KVM: x86/mmu: count KVM mmu usage in secondary pagetable stats.

Count the pages used by KVM mmu on x86 in memory stats under secondary
pagetable stats (e.g. "SecPageTables" in /proc/meminfo) to give better
visibility into the memory consumption of KVM mmu in a similar way to
how normal user page tables are accounted.

Add the inner helper in common KVM, ARM will also use it to count stats
in a future commit.

Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Acked-by: Marc Zyngier <maz@kernel.org> # generic KVM changes
Link: https://lore.kernel.org/r/20220823004639.2387269-3-yosryahmed@google.com
Link: https://lore.kernel.org/r/20220823004639.2387269-4-yosryahmed@google.com
[sean: squash x86 usage to workaround modpost issues]
Signed-off-by: Sean Christopherson <seanjc@google.com>

3 files changed, 39 insertions, 2 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d25d55b1f0b5..32b60a6b83bd 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1665,6 +1665,18 @@ static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
 }
 
+static void kvm_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	kvm_mod_used_mmu_pages(kvm, +1);
+	kvm_account_pgtable_pages((void *)sp->spt, +1);
+}
+
+static void kvm_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	kvm_mod_used_mmu_pages(kvm, -1);
+	kvm_account_pgtable_pages((void *)sp->spt, -1);
+}
+
 static void kvm_mmu_free_shadow_page(struct kvm_mmu_page *sp)
 {
 	MMU_WARN_ON(!is_empty_shadow_page(sp->spt));
@@ -2122,7 +2134,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm,
 	 */
 	sp->mmu_valid_gen = kvm->arch.mmu_valid_gen;
 	list_add(&sp->link, &kvm->arch.active_mmu_pages);
-	kvm_mod_used_mmu_pages(kvm, +1);
+	kvm_account_mmu_page(kvm, sp);
 
 	sp->gfn = gfn;
 	sp->role = role;
@@ -2456,7 +2468,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 			list_add(&sp->link, invalid_list);
 		else
 			list_move(&sp->link, invalid_list);
-		kvm_mod_used_mmu_pages(kvm, -1);
+		kvm_unaccount_mmu_page(kvm, sp);
 	} else {
 		/*
 		 * Remove the active root from the active page list, the root
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index bf2ccf9debca..672f0432d777 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -372,6 +372,16 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
 	}
 }
 
+static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	kvm_account_pgtable_pages((void *)sp->spt, +1);
+}
+
+static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	kvm_account_pgtable_pages((void *)sp->spt, -1);
+}
+
 /**
  * tdp_mmu_unlink_sp() - Remove a shadow page from the list of used pages
  *
@@ -384,6 +394,7 @@ 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)
 {
+	tdp_unaccount_mmu_page(kvm, sp);
 	if (shared)
 		spin_lock(&kvm->arch.tdp_mmu_pages_lock);
 	else
@@ -1132,6 +1143,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
 	if (account_nx)
 		account_huge_nx_page(kvm, sp);
 	spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+	tdp_account_mmu_page(kvm, sp);
 
 	return 0;
 }
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f4519d3689e1..04c7e5f2f727 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2248,6 +2248,19 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
 #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
 
 /*
+ * If more than one page is being (un)accounted, @virt must be the address of
+ * the first page of a block of pages what were allocated together (i.e
+ * accounted together).
+ *
+ * kvm_account_pgtable_pages() is thread-safe because mod_lruvec_page_state()
+ * is thread-safe.
+ */
+static inline void kvm_account_pgtable_pages(void *virt, int nr)
+{
+	mod_lruvec_page_state(virt_to_page(virt), NR_SECONDARY_PAGETABLE, nr);
+}
+
+/*
  * This defines how many reserved entries we want to keep before we
  * kick the vcpu to the userspace to avoid dirty ring full.  This
  * value can be tuned to higher if e.g. PML is enabled on the host.