eth0 protocol all pref 1 parent 1: handle 1 flow hash keys dst perturb 1 divisor 32
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      6e765a00
    • D
      net: sctp: migrate most recently used transport to ktime · e575235f
      由 Daniel Borkmann 提交于 
      Be more precise in transport path selection and use ktime
helpers instead of jiffies to compare and pick the better
primary and secondary recently used transports. This also
avoids any side-effects during a possible roll-over, and
could lead to better path decision-making.
Signed-off-by: NDaniel Borkmann <dborkman@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      e575235f
  17. 11 6月, 2014 1 次提交
  19. 05 6月, 2014 3 次提交
  21. 03 6月, 2014 2 次提交
    • E
      net: fix inet_getid() and ipv6_select_ident() bugs · 39c36094
      由 Eric Dumazet 提交于 
      I noticed we were sending wrong IPv4 ID in TCP flows when MTU discovery
is disabled.
Note how GSO/TSO packets do not have monotonically incrementing ID.

06:37:41.575531 IP (id 14227, proto: TCP (6), length: 4396)
06:37:41.575534 IP (id 14272, proto: TCP (6), length: 65212)
06:37:41.575544 IP (id 14312, proto: TCP (6), length: 57972)
06:37:41.575678 IP (id 14317, proto: TCP (6), length: 7292)
06:37:41.575683 IP (id 14361, proto: TCP (6), length: 63764)

It appears I introduced this bug in linux-3.1.

inet_getid() must return the old value of peer->ip_id_count,
not the new one.

Lets revert this part, and remove the prevention of
a null identification field in IPv6 Fragment Extension Header,
which is dubious and not even done properly.

Fixes: 87c48fa3 ("ipv6: make fragment identifications less predictable")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      39c36094
    • E
      inetpeer: get rid of ip_id_count · 73f156a6
      由 Eric Dumazet 提交于 
      Ideally, we would need to generate IP ID using a per destination IP
generator.

linux kernels used inet_peer cache for this purpose, but this had a huge
cost on servers disabling MTU discovery.

1) each inet_peer struct consumes 192 bytes

2) inetpeer cache uses a binary tree of inet_peer structs,
   with a nominal size of ~66000 elements under load.

3) lookups in this tree are hitting a lot of cache lines, as tree depth
   is about 20.

4) If server deals with many tcp flows, we have a high probability of
   not finding the inet_peer, allocating a fresh one, inserting it in
   the tree with same initial ip_id_count, (cf secure_ip_id())

5) We garbage collect inet_peer aggressively.

IP ID generation do not have to be 'perfect'

Goal is trying to avoid duplicates in a short period of time,
so that reassembly units have a chance to complete reassembly of
fragments belonging to one message before receiving other fragments
with a recycled ID.

We simply use an array of generators, and a Jenkin hash using the dst IP
as a key.

ipv6_select_ident() is put back into net/ipv6/ip6_output.c where it
belongs (it is only used from this file)

secure_ip_id() and secure_ipv6_id() no longer are needed.

Rename ip_select_ident_more() to ip_select_ident_segs() to avoid
unnecessary decrement/increment of the number of segments.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      73f156a6
  23. 26 5月, 2014 1 次提交
    • L
      mac80211: add a single-transaction driver op to switch contexts · 1a5f0c13
      由 Luciano Coelho 提交于 
      In some cases, when the driver is already using all the channel
contexts it can handle at once, we have to do an in-place switch
(ie. we cannot afford using an extra context temporarily for the
transaction).  But some drivers may not support switching the channel
context assigned to a vif on the fly (ie. without unassigning and
assigning it) while others may only work if the context is changed on
the fly, without unassigning it first.

To allow these different scenarios, add a new driver operation that
let's the driver decide how to handle an in-place switch.
Signed-off-by: NLuciano Coelho <luciano.coelho@intel.com>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      1a5f0c13
  25. 24 5月, 2014 3 次提交
  27. 23 5月, 2014 2 次提交
    • E
      net: Add a software TSO helper API · e876f208
      由 Ezequiel Garcia 提交于 
      Although the implementation probably needs a lot of work, this initial API
allows to implement software TSO in mvneta and mv643xx_eth drivers in a not
so intrusive way.
Signed-off-by: NEzequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      e876f208
    • N
      tcp: make cwnd-limited checks measurement-based, and gentler · ca8a2263
      由 Neal Cardwell 提交于 
      Experience with the recent e114a710 ("tcp: fix cwnd limited
checking to improve congestion control") has shown that there are
common cases where that commit can cause cwnd to be much larger than
necessary. This leads to TSO autosizing cooking skbs that are too
large, among other things.

The main problems seemed to be:

(1) That commit attempted to predict the future behavior of the
connection by looking at the write queue (if TSO or TSQ limit
sending). That prediction sometimes overestimated future outstanding
packets.

(2) That commit always allowed cwnd to grow to twice the number of
outstanding packets (even in congestion avoidance, where this is not
needed).

This commit improves both of these, by:

(1) Switching to a measurement-based approach where we explicitly
track the largest number of packets in flight during the past window
("max_packets_out"), and remember whether we were cwnd-limited at the
moment we finished sending that flight.

(2) Only allowing cwnd to grow to twice the number of outstanding
packets ("max_packets_out") in slow start. In congestion avoidance
mode we now only allow cwnd to grow if it was fully utilized.
Signed-off-by: NNeal Cardwell <ncardwell@google.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      ca8a2263
  29. 22 5月, 2014 1 次提交
    • E
      cfg80211: allow RSSI compensation · 67af9811
      由 Emmanuel Grumbach 提交于 
      Channels in 2.4GHz band overlap, this means that if we
send a probe request on channel 1 and then move to channel
2, we will hear the probe response on channel 2. In this
case, the RSSI will be lower than if we had heard it on
the channel on which it was sent (1 in this case).

The firmware / low level driver can parse the channel in
the DS IE or HT IE and compensate the RSSI so that it will
still have a valid value even if we heard the frame on an
adjacent channel. This can be done up to a certain offset.

Add this offset as a configuration for the low level driver.
A low level driver that can compensate the low RSSI in this
case should assign the maximal offset for which the RSSI
value is still valid.
Signed-off-by: NEmmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
      67af9811
  31. 21 5月, 2014 2 次提交
  33. 20 5月, 2014 3 次提交
  35. 19 5月, 2014 3 次提交