From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx0a-001b2d01.pphosted.com (mx0b-001b2d01.pphosted.com [148.163.158.5]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 3sYqpF2RRlzDrqB for ; Wed, 14 Sep 2016 15:28:37 +1000 (AEST) Received: from pps.filterd (m0098416.ppops.net [127.0.0.1]) by mx0b-001b2d01.pphosted.com (8.16.0.17/8.16.0.17) with SMTP id u8E5SRmW005612 for ; Wed, 14 Sep 2016 01:28:34 -0400 Received: from e23smtp03.au.ibm.com (e23smtp03.au.ibm.com [202.81.31.145]) by mx0b-001b2d01.pphosted.com with ESMTP id 25evyusj4m-1 (version=TLSv1.2 cipher=AES256-SHA bits=256 verify=NOT) for ; Wed, 14 Sep 2016 01:28:34 -0400 Received: from localhost by e23smtp03.au.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Wed, 14 Sep 2016 15:28:06 +1000 Received: from d23relay10.au.ibm.com (d23relay10.au.ibm.com [9.190.26.77]) by d23dlp03.au.ibm.com (Postfix) with ESMTP id F059B3578053 for ; Wed, 14 Sep 2016 15:28:04 +1000 (EST) Received: from d23av01.au.ibm.com (d23av01.au.ibm.com [9.190.234.96]) by d23relay10.au.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id u8E5S4IA50331680 for ; Wed, 14 Sep 2016 15:28:04 +1000 Received: from d23av01.au.ibm.com (localhost [127.0.0.1]) by d23av01.au.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id u8E5S4s8003773 for ; Wed, 14 Sep 2016 15:28:04 +1000 Date: Wed, 14 Sep 2016 10:58:03 +0530 From: Anshuman Khandual MIME-Version: 1.0 To: Michael Ellerman , linuxppc-dev@lists.ozlabs.org CC: aneesh.kumar@linux.vnet.ibm.com Subject: Re: [RFC] KVM: PPC: Book3S HV: Fall back to same size HPT in allocation ioctl References: <1473678797-22069-1-git-send-email-khandual@linux.vnet.ibm.com> <87bmzrpd37.fsf@concordia.ellerman.id.au> In-Reply-To: <87bmzrpd37.fsf@concordia.ellerman.id.au> Content-Type: text/plain; charset=windows-1252 Message-Id: <57D8DFE3.50700@linux.vnet.ibm.com> List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On 09/14/2016 05:27 AM, Michael Ellerman wrote: > Anshuman Khandual writes: Not sure whether this mail ever went. Sending it again. > >> > When the HPT size is explicitly passed on from the userspace, currently >> > the KVM_PPC_ALLOCATE_HTAB will try to allocate the requested size of HPT >> > from reserved CMA area and if that is not possible, the allocation just >> > fails. With the commit 572abd563befd56 ("KVM: PPC: Book3S HV: Don't fall >> > back to smaller HPT size in allocation ioctl"), it does not even try to >> > allocate the same order pages from the page allocator before failing for >> > good. Same order allocation should be attempted from the page allocator >> > as a fallback option when the CMA allocation attempt fails. > It looks like if CMA is not configured we will just fail instantly. Right and also we have this fallback registered any way. I wonder why we are still debating about the need of a fallback mechanism when we already have got one. > > So this does look like something we should fix. > > But I think it is just a bug in commit 572abd563bef ("KVM: PPC: Book3S > HV: Don't fall back to smaller HPT size in allocation ioctl"), which did: Hmm, I think its something the commit missed to accommodate for. But maybe yes, its a bug in the commit. > > diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c > index 1f9c0a17f445..10722b1e38b5 100644 > --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c > +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c > @@ -70,7 +70,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp) > } > > /* Lastly try successively smaller sizes from the page allocator */ > - while (!hpt && order > PPC_MIN_HPT_ORDER) { > + /* Only do this if userspace didn't specify a size via ioctl */ > + while (!hpt && order > PPC_MIN_HPT_ORDER && !htab_orderp) { > hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT| > __GFP_NOWARN, order - PAGE_SHIFT); > if (!hpt) > > > Instead of guarding the loop entry with !htab_orderp, it should have > allowed the loop to enter, but prevented it from iterating if the > allocation fails and htab_orderp != 0. Right and thats what Aneesh's proposed patch (in the other thread) does.