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

Pull KVM updates from Paolo Bonzini:
 "Small release overall.

  x86:
   - miscellaneous fixes
   - AVIC support (local APIC virtualization, AMD version)

  s390:
   - polling for interrupts after a VCPU goes to halted state is now
     enabled for s390
   - use hardware provided information about facility bits that do not
     need any hypervisor activity, and other fixes for cpu models and
     facilities
   - improve perf output
   - floating interrupt controller improvements.

  MIPS:
   - miscellaneous fixes

  PPC:
   - bugfixes only

  ARM:
   - 16K page size support
   - generic firmware probing layer for timer and GIC

  Christoffer Dall (KVM-ARM maintainer) says:
    "There are a few changes in this pull request touching things
     outside KVM, but they should all carry the necessary acks and it
     made the merge process much easier to do it this way."

  though actually the irqchip maintainers' acks didn't make it into the
  patches.  Marc Zyngier, who is both irqchip and KVM-ARM maintainer,
  later acked at http://mid.gmane.org/573351D1.4060303@arm.com ('more
  formally and for documentation purposes')"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (82 commits)
  KVM: MTRR: remove MSR 0x2f8
  KVM: x86: make hwapic_isr_update and hwapic_irr_update look the same
  svm: Manage vcpu load/unload when enable AVIC
  svm: Do not intercept CR8 when enable AVIC
  svm: Do not expose x2APIC when enable AVIC
  KVM: x86: Introducing kvm_x86_ops.apicv_post_state_restore
  svm: Add VMEXIT handlers for AVIC
  svm: Add interrupt injection via AVIC
  KVM: x86: Detect and Initialize AVIC support
  svm: Introduce new AVIC VMCB registers
  KVM: split kvm_vcpu_wake_up from kvm_vcpu_kick
  KVM: x86: Introducing kvm_x86_ops VCPU blocking/unblocking hooks
  KVM: x86: Introducing kvm_x86_ops VM init/destroy hooks
  KVM: x86: Rename kvm_apic_get_reg to kvm_lapic_get_reg
  KVM: x86: Misc LAPIC changes to expose helper functions
  KVM: shrink halt polling even more for invalid wakeups
  KVM: s390: set halt polling to 80 microseconds
  KVM: halt_polling: provide a way to qualify wakeups during poll
  KVM: PPC: Book3S HV: Re-enable XICS fast path for irqfd-generated interrupts
  kvm: Conditionally register IRQ bypass consumer
  ...

2 files changed, 222 insertions, 188 deletions

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9ef013d86cc5..237d5d82f0af 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -444,7 +444,7 @@ static void update_vttbr(struct kvm *kvm)
 	kvm_next_vmid &= (1 << kvm_vmid_bits) - 1;
 
 	/* update vttbr to be used with the new vmid */
-	pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm));
+	pgd_phys = virt_to_phys(kvm->arch.pgd);
 	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
 	kvm->arch.vttbr = pgd_phys | vmid;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index be302128c5d7..45c43aecb8f2 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -43,11 +43,9 @@ static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
 
+#define S2_PGD_SIZE	(PTRS_PER_S2_PGD * sizeof(pgd_t))
 #define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
 
-#define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
-#define kvm_pud_huge(_x)	pud_huge(_x)
-
 #define KVM_S2PTE_FLAG_IS_IOMAP		(1UL << 0)
 #define KVM_S2_FLAG_LOGGING_ACTIVE	(1UL << 1)
 
@@ -69,14 +67,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
-	/*
-	 * This function also gets called when dealing with HYP page
-	 * tables. As HYP doesn't have an associated struct kvm (and
-	 * the HYP page tables are fairly static), we don't do
-	 * anything there.
-	 */
-	if (kvm)
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
+	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
 }
 
 /*
@@ -115,7 +106,7 @@ static bool kvm_is_device_pfn(unsigned long pfn)
  */
 static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
 {
-	if (!kvm_pmd_huge(*pmd))
+	if (!pmd_thp_or_huge(*pmd))
 		return;
 
 	pmd_clear(pmd);
@@ -155,29 +146,29 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
-static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
+static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
 {
-	pud_t *pud_table __maybe_unused = pud_offset(pgd, 0);
-	pgd_clear(pgd);
+	pud_t *pud_table __maybe_unused = stage2_pud_offset(pgd, 0UL);
+	stage2_pgd_clear(pgd);
 	kvm_tlb_flush_vmid_ipa(kvm, addr);
-	pud_free(NULL, pud_table);
+	stage2_pud_free(pud_table);
 	put_page(virt_to_page(pgd));
 }
 
-static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
+static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
-	pmd_t *pmd_table = pmd_offset(pud, 0);
-	VM_BUG_ON(pud_huge(*pud));
-	pud_clear(pud);
+	pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(pud, 0);
+	VM_BUG_ON(stage2_pud_huge(*pud));
+	stage2_pud_clear(pud);
 	kvm_tlb_flush_vmid_ipa(kvm, addr);
-	pmd_free(NULL, pmd_table);
+	stage2_pmd_free(pmd_table);
 	put_page(virt_to_page(pud));
 }
 
-static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
+static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 {
 	pte_t *pte_table = pte_offset_kernel(pmd, 0);
-	VM_BUG_ON(kvm_pmd_huge(*pmd));
+	VM_BUG_ON(pmd_thp_or_huge(*pmd));
 	pmd_clear(pmd);
 	kvm_tlb_flush_vmid_ipa(kvm, addr);
 	pte_free_kernel(NULL, pte_table);
@@ -204,7 +195,7 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
  * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
  * the IO subsystem will never hit in the cache.
  */
-static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
+static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
 		       phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t start_addr = addr;
@@ -226,21 +217,21 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
-	if (kvm_pte_table_empty(kvm, start_pte))
-		clear_pmd_entry(kvm, pmd, start_addr);
+	if (stage2_pte_table_empty(start_pte))
+		clear_stage2_pmd_entry(kvm, pmd, start_addr);
 }
 
-static void unmap_pmds(struct kvm *kvm, pud_t *pud,
+static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
 		       phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t next, start_addr = addr;
 	pmd_t *pmd, *start_pmd;
 
-	start_pmd = pmd = pmd_offset(pud, addr);
+	start_pmd = pmd = stage2_pmd_offset(pud, addr);
 	do {
-		next = kvm_pmd_addr_end(addr, end);
+		next = stage2_pmd_addr_end(addr, end);
 		if (!pmd_none(*pmd)) {
-			if (kvm_pmd_huge(*pmd)) {
+			if (pmd_thp_or_huge(*pmd)) {
 				pmd_t old_pmd = *pmd;
 
 				pmd_clear(pmd);
@@ -250,57 +241,64 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud,
 
 				put_page(virt_to_page(pmd));
 			} else {
-				unmap_ptes(kvm, pmd, addr, next);
+				unmap_stage2_ptes(kvm, pmd, addr, next);
 			}
 		}
 	} while (pmd++, addr = next, addr != end);
 
-	if (kvm_pmd_table_empty(kvm, start_pmd))
-		clear_pud_entry(kvm, pud, start_addr);
+	if (stage2_pmd_table_empty(start_pmd))
+		clear_stage2_pud_entry(kvm, pud, start_addr);
 }
 
-static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
+static void unmap_stage2_puds(struct kvm *kvm, pgd_t *pgd,
 		       phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t next, start_addr = addr;
 	pud_t *pud, *start_pud;
 
-	start_pud = pud = pud_offset(pgd, addr);
+	start_pud = pud = stage2_pud_offset(pgd, addr);
 	do {
-		next = kvm_pud_addr_end(addr, end);
-		if (!pud_none(*pud)) {
-			if (pud_huge(*pud)) {
+		next = stage2_pud_addr_end(addr, end);
+		if (!stage2_pud_none(*pud)) {
+			if (stage2_pud_huge(*pud)) {
 				pud_t old_pud = *pud;
 
-				pud_clear(pud);
+				stage2_pud_clear(pud);
 				kvm_tlb_flush_vmid_ipa(kvm, addr);
-
 				kvm_flush_dcache_pud(old_pud);
-
 				put_page(virt_to_page(pud));
 			} else {
-				unmap_pmds(kvm, pud, addr, next);
+				unmap_stage2_pmds(kvm, pud, addr, next);
 			}
 		}
 	} while (pud++, addr = next, addr != end);
 
-	if (kvm_pud_table_empty(kvm, start_pud))
-		clear_pgd_entry(kvm, pgd, start_addr);
+	if (stage2_pud_table_empty(start_pud))
+		clear_stage2_pgd_entry(kvm, pgd, start_addr);
 }
 
-
-static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
-			phys_addr_t start, u64 size)
+/**
+ * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
+ * @kvm:   The VM pointer
+ * @start: The intermediate physical base address of the range to unmap
+ * @size:  The size of the area to unmap
+ *
+ * Clear a range of stage-2 mappings, lowering the various ref-counts.  Must
+ * be called while holding mmu_lock (unless for freeing the stage2 pgd before
+ * destroying the VM), otherwise another faulting VCPU may come in and mess
+ * with things behind our backs.
+ */
+static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 {
 	pgd_t *pgd;
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
 
-	pgd = pgdp + kvm_pgd_index(addr);
+	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
 	do {
-		next = kvm_pgd_addr_end(addr, end);
-		if (!pgd_none(*pgd))
-			unmap_puds(kvm, pgd, addr, next);
+		next = stage2_pgd_addr_end(addr, end);
+		if (!stage2_pgd_none(*pgd))
+			unmap_stage2_puds(kvm, pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -322,11 +320,11 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
 	pmd_t *pmd;
 	phys_addr_t next;
 
-	pmd = pmd_offset(pud, addr);
+	pmd = stage2_pmd_offset(pud, addr);
 	do {
-		next = kvm_pmd_addr_end(addr, end);
+		next = stage2_pmd_addr_end(addr, end);
 		if (!pmd_none(*pmd)) {
-			if (kvm_pmd_huge(*pmd))
+			if (pmd_thp_or_huge(*pmd))
 				kvm_flush_dcache_pmd(*pmd);
 			else
 				stage2_flush_ptes(kvm, pmd, addr, next);
@@ -340,11 +338,11 @@ static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
 	pud_t *pud;
 	phys_addr_t next;
 
-	pud = pud_offset(pgd, addr);
+	pud = stage2_pud_offset(pgd, addr);
 	do {
-		next = kvm_pud_addr_end(addr, end);
-		if (!pud_none(*pud)) {
-			if (pud_huge(*pud))
+		next = stage2_pud_addr_end(addr, end);
+		if (!stage2_pud_none(*pud)) {
+			if (stage2_pud_huge(*pud))
 				kvm_flush_dcache_pud(*pud);
 			else
 				stage2_flush_pmds(kvm, pud, addr, next);
@@ -360,9 +358,9 @@ static void stage2_flush_memslot(struct kvm *kvm,
 	phys_addr_t next;
 	pgd_t *pgd;
 
-	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
+	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
 	do {
-		next = kvm_pgd_addr_end(addr, end);
+		next = stage2_pgd_addr_end(addr, end);
 		stage2_flush_puds(kvm, pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
@@ -391,6 +389,100 @@ static void stage2_flush_vm(struct kvm *kvm)
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
+static void clear_hyp_pgd_entry(pgd_t *pgd)
+{
+	pud_t *pud_table __maybe_unused = pud_offset(pgd, 0UL);
+	pgd_clear(pgd);
+	pud_free(NULL, pud_table);
+	put_page(virt_to_page(pgd));
+}
+
+static void clear_hyp_pud_entry(pud_t *pud)
+{
+	pmd_t *pmd_table __maybe_unused = pmd_offset(pud, 0);
+	VM_BUG_ON(pud_huge(*pud));
+	pud_clear(pud);
+	pmd_free(NULL, pmd_table);
+	put_page(virt_to_page(pud));
+}
+
+static void clear_hyp_pmd_entry(pmd_t *pmd)
+{
+	pte_t *pte_table = pte_offset_kernel(pmd, 0);
+	VM_BUG_ON(pmd_thp_or_huge(*pmd));
+	pmd_clear(pmd);
+	pte_free_kernel(NULL, pte_table);
+	put_page(virt_to_page(pmd));
+}
+
+static void unmap_hyp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
+{
+	pte_t *pte, *start_pte;
+
+	start_pte = pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte)) {
+			kvm_set_pte(pte, __pte(0));
+			put_page(virt_to_page(pte));
+		}
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+
+	if (hyp_pte_table_empty(start_pte))
+		clear_hyp_pmd_entry(pmd);
+}
+
+static void unmap_hyp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next;
+	pmd_t *pmd, *start_pmd;
+
+	start_pmd = pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		/* Hyp doesn't use huge pmds */
+		if (!pmd_none(*pmd))
+			unmap_hyp_ptes(pmd, addr, next);
+	} while (pmd++, addr = next, addr != end);
+
+	if (hyp_pmd_table_empty(start_pmd))
+		clear_hyp_pud_entry(pud);
+}
+
+static void unmap_hyp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t next;
+	pud_t *pud, *start_pud;
+
+	start_pud = pud = pud_offset(pgd, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		/* Hyp doesn't use huge puds */
+		if (!pud_none(*pud))
+			unmap_hyp_pmds(pud, addr, next);
+	} while (pud++, addr = next, addr != end);
+
+	if (hyp_pud_table_empty(start_pud))
+		clear_hyp_pgd_entry(pgd);
+}
+
+static void unmap_hyp_range(pgd_t *pgdp, phys_addr_t start, u64 size)
+{
+	pgd_t *pgd;
+	phys_addr_t addr = start, end = start + size;
+	phys_addr_t next;
+
+	/*
+	 * We don't unmap anything from HYP, except at the hyp tear down.
+	 * Hence, we don't have to invalidate the TLBs here.
+	 */
+	pgd = pgdp + pgd_index(addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (!pgd_none(*pgd))
+			unmap_hyp_puds(pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
 /**
  * free_boot_hyp_pgd - free HYP boot page tables
  *
@@ -401,14 +493,14 @@ void free_boot_hyp_pgd(void)
 	mutex_lock(&kvm_hyp_pgd_mutex);
 
 	if (boot_hyp_pgd) {
-		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
-		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
+		unmap_hyp_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
+		unmap_hyp_range(boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
 		boot_hyp_pgd = NULL;
 	}
 
 	if (hyp_pgd)
-		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
+		unmap_hyp_range(hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 
 	mutex_unlock(&kvm_hyp_pgd_mutex);
 }
@@ -433,9 +525,9 @@ void free_hyp_pgds(void)
 
 	if (hyp_pgd) {
 		for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE)
-			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_hyp_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
-			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_hyp_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 
 		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
 		hyp_pgd = NULL;
@@ -645,20 +737,6 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
 				     __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE);
 }
 
-/* Free the HW pgd, one page at a time */
-static void kvm_free_hwpgd(void *hwpgd)
-{
-	free_pages_exact(hwpgd, kvm_get_hwpgd_size());
-}
-
-/* Allocate the HW PGD, making sure that each page gets its own refcount */
-static void *kvm_alloc_hwpgd(void)
-{
-	unsigned int size = kvm_get_hwpgd_size();
-
-	return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
-}
-
 /**
  * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
  * @kvm:	The KVM struct pointer for the VM.
@@ -673,81 +751,22 @@ static void *kvm_alloc_hwpgd(void)
 int kvm_alloc_stage2_pgd(struct kvm *kvm)
 {
 	pgd_t *pgd;
-	void *hwpgd;
 
 	if (kvm->arch.pgd != NULL) {
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
 
-	hwpgd = kvm_alloc_hwpgd();
-	if (!hwpgd)
+	/* Allocate the HW PGD, making sure that each page gets its own refcount */
+	pgd = alloc_pages_exact(S2_PGD_SIZE, GFP_KERNEL | __GFP_ZERO);
+	if (!pgd)
 		return -ENOMEM;
 
-	/* When the kernel uses more levels of page tables than the
-	 * guest, we allocate a fake PGD and pre-populate it to point
-	 * to the next-level page table, which will be the real
-	 * initial page table pointed to by the VTTBR.
-	 *
-	 * When KVM_PREALLOC_LEVEL==2, we allocate a single page for
-	 * the PMD and the kernel will use folded pud.
-	 * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD
-	 * pages.
-	 */
-	if (KVM_PREALLOC_LEVEL > 0) {
-		int i;
-
-		/*
-		 * Allocate fake pgd for the page table manipulation macros to
-		 * work.  This is not used by the hardware and we have no
-		 * alignment requirement for this allocation.
-		 */
-		pgd = kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
-				GFP_KERNEL | __GFP_ZERO);
-
-		if (!pgd) {
-			kvm_free_hwpgd(hwpgd);
-			return -ENOMEM;
-		}
-
-		/* Plug the HW PGD into the fake one. */
-		for (i = 0; i < PTRS_PER_S2_PGD; i++) {
-			if (KVM_PREALLOC_LEVEL == 1)
-				pgd_populate(NULL, pgd + i,
-					     (pud_t *)hwpgd + i * PTRS_PER_PUD);
-			else if (KVM_PREALLOC_LEVEL == 2)
-				pud_populate(NULL, pud_offset(pgd, 0) + i,
-					     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
-		}
-	} else {
-		/*
-		 * Allocate actual first-level Stage-2 page table used by the
-		 * hardware for Stage-2 page table walks.
-		 */
-		pgd = (pgd_t *)hwpgd;
-	}
-
 	kvm_clean_pgd(pgd);
 	kvm->arch.pgd = pgd;
 	return 0;
 }
 
-/**
- * unmap_stage2_range -- Clear stage2 page table entries to unmap a range
- * @kvm:   The VM pointer
- * @start: The intermediate physical base address of the range to unmap
- * @size:  The size of the area to unmap
- *
- * Clear a range of stage-2 mappings, lowering the various ref-counts.  Must
- * be called while holding mmu_lock (unless for freeing the stage2 pgd before
- * destroying the VM), otherwise another faulting VCPU may come in and mess
- * with things behind our backs.
- */
-static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
-{
-	unmap_range(kvm, kvm->arch.pgd, start, size);
-}
-
 static void stage2_unmap_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
@@ -830,10 +849,8 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 		return;
 
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
-	kvm_free_hwpgd(kvm_get_hwpgd(kvm));
-	if (KVM_PREALLOC_LEVEL > 0)
-		kfree(kvm->arch.pgd);
-
+	/* Free the HW pgd, one page at a time */
+	free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
 	kvm->arch.pgd = NULL;
 }
 
@@ -843,16 +860,16 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pgd_t *pgd;
 	pud_t *pud;
 
-	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
-	if (WARN_ON(pgd_none(*pgd))) {
+	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
+	if (WARN_ON(stage2_pgd_none(*pgd))) {
 		if (!cache)
 			return NULL;
 		pud = mmu_memory_cache_alloc(cache);
-		pgd_populate(NULL, pgd, pud);
+		stage2_pgd_populate(pgd, pud);
 		get_page(virt_to_page(pgd));
 	}
 
-	return pud_offset(pgd, addr);
+	return stage2_pud_offset(pgd, addr);
 }
 
 static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
@@ -862,15 +879,15 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pmd_t *pmd;
 
 	pud = stage2_get_pud(kvm, cache, addr);
-	if (pud_none(*pud)) {
+	if (stage2_pud_none(*pud)) {
 		if (!cache)
 			return NULL;
 		pmd = mmu_memory_cache_alloc(cache);
-		pud_populate(NULL, pud, pmd);
+		stage2_pud_populate(pud, pmd);
 		get_page(virt_to_page(pud));
 	}
 
-	return pmd_offset(pud, addr);
+	return stage2_pmd_offset(pud, addr);
 }
 
 static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
@@ -893,11 +910,14 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 	VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd));
 
 	old_pmd = *pmd;
-	kvm_set_pmd(pmd, *new_pmd);
-	if (pmd_present(old_pmd))
+	if (pmd_present(old_pmd)) {
+		pmd_clear(pmd);
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	else
+	} else {
 		get_page(virt_to_page(pmd));
+	}
+
+	kvm_set_pmd(pmd, *new_pmd);
 	return 0;
 }
 
@@ -946,15 +966,38 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
 
 	/* Create 2nd stage page table mapping - Level 3 */
 	old_pte = *pte;
-	kvm_set_pte(pte, *new_pte);
-	if (pte_present(old_pte))
+	if (pte_present(old_pte)) {
+		kvm_set_pte(pte, __pte(0));
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
-	else
+	} else {
 		get_page(virt_to_page(pte));
+	}
 
+	kvm_set_pte(pte, *new_pte);
 	return 0;
 }
 
+#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static int stage2_ptep_test_and_clear_young(pte_t *pte)
+{
+	if (pte_young(*pte)) {
+		*pte = pte_mkold(*pte);
+		return 1;
+	}
+	return 0;
+}
+#else
+static int stage2_ptep_test_and_clear_young(pte_t *pte)
+{
+	return __ptep_test_and_clear_young(pte);
+}
+#endif
+
+static int stage2_pmdp_test_and_clear_young(pmd_t *pmd)
+{
+	return stage2_ptep_test_and_clear_young((pte_t *)pmd);
+}
+
 /**
  * kvm_phys_addr_ioremap - map a device range to guest IPA
  *
@@ -978,7 +1021,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 		pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
 
 		if (writable)
-			kvm_set_s2pte_writable(&pte);
+			pte = kvm_s2pte_mkwrite(pte);
 
 		ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES,
 						KVM_NR_MEM_OBJS);
@@ -1078,12 +1121,12 @@ static void stage2_wp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end)
 	pmd_t *pmd;
 	phys_addr_t next;
 
-	pmd = pmd_offset(pud, addr);
+	pmd = stage2_pmd_offset(pud, addr);
 
 	do {
-		next = kvm_pmd_addr_end(addr, end);
+		next = stage2_pmd_addr_end(addr, end);
 		if (!pmd_none(*pmd)) {
-			if (kvm_pmd_huge(*pmd)) {
+			if (pmd_thp_or_huge(*pmd)) {
 				if (!kvm_s2pmd_readonly(pmd))
 					kvm_set_s2pmd_readonly(pmd);
 			} else {
@@ -1106,12 +1149,12 @@ static void  stage2_wp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end)
 	pud_t *pud;
 	phys_addr_t next;
 
-	pud = pud_offset(pgd, addr);
+	pud = stage2_pud_offset(pgd, addr);
 	do {
-		next = kvm_pud_addr_end(addr, end);
-		if (!pud_none(*pud)) {
+		next = stage2_pud_addr_end(addr, end);
+		if (!stage2_pud_none(*pud)) {
 			/* TODO:PUD not supported, revisit later if supported */
-			BUG_ON(kvm_pud_huge(*pud));
+			BUG_ON(stage2_pud_huge(*pud));
 			stage2_wp_pmds(pud, addr, next);
 		}
 	} while (pud++, addr = next, addr != end);
@@ -1128,7 +1171,7 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 	pgd_t *pgd;
 	phys_addr_t next;
 
-	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
+	pgd = kvm->arch.pgd + stage2_pgd_index(addr);
 	do {
 		/*
 		 * Release kvm_mmu_lock periodically if the memory region is
@@ -1140,8 +1183,8 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 		if (need_resched() || spin_needbreak(&kvm->mmu_lock))
 			cond_resched_lock(&kvm->mmu_lock);
 
-		next = kvm_pgd_addr_end(addr, end);
-		if (pgd_present(*pgd))
+		next = stage2_pgd_addr_end(addr, end);
+		if (stage2_pgd_present(*pgd))
 			stage2_wp_puds(pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
@@ -1320,7 +1363,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
 		new_pmd = pmd_mkhuge(new_pmd);
 		if (writable) {
-			kvm_set_s2pmd_writable(&new_pmd);
+			new_pmd = kvm_s2pmd_mkwrite(new_pmd);
 			kvm_set_pfn_dirty(pfn);
 		}
 		coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached);
@@ -1329,7 +1372,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		pte_t new_pte = pfn_pte(pfn, mem_type);
 
 		if (writable) {
-			kvm_set_s2pte_writable(&new_pte);
+			new_pte = kvm_s2pte_mkwrite(new_pte);
 			kvm_set_pfn_dirty(pfn);
 			mark_page_dirty(kvm, gfn);
 		}
@@ -1348,6 +1391,8 @@ out_unlock:
  * Resolve the access fault by making the page young again.
  * Note that because the faulting entry is guaranteed not to be
  * cached in the TLB, we don't need to invalidate anything.
+ * Only the HW Access Flag updates are supported for Stage 2 (no DBM),
+ * so there is no need for atomic (pte|pmd)_mkyoung operations.
  */
 static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 {
@@ -1364,7 +1409,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 	if (!pmd || pmd_none(*pmd))	/* Nothing there */
 		goto out;
 
-	if (kvm_pmd_huge(*pmd)) {	/* THP, HugeTLB */
+	if (pmd_thp_or_huge(*pmd)) {	/* THP, HugeTLB */
 		*pmd = pmd_mkyoung(*pmd);
 		pfn = pmd_pfn(*pmd);
 		pfn_valid = true;
@@ -1588,25 +1633,14 @@ static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
 	if (!pmd || pmd_none(*pmd))	/* Nothing there */
 		return 0;
 
-	if (kvm_pmd_huge(*pmd)) {	/* THP, HugeTLB */
-		if (pmd_young(*pmd)) {
-			*pmd = pmd_mkold(*pmd);
-			return 1;
-		}
-
-		return 0;
-	}
+	if (pmd_thp_or_huge(*pmd))	/* THP, HugeTLB */
+		return stage2_pmdp_test_and_clear_young(pmd);
 
 	pte = pte_offset_kernel(pmd, gpa);
 	if (pte_none(*pte))
 		return 0;
 
-	if (pte_young(*pte)) {
-		*pte = pte_mkold(*pte);	/* Just a page... */
-		return 1;
-	}
-
-	return 0;
+	return stage2_ptep_test_and_clear_young(pte);
 }
 
 static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
@@ -1618,7 +1652,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
 	if (!pmd || pmd_none(*pmd))	/* Nothing there */
 		return 0;
 
-	if (kvm_pmd_huge(*pmd))		/* THP, HugeTLB */
+	if (pmd_thp_or_huge(*pmd))		/* THP, HugeTLB */
 		return pmd_young(*pmd);
 
 	pte = pte_offset_kernel(pmd, gpa);