Re: inconsistent lock/deadlock crash, vanilla 3.3.4, 32bit, tcp
From: David Miller <davem@davemloft.net>
Date: 2012-04-30 17:40:46
Also in:
lkml
From: David Miller <davem@davemloft.net>
Date: 2012-04-30 17:40:46
Also in:
lkml
From: Eric Dumazet <redacted> Date: Sun, 29 Apr 2012 11:21:56 +0200
From: Eric Dumazet <edumazet@google.com> [PATCH] net: fix sk_sockets_allocated_read_positive Denys Fedoryshchenko reported frequent crashes on a proxy server and kindly provided a lockdep report that explains it all :
...
Bug is that sk_sockets_allocated_read_positive() calls percpu_counter_sum_positive() without BH being disabled. This bug was added in commit 180d8cd942ce33 (foundations of per-cgroup memory pressure controlling.), since previous code was using percpu_counter_read_positive() which is IRQ safe. In __sk_mem_schedule() we dont need the precise count of allocated sockets and can revert to previous behavior. Reported-by: Denys Fedoryshchenko <redacted> Sined-off-by: Eric Dumazet [off-list ref]
Applied, thanks.