From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gleb Natapov Subject: [PATCHv5 0/4] improve speed of "rep ins" emulation Date: Mon, 30 Jul 2012 17:38:17 +0300 Message-ID: <1343659101-24877-1-git-send-email-gleb@redhat.com> Cc: avi@redhat.com, mtosatti@redhat.com To: kvm@vger.kernel.org Return-path: Received: from mx1.redhat.com ([209.132.183.28]:14463 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754450Ab2G3Oi1 (ORCPT ); Mon, 30 Jul 2012 10:38:27 -0400 Received: from int-mx12.intmail.prod.int.phx2.redhat.com (int-mx12.intmail.prod.int.phx2.redhat.com [10.5.11.25]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id q6UEcR3x015676 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Mon, 30 Jul 2012 10:38:27 -0400 Sender: kvm-owner@vger.kernel.org List-ID: And now for something completely different. So this series (or rather the last patch of it) takes different approach to "rep ins" optimization. Instead of writing separate fast path for it do the fast path inside emulator itself. This way nobody can say the code is not reused! Patch 1,2 are now, strictly speaking, not needed, but I think this is still nice cleanup and, in case of patch 1, eliminates some ifs at each KVM_RUN ioctl. Gleb Natapov (4): Provide userspace IO exit completion callback. KVM: emulator: make x86 emulation modes enum instead of defines KVM: emulator: string_addr_inc() cleanup KVM: emulator: optimize "rep ins" handling. arch/x86/include/asm/kvm_emulate.h | 26 +++++----- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/emulate.c | 48 ++++++++++++++----- arch/x86/kvm/x86.c | 92 +++++++++++++++++++++--------------- 4 files changed, 104 insertions(+), 63 deletions(-) -- 1.7.10