From 0e90b31f4ba77027a7c21cbfc66404df0851ca21 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Fri, 20 Jan 2012 04:57:16 +0000 Subject: net: introduce res_counter_charge_nofail() for socket allocations There is a case in __sk_mem_schedule(), where an allocation is beyond the maximum, but yet we are allowed to proceed. It happens under the following condition: sk->sk_wmem_queued + size >= sk->sk_sndbuf The network code won't revert the allocation in this case, meaning that at some point later it'll try to do it. Since this is never communicated to the underlying res_counter code, there is an inbalance in res_counter uncharge operation. I see two ways of fixing this: 1) storing the information about those allocations somewhere in memcg, and then deducting from that first, before we start draining the res_counter, 2) providing a slightly different allocation function for the res_counter, that matches the original behavior of the network code more closely. I decided to go for #2 here, believing it to be more elegant, since #1 would require us to do basically that, but in a more obscure way. Signed-off-by: Glauber Costa Cc: KAMEZAWA Hiroyuki Cc: Johannes Weiner Cc: Michal Hocko CC: Tejun Heo CC: Li Zefan CC: Laurent Chavey Acked-by: Tejun Heo Signed-off-by: David S. Miller --- kernel/res_counter.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'kernel/res_counter.c') diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 6d269cce7aa..d508363858b 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -66,6 +66,31 @@ done: return ret; } +int res_counter_charge_nofail(struct res_counter *counter, unsigned long val, + struct res_counter **limit_fail_at) +{ + int ret, r; + unsigned long flags; + struct res_counter *c; + + r = ret = 0; + *limit_fail_at = NULL; + local_irq_save(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + r = res_counter_charge_locked(c, val); + if (r) + c->usage += val; + spin_unlock(&c->lock); + if (r < 0 && ret == 0) { + *limit_fail_at = c; + ret = r; + } + } + local_irq_restore(flags); + + return ret; +} void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) { if (WARN_ON(counter->usage < val)) -- cgit v1.2.3-18-g5258