Merge branch 'next' (accumulated 3.16 merge window patches) into master

Now that 3.15 is released, this merges the 'next' branch into 'master',
bringing us to the normal situation where my 'master' branch is the
merge window.

* accumulated work in next: (6809 commits)
  ufs: sb mutex merge + mutex_destroy
  powerpc: update comments for generic idle conversion
  cris: update comments for generic idle conversion
  idle: remove cpu_idle() forward declarations
  nbd: zero from and len fields in NBD_CMD_DISCONNECT.
  mm: convert some level-less printks to pr_*
  MAINTAINERS: adi-buildroot-devel is moderated
  MAINTAINERS: add linux-api for review of API/ABI changes
  mm/kmemleak-test.c: use pr_fmt for logging
  fs/dlm/debug_fs.c: replace seq_printf by seq_puts
  fs/dlm/lockspace.c: convert simple_str to kstr
  fs/dlm/config.c: convert simple_str to kstr
  mm: mark remap_file_pages() syscall as deprecated
  mm: memcontrol: remove unnecessary memcg argument from soft limit functions
  mm: memcontrol: clean up memcg zoneinfo lookup
  mm/memblock.c: call kmemleak directly from memblock_(alloc|free)
  mm/mempool.c: update the kmemleak stack trace for mempool allocations
  lib/radix-tree.c: update the kmemleak stack trace for radix tree allocations
  mm: introduce kmemleak_update_trace()
  mm/kmemleak.c: use %u to print ->checksum
  ...

27 files changed, 539 insertions, 274 deletions

diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 1d4706114a45..fa934fe080c1 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -412,9 +412,4 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic64_dec_and_test(_v)	(atomic64_sub_return(1, _v) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
 #endif /* __ARCH_S390_ATOMIC__  */
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 578680f6207a..19ff956b752b 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -27,8 +27,9 @@
 #define smp_rmb()			rmb()
 #define smp_wmb()			wmb()
 #define smp_read_barrier_depends()	read_barrier_depends()
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
+
+#define smp_mb__before_atomic()		smp_mb()
+#define smp_mb__after_atomic()		smp_mb()
 
 #define set_mb(var, value)		do { var = value; mb(); } while (0)
 
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index a9c2c0686177..b80e456d6428 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -229,5 +229,5 @@ int ccw_device_siosl(struct ccw_device *);
 
 extern void ccw_device_get_schid(struct ccw_device *, struct subchannel_id *);
 
-extern void *ccw_device_get_chp_desc(struct ccw_device *, int);
+struct channel_path_desc *ccw_device_get_chp_desc(struct ccw_device *, int);
 #endif /* _S390_CCWDEV_H_ */
diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h
index ebc2913f9ee0..057ce0ca6377 100644
--- a/arch/s390/include/asm/ccwgroup.h
+++ b/arch/s390/include/asm/ccwgroup.h
@@ -10,6 +10,8 @@ struct ccw_driver;
  * @count: number of attached slave devices
  * @dev: embedded device structure
  * @cdev: variable number of slave devices, allocated as needed
+ * @ungroup_work: work to be done when a ccwgroup notifier has action
+ *	type %BUS_NOTIFY_UNBIND_DRIVER
  */
 struct ccwgroup_device {
 	enum {
diff --git a/arch/s390/include/asm/chpid.h b/arch/s390/include/asm/chpid.h
index 38c405ef89ce..7298eec98541 100644
--- a/arch/s390/include/asm/chpid.h
+++ b/arch/s390/include/asm/chpid.h
@@ -8,6 +8,17 @@
 #include <uapi/asm/chpid.h>
 #include <asm/cio.h>
 
+struct channel_path_desc {
+	u8 flags;
+	u8 lsn;
+	u8 desc;
+	u8 chpid;
+	u8 swla;
+	u8 zeroes;
+	u8 chla;
+	u8 chpp;
+} __packed;
+
 static inline void chp_id_init(struct chp_id *chpid)
 {
 	memset(chpid, 0, sizeof(struct chp_id));
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index 4e63f1a13600..31ab9f346d7e 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -57,6 +57,20 @@ static inline void __ctl_clear_bit(unsigned int cr, unsigned int bit)
 void smp_ctl_set_bit(int cr, int bit);
 void smp_ctl_clear_bit(int cr, int bit);
 
+union ctlreg0 {
+	unsigned long val;
+	struct {
+#ifdef CONFIG_64BIT
+		unsigned long	   : 32;
+#endif
+		unsigned long	   : 3;
+		unsigned long lap  : 1; /* Low-address-protection control */
+		unsigned long	   : 4;
+		unsigned long edat : 1; /* Enhanced-DAT-enablement control */
+		unsigned long	   : 23;
+	};
+};
+
 #ifdef CONFIG_SMP
 # define ctl_set_bit(cr, bit) smp_ctl_set_bit(cr, bit)
 # define ctl_clear_bit(cr, bit) smp_ctl_clear_bit(cr, bit)
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 69cf5b5eddc9..a4811aa0304d 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -29,7 +29,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, newval, ret;
 
-	update_primary_asce(current);
+	load_kernel_asce();
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
@@ -79,7 +79,7 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 {
 	int ret;
 
-	update_primary_asce(current);
+	load_kernel_asce();
 	asm volatile(
 		"   sacf 256\n"
 		"0: cs   %1,%4,0(%5)\n"
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 154b60089be9..4181d7baabba 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -32,16 +32,26 @@
 #define KVM_NR_IRQCHIPS 1
 #define KVM_IRQCHIP_NUM_PINS 4096
 
+#define SIGP_CTRL_C	0x00800000
+
 struct sca_entry {
-	atomic_t scn;
+	atomic_t ctrl;
 	__u32	reserved;
 	__u64	sda;
 	__u64	reserved2[2];
 } __attribute__((packed));
 
+union ipte_control {
+	unsigned long val;
+	struct {
+		unsigned long k  : 1;
+		unsigned long kh : 31;
+		unsigned long kg : 32;
+	};
+};
 
 struct sca_block {
-	__u64	ipte_control;
+	union ipte_control ipte_control;
 	__u64	reserved[5];
 	__u64	mcn;
 	__u64	reserved2;
@@ -64,6 +74,7 @@ struct sca_block {
 #define CPUSTAT_ZARCH      0x00000800
 #define CPUSTAT_MCDS       0x00000100
 #define CPUSTAT_SM         0x00000080
+#define CPUSTAT_IBS        0x00000040
 #define CPUSTAT_G          0x00000008
 #define CPUSTAT_GED        0x00000004
 #define CPUSTAT_J          0x00000002
@@ -71,7 +82,9 @@ struct sca_block {
 
 struct kvm_s390_sie_block {
 	atomic_t cpuflags;		/* 0x0000 */
-	__u32	prefix;			/* 0x0004 */
+	__u32 : 1;			/* 0x0004 */
+	__u32 prefix : 18;
+	__u32 : 13;
 	__u8	reserved08[4];		/* 0x0008 */
 #define PROG_IN_SIE (1<<0)
 	__u32	prog0c;			/* 0x000c */
@@ -85,12 +98,27 @@ struct kvm_s390_sie_block {
 	__u8	reserved40[4];		/* 0x0040 */
 #define LCTL_CR0	0x8000
 #define LCTL_CR6	0x0200
+#define LCTL_CR9	0x0040
+#define LCTL_CR10	0x0020
+#define LCTL_CR11	0x0010
 #define LCTL_CR14	0x0002
 	__u16   lctl;			/* 0x0044 */
 	__s16	icpua;			/* 0x0046 */
-#define ICTL_LPSW 0x00400000
+#define ICTL_PINT	0x20000000
+#define ICTL_LPSW	0x00400000
+#define ICTL_STCTL	0x00040000
+#define ICTL_ISKE	0x00004000
+#define ICTL_SSKE	0x00002000
+#define ICTL_RRBE	0x00001000
+#define ICTL_TPROT	0x00000200
 	__u32	ictl;			/* 0x0048 */
 	__u32	eca;			/* 0x004c */
+#define ICPT_INST	0x04
+#define ICPT_PROGI	0x08
+#define ICPT_INSTPROGI	0x0C
+#define ICPT_OPEREXC	0x2C
+#define ICPT_PARTEXEC	0x38
+#define ICPT_IOINST	0x40
 	__u8	icptcode;		/* 0x0050 */
 	__u8	reserved51;		/* 0x0051 */
 	__u16	ihcpu;			/* 0x0052 */
@@ -109,9 +137,24 @@ struct kvm_s390_sie_block {
 	psw_t	gpsw;			/* 0x0090 */
 	__u64	gg14;			/* 0x00a0 */
 	__u64	gg15;			/* 0x00a8 */
-	__u8	reservedb0[30];		/* 0x00b0 */
-	__u16   iprcc;			/* 0x00ce */
-	__u8	reservedd0[48];		/* 0x00d0 */
+	__u8	reservedb0[20];		/* 0x00b0 */
+	__u16	extcpuaddr;		/* 0x00c4 */
+	__u16	eic;			/* 0x00c6 */
+	__u32	reservedc8;		/* 0x00c8 */
+	__u16	pgmilc;			/* 0x00cc */
+	__u16	iprcc;			/* 0x00ce */
+	__u32	dxc;			/* 0x00d0 */
+	__u16	mcn;			/* 0x00d4 */
+	__u8	perc;			/* 0x00d6 */
+	__u8	peratmid;		/* 0x00d7 */
+	__u64	peraddr;		/* 0x00d8 */
+	__u8	eai;			/* 0x00e0 */
+	__u8	peraid;			/* 0x00e1 */
+	__u8	oai;			/* 0x00e2 */
+	__u8	armid;			/* 0x00e3 */
+	__u8	reservede4[4];		/* 0x00e4 */
+	__u64	tecmc;			/* 0x00e8 */
+	__u8	reservedf0[16];		/* 0x00f0 */
 	__u64	gcr[16];		/* 0x0100 */
 	__u64	gbea;			/* 0x0180 */
 	__u8	reserved188[24];	/* 0x0188 */
@@ -146,6 +189,8 @@ struct kvm_vcpu_stat {
 	u32 exit_instruction;
 	u32 instruction_lctl;
 	u32 instruction_lctlg;
+	u32 instruction_stctl;
+	u32 instruction_stctg;
 	u32 exit_program_interruption;
 	u32 exit_instr_and_program;
 	u32 deliver_external_call;
@@ -164,6 +209,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_stpx;
 	u32 instruction_stap;
 	u32 instruction_storage_key;
+	u32 instruction_ipte_interlock;
 	u32 instruction_stsch;
 	u32 instruction_chsc;
 	u32 instruction_stsi;
@@ -183,13 +229,58 @@ struct kvm_vcpu_stat {
 	u32 diagnose_9c;
 };
 
-#define PGM_OPERATION            0x01
-#define PGM_PRIVILEGED_OP	 0x02
-#define PGM_EXECUTE              0x03
-#define PGM_PROTECTION           0x04
-#define PGM_ADDRESSING           0x05
-#define PGM_SPECIFICATION        0x06
-#define PGM_DATA                 0x07
+#define PGM_OPERATION			0x01
+#define PGM_PRIVILEGED_OP		0x02
+#define PGM_EXECUTE			0x03
+#define PGM_PROTECTION			0x04
+#define PGM_ADDRESSING			0x05
+#define PGM_SPECIFICATION		0x06
+#define PGM_DATA			0x07
+#define PGM_FIXED_POINT_OVERFLOW	0x08
+#define PGM_FIXED_POINT_DIVIDE		0x09
+#define PGM_DECIMAL_OVERFLOW		0x0a
+#define PGM_DECIMAL_DIVIDE		0x0b
+#define PGM_HFP_EXPONENT_OVERFLOW	0x0c
+#define PGM_HFP_EXPONENT_UNDERFLOW	0x0d
+#define PGM_HFP_SIGNIFICANCE		0x0e
+#define PGM_HFP_DIVIDE			0x0f
+#define PGM_SEGMENT_TRANSLATION		0x10
+#define PGM_PAGE_TRANSLATION		0x11
+#define PGM_TRANSLATION_SPEC		0x12
+#define PGM_SPECIAL_OPERATION		0x13
+#define PGM_OPERAND			0x15
+#define PGM_TRACE_TABEL			0x16
+#define PGM_SPACE_SWITCH		0x1c
+#define PGM_HFP_SQUARE_ROOT		0x1d
+#define PGM_PC_TRANSLATION_SPEC		0x1f
+#define PGM_AFX_TRANSLATION		0x20
+#define PGM_ASX_TRANSLATION		0x21
+#define PGM_LX_TRANSLATION		0x22
+#define PGM_EX_TRANSLATION		0x23
+#define PGM_PRIMARY_AUTHORITY		0x24
+#define PGM_SECONDARY_AUTHORITY		0x25
+#define PGM_LFX_TRANSLATION		0x26
+#define PGM_LSX_TRANSLATION		0x27
+#define PGM_ALET_SPECIFICATION		0x28
+#define PGM_ALEN_TRANSLATION		0x29
+#define PGM_ALE_SEQUENCE		0x2a
+#define PGM_ASTE_VALIDITY		0x2b
+#define PGM_ASTE_SEQUENCE		0x2c
+#define PGM_EXTENDED_AUTHORITY		0x2d
+#define PGM_LSTE_SEQUENCE		0x2e
+#define PGM_ASTE_INSTANCE		0x2f
+#define PGM_STACK_FULL			0x30
+#define PGM_STACK_EMPTY			0x31
+#define PGM_STACK_SPECIFICATION		0x32
+#define PGM_STACK_TYPE			0x33
+#define PGM_STACK_OPERATION		0x34
+#define PGM_ASCE_TYPE			0x38
+#define PGM_REGION_FIRST_TRANS		0x39
+#define PGM_REGION_SECOND_TRANS		0x3a
+#define PGM_REGION_THIRD_TRANS		0x3b
+#define PGM_MONITOR			0x40
+#define PGM_PER				0x80
+#define PGM_CRYPTO_OPERATION		0x119
 
 struct kvm_s390_interrupt_info {
 	struct list_head list;
@@ -229,6 +320,45 @@ struct kvm_s390_float_interrupt {
 	unsigned int irq_count;
 };
 
+struct kvm_hw_wp_info_arch {
+	unsigned long addr;
+	unsigned long phys_addr;
+	int len;
+	char *old_data;
+};
+
+struct kvm_hw_bp_info_arch {
+	unsigned long addr;
+	int len;
+};
+
+/*
+ * Only the upper 16 bits of kvm_guest_debug->control are arch specific.
+ * Further KVM_GUESTDBG flags which an be used from userspace can be found in
+ * arch/s390/include/uapi/asm/kvm.h
+ */
+#define KVM_GUESTDBG_EXIT_PENDING 0x10000000
+
+#define guestdbg_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)
+#define guestdbg_sstep_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+#define guestdbg_hw_bp_enabled(vcpu) \
+		(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+#define guestdbg_exit_pending(vcpu) (guestdbg_enabled(vcpu) && \
+		(vcpu->guest_debug & KVM_GUESTDBG_EXIT_PENDING))
+
+struct kvm_guestdbg_info_arch {
+	unsigned long cr0;
+	unsigned long cr9;
+	unsigned long cr10;
+	unsigned long cr11;
+	struct kvm_hw_bp_info_arch *hw_bp_info;
+	struct kvm_hw_wp_info_arch *hw_wp_info;
+	int nr_hw_bp;
+	int nr_hw_wp;
+	unsigned long last_bp;
+};
 
 struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
@@ -238,11 +368,13 @@ struct kvm_vcpu_arch {
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct tasklet_struct tasklet;
+	struct kvm_s390_pgm_info pgm;
 	union  {
 		struct cpuid	cpu_id;
 		u64		stidp_data;
 	};
 	struct gmap *gmap;
+	struct kvm_guestdbg_info_arch guestdbg;
 #define KVM_S390_PFAULT_TOKEN_INVALID	(-1UL)
 	unsigned long pfault_token;
 	unsigned long pfault_select;
@@ -285,7 +417,10 @@ struct kvm_arch{
 	struct gmap *gmap;
 	int css_support;
 	int use_irqchip;
+	int use_cmma;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
+	wait_queue_head_t ipte_wq;
+	spinlock_t start_stop_lock;
 };
 
 #define KVM_HVA_ERR_BAD		(-1UL)
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index bbf8141408cd..4349197ab9df 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -56,13 +56,14 @@ struct _lowcore {
 	__u16	pgm_code;			/* 0x008e */
 	__u32	trans_exc_code;			/* 0x0090 */
 	__u16	mon_class_num;			/* 0x0094 */
-	__u16	per_perc_atmid;			/* 0x0096 */
+	__u8	per_code;			/* 0x0096 */
+	__u8	per_atmid;			/* 0x0097 */
 	__u32	per_address;			/* 0x0098 */
 	__u32	monitor_code;			/* 0x009c */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
 	__u8	op_access_id;			/* 0x00a2 */
-	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	ar_mode_id;			/* 0x00a3 */
 	__u8	pad_0x00a4[0x00b8-0x00a4];	/* 0x00a4 */
 	__u16	subchannel_id;			/* 0x00b8 */
 	__u16	subchannel_nr;			/* 0x00ba */
@@ -93,7 +94,9 @@ struct _lowcore {
 	__u32	save_area_sync[8];		/* 0x0200 */
 	__u32	save_area_async[8];		/* 0x0220 */
 	__u32	save_area_restart[1];		/* 0x0240 */
-	__u8	pad_0x0244[0x0248-0x0244];	/* 0x0244 */
+
+	/* CPU flags. */
+	__u32	cpu_flags;			/* 0x0244 */
 
 	/* Return psws. */
 	psw_t	return_psw;			/* 0x0248 */
@@ -139,12 +142,9 @@ struct _lowcore {
 	__u32	percpu_offset;			/* 0x02f0 */
 	__u32	machine_flags;			/* 0x02f4 */
 	__u32	ftrace_func;			/* 0x02f8 */
-	__u8	pad_0x02fc[0x0300-0x02fc];	/* 0x02fc */
-
-	/* Interrupt response block */
-	__u8	irb[64];			/* 0x0300 */
+	__u32	spinlock_lockval;		/* 0x02fc */
 
-	__u8	pad_0x0340[0x0e00-0x0340];	/* 0x0340 */
+	__u8	pad_0x0300[0x0e00-0x0300];	/* 0x0300 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
@@ -196,12 +196,13 @@ struct _lowcore {
 	__u16	pgm_code;			/* 0x008e */
 	__u32	data_exc_code;			/* 0x0090 */
 	__u16	mon_class_num;			/* 0x0094 */
-	__u16	per_perc_atmid;			/* 0x0096 */
+	__u8	per_code;			/* 0x0096 */
+	__u8	per_atmid;			/* 0x0097 */
 	__u64	per_address;			/* 0x0098 */
 	__u8	exc_access_id;			/* 0x00a0 */
 	__u8	per_access_id;			/* 0x00a1 */
 	__u8	op_access_id;			/* 0x00a2 */
-	__u8	ar_access_id;			/* 0x00a3 */
+	__u8	ar_mode_id;			/* 0x00a3 */
 	__u8	pad_0x00a4[0x00a8-0x00a4];	/* 0x00a4 */
 	__u64	trans_exc_code;			/* 0x00a8 */
 	__u64	monitor_code;			/* 0x00b0 */
@@ -237,7 +238,9 @@ struct _lowcore {
 	__u64	save_area_sync[8];		/* 0x0200 */
 	__u64	save_area_async[8];		/* 0x0240 */
 	__u64	save_area_restart[1];		/* 0x0280 */
-	__u8	pad_0x0288[0x0290-0x0288];	/* 0x0288 */
+
+	/* CPU flags. */
+	__u64	cpu_flags;			/* 0x0288 */
 
 	/* Return psws. */
 	psw_t	return_psw;			/* 0x0290 */
@@ -285,15 +288,13 @@ struct _lowcore {
 	__u64	machine_flags;			/* 0x0388 */
 	__u64	ftrace_func;			/* 0x0390 */
 	__u64	gmap;				/* 0x0398 */
-	__u8	pad_0x03a0[0x0400-0x03a0];	/* 0x03a0 */
-
-	/* Interrupt response block. */
-	__u8	irb[64];			/* 0x0400 */
+	__u32	spinlock_lockval;		/* 0x03a0 */
+	__u8	pad_0x03a0[0x0400-0x03a4];	/* 0x03a4 */
 
 	/* Per cpu primary space access list */
-	__u32	paste[16];			/* 0x0440 */
+	__u32	paste[16];			/* 0x0400 */
 
-	__u8	pad_0x0480[0x0e00-0x0480];	/* 0x0480 */
+	__u8	pad_0x04c0[0x0e00-0x0440];	/* 0x0440 */
 
 	/*
 	 * 0xe00 contains the address of the IPL Parameter Information
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index f77695a82f64..a5e656260a70 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -16,6 +16,8 @@ typedef struct {
 	unsigned long vdso_base;
 	/* The mmu context has extended page tables. */
 	unsigned int has_pgste:1;
+	/* The mmu context uses storage keys. */
+	unsigned int use_skey:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						      \
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 71be346d0e3c..c28f32a45af5 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -23,6 +23,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #endif
 	mm->context.has_pgste = 0;
+	mm->context.use_skey = 0;
 	mm->context.asce_limit = STACK_TOP_MAX;
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
@@ -30,33 +31,31 @@ static inline int init_new_context(struct task_struct *tsk,
 
 #define destroy_context(mm)             do { } while (0)
 
-static inline void update_user_asce(struct mm_struct *mm, int load_primary)
+static inline void set_user_asce(struct mm_struct *mm)
 {
 	pgd_t *pgd = mm->pgd;
 
 	S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd);
-	if (load_primary)
-		__ctl_load(S390_lowcore.user_asce, 1, 1);
 	set_fs(current->thread.mm_segment);
+	set_cpu_flag(CIF_ASCE);
 }
 
-static inline void clear_user_asce(struct mm_struct *mm, int load_primary)
+static inline void clear_user_asce(void)
 {
 	S390_lowcore.user_asce = S390_lowcore.kernel_asce;
 
-	if (load_primary)
-		__ctl_load(S390_lowcore.user_asce, 1, 1);
+	__ctl_load(S390_lowcore.user_asce, 1, 1);
 	__ctl_load(S390_lowcore.user_asce, 7, 7);
 }
 
-static inline void update_primary_asce(struct task_struct *tsk)
+static inline void load_kernel_asce(void)
 {
 	unsigned long asce;
 
 	__ctl_store(asce, 1, 1);
 	if (asce != S390_lowcore.kernel_asce)
 		__ctl_load(S390_lowcore.kernel_asce, 1, 1);
-	set_tsk_thread_flag(tsk, TIF_ASCE);
+	set_cpu_flag(CIF_ASCE);
 }
 
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
@@ -64,25 +63,17 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	int cpu = smp_processor_id();
 
-	update_primary_asce(tsk);
 	if (prev == next)
 		return;
 	if (MACHINE_HAS_TLB_LC)
 		cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
-	if (atomic_inc_return(&next->context.attach_count) >> 16) {
-		/* Delay update_user_asce until all TLB flushes are done. */
-		set_tsk_thread_flag(tsk, TIF_TLB_WAIT);
-		/* Clear old ASCE by loading the kernel ASCE. */
-		clear_user_asce(next, 0);
-	} else {
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-		update_user_asce(next, 0);
-		if (next->context.flush_mm)
-			/* Flush pending TLBs */
-			__tlb_flush_mm(next);
-	}
+	/* Clear old ASCE by loading the kernel ASCE. */
+	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
+	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
+	/* Delay loading of the new ASCE to control registers CR1 & CR7 */
+	set_cpu_flag(CIF_ASCE);
+	atomic_inc(&next->context.attach_count);
 	atomic_dec(&prev->context.attach_count);
-	WARN_ON(atomic_read(&prev->context.attach_count) < 0);
 	if (MACHINE_HAS_TLB_LC)
 		cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
 }
@@ -93,15 +84,14 @@ static inline void finish_arch_post_lock_switch(void)
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 
-	if (!test_tsk_thread_flag(tsk, TIF_TLB_WAIT))
+	if (!mm)
 		return;
 	preempt_disable();
-	clear_tsk_thread_flag(tsk, TIF_TLB_WAIT);
 	while (atomic_read(&mm->context.attach_count) >> 16)
 		cpu_relax();
 
 	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-	update_user_asce(mm, 0);
+	set_user_asce(mm);
 	if (mm->context.flush_mm)
 		__tlb_flush_mm(mm);
 	preempt_enable();
@@ -113,7 +103,9 @@ static inline void finish_arch_post_lock_switch(void)
 static inline void activate_mm(struct mm_struct *prev,
                                struct mm_struct *next)
 {
-        switch_mm(prev, next, current);
+	switch_mm(prev, next, current);
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
+	set_user_asce(next);
 }
 
 static inline void arch_dup_mmap(struct mm_struct *oldmm,
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 2583466f576b..c030900320e0 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -78,10 +78,16 @@ struct zpci_dev {
 	enum zpci_state state;
 	u32		fid;		/* function ID, used by sclp */
 	u32		fh;		/* function handle, used by insn's */
+	u16		vfn;		/* virtual function number */
 	u16		pchid;		/* physical channel ID */
 	u8		pfgid;		/* function group ID */
+	u8		pft;		/* pci function type */
 	u16		domain;
 
+	u8 pfip[CLP_PFIP_NR_SEGMENTS];	/* pci function internal path */
+	u32 uid;			/* user defined id */
+	u8 util_str[CLP_UTIL_STR_LEN];	/* utility string */
+
 	/* IRQ stuff */
 	u64		msi_addr;	/* MSI address */
 	struct airq_iv *aibv;		/* adapter interrupt bit vector */
@@ -120,6 +126,8 @@ static inline bool zdev_enabled(struct zpci_dev *zdev)
 	return (zdev->fh & (1UL << 31)) ? true : false;
 }
 
+extern const struct attribute_group *zpci_attr_groups[];
+
 /* -----------------------------------------------------------------------------
   Prototypes
 ----------------------------------------------------------------------------- */
@@ -166,10 +174,6 @@ static inline void zpci_exit_slot(struct zpci_dev *zdev) {}
 struct zpci_dev *get_zdev(struct pci_dev *);
 struct zpci_dev *get_zdev_by_fid(u32);
 
-/* sysfs */
-int zpci_sysfs_add_device(struct device *);
-void zpci_sysfs_remove_device(struct device *);
-
 /* DMA */
 int zpci_dma_init(void);
 void zpci_dma_exit(void);
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index d31d739f8689..dd78f92f1cce 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -44,6 +44,7 @@ struct clp_fh_list_entry {
 #define CLP_SET_DISABLE_PCI_FN	1	/* Yes, 1 disables it */
 
 #define CLP_UTIL_STR_LEN	64
+#define CLP_PFIP_NR_SEGMENTS	4
 
 /* List PCI functions request */
 struct clp_req_list_pci {
@@ -85,7 +86,7 @@ struct clp_rsp_query_pci {
 	struct clp_rsp_hdr hdr;
 	u32 fmt			:  4;	/* cmd request block format */
 	u32			: 28;
-	u64 reserved1;
+	u64			: 64;
 	u16 vfn;			/* virtual fn number */
 	u16			:  7;
 	u16 util_str_avail	:  1;	/* utility string available? */
@@ -94,10 +95,13 @@ struct clp_rsp_query_pci {
 	u8 bar_size[PCI_BAR_COUNT];
 	u16 pchid;
 	u32 bar[PCI_BAR_COUNT];
-	u64 reserved2;
+	u8 pfip[CLP_PFIP_NR_SEGMENTS];	/* pci function internal path */
+	u32			: 24;
+	u8 pft;				/* pci function type */
 	u64 sdma;			/* start dma as */
 	u64 edma;			/* end dma as */
-	u64 reserved3[6];
+	u32 reserved[11];
+	u32 uid;			/* user defined id */
 	u8 util_str[CLP_UTIL_STR_LEN];	/* utility string */
 } __packed;
 
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 884017cbfa9f..9e18a61d3df3 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -22,7 +22,8 @@ unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
 
-void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long);
+void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long,
+			    bool init_skey);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned long key, bool nq);
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 12f75313e086..fcba5e03839f 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -309,7 +309,8 @@ extern unsigned long MODULES_END;
 #define PGSTE_HC_BIT	0x00200000UL
 #define PGSTE_GR_BIT	0x00040000UL
 #define PGSTE_GC_BIT	0x00020000UL
-#define PGSTE_IN_BIT	0x00008000UL	/* IPTE notify bit */
+#define PGSTE_UC_BIT	0x00008000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x00004000UL	/* IPTE notify bit */
 
 #else /* CONFIG_64BIT */
 
@@ -391,7 +392,8 @@ extern unsigned long MODULES_END;
 #define PGSTE_HC_BIT	0x0020000000000000UL
 #define PGSTE_GR_BIT	0x0004000000000000UL
 #define PGSTE_GC_BIT	0x0002000000000000UL
-#define PGSTE_IN_BIT	0x0000800000000000UL	/* IPTE notify bit */
+#define PGSTE_UC_BIT	0x0000800000000000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x0000400000000000UL	/* IPTE notify bit */
 
 #endif /* CONFIG_64BIT */
 
@@ -466,6 +468,16 @@ static inline int mm_has_pgste(struct mm_struct *mm)
 #endif
 	return 0;
 }
+
+static inline int mm_use_skey(struct mm_struct *mm)
+{
+#ifdef CONFIG_PGSTE
+	if (mm->context.use_skey)
+		return 1;
+#endif
+	return 0;
+}
+
 /*
  * pgd/pmd/pte query functions
  */
@@ -699,26 +711,17 @@ static inline void pgste_set(pte_t *ptep, pgste_t pgste)
 #endif
 }
 
-static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
+static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste,
+				       struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE
 	unsigned long address, bits, skey;
 
-	if (pte_val(*ptep) & _PAGE_INVALID)
+	if (!mm_use_skey(mm) || pte_val(*ptep) & _PAGE_INVALID)
 		return pgste;
 	address = pte_val(*ptep) & PAGE_MASK;
 	skey = (unsigned long) page_get_storage_key(address);
 	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
-	if (!(pgste_val(pgste) & PGSTE_HC_BIT) && (bits & _PAGE_CHANGED)) {
-		/* Transfer dirty + referenced bit to host bits in pgste */
-		pgste_val(pgste) |= bits << 52;
-		page_set_storage_key(address, skey ^ bits, 0);
-	} else if (!(pgste_val(pgste) & PGSTE_HR_BIT) &&
-		   (bits & _PAGE_REFERENCED)) {
-		/* Transfer referenced bit to host bit in pgste */
-		pgste_val(pgste) |= PGSTE_HR_BIT;
-		page_reset_referenced(address);
-	}
 	/* Transfer page changed & referenced bit to guest bits in pgste */
 	pgste_val(pgste) |= bits << 48;		/* GR bit & GC bit */
 	/* Copy page access key and fetch protection bit to pgste */
@@ -729,25 +732,14 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 
 }
 
-static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
-{
-#ifdef CONFIG_PGSTE
-	if (pte_val(*ptep) & _PAGE_INVALID)
-		return pgste;
-	/* Get referenced bit from storage key */
-	if (page_reset_referenced(pte_val(*ptep) & PAGE_MASK))
-		pgste_val(pgste) |= PGSTE_HR_BIT | PGSTE_GR_BIT;
-#endif
-	return pgste;
-}
-
-static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
+static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry,
+				 struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE
 	unsigned long address;
 	unsigned long nkey;
 
-	if (pte_val(entry) & _PAGE_INVALID)
+	if (!mm_use_skey(mm) || pte_val(entry) & _PAGE_INVALID)
 		return;
 	VM_BUG_ON(!(pte_val(*ptep) & _PAGE_INVALID));
 	address = pte_val(entry) & PAGE_MASK;
@@ -757,23 +749,30 @@ static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry)
 	 * key C/R to 0.
 	 */
 	nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+	nkey |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
 	page_set_storage_key(address, nkey, 0);
 #endif
 }
 
-static inline void pgste_set_pte(pte_t *ptep, pte_t entry)
+static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 {
-	if (!MACHINE_HAS_ESOP &&
-	    (pte_val(entry) & _PAGE_PRESENT) &&
-	    (pte_val(entry) & _PAGE_WRITE)) {
-		/*
-		 * Without enhanced suppression-on-protection force
-		 * the dirty bit on for all writable ptes.
-		 */
-		pte_val(entry) |= _PAGE_DIRTY;
-		pte_val(entry) &= ~_PAGE_PROTECT;
+	if ((pte_val(entry) & _PAGE_PRESENT) &&
+	    (pte_val(entry) & _PAGE_WRITE) &&
+	    !(pte_val(entry) & _PAGE_INVALID)) {
+		if (!MACHINE_HAS_ESOP) {
+			/*
+			 * Without enhanced suppression-on-protection force
+			 * the dirty bit on for all writable ptes.
+			 */
+			pte_val(entry) |= _PAGE_DIRTY;
+			pte_val(entry) &= ~_PAGE_PROTECT;
+		}
+		if (!(pte_val(entry) & _PAGE_PROTECT))
+			/* This pte allows write access, set user-dirty */
+			pgste_val(pgste) |= PGSTE_UC_BIT;
 	}
 	*ptep = entry;
+	return pgste;
 }
 
 /**
@@ -839,6 +838,8 @@ unsigned long __gmap_fault(unsigned long address, struct gmap *);
 unsigned long gmap_fault(unsigned long address, struct gmap *);
 void gmap_discard(unsigned long from, unsigned long to, struct gmap *);
 void __gmap_zap(unsigned long address, struct gmap *);
+bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *);
+
 
 void gmap_register_ipte_notifier(struct gmap_notifier *);
 void gmap_unregister_ipte_notifier(struct gmap_notifier *);
@@ -870,8 +871,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
-		pgste_set_key(ptep, pgste, entry);
-		pgste_set_pte(ptep, entry);
+		pgste_set_key(ptep, pgste, entry, mm);
+		pgste = pgste_set_pte(ptep, pgste, entry);
 		pgste_set_unlock(ptep, pgste);
 	} else {
 		if (!(pte_val(entry) & _PAGE_INVALID) && MACHINE_HAS_EDAT1)
@@ -1017,45 +1018,6 @@ static inline pte_t pte_mkhuge(pte_t pte)
 }
 #endif
 
-/*
- * Get (and clear) the user dirty bit for a pte.
- */
-static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
-						 pte_t *ptep)
-{
-	pgste_t pgste;
-	int dirty = 0;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_update_all(ptep, pgste);
-		dirty = !!(pgste_val(pgste) & PGSTE_HC_BIT);
-		pgste_val(pgste) &= ~PGSTE_HC_BIT;
-		pgste_set_unlock(ptep, pgste);
-		return dirty;
-	}
-	return dirty;
-}
-
-/*
- * Get (and clear) the user referenced bit for a pte.
- */
-static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
-						 pte_t *ptep)
-{
-	pgste_t pgste;
-	int young = 0;
-
-	if (mm_has_pgste(mm)) {
-		pgste = pgste_get_lock(ptep);
-		pgste = pgste_update_young(ptep, pgste);
-		young = !!(pgste_val(pgste) & PGSTE_HR_BIT);
-		pgste_val(pgste) &= ~PGSTE_HR_BIT;
-		pgste_set_unlock(ptep, pgste);
-	}
-	return young;
-}
-
 static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 {
 	unsigned long pto = (unsigned long) ptep;
@@ -1118,6 +1080,36 @@ static inline void ptep_flush_lazy(struct mm_struct *mm,
 	atomic_sub(0x10000, &mm->context.attach_count);
 }
 
+/*
+ * Get (and clear) the user dirty bit for a pte.
+ */
+static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm,
+						 unsigned long addr,
+						 pte_t *ptep)
+{
+	pgste_t pgste;
+	pte_t pte;
+	int dirty;
+
+	if (!mm_has_pgste(mm))
+		return 0;
+	pgste = pgste_get_lock(ptep);
+	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
+	pgste_val(pgste) &= ~PGSTE_UC_BIT;
+	pte = *ptep;
+	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
+		pgste = pgste_ipte_notify(mm, ptep, pgste);
+		__ptep_ipte(addr, ptep);
+		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
+			pte_val(pte) |= _PAGE_PROTECT;
+		else
+			pte_val(pte) |= _PAGE_INVALID;
+		*ptep = pte;
+	}
+	pgste_set_unlock(ptep, pgste);
+	return dirty;
+}
+
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long addr, pte_t *ptep)
@@ -1137,7 +1129,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 	pte = pte_mkold(pte);
 
 	if (mm_has_pgste(vma->vm_mm)) {
-		pgste_set_pte(ptep, pte);
+		pgste = pgste_set_pte(ptep, pgste, pte);
 		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = pte;
@@ -1182,7 +1174,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	pte_val(*ptep) = _PAGE_INVALID;
 
 	if (mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, mm);
 		pgste_set_unlock(ptep, pgste);
 	}
 	return pte;
@@ -1205,7 +1197,7 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
 	ptep_flush_lazy(mm, address, ptep);
 
 	if (mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, mm);
 		pgste_set(ptep, pgste);
 	}
 	return pte;
@@ -1219,8 +1211,8 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get(ptep);
-		pgste_set_key(ptep, pgste, pte);
-		pgste_set_pte(ptep, pte);
+		pgste_set_key(ptep, pgste, pte, mm);
+		pgste = pgste_set_pte(ptep, pgste, pte);
 		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = pte;
@@ -1246,7 +1238,7 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
 		if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) ==
 		    _PGSTE_GPS_USAGE_UNUSED)
 			pte_val(pte) |= _PAGE_UNUSED;
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, vma->vm_mm);
 		pgste_set_unlock(ptep, pgste);
 	}
 	return pte;
@@ -1278,7 +1270,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 	pte_val(*ptep) = _PAGE_INVALID;
 
 	if (!full && mm_has_pgste(mm)) {
-		pgste = pgste_update_all(&pte, pgste);
+		pgste = pgste_update_all(&pte, pgste, mm);
 		pgste_set_unlock(ptep, pgste);
 	}
 	return pte;
@@ -1301,7 +1293,7 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
 		pte = pte_wrprotect(pte);
 
 		if (mm_has_pgste(mm)) {
-			pgste_set_pte(ptep, pte);
+			pgste = pgste_set_pte(ptep, pgste, pte);
 			pgste_set_unlock(ptep, pgste);
 		} else
 			*ptep = pte;
@@ -1326,7 +1318,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
 	ptep_flush_direct(vma->vm_mm, address, ptep);
 
 	if (mm_has_pgste(vma->vm_mm)) {
-		pgste_set_pte(ptep, entry);
+		pgste = pgste_set_pte(ptep, pgste, entry);
 		pgste_set_unlock(ptep, pgste);
 	} else
 		*ptep = entry;
@@ -1734,6 +1726,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 extern int vmem_add_mapping(unsigned long start, unsigned long size);
 extern int vmem_remove_mapping(unsigned long start, unsigned long size);
 extern int s390_enable_sie(void);
+extern void s390_enable_skey(void);
 
 /*
  * No page table caches to initialise
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index dc5fc4f90e52..6f02d452bbee 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -11,6 +11,13 @@
 #ifndef __ASM_S390_PROCESSOR_H
 #define __ASM_S390_PROCESSOR_H
 
+#define CIF_MCCK_PENDING	0	/* machine check handling is pending */
+#define CIF_ASCE		1	/* user asce needs fixup / uaccess */
+
+#define _CIF_MCCK_PENDING	(1<<CIF_MCCK_PENDING)
+#define _CIF_ASCE		(1<<CIF_ASCE)
+
+
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
@@ -21,6 +28,21 @@
 #include <asm/setup.h>
 #include <asm/runtime_instr.h>
 
+static inline void set_cpu_flag(int flag)
+{
+	S390_lowcore.cpu_flags |= (1U << flag);
+}
+
+static inline void clear_cpu_flag(int flag)
+{
+	S390_lowcore.cpu_flags &= ~(1U << flag);
+}
+
+static inline int test_cpu_flag(int flag)
+{
+	return !!(S390_lowcore.cpu_flags & (1U << flag));
+}
+
 /*
  * Default implementation of macro that returns current
  * instruction pointer ("program counter").
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index f4783c0b7b43..55d69dd7473c 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -8,6 +8,12 @@
 
 #include <uapi/asm/ptrace.h>
 
+#define PIF_SYSCALL		0	/* inside a system call */
+#define PIF_PER_TRAP		1	/* deliver sigtrap on return to user */
+
+#define _PIF_SYSCALL		(1<<PIF_SYSCALL)
+#define _PIF_PER_TRAP		(1<<PIF_PER_TRAP)
+
 #ifndef __ASSEMBLY__
 
 #define PSW_KERNEL_BITS	(PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_ASC_HOME | \
@@ -16,6 +22,50 @@
 			 PSW_DEFAULT_KEY | PSW_MASK_BASE | PSW_MASK_MCHECK | \
 			 PSW_MASK_PSTATE | PSW_ASC_PRIMARY)
 
+struct psw_bits {
+	unsigned long long	: 1;
+	unsigned long long r	: 1; /* PER-Mask */
+	unsigned long long	: 3;
+	unsigned long long t	: 1; /* DAT Mode */
+	unsigned long long i	: 1; /* Input/Output Mask */
+	unsigned long long e	: 1; /* External Mask */
+	unsigned long long key	: 4; /* PSW Key */
+	unsigned long long	: 1;
+	unsigned long long m	: 1; /* Machine-Check Mask */
+	unsigned long long w	: 1; /* Wait State */
+	unsigned long long p	: 1; /* Problem State */
+	unsigned long long as	: 2; /* Address Space Control */
+	unsigned long long cc	: 2; /* Condition Code */
+	unsigned long long pm	: 4; /* Program Mask */
+	unsigned long long ri	: 1; /* Runtime Instrumentation */
+	unsigned long long	: 6;
+	unsigned long long eaba : 2; /* Addressing Mode */
+#ifdef CONFIG_64BIT
+	unsigned long long	: 31;
+	unsigned long long ia	: 64;/* Instruction Address */
+#else
+	unsigned long long ia	: 31;/* Instruction Address */
+#endif
+};
+
+enum {
+	PSW_AMODE_24BIT = 0,
+	PSW_AMODE_31BIT = 1,
+	PSW_AMODE_64BIT = 3
+};
+
+enum {
+	PSW_AS_PRIMARY	 = 0,
+	PSW_AS_ACCREG	 = 1,
+	PSW_AS_SECONDARY = 2,
+	PSW_AS_HOME	 = 3
+};
+
+#define psw_bits(__psw) (*({			\
+	typecheck(psw_t, __psw);		\
+	&(*(struct psw_bits *)(&(__psw)));	\
+}))
+
 /*
  * The pt_regs struct defines the way the registers are stored on
  * the stack during a system call.
@@ -29,6 +79,7 @@ struct pt_regs
 	unsigned int int_code;
 	unsigned int int_parm;
 	unsigned long int_parm_long;
+	unsigned long flags;
 };
 
 /*
@@ -79,6 +130,21 @@ struct per_struct_kernel {
 #define PER_CONTROL_SUSPENSION		0x00400000UL
 #define PER_CONTROL_ALTERATION		0x00200000UL
 
+static inline void set_pt_regs_flag(struct pt_regs *regs, int flag)
+{
+	regs->flags |= (1U << flag);
+}
+
+static inline void clear_pt_regs_flag(struct pt_regs *regs, int flag)
+{
+	regs->flags &= ~(1U << flag);
+}
+
+static inline int test_pt_regs_flag(struct pt_regs *regs, int flag)
+{
+	return !!(regs->flags & (1U << flag));
+}
+
 /*
  * These are defined as per linux/ptrace.h, which see.
  */
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 2f5e9932b4de..1aba89b53cb9 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -28,7 +28,11 @@ struct sclp_ipl_info {
 
 struct sclp_cpu_entry {
 	u8 address;
-	u8 reserved0[13];
+	u8 reserved0[2];
+	u8 : 3;
+	u8 siif : 1;
+	u8 : 4;
+	u8 reserved2[10];
 	u8 type;
 	u8 reserved1;
 } __attribute__((packed));
@@ -61,5 +65,7 @@ int sclp_pci_deconfigure(u32 fid);
 int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
 unsigned long sclp_get_hsa_size(void);
 void sclp_early_detect(void);
+int sclp_has_siif(void);
+unsigned int sclp_get_ibc(void);
 
 #endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index b31b22dba948..089a49814c50 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -9,7 +9,6 @@
 
 
 #define PARMAREA		0x10400
-#define MEMORY_CHUNKS		256
 
 #ifndef __ASSEMBLY__
 
@@ -31,22 +30,11 @@
 #endif /* CONFIG_64BIT */
 #define COMMAND_LINE      ((char *)            (0x10480))
 
-#define CHUNK_READ_WRITE 0
-#define CHUNK_READ_ONLY  1
-
-struct mem_chunk {
-	unsigned long addr;
-	unsigned long size;
-	int type;
-};
-
-extern struct mem_chunk memory_chunk[];
 extern int memory_end_set;
 extern unsigned long memory_end;
+extern unsigned long max_physmem_end;
 
-void detect_memory_layout(struct mem_chunk chunk[], unsigned long maxsize);
-void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
-		     unsigned long size);
+extern void detect_memory_memblock(void);
 
 /*
  * Machine features detected in head.S
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 21703f85b48d..4f1307962a95 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -30,7 +30,6 @@ extern int smp_store_status(int cpu);
 extern int smp_vcpu_scheduled(int cpu);
 extern void smp_yield_cpu(int cpu);
 extern void smp_yield(void);
-extern void smp_stop_cpu(void);
 extern void smp_cpu_set_polarization(int cpu, int val);
 extern int smp_cpu_get_polarization(int cpu);
 extern void smp_fill_possible_mask(void);
@@ -54,6 +53,8 @@ static inline void smp_yield_cpu(int cpu) { }
 static inline void smp_yield(void) { }
 static inline void smp_fill_possible_mask(void) { }
 
+#endif /* CONFIG_SMP */
+
 static inline void smp_stop_cpu(void)
 {
 	u16 pcpu = stap();
@@ -64,8 +65,6 @@ static inline void smp_stop_cpu(void)
 	}
 }
 
-#endif /* CONFIG_SMP */
-
 #ifdef CONFIG_HOTPLUG_CPU
 extern int smp_rescan_cpus(void);
 extern void __noreturn cpu_die(void);
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 83e5d216105e..96879f7ad6da 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -11,18 +11,21 @@
 
 #include <linux/smp.h>
 
+#define SPINLOCK_LOCKVAL (S390_lowcore.spinlock_lockval)
+
 extern int spin_retry;
 
 static inline int
-_raw_compare_and_swap(volatile unsigned int *lock,
-		      unsigned int old, unsigned int new)
+_raw_compare_and_swap(unsigned int *lock, unsigned int old, unsigned int new)
 {
+	unsigned int old_expected = old;
+
 	asm volatile(
 		"	cs	%0,%3,%1"
 		: "=d" (old), "=Q" (*lock)
 		: "0" (old), "d" (new), "Q" (*lock)
 		: "cc", "memory" );
-	return old;
+	return old == old_expected;
 }
 
 /*
@@ -34,57 +37,69 @@ _raw_compare_and_swap(volatile unsigned int *lock,
  * (the type definitions are in asm/spinlock_types.h)
  */
 
-#define arch_spin_is_locked(x) ((x)->owner_cpu != 0)
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) \
-		 arch_spin_relax(lock); } while (0)
+void arch_spin_lock_wait(arch_spinlock_t *);
+int arch_spin_trylock_retry(arch_spinlock_t *);
+void arch_spin_relax(arch_spinlock_t *);
+void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
 
-extern void arch_spin_lock_wait(arch_spinlock_t *);
-extern void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags);
-extern int arch_spin_trylock_retry(arch_spinlock_t *);
-extern void arch_spin_relax(arch_spinlock_t *lock);
+static inline u32 arch_spin_lockval(int cpu)
+{
+	return ~cpu;
+}
 
 static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {
-	return lock.owner_cpu == 0;
+	return lock.lock == 0;
 }
 
-static inline void arch_spin_lock(arch_spinlock_t *lp)
+static inline int arch_spin_is_locked(arch_spinlock_t *lp)
 {
-	int old;
+	return ACCESS_ONCE(lp->lock) != 0;
+}
 
-	old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id());
-	if (likely(old == 0))
-		return;
-	arch_spin_lock_wait(lp);
+static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
+{
+	barrier();
+	return likely(arch_spin_value_unlocked(*lp) &&
+		      _raw_compare_and_swap(&lp->lock, 0, SPINLOCK_LOCKVAL));
 }
 
-static inline void arch_spin_lock_flags(arch_spinlock_t *lp,
-					 unsigned long flags)
+static inline int arch_spin_tryrelease_once(arch_spinlock_t *lp)
 {
-	int old;
+	return _raw_compare_and_swap(&lp->lock, SPINLOCK_LOCKVAL, 0);
+}
 
-	old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id());
-	if (likely(old == 0))
-		return;
-	arch_spin_lock_wait_flags(lp, flags);
+static inline void arch_spin_lock(arch_spinlock_t *lp)
+{
+	if (!arch_spin_trylock_once(lp))
+		arch_spin_lock_wait(lp);
 }
 
-static inline int arch_spin_trylock(arch_spinlock_t *lp)
+static inline void arch_spin_lock_flags(arch_spinlock_t *lp,
+					unsigned long flags)
 {
-	int old;
+	if (!arch_spin_trylock_once(lp))
+		arch_spin_lock_wait_flags(lp, flags);
+}
 
-	old = _raw_compare_and_swap(&lp->owner_cpu, 0, ~smp_processor_id());
-	if (likely(old == 0))
-		return 1;
-	return arch_spin_trylock_retry(lp);
+static inline int arch_spin_trylock(arch_spinlock_t *lp)
+{
+	if (!arch_spin_trylock_once(lp))
+		return arch_spin_trylock_retry(lp);
+	return 1;
 }
 
 static inline void arch_spin_unlock(arch_spinlock_t *lp)
 {
-	_raw_compare_and_swap(&lp->owner_cpu, lp->owner_cpu, 0);
+	arch_spin_tryrelease_once(lp);
+}
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	while (arch_spin_is_locked(lock))
+		arch_spin_relax(lock);
 }
-		
+
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
@@ -115,42 +130,50 @@ extern void _raw_write_lock_wait(arch_rwlock_t *lp);
 extern void _raw_write_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags);
 extern int _raw_write_trylock_retry(arch_rwlock_t *lp);
 
+static inline int arch_read_trylock_once(arch_rwlock_t *rw)
+{
+	unsigned int old = ACCESS_ONCE(rw->lock);
+	return likely((int) old >= 0 &&
+		      _raw_compare_and_swap(&rw->lock, old, old + 1));
+}
+
+static inline int arch_write_trylock_once(arch_rwlock_t *rw)
+{
+	unsigned int old = ACCESS_ONCE(rw->lock);
+	return likely(old == 0 &&
+		      _raw_compare_and_swap(&rw->lock, 0, 0x80000000));
+}
+
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
-	unsigned int old;
-	old = rw->lock & 0x7fffffffU;
-	if (_raw_compare_and_swap(&rw->lock, old, old + 1) != old)
+	if (!arch_read_trylock_once(rw))
 		_raw_read_lock_wait(rw);
 }
 
 static inline void arch_read_lock_flags(arch_rwlock_t *rw, unsigned long flags)
 {
-	unsigned int old;
-	old = rw->lock & 0x7fffffffU;
-	if (_raw_compare_and_swap(&rw->lock, old, old + 1) != old)
+	if (!arch_read_trylock_once(rw))
 		_raw_read_lock_wait_flags(rw, flags);
 }
 
 static inline void arch_read_unlock(arch_rwlock_t *rw)
 {
-	unsigned int old, cmp;
+	unsigned int old;
 
-	old = rw->lock;
 	do {
-		cmp = old;
-		old = _raw_compare_and_swap(&rw->lock, old, old - 1);
-	} while (cmp != old);
+		old = ACCESS_ONCE(rw->lock);
+	} while (!_raw_compare_and_swap(&rw->lock, old, old - 1));
 }
 
 static inline void arch_write_lock(arch_rwlock_t *rw)
 {
-	if (unlikely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) != 0))
+	if (!arch_write_trylock_once(rw))
 		_raw_write_lock_wait(rw);
 }
 
 static inline void arch_write_lock_flags(arch_rwlock_t *rw, unsigned long flags)
 {
-	if (unlikely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) != 0))
+	if (!arch_write_trylock_once(rw))
 		_raw_write_lock_wait_flags(rw, flags);
 }
 
@@ -161,18 +184,16 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-	unsigned int old;
-	old = rw->lock & 0x7fffffffU;
-	if (likely(_raw_compare_and_swap(&rw->lock, old, old + 1) == old))
-		return 1;
-	return _raw_read_trylock_retry(rw);
+	if (!arch_read_trylock_once(rw))
+		return _raw_read_trylock_retry(rw);
+	return 1;
 }
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	if (likely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000) == 0))
-		return 1;
-	return _raw_write_trylock_retry(rw);
+	if (!arch_write_trylock_once(rw))
+		return _raw_write_trylock_retry(rw);
+	return 1;
 }
 
 #define arch_read_relax(lock)	cpu_relax()
diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h
index 9c76656a0af0..b2cd6ff7c2c5 100644
--- a/arch/s390/include/asm/spinlock_types.h
+++ b/arch/s390/include/asm/spinlock_types.h
@@ -6,13 +6,13 @@
 #endif
 
 typedef struct {
-	volatile unsigned int owner_cpu;
+	unsigned int lock;
 } __attribute__ ((aligned (4))) arch_spinlock_t;
 
-#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED { .lock = 0, }
 
 typedef struct {
-	volatile unsigned int lock;
+	unsigned int lock;
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index e759181357fc..29c81f82705e 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -132,7 +132,6 @@ static inline void restore_access_regs(unsigned int *acrs)
 		update_cr_regs(next);					\
 	}								\
 	prev = __switch_to(prev,next);					\
-	update_primary_asce(current);					\
 } while (0)
 
 #define finish_arch_switch(prev) do {					     \
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 777687055e7b..abad78d5b10c 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -28,7 +28,7 @@ extern const unsigned int sys_call_table_emu[];
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {
-	return test_tsk_thread_flag(task, TIF_SYSCALL) ?
+	return test_pt_regs_flag(regs, PIF_SYSCALL) ?
 		(regs->int_code & 0xffff) : -1;
 }
 
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 50630e6a35de..b833e9c0bfbf 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -77,32 +77,22 @@ static inline struct thread_info *current_thread_info(void)
 /*
  * thread information flags bit numbers
  */
-#define TIF_SYSCALL		0	/* inside a system call */
-#define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
-#define TIF_SIGPENDING		2	/* signal pending */
-#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
-#define TIF_TLB_WAIT		4	/* wait for TLB flush completion */
-#define TIF_ASCE		5	/* primary asce needs fixup / uaccess */
-#define TIF_PER_TRAP		6	/* deliver sigtrap on return to user */
-#define TIF_MCCK_PENDING	7	/* machine check handling is pending */
-#define TIF_SYSCALL_TRACE	8	/* syscall trace active */
-#define TIF_SYSCALL_AUDIT	9	/* syscall auditing active */
-#define TIF_SECCOMP		10	/* secure computing */
-#define TIF_SYSCALL_TRACEPOINT	11	/* syscall tracepoint instrumentation */
-#define TIF_31BIT		17	/* 32bit process */
-#define TIF_MEMDIE		18	/* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK	19	/* restore signal mask in do_signal() */
-#define TIF_SINGLE_STEP		20	/* This task is single stepped */
-#define TIF_BLOCK_STEP		21	/* This task is block stepped */
+#define TIF_NOTIFY_RESUME	0	/* callback before returning to user */
+#define TIF_SIGPENDING		1	/* signal pending */
+#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_SYSCALL_TRACE	3	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	4	/* syscall auditing active */
+#define TIF_SECCOMP		5	/* secure computing */
+#define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
+#define TIF_31BIT		16	/* 32bit process */
+#define TIF_MEMDIE		17	/* is terminating due to OOM killer */
+#define TIF_RESTORE_SIGMASK	18	/* restore signal mask in do_signal() */
+#define TIF_SINGLE_STEP		19	/* This task is single stepped */
+#define TIF_BLOCK_STEP		20	/* This task is block stepped */
 
-#define _TIF_SYSCALL		(1<<TIF_SYSCALL)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
-#define _TIF_TLB_WAIT		(1<<TIF_TLB_WAIT)
-#define _TIF_ASCE		(1<<TIF_ASCE)
-#define _TIF_PER_TRAP		(1<<TIF_PER_TRAP)
-#define _TIF_MCCK_PENDING	(1<<TIF_MCCK_PENDING)
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 05425b18c0aa..56af53093d24 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -26,21 +26,12 @@ extern struct cpu_topology_s390 cpu_topology[NR_CPUS];
 
 #define mc_capable() 1
 
-static inline const struct cpumask *cpu_coregroup_mask(int cpu)
-{
-	return &cpu_topology[cpu].core_mask;
-}
-
-static inline const struct cpumask *cpu_book_mask(int cpu)
-{
-	return &cpu_topology[cpu].book_mask;
-}
-
 int topology_cpu_init(struct cpu *);
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
 void store_topology(struct sysinfo_15_1_x *info);
 void topology_expect_change(void);
+const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #else /* CONFIG_SCHED_BOOK */
 
@@ -64,8 +55,6 @@ static inline void s390_init_cpu_topology(void)
 };
 #endif
 
-#define SD_BOOK_INIT	SD_CPU_INIT
-
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_S390_TOPOLOGY_H */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 1be64a1506d0..cd4c68e0398d 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -132,6 +132,34 @@ unsigned long __must_check __copy_to_user(void __user *to, const void *from,
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+
+#define __put_get_user_asm(to, from, size, spec)		\
+({								\
+	register unsigned long __reg0 asm("0") = spec;		\
+	int __rc;						\
+								\
+	asm volatile(						\
+		"0:	mvcos	%1,%3,%2\n"			\
+		"1:	xr	%0,%0\n"			\
+		"2:\n"						\
+		".pushsection .fixup, \"ax\"\n"			\
+		"3:	lhi	%0,%5\n"			\
+		"	jg	2b\n"				\
+		".popsection\n"					\
+		EX_TABLE(0b,3b) EX_TABLE(1b,3b)			\
+		: "=d" (__rc), "=Q" (*(to))			\
+		: "d" (size), "Q" (*(from)),			\
+		  "d" (__reg0), "K" (-EFAULT)			\
+		: "cc");					\
+	__rc;							\
+})
+
+#define __put_user_fn(x, ptr, size) __put_get_user_asm(ptr, x, size, 0x810000UL)
+#define __get_user_fn(x, ptr, size) __put_get_user_asm(x, ptr, size, 0x81UL)
+
+#else /* CONFIG_HAVE_MARCH_Z10_FEATURES */
+
 static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 {
 	size = __copy_to_user(ptr, x, size);
@@ -144,6 +172,8 @@ static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long s
 	return size ? -EFAULT : 0;
 }
 
+#endif /* CONFIG_HAVE_MARCH_Z10_FEATURES */
+
 /*
  * These are the main single-value transfer routines.  They automatically
  * use the right size if we just have the right pointer type.