Return-path: Received: from shards.monkeyblade.net ([149.20.54.216]:48467 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751146Ab2HVE0k (ORCPT ); Wed, 22 Aug 2012 00:26:40 -0400 Date: Tue, 21 Aug 2012 21:26:39 -0700 (PDT) Message-Id: <20120821.212639.516363749620870558.davem@davemloft.net> (sfid-20120822_062644_879106_EB0D846E) To: Larry.Finger@lwfinger.net Cc: eric.dumazet@gmail.com, ncardwell@google.com, linville@tuxdriver.com, linux-wireless@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: Regression associated with commit c8628155ece3 - "tcp: reduce out_of_order memory use" From: David Miller In-Reply-To: <50345B12.1050600@lwfinger.net> References: <50345B12.1050600@lwfinger.net> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Sender: linux-wireless-owner@vger.kernel.org List-ID: From: Larry Finger Date: Tue, 21 Aug 2012 23:07:46 -0500 > I find it hard to understand why this patch should cause these > effects; however, I have verified that a kernel generated from "git > checkout e86b2919" works fine. This commit is immediately before the > patch in question. I can guarentee it's improper skb->truesize setting in these drivers, or use of too huge buffer sizes compared to the amount of data contained within the packet.