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

Pull KVM updates from Paolo Bonzini:
 "ARM:

   - More progress on the protected VM front, now with the full fixed
     feature set as well as the limitation of some hypercalls after
     initialisation.

   - Cleanup of the RAZ/WI sysreg handling, which was pointlessly
     complicated

   - Fixes for the vgic placement in the IPA space, together with a
     bunch of selftests

   - More memcg accounting of the memory allocated on behalf of a guest

   - Timer and vgic selftests

   - Workarounds for the Apple M1 broken vgic implementation

   - KConfig cleanups

   - New kvmarm.mode=none option, for those who really dislike us

  RISC-V:

   - New KVM port.

  x86:

   - New API to control TSC offset from userspace

   - TSC scaling for nested hypervisors on SVM

   - Switch masterclock protection from raw_spin_lock to seqcount

   - Clean up function prototypes in the page fault code and avoid
     repeated memslot lookups

   - Convey the exit reason to userspace on emulation failure

   - Configure time between NX page recovery iterations

   - Expose Predictive Store Forwarding Disable CPUID leaf

   - Allocate page tracking data structures lazily (if the i915 KVM-GT
     functionality is not compiled in)

   - Cleanups, fixes and optimizations for the shadow MMU code

  s390:

   - SIGP Fixes

   - initial preparations for lazy destroy of secure VMs

   - storage key improvements/fixes

   - Log the guest CPNC

  Starting from this release, KVM-PPC patches will come from Michael
  Ellerman's PPC tree"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
  RISC-V: KVM: fix boolreturn.cocci warnings
  RISC-V: KVM: remove unneeded semicolon
  RISC-V: KVM: Fix GPA passed to __kvm_riscv_hfence_gvma_xyz() functions
  RISC-V: KVM: Factor-out FP virtualization into separate sources
  KVM: s390: add debug statement for diag 318 CPNC data
  KVM: s390: pv: properly handle page flags for protected guests
  KVM: s390: Fix handle_sske page fault handling
  KVM: x86: SGX must obey the KVM_INTERNAL_ERROR_EMULATION protocol
  KVM: x86: On emulation failure, convey the exit reason, etc. to userspace
  KVM: x86: Get exit_reason as part of kvm_x86_ops.get_exit_info
  KVM: x86: Clarify the kvm_run.emulation_failure structure layout
  KVM: s390: Add a routine for setting userspace CPU state
  KVM: s390: Simplify SIGP Set Arch handling
  KVM: s390: pv: avoid stalls when making pages secure
  KVM: s390: pv: avoid stalls for kvm_s390_pv_init_vm
  KVM: s390: pv: avoid double free of sida page
  KVM: s390: pv: add macros for UVC CC values
  s390/mm: optimize reset_guest_reference_bit()
  s390/mm: optimize set_guest_storage_key()
  s390/mm: no need for pte_alloc_map_lock() if we know the pmd is present
  ...

11 files changed, 196 insertions, 75 deletions

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index b61426c9ef17..e43416950245 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1074,8 +1074,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	pte_t res;
 
 	res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
+	/* At this point the reference through the mapping is still present */
 	if (mm_is_protected(mm) && pte_present(res))
-		uv_convert_from_secure(pte_val(res) & PAGE_MASK);
+		uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK);
 	return res;
 }
 
@@ -1091,8 +1092,9 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
 	pte_t res;
 
 	res = ptep_xchg_direct(vma->vm_mm, addr, ptep, __pte(_PAGE_INVALID));
+	/* At this point the reference through the mapping is still present */
 	if (mm_is_protected(vma->vm_mm) && pte_present(res))
-		uv_convert_from_secure(pte_val(res) & PAGE_MASK);
+		uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK);
 	return res;
 }
 
@@ -1116,8 +1118,9 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 	} else {
 		res = ptep_xchg_lazy(mm, addr, ptep, __pte(_PAGE_INVALID));
 	}
+	/* At this point the reference through the mapping is still present */
 	if (mm_is_protected(mm) && pte_present(res))
-		uv_convert_from_secure(pte_val(res) & PAGE_MASK);
+		uv_convert_owned_from_secure(pte_val(res) & PAGE_MASK);
 	return res;
 }
 
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index fe92a4caf5ec..72d3e49c2860 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -18,6 +18,11 @@
 #include <asm/page.h>
 #include <asm/gmap.h>
 
+#define UVC_CC_OK	0
+#define UVC_CC_ERROR	1
+#define UVC_CC_BUSY	2
+#define UVC_CC_PARTIAL	3
+
 #define UVC_RC_EXECUTED		0x0001
 #define UVC_RC_INV_CMD		0x0002
 #define UVC_RC_INV_STATE	0x0003
@@ -351,8 +356,9 @@ static inline int is_prot_virt_host(void)
 }
 
 int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
-int uv_destroy_page(unsigned long paddr);
+int uv_destroy_owned_page(unsigned long paddr);
 int uv_convert_from_secure(unsigned long paddr);
+int uv_convert_owned_from_secure(unsigned long paddr);
 int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
 
 void setup_uv(void);
@@ -360,7 +366,7 @@ void setup_uv(void);
 #define is_prot_virt_host() 0
 static inline void setup_uv(void) {}
 
-static inline int uv_destroy_page(unsigned long paddr)
+static inline int uv_destroy_owned_page(unsigned long paddr)
 {
 	return 0;
 }
@@ -369,6 +375,11 @@ static inline int uv_convert_from_secure(unsigned long paddr)
 {
 	return 0;
 }
+
+static inline int uv_convert_owned_from_secure(unsigned long paddr)
+{
+	return 0;
+}
 #endif
 
 #endif /* _ASM_S390_UV_H */
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 5a656c7b7a67..8b0e62507d62 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -100,7 +100,7 @@ static int uv_pin_shared(unsigned long paddr)
  *
  * @paddr: Absolute host address of page to be destroyed
  */
-int uv_destroy_page(unsigned long paddr)
+static int uv_destroy_page(unsigned long paddr)
 {
 	struct uv_cb_cfs uvcb = {
 		.header.cmd = UVC_CMD_DESTR_SEC_STOR,
@@ -121,6 +121,22 @@ int uv_destroy_page(unsigned long paddr)
 }
 
 /*
+ * The caller must already hold a reference to the page
+ */
+int uv_destroy_owned_page(unsigned long paddr)
+{
+	struct page *page = phys_to_page(paddr);
+	int rc;
+
+	get_page(page);
+	rc = uv_destroy_page(paddr);
+	if (!rc)
+		clear_bit(PG_arch_1, &page->flags);
+	put_page(page);
+	return rc;
+}
+
+/*
  * Requests the Ultravisor to encrypt a guest page and make it
  * accessible to the host for paging (export).
  *
@@ -140,6 +156,22 @@ int uv_convert_from_secure(unsigned long paddr)
 }
 
 /*
+ * The caller must already hold a reference to the page
+ */
+int uv_convert_owned_from_secure(unsigned long paddr)
+{
+	struct page *page = phys_to_page(paddr);
+	int rc;
+
+	get_page(page);
+	rc = uv_convert_from_secure(paddr);
+	if (!rc)
+		clear_bit(PG_arch_1, &page->flags);
+	put_page(page);
+	return rc;
+}
+
+/*
  * Calculate the expected ref_count for a page that would otherwise have no
  * further pins. This was cribbed from similar functions in other places in
  * the kernel, but with some slight modifications. We know that a secure
@@ -165,7 +197,7 @@ static int make_secure_pte(pte_t *ptep, unsigned long addr,
 {
 	pte_t entry = READ_ONCE(*ptep);
 	struct page *page;
-	int expected, rc = 0;
+	int expected, cc = 0;
 
 	if (!pte_present(entry))
 		return -ENXIO;
@@ -181,12 +213,25 @@ static int make_secure_pte(pte_t *ptep, unsigned long addr,
 	if (!page_ref_freeze(page, expected))
 		return -EBUSY;
 	set_bit(PG_arch_1, &page->flags);
-	rc = uv_call(0, (u64)uvcb);
+	/*
+	 * If the UVC does not succeed or fail immediately, we don't want to
+	 * loop for long, or we might get stall notifications.
+	 * On the other hand, this is a complex scenario and we are holding a lot of
+	 * locks, so we can't easily sleep and reschedule. We try only once,
+	 * and if the UVC returned busy or partial completion, we return
+	 * -EAGAIN and we let the callers deal with it.
+	 */
+	cc = __uv_call(0, (u64)uvcb);
 	page_ref_unfreeze(page, expected);
-	/* Return -ENXIO if the page was not mapped, -EINVAL otherwise */
-	if (rc)
-		rc = uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
-	return rc;
+	/*
+	 * Return -ENXIO if the page was not mapped, -EINVAL for other errors.
+	 * If busy or partially completed, return -EAGAIN.
+	 */
+	if (cc == UVC_CC_OK)
+		return 0;
+	else if (cc == UVC_CC_BUSY || cc == UVC_CC_PARTIAL)
+		return -EAGAIN;
+	return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
 }
 
 /*
@@ -212,7 +257,7 @@ again:
 	uaddr = __gmap_translate(gmap, gaddr);
 	if (IS_ERR_VALUE(uaddr))
 		goto out;
-	vma = find_vma(gmap->mm, uaddr);
+	vma = vma_lookup(gmap->mm, uaddr);
 	if (!vma)
 		goto out;
 	/*
@@ -239,6 +284,10 @@ out:
 	mmap_read_unlock(gmap->mm);
 
 	if (rc == -EAGAIN) {
+		/*
+		 * If we are here because the UVC returned busy or partial
+		 * completion, this is just a useless check, but it is safe.
+		 */
 		wait_on_page_writeback(page);
 	} else if (rc == -EBUSY) {
 		/*
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 2bd8f854f1b4..d07ff646d844 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -518,6 +518,11 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu)
 	 */
 	if (rc == -EINVAL)
 		return 0;
+	/*
+	 * If we got -EAGAIN here, we simply return it. It will eventually
+	 * get propagated all the way to userspace, which should then try
+	 * again.
+	 */
 	return rc;
 }
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 1c97493d21e1..c6257f625929 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2487,8 +2487,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	case KVM_S390_PV_COMMAND: {
 		struct kvm_pv_cmd args;
 
-		/* protvirt means user sigp */
-		kvm->arch.user_cpu_state_ctrl = 1;
+		/* protvirt means user cpu state */
+		kvm_s390_set_user_cpu_state_ctrl(kvm);
 		r = 0;
 		if (!is_prot_virt_host()) {
 			r = -EINVAL;
@@ -3802,7 +3802,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	vcpu_load(vcpu);
 
 	/* user space knows about this interface - let it control the state */
-	vcpu->kvm->arch.user_cpu_state_ctrl = 1;
+	kvm_s390_set_user_cpu_state_ctrl(vcpu->kvm);
 
 	switch (mp_state->mp_state) {
 	case KVM_MP_STATE_STOPPED:
@@ -4255,6 +4255,7 @@ static void sync_regs_fmt2(struct kvm_vcpu *vcpu)
 	if (kvm_run->kvm_dirty_regs & KVM_SYNC_DIAG318) {
 		vcpu->arch.diag318_info.val = kvm_run->s.regs.diag318;
 		vcpu->arch.sie_block->cpnc = vcpu->arch.diag318_info.cpnc;
+		VCPU_EVENT(vcpu, 3, "setting cpnc to %d", vcpu->arch.diag318_info.cpnc);
 	}
 	/*
 	 * If userspace sets the riccb (e.g. after migration) to a valid state,
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 52bc8fbaa60a..c07a050d757d 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -208,6 +208,15 @@ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm)
 	return kvm->arch.user_cpu_state_ctrl != 0;
 }
 
+static inline void kvm_s390_set_user_cpu_state_ctrl(struct kvm *kvm)
+{
+	if (kvm->arch.user_cpu_state_ctrl)
+		return;
+
+	VM_EVENT(kvm, 3, "%s", "ENABLE: Userspace CPU state control");
+	kvm->arch.user_cpu_state_ctrl = 1;
+}
+
 /* implemented in pv.c */
 int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
 int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 53da4ceb16a3..417154b314a6 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -397,6 +397,8 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 		mmap_read_unlock(current->mm);
 		if (rc == -EFAULT)
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		if (rc == -EAGAIN)
+			continue;
 		if (rc < 0)
 			return rc;
 		start += PAGE_SIZE;
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index c8841f476e91..00d272d134c2 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -16,18 +16,17 @@
 
 int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 {
-	int cc = 0;
+	int cc;
 
-	if (kvm_s390_pv_cpu_get_handle(vcpu)) {
-		cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu),
-				   UVC_CMD_DESTROY_SEC_CPU, rc, rrc);
+	if (!kvm_s390_pv_cpu_get_handle(vcpu))
+		return 0;
+
+	cc = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu), UVC_CMD_DESTROY_SEC_CPU, rc, rrc);
+
+	KVM_UV_EVENT(vcpu->kvm, 3, "PROTVIRT DESTROY VCPU %d: rc %x rrc %x",
+		     vcpu->vcpu_id, *rc, *rrc);
+	WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x", *rc, *rrc);
 
-		KVM_UV_EVENT(vcpu->kvm, 3,
-			     "PROTVIRT DESTROY VCPU %d: rc %x rrc %x",
-			     vcpu->vcpu_id, *rc, *rrc);
-		WARN_ONCE(cc, "protvirt destroy cpu failed rc %x rrc %x",
-			  *rc, *rrc);
-	}
 	/* Intended memory leak for something that should never happen. */
 	if (!cc)
 		free_pages(vcpu->arch.pv.stor_base,
@@ -196,7 +195,7 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	uvcb.conf_base_stor_origin = (u64)kvm->arch.pv.stor_base;
 	uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var;
 
-	cc = uv_call(0, (u64)&uvcb);
+	cc = uv_call_sched(0, (u64)&uvcb);
 	*rc = uvcb.header.rc;
 	*rrc = uvcb.header.rrc;
 	KVM_UV_EVENT(kvm, 3, "PROTVIRT CREATE VM: handle %llx len %llx rc %x rrc %x",
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 683036c1c92a..cf4de80bd541 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -151,22 +151,10 @@ static int __sigp_stop_and_store_status(struct kvm_vcpu *vcpu,
 static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter,
 			   u64 *status_reg)
 {
-	unsigned int i;
-	struct kvm_vcpu *v;
-	bool all_stopped = true;
-
-	kvm_for_each_vcpu(i, v, vcpu->kvm) {
-		if (v == vcpu)
-			continue;
-		if (!is_vcpu_stopped(v))
-			all_stopped = false;
-	}
-
 	*status_reg &= 0xffffffff00000000UL;
 
 	/* Reject set arch order, with czam we're always in z/Arch mode. */
-	*status_reg |= (all_stopped ? SIGP_STATUS_INVALID_PARAMETER :
-					SIGP_STATUS_INCORRECT_STATE);
+	*status_reg |= SIGP_STATUS_INVALID_PARAMETER;
 	return SIGP_CC_STATUS_STORED;
 }
 
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 4d3b33ce81c6..dfee0ebb2fac 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -672,6 +672,7 @@ EXPORT_SYMBOL_GPL(gmap_fault);
  */
 void __gmap_zap(struct gmap *gmap, unsigned long gaddr)
 {
+	struct vm_area_struct *vma;
 	unsigned long vmaddr;
 	spinlock_t *ptl;
 	pte_t *ptep;
@@ -681,11 +682,17 @@ void __gmap_zap(struct gmap *gmap, unsigned long gaddr)
 						   gaddr >> PMD_SHIFT);
 	if (vmaddr) {
 		vmaddr |= gaddr & ~PMD_MASK;
+
+		vma = vma_lookup(gmap->mm, vmaddr);
+		if (!vma || is_vm_hugetlb_page(vma))
+			return;
+
 		/* Get pointer to the page table entry */
 		ptep = get_locked_pte(gmap->mm, vmaddr, &ptl);
-		if (likely(ptep))
+		if (likely(ptep)) {
 			ptep_zap_unused(gmap->mm, vmaddr, ptep, 0);
-		pte_unmap_unlock(ptep, ptl);
+			pte_unmap_unlock(ptep, ptl);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(__gmap_zap);
@@ -2677,8 +2684,10 @@ static int __s390_reset_acc(pte_t *ptep, unsigned long addr,
 {
 	pte_t pte = READ_ONCE(*ptep);
 
+	/* There is a reference through the mapping */
 	if (pte_present(pte))
-		WARN_ON_ONCE(uv_destroy_page(pte_val(pte) & PAGE_MASK));
+		WARN_ON_ONCE(uv_destroy_owned_page(pte_val(pte) & PAGE_MASK));
+
 	return 0;
 }
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 034721a68d8f..c16232cd0ec5 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -429,22 +429,36 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 }
 
 #ifdef CONFIG_PGSTE
-static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
+static int pmd_lookup(struct mm_struct *mm, unsigned long addr, pmd_t **pmdp)
 {
+	struct vm_area_struct *vma;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
-	pmd_t *pmd;
+
+	/* We need a valid VMA, otherwise this is clearly a fault. */
+	vma = vma_lookup(mm, addr);
+	if (!vma)
+		return -EFAULT;
 
 	pgd = pgd_offset(mm, addr);
-	p4d = p4d_alloc(mm, pgd, addr);
-	if (!p4d)
-		return NULL;
-	pud = pud_alloc(mm, p4d, addr);
-	if (!pud)
-		return NULL;
-	pmd = pmd_alloc(mm, pud, addr);
-	return pmd;
+	if (!pgd_present(*pgd))
+		return -ENOENT;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return -ENOENT;
+
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return -ENOENT;
+
+	/* Large PUDs are not supported yet. */
+	if (pud_large(*pud))
+		return -EFAULT;
+
+	*pmdp = pmd_offset(pud, addr);
+	return 0;
 }
 #endif
 
@@ -778,14 +792,23 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	pmd_t *pmdp;
 	pte_t *ptep;
 
-	pmdp = pmd_alloc_map(mm, addr);
-	if (unlikely(!pmdp))
+	/*
+	 * If we don't have a PTE table and if there is no huge page mapped,
+	 * we can ignore attempts to set the key to 0, because it already is 0.
+	 */
+	switch (pmd_lookup(mm, addr, &pmdp)) {
+	case -ENOENT:
+		return key ? -EFAULT : 0;
+	case 0:
+		break;
+	default:
 		return -EFAULT;
+	}
 
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
-		return -EFAULT;
+		return key ? -EFAULT : 0;
 	}
 
 	if (pmd_large(*pmdp)) {
@@ -801,10 +824,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	}
 	spin_unlock(ptl);
 
-	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
-	if (unlikely(!ptep))
-		return -EFAULT;
-
+	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	new = old = pgste_get_lock(ptep);
 	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
 			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
@@ -881,14 +901,23 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	pte_t *ptep;
 	int cc = 0;
 
-	pmdp = pmd_alloc_map(mm, addr);
-	if (unlikely(!pmdp))
+	/*
+	 * If we don't have a PTE table and if there is no huge page mapped,
+	 * the storage key is 0 and there is nothing for us to do.
+	 */
+	switch (pmd_lookup(mm, addr, &pmdp)) {
+	case -ENOENT:
+		return 0;
+	case 0:
+		break;
+	default:
 		return -EFAULT;
+	}
 
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
 		spin_unlock(ptl);
-		return -EFAULT;
+		return 0;
 	}
 
 	if (pmd_large(*pmdp)) {
@@ -900,10 +929,7 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	}
 	spin_unlock(ptl);
 
-	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
-	if (unlikely(!ptep))
-		return -EFAULT;
-
+	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	new = old = pgste_get_lock(ptep);
 	/* Reset guest reference bit only */
 	pgste_val(new) &= ~PGSTE_GR_BIT;
@@ -935,15 +961,24 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	pmd_t *pmdp;
 	pte_t *ptep;
 
-	pmdp = pmd_alloc_map(mm, addr);
-	if (unlikely(!pmdp))
+	/*
+	 * If we don't have a PTE table and if there is no huge page mapped,
+	 * the storage key is 0.
+	 */
+	*key = 0;
+
+	switch (pmd_lookup(mm, addr, &pmdp)) {
+	case -ENOENT:
+		return 0;
+	case 0:
+		break;
+	default:
 		return -EFAULT;
+	}
 
 	ptl = pmd_lock(mm, pmdp);
 	if (!pmd_present(*pmdp)) {
-		/* Not yet mapped memory has a zero key */
 		spin_unlock(ptl);
-		*key = 0;
 		return 0;
 	}
 
@@ -956,10 +991,7 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	}
 	spin_unlock(ptl);
 
-	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
-	if (unlikely(!ptep))
-		return -EFAULT;
-
+	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	pgste = pgste_get_lock(ptep);
 	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
 	paddr = pte_val(*ptep) & PAGE_MASK;
@@ -988,6 +1020,7 @@ EXPORT_SYMBOL(get_guest_storage_key);
 int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 			unsigned long *oldpte, unsigned long *oldpgste)
 {
+	struct vm_area_struct *vma;
 	unsigned long pgstev;
 	spinlock_t *ptl;
 	pgste_t pgste;
@@ -997,6 +1030,10 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 	WARN_ON_ONCE(orc > ESSA_MAX);
 	if (unlikely(orc > ESSA_MAX))
 		return -EINVAL;
+
+	vma = vma_lookup(mm, hva);
+	if (!vma || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
@@ -1089,10 +1126,14 @@ EXPORT_SYMBOL(pgste_perform_essa);
 int set_pgste_bits(struct mm_struct *mm, unsigned long hva,
 			unsigned long bits, unsigned long value)
 {
+	struct vm_area_struct *vma;
 	spinlock_t *ptl;
 	pgste_t new;
 	pte_t *ptep;
 
+	vma = vma_lookup(mm, hva);
+	if (!vma || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
@@ -1117,9 +1158,13 @@ EXPORT_SYMBOL(set_pgste_bits);
  */
 int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep)
 {
+	struct vm_area_struct *vma;
 	spinlock_t *ptl;
 	pte_t *ptep;
 
+	vma = vma_lookup(mm, hva);
+	if (!vma || is_vm_hugetlb_page(vma))
+		return -EFAULT;
 	ptep = get_locked_pte(mm, hva, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;