From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752423AbbDCHaS (ORCPT ); Fri, 3 Apr 2015 03:30:18 -0400 Received: from mga02.intel.com ([134.134.136.20]:3311 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751512AbbDCHaQ (ORCPT ); Fri, 3 Apr 2015 03:30:16 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.11,516,1422950400"; d="scan'208";a="708329379" Message-ID: <551E40F7.5020408@linux.intel.com> Date: Fri, 03 Apr 2015 15:27:51 +0800 From: Xiao Guangrong User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.5.0 MIME-Version: 1.0 To: Wanpeng Li , kvm@vger.kernel.org, linux-kernel@vger.kernel.org CC: Paolo Bonzini Subject: Re: [PATCH v2] kvm: mmu: lazy collapse small sptes into large sptes References: <1428041361-4741-1-git-send-email-wanpeng.li@linux.intel.com> In-Reply-To: <1428041361-4741-1-git-send-email-wanpeng.li@linux.intel.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 04/03/2015 02:09 PM, Wanpeng Li wrote: > There are two scenarios for the requirement of collapsing small sptes > into large sptes. > - dirty logging tracks sptes in 4k granularity, so large sptes are split, > the large sptes will be reallocated in the destination machine and the > guest in the source machine will be destroyed when live migration successfully. > However, the guest in the source machine will continue to run if live migration > fail due to some reasons, the sptes still keep small which lead to bad > performance. > - our customers write tools to track the dirty speed of guests by EPT D bit/PML > in order to determine the most appropriate one to be live migrated, however > sptes will still keep small after tracking dirty speed. > > This patch introduce lazy collapse small sptes into large sptes, the memory region > will be scanned on the ioctl context when dirty log is stopped, the ones which can > be collapsed into large pages will be dropped during the scan, it depends the on > later #PF to reallocate all large sptes. > > Signed-off-by: Wanpeng Li > --- > v1 -> v2: > * use 'bool' instead of 'int' > * add more comments > * fix can not get the next spte after drop the current spte > > arch/x86/include/asm/kvm_host.h | 2 ++ > arch/x86/kvm/mmu.c | 71 +++++++++++++++++++++++++++++++++++++++++ > arch/x86/kvm/x86.c | 19 +++++++++++ > 3 files changed, 92 insertions(+) > > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h > index 30b28dc..91b5bdb 100644 > --- a/arch/x86/include/asm/kvm_host.h > +++ b/arch/x86/include/asm/kvm_host.h > @@ -854,6 +854,8 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, > void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); > void kvm_mmu_slot_remove_write_access(struct kvm *kvm, > struct kvm_memory_slot *memslot); > +void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, > + struct kvm_memory_slot *memslot); > void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, > struct kvm_memory_slot *memslot); > void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, > diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c > index cee7592..df3f2e3 100644 > --- a/arch/x86/kvm/mmu.c > +++ b/arch/x86/kvm/mmu.c > @@ -4465,6 +4465,77 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, > kvm_flush_remote_tlbs(kvm); > } > > +static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, > + unsigned long *rmapp) > +{ > + u64 *sptep; > + struct rmap_iterator iter; > + int need_tlb_flush = 0; > + pfn_t pfn; > + struct kvm_mmu_page *sp; > + > + while ((sptep = rmap_get_first(*rmapp, &iter))) { > + BUG_ON(!(*sptep & PT_PRESENT_MASK)); > + > + sp = page_header(__pa(sptep)); > + pfn = spte_to_pfn(*sptep); > + > + /* > + * Let support EPT only now, an efficient way need to be figure > + * out to let these code be aware what mapping level used in > + * guest. This English seems strange... but i am not good at it. :) > + */ > + if (sp->role.direct && > + !kvm_is_reserved_pfn(pfn) && > + PageTransCompound(pfn_to_page(pfn))) { > + drop_spte(kvm, sptep); > + need_tlb_flush = 1; > + } If the conditions are not comfortable, it does loop forever... Otherwise, it looks good to me. Reviewed-by: Xiao Guangrong