Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752464AbdI1IbF (ORCPT ); Thu, 28 Sep 2017 04:31:05 -0400 Received: from mx2.suse.de ([195.135.220.15]:43935 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752392AbdI1IbD (ORCPT ); Thu, 28 Sep 2017 04:31:03 -0400 From: Luis Henriques To: Tejun Heo Cc: Dennis Zhou , Christoph Lameter , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH 2/2] percpu: fix iteration to prevent skipping over block References: <1506548100-31247-1-git-send-email-dennisszhou@gmail.com> <1506548100-31247-3-git-send-email-dennisszhou@gmail.com> <20170927215125.GB15129@devbig577.frc2.facebook.com> Date: Thu, 28 Sep 2017 09:31:00 +0100 In-Reply-To: <20170927215125.GB15129@devbig577.frc2.facebook.com> (Tejun Heo's message of "Wed, 27 Sep 2017 14:51:25 -0700") Message-ID: <87lgkzkywr.fsf@hermes> MIME-Version: 1.0 Content-Type: text/plain Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1271 Lines: 31 Tejun Heo writes: > On Wed, Sep 27, 2017 at 04:35:00PM -0500, Dennis Zhou wrote: >> The iterator functions pcpu_next_md_free_region and >> pcpu_next_fit_region use the block offset to determine if they have >> checked the area in the prior iteration. However, this causes an issue >> when the block offset is greater than subsequent block contig hints. If >> within the iterator it moves to check subsequent blocks, it may fail in >> the second predicate due to the block offset not being cleared. Thus, >> this causes the allocator to skip over blocks leading to false failures >> when allocating from the reserved chunk. While this happens in the >> general case as well, it will only fail if it cannot allocate a new >> chunk. >> >> This patch resets the block offset to 0 to pass the second predicate >> when checking subseqent blocks within the iterator function. >> >> Signed-off-by: Dennis Zhou >> Reported-by: Luis Henriques > > Luis, can you please verify that this fixes the allocaiton failure you > were seeing? I can confirm that I'm no longer seeing the allocation failure after applying these patches. Feel free to add my: Tested-by: Luis Henriques Cheers, -- Luis