From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Laight Subject: RE: order:1 failure in ipoib_cm_alloc_rx_skb Date: Fri, 22 Aug 2014 09:00:50 +0000 Message-ID: <063D6719AE5E284EB5DD2968C1650D6D1747EEE3@AcuExch.aculab.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset="Windows-1252" Content-Transfer-Encoding: 8BIT To: 'Venkat Venkatsubra' , "netdev@vger.kernel.org" Return-path: Received: from mx0.aculab.com ([213.249.233.131]:33476 "HELO mx0.aculab.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1752042AbaHVJCP convert rfc822-to-8bit (ORCPT ); Fri, 22 Aug 2014 05:02:15 -0400 Received: from mx0.aculab.com ([127.0.0.1]) by localhost (mx0.aculab.com [127.0.0.1]) (amavisd-new, port 10024) with SMTP id 20251-06 for ; Fri, 22 Aug 2014 10:02:06 +0100 (BST) In-Reply-To: Content-Language: en-US Sender: netdev-owner@vger.kernel.org List-ID: From: Venkat Venkatsubra > Hello All, > > Many of our customers have hit this order:1 failure in ipoib_cm_alloc_rx_skb causing softlockup: > .... > skb = dev_alloc_skb(IPOIB_CM_HEAD_SIZE + 12); > .... Notwithstanding any other problems, that allocation could fail even if the size were small enough that the entire skb would fit in one page. So the driver needs changing so that the allocation failure doesn't cause a deadlock. OTOH if you can't allocate 8k of contiguous address space and memory the system is unlikely to be working very well at all. David