From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pg0-f67.google.com ([74.125.83.67]:43766 "EHLO mail-pg0-f67.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750995AbeBWDpa (ORCPT ); Thu, 22 Feb 2018 22:45:30 -0500 Received: by mail-pg0-f67.google.com with SMTP id f6so2867552pgs.10 for ; Thu, 22 Feb 2018 19:45:29 -0800 (PST) Message-ID: <1519357527.55655.66.camel@gmail.com> Subject: [PATCH v2 net] net_sched: gen_estimator: fix broken estimators based on percpu stats From: Eric Dumazet To: David Miller Cc: netdev , John Fastabend , Cong Wang , Jamal Hadi Salim , Jiri Pirko Date: Thu, 22 Feb 2018 19:45:27 -0800 In-Reply-To: <1519356974.55655.63.camel@gmail.com> References: <1519356974.55655.63.camel@gmail.com> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: netdev-owner@vger.kernel.org List-ID: From: Eric Dumazet pfifo_fast got percpu stats lately, uncovering a bug I introduced last year in linux-4.10. I missed the fact that we have to clear our temporary storage before calling __gnet_stats_copy_basic() in the case of percpu stats. Without this fix, rate estimators (tc qd replace dev xxx root est 1sec 4sec pfifo_fast) are utterly broken. Fixes: 1c0d32fde5bd ("net_sched: gen_estimator: complete rewrite of rate estimators") Signed-off-by: Eric Dumazet --- v2: Perform the zeroing in est_fetch_counters() instead of caller(s)  net/core/gen_estimator.c |    1 +  1 file changed, 1 insertion(+) diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 0a3f88f08727f1f1217560407ff539c8a8c17496..98fd12721221e4aa26e4d11be9de6c0305fb6dd9 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -66,6 +66,7 @@ struct net_rate_estimator { static void est_fetch_counters(struct net_rate_estimator *e, struct gnet_stats_basic_packed *b) { + memset(b, 0, sizeof(*b)); if (e->stats_lock) spin_lock(e->stats_lock);