From patchwork Wed Apr 28 11:57:01 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Lai Jiangshan X-Patchwork-Id: 95663 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter.kernel.org (8.14.3/8.14.3) with ESMTP id o3SBv0KC028916 for ; Wed, 28 Apr 2010 11:57:00 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754356Ab0D1L4Q (ORCPT ); Wed, 28 Apr 2010 07:56:16 -0400 Received: from cn.fujitsu.com ([222.73.24.84]:57952 "EHLO song.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1754278Ab0D1L4P (ORCPT ); Wed, 28 Apr 2010 07:56:15 -0400 Received: from tang.cn.fujitsu.com (tang.cn.fujitsu.com [10.167.250.3]) by song.cn.fujitsu.com (Postfix) with ESMTP id A540F17012C; Wed, 28 Apr 2010 19:56:11 +0800 (CST) Received: from fnst.cn.fujitsu.com (tang.cn.fujitsu.com [127.0.0.1]) by tang.cn.fujitsu.com (8.14.3/8.13.1) with ESMTP id o3SBsNOw024013; Wed, 28 Apr 2010 19:54:24 +0800 Received: from [10.167.141.204] (unknown [10.167.141.204]) by fnst.cn.fujitsu.com (Postfix) with ESMTPA id CD852DC2FF; Wed, 28 Apr 2010 19:59:17 +0800 (CST) Message-ID: <4BD8228D.7090708@cn.fujitsu.com> Date: Wed, 28 Apr 2010 19:57:01 +0800 From: Lai Jiangshan User-Agent: Thunderbird 2.0.0.6 (Windows/20070728) MIME-Version: 1.0 To: Avi Kivity , Marcelo Tosatti , LKML , kvm@vger.kernel.org Subject: [PATCH] kvm mmu: reduce 50% memory usage Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter.kernel.org [140.211.167.41]); Wed, 28 Apr 2010 11:57:01 +0000 (UTC) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index ddfa865..a5c6719 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -393,6 +393,22 @@ static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd) kfree(rd); } +static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index) +{ + if (!sp->role.direct) + return sp->gfns[index]; + + return sp->gfn + (index << ((sp->role.level - 1) * PT64_LEVEL_BITS)); +} + +static void kvm_mmu_page_set_gfn(struct kvm_mmu_page *sp, int index, gfn_t gfn) +{ + if (sp->role.direct) + BUG_ON(gfn != kvm_mmu_page_get_gfn(sp, index)); + else + sp->gfns[index] = gfn; +} + /* * Return the pointer to the largepage write count for a given * gfn, handling slots that are not large page aligned. @@ -543,7 +559,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) return count; gfn = unalias_gfn(vcpu->kvm, gfn); sp = page_header(__pa(spte)); - sp->gfns[spte - sp->spt] = gfn; + kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); if (!*rmapp) { rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte); @@ -601,6 +617,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) struct kvm_rmap_desc *prev_desc; struct kvm_mmu_page *sp; pfn_t pfn; + gfn_t gfn; unsigned long *rmapp; int i; @@ -612,7 +629,8 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) kvm_set_pfn_accessed(pfn); if (is_writable_pte(*spte)) kvm_set_pfn_dirty(pfn); - rmapp = gfn_to_rmap(kvm, sp->gfns[spte - sp->spt], sp->role.level); + gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); + rmapp = gfn_to_rmap(kvm, gfn, sp->role.level); if (!*rmapp) { printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte); BUG(); @@ -896,7 +914,8 @@ static void kvm_mmu_free_page(struct kvm *kvm, struct kvm_mmu_page *sp) ASSERT(is_empty_shadow_page(sp->spt)); list_del(&sp->link); __free_page(virt_to_page(sp->spt)); - __free_page(virt_to_page(sp->gfns)); + if (!sp->role.direct) + __free_page(virt_to_page(sp->gfns)); kfree(sp); ++kvm->arch.n_free_mmu_pages; } @@ -907,13 +926,15 @@ static unsigned kvm_page_table_hashfn(gfn_t gfn) } static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, - u64 *parent_pte) + u64 *parent_pte, int direct) { struct kvm_mmu_page *sp; sp = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_header_cache, sizeof *sp); sp->spt = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE); - sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE); + if (!direct) + sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, + PAGE_SIZE); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); @@ -1347,7 +1368,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, return sp; } ++vcpu->kvm->stat.mmu_cache_miss; - sp = kvm_mmu_alloc_page(vcpu, parent_pte); + sp = kvm_mmu_alloc_page(vcpu, parent_pte, direct); if (!sp) return sp; sp->gfn = gfn; @@ -3314,7 +3335,7 @@ void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) if (*sptep & PT_WRITABLE_MASK) { rev_sp = page_header(__pa(sptep)); - gfn = rev_sp->gfns[sptep - rev_sp->spt]; + gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt); if (!gfn_to_memslot(kvm, gfn)) { if (!printk_ratelimit()) @@ -3328,8 +3349,7 @@ void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], - rev_sp->role.level); + rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level); if (!*rmapp) { if (!printk_ratelimit()) return; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index d0cc07e..702c016 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -576,6 +576,9 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) offset = nr_present = 0; + /* direct kvm_mmu_page can not be unsync. */ + BUG_ON(sp->role.direct); + if (PTTYPE == 32) offset = sp->role.quadrant << PT64_LEVEL_BITS;