Re: [PATCH v3 2/6] KVM: x86/mmu: Track the number of TDP MMU pages, but not the actual pages

[Sean Christopherson <seanjc@google.com>]

[-- Attachment #1: Type: text/plain, Size: 665 bytes --]

On Fri, Apr 01, 2022, Mingwei Zhang wrote:
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index f05423545e6d..5ca78a89d8ed 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -24,7 +24,6 @@ bool kvm_mmu_init_tdp_mmu(struct kvm *kvm)
>  
>  	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
>  	spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
> -	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
>  	kvm->arch.tdp_mmu_zap_wq =
>  		alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0);

This has a minor conflict with kvm/next and kvm/queue, attached a new version since
you'll need a v3 (foreshadowing...).

[-- Attachment #2: 0001-KVM-x86-mmu-Track-the-number-of-TDP-MMU-pages-but-no.patch --]
[-- Type: text/x-diff, Size: 4419 bytes --]

From 3d0c2796b22c75e3ab279cbcd3036c44500a6744 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 1 Apr 2022 06:36:32 +0000
Subject: [PATCH] KVM: x86/mmu: Track the number of TDP MMU pages, but not the
 actual pages

Track the number of TDP MMU "shadow" pages instead of tracking the pages
themselves. With the NX huge page list manipulation moved out of the common
linking flow, elminating the list-based tracking means the happy path of
adding a shadow page doesn't need to acquire a spinlock and can instead
inc/dec an atomic.

Keep the tracking as the WARN during TDP MMU teardown on leaked shadow
pages is very, very useful for detecting KVM bugs.

Tracking the number of pages will also make it trivial to expose the
counter to userspace as a stat in the future, which may or may not be
desirable.

Note, the TDP MMU needs to use a separate counter (and stat if that ever
comes to be) from the existing n_used_mmu_pages. The TDP MMU doesn't bother
supporting the shrinker nor does it honor KVM_SET_NR_MMU_PAGES (because the
TDP MMU consumes so few pages relative to shadow paging), and including TDP
MMU pages in that counter would break both the shrinker and shadow MMUs,
e.g. if a VM is using nested TDP.

Cc: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Mingwei Zhang <mizhang@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h | 11 +++--------
 arch/x86/kvm/mmu/tdp_mmu.c      | 16 ++++++++--------
 2 files changed, 11 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 676705ad1e23..8a80056cf841 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1192,6 +1192,9 @@ struct kvm_arch {
 	 */
 	bool tdp_mmu_enabled;
 
+	/* The number of TDP MMU pages across all roots. */
+	atomic64_t tdp_mmu_pages;
+
 	/*
 	 * List of struct kvm_mmu_pages being used as roots.
 	 * All struct kvm_mmu_pages in the list should have
@@ -1212,18 +1215,10 @@ struct kvm_arch {
 	 */
 	struct list_head tdp_mmu_roots;
 
-	/*
-	 * List of struct kvmp_mmu_pages not being used as roots.
-	 * All struct kvm_mmu_pages in the list should have
-	 * tdp_mmu_page set and a tdp_mmu_root_count of 0.
-	 */
-	struct list_head tdp_mmu_pages;
-
 	/*
 	 * Protects accesses to the following fields when the MMU lock
 	 * is held in read mode:
 	 *  - tdp_mmu_roots (above)
-	 *  - tdp_mmu_pages (above)
 	 *  - the link field of struct kvm_mmu_pages used by the TDP MMU
 	 *  - lpage_disallowed_mmu_pages
 	 *  - the lpage_disallowed_link field of struct kvm_mmu_pages used
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index d6417740646a..1f44826cf794 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -29,7 +29,6 @@ int kvm_mmu_init_tdp_mmu(struct kvm *kvm)
 	kvm->arch.tdp_mmu_enabled = true;
 	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
 	spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
-	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
 	kvm->arch.tdp_mmu_zap_wq = wq;
 	return 1;
 }
@@ -54,7 +53,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	flush_workqueue(kvm->arch.tdp_mmu_zap_wq);
 	destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);
 
-	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages));
+	WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
 
 	/*
@@ -384,14 +383,17 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
 static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
 			      bool shared)
 {
+	atomic64_dec(&kvm->arch.tdp_mmu_pages);
+
+	if (!sp->lpage_disallowed)
+		return;
+
 	if (shared)
 		spin_lock(&kvm->arch.tdp_mmu_pages_lock);
 	else
 		lockdep_assert_held_write(&kvm->mmu_lock);
 
-	list_del(&sp->link);
-	if (sp->lpage_disallowed)
-		unaccount_huge_nx_page(kvm, sp);
+	unaccount_huge_nx_page(kvm, sp);
 
 	if (shared)
 		spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
@@ -1119,9 +1121,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
 		tdp_mmu_set_spte(kvm, iter, spte);
 	}
 
-	spin_lock(&kvm->arch.tdp_mmu_pages_lock);
-	list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
-	spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+	atomic64_inc(&kvm->arch.tdp_mmu_pages);
 
 	return 0;
 }

base-commit: 88d1a6895b71b580b8fc98c23824aafa49d4948e
-- 
2.35.1.1094.g7c7d902a7c-goog