linux.git/net/ipv4/ip_input.c, branch v2.6.14 Linux kernel source tree [NET]: use __read_mostly on kmem_cache_t , DEFINE_SNMP_STAT pointers 2005-08-29T23:11:18+00:00 Eric Dumazet dada1@cosmosbay.com 2005-08-26T19:05:31+00:00 ba89966c1984513f4f2cc0a6c182266be44ddd03 This patch puts mostly read only data in the right section (read_mostly), to help sharing of these data between CPUS without memory ping pongs. On one of my production machine, tcp_statistics was sitting in a heavily modified cache line, so *every* SNMP update had to force a reload. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
This patch puts mostly read only data in the right section
(read_mostly), to help sharing of these data between CPUS without
memory ping pongs.

On one of my production machine, tcp_statistics was sitting in a
heavily modified cache line, so *every* SNMP update had to force a
reload.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[IPV4]: Module export of ip_rcv() no longer needed. 2005-08-29T23:08:23+00:00 Ralf Baechle ralf@linux-mips.org 2005-08-24T18:38:53+00:00 3625796806419d97641d90e0f197eab9b952212e With ip_rcv nowhere outside the IP stack being used anymore it's EXPORT_SYMBOL is not needed any longer either. Signed-off-by: Ralf Baechle DL5RB <ralf@linux-mips.org> Signed-off-by: David S. Miller <davem@davemloft.net> 
With ip_rcv nowhere outside the IP stack being used anymore it's
EXPORT_SYMBOL is not needed any longer either.

Signed-off-by: Ralf Baechle DL5RB <ralf@linux-mips.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
[IPV4]: Avoid common branch mispredictions in ip_rcv_finish() 2005-08-29T23:03:03+00:00 Thomas Graf tgraf@suug.ch 2005-08-21T00:26:30+00:00 3e192beaf5ef260a31e84a12c0a04eff2eec02ab Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net> 
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
[IPV4]: Move ip options parsing out of ip_rcv_finish() 2005-08-29T23:03:00+00:00 Thomas Graf tgraf@suug.ch 2005-08-21T00:26:12+00:00 d245407e758b14c464c609b632873f85709360c7 Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net> 
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
[IPV4]: Avoid common branch misprediction while checking csum in ip_rcv() 2005-08-29T23:02:57+00:00 Thomas Graf tgraf@suug.ch 2005-08-21T00:25:52+00:00 e9c604227391308b185aa6b14c7f93b0a0c2e51b Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net> 
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
[IPV4]: Consistency and whitespace cleanup of ip_rcv() 2005-08-29T23:02:53+00:00 Thomas Graf tgraf@suug.ch 2005-08-21T00:25:29+00:00 58615242417638794a5ba299c49e3fbd6f47c2a3 Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net> 
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
[IPV4/6]: Check if packet was actually delivered to a raw socket to decide whether to send an ICMP unreachable 2005-08-29T22:37:22+00:00 Patrick McHardy kaber@trash.net 2005-08-10T02:45:02+00:00 d13964f4490157b8a290903362bfbc54f750a6bc Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net> 
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
[NET]: Kill skb->real_dev 2005-08-29T22:32:25+00:00 David S. Miller davem@davemloft.net 2005-08-10T02:34:12+00:00 f2ccd8fa06c8e302116e71df372f5c1f83432e03 Bonding just wants the device before the skb_bond() decapsulation occurs, so simply pass that original device into packet_type->func() as an argument. It remains to be seen whether we can use this same exact thing to get rid of skb->input_dev as well. Signed-off-by: David S. Miller <davem@davemloft.net> 
Bonding just wants the device before the skb_bond()
decapsulation occurs, so simply pass that original
device into packet_type->func() as an argument.

It remains to be seen whether we can use this same
exact thing to get rid of skb->input_dev as well.

Signed-off-by: David S. Miller <davem@davemloft.net>
[IPV4]: Snmpv2 Mib IP counter ipInAddrErrors support 2005-06-28T20:06:23+00:00 Dietmar Eggemann dietmar.eggemann@gmx.de 2005-06-28T20:06:23+00:00 2c2910a401f1ce2ac9136171e7522e731e1a2a8c I followed Thomas' proposal to see every martian destination as a case where the ipInAddrErrors counter has to be incremented. There are two advantages by doing so: (1) The relation between the ipInReceive counter and all the other ipInXXX counters is more accurate in the case the RTN_UNICAST code check fails and (2) it makes the code in ip_route_input_slow easier. Signed-off-by: Dietmar Eggemann <dietmar.eggemann@gmx.de> Signed-off-by: David S. Miller <davem@davemloft.net> 
I followed Thomas' proposal to see every martian destination as a case
where the ipInAddrErrors counter has to be incremented. There are
two advantages by doing so: (1) The relation between the ipInReceive
counter and all the other ipInXXX counters is more accurate in the
case the RTN_UNICAST code check fails and (2) it makes the code in
ip_route_input_slow easier.

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@gmx.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
[NETFILTER]: Drop conntrack reference in ip_call_ra_chain()/ip_mr_input() 2005-06-21T21:06:24+00:00 Patrick McHardy kaber@trash.net 2005-06-21T21:06:24+00:00 2715bcf9efc34063e05009f188eb896c462ae925 Drop reference before handing the packets to raw_rcv() Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net> 
Drop reference before handing the packets to raw_rcv()

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>