KVM: s390: Fixes and features for 4.14

- merge of topic branch tlb-flushing from the s390 tree to get the
   no-dat base features
 - merge of kvm/master to avoid conflicts with additional sthyi fixes
 - wire up the no-dat enhancements in KVM
 - multiple epoch facility (z14 feature)
 - Configuration z/Architecture Mode
 - more sthyi fixes
 - gdb server range checking fix
 - small code cleanups
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQIcBAABAgAGBQJZqQt+AAoJEBF7vIC1phx82jcP/0PgDUFpyaq50R1LhoLoXfsv
 55x8hZFJzkBTapv6ckb9MP1J90htbmYXUDbgk/JS7ElenLvLw6r9QenHJnLYRoJ4
 s4ApooG5/wpbQWdxfqZaNHZEV1/Fgvv+R348k8cFfhrzJdOd0p7I+qkd5FOX2VTl
 NGk+cR03yhtPOYeUb90k40k0kGmY7acdnYe2txUoh7qC38vPVwMJA6S01mWbB3sm
 ApQN9hzGvXhT833dVTNMS33uCds/9nCHtMn0viqTfs9AWKIs62nK4L54c5dgZWpH
 u7+ji5OUEbV+8QQH5G1OmWUIo3sKO5MVS0P9jbh0bIIdUZvUKdchFP8bQcmde02E
 IgYgjbgmKc8Zec+Z0PHs5Gy+VbGXpqg0nvwyzK96fh/KM7aepxHUfDOdWWj8qbgI
 4sc2fe5JFkP5IldYgJlMPSm4GqLNDkbGFnLralkaqhRvjS1sNjgXxcCclLQQaI5H
 kMklzkNpMQ9yC7pYLjq7AKOzmMdHqq90rAIq0zQSYQjMoiC2RLYFyjFwsK3KlmeJ
 GRgYrIZOVkYONZhT4F81piGcuRsbCGSXZ5I5i/QxJ/EgNGO8EcGrrONAk1NW9Dsp
 q9qu/aKXOzGe57jjP+MonH4bcrHLCmcpkxS9sgiECu0PtutzbGdZPUXA9Pj9YMON
 7kQXrwPgEHhn62+l/JdO
 =N/6G
 -----END PGP SIGNATURE-----

Merge tag 'kvm-s390-next-4.14-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux

KVM: s390: Fixes and features for 4.14

- merge of topic branch tlb-flushing from the s390 tree to get the
  no-dat base features
- merge of kvm/master to avoid conflicts with additional sthyi fixes
- wire up the no-dat enhancements in KVM
- multiple epoch facility (z14 feature)
- Configuration z/Architecture Mode
- more sthyi fixes
- gdb server range checking fix
- small code cleanups

Documentation/virtual/kvm/devices/vm.txt

@@ -176,7 +176,8 @@ Architectures: s390
 
 3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH
 
-Allows user space to set/get the TOD clock extension (u8).
+Allows user space to set/get the TOD clock extension (u8) (superseded by
+KVM_S390_VM_TOD_EXT).
 
 Parameters: address of a buffer in user space to store the data (u8) to
 Returns:    -EFAULT if the given address is not accessible from kernel space
@@ -190,6 +191,17 @@ the POP (u64).
 Parameters: address of a buffer in user space to store the data (u64) to
 Returns:    -EFAULT if the given address is not accessible from kernel space
 
+3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT
+Allows user space to set/get bits 0-63 of the TOD clock register as defined in
+the POP (u64). If the guest CPU model supports the TOD clock extension (u8), it
+also allows user space to get/set it. If the guest CPU model does not support
+it, it is stored as 0 and not allowed to be set to a value != 0.
+
+Parameters: address of a buffer in user space to store the data
+            (kvm_s390_vm_tod_clock) to
+Returns:    -EFAULT if the given address is not accessible from kernel space
+	    -EINVAL if setting the TOD clock extension to != 0 is not supported
+
 4. GROUP: KVM_S390_VM_CRYPTO
 Architectures: s390
 

arch/s390/include/asm/kvm_host.h

@@ -226,7 +226,9 @@ struct kvm_s390_sie_block {
 #define ECB3_RI  0x01
 	__u8    ecb3;			/* 0x0063 */
 	__u32	scaol;			/* 0x0064 */
-	__u8	reserved68[4];		/* 0x0068 */
+	__u8	reserved68;		/* 0x0068 */
+	__u8    epdx;			/* 0x0069 */
+	__u8    reserved6a[2];		/* 0x006a */
 	__u32	todpr;			/* 0x006c */
 	__u8	reserved70[16];		/* 0x0070 */
 	__u64	mso;			/* 0x0080 */
@@ -265,6 +267,7 @@ struct kvm_s390_sie_block {
 	__u64	cbrlo;			/* 0x01b8 */
 	__u8	reserved1c0[8];		/* 0x01c0 */
 #define ECD_HOSTREGMGMT	0x20000000
+#define ECD_MEF		0x08000000
 	__u32	ecd;			/* 0x01c8 */
 	__u8	reserved1cc[18];	/* 0x01cc */
 	__u64	pp;			/* 0x01de */
@@ -739,6 +742,7 @@ struct kvm_arch{
 	struct kvm_s390_cpu_model model;
 	struct kvm_s390_crypto crypto;
 	struct kvm_s390_vsie vsie;
+	u8 epdx;
 	u64 epoch;
 	struct kvm_s390_migration_state *migration_state;
 	/* subset of available cpu features enabled by user space */

arch/s390/include/asm/page-states.h

@@ -13,7 +13,8 @@
 #define ESSA_SET_POT_VOLATILE		4
 #define ESSA_SET_STABLE_RESIDENT	5
 #define ESSA_SET_STABLE_IF_RESIDENT	6
+#define ESSA_SET_STABLE_NODAT		7
 
-#define ESSA_MAX	ESSA_SET_STABLE_IF_RESIDENT
+#define ESSA_MAX	ESSA_SET_STABLE_NODAT
 
 #endif

arch/s390/include/asm/page.h

@@ -133,6 +133,9 @@ static inline int page_reset_referenced(unsigned long addr)
 struct page;
 void arch_free_page(struct page *page, int order);
 void arch_alloc_page(struct page *page, int order);
+void arch_set_page_dat(struct page *page, int order);
+void arch_set_page_nodat(struct page *page, int order);
+int arch_test_page_nodat(struct page *page);
 void arch_set_page_states(int make_stable);
 
 static inline int devmem_is_allowed(unsigned long pfn)

arch/s390/include/asm/pgtable.h

@@ -376,6 +376,7 @@ static inline int is_module_addr(void *addr)
 
 /* Guest Page State used for virtualization */
 #define _PGSTE_GPS_ZERO			0x0000000080000000UL
+#define _PGSTE_GPS_NODAT		0x0000000040000000UL
 #define _PGSTE_GPS_USAGE_MASK		0x0000000003000000UL
 #define _PGSTE_GPS_USAGE_STABLE		0x0000000000000000UL
 #define _PGSTE_GPS_USAGE_UNUSED		0x0000000001000000UL
@@ -952,15 +953,30 @@ static inline pte_t pte_mkhuge(pte_t pte)
 #define IPTE_GLOBAL	0
 #define	IPTE_LOCAL	1
 
-static inline void __ptep_ipte(unsigned long address, pte_t *ptep, int local)
+#define IPTE_NODAT	0x400
+#define IPTE_GUEST_ASCE	0x800
+
+static inline void __ptep_ipte(unsigned long address, pte_t *ptep,
+			       unsigned long opt, unsigned long asce,
+			       int local)
 {
 	unsigned long pto = (unsigned long) ptep;
 
+	if (__builtin_constant_p(opt) && opt == 0) {
 		/* Invalidation + TLB flush for the pte */
 		asm volatile(
 			"	.insn	rrf,0xb2210000,%[r1],%[r2],0,%[m4]"
 			: "+m" (*ptep) : [r1] "a" (pto), [r2] "a" (address),
 			  [m4] "i" (local));
+		return;
+	}
+
+	/* Invalidate ptes with options + TLB flush of the ptes */
+	opt = opt | (asce & _ASCE_ORIGIN);
+	asm volatile(
+		"	.insn	rrf,0xb2210000,%[r1],%[r2],%[r3],%[m4]"
+		: [r2] "+a" (address), [r3] "+a" (opt)
+		: [r1] "a" (pto), [m4] "i" (local) : "memory");
 }
 
 static inline void __ptep_ipte_range(unsigned long address, int nr,
@@ -1341,31 +1357,61 @@ static inline void __pmdp_csp(pmd_t *pmdp)
 #define IDTE_GLOBAL	0
 #define IDTE_LOCAL	1
 
-static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp, int local)
+#define IDTE_PTOA	0x0800
+#define IDTE_NODAT	0x1000
+#define IDTE_GUEST_ASCE	0x2000
+
+static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
+			       unsigned long opt, unsigned long asce,
+			       int local)
 {
 	unsigned long sto;
 
-	sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t);
+	sto = (unsigned long) pmdp - pmd_index(addr) * sizeof(pmd_t);
+	if (__builtin_constant_p(opt) && opt == 0) {
+		/* flush without guest asce */
 		asm volatile(
 			"	.insn	rrf,0xb98e0000,%[r1],%[r2],0,%[m4]"
 			: "+m" (*pmdp)
-		: [r1] "a" (sto), [r2] "a" ((address & HPAGE_MASK)),
+			: [r1] "a" (sto), [r2] "a" ((addr & HPAGE_MASK)),
 			  [m4] "i" (local)
 			: "cc" );
+	} else {
+		/* flush with guest asce */
+		asm volatile(
+			"	.insn	rrf,0xb98e0000,%[r1],%[r2],%[r3],%[m4]"
+			: "+m" (*pmdp)
+			: [r1] "a" (sto), [r2] "a" ((addr & HPAGE_MASK) | opt),
+			  [r3] "a" (asce), [m4] "i" (local)
+			: "cc" );
+	}
 }
 
-static inline void __pudp_idte(unsigned long address, pud_t *pudp, int local)
+static inline void __pudp_idte(unsigned long addr, pud_t *pudp,
+			       unsigned long opt, unsigned long asce,
+			       int local)
 {
 	unsigned long r3o;
 
-	r3o = (unsigned long) pudp - pud_index(address) * sizeof(pud_t);
+	r3o = (unsigned long) pudp - pud_index(addr) * sizeof(pud_t);
 	r3o |= _ASCE_TYPE_REGION3;
+	if (__builtin_constant_p(opt) && opt == 0) {
+		/* flush without guest asce */
 		asm volatile(
 			"	.insn	rrf,0xb98e0000,%[r1],%[r2],0,%[m4]"
 			: "+m" (*pudp)
-		: [r1] "a" (r3o), [r2] "a" ((address & PUD_MASK)),
+			: [r1] "a" (r3o), [r2] "a" ((addr & PUD_MASK)),
 			  [m4] "i" (local)
 			: "cc");
+	} else {
+		/* flush with guest asce */
+		asm volatile(
+			"	.insn	rrf,0xb98e0000,%[r1],%[r2],%[r3],%[m4]"
+			: "+m" (*pudp)
+			: [r1] "a" (r3o), [r2] "a" ((addr & PUD_MASK) | opt),
+			  [r3] "a" (asce), [m4] "i" (local)
+			: "cc" );
+	}
 }
 
 pmd_t pmdp_xchg_direct(struct mm_struct *, unsigned long, pmd_t *, pmd_t);

arch/s390/include/asm/setup.h

@@ -29,8 +29,9 @@
 #define MACHINE_FLAG_TE		_BITUL(11)
 #define MACHINE_FLAG_TLB_LC	_BITUL(12)
 #define MACHINE_FLAG_VX		_BITUL(13)
-#define MACHINE_FLAG_NX		_BITUL(14)
+#define MACHINE_FLAG_TLB_GUEST	_BITUL(14)
-#define MACHINE_FLAG_GS		_BITUL(15)
+#define MACHINE_FLAG_NX		_BITUL(15)
+#define MACHINE_FLAG_GS		_BITUL(16)
 
 #define LPP_MAGIC		_BITUL(31)
 #define LPP_PFAULT_PID_MASK	_AC(0xffffffff, UL)
@@ -68,6 +69,7 @@ extern void detect_memory_memblock(void);
 #define MACHINE_HAS_TE		(S390_lowcore.machine_flags & MACHINE_FLAG_TE)
 #define MACHINE_HAS_TLB_LC	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
 #define MACHINE_HAS_VX		(S390_lowcore.machine_flags & MACHINE_FLAG_VX)
+#define MACHINE_HAS_TLB_GUEST	(S390_lowcore.machine_flags & MACHINE_FLAG_TLB_GUEST)
 #define MACHINE_HAS_NX		(S390_lowcore.machine_flags & MACHINE_FLAG_NX)
 #define MACHINE_HAS_GS		(S390_lowcore.machine_flags & MACHINE_FLAG_GS)
 
@@ -106,7 +108,8 @@ extern void pfault_fini(void);
 
 void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault);
 
-extern void cmma_init(void);
+void cmma_init(void);
+void cmma_init_nodat(void);
 
 extern void (*_machine_restart)(char *command);
 extern void (*_machine_halt)(void);

arch/s390/include/asm/tlbflush.h

@@ -20,10 +20,15 @@ static inline void __tlb_flush_local(void)
  */
 static inline void __tlb_flush_idte(unsigned long asce)
 {
+	unsigned long opt;
+
+	opt = IDTE_PTOA;
+	if (MACHINE_HAS_TLB_GUEST)
+		opt |= IDTE_GUEST_ASCE;
 	/* Global TLB flush for the mm */
 	asm volatile(
 		"	.insn	rrf,0xb98e0000,0,%0,%1,0"
-		: : "a" (2048), "a" (asce) : "cc");
+		: : "a" (opt), "a" (asce) : "cc");
 }
 
 #ifdef CONFIG_SMP

arch/s390/include/uapi/asm/kvm.h

@@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req {
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW		0
 #define KVM_S390_VM_TOD_HIGH		1
+#define KVM_S390_VM_TOD_EXT		2
+
+struct kvm_s390_vm_tod_clock {
+	__u8  epoch_idx;
+	__u64 tod;
+};
 
 /* kvm attributes for KVM_S390_VM_CPU_MODEL */
 /* processor related attributes are r/w */

arch/s390/kernel/suspend.c

@@ -98,10 +98,16 @@ int page_key_alloc(unsigned long pages)
  */
 void page_key_read(unsigned long *pfn)
 {
+	struct page *page;
 	unsigned long addr;
+	unsigned char key;
 
-	addr = (unsigned long) page_address(pfn_to_page(*pfn));
+	page = pfn_to_page(*pfn);
-	*(unsigned char *) pfn = (unsigned char) page_get_storage_key(addr);
+	addr = (unsigned long) page_address(page);
+	key = (unsigned char) page_get_storage_key(addr) & 0x7f;
+	if (arch_test_page_nodat(page))
+		key |= 0x80;
+	*(unsigned char *) pfn = key;
 }
 
 /*
@@ -126,8 +132,16 @@ void page_key_memorize(unsigned long *pfn)
  */
 void page_key_write(void *address)
 {
-	page_set_storage_key((unsigned long) address,
+	struct page *page;
-			     page_key_rp->data[page_key_rx], 0);
+	unsigned char key;
+
+	key = page_key_rp->data[page_key_rx];
+	page_set_storage_key((unsigned long) address, key & 0x7f, 0);
+	page = virt_to_page(address);
+	if (key & 0x80)
+		arch_set_page_nodat(page, 0);
+	else
+		arch_set_page_dat(page, 0);
 	if (++page_key_rx >= PAGE_KEY_DATA_SIZE)
 		return;
 	page_key_rp = page_key_rp->next;

arch/s390/kernel/vdso.c

@@ -157,6 +157,8 @@ int vdso_alloc_per_cpu(struct lowcore *lowcore)
 	page_frame = get_zeroed_page(GFP_KERNEL);
 	if (!segment_table || !page_table || !page_frame)
 		goto out;
+	arch_set_page_dat(virt_to_page(segment_table), SEGMENT_ORDER);
+	arch_set_page_dat(virt_to_page(page_table), 0);
 
 	/* Initialize per-cpu vdso data page */
 	vd = (struct vdso_per_cpu_data *) page_frame;

arch/s390/kvm/guestdbg.c

@@ -308,7 +308,7 @@ static inline int in_addr_range(u64 addr, u64 a, u64 b)
 		return (addr >= a) && (addr <= b);
 	else
 		/* "overflowing" interval */
-		return (addr <= a) && (addr >= b);
+		return (addr >= a) || (addr <= b);
 }
 
 #define end_of_range(bp_info) (bp_info->addr + bp_info->len - 1)

arch/s390/kvm/interrupt.c

@@ -2479,6 +2479,7 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
 	struct kvm_s390_mchk_info *mchk;
 	union mci mci;
 	__u64 cr14 = 0;         /* upper bits are not used */
+	int rc;
 
 	mci.val = mcck_info->mcic;
 	if (mci.sr)
@@ -2496,12 +2497,13 @@ void kvm_s390_reinject_machine_check(struct kvm_vcpu *vcpu,
 	if (mci.ck) {
 		/* Inject the floating machine check */
 		inti.type = KVM_S390_MCHK;
-		WARN_ON_ONCE(__inject_vm(vcpu->kvm, &inti));
+		rc = __inject_vm(vcpu->kvm, &inti);
 	} else {
 		/* Inject the machine check to specified vcpu */
 		irq.type = KVM_S390_MCHK;
-		WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
+		rc = kvm_s390_inject_vcpu(vcpu, &irq);
 	}
+	WARN_ON_ONCE(rc);
 }
 
 int kvm_set_routing_entry(struct kvm *kvm,

arch/s390/kvm/kvm-s390.c

@@ -130,6 +130,12 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
+struct kvm_s390_tod_clock_ext {
+	__u8 epoch_idx;
+	__u64 tod;
+	__u8 reserved[7];
+} __packed;
+
 /* allow nested virtualization in KVM (if enabled by user space) */
 static int nested;
 module_param(nested, int, S_IRUGO);
@@ -874,6 +880,26 @@ static int kvm_s390_vm_get_migration(struct kvm *kvm,
 	return 0;
 }
 
+static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_tod_clock gtod;
+
+	if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
+		return -EFAULT;
+
+	if (test_kvm_facility(kvm, 139))
+		kvm_s390_set_tod_clock_ext(kvm, &gtod);
+	else if (gtod.epoch_idx == 0)
+		kvm_s390_set_tod_clock(kvm, gtod.tod);
+	else
+		return -EINVAL;
+
+	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",
+		gtod.epoch_idx, gtod.tod);
+
+	return 0;
+}
+
 static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	u8 gtod_high;
@@ -909,6 +935,9 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
 		return -EINVAL;
 
 	switch (attr->attr) {
+	case KVM_S390_VM_TOD_EXT:
+		ret = kvm_s390_set_tod_ext(kvm, attr);
+		break;
 	case KVM_S390_VM_TOD_HIGH:
 		ret = kvm_s390_set_tod_high(kvm, attr);
 		break;
@@ -922,6 +951,43 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
 	return ret;
 }
 
+static void kvm_s390_get_tod_clock_ext(struct kvm *kvm,
+					struct kvm_s390_vm_tod_clock *gtod)
+{
+	struct kvm_s390_tod_clock_ext htod;
+
+	preempt_disable();
+
+	get_tod_clock_ext((char *)&htod);
+
+	gtod->tod = htod.tod + kvm->arch.epoch;
+	gtod->epoch_idx = htod.epoch_idx + kvm->arch.epdx;
+
+	if (gtod->tod < htod.tod)
+		gtod->epoch_idx += 1;
+
+	preempt_enable();
+}
+
+static int kvm_s390_get_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_tod_clock gtod;
+
+	memset(&gtod, 0, sizeof(gtod));
+
+	if (test_kvm_facility(kvm, 139))
+		kvm_s390_get_tod_clock_ext(kvm, &gtod);
+	else
+		gtod.tod = kvm_s390_get_tod_clock_fast(kvm);
+
+	if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
+		return -EFAULT;
+
+	VM_EVENT(kvm, 3, "QUERY: TOD extension: 0x%x, TOD base: 0x%llx",
+		gtod.epoch_idx, gtod.tod);
+	return 0;
+}
+
 static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	u8 gtod_high = 0;
@@ -954,6 +1020,9 @@ static int kvm_s390_get_tod(struct kvm *kvm, struct kvm_device_attr *attr)
 		return -EINVAL;
 
 	switch (attr->attr) {
+	case KVM_S390_VM_TOD_EXT:
+		ret = kvm_s390_get_tod_ext(kvm, attr);
+		break;
 	case KVM_S390_VM_TOD_HIGH:
 		ret = kvm_s390_get_tod_high(kvm, attr);
 		break;
@@ -1505,7 +1574,7 @@ static int kvm_s390_get_cmma_bits(struct kvm *kvm,
 		if (r < 0)
 			pgstev = 0;
 		/* save the value */
-		res[i++] = (pgstev >> 24) & 0x3;
+		res[i++] = (pgstev >> 24) & 0x43;
 		/*
 		 * if the next bit is too far away, stop.
 		 * if we reached the previous "next", find the next one
@@ -1583,7 +1652,7 @@ static int kvm_s390_set_cmma_bits(struct kvm *kvm,
 
 		pgstev = bits[i];
 		pgstev = pgstev << 24;
-		mask &= _PGSTE_GPS_USAGE_MASK;
+		mask &= _PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT;
 		set_pgste_bits(kvm->mm, hva, mask, pgstev);
 	}
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
@@ -1858,8 +1927,16 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	memcpy(kvm->arch.model.fac_list, kvm->arch.model.fac_mask,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 
+	/* we are always in czam mode - even on pre z14 machines */
+	set_kvm_facility(kvm->arch.model.fac_mask, 138);
+	set_kvm_facility(kvm->arch.model.fac_list, 138);
+	/* we emulate STHYI in kvm */
 	set_kvm_facility(kvm->arch.model.fac_mask, 74);
 	set_kvm_facility(kvm->arch.model.fac_list, 74);
+	if (MACHINE_HAS_TLB_GUEST) {
+		set_kvm_facility(kvm->arch.model.fac_mask, 147);
+		set_kvm_facility(kvm->arch.model.fac_list, 147);
+	}
 
 	kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid();
 	kvm->arch.model.ibc = sclp.ibc & 0x0fff;
@@ -2369,6 +2446,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->eca |= ECA_VX;
 		vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
 	}
+	if (test_kvm_facility(vcpu->kvm, 139))
+		vcpu->arch.sie_block->ecd |= ECD_MEF;
+
 	vcpu->arch.sie_block->sdnxo = ((unsigned long) &vcpu->run->s.regs.sdnx)
 					| SDNXC;
 	vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
@@ -2860,6 +2940,35 @@ retry:
 	return 0;
 }
 
+void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
+				 const struct kvm_s390_vm_tod_clock *gtod)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_s390_tod_clock_ext htod;
+	int i;
+
+	mutex_lock(&kvm->lock);
+	preempt_disable();
+
+	get_tod_clock_ext((char *)&htod);
+
+	kvm->arch.epoch = gtod->tod - htod.tod;
+	kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx;
+
+	if (kvm->arch.epoch > gtod->tod)
+		kvm->arch.epdx -= 1;
+
+	kvm_s390_vcpu_block_all(kvm);
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		vcpu->arch.sie_block->epoch = kvm->arch.epoch;
+		vcpu->arch.sie_block->epdx  = kvm->arch.epdx;
+	}
+
+	kvm_s390_vcpu_unblock_all(kvm);
+	preempt_enable();
+	mutex_unlock(&kvm->lock);
+}
+
 void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod)
 {
 	struct kvm_vcpu *vcpu;

arch/s390/kvm/kvm-s390.h

@@ -272,6 +272,8 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
 int handle_sthyi(struct kvm_vcpu *vcpu);
 
 /* implemented in kvm-s390.c */
+void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
+				 const struct kvm_s390_vm_tod_clock *gtod);
 void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod);
 long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);

arch/s390/kvm/priv.c

@@ -988,6 +988,8 @@ static inline int do_essa(struct kvm_vcpu *vcpu, const int orc)
 		if (pgstev & _PGSTE_GPS_ZERO)
 			res |= 1;
 	}
+	if (pgstev & _PGSTE_GPS_NODAT)
+		res |= 0x20;
 	vcpu->run->s.regs.gprs[r1] = res;
 	/*
 	 * It is possible that all the normal 511 slots were full, in which case
@@ -1027,7 +1029,9 @@ static int handle_essa(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 	/* Check for invalid operation request code */
 	orc = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
-	if (orc > ESSA_MAX)
+	/* ORCs 0-6 are always valid */
+	if (orc > (test_kvm_facility(vcpu->kvm, 147) ? ESSA_SET_STABLE_NODAT
+						: ESSA_SET_STABLE_IF_RESIDENT))
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	if (likely(!vcpu->kvm->arch.migration_state)) {

arch/s390/kvm/sigp.c

@@ -155,29 +155,26 @@ static int __sigp_stop_and_store_status(struct kvm_vcpu *vcpu,
 	return rc;
 }
 
-static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
+static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter,
+			   u64 *status_reg)
 {
-	int rc;
 	unsigned int i;
 	struct kvm_vcpu *v;
+	bool all_stopped = true;
 
-	switch (parameter & 0xff) {
-	case 0:
-		rc = SIGP_CC_NOT_OPERATIONAL;
-		break;
-	case 1:
-	case 2:
 	kvm_for_each_vcpu(i, v, vcpu->kvm) {
-			v->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+		if (v == vcpu)
-			kvm_clear_async_pf_completion_queue(v);
+			continue;
+		if (!is_vcpu_stopped(v))
+			all_stopped = false;
 	}
 
-		rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+	*status_reg &= 0xffffffff00000000UL;
-		break;
+
-	default:
+	/* Reject set arch order, with czam we're always in z/Arch mode. */
-		rc = -EOPNOTSUPP;
+	*status_reg |= (all_stopped ? SIGP_STATUS_INVALID_PARAMETER :
-	}
+					SIGP_STATUS_INCORRECT_STATE);
-	return rc;
+	return SIGP_CC_STATUS_STORED;
 }
 
 static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
@@ -446,7 +443,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 	switch (order_code) {
 	case SIGP_SET_ARCHITECTURE:
 		vcpu->stat.instruction_sigp_arch++;
-		rc = __sigp_set_arch(vcpu, parameter);
+		rc = __sigp_set_arch(vcpu, parameter,
+				     &vcpu->run->s.regs.gprs[r1]);
 		break;
 	default:
 		rc = handle_sigp_dst(vcpu, order_code, cpu_addr,

arch/s390/kvm/sthyi.c

@@ -394,7 +394,7 @@ static int sthyi(u64 vaddr)
 		"srl     %[cc],28\n"
 		: [cc] "=d" (cc)
 		: [code] "d" (code), [addr] "a" (addr)
-		: "memory", "cc");
+		: "3", "memory", "cc");
 	return cc;
 }
 
@@ -425,7 +425,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
 	VCPU_EVENT(vcpu, 3, "STHYI: fc: %llu addr: 0x%016llx", code, addr);
 	trace_kvm_s390_handle_sthyi(vcpu, code, addr);
 
-	if (reg1 == reg2 || reg1 & 1 || reg2 & 1 || addr & ~PAGE_MASK)
+	if (reg1 == reg2 || reg1 & 1 || reg2 & 1)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	if (code & 0xffff) {
@@ -433,13 +433,8 @@ int handle_sthyi(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	/*
+	if (addr & ~PAGE_MASK)
-	 * If the page has not yet been faulted in, we want to do that
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
-	 * now and not after all the expensive calculations.
-	 */
-	r = write_guest(vcpu, addr, reg2, &cc, 1);
-	if (r)
-		return kvm_s390_inject_prog_cond(vcpu, r);
 
 	sctns = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!sctns)

arch/s390/kvm/vsie.c

@@ -349,6 +349,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		scb_s->eca |= scb_o->eca & ECA_IB;
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_CEI))
 		scb_s->eca |= scb_o->eca & ECA_CEI;
+	/* Epoch Extension */
+	if (test_kvm_facility(vcpu->kvm, 139))
+		scb_s->ecd |= scb_o->ecd & ECD_MEF;
 
 	prepare_ibc(vcpu, vsie_page);
 	rc = shadow_crycb(vcpu, vsie_page);
@@ -806,8 +809,6 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
 	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
-	struct mcck_volatile_info *mcck_info;
-	struct sie_page *sie_page;
 	int rc;
 
 	handle_last_fault(vcpu, vsie_page);
@@ -831,9 +832,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 
 	if (rc == -EINTR) {
 		VCPU_EVENT(vcpu, 3, "%s", "machine check");
-		sie_page = container_of(scb_s, struct sie_page, sie_block);
+		kvm_s390_reinject_machine_check(vcpu, &vsie_page->mcck_info);
-		mcck_info = &sie_page->mcck_info;
-		kvm_s390_reinject_machine_check(vcpu, mcck_info);
 		return 0;
 	}
 
@@ -919,6 +918,13 @@ static void register_shadow_scb(struct kvm_vcpu *vcpu,
 	 */
 	preempt_disable();
 	scb_s->epoch += vcpu->kvm->arch.epoch;
+
+	if (scb_s->ecd & ECD_MEF) {
+		scb_s->epdx += vcpu->kvm->arch.epdx;
+		if (scb_s->epoch < vcpu->kvm->arch.epoch)
+			scb_s->epdx += 1;
+	}
+
 	preempt_enable();
 }
 

arch/s390/mm/init.c

@@ -137,6 +137,8 @@ void __init mem_init(void)
 	free_all_bootmem();
 	setup_zero_pages();	/* Setup zeroed pages. */
 
+	cmma_init_nodat();
+
 	mem_init_print_info(NULL);
 }
 

arch/s390/mm/page-states.c

@@ -10,9 +10,10 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/memblock.h>
 #include <linux/gfp.h>
 #include <linux/init.h>
-
+#include <asm/facility.h>
 #include <asm/page-states.h>
 
 static int cmma_flag = 1;
@@ -36,14 +37,16 @@ __setup("cmma=", cmma);
 static inline int cmma_test_essa(void)
 {
 	register unsigned long tmp asm("0") = 0;
-	register int rc asm("1") = -EOPNOTSUPP;
+	register int rc asm("1");
 
+	/* test ESSA_GET_STATE */
 	asm volatile(
-		"       .insn rrf,0xb9ab0000,%1,%1,0,0\n"
+		"	.insn	rrf,0xb9ab0000,%1,%1,%2,0\n"
 		"0:     la      %0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
-		: "+&d" (rc), "+&d" (tmp));
+		: "=&d" (rc), "+&d" (tmp)
+		: "i" (ESSA_GET_STATE), "0" (-EOPNOTSUPP));
 	return rc;
 }
 
@@ -51,11 +54,26 @@ void __init cmma_init(void)
 {
 	if (!cmma_flag)
 		return;
-	if (cmma_test_essa())
+	if (cmma_test_essa()) {
 		cmma_flag = 0;
+		return;
+	}
+	if (test_facility(147))
+		cmma_flag = 2;
 }
 
-static inline void set_page_unstable(struct page *page, int order)
+static inline unsigned char get_page_state(struct page *page)
+{
+	unsigned char state;
+
+	asm volatile("	.insn	rrf,0xb9ab0000,%0,%1,%2,0"
+		     : "=&d" (state)
+		     : "a" (page_to_phys(page)),
+		       "i" (ESSA_GET_STATE));
+	return state & 0x3f;
+}
+
+static inline void set_page_unused(struct page *page, int order)
 {
 	int i, rc;
 
@@ -66,14 +84,7 @@ static inline void set_page_unstable(struct page *page, int order)
 			       "i" (ESSA_SET_UNUSED));
 }
 
-void arch_free_page(struct page *page, int order)
+static inline void set_page_stable_dat(struct page *page, int order)
-{
-	if (!cmma_flag)
-		return;
-	set_page_unstable(page, order);
-}
-
-static inline void set_page_stable(struct page *page, int order)
 {
 	int i, rc;
 
@@ -84,11 +95,162 @@ static inline void set_page_stable(struct page *page, int order)
 			       "i" (ESSA_SET_STABLE));
 }
 
+static inline void set_page_stable_nodat(struct page *page, int order)
+{
+	int i, rc;
+
+	for (i = 0; i < (1 << order); i++)
+		asm volatile(".insn rrf,0xb9ab0000,%0,%1,%2,0"
+			     : "=&d" (rc)
+			     : "a" (page_to_phys(page + i)),
+			       "i" (ESSA_SET_STABLE_NODAT));
+}
+
+static void mark_kernel_pmd(pud_t *pud, unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	struct page *page;
+	pmd_t *pmd;
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(*pmd) || pmd_large(*pmd))
+			continue;
+		page = virt_to_page(pmd_val(*pmd));
+		set_bit(PG_arch_1, &page->flags);
+	} while (pmd++, addr = next, addr != end);
+}
+
+static void mark_kernel_pud(p4d_t *p4d, unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	struct page *page;
+	pud_t *pud;
+	int i;
+
+	pud = pud_offset(p4d, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none(*pud) || pud_large(*pud))
+			continue;
+		if (!pud_folded(*pud)) {
+			page = virt_to_page(pud_val(*pud));
+			for (i = 0; i < 3; i++)
+				set_bit(PG_arch_1, &page[i].flags);
+		}
+		mark_kernel_pmd(pud, addr, next);
+	} while (pud++, addr = next, addr != end);
+}
+
+static void mark_kernel_p4d(pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	struct page *page;
+	p4d_t *p4d;
+	int i;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none(*p4d))
+			continue;
+		if (!p4d_folded(*p4d)) {
+			page = virt_to_page(p4d_val(*p4d));
+			for (i = 0; i < 3; i++)
+				set_bit(PG_arch_1, &page[i].flags);
+		}
+		mark_kernel_pud(p4d, addr, next);
+	} while (p4d++, addr = next, addr != end);
+}
+
+static void mark_kernel_pgd(void)
+{
+	unsigned long addr, next;
+	struct page *page;
+	pgd_t *pgd;
+	int i;
+
+	addr = 0;
+	pgd = pgd_offset_k(addr);
+	do {
+		next = pgd_addr_end(addr, MODULES_END);
+		if (pgd_none(*pgd))
+			continue;
+		if (!pgd_folded(*pgd)) {
+			page = virt_to_page(pgd_val(*pgd));
+			for (i = 0; i < 3; i++)
+				set_bit(PG_arch_1, &page[i].flags);
+		}
+		mark_kernel_p4d(pgd, addr, next);
+	} while (pgd++, addr = next, addr != MODULES_END);
+}
+
+void __init cmma_init_nodat(void)
+{
+	struct memblock_region *reg;
+	struct page *page;
+	unsigned long start, end, ix;
+
+	if (cmma_flag < 2)
+		return;
+	/* Mark pages used in kernel page tables */
+	mark_kernel_pgd();
+
+	/* Set all kernel pages not used for page tables to stable/no-dat */
+	for_each_memblock(memory, reg) {
+		start = memblock_region_memory_base_pfn(reg);
+		end = memblock_region_memory_end_pfn(reg);
+		page = pfn_to_page(start);
+		for (ix = start; ix < end; ix++, page++) {
+			if (__test_and_clear_bit(PG_arch_1, &page->flags))
+				continue;	/* skip page table pages */
+			if (!list_empty(&page->lru))
+				continue;	/* skip free pages */
+			set_page_stable_nodat(page, 0);
+		}
+	}
+}
+
+void arch_free_page(struct page *page, int order)
+{
+	if (!cmma_flag)
+		return;
+	set_page_unused(page, order);
+}
+
 void arch_alloc_page(struct page *page, int order)
 {
 	if (!cmma_flag)
 		return;
-	set_page_stable(page, order);
+	if (cmma_flag < 2)
+		set_page_stable_dat(page, order);
+	else
+		set_page_stable_nodat(page, order);
+}
+
+void arch_set_page_dat(struct page *page, int order)
+{
+	if (!cmma_flag)
+		return;
+	set_page_stable_dat(page, order);
+}
+
+void arch_set_page_nodat(struct page *page, int order)
+{
+	if (cmma_flag < 2)
+		return;
+	set_page_stable_nodat(page, order);
+}
+
+int arch_test_page_nodat(struct page *page)
+{
+	unsigned char state;
+
+	if (cmma_flag < 2)
+		return 0;
+	state = get_page_state(page);
+	return !!(state & 0x20);
 }
 
 void arch_set_page_states(int make_stable)
@@ -108,9 +270,9 @@ void arch_set_page_states(int make_stable)
 			list_for_each(l, &zone->free_area[order].free_list[t]) {
 				page = list_entry(l, struct page, lru);
 				if (make_stable)
-					set_page_stable(page, order);
+					set_page_stable_dat(page, 0);
 				else
-					set_page_unstable(page, order);
+					set_page_unused(page, order);
 			}
 		}
 		spin_unlock_irqrestore(&zone->lock, flags);

arch/s390/mm/pageattr.c

@@ -328,7 +328,7 @@ static void ipte_range(pte_t *pte, unsigned long address, int nr)
 		return;
 	}
 	for (i = 0; i < nr; i++) {
-		__ptep_ipte(address, pte, IPTE_GLOBAL);
+		__ptep_ipte(address, pte, 0, 0, IPTE_GLOBAL);
 		address += PAGE_SIZE;
 		pte++;
 	}

arch/s390/mm/pgalloc.c

@@ -57,6 +57,7 @@ unsigned long *crst_table_alloc(struct mm_struct *mm)
 
 	if (!page)
 		return NULL;
+	arch_set_page_dat(page, 2);
 	return (unsigned long *) page_to_phys(page);
 }
 
@@ -214,6 +215,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 		__free_page(page);
 		return NULL;
 	}
+	arch_set_page_dat(page, 0);
 	/* Initialize page table */
 	table = (unsigned long *) page_to_phys(page);
 	if (mm_alloc_pgste(mm)) {

arch/s390/mm/pgtable.c

@@ -25,8 +25,49 @@
 #include <asm/mmu_context.h>
 #include <asm/page-states.h>
 
+static inline void ptep_ipte_local(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, int nodat)
+{
+	unsigned long opt, asce;
+
+	if (MACHINE_HAS_TLB_GUEST) {
+		opt = 0;
+		asce = READ_ONCE(mm->context.gmap_asce);
+		if (asce == 0UL || nodat)
+			opt |= IPTE_NODAT;
+		if (asce != -1UL) {
+			asce = asce ? : mm->context.asce;
+			opt |= IPTE_GUEST_ASCE;
+		}
+		__ptep_ipte(addr, ptep, opt, asce, IPTE_LOCAL);
+	} else {
+		__ptep_ipte(addr, ptep, 0, 0, IPTE_LOCAL);
+	}
+}
+
+static inline void ptep_ipte_global(struct mm_struct *mm, unsigned long addr,
+				    pte_t *ptep, int nodat)
+{
+	unsigned long opt, asce;
+
+	if (MACHINE_HAS_TLB_GUEST) {
+		opt = 0;
+		asce = READ_ONCE(mm->context.gmap_asce);
+		if (asce == 0UL || nodat)
+			opt |= IPTE_NODAT;
+		if (asce != -1UL) {
+			asce = asce ? : mm->context.asce;
+			opt |= IPTE_GUEST_ASCE;
+		}
+		__ptep_ipte(addr, ptep, opt, asce, IPTE_GLOBAL);
+	} else {
+		__ptep_ipte(addr, ptep, 0, 0, IPTE_GLOBAL);
+	}
+}
+
 static inline pte_t ptep_flush_direct(struct mm_struct *mm,
-				      unsigned long addr, pte_t *ptep)
+				      unsigned long addr, pte_t *ptep,
+				      int nodat)
 {
 	pte_t old;
 
@@ -36,15 +77,16 @@ static inline pte_t ptep_flush_direct(struct mm_struct *mm,
 	atomic_inc(&mm->context.flush_count);
 	if (MACHINE_HAS_TLB_LC &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
-		__ptep_ipte(addr, ptep, IPTE_LOCAL);
+		ptep_ipte_local(mm, addr, ptep, nodat);
 	else
-		__ptep_ipte(addr, ptep, IPTE_GLOBAL);
+		ptep_ipte_global(mm, addr, ptep, nodat);
 	atomic_dec(&mm->context.flush_count);
 	return old;
 }
 
 static inline pte_t ptep_flush_lazy(struct mm_struct *mm,
-				    unsigned long addr, pte_t *ptep)
+				    unsigned long addr, pte_t *ptep,
+				    int nodat)
 {
 	pte_t old;
 
@@ -57,7 +99,7 @@ static inline pte_t ptep_flush_lazy(struct mm_struct *mm,
 		pte_val(*ptep) |= _PAGE_INVALID;
 		mm->context.flush_mm = 1;
 	} else
-		__ptep_ipte(addr, ptep, IPTE_GLOBAL);
+		ptep_ipte_global(mm, addr, ptep, nodat);
 	atomic_dec(&mm->context.flush_count);
 	return old;
 }
@@ -229,10 +271,12 @@ pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr,
 {
 	pgste_t pgste;
 	pte_t old;
+	int nodat;
 
 	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
-	old = ptep_flush_direct(mm, addr, ptep);
+	nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT);
+	old = ptep_flush_direct(mm, addr, ptep, nodat);
 	old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
 	preempt_enable();
 	return old;
@@ -244,10 +288,12 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr,
 {
 	pgste_t pgste;
 	pte_t old;
+	int nodat;
 
 	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
-	old = ptep_flush_lazy(mm, addr, ptep);
+	nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT);
+	old = ptep_flush_lazy(mm, addr, ptep, nodat);
 	old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
 	preempt_enable();
 	return old;
@@ -259,10 +305,12 @@ pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
 {
 	pgste_t pgste;
 	pte_t old;
+	int nodat;
 
 	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
-	old = ptep_flush_lazy(mm, addr, ptep);
+	nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT);
+	old = ptep_flush_lazy(mm, addr, ptep, nodat);
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_update_all(old, pgste, mm);
 		pgste_set(ptep, pgste);
@@ -290,6 +338,28 @@ void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL(ptep_modify_prot_commit);
 
+static inline void pmdp_idte_local(struct mm_struct *mm,
+				   unsigned long addr, pmd_t *pmdp)
+{
+	if (MACHINE_HAS_TLB_GUEST)
+		__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
+			    mm->context.asce, IDTE_LOCAL);
+	else
+		__pmdp_idte(addr, pmdp, 0, 0, IDTE_LOCAL);
+}
+
+static inline void pmdp_idte_global(struct mm_struct *mm,
+				    unsigned long addr, pmd_t *pmdp)
+{
+	if (MACHINE_HAS_TLB_GUEST)
+		__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
+			    mm->context.asce, IDTE_GLOBAL);
+	else if (MACHINE_HAS_IDTE)
+		__pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL);
+	else
+		__pmdp_csp(pmdp);
+}
+
 static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
 				      unsigned long addr, pmd_t *pmdp)
 {
@@ -298,16 +368,12 @@ static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
 	old = *pmdp;
 	if (pmd_val(old) & _SEGMENT_ENTRY_INVALID)
 		return old;
-	if (!MACHINE_HAS_IDTE) {
-		__pmdp_csp(pmdp);
-		return old;
-	}
 	atomic_inc(&mm->context.flush_count);
 	if (MACHINE_HAS_TLB_LC &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
-		__pmdp_idte(addr, pmdp, IDTE_LOCAL);
+		pmdp_idte_local(mm, addr, pmdp);
 	else
-		__pmdp_idte(addr, pmdp, IDTE_GLOBAL);
+		pmdp_idte_global(mm, addr, pmdp);
 	atomic_dec(&mm->context.flush_count);
 	return old;
 }
@@ -325,10 +391,9 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 			  cpumask_of(smp_processor_id()))) {
 		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
 		mm->context.flush_mm = 1;
-	} else if (MACHINE_HAS_IDTE)
+	} else {
-		__pmdp_idte(addr, pmdp, IDTE_GLOBAL);
+		pmdp_idte_global(mm, addr, pmdp);
-	else
+	}
-		__pmdp_csp(pmdp);
 	atomic_dec(&mm->context.flush_count);
 	return old;
 }
@@ -359,6 +424,32 @@ pmd_t pmdp_xchg_lazy(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL(pmdp_xchg_lazy);
 
+static inline void pudp_idte_local(struct mm_struct *mm,
+				   unsigned long addr, pud_t *pudp)
+{
+	if (MACHINE_HAS_TLB_GUEST)
+		__pudp_idte(addr, pudp, IDTE_NODAT | IDTE_GUEST_ASCE,
+			    mm->context.asce, IDTE_LOCAL);
+	else
+		__pudp_idte(addr, pudp, 0, 0, IDTE_LOCAL);
+}
+
+static inline void pudp_idte_global(struct mm_struct *mm,
+				    unsigned long addr, pud_t *pudp)
+{
+	if (MACHINE_HAS_TLB_GUEST)
+		__pudp_idte(addr, pudp, IDTE_NODAT | IDTE_GUEST_ASCE,
+			    mm->context.asce, IDTE_GLOBAL);
+	else if (MACHINE_HAS_IDTE)
+		__pudp_idte(addr, pudp, 0, 0, IDTE_GLOBAL);
+	else
+		/*
+		 * Invalid bit position is the same for pmd and pud, so we can
+		 * re-use _pmd_csp() here
+		 */
+		__pmdp_csp((pmd_t *) pudp);
+}
+
 static inline pud_t pudp_flush_direct(struct mm_struct *mm,
 				      unsigned long addr, pud_t *pudp)
 {
@@ -367,20 +458,12 @@ static inline pud_t pudp_flush_direct(struct mm_struct *mm,
 	old = *pudp;
 	if (pud_val(old) & _REGION_ENTRY_INVALID)
 		return old;
-	if (!MACHINE_HAS_IDTE) {
-		/*
-		 * Invalid bit position is the same for pmd and pud, so we can
-		 * re-use _pmd_csp() here
-		 */
-		__pmdp_csp((pmd_t *) pudp);
-		return old;
-	}
 	atomic_inc(&mm->context.flush_count);
 	if (MACHINE_HAS_TLB_LC &&
 	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
-		__pudp_idte(addr, pudp, IDTE_LOCAL);
+		pudp_idte_local(mm, addr, pudp);
 	else
-		__pudp_idte(addr, pudp, IDTE_GLOBAL);
+		pudp_idte_global(mm, addr, pudp);
 	atomic_dec(&mm->context.flush_count);
 	return old;
 }
@@ -482,7 +565,7 @@ int ptep_force_prot(struct mm_struct *mm, unsigned long addr,
 {
 	pte_t entry;
 	pgste_t pgste;
-	int pte_i, pte_p;
+	int pte_i, pte_p, nodat;
 
 	pgste = pgste_get_lock(ptep);
 	entry = *ptep;
@@ -495,13 +578,14 @@ int ptep_force_prot(struct mm_struct *mm, unsigned long addr,
 		return -EAGAIN;
 	}
 	/* Change access rights and set pgste bit */
+	nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT);
 	if (prot == PROT_NONE && !pte_i) {
-		ptep_flush_direct(mm, addr, ptep);
+		ptep_flush_direct(mm, addr, ptep, nodat);
 		pgste = pgste_update_all(entry, pgste, mm);
 		pte_val(entry) |= _PAGE_INVALID;
 	}
 	if (prot == PROT_READ && !pte_p) {
-		ptep_flush_direct(mm, addr, ptep);
+		ptep_flush_direct(mm, addr, ptep, nodat);
 		pte_val(entry) &= ~_PAGE_INVALID;
 		pte_val(entry) |= _PAGE_PROTECT;
 	}
@@ -541,10 +625,12 @@ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
 void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep)
 {
 	pgste_t pgste;
+	int nodat;
 
 	pgste = pgste_get_lock(ptep);
 	/* notifier is called by the caller */
-	ptep_flush_direct(mm, saddr, ptep);
+	nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT);
+	ptep_flush_direct(mm, saddr, ptep, nodat);
 	/* don't touch the storage key - it belongs to parent pgste */
 	pgste = pgste_set_pte(ptep, pgste, __pte(_PAGE_INVALID));
 	pgste_set_unlock(ptep, pgste);
@@ -617,6 +703,7 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
 	pte_t *ptep;
 	pte_t pte;
 	bool dirty;
+	int nodat;
 
 	pgd = pgd_offset(mm, addr);
 	p4d = p4d_alloc(mm, pgd, addr);
@@ -645,7 +732,8 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
 	pte = *ptep;
 	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
 		pgste = pgste_pte_notify(mm, addr, ptep, pgste);
-		__ptep_ipte(addr, ptep, IPTE_GLOBAL);
+		nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT);
+		ptep_ipte_global(mm, addr, ptep, nodat);
 		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
 			pte_val(pte) |= _PAGE_PROTECT;
 		else
@@ -831,7 +919,7 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 	case ESSA_GET_STATE:
 		break;
 	case ESSA_SET_STABLE:
-		pgstev &= ~_PGSTE_GPS_USAGE_MASK;
+		pgstev &= ~(_PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT);
 		pgstev |= _PGSTE_GPS_USAGE_STABLE;
 		break;
 	case ESSA_SET_UNUSED:
@@ -877,6 +965,10 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 			pgstev |= _PGSTE_GPS_USAGE_STABLE;
 		}
 		break;
+	case ESSA_SET_STABLE_NODAT:
+		pgstev &= ~_PGSTE_GPS_USAGE_MASK;
+		pgstev |= _PGSTE_GPS_USAGE_STABLE | _PGSTE_GPS_NODAT;
+		break;
 	default:
 		/* we should never get here! */
 		break;

arch/s390/tools/gen_facilities.c

@@ -80,6 +80,7 @@ static struct facility_def facility_defs[] = {
 			78, /* enhanced-DAT 2 */
 			130, /* instruction-execution-protection */
 			131, /* enhanced-SOP 2 and side-effect */
+			139, /* multiple epoch facility */
 			146, /* msa extension 8 */
 			-1  /* END */
 		}

drivers/s390/char/sclp_early.c

@@ -39,7 +39,7 @@ struct read_info_sccb {
 	u8	fac84;			/* 84 */
 	u8	fac85;			/* 85 */
 	u8	_pad_86[91 - 86];	/* 86-90 */
-	u8	flags;			/* 91 */
+	u8	fac91;			/* 91 */
 	u8	_pad_92[98 - 92];	/* 92-97 */
 	u8	fac98;			/* 98 */
 	u8	hamaxpow;		/* 99 */
@@ -103,6 +103,8 @@ static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb)
 	sclp.has_kss = !!(sccb->fac98 & 0x01);
 	if (sccb->fac85 & 0x02)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP;
+	if (sccb->fac91 & 0x40)
+		S390_lowcore.machine_flags |= MACHINE_FLAG_TLB_GUEST;
 	sclp.rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2;
 	sclp.rzm = sccb->rnsize ? sccb->rnsize : sccb->rnsize2;
 	sclp.rzm <<= 20;
@@ -139,7 +141,7 @@ static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb)
 
 	/* Save IPL information */
 	sclp_ipl_info.is_valid = 1;
-	if (sccb->flags & 0x2)
+	if (sccb->fac91 & 0x2)
 		sclp_ipl_info.has_dump = 1;
 	memcpy(&sclp_ipl_info.loadparm, &sccb->loadparm, LOADPARM_LEN);