From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932343Ab2F1CBJ (ORCPT ); Wed, 27 Jun 2012 22:01:09 -0400 Received: from tama50.ecl.ntt.co.jp ([129.60.39.147]:34272 "EHLO tama50.ecl.ntt.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932243Ab2F1CBH (ORCPT ); Wed, 27 Jun 2012 22:01:07 -0400 Date: Thu, 28 Jun 2012 11:00:55 +0900 From: Takuya Yoshikawa To: avi@redhat.com, mtosatti@redhat.com Cc: agraf@suse.de, paulus@samba.org, aarcange@redhat.com, kvm@vger.kernel.org, kvm-ppc@vger.kernel.org, linux-kernel@vger.kernel.org, takuya.yoshikawa@gmail.com Subject: [PATCH 4/6] KVM: Introduce kvm_unmap_hva_range() for kvm_mmu_notifier_invalidate_range_start() Message-Id: <20120628110055.eff4db99.yoshikawa.takuya@oss.ntt.co.jp> In-Reply-To: <20120628105733.ccd9abb3.yoshikawa.takuya@oss.ntt.co.jp> References: <20120628105733.ccd9abb3.yoshikawa.takuya@oss.ntt.co.jp> X-Mailer: Sylpheed 3.1.0 (GTK+ 2.24.4; x86_64-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org When we tested KVM under memory pressure, with THP enabled on the host, we noticed that MMU notifier took a long time to invalidate huge pages. Since the invalidation was done with mmu_lock held, it not only wasted the CPU but also made the host harder to respond. This patch mitigates this by using kvm_handle_hva_range(). Signed-off-by: Takuya Yoshikawa Cc: Alexander Graf Cc: Paul Mackerras --- arch/powerpc/include/asm/kvm_host.h | 2 ++ arch/powerpc/kvm/book3s_64_mmu_hv.c | 7 +++++++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/mmu.c | 5 +++++ virt/kvm/kvm_main.c | 3 +-- 5 files changed, 16 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 50ea12f..572ad01 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -52,6 +52,8 @@ struct kvm; extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); +extern int kvm_unmap_hva_range(struct kvm *kvm, + unsigned long start, unsigned long end); extern int kvm_age_hva(struct kvm *kvm, unsigned long hva); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 688e3a1..2ffa32a 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -870,6 +870,13 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; } +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +{ + if (kvm->arch.using_mmu_notifiers) + kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp); + return 0; +} + static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, unsigned long gfn) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 24b7647..5aab8d4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -942,6 +942,7 @@ extern bool kvm_rebooting; #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_age_hva(struct kvm *kvm, unsigned long hva); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b1f64b1..edf54ae 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1248,6 +1248,11 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp); } +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +{ + return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); +} + void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) { kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 636bd08..c597d00 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -332,8 +332,7 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; - for (; start < end; start += PAGE_SIZE) - need_tlb_flush |= kvm_unmap_hva(kvm, start); + need_tlb_flush = kvm_unmap_hva_range(kvm, start, end); need_tlb_flush |= kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) -- 1.7.5.4 From mboxrd@z Thu Jan 1 00:00:00 1970 From: Takuya Yoshikawa Date: Thu, 28 Jun 2012 02:00:55 +0000 Subject: [PATCH 4/6] KVM: Introduce kvm_unmap_hva_range() for kvm_mmu_notifier_invalidate_range_start() Message-Id: <20120628110055.eff4db99.yoshikawa.takuya@oss.ntt.co.jp> List-Id: References: <20120628105733.ccd9abb3.yoshikawa.takuya@oss.ntt.co.jp> In-Reply-To: <20120628105733.ccd9abb3.yoshikawa.takuya@oss.ntt.co.jp> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: avi@redhat.com, mtosatti@redhat.com Cc: agraf@suse.de, paulus@samba.org, aarcange@redhat.com, kvm@vger.kernel.org, kvm-ppc@vger.kernel.org, linux-kernel@vger.kernel.org, takuya.yoshikawa@gmail.com When we tested KVM under memory pressure, with THP enabled on the host, we noticed that MMU notifier took a long time to invalidate huge pages. Since the invalidation was done with mmu_lock held, it not only wasted the CPU but also made the host harder to respond. This patch mitigates this by using kvm_handle_hva_range(). Signed-off-by: Takuya Yoshikawa Cc: Alexander Graf Cc: Paul Mackerras --- arch/powerpc/include/asm/kvm_host.h | 2 ++ arch/powerpc/kvm/book3s_64_mmu_hv.c | 7 +++++++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/mmu.c | 5 +++++ virt/kvm/kvm_main.c | 3 +-- 5 files changed, 16 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 50ea12f..572ad01 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -52,6 +52,8 @@ struct kvm; extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); +extern int kvm_unmap_hva_range(struct kvm *kvm, + unsigned long start, unsigned long end); extern int kvm_age_hva(struct kvm *kvm, unsigned long hva); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 688e3a1..2ffa32a 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -870,6 +870,13 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; } +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +{ + if (kvm->arch.using_mmu_notifiers) + kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp); + return 0; +} + static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, unsigned long gfn) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 24b7647..5aab8d4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -942,6 +942,7 @@ extern bool kvm_rebooting; #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_age_hva(struct kvm *kvm, unsigned long hva); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b1f64b1..edf54ae 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1248,6 +1248,11 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp); } +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +{ + return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); +} + void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) { kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 636bd08..c597d00 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -332,8 +332,7 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; - for (; start < end; start += PAGE_SIZE) - need_tlb_flush |= kvm_unmap_hva(kvm, start); + need_tlb_flush = kvm_unmap_hva_range(kvm, start, end); need_tlb_flush |= kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) -- 1.7.5.4