linux.git/net/ipv4/proc.c, branch v2.6.29 Linux kernel source tree net: Fix percpu counters deadlock 2008-12-30T07:04:08+00:00 Herbert Xu herbert@gondor.apana.org.au 2008-12-30T07:04:08+00:00 eb4dea5853046727bfbb579f0c9a8cae7369f7c6 When we converted the protocol atomic counters such as the orphan count and the total socket count deadlocks were introduced due to the mismatch in BH status of the spots that used the percpu counter operations. Based on the diagnosis and patch by Peter Zijlstra, this patch fixes these issues by disabling BH where we may be in process context. Reported-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Tested-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net> 
When we converted the protocol atomic counters such as the orphan
count and the total socket count deadlocks were introduced due to
the mismatch in BH status of the spots that used the percpu counter
operations.

Based on the diagnosis and patch by Peter Zijlstra, this patch
fixes these issues by disabling BH where we may be in process
context.

Reported-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Tested-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: Use a percpu_counter for orphan_count 2008-11-26T05:17:14+00:00 Eric Dumazet dada1@cosmosbay.com 2008-11-26T05:17:14+00:00 dd24c00191d5e4a1ae896aafe33c6b8095ab4bd1 Instead of using one atomic_t per protocol, use a percpu_counter for "orphan_count", to reduce cache line contention on heavy duty network servers. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Instead of using one atomic_t per protocol, use a percpu_counter
for "orphan_count", to reduce cache line contention on
heavy duty network servers. 

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: Use a percpu_counter for sockets_allocated 2008-11-26T05:16:35+00:00 Eric Dumazet dada1@cosmosbay.com 2008-11-26T05:16:35+00:00 1748376b6626acf59c24e9592ac67b3fe2a0e026 Instead of using one atomic_t per protocol, use a percpu_counter for "sockets_allocated", to reduce cache line contention on heavy duty network servers. Note : We revert commit (248969ae31e1b3276fc4399d67ce29a5d81e6fd9 net: af_unix can make unix_nr_socks visbile in /proc), since it is not anymore used after sock_prot_inuse_add() addition Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Instead of using one atomic_t per protocol, use a percpu_counter
for "sockets_allocated", to reduce cache line contention on
heavy duty network servers. 

Note : We revert commit (248969ae31e1b3276fc4399d67ce29a5d81e6fd9
net: af_unix can make unix_nr_socks visbile in /proc),
since it is not anymore used after sock_prot_inuse_add() addition

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp: add some mibs to track collapsing 2008-11-25T05:27:22+00:00 Ilpo Järvinen ilpo.jarvinen@helsinki.fi 2008-11-25T05:27:22+00:00 111cc8b913b42ef07793648b1699288332f273e1 Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net> 
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: fix /proc/net/snmp as memory corruptor 2008-11-11T05:43:08+00:00 Eric Dumazet dada1@cosmosbay.com 2008-11-11T05:43:08+00:00 b971e7ac834e9f4bda96d5a96ae9abccd01c1dd8 icmpmsg_put() can happily corrupt kernel memory, using a static table and forgetting to reset an array index in a loop. Remove the static array since its not safe without proper locking. Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
icmpmsg_put() can happily corrupt kernel memory, using a static
table and forgetting to reset an array index in a loop.

Remove the static array since its not safe without proper locking.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp: MD5: Use MIB counter instead of warning for MD5 mismatch. 2008-07-30T10:27:25+00:00 David S. Miller davem@davemloft.net 2008-07-30T10:03:15+00:00 785957d3e8c6fb37b18bf671923a76dbd8240025 From a report by Matti Aarnio, and preliminary patch by Adam Langley. Signed-off-by: David S. Miller <davem@davemloft.net> 
From a report by Matti Aarnio, and preliminary patch by Adam Langley.

Signed-off-by: David S. Miller <davem@davemloft.net>
proc: consolidate per-net single-release callers 2008-07-18T11:07:44+00:00 Pavel Emelyanov xemul@openvz.org 2008-07-18T11:07:44+00:00 b6fcbdb4f283f7ba67cec3cda6be23da8e959031 They are symmetrical to single_open ones :) Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net> 
They are symmetrical to single_open ones :)

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
proc: consolidate per-net single_open callers 2008-07-18T11:07:21+00:00 Pavel Emelyanov xemul@openvz.org 2008-07-18T11:07:21+00:00 de05c557b24c7dffc6d392e3db120cf11c9f6ae7 There are already 7 of them - time to kill some duplicate code. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net> 
There are already 7 of them - time to kill some duplicate code.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
proc: clean the ip_misc_proc_init and ip_proc_init_net error paths 2008-07-18T11:06:50+00:00 Pavel Emelyanov xemul@openvz.org 2008-07-18T11:06:50+00:00 60bdde95807e982a824be9cfdd35055cc721a88a After all this stuff is moved outside, this function can look better. Besides, I tuned the error path in ip_proc_init_net to make it have only 2 exit points, not 3. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net> 
After all this stuff is moved outside, this function can look better.

Besides, I tuned the error path in ip_proc_init_net to make it have
only 2 exit points, not 3.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
proc: show per-net ip_devconf.forwarding in /proc/net/snmp 2008-07-18T11:06:26+00:00 Pavel Emelyanov xemul@openvz.org 2008-07-18T11:06:26+00:00 8e3461d01bdbc3dbf993448ed9ad4acaaeb6495d This one has become per-net long ago, but the appropriate file is per-net only now. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net> 
This one has become per-net long ago, but the appropriate file
is per-net only now.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>