1 files changed, 203 insertions, 117 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 835426254e76..c8ebe542c565 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -14,6 +14,7 @@
  *   Yaniv Kamay  <yaniv@qumranet.com>
  *   Avi Kivity   <avi@qumranet.com>
  */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include "irq.h"
 #include "ioapic.h"
@@ -43,6 +44,7 @@
 #include <linux/uaccess.h>
 #include <linux/hash.h>
 #include <linux/kern_levels.h>
+#include <linux/kstrtox.h>
 #include <linux/kthread.h>
 
 #include <asm/page.h>
@@ -99,6 +101,13 @@ module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644);
  */
 bool tdp_enabled = false;
 
+static bool __ro_after_init tdp_mmu_allowed;
+
+#ifdef CONFIG_X86_64
+bool __read_mostly tdp_mmu_enabled = true;
+module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0444);
+#endif
+
 static int max_huge_page_level __read_mostly;
 static int tdp_root_level __read_mostly;
 static int max_tdp_level __read_mostly;
@@ -261,6 +270,17 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
 	kvm_flush_remote_tlbs_with_range(kvm, &range);
 }
 
+static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index);
+
+/* Flush the range of guest memory mapped by the given SPTE. */
+static void kvm_flush_remote_tlbs_sptep(struct kvm *kvm, u64 *sptep)
+{
+	struct kvm_mmu_page *sp = sptep_to_sp(sptep);
+	gfn_t gfn = kvm_mmu_page_get_gfn(sp, spte_index(sptep));
+
+	kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level);
+}
+
 static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
 			   unsigned int access)
 {
@@ -609,9 +629,14 @@ static bool mmu_spte_age(u64 *sptep)
 	return true;
 }
 
+static inline bool is_tdp_mmu_active(struct kvm_vcpu *vcpu)
+{
+	return tdp_mmu_enabled && vcpu->arch.mmu->root_role.direct;
+}
+
 static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu)
 {
-	if (is_tdp_mmu(vcpu->arch.mmu)) {
+	if (is_tdp_mmu_active(vcpu)) {
 		kvm_tdp_mmu_walk_lockless_begin();
 	} else {
 		/*
@@ -630,7 +655,7 @@ static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu)
 
 static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
 {
-	if (is_tdp_mmu(vcpu->arch.mmu)) {
+	if (is_tdp_mmu_active(vcpu)) {
 		kvm_tdp_mmu_walk_lockless_end();
 	} else {
 		/*
@@ -800,7 +825,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	kvm_mmu_gfn_disallow_lpage(slot, gfn);
 
 	if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
-		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+		kvm_flush_remote_tlbs_gfn(kvm, gfn, PG_LEVEL_4K);
 }
 
 void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -1174,8 +1199,7 @@ static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush)
 	drop_spte(kvm, sptep);
 
 	if (flush)
-		kvm_flush_remote_tlbs_with_address(kvm, sp->gfn,
-			KVM_PAGES_PER_HPAGE(sp->role.level));
+		kvm_flush_remote_tlbs_sptep(kvm, sptep);
 }
 
 /*
@@ -1279,7 +1303,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 {
 	struct kvm_rmap_head *rmap_head;
 
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
 				slot->base_gfn + gfn_offset, mask, true);
 
@@ -1312,7 +1336,7 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 {
 	struct kvm_rmap_head *rmap_head;
 
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot,
 				slot->base_gfn + gfn_offset, mask, false);
 
@@ -1395,7 +1419,7 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 		}
 	}
 
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		write_protected |=
 			kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn, min_level);
 
@@ -1456,7 +1480,7 @@ restart:
 	}
 
 	if (need_flush && kvm_available_flush_tlb_with_range()) {
-		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
+		kvm_flush_remote_tlbs_gfn(kvm, gfn, level);
 		return false;
 	}
 
@@ -1558,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (kvm_memslots_have_rmaps(kvm))
 		flush = kvm_handle_gfn_range(kvm, range, kvm_zap_rmap);
 
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
 
 	return flush;
@@ -1571,7 +1595,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (kvm_memslots_have_rmaps(kvm))
 		flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmap);
 
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range);
 
 	return flush;
@@ -1626,8 +1650,7 @@ static void __rmap_add(struct kvm *kvm,
 		kvm->stat.max_mmu_rmap_size = rmap_count;
 	if (rmap_count > RMAP_RECYCLE_THRESHOLD) {
 		kvm_zap_all_rmap_sptes(kvm, rmap_head);
-		kvm_flush_remote_tlbs_with_address(
-				kvm, sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level));
+		kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level);
 	}
 }
 
@@ -1646,7 +1669,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (kvm_memslots_have_rmaps(kvm))
 		young = kvm_handle_gfn_range(kvm, range, kvm_age_rmap);
 
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		young |= kvm_tdp_mmu_age_gfn_range(kvm, range);
 
 	return young;
@@ -1659,7 +1682,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (kvm_memslots_have_rmaps(kvm))
 		young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmap);
 
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		young |= kvm_tdp_mmu_test_age_gfn(kvm, range);
 
 	return young;
@@ -1921,7 +1944,7 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 		return true;
 
 	/* TDP MMU pages do not use the MMU generation. */
-	return !sp->tdp_mmu_page &&
+	return !is_tdp_mmu_page(sp) &&
 	       unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
 }
 
@@ -2355,7 +2378,16 @@ static void __link_shadow_page(struct kvm *kvm,
 
 	mmu_page_add_parent_pte(cache, sp, sptep);
 
-	if (sp->unsync_children || sp->unsync)
+	/*
+	 * The non-direct sub-pagetable must be updated before linking.  For
+	 * L1 sp, the pagetable is updated via kvm_sync_page() in
+	 * kvm_mmu_find_shadow_page() without write-protecting the gfn,
+	 * so sp->unsync can be true or false.  For higher level non-direct
+	 * sp, the pagetable is updated/synced via mmu_sync_children() in
+	 * FNAME(fetch)(), so sp->unsync_children can only be false.
+	 * WARN_ON_ONCE() if anything happens unexpectedly.
+	 */
+	if (WARN_ON_ONCE(sp->unsync_children) || sp->unsync)
 		mark_unsync(sptep);
 }
 
@@ -2383,7 +2415,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			return;
 
 		drop_parent_pte(child, sptep);
-		kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1);
+		kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep);
 	}
 }
 
@@ -2867,8 +2899,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	}
 
 	if (flush)
-		kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn,
-				KVM_PAGES_PER_HPAGE(level));
+		kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level);
 
 	pgprintk("%s: setting spte %llx\n", __func__, *sptep);
 
@@ -3116,11 +3147,11 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
 	    !is_large_pte(spte) &&
 	    spte_to_child_sp(spte)->nx_huge_page_disallowed) {
 		/*
-		 * A small SPTE exists for this pfn, but FNAME(fetch)
-		 * and __direct_map would like to create a large PTE
-		 * instead: just force them to go down another level,
-		 * patching back for them into pfn the next 9 bits of
-		 * the address.
+		 * A small SPTE exists for this pfn, but FNAME(fetch),
+		 * direct_map(), or kvm_tdp_mmu_map() would like to create a
+		 * large PTE instead: just force them to go down another level,
+		 * patching back for them into pfn the next 9 bits of the
+		 * address.
 		 */
 		u64 page_mask = KVM_PAGES_PER_HPAGE(cur_level) -
 				KVM_PAGES_PER_HPAGE(cur_level - 1);
@@ -3129,7 +3160,7 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
 	}
 }
 
-static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+static int direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_shadow_walk_iterator it;
 	struct kvm_mmu_page *sp;
@@ -3147,7 +3178,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 		if (fault->nx_huge_page_workaround_enabled)
 			disallowed_hugepage_adjust(fault, *it.sptep, it.level);
 
-		base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+		base_gfn = gfn_round_for_level(fault->gfn, it.level);
 		if (it.level == fault->goal_level)
 			break;
 
@@ -3173,14 +3204,16 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	return ret;
 }
 
-static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk)
+static void kvm_send_hwpoison_signal(struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk);
+	unsigned long hva = gfn_to_hva_memslot(slot, gfn);
+
+	send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, PAGE_SHIFT, current);
 }
 
-static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
+static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
-	if (is_sigpending_pfn(pfn)) {
+	if (is_sigpending_pfn(fault->pfn)) {
 		kvm_handle_signal_exit(vcpu);
 		return -EINTR;
 	}
@@ -3190,43 +3223,43 @@ static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
 	 * into the spte otherwise read access on readonly gfn also can
 	 * caused mmio page fault and treat it as mmio access.
 	 */
-	if (pfn == KVM_PFN_ERR_RO_FAULT)
+	if (fault->pfn == KVM_PFN_ERR_RO_FAULT)
 		return RET_PF_EMULATE;
 
-	if (pfn == KVM_PFN_ERR_HWPOISON) {
-		kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current);
+	if (fault->pfn == KVM_PFN_ERR_HWPOISON) {
+		kvm_send_hwpoison_signal(fault->slot, fault->gfn);
 		return RET_PF_RETRY;
 	}
 
 	return -EFAULT;
 }
 
-static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
-			       unsigned int access)
+static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu,
+				   struct kvm_page_fault *fault,
+				   unsigned int access)
 {
-	/* The pfn is invalid, report the error! */
-	if (unlikely(is_error_pfn(fault->pfn)))
-		return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn);
+	gva_t gva = fault->is_tdp ? 0 : fault->addr;
 
-	if (unlikely(!fault->slot)) {
-		gva_t gva = fault->is_tdp ? 0 : fault->addr;
+	vcpu_cache_mmio_info(vcpu, gva, fault->gfn,
+			     access & shadow_mmio_access_mask);
 
-		vcpu_cache_mmio_info(vcpu, gva, fault->gfn,
-				     access & shadow_mmio_access_mask);
-		/*
-		 * If MMIO caching is disabled, emulate immediately without
-		 * touching the shadow page tables as attempting to install an
-		 * MMIO SPTE will just be an expensive nop.  Do not cache MMIO
-		 * whose gfn is greater than host.MAXPHYADDR, any guest that
-		 * generates such gfns is running nested and is being tricked
-		 * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if
-		 * and only if L1's MAXPHYADDR is inaccurate with respect to
-		 * the hardware's).
-		 */
-		if (unlikely(!enable_mmio_caching) ||
-		    unlikely(fault->gfn > kvm_mmu_max_gfn()))
-			return RET_PF_EMULATE;
-	}
+	/*
+	 * If MMIO caching is disabled, emulate immediately without
+	 * touching the shadow page tables as attempting to install an
+	 * MMIO SPTE will just be an expensive nop.
+	 */
+	if (unlikely(!enable_mmio_caching))
+		return RET_PF_EMULATE;
+
+	/*
+	 * Do not create an MMIO SPTE for a gfn greater than host.MAXPHYADDR,
+	 * any guest that generates such gfns is running nested and is being
+	 * tricked by L0 userspace (you can observe gfn > L1.MAXPHYADDR if and
+	 * only if L1's MAXPHYADDR is inaccurate with respect to the
+	 * hardware's).
+	 */
+	if (unlikely(fault->gfn > kvm_mmu_max_gfn()))
+		return RET_PF_EMULATE;
 
 	return RET_PF_CONTINUE;
 }
@@ -3350,7 +3383,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	do {
 		u64 new_spte;
 
-		if (is_tdp_mmu(vcpu->arch.mmu))
+		if (tdp_mmu_enabled)
 			sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->addr, &spte);
 		else
 			sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte);
@@ -3433,8 +3466,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 		}
 
 		if (++retry_count > 4) {
-			printk_once(KERN_WARNING
-				"kvm: Fast #PF retrying more than 4 times.\n");
+			pr_warn_once("Fast #PF retrying more than 4 times.\n");
 			break;
 		}
 
@@ -3596,7 +3628,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 	if (r < 0)
 		goto out_unlock;
 
-	if (is_tdp_mmu_enabled(vcpu->kvm)) {
+	if (tdp_mmu_enabled) {
 		root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu);
 		mmu->root.hpa = root;
 	} else if (shadow_root_level >= PT64_ROOT_4LEVEL) {
@@ -4026,7 +4058,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 
 	walk_shadow_page_lockless_begin(vcpu);
 
-	if (is_tdp_mmu(vcpu->arch.mmu))
+	if (is_tdp_mmu_active(vcpu))
 		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
 	else
 		leaf = get_walk(vcpu, addr, sptes, &root);
@@ -4174,7 +4206,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
 }
 
-static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
+static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	struct kvm_memory_slot *slot = fault->slot;
 	bool async;
@@ -4235,12 +4267,33 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	return RET_PF_CONTINUE;
 }
 
+static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
+			   unsigned int access)
+{
+	int ret;
+
+	fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+	smp_rmb();
+
+	ret = __kvm_faultin_pfn(vcpu, fault);
+	if (ret != RET_PF_CONTINUE)
+		return ret;
+
+	if (unlikely(is_error_pfn(fault->pfn)))
+		return kvm_handle_error_pfn(vcpu, fault);
+
+	if (unlikely(!fault->slot))
+		return kvm_handle_noslot_fault(vcpu, fault, access);
+
+	return RET_PF_CONTINUE;
+}
+
 /*
  * Returns true if the page fault is stale and needs to be retried, i.e. if the
  * root was invalidated by a memslot update or a relevant mmu_notifier fired.
  */
 static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
-				struct kvm_page_fault *fault, int mmu_seq)
+				struct kvm_page_fault *fault)
 {
 	struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa);
 
@@ -4260,19 +4313,13 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 		return true;
 
 	return fault->slot &&
-	       mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+	       mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva);
 }
 
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
-	bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu);
-
-	unsigned long mmu_seq;
 	int r;
 
-	fault->gfn = fault->addr >> PAGE_SHIFT;
-	fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn);
-
 	if (page_fault_handle_page_track(vcpu, fault))
 		return RET_PF_EMULATE;
 
@@ -4284,41 +4331,24 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	if (r)
 		return r;
 
-	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
-	smp_rmb();
-
-	r = kvm_faultin_pfn(vcpu, fault);
-	if (r != RET_PF_CONTINUE)
-		return r;
-
-	r = handle_abnormal_pfn(vcpu, fault, ACC_ALL);
+	r = kvm_faultin_pfn(vcpu, fault, ACC_ALL);
 	if (r != RET_PF_CONTINUE)
 		return r;
 
 	r = RET_PF_RETRY;
+	write_lock(&vcpu->kvm->mmu_lock);
 
-	if (is_tdp_mmu_fault)
-		read_lock(&vcpu->kvm->mmu_lock);
-	else
-		write_lock(&vcpu->kvm->mmu_lock);
+	if (is_page_fault_stale(vcpu, fault))
+		goto out_unlock;
 
-	if (is_page_fault_stale(vcpu, fault, mmu_seq))
+	r = make_mmu_pages_available(vcpu);
+	if (r)
 		goto out_unlock;
 
-	if (is_tdp_mmu_fault) {
-		r = kvm_tdp_mmu_map(vcpu, fault);
-	} else {
-		r = make_mmu_pages_available(vcpu);
-		if (r)
-			goto out_unlock;
-		r = __direct_map(vcpu, fault);
-	}
+	r = direct_map(vcpu, fault);
 
 out_unlock:
-	if (is_tdp_mmu_fault)
-		read_unlock(&vcpu->kvm->mmu_lock);
-	else
-		write_unlock(&vcpu->kvm->mmu_lock);
+	write_unlock(&vcpu->kvm->mmu_lock);
 	kvm_release_pfn_clean(fault->pfn);
 	return r;
 }
@@ -4366,6 +4396,42 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 }
 EXPORT_SYMBOL_GPL(kvm_handle_page_fault);
 
+#ifdef CONFIG_X86_64
+static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu,
+				  struct kvm_page_fault *fault)
+{
+	int r;
+
+	if (page_fault_handle_page_track(vcpu, fault))
+		return RET_PF_EMULATE;
+
+	r = fast_page_fault(vcpu, fault);
+	if (r != RET_PF_INVALID)
+		return r;
+
+	r = mmu_topup_memory_caches(vcpu, false);
+	if (r)
+		return r;
+
+	r = kvm_faultin_pfn(vcpu, fault, ACC_ALL);
+	if (r != RET_PF_CONTINUE)
+		return r;
+
+	r = RET_PF_RETRY;
+	read_lock(&vcpu->kvm->mmu_lock);
+
+	if (is_page_fault_stale(vcpu, fault))
+		goto out_unlock;
+
+	r = kvm_tdp_mmu_map(vcpu, fault);
+
+out_unlock:
+	read_unlock(&vcpu->kvm->mmu_lock);
+	kvm_release_pfn_clean(fault->pfn);
+	return r;
+}
+#endif
+
 int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	/*
@@ -4383,13 +4449,19 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
 		for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) {
 			int page_num = KVM_PAGES_PER_HPAGE(fault->max_level);
-			gfn_t base = (fault->addr >> PAGE_SHIFT) & ~(page_num - 1);
+			gfn_t base = gfn_round_for_level(fault->gfn,
+							 fault->max_level);
 
 			if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num))
 				break;
 		}
 	}
 
+#ifdef CONFIG_X86_64
+	if (tdp_mmu_enabled)
+		return kvm_tdp_mmu_page_fault(vcpu, fault);
+#endif
+
 	return direct_page_fault(vcpu, fault);
 }
 
@@ -4494,10 +4566,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd)
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
 	union kvm_mmu_page_role new_role = mmu->root_role;
 
-	if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role)) {
-		/* kvm_mmu_ensure_valid_pgd will set up a new root.  */
+	/*
+	 * Return immediately if no usable root was found, kvm_mmu_reload()
+	 * will establish a valid root prior to the next VM-Enter.
+	 */
+	if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role))
 		return;
-	}
 
 	/*
 	 * It's possible that the cached previous root page is obsolete because
@@ -5719,6 +5793,9 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level,
 	tdp_root_level = tdp_forced_root_level;
 	max_tdp_level = tdp_max_root_level;
 
+#ifdef CONFIG_X86_64
+	tdp_mmu_enabled = tdp_mmu_allowed && tdp_enabled;
+#endif
 	/*
 	 * max_huge_page_level reflects KVM's MMU capabilities irrespective
 	 * of kernel support, e.g. KVM may be capable of using 1GB pages when
@@ -5966,7 +6043,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
 	 * write and in the same critical section as making the reload request,
 	 * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield.
 	 */
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		kvm_tdp_mmu_invalidate_all_roots(kvm);
 
 	/*
@@ -5991,7 +6068,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
 	 * Deferring the zap until the final reference to the root is put would
 	 * lead to use-after-free.
 	 */
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		kvm_tdp_mmu_zap_invalidated_roots(kvm);
 }
 
@@ -6017,9 +6094,11 @@ 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_init_tdp_mmu(kvm);
-	if (r < 0)
-		return r;
+	if (tdp_mmu_enabled) {
+		r = kvm_mmu_init_tdp_mmu(kvm);
+		if (r < 0)
+			return r;
+	}
 
 	node->track_write = kvm_mmu_pte_write;
 	node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
@@ -6049,7 +6128,8 @@ void kvm_mmu_uninit_vm(struct kvm *kvm)
 
 	kvm_page_track_unregister_notifier(kvm, node);
 
-	kvm_mmu_uninit_tdp_mmu(kvm);
+	if (tdp_mmu_enabled)
+		kvm_mmu_uninit_tdp_mmu(kvm);
 
 	mmu_free_vm_memory_caches(kvm);
 }
@@ -6103,7 +6183,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
-	if (is_tdp_mmu_enabled(kvm)) {
+	if (tdp_mmu_enabled) {
 		for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
 			flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start,
 						      gfn_end, true, flush);
@@ -6136,7 +6216,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
 		write_unlock(&kvm->mmu_lock);
 	}
 
-	if (is_tdp_mmu_enabled(kvm)) {
+	if (tdp_mmu_enabled) {
 		read_lock(&kvm->mmu_lock);
 		kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level);
 		read_unlock(&kvm->mmu_lock);
@@ -6379,7 +6459,7 @@ void kvm_mmu_try_split_huge_pages(struct kvm *kvm,
 				   u64 start, u64 end,
 				   int target_level)
 {
-	if (!is_tdp_mmu_enabled(kvm))
+	if (!tdp_mmu_enabled)
 		return;
 
 	if (kvm_memslots_have_rmaps(kvm))
@@ -6400,7 +6480,7 @@ void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm,
 	u64 start = memslot->base_gfn;
 	u64 end = start + memslot->npages;
 
-	if (!is_tdp_mmu_enabled(kvm))
+	if (!tdp_mmu_enabled)
 		return;
 
 	if (kvm_memslots_have_rmaps(kvm)) {
@@ -6450,8 +6530,7 @@ restart:
 			kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
 
 			if (kvm_available_flush_tlb_with_range())
-				kvm_flush_remote_tlbs_with_address(kvm, sp->gfn,
-					KVM_PAGES_PER_HPAGE(sp->role.level));
+				kvm_flush_remote_tlbs_sptep(kvm, sptep);
 			else
 				need_tlb_flush = 1;
 
@@ -6483,7 +6562,7 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 		write_unlock(&kvm->mmu_lock);
 	}
 
-	if (is_tdp_mmu_enabled(kvm)) {
+	if (tdp_mmu_enabled) {
 		read_lock(&kvm->mmu_lock);
 		kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot);
 		read_unlock(&kvm->mmu_lock);
@@ -6518,7 +6597,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 		write_unlock(&kvm->mmu_lock);
 	}
 
-	if (is_tdp_mmu_enabled(kvm)) {
+	if (tdp_mmu_enabled) {
 		read_lock(&kvm->mmu_lock);
 		kvm_tdp_mmu_clear_dirty_slot(kvm, memslot);
 		read_unlock(&kvm->mmu_lock);
@@ -6553,7 +6632,7 @@ restart:
 
 	kvm_mmu_commit_zap_page(kvm, &invalid_list);
 
-	if (is_tdp_mmu_enabled(kvm))
+	if (tdp_mmu_enabled)
 		kvm_tdp_mmu_zap_all(kvm);
 
 	write_unlock(&kvm->mmu_lock);
@@ -6579,7 +6658,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen)
 	 * zap all shadow pages.
 	 */
 	if (unlikely(gen == 0)) {
-		kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n");
+		kvm_debug_ratelimited("zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_zap_all_fast(kvm);
 	}
 }
@@ -6684,7 +6763,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
 		new_val = 1;
 	else if (sysfs_streq(val, "auto"))
 		new_val = get_nx_auto_mode();
-	else if (strtobool(val, &new_val) < 0)
+	else if (kstrtobool(val, &new_val) < 0)
 		return -EINVAL;
 
 	__set_nx_huge_pages(new_val);
@@ -6718,6 +6797,13 @@ void __init kvm_mmu_x86_module_init(void)
 	if (nx_huge_pages == -1)
 		__set_nx_huge_pages(get_nx_auto_mode());
 
+	/*
+	 * Snapshot userspace's desire to enable the TDP MMU. Whether or not the
+	 * TDP MMU is actually enabled is determined in kvm_configure_mmu()
+	 * when the vendor module is loaded.
+	 */
+	tdp_mmu_allowed = tdp_mmu_enabled;
+
 	kvm_mmu_spte_module_init();
 }