diff options
| author | David S. Miller <davem@davemloft.net> | 2010-08-25 02:27:49 -0700 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@suse.de> | 2010-09-26 17:18:13 -0700 |
| commit | fd31b5dcb8c69c007705caa9dccdaa371f21b4f0 (patch) | |
| tree | fc4aeff76ffcbfb463f601def7190062e4dcae78 /net/unix/af_unix.c | |
| parent | 515b723e04cb4df7f96c59dee019d126df707fc0 (diff) | |
| download | kernel-crypto-fd31b5dcb8c69c007705caa9dccdaa371f21b4f0.tar.gz kernel-crypto-fd31b5dcb8c69c007705caa9dccdaa371f21b4f0.tar.xz kernel-crypto-fd31b5dcb8c69c007705caa9dccdaa371f21b4f0.zip | |
tcp: Combat per-cpu skew in orphan tests.
[ Upstream commit ad1af0fedba14f82b240a03fe20eb9b2fdbd0357 ]
As reported by Anton Blanchard when we use
percpu_counter_read_positive() to make our orphan socket limit checks,
the check can be off by up to num_cpus_online() * batch (which is 32
by default) which on a 128 cpu machine can be as large as the default
orphan limit itself.
Fix this by doing the full expensive sum check if the optimized check
triggers.
Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Diffstat (limited to 'net/unix/af_unix.c')
0 files changed, 0 insertions, 0 deletions