[PATCH v2 3/3] KVM: x86/mmu: Defer allocation of shadow MMU's hashed page list

[Sean Christopherson <seanjc@google.com>]

When the TDP MMU is enabled, i.e. when the shadow MMU isn't used until a
nested TDP VM is run, defer allocation of the array of hashed lists used
to track shadow MMU pages until the first shadow root is allocated.

Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c | 40 ++++++++++++++++++++++++++++++----------
 1 file changed, 30 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 6b9c72405860..213009cdba15 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1982,14 +1982,25 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp)
 	return true;
 }
 
+static __ro_after_init HLIST_HEAD(empty_page_hash);
+
+static struct hlist_head *kvm_get_mmu_page_hash(struct kvm *kvm, gfn_t gfn)
+{
+	struct hlist_head *page_hash = READ_ONCE(kvm->arch.mmu_page_hash);
+
+	if (!page_hash)
+		return &empty_page_hash;
+
+	return &page_hash[kvm_page_table_hashfn(gfn)];
+}
+
 #define for_each_valid_sp(_kvm, _sp, _list)				\
 	hlist_for_each_entry(_sp, _list, hash_link)			\
 		if (is_obsolete_sp((_kvm), (_sp))) {			\
 		} else
 
 #define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn)		\
-	for_each_valid_sp(_kvm, _sp,					\
-	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)])	\
+	for_each_valid_sp(_kvm, _sp, kvm_get_mmu_page_hash(_kvm, _gfn))	\
 		if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else
 
 static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
@@ -2357,6 +2368,7 @@ static struct kvm_mmu_page *__kvm_mmu_get_shadow_page(struct kvm *kvm,
 	struct kvm_mmu_page *sp;
 	bool created = false;
 
+	BUG_ON(!kvm->arch.mmu_page_hash);
 	sp_list = &kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)];
 
 	sp = kvm_mmu_find_shadow_page(kvm, vcpu, gfn, sp_list, role);
@@ -3884,11 +3896,14 @@ static int kvm_mmu_alloc_page_hash(struct kvm *kvm)
 {
 	typeof(kvm->arch.mmu_page_hash) h;
 
+	if (kvm->arch.mmu_page_hash)
+		return 0;
+
 	h = kcalloc(KVM_NUM_MMU_PAGES, sizeof(*h), GFP_KERNEL_ACCOUNT);
 	if (!h)
 		return -ENOMEM;
 
-	kvm->arch.mmu_page_hash = h;
+	WRITE_ONCE(kvm->arch.mmu_page_hash, h);
 	return 0;
 }
 
@@ -3911,9 +3926,13 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
 	if (kvm_shadow_root_allocated(kvm))
 		goto out_unlock;
 
+	r = kvm_mmu_alloc_page_hash(kvm);
+	if (r)
+		goto out_unlock;
+
 	/*
-	 * Check if anything actually needs to be allocated, e.g. all metadata
-	 * will be allocated upfront if TDP is disabled.
+	 * Check if memslot metadata actually needs to be allocated, e.g. all
+	 * metadata will be allocated upfront if TDP is disabled.
 	 */
 	if (kvm_memslots_have_rmaps(kvm) &&
 	    kvm_page_track_write_tracking_enabled(kvm))
@@ -6694,12 +6713,13 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 	INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
 	spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
 
-	r = kvm_mmu_alloc_page_hash(kvm);
-	if (r)
-		return r;
-
-	if (tdp_mmu_enabled)
+	if (tdp_mmu_enabled) {
 		kvm_mmu_init_tdp_mmu(kvm);
+	} else {
+		r = kvm_mmu_alloc_page_hash(kvm);
+		if (r)
+			return r;
+	}
 
 	kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
 	kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
-- 
2.49.0.472.ge94155a9ec-goog