Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "RISCV:

   - Use common KVM implementation of MMU memory caches

   - SBI v0.2 support for Guest

   - Initial KVM selftests support

   - Fix to avoid spurious virtual interrupts after clearing hideleg CSR

   - Update email address for Anup and Atish

  ARM:

   - Simplification of the 'vcpu first run' by integrating it into KVM's
     'pid change' flow

   - Refactoring of the FP and SVE state tracking, also leading to a
     simpler state and less shared data between EL1 and EL2 in the nVHE
     case

   - Tidy up the header file usage for the nvhe hyp object

   - New HYP unsharing mechanism, finally allowing pages to be unmapped
     from the Stage-1 EL2 page-tables

   - Various pKVM cleanups around refcounting and sharing

   - A couple of vgic fixes for bugs that would trigger once the vcpu
     xarray rework is merged, but not sooner

   - Add minimal support for ARMv8.7's PMU extension

   - Rework kvm_pgtable initialisation ahead of the NV work

   - New selftest for IRQ injection

   - Teach selftests about the lack of default IPA space and page sizes

   - Expand sysreg selftest to deal with Pointer Authentication

   - The usual bunch of cleanups and doc update

  s390:

   - fix sigp sense/start/stop/inconsistency

   - cleanups

  x86:

   - Clean up some function prototypes more

   - improved gfn_to_pfn_cache with proper invalidation, used by Xen
     emulation

   - add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery

   - completely remove potential TOC/TOU races in nested SVM consistency
     checks

   - update some PMCs on emulated instructions

   - Intel AMX support (joint work between Thomas and Intel)

   - large MMU cleanups

   - module parameter to disable PMU virtualization

   - cleanup register cache

   - first part of halt handling cleanups

   - Hyper-V enlightened MSR bitmap support for nested hypervisors

  Generic:

   - clean up Makefiles

   - introduce CONFIG_HAVE_KVM_DIRTY_RING

   - optimize memslot lookup using a tree

   - optimize vCPU array usage by converting to xarray"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (268 commits)
  x86/fpu: Fix inline prefix warnings
  selftest: kvm: Add amx selftest
  selftest: kvm: Move struct kvm_x86_state to header
  selftest: kvm: Reorder vcpu_load_state steps for AMX
  kvm: x86: Disable interception for IA32_XFD on demand
  x86/fpu: Provide fpu_sync_guest_vmexit_xfd_state()
  kvm: selftests: Add support for KVM_CAP_XSAVE2
  kvm: x86: Add support for getting/setting expanded xstate buffer
  x86/fpu: Add uabi_size to guest_fpu
  kvm: x86: Add CPUID support for Intel AMX
  kvm: x86: Add XCR0 support for Intel AMX
  kvm: x86: Disable RDMSR interception of IA32_XFD_ERR
  kvm: x86: Emulate IA32_XFD_ERR for guest
  kvm: x86: Intercept #NM for saving IA32_XFD_ERR
  x86/fpu: Prepare xfd_err in struct fpu_guest
  kvm: x86: Add emulation for IA32_XFD
  x86/fpu: Provide fpu_update_guest_xfd() for IA32_XFD emulation
  kvm: x86: Enable dynamic xfeatures at KVM_SET_CPUID2
  x86/fpu: Provide fpu_enable_guest_xfd_features() for KVM
  x86/fpu: Add guest support to xfd_enable_feature()
  ...

8 files changed, 86 insertions, 142 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index fcdf3f8bb59a..1d275e9d76b5 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -335,12 +335,6 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 	return likely(kvm_gen == spte_gen);
 }
 
-static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
-                                  struct x86_exception *exception)
-{
-        return gpa;
-}
-
 static int is_cpuid_PSE36(void)
 {
 	return 1;
@@ -1454,7 +1448,7 @@ static bool kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
-	int need_flush = 0;
+	bool need_flush = false;
 	u64 new_spte;
 	kvm_pfn_t new_pfn;
 
@@ -1466,7 +1460,7 @@ restart:
 		rmap_printk("spte %p %llx gfn %llx (%d)\n",
 			    sptep, *sptep, gfn, level);
 
-		need_flush = 1;
+		need_flush = true;
 
 		if (pte_write(pte)) {
 			pte_list_remove(kvm, rmap_head, sptep);
@@ -1482,7 +1476,7 @@ restart:
 
 	if (need_flush && kvm_available_flush_tlb_with_range()) {
 		kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
-		return 0;
+		return false;
 	}
 
 	return need_flush;
@@ -1623,8 +1617,8 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 
 	for_each_rmap_spte(rmap_head, &iter, sptep)
 		if (is_accessed_spte(*sptep))
-			return 1;
-	return 0;
+			return true;
+	return false;
 }
 
 #define RMAP_RECYCLE_THRESHOLD 1000
@@ -2086,10 +2080,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	role = vcpu->arch.mmu->mmu_role.base;
 	role.level = level;
 	role.direct = direct;
-	if (role.direct)
-		role.gpte_is_8_bytes = true;
 	role.access = access;
-	if (!direct_mmu && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
+	if (role.has_4_byte_gpte) {
 		quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
 		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
 		role.quadrant = quadrant;
@@ -2565,10 +2557,10 @@ static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
 	return r;
 }
 
-static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+static void kvm_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
 	trace_kvm_mmu_unsync_page(sp);
-	++vcpu->kvm->stat.mmu_unsync;
+	++kvm->stat.mmu_unsync;
 	sp->unsync = 1;
 
 	kvm_mmu_mark_parents_unsync(sp);
@@ -2580,7 +2572,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
  * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must
  * be write-protected.
  */
-int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
+int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 			    gfn_t gfn, bool can_unsync, bool prefetch)
 {
 	struct kvm_mmu_page *sp;
@@ -2591,7 +2583,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	 * track machinery is used to write-protect upper-level shadow pages,
 	 * i.e. this guards the role.level == 4K assertion below!
 	 */
-	if (kvm_slot_page_track_is_active(vcpu, slot, gfn, KVM_PAGE_TRACK_WRITE))
+	if (kvm_slot_page_track_is_active(kvm, slot, gfn, KVM_PAGE_TRACK_WRITE))
 		return -EPERM;
 
 	/*
@@ -2600,7 +2592,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 	 * that case, KVM must complete emulation of the guest TLB flush before
 	 * allowing shadow pages to become unsync (writable by the guest).
 	 */
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
+	for_each_gfn_indirect_valid_sp(kvm, sp, gfn) {
 		if (!can_unsync)
 			return -EPERM;
 
@@ -2619,7 +2611,7 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 		 */
 		if (!locked) {
 			locked = true;
-			spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock);
+			spin_lock(&kvm->arch.mmu_unsync_pages_lock);
 
 			/*
 			 * Recheck after taking the spinlock, a different vCPU
@@ -2634,10 +2626,10 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
 		}
 
 		WARN_ON(sp->role.level != PG_LEVEL_4K);
-		kvm_unsync_page(vcpu, sp);
+		kvm_unsync_page(kvm, sp);
 	}
 	if (locked)
-		spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock);
+		spin_unlock(&kvm->arch.mmu_unsync_pages_lock);
 
 	/*
 	 * We need to ensure that the marking of unsync pages is visible
@@ -3409,7 +3401,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
-	int r = 0, i;
+	int r = 0, i, bkt;
 
 	/*
 	 * Check if this is the first shadow root being allocated before
@@ -3434,7 +3426,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
 
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
 		slots = __kvm_memslots(kvm, i);
-		kvm_for_each_memslot(slot, slots) {
+		kvm_for_each_memslot(slot, bkt, slots) {
 			/*
 			 * Both of these functions are no-ops if the target is
 			 * already allocated, so unconditionally calling both
@@ -3734,21 +3726,13 @@ void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
 }
 
-static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr,
-				  u32 access, struct x86_exception *exception)
+static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+				  gpa_t vaddr, u32 access,
+				  struct x86_exception *exception)
 {
 	if (exception)
 		exception->error_code = 0;
-	return vaddr;
-}
-
-static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr,
-					 u32 access,
-					 struct x86_exception *exception)
-{
-	if (exception)
-		exception->error_code = 0;
-	return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception);
+	return kvm_translate_gpa(vcpu, mmu, vaddr, access, exception);
 }
 
 static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
@@ -3888,7 +3872,7 @@ static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
 	 * guest is writing the page which is write tracked which can
 	 * not be fixed by page fault handler.
 	 */
-	if (kvm_slot_page_track_is_active(vcpu, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE))
+	if (kvm_slot_page_track_is_active(vcpu->kvm, fault->slot, fault->gfn, KVM_PAGE_TRACK_WRITE))
 		return true;
 
 	return false;
@@ -4388,22 +4372,28 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 
 static void
 __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
-			    u64 pa_bits_rsvd, bool execonly)
+			    u64 pa_bits_rsvd, bool execonly, int huge_page_level)
 {
 	u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51);
+	u64 large_1g_rsvd = 0, large_2m_rsvd = 0;
 	u64 bad_mt_xwr;
 
+	if (huge_page_level < PG_LEVEL_1G)
+		large_1g_rsvd = rsvd_bits(7, 7);
+	if (huge_page_level < PG_LEVEL_2M)
+		large_2m_rsvd = rsvd_bits(7, 7);
+
 	rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7);
 	rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7);
-	rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6);
-	rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6);
+	rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6) | large_1g_rsvd;
+	rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6) | large_2m_rsvd;
 	rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd;
 
 	/* large page */
 	rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4];
 	rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3];
-	rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29);
-	rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20);
+	rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29) | large_1g_rsvd;
+	rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20) | large_2m_rsvd;
 	rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0];
 
 	bad_mt_xwr = 0xFFull << (2 * 8);	/* bits 3..5 must not be 2 */
@@ -4419,10 +4409,11 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
 }
 
 static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
-		struct kvm_mmu *context, bool execonly)
+		struct kvm_mmu *context, bool execonly, int huge_page_level)
 {
 	__reset_rsvds_bits_mask_ept(&context->guest_rsvd_check,
-				    vcpu->arch.reserved_gpa_bits, execonly);
+				    vcpu->arch.reserved_gpa_bits, execonly,
+				    huge_page_level);
 }
 
 static inline u64 reserved_hpa_bits(void)
@@ -4498,7 +4489,8 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 					false, true);
 	else
 		__reset_rsvds_bits_mask_ept(shadow_zero_check,
-					    reserved_hpa_bits(), false);
+					    reserved_hpa_bits(), false,
+					    max_huge_page_level);
 
 	if (!shadow_me_mask)
 		return;
@@ -4518,7 +4510,8 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 				struct kvm_mmu *context, bool execonly)
 {
 	__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
-				    reserved_hpa_bits(), execonly);
+				    reserved_hpa_bits(), execonly,
+				    max_huge_page_level);
 }
 
 #define BYTE_MASK(access) \
@@ -4767,7 +4760,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu,
 	role.base.ad_disabled = (shadow_accessed_mask == 0);
 	role.base.level = kvm_mmu_get_tdp_level(vcpu);
 	role.base.direct = true;
-	role.base.gpte_is_8_bytes = true;
+	role.base.has_4_byte_gpte = false;
 
 	return role;
 }
@@ -4812,7 +4805,7 @@ kvm_calc_shadow_root_page_role_common(struct kvm_vcpu *vcpu,
 
 	role.base.smep_andnot_wp = role.ext.cr4_smep && !____is_cr0_wp(regs);
 	role.base.smap_andnot_wp = role.ext.cr4_smap && !____is_cr0_wp(regs);
-	role.base.gpte_is_8_bytes = ____is_cr0_pg(regs) && ____is_cr4_pae(regs);
+	role.base.has_4_byte_gpte = ____is_cr0_pg(regs) && !____is_cr4_pae(regs);
 
 	return role;
 }
@@ -4911,7 +4904,7 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
 	role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm;
 
 	role.base.level = level;
-	role.base.gpte_is_8_bytes = true;
+	role.base.has_4_byte_gpte = false;
 	role.base.direct = false;
 	role.base.ad_disabled = !accessed_dirty;
 	role.base.guest_mode = true;
@@ -4926,7 +4919,8 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
 }
 
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
-			     bool accessed_dirty, gpa_t new_eptp)
+			     int huge_page_level, bool accessed_dirty,
+			     gpa_t new_eptp)
 {
 	struct kvm_mmu *context = &vcpu->arch.guest_mmu;
 	u8 level = vmx_eptp_page_walk_level(new_eptp);
@@ -4953,7 +4947,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 
 	update_permission_bitmask(context, true);
 	context->pkru_mask = 0;
-	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
+	reset_rsvds_bits_mask_ept(vcpu, context, execonly, huge_page_level);
 	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
@@ -5017,13 +5011,13 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 	 * the gva_to_gpa functions between mmu and nested_mmu are swapped.
 	 */
 	if (!is_paging(vcpu))
-		g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested;
+		g_context->gva_to_gpa = nonpaging_gva_to_gpa;
 	else if (is_long_mode(vcpu))
-		g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
+		g_context->gva_to_gpa = paging64_gva_to_gpa;
 	else if (is_pae(vcpu))
-		g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
+		g_context->gva_to_gpa = paging64_gva_to_gpa;
 	else
-		g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
+		g_context->gva_to_gpa = paging32_gva_to_gpa;
 
 	reset_guest_paging_metadata(vcpu, g_context);
 }
@@ -5188,7 +5182,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
 		 gpa, bytes, sp->role.word);
 
 	offset = offset_in_page(gpa);
-	pte_size = sp->role.gpte_is_8_bytes ? 8 : 4;
+	pte_size = sp->role.has_4_byte_gpte ? 4 : 8;
 
 	/*
 	 * Sometimes, the OS only writes the last one bytes to update status
@@ -5212,7 +5206,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
 	page_offset = offset_in_page(gpa);
 	level = sp->role.level;
 	*nspte = 1;
-	if (!sp->role.gpte_is_8_bytes) {
+	if (sp->role.has_4_byte_gpte) {
 		page_offset <<= 1;	/* 32->64 */
 		/*
 		 * A 32-bit pde maps 4MB while the shadow pdes map
@@ -5524,10 +5518,13 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
 
 	mmu->root_hpa = INVALID_PAGE;
 	mmu->root_pgd = 0;
-	mmu->translate_gpa = translate_gpa;
 	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
 		mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
 
+	/* vcpu->arch.guest_mmu isn't used when !tdp_enabled. */
+	if (!tdp_enabled && mmu == &vcpu->arch.guest_mmu)
+		return 0;
+
 	/*
 	 * When using PAE paging, the four PDPTEs are treated as 'root' pages,
 	 * while the PDP table is a per-vCPU construct that's allocated at MMU
@@ -5537,7 +5534,7 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
 	 * generally doesn't use PAE paging and can skip allocating the PDP
 	 * table.  The main exception, handled here, is SVM's 32-bit NPT.  The
 	 * other exception is for shadowing L1's 32-bit or PAE NPT on 64-bit
-	 * KVM; that horror is handled on-demand by mmu_alloc_shadow_roots().
+	 * KVM; that horror is handled on-demand by mmu_alloc_special_roots().
 	 */
 	if (tdp_enabled && kvm_mmu_get_tdp_level(vcpu) > PT32E_ROOT_LEVEL)
 		return 0;
@@ -5582,8 +5579,6 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu = &vcpu->arch.root_mmu;
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
 
-	vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
-
 	ret = __kvm_mmu_create(vcpu, &vcpu->arch.guest_mmu);
 	if (ret)
 		return ret;
@@ -5742,6 +5737,7 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 {
 	const struct kvm_memory_slot *memslot;
 	struct kvm_memslots *slots;
+	struct kvm_memslot_iter iter;
 	bool flush = false;
 	gfn_t start, end;
 	int i;
@@ -5751,10 +5747,12 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
 		slots = __kvm_memslots(kvm, i);
-		kvm_for_each_memslot(memslot, slots) {
+
+		kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) {
+			memslot = iter.slot;
 			start = max(gfn_start, memslot->base_gfn);
 			end = min(gfn_end, memslot->base_gfn + memslot->npages);
-			if (start >= end)
+			if (WARN_ON_ONCE(start >= end))
 				continue;
 
 			flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp,
@@ -5775,6 +5773,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 	bool flush;
 	int i;
 
+	if (WARN_ON_ONCE(gfn_end <= gfn_start))
+		return;
+
 	write_lock(&kvm->mmu_lock);
 
 	kvm_inc_notifier_count(kvm, gfn_start, gfn_end);
@@ -6164,30 +6165,6 @@ out:
 	return ret;
 }
 
-/*
- * Calculate mmu pages needed for kvm.
- */
-unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
-{
-	unsigned long nr_mmu_pages;
-	unsigned long nr_pages = 0;
-	struct kvm_memslots *slots;
-	struct kvm_memory_slot *memslot;
-	int i;
-
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		slots = __kvm_memslots(kvm, i);
-
-		kvm_for_each_memslot(memslot, slots)
-			nr_pages += memslot->npages;
-	}
-
-	nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
-	nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
-
-	return nr_mmu_pages;
-}
-
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_unload(vcpu);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 52c6527b1a06..da6166b5c377 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -104,7 +104,7 @@ static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
 	return kvm_mmu_role_as_id(sp->role);
 }
 
-static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
+static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp)
 {
 	/*
 	 * When using the EPT page-modification log, the GPAs in the CPU dirty
@@ -112,13 +112,12 @@ static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
 	 * on write protection to record dirty pages, which bypasses PML, since
 	 * writes now result in a vmexit.  Note, the check on CPU dirty logging
 	 * being enabled is mandatory as the bits used to denote WP-only SPTEs
-	 * are reserved for NPT w/ PAE (32-bit KVM).
+	 * are reserved for PAE paging (32-bit KVM).
 	 */
-	return vcpu->arch.mmu == &vcpu->arch.guest_mmu &&
-	       kvm_x86_ops.cpu_dirty_log_size;
+	return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode;
 }
 
-int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
+int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot,
 			    gfn_t gfn, bool can_unsync, bool prefetch);
 
 void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn);
diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
index b8151bbca36a..de5e8e4e1aa7 100644
--- a/arch/x86/kvm/mmu/mmutrace.h
+++ b/arch/x86/kvm/mmu/mmutrace.h
@@ -35,7 +35,7 @@
 			 " %snxe %sad root %u %s%c",			\
 			 __entry->mmu_valid_gen,			\
 			 __entry->gfn, role.level,			\
-			 role.gpte_is_8_bytes ? 8 : 4,			\
+			 role.has_4_byte_gpte ? 4 : 8,			\
 			 role.quadrant,					\
 			 role.direct ? " direct" : "",			\
 			 access_str[role.access],			\
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index cc4eb5b7fb76..68eb1fb548b6 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -173,9 +173,9 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);
 /*
  * check if the corresponding access on the specified guest page is tracked.
  */
-bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu,
-				   struct kvm_memory_slot *slot, gfn_t gfn,
-				   enum kvm_page_track_mode mode)
+bool kvm_slot_page_track_is_active(struct kvm *kvm,
+				   const struct kvm_memory_slot *slot,
+				   gfn_t gfn, enum kvm_page_track_mode mode)
 {
 	int index;
 
@@ -186,7 +186,7 @@ bool kvm_slot_page_track_is_active(struct kvm_vcpu *vcpu,
 		return false;
 
 	if (mode == KVM_PAGE_TRACK_WRITE &&
-	    !kvm_page_track_write_tracking_enabled(vcpu->kvm))
+	    !kvm_page_track_write_tracking_enabled(kvm))
 		return false;
 
 	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 708a5d297fe1..5b5bdac97c7b 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -403,9 +403,8 @@ retry_walk:
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
-		real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
-					      nested_access,
-					      &walker->fault);
+		real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(table_gfn),
+					     nested_access, &walker->fault);
 
 		/*
 		 * FIXME: This can happen if emulation (for of an INS/OUTS
@@ -467,7 +466,7 @@ retry_walk:
 	if (PTTYPE == 32 && walker->level > PG_LEVEL_4K && is_cpuid_PSE36())
 		gfn += pse36_gfn_delta(pte);
 
-	real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault);
+	real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(gfn), access, &walker->fault);
 	if (real_gpa == UNMAPPED_GVA)
 		return 0;
 
@@ -547,16 +546,6 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
 					access);
 }
 
-#if PTTYPE != PTTYPE_EPT
-static int FNAME(walk_addr_nested)(struct guest_walker *walker,
-				   struct kvm_vcpu *vcpu, gva_t addr,
-				   u32 access)
-{
-	return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu,
-					addr, access);
-}
-#endif
-
 static bool
 FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		     u64 *spte, pt_element_t gpte, bool no_dirty_log)
@@ -1000,50 +989,29 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 }
 
 /* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
-static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access,
+static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+			       gpa_t addr, u32 access,
 			       struct x86_exception *exception)
 {
 	struct guest_walker walker;
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
-	r = FNAME(walk_addr)(&walker, vcpu, addr, access);
-
-	if (r) {
-		gpa = gfn_to_gpa(walker.gfn);
-		gpa |= addr & ~PAGE_MASK;
-	} else if (exception)
-		*exception = walker.fault;
-
-	return gpa;
-}
-
-#if PTTYPE != PTTYPE_EPT
-/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */
-static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
-				      u32 access,
-				      struct x86_exception *exception)
-{
-	struct guest_walker walker;
-	gpa_t gpa = UNMAPPED_GVA;
-	int r;
-
 #ifndef CONFIG_X86_64
 	/* A 64-bit GVA should be impossible on 32-bit KVM. */
-	WARN_ON_ONCE(vaddr >> 32);
+	WARN_ON_ONCE((addr >> 32) && mmu == vcpu->arch.walk_mmu);
 #endif
 
-	r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access);
+	r = FNAME(walk_addr_generic)(&walker, vcpu, mmu, addr, access);
 
 	if (r) {
 		gpa = gfn_to_gpa(walker.gfn);
-		gpa |= vaddr & ~PAGE_MASK;
+		gpa |= addr & ~PAGE_MASK;
 	} else if (exception)
 		*exception = walker.fault;
 
 	return gpa;
 }
-#endif
 
 /*
  * Using the cached information from sp->gfns is safe because:
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index fad546df0bba..351b04ad62a1 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -91,7 +91,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
 }
 
 bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-	       struct kvm_memory_slot *slot,
+	       const struct kvm_memory_slot *slot,
 	       unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn,
 	       u64 old_spte, bool prefetch, bool can_unsync,
 	       bool host_writable, u64 *new_spte)
@@ -102,7 +102,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 
 	if (sp->role.ad_disabled)
 		spte |= SPTE_TDP_AD_DISABLED_MASK;
-	else if (kvm_vcpu_ad_need_write_protect(vcpu))
+	else if (kvm_mmu_page_ad_need_write_protect(sp))
 		spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK;
 
 	/*
@@ -162,7 +162,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		 * e.g. it's write-tracked (upper-level SPs) or has one or more
 		 * shadow pages and unsync'ing pages is not allowed.
 		 */
-		if (mmu_try_to_unsync_pages(vcpu, slot, gfn, can_unsync, prefetch)) {
+		if (mmu_try_to_unsync_pages(vcpu->kvm, slot, gfn, can_unsync, prefetch)) {
 			pgprintk("%s: found shadow page for %llx, marking ro\n",
 				 __func__, gfn);
 			wrprot = true;
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index cc432f9a966b..a4af2a42695c 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -330,7 +330,7 @@ static inline u64 get_mmio_spte_generation(u64 spte)
 }
 
 bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-	       struct kvm_memory_slot *slot,
+	       const struct kvm_memory_slot *slot,
 	       unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn,
 	       u64 old_spte, bool prefetch, bool can_unsync,
 	       bool host_writable, u64 *new_spte);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 1beb4ca90560..7b1bc816b7c3 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -165,7 +165,7 @@ static union kvm_mmu_page_role page_role_for_level(struct kvm_vcpu *vcpu,
 	role = vcpu->arch.mmu->mmu_role.base;
 	role.level = level;
 	role.direct = true;
-	role.gpte_is_8_bytes = true;
+	role.has_4_byte_gpte = false;
 	role.access = ACC_ALL;
 	role.ad_disabled = !shadow_accessed_mask;