Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753193Ab1BBAoB (ORCPT ); Tue, 1 Feb 2011 19:44:01 -0500 Received: from mga01.intel.com ([192.55.52.88]:7970 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753175Ab1BBAn7 (ORCPT ); Tue, 1 Feb 2011 19:43:59 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.60,412,1291622400"; d="scan'208";a="883418080" From: Andi Kleen References: <20110201443.618138584@firstfloor.org> In-Reply-To: <20110201443.618138584@firstfloor.org> To: eric.dumazet@gmail.com, davem@davemloft.net, gregkh@suse.de, ak@linux.intel.com, linux-kernel@vger.kernel.org, stable@kernel.org Subject: [PATCH] [53/139] af_unix: limit unix_tot_inflight Message-Id: <20110202004409.4E70E3E09BD@tassilo.jf.intel.com> Date: Tue, 1 Feb 2011 16:44:09 -0800 (PST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1955 Lines: 59 2.6.35-longterm review patch. If anyone has any objections, please let me know. ------------------ From: Eric Dumazet [ Upstream commit 9915672d41273f5b77f1b3c29b391ffb7732b84b ] Vegard Nossum found a unix socket OOM was possible, posting an exploit program. My analysis is we can eat all LOWMEM memory before unix_gc() being called from unix_release_sock(). Moreover, the thread blocked in unix_gc() can consume huge amount of time to perform cleanup because of huge working set. One way to handle this is to have a sensible limit on unix_tot_inflight, tested from wait_for_unix_gc() and to force a call to unix_gc() if this limit is hit. This solves the OOM and also reduce overall latencies, and should not slowdown normal workloads. Reported-by: Vegard Nossum Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman Signed-off-by: Andi Kleen --- net/unix/garbage.c | 7 +++++++ 1 file changed, 7 insertions(+) Index: linux-2.6.35.y/net/unix/garbage.c =================================================================== --- linux-2.6.35.y.orig/net/unix/garbage.c +++ linux-2.6.35.y/net/unix/garbage.c @@ -259,9 +259,16 @@ static void inc_inflight_move_tail(struc } static bool gc_in_progress = false; +#define UNIX_INFLIGHT_TRIGGER_GC 16000 void wait_for_unix_gc(void) { + /* + * If number of inflight sockets is insane, + * force a garbage collect right now. + */ + if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress) + unix_gc(); wait_event(unix_gc_wait, gc_in_progress == false); } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/