From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753118Ab1DRH1g (ORCPT ); Mon, 18 Apr 2011 03:27:36 -0400 Received: from mail-wy0-f174.google.com ([74.125.82.174]:41344 "EHLO mail-wy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751684Ab1DRH1b (ORCPT ); Mon, 18 Apr 2011 03:27:31 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=subject:from:to:cc:in-reply-to:references:content-type:date :message-id:mime-version:x-mailer:content-transfer-encoding; b=Hq8OCu+Cd4hexHM3Dk4wwfUfQXipZTnITF1VD7v142tAUHF5g6u4I2N66LZbniM3sh AD1rvEhPvUPqa4Ci+Ca9DiIFen5+kwqECNQV5MWP33ojyjZ9U3N/suTZcETMFRhTJmY4 HGgfSF1eVLVxs1uUCwrYg6lFFmD+3W5kdx2Hw= Subject: Re: [PATCH] mm: Check if PTE is already allocated during page fault From: raz ben yehuda To: Andrea Arcangeli Cc: Mel Gorman , akpm@linux-foundation.org, riel@redhat.com, kosaki.motohiro@jp.fujitsu.com, lkml , linux-mm@kvack.org, stable@kernel.org, shai@scalex86.com In-Reply-To: <20110415150606.GP15707@random.random> References: <20110415101248.GB22688@suse.de> <20110415143916.GN15707@random.random> <20110415150606.GP15707@random.random> Content-Type: text/plain; charset="UTF-8" Date: Mon, 18 Apr 2011 10:21:13 +0300 Message-ID: <1303111273.3425.0.camel@raz.scalemp.com> Mime-Version: 1.0 X-Mailer: Evolution 2.32.0 (2.32.0-2.fc14) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org patch works great. thank you Andrea. On Fri, 2011-04-15 at 17:06 +0200, Andrea Arcangeli wrote: > On Fri, Apr 15, 2011 at 04:39:16PM +0200, Andrea Arcangeli wrote: > > On Fri, Apr 15, 2011 at 11:12:4A.M +0100, Mel Gorman wrote: > > > diff --git a/mm/memory.c b/mm/memory.c > > > index 5823698..1659574 100644 > > > --- a/mm/memory.c > > > +++ b/mm/memory.c > > > @@ -3322,7 +3322,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, > > > * run pte_offset_map on the pmd, if an huge pmd could > > > * materialize from under us from a different thread. > > > */ > > > - if (unlikely(__pte_alloc(mm, vma, pmd, address))) > > > + if (unlikely(pmd_none(*pmd)) && __pte_alloc(mm, vma, pmd, address)) > > I started hacking on this and I noticed it'd be better to extend the > unlikely through the end. At first review I didn't notice the > parenthesis closure stops after pte_none and __pte_alloc is now > uncovered. I'd prefer this: > > if (unlikely(pmd_none(*pmd) && __pte_alloc(mm, vma, pmd, address))) > > I mean the real unlikely thing is that we return VM_FAULT_OOM, if we > end up calling __pte_alloc or not, depends on the app. Generally it > sounds more frequent that the pte is not none, so it's not wrong, but > it's even less likely that __pte_alloc fails so that can be taken into > account too, and __pte_alloc runs still quite frequently. So either > above or: > > if (unlikely(pmd_none(*pmd)) && unlikely(__pte_alloc(mm, vma, pmd, address))) > > I generally prefer unlikely only when it's 100% sure thing it's less > likely (like the VM_FAULT_OOM), so the first version I guess it's > enough (I'm afraid unlikely for pte_none too, may make gcc generate a > far away jump possibly going out of l1 icache for a case that is only > 512 times less likely at best). My point is that it's certainly hugely > more unlikely that __pte_alloc fails than the pte is none. > > This is a real nitpick though ;).