From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Hildenbrand Subject: Re: [PATCH/RFC] KVM: track pid for VCPU only on KVM_RUN ioctl Date: Tue, 19 Aug 2014 16:52:27 +0200 Message-ID: <20140819165227.37efbbd8@thinkpad-w530> References: <1407249854-2953-1-git-send-email-borntraeger@de.ibm.com> <53E38193.8060206@redhat.com> <53F30CF3.5030606@de.ibm.com> <53F3187E.6080706@redhat.com> <20140819132842.41b3c637@thinkpad-w530> <53F33DCD.2030509@redhat.com> <20140819141403.067487b5@thinkpad-w530> <53F35AC2.7010506@de.ibm.com> <20140819162306.3750c1b1@thinkpad-w530> <53F36341.9030702@de.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Paolo Bonzini , KVM , Gleb Natapov , Rik van Riel , Raghavendra K T , Michael Mueller To: Christian Borntraeger Return-path: Received: from e06smtp17.uk.ibm.com ([195.75.94.113]:39582 "EHLO e06smtp17.uk.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753403AbaHSOwg (ORCPT ); Tue, 19 Aug 2014 10:52:36 -0400 Received: from /spool/local by e06smtp17.uk.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Tue, 19 Aug 2014 15:52:34 +0100 Received: from b06cxnps4076.portsmouth.uk.ibm.com (d06relay13.portsmouth.uk.ibm.com [9.149.109.198]) by d06dlp03.portsmouth.uk.ibm.com (Postfix) with ESMTP id EF8071B08051 for ; Tue, 19 Aug 2014 15:53:25 +0100 (BST) Received: from d06av12.portsmouth.uk.ibm.com (d06av12.portsmouth.uk.ibm.com [9.149.37.247]) by b06cxnps4076.portsmouth.uk.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id s7JEqVAM34930868 for ; Tue, 19 Aug 2014 14:52:31 GMT Received: from d06av12.portsmouth.uk.ibm.com (localhost [127.0.0.1]) by d06av12.portsmouth.uk.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id s7JEqSSh017725 for ; Tue, 19 Aug 2014 08:52:30 -0600 In-Reply-To: <53F36341.9030702@de.ibm.com> Sender: kvm-owner@vger.kernel.org List-ID: > >> Hmm. We want to not only reduce, we want them be zero. > >> In addition to a reworked MP_STATE patch set, we might be able to change the code to call "KVM_S390_INITIAL_RESET" only from the cpu thread itself. > >> If that simplifies things, we could avoid doing KVM_S390_INITIAL_RESET on CPU creation, because we know that all kernel version will do an implicit cpu reset on cpu creation anyway. Can you have a try on this as well when reworking that code? We could then fix this rcu performance penalty independent from getting rid of that ioctl. > >> > >> Christian > >> > > > > Already working on it, only one ioctl left on vcpu creation that is called > > from wrong context, trying to hide from me. Restarts and resets are already > > Maybe its the synchronize when the oldpid is 0? Can you check the patch that I just sent? Already got that in my code. Seems to be an architecture specific one called from wrong context. (actually it is the third one being called after SET_MP_STATE and SET_SIGNAL_MASK). A few more minutes and I should have it :) David > > > blasting fast. > > > > David > > >